diff options
Diffstat (limited to 'arch')
925 files changed, 27724 insertions, 14420 deletions
diff --git a/arch/arc/boot/dts/angel4.dts b/arch/arc/boot/dts/angel4.dts index bcf662d21a57..5bb2fdaca02f 100644 --- a/arch/arc/boot/dts/angel4.dts +++ b/arch/arc/boot/dts/angel4.dts @@ -17,7 +17,7 @@ interrupt-parent = <&intc>; chosen { - bootargs = "console=ttyARC0,115200n8"; + bootargs = "console=ttyARC0,115200n8 earlyprintk=ttyARC0"; }; aliases { diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 2fd3162ec4df..c1d3d2da1191 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -55,4 +55,31 @@ extern void read_decode_cache_bcr(void); #endif /* !__ASSEMBLY__ */ +/* Instruction cache related Auxiliary registers */ +#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ +#define ARC_REG_IC_IVIC 0x10 +#define ARC_REG_IC_CTRL 0x11 +#define ARC_REG_IC_IVIL 0x19 +#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4) +#define ARC_REG_IC_PTAG 0x1E +#endif + +/* Bit val in IC_CTRL */ +#define IC_CTRL_CACHE_DISABLE 0x1 + +/* Data cache related Auxiliary registers */ +#define ARC_REG_DC_BCR 0x72 /* Build Config reg */ +#define ARC_REG_DC_IVDC 0x47 +#define ARC_REG_DC_CTRL 0x48 +#define ARC_REG_DC_IVDL 0x4A +#define ARC_REG_DC_FLSH 0x4B +#define ARC_REG_DC_FLDL 0x4C +#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4) +#define ARC_REG_DC_PTAG 0x5C +#endif + +/* Bit val in DC_CTRL */ +#define DC_CTRL_INV_MODE_FLUSH 0x40 +#define DC_CTRL_FLUSH_STATUS 0x100 + #endif /* _ASM_CACHE_H */ diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index 291a70db68b8..fb4efb648971 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -19,8 +19,6 @@ #include <asm-generic/irq.h> extern void arc_init_IRQ(void); -extern int get_hw_config_num_irq(void); - -void arc_local_timer_setup(unsigned int cpu); +void arc_local_timer_setup(void); #endif diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index 15334ab66b56..d99f9b37cd15 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -18,7 +18,6 @@ #ifndef __ASSEMBLY__ -#include <asm/arcregs.h> /* for STATUS_E1_MASK et all */ #include <asm/ptrace.h> /* Arch specific stuff which needs to be saved per task. @@ -41,15 +40,13 @@ struct thread_struct { /* Forward declaration, a strange C thing */ struct task_struct; -/* - * Return saved PC of a blocked thread. - */ +/* Return saved PC of a blocked thread */ unsigned long thread_saved_pc(struct task_struct *t); #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_SIZE + (void *)task_stack_page(p)) - 1) -/* Free all resources held by a thread. */ +/* Free all resources held by a thread */ #define release_thread(thread) do { } while (0) /* Prepare to copy thread state - unlazy all lazy status */ @@ -82,26 +79,8 @@ unsigned long thread_saved_pc(struct task_struct *t); #define KSTK_BLINK(tsk) KSTK_REG(tsk, 4) #define KSTK_FP(tsk) KSTK_REG(tsk, 0) -/* - * Do necessary setup to start up a newly executed thread. - * - * E1,E2 so that Interrupts are enabled in user mode - * L set, so Loop inhibited to begin with - * lp_start and lp_end seeded with bogus non-zero values so to easily catch - * the ARC700 sr to lp_start hardware bug - */ -#define start_thread(_regs, _pc, _usp) \ -do { \ - set_fs(USER_DS); /* reads from user space */ \ - (_regs)->ret = (_pc); \ - /* Interrupts enabled in User Mode */ \ - (_regs)->status32 = STATUS_U_MASK | STATUS_L_MASK \ - | STATUS_E1_MASK | STATUS_E2_MASK; \ - (_regs)->sp = (_usp); \ - /* bogus seed values for debugging */ \ - (_regs)->lp_start = 0x10; \ - (_regs)->lp_end = 0x80; \ -} while (0) +extern void start_thread(struct pt_regs * regs, unsigned long pc, + unsigned long usp); extern unsigned int get_wchan(struct task_struct *p); diff --git a/arch/arc/include/asm/sections.h b/arch/arc/include/asm/sections.h index 764f1e3ba752..09db952e14bd 100644 --- a/arch/arc/include/asm/sections.h +++ b/arch/arc/include/asm/sections.h @@ -12,6 +12,5 @@ #include <asm-generic/sections.h> extern char __arc_dccm_base[]; -extern char __dtb_start[]; #endif diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild index 18fefaea73fd..f50d02df78d5 100644 --- a/arch/arc/include/uapi/asm/Kbuild +++ b/arch/arc/include/uapi/asm/Kbuild @@ -2,11 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm header-y += elf.h header-y += page.h -header-y += setup.h -header-y += byteorder.h header-y += cachectl.h -header-y += ptrace.h -header-y += sigcontext.h -header-y += signal.h -header-y += swab.h -header-y += unistd.h diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c index b6dc4e21fd32..0b3ef4025d89 100644 --- a/arch/arc/kernel/devtree.c +++ b/arch/arc/kernel/devtree.c @@ -42,7 +42,7 @@ const struct machine_desc * __init setup_machine_fdt(void *dt) const struct machine_desc *mdesc; unsigned long dt_root; void *clk; - unsigned long len; + int len; if (!early_init_dt_scan(dt)) return NULL; diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 29b82adbf0b4..83a046a7cd06 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -156,7 +156,7 @@ ARCFP_DATA int1_saved_reg int1_saved_reg: .zero 4 -/* Each Interrupt level needs it's own scratch */ +/* Each Interrupt level needs its own scratch */ #ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS ARCFP_DATA int2_saved_reg @@ -473,7 +473,7 @@ trap_with_param: lr r0, [efa] mov r1, sp - ; Now that we have read EFA, its safe to do "fake" rtie + ; Now that we have read EFA, it is safe to do "fake" rtie ; and get out of CPU exception mode FAKE_RET_FROM_EXCPN r11 @@ -678,9 +678,9 @@ not_exception: brne r9, event_IRQ2, 149f ;------------------------------------------------------------------ - ; if L2 IRQ interrupted a L1 ISR, we'd disbaled preemption earlier - ; so that sched doesnt move to new task, causing L1 to be delayed - ; undeterministically. Now that we've achieved that, lets reset + ; if L2 IRQ interrupted an L1 ISR, we'd disabled preemption earlier + ; so that sched doesn't move to new task, causing L1 to be delayed + ; undeterministically. Now that we've achieved that, let's reset ; things to what they were, before returning from L2 context ;---------------------------------------------------------------- @@ -736,7 +736,7 @@ ENTRY(ret_from_fork) ; put last task in scheduler queue bl @schedule_tail - ; If kernel thread, jump to it's entry-point + ; If kernel thread, jump to its entry-point ld r9, [sp, PT_status32] brne r9, 0, 1f diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 4ad04915dc6b..07a58f2d3077 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -12,10 +12,42 @@ * to skip certain things during boot on simulator */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/entry.h> -#include <linux/linkage.h> #include <asm/arcregs.h> +#include <asm/cache.h> + +.macro CPU_EARLY_SETUP + + ; Setting up Vectror Table (in case exception happens in early boot + sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + + ; Disable I-cache/D-cache if kernel so configured + lr r5, [ARC_REG_IC_BCR] + breq r5, 0, 1f ; I$ doesn't exist + lr r5, [ARC_REG_IC_CTRL] +#ifdef CONFIG_ARC_HAS_ICACHE + bclr r5, r5, 0 ; 0 - Enable, 1 is Disable +#else + bset r5, r5, 0 ; I$ exists, but is not used +#endif + sr r5, [ARC_REG_IC_CTRL] + +1: + lr r5, [ARC_REG_DC_BCR] + breq r5, 0, 1f ; D$ doesn't exist + lr r5, [ARC_REG_DC_CTRL] + bclr r5, r5, 6 ; Invalidate (discard w/o wback) +#ifdef CONFIG_ARC_HAS_DCACHE + bclr r5, r5, 0 ; Enable (+Inv) +#else + bset r5, r5, 0 ; Disable (+Inv) +#endif + sr r5, [ARC_REG_DC_CTRL] + +1: +.endm .cpu A7 @@ -27,7 +59,7 @@ stext: ; Don't clobber r0-r2 yet. It might have bootloader provided info ;------------------------------------------------------------------- - sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + CPU_EARLY_SETUP #ifdef CONFIG_SMP ; Ensure Boot (Master) proceeds. Others wait in platform dependent way @@ -90,7 +122,7 @@ stext: first_lines_of_secondary: - sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + CPU_EARLY_SETUP ; setup per-cpu idle task as "current" on this CPU ld r0, [@secondary_idle_tsk] diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c index a4b141ee9a6a..7d653c0d0773 100644 --- a/arch/arc/kernel/irq.c +++ b/arch/arc/kernel/irq.c @@ -150,24 +150,6 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs) set_irq_regs(old_regs); } -int get_hw_config_num_irq(void) -{ - uint32_t val = read_aux_reg(ARC_REG_VECBASE_BCR); - - switch (val & 0x03) { - case 0: - return 16; - case 1: - return 32; - case 2: - return 8; - default: - return 0; - } - - return 0; -} - /* * arch_local_irq_enable - Enable interrupts. * diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 07a3a968fe49..fdd89715d2d3 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -151,6 +151,29 @@ int copy_thread(unsigned long clone_flags, } /* + * Do necessary setup to start up a new user task + */ +void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp) +{ + set_fs(USER_DS); /* user space */ + + regs->sp = usp; + regs->ret = pc; + + /* + * [U]ser Mode bit set + * [L] ZOL loop inhibited to begin with - cleared by a LP insn + * Interrupts enabled + */ + regs->status32 = STATUS_U_MASK | STATUS_L_MASK | + STATUS_E1_MASK | STATUS_E2_MASK; + + /* bogus seed values for debugging */ + regs->lp_start = 0x10; + regs->lp_end = 0x80; +} + +/* * Some archs flush debug and FPU info here */ void flush_thread(void) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 40859e5619f9..cf90b6f4d3e0 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -138,7 +138,7 @@ void start_kernel_secondary(void) if (machine_desc->init_smp) machine_desc->init_smp(smp_processor_id()); - arc_local_timer_setup(cpu); + arc_local_timer_setup(); local_irq_enable(); preempt_disable(); diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c index 71c42521c77f..36c2aa99436f 100644 --- a/arch/arc/kernel/time.c +++ b/arch/arc/kernel/time.c @@ -219,12 +219,13 @@ static struct irqaction arc_timer_irq = { /* * Setup the local event timer for @cpu */ -void arc_local_timer_setup(unsigned int cpu) +void arc_local_timer_setup() { - struct clock_event_device *clk = &per_cpu(arc_clockevent_device, cpu); + struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device); + int cpu = smp_processor_id(); - clk->cpumask = cpumask_of(cpu); - clockevents_config_and_register(clk, arc_get_core_freq(), + evt->cpumask = cpumask_of(cpu); + clockevents_config_and_register(evt, arc_get_core_freq(), 0, ARC_TIMER_MAX); /* @@ -261,7 +262,7 @@ void __init time_init(void) clocksource_register_hz(&arc_counter, arc_get_core_freq()); /* sets up the periodic event timer */ - arc_local_timer_setup(smp_processor_id()); + arc_local_timer_setup(); if (machine_desc->init_time) machine_desc->init_time(); diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 73a7450ee622..1badf9b84b51 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -86,12 +86,13 @@ static void show_faulting_vma(unsigned long address, char *buf) unsigned long ino = 0; dev_t dev = 0; char *nm = buf; + struct mm_struct *active_mm = current->active_mm; /* can't use print_vma_addr() yet as it doesn't check for * non-inclusive vma */ - - vma = find_vma(current->active_mm, address); + down_read(&active_mm->mmap_sem); + vma = find_vma(active_mm, address); /* check against the find_vma( ) behaviour which returns the next VMA * if the container VMA is not found @@ -110,9 +111,10 @@ static void show_faulting_vma(unsigned long address, char *buf) vma->vm_start < TASK_UNMAPPED_BASE ? address : address - vma->vm_start, nm, vma->vm_start, vma->vm_end); - } else { + } else pr_info(" @No matching VMA found\n"); - } + + up_read(&active_mm->mmap_sem); } static void show_ecr_verbose(struct pt_regs *regs) diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c index 89edf7961a2f..1f676c4794e0 100644 --- a/arch/arc/mm/cache_arc700.c +++ b/arch/arc/mm/cache_arc700.c @@ -73,33 +73,6 @@ #include <asm/cachectl.h> #include <asm/setup.h> -/* Instruction cache related Auxiliary registers */ -#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ -#define ARC_REG_IC_IVIC 0x10 -#define ARC_REG_IC_CTRL 0x11 -#define ARC_REG_IC_IVIL 0x19 -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_IC_PTAG 0x1E -#endif - -/* Bit val in IC_CTRL */ -#define IC_CTRL_CACHE_DISABLE 0x1 - -/* Data cache related Auxiliary registers */ -#define ARC_REG_DC_BCR 0x72 /* Build Config reg */ -#define ARC_REG_DC_IVDC 0x47 -#define ARC_REG_DC_CTRL 0x48 -#define ARC_REG_DC_IVDL 0x4A -#define ARC_REG_DC_FLSH 0x4B -#define ARC_REG_DC_FLDL 0x4C -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_DC_PTAG 0x5C -#endif - -/* Bit val in DC_CTRL */ -#define DC_CTRL_INV_MODE_FLUSH 0x40 -#define DC_CTRL_FLUSH_STATUS 0x100 - char *arc_cache_mumbojumbo(int c, char *buf, int len) { int n = 0; @@ -168,72 +141,43 @@ void read_decode_cache_bcr(void) */ void arc_cache_init(void) { - unsigned int cpu = smp_processor_id(); - struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; - struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache; - unsigned int dcache_does_alias, temp; + unsigned int __maybe_unused cpu = smp_processor_id(); + struct cpuinfo_arc_cache __maybe_unused *ic, __maybe_unused *dc; char str[256]; printk(arc_cache_mumbojumbo(0, str, sizeof(str))); - if (!ic->ver) - goto chk_dc; - -#ifdef CONFIG_ARC_HAS_ICACHE - /* 1. Confirm some of I-cache params which Linux assumes */ - if (ic->line_len != L1_CACHE_BYTES) - panic("Cache H/W doesn't match kernel Config"); - - if (ic->ver != CONFIG_ARC_MMU_VER) - panic("Cache ver doesn't match MMU ver\n"); -#endif - - /* Enable/disable I-Cache */ - temp = read_aux_reg(ARC_REG_IC_CTRL); - #ifdef CONFIG_ARC_HAS_ICACHE - temp &= ~IC_CTRL_CACHE_DISABLE; -#else - temp |= IC_CTRL_CACHE_DISABLE; + ic = &cpuinfo_arc700[cpu].icache; + if (ic->ver) { + if (ic->line_len != L1_CACHE_BYTES) + panic("ICache line [%d] != kernel Config [%d]", + ic->line_len, L1_CACHE_BYTES); + + if (ic->ver != CONFIG_ARC_MMU_VER) + panic("Cache ver [%d] doesn't match MMU ver [%d]\n", + ic->ver, CONFIG_ARC_MMU_VER); + } #endif - write_aux_reg(ARC_REG_IC_CTRL, temp); - -chk_dc: - if (!dc->ver) - return; - #ifdef CONFIG_ARC_HAS_DCACHE - if (dc->line_len != L1_CACHE_BYTES) - panic("Cache H/W doesn't match kernel Config"); + dc = &cpuinfo_arc700[cpu].dcache; + if (dc->ver) { + unsigned int dcache_does_alias; - /* check for D-Cache aliasing */ - dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE; + if (dc->line_len != L1_CACHE_BYTES) + panic("DCache line [%d] != kernel Config [%d]", + dc->line_len, L1_CACHE_BYTES); - if (dcache_does_alias && !cache_is_vipt_aliasing()) - panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); - else if (!dcache_does_alias && cache_is_vipt_aliasing()) - panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); -#endif - - /* Set the default Invalidate Mode to "simpy discard dirty lines" - * as this is more frequent then flush before invalidate - * Ofcourse we toggle this default behviour when desired - */ - temp = read_aux_reg(ARC_REG_DC_CTRL); - temp &= ~DC_CTRL_INV_MODE_FLUSH; + /* check for D-Cache aliasing */ + dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE; -#ifdef CONFIG_ARC_HAS_DCACHE - /* Enable D-Cache: Clear Bit 0 */ - write_aux_reg(ARC_REG_DC_CTRL, temp & ~IC_CTRL_CACHE_DISABLE); -#else - /* Flush D cache */ - write_aux_reg(ARC_REG_DC_FLSH, 0x1); - /* Disable D cache */ - write_aux_reg(ARC_REG_DC_CTRL, temp | IC_CTRL_CACHE_DISABLE); + if (dcache_does_alias && !cache_is_vipt_aliasing()) + panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + else if (!dcache_does_alias && cache_is_vipt_aliasing()) + panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + } #endif - - return; } #define OP_INV 0x1 @@ -253,12 +197,16 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, if (cacheop == OP_INV_IC) { aux_cmd = ARC_REG_IC_IVIL; +#if (CONFIG_ARC_MMU_VER > 2) aux_tag = ARC_REG_IC_PTAG; +#endif } else { /* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */ aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL; +#if (CONFIG_ARC_MMU_VER > 2) aux_tag = ARC_REG_DC_PTAG; +#endif } /* Ensure we properly floor/ceil the non-line aligned/sized requests diff --git a/arch/arc/plat-arcfpga/Kconfig b/arch/arc/plat-arcfpga/Kconfig index 33058aa40e77..e27bb5cc3c1e 100644 --- a/arch/arc/plat-arcfpga/Kconfig +++ b/arch/arc/plat-arcfpga/Kconfig @@ -48,36 +48,4 @@ config ARC_SERIAL_BAUD help Baud rate for the ARC UART -menuconfig ARC_HAS_BVCI_LAT_UNIT - bool "BVCI Bus Latency Unit" - depends on ARC_BOARD_ML509 || ARC_BOARD_ANGEL4 - help - IP to add artificial latency to BVCI Bus Based FPGA builds. - The default latency (even worst case) for FPGA is non-realistic - (~10 SDRAM, ~5 SSRAM). - -config BVCI_LAT_UNITS - hex "Latency Unit(s) Bitmap" - default "0x0" - depends on ARC_HAS_BVCI_LAT_UNIT - help - There are multiple Latency Units corresponding to the many - interfaces of the system bus arbiter (both CPU side as well as - the peripheral side). - To add latency to ALL memory transaction, choose Unit 0, otherwise - for finer grainer - interface wise latency, specify a bitmap (1 bit - per unit) of all units. e.g. 1,2,12 will be 0x1003 - - Unit 0 - System Arb and Mem Controller - Unit 1 - I$ and System Bus - Unit 2 - D$ and System Bus - .. - Unit 12 - IDE Disk controller and System Bus - -config BVCI_LAT_CYCLES - int "Latency Value in cycles" - range 0 63 - default "30" - depends on ARC_HAS_BVCI_LAT_UNIT - endif diff --git a/arch/arc/plat-arcfpga/Makefile b/arch/arc/plat-arcfpga/Makefile index a44e22ebc1b7..4d1bddc34b5b 100644 --- a/arch/arc/plat-arcfpga/Makefile +++ b/arch/arc/plat-arcfpga/Makefile @@ -9,4 +9,4 @@ KBUILD_CFLAGS += -Iarch/arc/plat-arcfpga/include obj-y := platform.o irq.o -obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_ISS_SMP_EXTN) += smp.o diff --git a/arch/arc/plat-arcfpga/platform.c b/arch/arc/plat-arcfpga/platform.c index 19b76b61f44b..61c7e5997387 100644 --- a/arch/arc/plat-arcfpga/platform.c +++ b/arch/arc/plat-arcfpga/platform.c @@ -22,59 +22,6 @@ #include <plat/smp.h> #include <plat/irq.h> -/*-----------------------BVCI Latency Unit -----------------------------*/ - -#ifdef CONFIG_ARC_HAS_BVCI_LAT_UNIT - -int lat_cycles = CONFIG_BVCI_LAT_CYCLES; - -/* BVCI Bus Profiler: Latency Unit */ -static void __init setup_bvci_lat_unit(void) -{ -#define MAX_BVCI_UNITS 12 - - unsigned int i; - unsigned int *base = (unsigned int *)BVCI_LAT_UNIT_BASE; - const unsigned long units_req = CONFIG_BVCI_LAT_UNITS; - const unsigned int REG_UNIT = 21; - const unsigned int REG_VAL = 22; - - /* - * There are multiple Latency Units corresponding to the many - * interfaces of the system bus arbiter (both CPU side as well as - * the peripheral side). - * - * Unit 0 - System Arb and Mem Controller - adds latency to all - * memory trasactions - * Unit 1 - I$ and System Bus - * Unit 2 - D$ and System Bus - * .. - * Unit 12 - IDE Disk controller and System Bus - * - * The programmers model requires writing to lat_unit reg first - * and then the latency value (cycles) to lat_value reg - */ - - if (CONFIG_BVCI_LAT_UNITS == 0) { - writel(0, base + REG_UNIT); - writel(lat_cycles, base + REG_VAL); - pr_info("BVCI Latency for all Memory Transactions %d cycles\n", - lat_cycles); - } else { - for_each_set_bit(i, &units_req, MAX_BVCI_UNITS) { - writel(i + 1, base + REG_UNIT); /* loop is 0 based */ - writel(lat_cycles, base + REG_VAL); - pr_info("BVCI Latency for Unit[%d] = %d cycles\n", - (i + 1), lat_cycles); - } - } -} -#else -static void __init setup_bvci_lat_unit(void) -{ -} -#endif - /*----------------------- Platform Devices -----------------------------*/ #if IS_ENABLED(CONFIG_SERIAL_ARC) @@ -132,16 +79,11 @@ static void arc_fpga_serial_init(void) ARRAY_SIZE(fpga_early_devs)); /* - * ARC console driver registers itself as an early platform driver - * of class "earlyprintk". - * Install it here, followed by probe of devices. - * The installation here doesn't require earlyprintk in command line - * To do so however, replace the lines below with - * parse_early_param(); - * early_platform_driver_probe("earlyprintk", 1, 1); - * ^^ + * ARC console driver registers (build time) as an early platform driver + * of class "earlyprintk". However it needs explicit cmdline toggle + * "earlyprintk=ttyARC0" to be successfuly runtime registered. + * Otherwise the early probe below fails to find the driver */ - early_platform_driver_register_all("earlyprintk"); early_platform_driver_probe("earlyprintk", 1, 0); /* @@ -165,11 +107,9 @@ static void __init plat_fpga_early_init(void) { pr_info("[plat-arcfpga]: registering early dev resources\n"); - setup_bvci_lat_unit(); - arc_fpga_serial_init(); -#ifdef CONFIG_SMP +#ifdef CONFIG_ISS_SMP_EXTN iss_model_init_early_smp(); #endif } @@ -211,7 +151,7 @@ MACHINE_START(ANGEL4, "angel4") .init_early = plat_fpga_early_init, .init_machine = plat_fpga_populate_dev, .init_irq = plat_fpga_init_IRQ, -#ifdef CONFIG_SMP +#ifdef CONFIG_ISS_SMP_EXTN .init_smp = iss_model_init_smp, #endif MACHINE_END diff --git a/arch/arc/plat-arcfpga/smp.c b/arch/arc/plat-arcfpga/smp.c index 8a12741f5f7a..92bad9122077 100644 --- a/arch/arc/plat-arcfpga/smp.c +++ b/arch/arc/plat-arcfpga/smp.c @@ -42,6 +42,24 @@ static void iss_model_smp_wakeup_cpu(int cpu, unsigned long pc) } +static inline int get_hw_config_num_irq(void) +{ + uint32_t val = read_aux_reg(ARC_REG_VECBASE_BCR); + + switch (val & 0x03) { + case 0: + return 16; + case 1: + return 32; + case 2: + return 8; + default: + return 0; + } + + return 0; +} + /* * Any SMP specific init any CPU does when it comes up. * Here we setup the CPU to enable Inter-Processor-Interrupts diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 071dce78959a..87b63fde06d7 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -165,12 +165,9 @@ config TRACE_IRQFLAGS_SUPPORT bool default y -config RWSEM_GENERIC_SPINLOCK - bool - default y - config RWSEM_XCHGADD_ALGORITHM bool + default y config ARCH_HAS_ILOG2_U32 bool @@ -480,6 +477,7 @@ config ARCH_IOP13XX select PCI select PLAT_IOP select VMSPLIT_1G + select SPARSE_IRQ help Support for Intel's IOP13XX (XScale) family of processors. @@ -1088,11 +1086,6 @@ source "arch/arm/firmware/Kconfig" source arch/arm/mm/Kconfig -config ARM_NR_BANKS - int - default 16 if ARCH_EP93XX - default 8 - config IWMMXT bool "Enable iWMMXt support" depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_PJ4 || CPU_PJ4B @@ -1213,19 +1206,6 @@ config ARM_ERRATA_742231 register of the Cortex-A9 which reduces the linefill issuing capabilities of the processor. -config PL310_ERRATA_588369 - bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines" - depends on CACHE_L2X0 - help - The PL310 L2 cache controller implements three types of Clean & - Invalidate maintenance operations: by Physical Address - (offset 0x7F0), by Index/Way (0x7F8) and by Way (0x7FC). - They are architecturally defined to behave as the execution of a - clean operation followed immediately by an invalidate operation, - both performing to the same memory location. This functionality - is not correctly implemented in PL310 as clean lines are not - invalidated as a result of these operations. - config ARM_ERRATA_643719 bool "ARM errata: LoUIS bit field in CLIDR register is incorrect" depends on CPU_V7 && SMP @@ -1248,17 +1228,6 @@ config ARM_ERRATA_720789 tables. The workaround changes the TLB flushing routines to invalidate entries regardless of the ASID. -config PL310_ERRATA_727915 - bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption" - depends on CACHE_L2X0 - help - PL310 implements the Clean & Invalidate by Way L2 cache maintenance - operation (offset 0x7FC). This operation runs in background so that - PL310 can handle normal accesses while it is in progress. Under very - rare circumstances, due to this erratum, write data can be lost when - PL310 treats a cacheable write transaction during a Clean & - Invalidate by Way operation. - config ARM_ERRATA_743622 bool "ARM errata: Faulty hazard checking in the Store Buffer may lead to data corruption" depends on CPU_V7 @@ -1284,21 +1253,6 @@ config ARM_ERRATA_751472 operation is received by a CPU before the ICIALLUIS has completed, potentially leading to corrupted entries in the cache or TLB. -config PL310_ERRATA_753970 - bool "PL310 errata: cache sync operation may be faulty" - depends on CACHE_PL310 - help - This option enables the workaround for the 753970 PL310 (r3p0) erratum. - - Under some condition the effect of cache sync operation on - the store buffer still remains when the operation completes. - This means that the store buffer is always asked to drain and - this prevents it from merging any further writes. The workaround - is to replace the normal offset of cache sync operation (0x730) - by another offset targeting an unmapped PL310 register 0x740. - This has the same effect as the cache sync operation: store buffer - drain and waiting for all buffers empty. - config ARM_ERRATA_754322 bool "ARM errata: possible faulty MMU translations following an ASID switch" depends on CPU_V7 @@ -1347,18 +1301,6 @@ config ARM_ERRATA_764369 relevant cache maintenance functions and sets a specific bit in the diagnostic control register of the SCU. -config PL310_ERRATA_769419 - bool "PL310 errata: no automatic Store Buffer drain" - depends on CACHE_L2X0 - help - On revisions of the PL310 prior to r3p2, the Store Buffer does - not automatically drain. This can cause normal, non-cacheable - writes to be retained when the memory system is idle, leading - to suboptimal I/O performance for drivers using coherent DMA. - This option adds a write barrier to the cpu_idle loop so that, - on systems with an outer cache, the store buffer is drained - explicitly. - config ARM_ERRATA_775420 bool "ARM errata: A data cache maintenance operation which aborts, might lead to deadlock" depends on CPU_V7 @@ -2278,6 +2220,11 @@ config ARCH_SUSPEND_POSSIBLE config ARM_CPU_SUSPEND def_bool PM_SLEEP +config ARCH_HIBERNATION_POSSIBLE + bool + depends on MMU + default y if ARCH_SUSPEND_POSSIBLE + endmenu source "net/Kconfig" diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c index d1153c8a765a..9448aa0c6686 100644 --- a/arch/arm/boot/compressed/atags_to_fdt.c +++ b/arch/arm/boot/compressed/atags_to_fdt.c @@ -7,6 +7,8 @@ #define do_extend_cmdline 0 #endif +#define NR_BANKS 16 + static int node_offset(void *fdt, const char *node_path) { int offset = fdt_path_offset(fdt, node_path); diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index 794c73e5c4e4..db464d7eaca8 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -857,6 +857,35 @@ ti,hwmods = "hdq1w"; status = "disabled"; }; + + dss: dss@4832a000 { + compatible = "ti,omap3-dss"; + reg = <0x4832a000 0x200>; + status = "disabled"; + ti,hwmods = "dss_core"; + clocks = <&disp_clk>; + clock-names = "fck"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + dispc@4832a400 { + compatible = "ti,omap3-dispc"; + reg = <0x4832a400 0x400>; + interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>; + ti,hwmods = "dss_dispc"; + clocks = <&disp_clk>; + clock-names = "fck"; + }; + + rfbi: rfbi@4832a800 { + compatible = "ti,omap3-rfbi"; + reg = <0x4832a800 0x100>; + ti,hwmods = "dss_rfbi"; + clocks = <&disp_clk>; + clock-names = "fck"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts index c25d15837ce9..003766c47bbf 100644 --- a/arch/arm/boot/dts/am437x-gp-evm.dts +++ b/arch/arm/boot/dts/am437x-gp-evm.dts @@ -19,6 +19,10 @@ model = "TI AM437x GP EVM"; compatible = "ti,am437x-gp-evm","ti,am4372","ti,am43"; + aliases { + display0 = &lcd0; + }; + vmmcsd_fixed: fixedregulator-sd { compatible = "regulator-fixed"; regulator-name = "vmmcsd_fixed"; @@ -64,6 +68,44 @@ 0x02000069 /* LEFT */ 0x0201006c>; /* DOWN */ }; + + lcd0: display { + compatible = "osddisplays,osd057T0559-34ts", "panel-dpi"; + label = "lcd"; + + pinctrl-names = "default"; + pinctrl-0 = <&lcd_pins>; + + /* + * SelLCDorHDMI, LOW to select HDMI. This is not really the + * panel's enable GPIO, but we don't have HDMI driver support nor + * support to switch between two displays, so using this gpio as + * panel's enable should be safe. + */ + enable-gpios = <&gpio5 8 GPIO_ACTIVE_HIGH>; + + panel-timing { + clock-frequency = <33000000>; + hactive = <800>; + vactive = <480>; + hfront-porch = <210>; + hback-porch = <16>; + hsync-len = <30>; + vback-porch = <10>; + vfront-porch = <22>; + vsync-len = <13>; + hsync-active = <0>; + vsync-active = <0>; + de-active = <1>; + pixelclk-active = <1>; + }; + + port { + lcd_in: endpoint { + remote-endpoint = <&dpi_out>; + }; + }; + }; }; &am43xx_pinmux { @@ -171,6 +213,47 @@ 0x9c (PIN_OUTPUT | MUX_MODE0) /* gpmc_be0n_cle.gpmc_be0n_cle */ >; }; + + dss_pins: dss_pins { + pinctrl-single,pins = < + 0x020 (PIN_OUTPUT_PULLUP | MUX_MODE1) /*gpmc ad 8 -> DSS DATA 23 */ + 0x024 (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x028 (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x02c (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x030 (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x034 (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x038 (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x03c (PIN_OUTPUT_PULLUP | MUX_MODE1) /*gpmc ad 15 -> DSS DATA 16 */ + 0x0a0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS DATA 0 */ + 0x0a4 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0a8 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0ac (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0b0 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0b4 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0b8 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0bc (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0c0 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0c4 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0c8 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0cc (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0d0 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0d4 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0d8 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0dc (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS DATA 15 */ + 0x0e0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS VSYNC */ + 0x0e4 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS HSYNC */ + 0x0e8 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS PCLK */ + 0x0ec (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS AC BIAS EN */ + + >; + }; + + lcd_pins: lcd_pins { + pinctrl-single,pins = < + /* GPIO 5_8 to select LCD / HDMI */ + 0x238 (PIN_OUTPUT_PULLUP | MUX_MODE7) + >; + }; }; &i2c0 { @@ -359,3 +442,17 @@ }; }; }; + +&dss { + status = "ok"; + + pinctrl-names = "default"; + pinctrl-0 = <&dss_pins>; + + port { + dpi_out: endpoint@0 { + remote-endpoint = <&lcd_in>; + data-lines = <24>; + }; + }; +}; diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index ad362c50e32e..19f1f7e87597 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -19,6 +19,10 @@ model = "TI AM43x EPOS EVM"; compatible = "ti,am43x-epos-evm","ti,am4372","ti,am43"; + aliases { + display0 = &lcd0; + }; + vmmcsd_fixed: fixedregulator-sd { compatible = "regulator-fixed"; regulator-name = "vmmcsd_fixed"; @@ -27,6 +31,44 @@ enable-active-high; }; + lcd0: display { + compatible = "osddisplays,osd057T0559-34ts", "panel-dpi"; + label = "lcd"; + + pinctrl-names = "default"; + pinctrl-0 = <&lcd_pins>; + + /* + * SelLCDorHDMI, LOW to select HDMI. This is not really the + * panel's enable GPIO, but we don't have HDMI driver support nor + * support to switch between two displays, so using this gpio as + * panel's enable should be safe. + */ + enable-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>; + + panel-timing { + clock-frequency = <33000000>; + hactive = <800>; + vactive = <480>; + hfront-porch = <210>; + hback-porch = <16>; + hsync-len = <30>; + vback-porch = <10>; + vfront-porch = <22>; + vsync-len = <13>; + hsync-active = <0>; + vsync-active = <0>; + de-active = <1>; + pixelclk-active = <1>; + }; + + port { + lcd_in: endpoint { + remote-endpoint = <&dpi_out>; + }; + }; + }; + am43xx_pinmux: pinmux@44e10800 { cpsw_default: cpsw_default { pinctrl-single,pins = < @@ -161,6 +203,46 @@ 0x234 (PIN_INPUT_PULLUP | MUX_MODE1) /* cam1_wen.hdq_gpio */ >; }; + + dss_pins: dss_pins { + pinctrl-single,pins = < + 0x020 (PIN_OUTPUT_PULLUP | MUX_MODE1) /*gpmc ad 8 -> DSS DATA 23 */ + 0x024 (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x028 (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x02C (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x030 (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x034 (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x038 (PIN_OUTPUT_PULLUP | MUX_MODE1) + 0x03C (PIN_OUTPUT_PULLUP | MUX_MODE1) /*gpmc ad 15 -> DSS DATA 16 */ + 0x0A0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS DATA 0 */ + 0x0A4 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0A8 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0AC (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0B0 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0B4 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0B8 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0BC (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0C0 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0C4 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0C8 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0CC (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0D0 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0D4 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0D8 (PIN_OUTPUT_PULLUP | MUX_MODE0) + 0x0DC (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS DATA 15 */ + 0x0E0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS VSYNC */ + 0x0E4 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS HSYNC */ + 0x0E8 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS PCLK */ + 0x0EC (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS AC BIAS EN */ + >; + }; + + lcd_pins: lcd_pins { + pinctrl-single,pins = < + /* GPMC CLK -> GPIO 2_1 to select LCD / HDMI */ + 0x08C (PIN_OUTPUT_PULLUP | MUX_MODE7) + >; + }; }; matrix_keypad: matrix_keypad@0 { @@ -468,3 +550,17 @@ pinctrl-names = "default"; pinctrl-0 = <&hdq_pins>; }; + +&dss { + status = "ok"; + + pinctrl-names = "default"; + pinctrl-0 = <&dss_pins>; + + port { + dpi_out: endpoint@0 { + remote-endpoint = <&lcd_in>; + data-lines = <24>; + }; + }; +}; diff --git a/arch/arm/boot/dts/bcm21664.dtsi b/arch/arm/boot/dts/bcm21664.dtsi index 08a44d41b672..8b366822bb43 100644 --- a/arch/arm/boot/dts/bcm21664.dtsi +++ b/arch/arm/boot/dts/bcm21664.dtsi @@ -14,6 +14,8 @@ #include <dt-bindings/interrupt-controller/arm-gic.h> #include <dt-bindings/interrupt-controller/irq.h> +#include "dt-bindings/clock/bcm21664.h" + #include "skeleton.dtsi" / { @@ -43,7 +45,7 @@ compatible = "brcm,bcm21664-dw-apb-uart", "snps,dw-apb-uart"; status = "disabled"; reg = <0x3e000000 0x118>; - clocks = <&uartb_clk>; + clocks = <&slave_ccu BCM21664_SLAVE_CCU_UARTB>; interrupts = <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>; reg-shift = <2>; reg-io-width = <4>; @@ -53,7 +55,7 @@ compatible = "brcm,bcm21664-dw-apb-uart", "snps,dw-apb-uart"; status = "disabled"; reg = <0x3e001000 0x118>; - clocks = <&uartb2_clk>; + clocks = <&slave_ccu BCM21664_SLAVE_CCU_UARTB2>; interrupts = <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH>; reg-shift = <2>; reg-io-width = <4>; @@ -63,7 +65,7 @@ compatible = "brcm,bcm21664-dw-apb-uart", "snps,dw-apb-uart"; status = "disabled"; reg = <0x3e002000 0x118>; - clocks = <&uartb3_clk>; + clocks = <&slave_ccu BCM21664_SLAVE_CCU_UARTB3>; interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; reg-shift = <2>; reg-io-width = <4>; @@ -85,7 +87,7 @@ compatible = "brcm,kona-timer"; reg = <0x35006000 0x1c>; interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&hub_timer_clk>; + clocks = <&aon_ccu BCM21664_AON_CCU_HUB_TIMER>; }; gpio: gpio@35003000 { @@ -106,7 +108,7 @@ compatible = "brcm,kona-sdhci"; reg = <0x3f180000 0x801c>; interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&sdio1_clk>; + clocks = <&master_ccu BCM21664_MASTER_CCU_SDIO1>; status = "disabled"; }; @@ -114,7 +116,7 @@ compatible = "brcm,kona-sdhci"; reg = <0x3f190000 0x801c>; interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&sdio2_clk>; + clocks = <&master_ccu BCM21664_MASTER_CCU_SDIO2>; status = "disabled"; }; @@ -122,7 +124,7 @@ compatible = "brcm,kona-sdhci"; reg = <0x3f1a0000 0x801c>; interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&sdio3_clk>; + clocks = <&master_ccu BCM21664_MASTER_CCU_SDIO3>; status = "disabled"; }; @@ -130,7 +132,7 @@ compatible = "brcm,kona-sdhci"; reg = <0x3f1b0000 0x801c>; interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&sdio4_clk>; + clocks = <&master_ccu BCM21664_MASTER_CCU_SDIO4>; status = "disabled"; }; @@ -140,7 +142,7 @@ interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>; #address-cells = <1>; #size-cells = <0>; - clocks = <&bsc1_clk>; + clocks = <&slave_ccu BCM21664_SLAVE_CCU_BSC1>; status = "disabled"; }; @@ -150,7 +152,7 @@ interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>; #address-cells = <1>; #size-cells = <0>; - clocks = <&bsc2_clk>; + clocks = <&slave_ccu BCM21664_SLAVE_CCU_BSC2>; status = "disabled"; }; @@ -160,7 +162,7 @@ interrupts = <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>; #address-cells = <1>; #size-cells = <0>; - clocks = <&bsc3_clk>; + clocks = <&slave_ccu BCM21664_SLAVE_CCU_BSC3>; status = "disabled"; }; @@ -170,105 +172,149 @@ interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>; #address-cells = <1>; #size-cells = <0>; - clocks = <&bsc4_clk>; + clocks = <&slave_ccu BCM21664_SLAVE_CCU_BSC4>; status = "disabled"; }; clocks { - bsc1_clk: bsc1 { - compatible = "fixed-clock"; - clock-frequency = <13000000>; - #clock-cells = <0>; - }; + #address-cells = <1>; + #size-cells = <1>; + ranges; - bsc2_clk: bsc2 { - compatible = "fixed-clock"; - clock-frequency = <13000000>; + /* + * Fixed clocks are defined before CCUs whose + * clocks may depend on them. + */ + + ref_32k_clk: ref_32k { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <32768>; }; - bsc3_clk: bsc3 { - compatible = "fixed-clock"; - clock-frequency = <13000000>; + bbl_32k_clk: bbl_32k { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <32768>; }; - bsc4_clk: bsc4 { + ref_13m_clk: ref_13m { + #clock-cells = <0>; compatible = "fixed-clock"; clock-frequency = <13000000>; - #clock-cells = <0>; }; - pmu_bsc_clk: pmu_bsc { + var_13m_clk: var_13m { + #clock-cells = <0>; compatible = "fixed-clock"; clock-frequency = <13000000>; - #clock-cells = <0>; }; - hub_timer_clk: hub_timer { - compatible = "fixed-clock"; - clock-frequency = <32768>; + dft_19_5m_clk: dft_19_5m { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <19500000>; }; - pwm_clk: pwm { + ref_crystal_clk: ref_crystal { + #clock-cells = <0>; compatible = "fixed-clock"; clock-frequency = <26000000>; - #clock-cells = <0>; }; - sdio1_clk: sdio1 { - compatible = "fixed-clock"; - clock-frequency = <48000000>; + ref_52m_clk: ref_52m { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <52000000>; }; - sdio2_clk: sdio2 { - compatible = "fixed-clock"; - clock-frequency = <48000000>; + var_52m_clk: var_52m { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <52000000>; }; - sdio3_clk: sdio3 { - compatible = "fixed-clock"; - clock-frequency = <48000000>; + usb_otg_ahb_clk: usb_otg_ahb { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <52000000>; }; - sdio4_clk: sdio4 { - compatible = "fixed-clock"; - clock-frequency = <48000000>; + ref_96m_clk: ref_96m { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <96000000>; }; - tmon_1m_clk: tmon_1m { - compatible = "fixed-clock"; - clock-frequency = <1000000>; + var_96m_clk: var_96m { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <96000000>; }; - uartb_clk: uartb { - compatible = "fixed-clock"; - clock-frequency = <13000000>; + ref_104m_clk: ref_104m { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <104000000>; }; - uartb2_clk: uartb2 { - compatible = "fixed-clock"; - clock-frequency = <13000000>; + var_104m_clk: var_104m { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <104000000>; }; - uartb3_clk: uartb3 { - compatible = "fixed-clock"; - clock-frequency = <13000000>; + ref_156m_clk: ref_156m { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <156000000>; }; - usb_otg_ahb_clk: usb_otg_ahb { - compatible = "fixed-clock"; - clock-frequency = <52000000>; + var_156m_clk: var_156m { #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <156000000>; + }; + + root_ccu: root_ccu { + compatible = BCM21664_DT_ROOT_CCU_COMPAT; + reg = <0x35001000 0x0f00>; + #clock-cells = <1>; + clock-output-names = "frac_1m"; + }; + + aon_ccu: aon_ccu { + compatible = BCM21664_DT_AON_CCU_COMPAT; + reg = <0x35002000 0x0f00>; + #clock-cells = <1>; + clock-output-names = "hub_timer"; + }; + + master_ccu: master_ccu { + compatible = BCM21664_DT_MASTER_CCU_COMPAT; + reg = <0x3f001000 0x0f00>; + #clock-cells = <1>; + clock-output-names = "sdio1", + "sdio2", + "sdio3", + "sdio4", + "sdio1_sleep", + "sdio2_sleep", + "sdio3_sleep", + "sdio4_sleep"; + }; + + slave_ccu: slave_ccu { + compatible = BCM21664_DT_SLAVE_CCU_COMPAT; + reg = <0x3e011000 0x0f00>; + #clock-cells = <1>; + clock-output-names = "uartb", + "uartb2", + "uartb3", + "bsc1", + "bsc2", + "bsc3", + "bsc4"; }; }; diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi index d9f99e7deb83..c1414cb81fd4 100644 --- a/arch/arm/boot/dts/keystone.dtsi +++ b/arch/arm/boot/dts/keystone.dtsi @@ -66,9 +66,21 @@ ranges = <0x0 0x0 0x0 0xc0000000>; dma-ranges = <0x80000000 0x8 0x00000000 0x80000000>; + pllctrl: pll-controller@02310000 { + compatible = "ti,keystone-pllctrl", "syscon"; + reg = <0x02310000 0x200>; + }; + + devctrl: device-state-control@02620000 { + compatible = "ti,keystone-devctrl", "syscon"; + reg = <0x02620000 0x1000>; + }; + rstctrl: reset-controller { compatible = "ti,keystone-reset"; - reg = <0x023100e8 4>; /* pll reset control reg */ + ti,syscon-pll = <&pllctrl 0xe4>; + ti,syscon-dev = <&devctrl 0x328>; + ti,wdt-list = <0>; }; /include/ "keystone-clocks.dtsi" diff --git a/arch/arm/boot/dts/marco.dtsi b/arch/arm/boot/dts/marco.dtsi index 0c9647d28765..fb354225740a 100644 --- a/arch/arm/boot/dts/marco.dtsi +++ b/arch/arm/boot/dts/marco.dtsi @@ -36,7 +36,7 @@ ranges = <0x40000000 0x40000000 0xa0000000>; l2-cache-controller@c0030000 { - compatible = "sirf,marco-pl310-cache", "arm,pl310-cache"; + compatible = "arm,pl310-cache"; reg = <0xc0030000 0x1000>; interrupts = <0 59 0>; arm,tag-latency = <1 1 1>; diff --git a/arch/arm/boot/dts/omap3-evm-37xx.dts b/arch/arm/boot/dts/omap3-evm-37xx.dts index 9cba94bed7ad..a8bd4349c7d2 100644 --- a/arch/arm/boot/dts/omap3-evm-37xx.dts +++ b/arch/arm/boot/dts/omap3-evm-37xx.dts @@ -26,7 +26,44 @@ }; }; +&dss { + pinctrl-names = "default"; + pinctrl-0 = < + &dss_dpi_pins1 + &dss_dpi_pins2 + >; +}; + &omap3_pmx_core { + dss_dpi_pins1: pinmux_dss_dpi_pins2 { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0) /* dss_pclk.dss_pclk */ + OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT | MUX_MODE0) /* dss_hsync.dss_hsync */ + OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT | MUX_MODE0) /* dss_vsync.dss_vsync */ + OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT | MUX_MODE0) /* dss_acbias.dss_acbias */ + + OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT | MUX_MODE0) /* dss_data6.dss_data6 */ + OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT | MUX_MODE0) /* dss_data7.dss_data7 */ + OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT | MUX_MODE0) /* dss_data8.dss_data8 */ + OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT | MUX_MODE0) /* dss_data9.dss_data9 */ + OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT | MUX_MODE0) /* dss_data10.dss_data10 */ + OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT | MUX_MODE0) /* dss_data11.dss_data11 */ + OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT | MUX_MODE0) /* dss_data12.dss_data12 */ + OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT | MUX_MODE0) /* dss_data13.dss_data13 */ + OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT | MUX_MODE0) /* dss_data14.dss_data14 */ + OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT | MUX_MODE0) /* dss_data15.dss_data15 */ + OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT | MUX_MODE0) /* dss_data16.dss_data16 */ + OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT | MUX_MODE0) /* dss_data17.dss_data17 */ + + OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE3) /* dss_data18.dss_data0 */ + OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT | MUX_MODE3) /* dss_data19.dss_data1 */ + OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT | MUX_MODE3) /* dss_data20.dss_data2 */ + OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT | MUX_MODE3) /* dss_data21.dss_data3 */ + OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT | MUX_MODE3) /* dss_data22.dss_data4 */ + OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE3) /* dss_data23.dss_data5 */ + >; + }; + mmc1_pins: pinmux_mmc1_pins { pinctrl-single,pins = < 0x114 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* sdmmc1_clk.sdmmc1_clk */ @@ -75,6 +112,19 @@ }; }; +&omap3_pmx_wkup { + dss_dpi_pins2: pinmux_dss_dpi_pins1 { + pinctrl-single,pins = < + 0x0a (PIN_OUTPUT | MUX_MODE3) /* sys_boot0.dss_data18 */ + 0x0c (PIN_OUTPUT | MUX_MODE3) /* sys_boot1.dss_data19 */ + 0x10 (PIN_OUTPUT | MUX_MODE3) /* sys_boot3.dss_data20 */ + 0x12 (PIN_OUTPUT | MUX_MODE3) /* sys_boot4.dss_data21 */ + 0x14 (PIN_OUTPUT | MUX_MODE3) /* sys_boot5.dss_data22 */ + 0x16 (PIN_OUTPUT | MUX_MODE3) /* sys_boot6.dss_data23 */ + >; + }; +}; + &mmc1 { pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins>; diff --git a/arch/arm/boot/dts/omap3-evm-common.dtsi b/arch/arm/boot/dts/omap3-evm-common.dtsi index 3007e79c9cd6..8ae8f007c8ad 100644 --- a/arch/arm/boot/dts/omap3-evm-common.dtsi +++ b/arch/arm/boot/dts/omap3-evm-common.dtsi @@ -44,6 +44,11 @@ #include "twl4030.dtsi" #include "twl4030_omap3.dtsi" +#include "omap3-panel-sharp-ls037v7dw01.dtsi" + +&backlight0 { + gpios = <&twl_gpio 18 GPIO_ACTIVE_LOW>; +}; &i2c2 { clock-frequency = <400000>; @@ -61,6 +66,27 @@ }; }; +&lcd_3v3 { + gpio = <&gpio5 25 GPIO_ACTIVE_LOW>; /* gpio153 */ + enable-active-low; +}; + +&lcd0 { + enable-gpios = <&gpio5 24 GPIO_ACTIVE_HIGH>; /* gpio152, lcd INI */ + reset-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>; /* gpio155, lcd RESB */ + mode-gpios = <&gpio5 26 GPIO_ACTIVE_HIGH /* gpio154, lcd MO */ + &gpio1 2 GPIO_ACTIVE_HIGH /* gpio2, lcd LR */ + &gpio1 3 GPIO_ACTIVE_HIGH>; /* gpio3, lcd UD */ +}; + +&mcspi1 { + tsc2046@0 { + interrupt-parent = <&gpio6>; + interrupts = <15 0>; /* gpio175 */ + pendown-gpio = <&gpio6 15 0>; + }; +}; + &mmc1 { vmmc-supply = <&vmmc1>; vmmc_aux-supply = <&vsim>; diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts index f8ad125fa46f..021311f7964b 100644 --- a/arch/arm/boot/dts/omap3-gta04.dts +++ b/arch/arm/boot/dts/omap3-gta04.dts @@ -44,6 +44,36 @@ ti,mcbsp = <&mcbsp2>; ti,codec = <&twl_audio>; }; + + spi_lcd { + compatible = "spi-gpio"; + #address-cells = <0x1>; + #size-cells = <0x0>; + pinctrl-names = "default"; + pinctrl-0 = <&spi_gpio_pins>; + + gpio-sck = <&gpio1 12 0>; + gpio-miso = <&gpio1 18 0>; + gpio-mosi = <&gpio1 20 0>; + cs-gpios = <&gpio1 19 0>; + num-chipselects = <1>; + + /* lcd panel */ + lcd: td028ttec1@0 { + compatible = "toppoly,td028ttec1"; + reg = <0>; + spi-max-frequency = <100000>; + spi-cpol; + spi-cpha; + + label = "lcd"; + port { + lcd_in: endpoint { + remote-endpoint = <&dpi_out>; + }; + }; + }; + }; }; &omap3_pmx_core { @@ -78,6 +108,47 @@ 0x11e (PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc1_dat3.sdmmc1_dat3 */ >; }; + + dss_dpi_pins: pinmux_dss_dpi_pins { + pinctrl-single,pins = < + 0x0a4 (PIN_OUTPUT | MUX_MODE0) /* dss_pclk.dss_pclk */ + 0x0a6 (PIN_OUTPUT | MUX_MODE0) /* dss_hsync.dss_hsync */ + 0x0a8 (PIN_OUTPUT | MUX_MODE0) /* dss_vsync.dss_vsync */ + 0x0aa (PIN_OUTPUT | MUX_MODE0) /* dss_acbias.dss_acbias */ + 0x0ac (PIN_OUTPUT | MUX_MODE0) /* dss_data0.dss_data0 */ + 0x0ae (PIN_OUTPUT | MUX_MODE0) /* dss_data1.dss_data1 */ + 0x0b0 (PIN_OUTPUT | MUX_MODE0) /* dss_data2.dss_data2 */ + 0x0b2 (PIN_OUTPUT | MUX_MODE0) /* dss_data3.dss_data3 */ + 0x0b4 (PIN_OUTPUT | MUX_MODE0) /* dss_data4.dss_data4 */ + 0x0b6 (PIN_OUTPUT | MUX_MODE0) /* dss_data5.dss_data5 */ + 0x0b8 (PIN_OUTPUT | MUX_MODE0) /* dss_data6.dss_data6 */ + 0x0ba (PIN_OUTPUT | MUX_MODE0) /* dss_data7.dss_data7 */ + 0x0bc (PIN_OUTPUT | MUX_MODE0) /* dss_data8.dss_data8 */ + 0x0be (PIN_OUTPUT | MUX_MODE0) /* dss_data9.dss_data9 */ + 0x0c0 (PIN_OUTPUT | MUX_MODE0) /* dss_data10.dss_data10 */ + 0x0c2 (PIN_OUTPUT | MUX_MODE0) /* dss_data11.dss_data11 */ + 0x0c4 (PIN_OUTPUT | MUX_MODE0) /* dss_data12.dss_data12 */ + 0x0c6 (PIN_OUTPUT | MUX_MODE0) /* dss_data13.dss_data13 */ + 0x0c8 (PIN_OUTPUT | MUX_MODE0) /* dss_data14.dss_data14 */ + 0x0ca (PIN_OUTPUT | MUX_MODE0) /* dss_data15.dss_data15 */ + 0x0cc (PIN_OUTPUT | MUX_MODE0) /* dss_data16.dss_data16 */ + 0x0ce (PIN_OUTPUT | MUX_MODE0) /* dss_data17.dss_data17 */ + 0x0d0 (PIN_OUTPUT | MUX_MODE0) /* dss_data18.dss_data18 */ + 0x0d2 (PIN_OUTPUT | MUX_MODE0) /* dss_data19.dss_data19 */ + 0x0d4 (PIN_OUTPUT | MUX_MODE0) /* dss_data20.dss_data20 */ + 0x0d6 (PIN_OUTPUT | MUX_MODE0) /* dss_data21.dss_data21 */ + 0x0d8 (PIN_OUTPUT | MUX_MODE0) /* dss_data22.dss_data22 */ + 0x0da (PIN_OUTPUT | MUX_MODE0) /* dss_data23.dss_data23 */ + >; + }; + + spi_gpio_pins: spi_gpio_pinmux { + pinctrl-single,pins = <0x5a8 (PIN_OUTPUT | MUX_MODE4) /* clk */ + 0x5b6 (PIN_OUTPUT | MUX_MODE4) /* cs */ + 0x5b8 (PIN_OUTPUT | MUX_MODE4) /* tx */ + 0x5b4 (PIN_INPUT | MUX_MODE4) /* rx */ + >; + }; }; &i2c1 { @@ -219,3 +290,22 @@ regulator-min-microvolt = <2800000>; regulator-max-microvolt = <3150000>; }; + +/* Needed to power the DPI pins */ +&vpll2 { + regulator-always-on; +}; + +&dss { + pinctrl-names = "default"; + pinctrl-0 = < &dss_dpi_pins >; + + status = "okay"; + + port { + dpi_out: endpoint { + remote-endpoint = <&lcd_in>; + data-lines = <24>; + }; + }; +}; diff --git a/arch/arm/boot/dts/omap3-ldp.dts b/arch/arm/boot/dts/omap3-ldp.dts index 476ff158ddb3..af272c156e21 100644 --- a/arch/arm/boot/dts/omap3-ldp.dts +++ b/arch/arm/boot/dts/omap3-ldp.dts @@ -164,6 +164,11 @@ #include "twl4030.dtsi" #include "twl4030_omap3.dtsi" +#include "omap3-panel-sharp-ls037v7dw01.dtsi" + +&backlight0 { + gpios = <&twl_gpio 7 GPIO_ACTIVE_HIGH>; +}; &i2c2 { clock-frequency = <400000>; @@ -173,6 +178,25 @@ clock-frequency = <400000>; }; +/* tps61130rsa enabled by twl4030 regen */ +&lcd_3v3 { + regulator-always-on; +}; + +&lcd0 { + enable-gpios = <&twl_gpio 15 GPIO_ACTIVE_HIGH>; /* lcd INI */ + reset-gpios = <&gpio2 23 GPIO_ACTIVE_HIGH>; /* gpio55, lcd RESB */ + mode-gpios = <&gpio2 24 GPIO_ACTIVE_HIGH>; /* gpio56, lcd MO */ +}; + +&mcspi1 { + tsc2046@0 { + interrupt-parent = <&gpio2>; + interrupts = <22 0>; /* gpio54 */ + pendown-gpio = <&gpio2 22 0>; + }; +}; + &mmc1 { /* See 35xx errata 2.1.1.128 in SPRZ278F */ compatible = "ti,omap3-pre-es3-hsmmc"; @@ -251,8 +275,3 @@ /* Needed for ads7846 */ regulator-name = "vcc"; }; - -&vpll2 { - /* Needed for DSS */ - regulator-name = "vdds_dsi"; -}; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 059a8ff1e6ac..ae8ae3f4f9bf 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -651,9 +651,24 @@ * Also... order in the device tree actually matters here. */ tsc2005@0 { - compatible = "tsc2005"; + compatible = "ti,tsc2005"; spi-max-frequency = <6000000>; reg = <0>; + + vio-supply = <&vio>; + + reset-gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>; /* 104 */ + interrupts-extended = <&gpio4 4 IRQ_TYPE_EDGE_RISING>; /* 100 */ + + touchscreen-fuzz-x = <4>; + touchscreen-fuzz-y = <7>; + touchscreen-fuzz-pressure = <2>; + touchscreen-max-x = <4096>; + touchscreen-max-y = <4096>; + touchscreen-max-pressure = <2048>; + + ti,x-plate-ohms = <280>; + ti,esd-recovery-timeout-ms = <8000>; }; acx565akm@2 { diff --git a/arch/arm/boot/dts/omap3-overo-alto35-common.dtsi b/arch/arm/boot/dts/omap3-overo-alto35-common.dtsi index 19d64864a109..7aae8fb82c1f 100644 --- a/arch/arm/boot/dts/omap3-overo-alto35-common.dtsi +++ b/arch/arm/boot/dts/omap3-overo-alto35-common.dtsi @@ -11,6 +11,7 @@ */ #include "omap3-overo-common-peripherals.dtsi" +#include "omap3-overo-common-lcd35.dtsi" #include <dt-bindings/input/input.h> diff --git a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi index 19de6ff79686..17b82f82638a 100644 --- a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi +++ b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi @@ -11,6 +11,7 @@ */ #include "omap3-overo-common-peripherals.dtsi" +#include "omap3-overo-common-lcd43.dtsi" #include <dt-bindings/input/input.h> diff --git a/arch/arm/boot/dts/omap3-overo-common-dvi.dtsi b/arch/arm/boot/dts/omap3-overo-common-dvi.dtsi new file mode 100644 index 000000000000..802f704f67e5 --- /dev/null +++ b/arch/arm/boot/dts/omap3-overo-common-dvi.dtsi @@ -0,0 +1,111 @@ +/* + * Copyright (C) 2014 Florian Vaussard, EPFL Mobots group + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * DVI output for some Gumstix Overo boards (Tobi and Summit) + */ + +&omap3_pmx_core { + dss_dpi_pins: pinmux_dss_dpi_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0) /* dss_pclk.dss_pclk */ + OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT | MUX_MODE0) /* dss_hsync.dss_hsync */ + OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT | MUX_MODE0) /* dss_vsync.dss_vsync */ + OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT | MUX_MODE0) /* dss_acbias.dss_acbias */ + OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE0) /* dss_data0.dss_data0 */ + OMAP3_CORE1_IOPAD(0x20de, PIN_OUTPUT | MUX_MODE0) /* dss_data1.dss_data1 */ + OMAP3_CORE1_IOPAD(0x20e0, PIN_OUTPUT | MUX_MODE0) /* dss_data2.dss_data2 */ + OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE0) /* dss_data3.dss_data3 */ + OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE0) /* dss_data4.dss_data4 */ + OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE0) /* dss_data5.dss_data5 */ + OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT | MUX_MODE0) /* dss_data6.dss_data6 */ + OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT | MUX_MODE0) /* dss_data7.dss_data7 */ + OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT | MUX_MODE0) /* dss_data8.dss_data8 */ + OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT | MUX_MODE0) /* dss_data9.dss_data9 */ + OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT | MUX_MODE0) /* dss_data10.dss_data10 */ + OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT | MUX_MODE0) /* dss_data11.dss_data11 */ + OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT | MUX_MODE0) /* dss_data12.dss_data12 */ + OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT | MUX_MODE0) /* dss_data13.dss_data13 */ + OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT | MUX_MODE0) /* dss_data14.dss_data14 */ + OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT | MUX_MODE0) /* dss_data15.dss_data15 */ + OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT | MUX_MODE0) /* dss_data16.dss_data16 */ + OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT | MUX_MODE0) /* dss_data17.dss_data17 */ + OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE0) /* dss_data18.dss_data18 */ + OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT | MUX_MODE0) /* dss_data19.dss_data19 */ + OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT | MUX_MODE0) /* dss_data20.dss_data20 */ + OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT | MUX_MODE0) /* dss_data21.dss_data21 */ + OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT | MUX_MODE0) /* dss_data22.dss_data22 */ + OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE0) /* dss_data23.dss_data23 */ + >; + }; +}; + +/* Needed to power the DPI pins */ +&vpll2 { + regulator-always-on; +}; + +&dss { + status = "ok"; + + pinctrl-names = "default"; + pinctrl-0 = <&dss_dpi_pins>; + + port { + dpi_out: endpoint { + remote-endpoint = <&tfp410_in>; + data-lines = <24>; + }; + }; +}; + +/ { + aliases { + display0 = &dvi0; + }; + + tfp410: encoder@0 { + compatible = "ti,tfp410"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + tfp410_in: endpoint@0 { + remote-endpoint = <&dpi_out>; + }; + }; + + port@1 { + reg = <1>; + + tfp410_out: endpoint@0 { + remote-endpoint = <&dvi_connector_in>; + }; + }; + }; + }; + + dvi0: connector@0 { + compatible = "dvi-connector"; + label = "dvi"; + + digital; + ddc-i2c-bus = <&i2c3>; + + port { + dvi_connector_in: endpoint { + remote-endpoint = <&tfp410_out>; + }; + }; + }; +}; + diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi new file mode 100644 index 000000000000..233c69e50ae3 --- /dev/null +++ b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi @@ -0,0 +1,165 @@ +/* + * Copyright (C) 2014 Florian Vaussard, EPFL Mobots group + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * 4.3'' LCD panel output for some Gumstix Overo boards (Gallop43, Chestnut43) + */ + +&omap3_pmx_core { + dss_dpi_pins: pinmux_dss_dpi_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0) /* dss_pclk.dss_pclk */ + OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT | MUX_MODE0) /* dss_hsync.dss_hsync */ + OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT | MUX_MODE0) /* dss_vsync.dss_vsync */ + OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT | MUX_MODE0) /* dss_acbias.dss_acbias */ + OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE0) /* dss_data0.dss_data0 */ + OMAP3_CORE1_IOPAD(0x20de, PIN_OUTPUT | MUX_MODE0) /* dss_data1.dss_data1 */ + OMAP3_CORE1_IOPAD(0x20e0, PIN_OUTPUT | MUX_MODE0) /* dss_data2.dss_data2 */ + OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE0) /* dss_data3.dss_data3 */ + OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE0) /* dss_data4.dss_data4 */ + OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE0) /* dss_data5.dss_data5 */ + OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT | MUX_MODE0) /* dss_data6.dss_data6 */ + OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT | MUX_MODE0) /* dss_data7.dss_data7 */ + OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT | MUX_MODE0) /* dss_data8.dss_data8 */ + OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT | MUX_MODE0) /* dss_data9.dss_data9 */ + OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT | MUX_MODE0) /* dss_data10.dss_data10 */ + OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT | MUX_MODE0) /* dss_data11.dss_data11 */ + OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT | MUX_MODE0) /* dss_data12.dss_data12 */ + OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT | MUX_MODE0) /* dss_data13.dss_data13 */ + OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT | MUX_MODE0) /* dss_data14.dss_data14 */ + OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT | MUX_MODE0) /* dss_data15.dss_data15 */ + OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT | MUX_MODE0) /* dss_data16.dss_data16 */ + OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT | MUX_MODE0) /* dss_data17.dss_data17 */ + OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE0) /* dss_data18.dss_data18 */ + OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT | MUX_MODE0) /* dss_data19.dss_data19 */ + OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT | MUX_MODE0) /* dss_data20.dss_data20 */ + OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT | MUX_MODE0) /* dss_data21.dss_data21 */ + OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT | MUX_MODE0) /* dss_data22.dss_data22 */ + OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE0) /* dss_data23.dss_data23 */ + >; + }; + + lb035_pins: pinmux_lb035_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x2174, PIN_OUTPUT | MUX_MODE4) /* uart2_cts.gpio_144 */ + >; + }; + + backlight_pins: pinmux_backlight_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE4) /* uart2_rts.gpio_145 */ + >; + }; + + mcspi1_pins: pinmux_mcspi1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21c8, PIN_INPUT | MUX_MODE0) /* mcspi1_clk.mcspi1_clk */ + OMAP3_CORE1_IOPAD(0x21ca, PIN_INPUT | MUX_MODE0) /* mcspi1_simo.mcspi1_simo */ + OMAP3_CORE1_IOPAD(0x21cc, PIN_INPUT | MUX_MODE0) /* mcspi1_somi.mcspi1_somi */ + OMAP3_CORE1_IOPAD(0x21ce, PIN_INPUT | MUX_MODE0) /* mcspi1_cs0.mcspi1_cs0 */ + >; + }; + + ads7846_pins: pinmux_ads7846_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x2138, PIN_INPUT_PULLDOWN | MUX_MODE4) /* csi2_dx1.gpio_114 */ + >; + }; +}; + +/* Needed to power the DPI pins */ +&vpll2 { + regulator-always-on; +}; + +&dss { + status = "ok"; + + pinctrl-names = "default"; + pinctrl-0 = <&dss_dpi_pins>; + + port { + dpi_out: endpoint { + remote-endpoint = <&lcd_in>; + data-lines = <24>; + }; + }; +}; + +/ { + aliases { + display0 = &lcd0; + }; + + ads7846reg: ads7846-reg { + compatible = "regulator-fixed"; + regulator-name = "ads7846-reg"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + backlight { + compatible = "gpio-backlight"; + + pinctrl-names = "default"; + pinctrl-0 = <&backlight_pins>; + gpios = <&gpio5 17 GPIO_ACTIVE_HIGH>; /* gpio_145 */ + + default-on; + }; +}; + +&mcspi1 { + pinctrl-names = "default"; + pinctrl-0 = <&mcspi1_pins>; + + lcd0: display@0 { + compatible = "lgphilips,lb035q02"; + label = "lcd"; + + reg = <1>; /* CS1 */ + spi-max-frequency = <10000000>; + spi-cpol; + spi-cpha; + + pinctrl-names = "default"; + pinctrl-0 = <&lb035_pins>; + enable-gpios = <&gpio5 16 GPIO_ACTIVE_HIGH>; /* gpio_144 */ + + port { + lcd_in: endpoint { + remote-endpoint = <&dpi_out>; + }; + }; + }; + + /* touch controller */ + ads7846@0 { + pinctrl-names = "default"; + pinctrl-0 = <&ads7846_pins>; + + compatible = "ti,ads7846"; + vcc-supply = <&ads7846reg>; + + reg = <0>; /* CS0 */ + spi-max-frequency = <1500000>; + + interrupt-parent = <&gpio4>; + interrupts = <18 0>; /* gpio_114 */ + pendown-gpio = <&gpio4 18 0>; + + ti,x-min = /bits/ 16 <0x0>; + ti,x-max = /bits/ 16 <0x0fff>; + ti,y-min = /bits/ 16 <0x0>; + ti,y-max = /bits/ 16 <0x0fff>; + ti,x-plate-ohms = /bits/ 16 <180>; + ti,pressure-max = /bits/ 16 <255>; + + linux,wakeup; + }; +}; diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi new file mode 100644 index 000000000000..f5395b7da912 --- /dev/null +++ b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi @@ -0,0 +1,178 @@ +/* + * Copyright (C) 2014 Florian Vaussard, EPFL Mobots group + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * 4.3'' LCD panel output for some Gumstix Overo boards (Gallop43, Chestnut43) + */ + +&omap3_pmx_core { + dss_dpi_pins: pinmux_dss_dpi_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0) /* dss_pclk.dss_pclk */ + OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT | MUX_MODE0) /* dss_hsync.dss_hsync */ + OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT | MUX_MODE0) /* dss_vsync.dss_vsync */ + OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT | MUX_MODE0) /* dss_acbias.dss_acbias */ + OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE0) /* dss_data0.dss_data0 */ + OMAP3_CORE1_IOPAD(0x20de, PIN_OUTPUT | MUX_MODE0) /* dss_data1.dss_data1 */ + OMAP3_CORE1_IOPAD(0x20e0, PIN_OUTPUT | MUX_MODE0) /* dss_data2.dss_data2 */ + OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE0) /* dss_data3.dss_data3 */ + OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE0) /* dss_data4.dss_data4 */ + OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE0) /* dss_data5.dss_data5 */ + OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT | MUX_MODE0) /* dss_data6.dss_data6 */ + OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT | MUX_MODE0) /* dss_data7.dss_data7 */ + OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT | MUX_MODE0) /* dss_data8.dss_data8 */ + OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT | MUX_MODE0) /* dss_data9.dss_data9 */ + OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT | MUX_MODE0) /* dss_data10.dss_data10 */ + OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT | MUX_MODE0) /* dss_data11.dss_data11 */ + OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT | MUX_MODE0) /* dss_data12.dss_data12 */ + OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT | MUX_MODE0) /* dss_data13.dss_data13 */ + OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT | MUX_MODE0) /* dss_data14.dss_data14 */ + OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT | MUX_MODE0) /* dss_data15.dss_data15 */ + OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT | MUX_MODE0) /* dss_data16.dss_data16 */ + OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT | MUX_MODE0) /* dss_data17.dss_data17 */ + OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE0) /* dss_data18.dss_data18 */ + OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT | MUX_MODE0) /* dss_data19.dss_data19 */ + OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT | MUX_MODE0) /* dss_data20.dss_data20 */ + OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT | MUX_MODE0) /* dss_data21.dss_data21 */ + OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT | MUX_MODE0) /* dss_data22.dss_data22 */ + OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE0) /* dss_data23.dss_data23 */ + >; + }; + + lte430_pins: pinmux_lte430_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x2174, PIN_OUTPUT | MUX_MODE4) /* uart2_cts.gpio_144 */ + >; + }; + + backlight_pins: pinmux_backlight_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE4) /* uart2_rts.gpio_145 */ + >; + }; + + mcspi1_pins: pinmux_mcspi1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21c8, PIN_INPUT | MUX_MODE0) /* mcspi1_clk.mcspi1_clk */ + OMAP3_CORE1_IOPAD(0x21ca, PIN_INPUT | MUX_MODE0) /* mcspi1_simo.mcspi1_simo */ + OMAP3_CORE1_IOPAD(0x21cc, PIN_INPUT | MUX_MODE0) /* mcspi1_somi.mcspi1_somi */ + OMAP3_CORE1_IOPAD(0x21ce, PIN_INPUT | MUX_MODE0) /* mcspi1_cs0.mcspi1_cs0 */ + >; + }; + + ads7846_pins: pinmux_ads7846_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x2138, PIN_INPUT_PULLDOWN | MUX_MODE4) /* csi2_dx1.gpio_114 */ + >; + }; +}; + +/* Needed to power the DPI pins */ +&vpll2 { + regulator-always-on; +}; + +&dss { + status = "ok"; + + pinctrl-names = "default"; + pinctrl-0 = <&dss_dpi_pins>; + + port { + dpi_out: endpoint { + remote-endpoint = <&lcd_in>; + data-lines = <24>; + }; + }; +}; + +/ { + aliases { + display0 = &lcd0; + }; + + lcd0: display@0 { + compatible = "samsung,lte430wq-f0c", "panel-dpi"; + label = "lcd"; + + pinctrl-names = "default"; + pinctrl-0 = <<e430_pins>; + enable-gpios = <&gpio5 16 GPIO_ACTIVE_HIGH>; /* gpio_144 */ + + port { + lcd_in: endpoint { + remote-endpoint = <&dpi_out>; + }; + }; + + panel-timing { + clock-frequency = <9200000>; + hactive = <480>; + vactive = <272>; + hfront-porch = <8>; + hback-porch = <4>; + hsync-len = <41>; + vback-porch = <2>; + vfront-porch = <4>; + vsync-len = <10>; + + hsync-active = <0>; + vsync-active = <0>; + de-active = <1>; + pixelclk-active = <1>; + }; + }; + + ads7846reg: ads7846-reg { + compatible = "regulator-fixed"; + regulator-name = "ads7846-reg"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + backlight { + compatible = "gpio-backlight"; + + pinctrl-names = "default"; + pinctrl-0 = <&backlight_pins>; + gpios = <&gpio5 17 GPIO_ACTIVE_HIGH>; /* gpio_145 */ + + default-on; + }; +}; + +&mcspi1 { + pinctrl-names = "default"; + pinctrl-0 = <&mcspi1_pins>; + + /* touch controller */ + ads7846@0 { + pinctrl-names = "default"; + pinctrl-0 = <&ads7846_pins>; + + compatible = "ti,ads7846"; + vcc-supply = <&ads7846reg>; + + reg = <0>; /* CS0 */ + spi-max-frequency = <1500000>; + + interrupt-parent = <&gpio4>; + interrupts = <18 0>; /* gpio_114 */ + pendown-gpio = <&gpio4 18 0>; + + ti,x-min = /bits/ 16 <0x0>; + ti,x-max = /bits/ 16 <0x0fff>; + ti,y-min = /bits/ 16 <0x0>; + ti,y-max = /bits/ 16 <0x0fff>; + ti,x-plate-ohms = /bits/ 16 <180>; + ti,pressure-max = /bits/ 16 <255>; + + linux,wakeup; + }; +}; + diff --git a/arch/arm/boot/dts/omap3-overo-gallop43-common.dtsi b/arch/arm/boot/dts/omap3-overo-gallop43-common.dtsi index 5e848c26986b..49d2254a99b0 100644 --- a/arch/arm/boot/dts/omap3-overo-gallop43-common.dtsi +++ b/arch/arm/boot/dts/omap3-overo-gallop43-common.dtsi @@ -11,6 +11,7 @@ */ #include "omap3-overo-common-peripherals.dtsi" +#include "omap3-overo-common-lcd43.dtsi" #include <dt-bindings/input/input.h> diff --git a/arch/arm/boot/dts/omap3-overo-palo43-common.dtsi b/arch/arm/boot/dts/omap3-overo-palo43-common.dtsi index abea232825b9..087aedf5b902 100644 --- a/arch/arm/boot/dts/omap3-overo-palo43-common.dtsi +++ b/arch/arm/boot/dts/omap3-overo-palo43-common.dtsi @@ -11,6 +11,7 @@ */ #include "omap3-overo-common-peripherals.dtsi" +#include "omap3-overo-common-lcd43.dtsi" #include <dt-bindings/input/input.h> diff --git a/arch/arm/boot/dts/omap3-overo-summit-common.dtsi b/arch/arm/boot/dts/omap3-overo-summit-common.dtsi index 999d1cd4a09f..0ac97ba98549 100644 --- a/arch/arm/boot/dts/omap3-overo-summit-common.dtsi +++ b/arch/arm/boot/dts/omap3-overo-summit-common.dtsi @@ -11,6 +11,7 @@ */ #include "omap3-overo-common-peripherals.dtsi" +#include "omap3-overo-common-dvi.dtsi" / { leds { diff --git a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi index 13df50b39442..9e24b6a1d07b 100644 --- a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi +++ b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi @@ -11,6 +11,7 @@ */ #include "omap3-overo-common-peripherals.dtsi" +#include "omap3-overo-common-dvi.dtsi" / { leds { diff --git a/arch/arm/boot/dts/omap3-panel-sharp-ls037v7dw01.dtsi b/arch/arm/boot/dts/omap3-panel-sharp-ls037v7dw01.dtsi new file mode 100644 index 000000000000..f4b1a61853e3 --- /dev/null +++ b/arch/arm/boot/dts/omap3-panel-sharp-ls037v7dw01.dtsi @@ -0,0 +1,71 @@ +/* + * Common file for omap dpi panels with QVGA and reset pins + * + * Note that the board specifc DTS file needs to specify + * at minimum the GPIO enable-gpios for display, and + * gpios for gpio-backlight. + */ + +/ { + aliases { + display0 = &lcd0; + }; + + backlight0: backlight { + compatible = "gpio-backlight"; + default-on; + }; + + /* 3.3V GPIO controlled regulator for LCD_ENVDD */ + lcd_3v3: regulator-lcd-3v3 { + compatible = "regulator-fixed"; + regulator-name = "lcd_3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + startup-delay-us = <70000>; + }; + + lcd0: display { + compatible = "sharp,ls037v7dw01"; + label = "lcd"; + power-supply = <&lcd_3v3>; + + port { + lcd_in: endpoint { + remote-endpoint = <&dpi_out>; + }; + }; + }; +}; + +/* Needed to power the DPI pins */ +&vpll2 { + regulator-always-on; +}; + +&dss { + status = "ok"; + port { + dpi_out: endpoint { + remote-endpoint = <&lcd_in>; + data-lines = <18>; + }; + }; +}; + +&mcspi1 { + tsc2046@0 { + reg = <0>; /* CS0 */ + compatible = "ti,tsc2046"; + spi-max-frequency = <1000000>; + vcc-supply = <&lcd_3v3>; + ti,x-min = /bits/ 16 <0>; + ti,x-max = /bits/ 16 <8000>; + ti,y-min = /bits/ 16 <0>; + ti,y-max = /bits/ 16 <4800>; + ti,x-plate-ohms = /bits/ 16 <40>; + ti,pressure-max = /bits/ 16 <255>; + ti,swap-xy; + linux,wakeup; + }; +}; diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts index cd53a64d8f2e..6dc84d9f9b4c 100644 --- a/arch/arm/boot/dts/omap4-duovero-parlor.dts +++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts @@ -15,6 +15,10 @@ model = "OMAP4430 Gumstix Duovero on Parlor"; compatible = "gumstix,omap4-duovero-parlor", "gumstix,omap4-duovero", "ti,omap4430", "ti,omap4"; + aliases { + display0 = &hdmi0; + }; + leds { compatible = "gpio-leds"; led0 { @@ -35,6 +39,21 @@ gpio-key,wakeup; }; }; + + hdmi0: connector@0 { + compatible = "hdmi-connector"; + label = "hdmi"; + + type = "d"; + + hpd-gpios = <&gpio2 31 GPIO_ACTIVE_HIGH>; /* gpio_63 */ + + port { + hdmi_connector_in: endpoint { + remote-endpoint = <&hdmi_out>; + }; + }; + }; }; &omap4_pmx_core { @@ -77,6 +96,15 @@ OMAP4_IOPAD(0x070, PIN_INPUT_PULLUP | MUX_MODE3) /* gpmc_a24.gpio_48: amdix enabled */ >; }; + + dss_hdmi_pins: pinmux_dss_hdmi_pins { + pinctrl-single,pins = < + OMAP4_IOPAD(0x098, PIN_INPUT | MUX_MODE3) /* hdmi_hpd.gpio_63 */ + OMAP4_IOPAD(0x09a, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_cec.hdmi_cec */ + OMAP4_IOPAD(0x09c, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_ddc_scl.hdmi_ddc_scl */ + OMAP4_IOPAD(0x09e, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_ddc_sda.hdmi_ddc_sda */ + >; + }; }; &i2c2 { @@ -143,4 +171,20 @@ }; }; +&dss { + status = "ok"; +}; + +&hdmi { + status = "ok"; + + pinctrl-names = "default"; + pinctrl-0 = <&dss_hdmi_pins>; + + port { + hdmi_out: endpoint { + remote-endpoint = <&hdmi_connector_in>; + }; + }; +}; diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index 43a587e097d4..7e26d222bfe3 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -922,6 +922,8 @@ ti,hwmods = "dss_hdmi"; clocks = <&dss_48mhz_clk>, <&dss_sys_clk>; clock-names = "fck", "sys_clk"; + dmas = <&sdma 76>; + dma-names = "audio_tx"; }; }; }; diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts index 3b99ec25b748..1e1b05768cec 100644 --- a/arch/arm/boot/dts/omap5-uevm.dts +++ b/arch/arm/boot/dts/omap5-uevm.dts @@ -20,6 +20,10 @@ reg = <0x80000000 0x7F000000>; /* 2032 MB */ }; + aliases { + display0 = &hdmi0; + }; + vmmcsd_fixed: fixedregulator-mmcsd { compatible = "regulator-fixed"; regulator-name = "vmmcsd_fixed"; @@ -51,6 +55,51 @@ default-state = "off"; }; }; + + tpd12s015: encoder@0 { + compatible = "ti,tpd12s015"; + + pinctrl-names = "default"; + pinctrl-0 = <&tpd12s015_pins>; + + gpios = <&gpio9 0 GPIO_ACTIVE_HIGH>, /* TCA6424A P01, CT CP HPD */ + <&gpio9 1 GPIO_ACTIVE_HIGH>, /* TCA6424A P00, LS OE */ + <&gpio7 1 GPIO_ACTIVE_HIGH>; /* GPIO 193, HPD */ + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + tpd12s015_in: endpoint@0 { + remote-endpoint = <&hdmi_out>; + }; + }; + + port@1 { + reg = <1>; + + tpd12s015_out: endpoint@0 { + remote-endpoint = <&hdmi_connector_in>; + }; + }; + }; + }; + + hdmi0: connector@0 { + compatible = "hdmi-connector"; + label = "hdmi"; + + type = "b"; + + port { + hdmi_connector_in: endpoint { + remote-endpoint = <&tpd12s015_out>; + }; + }; + }; }; &omap5_pmx_core { @@ -183,6 +232,19 @@ >; }; + dss_hdmi_pins: pinmux_dss_hdmi_pins { + pinctrl-single,pins = < + 0x0fc (PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_cec.hdmi_cec */ + 0x100 (PIN_INPUT | MUX_MODE0) /* hdmi_ddc_scl.hdmi_ddc_scl */ + 0x102 (PIN_INPUT | MUX_MODE0) /* hdmi_ddc_sda.hdmi_ddc_sda */ + >; + }; + + tpd12s015_pins: pinmux_tpd12s015_pins { + pinctrl-single,pins = < + 0x0fe (PIN_INPUT_PULLDOWN | MUX_MODE6) /* hdmi_hpd.gpio7_193 */ + >; + }; }; &omap5_pmx_wkup { @@ -434,6 +496,13 @@ pinctrl-0 = <&i2c5_pins>; clock-frequency = <400000>; + + gpio9: gpio@22 { + compatible = "ti,tca6424"; + reg = <0x22>; + gpio-controller; + #gpio-cells = <2>; + }; }; &mcbsp3 { @@ -491,3 +560,21 @@ &cpu0 { cpu0-supply = <&smps123_reg>; }; + +&dss { + status = "ok"; +}; + +&hdmi { + status = "ok"; + vdda-supply = <&ldo4_reg>; + + pinctrl-names = "default"; + pinctrl-0 = <&dss_hdmi_pins>; + + port { + hdmi_out: endpoint { + remote-endpoint = <&tpd12s015_in>; + }; + }; +}; diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index e58be57984ab..3bfda16c8b52 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -924,6 +924,68 @@ ti,hwmods = "sata"; }; + dss: dss@58000000 { + compatible = "ti,omap5-dss"; + reg = <0x58000000 0x80>; + status = "disabled"; + ti,hwmods = "dss_core"; + clocks = <&dss_dss_clk>; + clock-names = "fck"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + dispc@58001000 { + compatible = "ti,omap5-dispc"; + reg = <0x58001000 0x1000>; + interrupts = <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>; + ti,hwmods = "dss_dispc"; + clocks = <&dss_dss_clk>; + clock-names = "fck"; + }; + + dsi1: encoder@58004000 { + compatible = "ti,omap5-dsi"; + reg = <0x58004000 0x200>, + <0x58004200 0x40>, + <0x58004300 0x40>; + reg-names = "proto", "phy", "pll"; + interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + ti,hwmods = "dss_dsi1"; + clocks = <&dss_dss_clk>, <&dss_sys_clk>; + clock-names = "fck", "sys_clk"; + }; + + dsi2: encoder@58005000 { + compatible = "ti,omap5-dsi"; + reg = <0x58009000 0x200>, + <0x58009200 0x40>, + <0x58009300 0x40>; + reg-names = "proto", "phy", "pll"; + interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + ti,hwmods = "dss_dsi2"; + clocks = <&dss_dss_clk>, <&dss_sys_clk>; + clock-names = "fck", "sys_clk"; + }; + + hdmi: encoder@58060000 { + compatible = "ti,omap5-hdmi"; + reg = <0x58040000 0x200>, + <0x58040200 0x80>, + <0x58040300 0x80>, + <0x58060000 0x19000>; + reg-names = "wp", "pll", "phy", "core"; + interrupts = <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + ti,hwmods = "dss_hdmi"; + clocks = <&dss_48mhz_clk>, <&dss_sys_clk>; + clock-names = "fck", "sys_clk"; + dmas = <&sdma 76>; + dma-names = "audio_tx"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/prima2.dtsi b/arch/arm/boot/dts/prima2.dtsi index 3df7ba860282..963b7e54ab15 100644 --- a/arch/arm/boot/dts/prima2.dtsi +++ b/arch/arm/boot/dts/prima2.dtsi @@ -48,7 +48,7 @@ ranges = <0x40000000 0x40000000 0x80000000>; l2-cache-controller@80040000 { - compatible = "arm,pl310-cache", "sirf,prima2-pl310-cache"; + compatible = "arm,pl310-cache"; reg = <0x80040000 0x1000>; interrupts = <59>; arm,tag-latency = <1 1 1>; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index c7b794ed337d..d96e179490ce 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -713,7 +713,7 @@ }; i2c0: i2c@01c2ac00 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun4i-a10-i2c"; reg = <0x01c2ac00 0x400>; interrupts = <7>; clocks = <&apb1_gates 0>; @@ -724,7 +724,7 @@ }; i2c1: i2c@01c2b000 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun4i-a10-i2c"; reg = <0x01c2b000 0x400>; interrupts = <8>; clocks = <&apb1_gates 1>; @@ -735,7 +735,7 @@ }; i2c2: i2c@01c2b400 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun4i-a10-i2c"; reg = <0x01c2b400 0x400>; interrupts = <9>; clocks = <&apb1_gates 2>; diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi index aa1dd59dc34a..b64f705d9008 100644 --- a/arch/arm/boot/dts/sun5i-a10s.dtsi +++ b/arch/arm/boot/dts/sun5i-a10s.dtsi @@ -560,7 +560,7 @@ i2c0: i2c@01c2ac00 { #address-cells = <1>; #size-cells = <0>; - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun5i-a10s-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2ac00 0x400>; interrupts = <7>; clocks = <&apb1_gates 0>; @@ -571,7 +571,7 @@ i2c1: i2c@01c2b000 { #address-cells = <1>; #size-cells = <0>; - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun5i-a10s-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2b000 0x400>; interrupts = <8>; clocks = <&apb1_gates 1>; @@ -582,7 +582,7 @@ i2c2: i2c@01c2b400 { #address-cells = <1>; #size-cells = <0>; - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun5i-a10s-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2b400 0x400>; interrupts = <9>; clocks = <&apb1_gates 2>; diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi index c9fdb7b3ecd9..3b2a94c40f6e 100644 --- a/arch/arm/boot/dts/sun5i-a13.dtsi +++ b/arch/arm/boot/dts/sun5i-a13.dtsi @@ -486,7 +486,7 @@ }; i2c0: i2c@01c2ac00 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun5i-a13-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2ac00 0x400>; interrupts = <7>; clocks = <&apb1_gates 0>; @@ -497,7 +497,7 @@ }; i2c1: i2c@01c2b000 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun5i-a13-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2b000 0x400>; interrupts = <8>; clocks = <&apb1_gates 1>; @@ -508,7 +508,7 @@ }; i2c2: i2c@01c2b400 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun5i-a13-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2b400 0x400>; interrupts = <9>; clocks = <&apb1_gates 2>; diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index 0f4ea4990d2c..a9dfa12eb735 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -621,6 +621,17 @@ status = "disabled"; }; + timer@01c60000 { + compatible = "allwinner,sun6i-a31-hstimer", "allwinner,sun7i-a20-hstimer"; + reg = <0x01c60000 0x1000>; + interrupts = <0 51 4>, + <0 52 4>, + <0 53 4>, + <0 54 4>; + clocks = <&ahb1_gates 19>; + resets = <&ahb1_rst 19>; + }; + spi0: spi@01c68000 { compatible = "allwinner,sun6i-a31-spi"; reg = <0x01c68000 0x1000>; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 385933bac114..01e94664232a 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -863,7 +863,7 @@ }; i2c0: i2c@01c2ac00 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun7i-a20-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2ac00 0x400>; interrupts = <0 7 4>; clocks = <&apb1_gates 0>; @@ -874,7 +874,7 @@ }; i2c1: i2c@01c2b000 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun7i-a20-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2b000 0x400>; interrupts = <0 8 4>; clocks = <&apb1_gates 1>; @@ -885,7 +885,7 @@ }; i2c2: i2c@01c2b400 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun7i-a20-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2b400 0x400>; interrupts = <0 9 4>; clocks = <&apb1_gates 2>; @@ -896,7 +896,7 @@ }; i2c3: i2c@01c2b800 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun7i-a20-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2b800 0x400>; interrupts = <0 88 4>; clocks = <&apb1_gates 3>; @@ -907,7 +907,7 @@ }; i2c4: i2c@01c2c000 { - compatible = "allwinner,sun4i-i2c"; + compatible = "allwinner,sun7i-a20-i2c", "allwinner,sun4i-a10-i2c"; reg = <0x01c2c000 0x400>; interrupts = <0 89 4>; clocks = <&apb1_gates 15>; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts index c544a5504591..d2709b73316b 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts @@ -88,6 +88,14 @@ interrupts = <1 13 0x304>; }; + timer@2c000200 { + compatible = "arm,cortex-a5-global-timer", + "arm,cortex-a9-global-timer"; + reg = <0x2c000200 0x20>; + interrupts = <1 11 0x304>; + clocks = <&oscclk0>; + }; + watchdog@2c000620 { compatible = "arm,cortex-a5-twd-wdt"; reg = <0x2c000620 0x20>; @@ -120,7 +128,7 @@ compatible = "arm,vexpress,config-bus"; arm,vexpress,config-bridge = <&v2m_sysreg>; - osc@0 { + oscclk0: osc@0 { /* CPU and internal AXI reference clock */ compatible = "arm,vexpress-osc"; arm,vexpress-sysreg,func = <1 0>; diff --git a/arch/arm/boot/dts/vf610.dtsi b/arch/arm/boot/dts/vf610.dtsi index 73355ddc5186..6cc314e7b8fb 100644 --- a/arch/arm/boot/dts/vf610.dtsi +++ b/arch/arm/boot/dts/vf610.dtsi @@ -371,6 +371,19 @@ status = "disabled"; }; + ftm: ftm@400b8000 { + compatible = "fsl,ftm-timer"; + reg = <0x400b8000 0x1000 0x400b9000 0x1000>; + interrupts = <0 44 IRQ_TYPE_LEVEL_HIGH>; + clock-names = "ftm-evt", "ftm-src", + "ftm-evt-counter-en", "ftm-src-counter-en"; + clocks = <&clks VF610_CLK_FTM2>, + <&clks VF610_CLK_FTM3>, + <&clks VF610_CLK_FTM2_EXT_FIX_EN>, + <&clks VF610_CLK_FTM3_EXT_FIX_EN>; + status = "disabled"; + }; + fec0: ethernet@400d0000 { compatible = "fsl,mvf600-fec"; reg = <0x400d0000 0x1000>; diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c index 86fd60fefbc9..f91136ab447e 100644 --- a/arch/arm/common/mcpm_entry.c +++ b/arch/arm/common/mcpm_entry.c @@ -106,14 +106,14 @@ void mcpm_cpu_power_down(void) BUG(); } -int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster) +int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster) { int ret; - if (WARN_ON_ONCE(!platform_ops || !platform_ops->power_down_finish)) + if (WARN_ON_ONCE(!platform_ops || !platform_ops->wait_for_powerdown)) return -EUNATCH; - ret = platform_ops->power_down_finish(cpu, cluster); + ret = platform_ops->wait_for_powerdown(cpu, cluster); if (ret) pr_warn("%s: cpu %u, cluster %u failed to power down (%d)\n", __func__, cpu, cluster, ret); diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c index 177251a4dd9a..92e54d7c6f46 100644 --- a/arch/arm/common/mcpm_platsmp.c +++ b/arch/arm/common/mcpm_platsmp.c @@ -62,7 +62,7 @@ static int mcpm_cpu_kill(unsigned int cpu) cpu_to_pcpu(cpu, &pcpu, &pcluster); - return !mcpm_cpu_power_down_finish(pcpu, pcluster); + return !mcpm_wait_for_cpu_powerdown(pcpu, pcluster); } static int mcpm_cpu_disable(unsigned int cpu) diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig index 5bae19557591..c1f5adc5493e 100644 --- a/arch/arm/configs/integrator_defconfig +++ b/arch/arm/configs/integrator_defconfig @@ -73,7 +73,6 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_LEDS_TRIGGER_CPU=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_PL030=y -CONFIG_COMMON_CLK_DEBUG=y CONFIG_EXT2_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig index 095bb52671f6..932ae40fb128 100644 --- a/arch/arm/configs/keystone_defconfig +++ b/arch/arm/configs/keystone_defconfig @@ -112,6 +112,7 @@ CONFIG_MTD_PLATRAM=y CONFIG_MTD_M25P80=y CONFIG_MTD_NAND=y CONFIG_MTD_NAND_DAVINCI=y +CONFIG_MTD_SPI_NOR=y CONFIG_MTD_UBI=y CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y @@ -131,6 +132,9 @@ CONFIG_SPI=y CONFIG_SPI_DAVINCI=y CONFIG_SPI_SPIDEV=y # CONFIG_HWMON is not set +CONFIG_POWER_SUPPLY=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_KEYSTONE=y CONFIG_WATCHDOG=y CONFIG_WATCHDOG_CORE=y CONFIG_DAVINCI_WATCHDOG=y @@ -145,7 +149,6 @@ CONFIG_USB_DWC3_VERBOSE=y CONFIG_KEYSTONE_USB_PHY=y CONFIG_DMADEVICES=y CONFIG_TI_EDMA=y -CONFIG_COMMON_CLK_DEBUG=y CONFIG_MEMORY=y CONFIG_TI_AEMIF=y CONFIG_EXT4_FS=y diff --git a/arch/arm/configs/vt8500_v6_v7_defconfig b/arch/arm/configs/vt8500_v6_v7_defconfig index f0520176acd0..9e7a25639690 100644 --- a/arch/arm/configs/vt8500_v6_v7_defconfig +++ b/arch/arm/configs/vt8500_v6_v7_defconfig @@ -73,7 +73,6 @@ CONFIG_LEDS_TRIGGERS=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_VT8500=y CONFIG_DMADEVICES=y -CONFIG_COMMON_CLK_DEBUG=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_PWM=y CONFIG_PWM_VT8500=y diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index 23e728ecf8ab..f5a357601983 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -21,6 +21,7 @@ generic-y += parport.h generic-y += poll.h generic-y += preempt.h generic-y += resource.h +generic-y += rwsem.h generic-y += sections.h generic-y += segment.h generic-y += sembuf.h diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index b974184f9941..57f0584e8d97 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -312,7 +312,7 @@ * you cannot return to the original mode. */ .macro safe_svcmode_maskall reg:req -#if __LINUX_ARM_ARCH__ >= 6 +#if __LINUX_ARM_ARCH__ >= 6 && !defined(CONFIG_CPU_V7M) mrs \reg , cpsr eor \reg, \reg, #HYP_MODE tst \reg, #MODE_MASK diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 8b8b61685a34..fd43f7f55b70 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -212,7 +212,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, static inline void __flush_icache_all(void) { __flush_icache_preferred(); - dsb(); + dsb(ishst); } /* @@ -487,4 +487,6 @@ int set_memory_rw(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); +void flush_uprobe_xol_access(struct page *page, unsigned long uaddr, + void *kaddr, unsigned long len); #endif diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h index 6493802f880a..c3f11524f10c 100644 --- a/arch/arm/include/asm/cp15.h +++ b/arch/arm/include/asm/cp15.h @@ -42,24 +42,23 @@ #ifndef __ASSEMBLY__ #if __LINUX_ARM_ARCH__ >= 4 -#define vectors_high() (cr_alignment & CR_V) +#define vectors_high() (get_cr() & CR_V) #else #define vectors_high() (0) #endif #ifdef CONFIG_CPU_CP15 -extern unsigned long cr_no_alignment; /* defined in entry-armv.S */ extern unsigned long cr_alignment; /* defined in entry-armv.S */ -static inline unsigned int get_cr(void) +static inline unsigned long get_cr(void) { - unsigned int val; + unsigned long val; asm("mrc p15, 0, %0, c1, c0, 0 @ get CR" : "=r" (val) : : "cc"); return val; } -static inline void set_cr(unsigned int val) +static inline void set_cr(unsigned long val) { asm volatile("mcr p15, 0, %0, c1, c0, 0 @ set CR" : : "r" (val) : "cc"); @@ -80,10 +79,6 @@ static inline void set_auxcr(unsigned int val) isb(); } -#ifndef CONFIG_SMP -extern void adjust_cr(unsigned long mask, unsigned long set); -#endif - #define CPACC_FULL(n) (3 << (n * 2)) #define CPACC_SVC(n) (1 << (n * 2)) #define CPACC_DISABLE(n) (0 << (n * 2)) @@ -106,13 +101,17 @@ static inline void set_copro_access(unsigned int val) #else /* ifdef CONFIG_CPU_CP15 */ /* - * cr_alignment and cr_no_alignment are tightly coupled to cp15 (at least in the - * minds of the developers). Yielding 0 for machines without a cp15 (and making - * it read-only) is fine for most cases and saves quite some #ifdeffery. + * cr_alignment is tightly coupled to cp15 (at least in the minds of the + * developers). Yielding 0 for machines without a cp15 (and making it + * read-only) is fine for most cases and saves quite some #ifdeffery. */ -#define cr_no_alignment UL(0) #define cr_alignment UL(0) +static inline unsigned long get_cr(void) +{ + return 0; +} + #endif /* ifdef CONFIG_CPU_CP15 / else */ #endif /* ifndef __ASSEMBLY__ */ diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index 4764344367d4..8c2b7321a478 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -72,6 +72,7 @@ #define ARM_CPU_PART_CORTEX_A15 0xC0F0 #define ARM_CPU_PART_CORTEX_A7 0xC070 #define ARM_CPU_PART_CORTEX_A12 0xC0D0 +#define ARM_CPU_PART_CORTEX_A17 0xC0E0 #define ARM_CPU_XSCALE_ARCH_MASK 0xe000 #define ARM_CPU_XSCALE_ARCH_V1 0x2000 diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index e701a4d9aa59..c45b61a4b4a5 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -58,21 +58,37 @@ static inline int dma_set_mask(struct device *dev, u64 mask) #ifndef __arch_pfn_to_dma static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn) { + if (dev) + pfn -= dev->dma_pfn_offset; return (dma_addr_t)__pfn_to_bus(pfn); } static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr) { - return __bus_to_pfn(addr); + unsigned long pfn = __bus_to_pfn(addr); + + if (dev) + pfn += dev->dma_pfn_offset; + + return pfn; } static inline void *dma_to_virt(struct device *dev, dma_addr_t addr) { + if (dev) { + unsigned long pfn = dma_to_pfn(dev, addr); + + return phys_to_virt(__pfn_to_phys(pfn)); + } + return (void *)__bus_to_virt((unsigned long)addr); } static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) { + if (dev) + return pfn_to_dma(dev, virt_to_pfn(addr)); + return (dma_addr_t)__virt_to_bus((unsigned long)(addr)); } @@ -105,6 +121,13 @@ static inline unsigned long dma_max_pfn(struct device *dev) } #define dma_max_pfn(dev) dma_max_pfn(dev) +static inline int set_arch_dma_coherent_ops(struct device *dev) +{ + set_dma_ops(dev, &arm_coherent_dma_ops); + return 0; +} +#define set_arch_dma_coherent_ops(dev) set_arch_dma_coherent_ops(dev) + static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) { unsigned int offset = paddr & ~PAGE_MASK; diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h index bbae919bceb4..74124b0d0d79 100644 --- a/arch/arm/include/asm/fixmap.h +++ b/arch/arm/include/asm/fixmap.h @@ -1,24 +1,11 @@ #ifndef _ASM_FIXMAP_H #define _ASM_FIXMAP_H -/* - * Nothing too fancy for now. - * - * On ARM we already have well known fixed virtual addresses imposed by - * the architecture such as the vector page which is located at 0xffff0000, - * therefore a second level page table is already allocated covering - * 0xfff00000 upwards. - * - * The cache flushing code in proc-xscale.S uses the virtual area between - * 0xfffe0000 and 0xfffeffff. - */ - -#define FIXADDR_START 0xfff00000UL -#define FIXADDR_TOP 0xfffe0000UL +#define FIXADDR_START 0xffc00000UL +#define FIXADDR_TOP 0xffe00000UL #define FIXADDR_SIZE (FIXADDR_TOP - FIXADDR_START) -#define FIX_KMAP_BEGIN 0 -#define FIX_KMAP_END (FIXADDR_SIZE >> PAGE_SHIFT) +#define FIX_KMAP_NR_PTES (FIXADDR_SIZE >> PAGE_SHIFT) #define __fix_to_virt(x) (FIXADDR_START + ((x) << PAGE_SHIFT)) #define __virt_to_fix(x) (((x) - FIXADDR_START) >> PAGE_SHIFT) @@ -27,7 +14,7 @@ extern void __this_fixmap_does_not_exist(void); static inline unsigned long fix_to_virt(const unsigned int idx) { - if (idx >= FIX_KMAP_END) + if (idx >= FIX_KMAP_NR_PTES) __this_fixmap_does_not_exist(); return __fix_to_virt(idx); } diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h index f89515adac60..eb577f4f5f70 100644 --- a/arch/arm/include/asm/ftrace.h +++ b/arch/arm/include/asm/ftrace.h @@ -52,15 +52,7 @@ extern inline void *return_address(unsigned int level) #endif -#define HAVE_ARCH_CALLER_ADDR - -#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -#define CALLER_ADDR1 ((unsigned long)return_address(1)) -#define CALLER_ADDR2 ((unsigned long)return_address(2)) -#define CALLER_ADDR3 ((unsigned long)return_address(3)) -#define CALLER_ADDR4 ((unsigned long)return_address(4)) -#define CALLER_ADDR5 ((unsigned long)return_address(5)) -#define CALLER_ADDR6 ((unsigned long)return_address(6)) +#define ftrace_return_addr(n) return_address(n) #endif /* ifndef __ASSEMBLY__ */ diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h index c81adc08b3fb..a3c24cd5b7c8 100644 --- a/arch/arm/include/asm/glue-cache.h +++ b/arch/arm/include/asm/glue-cache.h @@ -130,22 +130,22 @@ #endif #ifndef __ASSEMBLER__ -extern inline void nop_flush_icache_all(void) { } -extern inline void nop_flush_kern_cache_all(void) { } -extern inline void nop_flush_kern_cache_louis(void) { } -extern inline void nop_flush_user_cache_all(void) { } -extern inline void nop_flush_user_cache_range(unsigned long a, +static inline void nop_flush_icache_all(void) { } +static inline void nop_flush_kern_cache_all(void) { } +static inline void nop_flush_kern_cache_louis(void) { } +static inline void nop_flush_user_cache_all(void) { } +static inline void nop_flush_user_cache_range(unsigned long a, unsigned long b, unsigned int c) { } -extern inline void nop_coherent_kern_range(unsigned long a, unsigned long b) { } -extern inline int nop_coherent_user_range(unsigned long a, +static inline void nop_coherent_kern_range(unsigned long a, unsigned long b) { } +static inline int nop_coherent_user_range(unsigned long a, unsigned long b) { return 0; } -extern inline void nop_flush_kern_dcache_area(void *a, size_t s) { } +static inline void nop_flush_kern_dcache_area(void *a, size_t s) { } -extern inline void nop_dma_flush_range(const void *a, const void *b) { } +static inline void nop_dma_flush_range(const void *a, const void *b) { } -extern inline void nop_dma_map_area(const void *s, size_t l, int f) { } -extern inline void nop_dma_unmap_area(const void *s, size_t l, int f) { } +static inline void nop_dma_map_area(const void *s, size_t l, int f) { } +static inline void nop_dma_unmap_area(const void *s, size_t l, int f) { } #endif #ifndef MULTI_CACHE diff --git a/arch/arm/include/asm/glue-df.h b/arch/arm/include/asm/glue-df.h index 6b70f1b46a6e..04e18b656659 100644 --- a/arch/arm/include/asm/glue-df.h +++ b/arch/arm/include/asm/glue-df.h @@ -31,14 +31,6 @@ #undef CPU_DABORT_HANDLER #undef MULTI_DABORT -#if defined(CONFIG_CPU_ARM710) -# ifdef CPU_DABORT_HANDLER -# define MULTI_DABORT 1 -# else -# define CPU_DABORT_HANDLER cpu_arm7_data_abort -# endif -#endif - #ifdef CONFIG_CPU_ABRT_EV4 # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index 6795ff743b3d..3a5ec1c25659 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -26,8 +26,8 @@ #define L2X0_CACHE_TYPE 0x004 #define L2X0_CTRL 0x100 #define L2X0_AUX_CTRL 0x104 -#define L2X0_TAG_LATENCY_CTRL 0x108 -#define L2X0_DATA_LATENCY_CTRL 0x10C +#define L310_TAG_LATENCY_CTRL 0x108 +#define L310_DATA_LATENCY_CTRL 0x10C #define L2X0_EVENT_CNT_CTRL 0x200 #define L2X0_EVENT_CNT1_CFG 0x204 #define L2X0_EVENT_CNT0_CFG 0x208 @@ -54,53 +54,93 @@ #define L2X0_LOCKDOWN_WAY_D_BASE 0x900 #define L2X0_LOCKDOWN_WAY_I_BASE 0x904 #define L2X0_LOCKDOWN_STRIDE 0x08 -#define L2X0_ADDR_FILTER_START 0xC00 -#define L2X0_ADDR_FILTER_END 0xC04 +#define L310_ADDR_FILTER_START 0xC00 +#define L310_ADDR_FILTER_END 0xC04 #define L2X0_TEST_OPERATION 0xF00 #define L2X0_LINE_DATA 0xF10 #define L2X0_LINE_TAG 0xF30 #define L2X0_DEBUG_CTRL 0xF40 -#define L2X0_PREFETCH_CTRL 0xF60 -#define L2X0_POWER_CTRL 0xF80 -#define L2X0_DYNAMIC_CLK_GATING_EN (1 << 1) -#define L2X0_STNDBY_MODE_EN (1 << 0) +#define L310_PREFETCH_CTRL 0xF60 +#define L310_POWER_CTRL 0xF80 +#define L310_DYNAMIC_CLK_GATING_EN (1 << 1) +#define L310_STNDBY_MODE_EN (1 << 0) /* Registers shifts and masks */ #define L2X0_CACHE_ID_PART_MASK (0xf << 6) #define L2X0_CACHE_ID_PART_L210 (1 << 6) +#define L2X0_CACHE_ID_PART_L220 (2 << 6) #define L2X0_CACHE_ID_PART_L310 (3 << 6) #define L2X0_CACHE_ID_RTL_MASK 0x3f -#define L2X0_CACHE_ID_RTL_R0P0 0x0 -#define L2X0_CACHE_ID_RTL_R1P0 0x2 -#define L2X0_CACHE_ID_RTL_R2P0 0x4 -#define L2X0_CACHE_ID_RTL_R3P0 0x5 -#define L2X0_CACHE_ID_RTL_R3P1 0x6 -#define L2X0_CACHE_ID_RTL_R3P2 0x8 +#define L210_CACHE_ID_RTL_R0P2_02 0x00 +#define L210_CACHE_ID_RTL_R0P1 0x01 +#define L210_CACHE_ID_RTL_R0P2_01 0x02 +#define L210_CACHE_ID_RTL_R0P3 0x03 +#define L210_CACHE_ID_RTL_R0P4 0x0b +#define L210_CACHE_ID_RTL_R0P5 0x0f +#define L220_CACHE_ID_RTL_R1P7_01REL0 0x06 +#define L310_CACHE_ID_RTL_R0P0 0x00 +#define L310_CACHE_ID_RTL_R1P0 0x02 +#define L310_CACHE_ID_RTL_R2P0 0x04 +#define L310_CACHE_ID_RTL_R3P0 0x05 +#define L310_CACHE_ID_RTL_R3P1 0x06 +#define L310_CACHE_ID_RTL_R3P1_50REL0 0x07 +#define L310_CACHE_ID_RTL_R3P2 0x08 +#define L310_CACHE_ID_RTL_R3P3 0x09 -#define L2X0_AUX_CTRL_MASK 0xc0000fff +/* L2C auxiliary control register - bits common to L2C-210/220/310 */ +#define L2C_AUX_CTRL_WAY_SIZE_SHIFT 17 +#define L2C_AUX_CTRL_WAY_SIZE_MASK (7 << 17) +#define L2C_AUX_CTRL_WAY_SIZE(n) ((n) << 17) +#define L2C_AUX_CTRL_EVTMON_ENABLE BIT(20) +#define L2C_AUX_CTRL_PARITY_ENABLE BIT(21) +#define L2C_AUX_CTRL_SHARED_OVERRIDE BIT(22) +/* L2C-210/220 common bits */ #define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT 0 -#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK 0x7 +#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK (7 << 0) #define L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT 3 -#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK (0x7 << 3) +#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK (7 << 3) #define L2X0_AUX_CTRL_TAG_LATENCY_SHIFT 6 -#define L2X0_AUX_CTRL_TAG_LATENCY_MASK (0x7 << 6) +#define L2X0_AUX_CTRL_TAG_LATENCY_MASK (7 << 6) #define L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT 9 -#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK (0x7 << 9) -#define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT 16 -#define L2X0_AUX_CTRL_WAY_SIZE_SHIFT 17 -#define L2X0_AUX_CTRL_WAY_SIZE_MASK (0x7 << 17) -#define L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT 22 -#define L2X0_AUX_CTRL_NS_LOCKDOWN_SHIFT 26 -#define L2X0_AUX_CTRL_NS_INT_CTRL_SHIFT 27 -#define L2X0_AUX_CTRL_DATA_PREFETCH_SHIFT 28 -#define L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT 29 -#define L2X0_AUX_CTRL_EARLY_BRESP_SHIFT 30 +#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK (7 << 9) +#define L2X0_AUX_CTRL_ASSOC_SHIFT 13 +#define L2X0_AUX_CTRL_ASSOC_MASK (15 << 13) +/* L2C-210 specific bits */ +#define L210_AUX_CTRL_WRAP_DISABLE BIT(12) +#define L210_AUX_CTRL_WA_OVERRIDE BIT(23) +#define L210_AUX_CTRL_EXCLUSIVE_ABORT BIT(24) +/* L2C-220 specific bits */ +#define L220_AUX_CTRL_EXCLUSIVE_CACHE BIT(12) +#define L220_AUX_CTRL_FWA_SHIFT 23 +#define L220_AUX_CTRL_FWA_MASK (3 << 23) +#define L220_AUX_CTRL_NS_LOCKDOWN BIT(26) +#define L220_AUX_CTRL_NS_INT_CTRL BIT(27) +/* L2C-310 specific bits */ +#define L310_AUX_CTRL_FULL_LINE_ZERO BIT(0) /* R2P0+ */ +#define L310_AUX_CTRL_HIGHPRIO_SO_DEV BIT(10) /* R2P0+ */ +#define L310_AUX_CTRL_STORE_LIMITATION BIT(11) /* R2P0+ */ +#define L310_AUX_CTRL_EXCLUSIVE_CACHE BIT(12) +#define L310_AUX_CTRL_ASSOCIATIVITY_16 BIT(16) +#define L310_AUX_CTRL_CACHE_REPLACE_RR BIT(25) /* R2P0+ */ +#define L310_AUX_CTRL_NS_LOCKDOWN BIT(26) +#define L310_AUX_CTRL_NS_INT_CTRL BIT(27) +#define L310_AUX_CTRL_DATA_PREFETCH BIT(28) +#define L310_AUX_CTRL_INSTR_PREFETCH BIT(29) +#define L310_AUX_CTRL_EARLY_BRESP BIT(30) /* R2P0+ */ -#define L2X0_LATENCY_CTRL_SETUP_SHIFT 0 -#define L2X0_LATENCY_CTRL_RD_SHIFT 4 -#define L2X0_LATENCY_CTRL_WR_SHIFT 8 +#define L310_LATENCY_CTRL_SETUP(n) ((n) << 0) +#define L310_LATENCY_CTRL_RD(n) ((n) << 4) +#define L310_LATENCY_CTRL_WR(n) ((n) << 8) -#define L2X0_ADDR_FILTER_EN 1 +#define L310_ADDR_FILTER_EN 1 + +#define L310_PREFETCH_CTRL_OFFSET_MASK 0x1f +#define L310_PREFETCH_CTRL_DBL_LINEFILL_INCR BIT(23) +#define L310_PREFETCH_CTRL_PREFETCH_DROP BIT(24) +#define L310_PREFETCH_CTRL_DBL_LINEFILL_WRAP BIT(27) +#define L310_PREFETCH_CTRL_DATA_PREFETCH BIT(28) +#define L310_PREFETCH_CTRL_INSTR_PREFETCH BIT(29) +#define L310_PREFETCH_CTRL_DBL_LINEFILL BIT(30) #define L2X0_CTRL_EN 1 diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h index 91b99abe7a95..535579511ed0 100644 --- a/arch/arm/include/asm/highmem.h +++ b/arch/arm/include/asm/highmem.h @@ -18,6 +18,7 @@ } while (0) extern pte_t *pkmap_page_table; +extern pte_t *fixmap_page_table; extern void *kmap_high(struct page *page); extern void kunmap_high(struct page *page); diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index 8aa4cca74501..3d23418cbddd 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -179,6 +179,12 @@ static inline void __iomem *__typesafe_io(unsigned long addr) /* PCI fixed i/o mapping */ #define PCI_IO_VIRT_BASE 0xfee00000 +#if defined(CONFIG_PCI) +void pci_ioremap_set_mem_type(int mem_type); +#else +static inline void pci_ioremap_set_mem_type(int mem_type) {} +#endif + extern int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr); /* diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 17a3fa2979e8..060a75e99263 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -14,7 +14,6 @@ #include <linux/reboot.h> struct tag; -struct meminfo; struct pt_regs; struct smp_operations; #ifdef CONFIG_SMP @@ -45,10 +44,12 @@ struct machine_desc { unsigned char reserve_lp1 :1; /* never has lp1 */ unsigned char reserve_lp2 :1; /* never has lp2 */ enum reboot_mode reboot_mode; /* default restart mode */ + unsigned l2c_aux_val; /* L2 cache aux value */ + unsigned l2c_aux_mask; /* L2 cache aux mask */ + void (*l2c_write_sec)(unsigned long, unsigned); struct smp_operations *smp; /* SMP operations */ bool (*smp_init)(void); - void (*fixup)(struct tag *, char **, - struct meminfo *); + void (*fixup)(struct tag *, char **); void (*init_meminfo)(void); void (*reserve)(void);/* reserve mem blocks */ void (*map_io)(void);/* IO mapping function */ diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h index a5ff410dcdb6..d9702eb0b02b 100644 --- a/arch/arm/include/asm/mcpm.h +++ b/arch/arm/include/asm/mcpm.h @@ -98,14 +98,14 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster); * previously in which case the caller should take appropriate action. * * On success, the CPU is not guaranteed to be truly halted until - * mcpm_cpu_power_down_finish() subsequently returns non-zero for the + * mcpm_wait_for_cpu_powerdown() subsequently returns non-zero for the * specified cpu. Until then, other CPUs should make sure they do not * trash memory the target CPU might be executing/accessing. */ void mcpm_cpu_power_down(void); /** - * mcpm_cpu_power_down_finish - wait for a specified CPU to halt, and + * mcpm_wait_for_cpu_powerdown - wait for a specified CPU to halt, and * make sure it is powered off * * @cpu: CPU number within given cluster @@ -127,7 +127,7 @@ void mcpm_cpu_power_down(void); * - zero if the CPU is in a safely parked state * - nonzero otherwise (e.g., timeout) */ -int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster); +int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster); /** * mcpm_cpu_suspend - bring the calling CPU in a suspended state @@ -171,7 +171,7 @@ int mcpm_cpu_powered_up(void); struct mcpm_platform_ops { int (*power_up)(unsigned int cpu, unsigned int cluster); void (*power_down)(void); - int (*power_down_finish)(unsigned int cpu, unsigned int cluster); + int (*wait_for_powerdown)(unsigned int cpu, unsigned int cluster); void (*suspend)(u64); void (*powered_up)(void); }; diff --git a/arch/arm/include/asm/memblock.h b/arch/arm/include/asm/memblock.h index c2f5102ae659..bf47a6c110a2 100644 --- a/arch/arm/include/asm/memblock.h +++ b/arch/arm/include/asm/memblock.h @@ -1,10 +1,9 @@ #ifndef _ASM_ARM_MEMBLOCK_H #define _ASM_ARM_MEMBLOCK_H -struct meminfo; struct machine_desc; -void arm_memblock_init(struct meminfo *, const struct machine_desc *); +void arm_memblock_init(const struct machine_desc *); phys_addr_t arm_memblock_steal(phys_addr_t size, phys_addr_t align); #endif diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 02fa2558f662..2b751464d6ff 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -83,8 +83,6 @@ */ #define IOREMAP_MAX_ORDER 24 -#define CONSISTENT_END (0xffe00000UL) - #else /* CONFIG_MMU */ /* diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h index f94784f0e3a6..891a56b35bcf 100644 --- a/arch/arm/include/asm/outercache.h +++ b/arch/arm/include/asm/outercache.h @@ -28,53 +28,84 @@ struct outer_cache_fns { void (*clean_range)(unsigned long, unsigned long); void (*flush_range)(unsigned long, unsigned long); void (*flush_all)(void); - void (*inv_all)(void); void (*disable)(void); #ifdef CONFIG_OUTER_CACHE_SYNC void (*sync)(void); #endif - void (*set_debug)(unsigned long); void (*resume)(void); + + /* This is an ARM L2C thing */ + void (*write_sec)(unsigned long, unsigned); }; extern struct outer_cache_fns outer_cache; #ifdef CONFIG_OUTER_CACHE - +/** + * outer_inv_range - invalidate range of outer cache lines + * @start: starting physical address, inclusive + * @end: end physical address, exclusive + */ static inline void outer_inv_range(phys_addr_t start, phys_addr_t end) { if (outer_cache.inv_range) outer_cache.inv_range(start, end); } + +/** + * outer_clean_range - clean dirty outer cache lines + * @start: starting physical address, inclusive + * @end: end physical address, exclusive + */ static inline void outer_clean_range(phys_addr_t start, phys_addr_t end) { if (outer_cache.clean_range) outer_cache.clean_range(start, end); } + +/** + * outer_flush_range - clean and invalidate outer cache lines + * @start: starting physical address, inclusive + * @end: end physical address, exclusive + */ static inline void outer_flush_range(phys_addr_t start, phys_addr_t end) { if (outer_cache.flush_range) outer_cache.flush_range(start, end); } +/** + * outer_flush_all - clean and invalidate all cache lines in the outer cache + * + * Note: depending on implementation, this may not be atomic - it must + * only be called with interrupts disabled and no other active outer + * cache masters. + * + * It is intended that this function is only used by implementations + * needing to override the outer_cache.disable() method due to security. + * (Some implementations perform this as a clean followed by an invalidate.) + */ static inline void outer_flush_all(void) { if (outer_cache.flush_all) outer_cache.flush_all(); } -static inline void outer_inv_all(void) -{ - if (outer_cache.inv_all) - outer_cache.inv_all(); -} - -static inline void outer_disable(void) -{ - if (outer_cache.disable) - outer_cache.disable(); -} +/** + * outer_disable - clean, invalidate and disable the outer cache + * + * Disable the outer cache, ensuring that any data contained in the outer + * cache is pushed out to lower levels of system memory. The note and + * conditions above concerning outer_flush_all() applies here. + */ +extern void outer_disable(void); +/** + * outer_resume - restore the cache configuration and re-enable outer cache + * + * Restore any configuration that the cache had when previously enabled, + * and re-enable the outer cache. + */ static inline void outer_resume(void) { if (outer_cache.resume) @@ -90,13 +121,18 @@ static inline void outer_clean_range(phys_addr_t start, phys_addr_t end) static inline void outer_flush_range(phys_addr_t start, phys_addr_t end) { } static inline void outer_flush_all(void) { } -static inline void outer_inv_all(void) { } static inline void outer_disable(void) { } static inline void outer_resume(void) { } #endif #ifdef CONFIG_OUTER_CACHE_SYNC +/** + * outer_sync - perform a sync point for outer cache + * + * Ensure that all outer cache operations are complete and any store + * buffers are drained. + */ static inline void outer_sync(void) { if (outer_cache.sync) diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h index b681575ad3de..cd94ef2ef283 100644 --- a/arch/arm/include/asm/prom.h +++ b/arch/arm/include/asm/prom.h @@ -14,7 +14,6 @@ #ifdef CONFIG_OF extern const struct machine_desc *setup_machine_fdt(unsigned int dt_phys); -extern void arm_dt_memblock_reserve(void); extern void __init arm_dt_init_cpu_maps(void); #else /* CONFIG_OF */ @@ -24,7 +23,6 @@ static inline const struct machine_desc *setup_machine_fdt(unsigned int dt_phys) return NULL; } -static inline void arm_dt_memblock_reserve(void) { } static inline void arm_dt_init_cpu_maps(void) { } #endif /* CONFIG_OF */ diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h index 8d6a089dfb76..e0adb9f1bf94 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -21,34 +21,6 @@ #define __tagtable(tag, fn) \ static const struct tagtable __tagtable_##fn __tag = { tag, fn } -/* - * Memory map description - */ -#define NR_BANKS CONFIG_ARM_NR_BANKS - -struct membank { - phys_addr_t start; - phys_addr_t size; - unsigned int highmem; -}; - -struct meminfo { - int nr_banks; - struct membank bank[NR_BANKS]; -}; - -extern struct meminfo meminfo; - -#define for_each_bank(iter,mi) \ - for (iter = 0; iter < (mi)->nr_banks; iter++) - -#define bank_pfn_start(bank) __phys_to_pfn((bank)->start) -#define bank_pfn_end(bank) __phys_to_pfn((bank)->start + (bank)->size) -#define bank_pfn_size(bank) ((bank)->size >> PAGE_SHIFT) -#define bank_phys_start(bank) (bank)->start -#define bank_phys_end(bank) ((bank)->start + (bank)->size) -#define bank_phys_size(bank) (bank)->size - extern int arm_add_memory(u64 start, u64 size); extern void early_print(const char *str, ...); extern void dump_machine_table(void); diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 040619c32d68..38ddd9f83d0e 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -39,6 +39,7 @@ obj-$(CONFIG_ARTHUR) += arthur.o obj-$(CONFIG_ISA_DMA) += dma-isa.o obj-$(CONFIG_PCI) += bios32.o isa.o obj-$(CONFIG_ARM_CPU_SUSPEND) += sleep.o suspend.o +obj-$(CONFIG_HIBERNATION) += hibernate.o obj-$(CONFIG_SMP) += smp.o ifdef CONFIG_MMU obj-$(CONFIG_SMP) += smp_tlb.o diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c index 8c14de8180c0..7807ef58a2ab 100644 --- a/arch/arm/kernel/atags_parse.c +++ b/arch/arm/kernel/atags_parse.c @@ -22,6 +22,7 @@ #include <linux/fs.h> #include <linux/root_dev.h> #include <linux/screen_info.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/system_info.h> @@ -222,10 +223,10 @@ setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr) } if (mdesc->fixup) - mdesc->fixup(tags, &from, &meminfo); + mdesc->fixup(tags, &from); if (tags->hdr.tag == ATAG_CORE) { - if (meminfo.nr_banks != 0) + if (memblock_phys_mem_size()) squash_mem_tags(tags); save_atags(tags); parse_tags(tags); diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index c7419a585ddc..e94a157ddff1 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -27,56 +27,23 @@ #include <asm/mach/arch.h> #include <asm/mach-types.h> -void __init early_init_dt_add_memory_arch(u64 base, u64 size) -{ - arm_add_memory(base, size); -} - -void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) -{ - return memblock_virt_alloc(size, align); -} - -void __init arm_dt_memblock_reserve(void) -{ - u64 *reserve_map, base, size; - - if (!initial_boot_params) - return; - /* Reserve the dtb region */ - memblock_reserve(virt_to_phys(initial_boot_params), - be32_to_cpu(initial_boot_params->totalsize)); +#ifdef CONFIG_SMP +extern struct of_cpu_method __cpu_method_of_table[]; - /* - * Process the reserve map. This will probably overlap the initrd - * and dtb locations which are already reserved, but overlaping - * doesn't hurt anything - */ - reserve_map = ((void*)initial_boot_params) + - be32_to_cpu(initial_boot_params->off_mem_rsvmap); - while (1) { - base = be64_to_cpup(reserve_map++); - size = be64_to_cpup(reserve_map++); - if (!size) - break; - memblock_reserve(base, size); - } -} +static const struct of_cpu_method __cpu_method_of_table_sentinel + __used __section(__cpu_method_of_table_end); -#ifdef CONFIG_SMP -extern struct of_cpu_method __cpu_method_of_table_begin[]; -extern struct of_cpu_method __cpu_method_of_table_end[]; static int __init set_smp_ops_by_method(struct device_node *node) { const char *method; - struct of_cpu_method *m = __cpu_method_of_table_begin; + struct of_cpu_method *m = __cpu_method_of_table; if (of_property_read_string(node, "enable-method", &method)) return 0; - for (; m < __cpu_method_of_table_end; m++) + for (; m->method; m++) if (!strcmp(m->method, method)) { smp_set_ops(m->ops); return 1; @@ -252,7 +219,7 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) if (!mdesc) { const char *prop; - long size; + int size; unsigned long dt_root; early_print("\nError: unrecognized/unsupported " diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 1879e8dd2acc..52a949a8077d 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -344,7 +344,7 @@ ENDPROC(__pabt_svc) @ @ Enable the alignment trap while in kernel mode @ - alignment_trap r0 + alignment_trap r0, .LCcralign @ @ Clear FP to mark the first stack frame @@ -413,6 +413,11 @@ __und_usr: @ adr r9, BSYM(ret_from_exception) + @ IRQs must be enabled before attempting to read the instruction from + @ user space since that could cause a page/translation fault if the + @ page table was modified by another CPU. + enable_irq + tst r3, #PSR_T_BIT @ Thumb mode? bne __und_usr_thumb sub r4, r2, #4 @ ARM instr at LR - 4 @@ -484,7 +489,8 @@ ENDPROC(__und_usr) */ .pushsection .fixup, "ax" .align 2 -4: mov pc, r9 +4: str r4, [sp, #S_PC] @ retry current instruction + mov pc, r9 .popsection .pushsection __ex_table,"a" .long 1b, 4b @@ -517,7 +523,7 @@ ENDPROC(__und_usr) * r9 = normal "successful" return address * r10 = this threads thread_info structure * lr = unrecognised instruction return address - * IRQs disabled, FIQs enabled. + * IRQs enabled, FIQs enabled. */ @ @ Fall-through from Thumb-2 __und_usr @@ -624,7 +630,6 @@ call_fpe: #endif do_fpe: - enable_irq ldr r4, .LCfp add r10, r10, #TI_FPSTATE @ r10 = workspace ldr pc, [r4] @ Call FP module USR entry point @@ -652,8 +657,7 @@ __und_usr_fault_32: b 1f __und_usr_fault_16: mov r1, #2 -1: enable_irq - mov r0, sp +1: mov r0, sp adr lr, BSYM(ret_from_exception) b __und_fault ENDPROC(__und_usr_fault_32) @@ -1143,11 +1147,8 @@ __vectors_start: .data .globl cr_alignment - .globl cr_no_alignment cr_alignment: .space 4 -cr_no_alignment: - .space 4 #ifdef CONFIG_MULTI_IRQ_HANDLER .globl handle_arch_irq diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index a2dcafdf1bc8..7139d4a7dea7 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -365,13 +365,7 @@ ENTRY(vector_swi) str r0, [sp, #S_OLD_R0] @ Save OLD_R0 #endif zero_fp - -#ifdef CONFIG_ALIGNMENT_TRAP - ldr ip, __cr_alignment - ldr ip, [ip] - mcr p15, 0, ip, c1, c0 @ update control register -#endif - + alignment_trap ip, __cr_alignment enable_irq ct_user_exit get_thread_info tsk diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index efb208de75ec..5d702f8900b1 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -37,9 +37,9 @@ #endif .endm - .macro alignment_trap, rtemp + .macro alignment_trap, rtemp, label #ifdef CONFIG_ALIGNMENT_TRAP - ldr \rtemp, .LCcralign + ldr \rtemp, \label ldr \rtemp, [\rtemp] mcr p15, 0, \rtemp, c1, c0 #endif diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index c108ddcb9ba4..af9a8a927a4e 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -14,6 +14,7 @@ #include <linux/ftrace.h> #include <linux/uaccess.h> +#include <linux/module.h> #include <asm/cacheflush.h> #include <asm/opcodes.h> @@ -63,6 +64,18 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr) } #endif +int ftrace_arch_code_modify_prepare(void) +{ + set_all_modules_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_all_modules_text_ro(); + return 0; +} + static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr) { return arm_gen_branch_link(pc, addr); diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index c96ecacb2021..572a38335c96 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -99,8 +99,7 @@ __mmap_switched: str r1, [r5] @ Save machine type str r2, [r6] @ Save atags pointer cmp r7, #0 - bicne r4, r0, #CR_A @ Clear 'A' bit - stmneia r7, {r0, r4} @ Save control register values + strne r0, [r7] @ Save control register values b start_kernel ENDPROC(__mmap_switched) diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 591d6e4a6492..2c35f0ff2fdc 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -475,7 +475,7 @@ ENDPROC(__turn_mmu_on) #ifdef CONFIG_SMP_ON_UP - __INIT + __HEAD __fixup_smp: and r3, r9, #0x000f0000 @ architecture version teq r3, #0x000f0000 @ CPU ID supported? diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c new file mode 100644 index 000000000000..bb8b79648643 --- /dev/null +++ b/arch/arm/kernel/hibernate.c @@ -0,0 +1,107 @@ +/* + * Hibernation support specific for ARM + * + * Derived from work on ARM hibernation support by: + * + * Ubuntu project, hibernation support for mach-dove + * Copyright (C) 2010 Nokia Corporation (Hiroshi Doyu) + * Copyright (C) 2010 Texas Instruments, Inc. (Teerth Reddy et al.) + * https://lkml.org/lkml/2010/6/18/4 + * https://lists.linux-foundation.org/pipermail/linux-pm/2010-June/027422.html + * https://patchwork.kernel.org/patch/96442/ + * + * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> + * + * License terms: GNU General Public License (GPL) version 2 + */ + +#include <linux/mm.h> +#include <linux/suspend.h> +#include <asm/system_misc.h> +#include <asm/idmap.h> +#include <asm/suspend.h> +#include <asm/memory.h> + +extern const void __nosave_begin, __nosave_end; + +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin); + unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1); + + return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn); +} + +void notrace save_processor_state(void) +{ + WARN_ON(num_online_cpus() != 1); + local_fiq_disable(); +} + +void notrace restore_processor_state(void) +{ + local_fiq_enable(); +} + +/* + * Snapshot kernel memory and reset the system. + * + * swsusp_save() is executed in the suspend finisher so that the CPU + * context pointer and memory are part of the saved image, which is + * required by the resume kernel image to restart execution from + * swsusp_arch_suspend(). + * + * soft_restart is not technically needed, but is used to get success + * returned from cpu_suspend. + * + * When soft reboot completes, the hibernation snapshot is written out. + */ +static int notrace arch_save_image(unsigned long unused) +{ + int ret; + + ret = swsusp_save(); + if (ret == 0) + soft_restart(virt_to_phys(cpu_resume)); + return ret; +} + +/* + * Save the current CPU state before suspend / poweroff. + */ +int notrace swsusp_arch_suspend(void) +{ + return cpu_suspend(0, arch_save_image); +} + +/* + * Restore page contents for physical pages that were in use during loading + * hibernation image. Switch to idmap_pgd so the physical page tables + * are overwritten with the same contents. + */ +static void notrace arch_restore_image(void *unused) +{ + struct pbe *pbe; + + cpu_switch_mm(idmap_pgd, &init_mm); + for (pbe = restore_pblist; pbe; pbe = pbe->next) + copy_page(pbe->orig_address, pbe->address); + + soft_restart(virt_to_phys(cpu_resume)); +} + +static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata; + +/* + * Resume from the hibernation image. + * Due to the kernel heap / data restore, stack contents change underneath + * and that would make function calls impossible; switch to a temporary + * stack within the nosave region to avoid that problem. + */ +int swsusp_arch_resume(void) +{ + extern void call_with_stack(void (*fn)(void *), void *arg, void *sp); + call_with_stack(arch_restore_image, 0, + resume_stack + ARRAY_SIZE(resume_stack)); + return 0; +} diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 9723d17b8f38..2c4257604513 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -37,6 +37,7 @@ #include <linux/proc_fs.h> #include <linux/export.h> +#include <asm/hardware/cache-l2x0.h> #include <asm/exception.h> #include <asm/mach/arch.h> #include <asm/mach/irq.h> @@ -115,10 +116,21 @@ EXPORT_SYMBOL_GPL(set_irq_flags); void __init init_IRQ(void) { + int ret; + if (IS_ENABLED(CONFIG_OF) && !machine_desc->init_irq) irqchip_init(); else machine_desc->init_irq(); + + if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_CACHE_L2X0) && + (machine_desc->l2c_aux_mask || machine_desc->l2c_aux_val)) { + outer_cache.write_sec = machine_desc->l2c_write_sec; + ret = l2x0_of_init(machine_desc->l2c_aux_val, + machine_desc->l2c_aux_mask); + if (ret) + pr_err("L2C: failed to init: %d\n", ret); + } } #ifdef CONFIG_MULTI_IRQ_HANDLER diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c index 346485910732..9d1cf7156895 100644 --- a/arch/arm/kernel/isa.c +++ b/arch/arm/kernel/isa.c @@ -20,7 +20,7 @@ static unsigned int isa_membase, isa_portbase, isa_portshift; -static ctl_table ctl_isa_vars[4] = { +static struct ctl_table ctl_isa_vars[4] = { { .procname = "membase", .data = &isa_membase, @@ -44,7 +44,7 @@ static ctl_table ctl_isa_vars[4] = { static struct ctl_table_header *isa_sysctl_header; -static ctl_table ctl_isa[2] = { +static struct ctl_table ctl_isa[2] = { { .procname = "isa", .mode = 0555, @@ -52,7 +52,7 @@ static ctl_table ctl_isa[2] = { }, {} }; -static ctl_table ctl_bus[2] = { +static struct ctl_table ctl_bus[2] = { { .procname = "bus", .mode = 0555, diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S index 2452dd1bef53..a5599cfc43cb 100644 --- a/arch/arm/kernel/iwmmxt.S +++ b/arch/arm/kernel/iwmmxt.S @@ -18,6 +18,7 @@ #include <asm/ptrace.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> +#include <asm/assembler.h> #if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B) #define PJ4(code...) code @@ -65,17 +66,18 @@ * r9 = ret_from_exception * lr = undefined instr exit * - * called from prefetch exception handler with interrupts disabled + * called from prefetch exception handler with interrupts enabled */ ENTRY(iwmmxt_task_enable) + inc_preempt_count r10, r3 XSC(mrc p15, 0, r2, c15, c1, 0) PJ4(mrc p15, 0, r2, c1, c0, 2) @ CP0 and CP1 accessible? XSC(tst r2, #0x3) PJ4(tst r2, #0xf) - movne pc, lr @ if so no business here + bne 4f @ if so no business here @ enable access to CP0 and CP1 XSC(orr r2, r2, #0x3) XSC(mcr p15, 0, r2, c15, c1, 0) @@ -136,7 +138,7 @@ concan_dump: wstrd wR15, [r1, #MMX_WR15] 2: teq r0, #0 @ anything to load? - moveq pc, lr + beq 3f concan_load: @@ -169,8 +171,14 @@ concan_load: @ clear CUP/MUP (only if r1 != 0) teq r1, #0 mov r2, #0 - moveq pc, lr + beq 3f tmcr wCon, r2 + +3: +#ifdef CONFIG_PREEMPT_COUNT + get_thread_info r10 +#endif +4: dec_preempt_count r10, r3 mov pc, lr /* diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 51798d7854ac..a71ae1523620 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -221,6 +221,7 @@ static struct notifier_block cpu_pmu_hotplug_notifier = { * PMU platform driver and devicetree bindings. */ static struct of_device_id cpu_pmu_of_device_ids[] = { + {.compatible = "arm,cortex-a17-pmu", .data = armv7_a17_pmu_init}, {.compatible = "arm,cortex-a15-pmu", .data = armv7_a15_pmu_init}, {.compatible = "arm,cortex-a12-pmu", .data = armv7_a12_pmu_init}, {.compatible = "arm,cortex-a9-pmu", .data = armv7_a9_pmu_init}, diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index f4ef3981ed02..2037f7205987 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -1599,6 +1599,13 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu) return 0; } +static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7_a12_pmu_init(cpu_pmu); + cpu_pmu->name = "ARMv7 Cortex-A17"; + return 0; +} + /* * Krait Performance Monitor Region Event Selection Register (PMRESRn) * @@ -2021,6 +2028,11 @@ static inline int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu) return -ENODEV; } +static inline int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu) +{ + return -ENODEV; +} + static inline int krait_pmu_init(struct arm_pmu *cpu_pmu) { return -ENODEV; diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 50e198c1e9c8..8a16ee5d8a95 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -72,6 +72,7 @@ static int __init fpe_setup(char *line) __setup("fpe=", fpe_setup); #endif +extern void init_default_cache_policy(unsigned long); extern void paging_init(const struct machine_desc *desc); extern void early_paging_init(const struct machine_desc *, struct proc_info_list *); @@ -590,7 +591,7 @@ static void __init setup_processor(void) pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n", cpu_name, read_cpuid_id(), read_cpuid_id() & 15, - proc_arch[cpu_architecture()], cr_alignment); + proc_arch[cpu_architecture()], get_cr()); snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c", list->arch_name, ENDIANNESS); @@ -603,7 +604,9 @@ static void __init setup_processor(void) #ifndef CONFIG_ARM_THUMB elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT); #endif - +#ifdef CONFIG_MMU + init_default_cache_policy(list->__cpu_mm_mmu_flags); +#endif erratum_a15_798181_init(); feat_v6_fixup(); @@ -628,15 +631,8 @@ void __init dump_machine_table(void) int __init arm_add_memory(u64 start, u64 size) { - struct membank *bank = &meminfo.bank[meminfo.nr_banks]; u64 aligned_start; - if (meminfo.nr_banks >= NR_BANKS) { - pr_crit("NR_BANKS too low, ignoring memory at 0x%08llx\n", - (long long)start); - return -EINVAL; - } - /* * Ensure that start/size are aligned to a page boundary. * Size is appropriately rounded down, start is rounded up. @@ -677,17 +673,17 @@ int __init arm_add_memory(u64 start, u64 size) aligned_start = PHYS_OFFSET; } - bank->start = aligned_start; - bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1); + start = aligned_start; + size = size & ~(phys_addr_t)(PAGE_SIZE - 1); /* * Check whether this memory region has non-zero size or * invalid node number. */ - if (bank->size == 0) + if (size == 0) return -EINVAL; - meminfo.nr_banks++; + memblock_add(start, size); return 0; } @@ -695,6 +691,7 @@ int __init arm_add_memory(u64 start, u64 size) * Pick out the memory size. We look for mem=size@start, * where start and size are "size[KkMm]" */ + static int __init early_mem(char *p) { static int usermem __initdata = 0; @@ -709,7 +706,8 @@ static int __init early_mem(char *p) */ if (usermem == 0) { usermem = 1; - meminfo.nr_banks = 0; + memblock_remove(memblock_start_of_DRAM(), + memblock_end_of_DRAM() - memblock_start_of_DRAM()); } start = PHYS_OFFSET; @@ -854,13 +852,6 @@ static void __init reserve_crashkernel(void) static inline void reserve_crashkernel(void) {} #endif /* CONFIG_KEXEC */ -static int __init meminfo_cmp(const void *_a, const void *_b) -{ - const struct membank *a = _a, *b = _b; - long cmp = bank_pfn_start(a) - bank_pfn_start(b); - return cmp < 0 ? -1 : cmp > 0 ? 1 : 0; -} - void __init hyp_mode_check(void) { #ifdef CONFIG_ARM_VIRT_EXT @@ -903,12 +894,10 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); - sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL); - early_paging_init(mdesc, lookup_processor_type(read_cpuid_id())); setup_dma_zone(mdesc); sanity_check_meminfo(); - arm_memblock_init(&meminfo, mdesc); + arm_memblock_init(mdesc); paging_init(mdesc); request_standard_resources(mdesc); diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index b907d9b790ab..1b880db2a033 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -127,6 +127,10 @@ ENDPROC(cpu_resume_after_mmu) .align ENTRY(cpu_resume) ARM_BE8(setend be) @ ensure we are in BE mode +#ifdef CONFIG_ARM_VIRT_EXT + bl __hyp_stub_install_secondary +#endif + safe_svcmode_maskall r1 mov r1, #0 ALT_SMP(mrc p15, 0, r0, c0, c0, 5) ALT_UP_B(1f) @@ -144,7 +148,6 @@ ARM_BE8(setend be) @ ensure we are in BE mode ldr r0, [r0, #SLEEP_SAVE_SP_PHYS] ldr r0, [r0, r1, lsl #2] - setmode PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1 @ set SVC, irqs off @ load phys pgd, stack, resume fn ARM( ldmia r0!, {r1, sp, pc} ) THUMB( ldmia r0!, {r1, r2, r3} ) diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index af4e8c8a5422..f065eb05d254 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -3,6 +3,7 @@ #include <linux/stacktrace.h> #include <asm/stacktrace.h> +#include <asm/traps.h> #if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) /* @@ -61,6 +62,7 @@ EXPORT_SYMBOL(walk_stackframe); #ifdef CONFIG_STACKTRACE struct stack_trace_data { struct stack_trace *trace; + unsigned long last_pc; unsigned int no_sched_functions; unsigned int skip; }; @@ -69,6 +71,7 @@ static int save_trace(struct stackframe *frame, void *d) { struct stack_trace_data *data = d; struct stack_trace *trace = data->trace; + struct pt_regs *regs; unsigned long addr = frame->pc; if (data->no_sched_functions && in_sched_functions(addr)) @@ -80,16 +83,39 @@ static int save_trace(struct stackframe *frame, void *d) trace->entries[trace->nr_entries++] = addr; + if (trace->nr_entries >= trace->max_entries) + return 1; + + /* + * in_exception_text() is designed to test if the PC is one of + * the functions which has an exception stack above it, but + * unfortunately what is in frame->pc is the return LR value, + * not the saved PC value. So, we need to track the previous + * frame PC value when doing this. + */ + addr = data->last_pc; + data->last_pc = frame->pc; + if (!in_exception_text(addr)) + return 0; + + regs = (struct pt_regs *)frame->sp; + + trace->entries[trace->nr_entries++] = regs->ARM_pc; + return trace->nr_entries >= trace->max_entries; } -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +/* This must be noinline to so that our skip calculation works correctly */ +static noinline void __save_stack_trace(struct task_struct *tsk, + struct stack_trace *trace, unsigned int nosched) { struct stack_trace_data data; struct stackframe frame; data.trace = trace; + data.last_pc = ULONG_MAX; data.skip = trace->skip; + data.no_sched_functions = nosched; if (tsk != current) { #ifdef CONFIG_SMP @@ -102,7 +128,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; return; #else - data.no_sched_functions = 1; frame.fp = thread_saved_fp(tsk); frame.sp = thread_saved_sp(tsk); frame.lr = 0; /* recovered from the stack */ @@ -111,11 +136,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) } else { register unsigned long current_sp asm ("sp"); - data.no_sched_functions = 0; + /* We don't want this function nor the caller */ + data.skip += 2; frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_sp; frame.lr = (unsigned long)__builtin_return_address(0); - frame.pc = (unsigned long)save_stack_trace_tsk; + frame.pc = (unsigned long)__save_stack_trace; } walk_stackframe(&frame, save_trace, &data); @@ -123,9 +149,33 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; } +void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) +{ + struct stack_trace_data data; + struct stackframe frame; + + data.trace = trace; + data.skip = trace->skip; + data.no_sched_functions = 0; + + frame.fp = regs->ARM_fp; + frame.sp = regs->ARM_sp; + frame.lr = regs->ARM_lr; + frame.pc = regs->ARM_pc; + + walk_stackframe(&frame, save_trace, &data); + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = ULONG_MAX; +} + +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + __save_stack_trace(tsk, trace, 1); +} + void save_stack_trace(struct stack_trace *trace) { - save_stack_trace_tsk(current, trace); + __save_stack_trace(current, trace, 0); } EXPORT_SYMBOL_GPL(save_stack_trace); #endif diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 71e1fec6d31a..3997c411c140 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -91,13 +91,13 @@ static void __init parse_dt_topology(void) { const struct cpu_efficiency *cpu_eff; struct device_node *cn = NULL; - unsigned long min_capacity = (unsigned long)(-1); + unsigned long min_capacity = ULONG_MAX; unsigned long max_capacity = 0; unsigned long capacity = 0; - int alloc_size, cpu = 0; + int cpu = 0; - alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity); - __cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT); + __cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity), + GFP_NOWAIT); for_each_possible_cpu(cpu) { const u32 *rate; diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c index cb791ac6a003..e67682f02cb2 100644 --- a/arch/arm/kernel/unwind.c +++ b/arch/arm/kernel/unwind.c @@ -31,7 +31,7 @@ #warning Your compiler does not have EABI support. #warning ARM unwind is known to compile only with EABI compilers. #warning Change compiler or disable ARM_UNWIND option. -#elif (__GNUC__ == 4 && __GNUC_MINOR__ <= 2) +#elif (__GNUC__ == 4 && __GNUC_MINOR__ <= 2) && !defined(__clang__) #warning Your compiler is too buggy; it is known to not compile ARM unwind support. #warning Change compiler or disable ARM_UNWIND option. #endif diff --git a/arch/arm/kernel/uprobes.c b/arch/arm/kernel/uprobes.c index f9bacee973bf..56adf9c1fde0 100644 --- a/arch/arm/kernel/uprobes.c +++ b/arch/arm/kernel/uprobes.c @@ -113,6 +113,26 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, return 0; } +void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, + void *src, unsigned long len) +{ + void *xol_page_kaddr = kmap_atomic(page); + void *dst = xol_page_kaddr + (vaddr & ~PAGE_MASK); + + preempt_disable(); + + /* Initialize the slot */ + memcpy(dst, src, len); + + /* flush caches (dcache/icache) */ + flush_uprobe_xol_access(page, vaddr, dst, len); + + preempt_enable(); + + kunmap_atomic(xol_page_kaddr); +} + + int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { struct uprobe_task *utask = current->utask; diff --git a/arch/arm/mach-at91/sysirq_mask.c b/arch/arm/mach-at91/sysirq_mask.c index 2ba694f9626b..f8bc3511a8c8 100644 --- a/arch/arm/mach-at91/sysirq_mask.c +++ b/arch/arm/mach-at91/sysirq_mask.c @@ -25,24 +25,28 @@ #include "generic.h" -#define AT91_RTC_IDR 0x24 /* Interrupt Disable Register */ -#define AT91_RTC_IMR 0x28 /* Interrupt Mask Register */ +#define AT91_RTC_IDR 0x24 /* Interrupt Disable Register */ +#define AT91_RTC_IMR 0x28 /* Interrupt Mask Register */ +#define AT91_RTC_IRQ_MASK 0x1f /* Available IRQs mask */ void __init at91_sysirq_mask_rtc(u32 rtc_base) { void __iomem *base; - u32 mask; base = ioremap(rtc_base, 64); if (!base) return; - mask = readl_relaxed(base + AT91_RTC_IMR); - if (mask) { - pr_info("AT91: Disabling rtc irq\n"); - writel_relaxed(mask, base + AT91_RTC_IDR); - (void)readl_relaxed(base + AT91_RTC_IMR); /* flush */ - } + /* + * sam9x5 SoCs have the following errata: + * "RTC: Interrupt Mask Register cannot be used + * Interrupt Mask Register read always returns 0." + * + * Hence we're not relying on IMR values to disable + * interrupts. + */ + writel_relaxed(AT91_RTC_IRQ_MASK, base + AT91_RTC_IDR); + (void)readl_relaxed(base + AT91_RTC_IMR); /* flush */ iounmap(base); } diff --git a/arch/arm/mach-bcm/bcm_5301x.c b/arch/arm/mach-bcm/bcm_5301x.c index edff69761e04..e9bcbdbce555 100644 --- a/arch/arm/mach-bcm/bcm_5301x.c +++ b/arch/arm/mach-bcm/bcm_5301x.c @@ -43,19 +43,14 @@ static void __init bcm5301x_init_early(void) "imprecise external abort"); } -static void __init bcm5301x_dt_init(void) -{ - l2x0_of_init(0, ~0UL); - of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); -} - static const char __initconst *bcm5301x_dt_compat[] = { "brcm,bcm4708", NULL, }; DT_MACHINE_START(BCM5301X, "BCM5301X") + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, .init_early = bcm5301x_init_early, - .init_machine = bcm5301x_dt_init, .dt_compat = bcm5301x_dt_compat, MACHINE_END diff --git a/arch/arm/mach-berlin/berlin.c b/arch/arm/mach-berlin/berlin.c index 025bcb5473eb..ac181c6797ee 100644 --- a/arch/arm/mach-berlin/berlin.c +++ b/arch/arm/mach-berlin/berlin.c @@ -18,16 +18,6 @@ #include <asm/hardware/cache-l2x0.h> #include <asm/mach/arch.h> -static void __init berlin_init_machine(void) -{ - /* - * with DT probing for L2CCs, berlin_init_machine can be removed. - * Note: 88DE3005 (Armada 1500-mini) uses pl310 l2cc - */ - l2x0_of_init(0x70c00000, 0xfeffffff); - of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); -} - static const char * const berlin_dt_compat[] = { "marvell,berlin", NULL, @@ -35,5 +25,10 @@ static const char * const berlin_dt_compat[] = { DT_MACHINE_START(BERLIN_DT, "Marvell Berlin") .dt_compat = berlin_dt_compat, - .init_machine = berlin_init_machine, + /* + * with DT probing for L2CCs, berlin_init_machine can be removed. + * Note: 88DE3005 (Armada 1500-mini) uses pl310 l2cc + */ + .l2c_aux_val = 0x30c00000, + .l2c_aux_mask = 0xfeffffff, MACHINE_END diff --git a/arch/arm/mach-clps711x/board-clep7312.c b/arch/arm/mach-clps711x/board-clep7312.c index 221b9de32dd6..94a7add88a3f 100644 --- a/arch/arm/mach-clps711x/board-clep7312.c +++ b/arch/arm/mach-clps711x/board-clep7312.c @@ -18,6 +18,7 @@ #include <linux/init.h> #include <linux/types.h> #include <linux/string.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/mach-types.h> @@ -26,11 +27,9 @@ #include "common.h" static void __init -fixup_clep7312(struct tag *tags, char **cmdline, struct meminfo *mi) +fixup_clep7312(struct tag *tags, char **cmdline) { - mi->nr_banks=1; - mi->bank[0].start = 0xc0000000; - mi->bank[0].size = 0x01000000; + memblock_add(0xc0000000, 0x01000000); } MACHINE_START(CLEP7212, "Cirrus Logic 7212/7312") diff --git a/arch/arm/mach-clps711x/board-edb7211.c b/arch/arm/mach-clps711x/board-edb7211.c index 077609841f14..f9828f89972a 100644 --- a/arch/arm/mach-clps711x/board-edb7211.c +++ b/arch/arm/mach-clps711x/board-edb7211.c @@ -16,6 +16,7 @@ #include <linux/interrupt.h> #include <linux/backlight.h> #include <linux/platform_device.h> +#include <linux/memblock.h> #include <linux/mtd/physmap.h> #include <linux/mtd/partitions.h> @@ -133,7 +134,7 @@ static void __init edb7211_reserve(void) } static void __init -fixup_edb7211(struct tag *tags, char **cmdline, struct meminfo *mi) +fixup_edb7211(struct tag *tags, char **cmdline) { /* * Bank start addresses are not present in the information @@ -143,11 +144,8 @@ fixup_edb7211(struct tag *tags, char **cmdline, struct meminfo *mi) * Banks sizes _are_ present in the param block, but we're * not using that information yet. */ - mi->bank[0].start = 0xc0000000; - mi->bank[0].size = SZ_8M; - mi->bank[1].start = 0xc1000000; - mi->bank[1].size = SZ_8M; - mi->nr_banks = 2; + memblock_add(0xc0000000, SZ_8M); + memblock_add(0xc1000000, SZ_8M); } static void __init edb7211_init(void) diff --git a/arch/arm/mach-clps711x/board-p720t.c b/arch/arm/mach-clps711x/board-p720t.c index 67b733744ed7..0cf0e51e6546 100644 --- a/arch/arm/mach-clps711x/board-p720t.c +++ b/arch/arm/mach-clps711x/board-p720t.c @@ -295,7 +295,7 @@ static struct generic_bl_info p720t_lcd_backlight_pdata = { }; static void __init -fixup_p720t(struct tag *tag, char **cmdline, struct meminfo *mi) +fixup_p720t(struct tag *tag, char **cmdline) { /* * Our bootloader doesn't setup any tags (yet). diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c index 2ae28a69e3e5..f85449a6accd 100644 --- a/arch/arm/mach-cns3xxx/core.c +++ b/arch/arm/mach-cns3xxx/core.c @@ -272,9 +272,9 @@ void __init cns3xxx_l2x0_init(void) * * 1 cycle of latency for setup, read and write accesses */ - val = readl(base + L2X0_TAG_LATENCY_CTRL); + val = readl(base + L310_TAG_LATENCY_CTRL); val &= 0xfffff888; - writel(val, base + L2X0_TAG_LATENCY_CTRL); + writel(val, base + L310_TAG_LATENCY_CTRL); /* * Data RAM Control register @@ -285,12 +285,12 @@ void __init cns3xxx_l2x0_init(void) * * 1 cycle of latency for setup, read and write accesses */ - val = readl(base + L2X0_DATA_LATENCY_CTRL); + val = readl(base + L310_DATA_LATENCY_CTRL); val &= 0xfffff888; - writel(val, base + L2X0_DATA_LATENCY_CTRL); + writel(val, base + L310_DATA_LATENCY_CTRL); /* 32 KiB, 8-way, parity disable */ - l2x0_init(base, 0x00540000, 0xfe000fff); + l2x0_init(base, 0x00500000, 0xfe0f0fff); } #endif /* CONFIG_CACHE_L2X0 */ diff --git a/arch/arm/mach-ep93xx/crunch-bits.S b/arch/arm/mach-ep93xx/crunch-bits.S index 0ec9bb48fab9..e96923a3017b 100644 --- a/arch/arm/mach-ep93xx/crunch-bits.S +++ b/arch/arm/mach-ep93xx/crunch-bits.S @@ -16,6 +16,7 @@ #include <asm/ptrace.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> +#include <asm/assembler.h> #include <mach/ep93xx-regs.h> /* @@ -62,14 +63,16 @@ * r9 = ret_from_exception * lr = undefined instr exit * - * called from prefetch exception handler with interrupts disabled + * called from prefetch exception handler with interrupts enabled */ ENTRY(crunch_task_enable) + inc_preempt_count r10, r3 + ldr r8, =(EP93XX_APB_VIRT_BASE + 0x00130000) @ syscon addr ldr r1, [r8, #0x80] tst r1, #0x00800000 @ access to crunch enabled? - movne pc, lr @ if so no business here + bne 2f @ if so no business here mov r3, #0xaa @ unlock syscon swlock str r3, [r8, #0xc0] orr r1, r1, #0x00800000 @ enable access to crunch @@ -142,7 +145,7 @@ crunch_save: teq r0, #0 @ anything to load? cfldr64eq mvdx0, [r1, #CRUNCH_MVDX0] @ mvdx0 was clobbered - moveq pc, lr + beq 1f crunch_load: cfldr64 mvdx0, [r0, #CRUNCH_DSPSC] @ load status word @@ -190,6 +193,11 @@ crunch_load: cfldr64 mvdx14, [r0, #CRUNCH_MVDX14] cfldr64 mvdx15, [r0, #CRUNCH_MVDX15] +1: +#ifdef CONFIG_PREEMPT_COUNT + get_thread_info r10 +#endif +2: dec_preempt_count r10, r3 mov pc, lr /* diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h index 80b90e346ca0..16617bdb37a9 100644 --- a/arch/arm/mach-exynos/common.h +++ b/arch/arm/mach-exynos/common.h @@ -153,7 +153,6 @@ enum sys_powerdown { NUM_SYS_POWERDOWN, }; -extern unsigned long l2x0_regs_phys; struct exynos_pmu_conf { void __iomem *reg; unsigned int val[NUM_SYS_POWERDOWN]; diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c index bc43e22693b7..90aab4d75d08 100644 --- a/arch/arm/mach-exynos/exynos.c +++ b/arch/arm/mach-exynos/exynos.c @@ -30,9 +30,6 @@ #include "mfc.h" #include "regs-pmu.h" -#define L2_AUX_VAL 0x7C470001 -#define L2_AUX_MASK 0xC200ffff - static struct map_desc exynos4_iodesc[] __initdata = { { .virtual = (unsigned long)S3C_VA_SYS, @@ -202,7 +199,7 @@ static int __init exynos_fdt_map_chipid(unsigned long node, const char *uname, { struct map_desc iodesc; __be32 *reg; - unsigned long len; + int len; if (!of_flat_dt_is_compatible(node, "samsung,exynos4210-chipid") && !of_flat_dt_is_compatible(node, "samsung,exynos5440-clock")) @@ -246,25 +243,6 @@ void __init exynos_init_io(void) exynos_map_io(); } -static int __init exynos4_l2x0_cache_init(void) -{ - int ret; - - if (!soc_is_exynos4()) - return 0; - - ret = l2x0_of_init(L2_AUX_VAL, L2_AUX_MASK); - if (ret) - return ret; - - if (IS_ENABLED(CONFIG_S5P_SLEEP)) { - l2x0_regs_phys = virt_to_phys(&l2x0_saved_regs); - clean_dcache_area(&l2x0_regs_phys, sizeof(unsigned long)); - } - return 0; -} -early_initcall(exynos4_l2x0_cache_init); - static void __init exynos_dt_machine_init(void) { struct device_node *i2c_np; @@ -333,6 +311,8 @@ static void __init exynos_reserve(void) DT_MACHINE_START(EXYNOS_DT, "SAMSUNG EXYNOS (Flattened Device Tree)") /* Maintainer: Thomas Abraham <thomas.abraham@linaro.org> */ /* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */ + .l2c_aux_val = 0x3c400001, + .l2c_aux_mask = 0xc20fffff, .smp = smp_ops(exynos_smp_ops), .map_io = exynos_init_io, .init_early = exynos_firmware_init, diff --git a/arch/arm/mach-exynos/sleep.S b/arch/arm/mach-exynos/sleep.S index a2613e944e10..108a45f4bb62 100644 --- a/arch/arm/mach-exynos/sleep.S +++ b/arch/arm/mach-exynos/sleep.S @@ -16,8 +16,6 @@ */ #include <linux/linkage.h> -#include <asm/asm-offsets.h> -#include <asm/hardware/cache-l2x0.h> #define CPU_MASK 0xff0ffff0 #define CPU_CORTEX_A9 0x410fc090 @@ -53,33 +51,7 @@ ENTRY(exynos_cpu_resume) and r0, r0, r1 ldr r1, =CPU_CORTEX_A9 cmp r0, r1 - bne skip_l2_resume - adr r0, l2x0_regs_phys - ldr r0, [r0] - cmp r0, #0 - beq skip_l2_resume - ldr r1, [r0, #L2X0_R_PHY_BASE] - ldr r2, [r1, #L2X0_CTRL] - tst r2, #0x1 - bne skip_l2_resume - ldr r2, [r0, #L2X0_R_AUX_CTRL] - str r2, [r1, #L2X0_AUX_CTRL] - ldr r2, [r0, #L2X0_R_TAG_LATENCY] - str r2, [r1, #L2X0_TAG_LATENCY_CTRL] - ldr r2, [r0, #L2X0_R_DATA_LATENCY] - str r2, [r1, #L2X0_DATA_LATENCY_CTRL] - ldr r2, [r0, #L2X0_R_PREFETCH_CTRL] - str r2, [r1, #L2X0_PREFETCH_CTRL] - ldr r2, [r0, #L2X0_R_PWR_CTRL] - str r2, [r1, #L2X0_POWER_CTRL] - mov r2, #1 - str r2, [r1, #L2X0_CTRL] -skip_l2_resume: + bleq l2c310_early_resume #endif b cpu_resume ENDPROC(exynos_cpu_resume) -#ifdef CONFIG_CACHE_L2X0 - .globl l2x0_regs_phys -l2x0_regs_phys: - .long 0 -#endif diff --git a/arch/arm/mach-footbridge/cats-hw.c b/arch/arm/mach-footbridge/cats-hw.c index da0415094856..8f05489671b7 100644 --- a/arch/arm/mach-footbridge/cats-hw.c +++ b/arch/arm/mach-footbridge/cats-hw.c @@ -76,7 +76,7 @@ __initcall(cats_hw_init); * hard reboots fail on early boards. */ static void __init -fixup_cats(struct tag *tags, char **cmdline, struct meminfo *mi) +fixup_cats(struct tag *tags, char **cmdline) { #if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) screen_info.orig_video_lines = 25; diff --git a/arch/arm/mach-footbridge/netwinder-hw.c b/arch/arm/mach-footbridge/netwinder-hw.c index eb1fa5c84723..cdee08c6d239 100644 --- a/arch/arm/mach-footbridge/netwinder-hw.c +++ b/arch/arm/mach-footbridge/netwinder-hw.c @@ -620,7 +620,7 @@ __initcall(nw_hw_init); * the parameter page. */ static void __init -fixup_netwinder(struct tag *tags, char **cmdline, struct meminfo *mi) +fixup_netwinder(struct tag *tags, char **cmdline) { #ifdef CONFIG_ISAPNP extern int isapnp_disable; diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c index c7de89b263dd..8c35ae4ff176 100644 --- a/arch/arm/mach-highbank/highbank.c +++ b/arch/arm/mach-highbank/highbank.c @@ -51,11 +51,13 @@ static void __init highbank_scu_map_io(void) } -static void highbank_l2x0_disable(void) +static void highbank_l2c310_write_sec(unsigned long val, unsigned reg) { - outer_flush_all(); - /* Disable PL310 L2 Cache controller */ - highbank_smc1(0x102, 0x0); + if (reg == L2X0_CTRL) + highbank_smc1(0x102, val); + else + WARN_ONCE(1, "Highbank L2C310: ignoring write to reg 0x%x\n", + reg); } static void __init highbank_init_irq(void) @@ -64,14 +66,6 @@ static void __init highbank_init_irq(void) if (of_find_compatible_node(NULL, NULL, "arm,cortex-a9")) highbank_scu_map_io(); - - /* Enable PL310 L2 Cache controller */ - if (IS_ENABLED(CONFIG_CACHE_L2X0) && - of_find_compatible_node(NULL, NULL, "arm,pl310-cache")) { - highbank_smc1(0x102, 0x1); - l2x0_of_init(0, ~0UL); - outer_cache.disable = highbank_l2x0_disable; - } } static void highbank_power_off(void) @@ -185,6 +179,9 @@ DT_MACHINE_START(HIGHBANK, "Highbank") #if defined(CONFIG_ZONE_DMA) && defined(CONFIG_ARM_LPAE) .dma_zone_size = (4ULL * SZ_1G), #endif + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, + .l2c_write_sec = highbank_l2c310_write_sec, .init_irq = highbank_init_irq, .init_machine = highbank_init, .dt_compat = highbank_match, diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c index a4d5e425cd82..71c86a2f856d 100644 --- a/arch/arm/mach-imx/clk-imx35.c +++ b/arch/arm/mach-imx/clk-imx35.c @@ -289,14 +289,12 @@ int __init mx35_clocks_init(void) return 0; } -static int __init mx35_clocks_init_dt(struct device_node *ccm_node) +static void __init mx35_clocks_init_dt(struct device_node *ccm_node) { clk_data.clks = clk; clk_data.clk_num = ARRAY_SIZE(clk); of_clk_add_provider(ccm_node, of_clk_src_onecell_get, &clk_data); mx35_clocks_init(); - - return 0; } CLK_OF_DECLARE(imx35, "fsl,imx35-ccm", mx35_clocks_init_dt); diff --git a/arch/arm/mach-imx/mach-vf610.c b/arch/arm/mach-imx/mach-vf610.c index 2d8aef5a6efa..c44602758120 100644 --- a/arch/arm/mach-imx/mach-vf610.c +++ b/arch/arm/mach-imx/mach-vf610.c @@ -20,19 +20,14 @@ static void __init vf610_init_machine(void) of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); } -static void __init vf610_init_irq(void) -{ - l2x0_of_init(0, ~0UL); - irqchip_init(); -} - static const char *vf610_dt_compat[] __initconst = { "fsl,vf610", NULL, }; DT_MACHINE_START(VYBRID_VF610, "Freescale Vybrid VF610 (Device Tree)") - .init_irq = vf610_init_irq, + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, .init_machine = vf610_init_machine, .dt_compat = vf610_dt_compat, .restart = mxc_restart, diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S index 20048ff05739..fe123b079c05 100644 --- a/arch/arm/mach-imx/suspend-imx6.S +++ b/arch/arm/mach-imx/suspend-imx6.S @@ -334,28 +334,10 @@ ENDPROC(imx6_suspend) * turned into relative ones. */ -#ifdef CONFIG_CACHE_L2X0 - .macro pl310_resume - adr r0, l2x0_saved_regs_offset - ldr r2, [r0] - add r2, r2, r0 - ldr r0, [r2, #L2X0_R_PHY_BASE] @ get physical base of l2x0 - ldr r1, [r2, #L2X0_R_AUX_CTRL] @ get aux_ctrl value - str r1, [r0, #L2X0_AUX_CTRL] @ restore aux_ctrl - mov r1, #0x1 - str r1, [r0, #L2X0_CTRL] @ re-enable L2 - .endm - -l2x0_saved_regs_offset: - .word l2x0_saved_regs - . - -#else - .macro pl310_resume - .endm -#endif - ENTRY(v7_cpu_resume) bl v7_invalidate_l1 - pl310_resume +#ifdef CONFIG_CACHE_L2X0 + bl l2c310_early_resume +#endif b cpu_resume ENDPROC(v7_cpu_resume) diff --git a/arch/arm/mach-imx/system.c b/arch/arm/mach-imx/system.c index 5e3027d3692f..3b0733edb68c 100644 --- a/arch/arm/mach-imx/system.c +++ b/arch/arm/mach-imx/system.c @@ -124,7 +124,7 @@ void __init imx_init_l2cache(void) } /* Configure the L2 PREFETCH and POWER registers */ - val = readl_relaxed(l2x0_base + L2X0_PREFETCH_CTRL); + val = readl_relaxed(l2x0_base + L310_PREFETCH_CTRL); val |= 0x70800000; /* * The L2 cache controller(PL310) version on the i.MX6D/Q is r3p1-50rel0 @@ -137,14 +137,12 @@ void __init imx_init_l2cache(void) */ if (cpu_is_imx6q()) val &= ~(1 << 30 | 1 << 23); - writel_relaxed(val, l2x0_base + L2X0_PREFETCH_CTRL); - val = L2X0_DYNAMIC_CLK_GATING_EN | L2X0_STNDBY_MODE_EN; - writel_relaxed(val, l2x0_base + L2X0_POWER_CTRL); + writel_relaxed(val, l2x0_base + L310_PREFETCH_CTRL); iounmap(l2x0_base); of_node_put(np); out: - l2x0_of_init(0, ~0UL); + l2x0_of_init(0, ~0); } #endif diff --git a/arch/arm/mach-iop13xx/include/mach/irqs.h b/arch/arm/mach-iop13xx/include/mach/irqs.h index 054e7acb5bfa..e8d24d32121a 100644 --- a/arch/arm/mach-iop13xx/include/mach/irqs.h +++ b/arch/arm/mach-iop13xx/include/mach/irqs.h @@ -191,6 +191,4 @@ static inline u32 read_intpnd_3(void) #define NR_IOP13XX_IRQS (IRQ_IOP13XX_HPI + 1) #endif -#define NR_IRQS NR_IOP13XX_IRQS - #endif /* _IOP13XX_IRQ_H_ */ diff --git a/arch/arm/mach-iop13xx/include/mach/time.h b/arch/arm/mach-iop13xx/include/mach/time.h index f1c00d6d560b..15bc9bb78a6b 100644 --- a/arch/arm/mach-iop13xx/include/mach/time.h +++ b/arch/arm/mach-iop13xx/include/mach/time.h @@ -1,5 +1,8 @@ #ifndef _IOP13XX_TIME_H_ #define _IOP13XX_TIME_H_ + +#include <mach/irqs.h> + #define IRQ_IOP_TIMER0 IRQ_IOP13XX_TIMER0 #define IOP_TMR_EN 0x02 diff --git a/arch/arm/mach-iop13xx/iq81340mc.c b/arch/arm/mach-iop13xx/iq81340mc.c index 02a8228ac2d3..9cd07d396093 100644 --- a/arch/arm/mach-iop13xx/iq81340mc.c +++ b/arch/arm/mach-iop13xx/iq81340mc.c @@ -93,4 +93,5 @@ MACHINE_START(IQ81340MC, "Intel IQ81340MC") .init_time = iq81340mc_timer_init, .init_machine = iq81340mc_init, .restart = iop13xx_restart, + .nr_irqs = NR_IOP13XX_IRQS, MACHINE_END diff --git a/arch/arm/mach-iop13xx/iq81340sc.c b/arch/arm/mach-iop13xx/iq81340sc.c index 1b80f10722b3..b3ec11cb707e 100644 --- a/arch/arm/mach-iop13xx/iq81340sc.c +++ b/arch/arm/mach-iop13xx/iq81340sc.c @@ -95,4 +95,5 @@ MACHINE_START(IQ81340SC, "Intel IQ81340SC") .init_time = iq81340sc_timer_init, .init_machine = iq81340sc_init, .restart = iop13xx_restart, + .nr_irqs = NR_IOP13XX_IRQS, MACHINE_END diff --git a/arch/arm/mach-iop13xx/msi.c b/arch/arm/mach-iop13xx/msi.c index 560d5b2dec22..e7730cf9c15d 100644 --- a/arch/arm/mach-iop13xx/msi.c +++ b/arch/arm/mach-iop13xx/msi.c @@ -23,10 +23,7 @@ #include <linux/msi.h> #include <asm/mach/irq.h> #include <asm/irq.h> - - -#define IOP13XX_NUM_MSI_IRQS 128 -static DECLARE_BITMAP(msi_irq_in_use, IOP13XX_NUM_MSI_IRQS); +#include <mach/irqs.h> /* IMIPR0 CP6 R8 Page 1 */ @@ -121,41 +118,6 @@ void __init iop13xx_msi_init(void) irq_set_chained_handler(IRQ_IOP13XX_INBD_MSI, iop13xx_msi_handler); } -/* - * Dynamic irq allocate and deallocation - */ -int create_irq(void) -{ - int irq, pos; - -again: - pos = find_first_zero_bit(msi_irq_in_use, IOP13XX_NUM_MSI_IRQS); - irq = IRQ_IOP13XX_MSI_0 + pos; - if (irq > NR_IRQS) - return -ENOSPC; - /* test_and_set_bit operates on 32-bits at a time */ - if (test_and_set_bit(pos, msi_irq_in_use)) - goto again; - - dynamic_irq_init(irq); - - return irq; -} - -void destroy_irq(unsigned int irq) -{ - int pos = irq - IRQ_IOP13XX_MSI_0; - - dynamic_irq_cleanup(irq); - - clear_bit(pos, msi_irq_in_use); -} - -void arch_teardown_msi_irq(unsigned int irq) -{ - destroy_irq(irq); -} - static void iop13xx_msi_nop(struct irq_data *d) { return; @@ -172,12 +134,17 @@ static struct irq_chip iop13xx_msi_chip = { int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) { - int id, irq = create_irq(); + int id, irq = irq_alloc_desc_from(IRQ_IOP13XX_MSI_0, -1); struct msi_msg msg; if (irq < 0) return irq; + if (irq >= NR_IOP13XX_IRQS) { + irq_free_desc(irq); + return -ENOSPC; + } + irq_set_msi_desc(irq, desc); msg.address_hi = 0x0; @@ -191,3 +158,8 @@ int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) return 0; } + +void arch_teardown_msi_irq(unsigned int irq) +{ + irq_free_desc(irq); +} diff --git a/arch/arm/mach-iop13xx/setup.c b/arch/arm/mach-iop13xx/setup.c index 96e6c7a6793b..bca96f433495 100644 --- a/arch/arm/mach-iop13xx/setup.c +++ b/arch/arm/mach-iop13xx/setup.c @@ -27,6 +27,7 @@ #include <mach/hardware.h> #include <asm/irq.h> #include <asm/hardware/iop_adma.h> +#include <mach/irqs.h> #define IOP13XX_UART_XTAL 33334000 #define IOP13XX_SETUP_DEBUG 0 diff --git a/arch/arm/mach-iop13xx/tpmi.c b/arch/arm/mach-iop13xx/tpmi.c index 6fdad7a0425a..db511ec2b1df 100644 --- a/arch/arm/mach-iop13xx/tpmi.c +++ b/arch/arm/mach-iop13xx/tpmi.c @@ -24,6 +24,7 @@ #include <linux/io.h> #include <asm/irq.h> #include <asm/sizes.h> +#include <mach/irqs.h> /* assumes CONTROLLER_ONLY# is never asserted in the ESSR register */ #define IOP13XX_TPMI_MMR(dev) IOP13XX_REG_ADDR32_PHYS(0x48000 + (dev << 12)) diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c index e0b9e1b9cf30..7f352de26099 100644 --- a/arch/arm/mach-keystone/keystone.c +++ b/arch/arm/mach-keystone/keystone.c @@ -14,60 +14,100 @@ #include <linux/init.h> #include <linux/of_platform.h> #include <linux/of_address.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/mach/map.h> #include <asm/mach/arch.h> #include <asm/mach/time.h> #include <asm/smp_plat.h> +#include <asm/memory.h> -#include "keystone.h" +#include "memory.h" -#define PLL_RESET_WRITE_KEY_MASK 0xffff0000 -#define PLL_RESET_WRITE_KEY 0x5a69 -#define PLL_RESET BIT(16) +#include "keystone.h" -static void __iomem *keystone_rstctrl; +static struct notifier_block platform_nb; +static unsigned long keystone_dma_pfn_offset __read_mostly; -static void __init keystone_init(void) +static int keystone_platform_notifier(struct notifier_block *nb, + unsigned long event, void *data) { - struct device_node *node; + struct device *dev = data; - node = of_find_compatible_node(NULL, NULL, "ti,keystone-reset"); - if (WARN_ON(!node)) - pr_warn("ti,keystone-reset node undefined\n"); + if (event != BUS_NOTIFY_ADD_DEVICE) + return NOTIFY_DONE; - keystone_rstctrl = of_iomap(node, 0); - if (WARN_ON(!keystone_rstctrl)) - pr_warn("ti,keystone-reset iomap error\n"); + if (!dev) + return NOTIFY_BAD; + if (!dev->of_node) { + dev->dma_pfn_offset = keystone_dma_pfn_offset; + dev_err(dev, "set dma_pfn_offset%08lx\n", + dev->dma_pfn_offset); + } + return NOTIFY_OK; +} + +static void __init keystone_init(void) +{ keystone_pm_runtime_init(); + if (platform_nb.notifier_call) + bus_register_notifier(&platform_bus_type, &platform_nb); of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); } -static const char *keystone_match[] __initconst = { - "ti,keystone", - NULL, -}; +static phys_addr_t keystone_virt_to_idmap(unsigned long x) +{ + return (phys_addr_t)(x) - CONFIG_PAGE_OFFSET + KEYSTONE_LOW_PHYS_START; +} -void keystone_restart(enum reboot_mode mode, const char *cmd) +static void __init keystone_init_meminfo(void) { - u32 val; + bool lpae = IS_ENABLED(CONFIG_ARM_LPAE); + bool pvpatch = IS_ENABLED(CONFIG_ARM_PATCH_PHYS_VIRT); + phys_addr_t offset = PHYS_OFFSET - KEYSTONE_LOW_PHYS_START; + phys_addr_t mem_start, mem_end; + + mem_start = memblock_start_of_DRAM(); + mem_end = memblock_end_of_DRAM(); + + /* nothing to do if we are running out of the <32-bit space */ + if (mem_start >= KEYSTONE_LOW_PHYS_START && + mem_end <= KEYSTONE_LOW_PHYS_END) + return; + + if (!lpae || !pvpatch) { + pr_crit("Enable %s%s%s to run outside 32-bit space\n", + !lpae ? __stringify(CONFIG_ARM_LPAE) : "", + (!lpae && !pvpatch) ? " and " : "", + !pvpatch ? __stringify(CONFIG_ARM_PATCH_PHYS_VIRT) : ""); + } + + if (mem_start < KEYSTONE_HIGH_PHYS_START || + mem_end > KEYSTONE_HIGH_PHYS_END) { + pr_crit("Invalid address space for memory (%08llx-%08llx)\n", + (u64)mem_start, (u64)mem_end); + } - BUG_ON(!keystone_rstctrl); + offset += KEYSTONE_HIGH_PHYS_START; + __pv_phys_pfn_offset = PFN_DOWN(offset); + __pv_offset = (offset - PAGE_OFFSET); - /* Enable write access to RSTCTRL */ - val = readl(keystone_rstctrl); - val &= PLL_RESET_WRITE_KEY_MASK; - val |= PLL_RESET_WRITE_KEY; - writel(val, keystone_rstctrl); + /* Populate the arch idmap hook */ + arch_virt_to_idmap = keystone_virt_to_idmap; + platform_nb.notifier_call = keystone_platform_notifier; + keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START - + KEYSTONE_LOW_PHYS_START); - /* Reset the SOC */ - val = readl(keystone_rstctrl); - val &= ~PLL_RESET; - writel(val, keystone_rstctrl); + pr_info("Switching to high address space at 0x%llx\n", (u64)offset); } +static const char *keystone_match[] __initconst = { + "ti,keystone", + NULL, +}; + DT_MACHINE_START(KEYSTONE, "Keystone") #if defined(CONFIG_ZONE_DMA) && defined(CONFIG_ARM_LPAE) .dma_zone_size = SZ_2G, @@ -75,5 +115,5 @@ DT_MACHINE_START(KEYSTONE, "Keystone") .smp = smp_ops(keystone_smp_ops), .init_machine = keystone_init, .dt_compat = keystone_match, - .restart = keystone_restart, + .init_meminfo = keystone_init_meminfo, MACHINE_END diff --git a/arch/arm/mach-keystone/memory.h b/arch/arm/mach-keystone/memory.h new file mode 100644 index 000000000000..b854fb18eef1 --- /dev/null +++ b/arch/arm/mach-keystone/memory.h @@ -0,0 +1,24 @@ +/* + * Copyright 2014 Texas Instruments, Inc. + * Santosh Shilimkar <santosh.shilimkar@ti.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + */ +#ifndef __MEMORY_H +#define __MEMORY_H + +#define MAX_PHYSMEM_BITS 36 +#define SECTION_SIZE_BITS 34 + +#define KEYSTONE_LOW_PHYS_START 0x80000000ULL +#define KEYSTONE_LOW_PHYS_SIZE 0x80000000ULL /* 2G */ +#define KEYSTONE_LOW_PHYS_END (KEYSTONE_LOW_PHYS_START + \ + KEYSTONE_LOW_PHYS_SIZE - 1) + +#define KEYSTONE_HIGH_PHYS_START 0x800000000ULL +#define KEYSTONE_HIGH_PHYS_SIZE 0x400000000ULL /* 16G */ +#define KEYSTONE_HIGH_PHYS_END (KEYSTONE_HIGH_PHYS_START + \ + KEYSTONE_HIGH_PHYS_SIZE - 1) +#endif /* __MEMORY_H */ diff --git a/arch/arm/mach-keystone/platsmp.c b/arch/arm/mach-keystone/platsmp.c index 5cf0683577ea..5f46a7cf907b 100644 --- a/arch/arm/mach-keystone/platsmp.c +++ b/arch/arm/mach-keystone/platsmp.c @@ -17,13 +17,16 @@ #include <linux/io.h> #include <asm/smp_plat.h> +#include <asm/prom.h> +#include <asm/tlbflush.h> +#include <asm/pgtable.h> #include "keystone.h" static int keystone_smp_boot_secondary(unsigned int cpu, struct task_struct *idle) { - unsigned long start = virt_to_phys(&secondary_startup); + unsigned long start = virt_to_idmap(&secondary_startup); int error; pr_debug("keystone-smp: booting cpu %d, vector %08lx\n", @@ -36,6 +39,19 @@ static int keystone_smp_boot_secondary(unsigned int cpu, return error; } +#ifdef CONFIG_ARM_LPAE +static void __cpuinit keystone_smp_secondary_initmem(unsigned int cpu) +{ + pgd_t *pgd0 = pgd_offset_k(0); + cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET); + local_flush_tlb_all(); +} +#else +static inline void __cpuinit keystone_smp_secondary_initmem(unsigned int cpu) +{} +#endif + struct smp_operations keystone_smp_ops __initdata = { .smp_boot_secondary = keystone_smp_boot_secondary, + .smp_secondary_init = keystone_smp_secondary_initmem, }; diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c index a77529887cbc..61bfe584a9d7 100644 --- a/arch/arm/mach-msm/board-halibut.c +++ b/arch/arm/mach-msm/board-halibut.c @@ -83,11 +83,6 @@ static void __init halibut_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init halibut_fixup(struct tag *tags, char **cmdline, - struct meminfo *mi) -{ -} - static void __init halibut_map_io(void) { msm_map_common_io(); @@ -100,7 +95,6 @@ static void __init halibut_init_late(void) MACHINE_START(HALIBUT, "Halibut Board (QCT SURF7200A)") .atag_offset = 0x100, - .fixup = halibut_fixup, .map_io = halibut_map_io, .init_early = halibut_init_early, .init_irq = halibut_init_irq, diff --git a/arch/arm/mach-msm/board-mahimahi.c b/arch/arm/mach-msm/board-mahimahi.c index 7d9981cb400e..873c3ca3cd7e 100644 --- a/arch/arm/mach-msm/board-mahimahi.c +++ b/arch/arm/mach-msm/board-mahimahi.c @@ -22,6 +22,7 @@ #include <linux/io.h> #include <linux/kernel.h> #include <linux/platform_device.h> +#include <linux/memblock.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> @@ -52,16 +53,10 @@ static void __init mahimahi_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init mahimahi_fixup(struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init mahimahi_fixup(struct tag *tags, char **cmdline) { - mi->nr_banks = 2; - mi->bank[0].start = PHYS_OFFSET; - mi->bank[0].node = PHYS_TO_NID(PHYS_OFFSET); - mi->bank[0].size = (219*1024*1024); - mi->bank[1].start = MSM_HIGHMEM_BASE; - mi->bank[1].node = PHYS_TO_NID(MSM_HIGHMEM_BASE); - mi->bank[1].size = MSM_HIGHMEM_SIZE; + memblock_add(PHYS_OFFSET, 219*SZ_1M); + memblock_add(MSM_HIGHMEM_BASE, MSM_HIGHMEM_SIZE); } static void __init mahimahi_map_io(void) diff --git a/arch/arm/mach-msm/board-msm7x30.c b/arch/arm/mach-msm/board-msm7x30.c index 0c4c200e1221..245884319d2e 100644 --- a/arch/arm/mach-msm/board-msm7x30.c +++ b/arch/arm/mach-msm/board-msm7x30.c @@ -40,8 +40,7 @@ #include "proc_comm.h" #include "common.h" -static void __init msm7x30_fixup(struct tag *tag, char **cmdline, - struct meminfo *mi) +static void __init msm7x30_fixup(struct tag *tag, char **cmdline) { for (; tag->hdr.size; tag = tag_next(tag)) if (tag->hdr.tag == ATAG_MEM && tag->u.mem.start == 0x200000) { diff --git a/arch/arm/mach-msm/board-sapphire.c b/arch/arm/mach-msm/board-sapphire.c index 327605174d63..e50967926dcd 100644 --- a/arch/arm/mach-msm/board-sapphire.c +++ b/arch/arm/mach-msm/board-sapphire.c @@ -35,6 +35,7 @@ #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> +#include <linux/memblock.h> #include "gpio_chip.h" #include "board-sapphire.h" @@ -74,22 +75,18 @@ static struct map_desc sapphire_io_desc[] __initdata = { } }; -static void __init sapphire_fixup(struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init sapphire_fixup(struct tag *tags, char **cmdline) { int smi_sz = parse_tag_smi((const struct tag *)tags); - mi->nr_banks = 1; - mi->bank[0].start = PHYS_OFFSET; - mi->bank[0].node = PHYS_TO_NID(PHYS_OFFSET); if (smi_sz == 32) { - mi->bank[0].size = (84*1024*1024); + memblock_add(PHYS_OFFSET, 84*SZ_1M); } else if (smi_sz == 64) { - mi->bank[0].size = (101*1024*1024); + memblock_add(PHYS_OFFSET, 101*SZ_1M); } else { + memblock_add(PHYS_OFFSET, 101*SZ_1M); /* Give a default value when not get smi size */ smi_sz = 64; - mi->bank[0].size = (101*1024*1024); } } diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c index 5edfbd904d06..f72b07de2152 100644 --- a/arch/arm/mach-msm/board-trout.c +++ b/arch/arm/mach-msm/board-trout.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/platform_device.h> #include <linux/clkdev.h> +#include <linux/memblock.h> #include <asm/system_info.h> #include <asm/mach-types.h> @@ -55,12 +56,9 @@ static void __init trout_init_irq(void) msm_init_irq(); } -static void __init trout_fixup(struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init trout_fixup(struct tag *tags, char **cmdline) { - mi->nr_banks = 1; - mi->bank[0].start = PHYS_OFFSET; - mi->bank[0].size = (101*1024*1024); + memblock_add(PHYS_OFFSET, 101*SZ_1M); } static void __init trout_init(void) diff --git a/arch/arm/mach-mvebu/board-v7.c b/arch/arm/mach-mvebu/board-v7.c index 01cfce6ac20b..8bb742fdf5ca 100644 --- a/arch/arm/mach-mvebu/board-v7.c +++ b/arch/arm/mach-mvebu/board-v7.c @@ -78,7 +78,6 @@ static void __init mvebu_timer_and_clk_init(void) mvebu_scu_enable(); coherency_init(); BUG_ON(mvebu_mbus_dt_init(coherency_available())); - l2x0_of_init(0, ~0UL); if (of_machine_is_compatible("marvell,armada375")) hook_fault_code(16 + 6, armada_375_external_abort_wa, SIGBUS, 0, @@ -182,6 +181,8 @@ static const char * const armada_370_xp_dt_compat[] = { }; DT_MACHINE_START(ARMADA_370_XP_DT, "Marvell Armada 370/XP (Device Tree)") + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, .smp = smp_ops(armada_xp_smp_ops), .init_machine = mvebu_dt_init, .init_time = mvebu_timer_and_clk_init, @@ -195,6 +196,8 @@ static const char * const armada_375_dt_compat[] = { }; DT_MACHINE_START(ARMADA_375_DT, "Marvell Armada 375 (Device Tree)") + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, .init_time = mvebu_timer_and_clk_init, .init_machine = mvebu_dt_init, .restart = mvebu_restart, @@ -208,6 +211,8 @@ static const char * const armada_38x_dt_compat[] = { }; DT_MACHINE_START(ARMADA_38X_DT, "Marvell Armada 380/385 (Device Tree)") + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, .init_time = mvebu_timer_and_clk_init, .restart = mvebu_restart, .dt_compat = armada_38x_dt_compat, diff --git a/arch/arm/mach-nomadik/cpu-8815.c b/arch/arm/mach-nomadik/cpu-8815.c index 4a1065e41e9c..9116ca476d7c 100644 --- a/arch/arm/mach-nomadik/cpu-8815.c +++ b/arch/arm/mach-nomadik/cpu-8815.c @@ -143,23 +143,16 @@ static int __init cpu8815_mmcsd_init(void) } device_initcall(cpu8815_mmcsd_init); -static void __init cpu8815_init_of(void) -{ -#ifdef CONFIG_CACHE_L2X0 - /* At full speed latency must be >=2, so 0x249 in low bits */ - l2x0_of_init(0x00730249, 0xfe000fff); -#endif - of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); -} - static const char * cpu8815_board_compat[] = { "calaosystems,usb-s8815", NULL, }; DT_MACHINE_START(NOMADIK_DT, "Nomadik STn8815") + /* At full speed latency must be >=2, so 0x249 in low bits */ + .l2c_aux_val = 0x00700249, + .l2c_aux_mask = 0xfe0fefff, .map_io = cpu8815_map_io, - .init_machine = cpu8815_init_of, .restart = cpu8815_restart, .dt_compat = cpu8815_board_compat, MACHINE_END diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index cb31d4390d52..0ba482638ebf 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -65,6 +65,7 @@ config SOC_AM43XX select ARCH_HAS_OPP select ARM_GIC select MACH_OMAP_GENERIC + select MIGHT_HAVE_CACHE_L2X0 config SOC_DRA7XX bool "TI DRA7XX" diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c index 660bfc5a70d7..e2e52031f056 100644 --- a/arch/arm/mach-omap2/board-omap3beagle.c +++ b/arch/arm/mach-omap2/board-omap3beagle.c @@ -60,7 +60,8 @@ static struct pwm_lookup pwm_lookup[] = { /* LEDB -> PMU_STAT */ - PWM_LOOKUP("twl-pwmled", 1, "leds_pwm", "beagleboard::pmu_stat"), + PWM_LOOKUP("twl-pwmled", 1, "leds_pwm", "beagleboard::pmu_stat", + 7812500, PWM_POLARITY_NORMAL), }; static struct led_pwm pwm_leds[] = { diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h index d88aff7baff8..ff029737c8f0 100644 --- a/arch/arm/mach-omap2/common.h +++ b/arch/arm/mach-omap2/common.h @@ -91,6 +91,7 @@ extern void omap3_sync32k_timer_init(void); extern void omap3_secure_sync32k_timer_init(void); extern void omap3_gptimer_timer_init(void); extern void omap4_local_timer_init(void); +int omap_l2_cache_init(void); extern void omap5_realtime_timer_init(void); void omap2420_init_early(void); diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c index e58609b312c7..592ba0a0ecf3 100644 --- a/arch/arm/mach-omap2/devices.c +++ b/arch/arm/mach-omap2/devices.c @@ -18,7 +18,6 @@ #include <linux/slab.h> #include <linux/of.h> #include <linux/pinctrl/machine.h> -#include <linux/platform_data/omap4-keypad.h> #include <linux/platform_data/mailbox-omap.h> #include <asm/mach-types.h> @@ -29,7 +28,6 @@ #include "iomap.h" #include "omap_hwmod.h" #include "omap_device.h" -#include "omap4-keypad.h" #include "soc.h" #include "common.h" @@ -255,37 +253,6 @@ static inline void omap_init_camera(void) #endif } -int __init omap4_keyboard_init(struct omap4_keypad_platform_data - *sdp4430_keypad_data, struct omap_board_data *bdata) -{ - struct platform_device *pdev; - struct omap_hwmod *oh; - struct omap4_keypad_platform_data *keypad_data; - unsigned int id = -1; - char *oh_name = "kbd"; - char *name = "omap4-keypad"; - - oh = omap_hwmod_lookup(oh_name); - if (!oh) { - pr_err("Could not look up %s\n", oh_name); - return -ENODEV; - } - - keypad_data = sdp4430_keypad_data; - - pdev = omap_device_build(name, id, oh, keypad_data, - sizeof(struct omap4_keypad_platform_data)); - - if (IS_ERR(pdev)) { - WARN(1, "Can't build omap_device for %s:%s.\n", - name, oh->name); - return PTR_ERR(pdev); - } - oh->mux = omap_hwmod_mux_init(bdata->pads, bdata->pads_cnt); - - return 0; -} - #if defined(CONFIG_OMAP2PLUS_MBOX) || defined(CONFIG_OMAP2PLUS_MBOX_MODULE) static inline void __init omap_init_mbox(void) { diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c index 16d33d831287..bf852d7ae951 100644 --- a/arch/arm/mach-omap2/display.c +++ b/arch/arm/mach-omap2/display.c @@ -279,6 +279,8 @@ static enum omapdss_version __init omap_display_get_version(void) return OMAPDSS_VER_OMAP4; else if (soc_is_omap54xx()) return OMAPDSS_VER_OMAP5; + else if (soc_is_am43xx()) + return OMAPDSS_VER_AM43xx; else return OMAPDSS_VER_UNKNOWN; } @@ -555,65 +557,9 @@ int omap_dss_reset(struct omap_hwmod *oh) return r; } -/* list of 'compatible' nodes to convert to omapdss specific */ -static const char * const dss_compat_conv_list[] __initconst = { - "composite-connector", - "dvi-connector", - "hdmi-connector", - "panel-dpi", - "panel-dsi-cm", - "sony,acx565akm", - "svideo-connector", - "ti,tfp410", - "ti,tpd12s015", -}; - -/* prepend compatible string with "omapdss," */ -static __init void omapdss_omapify_node(struct device_node *node, - const char *compat) -{ - char *new_compat; - struct property *prop; - - new_compat = kasprintf(GFP_KERNEL, "omapdss,%s", compat); - - prop = kzalloc(sizeof(*prop), GFP_KERNEL); - - if (!prop) { - pr_err("omapdss_omapify_node: kzalloc failed\n"); - return; - } - - prop->name = "compatible"; - prop->value = new_compat; - prop->length = strlen(new_compat) + 1; - - of_update_property(node, prop); -} - -/* - * As omapdss panel drivers are omapdss specific, but we want to define the - * DT-data in generic manner, we convert the compatible strings of the panel - * nodes from "panel-foo" to "omapdss,panel-foo". This way we can have both - * correct DT data and omapdss specific drivers. - * - * When we get generic panel drivers to the kernel, this will be removed. - */ void __init omapdss_early_init_of(void) { - int i; - - for (i = 0; i < ARRAY_SIZE(dss_compat_conv_list); ++i) { - const char *compat = dss_compat_conv_list[i]; - struct device_node *node = NULL; - - while ((node = of_find_compatible_node(node, NULL, compat))) { - if (!of_device_is_available(node)) - continue; - omapdss_omapify_node(node, compat); - } - } } struct device_node * __init omapdss_find_dss_of_node(void) @@ -632,6 +578,10 @@ struct device_node * __init omapdss_find_dss_of_node(void) if (node) return node; + node = of_find_compatible_node(NULL, NULL, "ti,omap5-dss"); + if (node) + return node; + return NULL; } diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c index 852b19a367f0..2c0c2816900f 100644 --- a/arch/arm/mach-omap2/gpmc.c +++ b/arch/arm/mach-omap2/gpmc.c @@ -68,6 +68,9 @@ #define GPMC_ECC_BCH_RESULT_1 0x244 /* not available on OMAP2 */ #define GPMC_ECC_BCH_RESULT_2 0x248 /* not available on OMAP2 */ #define GPMC_ECC_BCH_RESULT_3 0x24c /* not available on OMAP2 */ +#define GPMC_ECC_BCH_RESULT_4 0x300 /* not available on OMAP2 */ +#define GPMC_ECC_BCH_RESULT_5 0x304 /* not available on OMAP2 */ +#define GPMC_ECC_BCH_RESULT_6 0x308 /* not available on OMAP2 */ /* GPMC ECC control settings */ #define GPMC_ECC_CTRL_ECCCLEAR 0x100 @@ -677,6 +680,12 @@ void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs) GPMC_BCH_SIZE * i; reg->gpmc_bch_result3[i] = gpmc_base + GPMC_ECC_BCH_RESULT_3 + GPMC_BCH_SIZE * i; + reg->gpmc_bch_result4[i] = gpmc_base + GPMC_ECC_BCH_RESULT_4 + + i * GPMC_BCH_SIZE; + reg->gpmc_bch_result5[i] = gpmc_base + GPMC_ECC_BCH_RESULT_5 + + i * GPMC_BCH_SIZE; + reg->gpmc_bch_result6[i] = gpmc_base + GPMC_ECC_BCH_RESULT_6 + + i * GPMC_BCH_SIZE; } } @@ -1412,6 +1421,12 @@ static int gpmc_probe_nand_child(struct platform_device *pdev, else gpmc_nand_data->ecc_opt = OMAP_ECC_BCH8_CODE_HW_DETECTION_SW; + else if (!strcmp(s, "bch16")) + if (gpmc_nand_data->elm_of_node) + gpmc_nand_data->ecc_opt = + OMAP_ECC_BCH16_CODE_HW; + else + pr_err("%s: BCH16 requires ELM support\n", __func__); else pr_err("%s: ti,nand-ecc-opt invalid value\n", __func__); diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index 4ec3b4a93843..8f559450c876 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -609,6 +609,7 @@ void __init am43xx_init_early(void) am43xx_clockdomains_init(); am43xx_hwmod_init(); omap_hwmod_init_postsetup(); + omap_l2_cache_init(); omap_clk_soc_init = am43xx_dt_clk_init; } @@ -640,6 +641,7 @@ void __init omap4430_init_early(void) omap44xx_clockdomains_init(); omap44xx_hwmod_init(); omap_hwmod_init_postsetup(); + omap_l2_cache_init(); omap_clk_soc_init = omap4xxx_dt_clk_init; } diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c index eb76e47091ad..4001325f90fb 100644 --- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c +++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c @@ -187,19 +187,15 @@ static void l2x0_pwrst_prepare(unsigned int cpu_id, unsigned int save_state) * in every restore MPUSS OFF path. */ #ifdef CONFIG_CACHE_L2X0 -static void save_l2x0_context(void) +static void __init save_l2x0_context(void) { - u32 val; - void __iomem *l2x0_base = omap4_get_l2cache_base(); - if (l2x0_base) { - val = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); - writel_relaxed(val, sar_base + L2X0_AUXCTRL_OFFSET); - val = readl_relaxed(l2x0_base + L2X0_PREFETCH_CTRL); - writel_relaxed(val, sar_base + L2X0_PREFETCH_CTRL_OFFSET); - } + writel_relaxed(l2x0_saved_regs.aux_ctrl, + sar_base + L2X0_AUXCTRL_OFFSET); + writel_relaxed(l2x0_saved_regs.prefetch_ctrl, + sar_base + L2X0_PREFETCH_CTRL_OFFSET); } #else -static void save_l2x0_context(void) +static void __init save_l2x0_context(void) {} #endif diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c index 99b0154493a4..326cd982a3cb 100644 --- a/arch/arm/mach-omap2/omap4-common.c +++ b/arch/arm/mach-omap2/omap4-common.c @@ -167,75 +167,57 @@ void __iomem *omap4_get_l2cache_base(void) return l2cache_base; } -static void omap4_l2x0_disable(void) +static void omap4_l2c310_write_sec(unsigned long val, unsigned reg) { - outer_flush_all(); - /* Disable PL310 L2 Cache controller */ - omap_smc1(0x102, 0x0); -} + unsigned smc_op; -static void omap4_l2x0_set_debug(unsigned long val) -{ - /* Program PL310 L2 Cache controller debug register */ - omap_smc1(0x100, val); + switch (reg) { + case L2X0_CTRL: + smc_op = OMAP4_MON_L2X0_CTRL_INDEX; + break; + + case L2X0_AUX_CTRL: + smc_op = OMAP4_MON_L2X0_AUXCTRL_INDEX; + break; + + case L2X0_DEBUG_CTRL: + smc_op = OMAP4_MON_L2X0_DBG_CTRL_INDEX; + break; + + case L310_PREFETCH_CTRL: + smc_op = OMAP4_MON_L2X0_PREFETCH_INDEX; + break; + + default: + WARN_ONCE(1, "OMAP L2C310: ignoring write to reg 0x%x\n", reg); + return; + } + + omap_smc1(smc_op, val); } -static int __init omap_l2_cache_init(void) +int __init omap_l2_cache_init(void) { - u32 aux_ctrl = 0; - - /* - * To avoid code running on other OMAPs in - * multi-omap builds - */ - if (!cpu_is_omap44xx()) - return -ENODEV; + u32 aux_ctrl; /* Static mapping, never released */ l2cache_base = ioremap(OMAP44XX_L2CACHE_BASE, SZ_4K); if (WARN_ON(!l2cache_base)) return -ENOMEM; - /* - * 16-way associativity, parity disabled - * Way size - 32KB (es1.0) - * Way size - 64KB (es2.0 +) - */ - aux_ctrl = ((1 << L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT) | - (0x1 << 25) | - (0x1 << L2X0_AUX_CTRL_NS_LOCKDOWN_SHIFT) | - (0x1 << L2X0_AUX_CTRL_NS_INT_CTRL_SHIFT)); - - if (omap_rev() == OMAP4430_REV_ES1_0) { - aux_ctrl |= 0x2 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT; - } else { - aux_ctrl |= ((0x3 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT) | - (1 << L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT) | - (1 << L2X0_AUX_CTRL_DATA_PREFETCH_SHIFT) | - (1 << L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT) | - (1 << L2X0_AUX_CTRL_EARLY_BRESP_SHIFT)); - } - if (omap_rev() != OMAP4430_REV_ES1_0) - omap_smc1(0x109, aux_ctrl); - - /* Enable PL310 L2 Cache controller */ - omap_smc1(0x102, 0x1); + /* 16-way associativity, parity disabled, way size - 64KB (es2.0 +) */ + aux_ctrl = L2C_AUX_CTRL_SHARED_OVERRIDE | + L310_AUX_CTRL_DATA_PREFETCH | + L310_AUX_CTRL_INSTR_PREFETCH; + outer_cache.write_sec = omap4_l2c310_write_sec; if (of_have_populated_dt()) - l2x0_of_init(aux_ctrl, L2X0_AUX_CTRL_MASK); + l2x0_of_init(aux_ctrl, 0xcf9fffff); else - l2x0_init(l2cache_base, aux_ctrl, L2X0_AUX_CTRL_MASK); - - /* - * Override default outer_cache.disable with a OMAP4 - * specific one - */ - outer_cache.disable = omap4_l2x0_disable; - outer_cache.set_debug = omap4_l2x0_set_debug; + l2x0_init(l2cache_base, aux_ctrl, 0xcf9fffff); return 0; } -omap_early_initcall(omap_l2_cache_init); #endif void __iomem *omap4_get_sar_ram_base(void) diff --git a/arch/arm/mach-omap2/omap4-keypad.h b/arch/arm/mach-omap2/omap4-keypad.h deleted file mode 100644 index 20de0d5a7e77..000000000000 --- a/arch/arm/mach-omap2/omap4-keypad.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef ARCH_ARM_PLAT_OMAP4_KEYPAD_H -#define ARCH_ARM_PLAT_OMAP4_KEYPAD_H - -struct omap_board_data; - -extern int omap4_keyboard_init(struct omap4_keypad_platform_data *, - struct omap_board_data *); -#endif diff --git a/arch/arm/mach-orion5x/board-dt.c b/arch/arm/mach-orion5x/board-dt.c index 35d418faf8f1..79f033b1ddff 100644 --- a/arch/arm/mach-orion5x/board-dt.c +++ b/arch/arm/mach-orion5x/board-dt.c @@ -45,7 +45,7 @@ static void __init orion5x_dt_init(void) orion5x_id(&dev, &rev, &dev_name); printk(KERN_INFO "Orion ID: %s. TCLK=%d.\n", dev_name, orion5x_tclk); - BUG_ON(mvebu_mbus_dt_init()); + BUG_ON(mvebu_mbus_dt_init(false)); /* * Setup Orion address map diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c index 3f1de1111e0f..6bbb7b55c6d1 100644 --- a/arch/arm/mach-orion5x/common.c +++ b/arch/arm/mach-orion5x/common.c @@ -365,8 +365,7 @@ void orion5x_restart(enum reboot_mode mode, const char *cmd) * Many orion-based systems have buggy bootloader implementations. * This is a common fixup for bogus memory tags. */ -void __init tag_fixup_mem32(struct tag *t, char **from, - struct meminfo *meminfo) +void __init tag_fixup_mem32(struct tag *t, char **from) { for (; t->hdr.size; t = tag_next(t)) if (t->hdr.tag == ATAG_MEM && diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h index 26d6f34b6027..cd0389c6e822 100644 --- a/arch/arm/mach-orion5x/common.h +++ b/arch/arm/mach-orion5x/common.h @@ -64,9 +64,8 @@ int orion5x_pci_sys_setup(int nr, struct pci_sys_data *sys); struct pci_bus *orion5x_pci_sys_scan_bus(int nr, struct pci_sys_data *sys); int orion5x_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin); -struct meminfo; struct tag; -extern void __init tag_fixup_mem32(struct tag *, char **, struct meminfo *); +extern void __init tag_fixup_mem32(struct tag *, char **); #ifdef CONFIG_MACH_MSS2_DT extern void mss2_init(void); diff --git a/arch/arm/mach-prima2/Makefile b/arch/arm/mach-prima2/Makefile index 7a6b4a323125..8846e7d87ea5 100644 --- a/arch/arm/mach-prima2/Makefile +++ b/arch/arm/mach-prima2/Makefile @@ -2,7 +2,6 @@ obj-y += rstc.o obj-y += common.o obj-y += rtciobrg.o obj-$(CONFIG_DEBUG_LL) += lluart.o -obj-$(CONFIG_CACHE_L2X0) += l2x0.o obj-$(CONFIG_SUSPEND) += pm.o sleep.o obj-$(CONFIG_SMP) += platsmp.o headsmp.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o diff --git a/arch/arm/mach-prima2/common.c b/arch/arm/mach-prima2/common.c index 47c7819edb9b..a860ea27e8ae 100644 --- a/arch/arm/mach-prima2/common.c +++ b/arch/arm/mach-prima2/common.c @@ -34,6 +34,8 @@ static const char *atlas6_dt_match[] __initconst = { DT_MACHINE_START(ATLAS6_DT, "Generic ATLAS6 (Flattened Device Tree)") /* Maintainer: Barry Song <baohua.song@csr.com> */ + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, .map_io = sirfsoc_map_io, .init_late = sirfsoc_init_late, .dt_compat = atlas6_dt_match, @@ -48,6 +50,8 @@ static const char *prima2_dt_match[] __initconst = { DT_MACHINE_START(PRIMA2_DT, "Generic PRIMA2 (Flattened Device Tree)") /* Maintainer: Barry Song <baohua.song@csr.com> */ + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, .map_io = sirfsoc_map_io, .dma_zone_size = SZ_256M, .init_late = sirfsoc_init_late, @@ -63,6 +67,8 @@ static const char *marco_dt_match[] __initconst = { DT_MACHINE_START(MARCO_DT, "Generic MARCO (Flattened Device Tree)") /* Maintainer: Barry Song <baohua.song@csr.com> */ + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, .smp = smp_ops(sirfsoc_smp_ops), .map_io = sirfsoc_map_io, .init_late = sirfsoc_init_late, diff --git a/arch/arm/mach-prima2/l2x0.c b/arch/arm/mach-prima2/l2x0.c deleted file mode 100644 index c7102539c0b0..000000000000 --- a/arch/arm/mach-prima2/l2x0.c +++ /dev/null @@ -1,49 +0,0 @@ -/* - * l2 cache initialization for CSR SiRFprimaII - * - * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company. - * - * Licensed under GPLv2 or later. - */ - -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/of.h> -#include <asm/hardware/cache-l2x0.h> - -struct l2x0_aux { - u32 val; - u32 mask; -}; - -static const struct l2x0_aux prima2_l2x0_aux __initconst = { - .val = 2 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT, - .mask = 0, -}; - -static const struct l2x0_aux marco_l2x0_aux __initconst = { - .val = (2 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT) | - (1 << L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT), - .mask = L2X0_AUX_CTRL_MASK, -}; - -static const struct of_device_id sirf_l2x0_ids[] __initconst = { - { .compatible = "sirf,prima2-pl310-cache", .data = &prima2_l2x0_aux, }, - { .compatible = "sirf,marco-pl310-cache", .data = &marco_l2x0_aux, }, - {}, -}; - -static int __init sirfsoc_l2x0_init(void) -{ - struct device_node *np; - const struct l2x0_aux *aux; - - np = of_find_matching_node(NULL, sirf_l2x0_ids); - if (np) { - aux = of_match_node(sirf_l2x0_ids, np)->data; - return l2x0_of_init(aux->val, aux->mask); - } - - return 0; -} -early_initcall(sirfsoc_l2x0_init); diff --git a/arch/arm/mach-prima2/pm.c b/arch/arm/mach-prima2/pm.c index c4525a88e5da..96e9bc102117 100644 --- a/arch/arm/mach-prima2/pm.c +++ b/arch/arm/mach-prima2/pm.c @@ -71,7 +71,6 @@ static int sirfsoc_pm_enter(suspend_state_t state) case PM_SUSPEND_MEM: sirfsoc_pre_suspend_power_off(); - outer_flush_all(); outer_disable(); /* go zzz */ cpu_suspend(0, sirfsoc_finish_suspend); diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c index 584439bfa59f..4d3588d26c2a 100644 --- a/arch/arm/mach-pxa/cm-x300.c +++ b/arch/arm/mach-pxa/cm-x300.c @@ -837,8 +837,7 @@ static void __init cm_x300_init(void) cm_x300_init_bl(); } -static void __init cm_x300_fixup(struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init cm_x300_fixup(struct tag *tags, char **cmdline) { /* Make sure that mi->bank[0].start = PHYS_ADDR */ for (; tags->hdr.size; tags = tag_next(tags)) diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c index 57d60542f982..91dd1c7cdbcd 100644 --- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -34,6 +34,7 @@ #include <linux/input/matrix_keypad.h> #include <linux/gpio_keys.h> #include <linux/module.h> +#include <linux/memblock.h> #include <video/w100fb.h> #include <asm/setup.h> @@ -753,16 +754,13 @@ static void __init corgi_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init fixup_corgi(struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init fixup_corgi(struct tag *tags, char **cmdline) { sharpsl_save_param(); - mi->nr_banks=1; - mi->bank[0].start = 0xa0000000; if (machine_is_corgi()) - mi->bank[0].size = (32*1024*1024); + memblock_add(0xa0000000, SZ_32M); else - mi->bank[0].size = (64*1024*1024); + memblock_add(0xa0000000, SZ_64M); } #ifdef CONFIG_MACH_CORGI diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c index 8280ebcaab9f..cfb864173ce3 100644 --- a/arch/arm/mach-pxa/eseries.c +++ b/arch/arm/mach-pxa/eseries.c @@ -21,6 +21,7 @@ #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> #include <linux/usb/gpio_vbus.h> +#include <linux/memblock.h> #include <video/w100fb.h> @@ -41,14 +42,12 @@ #include "clock.h" /* Only e800 has 128MB RAM */ -void __init eseries_fixup(struct tag *tags, char **cmdline, struct meminfo *mi) +void __init eseries_fixup(struct tag *tags, char **cmdline) { - mi->nr_banks=1; - mi->bank[0].start = 0xa0000000; if (machine_is_e800()) - mi->bank[0].size = (128*1024*1024); + memblock_add(0xa0000000, SZ_128M); else - mi->bank[0].size = (64*1024*1024); + memblock_add(0xa0000000, SZ_64M); } struct gpio_vbus_mach_info e7xx_udc_info = { diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c index a7c30eb0c8db..c66ad4edc5e3 100644 --- a/arch/arm/mach-pxa/hx4700.c +++ b/arch/arm/mach-pxa/hx4700.c @@ -574,7 +574,8 @@ static struct platform_device backlight = { }; static struct pwm_lookup hx4700_pwm_lookup[] = { - PWM_LOOKUP("pxa27x-pwm.1", 0, "pwm-backlight", NULL), + PWM_LOOKUP("pxa27x-pwm.1", 0, "pwm-backlight", NULL, + 30923, PWM_POLARITY_NORMAL), }; /* diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c index aedf053a1de5..131991629116 100644 --- a/arch/arm/mach-pxa/poodle.c +++ b/arch/arm/mach-pxa/poodle.c @@ -29,6 +29,7 @@ #include <linux/spi/ads7846.h> #include <linux/spi/pxa2xx_spi.h> #include <linux/mtd/sharpsl.h> +#include <linux/memblock.h> #include <mach/hardware.h> #include <asm/mach-types.h> @@ -456,13 +457,10 @@ static void __init poodle_init(void) poodle_init_spi(); } -static void __init fixup_poodle(struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init fixup_poodle(struct tag *tags, char **cmdline) { sharpsl_save_param(); - mi->nr_banks=1; - mi->bank[0].start = 0xa0000000; - mi->bank[0].size = (32*1024*1024); + memblock_add(0xa0000000, SZ_32M); } MACHINE_START(POODLE, "SHARP Poodle") diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 0b11c1af51c4..840c3a48e720 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -32,6 +32,7 @@ #include <linux/io.h> #include <linux/module.h> #include <linux/reboot.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/mach-types.h> @@ -971,13 +972,10 @@ static void __init spitz_init(void) spitz_i2c_init(); } -static void __init spitz_fixup(struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init spitz_fixup(struct tag *tags, char **cmdline) { sharpsl_save_param(); - mi->nr_banks = 1; - mi->bank[0].start = 0xa0000000; - mi->bank[0].size = (64*1024*1024); + memblock_add(0xa0000000, SZ_64M); } #ifdef CONFIG_MACH_SPITZ diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c index ef5557b807ed..c158a6e3e0aa 100644 --- a/arch/arm/mach-pxa/tosa.c +++ b/arch/arm/mach-pxa/tosa.c @@ -37,6 +37,7 @@ #include <linux/i2c/pxa-i2c.h> #include <linux/usb/gpio_vbus.h> #include <linux/reboot.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/mach-types.h> @@ -960,13 +961,10 @@ static void __init tosa_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init fixup_tosa(struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init fixup_tosa(struct tag *tags, char **cmdline) { sharpsl_save_param(); - mi->nr_banks=1; - mi->bank[0].start = 0xa0000000; - mi->bank[0].size = (64*1024*1024); + memblock_add(0xa0000000, SZ_64M); } MACHINE_START(TOSA, "SHARP Tosa") diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index 960b8dd78c44..8c1b39a0caa0 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -31,6 +31,7 @@ #include <linux/amba/mmci.h> #include <linux/gfp.h> #include <linux/mtd/physmap.h> +#include <linux/memblock.h> #include <mach/hardware.h> #include <asm/irq.h> @@ -385,19 +386,15 @@ void __init realview_timer_init(unsigned int timer_irq) /* * Setup the memory banks. */ -void realview_fixup(struct tag *tags, char **from, struct meminfo *meminfo) +void realview_fixup(struct tag *tags, char **from) { /* * Most RealView platforms have 512MB contiguous RAM at 0x70000000. * Half of this is mirrored at 0. */ #ifdef CONFIG_REALVIEW_HIGH_PHYS_OFFSET - meminfo->bank[0].start = 0x70000000; - meminfo->bank[0].size = SZ_512M; - meminfo->nr_banks = 1; + memblock_add(0x70000000, SZ_512M); #else - meminfo->bank[0].start = 0; - meminfo->bank[0].size = SZ_256M; - meminfo->nr_banks = 1; + memblock_add(0, SZ_256M); #endif } diff --git a/arch/arm/mach-realview/core.h b/arch/arm/mach-realview/core.h index 13dc830ef469..868ece221978 100644 --- a/arch/arm/mach-realview/core.h +++ b/arch/arm/mach-realview/core.h @@ -52,8 +52,7 @@ extern int realview_flash_register(struct resource *res, u32 num); extern int realview_eth_register(const char *name, struct resource *res); extern int realview_usb_register(struct resource *res); extern void realview_init_early(void); -extern void realview_fixup(struct tag *tags, char **from, - struct meminfo *meminfo); +extern void realview_fixup(struct tag *tags, char **from); extern struct smp_operations realview_smp_ops; extern void realview_cpu_die(unsigned int cpu); diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c index 6bb070e80128..739d4f113097 100644 --- a/arch/arm/mach-realview/realview_eb.c +++ b/arch/arm/mach-realview/realview_eb.c @@ -442,8 +442,13 @@ static void __init realview_eb_init(void) realview_eb11mp_fixup(); #ifdef CONFIG_CACHE_L2X0 - /* 1MB (128KB/way), 8-way associativity, evmon/parity/share enabled - * Bits: .... ...0 0111 1001 0000 .... .... .... */ + /* + * The PL220 needs to be manually configured as the hardware + * doesn't report the correct sizes. + * 1MB (128KB/way), 8-way associativity, event monitor and + * parity enabled, ignore share bit, no force write allocate + * Bits: .... ...0 0111 1001 0000 .... .... .... + */ l2x0_init(__io_address(REALVIEW_EB11MP_L220_BASE), 0x00790000, 0xfe000fff); #endif platform_device_register(&pmu_device); diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c index 173f2c15de49..b0e0dcaed944 100644 --- a/arch/arm/mach-realview/realview_pb1176.c +++ b/arch/arm/mach-realview/realview_pb1176.c @@ -32,6 +32,7 @@ #include <linux/irqchip/arm-gic.h> #include <linux/platform_data/clk-realview.h> #include <linux/reboot.h> +#include <linux/memblock.h> #include <mach/hardware.h> #include <asm/irq.h> @@ -339,15 +340,12 @@ static void realview_pb1176_restart(enum reboot_mode mode, const char *cmd) dsb(); } -static void realview_pb1176_fixup(struct tag *tags, char **from, - struct meminfo *meminfo) +static void realview_pb1176_fixup(struct tag *tags, char **from) { /* * RealView PB1176 only has 128MB of RAM mapped at 0. */ - meminfo->bank[0].start = 0; - meminfo->bank[0].size = SZ_128M; - meminfo->nr_banks = 1; + memblock_add(0, SZ_128M); } static void __init realview_pb1176_init(void) @@ -355,7 +353,13 @@ static void __init realview_pb1176_init(void) int i; #ifdef CONFIG_CACHE_L2X0 - /* 128Kb (16Kb/way) 8-way associativity. evmon/parity/share enabled. */ + /* + * The PL220 needs to be manually configured as the hardware + * doesn't report the correct sizes. + * 128kB (16kB/way), 8-way associativity, event monitor and + * parity enabled, ignore share bit, no force write allocate + * Bits: .... ...0 0111 0011 0000 .... .... .... + */ l2x0_init(__io_address(REALVIEW_PB1176_L220_BASE), 0x00730000, 0xfe000fff); #endif diff --git a/arch/arm/mach-realview/realview_pb11mp.c b/arch/arm/mach-realview/realview_pb11mp.c index bde7e6b1fd44..47bf55fdbf27 100644 --- a/arch/arm/mach-realview/realview_pb11mp.c +++ b/arch/arm/mach-realview/realview_pb11mp.c @@ -337,8 +337,13 @@ static void __init realview_pb11mp_init(void) int i; #ifdef CONFIG_CACHE_L2X0 - /* 1MB (128KB/way), 8-way associativity, evmon/parity/share enabled - * Bits: .... ...0 0111 1001 0000 .... .... .... */ + /* + * The PL220 needs to be manually configured as the hardware + * doesn't report the correct sizes. + * 1MB (128KB/way), 8-way associativity, event monitor and + * parity enabled, ignore share bit, no force write allocate + * Bits: .... ...0 0111 1001 0000 .... .... .... + */ l2x0_init(__io_address(REALVIEW_TC11MP_L220_BASE), 0x00790000, 0xfe000fff); #endif diff --git a/arch/arm/mach-realview/realview_pbx.c b/arch/arm/mach-realview/realview_pbx.c index 72c96caebefa..d89eb4023467 100644 --- a/arch/arm/mach-realview/realview_pbx.c +++ b/arch/arm/mach-realview/realview_pbx.c @@ -29,6 +29,7 @@ #include <linux/irqchip/arm-gic.h> #include <linux/platform_data/clk-realview.h> #include <linux/reboot.h> +#include <linux/memblock.h> #include <asm/irq.h> #include <asm/mach-types.h> @@ -325,23 +326,19 @@ static void __init realview_pbx_timer_init(void) realview_pbx_twd_init(); } -static void realview_pbx_fixup(struct tag *tags, char **from, - struct meminfo *meminfo) +static void realview_pbx_fixup(struct tag *tags, char **from) { #ifdef CONFIG_SPARSEMEM /* * Memory configuration with SPARSEMEM enabled on RealView PBX (see * asm/mach/memory.h for more information). */ - meminfo->bank[0].start = 0; - meminfo->bank[0].size = SZ_256M; - meminfo->bank[1].start = 0x20000000; - meminfo->bank[1].size = SZ_512M; - meminfo->bank[2].start = 0x80000000; - meminfo->bank[2].size = SZ_256M; - meminfo->nr_banks = 3; + + memblock_add(0, SZ_256M); + memblock_add(0x20000000, SZ_512M); + memblock_add(0x80000000, SZ_256M); #else - realview_fixup(tags, from, meminfo); + realview_fixup(tags, from); #endif } @@ -370,8 +367,8 @@ static void __init realview_pbx_init(void) __io_address(REALVIEW_PBX_TILE_L220_BASE); /* set RAM latencies to 1 cycle for eASIC */ - writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL); - writel(0, l2x0_base + L2X0_DATA_LATENCY_CTRL); + writel(0, l2x0_base + L310_TAG_LATENCY_CTRL); + writel(0, l2x0_base + L310_DATA_LATENCY_CTRL); /* 16KB way size, 8-way associativity, parity disabled * Bits: .. 0 0 0 0 1 00 1 0 1 001 0 000 0 .... .... .... */ diff --git a/arch/arm/mach-rockchip/rockchip.c b/arch/arm/mach-rockchip/rockchip.c index 4499b0a31a27..968cc348e624 100644 --- a/arch/arm/mach-rockchip/rockchip.c +++ b/arch/arm/mach-rockchip/rockchip.c @@ -24,12 +24,6 @@ #include <asm/hardware/cache-l2x0.h> #include "core.h" -static void __init rockchip_dt_init(void) -{ - l2x0_of_init(0, ~0UL); - of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); -} - static const char * const rockchip_board_dt_compat[] = { "rockchip,rk2928", "rockchip,rk3066a", @@ -39,6 +33,7 @@ static const char * const rockchip_board_dt_compat[] = { }; DT_MACHINE_START(ROCKCHIP_DT, "Rockchip Cortex-A9 (Device Tree)") - .init_machine = rockchip_dt_init, + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, .dt_compat = rockchip_board_dt_compat, MACHINE_END diff --git a/arch/arm/mach-s3c24xx/mach-smdk2413.c b/arch/arm/mach-s3c24xx/mach-smdk2413.c index a38f8a049e22..fb3b80e44595 100644 --- a/arch/arm/mach-s3c24xx/mach-smdk2413.c +++ b/arch/arm/mach-s3c24xx/mach-smdk2413.c @@ -22,6 +22,7 @@ #include <linux/serial_s3c.h> #include <linux/platform_device.h> #include <linux/io.h> +#include <linux/memblock.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> @@ -93,13 +94,10 @@ static struct platform_device *smdk2413_devices[] __initdata = { &s3c2412_device_dma, }; -static void __init smdk2413_fixup(struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init smdk2413_fixup(struct tag *tags, char **cmdline) { if (tags != phys_to_virt(S3C2410_SDRAM_PA + 0x100)) { - mi->nr_banks=1; - mi->bank[0].start = 0x30000000; - mi->bank[0].size = SZ_64M; + memblock_add(0x30000000, SZ_64M); } } diff --git a/arch/arm/mach-s3c24xx/mach-vstms.c b/arch/arm/mach-s3c24xx/mach-vstms.c index 6b706c915387..9104c2be36c9 100644 --- a/arch/arm/mach-s3c24xx/mach-vstms.c +++ b/arch/arm/mach-s3c24xx/mach-vstms.c @@ -23,6 +23,7 @@ #include <linux/mtd/nand.h> #include <linux/mtd/nand_ecc.h> #include <linux/mtd/partitions.h> +#include <linux/memblock.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> @@ -129,13 +130,10 @@ static struct platform_device *vstms_devices[] __initdata = { &s3c2412_device_dma, }; -static void __init vstms_fixup(struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init vstms_fixup(struct tag *tags, char **cmdline) { if (tags != phys_to_virt(S3C2410_SDRAM_PA + 0x100)) { - mi->nr_banks=1; - mi->bank[0].start = 0x30000000; - mi->bank[0].size = SZ_64M; + memblock_add(0x30000000, SZ_64M); } } diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c index b41a38a75844..c1ce921c4088 100644 --- a/arch/arm/mach-s5pv210/mach-goni.c +++ b/arch/arm/mach-s5pv210/mach-goni.c @@ -49,11 +49,6 @@ #include <plat/clock.h> #include <plat/samsung-time.h> #include <plat/mfc.h> -#include <plat/camport.h> - -#include <media/v4l2-mediabus.h> -#include <media/s5p_fimc.h> -#include <media/noon010pc30.h> #include "common.h" @@ -239,14 +234,6 @@ static void __init goni_radio_init(void) /* TSP */ static struct mxt_platform_data qt602240_platform_data = { - .x_line = 17, - .y_line = 11, - .x_size = 800, - .y_size = 480, - .blen = 0x21, - .threshold = 0x28, - .voltage = 2800000, /* 2.8V */ - .orient = MXT_DIAGONAL, .irqflags = IRQF_TRIGGER_FALLING, }; @@ -285,14 +272,6 @@ static void __init goni_tsp_init(void) /* USB OTG */ static struct s3c_hsotg_plat goni_hsotg_pdata; -static void goni_camera_init(void) -{ - s5pv210_fimc_setup_gpio(S5P_CAMPORT_A); - - /* Set max driver strength on CAM_A_CLKOUT pin. */ - s5p_gpio_set_drvstr(S5PV210_GPE1(3), S5P_GPIO_DRVSTR_LV4); -} - /* MAX8998 regulators */ #if defined(CONFIG_REGULATOR_MAX8998) || defined(CONFIG_REGULATOR_MAX8998_MODULE) @@ -825,34 +804,6 @@ static void goni_setup_sdhci(void) s3c_sdhci2_set_platdata(&goni_hsmmc2_data); }; -static struct noon010pc30_platform_data noon010pc30_pldata = { - .clk_rate = 16000000UL, - .gpio_nreset = S5PV210_GPB(2), /* CAM_CIF_NRST */ - .gpio_nstby = S5PV210_GPB(0), /* CAM_CIF_NSTBY */ -}; - -static struct i2c_board_info noon010pc30_board_info = { - I2C_BOARD_INFO("NOON010PC30", 0x60 >> 1), - .platform_data = &noon010pc30_pldata, -}; - -static struct fimc_source_info goni_camera_sensors[] = { - { - .mux_id = 0, - .flags = V4L2_MBUS_PCLK_SAMPLE_FALLING | - V4L2_MBUS_VSYNC_ACTIVE_LOW, - .fimc_bus_type = FIMC_BUS_TYPE_ITU_601, - .board_info = &noon010pc30_board_info, - .i2c_bus_num = 0, - .clk_frequency = 16000000UL, - }, -}; - -static struct s5p_platform_fimc goni_fimc_md_platdata __initdata = { - .source_info = goni_camera_sensors, - .num_clients = ARRAY_SIZE(goni_camera_sensors), -}; - /* Audio device */ static struct platform_device goni_device_audio = { .name = "smdk-audio", @@ -874,10 +825,6 @@ static struct platform_device *goni_devices[] __initdata = { &s5p_device_mixer, &s5p_device_sdo, &s3c_device_i2c0, - &s5p_device_fimc0, - &s5p_device_fimc1, - &s5p_device_fimc2, - &s5p_device_fimc_md, &s3c_device_hsmmc0, &s3c_device_hsmmc1, &s3c_device_hsmmc2, @@ -946,14 +893,8 @@ static void __init goni_machine_init(void) /* FB */ s3c_fb_set_platdata(&goni_lcd_pdata); - /* FIMC */ - s3c_set_platdata(&goni_fimc_md_platdata, sizeof(goni_fimc_md_platdata), - &s5p_device_fimc_md); - s3c_hsotg_set_platdata(&goni_hsotg_pdata); - goni_camera_init(); - /* SPI */ spi_register_board_info(spi_board_info, ARRAY_SIZE(spi_board_info)); diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c index 8443a27bca2f..7dd894ece9ae 100644 --- a/arch/arm/mach-sa1100/assabet.c +++ b/arch/arm/mach-sa1100/assabet.c @@ -531,7 +531,7 @@ static void __init get_assabet_scr(void) } static void __init -fixup_assabet(struct tag *tags, char **cmdline, struct meminfo *mi) +fixup_assabet(struct tag *tags, char **cmdline) { /* This must be done before any call to machine_has_neponset() */ map_sa1100_gpio_regs(); diff --git a/arch/arm/mach-shmobile/board-armadillo800eva-reference.c b/arch/arm/mach-shmobile/board-armadillo800eva-reference.c index 57d246eb8813..f660fbb96e0b 100644 --- a/arch/arm/mach-shmobile/board-armadillo800eva-reference.c +++ b/arch/arm/mach-shmobile/board-armadillo800eva-reference.c @@ -164,8 +164,8 @@ static void __init eva_init(void) r8a7740_meram_workaround(); #ifdef CONFIG_CACHE_L2X0 - /* Early BRESP enable, Shared attribute override enable, 32K*8way */ - l2x0_init(IOMEM(0xf0002000), 0x40440000, 0x82000fff); + /* Shared attribute override enable, 32K*8way */ + l2x0_init(IOMEM(0xf0002000), 0x00400000, 0xc20f0fff); #endif r8a7740_add_standard_devices_dt(); diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c index bc2cf7a89534..30fcac73a540 100644 --- a/arch/arm/mach-shmobile/board-armadillo800eva.c +++ b/arch/arm/mach-shmobile/board-armadillo800eva.c @@ -31,7 +31,7 @@ #include <linux/gpio_keys.h> #include <linux/regulator/driver.h> #include <linux/pinctrl/machine.h> -#include <linux/platform_data/pwm-renesas-tpu.h> +#include <linux/pwm.h> #include <linux/pwm_backlight.h> #include <linux/regulator/fixed.h> #include <linux/regulator/gpio-regulator.h> @@ -399,24 +399,16 @@ static struct resource pwm_resources[] = { }, }; -static struct tpu_pwm_platform_data pwm_device_data = { - .channels[2] = { - .polarity = PWM_POLARITY_INVERSED, - } -}; - static struct platform_device pwm_device = { .name = "renesas-tpu-pwm", .id = -1, - .dev = { - .platform_data = &pwm_device_data, - }, .num_resources = ARRAY_SIZE(pwm_resources), .resource = pwm_resources, }; static struct pwm_lookup pwm_lookup[] = { - PWM_LOOKUP("renesas-tpu-pwm", 2, "pwm-backlight.0", NULL), + PWM_LOOKUP("renesas-tpu-pwm", 2, "pwm-backlight.0", NULL, + 33333, PWM_POLARITY_INVERSED), }; /* LCDC and backlight */ @@ -1271,8 +1263,8 @@ static void __init eva_init(void) #ifdef CONFIG_CACHE_L2X0 - /* Early BRESP enable, Shared attribute override enable, 32K*8way */ - l2x0_init(IOMEM(0xf0002000), 0x40440000, 0x82000fff); + /* Shared attribute override enable, 32K*8way */ + l2x0_init(IOMEM(0xf0002000), 0x00400000, 0xc20f0fff); #endif i2c_register_board_info(0, i2c0_devices, ARRAY_SIZE(i2c0_devices)); diff --git a/arch/arm/mach-shmobile/board-kzm9g-reference.c b/arch/arm/mach-shmobile/board-kzm9g-reference.c index 598e32488410..a735a1d80c28 100644 --- a/arch/arm/mach-shmobile/board-kzm9g-reference.c +++ b/arch/arm/mach-shmobile/board-kzm9g-reference.c @@ -36,8 +36,8 @@ static void __init kzm_init(void) sh73a0_add_standard_devices_dt(); #ifdef CONFIG_CACHE_L2X0 - /* Early BRESP enable, Shared attribute override enable, 64K*8way */ - l2x0_init(IOMEM(0xf0100000), 0x40460000, 0x82000fff); + /* Shared attribute override enable, 64K*8way */ + l2x0_init(IOMEM(0xf0100000), 0x00400000, 0xc20f0fff); #endif } diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c index 03dc3ac84502..f94ec8ca42c1 100644 --- a/arch/arm/mach-shmobile/board-kzm9g.c +++ b/arch/arm/mach-shmobile/board-kzm9g.c @@ -876,8 +876,8 @@ static void __init kzm_init(void) gpio_request_one(223, GPIOF_IN, NULL); /* IRQ8 */ #ifdef CONFIG_CACHE_L2X0 - /* Early BRESP enable, Shared attribute override enable, 64K*8way */ - l2x0_init(IOMEM(0xf0100000), 0x40460000, 0x82000fff); + /* Shared attribute override enable, 64K*8way */ + l2x0_init(IOMEM(0xf0100000), 0x00400000, 0xc20f0fff); #endif i2c_register_board_info(0, i2c0_devices, ARRAY_SIZE(i2c0_devices)); diff --git a/arch/arm/mach-shmobile/setup-r8a7778.c b/arch/arm/mach-shmobile/setup-r8a7778.c index 8c02e24f2483..d311ef903b39 100644 --- a/arch/arm/mach-shmobile/setup-r8a7778.c +++ b/arch/arm/mach-shmobile/setup-r8a7778.c @@ -285,10 +285,10 @@ void __init r8a7778_add_dt_devices(void) void __iomem *base = ioremap_nocache(0xf0100000, 0x1000); if (base) { /* - * Early BRESP enable, Shared attribute override enable, 64K*16way + * Shared attribute override enable, 64K*16way * don't call iounmap(base) */ - l2x0_init(base, 0x40470000, 0x82000fff); + l2x0_init(base, 0x00400000, 0xc20f0fff); } #endif diff --git a/arch/arm/mach-shmobile/setup-r8a7779.c b/arch/arm/mach-shmobile/setup-r8a7779.c index d197b5adc886..aba4ed652d54 100644 --- a/arch/arm/mach-shmobile/setup-r8a7779.c +++ b/arch/arm/mach-shmobile/setup-r8a7779.c @@ -660,8 +660,8 @@ static struct platform_device *r8a7779_standard_devices[] __initdata = { void __init r8a7779_add_standard_devices(void) { #ifdef CONFIG_CACHE_L2X0 - /* Early BRESP enable, Shared attribute override enable, 64K*16way */ - l2x0_init(IOMEM(0xf0100000), 0x40470000, 0x82000fff); + /* Shared attribute override enable, 64K*16way */ + l2x0_init(IOMEM(0xf0100000), 0x00400000, 0xc20f0fff); #endif r8a7779_pm_init(); diff --git a/arch/arm/mach-socfpga/socfpga.c b/arch/arm/mach-socfpga/socfpga.c index d86231e11b34..adbf38314ca8 100644 --- a/arch/arm/mach-socfpga/socfpga.c +++ b/arch/arm/mach-socfpga/socfpga.c @@ -98,22 +98,17 @@ static void socfpga_cyclone5_restart(enum reboot_mode mode, const char *cmd) writel(temp, rst_manager_base_addr + SOCFPGA_RSTMGR_CTRL); } -static void __init socfpga_cyclone5_init(void) -{ - l2x0_of_init(0, ~0UL); - of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); -} - static const char *altera_dt_match[] = { "altr,socfpga", NULL }; DT_MACHINE_START(SOCFPGA, "Altera SOCFPGA") + .l2c_aux_val = 0, + .l2c_aux_mask = ~0, .smp = smp_ops(socfpga_smp_ops), .map_io = socfpga_map_io, .init_irq = socfpga_init_irq, - .init_machine = socfpga_cyclone5_init, .restart = socfpga_cyclone5_restart, .dt_compat = altera_dt_match, MACHINE_END diff --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c index c19751fff2c6..fd4297713d67 100644 --- a/arch/arm/mach-spear/platsmp.c +++ b/arch/arm/mach-spear/platsmp.c @@ -20,6 +20,18 @@ #include <mach/spear.h> #include "generic.h" +/* + * Write pen_release in a way that is guaranteed to be visible to all + * observers, irrespective of whether they're taking part in coherency + * or not. This is necessary for the hotplug code to work reliably. + */ +static void write_pen_release(int val) +{ + pen_release = val; + smp_wmb(); + sync_cache_w(&pen_release); +} + static DEFINE_SPINLOCK(boot_lock); static void __iomem *scu_base = IOMEM(VA_SCU_BASE); @@ -30,8 +42,7 @@ static void spear13xx_secondary_init(unsigned int cpu) * let the primary processor know we're out of the * pen, then head off into the C entry point */ - pen_release = -1; - smp_wmb(); + write_pen_release(-1); /* * Synchronise with the boot thread. @@ -58,9 +69,7 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) * Note that "pen_release" is the hardware CPU ID, whereas * "cpu" is Linux's internal ID. */ - pen_release = cpu; - flush_cache_all(); - outer_flush_all(); + write_pen_release(cpu); timeout = jiffies + (1 * HZ); while (time_before(jiffies, timeout)) { diff --git a/arch/arm/mach-spear/spear13xx.c b/arch/arm/mach-spear/spear13xx.c index 7aa6e8cf830f..c9897ea38980 100644 --- a/arch/arm/mach-spear/spear13xx.c +++ b/arch/arm/mach-spear/spear13xx.c @@ -38,15 +38,15 @@ void __init spear13xx_l2x0_init(void) if (!IS_ENABLED(CONFIG_CACHE_L2X0)) return; - writel_relaxed(0x06, VA_L2CC_BASE + L2X0_PREFETCH_CTRL); + writel_relaxed(0x06, VA_L2CC_BASE + L310_PREFETCH_CTRL); /* * Program following latencies in order to make * SPEAr1340 work at 600 MHz */ - writel_relaxed(0x221, VA_L2CC_BASE + L2X0_TAG_LATENCY_CTRL); - writel_relaxed(0x441, VA_L2CC_BASE + L2X0_DATA_LATENCY_CTRL); - l2x0_init(VA_L2CC_BASE, 0x70A60001, 0xfe00ffff); + writel_relaxed(0x221, VA_L2CC_BASE + L310_TAG_LATENCY_CTRL); + writel_relaxed(0x441, VA_L2CC_BASE + L310_DATA_LATENCY_CTRL); + l2x0_init(VA_L2CC_BASE, 0x30a00001, 0xfe0fffff); } /* diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c index df731f2322fa..3cf6ef8d4317 100644 --- a/arch/arm/mach-sti/board-dt.c +++ b/arch/arm/mach-sti/board-dt.c @@ -14,25 +14,6 @@ #include "smp.h" -void __init stih41x_l2x0_init(void) -{ - u32 way_size = 0x4; - u32 aux_ctrl; - /* may be this can be encoded in macros like BIT*() */ - aux_ctrl = (0x1 << L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT) | - (0x1 << L2X0_AUX_CTRL_DATA_PREFETCH_SHIFT) | - (0x1 << L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT) | - (way_size << L2X0_AUX_CTRL_WAY_SIZE_SHIFT); - - l2x0_of_init(aux_ctrl, L2X0_AUX_CTRL_MASK); -} - -static void __init stih41x_machine_init(void) -{ - stih41x_l2x0_init(); - of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); -} - static const char *stih41x_dt_match[] __initdata = { "st,stih415", "st,stih416", @@ -41,7 +22,11 @@ static const char *stih41x_dt_match[] __initdata = { }; DT_MACHINE_START(STM, "STiH415/416 SoC with Flattened Device Tree") - .init_machine = stih41x_machine_init, - .smp = smp_ops(sti_smp_ops), .dt_compat = stih41x_dt_match, + .l2c_aux_val = L2C_AUX_CTRL_SHARED_OVERRIDE | + L310_AUX_CTRL_DATA_PREFETCH | + L310_AUX_CTRL_INSTR_PREFETCH | + L2C_AUX_CTRL_WAY_SIZE(4), + .l2c_aux_mask = 0xc0000fff, + .smp = smp_ops(sti_smp_ops), MACHINE_END diff --git a/arch/arm/mach-tegra/pm.h b/arch/arm/mach-tegra/pm.h index 6e92a7c2ecbd..f4a89698e5b0 100644 --- a/arch/arm/mach-tegra/pm.h +++ b/arch/arm/mach-tegra/pm.h @@ -35,8 +35,6 @@ void tegra20_sleep_core_init(void); void tegra30_lp1_iram_hook(void); void tegra30_sleep_core_init(void); -extern unsigned long l2x0_saved_regs_addr; - void tegra_clear_cpu_in_lp2(void); bool tegra_set_cpu_in_lp2(void); diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S index 8c1ba4fea384..578d4d1ad648 100644 --- a/arch/arm/mach-tegra/reset-handler.S +++ b/arch/arm/mach-tegra/reset-handler.S @@ -19,7 +19,6 @@ #include <asm/cache.h> #include <asm/asm-offsets.h> -#include <asm/hardware/cache-l2x0.h> #include "flowctrl.h" #include "fuse.h" @@ -78,8 +77,10 @@ ENTRY(tegra_resume) str r1, [r0] #endif +#ifdef CONFIG_CACHE_L2X0 /* L2 cache resume & re-enable */ - l2_cache_resume r0, r1, r2, l2x0_saved_regs_addr + bl l2c310_early_resume +#endif end_ca9_scu_l2_resume: mov32 r9, 0xc0f cmp r8, r9 @@ -89,12 +90,6 @@ end_ca9_scu_l2_resume: ENDPROC(tegra_resume) #endif -#ifdef CONFIG_CACHE_L2X0 - .globl l2x0_saved_regs_addr -l2x0_saved_regs_addr: - .long 0 -#endif - .align L1_CACHE_SHIFT ENTRY(__tegra_cpu_reset_handler_start) diff --git a/arch/arm/mach-tegra/sleep.h b/arch/arm/mach-tegra/sleep.h index a4edbb3abd3d..339fe42cd6fb 100644 --- a/arch/arm/mach-tegra/sleep.h +++ b/arch/arm/mach-tegra/sleep.h @@ -120,37 +120,6 @@ mov \tmp1, \tmp1, lsr #8 .endm -/* Macro to resume & re-enable L2 cache */ -#ifndef L2X0_CTRL_EN -#define L2X0_CTRL_EN 1 -#endif - -#ifdef CONFIG_CACHE_L2X0 -.macro l2_cache_resume, tmp1, tmp2, tmp3, phys_l2x0_saved_regs - W(adr) \tmp1, \phys_l2x0_saved_regs - ldr \tmp1, [\tmp1] - ldr \tmp2, [\tmp1, #L2X0_R_PHY_BASE] - ldr \tmp3, [\tmp2, #L2X0_CTRL] - tst \tmp3, #L2X0_CTRL_EN - bne exit_l2_resume - ldr \tmp3, [\tmp1, #L2X0_R_TAG_LATENCY] - str \tmp3, [\tmp2, #L2X0_TAG_LATENCY_CTRL] - ldr \tmp3, [\tmp1, #L2X0_R_DATA_LATENCY] - str \tmp3, [\tmp2, #L2X0_DATA_LATENCY_CTRL] - ldr \tmp3, [\tmp1, #L2X0_R_PREFETCH_CTRL] - str \tmp3, [\tmp2, #L2X0_PREFETCH_CTRL] - ldr \tmp3, [\tmp1, #L2X0_R_PWR_CTRL] - str \tmp3, [\tmp2, #L2X0_POWER_CTRL] - ldr \tmp3, [\tmp1, #L2X0_R_AUX_CTRL] - str \tmp3, [\tmp2, #L2X0_AUX_CTRL] - mov \tmp3, #L2X0_CTRL_EN - str \tmp3, [\tmp2, #L2X0_CTRL] -exit_l2_resume: -.endm -#else /* CONFIG_CACHE_L2X0 */ -.macro l2_cache_resume, tmp1, tmp2, tmp3, phys_l2x0_saved_regs -.endm -#endif /* CONFIG_CACHE_L2X0 */ #else void tegra_pen_lock(void); void tegra_pen_unlock(void); diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c index 6191603379e1..15ac9fcc96b1 100644 --- a/arch/arm/mach-tegra/tegra.c +++ b/arch/arm/mach-tegra/tegra.c @@ -70,40 +70,12 @@ u32 tegra_uart_config[3] = { 0, }; -static void __init tegra_init_cache(void) -{ -#ifdef CONFIG_CACHE_L2X0 - static const struct of_device_id pl310_ids[] __initconst = { - { .compatible = "arm,pl310-cache", }, - {} - }; - - struct device_node *np; - int ret; - void __iomem *p = IO_ADDRESS(TEGRA_ARM_PERIF_BASE) + 0x3000; - u32 aux_ctrl, cache_type; - - np = of_find_matching_node(NULL, pl310_ids); - if (!np) - return; - - cache_type = readl(p + L2X0_CACHE_TYPE); - aux_ctrl = (cache_type & 0x700) << (17-8); - aux_ctrl |= 0x7C400001; - - ret = l2x0_of_init(aux_ctrl, 0x8200c3fe); - if (!ret) - l2x0_saved_regs_addr = virt_to_phys(&l2x0_saved_regs); -#endif -} - static void __init tegra_init_early(void) { of_register_trusted_foundations(); tegra_apb_io_init(); tegra_init_fuse(); tegra_cpu_reset_handler_init(); - tegra_init_cache(); tegra_powergate_init(); tegra_hotplug_init(); } @@ -191,8 +163,10 @@ static const char * const tegra_dt_board_compat[] = { }; DT_MACHINE_START(TEGRA_DT, "NVIDIA Tegra SoC (Flattened Device Tree)") - .map_io = tegra_map_common_io, + .l2c_aux_val = 0x3c400001, + .l2c_aux_mask = 0xc20fc3fe, .smp = smp_ops(tegra_smp_ops), + .map_io = tegra_map_common_io, .init_early = tegra_init_early, .init_irq = tegra_dt_init_irq, .init_machine = tegra_dt_init, diff --git a/arch/arm/mach-ux500/cache-l2x0.c b/arch/arm/mach-ux500/cache-l2x0.c index 264f894c0e3d..842ebedbdd1c 100644 --- a/arch/arm/mach-ux500/cache-l2x0.c +++ b/arch/arm/mach-ux500/cache-l2x0.c @@ -35,10 +35,16 @@ static int __init ux500_l2x0_unlock(void) return 0; } -static int __init ux500_l2x0_init(void) +static void ux500_l2c310_write_sec(unsigned long val, unsigned reg) { - u32 aux_val = 0x3e000000; + /* + * We can't write to secure registers as we are in non-secure + * mode, until we have some SMI service available. + */ +} +static int __init ux500_l2x0_init(void) +{ if (cpu_is_u8500_family() || cpu_is_ux540_family()) l2x0_base = __io_address(U8500_L2CC_BASE); else @@ -48,28 +54,12 @@ static int __init ux500_l2x0_init(void) /* Unlock before init */ ux500_l2x0_unlock(); - /* DBx540's L2 has 128KB way size */ - if (cpu_is_ux540_family()) - /* 128KB way size */ - aux_val |= (0x4 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT); - else - /* 64KB way size */ - aux_val |= (0x3 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT); + outer_cache.write_sec = ux500_l2c310_write_sec; - /* 64KB way size, 8 way associativity, force WA */ if (of_have_populated_dt()) - l2x0_of_init(aux_val, 0xc0000fff); + l2x0_of_init(0, ~0); else - l2x0_init(l2x0_base, aux_val, 0xc0000fff); - - /* - * We can't disable l2 as we are in non secure mode, currently - * this seems be called only during kexec path. So let's - * override outer.disable with nasty assignment until we have - * some SMI service available. - */ - outer_cache.disable = NULL; - outer_cache.set_debug = NULL; + l2x0_init(l2x0_base, 0, ~0); return 0; } diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig index b8ac752fd24b..90249cfc37b3 100644 --- a/arch/arm/mach-vexpress/Kconfig +++ b/arch/arm/mach-vexpress/Kconfig @@ -4,6 +4,7 @@ config ARCH_VEXPRESS select ARCH_SUPPORTS_BIG_ENDIAN select ARM_AMBA select ARM_GIC + select ARM_GLOBAL_TIMER select ARM_TIMER_SP804 select COMMON_CLK_VERSATILE select HAVE_ARM_SCU if SMP diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c index 494d70bfddad..86150d7a2e7d 100644 --- a/arch/arm/mach-vexpress/ct-ca9x4.c +++ b/arch/arm/mach-vexpress/ct-ca9x4.c @@ -45,6 +45,23 @@ static void __init ct_ca9x4_map_io(void) iotable_init(ct_ca9x4_io_desc, ARRAY_SIZE(ct_ca9x4_io_desc)); } +static void __init ca9x4_l2_init(void) +{ +#ifdef CONFIG_CACHE_L2X0 + void __iomem *l2x0_base = ioremap(CT_CA9X4_L2CC, SZ_4K); + + if (l2x0_base) { + /* set RAM latencies to 1 cycle for this core tile. */ + writel(0, l2x0_base + L310_TAG_LATENCY_CTRL); + writel(0, l2x0_base + L310_DATA_LATENCY_CTRL); + + l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff); + } else { + pr_err("L2C: unable to map L2 cache controller\n"); + } +#endif +} + #ifdef CONFIG_HAVE_ARM_TWD static DEFINE_TWD_LOCAL_TIMER(twd_local_timer, A9_MPCORE_TWD, IRQ_LOCALTIMER); @@ -63,6 +80,7 @@ static void __init ct_ca9x4_init_irq(void) gic_init(0, 29, ioremap(A9_MPCORE_GIC_DIST, SZ_4K), ioremap(A9_MPCORE_GIC_CPU, SZ_256)); ca9x4_twd_init(); + ca9x4_l2_init(); } static int ct_ca9x4_clcd_setup(struct clcd_fb *fb) @@ -146,16 +164,6 @@ static void __init ct_ca9x4_init(void) { int i; -#ifdef CONFIG_CACHE_L2X0 - void __iomem *l2x0_base = ioremap(CT_CA9X4_L2CC, SZ_4K); - - /* set RAM latencies to 1 cycle for this core tile. */ - writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL); - writel(0, l2x0_base + L2X0_DATA_LATENCY_CTRL); - - l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff); -#endif - for (i = 0; i < ARRAY_SIZE(ct_ca9x4_amba_devs); i++) amba_device_register(ct_ca9x4_amba_devs[i], &iomem_resource); diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c index 29e7785a54bc..b743a0ae02ce 100644 --- a/arch/arm/mach-vexpress/tc2_pm.c +++ b/arch/arm/mach-vexpress/tc2_pm.c @@ -209,7 +209,7 @@ static int tc2_core_in_reset(unsigned int cpu, unsigned int cluster) #define POLL_MSEC 10 #define TIMEOUT_MSEC 1000 -static int tc2_pm_power_down_finish(unsigned int cpu, unsigned int cluster) +static int tc2_pm_wait_for_powerdown(unsigned int cpu, unsigned int cluster) { unsigned tries; @@ -290,7 +290,7 @@ static void tc2_pm_powered_up(void) static const struct mcpm_platform_ops tc2_pm_power_ops = { .power_up = tc2_pm_power_up, .power_down = tc2_pm_power_down, - .power_down_finish = tc2_pm_power_down_finish, + .wait_for_powerdown = tc2_pm_wait_for_powerdown, .suspend = tc2_pm_suspend, .powered_up = tc2_pm_powered_up, }; diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c index 38f4f6f37770..6ff681a24ba7 100644 --- a/arch/arm/mach-vexpress/v2m.c +++ b/arch/arm/mach-vexpress/v2m.c @@ -372,7 +372,6 @@ MACHINE_END static void __init v2m_dt_init(void) { - l2x0_of_init(0x00400000, 0xfe0fffff); of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); } @@ -383,6 +382,8 @@ static const char * const v2m_dt_match[] __initconst = { DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express") .dt_compat = v2m_dt_match, + .l2c_aux_val = 0x00400000, + .l2c_aux_mask = 0xfe0fffff, .smp = smp_ops(vexpress_smp_dt_ops), .smp_init = smp_init_ops(vexpress_smp_init_ops), .init_machine = v2m_dt_init, diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c index edbd9d83f407..31a6fa40ba37 100644 --- a/arch/arm/mach-zynq/common.c +++ b/arch/arm/mach-zynq/common.c @@ -109,11 +109,6 @@ static void __init zynq_init_machine(void) struct soc_device *soc_dev; struct device *parent = NULL; - /* - * 64KB way size, 8-way associativity, parity disabled - */ - l2x0_of_init(0x02060000, 0xF0F0FFFF); - soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); if (!soc_dev_attr) goto out; @@ -202,6 +197,9 @@ static const char * const zynq_dt_match[] = { }; DT_MACHINE_START(XILINX_EP107, "Xilinx Zynq Platform") + /* 64KB way size, 8-way associativity, parity disabled */ + .l2c_aux_val = 0x02000000, + .l2c_aux_mask = 0xf0ffffff, .smp = smp_ops(zynq_smp_ops), .map_io = zynq_map_io, .init_irq = zynq_irq_init, diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 5bf7c3c3b301..eda0dd0ab97b 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -897,6 +897,57 @@ config CACHE_PL310 This option enables optimisations for the PL310 cache controller. +config PL310_ERRATA_588369 + bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines" + depends on CACHE_L2X0 + help + The PL310 L2 cache controller implements three types of Clean & + Invalidate maintenance operations: by Physical Address + (offset 0x7F0), by Index/Way (0x7F8) and by Way (0x7FC). + They are architecturally defined to behave as the execution of a + clean operation followed immediately by an invalidate operation, + both performing to the same memory location. This functionality + is not correctly implemented in PL310 as clean lines are not + invalidated as a result of these operations. + +config PL310_ERRATA_727915 + bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption" + depends on CACHE_L2X0 + help + PL310 implements the Clean & Invalidate by Way L2 cache maintenance + operation (offset 0x7FC). This operation runs in background so that + PL310 can handle normal accesses while it is in progress. Under very + rare circumstances, due to this erratum, write data can be lost when + PL310 treats a cacheable write transaction during a Clean & + Invalidate by Way operation. + +config PL310_ERRATA_753970 + bool "PL310 errata: cache sync operation may be faulty" + depends on CACHE_PL310 + help + This option enables the workaround for the 753970 PL310 (r3p0) erratum. + + Under some condition the effect of cache sync operation on + the store buffer still remains when the operation completes. + This means that the store buffer is always asked to drain and + this prevents it from merging any further writes. The workaround + is to replace the normal offset of cache sync operation (0x730) + by another offset targeting an unmapped PL310 register 0x740. + This has the same effect as the cache sync operation: store buffer + drain and waiting for all buffers empty. + +config PL310_ERRATA_769419 + bool "PL310 errata: no automatic Store Buffer drain" + depends on CACHE_L2X0 + help + On revisions of the PL310 prior to r3p2, the Store Buffer does + not automatically drain. This can cause normal, non-cacheable + writes to be retained when the memory system is idle, leading + to suboptimal I/O performance for drivers using coherent DMA. + This option adds a write barrier to the cpu_idle loop so that, + on systems with an outer cache, the store buffer is drained + explicitly. + config CACHE_TAUROS2 bool "Enable the Tauros2 L2 cache controller" depends on (ARCH_DOVE || ARCH_MMP || CPU_PJ4) diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 7f39ce2f841f..91da64de440f 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -95,7 +95,8 @@ obj-$(CONFIG_CPU_V7M) += proc-v7m.o AFLAGS_proc-v6.o :=-Wa,-march=armv6 AFLAGS_proc-v7.o :=-Wa,-march=armv7-a +obj-$(CONFIG_OUTER_CACHE) += l2c-common.o obj-$(CONFIG_CACHE_FEROCEON_L2) += cache-feroceon-l2.o -obj-$(CONFIG_CACHE_L2X0) += cache-l2x0.o +obj-$(CONFIG_CACHE_L2X0) += cache-l2x0.o l2c-l2x0-resume.o obj-$(CONFIG_CACHE_XSC3L2) += cache-xsc3l2.o obj-$(CONFIG_CACHE_TAUROS2) += cache-tauros2.o diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 924036473b16..b8cb1a2688a0 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -28,6 +28,7 @@ #include <asm/opcodes.h> #include "fault.h" +#include "mm.h" /* * 32-bit misaligned trap handler (c) 1998 San Mehat (CCC) -July 1998 @@ -81,6 +82,7 @@ static unsigned long ai_word; static unsigned long ai_dword; static unsigned long ai_multi; static int ai_usermode; +static unsigned long cr_no_alignment; core_param(alignment, ai_usermode, int, 0600); @@ -91,7 +93,7 @@ core_param(alignment, ai_usermode, int, 0600); /* Return true if and only if the ARMv6 unaligned access model is in use. */ static bool cpu_is_v6_unaligned(void) { - return cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U); + return cpu_architecture() >= CPU_ARCH_ARMv6 && get_cr() & CR_U; } static int safe_usermode(int new_usermode, bool warn) @@ -949,6 +951,13 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; } +static int __init noalign_setup(char *__unused) +{ + set_cr(__clear_cr(CR_A)); + return 1; +} +__setup("noalign", noalign_setup); + /* * This needs to be done after sysctl_init, otherwise sys/ will be * overwritten. Actually, this shouldn't be in sys/ at all since @@ -966,14 +975,12 @@ static int __init alignment_init(void) return -ENOMEM; #endif -#ifdef CONFIG_CPU_CP15 if (cpu_is_v6_unaligned()) { - cr_alignment &= ~CR_A; - cr_no_alignment &= ~CR_A; - set_cr(cr_alignment); + set_cr(__clear_cr(CR_A)); ai_usermode = safe_usermode(ai_usermode, false); } -#endif + + cr_no_alignment = get_cr() & ~CR_A; hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN, "alignment exception"); diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index dc814a548056..e028a7f2ebcc 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -350,7 +350,6 @@ void __init feroceon_l2_init(int __l2_wt_override) outer_cache.inv_range = feroceon_l2_inv_range; outer_cache.clean_range = feroceon_l2_clean_range; outer_cache.flush_range = feroceon_l2_flush_range; - outer_cache.inv_all = l2_inv_all; enable_l2(); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 7abde2ce8973..efc5cabf70e0 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -16,18 +16,33 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/cpu.h> #include <linux/err.h> #include <linux/init.h> +#include <linux/smp.h> #include <linux/spinlock.h> #include <linux/io.h> #include <linux/of.h> #include <linux/of_address.h> #include <asm/cacheflush.h> +#include <asm/cp15.h> +#include <asm/cputype.h> #include <asm/hardware/cache-l2x0.h> #include "cache-tauros3.h" #include "cache-aurora-l2.h" +struct l2c_init_data { + const char *type; + unsigned way_size_0; + unsigned num_lock; + void (*of_parse)(const struct device_node *, u32 *, u32 *); + void (*enable)(void __iomem *, u32, unsigned); + void (*fixup)(void __iomem *, u32, struct outer_cache_fns *); + void (*save)(void __iomem *); + struct outer_cache_fns outer_cache; +}; + #define CACHE_LINE_SIZE 32 static void __iomem *l2x0_base; @@ -36,96 +51,116 @@ static u32 l2x0_way_mask; /* Bitmask of active ways */ static u32 l2x0_size; static unsigned long sync_reg_offset = L2X0_CACHE_SYNC; -/* Aurora don't have the cache ID register available, so we have to - * pass it though the device tree */ -static u32 cache_id_part_number_from_dt; - struct l2x0_regs l2x0_saved_regs; -struct l2x0_of_data { - void (*setup)(const struct device_node *, u32 *, u32 *); - void (*save)(void); - struct outer_cache_fns outer_cache; -}; - -static bool of_init = false; - -static inline void cache_wait_way(void __iomem *reg, unsigned long mask) +/* + * Common code for all cache controllers. + */ +static inline void l2c_wait_mask(void __iomem *reg, unsigned long mask) { /* wait for cache operation by line or way to complete */ while (readl_relaxed(reg) & mask) cpu_relax(); } -#ifdef CONFIG_CACHE_PL310 -static inline void cache_wait(void __iomem *reg, unsigned long mask) +/* + * By default, we write directly to secure registers. Platforms must + * override this if they are running non-secure. + */ +static void l2c_write_sec(unsigned long val, void __iomem *base, unsigned reg) { - /* cache operations by line are atomic on PL310 */ + if (val == readl_relaxed(base + reg)) + return; + if (outer_cache.write_sec) + outer_cache.write_sec(val, reg); + else + writel_relaxed(val, base + reg); } -#else -#define cache_wait cache_wait_way -#endif -static inline void cache_sync(void) +/* + * This should only be called when we have a requirement that the + * register be written due to a work-around, as platforms running + * in non-secure mode may not be able to access this register. + */ +static inline void l2c_set_debug(void __iomem *base, unsigned long val) { - void __iomem *base = l2x0_base; - - writel_relaxed(0, base + sync_reg_offset); - cache_wait(base + L2X0_CACHE_SYNC, 1); + l2c_write_sec(val, base, L2X0_DEBUG_CTRL); } -static inline void l2x0_clean_line(unsigned long addr) +static void __l2c_op_way(void __iomem *reg) { - void __iomem *base = l2x0_base; - cache_wait(base + L2X0_CLEAN_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(l2x0_way_mask, reg); + l2c_wait_mask(reg, l2x0_way_mask); } -static inline void l2x0_inv_line(unsigned long addr) +static inline void l2c_unlock(void __iomem *base, unsigned num) { - void __iomem *base = l2x0_base; - cache_wait(base + L2X0_INV_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_INV_LINE_PA); + unsigned i; + + for (i = 0; i < num; i++) { + writel_relaxed(0, base + L2X0_LOCKDOWN_WAY_D_BASE + + i * L2X0_LOCKDOWN_STRIDE); + writel_relaxed(0, base + L2X0_LOCKDOWN_WAY_I_BASE + + i * L2X0_LOCKDOWN_STRIDE); + } } -#if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915) -static inline void debug_writel(unsigned long val) +/* + * Enable the L2 cache controller. This function must only be + * called when the cache controller is known to be disabled. + */ +static void l2c_enable(void __iomem *base, u32 aux, unsigned num_lock) { - if (outer_cache.set_debug) - outer_cache.set_debug(val); + unsigned long flags; + + l2c_write_sec(aux, base, L2X0_AUX_CTRL); + + l2c_unlock(base, num_lock); + + local_irq_save(flags); + __l2c_op_way(base + L2X0_INV_WAY); + writel_relaxed(0, base + sync_reg_offset); + l2c_wait_mask(base + sync_reg_offset, 1); + local_irq_restore(flags); + + l2c_write_sec(L2X0_CTRL_EN, base, L2X0_CTRL); } -static void pl310_set_debug(unsigned long val) +static void l2c_disable(void) { - writel_relaxed(val, l2x0_base + L2X0_DEBUG_CTRL); + void __iomem *base = l2x0_base; + + outer_cache.flush_all(); + l2c_write_sec(0, base, L2X0_CTRL); + dsb(st); } -#else -/* Optimised out for non-errata case */ -static inline void debug_writel(unsigned long val) + +#ifdef CONFIG_CACHE_PL310 +static inline void cache_wait(void __iomem *reg, unsigned long mask) { + /* cache operations by line are atomic on PL310 */ } - -#define pl310_set_debug NULL +#else +#define cache_wait l2c_wait_mask #endif -#ifdef CONFIG_PL310_ERRATA_588369 -static inline void l2x0_flush_line(unsigned long addr) +static inline void cache_sync(void) { void __iomem *base = l2x0_base; - /* Clean by PA followed by Invalidate by PA */ - cache_wait(base + L2X0_CLEAN_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA); - cache_wait(base + L2X0_INV_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_INV_LINE_PA); + writel_relaxed(0, base + sync_reg_offset); + cache_wait(base + L2X0_CACHE_SYNC, 1); } -#else -static inline void l2x0_flush_line(unsigned long addr) +#if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915) +static inline void debug_writel(unsigned long val) +{ + l2c_set_debug(l2x0_base, val); +} +#else +/* Optimised out for non-errata case */ +static inline void debug_writel(unsigned long val) { - void __iomem *base = l2x0_base; - cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_CLEAN_INV_LINE_PA); } #endif @@ -141,8 +176,7 @@ static void l2x0_cache_sync(void) static void __l2x0_flush_all(void) { debug_writel(0x03); - writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY); - cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask); + __l2c_op_way(l2x0_base + L2X0_CLEAN_INV_WAY); cache_sync(); debug_writel(0x00); } @@ -157,275 +191,883 @@ static void l2x0_flush_all(void) raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_clean_all(void) +static void l2x0_disable(void) { unsigned long flags; - /* clean all ways */ raw_spin_lock_irqsave(&l2x0_lock, flags); - writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_WAY); - cache_wait_way(l2x0_base + L2X0_CLEAN_WAY, l2x0_way_mask); - cache_sync(); + __l2x0_flush_all(); + l2c_write_sec(0, l2x0_base, L2X0_CTRL); + dsb(st); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_inv_all(void) +static void l2c_save(void __iomem *base) { - unsigned long flags; + l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); +} - /* invalidate all ways */ - raw_spin_lock_irqsave(&l2x0_lock, flags); - /* Invalidating when L2 is enabled is a nono */ - BUG_ON(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN); - writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY); - cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask); - cache_sync(); - raw_spin_unlock_irqrestore(&l2x0_lock, flags); +/* + * L2C-210 specific code. + * + * The L2C-2x0 PA, set/way and sync operations are atomic, but we must + * ensure that no background operation is running. The way operations + * are all background tasks. + * + * While a background operation is in progress, any new operation is + * ignored (unspecified whether this causes an error.) Thankfully, not + * used on SMP. + * + * Never has a different sync register other than L2X0_CACHE_SYNC, but + * we use sync_reg_offset here so we can share some of this with L2C-310. + */ +static void __l2c210_cache_sync(void __iomem *base) +{ + writel_relaxed(0, base + sync_reg_offset); } -static void l2x0_inv_range(unsigned long start, unsigned long end) +static void __l2c210_op_pa_range(void __iomem *reg, unsigned long start, + unsigned long end) +{ + while (start < end) { + writel_relaxed(start, reg); + start += CACHE_LINE_SIZE; + } +} + +static void l2c210_inv_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; - unsigned long flags; - raw_spin_lock_irqsave(&l2x0_lock, flags); if (start & (CACHE_LINE_SIZE - 1)) { start &= ~(CACHE_LINE_SIZE - 1); - debug_writel(0x03); - l2x0_flush_line(start); - debug_writel(0x00); + writel_relaxed(start, base + L2X0_CLEAN_INV_LINE_PA); start += CACHE_LINE_SIZE; } if (end & (CACHE_LINE_SIZE - 1)) { end &= ~(CACHE_LINE_SIZE - 1); - debug_writel(0x03); - l2x0_flush_line(end); - debug_writel(0x00); + writel_relaxed(end, base + L2X0_CLEAN_INV_LINE_PA); } + __l2c210_op_pa_range(base + L2X0_INV_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c210_clean_range(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + + start &= ~(CACHE_LINE_SIZE - 1); + __l2c210_op_pa_range(base + L2X0_CLEAN_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c210_flush_range(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + + start &= ~(CACHE_LINE_SIZE - 1); + __l2c210_op_pa_range(base + L2X0_CLEAN_INV_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c210_flush_all(void) +{ + void __iomem *base = l2x0_base; + + BUG_ON(!irqs_disabled()); + + __l2c_op_way(base + L2X0_CLEAN_INV_WAY); + __l2c210_cache_sync(base); +} + +static void l2c210_sync(void) +{ + __l2c210_cache_sync(l2x0_base); +} + +static void l2c210_resume(void) +{ + void __iomem *base = l2x0_base; + + if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) + l2c_enable(base, l2x0_saved_regs.aux_ctrl, 1); +} + +static const struct l2c_init_data l2c210_data __initconst = { + .type = "L2C-210", + .way_size_0 = SZ_8K, + .num_lock = 1, + .enable = l2c_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c_disable, + .sync = l2c210_sync, + .resume = l2c210_resume, + }, +}; + +/* + * L2C-220 specific code. + * + * All operations are background operations: they have to be waited for. + * Conflicting requests generate a slave error (which will cause an + * imprecise abort.) Never uses sync_reg_offset, so we hard-code the + * sync register here. + * + * However, we can re-use the l2c210_resume call. + */ +static inline void __l2c220_cache_sync(void __iomem *base) +{ + writel_relaxed(0, base + L2X0_CACHE_SYNC); + l2c_wait_mask(base + L2X0_CACHE_SYNC, 1); +} + +static void l2c220_op_way(void __iomem *base, unsigned reg) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&l2x0_lock, flags); + __l2c_op_way(base + reg); + __l2c220_cache_sync(base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static unsigned long l2c220_op_pa_range(void __iomem *reg, unsigned long start, + unsigned long end, unsigned long flags) +{ + raw_spinlock_t *lock = &l2x0_lock; + while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); while (start < blk_end) { - l2x0_inv_line(start); + l2c_wait_mask(reg, 1); + writel_relaxed(start, reg); start += CACHE_LINE_SIZE; } if (blk_end < end) { - raw_spin_unlock_irqrestore(&l2x0_lock, flags); - raw_spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(lock, flags); + raw_spin_lock_irqsave(lock, flags); } } - cache_wait(base + L2X0_INV_LINE_PA, 1); - cache_sync(); - raw_spin_unlock_irqrestore(&l2x0_lock, flags); + + return flags; } -static void l2x0_clean_range(unsigned long start, unsigned long end) +static void l2c220_inv_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; unsigned long flags; - if ((end - start) >= l2x0_size) { - l2x0_clean_all(); - return; - } - raw_spin_lock_irqsave(&l2x0_lock, flags); - start &= ~(CACHE_LINE_SIZE - 1); - while (start < end) { - unsigned long blk_end = start + min(end - start, 4096UL); - - while (start < blk_end) { - l2x0_clean_line(start); + if ((start | end) & (CACHE_LINE_SIZE - 1)) { + if (start & (CACHE_LINE_SIZE - 1)) { + start &= ~(CACHE_LINE_SIZE - 1); + writel_relaxed(start, base + L2X0_CLEAN_INV_LINE_PA); start += CACHE_LINE_SIZE; } - if (blk_end < end) { - raw_spin_unlock_irqrestore(&l2x0_lock, flags); - raw_spin_lock_irqsave(&l2x0_lock, flags); + if (end & (CACHE_LINE_SIZE - 1)) { + end &= ~(CACHE_LINE_SIZE - 1); + l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1); + writel_relaxed(end, base + L2X0_CLEAN_INV_LINE_PA); } } - cache_wait(base + L2X0_CLEAN_LINE_PA, 1); - cache_sync(); + + flags = l2c220_op_pa_range(base + L2X0_INV_LINE_PA, + start, end, flags); + l2c_wait_mask(base + L2X0_INV_LINE_PA, 1); + __l2c220_cache_sync(base); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_flush_range(unsigned long start, unsigned long end) +static void l2c220_clean_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; unsigned long flags; + start &= ~(CACHE_LINE_SIZE - 1); if ((end - start) >= l2x0_size) { - l2x0_flush_all(); + l2c220_op_way(base, L2X0_CLEAN_WAY); return; } raw_spin_lock_irqsave(&l2x0_lock, flags); + flags = l2c220_op_pa_range(base + L2X0_CLEAN_LINE_PA, + start, end, flags); + l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1); + __l2c220_cache_sync(base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2c220_flush_range(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + unsigned long flags; + start &= ~(CACHE_LINE_SIZE - 1); + if ((end - start) >= l2x0_size) { + l2c220_op_way(base, L2X0_CLEAN_INV_WAY); + return; + } + + raw_spin_lock_irqsave(&l2x0_lock, flags); + flags = l2c220_op_pa_range(base + L2X0_CLEAN_INV_LINE_PA, + start, end, flags); + l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1); + __l2c220_cache_sync(base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2c220_flush_all(void) +{ + l2c220_op_way(l2x0_base, L2X0_CLEAN_INV_WAY); +} + +static void l2c220_sync(void) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&l2x0_lock, flags); + __l2c220_cache_sync(l2x0_base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2c220_enable(void __iomem *base, u32 aux, unsigned num_lock) +{ + /* + * Always enable non-secure access to the lockdown registers - + * we write to them as part of the L2C enable sequence so they + * need to be accessible. + */ + aux |= L220_AUX_CTRL_NS_LOCKDOWN; + + l2c_enable(base, aux, num_lock); +} + +static const struct l2c_init_data l2c220_data = { + .type = "L2C-220", + .way_size_0 = SZ_8K, + .num_lock = 1, + .enable = l2c220_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c220_inv_range, + .clean_range = l2c220_clean_range, + .flush_range = l2c220_flush_range, + .flush_all = l2c220_flush_all, + .disable = l2c_disable, + .sync = l2c220_sync, + .resume = l2c210_resume, + }, +}; + +/* + * L2C-310 specific code. + * + * Very similar to L2C-210, the PA, set/way and sync operations are atomic, + * and the way operations are all background tasks. However, issuing an + * operation while a background operation is in progress results in a + * SLVERR response. We can reuse: + * + * __l2c210_cache_sync (using sync_reg_offset) + * l2c210_sync + * l2c210_inv_range (if 588369 is not applicable) + * l2c210_clean_range + * l2c210_flush_range (if 588369 is not applicable) + * l2c210_flush_all (if 727915 is not applicable) + * + * Errata: + * 588369: PL310 R0P0->R1P0, fixed R2P0. + * Affects: all clean+invalidate operations + * clean and invalidate skips the invalidate step, so we need to issue + * separate operations. We also require the above debug workaround + * enclosing this code fragment on affected parts. On unaffected parts, + * we must not use this workaround without the debug register writes + * to avoid exposing a problem similar to 727915. + * + * 727915: PL310 R2P0->R3P0, fixed R3P1. + * Affects: clean+invalidate by way + * clean and invalidate by way runs in the background, and a store can + * hit the line between the clean operation and invalidate operation, + * resulting in the store being lost. + * + * 752271: PL310 R3P0->R3P1-50REL0, fixed R3P2. + * Affects: 8x64-bit (double fill) line fetches + * double fill line fetches can fail to cause dirty data to be evicted + * from the cache before the new data overwrites the second line. + * + * 753970: PL310 R3P0, fixed R3P1. + * Affects: sync + * prevents merging writes after the sync operation, until another L2C + * operation is performed (or a number of other conditions.) + * + * 769419: PL310 R0P0->R3P1, fixed R3P2. + * Affects: store buffer + * store buffer is not automatically drained. + */ +static void l2c310_inv_range_erratum(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + + if ((start | end) & (CACHE_LINE_SIZE - 1)) { + unsigned long flags; + + /* Erratum 588369 for both clean+invalidate operations */ + raw_spin_lock_irqsave(&l2x0_lock, flags); + l2c_set_debug(base, 0x03); + + if (start & (CACHE_LINE_SIZE - 1)) { + start &= ~(CACHE_LINE_SIZE - 1); + writel_relaxed(start, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(start, base + L2X0_INV_LINE_PA); + start += CACHE_LINE_SIZE; + } + + if (end & (CACHE_LINE_SIZE - 1)) { + end &= ~(CACHE_LINE_SIZE - 1); + writel_relaxed(end, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(end, base + L2X0_INV_LINE_PA); + } + + l2c_set_debug(base, 0x00); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); + } + + __l2c210_op_pa_range(base + L2X0_INV_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c310_flush_range_erratum(unsigned long start, unsigned long end) +{ + raw_spinlock_t *lock = &l2x0_lock; + unsigned long flags; + void __iomem *base = l2x0_base; + + raw_spin_lock_irqsave(lock, flags); while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); - debug_writel(0x03); + l2c_set_debug(base, 0x03); while (start < blk_end) { - l2x0_flush_line(start); + writel_relaxed(start, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(start, base + L2X0_INV_LINE_PA); start += CACHE_LINE_SIZE; } - debug_writel(0x00); + l2c_set_debug(base, 0x00); if (blk_end < end) { - raw_spin_unlock_irqrestore(&l2x0_lock, flags); - raw_spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(lock, flags); + raw_spin_lock_irqsave(lock, flags); } } - cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); - cache_sync(); - raw_spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(lock, flags); + __l2c210_cache_sync(base); } -static void l2x0_disable(void) +static void l2c310_flush_all_erratum(void) { + void __iomem *base = l2x0_base; unsigned long flags; raw_spin_lock_irqsave(&l2x0_lock, flags); - __l2x0_flush_all(); - writel_relaxed(0, l2x0_base + L2X0_CTRL); - dsb(st); + l2c_set_debug(base, 0x03); + __l2c_op_way(base + L2X0_CLEAN_INV_WAY); + l2c_set_debug(base, 0x00); + __l2c210_cache_sync(base); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_unlock(u32 cache_id) +static void __init l2c310_save(void __iomem *base) { - int lockregs; - int i; + unsigned revision; - switch (cache_id & L2X0_CACHE_ID_PART_MASK) { - case L2X0_CACHE_ID_PART_L310: - lockregs = 8; - break; - case AURORA_CACHE_ID: - lockregs = 4; + l2c_save(base); + + l2x0_saved_regs.tag_latency = readl_relaxed(base + + L310_TAG_LATENCY_CTRL); + l2x0_saved_regs.data_latency = readl_relaxed(base + + L310_DATA_LATENCY_CTRL); + l2x0_saved_regs.filter_end = readl_relaxed(base + + L310_ADDR_FILTER_END); + l2x0_saved_regs.filter_start = readl_relaxed(base + + L310_ADDR_FILTER_START); + + revision = readl_relaxed(base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + /* From r2p0, there is Prefetch offset/control register */ + if (revision >= L310_CACHE_ID_RTL_R2P0) + l2x0_saved_regs.prefetch_ctrl = readl_relaxed(base + + L310_PREFETCH_CTRL); + + /* From r3p0, there is Power control register */ + if (revision >= L310_CACHE_ID_RTL_R3P0) + l2x0_saved_regs.pwr_ctrl = readl_relaxed(base + + L310_POWER_CTRL); +} + +static void l2c310_resume(void) +{ + void __iomem *base = l2x0_base; + + if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) { + unsigned revision; + + /* restore pl310 setup */ + writel_relaxed(l2x0_saved_regs.tag_latency, + base + L310_TAG_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.data_latency, + base + L310_DATA_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.filter_end, + base + L310_ADDR_FILTER_END); + writel_relaxed(l2x0_saved_regs.filter_start, + base + L310_ADDR_FILTER_START); + + revision = readl_relaxed(base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + if (revision >= L310_CACHE_ID_RTL_R2P0) + l2c_write_sec(l2x0_saved_regs.prefetch_ctrl, base, + L310_PREFETCH_CTRL); + if (revision >= L310_CACHE_ID_RTL_R3P0) + l2c_write_sec(l2x0_saved_regs.pwr_ctrl, base, + L310_POWER_CTRL); + + l2c_enable(base, l2x0_saved_regs.aux_ctrl, 8); + + /* Re-enable full-line-of-zeros for Cortex-A9 */ + if (l2x0_saved_regs.aux_ctrl & L310_AUX_CTRL_FULL_LINE_ZERO) + set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1)); + } +} + +static int l2c310_cpu_enable_flz(struct notifier_block *nb, unsigned long act, void *data) +{ + switch (act & ~CPU_TASKS_FROZEN) { + case CPU_STARTING: + set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1)); break; - default: - /* L210 and unknown types */ - lockregs = 1; + case CPU_DYING: + set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1))); break; } + return NOTIFY_OK; +} - for (i = 0; i < lockregs; i++) { - writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE + - i * L2X0_LOCKDOWN_STRIDE); - writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE + - i * L2X0_LOCKDOWN_STRIDE); +static void __init l2c310_enable(void __iomem *base, u32 aux, unsigned num_lock) +{ + unsigned rev = readl_relaxed(base + L2X0_CACHE_ID) & L2X0_CACHE_ID_PART_MASK; + bool cortex_a9 = read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9; + + if (rev >= L310_CACHE_ID_RTL_R2P0) { + if (cortex_a9) { + aux |= L310_AUX_CTRL_EARLY_BRESP; + pr_info("L2C-310 enabling early BRESP for Cortex-A9\n"); + } else if (aux & L310_AUX_CTRL_EARLY_BRESP) { + pr_warn("L2C-310 early BRESP only supported with Cortex-A9\n"); + aux &= ~L310_AUX_CTRL_EARLY_BRESP; + } + } + + if (cortex_a9) { + u32 aux_cur = readl_relaxed(base + L2X0_AUX_CTRL); + u32 acr = get_auxcr(); + + pr_debug("Cortex-A9 ACR=0x%08x\n", acr); + + if (acr & BIT(3) && !(aux_cur & L310_AUX_CTRL_FULL_LINE_ZERO)) + pr_err("L2C-310: full line of zeros enabled in Cortex-A9 but not L2C-310 - invalid\n"); + + if (aux & L310_AUX_CTRL_FULL_LINE_ZERO && !(acr & BIT(3))) + pr_err("L2C-310: enabling full line of zeros but not enabled in Cortex-A9\n"); + + if (!(aux & L310_AUX_CTRL_FULL_LINE_ZERO) && !outer_cache.write_sec) { + aux |= L310_AUX_CTRL_FULL_LINE_ZERO; + pr_info("L2C-310 full line of zeros enabled for Cortex-A9\n"); + } + } else if (aux & (L310_AUX_CTRL_FULL_LINE_ZERO | L310_AUX_CTRL_EARLY_BRESP)) { + pr_err("L2C-310: disabling Cortex-A9 specific feature bits\n"); + aux &= ~(L310_AUX_CTRL_FULL_LINE_ZERO | L310_AUX_CTRL_EARLY_BRESP); + } + + if (aux & (L310_AUX_CTRL_DATA_PREFETCH | L310_AUX_CTRL_INSTR_PREFETCH)) { + u32 prefetch = readl_relaxed(base + L310_PREFETCH_CTRL); + + pr_info("L2C-310 %s%s prefetch enabled, offset %u lines\n", + aux & L310_AUX_CTRL_INSTR_PREFETCH ? "I" : "", + aux & L310_AUX_CTRL_DATA_PREFETCH ? "D" : "", + 1 + (prefetch & L310_PREFETCH_CTRL_OFFSET_MASK)); + } + + /* r3p0 or later has power control register */ + if (rev >= L310_CACHE_ID_RTL_R3P0) { + u32 power_ctrl; + + l2c_write_sec(L310_DYNAMIC_CLK_GATING_EN | L310_STNDBY_MODE_EN, + base, L310_POWER_CTRL); + power_ctrl = readl_relaxed(base + L310_POWER_CTRL); + pr_info("L2C-310 dynamic clock gating %sabled, standby mode %sabled\n", + power_ctrl & L310_DYNAMIC_CLK_GATING_EN ? "en" : "dis", + power_ctrl & L310_STNDBY_MODE_EN ? "en" : "dis"); + } + + /* + * Always enable non-secure access to the lockdown registers - + * we write to them as part of the L2C enable sequence so they + * need to be accessible. + */ + aux |= L310_AUX_CTRL_NS_LOCKDOWN; + + l2c_enable(base, aux, num_lock); + + if (aux & L310_AUX_CTRL_FULL_LINE_ZERO) { + set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1)); + cpu_notifier(l2c310_cpu_enable_flz, 0); } } -void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) +static void __init l2c310_fixup(void __iomem *base, u32 cache_id, + struct outer_cache_fns *fns) { - u32 aux; - u32 cache_id; - u32 way_size = 0; - int ways; - int way_size_shift = L2X0_WAY_SIZE_SHIFT; - const char *type; + unsigned revision = cache_id & L2X0_CACHE_ID_RTL_MASK; + const char *errata[8]; + unsigned n = 0; + + if (IS_ENABLED(CONFIG_PL310_ERRATA_588369) && + revision < L310_CACHE_ID_RTL_R2P0 && + /* For bcm compatibility */ + fns->inv_range == l2c210_inv_range) { + fns->inv_range = l2c310_inv_range_erratum; + fns->flush_range = l2c310_flush_range_erratum; + errata[n++] = "588369"; + } - l2x0_base = base; - if (cache_id_part_number_from_dt) - cache_id = cache_id_part_number_from_dt; - else - cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID); - aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); + if (IS_ENABLED(CONFIG_PL310_ERRATA_727915) && + revision >= L310_CACHE_ID_RTL_R2P0 && + revision < L310_CACHE_ID_RTL_R3P1) { + fns->flush_all = l2c310_flush_all_erratum; + errata[n++] = "727915"; + } + + if (revision >= L310_CACHE_ID_RTL_R3P0 && + revision < L310_CACHE_ID_RTL_R3P2) { + u32 val = readl_relaxed(base + L310_PREFETCH_CTRL); + /* I don't think bit23 is required here... but iMX6 does so */ + if (val & (BIT(30) | BIT(23))) { + val &= ~(BIT(30) | BIT(23)); + l2c_write_sec(val, base, L310_PREFETCH_CTRL); + errata[n++] = "752271"; + } + } + + if (IS_ENABLED(CONFIG_PL310_ERRATA_753970) && + revision == L310_CACHE_ID_RTL_R3P0) { + sync_reg_offset = L2X0_DUMMY_REG; + errata[n++] = "753970"; + } + + if (IS_ENABLED(CONFIG_PL310_ERRATA_769419)) + errata[n++] = "769419"; + + if (n) { + unsigned i; + pr_info("L2C-310 errat%s", n > 1 ? "a" : "um"); + for (i = 0; i < n; i++) + pr_cont(" %s", errata[i]); + pr_cont(" enabled\n"); + } +} + +static void l2c310_disable(void) +{ + /* + * If full-line-of-zeros is enabled, we must first disable it in the + * Cortex-A9 auxiliary control register before disabling the L2 cache. + */ + if (l2x0_saved_regs.aux_ctrl & L310_AUX_CTRL_FULL_LINE_ZERO) + set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1))); + + l2c_disable(); +} + +static const struct l2c_init_data l2c310_init_fns __initconst = { + .type = "L2C-310", + .way_size_0 = SZ_8K, + .num_lock = 8, + .enable = l2c310_enable, + .fixup = l2c310_fixup, + .save = l2c310_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .sync = l2c210_sync, + .resume = l2c310_resume, + }, +}; + +static void __init __l2c_init(const struct l2c_init_data *data, + u32 aux_val, u32 aux_mask, u32 cache_id) +{ + struct outer_cache_fns fns; + unsigned way_size_bits, ways; + u32 aux, old_aux; + + /* + * Sanity check the aux values. aux_mask is the bits we preserve + * from reading the hardware register, and aux_val is the bits we + * set. + */ + if (aux_val & aux_mask) + pr_alert("L2C: platform provided aux values permit register corruption.\n"); + + old_aux = aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); aux &= aux_mask; aux |= aux_val; + if (old_aux != aux) + pr_warn("L2C: DT/platform modifies aux control register: 0x%08x -> 0x%08x\n", + old_aux, aux); + /* Determine the number of ways */ switch (cache_id & L2X0_CACHE_ID_PART_MASK) { case L2X0_CACHE_ID_PART_L310: + if ((aux_val | ~aux_mask) & (L2C_AUX_CTRL_WAY_SIZE_MASK | L310_AUX_CTRL_ASSOCIATIVITY_16)) + pr_warn("L2C: DT/platform tries to modify or specify cache size\n"); if (aux & (1 << 16)) ways = 16; else ways = 8; - type = "L310"; -#ifdef CONFIG_PL310_ERRATA_753970 - /* Unmapped register. */ - sync_reg_offset = L2X0_DUMMY_REG; -#endif - if ((cache_id & L2X0_CACHE_ID_RTL_MASK) <= L2X0_CACHE_ID_RTL_R3P0) - outer_cache.set_debug = pl310_set_debug; break; + case L2X0_CACHE_ID_PART_L210: + case L2X0_CACHE_ID_PART_L220: ways = (aux >> 13) & 0xf; - type = "L210"; break; case AURORA_CACHE_ID: - sync_reg_offset = AURORA_SYNC_REG; ways = (aux >> 13) & 0xf; ways = 2 << ((ways + 1) >> 2); - way_size_shift = AURORA_WAY_SIZE_SHIFT; - type = "Aurora"; break; + default: /* Assume unknown chips have 8 ways */ ways = 8; - type = "L2x0 series"; break; } l2x0_way_mask = (1 << ways) - 1; /* - * L2 cache Size = Way size * Number of ways + * way_size_0 is the size that a way_size value of zero would be + * given the calculation: way_size = way_size_0 << way_size_bits. + * So, if way_size_bits=0 is reserved, but way_size_bits=1 is 16k, + * then way_size_0 would be 8k. + * + * L2 cache size = number of ways * way size. */ - way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17; - way_size = 1 << (way_size + way_size_shift); + way_size_bits = (aux & L2C_AUX_CTRL_WAY_SIZE_MASK) >> + L2C_AUX_CTRL_WAY_SIZE_SHIFT; + l2x0_size = ways * (data->way_size_0 << way_size_bits); - l2x0_size = ways * way_size * SZ_1K; + fns = data->outer_cache; + fns.write_sec = outer_cache.write_sec; + if (data->fixup) + data->fixup(l2x0_base, cache_id, &fns); /* - * Check if l2x0 controller is already enabled. - * If you are booting from non-secure mode - * accessing the below registers will fault. + * Check if l2x0 controller is already enabled. If we are booting + * in non-secure mode accessing the below registers will fault. */ - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - /* Make sure that I&D is not locked down when starting */ - l2x0_unlock(cache_id); + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) + data->enable(l2x0_base, aux, data->num_lock); - /* l2x0 controller is disabled */ - writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); + outer_cache = fns; - l2x0_inv_all(); - - /* enable L2X0 */ - writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL); - } + /* + * It is strange to save the register state before initialisation, + * but hey, this is what the DT implementations decided to do. + */ + if (data->save) + data->save(l2x0_base); /* Re-read it in case some bits are reserved. */ aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); - /* Save the value for resuming. */ - l2x0_saved_regs.aux_ctrl = aux; + pr_info("%s cache controller enabled, %d ways, %d kB\n", + data->type, ways, l2x0_size >> 10); + pr_info("%s: CACHE_ID 0x%08x, AUX_CTRL 0x%08x\n", + data->type, cache_id, aux); +} + +void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) +{ + const struct l2c_init_data *data; + u32 cache_id; + + l2x0_base = base; + + cache_id = readl_relaxed(base + L2X0_CACHE_ID); + + switch (cache_id & L2X0_CACHE_ID_PART_MASK) { + default: + case L2X0_CACHE_ID_PART_L210: + data = &l2c210_data; + break; - if (!of_init) { - outer_cache.inv_range = l2x0_inv_range; - outer_cache.clean_range = l2x0_clean_range; - outer_cache.flush_range = l2x0_flush_range; - outer_cache.sync = l2x0_cache_sync; - outer_cache.flush_all = l2x0_flush_all; - outer_cache.inv_all = l2x0_inv_all; - outer_cache.disable = l2x0_disable; + case L2X0_CACHE_ID_PART_L220: + data = &l2c220_data; + break; + + case L2X0_CACHE_ID_PART_L310: + data = &l2c310_init_fns; + break; } - pr_info("%s cache controller enabled\n", type); - pr_info("l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d kB\n", - ways, cache_id, aux, l2x0_size >> 10); + __l2c_init(data, aux_val, aux_mask, cache_id); } #ifdef CONFIG_OF static int l2_wt_override; +/* Aurora don't have the cache ID register available, so we have to + * pass it though the device tree */ +static u32 cache_id_part_number_from_dt; + +static void __init l2x0_of_parse(const struct device_node *np, + u32 *aux_val, u32 *aux_mask) +{ + u32 data[2] = { 0, 0 }; + u32 tag = 0; + u32 dirty = 0; + u32 val = 0, mask = 0; + + of_property_read_u32(np, "arm,tag-latency", &tag); + if (tag) { + mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK; + val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT; + } + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1]) { + mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK | + L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK; + val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) | + ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT); + } + + of_property_read_u32(np, "arm,dirty-latency", &dirty); + if (dirty) { + mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK; + val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT; + } + + *aux_val &= ~mask; + *aux_val |= val; + *aux_mask &= ~mask; +} + +static const struct l2c_init_data of_l2c210_data __initconst = { + .type = "L2C-210", + .way_size_0 = SZ_8K, + .num_lock = 1, + .of_parse = l2x0_of_parse, + .enable = l2c_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c_disable, + .sync = l2c210_sync, + .resume = l2c210_resume, + }, +}; + +static const struct l2c_init_data of_l2c220_data __initconst = { + .type = "L2C-220", + .way_size_0 = SZ_8K, + .num_lock = 1, + .of_parse = l2x0_of_parse, + .enable = l2c220_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c220_inv_range, + .clean_range = l2c220_clean_range, + .flush_range = l2c220_flush_range, + .flush_all = l2c220_flush_all, + .disable = l2c_disable, + .sync = l2c220_sync, + .resume = l2c210_resume, + }, +}; + +static void __init l2c310_of_parse(const struct device_node *np, + u32 *aux_val, u32 *aux_mask) +{ + u32 data[3] = { 0, 0, 0 }; + u32 tag[3] = { 0, 0, 0 }; + u32 filter[2] = { 0, 0 }; + + of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag)); + if (tag[0] && tag[1] && tag[2]) + writel_relaxed( + L310_LATENCY_CTRL_RD(tag[0] - 1) | + L310_LATENCY_CTRL_WR(tag[1] - 1) | + L310_LATENCY_CTRL_SETUP(tag[2] - 1), + l2x0_base + L310_TAG_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1] && data[2]) + writel_relaxed( + L310_LATENCY_CTRL_RD(data[0] - 1) | + L310_LATENCY_CTRL_WR(data[1] - 1) | + L310_LATENCY_CTRL_SETUP(data[2] - 1), + l2x0_base + L310_DATA_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,filter-ranges", + filter, ARRAY_SIZE(filter)); + if (filter[1]) { + writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M), + l2x0_base + L310_ADDR_FILTER_END); + writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L310_ADDR_FILTER_EN, + l2x0_base + L310_ADDR_FILTER_START); + } +} + +static const struct l2c_init_data of_l2c310_data __initconst = { + .type = "L2C-310", + .way_size_0 = SZ_8K, + .num_lock = 8, + .of_parse = l2c310_of_parse, + .enable = l2c310_enable, + .fixup = l2c310_fixup, + .save = l2c310_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .sync = l2c210_sync, + .resume = l2c310_resume, + }, +}; + /* * Note that the end addresses passed to Linux primitives are * noninclusive, while the hardware cache range operations use @@ -524,6 +1166,100 @@ static void aurora_flush_range(unsigned long start, unsigned long end) } } +static void aurora_save(void __iomem *base) +{ + l2x0_saved_regs.ctrl = readl_relaxed(base + L2X0_CTRL); + l2x0_saved_regs.aux_ctrl = readl_relaxed(base + L2X0_AUX_CTRL); +} + +static void aurora_resume(void) +{ + void __iomem *base = l2x0_base; + + if (!(readl(base + L2X0_CTRL) & L2X0_CTRL_EN)) { + writel_relaxed(l2x0_saved_regs.aux_ctrl, base + L2X0_AUX_CTRL); + writel_relaxed(l2x0_saved_regs.ctrl, base + L2X0_CTRL); + } +} + +/* + * For Aurora cache in no outer mode, enable via the CP15 coprocessor + * broadcasting of cache commands to L2. + */ +static void __init aurora_enable_no_outer(void __iomem *base, u32 aux, + unsigned num_lock) +{ + u32 u; + + asm volatile("mrc p15, 1, %0, c15, c2, 0" : "=r" (u)); + u |= AURORA_CTRL_FW; /* Set the FW bit */ + asm volatile("mcr p15, 1, %0, c15, c2, 0" : : "r" (u)); + + isb(); + + l2c_enable(base, aux, num_lock); +} + +static void __init aurora_fixup(void __iomem *base, u32 cache_id, + struct outer_cache_fns *fns) +{ + sync_reg_offset = AURORA_SYNC_REG; +} + +static void __init aurora_of_parse(const struct device_node *np, + u32 *aux_val, u32 *aux_mask) +{ + u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU; + u32 mask = AURORA_ACR_REPLACEMENT_MASK; + + of_property_read_u32(np, "cache-id-part", + &cache_id_part_number_from_dt); + + /* Determine and save the write policy */ + l2_wt_override = of_property_read_bool(np, "wt-override"); + + if (l2_wt_override) { + val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY; + mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK; + } + + *aux_val &= ~mask; + *aux_val |= val; + *aux_mask &= ~mask; +} + +static const struct l2c_init_data of_aurora_with_outer_data __initconst = { + .type = "Aurora", + .way_size_0 = SZ_4K, + .num_lock = 4, + .of_parse = aurora_of_parse, + .enable = l2c_enable, + .fixup = aurora_fixup, + .save = aurora_save, + .outer_cache = { + .inv_range = aurora_inv_range, + .clean_range = aurora_clean_range, + .flush_range = aurora_flush_range, + .flush_all = l2x0_flush_all, + .disable = l2x0_disable, + .sync = l2x0_cache_sync, + .resume = aurora_resume, + }, +}; + +static const struct l2c_init_data of_aurora_no_outer_data __initconst = { + .type = "Aurora", + .way_size_0 = SZ_4K, + .num_lock = 4, + .of_parse = aurora_of_parse, + .enable = aurora_enable_no_outer, + .fixup = aurora_fixup, + .save = aurora_save, + .outer_cache = { + .resume = aurora_resume, + }, +}; + /* * For certain Broadcom SoCs, depending on the address range, different offsets * need to be added to the address before passing it to L2 for @@ -588,16 +1324,16 @@ static void bcm_inv_range(unsigned long start, unsigned long end) /* normal case, no cross section between start and end */ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) { - l2x0_inv_range(new_start, new_end); + l2c210_inv_range(new_start, new_end); return; } /* They cross sections, so it can only be a cross from section * 2 to section 3 */ - l2x0_inv_range(new_start, + l2c210_inv_range(new_start, bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1)); - l2x0_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), + l2c210_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), new_end); } @@ -610,26 +1346,21 @@ static void bcm_clean_range(unsigned long start, unsigned long end) if (unlikely(end <= start)) return; - if ((end - start) >= l2x0_size) { - l2x0_clean_all(); - return; - } - new_start = bcm_l2_phys_addr(start); new_end = bcm_l2_phys_addr(end); /* normal case, no cross section between start and end */ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) { - l2x0_clean_range(new_start, new_end); + l2c210_clean_range(new_start, new_end); return; } /* They cross sections, so it can only be a cross from section * 2 to section 3 */ - l2x0_clean_range(new_start, + l2c210_clean_range(new_start, bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1)); - l2x0_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), + l2c210_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), new_end); } @@ -643,7 +1374,7 @@ static void bcm_flush_range(unsigned long start, unsigned long end) return; if ((end - start) >= l2x0_size) { - l2x0_flush_all(); + outer_cache.flush_all(); return; } @@ -652,283 +1383,67 @@ static void bcm_flush_range(unsigned long start, unsigned long end) /* normal case, no cross section between start and end */ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) { - l2x0_flush_range(new_start, new_end); + l2c210_flush_range(new_start, new_end); return; } /* They cross sections, so it can only be a cross from section * 2 to section 3 */ - l2x0_flush_range(new_start, + l2c210_flush_range(new_start, bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1)); - l2x0_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), + l2c210_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), new_end); } -static void __init l2x0_of_setup(const struct device_node *np, - u32 *aux_val, u32 *aux_mask) -{ - u32 data[2] = { 0, 0 }; - u32 tag = 0; - u32 dirty = 0; - u32 val = 0, mask = 0; - - of_property_read_u32(np, "arm,tag-latency", &tag); - if (tag) { - mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK; - val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT; - } - - of_property_read_u32_array(np, "arm,data-latency", - data, ARRAY_SIZE(data)); - if (data[0] && data[1]) { - mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK | - L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK; - val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) | - ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT); - } - - of_property_read_u32(np, "arm,dirty-latency", &dirty); - if (dirty) { - mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK; - val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT; - } - - *aux_val &= ~mask; - *aux_val |= val; - *aux_mask &= ~mask; -} - -static void __init pl310_of_setup(const struct device_node *np, - u32 *aux_val, u32 *aux_mask) -{ - u32 data[3] = { 0, 0, 0 }; - u32 tag[3] = { 0, 0, 0 }; - u32 filter[2] = { 0, 0 }; - - of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag)); - if (tag[0] && tag[1] && tag[2]) - writel_relaxed( - ((tag[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | - ((tag[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | - ((tag[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), - l2x0_base + L2X0_TAG_LATENCY_CTRL); - - of_property_read_u32_array(np, "arm,data-latency", - data, ARRAY_SIZE(data)); - if (data[0] && data[1] && data[2]) - writel_relaxed( - ((data[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | - ((data[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | - ((data[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), - l2x0_base + L2X0_DATA_LATENCY_CTRL); - - of_property_read_u32_array(np, "arm,filter-ranges", - filter, ARRAY_SIZE(filter)); - if (filter[1]) { - writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M), - l2x0_base + L2X0_ADDR_FILTER_END); - writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L2X0_ADDR_FILTER_EN, - l2x0_base + L2X0_ADDR_FILTER_START); - } -} - -static void __init pl310_save(void) -{ - u32 l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & - L2X0_CACHE_ID_RTL_MASK; - - l2x0_saved_regs.tag_latency = readl_relaxed(l2x0_base + - L2X0_TAG_LATENCY_CTRL); - l2x0_saved_regs.data_latency = readl_relaxed(l2x0_base + - L2X0_DATA_LATENCY_CTRL); - l2x0_saved_regs.filter_end = readl_relaxed(l2x0_base + - L2X0_ADDR_FILTER_END); - l2x0_saved_regs.filter_start = readl_relaxed(l2x0_base + - L2X0_ADDR_FILTER_START); - - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { - /* - * From r2p0, there is Prefetch offset/control register - */ - l2x0_saved_regs.prefetch_ctrl = readl_relaxed(l2x0_base + - L2X0_PREFETCH_CTRL); - /* - * From r3p0, there is Power control register - */ - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) - l2x0_saved_regs.pwr_ctrl = readl_relaxed(l2x0_base + - L2X0_POWER_CTRL); - } -} +/* Broadcom L2C-310 start from ARMs R3P2 or later, and require no fixups */ +static const struct l2c_init_data of_bcm_l2x0_data __initconst = { + .type = "BCM-L2C-310", + .way_size_0 = SZ_8K, + .num_lock = 8, + .of_parse = l2c310_of_parse, + .enable = l2c310_enable, + .save = l2c310_save, + .outer_cache = { + .inv_range = bcm_inv_range, + .clean_range = bcm_clean_range, + .flush_range = bcm_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .sync = l2c210_sync, + .resume = l2c310_resume, + }, +}; -static void aurora_save(void) +static void __init tauros3_save(void __iomem *base) { - l2x0_saved_regs.ctrl = readl_relaxed(l2x0_base + L2X0_CTRL); - l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); -} + l2c_save(base); -static void __init tauros3_save(void) -{ l2x0_saved_regs.aux2_ctrl = - readl_relaxed(l2x0_base + TAUROS3_AUX2_CTRL); + readl_relaxed(base + TAUROS3_AUX2_CTRL); l2x0_saved_regs.prefetch_ctrl = - readl_relaxed(l2x0_base + L2X0_PREFETCH_CTRL); -} - -static void l2x0_resume(void) -{ - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - /* restore aux ctrl and enable l2 */ - l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID)); - - writel_relaxed(l2x0_saved_regs.aux_ctrl, l2x0_base + - L2X0_AUX_CTRL); - - l2x0_inv_all(); - - writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL); - } -} - -static void pl310_resume(void) -{ - u32 l2x0_revision; - - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - /* restore pl310 setup */ - writel_relaxed(l2x0_saved_regs.tag_latency, - l2x0_base + L2X0_TAG_LATENCY_CTRL); - writel_relaxed(l2x0_saved_regs.data_latency, - l2x0_base + L2X0_DATA_LATENCY_CTRL); - writel_relaxed(l2x0_saved_regs.filter_end, - l2x0_base + L2X0_ADDR_FILTER_END); - writel_relaxed(l2x0_saved_regs.filter_start, - l2x0_base + L2X0_ADDR_FILTER_START); - - l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & - L2X0_CACHE_ID_RTL_MASK; - - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { - writel_relaxed(l2x0_saved_regs.prefetch_ctrl, - l2x0_base + L2X0_PREFETCH_CTRL); - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) - writel_relaxed(l2x0_saved_regs.pwr_ctrl, - l2x0_base + L2X0_POWER_CTRL); - } - } - - l2x0_resume(); -} - -static void aurora_resume(void) -{ - if (!(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - writel_relaxed(l2x0_saved_regs.aux_ctrl, - l2x0_base + L2X0_AUX_CTRL); - writel_relaxed(l2x0_saved_regs.ctrl, l2x0_base + L2X0_CTRL); - } + readl_relaxed(base + L310_PREFETCH_CTRL); } static void tauros3_resume(void) { - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { + void __iomem *base = l2x0_base; + + if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) { writel_relaxed(l2x0_saved_regs.aux2_ctrl, - l2x0_base + TAUROS3_AUX2_CTRL); + base + TAUROS3_AUX2_CTRL); writel_relaxed(l2x0_saved_regs.prefetch_ctrl, - l2x0_base + L2X0_PREFETCH_CTRL); - } + base + L310_PREFETCH_CTRL); - l2x0_resume(); -} - -static void __init aurora_broadcast_l2_commands(void) -{ - __u32 u; - /* Enable Broadcasting of cache commands to L2*/ - __asm__ __volatile__("mrc p15, 1, %0, c15, c2, 0" : "=r"(u)); - u |= AURORA_CTRL_FW; /* Set the FW bit */ - __asm__ __volatile__("mcr p15, 1, %0, c15, c2, 0\n" : : "r"(u)); - isb(); -} - -static void __init aurora_of_setup(const struct device_node *np, - u32 *aux_val, u32 *aux_mask) -{ - u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU; - u32 mask = AURORA_ACR_REPLACEMENT_MASK; - - of_property_read_u32(np, "cache-id-part", - &cache_id_part_number_from_dt); - - /* Determine and save the write policy */ - l2_wt_override = of_property_read_bool(np, "wt-override"); - - if (l2_wt_override) { - val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY; - mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK; + l2c_enable(base, l2x0_saved_regs.aux_ctrl, 8); } - - *aux_val &= ~mask; - *aux_val |= val; - *aux_mask &= ~mask; } -static const struct l2x0_of_data pl310_data = { - .setup = pl310_of_setup, - .save = pl310_save, - .outer_cache = { - .resume = pl310_resume, - .inv_range = l2x0_inv_range, - .clean_range = l2x0_clean_range, - .flush_range = l2x0_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - -static const struct l2x0_of_data l2x0_data = { - .setup = l2x0_of_setup, - .save = NULL, - .outer_cache = { - .resume = l2x0_resume, - .inv_range = l2x0_inv_range, - .clean_range = l2x0_clean_range, - .flush_range = l2x0_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - -static const struct l2x0_of_data aurora_with_outer_data = { - .setup = aurora_of_setup, - .save = aurora_save, - .outer_cache = { - .resume = aurora_resume, - .inv_range = aurora_inv_range, - .clean_range = aurora_clean_range, - .flush_range = aurora_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - -static const struct l2x0_of_data aurora_no_outer_data = { - .setup = aurora_of_setup, - .save = aurora_save, - .outer_cache = { - .resume = aurora_resume, - }, -}; - -static const struct l2x0_of_data tauros3_data = { - .setup = NULL, +static const struct l2c_init_data of_tauros3_data __initconst = { + .type = "Tauros3", + .way_size_0 = SZ_8K, + .num_lock = 8, + .enable = l2c_enable, .save = tauros3_save, /* Tauros3 broadcasts L1 cache operations to L2 */ .outer_cache = { @@ -936,43 +1451,26 @@ static const struct l2x0_of_data tauros3_data = { }, }; -static const struct l2x0_of_data bcm_l2x0_data = { - .setup = pl310_of_setup, - .save = pl310_save, - .outer_cache = { - .resume = pl310_resume, - .inv_range = bcm_inv_range, - .clean_range = bcm_clean_range, - .flush_range = bcm_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - +#define L2C_ID(name, fns) { .compatible = name, .data = (void *)&fns } static const struct of_device_id l2x0_ids[] __initconst = { - { .compatible = "arm,l210-cache", .data = (void *)&l2x0_data }, - { .compatible = "arm,l220-cache", .data = (void *)&l2x0_data }, - { .compatible = "arm,pl310-cache", .data = (void *)&pl310_data }, - { .compatible = "bcm,bcm11351-a2-pl310-cache", /* deprecated name */ - .data = (void *)&bcm_l2x0_data}, - { .compatible = "brcm,bcm11351-a2-pl310-cache", - .data = (void *)&bcm_l2x0_data}, - { .compatible = "marvell,aurora-outer-cache", - .data = (void *)&aurora_with_outer_data}, - { .compatible = "marvell,aurora-system-cache", - .data = (void *)&aurora_no_outer_data}, - { .compatible = "marvell,tauros3-cache", - .data = (void *)&tauros3_data }, + L2C_ID("arm,l210-cache", of_l2c210_data), + L2C_ID("arm,l220-cache", of_l2c220_data), + L2C_ID("arm,pl310-cache", of_l2c310_data), + L2C_ID("brcm,bcm11351-a2-pl310-cache", of_bcm_l2x0_data), + L2C_ID("marvell,aurora-outer-cache", of_aurora_with_outer_data), + L2C_ID("marvell,aurora-system-cache", of_aurora_no_outer_data), + L2C_ID("marvell,tauros3-cache", of_tauros3_data), + /* Deprecated IDs */ + L2C_ID("bcm,bcm11351-a2-pl310-cache", of_bcm_l2x0_data), {} }; int __init l2x0_of_init(u32 aux_val, u32 aux_mask) { + const struct l2c_init_data *data; struct device_node *np; - const struct l2x0_of_data *data; struct resource res; + u32 cache_id, old_aux; np = of_find_matching_node(NULL, l2x0_ids); if (!np) @@ -989,23 +1487,29 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask) data = of_match_node(l2x0_ids, np)->data; - /* L2 configuration can only be changed if the cache is disabled */ - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - if (data->setup) - data->setup(np, &aux_val, &aux_mask); - - /* For aurora cache in no outer mode select the - * correct mode using the coprocessor*/ - if (data == &aurora_no_outer_data) - aurora_broadcast_l2_commands(); + old_aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); + if (old_aux != ((old_aux & aux_mask) | aux_val)) { + pr_warn("L2C: platform modifies aux control register: 0x%08x -> 0x%08x\n", + old_aux, (old_aux & aux_mask) | aux_val); + } else if (aux_mask != ~0U && aux_val != 0) { + pr_alert("L2C: platform provided aux values match the hardware, so have no effect. Please remove them.\n"); } - if (data->save) - data->save(); + /* All L2 caches are unified, so this property should be specified */ + if (!of_property_read_bool(np, "cache-unified")) + pr_err("L2C: device tree omits to specify unified cache\n"); + + /* L2 configuration can only be changed if the cache is disabled */ + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) + if (data->of_parse) + data->of_parse(np, &aux_val, &aux_mask); + + if (cache_id_part_number_from_dt) + cache_id = cache_id_part_number_from_dt; + else + cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID); - of_init = true; - memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache)); - l2x0_init(l2x0_base, aux_val, aux_mask); + __l2c_init(data, aux_val, aux_mask, cache_id); return 0; } diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 778bcf88ee79..615c99e38ba1 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -59,7 +59,7 @@ ENTRY(v7_invalidate_l1) bgt 2b cmp r2, #0 bgt 1b - dsb + dsb st isb mov pc, lr ENDPROC(v7_invalidate_l1) @@ -166,7 +166,7 @@ skip: finished: mov r10, #0 @ swith back to cache level 0 mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr - dsb + dsb st isb mov pc, lr ENDPROC(v7_flush_dcache_all) @@ -335,7 +335,7 @@ ENTRY(v7_flush_kern_dcache_area) add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_flush_kern_dcache_area) @@ -368,7 +368,7 @@ v7_dma_inv_range: add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_dma_inv_range) @@ -390,7 +390,7 @@ v7_dma_clean_range: add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_dma_clean_range) @@ -412,7 +412,7 @@ ENTRY(v7_dma_flush_range) add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_dma_flush_range) diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 5bef858568e6..4c88935654ca 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -885,7 +885,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { - unsigned long paddr; + phys_addr_t paddr; dma_cache_maint_page(page, off, size, dir, dmac_map_area); @@ -901,14 +901,15 @@ static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { - unsigned long paddr = page_to_phys(page) + off; + phys_addr_t paddr = page_to_phys(page) + off; /* FIXME: non-speculating: not required */ - /* don't bother invalidating if DMA to device */ - if (dir != DMA_TO_DEVICE) + /* in any case, don't bother invalidating if DMA to device */ + if (dir != DMA_TO_DEVICE) { outer_inv_range(paddr, paddr + size); - dma_cache_maint_page(page, off, size, dir, dmac_unmap_area); + dma_cache_maint_page(page, off, size, dir, dmac_unmap_area); + } /* * Mark the D-cache clean for these pages to avoid extra flushing. diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 3387e60e4ea3..43d54f5b26b9 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -104,17 +104,20 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig #define flush_icache_alias(pfn,vaddr,len) do { } while (0) #endif +#define FLAG_PA_IS_EXEC 1 +#define FLAG_PA_CORE_IN_MM 2 + static void flush_ptrace_access_other(void *args) { __flush_icache_all(); } -static -void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, - unsigned long uaddr, void *kaddr, unsigned long len) +static inline +void __flush_ptrace_access(struct page *page, unsigned long uaddr, void *kaddr, + unsigned long len, unsigned int flags) { if (cache_is_vivt()) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { + if (flags & FLAG_PA_CORE_IN_MM) { unsigned long addr = (unsigned long)kaddr; __cpuc_coherent_kern_range(addr, addr + len); } @@ -128,7 +131,7 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, } /* VIPT non-aliasing D-cache */ - if (vma->vm_flags & VM_EXEC) { + if (flags & FLAG_PA_IS_EXEC) { unsigned long addr = (unsigned long)kaddr; if (icache_is_vipt_aliasing()) flush_icache_alias(page_to_pfn(page), uaddr, len); @@ -140,6 +143,26 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, } } +static +void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, + unsigned long uaddr, void *kaddr, unsigned long len) +{ + unsigned int flags = 0; + if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) + flags |= FLAG_PA_CORE_IN_MM; + if (vma->vm_flags & VM_EXEC) + flags |= FLAG_PA_IS_EXEC; + __flush_ptrace_access(page, uaddr, kaddr, len, flags); +} + +void flush_uprobe_xol_access(struct page *page, unsigned long uaddr, + void *kaddr, unsigned long len) +{ + unsigned int flags = FLAG_PA_CORE_IN_MM|FLAG_PA_IS_EXEC; + + __flush_ptrace_access(page, uaddr, kaddr, len, flags); +} + /* * Copy user data from/to a page which is mapped into a different * processes address space. Really, we want to allow our "user diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index 21b9e1bf9b77..45aeaaca9052 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -18,6 +18,21 @@ #include <asm/tlbflush.h> #include "mm.h" +pte_t *fixmap_page_table; + +static inline void set_fixmap_pte(int idx, pte_t pte) +{ + unsigned long vaddr = __fix_to_virt(idx); + set_pte_ext(fixmap_page_table + idx, pte, 0); + local_flush_tlb_kernel_page(vaddr); +} + +static inline pte_t get_fixmap_pte(unsigned long vaddr) +{ + unsigned long idx = __virt_to_fix(vaddr); + return *(fixmap_page_table + idx); +} + void *kmap(struct page *page) { might_sleep(); @@ -63,20 +78,20 @@ void *kmap_atomic(struct page *page) type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + vaddr = __fix_to_virt(idx); #ifdef CONFIG_DEBUG_HIGHMEM /* * With debugging enabled, kunmap_atomic forces that entry to 0. * Make sure it was indeed properly unmapped. */ - BUG_ON(!pte_none(get_top_pte(vaddr))); + BUG_ON(!pte_none(*(fixmap_page_table + idx))); #endif /* * When debugging is off, kunmap_atomic leaves the previous mapping * in place, so the contained TLB flush ensures the TLB is updated * with the new mapping. */ - set_top_pte(vaddr, mk_pte(page, kmap_prot)); + set_fixmap_pte(idx, mk_pte(page, kmap_prot)); return (void *)vaddr; } @@ -94,8 +109,8 @@ void __kunmap_atomic(void *kvaddr) if (cache_is_vivt()) __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); #ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); - set_top_pte(vaddr, __pte(0)); + BUG_ON(vaddr != __fix_to_virt(idx)); + set_fixmap_pte(idx, __pte(0)); #else (void) idx; /* to kill a warning */ #endif @@ -117,11 +132,11 @@ void *kmap_atomic_pfn(unsigned long pfn) type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + vaddr = __fix_to_virt(idx); #ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(!pte_none(get_top_pte(vaddr))); + BUG_ON(!pte_none(*(fixmap_page_table + idx))); #endif - set_top_pte(vaddr, pfn_pte(pfn, kmap_prot)); + set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); return (void *)vaddr; } @@ -133,5 +148,5 @@ struct page *kmap_atomic_to_page(const void *ptr) if (vaddr < FIXADDR_START) return virt_to_page(ptr); - return pte_page(get_top_pte(vaddr)); + return pte_page(get_fixmap_pte(vaddr)); } diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index 54ee6163c181..66781bf34077 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -56,8 +56,3 @@ int pmd_huge(pmd_t pmd) { return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } - -int pmd_huge_support(void) -{ - return 1; -} diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 2a77ba8796ae..659c75d808dc 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -23,6 +23,7 @@ #include <linux/dma-contiguous.h> #include <linux/sizes.h> +#include <asm/cp15.h> #include <asm/mach-types.h> #include <asm/memblock.h> #include <asm/prom.h> @@ -36,6 +37,14 @@ #include "mm.h" +#ifdef CONFIG_CPU_CP15_MMU +unsigned long __init __clear_cr(unsigned long mask) +{ + cr_alignment = cr_alignment & ~mask; + return cr_alignment; +} +#endif + static phys_addr_t phys_initrd_start __initdata = 0; static unsigned long phys_initrd_size __initdata = 0; @@ -81,24 +90,21 @@ __tagtable(ATAG_INITRD2, parse_tag_initrd2); * initialization functions, as well as show_mem() for the skipping * of holes in the memory map. It is populated by arm_add_memory(). */ -struct meminfo meminfo; - void show_mem(unsigned int filter) { int free = 0, total = 0, reserved = 0; - int shared = 0, cached = 0, slab = 0, i; - struct meminfo * mi = &meminfo; + int shared = 0, cached = 0, slab = 0; + struct memblock_region *reg; printk("Mem-info:\n"); show_free_areas(filter); - for_each_bank (i, mi) { - struct membank *bank = &mi->bank[i]; + for_each_memblock (memory, reg) { unsigned int pfn1, pfn2; struct page *page, *end; - pfn1 = bank_pfn_start(bank); - pfn2 = bank_pfn_end(bank); + pfn1 = memblock_region_memory_base_pfn(reg); + pfn2 = memblock_region_memory_end_pfn(reg); page = pfn_to_page(pfn1); end = pfn_to_page(pfn2 - 1) + 1; @@ -115,8 +121,9 @@ void show_mem(unsigned int filter) free++; else shared += page_count(page) - 1; - page++; - } while (page < end); + pfn1++; + page = pfn_to_page(pfn1); + } while (pfn1 < pfn2); } printk("%d pages of RAM\n", total); @@ -130,16 +137,9 @@ void show_mem(unsigned int filter) static void __init find_limits(unsigned long *min, unsigned long *max_low, unsigned long *max_high) { - struct meminfo *mi = &meminfo; - int i; - - /* This assumes the meminfo array is properly sorted */ - *min = bank_pfn_start(&mi->bank[0]); - for_each_bank (i, mi) - if (mi->bank[i].highmem) - break; - *max_low = bank_pfn_end(&mi->bank[i - 1]); - *max_high = bank_pfn_end(&mi->bank[mi->nr_banks - 1]); + *max_low = PFN_DOWN(memblock_get_current_limit()); + *min = PFN_UP(memblock_start_of_DRAM()); + *max_high = PFN_DOWN(memblock_end_of_DRAM()); } #ifdef CONFIG_ZONE_DMA @@ -274,14 +274,8 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align) return phys; } -void __init arm_memblock_init(struct meminfo *mi, - const struct machine_desc *mdesc) +void __init arm_memblock_init(const struct machine_desc *mdesc) { - int i; - - for (i = 0; i < mi->nr_banks; i++) - memblock_add(mi->bank[i].start, mi->bank[i].size); - /* Register the kernel text, kernel data and initrd with memblock. */ #ifdef CONFIG_XIP_KERNEL memblock_reserve(__pa(_sdata), _end - _sdata); @@ -317,7 +311,6 @@ void __init arm_memblock_init(struct meminfo *mi, #endif arm_mm_memblock_reserve(); - arm_dt_memblock_reserve(); /* reserve any platform specific memblock areas */ if (mdesc->reserve) @@ -413,54 +406,53 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn) /* * The mem_map array can get very big. Free the unused area of the memory map. */ -static void __init free_unused_memmap(struct meminfo *mi) +static void __init free_unused_memmap(void) { - unsigned long bank_start, prev_bank_end = 0; - unsigned int i; + unsigned long start, prev_end = 0; + struct memblock_region *reg; /* * This relies on each bank being in address order. * The banks are sorted previously in bootmem_init(). */ - for_each_bank(i, mi) { - struct membank *bank = &mi->bank[i]; - - bank_start = bank_pfn_start(bank); + for_each_memblock(memory, reg) { + start = memblock_region_memory_base_pfn(reg); #ifdef CONFIG_SPARSEMEM /* * Take care not to free memmap entries that don't exist * due to SPARSEMEM sections which aren't present. */ - bank_start = min(bank_start, - ALIGN(prev_bank_end, PAGES_PER_SECTION)); + start = min(start, + ALIGN(prev_end, PAGES_PER_SECTION)); #else /* * Align down here since the VM subsystem insists that the * memmap entries are valid from the bank start aligned to * MAX_ORDER_NR_PAGES. */ - bank_start = round_down(bank_start, MAX_ORDER_NR_PAGES); + start = round_down(start, MAX_ORDER_NR_PAGES); #endif /* * If we had a previous bank, and there is a space * between the current bank and the previous, free it. */ - if (prev_bank_end && prev_bank_end < bank_start) - free_memmap(prev_bank_end, bank_start); + if (prev_end && prev_end < start) + free_memmap(prev_end, start); /* * Align up here since the VM subsystem insists that the * memmap entries are valid from the bank end aligned to * MAX_ORDER_NR_PAGES. */ - prev_bank_end = ALIGN(bank_pfn_end(bank), MAX_ORDER_NR_PAGES); + prev_end = ALIGN(memblock_region_memory_end_pfn(reg), + MAX_ORDER_NR_PAGES); } #ifdef CONFIG_SPARSEMEM - if (!IS_ALIGNED(prev_bank_end, PAGES_PER_SECTION)) - free_memmap(prev_bank_end, - ALIGN(prev_bank_end, PAGES_PER_SECTION)); + if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) + free_memmap(prev_end, + ALIGN(prev_end, PAGES_PER_SECTION)); #endif } @@ -536,7 +528,7 @@ void __init mem_init(void) set_max_mapnr(pfn_to_page(max_pfn) - mem_map); /* this will put all unused low memory onto the freelists */ - free_unused_memmap(&meminfo); + free_unused_memmap(); free_all_bootmem(); #ifdef CONFIG_SA1111 diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index f9c32ba73544..d1e5ad7ab3bc 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -438,6 +438,13 @@ void __arm_iounmap(volatile void __iomem *io_addr) EXPORT_SYMBOL(__arm_iounmap); #ifdef CONFIG_PCI +static int pci_ioremap_mem_type = MT_DEVICE; + +void pci_ioremap_set_mem_type(int mem_type) +{ + pci_ioremap_mem_type = mem_type; +} + int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr) { BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT); @@ -445,7 +452,7 @@ int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr) return ioremap_page_range(PCI_IO_VIRT_BASE + offset, PCI_IO_VIRT_BASE + offset + SZ_64K, phys_addr, - __pgprot(get_mem_type(MT_DEVICE)->prot_pte)); + __pgprot(get_mem_type(pci_ioremap_mem_type)->prot_pte)); } EXPORT_SYMBOL_GPL(pci_ioremap_io); #endif diff --git a/arch/arm/mm/l2c-common.c b/arch/arm/mm/l2c-common.c new file mode 100644 index 000000000000..10a3cf28c362 --- /dev/null +++ b/arch/arm/mm/l2c-common.c @@ -0,0 +1,20 @@ +/* + * Copyright (C) 2010 ARM Ltd. + * Written by Catalin Marinas <catalin.marinas@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/bug.h> +#include <linux/smp.h> +#include <asm/outercache.h> + +void outer_disable(void) +{ + WARN_ON(!irqs_disabled()); + WARN_ON(num_online_cpus() > 1); + + if (outer_cache.disable) + outer_cache.disable(); +} diff --git a/arch/arm/mm/l2c-l2x0-resume.S b/arch/arm/mm/l2c-l2x0-resume.S new file mode 100644 index 000000000000..99b05f21a59a --- /dev/null +++ b/arch/arm/mm/l2c-l2x0-resume.S @@ -0,0 +1,58 @@ +/* + * L2C-310 early resume code. This can be used by platforms to restore + * the settings of their L2 cache controller before restoring the + * processor state. + * + * This code can only be used to if you are running in the secure world. + */ +#include <linux/linkage.h> +#include <asm/hardware/cache-l2x0.h> + + .text + +ENTRY(l2c310_early_resume) + adr r0, 1f + ldr r2, [r0] + add r0, r2, r0 + + ldmia r0, {r1, r2, r3, r4, r5, r6, r7, r8} + @ r1 = phys address of L2C-310 controller + @ r2 = aux_ctrl + @ r3 = tag_latency + @ r4 = data_latency + @ r5 = filter_start + @ r6 = filter_end + @ r7 = prefetch_ctrl + @ r8 = pwr_ctrl + + @ Check that the address has been initialised + teq r1, #0 + moveq pc, lr + + @ The prefetch and power control registers are revision dependent + @ and can be written whether or not the L2 cache is enabled + ldr r0, [r1, #L2X0_CACHE_ID] + and r0, r0, #L2X0_CACHE_ID_RTL_MASK + cmp r0, #L310_CACHE_ID_RTL_R2P0 + strcs r7, [r1, #L310_PREFETCH_CTRL] + cmp r0, #L310_CACHE_ID_RTL_R3P0 + strcs r8, [r1, #L310_POWER_CTRL] + + @ Don't setup the L2 cache if it is already enabled + ldr r0, [r1, #L2X0_CTRL] + tst r0, #L2X0_CTRL_EN + movne pc, lr + + str r3, [r1, #L310_TAG_LATENCY_CTRL] + str r4, [r1, #L310_DATA_LATENCY_CTRL] + str r6, [r1, #L310_ADDR_FILTER_END] + str r5, [r1, #L310_ADDR_FILTER_START] + + str r2, [r1, #L2X0_AUX_CTRL] + mov r9, #L2X0_CTRL_EN + str r9, [r1, #L2X0_CTRL] + mov pc, lr +ENDPROC(l2c310_early_resume) + + .align +1: .long l2x0_saved_regs - . diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 7ea641b7aa7d..ce727d47275c 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -2,6 +2,8 @@ #include <linux/list.h> #include <linux/vmalloc.h> +#include <asm/pgtable.h> + /* the upper-most page table pointer */ extern pmd_t *top_pmd; @@ -93,3 +95,5 @@ extern phys_addr_t arm_lowmem_limit; void __init bootmem_init(void); void arm_mm_memblock_reserve(void); void dma_contiguous_remap(void); + +unsigned long __clear_cr(unsigned long mask); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index b68c6b22e1c8..ab14b79b03f0 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -35,6 +35,7 @@ #include <asm/mach/arch.h> #include <asm/mach/map.h> #include <asm/mach/pci.h> +#include <asm/fixmap.h> #include "mm.h" #include "tcm.h" @@ -117,28 +118,54 @@ static struct cachepolicy cache_policies[] __initdata = { }; #ifdef CONFIG_CPU_CP15 +static unsigned long initial_pmd_value __initdata = 0; + /* - * These are useful for identifying cache coherency - * problems by allowing the cache or the cache and - * writebuffer to be turned off. (Note: the write - * buffer should not be on and the cache off). + * Initialise the cache_policy variable with the initial state specified + * via the "pmd" value. This is used to ensure that on ARMv6 and later, + * the C code sets the page tables up with the same policy as the head + * assembly code, which avoids an illegal state where the TLBs can get + * confused. See comments in early_cachepolicy() for more information. */ -static int __init early_cachepolicy(char *p) +void __init init_default_cache_policy(unsigned long pmd) { int i; + initial_pmd_value = pmd; + + pmd &= PMD_SECT_TEX(1) | PMD_SECT_BUFFERABLE | PMD_SECT_CACHEABLE; + + for (i = 0; i < ARRAY_SIZE(cache_policies); i++) + if (cache_policies[i].pmd == pmd) { + cachepolicy = i; + break; + } + + if (i == ARRAY_SIZE(cache_policies)) + pr_err("ERROR: could not find cache policy\n"); +} + +/* + * These are useful for identifying cache coherency problems by allowing + * the cache or the cache and writebuffer to be turned off. (Note: the + * write buffer should not be on and the cache off). + */ +static int __init early_cachepolicy(char *p) +{ + int i, selected = -1; + for (i = 0; i < ARRAY_SIZE(cache_policies); i++) { int len = strlen(cache_policies[i].policy); if (memcmp(p, cache_policies[i].policy, len) == 0) { - cachepolicy = i; - cr_alignment &= ~cache_policies[i].cr_mask; - cr_no_alignment &= ~cache_policies[i].cr_mask; + selected = i; break; } } - if (i == ARRAY_SIZE(cache_policies)) - printk(KERN_ERR "ERROR: unknown or unsupported cache policy\n"); + + if (selected == -1) + pr_err("ERROR: unknown or unsupported cache policy\n"); + /* * This restriction is partly to do with the way we boot; it is * unpredictable to have memory mapped using two different sets of @@ -146,12 +173,18 @@ static int __init early_cachepolicy(char *p) * change these attributes once the initial assembly has setup the * page tables. */ - if (cpu_architecture() >= CPU_ARCH_ARMv6) { - printk(KERN_WARNING "Only cachepolicy=writeback supported on ARMv6 and later\n"); - cachepolicy = CPOLICY_WRITEBACK; + if (cpu_architecture() >= CPU_ARCH_ARMv6 && selected != cachepolicy) { + pr_warn("Only cachepolicy=%s supported on ARMv6 and later\n", + cache_policies[cachepolicy].policy); + return 0; + } + + if (selected != cachepolicy) { + unsigned long cr = __clear_cr(cache_policies[selected].cr_mask); + cachepolicy = selected; + flush_cache_all(); + set_cr(cr); } - flush_cache_all(); - set_cr(cr_alignment); return 0; } early_param("cachepolicy", early_cachepolicy); @@ -186,35 +219,6 @@ static int __init early_ecc(char *p) early_param("ecc", early_ecc); #endif -static int __init noalign_setup(char *__unused) -{ - cr_alignment &= ~CR_A; - cr_no_alignment &= ~CR_A; - set_cr(cr_alignment); - return 1; -} -__setup("noalign", noalign_setup); - -#ifndef CONFIG_SMP -void adjust_cr(unsigned long mask, unsigned long set) -{ - unsigned long flags; - - mask &= ~CR_A; - - set &= mask; - - local_irq_save(flags); - - cr_no_alignment = (cr_no_alignment & ~mask) | set; - cr_alignment = (cr_alignment & ~mask) | set; - - set_cr((get_cr() & ~mask) | set); - - local_irq_restore(flags); -} -#endif - #else /* ifdef CONFIG_CPU_CP15 */ static int __init early_cachepolicy(char *p) @@ -414,8 +418,17 @@ static void __init build_mem_type_table(void) cachepolicy = CPOLICY_WRITEBACK; ecc_mask = 0; } - if (is_smp()) - cachepolicy = CPOLICY_WRITEALLOC; + + if (is_smp()) { + if (cachepolicy != CPOLICY_WRITEALLOC) { + pr_warn("Forcing write-allocate cache policy for SMP\n"); + cachepolicy = CPOLICY_WRITEALLOC; + } + if (!(initial_pmd_value & PMD_SECT_S)) { + pr_warn("Forcing shared mappings for SMP\n"); + initial_pmd_value |= PMD_SECT_S; + } + } /* * Strip out features not present on earlier architectures. @@ -539,11 +552,12 @@ static void __init build_mem_type_table(void) mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; #endif - if (is_smp()) { - /* - * Mark memory with the "shared" attribute - * for SMP systems - */ + /* + * If the initial page tables were created with the S bit + * set, then we need to do the same here for the same + * reasons given in early_cachepolicy(). + */ + if (initial_pmd_value & PMD_SECT_S) { user_pgprot |= L_PTE_SHARED; kern_pgprot |= L_PTE_SHARED; vecs_pgprot |= L_PTE_SHARED; @@ -1061,74 +1075,47 @@ phys_addr_t arm_lowmem_limit __initdata = 0; void __init sanity_check_meminfo(void) { phys_addr_t memblock_limit = 0; - int i, j, highmem = 0; + int highmem = 0; phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1; + struct memblock_region *reg; - for (i = 0, j = 0; i < meminfo.nr_banks; i++) { - struct membank *bank = &meminfo.bank[j]; - phys_addr_t size_limit; - - *bank = meminfo.bank[i]; - size_limit = bank->size; + for_each_memblock(memory, reg) { + phys_addr_t block_start = reg->base; + phys_addr_t block_end = reg->base + reg->size; + phys_addr_t size_limit = reg->size; - if (bank->start >= vmalloc_limit) + if (reg->base >= vmalloc_limit) highmem = 1; else - size_limit = vmalloc_limit - bank->start; + size_limit = vmalloc_limit - reg->base; - bank->highmem = highmem; -#ifdef CONFIG_HIGHMEM - /* - * Split those memory banks which are partially overlapping - * the vmalloc area greatly simplifying things later. - */ - if (!highmem && bank->size > size_limit) { - if (meminfo.nr_banks >= NR_BANKS) { - printk(KERN_CRIT "NR_BANKS too low, " - "ignoring high memory\n"); - } else { - memmove(bank + 1, bank, - (meminfo.nr_banks - i) * sizeof(*bank)); - meminfo.nr_banks++; - i++; - bank[1].size -= size_limit; - bank[1].start = vmalloc_limit; - bank[1].highmem = highmem = 1; - j++; + if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) { + + if (highmem) { + pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n", + &block_start, &block_end); + memblock_remove(reg->base, reg->size); + continue; } - bank->size = size_limit; - } -#else - /* - * Highmem banks not allowed with !CONFIG_HIGHMEM. - */ - if (highmem) { - printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx " - "(!CONFIG_HIGHMEM).\n", - (unsigned long long)bank->start, - (unsigned long long)bank->start + bank->size - 1); - continue; - } - /* - * Check whether this memory bank would partially overlap - * the vmalloc area. - */ - if (bank->size > size_limit) { - printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx " - "to -%.8llx (vmalloc region overlap).\n", - (unsigned long long)bank->start, - (unsigned long long)bank->start + bank->size - 1, - (unsigned long long)bank->start + size_limit - 1); - bank->size = size_limit; + if (reg->size > size_limit) { + phys_addr_t overlap_size = reg->size - size_limit; + + pr_notice("Truncating RAM at %pa-%pa to -%pa", + &block_start, &block_end, &vmalloc_limit); + memblock_remove(vmalloc_limit, overlap_size); + block_end = vmalloc_limit; + } } -#endif - if (!bank->highmem) { - phys_addr_t bank_end = bank->start + bank->size; - if (bank_end > arm_lowmem_limit) - arm_lowmem_limit = bank_end; + if (!highmem) { + if (block_end > arm_lowmem_limit) { + if (reg->size > size_limit) + arm_lowmem_limit = vmalloc_limit; + else + arm_lowmem_limit = block_end; + } /* * Find the first non-section-aligned page, and point @@ -1144,35 +1131,15 @@ void __init sanity_check_meminfo(void) * occurs before any free memory is mapped. */ if (!memblock_limit) { - if (!IS_ALIGNED(bank->start, SECTION_SIZE)) - memblock_limit = bank->start; - else if (!IS_ALIGNED(bank_end, SECTION_SIZE)) - memblock_limit = bank_end; + if (!IS_ALIGNED(block_start, SECTION_SIZE)) + memblock_limit = block_start; + else if (!IS_ALIGNED(block_end, SECTION_SIZE)) + memblock_limit = arm_lowmem_limit; } - } - j++; - } -#ifdef CONFIG_HIGHMEM - if (highmem) { - const char *reason = NULL; - if (cache_is_vipt_aliasing()) { - /* - * Interactions between kmap and other mappings - * make highmem support with aliasing VIPT caches - * rather difficult. - */ - reason = "with VIPT aliasing cache"; - } - if (reason) { - printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n", - reason); - while (j > 0 && meminfo.bank[j - 1].highmem) - j--; } } -#endif - meminfo.nr_banks = j; + high_memory = __va(arm_lowmem_limit - 1) + 1; /* @@ -1359,6 +1326,9 @@ static void __init kmap_init(void) #ifdef CONFIG_HIGHMEM pkmap_page_table = early_pte_alloc(pmd_off_k(PKMAP_BASE), PKMAP_BASE, _PAGE_KERNEL_TABLE); + + fixmap_page_table = early_pte_alloc(pmd_off_k(FIXADDR_START), + FIXADDR_START, _PAGE_KERNEL_TABLE); #endif } @@ -1461,7 +1431,7 @@ void __init early_paging_init(const struct machine_desc *mdesc, * just complicate the code. */ flush_cache_louis(); - dsb(); + dsb(ishst); isb(); /* remap level 1 table */ diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 55764a7ef1f0..da1874f9f8cf 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -88,30 +88,35 @@ static unsigned long irbar_read(void) void __init sanity_check_meminfo_mpu(void) { int i; - struct membank *bank = meminfo.bank; phys_addr_t phys_offset = PHYS_OFFSET; phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size; - - /* Initially only use memory continuous from PHYS_OFFSET */ - if (bank_phys_start(&bank[0]) != phys_offset) - panic("First memory bank must be contiguous from PHYS_OFFSET"); - - /* Banks have already been sorted by start address */ - for (i = 1; i < meminfo.nr_banks; i++) { - if (bank[i].start <= bank_phys_end(&bank[0]) && - bank_phys_end(&bank[i]) > bank_phys_end(&bank[0])) { - bank[0].size = bank_phys_end(&bank[i]) - bank[0].start; + struct memblock_region *reg; + bool first = true; + phys_addr_t mem_start; + phys_addr_t mem_end; + + for_each_memblock(memory, reg) { + if (first) { + /* + * Initially only use memory continuous from + * PHYS_OFFSET */ + if (reg->base != phys_offset) + panic("First memory bank must be contiguous from PHYS_OFFSET"); + + mem_start = reg->base; + mem_end = reg->base + reg->size; + specified_mem_size = reg->size; + first = false; } else { - pr_notice("Ignoring RAM after 0x%.8lx. " - "First non-contiguous (ignored) bank start: 0x%.8lx\n", - (unsigned long)bank_phys_end(&bank[0]), - (unsigned long)bank_phys_start(&bank[i])); - break; + /* + * memblock auto merges contiguous blocks, remove + * all blocks afterwards + */ + pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n", + &mem_start, ®->base); + memblock_remove(reg->base, reg->size); } } - /* All contiguous banks are now merged in to the first bank */ - meminfo.nr_banks = 1; - specified_mem_size = bank[0].size; /* * MPU has curious alignment requirements: Size must be power of 2, and @@ -128,23 +133,24 @@ void __init sanity_check_meminfo_mpu(void) */ aligned_region_size = (phys_offset - 1) ^ (phys_offset); /* Find the max power-of-two sized region that fits inside our bank */ - rounded_mem_size = (1 << __fls(bank[0].size)) - 1; + rounded_mem_size = (1 << __fls(specified_mem_size)) - 1; /* The actual region size is the smaller of the two */ aligned_region_size = aligned_region_size < rounded_mem_size ? aligned_region_size + 1 : rounded_mem_size + 1; - if (aligned_region_size != specified_mem_size) - pr_warn("Truncating memory from 0x%.8lx to 0x%.8lx (MPU region constraints)", - (unsigned long)specified_mem_size, - (unsigned long)aligned_region_size); + if (aligned_region_size != specified_mem_size) { + pr_warn("Truncating memory from %pa to %pa (MPU region constraints)", + &specified_mem_size, &aligned_region_size); + memblock_remove(mem_start + aligned_region_size, + specified_mem_size - aligned_round_size); + + mem_end = mem_start + aligned_region_size; + } - meminfo.bank[0].size = aligned_region_size; - pr_debug("MPU Region from 0x%.8lx size 0x%.8lx (end 0x%.8lx))\n", - (unsigned long)phys_offset, - (unsigned long)aligned_region_size, - (unsigned long)bank_phys_end(&bank[0])); + pr_debug("MPU Region from %pa size %pa (end %pa))\n", + &phys_offset, &aligned_region_size, &mem_end); } @@ -292,7 +298,7 @@ void __init sanity_check_meminfo(void) { phys_addr_t end; sanity_check_meminfo_mpu(); - end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]); + end = memblock_end_of_DRAM(); high_memory = __va(end - 1) + 1; } diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 01a719e18bb0..22e3ad63500c 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -64,6 +64,14 @@ ENTRY(cpu_v7_switch_mm) mov pc, lr ENDPROC(cpu_v7_switch_mm) +#ifdef __ARMEB__ +#define rl r3 +#define rh r2 +#else +#define rl r2 +#define rh r3 +#endif + /* * cpu_v7_set_pte_ext(ptep, pte) * @@ -73,13 +81,13 @@ ENDPROC(cpu_v7_switch_mm) */ ENTRY(cpu_v7_set_pte_ext) #ifdef CONFIG_MMU - tst r2, #L_PTE_VALID + tst rl, #L_PTE_VALID beq 1f - tst r3, #1 << (57 - 32) @ L_PTE_NONE - bicne r2, #L_PTE_VALID + tst rh, #1 << (57 - 32) @ L_PTE_NONE + bicne rl, #L_PTE_VALID bne 1f - tst r3, #1 << (55 - 32) @ L_PTE_DIRTY - orreq r2, #L_PTE_RDONLY + tst rh, #1 << (55 - 32) @ L_PTE_DIRTY + orreq rl, #L_PTE_RDONLY 1: strd r2, r3, [r0] ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 195731d3813b..3db2c2f04a30 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -169,9 +169,31 @@ ENDPROC(cpu_pj4b_do_idle) globl_equ cpu_pj4b_do_idle, cpu_v7_do_idle #endif globl_equ cpu_pj4b_dcache_clean_area, cpu_v7_dcache_clean_area - globl_equ cpu_pj4b_do_suspend, cpu_v7_do_suspend - globl_equ cpu_pj4b_do_resume, cpu_v7_do_resume - globl_equ cpu_pj4b_suspend_size, cpu_v7_suspend_size +#ifdef CONFIG_ARM_CPU_SUSPEND +ENTRY(cpu_pj4b_do_suspend) + stmfd sp!, {r6 - r10} + mrc p15, 1, r6, c15, c1, 0 @ save CP15 - extra features + mrc p15, 1, r7, c15, c2, 0 @ save CP15 - Aux Func Modes Ctrl 0 + mrc p15, 1, r8, c15, c1, 2 @ save CP15 - Aux Debug Modes Ctrl 2 + mrc p15, 1, r9, c15, c1, 1 @ save CP15 - Aux Debug Modes Ctrl 1 + mrc p15, 0, r10, c9, c14, 0 @ save CP15 - PMC + stmia r0!, {r6 - r10} + ldmfd sp!, {r6 - r10} + b cpu_v7_do_suspend +ENDPROC(cpu_pj4b_do_suspend) + +ENTRY(cpu_pj4b_do_resume) + ldmia r0!, {r6 - r10} + mcr p15, 1, r6, c15, c1, 0 @ save CP15 - extra features + mcr p15, 1, r7, c15, c2, 0 @ save CP15 - Aux Func Modes Ctrl 0 + mcr p15, 1, r8, c15, c1, 2 @ save CP15 - Aux Debug Modes Ctrl 2 + mcr p15, 1, r9, c15, c1, 1 @ save CP15 - Aux Debug Modes Ctrl 1 + mcr p15, 0, r10, c9, c14, 0 @ save CP15 - PMC + b cpu_v7_do_resume +ENDPROC(cpu_pj4b_do_resume) +#endif +.globl cpu_pj4b_suspend_size +.equ cpu_pj4b_suspend_size, 4 * 14 #endif @@ -194,6 +216,7 @@ __v7_cr7mp_setup: __v7_ca7mp_setup: __v7_ca12mp_setup: __v7_ca15mp_setup: +__v7_ca17mp_setup: mov r10, #0 1: #ifdef CONFIG_SMP @@ -505,6 +528,16 @@ __v7_ca15mp_proc_info: .size __v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info /* + * ARM Ltd. Cortex A17 processor. + */ + .type __v7_ca17mp_proc_info, #object +__v7_ca17mp_proc_info: + .long 0x410fc0e0 + .long 0xff0ffff0 + __v7_proc __v7_ca17mp_setup + .size __v7_ca17mp_proc_info, . - __v7_ca17mp_proc_info + + /* * Qualcomm Inc. Krait processors. */ .type __krait_proc_info, #object diff --git a/arch/arm/plat-samsung/dev-backlight.c b/arch/arm/plat-samsung/dev-backlight.c index be4ad0b21c08..2157c5b539e6 100644 --- a/arch/arm/plat-samsung/dev-backlight.c +++ b/arch/arm/plat-samsung/dev-backlight.c @@ -124,8 +124,6 @@ void __init samsung_bl_set(struct samsung_bl_gpio_info *gpio_info, samsung_bl_data->pwm_period_ns = bl_data->pwm_period_ns; if (bl_data->enable_gpio >= 0) samsung_bl_data->enable_gpio = bl_data->enable_gpio; - if (bl_data->enable_gpio_flags) - samsung_bl_data->enable_gpio_flags = bl_data->enable_gpio_flags; if (bl_data->init) samsung_bl_data->init = bl_data->init; if (bl_data->notify) diff --git a/arch/arm/plat-samsung/s5p-dev-mfc.c b/arch/arm/plat-samsung/s5p-dev-mfc.c index 98087b655df0..469b86260fe3 100644 --- a/arch/arm/plat-samsung/s5p-dev-mfc.c +++ b/arch/arm/plat-samsung/s5p-dev-mfc.c @@ -125,8 +125,8 @@ device_initcall(s5p_mfc_memory_init); int __init s5p_fdt_alloc_mfc_mem(unsigned long node, const char *uname, int depth, void *data) { - __be32 *prop; - unsigned long len; + const __be32 *prop; + int len; struct s5p_mfc_dt_meminfo mfc_mem; if (!data) diff --git a/arch/arm/plat-samsung/s5p-sleep.S b/arch/arm/plat-samsung/s5p-sleep.S index c5001659bdf8..25c68ceb9e2b 100644 --- a/arch/arm/plat-samsung/s5p-sleep.S +++ b/arch/arm/plat-samsung/s5p-sleep.S @@ -22,7 +22,6 @@ */ #include <linux/linkage.h> -#include <asm/asm-offsets.h> .data .align diff --git a/arch/arm/vfp/entry.S b/arch/arm/vfp/entry.S index f0759e70fb86..fe6ca574d093 100644 --- a/arch/arm/vfp/entry.S +++ b/arch/arm/vfp/entry.S @@ -22,11 +22,10 @@ @ r9 = normal "successful" return address @ r10 = this threads thread_info structure @ lr = unrecognised instruction return address -@ IRQs disabled. +@ IRQs enabled. @ ENTRY(do_vfp) inc_preempt_count r10, r4 - enable_irq ldr r4, .LCvfp ldr r11, [r10, #TI_CPU] @ CPU number add r10, r10, #TI_VFPSTATE @ r10 = workspace diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index f5f63b715d91..7295419165e1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -30,12 +30,17 @@ config ARM64 select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK + select HAVE_C_RECORDMCOUNT select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_API_DEBUG select HAVE_DMA_ATTRS select HAVE_DMA_CONTIGUOUS + select HAVE_DYNAMIC_FTRACE select HAVE_EFFICIENT_UNALIGNED_ACCESS + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_GRAPH_TRACER select HAVE_GENERIC_DMA_COHERENT select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_MEMBLOCK @@ -43,6 +48,7 @@ config ARM64 select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_SYSCALL_TRACEPOINTS select IRQ_DOMAIN select MODULES_USE_ELF_RELA select NO_BOOTMEM @@ -245,6 +251,9 @@ config ARCH_WANT_HUGE_PMD_SHARE config HAVE_ARCH_TRANSPARENT_HUGEPAGE def_bool y +config ARCH_HAS_CACHE_LINE_SIZE + def_bool y + source "mm/Kconfig" config XEN_DOM0 @@ -283,6 +292,20 @@ config CMDLINE_FORCE This is useful if you cannot or don't want to change the command-line options your boot loader passes to the kernel. +config EFI + bool "UEFI runtime support" + depends on OF && !CPU_BIG_ENDIAN + select LIBFDT + select UCS2_STRING + select EFI_PARAMS_FROM_FDT + default y + help + This option provides support for runtime services provided + by UEFI firmware (such as non-volatile variables, realtime + clock, and platform reset). A UEFI stub is also provided to + allow the kernel to be booted as an EFI application. This + is only useful on systems that have UEFI firmware. + endmenu menu "Userspace binary formats" @@ -334,6 +357,8 @@ source "net/Kconfig" source "drivers/Kconfig" +source "drivers/firmware/Kconfig" + source "fs/Kconfig" source "arch/arm64/kvm/Kconfig" @@ -343,5 +368,8 @@ source "arch/arm64/Kconfig.debug" source "security/Kconfig" source "crypto/Kconfig" +if CRYPTO +source "arch/arm64/crypto/Kconfig" +endif source "lib/Kconfig" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 2fceb71ac3b7..8185a913c5ed 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -45,6 +45,7 @@ export TEXT_OFFSET GZFLAGS core-y += arch/arm64/kernel/ arch/arm64/mm/ core-$(CONFIG_KVM) += arch/arm64/kvm/ core-$(CONFIG_XEN) += arch/arm64/xen/ +core-$(CONFIG_CRYPTO) += arch/arm64/crypto/ libs-y := arch/arm64/lib/ $(libs-y) libs-y += $(LIBGCC) diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi index f8c40a66e65d..c5f0a47a1375 100644 --- a/arch/arm64/boot/dts/apm-storm.dtsi +++ b/arch/arm64/boot/dts/apm-storm.dtsi @@ -257,6 +257,19 @@ enable-offset = <0x0>; enable-mask = <0x39>; }; + + rtcclk: rtcclk@17000000 { + compatible = "apm,xgene-device-clock"; + #clock-cells = <1>; + clocks = <&socplldiv2 0>; + reg = <0x0 0x17000000 0x0 0x2000>; + reg-names = "csr-reg"; + csr-offset = <0xc>; + csr-mask = <0x2>; + enable-offset = <0x10>; + enable-mask = <0x2>; + clock-output-names = "rtcclk"; + }; }; serial0: serial@1c020000 { @@ -342,5 +355,13 @@ phys = <&phy3 0>; phy-names = "sata-phy"; }; + + rtc: rtc@10510000 { + compatible = "apm,xgene-rtc"; + reg = <0x0 0x10510000 0x0 0x400>; + interrupts = <0x0 0x46 0x4>; + #clock-cells = <1>; + clocks = <&rtcclk 0>; + }; }; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 7959dd0ca5d5..157e1d8d9a47 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1,11 +1,11 @@ # CONFIG_LOCALVERSION_AUTO is not set -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +CONFIG_AUDIT=y +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -27,6 +27,7 @@ CONFIG_ARCH_VEXPRESS=y CONFIG_ARCH_XGENE=y CONFIG_SMP=y CONFIG_PREEMPT=y +CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y CONFIG_CMDLINE="console=ttyAMA0" # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set @@ -44,7 +45,7 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DMA_CMA=y -CONFIG_SCSI=y +CONFIG_VIRTIO_BLK=y # CONFIG_SCSI_PROC_FS is not set CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOWLEVEL is not set @@ -56,20 +57,18 @@ CONFIG_SMC91X=y CONFIG_SMSC911X=y # CONFIG_WLAN is not set CONFIG_INPUT_EVDEV=y -# CONFIG_SERIO_I8042 is not set # CONFIG_SERIO_SERPORT is not set CONFIG_LEGACY_PTY_COUNT=16 CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_REGULATOR=y CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set @@ -79,27 +78,38 @@ CONFIG_USB_ISP1760_HCD=y CONFIG_USB_STORAGE=y CONFIG_MMC=y CONFIG_MMC_ARMMMCI=y +CONFIG_VIRTIO_MMIO=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y -CONFIG_EXT4_FS=y # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set # CONFIG_EXT3_FS_XATTR is not set +CONFIG_EXT4_FS=y CONFIG_FUSE_FS=y CONFIG_CUSE=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y +CONFIG_HUGETLBFS=y # CONFIG_MISC_FILESYSTEMS is not set CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y -CONFIG_MAGIC_SYSRQ=y +CONFIG_VIRTUALIZATION=y +CONFIG_KVM=y +CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y +CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y +CONFIG_LOCKUP_DETECTOR=y # CONFIG_SCHED_DEBUG is not set -CONFIG_DEBUG_INFO=y # CONFIG_FTRACE is not set -CONFIG_ATOMIC64_SELFTEST=y -CONFIG_VIRTIO_MMIO=y -CONFIG_VIRTIO_BLK=y +CONFIG_CRYPTO_ANSI_CPRNG=y +CONFIG_ARM64_CRYPTO=y +CONFIG_CRYPTO_SHA1_ARM64_CE=y +CONFIG_CRYPTO_SHA2_ARM64_CE=y +CONFIG_CRYPTO_GHASH_ARM64_CE=y +CONFIG_CRYPTO_AES_ARM64_CE=y +CONFIG_CRYPTO_AES_ARM64_CE_CCM=y +CONFIG_CRYPTO_AES_ARM64_CE_BLK=y +CONFIG_CRYPTO_AES_ARM64_NEON_BLK=y diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig new file mode 100644 index 000000000000..5562652c5316 --- /dev/null +++ b/arch/arm64/crypto/Kconfig @@ -0,0 +1,53 @@ + +menuconfig ARM64_CRYPTO + bool "ARM64 Accelerated Cryptographic Algorithms" + depends on ARM64 + help + Say Y here to choose from a selection of cryptographic algorithms + implemented using ARM64 specific CPU features or instructions. + +if ARM64_CRYPTO + +config CRYPTO_SHA1_ARM64_CE + tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)" + depends on ARM64 && KERNEL_MODE_NEON + select CRYPTO_HASH + +config CRYPTO_SHA2_ARM64_CE + tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)" + depends on ARM64 && KERNEL_MODE_NEON + select CRYPTO_HASH + +config CRYPTO_GHASH_ARM64_CE + tristate "GHASH (for GCM chaining mode) using ARMv8 Crypto Extensions" + depends on ARM64 && KERNEL_MODE_NEON + select CRYPTO_HASH + +config CRYPTO_AES_ARM64_CE + tristate "AES core cipher using ARMv8 Crypto Extensions" + depends on ARM64 && KERNEL_MODE_NEON + select CRYPTO_ALGAPI + select CRYPTO_AES + +config CRYPTO_AES_ARM64_CE_CCM + tristate "AES in CCM mode using ARMv8 Crypto Extensions" + depends on ARM64 && KERNEL_MODE_NEON + select CRYPTO_ALGAPI + select CRYPTO_AES + select CRYPTO_AEAD + +config CRYPTO_AES_ARM64_CE_BLK + tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions" + depends on ARM64 && KERNEL_MODE_NEON + select CRYPTO_BLKCIPHER + select CRYPTO_AES + select CRYPTO_ABLK_HELPER + +config CRYPTO_AES_ARM64_NEON_BLK + tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions" + depends on ARM64 && KERNEL_MODE_NEON + select CRYPTO_BLKCIPHER + select CRYPTO_AES + select CRYPTO_ABLK_HELPER + +endif diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile new file mode 100644 index 000000000000..2070a56ecc46 --- /dev/null +++ b/arch/arm64/crypto/Makefile @@ -0,0 +1,38 @@ +# +# linux/arch/arm64/crypto/Makefile +# +# Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org> +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License version 2 as +# published by the Free Software Foundation. +# + +obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o +sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o + +obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o +sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o + +obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o +ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o + +obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o +CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto + +obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o +aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o + +obj-$(CONFIG_CRYPTO_AES_ARM64_CE_BLK) += aes-ce-blk.o +aes-ce-blk-y := aes-glue-ce.o aes-ce.o + +obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o +aes-neon-blk-y := aes-glue-neon.o aes-neon.o + +AFLAGS_aes-ce.o := -DINTERLEAVE=2 -DINTERLEAVE_INLINE +AFLAGS_aes-neon.o := -DINTERLEAVE=4 + +CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS + +$(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE + $(call if_changed_dep,cc_o_c) diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S new file mode 100644 index 000000000000..432e4841cd81 --- /dev/null +++ b/arch/arm64/crypto/aes-ce-ccm-core.S @@ -0,0 +1,222 @@ +/* + * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions + * + * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> + + .text + .arch armv8-a+crypto + + /* + * void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes, + * u32 *macp, u8 const rk[], u32 rounds); + */ +ENTRY(ce_aes_ccm_auth_data) + ldr w8, [x3] /* leftover from prev round? */ + ld1 {v0.2d}, [x0] /* load mac */ + cbz w8, 1f + sub w8, w8, #16 + eor v1.16b, v1.16b, v1.16b +0: ldrb w7, [x1], #1 /* get 1 byte of input */ + subs w2, w2, #1 + add w8, w8, #1 + ins v1.b[0], w7 + ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */ + beq 8f /* out of input? */ + cbnz w8, 0b + eor v0.16b, v0.16b, v1.16b +1: ld1 {v3.2d}, [x4] /* load first round key */ + prfm pldl1strm, [x1] + cmp w5, #12 /* which key size? */ + add x6, x4, #16 + sub w7, w5, #2 /* modified # of rounds */ + bmi 2f + bne 5f + mov v5.16b, v3.16b + b 4f +2: mov v4.16b, v3.16b + ld1 {v5.2d}, [x6], #16 /* load 2nd round key */ +3: aese v0.16b, v4.16b + aesmc v0.16b, v0.16b +4: ld1 {v3.2d}, [x6], #16 /* load next round key */ + aese v0.16b, v5.16b + aesmc v0.16b, v0.16b +5: ld1 {v4.2d}, [x6], #16 /* load next round key */ + subs w7, w7, #3 + aese v0.16b, v3.16b + aesmc v0.16b, v0.16b + ld1 {v5.2d}, [x6], #16 /* load next round key */ + bpl 3b + aese v0.16b, v4.16b + subs w2, w2, #16 /* last data? */ + eor v0.16b, v0.16b, v5.16b /* final round */ + bmi 6f + ld1 {v1.16b}, [x1], #16 /* load next input block */ + eor v0.16b, v0.16b, v1.16b /* xor with mac */ + bne 1b +6: st1 {v0.2d}, [x0] /* store mac */ + beq 10f + adds w2, w2, #16 + beq 10f + mov w8, w2 +7: ldrb w7, [x1], #1 + umov w6, v0.b[0] + eor w6, w6, w7 + strb w6, [x0], #1 + subs w2, w2, #1 + beq 10f + ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */ + b 7b +8: mov w7, w8 + add w8, w8, #16 +9: ext v1.16b, v1.16b, v1.16b, #1 + adds w7, w7, #1 + bne 9b + eor v0.16b, v0.16b, v1.16b + st1 {v0.2d}, [x0] +10: str w8, [x3] + ret +ENDPROC(ce_aes_ccm_auth_data) + + /* + * void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[], + * u32 rounds); + */ +ENTRY(ce_aes_ccm_final) + ld1 {v3.2d}, [x2], #16 /* load first round key */ + ld1 {v0.2d}, [x0] /* load mac */ + cmp w3, #12 /* which key size? */ + sub w3, w3, #2 /* modified # of rounds */ + ld1 {v1.2d}, [x1] /* load 1st ctriv */ + bmi 0f + bne 3f + mov v5.16b, v3.16b + b 2f +0: mov v4.16b, v3.16b +1: ld1 {v5.2d}, [x2], #16 /* load next round key */ + aese v0.16b, v4.16b + aese v1.16b, v4.16b + aesmc v0.16b, v0.16b + aesmc v1.16b, v1.16b +2: ld1 {v3.2d}, [x2], #16 /* load next round key */ + aese v0.16b, v5.16b + aese v1.16b, v5.16b + aesmc v0.16b, v0.16b + aesmc v1.16b, v1.16b +3: ld1 {v4.2d}, [x2], #16 /* load next round key */ + subs w3, w3, #3 + aese v0.16b, v3.16b + aese v1.16b, v3.16b + aesmc v0.16b, v0.16b + aesmc v1.16b, v1.16b + bpl 1b + aese v0.16b, v4.16b + aese v1.16b, v4.16b + /* final round key cancels out */ + eor v0.16b, v0.16b, v1.16b /* en-/decrypt the mac */ + st1 {v0.2d}, [x0] /* store result */ + ret +ENDPROC(ce_aes_ccm_final) + + .macro aes_ccm_do_crypt,enc + ldr x8, [x6, #8] /* load lower ctr */ + ld1 {v0.2d}, [x5] /* load mac */ + rev x8, x8 /* keep swabbed ctr in reg */ +0: /* outer loop */ + ld1 {v1.1d}, [x6] /* load upper ctr */ + prfm pldl1strm, [x1] + add x8, x8, #1 + rev x9, x8 + cmp w4, #12 /* which key size? */ + sub w7, w4, #2 /* get modified # of rounds */ + ins v1.d[1], x9 /* no carry in lower ctr */ + ld1 {v3.2d}, [x3] /* load first round key */ + add x10, x3, #16 + bmi 1f + bne 4f + mov v5.16b, v3.16b + b 3f +1: mov v4.16b, v3.16b + ld1 {v5.2d}, [x10], #16 /* load 2nd round key */ +2: /* inner loop: 3 rounds, 2x interleaved */ + aese v0.16b, v4.16b + aese v1.16b, v4.16b + aesmc v0.16b, v0.16b + aesmc v1.16b, v1.16b +3: ld1 {v3.2d}, [x10], #16 /* load next round key */ + aese v0.16b, v5.16b + aese v1.16b, v5.16b + aesmc v0.16b, v0.16b + aesmc v1.16b, v1.16b +4: ld1 {v4.2d}, [x10], #16 /* load next round key */ + subs w7, w7, #3 + aese v0.16b, v3.16b + aese v1.16b, v3.16b + aesmc v0.16b, v0.16b + aesmc v1.16b, v1.16b + ld1 {v5.2d}, [x10], #16 /* load next round key */ + bpl 2b + aese v0.16b, v4.16b + aese v1.16b, v4.16b + subs w2, w2, #16 + bmi 6f /* partial block? */ + ld1 {v2.16b}, [x1], #16 /* load next input block */ + .if \enc == 1 + eor v2.16b, v2.16b, v5.16b /* final round enc+mac */ + eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */ + .else + eor v2.16b, v2.16b, v1.16b /* xor with crypted ctr */ + eor v1.16b, v2.16b, v5.16b /* final round enc */ + .endif + eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */ + st1 {v1.16b}, [x0], #16 /* write output block */ + bne 0b + rev x8, x8 + st1 {v0.2d}, [x5] /* store mac */ + str x8, [x6, #8] /* store lsb end of ctr (BE) */ +5: ret + +6: eor v0.16b, v0.16b, v5.16b /* final round mac */ + eor v1.16b, v1.16b, v5.16b /* final round enc */ + st1 {v0.2d}, [x5] /* store mac */ + add w2, w2, #16 /* process partial tail block */ +7: ldrb w9, [x1], #1 /* get 1 byte of input */ + umov w6, v1.b[0] /* get top crypted ctr byte */ + umov w7, v0.b[0] /* get top mac byte */ + .if \enc == 1 + eor w7, w7, w9 + eor w9, w9, w6 + .else + eor w9, w9, w6 + eor w7, w7, w9 + .endif + strb w9, [x0], #1 /* store out byte */ + strb w7, [x5], #1 /* store mac byte */ + subs w2, w2, #1 + beq 5b + ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */ + ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */ + b 7b + .endm + + /* + * void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes, + * u8 const rk[], u32 rounds, u8 mac[], + * u8 ctr[]); + * void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes, + * u8 const rk[], u32 rounds, u8 mac[], + * u8 ctr[]); + */ +ENTRY(ce_aes_ccm_encrypt) + aes_ccm_do_crypt 1 +ENDPROC(ce_aes_ccm_encrypt) + +ENTRY(ce_aes_ccm_decrypt) + aes_ccm_do_crypt 0 +ENDPROC(ce_aes_ccm_decrypt) diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c new file mode 100644 index 000000000000..9e6cdde9b43d --- /dev/null +++ b/arch/arm64/crypto/aes-ce-ccm-glue.c @@ -0,0 +1,297 @@ +/* + * aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions + * + * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <asm/neon.h> +#include <asm/unaligned.h> +#include <crypto/aes.h> +#include <crypto/algapi.h> +#include <crypto/scatterwalk.h> +#include <linux/crypto.h> +#include <linux/module.h> + +static int num_rounds(struct crypto_aes_ctx *ctx) +{ + /* + * # of rounds specified by AES: + * 128 bit key 10 rounds + * 192 bit key 12 rounds + * 256 bit key 14 rounds + * => n byte key => 6 + (n/4) rounds + */ + return 6 + ctx->key_length / 4; +} + +asmlinkage void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes, + u32 *macp, u32 const rk[], u32 rounds); + +asmlinkage void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes, + u32 const rk[], u32 rounds, u8 mac[], + u8 ctr[]); + +asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes, + u32 const rk[], u32 rounds, u8 mac[], + u8 ctr[]); + +asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[], + u32 rounds); + +static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key, + unsigned int key_len) +{ + struct crypto_aes_ctx *ctx = crypto_aead_ctx(tfm); + int ret; + + ret = crypto_aes_expand_key(ctx, in_key, key_len); + if (!ret) + return 0; + + tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; +} + +static int ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize) +{ + if ((authsize & 1) || authsize < 4) + return -EINVAL; + return 0; +} + +static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen) +{ + struct crypto_aead *aead = crypto_aead_reqtfm(req); + __be32 *n = (__be32 *)&maciv[AES_BLOCK_SIZE - 8]; + u32 l = req->iv[0] + 1; + + /* verify that CCM dimension 'L' is set correctly in the IV */ + if (l < 2 || l > 8) + return -EINVAL; + + /* verify that msglen can in fact be represented in L bytes */ + if (l < 4 && msglen >> (8 * l)) + return -EOVERFLOW; + + /* + * Even if the CCM spec allows L values of up to 8, the Linux cryptoapi + * uses a u32 type to represent msglen so the top 4 bytes are always 0. + */ + n[0] = 0; + n[1] = cpu_to_be32(msglen); + + memcpy(maciv, req->iv, AES_BLOCK_SIZE - l); + + /* + * Meaning of byte 0 according to CCM spec (RFC 3610/NIST 800-38C) + * - bits 0..2 : max # of bytes required to represent msglen, minus 1 + * (already set by caller) + * - bits 3..5 : size of auth tag (1 => 4 bytes, 2 => 6 bytes, etc) + * - bit 6 : indicates presence of authenticate-only data + */ + maciv[0] |= (crypto_aead_authsize(aead) - 2) << 2; + if (req->assoclen) + maciv[0] |= 0x40; + + memset(&req->iv[AES_BLOCK_SIZE - l], 0, l); + return 0; +} + +static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[]) +{ + struct crypto_aead *aead = crypto_aead_reqtfm(req); + struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead); + struct __packed { __be16 l; __be32 h; u16 len; } ltag; + struct scatter_walk walk; + u32 len = req->assoclen; + u32 macp = 0; + + /* prepend the AAD with a length tag */ + if (len < 0xff00) { + ltag.l = cpu_to_be16(len); + ltag.len = 2; + } else { + ltag.l = cpu_to_be16(0xfffe); + put_unaligned_be32(len, <ag.h); + ltag.len = 6; + } + + ce_aes_ccm_auth_data(mac, (u8 *)<ag, ltag.len, &macp, ctx->key_enc, + num_rounds(ctx)); + scatterwalk_start(&walk, req->assoc); + + do { + u32 n = scatterwalk_clamp(&walk, len); + u8 *p; + + if (!n) { + scatterwalk_start(&walk, sg_next(walk.sg)); + n = scatterwalk_clamp(&walk, len); + } + p = scatterwalk_map(&walk); + ce_aes_ccm_auth_data(mac, p, n, &macp, ctx->key_enc, + num_rounds(ctx)); + len -= n; + + scatterwalk_unmap(p); + scatterwalk_advance(&walk, n); + scatterwalk_done(&walk, 0, len); + } while (len); +} + +static int ccm_encrypt(struct aead_request *req) +{ + struct crypto_aead *aead = crypto_aead_reqtfm(req); + struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead); + struct blkcipher_desc desc = { .info = req->iv }; + struct blkcipher_walk walk; + u8 __aligned(8) mac[AES_BLOCK_SIZE]; + u8 buf[AES_BLOCK_SIZE]; + u32 len = req->cryptlen; + int err; + + err = ccm_init_mac(req, mac, len); + if (err) + return err; + + kernel_neon_begin_partial(6); + + if (req->assoclen) + ccm_calculate_auth_mac(req, mac); + + /* preserve the original iv for the final round */ + memcpy(buf, req->iv, AES_BLOCK_SIZE); + + blkcipher_walk_init(&walk, req->dst, req->src, len); + err = blkcipher_aead_walk_virt_block(&desc, &walk, aead, + AES_BLOCK_SIZE); + + while (walk.nbytes) { + u32 tail = walk.nbytes % AES_BLOCK_SIZE; + + if (walk.nbytes == len) + tail = 0; + + ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr, + walk.nbytes - tail, ctx->key_enc, + num_rounds(ctx), mac, walk.iv); + + len -= walk.nbytes - tail; + err = blkcipher_walk_done(&desc, &walk, tail); + } + if (!err) + ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx)); + + kernel_neon_end(); + + if (err) + return err; + + /* copy authtag to end of dst */ + scatterwalk_map_and_copy(mac, req->dst, req->cryptlen, + crypto_aead_authsize(aead), 1); + + return 0; +} + +static int ccm_decrypt(struct aead_request *req) +{ + struct crypto_aead *aead = crypto_aead_reqtfm(req); + struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead); + unsigned int authsize = crypto_aead_authsize(aead); + struct blkcipher_desc desc = { .info = req->iv }; + struct blkcipher_walk walk; + u8 __aligned(8) mac[AES_BLOCK_SIZE]; + u8 buf[AES_BLOCK_SIZE]; + u32 len = req->cryptlen - authsize; + int err; + + err = ccm_init_mac(req, mac, len); + if (err) + return err; + + kernel_neon_begin_partial(6); + + if (req->assoclen) + ccm_calculate_auth_mac(req, mac); + + /* preserve the original iv for the final round */ + memcpy(buf, req->iv, AES_BLOCK_SIZE); + + blkcipher_walk_init(&walk, req->dst, req->src, len); + err = blkcipher_aead_walk_virt_block(&desc, &walk, aead, + AES_BLOCK_SIZE); + + while (walk.nbytes) { + u32 tail = walk.nbytes % AES_BLOCK_SIZE; + + if (walk.nbytes == len) + tail = 0; + + ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr, + walk.nbytes - tail, ctx->key_enc, + num_rounds(ctx), mac, walk.iv); + + len -= walk.nbytes - tail; + err = blkcipher_walk_done(&desc, &walk, tail); + } + if (!err) + ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx)); + + kernel_neon_end(); + + if (err) + return err; + + /* compare calculated auth tag with the stored one */ + scatterwalk_map_and_copy(buf, req->src, req->cryptlen - authsize, + authsize, 0); + + if (memcmp(mac, buf, authsize)) + return -EBADMSG; + return 0; +} + +static struct crypto_alg ccm_aes_alg = { + .cra_name = "ccm(aes)", + .cra_driver_name = "ccm-aes-ce", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_AEAD, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct crypto_aes_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_aead_type, + .cra_module = THIS_MODULE, + .cra_aead = { + .ivsize = AES_BLOCK_SIZE, + .maxauthsize = AES_BLOCK_SIZE, + .setkey = ccm_setkey, + .setauthsize = ccm_setauthsize, + .encrypt = ccm_encrypt, + .decrypt = ccm_decrypt, + } +}; + +static int __init aes_mod_init(void) +{ + if (!(elf_hwcap & HWCAP_AES)) + return -ENODEV; + return crypto_register_alg(&ccm_aes_alg); +} + +static void __exit aes_mod_exit(void) +{ + crypto_unregister_alg(&ccm_aes_alg); +} + +module_init(aes_mod_init); +module_exit(aes_mod_exit); + +MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions"); +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("ccm(aes)"); diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c new file mode 100644 index 000000000000..2075e1acae6b --- /dev/null +++ b/arch/arm64/crypto/aes-ce-cipher.c @@ -0,0 +1,155 @@ +/* + * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions + * + * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <asm/neon.h> +#include <crypto/aes.h> +#include <linux/cpufeature.h> +#include <linux/crypto.h> +#include <linux/module.h> + +MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions"); +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); +MODULE_LICENSE("GPL v2"); + +struct aes_block { + u8 b[AES_BLOCK_SIZE]; +}; + +static int num_rounds(struct crypto_aes_ctx *ctx) +{ + /* + * # of rounds specified by AES: + * 128 bit key 10 rounds + * 192 bit key 12 rounds + * 256 bit key 14 rounds + * => n byte key => 6 + (n/4) rounds + */ + return 6 + ctx->key_length / 4; +} + +static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[]) +{ + struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm); + struct aes_block *out = (struct aes_block *)dst; + struct aes_block const *in = (struct aes_block *)src; + void *dummy0; + int dummy1; + + kernel_neon_begin_partial(4); + + __asm__(" ld1 {v0.16b}, %[in] ;" + " ld1 {v1.2d}, [%[key]], #16 ;" + " cmp %w[rounds], #10 ;" + " bmi 0f ;" + " bne 3f ;" + " mov v3.16b, v1.16b ;" + " b 2f ;" + "0: mov v2.16b, v1.16b ;" + " ld1 {v3.2d}, [%[key]], #16 ;" + "1: aese v0.16b, v2.16b ;" + " aesmc v0.16b, v0.16b ;" + "2: ld1 {v1.2d}, [%[key]], #16 ;" + " aese v0.16b, v3.16b ;" + " aesmc v0.16b, v0.16b ;" + "3: ld1 {v2.2d}, [%[key]], #16 ;" + " subs %w[rounds], %w[rounds], #3 ;" + " aese v0.16b, v1.16b ;" + " aesmc v0.16b, v0.16b ;" + " ld1 {v3.2d}, [%[key]], #16 ;" + " bpl 1b ;" + " aese v0.16b, v2.16b ;" + " eor v0.16b, v0.16b, v3.16b ;" + " st1 {v0.16b}, %[out] ;" + + : [out] "=Q"(*out), + [key] "=r"(dummy0), + [rounds] "=r"(dummy1) + : [in] "Q"(*in), + "1"(ctx->key_enc), + "2"(num_rounds(ctx) - 2) + : "cc"); + + kernel_neon_end(); +} + +static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[]) +{ + struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm); + struct aes_block *out = (struct aes_block *)dst; + struct aes_block const *in = (struct aes_block *)src; + void *dummy0; + int dummy1; + + kernel_neon_begin_partial(4); + + __asm__(" ld1 {v0.16b}, %[in] ;" + " ld1 {v1.2d}, [%[key]], #16 ;" + " cmp %w[rounds], #10 ;" + " bmi 0f ;" + " bne 3f ;" + " mov v3.16b, v1.16b ;" + " b 2f ;" + "0: mov v2.16b, v1.16b ;" + " ld1 {v3.2d}, [%[key]], #16 ;" + "1: aesd v0.16b, v2.16b ;" + " aesimc v0.16b, v0.16b ;" + "2: ld1 {v1.2d}, [%[key]], #16 ;" + " aesd v0.16b, v3.16b ;" + " aesimc v0.16b, v0.16b ;" + "3: ld1 {v2.2d}, [%[key]], #16 ;" + " subs %w[rounds], %w[rounds], #3 ;" + " aesd v0.16b, v1.16b ;" + " aesimc v0.16b, v0.16b ;" + " ld1 {v3.2d}, [%[key]], #16 ;" + " bpl 1b ;" + " aesd v0.16b, v2.16b ;" + " eor v0.16b, v0.16b, v3.16b ;" + " st1 {v0.16b}, %[out] ;" + + : [out] "=Q"(*out), + [key] "=r"(dummy0), + [rounds] "=r"(dummy1) + : [in] "Q"(*in), + "1"(ctx->key_dec), + "2"(num_rounds(ctx) - 2) + : "cc"); + + kernel_neon_end(); +} + +static struct crypto_alg aes_alg = { + .cra_name = "aes", + .cra_driver_name = "aes-ce", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_CIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx), + .cra_module = THIS_MODULE, + .cra_cipher = { + .cia_min_keysize = AES_MIN_KEY_SIZE, + .cia_max_keysize = AES_MAX_KEY_SIZE, + .cia_setkey = crypto_aes_set_key, + .cia_encrypt = aes_cipher_encrypt, + .cia_decrypt = aes_cipher_decrypt + } +}; + +static int __init aes_mod_init(void) +{ + return crypto_register_alg(&aes_alg); +} + +static void __exit aes_mod_exit(void) +{ + crypto_unregister_alg(&aes_alg); +} + +module_cpu_feature_match(AES, aes_mod_init); +module_exit(aes_mod_exit); diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S new file mode 100644 index 000000000000..685a18f731eb --- /dev/null +++ b/arch/arm64/crypto/aes-ce.S @@ -0,0 +1,133 @@ +/* + * linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with + * Crypto Extensions + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> + +#define AES_ENTRY(func) ENTRY(ce_ ## func) +#define AES_ENDPROC(func) ENDPROC(ce_ ## func) + + .arch armv8-a+crypto + + /* preload all round keys */ + .macro load_round_keys, rounds, rk + cmp \rounds, #12 + blo 2222f /* 128 bits */ + beq 1111f /* 192 bits */ + ld1 {v17.16b-v18.16b}, [\rk], #32 +1111: ld1 {v19.16b-v20.16b}, [\rk], #32 +2222: ld1 {v21.16b-v24.16b}, [\rk], #64 + ld1 {v25.16b-v28.16b}, [\rk], #64 + ld1 {v29.16b-v31.16b}, [\rk] + .endm + + /* prepare for encryption with key in rk[] */ + .macro enc_prepare, rounds, rk, ignore + load_round_keys \rounds, \rk + .endm + + /* prepare for encryption (again) but with new key in rk[] */ + .macro enc_switch_key, rounds, rk, ignore + load_round_keys \rounds, \rk + .endm + + /* prepare for decryption with key in rk[] */ + .macro dec_prepare, rounds, rk, ignore + load_round_keys \rounds, \rk + .endm + + .macro do_enc_Nx, de, mc, k, i0, i1, i2, i3 + aes\de \i0\().16b, \k\().16b + .ifnb \i1 + aes\de \i1\().16b, \k\().16b + .ifnb \i3 + aes\de \i2\().16b, \k\().16b + aes\de \i3\().16b, \k\().16b + .endif + .endif + aes\mc \i0\().16b, \i0\().16b + .ifnb \i1 + aes\mc \i1\().16b, \i1\().16b + .ifnb \i3 + aes\mc \i2\().16b, \i2\().16b + aes\mc \i3\().16b, \i3\().16b + .endif + .endif + .endm + + /* up to 4 interleaved encryption rounds with the same round key */ + .macro round_Nx, enc, k, i0, i1, i2, i3 + .ifc \enc, e + do_enc_Nx e, mc, \k, \i0, \i1, \i2, \i3 + .else + do_enc_Nx d, imc, \k, \i0, \i1, \i2, \i3 + .endif + .endm + + /* up to 4 interleaved final rounds */ + .macro fin_round_Nx, de, k, k2, i0, i1, i2, i3 + aes\de \i0\().16b, \k\().16b + .ifnb \i1 + aes\de \i1\().16b, \k\().16b + .ifnb \i3 + aes\de \i2\().16b, \k\().16b + aes\de \i3\().16b, \k\().16b + .endif + .endif + eor \i0\().16b, \i0\().16b, \k2\().16b + .ifnb \i1 + eor \i1\().16b, \i1\().16b, \k2\().16b + .ifnb \i3 + eor \i2\().16b, \i2\().16b, \k2\().16b + eor \i3\().16b, \i3\().16b, \k2\().16b + .endif + .endif + .endm + + /* up to 4 interleaved blocks */ + .macro do_block_Nx, enc, rounds, i0, i1, i2, i3 + cmp \rounds, #12 + blo 2222f /* 128 bits */ + beq 1111f /* 192 bits */ + round_Nx \enc, v17, \i0, \i1, \i2, \i3 + round_Nx \enc, v18, \i0, \i1, \i2, \i3 +1111: round_Nx \enc, v19, \i0, \i1, \i2, \i3 + round_Nx \enc, v20, \i0, \i1, \i2, \i3 +2222: .irp key, v21, v22, v23, v24, v25, v26, v27, v28, v29 + round_Nx \enc, \key, \i0, \i1, \i2, \i3 + .endr + fin_round_Nx \enc, v30, v31, \i0, \i1, \i2, \i3 + .endm + + .macro encrypt_block, in, rounds, t0, t1, t2 + do_block_Nx e, \rounds, \in + .endm + + .macro encrypt_block2x, i0, i1, rounds, t0, t1, t2 + do_block_Nx e, \rounds, \i0, \i1 + .endm + + .macro encrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2 + do_block_Nx e, \rounds, \i0, \i1, \i2, \i3 + .endm + + .macro decrypt_block, in, rounds, t0, t1, t2 + do_block_Nx d, \rounds, \in + .endm + + .macro decrypt_block2x, i0, i1, rounds, t0, t1, t2 + do_block_Nx d, \rounds, \i0, \i1 + .endm + + .macro decrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2 + do_block_Nx d, \rounds, \i0, \i1, \i2, \i3 + .endm + +#include "aes-modes.S" diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c new file mode 100644 index 000000000000..60f2f4c12256 --- /dev/null +++ b/arch/arm64/crypto/aes-glue.c @@ -0,0 +1,446 @@ +/* + * linux/arch/arm64/crypto/aes-glue.c - wrapper code for ARMv8 AES + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <asm/neon.h> +#include <asm/hwcap.h> +#include <crypto/aes.h> +#include <crypto/ablk_helper.h> +#include <crypto/algapi.h> +#include <linux/module.h> +#include <linux/cpufeature.h> + +#ifdef USE_V8_CRYPTO_EXTENSIONS +#define MODE "ce" +#define PRIO 300 +#define aes_ecb_encrypt ce_aes_ecb_encrypt +#define aes_ecb_decrypt ce_aes_ecb_decrypt +#define aes_cbc_encrypt ce_aes_cbc_encrypt +#define aes_cbc_decrypt ce_aes_cbc_decrypt +#define aes_ctr_encrypt ce_aes_ctr_encrypt +#define aes_xts_encrypt ce_aes_xts_encrypt +#define aes_xts_decrypt ce_aes_xts_decrypt +MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions"); +#else +#define MODE "neon" +#define PRIO 200 +#define aes_ecb_encrypt neon_aes_ecb_encrypt +#define aes_ecb_decrypt neon_aes_ecb_decrypt +#define aes_cbc_encrypt neon_aes_cbc_encrypt +#define aes_cbc_decrypt neon_aes_cbc_decrypt +#define aes_ctr_encrypt neon_aes_ctr_encrypt +#define aes_xts_encrypt neon_aes_xts_encrypt +#define aes_xts_decrypt neon_aes_xts_decrypt +MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON"); +MODULE_ALIAS("ecb(aes)"); +MODULE_ALIAS("cbc(aes)"); +MODULE_ALIAS("ctr(aes)"); +MODULE_ALIAS("xts(aes)"); +#endif + +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); +MODULE_LICENSE("GPL v2"); + +/* defined in aes-modes.S */ +asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], + int rounds, int blocks, int first); +asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], + int rounds, int blocks, int first); + +asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], + int rounds, int blocks, u8 iv[], int first); +asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], + int rounds, int blocks, u8 iv[], int first); + +asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], + int rounds, int blocks, u8 ctr[], int first); + +asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[], + int rounds, int blocks, u8 const rk2[], u8 iv[], + int first); +asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], + int rounds, int blocks, u8 const rk2[], u8 iv[], + int first); + +struct crypto_aes_xts_ctx { + struct crypto_aes_ctx key1; + struct crypto_aes_ctx __aligned(8) key2; +}; + +static int xts_set_key(struct crypto_tfm *tfm, const u8 *in_key, + unsigned int key_len) +{ + struct crypto_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm); + int ret; + + ret = crypto_aes_expand_key(&ctx->key1, in_key, key_len / 2); + if (!ret) + ret = crypto_aes_expand_key(&ctx->key2, &in_key[key_len / 2], + key_len / 2); + if (!ret) + return 0; + + tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; +} + +static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + int err, first, rounds = 6 + ctx->key_length / 4; + struct blkcipher_walk walk; + unsigned int blocks; + + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_neon_begin(); + for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) { + aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr, + (u8 *)ctx->key_enc, rounds, blocks, first); + err = blkcipher_walk_done(desc, &walk, 0); + } + kernel_neon_end(); + return err; +} + +static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + int err, first, rounds = 6 + ctx->key_length / 4; + struct blkcipher_walk walk; + unsigned int blocks; + + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_neon_begin(); + for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) { + aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr, + (u8 *)ctx->key_dec, rounds, blocks, first); + err = blkcipher_walk_done(desc, &walk, 0); + } + kernel_neon_end(); + return err; +} + +static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + int err, first, rounds = 6 + ctx->key_length / 4; + struct blkcipher_walk walk; + unsigned int blocks; + + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_neon_begin(); + for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) { + aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr, + (u8 *)ctx->key_enc, rounds, blocks, walk.iv, + first); + err = blkcipher_walk_done(desc, &walk, 0); + } + kernel_neon_end(); + return err; +} + +static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + int err, first, rounds = 6 + ctx->key_length / 4; + struct blkcipher_walk walk; + unsigned int blocks; + + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_neon_begin(); + for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) { + aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr, + (u8 *)ctx->key_dec, rounds, blocks, walk.iv, + first); + err = blkcipher_walk_done(desc, &walk, 0); + } + kernel_neon_end(); + return err; +} + +static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + int err, first, rounds = 6 + ctx->key_length / 4; + struct blkcipher_walk walk; + int blocks; + + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE); + + first = 1; + kernel_neon_begin(); + while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) { + aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr, + (u8 *)ctx->key_enc, rounds, blocks, walk.iv, + first); + first = 0; + nbytes -= blocks * AES_BLOCK_SIZE; + if (nbytes && nbytes == walk.nbytes % AES_BLOCK_SIZE) + break; + err = blkcipher_walk_done(desc, &walk, + walk.nbytes % AES_BLOCK_SIZE); + } + if (nbytes) { + u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE; + u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE; + u8 __aligned(8) tail[AES_BLOCK_SIZE]; + + /* + * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need + * to tell aes_ctr_encrypt() to only read half a block. + */ + blocks = (nbytes <= 8) ? -1 : 1; + + aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc, rounds, + blocks, walk.iv, first); + memcpy(tdst, tail, nbytes); + err = blkcipher_walk_done(desc, &walk, 0); + } + kernel_neon_end(); + + return err; +} + +static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + int err, first, rounds = 6 + ctx->key1.key_length / 4; + struct blkcipher_walk walk; + unsigned int blocks; + + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_neon_begin(); + for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) { + aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr, + (u8 *)ctx->key1.key_enc, rounds, blocks, + (u8 *)ctx->key2.key_enc, walk.iv, first); + err = blkcipher_walk_done(desc, &walk, 0); + } + kernel_neon_end(); + + return err; +} + +static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + int err, first, rounds = 6 + ctx->key1.key_length / 4; + struct blkcipher_walk walk; + unsigned int blocks; + + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_neon_begin(); + for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) { + aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr, + (u8 *)ctx->key1.key_dec, rounds, blocks, + (u8 *)ctx->key2.key_enc, walk.iv, first); + err = blkcipher_walk_done(desc, &walk, 0); + } + kernel_neon_end(); + + return err; +} + +static struct crypto_alg aes_algs[] = { { + .cra_name = "__ecb-aes-" MODE, + .cra_driver_name = "__driver-ecb-aes-" MODE, + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = crypto_aes_set_key, + .encrypt = ecb_encrypt, + .decrypt = ecb_decrypt, + }, +}, { + .cra_name = "__cbc-aes-" MODE, + .cra_driver_name = "__driver-cbc-aes-" MODE, + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = crypto_aes_set_key, + .encrypt = cbc_encrypt, + .decrypt = cbc_decrypt, + }, +}, { + .cra_name = "__ctr-aes-" MODE, + .cra_driver_name = "__driver-ctr-aes-" MODE, + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct crypto_aes_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = crypto_aes_set_key, + .encrypt = ctr_encrypt, + .decrypt = ctr_encrypt, + }, +}, { + .cra_name = "__xts-aes-" MODE, + .cra_driver_name = "__driver-xts-aes-" MODE, + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_xts_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_blkcipher = { + .min_keysize = 2 * AES_MIN_KEY_SIZE, + .max_keysize = 2 * AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = xts_set_key, + .encrypt = xts_encrypt, + .decrypt = xts_decrypt, + }, +}, { + .cra_name = "ecb(aes)", + .cra_driver_name = "ecb-aes-" MODE, + .cra_priority = PRIO, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_helper_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_init = ablk_init, + .cra_exit = ablk_exit, + .cra_ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + } +}, { + .cra_name = "cbc(aes)", + .cra_driver_name = "cbc-aes-" MODE, + .cra_priority = PRIO, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_helper_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_init = ablk_init, + .cra_exit = ablk_exit, + .cra_ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + } +}, { + .cra_name = "ctr(aes)", + .cra_driver_name = "ctr-aes-" MODE, + .cra_priority = PRIO, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct async_helper_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_init = ablk_init, + .cra_exit = ablk_exit, + .cra_ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + } +}, { + .cra_name = "xts(aes)", + .cra_driver_name = "xts-aes-" MODE, + .cra_priority = PRIO, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_helper_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_init = ablk_init, + .cra_exit = ablk_exit, + .cra_ablkcipher = { + .min_keysize = 2 * AES_MIN_KEY_SIZE, + .max_keysize = 2 * AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + } +} }; + +static int __init aes_init(void) +{ + return crypto_register_algs(aes_algs, ARRAY_SIZE(aes_algs)); +} + +static void __exit aes_exit(void) +{ + crypto_unregister_algs(aes_algs, ARRAY_SIZE(aes_algs)); +} + +#ifdef USE_V8_CRYPTO_EXTENSIONS +module_cpu_feature_match(AES, aes_init); +#else +module_init(aes_init); +#endif +module_exit(aes_exit); diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S new file mode 100644 index 000000000000..f6e372c528eb --- /dev/null +++ b/arch/arm64/crypto/aes-modes.S @@ -0,0 +1,532 @@ +/* + * linux/arch/arm64/crypto/aes-modes.S - chaining mode wrappers for AES + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* included by aes-ce.S and aes-neon.S */ + + .text + .align 4 + +/* + * There are several ways to instantiate this code: + * - no interleave, all inline + * - 2-way interleave, 2x calls out of line (-DINTERLEAVE=2) + * - 2-way interleave, all inline (-DINTERLEAVE=2 -DINTERLEAVE_INLINE) + * - 4-way interleave, 4x calls out of line (-DINTERLEAVE=4) + * - 4-way interleave, all inline (-DINTERLEAVE=4 -DINTERLEAVE_INLINE) + * + * Macros imported by this code: + * - enc_prepare - setup NEON registers for encryption + * - dec_prepare - setup NEON registers for decryption + * - enc_switch_key - change to new key after having prepared for encryption + * - encrypt_block - encrypt a single block + * - decrypt block - decrypt a single block + * - encrypt_block2x - encrypt 2 blocks in parallel (if INTERLEAVE == 2) + * - decrypt_block2x - decrypt 2 blocks in parallel (if INTERLEAVE == 2) + * - encrypt_block4x - encrypt 4 blocks in parallel (if INTERLEAVE == 4) + * - decrypt_block4x - decrypt 4 blocks in parallel (if INTERLEAVE == 4) + */ + +#if defined(INTERLEAVE) && !defined(INTERLEAVE_INLINE) +#define FRAME_PUSH stp x29, x30, [sp,#-16]! ; mov x29, sp +#define FRAME_POP ldp x29, x30, [sp],#16 + +#if INTERLEAVE == 2 + +aes_encrypt_block2x: + encrypt_block2x v0, v1, w3, x2, x6, w7 + ret +ENDPROC(aes_encrypt_block2x) + +aes_decrypt_block2x: + decrypt_block2x v0, v1, w3, x2, x6, w7 + ret +ENDPROC(aes_decrypt_block2x) + +#elif INTERLEAVE == 4 + +aes_encrypt_block4x: + encrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7 + ret +ENDPROC(aes_encrypt_block4x) + +aes_decrypt_block4x: + decrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7 + ret +ENDPROC(aes_decrypt_block4x) + +#else +#error INTERLEAVE should equal 2 or 4 +#endif + + .macro do_encrypt_block2x + bl aes_encrypt_block2x + .endm + + .macro do_decrypt_block2x + bl aes_decrypt_block2x + .endm + + .macro do_encrypt_block4x + bl aes_encrypt_block4x + .endm + + .macro do_decrypt_block4x + bl aes_decrypt_block4x + .endm + +#else +#define FRAME_PUSH +#define FRAME_POP + + .macro do_encrypt_block2x + encrypt_block2x v0, v1, w3, x2, x6, w7 + .endm + + .macro do_decrypt_block2x + decrypt_block2x v0, v1, w3, x2, x6, w7 + .endm + + .macro do_encrypt_block4x + encrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7 + .endm + + .macro do_decrypt_block4x + decrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7 + .endm + +#endif + + /* + * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, + * int blocks, int first) + * aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, + * int blocks, int first) + */ + +AES_ENTRY(aes_ecb_encrypt) + FRAME_PUSH + cbz w5, .LecbencloopNx + + enc_prepare w3, x2, x5 + +.LecbencloopNx: +#if INTERLEAVE >= 2 + subs w4, w4, #INTERLEAVE + bmi .Lecbenc1x +#if INTERLEAVE == 2 + ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */ + do_encrypt_block2x + st1 {v0.16b-v1.16b}, [x0], #32 +#else + ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */ + do_encrypt_block4x + st1 {v0.16b-v3.16b}, [x0], #64 +#endif + b .LecbencloopNx +.Lecbenc1x: + adds w4, w4, #INTERLEAVE + beq .Lecbencout +#endif +.Lecbencloop: + ld1 {v0.16b}, [x1], #16 /* get next pt block */ + encrypt_block v0, w3, x2, x5, w6 + st1 {v0.16b}, [x0], #16 + subs w4, w4, #1 + bne .Lecbencloop +.Lecbencout: + FRAME_POP + ret +AES_ENDPROC(aes_ecb_encrypt) + + +AES_ENTRY(aes_ecb_decrypt) + FRAME_PUSH + cbz w5, .LecbdecloopNx + + dec_prepare w3, x2, x5 + +.LecbdecloopNx: +#if INTERLEAVE >= 2 + subs w4, w4, #INTERLEAVE + bmi .Lecbdec1x +#if INTERLEAVE == 2 + ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */ + do_decrypt_block2x + st1 {v0.16b-v1.16b}, [x0], #32 +#else + ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */ + do_decrypt_block4x + st1 {v0.16b-v3.16b}, [x0], #64 +#endif + b .LecbdecloopNx +.Lecbdec1x: + adds w4, w4, #INTERLEAVE + beq .Lecbdecout +#endif +.Lecbdecloop: + ld1 {v0.16b}, [x1], #16 /* get next ct block */ + decrypt_block v0, w3, x2, x5, w6 + st1 {v0.16b}, [x0], #16 + subs w4, w4, #1 + bne .Lecbdecloop +.Lecbdecout: + FRAME_POP + ret +AES_ENDPROC(aes_ecb_decrypt) + + + /* + * aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, + * int blocks, u8 iv[], int first) + * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, + * int blocks, u8 iv[], int first) + */ + +AES_ENTRY(aes_cbc_encrypt) + cbz w6, .Lcbcencloop + + ld1 {v0.16b}, [x5] /* get iv */ + enc_prepare w3, x2, x5 + +.Lcbcencloop: + ld1 {v1.16b}, [x1], #16 /* get next pt block */ + eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */ + encrypt_block v0, w3, x2, x5, w6 + st1 {v0.16b}, [x0], #16 + subs w4, w4, #1 + bne .Lcbcencloop + ret +AES_ENDPROC(aes_cbc_encrypt) + + +AES_ENTRY(aes_cbc_decrypt) + FRAME_PUSH + cbz w6, .LcbcdecloopNx + + ld1 {v7.16b}, [x5] /* get iv */ + dec_prepare w3, x2, x5 + +.LcbcdecloopNx: +#if INTERLEAVE >= 2 + subs w4, w4, #INTERLEAVE + bmi .Lcbcdec1x +#if INTERLEAVE == 2 + ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */ + mov v2.16b, v0.16b + mov v3.16b, v1.16b + do_decrypt_block2x + eor v0.16b, v0.16b, v7.16b + eor v1.16b, v1.16b, v2.16b + mov v7.16b, v3.16b + st1 {v0.16b-v1.16b}, [x0], #32 +#else + ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */ + mov v4.16b, v0.16b + mov v5.16b, v1.16b + mov v6.16b, v2.16b + do_decrypt_block4x + sub x1, x1, #16 + eor v0.16b, v0.16b, v7.16b + eor v1.16b, v1.16b, v4.16b + ld1 {v7.16b}, [x1], #16 /* reload 1 ct block */ + eor v2.16b, v2.16b, v5.16b + eor v3.16b, v3.16b, v6.16b + st1 {v0.16b-v3.16b}, [x0], #64 +#endif + b .LcbcdecloopNx +.Lcbcdec1x: + adds w4, w4, #INTERLEAVE + beq .Lcbcdecout +#endif +.Lcbcdecloop: + ld1 {v1.16b}, [x1], #16 /* get next ct block */ + mov v0.16b, v1.16b /* ...and copy to v0 */ + decrypt_block v0, w3, x2, x5, w6 + eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */ + mov v7.16b, v1.16b /* ct is next iv */ + st1 {v0.16b}, [x0], #16 + subs w4, w4, #1 + bne .Lcbcdecloop +.Lcbcdecout: + FRAME_POP + ret +AES_ENDPROC(aes_cbc_decrypt) + + + /* + * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, + * int blocks, u8 ctr[], int first) + */ + +AES_ENTRY(aes_ctr_encrypt) + FRAME_PUSH + cbnz w6, .Lctrfirst /* 1st time around? */ + umov x5, v4.d[1] /* keep swabbed ctr in reg */ + rev x5, x5 +#if INTERLEAVE >= 2 + cmn w5, w4 /* 32 bit overflow? */ + bcs .Lctrinc + add x5, x5, #1 /* increment BE ctr */ + b .LctrincNx +#else + b .Lctrinc +#endif +.Lctrfirst: + enc_prepare w3, x2, x6 + ld1 {v4.16b}, [x5] + umov x5, v4.d[1] /* keep swabbed ctr in reg */ + rev x5, x5 +#if INTERLEAVE >= 2 + cmn w5, w4 /* 32 bit overflow? */ + bcs .Lctrloop +.LctrloopNx: + subs w4, w4, #INTERLEAVE + bmi .Lctr1x +#if INTERLEAVE == 2 + mov v0.8b, v4.8b + mov v1.8b, v4.8b + rev x7, x5 + add x5, x5, #1 + ins v0.d[1], x7 + rev x7, x5 + add x5, x5, #1 + ins v1.d[1], x7 + ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */ + do_encrypt_block2x + eor v0.16b, v0.16b, v2.16b + eor v1.16b, v1.16b, v3.16b + st1 {v0.16b-v1.16b}, [x0], #32 +#else + ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */ + dup v7.4s, w5 + mov v0.16b, v4.16b + add v7.4s, v7.4s, v8.4s + mov v1.16b, v4.16b + rev32 v8.16b, v7.16b + mov v2.16b, v4.16b + mov v3.16b, v4.16b + mov v1.s[3], v8.s[0] + mov v2.s[3], v8.s[1] + mov v3.s[3], v8.s[2] + ld1 {v5.16b-v7.16b}, [x1], #48 /* get 3 input blocks */ + do_encrypt_block4x + eor v0.16b, v5.16b, v0.16b + ld1 {v5.16b}, [x1], #16 /* get 1 input block */ + eor v1.16b, v6.16b, v1.16b + eor v2.16b, v7.16b, v2.16b + eor v3.16b, v5.16b, v3.16b + st1 {v0.16b-v3.16b}, [x0], #64 + add x5, x5, #INTERLEAVE +#endif + cbz w4, .LctroutNx +.LctrincNx: + rev x7, x5 + ins v4.d[1], x7 + b .LctrloopNx +.LctroutNx: + sub x5, x5, #1 + rev x7, x5 + ins v4.d[1], x7 + b .Lctrout +.Lctr1x: + adds w4, w4, #INTERLEAVE + beq .Lctrout +#endif +.Lctrloop: + mov v0.16b, v4.16b + encrypt_block v0, w3, x2, x6, w7 + subs w4, w4, #1 + bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */ + ld1 {v3.16b}, [x1], #16 + eor v3.16b, v0.16b, v3.16b + st1 {v3.16b}, [x0], #16 + beq .Lctrout +.Lctrinc: + adds x5, x5, #1 /* increment BE ctr */ + rev x7, x5 + ins v4.d[1], x7 + bcc .Lctrloop /* no overflow? */ + umov x7, v4.d[0] /* load upper word of ctr */ + rev x7, x7 /* ... to handle the carry */ + add x7, x7, #1 + rev x7, x7 + ins v4.d[0], x7 + b .Lctrloop +.Lctrhalfblock: + ld1 {v3.8b}, [x1] + eor v3.8b, v0.8b, v3.8b + st1 {v3.8b}, [x0] +.Lctrout: + FRAME_POP + ret +AES_ENDPROC(aes_ctr_encrypt) + .ltorg + + + /* + * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds, + * int blocks, u8 const rk2[], u8 iv[], int first) + * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds, + * int blocks, u8 const rk2[], u8 iv[], int first) + */ + + .macro next_tweak, out, in, const, tmp + sshr \tmp\().2d, \in\().2d, #63 + and \tmp\().16b, \tmp\().16b, \const\().16b + add \out\().2d, \in\().2d, \in\().2d + ext \tmp\().16b, \tmp\().16b, \tmp\().16b, #8 + eor \out\().16b, \out\().16b, \tmp\().16b + .endm + +.Lxts_mul_x: + .word 1, 0, 0x87, 0 + +AES_ENTRY(aes_xts_encrypt) + FRAME_PUSH + cbz w7, .LxtsencloopNx + + ld1 {v4.16b}, [x6] + enc_prepare w3, x5, x6 + encrypt_block v4, w3, x5, x6, w7 /* first tweak */ + enc_switch_key w3, x2, x6 + ldr q7, .Lxts_mul_x + b .LxtsencNx + +.LxtsencloopNx: + ldr q7, .Lxts_mul_x + next_tweak v4, v4, v7, v8 +.LxtsencNx: +#if INTERLEAVE >= 2 + subs w4, w4, #INTERLEAVE + bmi .Lxtsenc1x +#if INTERLEAVE == 2 + ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */ + next_tweak v5, v4, v7, v8 + eor v0.16b, v0.16b, v4.16b + eor v1.16b, v1.16b, v5.16b + do_encrypt_block2x + eor v0.16b, v0.16b, v4.16b + eor v1.16b, v1.16b, v5.16b + st1 {v0.16b-v1.16b}, [x0], #32 + cbz w4, .LxtsencoutNx + next_tweak v4, v5, v7, v8 + b .LxtsencNx +.LxtsencoutNx: + mov v4.16b, v5.16b + b .Lxtsencout +#else + ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */ + next_tweak v5, v4, v7, v8 + eor v0.16b, v0.16b, v4.16b + next_tweak v6, v5, v7, v8 + eor v1.16b, v1.16b, v5.16b + eor v2.16b, v2.16b, v6.16b + next_tweak v7, v6, v7, v8 + eor v3.16b, v3.16b, v7.16b + do_encrypt_block4x + eor v3.16b, v3.16b, v7.16b + eor v0.16b, v0.16b, v4.16b + eor v1.16b, v1.16b, v5.16b + eor v2.16b, v2.16b, v6.16b + st1 {v0.16b-v3.16b}, [x0], #64 + mov v4.16b, v7.16b + cbz w4, .Lxtsencout + b .LxtsencloopNx +#endif +.Lxtsenc1x: + adds w4, w4, #INTERLEAVE + beq .Lxtsencout +#endif +.Lxtsencloop: + ld1 {v1.16b}, [x1], #16 + eor v0.16b, v1.16b, v4.16b + encrypt_block v0, w3, x2, x6, w7 + eor v0.16b, v0.16b, v4.16b + st1 {v0.16b}, [x0], #16 + subs w4, w4, #1 + beq .Lxtsencout + next_tweak v4, v4, v7, v8 + b .Lxtsencloop +.Lxtsencout: + FRAME_POP + ret +AES_ENDPROC(aes_xts_encrypt) + + +AES_ENTRY(aes_xts_decrypt) + FRAME_PUSH + cbz w7, .LxtsdecloopNx + + ld1 {v4.16b}, [x6] + enc_prepare w3, x5, x6 + encrypt_block v4, w3, x5, x6, w7 /* first tweak */ + dec_prepare w3, x2, x6 + ldr q7, .Lxts_mul_x + b .LxtsdecNx + +.LxtsdecloopNx: + ldr q7, .Lxts_mul_x + next_tweak v4, v4, v7, v8 +.LxtsdecNx: +#if INTERLEAVE >= 2 + subs w4, w4, #INTERLEAVE + bmi .Lxtsdec1x +#if INTERLEAVE == 2 + ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */ + next_tweak v5, v4, v7, v8 + eor v0.16b, v0.16b, v4.16b + eor v1.16b, v1.16b, v5.16b + do_decrypt_block2x + eor v0.16b, v0.16b, v4.16b + eor v1.16b, v1.16b, v5.16b + st1 {v0.16b-v1.16b}, [x0], #32 + cbz w4, .LxtsdecoutNx + next_tweak v4, v5, v7, v8 + b .LxtsdecNx +.LxtsdecoutNx: + mov v4.16b, v5.16b + b .Lxtsdecout +#else + ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */ + next_tweak v5, v4, v7, v8 + eor v0.16b, v0.16b, v4.16b + next_tweak v6, v5, v7, v8 + eor v1.16b, v1.16b, v5.16b + eor v2.16b, v2.16b, v6.16b + next_tweak v7, v6, v7, v8 + eor v3.16b, v3.16b, v7.16b + do_decrypt_block4x + eor v3.16b, v3.16b, v7.16b + eor v0.16b, v0.16b, v4.16b + eor v1.16b, v1.16b, v5.16b + eor v2.16b, v2.16b, v6.16b + st1 {v0.16b-v3.16b}, [x0], #64 + mov v4.16b, v7.16b + cbz w4, .Lxtsdecout + b .LxtsdecloopNx +#endif +.Lxtsdec1x: + adds w4, w4, #INTERLEAVE + beq .Lxtsdecout +#endif +.Lxtsdecloop: + ld1 {v1.16b}, [x1], #16 + eor v0.16b, v1.16b, v4.16b + decrypt_block v0, w3, x2, x6, w7 + eor v0.16b, v0.16b, v4.16b + st1 {v0.16b}, [x0], #16 + subs w4, w4, #1 + beq .Lxtsdecout + next_tweak v4, v4, v7, v8 + b .Lxtsdecloop +.Lxtsdecout: + FRAME_POP + ret +AES_ENDPROC(aes_xts_decrypt) diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S new file mode 100644 index 000000000000..b93170e1cc93 --- /dev/null +++ b/arch/arm64/crypto/aes-neon.S @@ -0,0 +1,382 @@ +/* + * linux/arch/arm64/crypto/aes-neon.S - AES cipher for ARMv8 NEON + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> + +#define AES_ENTRY(func) ENTRY(neon_ ## func) +#define AES_ENDPROC(func) ENDPROC(neon_ ## func) + + /* multiply by polynomial 'x' in GF(2^8) */ + .macro mul_by_x, out, in, temp, const + sshr \temp, \in, #7 + add \out, \in, \in + and \temp, \temp, \const + eor \out, \out, \temp + .endm + + /* preload the entire Sbox */ + .macro prepare, sbox, shiftrows, temp + adr \temp, \sbox + movi v12.16b, #0x40 + ldr q13, \shiftrows + movi v14.16b, #0x1b + ld1 {v16.16b-v19.16b}, [\temp], #64 + ld1 {v20.16b-v23.16b}, [\temp], #64 + ld1 {v24.16b-v27.16b}, [\temp], #64 + ld1 {v28.16b-v31.16b}, [\temp] + .endm + + /* do preload for encryption */ + .macro enc_prepare, ignore0, ignore1, temp + prepare .LForward_Sbox, .LForward_ShiftRows, \temp + .endm + + .macro enc_switch_key, ignore0, ignore1, temp + /* do nothing */ + .endm + + /* do preload for decryption */ + .macro dec_prepare, ignore0, ignore1, temp + prepare .LReverse_Sbox, .LReverse_ShiftRows, \temp + .endm + + /* apply SubBytes transformation using the the preloaded Sbox */ + .macro sub_bytes, in + sub v9.16b, \in\().16b, v12.16b + tbl \in\().16b, {v16.16b-v19.16b}, \in\().16b + sub v10.16b, v9.16b, v12.16b + tbx \in\().16b, {v20.16b-v23.16b}, v9.16b + sub v11.16b, v10.16b, v12.16b + tbx \in\().16b, {v24.16b-v27.16b}, v10.16b + tbx \in\().16b, {v28.16b-v31.16b}, v11.16b + .endm + + /* apply MixColumns transformation */ + .macro mix_columns, in + mul_by_x v10.16b, \in\().16b, v9.16b, v14.16b + rev32 v8.8h, \in\().8h + eor \in\().16b, v10.16b, \in\().16b + shl v9.4s, v8.4s, #24 + shl v11.4s, \in\().4s, #24 + sri v9.4s, v8.4s, #8 + sri v11.4s, \in\().4s, #8 + eor v9.16b, v9.16b, v8.16b + eor v10.16b, v10.16b, v9.16b + eor \in\().16b, v10.16b, v11.16b + .endm + + /* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */ + .macro inv_mix_columns, in + mul_by_x v11.16b, \in\().16b, v10.16b, v14.16b + mul_by_x v11.16b, v11.16b, v10.16b, v14.16b + eor \in\().16b, \in\().16b, v11.16b + rev32 v11.8h, v11.8h + eor \in\().16b, \in\().16b, v11.16b + mix_columns \in + .endm + + .macro do_block, enc, in, rounds, rk, rkp, i + ld1 {v15.16b}, [\rk] + add \rkp, \rk, #16 + mov \i, \rounds +1111: eor \in\().16b, \in\().16b, v15.16b /* ^round key */ + tbl \in\().16b, {\in\().16b}, v13.16b /* ShiftRows */ + sub_bytes \in + ld1 {v15.16b}, [\rkp], #16 + subs \i, \i, #1 + beq 2222f + .if \enc == 1 + mix_columns \in + .else + inv_mix_columns \in + .endif + b 1111b +2222: eor \in\().16b, \in\().16b, v15.16b /* ^round key */ + .endm + + .macro encrypt_block, in, rounds, rk, rkp, i + do_block 1, \in, \rounds, \rk, \rkp, \i + .endm + + .macro decrypt_block, in, rounds, rk, rkp, i + do_block 0, \in, \rounds, \rk, \rkp, \i + .endm + + /* + * Interleaved versions: functionally equivalent to the + * ones above, but applied to 2 or 4 AES states in parallel. + */ + + .macro sub_bytes_2x, in0, in1 + sub v8.16b, \in0\().16b, v12.16b + sub v9.16b, \in1\().16b, v12.16b + tbl \in0\().16b, {v16.16b-v19.16b}, \in0\().16b + tbl \in1\().16b, {v16.16b-v19.16b}, \in1\().16b + sub v10.16b, v8.16b, v12.16b + sub v11.16b, v9.16b, v12.16b + tbx \in0\().16b, {v20.16b-v23.16b}, v8.16b + tbx \in1\().16b, {v20.16b-v23.16b}, v9.16b + sub v8.16b, v10.16b, v12.16b + sub v9.16b, v11.16b, v12.16b + tbx \in0\().16b, {v24.16b-v27.16b}, v10.16b + tbx \in1\().16b, {v24.16b-v27.16b}, v11.16b + tbx \in0\().16b, {v28.16b-v31.16b}, v8.16b + tbx \in1\().16b, {v28.16b-v31.16b}, v9.16b + .endm + + .macro sub_bytes_4x, in0, in1, in2, in3 + sub v8.16b, \in0\().16b, v12.16b + tbl \in0\().16b, {v16.16b-v19.16b}, \in0\().16b + sub v9.16b, \in1\().16b, v12.16b + tbl \in1\().16b, {v16.16b-v19.16b}, \in1\().16b + sub v10.16b, \in2\().16b, v12.16b + tbl \in2\().16b, {v16.16b-v19.16b}, \in2\().16b + sub v11.16b, \in3\().16b, v12.16b + tbl \in3\().16b, {v16.16b-v19.16b}, \in3\().16b + tbx \in0\().16b, {v20.16b-v23.16b}, v8.16b + tbx \in1\().16b, {v20.16b-v23.16b}, v9.16b + sub v8.16b, v8.16b, v12.16b + tbx \in2\().16b, {v20.16b-v23.16b}, v10.16b + sub v9.16b, v9.16b, v12.16b + tbx \in3\().16b, {v20.16b-v23.16b}, v11.16b + sub v10.16b, v10.16b, v12.16b + tbx \in0\().16b, {v24.16b-v27.16b}, v8.16b + sub v11.16b, v11.16b, v12.16b + tbx \in1\().16b, {v24.16b-v27.16b}, v9.16b + sub v8.16b, v8.16b, v12.16b + tbx \in2\().16b, {v24.16b-v27.16b}, v10.16b + sub v9.16b, v9.16b, v12.16b + tbx \in3\().16b, {v24.16b-v27.16b}, v11.16b + sub v10.16b, v10.16b, v12.16b + tbx \in0\().16b, {v28.16b-v31.16b}, v8.16b + sub v11.16b, v11.16b, v12.16b + tbx \in1\().16b, {v28.16b-v31.16b}, v9.16b + tbx \in2\().16b, {v28.16b-v31.16b}, v10.16b + tbx \in3\().16b, {v28.16b-v31.16b}, v11.16b + .endm + + .macro mul_by_x_2x, out0, out1, in0, in1, tmp0, tmp1, const + sshr \tmp0\().16b, \in0\().16b, #7 + add \out0\().16b, \in0\().16b, \in0\().16b + sshr \tmp1\().16b, \in1\().16b, #7 + and \tmp0\().16b, \tmp0\().16b, \const\().16b + add \out1\().16b, \in1\().16b, \in1\().16b + and \tmp1\().16b, \tmp1\().16b, \const\().16b + eor \out0\().16b, \out0\().16b, \tmp0\().16b + eor \out1\().16b, \out1\().16b, \tmp1\().16b + .endm + + .macro mix_columns_2x, in0, in1 + mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14 + rev32 v10.8h, \in0\().8h + rev32 v11.8h, \in1\().8h + eor \in0\().16b, v8.16b, \in0\().16b + eor \in1\().16b, v9.16b, \in1\().16b + shl v12.4s, v10.4s, #24 + shl v13.4s, v11.4s, #24 + eor v8.16b, v8.16b, v10.16b + sri v12.4s, v10.4s, #8 + shl v10.4s, \in0\().4s, #24 + eor v9.16b, v9.16b, v11.16b + sri v13.4s, v11.4s, #8 + shl v11.4s, \in1\().4s, #24 + sri v10.4s, \in0\().4s, #8 + eor \in0\().16b, v8.16b, v12.16b + sri v11.4s, \in1\().4s, #8 + eor \in1\().16b, v9.16b, v13.16b + eor \in0\().16b, v10.16b, \in0\().16b + eor \in1\().16b, v11.16b, \in1\().16b + .endm + + .macro inv_mix_cols_2x, in0, in1 + mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14 + mul_by_x_2x v8, v9, v8, v9, v10, v11, v14 + eor \in0\().16b, \in0\().16b, v8.16b + eor \in1\().16b, \in1\().16b, v9.16b + rev32 v8.8h, v8.8h + rev32 v9.8h, v9.8h + eor \in0\().16b, \in0\().16b, v8.16b + eor \in1\().16b, \in1\().16b, v9.16b + mix_columns_2x \in0, \in1 + .endm + + .macro inv_mix_cols_4x, in0, in1, in2, in3 + mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14 + mul_by_x_2x v10, v11, \in2, \in3, v12, v13, v14 + mul_by_x_2x v8, v9, v8, v9, v12, v13, v14 + mul_by_x_2x v10, v11, v10, v11, v12, v13, v14 + eor \in0\().16b, \in0\().16b, v8.16b + eor \in1\().16b, \in1\().16b, v9.16b + eor \in2\().16b, \in2\().16b, v10.16b + eor \in3\().16b, \in3\().16b, v11.16b + rev32 v8.8h, v8.8h + rev32 v9.8h, v9.8h + rev32 v10.8h, v10.8h + rev32 v11.8h, v11.8h + eor \in0\().16b, \in0\().16b, v8.16b + eor \in1\().16b, \in1\().16b, v9.16b + eor \in2\().16b, \in2\().16b, v10.16b + eor \in3\().16b, \in3\().16b, v11.16b + mix_columns_2x \in0, \in1 + mix_columns_2x \in2, \in3 + .endm + + .macro do_block_2x, enc, in0, in1 rounds, rk, rkp, i + ld1 {v15.16b}, [\rk] + add \rkp, \rk, #16 + mov \i, \rounds +1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */ + eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */ + sub_bytes_2x \in0, \in1 + tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */ + tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */ + ld1 {v15.16b}, [\rkp], #16 + subs \i, \i, #1 + beq 2222f + .if \enc == 1 + mix_columns_2x \in0, \in1 + ldr q13, .LForward_ShiftRows + .else + inv_mix_cols_2x \in0, \in1 + ldr q13, .LReverse_ShiftRows + .endif + movi v12.16b, #0x40 + b 1111b +2222: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */ + eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */ + .endm + + .macro do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i + ld1 {v15.16b}, [\rk] + add \rkp, \rk, #16 + mov \i, \rounds +1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */ + eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */ + eor \in2\().16b, \in2\().16b, v15.16b /* ^round key */ + eor \in3\().16b, \in3\().16b, v15.16b /* ^round key */ + sub_bytes_4x \in0, \in1, \in2, \in3 + tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */ + tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */ + tbl \in2\().16b, {\in2\().16b}, v13.16b /* ShiftRows */ + tbl \in3\().16b, {\in3\().16b}, v13.16b /* ShiftRows */ + ld1 {v15.16b}, [\rkp], #16 + subs \i, \i, #1 + beq 2222f + .if \enc == 1 + mix_columns_2x \in0, \in1 + mix_columns_2x \in2, \in3 + ldr q13, .LForward_ShiftRows + .else + inv_mix_cols_4x \in0, \in1, \in2, \in3 + ldr q13, .LReverse_ShiftRows + .endif + movi v12.16b, #0x40 + b 1111b +2222: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */ + eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */ + eor \in2\().16b, \in2\().16b, v15.16b /* ^round key */ + eor \in3\().16b, \in3\().16b, v15.16b /* ^round key */ + .endm + + .macro encrypt_block2x, in0, in1, rounds, rk, rkp, i + do_block_2x 1, \in0, \in1, \rounds, \rk, \rkp, \i + .endm + + .macro decrypt_block2x, in0, in1, rounds, rk, rkp, i + do_block_2x 0, \in0, \in1, \rounds, \rk, \rkp, \i + .endm + + .macro encrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i + do_block_4x 1, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i + .endm + + .macro decrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i + do_block_4x 0, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i + .endm + +#include "aes-modes.S" + + .text + .align 4 +.LForward_ShiftRows: + .byte 0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3 + .byte 0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb + +.LReverse_ShiftRows: + .byte 0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb + .byte 0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3 + +.LForward_Sbox: + .byte 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5 + .byte 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76 + .byte 0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0 + .byte 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0 + .byte 0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc + .byte 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15 + .byte 0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a + .byte 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75 + .byte 0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0 + .byte 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84 + .byte 0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b + .byte 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf + .byte 0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85 + .byte 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8 + .byte 0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5 + .byte 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2 + .byte 0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17 + .byte 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73 + .byte 0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88 + .byte 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb + .byte 0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c + .byte 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79 + .byte 0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9 + .byte 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08 + .byte 0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6 + .byte 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a + .byte 0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e + .byte 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e + .byte 0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94 + .byte 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf + .byte 0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68 + .byte 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16 + +.LReverse_Sbox: + .byte 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38 + .byte 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb + .byte 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87 + .byte 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb + .byte 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d + .byte 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e + .byte 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2 + .byte 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25 + .byte 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16 + .byte 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92 + .byte 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda + .byte 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84 + .byte 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a + .byte 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06 + .byte 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02 + .byte 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b + .byte 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea + .byte 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73 + .byte 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85 + .byte 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e + .byte 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89 + .byte 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b + .byte 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20 + .byte 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4 + .byte 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31 + .byte 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f + .byte 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d + .byte 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef + .byte 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0 + .byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61 + .byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26 + .byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S new file mode 100644 index 000000000000..b9e6eaf41c9b --- /dev/null +++ b/arch/arm64/crypto/ghash-ce-core.S @@ -0,0 +1,95 @@ +/* + * Accelerated GHASH implementation with ARMv8 PMULL instructions. + * + * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> + * + * Based on arch/x86/crypto/ghash-pmullni-intel_asm.S + * + * Copyright (c) 2009 Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + * Vinodh Gopal + * Erdinc Ozturk + * Deniz Karakoyunlu + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + + DATA .req v0 + SHASH .req v1 + IN1 .req v2 + T1 .req v2 + T2 .req v3 + T3 .req v4 + VZR .req v5 + + .text + .arch armv8-a+crypto + + /* + * void pmull_ghash_update(int blocks, u64 dg[], const char *src, + * struct ghash_key const *k, const char *head) + */ +ENTRY(pmull_ghash_update) + ld1 {DATA.16b}, [x1] + ld1 {SHASH.16b}, [x3] + eor VZR.16b, VZR.16b, VZR.16b + + /* do the head block first, if supplied */ + cbz x4, 0f + ld1 {IN1.2d}, [x4] + b 1f + +0: ld1 {IN1.2d}, [x2], #16 + sub w0, w0, #1 +1: ext IN1.16b, IN1.16b, IN1.16b, #8 +CPU_LE( rev64 IN1.16b, IN1.16b ) + eor DATA.16b, DATA.16b, IN1.16b + + /* multiply DATA by SHASH in GF(2^128) */ + ext T2.16b, DATA.16b, DATA.16b, #8 + ext T3.16b, SHASH.16b, SHASH.16b, #8 + eor T2.16b, T2.16b, DATA.16b + eor T3.16b, T3.16b, SHASH.16b + + pmull2 T1.1q, SHASH.2d, DATA.2d // a1 * b1 + pmull DATA.1q, SHASH.1d, DATA.1d // a0 * b0 + pmull T2.1q, T2.1d, T3.1d // (a1 + a0)(b1 + b0) + eor T2.16b, T2.16b, T1.16b // (a0 * b1) + (a1 * b0) + eor T2.16b, T2.16b, DATA.16b + + ext T3.16b, VZR.16b, T2.16b, #8 + ext T2.16b, T2.16b, VZR.16b, #8 + eor DATA.16b, DATA.16b, T3.16b + eor T1.16b, T1.16b, T2.16b // <T1:DATA> is result of + // carry-less multiplication + + /* first phase of the reduction */ + shl T3.2d, DATA.2d, #1 + eor T3.16b, T3.16b, DATA.16b + shl T3.2d, T3.2d, #5 + eor T3.16b, T3.16b, DATA.16b + shl T3.2d, T3.2d, #57 + ext T2.16b, VZR.16b, T3.16b, #8 + ext T3.16b, T3.16b, VZR.16b, #8 + eor DATA.16b, DATA.16b, T2.16b + eor T1.16b, T1.16b, T3.16b + + /* second phase of the reduction */ + ushr T2.2d, DATA.2d, #5 + eor T2.16b, T2.16b, DATA.16b + ushr T2.2d, T2.2d, #1 + eor T2.16b, T2.16b, DATA.16b + ushr T2.2d, T2.2d, #1 + eor T1.16b, T1.16b, T2.16b + eor DATA.16b, DATA.16b, T1.16b + + cbnz w0, 0b + + st1 {DATA.16b}, [x1] + ret +ENDPROC(pmull_ghash_update) diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c new file mode 100644 index 000000000000..b92baf3f68c7 --- /dev/null +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -0,0 +1,155 @@ +/* + * Accelerated GHASH implementation with ARMv8 PMULL instructions. + * + * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include <asm/neon.h> +#include <asm/unaligned.h> +#include <crypto/internal/hash.h> +#include <linux/cpufeature.h> +#include <linux/crypto.h> +#include <linux/module.h> + +MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions"); +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); +MODULE_LICENSE("GPL v2"); + +#define GHASH_BLOCK_SIZE 16 +#define GHASH_DIGEST_SIZE 16 + +struct ghash_key { + u64 a; + u64 b; +}; + +struct ghash_desc_ctx { + u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)]; + u8 buf[GHASH_BLOCK_SIZE]; + u32 count; +}; + +asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src, + struct ghash_key const *k, const char *head); + +static int ghash_init(struct shash_desc *desc) +{ + struct ghash_desc_ctx *ctx = shash_desc_ctx(desc); + + *ctx = (struct ghash_desc_ctx){}; + return 0; +} + +static int ghash_update(struct shash_desc *desc, const u8 *src, + unsigned int len) +{ + struct ghash_desc_ctx *ctx = shash_desc_ctx(desc); + unsigned int partial = ctx->count % GHASH_BLOCK_SIZE; + + ctx->count += len; + + if ((partial + len) >= GHASH_BLOCK_SIZE) { + struct ghash_key *key = crypto_shash_ctx(desc->tfm); + int blocks; + + if (partial) { + int p = GHASH_BLOCK_SIZE - partial; + + memcpy(ctx->buf + partial, src, p); + src += p; + len -= p; + } + + blocks = len / GHASH_BLOCK_SIZE; + len %= GHASH_BLOCK_SIZE; + + kernel_neon_begin_partial(6); + pmull_ghash_update(blocks, ctx->digest, src, key, + partial ? ctx->buf : NULL); + kernel_neon_end(); + src += blocks * GHASH_BLOCK_SIZE; + } + if (len) + memcpy(ctx->buf + partial, src, len); + return 0; +} + +static int ghash_final(struct shash_desc *desc, u8 *dst) +{ + struct ghash_desc_ctx *ctx = shash_desc_ctx(desc); + unsigned int partial = ctx->count % GHASH_BLOCK_SIZE; + + if (partial) { + struct ghash_key *key = crypto_shash_ctx(desc->tfm); + + memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial); + + kernel_neon_begin_partial(6); + pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL); + kernel_neon_end(); + } + put_unaligned_be64(ctx->digest[1], dst); + put_unaligned_be64(ctx->digest[0], dst + 8); + + *ctx = (struct ghash_desc_ctx){}; + return 0; +} + +static int ghash_setkey(struct crypto_shash *tfm, + const u8 *inkey, unsigned int keylen) +{ + struct ghash_key *key = crypto_shash_ctx(tfm); + u64 a, b; + + if (keylen != GHASH_BLOCK_SIZE) { + crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; + } + + /* perform multiplication by 'x' in GF(2^128) */ + b = get_unaligned_be64(inkey); + a = get_unaligned_be64(inkey + 8); + + key->a = (a << 1) | (b >> 63); + key->b = (b << 1) | (a >> 63); + + if (b >> 63) + key->b ^= 0xc200000000000000UL; + + return 0; +} + +static struct shash_alg ghash_alg = { + .digestsize = GHASH_DIGEST_SIZE, + .init = ghash_init, + .update = ghash_update, + .final = ghash_final, + .setkey = ghash_setkey, + .descsize = sizeof(struct ghash_desc_ctx), + .base = { + .cra_name = "ghash", + .cra_driver_name = "ghash-ce", + .cra_priority = 200, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = GHASH_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct ghash_key), + .cra_module = THIS_MODULE, + }, +}; + +static int __init ghash_ce_mod_init(void) +{ + return crypto_register_shash(&ghash_alg); +} + +static void __exit ghash_ce_mod_exit(void) +{ + crypto_unregister_shash(&ghash_alg); +} + +module_cpu_feature_match(PMULL, ghash_ce_mod_init); +module_exit(ghash_ce_mod_exit); diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S new file mode 100644 index 000000000000..09d57d98609c --- /dev/null +++ b/arch/arm64/crypto/sha1-ce-core.S @@ -0,0 +1,153 @@ +/* + * sha1-ce-core.S - SHA-1 secure hash using ARMv8 Crypto Extensions + * + * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + + .text + .arch armv8-a+crypto + + k0 .req v0 + k1 .req v1 + k2 .req v2 + k3 .req v3 + + t0 .req v4 + t1 .req v5 + + dga .req q6 + dgav .req v6 + dgb .req s7 + dgbv .req v7 + + dg0q .req q12 + dg0s .req s12 + dg0v .req v12 + dg1s .req s13 + dg1v .req v13 + dg2s .req s14 + + .macro add_only, op, ev, rc, s0, dg1 + .ifc \ev, ev + add t1.4s, v\s0\().4s, \rc\().4s + sha1h dg2s, dg0s + .ifnb \dg1 + sha1\op dg0q, \dg1, t0.4s + .else + sha1\op dg0q, dg1s, t0.4s + .endif + .else + .ifnb \s0 + add t0.4s, v\s0\().4s, \rc\().4s + .endif + sha1h dg1s, dg0s + sha1\op dg0q, dg2s, t1.4s + .endif + .endm + + .macro add_update, op, ev, rc, s0, s1, s2, s3, dg1 + sha1su0 v\s0\().4s, v\s1\().4s, v\s2\().4s + add_only \op, \ev, \rc, \s1, \dg1 + sha1su1 v\s0\().4s, v\s3\().4s + .endm + + /* + * The SHA1 round constants + */ + .align 4 +.Lsha1_rcon: + .word 0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6 + + /* + * void sha1_ce_transform(int blocks, u8 const *src, u32 *state, + * u8 *head, long bytes) + */ +ENTRY(sha1_ce_transform) + /* load round constants */ + adr x6, .Lsha1_rcon + ld1r {k0.4s}, [x6], #4 + ld1r {k1.4s}, [x6], #4 + ld1r {k2.4s}, [x6], #4 + ld1r {k3.4s}, [x6] + + /* load state */ + ldr dga, [x2] + ldr dgb, [x2, #16] + + /* load partial state (if supplied) */ + cbz x3, 0f + ld1 {v8.4s-v11.4s}, [x3] + b 1f + + /* load input */ +0: ld1 {v8.4s-v11.4s}, [x1], #64 + sub w0, w0, #1 + +1: +CPU_LE( rev32 v8.16b, v8.16b ) +CPU_LE( rev32 v9.16b, v9.16b ) +CPU_LE( rev32 v10.16b, v10.16b ) +CPU_LE( rev32 v11.16b, v11.16b ) + +2: add t0.4s, v8.4s, k0.4s + mov dg0v.16b, dgav.16b + + add_update c, ev, k0, 8, 9, 10, 11, dgb + add_update c, od, k0, 9, 10, 11, 8 + add_update c, ev, k0, 10, 11, 8, 9 + add_update c, od, k0, 11, 8, 9, 10 + add_update c, ev, k1, 8, 9, 10, 11 + + add_update p, od, k1, 9, 10, 11, 8 + add_update p, ev, k1, 10, 11, 8, 9 + add_update p, od, k1, 11, 8, 9, 10 + add_update p, ev, k1, 8, 9, 10, 11 + add_update p, od, k2, 9, 10, 11, 8 + + add_update m, ev, k2, 10, 11, 8, 9 + add_update m, od, k2, 11, 8, 9, 10 + add_update m, ev, k2, 8, 9, 10, 11 + add_update m, od, k2, 9, 10, 11, 8 + add_update m, ev, k3, 10, 11, 8, 9 + + add_update p, od, k3, 11, 8, 9, 10 + add_only p, ev, k3, 9 + add_only p, od, k3, 10 + add_only p, ev, k3, 11 + add_only p, od + + /* update state */ + add dgbv.2s, dgbv.2s, dg1v.2s + add dgav.4s, dgav.4s, dg0v.4s + + cbnz w0, 0b + + /* + * Final block: add padding and total bit count. + * Skip if we have no total byte count in x4. In that case, the input + * size was not a round multiple of the block size, and the padding is + * handled by the C code. + */ + cbz x4, 3f + movi v9.2d, #0 + mov x8, #0x80000000 + movi v10.2d, #0 + ror x7, x4, #29 // ror(lsl(x4, 3), 32) + fmov d8, x8 + mov x4, #0 + mov v11.d[0], xzr + mov v11.d[1], x7 + b 2b + + /* store new state */ +3: str dga, [x2] + str dgb, [x2, #16] + ret +ENDPROC(sha1_ce_transform) diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c new file mode 100644 index 000000000000..6fe83f37a750 --- /dev/null +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -0,0 +1,174 @@ +/* + * sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions + * + * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <asm/neon.h> +#include <asm/unaligned.h> +#include <crypto/internal/hash.h> +#include <crypto/sha.h> +#include <linux/cpufeature.h> +#include <linux/crypto.h> +#include <linux/module.h> + +MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions"); +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); +MODULE_LICENSE("GPL v2"); + +asmlinkage void sha1_ce_transform(int blocks, u8 const *src, u32 *state, + u8 *head, long bytes); + +static int sha1_init(struct shash_desc *desc) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + + *sctx = (struct sha1_state){ + .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 }, + }; + return 0; +} + +static int sha1_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + unsigned int partial = sctx->count % SHA1_BLOCK_SIZE; + + sctx->count += len; + + if ((partial + len) >= SHA1_BLOCK_SIZE) { + int blocks; + + if (partial) { + int p = SHA1_BLOCK_SIZE - partial; + + memcpy(sctx->buffer + partial, data, p); + data += p; + len -= p; + } + + blocks = len / SHA1_BLOCK_SIZE; + len %= SHA1_BLOCK_SIZE; + + kernel_neon_begin_partial(16); + sha1_ce_transform(blocks, data, sctx->state, + partial ? sctx->buffer : NULL, 0); + kernel_neon_end(); + + data += blocks * SHA1_BLOCK_SIZE; + partial = 0; + } + if (len) + memcpy(sctx->buffer + partial, data, len); + return 0; +} + +static int sha1_final(struct shash_desc *desc, u8 *out) +{ + static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, }; + + struct sha1_state *sctx = shash_desc_ctx(desc); + __be64 bits = cpu_to_be64(sctx->count << 3); + __be32 *dst = (__be32 *)out; + int i; + + u32 padlen = SHA1_BLOCK_SIZE + - ((sctx->count + sizeof(bits)) % SHA1_BLOCK_SIZE); + + sha1_update(desc, padding, padlen); + sha1_update(desc, (const u8 *)&bits, sizeof(bits)); + + for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++) + put_unaligned_be32(sctx->state[i], dst++); + + *sctx = (struct sha1_state){}; + return 0; +} + +static int sha1_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + __be32 *dst = (__be32 *)out; + int blocks; + int i; + + if (sctx->count || !len || (len % SHA1_BLOCK_SIZE)) { + sha1_update(desc, data, len); + return sha1_final(desc, out); + } + + /* + * Use a fast path if the input is a multiple of 64 bytes. In + * this case, there is no need to copy data around, and we can + * perform the entire digest calculation in a single invocation + * of sha1_ce_transform() + */ + blocks = len / SHA1_BLOCK_SIZE; + + kernel_neon_begin_partial(16); + sha1_ce_transform(blocks, data, sctx->state, NULL, len); + kernel_neon_end(); + + for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++) + put_unaligned_be32(sctx->state[i], dst++); + + *sctx = (struct sha1_state){}; + return 0; +} + +static int sha1_export(struct shash_desc *desc, void *out) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + struct sha1_state *dst = out; + + *dst = *sctx; + return 0; +} + +static int sha1_import(struct shash_desc *desc, const void *in) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + struct sha1_state const *src = in; + + *sctx = *src; + return 0; +} + +static struct shash_alg alg = { + .init = sha1_init, + .update = sha1_update, + .final = sha1_final, + .finup = sha1_finup, + .export = sha1_export, + .import = sha1_import, + .descsize = sizeof(struct sha1_state), + .digestsize = SHA1_DIGEST_SIZE, + .statesize = sizeof(struct sha1_state), + .base = { + .cra_name = "sha1", + .cra_driver_name = "sha1-ce", + .cra_priority = 200, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +static int __init sha1_ce_mod_init(void) +{ + return crypto_register_shash(&alg); +} + +static void __exit sha1_ce_mod_fini(void) +{ + crypto_unregister_shash(&alg); +} + +module_cpu_feature_match(SHA1, sha1_ce_mod_init); +module_exit(sha1_ce_mod_fini); diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S new file mode 100644 index 000000000000..7f29fc031ea8 --- /dev/null +++ b/arch/arm64/crypto/sha2-ce-core.S @@ -0,0 +1,156 @@ +/* + * sha2-ce-core.S - core SHA-224/SHA-256 transform using v8 Crypto Extensions + * + * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + + .text + .arch armv8-a+crypto + + dga .req q20 + dgav .req v20 + dgb .req q21 + dgbv .req v21 + + t0 .req v22 + t1 .req v23 + + dg0q .req q24 + dg0v .req v24 + dg1q .req q25 + dg1v .req v25 + dg2q .req q26 + dg2v .req v26 + + .macro add_only, ev, rc, s0 + mov dg2v.16b, dg0v.16b + .ifeq \ev + add t1.4s, v\s0\().4s, \rc\().4s + sha256h dg0q, dg1q, t0.4s + sha256h2 dg1q, dg2q, t0.4s + .else + .ifnb \s0 + add t0.4s, v\s0\().4s, \rc\().4s + .endif + sha256h dg0q, dg1q, t1.4s + sha256h2 dg1q, dg2q, t1.4s + .endif + .endm + + .macro add_update, ev, rc, s0, s1, s2, s3 + sha256su0 v\s0\().4s, v\s1\().4s + add_only \ev, \rc, \s1 + sha256su1 v\s0\().4s, v\s2\().4s, v\s3\().4s + .endm + + /* + * The SHA-256 round constants + */ + .align 4 +.Lsha2_rcon: + .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5 + .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5 + .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3 + .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174 + .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc + .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da + .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7 + .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967 + .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13 + .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85 + .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3 + .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070 + .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5 + .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3 + .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208 + .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2 + + /* + * void sha2_ce_transform(int blocks, u8 const *src, u32 *state, + * u8 *head, long bytes) + */ +ENTRY(sha2_ce_transform) + /* load round constants */ + adr x8, .Lsha2_rcon + ld1 { v0.4s- v3.4s}, [x8], #64 + ld1 { v4.4s- v7.4s}, [x8], #64 + ld1 { v8.4s-v11.4s}, [x8], #64 + ld1 {v12.4s-v15.4s}, [x8] + + /* load state */ + ldp dga, dgb, [x2] + + /* load partial input (if supplied) */ + cbz x3, 0f + ld1 {v16.4s-v19.4s}, [x3] + b 1f + + /* load input */ +0: ld1 {v16.4s-v19.4s}, [x1], #64 + sub w0, w0, #1 + +1: +CPU_LE( rev32 v16.16b, v16.16b ) +CPU_LE( rev32 v17.16b, v17.16b ) +CPU_LE( rev32 v18.16b, v18.16b ) +CPU_LE( rev32 v19.16b, v19.16b ) + +2: add t0.4s, v16.4s, v0.4s + mov dg0v.16b, dgav.16b + mov dg1v.16b, dgbv.16b + + add_update 0, v1, 16, 17, 18, 19 + add_update 1, v2, 17, 18, 19, 16 + add_update 0, v3, 18, 19, 16, 17 + add_update 1, v4, 19, 16, 17, 18 + + add_update 0, v5, 16, 17, 18, 19 + add_update 1, v6, 17, 18, 19, 16 + add_update 0, v7, 18, 19, 16, 17 + add_update 1, v8, 19, 16, 17, 18 + + add_update 0, v9, 16, 17, 18, 19 + add_update 1, v10, 17, 18, 19, 16 + add_update 0, v11, 18, 19, 16, 17 + add_update 1, v12, 19, 16, 17, 18 + + add_only 0, v13, 17 + add_only 1, v14, 18 + add_only 0, v15, 19 + add_only 1 + + /* update state */ + add dgav.4s, dgav.4s, dg0v.4s + add dgbv.4s, dgbv.4s, dg1v.4s + + /* handled all input blocks? */ + cbnz w0, 0b + + /* + * Final block: add padding and total bit count. + * Skip if we have no total byte count in x4. In that case, the input + * size was not a round multiple of the block size, and the padding is + * handled by the C code. + */ + cbz x4, 3f + movi v17.2d, #0 + mov x8, #0x80000000 + movi v18.2d, #0 + ror x7, x4, #29 // ror(lsl(x4, 3), 32) + fmov d16, x8 + mov x4, #0 + mov v19.d[0], xzr + mov v19.d[1], x7 + b 2b + + /* store new state */ +3: stp dga, dgb, [x2] + ret +ENDPROC(sha2_ce_transform) diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c new file mode 100644 index 000000000000..c294e67d3925 --- /dev/null +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -0,0 +1,255 @@ +/* + * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions + * + * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <asm/neon.h> +#include <asm/unaligned.h> +#include <crypto/internal/hash.h> +#include <crypto/sha.h> +#include <linux/cpufeature.h> +#include <linux/crypto.h> +#include <linux/module.h> + +MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions"); +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); +MODULE_LICENSE("GPL v2"); + +asmlinkage int sha2_ce_transform(int blocks, u8 const *src, u32 *state, + u8 *head, long bytes); + +static int sha224_init(struct shash_desc *desc) +{ + struct sha256_state *sctx = shash_desc_ctx(desc); + + *sctx = (struct sha256_state){ + .state = { + SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3, + SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7, + } + }; + return 0; +} + +static int sha256_init(struct shash_desc *desc) +{ + struct sha256_state *sctx = shash_desc_ctx(desc); + + *sctx = (struct sha256_state){ + .state = { + SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3, + SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7, + } + }; + return 0; +} + +static int sha2_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + struct sha256_state *sctx = shash_desc_ctx(desc); + unsigned int partial = sctx->count % SHA256_BLOCK_SIZE; + + sctx->count += len; + + if ((partial + len) >= SHA256_BLOCK_SIZE) { + int blocks; + + if (partial) { + int p = SHA256_BLOCK_SIZE - partial; + + memcpy(sctx->buf + partial, data, p); + data += p; + len -= p; + } + + blocks = len / SHA256_BLOCK_SIZE; + len %= SHA256_BLOCK_SIZE; + + kernel_neon_begin_partial(28); + sha2_ce_transform(blocks, data, sctx->state, + partial ? sctx->buf : NULL, 0); + kernel_neon_end(); + + data += blocks * SHA256_BLOCK_SIZE; + partial = 0; + } + if (len) + memcpy(sctx->buf + partial, data, len); + return 0; +} + +static void sha2_final(struct shash_desc *desc) +{ + static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, }; + + struct sha256_state *sctx = shash_desc_ctx(desc); + __be64 bits = cpu_to_be64(sctx->count << 3); + u32 padlen = SHA256_BLOCK_SIZE + - ((sctx->count + sizeof(bits)) % SHA256_BLOCK_SIZE); + + sha2_update(desc, padding, padlen); + sha2_update(desc, (const u8 *)&bits, sizeof(bits)); +} + +static int sha224_final(struct shash_desc *desc, u8 *out) +{ + struct sha256_state *sctx = shash_desc_ctx(desc); + __be32 *dst = (__be32 *)out; + int i; + + sha2_final(desc); + + for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++) + put_unaligned_be32(sctx->state[i], dst++); + + *sctx = (struct sha256_state){}; + return 0; +} + +static int sha256_final(struct shash_desc *desc, u8 *out) +{ + struct sha256_state *sctx = shash_desc_ctx(desc); + __be32 *dst = (__be32 *)out; + int i; + + sha2_final(desc); + + for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++) + put_unaligned_be32(sctx->state[i], dst++); + + *sctx = (struct sha256_state){}; + return 0; +} + +static void sha2_finup(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + struct sha256_state *sctx = shash_desc_ctx(desc); + int blocks; + + if (sctx->count || !len || (len % SHA256_BLOCK_SIZE)) { + sha2_update(desc, data, len); + sha2_final(desc); + return; + } + + /* + * Use a fast path if the input is a multiple of 64 bytes. In + * this case, there is no need to copy data around, and we can + * perform the entire digest calculation in a single invocation + * of sha2_ce_transform() + */ + blocks = len / SHA256_BLOCK_SIZE; + + kernel_neon_begin_partial(28); + sha2_ce_transform(blocks, data, sctx->state, NULL, len); + kernel_neon_end(); + data += blocks * SHA256_BLOCK_SIZE; +} + +static int sha224_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + struct sha256_state *sctx = shash_desc_ctx(desc); + __be32 *dst = (__be32 *)out; + int i; + + sha2_finup(desc, data, len); + + for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++) + put_unaligned_be32(sctx->state[i], dst++); + + *sctx = (struct sha256_state){}; + return 0; +} + +static int sha256_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + struct sha256_state *sctx = shash_desc_ctx(desc); + __be32 *dst = (__be32 *)out; + int i; + + sha2_finup(desc, data, len); + + for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++) + put_unaligned_be32(sctx->state[i], dst++); + + *sctx = (struct sha256_state){}; + return 0; +} + +static int sha2_export(struct shash_desc *desc, void *out) +{ + struct sha256_state *sctx = shash_desc_ctx(desc); + struct sha256_state *dst = out; + + *dst = *sctx; + return 0; +} + +static int sha2_import(struct shash_desc *desc, const void *in) +{ + struct sha256_state *sctx = shash_desc_ctx(desc); + struct sha256_state const *src = in; + + *sctx = *src; + return 0; +} + +static struct shash_alg algs[] = { { + .init = sha224_init, + .update = sha2_update, + .final = sha224_final, + .finup = sha224_finup, + .export = sha2_export, + .import = sha2_import, + .descsize = sizeof(struct sha256_state), + .digestsize = SHA224_DIGEST_SIZE, + .statesize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha224", + .cra_driver_name = "sha224-ce", + .cra_priority = 200, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA256_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}, { + .init = sha256_init, + .update = sha2_update, + .final = sha256_final, + .finup = sha256_finup, + .export = sha2_export, + .import = sha2_import, + .descsize = sizeof(struct sha256_state), + .digestsize = SHA256_DIGEST_SIZE, + .statesize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha256", + .cra_driver_name = "sha256-ce", + .cra_priority = 200, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA256_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; + +static int __init sha2_ce_mod_init(void) +{ + return crypto_register_shashes(algs, ARRAY_SIZE(algs)); +} + +static void __exit sha2_ce_mod_fini(void) +{ + crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); +} + +module_cpu_feature_match(SHA2, sha2_ce_mod_init); +module_exit(sha2_ce_mod_fini); diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 83f71b3004a8..42c7eecd2bb6 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -40,6 +40,7 @@ generic-y += segment.h generic-y += sembuf.h generic-y += serial.h generic-y += shmbuf.h +generic-y += simd.h generic-y += sizes.h generic-y += socket.h generic-y += sockios.h diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index fd3e3924041b..5901480bfdca 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -21,6 +21,7 @@ #endif #include <asm/ptrace.h> +#include <asm/thread_info.h> /* * Stack pushing/popping (register pairs only). Equivalent to store decrement @@ -68,23 +69,31 @@ msr daifclr, #8 .endm - .macro disable_step, tmp + .macro disable_step_tsk, flgs, tmp + tbz \flgs, #TIF_SINGLESTEP, 9990f mrs \tmp, mdscr_el1 bic \tmp, \tmp, #1 msr mdscr_el1, \tmp + isb // Synchronise with enable_dbg +9990: .endm - .macro enable_step, tmp + .macro enable_step_tsk, flgs, tmp + tbz \flgs, #TIF_SINGLESTEP, 9990f + disable_dbg mrs \tmp, mdscr_el1 orr \tmp, \tmp, #1 msr mdscr_el1, \tmp +9990: .endm - .macro enable_dbg_if_not_stepping, tmp - mrs \tmp, mdscr_el1 - tbnz \tmp, #0, 9990f - enable_dbg -9990: +/* + * Enable both debug exceptions and interrupts. This is likely to be + * faster than two daifclr operations, since writes to this register + * are self-synchronising. + */ + .macro enable_dbg_and_irq + msr daifclr, #(8 | 2) .endm /* diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 57e8cb49824c..65f1569ac96e 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -157,7 +157,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) */ #define ATOMIC64_INIT(i) { (i) } -#define atomic64_read(v) (*(volatile long long *)&(v)->counter) +#define atomic64_read(v) (*(volatile long *)&(v)->counter) #define atomic64_set(v,i) (((v)->counter) = (i)) static inline void atomic64_add(u64 i, atomic64_t *v) diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 48b9e704af7c..6389d60574d9 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -25,12 +25,12 @@ #define wfi() asm volatile("wfi" : : : "memory") #define isb() asm volatile("isb" : : : "memory") -#define dmb(opt) asm volatile("dmb sy" : : : "memory") -#define dsb(opt) asm volatile("dsb sy" : : : "memory") +#define dmb(opt) asm volatile("dmb " #opt : : : "memory") +#define dsb(opt) asm volatile("dsb " #opt : : : "memory") -#define mb() dsb() -#define rmb() asm volatile("dsb ld" : : : "memory") -#define wmb() asm volatile("dsb st" : : : "memory") +#define mb() dsb(sy) +#define rmb() dsb(ld) +#define wmb() dsb(st) #ifndef CONFIG_SMP #define smp_mb() barrier() @@ -40,7 +40,7 @@ #define smp_store_release(p, v) \ do { \ compiletime_assert_atomic_type(*p); \ - smp_mb(); \ + barrier(); \ ACCESS_ONCE(*p) = (v); \ } while (0) @@ -48,15 +48,15 @@ do { \ ({ \ typeof(*p) ___p1 = ACCESS_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ - smp_mb(); \ + barrier(); \ ___p1; \ }) #else -#define smp_mb() asm volatile("dmb ish" : : : "memory") -#define smp_rmb() asm volatile("dmb ishld" : : : "memory") -#define smp_wmb() asm volatile("dmb ishst" : : : "memory") +#define smp_mb() dmb(ish) +#define smp_rmb() dmb(ishld) +#define smp_wmb() dmb(ishst) #define smp_store_release(p, v) \ do { \ diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 390308a67f0d..88cc05b5f3ac 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -16,6 +16,8 @@ #ifndef __ASM_CACHE_H #define __ASM_CACHE_H +#include <asm/cachetype.h> + #define L1_CACHE_SHIFT 6 #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) @@ -27,6 +29,15 @@ * the CPU. */ #define ARCH_DMA_MINALIGN L1_CACHE_BYTES -#define ARCH_SLAB_MINALIGN 8 + +#ifndef __ASSEMBLY__ + +static inline int cache_line_size(void) +{ + u32 cwg = cache_type_cwg(); + return cwg ? 4 << cwg : L1_CACHE_BYTES; +} + +#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 4c60e64a801c..a5176cf32dad 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -123,7 +123,7 @@ extern void flush_dcache_page(struct page *); static inline void __flush_icache_all(void) { asm("ic ialluis"); - dsb(); + dsb(ish); } #define flush_dcache_mmap_lock(mapping) \ @@ -150,7 +150,7 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end) * set_pte_at() called from vmap_pte_range() does not * have a DSB after cleaning the cache line. */ - dsb(); + dsb(ish); } static inline void flush_cache_vunmap(unsigned long start, unsigned long end) diff --git a/arch/arm64/include/asm/cachetype.h b/arch/arm64/include/asm/cachetype.h index 85f5f511352a..4b23e758d5e0 100644 --- a/arch/arm64/include/asm/cachetype.h +++ b/arch/arm64/include/asm/cachetype.h @@ -20,12 +20,16 @@ #define CTR_L1IP_SHIFT 14 #define CTR_L1IP_MASK 3 +#define CTR_CWG_SHIFT 24 +#define CTR_CWG_MASK 15 #define ICACHE_POLICY_RESERVED 0 #define ICACHE_POLICY_AIVIVT 1 #define ICACHE_POLICY_VIPT 2 #define ICACHE_POLICY_PIPT 3 +#ifndef __ASSEMBLY__ + static inline u32 icache_policy(void) { return (read_cpuid_cachetype() >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK; @@ -45,4 +49,11 @@ static inline int icache_is_aivivt(void) return icache_policy() == ICACHE_POLICY_AIVIVT; } +static inline u32 cache_type_cwg(void) +{ + return (read_cpuid_cachetype() >> CTR_CWG_SHIFT) & CTR_CWG_MASK; +} + +#endif /* __ASSEMBLY__ */ + #endif /* __ASM_CACHETYPE_H */ diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 57c0fa7bf711..ddb9d7830558 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -72,7 +72,12 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size } #define xchg(ptr,x) \ - ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)))) +({ \ + __typeof__(*(ptr)) __ret; \ + __ret = (__typeof__(*(ptr))) \ + __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \ + __ret; \ +}) static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size) diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index e71f81fe127a..253e33bc94fb 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -305,11 +305,6 @@ static inline int is_compat_thread(struct thread_info *thread) #else /* !CONFIG_COMPAT */ -static inline int is_compat_task(void) -{ - return 0; -} - static inline int is_compat_thread(struct thread_info *thread) { return 0; diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h new file mode 100644 index 000000000000..5a46c4e7f539 --- /dev/null +++ b/arch/arm64/include/asm/efi.h @@ -0,0 +1,14 @@ +#ifndef _ASM_EFI_H +#define _ASM_EFI_H + +#include <asm/io.h> + +#ifdef CONFIG_EFI +extern void efi_init(void); +extern void efi_idmap_init(void); +#else +#define efi_init() +#define efi_idmap_init() +#endif + +#endif /* _ASM_EFI_H */ diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index c4a7f940b387..72674f4c3871 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -18,9 +18,11 @@ #ifndef __ASM_ESR_H #define __ASM_ESR_H -#define ESR_EL1_EC_SHIFT (26) -#define ESR_EL1_IL (1U << 25) +#define ESR_EL1_WRITE (1 << 6) +#define ESR_EL1_CM (1 << 8) +#define ESR_EL1_IL (1 << 25) +#define ESR_EL1_EC_SHIFT (26) #define ESR_EL1_EC_UNKNOWN (0x00) #define ESR_EL1_EC_WFI (0x01) #define ESR_EL1_EC_CP15_32 (0x03) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index c43b4ac13008..50f559f574fe 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -37,8 +37,21 @@ struct fpsimd_state { u32 fpcr; }; }; + /* the id of the last cpu to have restored this state */ + unsigned int cpu; }; +/* + * Struct for stacking the bottom 'n' FP/SIMD registers. + */ +struct fpsimd_partial_state { + u32 fpsr; + u32 fpcr; + u32 num_regs; + __uint128_t vregs[32]; +}; + + #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f @@ -58,6 +71,16 @@ extern void fpsimd_load_state(struct fpsimd_state *state); extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); +extern void fpsimd_preserve_current_state(void); +extern void fpsimd_restore_current_state(void); +extern void fpsimd_update_current_state(struct fpsimd_state *state); + +extern void fpsimd_flush_task_state(struct task_struct *target); + +extern void fpsimd_save_partial_state(struct fpsimd_partial_state *state, + u32 num_regs); +extern void fpsimd_load_partial_state(struct fpsimd_partial_state *state); + #endif #endif diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index bbec599c96bd..768414d55e64 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -62,3 +62,38 @@ ldr w\tmpnr, [\state, #16 * 2 + 4] msr fpcr, x\tmpnr .endm + +.altmacro +.macro fpsimd_save_partial state, numnr, tmpnr1, tmpnr2 + mrs x\tmpnr1, fpsr + str w\numnr, [\state, #8] + mrs x\tmpnr2, fpcr + stp w\tmpnr1, w\tmpnr2, [\state] + adr x\tmpnr1, 0f + add \state, \state, x\numnr, lsl #4 + sub x\tmpnr1, x\tmpnr1, x\numnr, lsl #1 + br x\tmpnr1 + .irp qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0 + .irp qb, %(qa + 1) + stp q\qa, q\qb, [\state, # -16 * \qa - 16] + .endr + .endr +0: +.endm + +.macro fpsimd_restore_partial state, tmpnr1, tmpnr2 + ldp w\tmpnr1, w\tmpnr2, [\state] + msr fpsr, x\tmpnr1 + msr fpcr, x\tmpnr2 + adr x\tmpnr1, 0f + ldr w\tmpnr2, [\state, #8] + add \state, \state, x\tmpnr2, lsl #4 + sub x\tmpnr1, x\tmpnr1, x\tmpnr2, lsl #1 + br x\tmpnr1 + .irp qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0 + .irp qb, %(qa + 1) + ldp q\qa, q\qb, [\state, # -16 * \qa - 16] + .endr + .endr +0: +.endm diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h new file mode 100644 index 000000000000..c5534facf941 --- /dev/null +++ b/arch/arm64/include/asm/ftrace.h @@ -0,0 +1,59 @@ +/* + * arch/arm64/include/asm/ftrace.h + * + * Copyright (C) 2013 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __ASM_FTRACE_H +#define __ASM_FTRACE_H + +#include <asm/insn.h> + +#define MCOUNT_ADDR ((unsigned long)_mcount) +#define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE + +#ifndef __ASSEMBLY__ +#include <linux/compat.h> + +extern void _mcount(unsigned long); +extern void *return_address(unsigned int); + +struct dyn_arch_ftrace { + /* No extra data needed for arm64 */ +}; + +extern unsigned long ftrace_graph_call; + +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + /* + * addr is the address of the mcount call instruction. + * recordmcount does the necessary offset calculation. + */ + return addr; +} + +#define ftrace_return_address(n) return_address(n) + +/* + * Because AArch32 mode does not share the same syscall table with AArch64, + * tracing compat syscalls may result in reporting bogus syscalls or even + * hang-up, so just do not trace them. + * See kernel/trace/trace_syscalls.c + * + * x86 code says: + * If the user realy wants these, then they should use the + * raw syscall tracepoints with filtering. + */ +#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS +static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) +{ + return is_compat_task(); +} +#endif /* ifndef __ASSEMBLY__ */ + +#endif /* __ASM_FTRACE_H */ diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index ae4801d77514..0be67821f9ce 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -20,7 +20,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 5 +#define NR_IPI 6 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index c44ad39ed310..dc1f73b13e74 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -21,6 +21,7 @@ /* A64 instructions are always 32 bits. */ #define AARCH64_INSN_SIZE 4 +#ifndef __ASSEMBLY__ /* * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a * Section C3.1 "A64 instruction index by encoding": @@ -104,5 +105,6 @@ bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn); int aarch64_insn_patch_text_nosync(void *addr, u32 insn); int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt); int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt); +#endif /* __ASSEMBLY__ */ #endif /* __ASM_INSN_H */ diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index a1bef78f0303..e0ecdcf6632d 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -230,19 +230,11 @@ extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot extern void __iounmap(volatile void __iomem *addr); extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); -#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) - #define ioremap(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE)) #define ioremap_nocache(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE)) #define ioremap_wc(addr, size) __ioremap((addr), (size), __pgprot(PROT_NORMAL_NC)) #define iounmap __iounmap -#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF) -#define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PTE_PXN | PTE_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) - #define ARCH_HAS_IOREMAP_WC #include <asm-generic/iomap.h> diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index aff0292c8f4d..c2f006c48bdb 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -31,5 +31,7 @@ extern void paging_init(void); extern void setup_mm_for_reboot(void); extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); extern void init_mem_pgprot(void); +/* create an identity mapping for memory (or io if map_io is true) */ +extern void create_id_mapping(phys_addr_t addr, phys_addr_t size, int map_io); #endif diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h index b0cc58a97780..13ce4cc18e26 100644 --- a/arch/arm64/include/asm/neon.h +++ b/arch/arm64/include/asm/neon.h @@ -8,7 +8,11 @@ * published by the Free Software Foundation. */ +#include <linux/types.h> + #define cpu_has_neon() (1) -void kernel_neon_begin(void); +#define kernel_neon_begin() kernel_neon_begin_partial(32) + +void kernel_neon_begin_partial(u32 num_regs); void kernel_neon_end(void); diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 5fc8a66c3924..955e8c5f0afb 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -29,6 +29,8 @@ */ #define PUD_TABLE_BIT (_AT(pgdval_t, 1) << 1) +#define PUD_TYPE_MASK (_AT(pgdval_t, 3) << 0) +#define PUD_TYPE_SECT (_AT(pgdval_t, 1) << 0) /* * Level 2 descriptor (PMD). diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index e2f96748859b..598cc384fc1c 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -52,66 +52,59 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #endif #define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd_val(pgd)) -/* - * The pgprot_* and protection_map entries will be fixed up at runtime to - * include the cachable and bufferable bits based on memory policy, as well as - * any architecture dependent bits like global/ASID and SMP shared mapping - * bits. - */ -#define _PAGE_DEFAULT PTE_TYPE_PAGE | PTE_AF +#ifdef CONFIG_SMP +#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) +#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) +#else +#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF) +#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF) +#endif -extern pgprot_t pgprot_default; +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL)) -#define __pgprot_modify(prot,mask,bits) \ - __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) +#define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) +#define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) -#define _MOD_PROT(p, b) __pgprot_modify(p, 0, b) +#define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) -#define PAGE_NONE __pgprot_modify(pgprot_default, PTE_TYPE_MASK, PTE_PROT_NONE | PTE_PXN | PTE_UXN) -#define PAGE_SHARED _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) -#define PAGE_SHARED_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) -#define PAGE_COPY _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) -#define PAGE_COPY_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN) -#define PAGE_READONLY _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) -#define PAGE_READONLY_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN) -#define PAGE_KERNEL _MOD_PROT(pgprot_default, PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) -#define PAGE_KERNEL_EXEC _MOD_PROT(pgprot_default, PTE_UXN | PTE_DIRTY | PTE_WRITE) +#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) +#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) -#define PAGE_HYP _MOD_PROT(pgprot_default, PTE_HYP) +#define PAGE_HYP __pgprot(_PAGE_DEFAULT | PTE_HYP) #define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) -#define PAGE_S2 __pgprot_modify(pgprot_default, PTE_S2_MEMATTR_MASK, PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) +#define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) #define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDWR | PTE_UXN) -#define __PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) -#define __PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) -#define __PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) -#define __PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) -#define __PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) -#define __PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) -#define __PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) - -#endif /* __ASSEMBLY__ */ - -#define __P000 __PAGE_NONE -#define __P001 __PAGE_READONLY -#define __P010 __PAGE_COPY -#define __P011 __PAGE_COPY -#define __P100 __PAGE_READONLY_EXEC -#define __P101 __PAGE_READONLY_EXEC -#define __P110 __PAGE_COPY_EXEC -#define __P111 __PAGE_COPY_EXEC - -#define __S000 __PAGE_NONE -#define __S001 __PAGE_READONLY -#define __S010 __PAGE_SHARED -#define __S011 __PAGE_SHARED -#define __S100 __PAGE_READONLY_EXEC -#define __S101 __PAGE_READONLY_EXEC -#define __S110 __PAGE_SHARED_EXEC -#define __S111 __PAGE_SHARED_EXEC +#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) +#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) +#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) +#define PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) +#define PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) +#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) +#define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) + +#define __P000 PAGE_NONE +#define __P001 PAGE_READONLY +#define __P010 PAGE_COPY +#define __P011 PAGE_COPY +#define __P100 PAGE_READONLY_EXEC +#define __P101 PAGE_READONLY_EXEC +#define __P110 PAGE_COPY_EXEC +#define __P111 PAGE_COPY_EXEC + +#define __S000 PAGE_NONE +#define __S001 PAGE_READONLY +#define __S010 PAGE_SHARED +#define __S011 PAGE_SHARED +#define __S100 PAGE_READONLY_EXEC +#define __S101 PAGE_READONLY_EXEC +#define __S110 PAGE_SHARED_EXEC +#define __S111 PAGE_SHARED_EXEC -#ifndef __ASSEMBLY__ /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. @@ -265,6 +258,7 @@ static inline pmd_t pte_pmd(pte_t pte) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) #define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK)) +#define pud_pfn(pud) (((pud_val(pud) & PUD_MASK) & PHYS_MASK) >> PAGE_SHIFT) #define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)) @@ -273,6 +267,9 @@ static inline int has_transparent_hugepage(void) return 1; } +#define __pgprot_modify(prot,mask,bits) \ + __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) + /* * Mark the prot value as uncacheable and unbufferable. */ @@ -295,11 +292,17 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) +#ifdef ARM64_64K_PAGES +#define pud_sect(pud) (0) +#else +#define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ + PUD_TYPE_SECT) +#endif static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { *pmdp = pmd; - dsb(); + dsb(ishst); } static inline void pmd_clear(pmd_t *pmdp) @@ -329,7 +332,7 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd) static inline void set_pud(pud_t *pudp, pud_t pud) { *pudp = pud; - dsb(); + dsb(ishst); } static inline void pud_clear(pud_t *pudp) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 45b20cd6cbca..34de2a8f7d93 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -79,6 +79,7 @@ struct thread_struct { unsigned long tp_value; struct fpsimd_state fpsimd_state; unsigned long fault_address; /* fault info */ + unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ }; diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index c7ba261dd4b3..a429b5940be2 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -135,6 +135,11 @@ struct pt_regs { #define user_stack_pointer(regs) \ (!compat_user_mode(regs)) ? ((regs)->sp) : ((regs)->compat_sp) +static inline unsigned long regs_return_value(struct pt_regs *regs) +{ + return regs->regs[0]; +} + /* * Are the current registers suitable for user mode? (used to maintain * security in signal handlers) diff --git a/arch/arm64/include/asm/sigcontext.h b/arch/arm64/include/asm/sigcontext.h deleted file mode 100644 index dca1094acc74..000000000000 --- a/arch/arm64/include/asm/sigcontext.h +++ /dev/null @@ -1,31 +0,0 @@ -/* - * Copyright (C) 2012 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ -#ifndef __ASM_SIGCONTEXT_H -#define __ASM_SIGCONTEXT_H - -#include <uapi/asm/sigcontext.h> - -/* - * Auxiliary context saved in the sigcontext.__reserved array. Not exported to - * user space as it will change with the addition of new context. User space - * should check the magic/size information. - */ -struct aux_context { - struct fpsimd_context fpsimd; - /* additional context to be added before "end" */ - struct _aarch64_ctx end; -}; -#endif diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h index 3ee8b303d9a9..64d2d4884a9d 100644 --- a/arch/arm64/include/asm/string.h +++ b/arch/arm64/include/asm/string.h @@ -22,6 +22,18 @@ extern char *strrchr(const char *, int c); #define __HAVE_ARCH_STRCHR extern char *strchr(const char *, int c); +#define __HAVE_ARCH_STRCMP +extern int strcmp(const char *, const char *); + +#define __HAVE_ARCH_STRNCMP +extern int strncmp(const char *, const char *, __kernel_size_t); + +#define __HAVE_ARCH_STRLEN +extern __kernel_size_t strlen(const char *); + +#define __HAVE_ARCH_STRNLEN +extern __kernel_size_t strnlen(const char *, __kernel_size_t); + #define __HAVE_ARCH_MEMCPY extern void *memcpy(void *, const void *, __kernel_size_t); @@ -34,4 +46,7 @@ extern void *memchr(const void *, int, __kernel_size_t); #define __HAVE_ARCH_MEMSET extern void *memset(void *, int, __kernel_size_t); +#define __HAVE_ARCH_MEMCMP +extern int memcmp(const void *, const void *, size_t); + #endif diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index 70ba9d4ee978..383771eb0b87 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -18,6 +18,7 @@ #include <linux/err.h> +extern const void *sys_call_table[]; static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 7b8e3a2a00fb..e40b6d06d515 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -91,6 +91,9 @@ static inline struct thread_info *current_thread_info(void) /* * thread information flags: * TIF_SYSCALL_TRACE - syscall trace active + * TIF_SYSCALL_TRACEPOINT - syscall tracepoint for ftrace + * TIF_SYSCALL_AUDIT - syscall auditing + * TIF_SECOMP - syscall secure computing * TIF_SIGPENDING - signal pending * TIF_NEED_RESCHED - rescheduling necessary * TIF_NOTIFY_RESUME - callback before returning to user @@ -99,7 +102,11 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SIGPENDING 0 #define TIF_NEED_RESCHED 1 #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ +#define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ #define TIF_SYSCALL_TRACE 8 +#define TIF_SYSCALL_AUDIT 9 +#define TIF_SYSCALL_TRACEPOINT 10 +#define TIF_SECCOMP 11 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_FREEZE 19 #define TIF_RESTORE_SIGMASK 20 @@ -110,10 +117,18 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) +#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) +#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) +#define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME) + _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE) + +#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ + _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP) #endif /* __KERNEL__ */ #endif /* __ASM_THREAD_INFO_H */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 8b482035cfc2..b9349c4513ea 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -72,9 +72,9 @@ extern struct cpu_tlb_fns cpu_tlb; */ static inline void flush_tlb_all(void) { - dsb(); + dsb(ishst); asm("tlbi vmalle1is"); - dsb(); + dsb(ish); isb(); } @@ -82,9 +82,9 @@ static inline void flush_tlb_mm(struct mm_struct *mm) { unsigned long asid = (unsigned long)ASID(mm) << 48; - dsb(); + dsb(ishst); asm("tlbi aside1is, %0" : : "r" (asid)); - dsb(); + dsb(ish); } static inline void flush_tlb_page(struct vm_area_struct *vma, @@ -93,16 +93,36 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr = uaddr >> 12 | ((unsigned long)ASID(vma->vm_mm) << 48); - dsb(); + dsb(ishst); asm("tlbi vae1is, %0" : : "r" (addr)); - dsb(); + dsb(ish); } -/* - * Convert calls to our calling convention. - */ -#define flush_tlb_range(vma,start,end) __cpu_flush_user_tlb_range(start,end,vma) -#define flush_tlb_kernel_range(s,e) __cpu_flush_kern_tlb_range(s,e) +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48; + unsigned long addr; + start = asid | (start >> 12); + end = asid | (end >> 12); + + dsb(ishst); + for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) + asm("tlbi vae1is, %0" : : "r"(addr)); + dsb(ish); +} + +static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + unsigned long addr; + start >>= 12; + end >>= 12; + + dsb(ishst); + for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) + asm("tlbi vaae1is, %0" : : "r"(addr)); + dsb(ish); +} /* * On AArch64, the cache coherency is handled via the set_pte_at() function. @@ -114,7 +134,7 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, * set_pte() does not have a DSB, so make sure that the page table * write is visible. */ - dsb(); + dsb(ishst); } #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 0172e6d76bf3..7ebcd31ce51c 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -20,9 +20,6 @@ extern struct cpu_topology cpu_topology[NR_CPUS]; #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) #define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) -#define mc_capable() (cpu_topology[0].cluster_id != -1) -#define smt_capable() (cpu_topology[0].thread_id != -1) - void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index a4654c656a1e..e5f47df00c24 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -29,3 +29,5 @@ #endif #define __ARCH_WANT_SYS_CLONE #include <uapi/asm/unistd.h> + +#define NR_syscalls (__NR_syscalls) diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 690ad51cc901..b72cf405b3fe 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -53,5 +53,12 @@ struct fpsimd_context { __uint128_t vregs[32]; }; +/* ESR_EL1 context */ +#define ESR_MAGIC 0x45535201 + +struct esr_context { + struct _aarch64_ctx head; + u64 esr; +}; #endif /* _UAPI__ASM_SIGCONTEXT_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 7a6fce5167e9..cdaedad3afe5 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -4,15 +4,22 @@ CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET) AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) +CFLAGS_efi-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) \ + -I$(src)/../../../scripts/dtc/libfdt + +CFLAGS_REMOVE_ftrace.o = -pg +CFLAGS_REMOVE_insn.o = -pg +CFLAGS_REMOVE_return_address.o = -pg # Object file lists. arm64-obj-y := cputable.o debug-monitors.o entry.o irq.o fpsimd.o \ entry-fpsimd.o process.o ptrace.o setup.o signal.o \ sys.o stacktrace.o time.o traps.o io.o vdso.o \ - hyp-stub.o psci.o cpu_ops.o insn.o + hyp-stub.o psci.o cpu_ops.o insn.o return_address.o arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ sys_compat.o +arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o arm64-obj-$(CONFIG_SMP) += smp.o smp_spin_table.o topology.o arm64-obj-$(CONFIG_PERF_EVENTS) += perf_regs.o @@ -21,6 +28,7 @@ arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND) += sleep.o suspend.o arm64-obj-$(CONFIG_JUMP_LABEL) += jump_label.o arm64-obj-$(CONFIG_KGDB) += kgdb.o +arm64-obj-$(CONFIG_EFI) += efi.o efi-stub.o efi-entry.o obj-y += $(arm64-obj-y) vdso/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index 338b568cd8ae..a85843ddbde8 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -44,10 +44,15 @@ EXPORT_SYMBOL(memstart_addr); /* string / mem functions */ EXPORT_SYMBOL(strchr); EXPORT_SYMBOL(strrchr); +EXPORT_SYMBOL(strcmp); +EXPORT_SYMBOL(strncmp); +EXPORT_SYMBOL(strlen); +EXPORT_SYMBOL(strnlen); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memchr); +EXPORT_SYMBOL(memcmp); /* atomic bitops */ EXPORT_SYMBOL(set_bit); @@ -56,3 +61,7 @@ EXPORT_SYMBOL(clear_bit); EXPORT_SYMBOL(test_and_clear_bit); EXPORT_SYMBOL(change_bit); EXPORT_SYMBOL(test_and_change_bit); + +#ifdef CONFIG_FUNCTION_TRACER +EXPORT_SYMBOL(_mcount); +#endif diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S new file mode 100644 index 000000000000..66716c9b9e5f --- /dev/null +++ b/arch/arm64/kernel/efi-entry.S @@ -0,0 +1,109 @@ +/* + * EFI entry point. + * + * Copyright (C) 2013, 2014 Red Hat, Inc. + * Author: Mark Salter <msalter@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include <linux/linkage.h> +#include <linux/init.h> + +#include <asm/assembler.h> + +#define EFI_LOAD_ERROR 0x8000000000000001 + + __INIT + + /* + * We arrive here from the EFI boot manager with: + * + * * CPU in little-endian mode + * * MMU on with identity-mapped RAM + * * Icache and Dcache on + * + * We will most likely be running from some place other than where + * we want to be. The kernel image wants to be placed at TEXT_OFFSET + * from start of RAM. + */ +ENTRY(efi_stub_entry) + /* + * Create a stack frame to save FP/LR with extra space + * for image_addr variable passed to efi_entry(). + */ + stp x29, x30, [sp, #-32]! + + /* + * Call efi_entry to do the real work. + * x0 and x1 are already set up by firmware. Current runtime + * address of image is calculated and passed via *image_addr. + * + * unsigned long efi_entry(void *handle, + * efi_system_table_t *sys_table, + * unsigned long *image_addr) ; + */ + adrp x8, _text + add x8, x8, #:lo12:_text + add x2, sp, 16 + str x8, [x2] + bl efi_entry + cmn x0, #1 + b.eq efi_load_fail + + /* + * efi_entry() will have relocated the kernel image if necessary + * and we return here with device tree address in x0 and the kernel + * entry point stored at *image_addr. Save those values in registers + * which are callee preserved. + */ + mov x20, x0 // DTB address + ldr x0, [sp, #16] // relocated _text address + mov x21, x0 + + /* + * Flush dcache covering current runtime addresses + * of kernel text/data. Then flush all of icache. + */ + adrp x1, _text + add x1, x1, #:lo12:_text + adrp x2, _edata + add x2, x2, #:lo12:_edata + sub x1, x2, x1 + + bl __flush_dcache_area + ic ialluis + + /* Turn off Dcache and MMU */ + mrs x0, CurrentEL + cmp x0, #PSR_MODE_EL2t + ccmp x0, #PSR_MODE_EL2h, #0x4, ne + b.ne 1f + mrs x0, sctlr_el2 + bic x0, x0, #1 << 0 // clear SCTLR.M + bic x0, x0, #1 << 2 // clear SCTLR.C + msr sctlr_el2, x0 + isb + b 2f +1: + mrs x0, sctlr_el1 + bic x0, x0, #1 << 0 // clear SCTLR.M + bic x0, x0, #1 << 2 // clear SCTLR.C + msr sctlr_el1, x0 + isb +2: + /* Jump to kernel entry point */ + mov x0, x20 + mov x1, xzr + mov x2, xzr + mov x3, xzr + br x21 + +efi_load_fail: + mov x0, #EFI_LOAD_ERROR + ldp x29, x30, [sp], #32 + ret + +ENDPROC(efi_stub_entry) diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c new file mode 100644 index 000000000000..60e98a639ac5 --- /dev/null +++ b/arch/arm64/kernel/efi-stub.c @@ -0,0 +1,81 @@ +/* + * Copyright (C) 2013, 2014 Linaro Ltd; <roy.franz@linaro.org> + * + * This file implements the EFI boot stub for the arm64 kernel. + * Adapted from ARM version by Mark Salter <msalter@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include <linux/efi.h> +#include <linux/libfdt.h> +#include <asm/sections.h> +#include <generated/compile.h> +#include <generated/utsrelease.h> + +/* + * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from + * start of kernel and may not cross a 2MiB boundary. We set alignment to + * 2MiB so we know it won't cross a 2MiB boundary. + */ +#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */ +#define MAX_FDT_OFFSET SZ_512M + +#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) + +static void efi_char16_printk(efi_system_table_t *sys_table_arg, + efi_char16_t *str); + +static efi_status_t efi_open_volume(efi_system_table_t *sys_table, + void *__image, void **__fh); +static efi_status_t efi_file_close(void *handle); + +static efi_status_t +efi_file_read(void *handle, unsigned long *size, void *addr); + +static efi_status_t +efi_file_size(efi_system_table_t *sys_table, void *__fh, + efi_char16_t *filename_16, void **handle, u64 *file_sz); + +/* Include shared EFI stub code */ +#include "../../../drivers/firmware/efi/efi-stub-helper.c" +#include "../../../drivers/firmware/efi/fdt.c" +#include "../../../drivers/firmware/efi/arm-stub.c" + + +static efi_status_t handle_kernel_image(efi_system_table_t *sys_table, + unsigned long *image_addr, + unsigned long *image_size, + unsigned long *reserve_addr, + unsigned long *reserve_size, + unsigned long dram_base, + efi_loaded_image_t *image) +{ + efi_status_t status; + unsigned long kernel_size, kernel_memsize = 0; + + /* Relocate the image, if required. */ + kernel_size = _edata - _text; + if (*image_addr != (dram_base + TEXT_OFFSET)) { + kernel_memsize = kernel_size + (_end - _edata); + status = efi_relocate_kernel(sys_table, image_addr, + kernel_size, kernel_memsize, + dram_base + TEXT_OFFSET, + PAGE_SIZE); + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Failed to relocate kernel\n"); + return status; + } + if (*image_addr != (dram_base + TEXT_OFFSET)) { + pr_efi_err(sys_table, "Failed to alloc kernel memory\n"); + efi_free(sys_table, kernel_memsize, *image_addr); + return EFI_ERROR; + } + *image_size = kernel_memsize; + } + + + return EFI_SUCCESS; +} diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c new file mode 100644 index 000000000000..14db1f6e8d7f --- /dev/null +++ b/arch/arm64/kernel/efi.c @@ -0,0 +1,469 @@ +/* + * Extensible Firmware Interface + * + * Based on Extensible Firmware Interface Specification version 2.4 + * + * Copyright (C) 2013, 2014 Linaro Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/efi.h> +#include <linux/export.h> +#include <linux/memblock.h> +#include <linux/bootmem.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/sched.h> +#include <linux/slab.h> + +#include <asm/cacheflush.h> +#include <asm/efi.h> +#include <asm/tlbflush.h> +#include <asm/mmu_context.h> + +struct efi_memory_map memmap; + +static efi_runtime_services_t *runtime; + +static u64 efi_system_table; + +static int uefi_debug __initdata; +static int __init uefi_debug_setup(char *str) +{ + uefi_debug = 1; + + return 0; +} +early_param("uefi_debug", uefi_debug_setup); + +static int __init is_normal_ram(efi_memory_desc_t *md) +{ + if (md->attribute & EFI_MEMORY_WB) + return 1; + return 0; +} + +static void __init efi_setup_idmap(void) +{ + struct memblock_region *r; + efi_memory_desc_t *md; + u64 paddr, npages, size; + + for_each_memblock(memory, r) + create_id_mapping(r->base, r->size, 0); + + /* map runtime io spaces */ + for_each_efi_memory_desc(&memmap, md) { + if (!(md->attribute & EFI_MEMORY_RUNTIME) || is_normal_ram(md)) + continue; + paddr = md->phys_addr; + npages = md->num_pages; + memrange_efi_to_native(&paddr, &npages); + size = npages << PAGE_SHIFT; + create_id_mapping(paddr, size, 1); + } +} + +static int __init uefi_init(void) +{ + efi_char16_t *c16; + char vendor[100] = "unknown"; + int i, retval; + + efi.systab = early_memremap(efi_system_table, + sizeof(efi_system_table_t)); + if (efi.systab == NULL) { + pr_warn("Unable to map EFI system table.\n"); + return -ENOMEM; + } + + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); + + /* + * Verify the EFI Table + */ + if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) { + pr_err("System table signature incorrect\n"); + return -EINVAL; + } + if ((efi.systab->hdr.revision >> 16) < 2) + pr_warn("Warning: EFI system table version %d.%02d, expected 2.00 or greater\n", + efi.systab->hdr.revision >> 16, + efi.systab->hdr.revision & 0xffff); + + /* Show what we know for posterity */ + c16 = early_memremap(efi.systab->fw_vendor, + sizeof(vendor)); + if (c16) { + for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i) + vendor[i] = c16[i]; + vendor[i] = '\0'; + } + + pr_info("EFI v%u.%.02u by %s\n", + efi.systab->hdr.revision >> 16, + efi.systab->hdr.revision & 0xffff, vendor); + + retval = efi_config_init(NULL); + if (retval == 0) + set_bit(EFI_CONFIG_TABLES, &efi.flags); + + early_memunmap(c16, sizeof(vendor)); + early_memunmap(efi.systab, sizeof(efi_system_table_t)); + + return retval; +} + +static __initdata char memory_type_name[][32] = { + {"Reserved"}, + {"Loader Code"}, + {"Loader Data"}, + {"Boot Code"}, + {"Boot Data"}, + {"Runtime Code"}, + {"Runtime Data"}, + {"Conventional Memory"}, + {"Unusable Memory"}, + {"ACPI Reclaim Memory"}, + {"ACPI Memory NVS"}, + {"Memory Mapped I/O"}, + {"MMIO Port Space"}, + {"PAL Code"}, +}; + +/* + * Return true for RAM regions we want to permanently reserve. + */ +static __init int is_reserve_region(efi_memory_desc_t *md) +{ + if (!is_normal_ram(md)) + return 0; + + if (md->attribute & EFI_MEMORY_RUNTIME) + return 1; + + if (md->type == EFI_ACPI_RECLAIM_MEMORY || + md->type == EFI_RESERVED_TYPE) + return 1; + + return 0; +} + +static __init void reserve_regions(void) +{ + efi_memory_desc_t *md; + u64 paddr, npages, size; + + if (uefi_debug) + pr_info("Processing EFI memory map:\n"); + + for_each_efi_memory_desc(&memmap, md) { + paddr = md->phys_addr; + npages = md->num_pages; + + if (uefi_debug) + pr_info(" 0x%012llx-0x%012llx [%s]", + paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1, + memory_type_name[md->type]); + + memrange_efi_to_native(&paddr, &npages); + size = npages << PAGE_SHIFT; + + if (is_normal_ram(md)) + early_init_dt_add_memory_arch(paddr, size); + + if (is_reserve_region(md) || + md->type == EFI_BOOT_SERVICES_CODE || + md->type == EFI_BOOT_SERVICES_DATA) { + memblock_reserve(paddr, size); + if (uefi_debug) + pr_cont("*"); + } + + if (uefi_debug) + pr_cont("\n"); + } +} + + +static u64 __init free_one_region(u64 start, u64 end) +{ + u64 size = end - start; + + if (uefi_debug) + pr_info(" EFI freeing: 0x%012llx-0x%012llx\n", start, end - 1); + + free_bootmem_late(start, size); + return size; +} + +static u64 __init free_region(u64 start, u64 end) +{ + u64 map_start, map_end, total = 0; + + if (end <= start) + return total; + + map_start = (u64)memmap.phys_map; + map_end = PAGE_ALIGN(map_start + (memmap.map_end - memmap.map)); + map_start &= PAGE_MASK; + + if (start < map_end && end > map_start) { + /* region overlaps UEFI memmap */ + if (start < map_start) + total += free_one_region(start, map_start); + + if (map_end < end) + total += free_one_region(map_end, end); + } else + total += free_one_region(start, end); + + return total; +} + +static void __init free_boot_services(void) +{ + u64 total_freed = 0; + u64 keep_end, free_start, free_end; + efi_memory_desc_t *md; + + /* + * If kernel uses larger pages than UEFI, we have to be careful + * not to inadvertantly free memory we want to keep if there is + * overlap at the kernel page size alignment. We do not want to + * free is_reserve_region() memory nor the UEFI memmap itself. + * + * The memory map is sorted, so we keep track of the end of + * any previous region we want to keep, remember any region + * we want to free and defer freeing it until we encounter + * the next region we want to keep. This way, before freeing + * it, we can clip it as needed to avoid freeing memory we + * want to keep for UEFI. + */ + + keep_end = 0; + free_start = 0; + + for_each_efi_memory_desc(&memmap, md) { + u64 paddr, npages, size; + + if (is_reserve_region(md)) { + /* + * We don't want to free any memory from this region. + */ + if (free_start) { + /* adjust free_end then free region */ + if (free_end > md->phys_addr) + free_end -= PAGE_SIZE; + total_freed += free_region(free_start, free_end); + free_start = 0; + } + keep_end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT); + continue; + } + + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) { + /* no need to free this region */ + continue; + } + + /* + * We want to free memory from this region. + */ + paddr = md->phys_addr; + npages = md->num_pages; + memrange_efi_to_native(&paddr, &npages); + size = npages << PAGE_SHIFT; + + if (free_start) { + if (paddr <= free_end) + free_end = paddr + size; + else { + total_freed += free_region(free_start, free_end); + free_start = paddr; + free_end = paddr + size; + } + } else { + free_start = paddr; + free_end = paddr + size; + } + if (free_start < keep_end) { + free_start += PAGE_SIZE; + if (free_start >= free_end) + free_start = 0; + } + } + if (free_start) + total_freed += free_region(free_start, free_end); + + if (total_freed) + pr_info("Freed 0x%llx bytes of EFI boot services memory", + total_freed); +} + +void __init efi_init(void) +{ + struct efi_fdt_params params; + + /* Grab UEFI information placed in FDT by stub */ + if (!efi_get_fdt_params(¶ms, uefi_debug)) + return; + + efi_system_table = params.system_table; + + memblock_reserve(params.mmap & PAGE_MASK, + PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK))); + memmap.phys_map = (void *)params.mmap; + memmap.map = early_memremap(params.mmap, params.mmap_size); + memmap.map_end = memmap.map + params.mmap_size; + memmap.desc_size = params.desc_size; + memmap.desc_version = params.desc_ver; + + if (uefi_init() < 0) + return; + + reserve_regions(); +} + +void __init efi_idmap_init(void) +{ + if (!efi_enabled(EFI_BOOT)) + return; + + /* boot time idmap_pg_dir is incomplete, so fill in missing parts */ + efi_setup_idmap(); +} + +static int __init remap_region(efi_memory_desc_t *md, void **new) +{ + u64 paddr, vaddr, npages, size; + + paddr = md->phys_addr; + npages = md->num_pages; + memrange_efi_to_native(&paddr, &npages); + size = npages << PAGE_SHIFT; + + if (is_normal_ram(md)) + vaddr = (__force u64)ioremap_cache(paddr, size); + else + vaddr = (__force u64)ioremap(paddr, size); + + if (!vaddr) { + pr_err("Unable to remap 0x%llx pages @ %p\n", + npages, (void *)paddr); + return 0; + } + + /* adjust for any rounding when EFI and system pagesize differs */ + md->virt_addr = vaddr + (md->phys_addr - paddr); + + if (uefi_debug) + pr_info(" EFI remap 0x%012llx => %p\n", + md->phys_addr, (void *)md->virt_addr); + + memcpy(*new, md, memmap.desc_size); + *new += memmap.desc_size; + + return 1; +} + +/* + * Switch UEFI from an identity map to a kernel virtual map + */ +static int __init arm64_enter_virtual_mode(void) +{ + efi_memory_desc_t *md; + phys_addr_t virtmap_phys; + void *virtmap, *virt_md; + efi_status_t status; + u64 mapsize; + int count = 0; + unsigned long flags; + + if (!efi_enabled(EFI_BOOT)) { + pr_info("EFI services will not be available.\n"); + return -1; + } + + pr_info("Remapping and enabling EFI services.\n"); + + /* replace early memmap mapping with permanent mapping */ + mapsize = memmap.map_end - memmap.map; + early_memunmap(memmap.map, mapsize); + memmap.map = (__force void *)ioremap_cache((phys_addr_t)memmap.phys_map, + mapsize); + memmap.map_end = memmap.map + mapsize; + + efi.memmap = &memmap; + + /* Map the runtime regions */ + virtmap = kmalloc(mapsize, GFP_KERNEL); + if (!virtmap) { + pr_err("Failed to allocate EFI virtual memmap\n"); + return -1; + } + virtmap_phys = virt_to_phys(virtmap); + virt_md = virtmap; + + for_each_efi_memory_desc(&memmap, md) { + if (!(md->attribute & EFI_MEMORY_RUNTIME)) + continue; + if (remap_region(md, &virt_md)) + ++count; + } + + efi.systab = (__force void *)efi_lookup_mapped_addr(efi_system_table); + if (efi.systab) + set_bit(EFI_SYSTEM_TABLES, &efi.flags); + + local_irq_save(flags); + cpu_switch_mm(idmap_pg_dir, &init_mm); + + /* Call SetVirtualAddressMap with the physical address of the map */ + runtime = efi.systab->runtime; + efi.set_virtual_address_map = runtime->set_virtual_address_map; + + status = efi.set_virtual_address_map(count * memmap.desc_size, + memmap.desc_size, + memmap.desc_version, + (efi_memory_desc_t *)virtmap_phys); + cpu_set_reserved_ttbr0(); + flush_tlb_all(); + local_irq_restore(flags); + + kfree(virtmap); + + free_boot_services(); + + if (status != EFI_SUCCESS) { + pr_err("Failed to set EFI virtual address map! [%lx]\n", + status); + return -1; + } + + /* Set up runtime services function pointers */ + runtime = efi.systab->runtime; + efi.get_time = runtime->get_time; + efi.set_time = runtime->set_time; + efi.get_wakeup_time = runtime->get_wakeup_time; + efi.set_wakeup_time = runtime->set_wakeup_time; + efi.get_variable = runtime->get_variable; + efi.get_next_variable = runtime->get_next_variable; + efi.set_variable = runtime->set_variable; + efi.query_variable_info = runtime->query_variable_info; + efi.update_capsule = runtime->update_capsule; + efi.query_capsule_caps = runtime->query_capsule_caps; + efi.get_next_high_mono_count = runtime->get_next_high_mono_count; + efi.reset_system = runtime->reset_system; + + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); + + return 0; +} +early_initcall(arm64_enter_virtual_mode); diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S index 6a27cd6dbfa6..d358ccacfc00 100644 --- a/arch/arm64/kernel/entry-fpsimd.S +++ b/arch/arm64/kernel/entry-fpsimd.S @@ -41,3 +41,27 @@ ENTRY(fpsimd_load_state) fpsimd_restore x0, 8 ret ENDPROC(fpsimd_load_state) + +#ifdef CONFIG_KERNEL_MODE_NEON + +/* + * Save the bottom n FP registers. + * + * x0 - pointer to struct fpsimd_partial_state + */ +ENTRY(fpsimd_save_partial_state) + fpsimd_save_partial x0, 1, 8, 9 + ret +ENDPROC(fpsimd_load_partial_state) + +/* + * Load the bottom n FP registers. + * + * x0 - pointer to struct fpsimd_partial_state + */ +ENTRY(fpsimd_load_partial_state) + fpsimd_restore_partial x0, 8, 9 + ret +ENDPROC(fpsimd_load_partial_state) + +#endif diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S new file mode 100644 index 000000000000..b051871f2965 --- /dev/null +++ b/arch/arm64/kernel/entry-ftrace.S @@ -0,0 +1,218 @@ +/* + * arch/arm64/kernel/entry-ftrace.S + * + * Copyright (C) 2013 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/ftrace.h> +#include <asm/insn.h> + +/* + * Gcc with -pg will put the following code in the beginning of each function: + * mov x0, x30 + * bl _mcount + * [function's body ...] + * "bl _mcount" may be replaced to "bl ftrace_caller" or NOP if dynamic + * ftrace is enabled. + * + * Please note that x0 as an argument will not be used here because we can + * get lr(x30) of instrumented function at any time by winding up call stack + * as long as the kernel is compiled without -fomit-frame-pointer. + * (or CONFIG_FRAME_POINTER, this is forced on arm64) + * + * stack layout after mcount_enter in _mcount(): + * + * current sp/fp => 0:+-----+ + * in _mcount() | x29 | -> instrumented function's fp + * +-----+ + * | x30 | -> _mcount()'s lr (= instrumented function's pc) + * old sp => +16:+-----+ + * when instrumented | | + * function calls | ... | + * _mcount() | | + * | | + * instrumented => +xx:+-----+ + * function's fp | x29 | -> parent's fp + * +-----+ + * | x30 | -> instrumented function's lr (= parent's pc) + * +-----+ + * | ... | + */ + + .macro mcount_enter + stp x29, x30, [sp, #-16]! + mov x29, sp + .endm + + .macro mcount_exit + ldp x29, x30, [sp], #16 + ret + .endm + + .macro mcount_adjust_addr rd, rn + sub \rd, \rn, #AARCH64_INSN_SIZE + .endm + + /* for instrumented function's parent */ + .macro mcount_get_parent_fp reg + ldr \reg, [x29] + ldr \reg, [\reg] + .endm + + /* for instrumented function */ + .macro mcount_get_pc0 reg + mcount_adjust_addr \reg, x30 + .endm + + .macro mcount_get_pc reg + ldr \reg, [x29, #8] + mcount_adjust_addr \reg, \reg + .endm + + .macro mcount_get_lr reg + ldr \reg, [x29] + ldr \reg, [\reg, #8] + mcount_adjust_addr \reg, \reg + .endm + + .macro mcount_get_lr_addr reg + ldr \reg, [x29] + add \reg, \reg, #8 + .endm + +#ifndef CONFIG_DYNAMIC_FTRACE +/* + * void _mcount(unsigned long return_address) + * @return_address: return address to instrumented function + * + * This function makes calls, if enabled, to: + * - tracer function to probe instrumented function's entry, + * - ftrace_graph_caller to set up an exit hook + */ +ENTRY(_mcount) +#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST + ldr x0, =ftrace_trace_stop + ldr x0, [x0] // if ftrace_trace_stop + ret // return; +#endif + mcount_enter + + ldr x0, =ftrace_trace_function + ldr x2, [x0] + adr x0, ftrace_stub + cmp x0, x2 // if (ftrace_trace_function + b.eq skip_ftrace_call // != ftrace_stub) { + + mcount_get_pc x0 // function's pc + mcount_get_lr x1 // function's lr (= parent's pc) + blr x2 // (*ftrace_trace_function)(pc, lr); + +#ifndef CONFIG_FUNCTION_GRAPH_TRACER +skip_ftrace_call: // return; + mcount_exit // } +#else + mcount_exit // return; + // } +skip_ftrace_call: + ldr x1, =ftrace_graph_return + ldr x2, [x1] // if ((ftrace_graph_return + cmp x0, x2 // != ftrace_stub) + b.ne ftrace_graph_caller + + ldr x1, =ftrace_graph_entry // || (ftrace_graph_entry + ldr x2, [x1] // != ftrace_graph_entry_stub)) + ldr x0, =ftrace_graph_entry_stub + cmp x0, x2 + b.ne ftrace_graph_caller // ftrace_graph_caller(); + + mcount_exit +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ +ENDPROC(_mcount) + +#else /* CONFIG_DYNAMIC_FTRACE */ +/* + * _mcount() is used to build the kernel with -pg option, but all the branch + * instructions to _mcount() are replaced to NOP initially at kernel start up, + * and later on, NOP to branch to ftrace_caller() when enabled or branch to + * NOP when disabled per-function base. + */ +ENTRY(_mcount) + ret +ENDPROC(_mcount) + +/* + * void ftrace_caller(unsigned long return_address) + * @return_address: return address to instrumented function + * + * This function is a counterpart of _mcount() in 'static' ftrace, and + * makes calls to: + * - tracer function to probe instrumented function's entry, + * - ftrace_graph_caller to set up an exit hook + */ +ENTRY(ftrace_caller) + mcount_enter + + mcount_get_pc0 x0 // function's pc + mcount_get_lr x1 // function's lr + + .global ftrace_call +ftrace_call: // tracer(pc, lr); + nop // This will be replaced with "bl xxx" + // where xxx can be any kind of tracer. + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .global ftrace_graph_call +ftrace_graph_call: // ftrace_graph_caller(); + nop // If enabled, this will be replaced + // "b ftrace_graph_caller" +#endif + + mcount_exit +ENDPROC(ftrace_caller) +#endif /* CONFIG_DYNAMIC_FTRACE */ + +ENTRY(ftrace_stub) + ret +ENDPROC(ftrace_stub) + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* + * void ftrace_graph_caller(void) + * + * Called from _mcount() or ftrace_caller() when function_graph tracer is + * selected. + * This function w/ prepare_ftrace_return() fakes link register's value on + * the call stack in order to intercept instrumented function's return path + * and run return_to_handler() later on its exit. + */ +ENTRY(ftrace_graph_caller) + mcount_get_lr_addr x0 // pointer to function's saved lr + mcount_get_pc x1 // function's pc + mcount_get_parent_fp x2 // parent's fp + bl prepare_ftrace_return // prepare_ftrace_return(&lr, pc, fp) + + mcount_exit +ENDPROC(ftrace_graph_caller) + +/* + * void return_to_handler(void) + * + * Run ftrace_return_to_handler() before going back to parent. + * @fp is checked against the value passed by ftrace_graph_caller() + * only when CONFIG_FUNCTION_GRAPH_FP_TEST is enabled. + */ +ENTRY(return_to_handler) + str x0, [sp, #-16]! + mov x0, x29 // parent's fp + bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp); + mov x30, x0 // restore the original return address + ldr x0, [sp], #16 + ret +END(return_to_handler) +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 39ac630d83de..bf017f4ffb4f 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -60,6 +60,9 @@ push x0, x1 .if \el == 0 mrs x21, sp_el0 + get_thread_info tsk // Ensure MDSCR_EL1.SS is clear, + ldr x19, [tsk, #TI_FLAGS] // since we can unmask debug + disable_step_tsk x19, x20 // exceptions when scheduling. .else add x21, sp, #S_FRAME_SIZE .endif @@ -259,7 +262,7 @@ el1_da: * Data abort handling */ mrs x0, far_el1 - enable_dbg_if_not_stepping x2 + enable_dbg // re-enable interrupts if they were enabled in the aborted context tbnz x23, #7, 1f // PSR_I_BIT enable_irq @@ -275,6 +278,7 @@ el1_sp_pc: * Stack or PC alignment exception handling */ mrs x0, far_el1 + enable_dbg mov x1, x25 mov x2, sp b do_sp_pc_abort @@ -282,6 +286,7 @@ el1_undef: /* * Undefined instruction */ + enable_dbg mov x0, sp b do_undefinstr el1_dbg: @@ -294,10 +299,11 @@ el1_dbg: mrs x0, far_el1 mov x2, sp // struct pt_regs bl do_debug_exception - + enable_dbg kernel_exit 1 el1_inv: // TODO: add support for undefined instructions in kernel mode + enable_dbg mov x0, sp mov x1, #BAD_SYNC mrs x2, esr_el1 @@ -307,7 +313,7 @@ ENDPROC(el1_sync) .align 6 el1_irq: kernel_entry 1 - enable_dbg_if_not_stepping x0 + enable_dbg #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off #endif @@ -332,8 +338,7 @@ ENDPROC(el1_irq) #ifdef CONFIG_PREEMPT el1_preempt: mov x24, lr -1: enable_dbg - bl preempt_schedule_irq // irq en/disable is done inside +1: bl preempt_schedule_irq // irq en/disable is done inside ldr x0, [tsk, #TI_FLAGS] // get new tasks TI_FLAGS tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling? ret x24 @@ -349,7 +354,7 @@ el0_sync: lsr x24, x25, #ESR_EL1_EC_SHIFT // exception class cmp x24, #ESR_EL1_EC_SVC64 // SVC in 64-bit state b.eq el0_svc - adr lr, ret_from_exception + adr lr, ret_to_user cmp x24, #ESR_EL1_EC_DABT_EL0 // data abort in EL0 b.eq el0_da cmp x24, #ESR_EL1_EC_IABT_EL0 // instruction abort in EL0 @@ -378,7 +383,7 @@ el0_sync_compat: lsr x24, x25, #ESR_EL1_EC_SHIFT // exception class cmp x24, #ESR_EL1_EC_SVC32 // SVC in 32-bit state b.eq el0_svc_compat - adr lr, ret_from_exception + adr lr, ret_to_user cmp x24, #ESR_EL1_EC_DABT_EL0 // data abort in EL0 b.eq el0_da cmp x24, #ESR_EL1_EC_IABT_EL0 // instruction abort in EL0 @@ -423,11 +428,8 @@ el0_da: */ mrs x0, far_el1 bic x0, x0, #(0xff << 56) - disable_step x1 - isb - enable_dbg // enable interrupts before calling the main handler - enable_irq + enable_dbg_and_irq mov x1, x25 mov x2, sp b do_mem_abort @@ -436,11 +438,8 @@ el0_ia: * Instruction abort handling */ mrs x0, far_el1 - disable_step x1 - isb - enable_dbg // enable interrupts before calling the main handler - enable_irq + enable_dbg_and_irq orr x1, x25, #1 << 24 // use reserved ISS bit for instruction aborts mov x2, sp b do_mem_abort @@ -448,6 +447,7 @@ el0_fpsimd_acc: /* * Floating Point or Advanced SIMD access */ + enable_dbg mov x0, x25 mov x1, sp b do_fpsimd_acc @@ -455,6 +455,7 @@ el0_fpsimd_exc: /* * Floating Point or Advanced SIMD exception */ + enable_dbg mov x0, x25 mov x1, sp b do_fpsimd_exc @@ -463,11 +464,8 @@ el0_sp_pc: * Stack or PC alignment exception handling */ mrs x0, far_el1 - disable_step x1 - isb - enable_dbg // enable interrupts before calling the main handler - enable_irq + enable_dbg_and_irq mov x1, x25 mov x2, sp b do_sp_pc_abort @@ -475,9 +473,9 @@ el0_undef: /* * Undefined instruction */ - mov x0, sp // enable interrupts before calling the main handler - enable_irq + enable_dbg_and_irq + mov x0, sp b do_undefinstr el0_dbg: /* @@ -485,11 +483,13 @@ el0_dbg: */ tbnz x24, #0, el0_inv // EL0 only mrs x0, far_el1 - disable_step x1 mov x1, x25 mov x2, sp - b do_debug_exception + bl do_debug_exception + enable_dbg + b ret_to_user el0_inv: + enable_dbg mov x0, sp mov x1, #BAD_SYNC mrs x2, esr_el1 @@ -500,15 +500,12 @@ ENDPROC(el0_sync) el0_irq: kernel_entry 0 el0_irq_naked: - disable_step x1 - isb enable_dbg #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off #endif irq_handler - get_thread_info tsk #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_on @@ -517,14 +514,6 @@ el0_irq_naked: ENDPROC(el0_irq) /* - * This is the return code to user mode for abort handlers - */ -ret_from_exception: - get_thread_info tsk - b ret_to_user -ENDPROC(ret_from_exception) - -/* * Register switch for AArch64. The callee-saved registers need to be saved * and restored. On entry: * x0 = previous task_struct (must be preserved across the switch) @@ -563,10 +552,7 @@ ret_fast_syscall: ldr x1, [tsk, #TI_FLAGS] and x2, x1, #_TIF_WORK_MASK cbnz x2, fast_work_pending - tbz x1, #TIF_SINGLESTEP, fast_exit - disable_dbg - enable_step x2 -fast_exit: + enable_step_tsk x1, x2 kernel_exit 0, ret = 1 /* @@ -576,7 +562,7 @@ fast_work_pending: str x0, [sp, #S_X0] // returned x0 work_pending: tbnz x1, #TIF_NEED_RESCHED, work_resched - /* TIF_SIGPENDING or TIF_NOTIFY_RESUME case */ + /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */ ldr x2, [sp, #S_PSTATE] mov x0, sp // 'regs' tst x2, #PSR_MODE_MASK // user mode regs? @@ -585,7 +571,6 @@ work_pending: bl do_notify_resume b ret_to_user work_resched: - enable_dbg bl schedule /* @@ -596,9 +581,7 @@ ret_to_user: ldr x1, [tsk, #TI_FLAGS] and x2, x1, #_TIF_WORK_MASK cbnz x2, work_pending - tbz x1, #TIF_SINGLESTEP, no_work_pending - disable_dbg - enable_step x2 + enable_step_tsk x1, x2 no_work_pending: kernel_exit 0, ret = 0 ENDPROC(ret_to_user) @@ -625,14 +608,11 @@ el0_svc: mov sc_nr, #__NR_syscalls el0_svc_naked: // compat entry point stp x0, scno, [sp, #S_ORIG_X0] // save the original x0 and syscall number - disable_step x16 - isb - enable_dbg - enable_irq + enable_dbg_and_irq - get_thread_info tsk - ldr x16, [tsk, #TI_FLAGS] // check for syscall tracing - tbnz x16, #TIF_SYSCALL_TRACE, __sys_trace // are we tracing syscalls? + ldr x16, [tsk, #TI_FLAGS] // check for syscall hooks + tst x16, #_TIF_SYSCALL_WORK + b.ne __sys_trace adr lr, ret_fast_syscall // return address cmp scno, sc_nr // check upper syscall limit b.hs ni_sys @@ -648,9 +628,8 @@ ENDPROC(el0_svc) * switches, and waiting for our parent to respond. */ __sys_trace: - mov x1, sp - mov w0, #0 // trace entry - bl syscall_trace + mov x0, sp + bl syscall_trace_enter adr lr, __sys_trace_return // return address uxtw scno, w0 // syscall number (possibly new) mov x1, sp // pointer to regs @@ -665,9 +644,8 @@ __sys_trace: __sys_trace_return: str x0, [sp] // save returned x0 - mov x1, sp - mov w0, #1 // trace exit - bl syscall_trace + mov x0, sp + bl syscall_trace_exit b ret_to_user /* diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 4aef42a04bdc..ad8aebb1cdef 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -35,6 +35,60 @@ #define FPEXC_IDF (1 << 7) /* + * In order to reduce the number of times the FPSIMD state is needlessly saved + * and restored, we need to keep track of two things: + * (a) for each task, we need to remember which CPU was the last one to have + * the task's FPSIMD state loaded into its FPSIMD registers; + * (b) for each CPU, we need to remember which task's userland FPSIMD state has + * been loaded into its FPSIMD registers most recently, or whether it has + * been used to perform kernel mode NEON in the meantime. + * + * For (a), we add a 'cpu' field to struct fpsimd_state, which gets updated to + * the id of the current CPU everytime the state is loaded onto a CPU. For (b), + * we add the per-cpu variable 'fpsimd_last_state' (below), which contains the + * address of the userland FPSIMD state of the task that was loaded onto the CPU + * the most recently, or NULL if kernel mode NEON has been performed after that. + * + * With this in place, we no longer have to restore the next FPSIMD state right + * when switching between tasks. Instead, we can defer this check to userland + * resume, at which time we verify whether the CPU's fpsimd_last_state and the + * task's fpsimd_state.cpu are still mutually in sync. If this is the case, we + * can omit the FPSIMD restore. + * + * As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to + * indicate whether or not the userland FPSIMD state of the current task is + * present in the registers. The flag is set unless the FPSIMD registers of this + * CPU currently contain the most recent userland FPSIMD state of the current + * task. + * + * For a certain task, the sequence may look something like this: + * - the task gets scheduled in; if both the task's fpsimd_state.cpu field + * contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu + * variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is + * cleared, otherwise it is set; + * + * - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's + * userland FPSIMD state is copied from memory to the registers, the task's + * fpsimd_state.cpu field is set to the id of the current CPU, the current + * CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the + * TIF_FOREIGN_FPSTATE flag is cleared; + * + * - the task executes an ordinary syscall; upon return to userland, the + * TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is + * restored; + * + * - the task executes a syscall which executes some NEON instructions; this is + * preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD + * register contents to memory, clears the fpsimd_last_state per-cpu variable + * and sets the TIF_FOREIGN_FPSTATE flag; + * + * - the task gets preempted after kernel_neon_end() is called; as we have not + * returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so + * whatever is in the FPSIMD registers is not saved to memory, but discarded. + */ +static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state); + +/* * Trapped FP/ASIMD access. */ void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) @@ -72,43 +126,137 @@ void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) void fpsimd_thread_switch(struct task_struct *next) { - /* check if not kernel threads */ - if (current->mm) + /* + * Save the current FPSIMD state to memory, but only if whatever is in + * the registers is in fact the most recent userland FPSIMD state of + * 'current'. + */ + if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE)) fpsimd_save_state(¤t->thread.fpsimd_state); - if (next->mm) - fpsimd_load_state(&next->thread.fpsimd_state); + + if (next->mm) { + /* + * If we are switching to a task whose most recent userland + * FPSIMD state is already in the registers of *this* cpu, + * we can skip loading the state from memory. Otherwise, set + * the TIF_FOREIGN_FPSTATE flag so the state will be loaded + * upon the next return to userland. + */ + struct fpsimd_state *st = &next->thread.fpsimd_state; + + if (__this_cpu_read(fpsimd_last_state) == st + && st->cpu == smp_processor_id()) + clear_ti_thread_flag(task_thread_info(next), + TIF_FOREIGN_FPSTATE); + else + set_ti_thread_flag(task_thread_info(next), + TIF_FOREIGN_FPSTATE); + } } void fpsimd_flush_thread(void) { - preempt_disable(); memset(¤t->thread.fpsimd_state, 0, sizeof(struct fpsimd_state)); - fpsimd_load_state(¤t->thread.fpsimd_state); + set_thread_flag(TIF_FOREIGN_FPSTATE); +} + +/* + * Save the userland FPSIMD state of 'current' to memory, but only if the state + * currently held in the registers does in fact belong to 'current' + */ +void fpsimd_preserve_current_state(void) +{ + preempt_disable(); + if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) + fpsimd_save_state(¤t->thread.fpsimd_state); + preempt_enable(); +} + +/* + * Load the userland FPSIMD state of 'current' from memory, but only if the + * FPSIMD state already held in the registers is /not/ the most recent FPSIMD + * state of 'current' + */ +void fpsimd_restore_current_state(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { + struct fpsimd_state *st = ¤t->thread.fpsimd_state; + + fpsimd_load_state(st); + this_cpu_write(fpsimd_last_state, st); + st->cpu = smp_processor_id(); + } + preempt_enable(); +} + +/* + * Load an updated userland FPSIMD state for 'current' from memory and set the + * flag that indicates that the FPSIMD register contents are the most recent + * FPSIMD state of 'current' + */ +void fpsimd_update_current_state(struct fpsimd_state *state) +{ + preempt_disable(); + fpsimd_load_state(state); + if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { + struct fpsimd_state *st = ¤t->thread.fpsimd_state; + + this_cpu_write(fpsimd_last_state, st); + st->cpu = smp_processor_id(); + } preempt_enable(); } +/* + * Invalidate live CPU copies of task t's FPSIMD state + */ +void fpsimd_flush_task_state(struct task_struct *t) +{ + t->thread.fpsimd_state.cpu = NR_CPUS; +} + #ifdef CONFIG_KERNEL_MODE_NEON +static DEFINE_PER_CPU(struct fpsimd_partial_state, hardirq_fpsimdstate); +static DEFINE_PER_CPU(struct fpsimd_partial_state, softirq_fpsimdstate); + /* * Kernel-side NEON support functions */ -void kernel_neon_begin(void) +void kernel_neon_begin_partial(u32 num_regs) { - /* Avoid using the NEON in interrupt context */ - BUG_ON(in_interrupt()); - preempt_disable(); + if (in_interrupt()) { + struct fpsimd_partial_state *s = this_cpu_ptr( + in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate); - if (current->mm) - fpsimd_save_state(¤t->thread.fpsimd_state); + BUG_ON(num_regs > 32); + fpsimd_save_partial_state(s, roundup(num_regs, 2)); + } else { + /* + * Save the userland FPSIMD state if we have one and if we + * haven't done so already. Clear fpsimd_last_state to indicate + * that there is no longer userland FPSIMD state in the + * registers. + */ + preempt_disable(); + if (current->mm && + !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE)) + fpsimd_save_state(¤t->thread.fpsimd_state); + this_cpu_write(fpsimd_last_state, NULL); + } } -EXPORT_SYMBOL(kernel_neon_begin); +EXPORT_SYMBOL(kernel_neon_begin_partial); void kernel_neon_end(void) { - if (current->mm) - fpsimd_load_state(¤t->thread.fpsimd_state); - - preempt_enable(); + if (in_interrupt()) { + struct fpsimd_partial_state *s = this_cpu_ptr( + in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate); + fpsimd_load_partial_state(s); + } else { + preempt_enable(); + } } EXPORT_SYMBOL(kernel_neon_end); @@ -120,12 +268,12 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self, { switch (cmd) { case CPU_PM_ENTER: - if (current->mm) + if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE)) fpsimd_save_state(¤t->thread.fpsimd_state); break; case CPU_PM_EXIT: if (current->mm) - fpsimd_load_state(¤t->thread.fpsimd_state); + set_thread_flag(TIF_FOREIGN_FPSTATE); break; case CPU_PM_ENTER_FAILED: default: diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c new file mode 100644 index 000000000000..7924d73b6476 --- /dev/null +++ b/arch/arm64/kernel/ftrace.c @@ -0,0 +1,176 @@ +/* + * arch/arm64/kernel/ftrace.c + * + * Copyright (C) 2013 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/ftrace.h> +#include <linux/swab.h> +#include <linux/uaccess.h> + +#include <asm/cacheflush.h> +#include <asm/ftrace.h> +#include <asm/insn.h> + +#ifdef CONFIG_DYNAMIC_FTRACE +/* + * Replace a single instruction, which may be a branch or NOP. + * If @validate == true, a replaced instruction is checked against 'old'. + */ +static int ftrace_modify_code(unsigned long pc, u32 old, u32 new, + bool validate) +{ + u32 replaced; + + /* + * Note: + * Due to modules and __init, code can disappear and change, + * we need to protect against faulting as well as code changing. + * We do this by aarch64_insn_*() which use the probe_kernel_*(). + * + * No lock is held here because all the modifications are run + * through stop_machine(). + */ + if (validate) { + if (aarch64_insn_read((void *)pc, &replaced)) + return -EFAULT; + + if (replaced != old) + return -EINVAL; + } + if (aarch64_insn_patch_text_nosync((void *)pc, new)) + return -EPERM; + + return 0; +} + +/* + * Replace tracer function in ftrace_caller() + */ +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long pc; + u32 new; + + pc = (unsigned long)&ftrace_call; + new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func, true); + + return ftrace_modify_code(pc, 0, new, false); +} + +/* + * Turn on the call to ftrace_caller() in instrumented function + */ +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long pc = rec->ip; + u32 old, new; + + old = aarch64_insn_gen_nop(); + new = aarch64_insn_gen_branch_imm(pc, addr, true); + + return ftrace_modify_code(pc, old, new, true); +} + +/* + * Turn off the call to ftrace_caller() in instrumented function + */ +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, + unsigned long addr) +{ + unsigned long pc = rec->ip; + u32 old, new; + + old = aarch64_insn_gen_branch_imm(pc, addr, true); + new = aarch64_insn_gen_nop(); + + return ftrace_modify_code(pc, old, new, true); +} + +int __init ftrace_dyn_arch_init(void) +{ + return 0; +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* + * function_graph tracer expects ftrace_return_to_handler() to be called + * on the way back to parent. For this purpose, this function is called + * in _mcount() or ftrace_caller() to replace return address (*parent) on + * the call stack to return_to_handler. + * + * Note that @frame_pointer is used only for sanity check later. + */ +void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long old; + struct ftrace_graph_ent trace; + int err; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + /* + * Note: + * No protection against faulting at *parent, which may be seen + * on other archs. It's unlikely on AArch64. + */ + old = *parent; + *parent = return_hooker; + + trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) { + *parent = old; + return; + } + + err = ftrace_push_return_trace(old, self_addr, &trace.depth, + frame_pointer); + if (err == -EBUSY) { + *parent = old; + return; + } +} + +#ifdef CONFIG_DYNAMIC_FTRACE +/* + * Turn on/off the call to ftrace_graph_caller() in ftrace_caller() + * depending on @enable. + */ +static int ftrace_modify_graph_caller(bool enable) +{ + unsigned long pc = (unsigned long)&ftrace_graph_call; + u32 branch, nop; + + branch = aarch64_insn_gen_branch_imm(pc, + (unsigned long)ftrace_graph_caller, false); + nop = aarch64_insn_gen_nop(); + + if (enable) + return ftrace_modify_code(pc, nop, branch, true); + else + return ftrace_modify_code(pc, branch, nop, true); +} + +int ftrace_enable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(true); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(false); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 0fd565000772..a96d3a6a63f6 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -108,8 +108,18 @@ /* * DO NOT MODIFY. Image header expected by Linux boot-loaders. */ +#ifdef CONFIG_EFI +efi_head: + /* + * This add instruction has no meaningful effect except that + * its opcode forms the magic "MZ" signature required by UEFI. + */ + add x13, x18, #0x16 + b stext +#else b stext // branch to kernel start, magic .long 0 // reserved +#endif .quad TEXT_OFFSET // Image load offset from start of RAM .quad 0 // reserved .quad 0 // reserved @@ -120,7 +130,109 @@ .byte 0x52 .byte 0x4d .byte 0x64 +#ifdef CONFIG_EFI + .long pe_header - efi_head // Offset to the PE header. +#else .word 0 // reserved +#endif + +#ifdef CONFIG_EFI + .align 3 +pe_header: + .ascii "PE" + .short 0 +coff_header: + .short 0xaa64 // AArch64 + .short 2 // nr_sections + .long 0 // TimeDateStamp + .long 0 // PointerToSymbolTable + .long 1 // NumberOfSymbols + .short section_table - optional_header // SizeOfOptionalHeader + .short 0x206 // Characteristics. + // IMAGE_FILE_DEBUG_STRIPPED | + // IMAGE_FILE_EXECUTABLE_IMAGE | + // IMAGE_FILE_LINE_NUMS_STRIPPED +optional_header: + .short 0x20b // PE32+ format + .byte 0x02 // MajorLinkerVersion + .byte 0x14 // MinorLinkerVersion + .long _edata - stext // SizeOfCode + .long 0 // SizeOfInitializedData + .long 0 // SizeOfUninitializedData + .long efi_stub_entry - efi_head // AddressOfEntryPoint + .long stext - efi_head // BaseOfCode + +extra_header_fields: + .quad 0 // ImageBase + .long 0x20 // SectionAlignment + .long 0x8 // FileAlignment + .short 0 // MajorOperatingSystemVersion + .short 0 // MinorOperatingSystemVersion + .short 0 // MajorImageVersion + .short 0 // MinorImageVersion + .short 0 // MajorSubsystemVersion + .short 0 // MinorSubsystemVersion + .long 0 // Win32VersionValue + + .long _edata - efi_head // SizeOfImage + + // Everything before the kernel image is considered part of the header + .long stext - efi_head // SizeOfHeaders + .long 0 // CheckSum + .short 0xa // Subsystem (EFI application) + .short 0 // DllCharacteristics + .quad 0 // SizeOfStackReserve + .quad 0 // SizeOfStackCommit + .quad 0 // SizeOfHeapReserve + .quad 0 // SizeOfHeapCommit + .long 0 // LoaderFlags + .long 0x6 // NumberOfRvaAndSizes + + .quad 0 // ExportTable + .quad 0 // ImportTable + .quad 0 // ResourceTable + .quad 0 // ExceptionTable + .quad 0 // CertificationTable + .quad 0 // BaseRelocationTable + + // Section table +section_table: + + /* + * The EFI application loader requires a relocation section + * because EFI applications must be relocatable. This is a + * dummy section as far as we are concerned. + */ + .ascii ".reloc" + .byte 0 + .byte 0 // end of 0 padding of section name + .long 0 + .long 0 + .long 0 // SizeOfRawData + .long 0 // PointerToRawData + .long 0 // PointerToRelocations + .long 0 // PointerToLineNumbers + .short 0 // NumberOfRelocations + .short 0 // NumberOfLineNumbers + .long 0x42100040 // Characteristics (section flags) + + + .ascii ".text" + .byte 0 + .byte 0 + .byte 0 // end of 0 padding of section name + .long _edata - stext // VirtualSize + .long stext - efi_head // VirtualAddress + .long _edata - stext // SizeOfRawData + .long stext - efi_head // PointerToRawData + + .long 0 // PointerToRelocations (0 for executables) + .long 0 // PointerToLineNumbers (0 for executables) + .short 0 // NumberOfRelocations (0 for executables) + .short 0 // NumberOfLineNumbers (0 for executables) + .long 0xe0500020 // Characteristics (section flags) + .align 5 +#endif ENTRY(stext) mov x21, x0 // x21=FDT @@ -230,11 +342,9 @@ ENTRY(set_cpu_boot_mode_flag) cmp w20, #BOOT_CPU_MODE_EL2 b.ne 1f add x1, x1, #4 -1: dc cvac, x1 // Clean potentially dirty cache line - dsb sy - str w20, [x1] // This CPU has booted in EL1 - dc civac, x1 // Clean&invalidate potentially stale cache line - dsb sy +1: str w20, [x1] // This CPU has booted in EL1 + dmb sy + dc ivac, x1 // Invalidate potentially stale cache line ret ENDPROC(set_cpu_boot_mode_flag) diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index bee789757806..df1cf15377b4 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -20,6 +20,7 @@ #define pr_fmt(fmt) "hw-breakpoint: " fmt +#include <linux/compat.h> #include <linux/cpu_pm.h> #include <linux/errno.h> #include <linux/hw_breakpoint.h> @@ -27,7 +28,6 @@ #include <linux/ptrace.h> #include <linux/smp.h> -#include <asm/compat.h> #include <asm/current.h> #include <asm/debug-monitors.h> #include <asm/hw_breakpoint.h> diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 6391485f342d..43b7c34f92cb 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -20,6 +20,7 @@ #include <stdarg.h> +#include <linux/compat.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/kernel.h> @@ -113,32 +114,62 @@ void arch_cpu_idle_dead(void) } #endif +/* + * Called by kexec, immediately prior to machine_kexec(). + * + * This must completely disable all secondary CPUs; simply causing those CPUs + * to execute e.g. a RAM-based pin loop is not sufficient. This allows the + * kexec'd kernel to use any and all RAM as it sees fit, without having to + * avoid any code or data used by any SW CPU pin loop. The CPU hotplug + * functionality embodied in disable_nonboot_cpus() to achieve this. + */ void machine_shutdown(void) { -#ifdef CONFIG_SMP - smp_send_stop(); -#endif + disable_nonboot_cpus(); } +/* + * Halting simply requires that the secondary CPUs stop performing any + * activity (executing tasks, handling interrupts). smp_send_stop() + * achieves this. + */ void machine_halt(void) { - machine_shutdown(); + local_irq_disable(); + smp_send_stop(); while (1); } +/* + * Power-off simply requires that the secondary CPUs stop performing any + * activity (executing tasks, handling interrupts). smp_send_stop() + * achieves this. When the system power is turned off, it will take all CPUs + * with it. + */ void machine_power_off(void) { - machine_shutdown(); + local_irq_disable(); + smp_send_stop(); if (pm_power_off) pm_power_off(); } +/* + * Restart requires that the secondary CPUs stop performing any activity + * while the primary CPU resets the system. Systems with a single CPU can + * use soft_restart() as their machine descriptor's .restart hook, since that + * will cause the only available CPU to reset. Systems with multiple CPUs must + * provide a HW restart implementation, to ensure that all CPUs reset at once. + * This is required so that any code running after reset on the primary CPU + * doesn't have to co-ordinate with other CPUs to ensure they aren't still + * executing pre-reset code, and using RAM that the primary CPU's code wishes + * to use. Implementing such co-ordination would be essentially impossible. + */ void machine_restart(char *cmd) { - machine_shutdown(); - /* Disable interrupts first */ local_irq_disable(); + smp_send_stop(); /* Now call the architecture specific reboot code. */ if (arm_pm_restart) @@ -205,7 +236,7 @@ void release_thread(struct task_struct *dead_task) int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - fpsimd_save_state(¤t->thread.fpsimd_state); + fpsimd_preserve_current_state(); *dst = *src; return 0; } @@ -300,7 +331,7 @@ struct task_struct *__switch_to(struct task_struct *prev, * Complete any pending TLB or cache maintenance on this CPU in case * the thread migrates to a different CPU. */ - dsb(); + dsb(ish); /* the actual thread switch */ last = cpu_switch_to(prev, next); diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 6a8928bba03c..3e926b9c0641 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -19,6 +19,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/compat.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/mm.h> @@ -41,6 +42,9 @@ #include <asm/traps.h> #include <asm/system_misc.h> +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + /* * TODO: does not yet catch signals sent when the child dies. * in exit.c or in signal.c. @@ -517,6 +521,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, return ret; target->thread.fpsimd_state.user_fpsimd = newstate; + fpsimd_flush_task_state(target); return ret; } @@ -764,6 +769,7 @@ static int compat_vfp_set(struct task_struct *target, uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK; } + fpsimd_flush_task_state(target); return ret; } @@ -1058,35 +1064,49 @@ long arch_ptrace(struct task_struct *child, long request, return ptrace_request(child, request, addr, data); } -asmlinkage int syscall_trace(int dir, struct pt_regs *regs) +enum ptrace_syscall_dir { + PTRACE_SYSCALL_ENTER = 0, + PTRACE_SYSCALL_EXIT, +}; + +static void tracehook_report_syscall(struct pt_regs *regs, + enum ptrace_syscall_dir dir) { + int regno; unsigned long saved_reg; - if (!test_thread_flag(TIF_SYSCALL_TRACE)) - return regs->syscallno; - - if (is_compat_task()) { - /* AArch32 uses ip (r12) for scratch */ - saved_reg = regs->regs[12]; - regs->regs[12] = dir; - } else { - /* - * Save X7. X7 is used to denote syscall entry/exit: - * X7 = 0 -> entry, = 1 -> exit - */ - saved_reg = regs->regs[7]; - regs->regs[7] = dir; - } + /* + * A scratch register (ip(r12) on AArch32, x7 on AArch64) is + * used to denote syscall entry/exit: + */ + regno = (is_compat_task() ? 12 : 7); + saved_reg = regs->regs[regno]; + regs->regs[regno] = dir; - if (dir) + if (dir == PTRACE_SYSCALL_EXIT) tracehook_report_syscall_exit(regs, 0); else if (tracehook_report_syscall_entry(regs)) regs->syscallno = ~0UL; - if (is_compat_task()) - regs->regs[12] = saved_reg; - else - regs->regs[7] = saved_reg; + regs->regs[regno] = saved_reg; +} + +asmlinkage int syscall_trace_enter(struct pt_regs *regs) +{ + if (test_thread_flag(TIF_SYSCALL_TRACE)) + tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); + + if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + trace_sys_enter(regs, regs->syscallno); return regs->syscallno; } + +asmlinkage void syscall_trace_exit(struct pt_regs *regs) +{ + if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + trace_sys_exit(regs, regs_return_value(regs)); + + if (test_thread_flag(TIF_SYSCALL_TRACE)) + tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); +} diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c new file mode 100644 index 000000000000..89102a6ffad5 --- /dev/null +++ b/arch/arm64/kernel/return_address.c @@ -0,0 +1,55 @@ +/* + * arch/arm64/kernel/return_address.c + * + * Copyright (C) 2013 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/export.h> +#include <linux/ftrace.h> + +#include <asm/stacktrace.h> + +struct return_address_data { + unsigned int level; + void *addr; +}; + +static int save_return_addr(struct stackframe *frame, void *d) +{ + struct return_address_data *data = d; + + if (!data->level) { + data->addr = (void *)frame->pc; + return 1; + } else { + --data->level; + return 0; + } +} + +void *return_address(unsigned int level) +{ + struct return_address_data data; + struct stackframe frame; + register unsigned long current_sp asm ("sp"); + + data.level = level + 2; + data.addr = NULL; + + frame.fp = (unsigned long)__builtin_frame_address(0); + frame.sp = current_sp; + frame.pc = (unsigned long)return_address; /* dummy */ + + walk_stackframe(&frame, save_return_addr, &data); + + if (!data.level) + return data.addr; + else + return NULL; +} +EXPORT_SYMBOL_GPL(return_address); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 7ec784653b29..46d1125571f6 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -25,6 +25,7 @@ #include <linux/utsname.h> #include <linux/initrd.h> #include <linux/console.h> +#include <linux/cache.h> #include <linux/bootmem.h> #include <linux/seq_file.h> #include <linux/screen_info.h> @@ -41,6 +42,7 @@ #include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/of_platform.h> +#include <linux/efi.h> #include <asm/fixmap.h> #include <asm/cputype.h> @@ -55,6 +57,7 @@ #include <asm/traps.h> #include <asm/memblock.h> #include <asm/psci.h> +#include <asm/efi.h> unsigned int processor_id; EXPORT_SYMBOL(processor_id); @@ -198,6 +201,8 @@ static void __init setup_processor(void) { struct cpu_info *cpu_info; u64 features, block; + u32 cwg; + int cls; cpu_info = lookup_processor_type(read_cpuid_id()); if (!cpu_info) { @@ -215,6 +220,18 @@ static void __init setup_processor(void) elf_hwcap = 0; /* + * Check for sane CTR_EL0.CWG value. + */ + cwg = cache_type_cwg(); + cls = cache_line_size(); + if (!cwg) + pr_warn("No Cache Writeback Granule information, assuming cache line size %d\n", + cls); + if (L1_CACHE_BYTES < cls) + pr_warn("L1_CACHE_BYTES smaller than the Cache Writeback Granule (%d < %d)\n", + L1_CACHE_BYTES, cls); + + /* * ID_AA64ISAR0_EL1 contains 4-bit wide signed feature blocks. * The blocks we test below represent incremental functionality * for non-negative values. Negative values are reserved. @@ -361,16 +378,18 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; - init_mem_pgprot(); early_ioremap_init(); parse_early_param(); + efi_init(); arm64_memblock_init(); paging_init(); request_standard_resources(); + efi_idmap_init(); + unflatten_device_tree(); psci_init(); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 890a591f75dd..6357b9c6c90e 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -17,6 +17,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/compat.h> #include <linux/errno.h> #include <linux/signal.h> #include <linux/personality.h> @@ -25,7 +26,6 @@ #include <linux/tracehook.h> #include <linux/ratelimit.h> -#include <asm/compat.h> #include <asm/debug-monitors.h> #include <asm/elf.h> #include <asm/cacheflush.h> @@ -51,7 +51,7 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx) int err; /* dump the hardware registers to the fpsimd_state structure */ - fpsimd_save_state(fpsimd); + fpsimd_preserve_current_state(); /* copy the FP and status/control registers */ err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs)); @@ -86,11 +86,8 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx) __get_user_error(fpsimd.fpcr, &ctx->fpcr, err); /* load the hardware registers from the fpsimd_state structure */ - if (!err) { - preempt_disable(); - fpsimd_load_state(&fpsimd); - preempt_enable(); - } + if (!err) + fpsimd_update_current_state(&fpsimd); return err ? -EFAULT : 0; } @@ -100,8 +97,7 @@ static int restore_sigframe(struct pt_regs *regs, { sigset_t set; int i, err; - struct aux_context __user *aux = - (struct aux_context __user *)sf->uc.uc_mcontext.__reserved; + void *aux = sf->uc.uc_mcontext.__reserved; err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set)); if (err == 0) @@ -121,8 +117,11 @@ static int restore_sigframe(struct pt_regs *regs, err |= !valid_user_regs(®s->user_regs); - if (err == 0) - err |= restore_fpsimd_context(&aux->fpsimd); + if (err == 0) { + struct fpsimd_context *fpsimd_ctx = + container_of(aux, struct fpsimd_context, head); + err |= restore_fpsimd_context(fpsimd_ctx); + } return err; } @@ -167,8 +166,8 @@ static int setup_sigframe(struct rt_sigframe __user *sf, struct pt_regs *regs, sigset_t *set) { int i, err = 0; - struct aux_context __user *aux = - (struct aux_context __user *)sf->uc.uc_mcontext.__reserved; + void *aux = sf->uc.uc_mcontext.__reserved; + struct _aarch64_ctx *end; /* set up the stack frame for unwinding */ __put_user_error(regs->regs[29], &sf->fp, err); @@ -185,12 +184,27 @@ static int setup_sigframe(struct rt_sigframe __user *sf, err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set)); - if (err == 0) - err |= preserve_fpsimd_context(&aux->fpsimd); + if (err == 0) { + struct fpsimd_context *fpsimd_ctx = + container_of(aux, struct fpsimd_context, head); + err |= preserve_fpsimd_context(fpsimd_ctx); + aux += sizeof(*fpsimd_ctx); + } + + /* fault information, if valid */ + if (current->thread.fault_code) { + struct esr_context *esr_ctx = + container_of(aux, struct esr_context, head); + __put_user_error(ESR_MAGIC, &esr_ctx->head.magic, err); + __put_user_error(sizeof(*esr_ctx), &esr_ctx->head.size, err); + __put_user_error(current->thread.fault_code, &esr_ctx->esr, err); + aux += sizeof(*esr_ctx); + } /* set the "end" magic */ - __put_user_error(0, &aux->end.magic, err); - __put_user_error(0, &aux->end.size, err); + end = aux; + __put_user_error(0, &end->magic, err); + __put_user_error(0, &end->size, err); return err; } @@ -416,4 +430,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); } + + if (thread_flags & _TIF_FOREIGN_FPSTATE) + fpsimd_restore_current_state(); + } diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index b3fc9f5ec6d3..3491c638f172 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -23,6 +23,7 @@ #include <linux/syscalls.h> #include <linux/ratelimit.h> +#include <asm/esr.h> #include <asm/fpsimd.h> #include <asm/signal32.h> #include <asm/uaccess.h> @@ -81,6 +82,8 @@ struct compat_vfp_sigframe { #define VFP_MAGIC 0x56465001 #define VFP_STORAGE_SIZE sizeof(struct compat_vfp_sigframe) +#define FSR_WRITE_SHIFT (11) + struct compat_aux_sigframe { struct compat_vfp_sigframe vfp; @@ -219,7 +222,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame) * Note that this also saves V16-31, which aren't visible * in AArch32. */ - fpsimd_save_state(fpsimd); + fpsimd_preserve_current_state(); /* Place structure header on the stack */ __put_user_error(magic, &frame->magic, err); @@ -282,11 +285,8 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame) * We don't need to touch the exception register, so * reload the hardware state. */ - if (!err) { - preempt_disable(); - fpsimd_load_state(&fpsimd); - preempt_enable(); - } + if (!err) + fpsimd_update_current_state(&fpsimd); return err ? -EFAULT : 0; } @@ -500,7 +500,9 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf, __put_user_error(regs->pstate, &sf->uc.uc_mcontext.arm_cpsr, err); __put_user_error((compat_ulong_t)0, &sf->uc.uc_mcontext.trap_no, err); - __put_user_error((compat_ulong_t)0, &sf->uc.uc_mcontext.error_code, err); + /* set the compat FSR WnR */ + __put_user_error(!!(current->thread.fault_code & ESR_EL1_WRITE) << + FSR_WRITE_SHIFT, &sf->uc.uc_mcontext.error_code, err); __put_user_error(current->thread.fault_address, &sf->uc.uc_mcontext.fault_address, err); __put_user_error(set->sig[0], &sf->uc.uc_mcontext.oldmask, err); diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index c3cb160edc69..40f38f46c8e0 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -35,6 +35,7 @@ #include <linux/clockchips.h> #include <linux/completion.h> #include <linux/of.h> +#include <linux/irq_work.h> #include <asm/atomic.h> #include <asm/cacheflush.h> @@ -62,6 +63,7 @@ enum ipi_msg_type { IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, IPI_TIMER, + IPI_IRQ_WORK, }; /* @@ -477,6 +479,14 @@ void arch_send_call_function_single_ipi(int cpu) smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); } +#ifdef CONFIG_IRQ_WORK +void arch_irq_work_raise(void) +{ + if (smp_cross_call) + smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK); +} +#endif + static const char *ipi_types[NR_IPI] = { #define S(x,s) [x - IPI_RESCHEDULE] = s S(IPI_RESCHEDULE, "Rescheduling interrupts"), @@ -484,6 +494,7 @@ static const char *ipi_types[NR_IPI] = { S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), S(IPI_TIMER, "Timer broadcast interrupts"), + S(IPI_IRQ_WORK, "IRQ work interrupts"), }; void show_ipi_list(struct seq_file *p, int prec) @@ -576,6 +587,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs) break; #endif +#ifdef CONFIG_IRQ_WORK + case IPI_IRQ_WORK: + irq_enter(); + irq_work_run(); + irq_exit(); + break; +#endif + default: pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr); break; diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c index 7a530d2cc807..0347d38eea29 100644 --- a/arch/arm64/kernel/smp_spin_table.c +++ b/arch/arm64/kernel/smp_spin_table.c @@ -30,7 +30,6 @@ extern void secondary_holding_pen(void); volatile unsigned long secondary_holding_pen_release = INVALID_HWID; static phys_addr_t cpu_release_addr[NR_CPUS]; -static DEFINE_RAW_SPINLOCK(boot_lock); /* * Write secondary_holding_pen_release in a way that is guaranteed to be @@ -94,14 +93,6 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu) static int smp_spin_table_cpu_boot(unsigned int cpu) { - unsigned long timeout; - - /* - * Set synchronisation state between this boot processor - * and the secondary one - */ - raw_spin_lock(&boot_lock); - /* * Update the pen release flag. */ @@ -112,34 +103,7 @@ static int smp_spin_table_cpu_boot(unsigned int cpu) */ sev(); - timeout = jiffies + (1 * HZ); - while (time_before(jiffies, timeout)) { - if (secondary_holding_pen_release == INVALID_HWID) - break; - udelay(10); - } - - /* - * Now the secondary core is starting up let it run its - * calibrations, then wait for it to finish - */ - raw_spin_unlock(&boot_lock); - - return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0; -} - -static void smp_spin_table_cpu_postboot(void) -{ - /* - * Let the primary processor know we're out of the pen. - */ - write_pen_release(INVALID_HWID); - - /* - * Synchronise with the boot thread. - */ - raw_spin_lock(&boot_lock); - raw_spin_unlock(&boot_lock); + return 0; } const struct cpu_operations smp_spin_table_ops = { @@ -147,5 +111,4 @@ const struct cpu_operations smp_spin_table_ops = { .cpu_init = smp_spin_table_cpu_init, .cpu_prepare = smp_spin_table_cpu_prepare, .cpu_boot = smp_spin_table_cpu_boot, - .cpu_postboot = smp_spin_table_cpu_postboot, }; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 38f0558f0c0a..55437ba1f5a4 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -35,7 +35,7 @@ * ldp x29, x30, [sp] * add sp, sp, #0x10 */ -int unwind_frame(struct stackframe *frame) +int notrace unwind_frame(struct stackframe *frame) { unsigned long high, low; unsigned long fp = frame->fp; diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 6815987b50f8..1a7125c3099b 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -18,6 +18,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/clockchips.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/interrupt.h> @@ -69,6 +70,8 @@ void __init time_init(void) of_clk_init(NULL); clocksource_of_init(); + tick_setup_hrtimer_broadcast(); + arch_timer_rate = arch_timer_get_rate(); if (!arch_timer_rate) panic("Unable to initialise architected timer.\n"); diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 3e06b0be4ec8..43514f905916 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -17,10 +17,192 @@ #include <linux/percpu.h> #include <linux/node.h> #include <linux/nodemask.h> +#include <linux/of.h> #include <linux/sched.h> #include <asm/topology.h> +static int __init get_cpu_for_node(struct device_node *node) +{ + struct device_node *cpu_node; + int cpu; + + cpu_node = of_parse_phandle(node, "cpu", 0); + if (!cpu_node) + return -1; + + for_each_possible_cpu(cpu) { + if (of_get_cpu_node(cpu, NULL) == cpu_node) { + of_node_put(cpu_node); + return cpu; + } + } + + pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name); + + of_node_put(cpu_node); + return -1; +} + +static int __init parse_core(struct device_node *core, int cluster_id, + int core_id) +{ + char name[10]; + bool leaf = true; + int i = 0; + int cpu; + struct device_node *t; + + do { + snprintf(name, sizeof(name), "thread%d", i); + t = of_get_child_by_name(core, name); + if (t) { + leaf = false; + cpu = get_cpu_for_node(t); + if (cpu >= 0) { + cpu_topology[cpu].cluster_id = cluster_id; + cpu_topology[cpu].core_id = core_id; + cpu_topology[cpu].thread_id = i; + } else { + pr_err("%s: Can't get CPU for thread\n", + t->full_name); + of_node_put(t); + return -EINVAL; + } + of_node_put(t); + } + i++; + } while (t); + + cpu = get_cpu_for_node(core); + if (cpu >= 0) { + if (!leaf) { + pr_err("%s: Core has both threads and CPU\n", + core->full_name); + return -EINVAL; + } + + cpu_topology[cpu].cluster_id = cluster_id; + cpu_topology[cpu].core_id = core_id; + } else if (leaf) { + pr_err("%s: Can't get CPU for leaf core\n", core->full_name); + return -EINVAL; + } + + return 0; +} + +static int __init parse_cluster(struct device_node *cluster, int depth) +{ + char name[10]; + bool leaf = true; + bool has_cores = false; + struct device_node *c; + static int cluster_id __initdata; + int core_id = 0; + int i, ret; + + /* + * First check for child clusters; we currently ignore any + * information about the nesting of clusters and present the + * scheduler with a flat list of them. + */ + i = 0; + do { + snprintf(name, sizeof(name), "cluster%d", i); + c = of_get_child_by_name(cluster, name); + if (c) { + leaf = false; + ret = parse_cluster(c, depth + 1); + of_node_put(c); + if (ret != 0) + return ret; + } + i++; + } while (c); + + /* Now check for cores */ + i = 0; + do { + snprintf(name, sizeof(name), "core%d", i); + c = of_get_child_by_name(cluster, name); + if (c) { + has_cores = true; + + if (depth == 0) { + pr_err("%s: cpu-map children should be clusters\n", + c->full_name); + of_node_put(c); + return -EINVAL; + } + + if (leaf) { + ret = parse_core(c, cluster_id, core_id++); + } else { + pr_err("%s: Non-leaf cluster with core %s\n", + cluster->full_name, name); + ret = -EINVAL; + } + + of_node_put(c); + if (ret != 0) + return ret; + } + i++; + } while (c); + + if (leaf && !has_cores) + pr_warn("%s: empty cluster\n", cluster->full_name); + + if (leaf) + cluster_id++; + + return 0; +} + +static int __init parse_dt_topology(void) +{ + struct device_node *cn, *map; + int ret = 0; + int cpu; + + cn = of_find_node_by_path("/cpus"); + if (!cn) { + pr_err("No CPU information found in DT\n"); + return 0; + } + + /* + * When topology is provided cpu-map is essentially a root + * cluster with restricted subnodes. + */ + map = of_get_child_by_name(cn, "cpu-map"); + if (!map) + goto out; + + ret = parse_cluster(map, 0); + if (ret != 0) + goto out_map; + + /* + * Check that all cores are in the topology; the SMP code will + * only mark cores described in the DT as possible. + */ + for_each_possible_cpu(cpu) { + if (cpu_topology[cpu].cluster_id == -1) { + pr_err("CPU%d: No topology information specified\n", + cpu); + ret = -EINVAL; + } + } + +out_map: + of_node_put(map); +out: + of_node_put(cn); + return ret; +} + /* * cpu topology table */ @@ -39,13 +221,9 @@ static void update_siblings_masks(unsigned int cpuid) if (cpuid_topo->cluster_id == -1) { /* - * DT does not contain topology information for this cpu - * reset it to default behaviour + * DT does not contain topology information for this cpu. */ pr_debug("CPU%u: No topology information configured\n", cpuid); - cpuid_topo->core_id = 0; - cpumask_set_cpu(cpuid, &cpuid_topo->core_sibling); - cpumask_set_cpu(cpuid, &cpuid_topo->thread_sibling); return; } @@ -74,22 +252,32 @@ void store_cpu_topology(unsigned int cpuid) update_siblings_masks(cpuid); } -/* - * init_cpu_topology is called at boot when only one cpu is running - * which prevent simultaneous write access to cpu_topology array - */ -void __init init_cpu_topology(void) +static void __init reset_cpu_topology(void) { unsigned int cpu; - /* init core mask and power*/ for_each_possible_cpu(cpu) { struct cpu_topology *cpu_topo = &cpu_topology[cpu]; cpu_topo->thread_id = -1; - cpu_topo->core_id = -1; + cpu_topo->core_id = 0; cpu_topo->cluster_id = -1; + cpumask_clear(&cpu_topo->core_sibling); + cpumask_set_cpu(cpu, &cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); + cpumask_set_cpu(cpu, &cpu_topo->thread_sibling); } } + +void __init init_cpu_topology(void) +{ + reset_cpu_topology(); + + /* + * Discard anything that was parsed if we hit an error so we + * don't use partial information. + */ + if (parse_dt_topology()) + reset_cpu_topology(); +} diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 7ffadddb645d..c43cfa9b8304 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -251,10 +251,13 @@ void die(const char *str, struct pt_regs *regs, int err) void arm64_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info, int err) { - if (user_mode(regs)) + if (user_mode(regs)) { + current->thread.fault_address = 0; + current->thread.fault_code = err; force_sig_info(info->si_signo, info, current); - else + } else { die(str, regs, err); + } } asmlinkage void __exception do_undefinstr(struct pt_regs *regs) diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 4ba7a55b49c7..f1e6d5c032e1 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -13,7 +13,7 @@ #define ARM_EXIT_DISCARD(x) x OUTPUT_ARCH(aarch64) -ENTRY(stext) +ENTRY(_text) jiffies = jiffies_64; diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 2c56012cb2d2..b0d1512acf08 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -630,9 +630,15 @@ ENTRY(__kvm_tlb_flush_vmid_ipa) * whole of Stage-1. Weep... */ tlbi ipas2e1is, x1 - dsb sy + /* + * We have to ensure completion of the invalidation at Stage-2, + * since a table walk on another CPU could refill a TLB with a + * complete (S1 + S2) walk based on the old Stage-2 mapping if + * the Stage-1 invalidation happened first. + */ + dsb ish tlbi vmalle1is - dsb sy + dsb ish isb msr vttbr_el2, xzr @@ -643,7 +649,7 @@ ENTRY(__kvm_flush_vm_context) dsb ishst tlbi alle1is ic ialluis - dsb sy + dsb ish ret ENDPROC(__kvm_flush_vm_context) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 03244582bc55..c59a1bdab5eb 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -71,13 +71,13 @@ static u32 get_ccsidr(u32 csselr) static void do_dc_cisw(u32 val) { asm volatile("dc cisw, %x0" : : "r" (val)); - dsb(); + dsb(ish); } static void do_dc_csw(u32 val) { asm volatile("dc csw, %x0" : : "r" (val)); - dsb(); + dsb(ish); } /* See note at ARM ARM B1.14.4 */ diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 328ce1a99daa..d98d3e39879e 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -1,4 +1,5 @@ lib-y := bitops.o clear_user.o delay.o copy_from_user.o \ copy_to_user.o copy_in_user.o copy_page.o \ clear_page.o memchr.o memcpy.o memmove.o memset.o \ + memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \ strchr.o strrchr.o diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S new file mode 100644 index 000000000000..6ea0776ba6de --- /dev/null +++ b/arch/arm64/lib/memcmp.S @@ -0,0 +1,258 @@ +/* + * Copyright (C) 2013 ARM Ltd. + * Copyright (C) 2013 Linaro. + * + * This code is based on glibc cortex strings work originally authored by Linaro + * and re-licensed under GPLv2 for the Linux kernel. The original code can + * be found @ + * + * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ + * files/head:/src/aarch64/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + +/* +* compare memory areas(when two memory areas' offset are different, +* alignment handled by the hardware) +* +* Parameters: +* x0 - const memory area 1 pointer +* x1 - const memory area 2 pointer +* x2 - the maximal compare byte length +* Returns: +* x0 - a compare result, maybe less than, equal to, or greater than ZERO +*/ + +/* Parameters and result. */ +src1 .req x0 +src2 .req x1 +limit .req x2 +result .req x0 + +/* Internal variables. */ +data1 .req x3 +data1w .req w3 +data2 .req x4 +data2w .req w4 +has_nul .req x5 +diff .req x6 +endloop .req x7 +tmp1 .req x8 +tmp2 .req x9 +tmp3 .req x10 +pos .req x11 +limit_wd .req x12 +mask .req x13 + +ENTRY(memcmp) + cbz limit, .Lret0 + eor tmp1, src1, src2 + tst tmp1, #7 + b.ne .Lmisaligned8 + ands tmp1, src1, #7 + b.ne .Lmutual_align + sub limit_wd, limit, #1 /* limit != 0, so no underflow. */ + lsr limit_wd, limit_wd, #3 /* Convert to Dwords. */ + /* + * The input source addresses are at alignment boundary. + * Directly compare eight bytes each time. + */ +.Lloop_aligned: + ldr data1, [src1], #8 + ldr data2, [src2], #8 +.Lstart_realigned: + subs limit_wd, limit_wd, #1 + eor diff, data1, data2 /* Non-zero if differences found. */ + csinv endloop, diff, xzr, cs /* Last Dword or differences. */ + cbz endloop, .Lloop_aligned + + /* Not reached the limit, must have found a diff. */ + tbz limit_wd, #63, .Lnot_limit + + /* Limit % 8 == 0 => the diff is in the last 8 bytes. */ + ands limit, limit, #7 + b.eq .Lnot_limit + /* + * The remained bytes less than 8. It is needed to extract valid data + * from last eight bytes of the intended memory range. + */ + lsl limit, limit, #3 /* bytes-> bits. */ + mov mask, #~0 +CPU_BE( lsr mask, mask, limit ) +CPU_LE( lsl mask, mask, limit ) + bic data1, data1, mask + bic data2, data2, mask + + orr diff, diff, mask + b .Lnot_limit + +.Lmutual_align: + /* + * Sources are mutually aligned, but are not currently at an + * alignment boundary. Round down the addresses and then mask off + * the bytes that precede the start point. + */ + bic src1, src1, #7 + bic src2, src2, #7 + ldr data1, [src1], #8 + ldr data2, [src2], #8 + /* + * We can not add limit with alignment offset(tmp1) here. Since the + * addition probably make the limit overflown. + */ + sub limit_wd, limit, #1/*limit != 0, so no underflow.*/ + and tmp3, limit_wd, #7 + lsr limit_wd, limit_wd, #3 + add tmp3, tmp3, tmp1 + add limit_wd, limit_wd, tmp3, lsr #3 + add limit, limit, tmp1/* Adjust the limit for the extra. */ + + lsl tmp1, tmp1, #3/* Bytes beyond alignment -> bits.*/ + neg tmp1, tmp1/* Bits to alignment -64. */ + mov tmp2, #~0 + /*mask off the non-intended bytes before the start address.*/ +CPU_BE( lsl tmp2, tmp2, tmp1 )/*Big-endian.Early bytes are at MSB*/ + /* Little-endian. Early bytes are at LSB. */ +CPU_LE( lsr tmp2, tmp2, tmp1 ) + + orr data1, data1, tmp2 + orr data2, data2, tmp2 + b .Lstart_realigned + + /*src1 and src2 have different alignment offset.*/ +.Lmisaligned8: + cmp limit, #8 + b.lo .Ltiny8proc /*limit < 8: compare byte by byte*/ + + and tmp1, src1, #7 + neg tmp1, tmp1 + add tmp1, tmp1, #8/*valid length in the first 8 bytes of src1*/ + and tmp2, src2, #7 + neg tmp2, tmp2 + add tmp2, tmp2, #8/*valid length in the first 8 bytes of src2*/ + subs tmp3, tmp1, tmp2 + csel pos, tmp1, tmp2, hi /*Choose the maximum.*/ + + sub limit, limit, pos + /*compare the proceeding bytes in the first 8 byte segment.*/ +.Ltinycmp: + ldrb data1w, [src1], #1 + ldrb data2w, [src2], #1 + subs pos, pos, #1 + ccmp data1w, data2w, #0, ne /* NZCV = 0b0000. */ + b.eq .Ltinycmp + cbnz pos, 1f /*diff occurred before the last byte.*/ + cmp data1w, data2w + b.eq .Lstart_align +1: + sub result, data1, data2 + ret + +.Lstart_align: + lsr limit_wd, limit, #3 + cbz limit_wd, .Lremain8 + + ands xzr, src1, #7 + b.eq .Lrecal_offset + /*process more leading bytes to make src1 aligned...*/ + add src1, src1, tmp3 /*backwards src1 to alignment boundary*/ + add src2, src2, tmp3 + sub limit, limit, tmp3 + lsr limit_wd, limit, #3 + cbz limit_wd, .Lremain8 + /*load 8 bytes from aligned SRC1..*/ + ldr data1, [src1], #8 + ldr data2, [src2], #8 + + subs limit_wd, limit_wd, #1 + eor diff, data1, data2 /*Non-zero if differences found.*/ + csinv endloop, diff, xzr, ne + cbnz endloop, .Lunequal_proc + /*How far is the current SRC2 from the alignment boundary...*/ + and tmp3, tmp3, #7 + +.Lrecal_offset:/*src1 is aligned now..*/ + neg pos, tmp3 +.Lloopcmp_proc: + /* + * Divide the eight bytes into two parts. First,backwards the src2 + * to an alignment boundary,load eight bytes and compare from + * the SRC2 alignment boundary. If all 8 bytes are equal,then start + * the second part's comparison. Otherwise finish the comparison. + * This special handle can garantee all the accesses are in the + * thread/task space in avoid to overrange access. + */ + ldr data1, [src1,pos] + ldr data2, [src2,pos] + eor diff, data1, data2 /* Non-zero if differences found. */ + cbnz diff, .Lnot_limit + + /*The second part process*/ + ldr data1, [src1], #8 + ldr data2, [src2], #8 + eor diff, data1, data2 /* Non-zero if differences found. */ + subs limit_wd, limit_wd, #1 + csinv endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/ + cbz endloop, .Lloopcmp_proc +.Lunequal_proc: + cbz diff, .Lremain8 + +/*There is differnence occured in the latest comparison.*/ +.Lnot_limit: +/* +* For little endian,reverse the low significant equal bits into MSB,then +* following CLZ can find how many equal bits exist. +*/ +CPU_LE( rev diff, diff ) +CPU_LE( rev data1, data1 ) +CPU_LE( rev data2, data2 ) + + /* + * The MS-non-zero bit of DIFF marks either the first bit + * that is different, or the end of the significant data. + * Shifting left now will bring the critical information into the + * top bits. + */ + clz pos, diff + lsl data1, data1, pos + lsl data2, data2, pos + /* + * We need to zero-extend (char is unsigned) the value and then + * perform a signed subtraction. + */ + lsr data1, data1, #56 + sub result, data1, data2, lsr #56 + ret + +.Lremain8: + /* Limit % 8 == 0 =>. all data are equal.*/ + ands limit, limit, #7 + b.eq .Lret0 + +.Ltiny8proc: + ldrb data1w, [src1], #1 + ldrb data2w, [src2], #1 + subs limit, limit, #1 + + ccmp data1w, data2w, #0, ne /* NZCV = 0b0000. */ + b.eq .Ltiny8proc + sub result, data1, data2 + ret +.Lret0: + mov result, #0 + ret +ENDPROC(memcmp) diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S index 27b5003609b6..8a9a96d3ddae 100644 --- a/arch/arm64/lib/memcpy.S +++ b/arch/arm64/lib/memcpy.S @@ -1,5 +1,13 @@ /* * Copyright (C) 2013 ARM Ltd. + * Copyright (C) 2013 Linaro. + * + * This code is based on glibc cortex strings work originally authored by Linaro + * and re-licensed under GPLv2 for the Linux kernel. The original code can + * be found @ + * + * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ + * files/head:/src/aarch64/ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -16,6 +24,7 @@ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/cache.h> /* * Copy a buffer from src to dest (alignment handled by the hardware) @@ -27,27 +36,166 @@ * Returns: * x0 - dest */ +dstin .req x0 +src .req x1 +count .req x2 +tmp1 .req x3 +tmp1w .req w3 +tmp2 .req x4 +tmp2w .req w4 +tmp3 .req x5 +tmp3w .req w5 +dst .req x6 + +A_l .req x7 +A_h .req x8 +B_l .req x9 +B_h .req x10 +C_l .req x11 +C_h .req x12 +D_l .req x13 +D_h .req x14 + ENTRY(memcpy) - mov x4, x0 - subs x2, x2, #8 - b.mi 2f -1: ldr x3, [x1], #8 - subs x2, x2, #8 - str x3, [x4], #8 - b.pl 1b -2: adds x2, x2, #4 - b.mi 3f - ldr w3, [x1], #4 - sub x2, x2, #4 - str w3, [x4], #4 -3: adds x2, x2, #2 - b.mi 4f - ldrh w3, [x1], #2 - sub x2, x2, #2 - strh w3, [x4], #2 -4: adds x2, x2, #1 - b.mi 5f - ldrb w3, [x1] - strb w3, [x4] -5: ret + mov dst, dstin + cmp count, #16 + /*When memory length is less than 16, the accessed are not aligned.*/ + b.lo .Ltiny15 + + neg tmp2, src + ands tmp2, tmp2, #15/* Bytes to reach alignment. */ + b.eq .LSrcAligned + sub count, count, tmp2 + /* + * Copy the leading memory data from src to dst in an increasing + * address order.By this way,the risk of overwritting the source + * memory data is eliminated when the distance between src and + * dst is less than 16. The memory accesses here are alignment. + */ + tbz tmp2, #0, 1f + ldrb tmp1w, [src], #1 + strb tmp1w, [dst], #1 +1: + tbz tmp2, #1, 2f + ldrh tmp1w, [src], #2 + strh tmp1w, [dst], #2 +2: + tbz tmp2, #2, 3f + ldr tmp1w, [src], #4 + str tmp1w, [dst], #4 +3: + tbz tmp2, #3, .LSrcAligned + ldr tmp1, [src],#8 + str tmp1, [dst],#8 + +.LSrcAligned: + cmp count, #64 + b.ge .Lcpy_over64 + /* + * Deal with small copies quickly by dropping straight into the + * exit block. + */ +.Ltail63: + /* + * Copy up to 48 bytes of data. At this point we only need the + * bottom 6 bits of count to be accurate. + */ + ands tmp1, count, #0x30 + b.eq .Ltiny15 + cmp tmp1w, #0x20 + b.eq 1f + b.lt 2f + ldp A_l, A_h, [src], #16 + stp A_l, A_h, [dst], #16 +1: + ldp A_l, A_h, [src], #16 + stp A_l, A_h, [dst], #16 +2: + ldp A_l, A_h, [src], #16 + stp A_l, A_h, [dst], #16 +.Ltiny15: + /* + * Prefer to break one ldp/stp into several load/store to access + * memory in an increasing address order,rather than to load/store 16 + * bytes from (src-16) to (dst-16) and to backward the src to aligned + * address,which way is used in original cortex memcpy. If keeping + * the original memcpy process here, memmove need to satisfy the + * precondition that src address is at least 16 bytes bigger than dst + * address,otherwise some source data will be overwritten when memove + * call memcpy directly. To make memmove simpler and decouple the + * memcpy's dependency on memmove, withdrew the original process. + */ + tbz count, #3, 1f + ldr tmp1, [src], #8 + str tmp1, [dst], #8 +1: + tbz count, #2, 2f + ldr tmp1w, [src], #4 + str tmp1w, [dst], #4 +2: + tbz count, #1, 3f + ldrh tmp1w, [src], #2 + strh tmp1w, [dst], #2 +3: + tbz count, #0, .Lexitfunc + ldrb tmp1w, [src] + strb tmp1w, [dst] + +.Lexitfunc: + ret + +.Lcpy_over64: + subs count, count, #128 + b.ge .Lcpy_body_large + /* + * Less than 128 bytes to copy, so handle 64 here and then jump + * to the tail. + */ + ldp A_l, A_h, [src],#16 + stp A_l, A_h, [dst],#16 + ldp B_l, B_h, [src],#16 + ldp C_l, C_h, [src],#16 + stp B_l, B_h, [dst],#16 + stp C_l, C_h, [dst],#16 + ldp D_l, D_h, [src],#16 + stp D_l, D_h, [dst],#16 + + tst count, #0x3f + b.ne .Ltail63 + ret + + /* + * Critical loop. Start at a new cache line boundary. Assuming + * 64 bytes per line this ensures the entire loop is in one line. + */ + .p2align L1_CACHE_SHIFT +.Lcpy_body_large: + /* pre-get 64 bytes data. */ + ldp A_l, A_h, [src],#16 + ldp B_l, B_h, [src],#16 + ldp C_l, C_h, [src],#16 + ldp D_l, D_h, [src],#16 +1: + /* + * interlace the load of next 64 bytes data block with store of the last + * loaded 64 bytes data. + */ + stp A_l, A_h, [dst],#16 + ldp A_l, A_h, [src],#16 + stp B_l, B_h, [dst],#16 + ldp B_l, B_h, [src],#16 + stp C_l, C_h, [dst],#16 + ldp C_l, C_h, [src],#16 + stp D_l, D_h, [dst],#16 + ldp D_l, D_h, [src],#16 + subs count, count, #64 + b.ge 1b + stp A_l, A_h, [dst],#16 + stp B_l, B_h, [dst],#16 + stp C_l, C_h, [dst],#16 + stp D_l, D_h, [dst],#16 + + tst count, #0x3f + b.ne .Ltail63 + ret ENDPROC(memcpy) diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S index b79fdfa42d39..57b19ea2dad4 100644 --- a/arch/arm64/lib/memmove.S +++ b/arch/arm64/lib/memmove.S @@ -1,5 +1,13 @@ /* * Copyright (C) 2013 ARM Ltd. + * Copyright (C) 2013 Linaro. + * + * This code is based on glibc cortex strings work originally authored by Linaro + * and re-licensed under GPLv2 for the Linux kernel. The original code can + * be found @ + * + * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ + * files/head:/src/aarch64/ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -16,6 +24,7 @@ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/cache.h> /* * Move a buffer from src to test (alignment handled by the hardware). @@ -28,30 +37,161 @@ * Returns: * x0 - dest */ +dstin .req x0 +src .req x1 +count .req x2 +tmp1 .req x3 +tmp1w .req w3 +tmp2 .req x4 +tmp2w .req w4 +tmp3 .req x5 +tmp3w .req w5 +dst .req x6 + +A_l .req x7 +A_h .req x8 +B_l .req x9 +B_h .req x10 +C_l .req x11 +C_h .req x12 +D_l .req x13 +D_h .req x14 + ENTRY(memmove) - cmp x0, x1 - b.ls memcpy - add x4, x0, x2 - add x1, x1, x2 - subs x2, x2, #8 - b.mi 2f -1: ldr x3, [x1, #-8]! - subs x2, x2, #8 - str x3, [x4, #-8]! - b.pl 1b -2: adds x2, x2, #4 - b.mi 3f - ldr w3, [x1, #-4]! - sub x2, x2, #4 - str w3, [x4, #-4]! -3: adds x2, x2, #2 - b.mi 4f - ldrh w3, [x1, #-2]! - sub x2, x2, #2 - strh w3, [x4, #-2]! -4: adds x2, x2, #1 - b.mi 5f - ldrb w3, [x1, #-1] - strb w3, [x4, #-1] -5: ret + cmp dstin, src + b.lo memcpy + add tmp1, src, count + cmp dstin, tmp1 + b.hs memcpy /* No overlap. */ + + add dst, dstin, count + add src, src, count + cmp count, #16 + b.lo .Ltail15 /*probably non-alignment accesses.*/ + + ands tmp2, src, #15 /* Bytes to reach alignment. */ + b.eq .LSrcAligned + sub count, count, tmp2 + /* + * process the aligned offset length to make the src aligned firstly. + * those extra instructions' cost is acceptable. It also make the + * coming accesses are based on aligned address. + */ + tbz tmp2, #0, 1f + ldrb tmp1w, [src, #-1]! + strb tmp1w, [dst, #-1]! +1: + tbz tmp2, #1, 2f + ldrh tmp1w, [src, #-2]! + strh tmp1w, [dst, #-2]! +2: + tbz tmp2, #2, 3f + ldr tmp1w, [src, #-4]! + str tmp1w, [dst, #-4]! +3: + tbz tmp2, #3, .LSrcAligned + ldr tmp1, [src, #-8]! + str tmp1, [dst, #-8]! + +.LSrcAligned: + cmp count, #64 + b.ge .Lcpy_over64 + + /* + * Deal with small copies quickly by dropping straight into the + * exit block. + */ +.Ltail63: + /* + * Copy up to 48 bytes of data. At this point we only need the + * bottom 6 bits of count to be accurate. + */ + ands tmp1, count, #0x30 + b.eq .Ltail15 + cmp tmp1w, #0x20 + b.eq 1f + b.lt 2f + ldp A_l, A_h, [src, #-16]! + stp A_l, A_h, [dst, #-16]! +1: + ldp A_l, A_h, [src, #-16]! + stp A_l, A_h, [dst, #-16]! +2: + ldp A_l, A_h, [src, #-16]! + stp A_l, A_h, [dst, #-16]! + +.Ltail15: + tbz count, #3, 1f + ldr tmp1, [src, #-8]! + str tmp1, [dst, #-8]! +1: + tbz count, #2, 2f + ldr tmp1w, [src, #-4]! + str tmp1w, [dst, #-4]! +2: + tbz count, #1, 3f + ldrh tmp1w, [src, #-2]! + strh tmp1w, [dst, #-2]! +3: + tbz count, #0, .Lexitfunc + ldrb tmp1w, [src, #-1] + strb tmp1w, [dst, #-1] + +.Lexitfunc: + ret + +.Lcpy_over64: + subs count, count, #128 + b.ge .Lcpy_body_large + /* + * Less than 128 bytes to copy, so handle 64 bytes here and then jump + * to the tail. + */ + ldp A_l, A_h, [src, #-16] + stp A_l, A_h, [dst, #-16] + ldp B_l, B_h, [src, #-32] + ldp C_l, C_h, [src, #-48] + stp B_l, B_h, [dst, #-32] + stp C_l, C_h, [dst, #-48] + ldp D_l, D_h, [src, #-64]! + stp D_l, D_h, [dst, #-64]! + + tst count, #0x3f + b.ne .Ltail63 + ret + + /* + * Critical loop. Start at a new cache line boundary. Assuming + * 64 bytes per line this ensures the entire loop is in one line. + */ + .p2align L1_CACHE_SHIFT +.Lcpy_body_large: + /* pre-load 64 bytes data. */ + ldp A_l, A_h, [src, #-16] + ldp B_l, B_h, [src, #-32] + ldp C_l, C_h, [src, #-48] + ldp D_l, D_h, [src, #-64]! +1: + /* + * interlace the load of next 64 bytes data block with store of the last + * loaded 64 bytes data. + */ + stp A_l, A_h, [dst, #-16] + ldp A_l, A_h, [src, #-16] + stp B_l, B_h, [dst, #-32] + ldp B_l, B_h, [src, #-32] + stp C_l, C_h, [dst, #-48] + ldp C_l, C_h, [src, #-48] + stp D_l, D_h, [dst, #-64]! + ldp D_l, D_h, [src, #-64]! + subs count, count, #64 + b.ge 1b + stp A_l, A_h, [dst, #-16] + stp B_l, B_h, [dst, #-32] + stp C_l, C_h, [dst, #-48] + stp D_l, D_h, [dst, #-64]! + + tst count, #0x3f + b.ne .Ltail63 + ret ENDPROC(memmove) diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S index 87e4a68fbbbc..7c72dfd36b63 100644 --- a/arch/arm64/lib/memset.S +++ b/arch/arm64/lib/memset.S @@ -1,5 +1,13 @@ /* * Copyright (C) 2013 ARM Ltd. + * Copyright (C) 2013 Linaro. + * + * This code is based on glibc cortex strings work originally authored by Linaro + * and re-licensed under GPLv2 for the Linux kernel. The original code can + * be found @ + * + * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ + * files/head:/src/aarch64/ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -16,6 +24,7 @@ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/cache.h> /* * Fill in the buffer with character c (alignment handled by the hardware) @@ -27,27 +36,181 @@ * Returns: * x0 - buf */ + +dstin .req x0 +val .req w1 +count .req x2 +tmp1 .req x3 +tmp1w .req w3 +tmp2 .req x4 +tmp2w .req w4 +zva_len_x .req x5 +zva_len .req w5 +zva_bits_x .req x6 + +A_l .req x7 +A_lw .req w7 +dst .req x8 +tmp3w .req w9 +tmp3 .req x9 + ENTRY(memset) - mov x4, x0 - and w1, w1, #0xff - orr w1, w1, w1, lsl #8 - orr w1, w1, w1, lsl #16 - orr x1, x1, x1, lsl #32 - subs x2, x2, #8 - b.mi 2f -1: str x1, [x4], #8 - subs x2, x2, #8 - b.pl 1b -2: adds x2, x2, #4 - b.mi 3f - sub x2, x2, #4 - str w1, [x4], #4 -3: adds x2, x2, #2 - b.mi 4f - sub x2, x2, #2 - strh w1, [x4], #2 -4: adds x2, x2, #1 - b.mi 5f - strb w1, [x4] -5: ret + mov dst, dstin /* Preserve return value. */ + and A_lw, val, #255 + orr A_lw, A_lw, A_lw, lsl #8 + orr A_lw, A_lw, A_lw, lsl #16 + orr A_l, A_l, A_l, lsl #32 + + cmp count, #15 + b.hi .Lover16_proc + /*All store maybe are non-aligned..*/ + tbz count, #3, 1f + str A_l, [dst], #8 +1: + tbz count, #2, 2f + str A_lw, [dst], #4 +2: + tbz count, #1, 3f + strh A_lw, [dst], #2 +3: + tbz count, #0, 4f + strb A_lw, [dst] +4: + ret + +.Lover16_proc: + /*Whether the start address is aligned with 16.*/ + neg tmp2, dst + ands tmp2, tmp2, #15 + b.eq .Laligned +/* +* The count is not less than 16, we can use stp to store the start 16 bytes, +* then adjust the dst aligned with 16.This process will make the current +* memory address at alignment boundary. +*/ + stp A_l, A_l, [dst] /*non-aligned store..*/ + /*make the dst aligned..*/ + sub count, count, tmp2 + add dst, dst, tmp2 + +.Laligned: + cbz A_l, .Lzero_mem + +.Ltail_maybe_long: + cmp count, #64 + b.ge .Lnot_short +.Ltail63: + ands tmp1, count, #0x30 + b.eq 3f + cmp tmp1w, #0x20 + b.eq 1f + b.lt 2f + stp A_l, A_l, [dst], #16 +1: + stp A_l, A_l, [dst], #16 +2: + stp A_l, A_l, [dst], #16 +/* +* The last store length is less than 16,use stp to write last 16 bytes. +* It will lead some bytes written twice and the access is non-aligned. +*/ +3: + ands count, count, #15 + cbz count, 4f + add dst, dst, count + stp A_l, A_l, [dst, #-16] /* Repeat some/all of last store. */ +4: + ret + + /* + * Critical loop. Start at a new cache line boundary. Assuming + * 64 bytes per line, this ensures the entire loop is in one line. + */ + .p2align L1_CACHE_SHIFT +.Lnot_short: + sub dst, dst, #16/* Pre-bias. */ + sub count, count, #64 +1: + stp A_l, A_l, [dst, #16] + stp A_l, A_l, [dst, #32] + stp A_l, A_l, [dst, #48] + stp A_l, A_l, [dst, #64]! + subs count, count, #64 + b.ge 1b + tst count, #0x3f + add dst, dst, #16 + b.ne .Ltail63 +.Lexitfunc: + ret + + /* + * For zeroing memory, check to see if we can use the ZVA feature to + * zero entire 'cache' lines. + */ +.Lzero_mem: + cmp count, #63 + b.le .Ltail63 + /* + * For zeroing small amounts of memory, it's not worth setting up + * the line-clear code. + */ + cmp count, #128 + b.lt .Lnot_short /*count is at least 128 bytes*/ + + mrs tmp1, dczid_el0 + tbnz tmp1, #4, .Lnot_short + mov tmp3w, #4 + and zva_len, tmp1w, #15 /* Safety: other bits reserved. */ + lsl zva_len, tmp3w, zva_len + + ands tmp3w, zva_len, #63 + /* + * ensure the zva_len is not less than 64. + * It is not meaningful to use ZVA if the block size is less than 64. + */ + b.ne .Lnot_short +.Lzero_by_line: + /* + * Compute how far we need to go to become suitably aligned. We're + * already at quad-word alignment. + */ + cmp count, zva_len_x + b.lt .Lnot_short /* Not enough to reach alignment. */ + sub zva_bits_x, zva_len_x, #1 + neg tmp2, dst + ands tmp2, tmp2, zva_bits_x + b.eq 2f /* Already aligned. */ + /* Not aligned, check that there's enough to copy after alignment.*/ + sub tmp1, count, tmp2 + /* + * grantee the remain length to be ZVA is bigger than 64, + * avoid to make the 2f's process over mem range.*/ + cmp tmp1, #64 + ccmp tmp1, zva_len_x, #8, ge /* NZCV=0b1000 */ + b.lt .Lnot_short + /* + * We know that there's at least 64 bytes to zero and that it's safe + * to overrun by 64 bytes. + */ + mov count, tmp1 +1: + stp A_l, A_l, [dst] + stp A_l, A_l, [dst, #16] + stp A_l, A_l, [dst, #32] + subs tmp2, tmp2, #64 + stp A_l, A_l, [dst, #48] + add dst, dst, #64 + b.ge 1b + /* We've overrun a bit, so adjust dst downwards.*/ + add dst, dst, tmp2 +2: + sub count, count, zva_len_x +3: + dc zva, dst + add dst, dst, zva_len_x + subs count, count, zva_len_x + b.ge 3b + ands count, count, zva_bits_x + b.ne .Ltail_maybe_long + ret ENDPROC(memset) diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S new file mode 100644 index 000000000000..42f828b06c59 --- /dev/null +++ b/arch/arm64/lib/strcmp.S @@ -0,0 +1,234 @@ +/* + * Copyright (C) 2013 ARM Ltd. + * Copyright (C) 2013 Linaro. + * + * This code is based on glibc cortex strings work originally authored by Linaro + * and re-licensed under GPLv2 for the Linux kernel. The original code can + * be found @ + * + * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ + * files/head:/src/aarch64/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + +/* + * compare two strings + * + * Parameters: + * x0 - const string 1 pointer + * x1 - const string 2 pointer + * Returns: + * x0 - an integer less than, equal to, or greater than zero + * if s1 is found, respectively, to be less than, to match, + * or be greater than s2. + */ + +#define REP8_01 0x0101010101010101 +#define REP8_7f 0x7f7f7f7f7f7f7f7f +#define REP8_80 0x8080808080808080 + +/* Parameters and result. */ +src1 .req x0 +src2 .req x1 +result .req x0 + +/* Internal variables. */ +data1 .req x2 +data1w .req w2 +data2 .req x3 +data2w .req w3 +has_nul .req x4 +diff .req x5 +syndrome .req x6 +tmp1 .req x7 +tmp2 .req x8 +tmp3 .req x9 +zeroones .req x10 +pos .req x11 + +ENTRY(strcmp) + eor tmp1, src1, src2 + mov zeroones, #REP8_01 + tst tmp1, #7 + b.ne .Lmisaligned8 + ands tmp1, src1, #7 + b.ne .Lmutual_align + + /* + * NUL detection works on the principle that (X - 1) & (~X) & 0x80 + * (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and + * can be done in parallel across the entire word. + */ +.Lloop_aligned: + ldr data1, [src1], #8 + ldr data2, [src2], #8 +.Lstart_realigned: + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + eor diff, data1, data2 /* Non-zero if differences found. */ + bic has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */ + orr syndrome, diff, has_nul + cbz syndrome, .Lloop_aligned + b .Lcal_cmpresult + +.Lmutual_align: + /* + * Sources are mutually aligned, but are not currently at an + * alignment boundary. Round down the addresses and then mask off + * the bytes that preceed the start point. + */ + bic src1, src1, #7 + bic src2, src2, #7 + lsl tmp1, tmp1, #3 /* Bytes beyond alignment -> bits. */ + ldr data1, [src1], #8 + neg tmp1, tmp1 /* Bits to alignment -64. */ + ldr data2, [src2], #8 + mov tmp2, #~0 + /* Big-endian. Early bytes are at MSB. */ +CPU_BE( lsl tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */ + /* Little-endian. Early bytes are at LSB. */ +CPU_LE( lsr tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */ + + orr data1, data1, tmp2 + orr data2, data2, tmp2 + b .Lstart_realigned + +.Lmisaligned8: + /* + * Get the align offset length to compare per byte first. + * After this process, one string's address will be aligned. + */ + and tmp1, src1, #7 + neg tmp1, tmp1 + add tmp1, tmp1, #8 + and tmp2, src2, #7 + neg tmp2, tmp2 + add tmp2, tmp2, #8 + subs tmp3, tmp1, tmp2 + csel pos, tmp1, tmp2, hi /*Choose the maximum. */ +.Ltinycmp: + ldrb data1w, [src1], #1 + ldrb data2w, [src2], #1 + subs pos, pos, #1 + ccmp data1w, #1, #0, ne /* NZCV = 0b0000. */ + ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */ + b.eq .Ltinycmp + cbnz pos, 1f /*find the null or unequal...*/ + cmp data1w, #1 + ccmp data1w, data2w, #0, cs + b.eq .Lstart_align /*the last bytes are equal....*/ +1: + sub result, data1, data2 + ret + +.Lstart_align: + ands xzr, src1, #7 + b.eq .Lrecal_offset + /*process more leading bytes to make str1 aligned...*/ + add src1, src1, tmp3 + add src2, src2, tmp3 + /*load 8 bytes from aligned str1 and non-aligned str2..*/ + ldr data1, [src1], #8 + ldr data2, [src2], #8 + + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + bic has_nul, tmp1, tmp2 + eor diff, data1, data2 /* Non-zero if differences found. */ + orr syndrome, diff, has_nul + cbnz syndrome, .Lcal_cmpresult + /*How far is the current str2 from the alignment boundary...*/ + and tmp3, tmp3, #7 +.Lrecal_offset: + neg pos, tmp3 +.Lloopcmp_proc: + /* + * Divide the eight bytes into two parts. First,backwards the src2 + * to an alignment boundary,load eight bytes from the SRC2 alignment + * boundary,then compare with the relative bytes from SRC1. + * If all 8 bytes are equal,then start the second part's comparison. + * Otherwise finish the comparison. + * This special handle can garantee all the accesses are in the + * thread/task space in avoid to overrange access. + */ + ldr data1, [src1,pos] + ldr data2, [src2,pos] + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + bic has_nul, tmp1, tmp2 + eor diff, data1, data2 /* Non-zero if differences found. */ + orr syndrome, diff, has_nul + cbnz syndrome, .Lcal_cmpresult + + /*The second part process*/ + ldr data1, [src1], #8 + ldr data2, [src2], #8 + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + bic has_nul, tmp1, tmp2 + eor diff, data1, data2 /* Non-zero if differences found. */ + orr syndrome, diff, has_nul + cbz syndrome, .Lloopcmp_proc + +.Lcal_cmpresult: + /* + * reversed the byte-order as big-endian,then CLZ can find the most + * significant zero bits. + */ +CPU_LE( rev syndrome, syndrome ) +CPU_LE( rev data1, data1 ) +CPU_LE( rev data2, data2 ) + + /* + * For big-endian we cannot use the trick with the syndrome value + * as carry-propagation can corrupt the upper bits if the trailing + * bytes in the string contain 0x01. + * However, if there is no NUL byte in the dword, we can generate + * the result directly. We ca not just subtract the bytes as the + * MSB might be significant. + */ +CPU_BE( cbnz has_nul, 1f ) +CPU_BE( cmp data1, data2 ) +CPU_BE( cset result, ne ) +CPU_BE( cneg result, result, lo ) +CPU_BE( ret ) +CPU_BE( 1: ) + /*Re-compute the NUL-byte detection, using a byte-reversed value. */ +CPU_BE( rev tmp3, data1 ) +CPU_BE( sub tmp1, tmp3, zeroones ) +CPU_BE( orr tmp2, tmp3, #REP8_7f ) +CPU_BE( bic has_nul, tmp1, tmp2 ) +CPU_BE( rev has_nul, has_nul ) +CPU_BE( orr syndrome, diff, has_nul ) + + clz pos, syndrome + /* + * The MS-non-zero bit of the syndrome marks either the first bit + * that is different, or the top bit of the first zero byte. + * Shifting left now will bring the critical information into the + * top bits. + */ + lsl data1, data1, pos + lsl data2, data2, pos + /* + * But we need to zero-extend (char is unsigned) the value and then + * perform a signed 32-bit subtraction. + */ + lsr data1, data1, #56 + sub result, data1, data2, lsr #56 + ret +ENDPROC(strcmp) diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S new file mode 100644 index 000000000000..987b68b9ce44 --- /dev/null +++ b/arch/arm64/lib/strlen.S @@ -0,0 +1,126 @@ +/* + * Copyright (C) 2013 ARM Ltd. + * Copyright (C) 2013 Linaro. + * + * This code is based on glibc cortex strings work originally authored by Linaro + * and re-licensed under GPLv2 for the Linux kernel. The original code can + * be found @ + * + * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ + * files/head:/src/aarch64/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + +/* + * calculate the length of a string + * + * Parameters: + * x0 - const string pointer + * Returns: + * x0 - the return length of specific string + */ + +/* Arguments and results. */ +srcin .req x0 +len .req x0 + +/* Locals and temporaries. */ +src .req x1 +data1 .req x2 +data2 .req x3 +data2a .req x4 +has_nul1 .req x5 +has_nul2 .req x6 +tmp1 .req x7 +tmp2 .req x8 +tmp3 .req x9 +tmp4 .req x10 +zeroones .req x11 +pos .req x12 + +#define REP8_01 0x0101010101010101 +#define REP8_7f 0x7f7f7f7f7f7f7f7f +#define REP8_80 0x8080808080808080 + +ENTRY(strlen) + mov zeroones, #REP8_01 + bic src, srcin, #15 + ands tmp1, srcin, #15 + b.ne .Lmisaligned + /* + * NUL detection works on the principle that (X - 1) & (~X) & 0x80 + * (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and + * can be done in parallel across the entire word. + */ + /* + * The inner loop deals with two Dwords at a time. This has a + * slightly higher start-up cost, but we should win quite quickly, + * especially on cores with a high number of issue slots per + * cycle, as we get much better parallelism out of the operations. + */ +.Lloop: + ldp data1, data2, [src], #16 +.Lrealigned: + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + sub tmp3, data2, zeroones + orr tmp4, data2, #REP8_7f + bic has_nul1, tmp1, tmp2 + bics has_nul2, tmp3, tmp4 + ccmp has_nul1, #0, #0, eq /* NZCV = 0000 */ + b.eq .Lloop + + sub len, src, srcin + cbz has_nul1, .Lnul_in_data2 +CPU_BE( mov data2, data1 ) /*prepare data to re-calculate the syndrome*/ + sub len, len, #8 + mov has_nul2, has_nul1 +.Lnul_in_data2: + /* + * For big-endian, carry propagation (if the final byte in the + * string is 0x01) means we cannot use has_nul directly. The + * easiest way to get the correct byte is to byte-swap the data + * and calculate the syndrome a second time. + */ +CPU_BE( rev data2, data2 ) +CPU_BE( sub tmp1, data2, zeroones ) +CPU_BE( orr tmp2, data2, #REP8_7f ) +CPU_BE( bic has_nul2, tmp1, tmp2 ) + + sub len, len, #8 + rev has_nul2, has_nul2 + clz pos, has_nul2 + add len, len, pos, lsr #3 /* Bits to bytes. */ + ret + +.Lmisaligned: + cmp tmp1, #8 + neg tmp1, tmp1 + ldp data1, data2, [src], #16 + lsl tmp1, tmp1, #3 /* Bytes beyond alignment -> bits. */ + mov tmp2, #~0 + /* Big-endian. Early bytes are at MSB. */ +CPU_BE( lsl tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */ + /* Little-endian. Early bytes are at LSB. */ +CPU_LE( lsr tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */ + + orr data1, data1, tmp2 + orr data2a, data2, tmp2 + csinv data1, data1, xzr, le + csel data2, data2, data2a, le + b .Lrealigned +ENDPROC(strlen) diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S new file mode 100644 index 000000000000..0224cf5a5533 --- /dev/null +++ b/arch/arm64/lib/strncmp.S @@ -0,0 +1,310 @@ +/* + * Copyright (C) 2013 ARM Ltd. + * Copyright (C) 2013 Linaro. + * + * This code is based on glibc cortex strings work originally authored by Linaro + * and re-licensed under GPLv2 for the Linux kernel. The original code can + * be found @ + * + * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ + * files/head:/src/aarch64/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + +/* + * compare two strings + * + * Parameters: + * x0 - const string 1 pointer + * x1 - const string 2 pointer + * x2 - the maximal length to be compared + * Returns: + * x0 - an integer less than, equal to, or greater than zero if s1 is found, + * respectively, to be less than, to match, or be greater than s2. + */ + +#define REP8_01 0x0101010101010101 +#define REP8_7f 0x7f7f7f7f7f7f7f7f +#define REP8_80 0x8080808080808080 + +/* Parameters and result. */ +src1 .req x0 +src2 .req x1 +limit .req x2 +result .req x0 + +/* Internal variables. */ +data1 .req x3 +data1w .req w3 +data2 .req x4 +data2w .req w4 +has_nul .req x5 +diff .req x6 +syndrome .req x7 +tmp1 .req x8 +tmp2 .req x9 +tmp3 .req x10 +zeroones .req x11 +pos .req x12 +limit_wd .req x13 +mask .req x14 +endloop .req x15 + +ENTRY(strncmp) + cbz limit, .Lret0 + eor tmp1, src1, src2 + mov zeroones, #REP8_01 + tst tmp1, #7 + b.ne .Lmisaligned8 + ands tmp1, src1, #7 + b.ne .Lmutual_align + /* Calculate the number of full and partial words -1. */ + /* + * when limit is mulitply of 8, if not sub 1, + * the judgement of last dword will wrong. + */ + sub limit_wd, limit, #1 /* limit != 0, so no underflow. */ + lsr limit_wd, limit_wd, #3 /* Convert to Dwords. */ + + /* + * NUL detection works on the principle that (X - 1) & (~X) & 0x80 + * (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and + * can be done in parallel across the entire word. + */ +.Lloop_aligned: + ldr data1, [src1], #8 + ldr data2, [src2], #8 +.Lstart_realigned: + subs limit_wd, limit_wd, #1 + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + eor diff, data1, data2 /* Non-zero if differences found. */ + csinv endloop, diff, xzr, pl /* Last Dword or differences.*/ + bics has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */ + ccmp endloop, #0, #0, eq + b.eq .Lloop_aligned + + /*Not reached the limit, must have found the end or a diff. */ + tbz limit_wd, #63, .Lnot_limit + + /* Limit % 8 == 0 => all bytes significant. */ + ands limit, limit, #7 + b.eq .Lnot_limit + + lsl limit, limit, #3 /* Bits -> bytes. */ + mov mask, #~0 +CPU_BE( lsr mask, mask, limit ) +CPU_LE( lsl mask, mask, limit ) + bic data1, data1, mask + bic data2, data2, mask + + /* Make sure that the NUL byte is marked in the syndrome. */ + orr has_nul, has_nul, mask + +.Lnot_limit: + orr syndrome, diff, has_nul + b .Lcal_cmpresult + +.Lmutual_align: + /* + * Sources are mutually aligned, but are not currently at an + * alignment boundary. Round down the addresses and then mask off + * the bytes that precede the start point. + * We also need to adjust the limit calculations, but without + * overflowing if the limit is near ULONG_MAX. + */ + bic src1, src1, #7 + bic src2, src2, #7 + ldr data1, [src1], #8 + neg tmp3, tmp1, lsl #3 /* 64 - bits(bytes beyond align). */ + ldr data2, [src2], #8 + mov tmp2, #~0 + sub limit_wd, limit, #1 /* limit != 0, so no underflow. */ + /* Big-endian. Early bytes are at MSB. */ +CPU_BE( lsl tmp2, tmp2, tmp3 ) /* Shift (tmp1 & 63). */ + /* Little-endian. Early bytes are at LSB. */ +CPU_LE( lsr tmp2, tmp2, tmp3 ) /* Shift (tmp1 & 63). */ + + and tmp3, limit_wd, #7 + lsr limit_wd, limit_wd, #3 + /* Adjust the limit. Only low 3 bits used, so overflow irrelevant.*/ + add limit, limit, tmp1 + add tmp3, tmp3, tmp1 + orr data1, data1, tmp2 + orr data2, data2, tmp2 + add limit_wd, limit_wd, tmp3, lsr #3 + b .Lstart_realigned + +/*when src1 offset is not equal to src2 offset...*/ +.Lmisaligned8: + cmp limit, #8 + b.lo .Ltiny8proc /*limit < 8... */ + /* + * Get the align offset length to compare per byte first. + * After this process, one string's address will be aligned.*/ + and tmp1, src1, #7 + neg tmp1, tmp1 + add tmp1, tmp1, #8 + and tmp2, src2, #7 + neg tmp2, tmp2 + add tmp2, tmp2, #8 + subs tmp3, tmp1, tmp2 + csel pos, tmp1, tmp2, hi /*Choose the maximum. */ + /* + * Here, limit is not less than 8, so directly run .Ltinycmp + * without checking the limit.*/ + sub limit, limit, pos +.Ltinycmp: + ldrb data1w, [src1], #1 + ldrb data2w, [src2], #1 + subs pos, pos, #1 + ccmp data1w, #1, #0, ne /* NZCV = 0b0000. */ + ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */ + b.eq .Ltinycmp + cbnz pos, 1f /*find the null or unequal...*/ + cmp data1w, #1 + ccmp data1w, data2w, #0, cs + b.eq .Lstart_align /*the last bytes are equal....*/ +1: + sub result, data1, data2 + ret + +.Lstart_align: + lsr limit_wd, limit, #3 + cbz limit_wd, .Lremain8 + /*process more leading bytes to make str1 aligned...*/ + ands xzr, src1, #7 + b.eq .Lrecal_offset + add src1, src1, tmp3 /*tmp3 is positive in this branch.*/ + add src2, src2, tmp3 + ldr data1, [src1], #8 + ldr data2, [src2], #8 + + sub limit, limit, tmp3 + lsr limit_wd, limit, #3 + subs limit_wd, limit_wd, #1 + + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + eor diff, data1, data2 /* Non-zero if differences found. */ + csinv endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/ + bics has_nul, tmp1, tmp2 + ccmp endloop, #0, #0, eq /*has_null is ZERO: no null byte*/ + b.ne .Lunequal_proc + /*How far is the current str2 from the alignment boundary...*/ + and tmp3, tmp3, #7 +.Lrecal_offset: + neg pos, tmp3 +.Lloopcmp_proc: + /* + * Divide the eight bytes into two parts. First,backwards the src2 + * to an alignment boundary,load eight bytes from the SRC2 alignment + * boundary,then compare with the relative bytes from SRC1. + * If all 8 bytes are equal,then start the second part's comparison. + * Otherwise finish the comparison. + * This special handle can garantee all the accesses are in the + * thread/task space in avoid to overrange access. + */ + ldr data1, [src1,pos] + ldr data2, [src2,pos] + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + bics has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */ + eor diff, data1, data2 /* Non-zero if differences found. */ + csinv endloop, diff, xzr, eq + cbnz endloop, .Lunequal_proc + + /*The second part process*/ + ldr data1, [src1], #8 + ldr data2, [src2], #8 + subs limit_wd, limit_wd, #1 + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + eor diff, data1, data2 /* Non-zero if differences found. */ + csinv endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/ + bics has_nul, tmp1, tmp2 + ccmp endloop, #0, #0, eq /*has_null is ZERO: no null byte*/ + b.eq .Lloopcmp_proc + +.Lunequal_proc: + orr syndrome, diff, has_nul + cbz syndrome, .Lremain8 +.Lcal_cmpresult: + /* + * reversed the byte-order as big-endian,then CLZ can find the most + * significant zero bits. + */ +CPU_LE( rev syndrome, syndrome ) +CPU_LE( rev data1, data1 ) +CPU_LE( rev data2, data2 ) + /* + * For big-endian we cannot use the trick with the syndrome value + * as carry-propagation can corrupt the upper bits if the trailing + * bytes in the string contain 0x01. + * However, if there is no NUL byte in the dword, we can generate + * the result directly. We can't just subtract the bytes as the + * MSB might be significant. + */ +CPU_BE( cbnz has_nul, 1f ) +CPU_BE( cmp data1, data2 ) +CPU_BE( cset result, ne ) +CPU_BE( cneg result, result, lo ) +CPU_BE( ret ) +CPU_BE( 1: ) + /* Re-compute the NUL-byte detection, using a byte-reversed value.*/ +CPU_BE( rev tmp3, data1 ) +CPU_BE( sub tmp1, tmp3, zeroones ) +CPU_BE( orr tmp2, tmp3, #REP8_7f ) +CPU_BE( bic has_nul, tmp1, tmp2 ) +CPU_BE( rev has_nul, has_nul ) +CPU_BE( orr syndrome, diff, has_nul ) + /* + * The MS-non-zero bit of the syndrome marks either the first bit + * that is different, or the top bit of the first zero byte. + * Shifting left now will bring the critical information into the + * top bits. + */ + clz pos, syndrome + lsl data1, data1, pos + lsl data2, data2, pos + /* + * But we need to zero-extend (char is unsigned) the value and then + * perform a signed 32-bit subtraction. + */ + lsr data1, data1, #56 + sub result, data1, data2, lsr #56 + ret + +.Lremain8: + /* Limit % 8 == 0 => all bytes significant. */ + ands limit, limit, #7 + b.eq .Lret0 +.Ltiny8proc: + ldrb data1w, [src1], #1 + ldrb data2w, [src2], #1 + subs limit, limit, #1 + + ccmp data1w, #1, #0, ne /* NZCV = 0b0000. */ + ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */ + b.eq .Ltiny8proc + sub result, data1, data2 + ret + +.Lret0: + mov result, #0 + ret +ENDPROC(strncmp) diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S new file mode 100644 index 000000000000..2ca665711bf2 --- /dev/null +++ b/arch/arm64/lib/strnlen.S @@ -0,0 +1,171 @@ +/* + * Copyright (C) 2013 ARM Ltd. + * Copyright (C) 2013 Linaro. + * + * This code is based on glibc cortex strings work originally authored by Linaro + * and re-licensed under GPLv2 for the Linux kernel. The original code can + * be found @ + * + * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ + * files/head:/src/aarch64/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + +/* + * determine the length of a fixed-size string + * + * Parameters: + * x0 - const string pointer + * x1 - maximal string length + * Returns: + * x0 - the return length of specific string + */ + +/* Arguments and results. */ +srcin .req x0 +len .req x0 +limit .req x1 + +/* Locals and temporaries. */ +src .req x2 +data1 .req x3 +data2 .req x4 +data2a .req x5 +has_nul1 .req x6 +has_nul2 .req x7 +tmp1 .req x8 +tmp2 .req x9 +tmp3 .req x10 +tmp4 .req x11 +zeroones .req x12 +pos .req x13 +limit_wd .req x14 + +#define REP8_01 0x0101010101010101 +#define REP8_7f 0x7f7f7f7f7f7f7f7f +#define REP8_80 0x8080808080808080 + +ENTRY(strnlen) + cbz limit, .Lhit_limit + mov zeroones, #REP8_01 + bic src, srcin, #15 + ands tmp1, srcin, #15 + b.ne .Lmisaligned + /* Calculate the number of full and partial words -1. */ + sub limit_wd, limit, #1 /* Limit != 0, so no underflow. */ + lsr limit_wd, limit_wd, #4 /* Convert to Qwords. */ + + /* + * NUL detection works on the principle that (X - 1) & (~X) & 0x80 + * (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and + * can be done in parallel across the entire word. + */ + /* + * The inner loop deals with two Dwords at a time. This has a + * slightly higher start-up cost, but we should win quite quickly, + * especially on cores with a high number of issue slots per + * cycle, as we get much better parallelism out of the operations. + */ +.Lloop: + ldp data1, data2, [src], #16 +.Lrealigned: + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + sub tmp3, data2, zeroones + orr tmp4, data2, #REP8_7f + bic has_nul1, tmp1, tmp2 + bic has_nul2, tmp3, tmp4 + subs limit_wd, limit_wd, #1 + orr tmp1, has_nul1, has_nul2 + ccmp tmp1, #0, #0, pl /* NZCV = 0000 */ + b.eq .Lloop + + cbz tmp1, .Lhit_limit /* No null in final Qword. */ + + /* + * We know there's a null in the final Qword. The easiest thing + * to do now is work out the length of the string and return + * MIN (len, limit). + */ + sub len, src, srcin + cbz has_nul1, .Lnul_in_data2 +CPU_BE( mov data2, data1 ) /*perpare data to re-calculate the syndrome*/ + + sub len, len, #8 + mov has_nul2, has_nul1 +.Lnul_in_data2: + /* + * For big-endian, carry propagation (if the final byte in the + * string is 0x01) means we cannot use has_nul directly. The + * easiest way to get the correct byte is to byte-swap the data + * and calculate the syndrome a second time. + */ +CPU_BE( rev data2, data2 ) +CPU_BE( sub tmp1, data2, zeroones ) +CPU_BE( orr tmp2, data2, #REP8_7f ) +CPU_BE( bic has_nul2, tmp1, tmp2 ) + + sub len, len, #8 + rev has_nul2, has_nul2 + clz pos, has_nul2 + add len, len, pos, lsr #3 /* Bits to bytes. */ + cmp len, limit + csel len, len, limit, ls /* Return the lower value. */ + ret + +.Lmisaligned: + /* + * Deal with a partial first word. + * We're doing two things in parallel here; + * 1) Calculate the number of words (but avoiding overflow if + * limit is near ULONG_MAX) - to do this we need to work out + * limit + tmp1 - 1 as a 65-bit value before shifting it; + * 2) Load and mask the initial data words - we force the bytes + * before the ones we are interested in to 0xff - this ensures + * early bytes will not hit any zero detection. + */ + ldp data1, data2, [src], #16 + + sub limit_wd, limit, #1 + and tmp3, limit_wd, #15 + lsr limit_wd, limit_wd, #4 + + add tmp3, tmp3, tmp1 + add limit_wd, limit_wd, tmp3, lsr #4 + + neg tmp4, tmp1 + lsl tmp4, tmp4, #3 /* Bytes beyond alignment -> bits. */ + + mov tmp2, #~0 + /* Big-endian. Early bytes are at MSB. */ +CPU_BE( lsl tmp2, tmp2, tmp4 ) /* Shift (tmp1 & 63). */ + /* Little-endian. Early bytes are at LSB. */ +CPU_LE( lsr tmp2, tmp2, tmp4 ) /* Shift (tmp1 & 63). */ + + cmp tmp1, #8 + + orr data1, data1, tmp2 + orr data2a, data2, tmp2 + + csinv data1, data1, xzr, le + csel data2, data2, data2a, le + b .Lrealigned + +.Lhit_limit: + mov len, limit + ret +ENDPROC(strnlen) diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index b51d36401d83..3ecb56c624d3 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -1,5 +1,5 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ cache.o copypage.o flush.o \ ioremap.o mmap.o pgd.o mmu.o \ - context.o tlb.o proc.o + context.o proc.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index fda756875fa6..23663837acff 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -31,7 +31,7 @@ * Corrupted registers: x0-x7, x9-x11 */ __flush_dcache_all: - dsb sy // ensure ordering with previous memory accesses + dmb sy // ensure ordering with previous memory accesses mrs x0, clidr_el1 // read clidr and x3, x0, #0x7000000 // extract loc from clidr lsr x3, x3, #23 // left align loc bit field @@ -128,7 +128,7 @@ USER(9f, dc cvau, x4 ) // clean D line to PoU add x4, x4, x2 cmp x4, x1 b.lo 1b - dsb sy + dsb ish icache_line_size x2, x3 sub x3, x2, #1 @@ -139,7 +139,7 @@ USER(9f, ic ivau, x4 ) // invalidate I line PoU cmp x4, x1 b.lo 1b 9: // ignore any faulting cache operation - dsb sy + dsb ish isb ret ENDPROC(flush_icache_range) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index c851eb44dc50..4164c5ace9f8 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -115,7 +115,7 @@ static void *__dma_alloc_noncoherent(struct device *dev, size_t size, for (i = 0; i < (size >> PAGE_SHIFT); i++) map[i] = page + i; coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP, - __get_dma_pgprot(attrs, pgprot_default, false)); + __get_dma_pgprot(attrs, __pgprot(PROT_NORMAL_NC), false)); kfree(map); if (!coherent_ptr) goto no_map; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index c23751b06120..bcc965e2cce1 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -32,6 +32,7 @@ #include <asm/exception.h> #include <asm/debug-monitors.h> +#include <asm/esr.h> #include <asm/system_misc.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -123,6 +124,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr, } tsk->thread.fault_address = addr; + tsk->thread.fault_code = esr; si.si_signo = sig; si.si_errno = 0; si.si_code = code; @@ -148,8 +150,6 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re #define VM_FAULT_BADMAP 0x010000 #define VM_FAULT_BADACCESS 0x020000 -#define ESR_WRITE (1 << 6) -#define ESR_CM (1 << 8) #define ESR_LNX_EXEC (1 << 24) static int __do_page_fault(struct mm_struct *mm, unsigned long addr, @@ -218,7 +218,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, if (esr & ESR_LNX_EXEC) { vm_flags = VM_EXEC; - } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) { + } else if ((esr & ESR_EL1_WRITE) && !(esr & ESR_EL1_CM)) { vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } @@ -525,7 +525,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr, info.si_errno = 0; info.si_code = inf->code; info.si_addr = (void __user *)addr; - arm64_notify_die("", regs, &info, esr); + arm64_notify_die("", regs, &info, 0); return 0; } diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 31eb959e9aa8..023747bf4dd7 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -58,11 +58,6 @@ int pud_huge(pud_t pud) #endif } -int pmd_huge_support(void) -{ - return 1; -} - static __init int setup_hugepagesz(char *opt) { unsigned long ps = memparse(opt, &opt); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 51d5352e6ad5..091d428d64ac 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -126,8 +126,6 @@ static void arm64_memory_present(void) void __init arm64_memblock_init(void) { - u64 *reserve_map, base, size; - /* Register the kernel text, kernel data and initrd with memblock */ memblock_reserve(__pa(_text), _end - _text); #ifdef CONFIG_BLK_DEV_INITRD @@ -142,25 +140,6 @@ void __init arm64_memblock_init(void) memblock_reserve(__pa(swapper_pg_dir), SWAPPER_DIR_SIZE); memblock_reserve(__pa(idmap_pg_dir), IDMAP_DIR_SIZE); - /* Reserve the dtb region */ - memblock_reserve(virt_to_phys(initial_boot_params), - be32_to_cpu(initial_boot_params->totalsize)); - - /* - * Process the reserve map. This will probably overlap the initrd - * and dtb locations which are already reserved, but overlapping - * doesn't hurt anything - */ - reserve_map = ((void*)initial_boot_params) + - be32_to_cpu(initial_boot_params->off_mem_rsvmap); - while (1) { - base = be64_to_cpup(reserve_map++); - size = be64_to_cpup(reserve_map++); - if (!size) - break; - memblock_reserve(base, size); - } - early_init_fdt_scan_reserved_mem(); dma_contiguous_reserve(0); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 0a472c41a67f..c43f1dd19489 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -43,11 +43,6 @@ struct page *empty_zero_page; EXPORT_SYMBOL(empty_zero_page); -pgprot_t pgprot_default; -EXPORT_SYMBOL(pgprot_default); - -static pmdval_t prot_sect_kernel; - struct cachepolicy { const char policy[16]; u64 mair; @@ -122,33 +117,6 @@ static int __init early_cachepolicy(char *p) } early_param("cachepolicy", early_cachepolicy); -/* - * Adjust the PMD section entries according to the CPU in use. - */ -void __init init_mem_pgprot(void) -{ - pteval_t default_pgprot; - int i; - - default_pgprot = PTE_ATTRINDX(MT_NORMAL); - prot_sect_kernel = PMD_TYPE_SECT | PMD_SECT_AF | PMD_ATTRINDX(MT_NORMAL); - -#ifdef CONFIG_SMP - /* - * Mark memory with the "shared" attribute for SMP systems - */ - default_pgprot |= PTE_SHARED; - prot_sect_kernel |= PMD_SECT_S; -#endif - - for (i = 0; i < 16; i++) { - unsigned long v = pgprot_val(protection_map[i]); - protection_map[i] = __pgprot(v | default_pgprot); - } - - pgprot_default = __pgprot(PTE_TYPE_PAGE | PTE_AF | default_pgprot); -} - pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { @@ -168,7 +136,8 @@ static void __init *early_alloc(unsigned long sz) } static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr, - unsigned long end, unsigned long pfn) + unsigned long end, unsigned long pfn, + pgprot_t prot) { pte_t *pte; @@ -180,16 +149,27 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr, pte = pte_offset_kernel(pmd, addr); do { - set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC)); + set_pte(pte, pfn_pte(pfn, prot)); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); } static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, - unsigned long end, phys_addr_t phys) + unsigned long end, phys_addr_t phys, + int map_io) { pmd_t *pmd; unsigned long next; + pmdval_t prot_sect; + pgprot_t prot_pte; + + if (map_io) { + prot_sect = PROT_SECT_DEVICE_nGnRE; + prot_pte = __pgprot(PROT_DEVICE_nGnRE); + } else { + prot_sect = PROT_SECT_NORMAL_EXEC; + prot_pte = PAGE_KERNEL_EXEC; + } /* * Check for initial section mappings in the pgd/pud and remove them. @@ -205,7 +185,7 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, /* try section mapping first */ if (((addr | next | phys) & ~SECTION_MASK) == 0) { pmd_t old_pmd =*pmd; - set_pmd(pmd, __pmd(phys | prot_sect_kernel)); + set_pmd(pmd, __pmd(phys | prot_sect)); /* * Check for previous table entries created during * boot (__create_page_tables) and flush them. @@ -213,21 +193,46 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, if (!pmd_none(old_pmd)) flush_tlb_all(); } else { - alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys)); + alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys), + prot_pte); } phys += next - addr; } while (pmd++, addr = next, addr != end); } static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, - unsigned long end, unsigned long phys) + unsigned long end, unsigned long phys, + int map_io) { pud_t *pud = pud_offset(pgd, addr); unsigned long next; do { next = pud_addr_end(addr, end); - alloc_init_pmd(pud, addr, next, phys); + + /* + * For 4K granule only, attempt to put down a 1GB block + */ + if (!map_io && (PAGE_SHIFT == 12) && + ((addr | next | phys) & ~PUD_MASK) == 0) { + pud_t old_pud = *pud; + set_pud(pud, __pud(phys | PROT_SECT_NORMAL_EXEC)); + + /* + * If we have an old value for a pud, it will + * be pointing to a pmd table that we no longer + * need (from swapper_pg_dir). + * + * Look up the old pmd table and free it. + */ + if (!pud_none(old_pud)) { + phys_addr_t table = __pa(pmd_offset(&old_pud, 0)); + memblock_free(table, PAGE_SIZE); + flush_tlb_all(); + } + } else { + alloc_init_pmd(pud, addr, next, phys, map_io); + } phys += next - addr; } while (pud++, addr = next, addr != end); } @@ -236,30 +241,44 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, * Create the page directory entries and any necessary page tables for the * mapping specified by 'md'. */ -static void __init create_mapping(phys_addr_t phys, unsigned long virt, - phys_addr_t size) +static void __init __create_mapping(pgd_t *pgd, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + int map_io) { unsigned long addr, length, end, next; - pgd_t *pgd; - - if (virt < VMALLOC_START) { - pr_warning("BUG: not creating mapping for 0x%016llx at 0x%016lx - outside kernel range\n", - phys, virt); - return; - } addr = virt & PAGE_MASK; length = PAGE_ALIGN(size + (virt & ~PAGE_MASK)); - pgd = pgd_offset_k(addr); end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgd, addr, next, phys); + alloc_init_pud(pgd, addr, next, phys, map_io); phys += next - addr; } while (pgd++, addr = next, addr != end); } +static void __init create_mapping(phys_addr_t phys, unsigned long virt, + phys_addr_t size) +{ + if (virt < VMALLOC_START) { + pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n", + &phys, virt); + return; + } + __create_mapping(pgd_offset_k(virt & PAGE_MASK), phys, virt, size, 0); +} + +void __init create_id_mapping(phys_addr_t addr, phys_addr_t size, int map_io) +{ + if ((addr >> PGDIR_SHIFT) >= ARRAY_SIZE(idmap_pg_dir)) { + pr_warn("BUG: not creating id mapping for %pa\n", &addr); + return; + } + __create_mapping(&idmap_pg_dir[pgd_index(addr)], + addr, addr, size, map_io); +} + static void __init map_mem(void) { struct memblock_region *reg; @@ -370,6 +389,9 @@ int kern_addr_valid(unsigned long addr) if (pud_none(*pud)) return 0; + if (pud_sect(*pud)) + return pfn_valid(pud_pfn(*pud)); + pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return 0; @@ -417,7 +439,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) if (!p) return -ENOMEM; - set_pmd(pmd, __pmd(__pa(p) | prot_sect_kernel)); + set_pmd(pmd, __pmd(__pa(p) | PROT_SECT_NORMAL)); } else vmemmap_verify((pte_t *)pmd, node, addr, next); } while (addr = next, addr != end); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 9042aff5e9e3..7736779c9809 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -182,7 +182,7 @@ ENDPROC(cpu_do_switch_mm) ENTRY(__cpu_setup) ic iallu // I+BTB cache invalidate tlbi vmalle1is // invalidate I + D TLBs - dsb sy + dsb ish mov x0, #3 << 20 msr cpacr_el1, x0 // Enable FP/ASIMD diff --git a/arch/arm64/mm/tlb.S b/arch/arm64/mm/tlb.S deleted file mode 100644 index 19da91e0cd27..000000000000 --- a/arch/arm64/mm/tlb.S +++ /dev/null @@ -1,71 +0,0 @@ -/* - * Based on arch/arm/mm/tlb.S - * - * Copyright (C) 1997-2002 Russell King - * Copyright (C) 2012 ARM Ltd. - * Written by Catalin Marinas <catalin.marinas@arm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ -#include <linux/linkage.h> -#include <asm/assembler.h> -#include <asm/asm-offsets.h> -#include <asm/page.h> -#include <asm/tlbflush.h> -#include "proc-macros.S" - -/* - * __cpu_flush_user_tlb_range(start, end, vma) - * - * Invalidate a range of TLB entries in the specified address space. - * - * - start - start address (may not be aligned) - * - end - end address (exclusive, may not be aligned) - * - vma - vma_struct describing address range - */ -ENTRY(__cpu_flush_user_tlb_range) - vma_vm_mm x3, x2 // get vma->vm_mm - mmid w3, x3 // get vm_mm->context.id - dsb sy - lsr x0, x0, #12 // align address - lsr x1, x1, #12 - bfi x0, x3, #48, #16 // start VA and ASID - bfi x1, x3, #48, #16 // end VA and ASID -1: tlbi vae1is, x0 // TLB invalidate by address and ASID - add x0, x0, #1 - cmp x0, x1 - b.lo 1b - dsb sy - ret -ENDPROC(__cpu_flush_user_tlb_range) - -/* - * __cpu_flush_kern_tlb_range(start,end) - * - * Invalidate a range of kernel TLB entries. - * - * - start - start address (may not be aligned) - * - end - end address (exclusive, may not be aligned) - */ -ENTRY(__cpu_flush_kern_tlb_range) - dsb sy - lsr x0, x0, #12 // align address - lsr x1, x1, #12 -1: tlbi vaae1is, x0 // TLB invalidate by address - add x0, x0, #1 - cmp x0, x1 - b.lo 1b - dsb sy - isb - ret -ENDPROC(__cpu_flush_kern_tlb_range) diff --git a/arch/blackfin/include/asm/ftrace.h b/arch/blackfin/include/asm/ftrace.h index 8a029505d7b7..2f1c3c2657ad 100644 --- a/arch/blackfin/include/asm/ftrace.h +++ b/arch/blackfin/include/asm/ftrace.h @@ -66,16 +66,7 @@ extern inline void *return_address(unsigned int level) #endif /* CONFIG_FRAME_POINTER */ -#define HAVE_ARCH_CALLER_ADDR - -/* inline function or macro may lead to unexpected result */ -#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -#define CALLER_ADDR1 ((unsigned long)return_address(1)) -#define CALLER_ADDR2 ((unsigned long)return_address(2)) -#define CALLER_ADDR3 ((unsigned long)return_address(3)) -#define CALLER_ADDR4 ((unsigned long)return_address(4)) -#define CALLER_ADDR5 ((unsigned long)return_address(5)) -#define CALLER_ADDR6 ((unsigned long)return_address(6)) +#define ftrace_return_address(n) return_address(n) #endif /* __ASSEMBLY__ */ diff --git a/arch/blackfin/include/asm/unistd.h b/arch/blackfin/include/asm/unistd.h index c35414bdf7bd..c8c8ff9eff61 100644 --- a/arch/blackfin/include/asm/unistd.h +++ b/arch/blackfin/include/asm/unistd.h @@ -12,7 +12,6 @@ #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_FADVISE64 #define __ARCH_WANT_SYS_GETPGRP diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c index e1f88e028cfe..8b8fe671b1a6 100644 --- a/arch/blackfin/kernel/ptrace.c +++ b/arch/blackfin/kernel/ptrace.c @@ -117,6 +117,7 @@ put_reg(struct task_struct *task, unsigned long regno, unsigned long data) int is_user_addr_valid(struct task_struct *child, unsigned long start, unsigned long len) { + bool valid; struct vm_area_struct *vma; struct sram_list_struct *sraml; @@ -124,9 +125,12 @@ is_user_addr_valid(struct task_struct *child, unsigned long start, unsigned long if (start + len < start) return -EIO; + down_read(&child->mm->mmap_sem); vma = find_vma(child->mm, start); - if (vma && start >= vma->vm_start && start + len <= vma->vm_end) - return 0; + valid = vma && start >= vma->vm_start && start + len <= vma->vm_end; + up_read(&child->mm->mmap_sem); + if (valid) + return 0; for (sraml = child->mm->context.sram_list; sraml; sraml = sraml->next) if (start >= (unsigned long)sraml->addr diff --git a/arch/c6x/kernel/setup.c b/arch/c6x/kernel/setup.c index 731db4b9014d..757128868d43 100644 --- a/arch/c6x/kernel/setup.c +++ b/arch/c6x/kernel/setup.c @@ -265,8 +265,8 @@ int __init c6x_add_memory(phys_addr_t start, unsigned long size) */ notrace void __init machine_init(unsigned long dt_ptr) { - struct boot_param_header *dtb = __va(dt_ptr); - struct boot_param_header *fdt = (struct boot_param_header *)_fdt_start; + const void *dtb = __va(dt_ptr); + const void *fdt = _fdt_start; /* interrupts must be masked */ set_creg(IER, 2); diff --git a/arch/cris/arch-v10/drivers/gpio.c b/arch/cris/arch-v10/drivers/gpio.c index f4374bae4fb4..64285e0d3481 100644 --- a/arch/cris/arch-v10/drivers/gpio.c +++ b/arch/cris/arch-v10/drivers/gpio.c @@ -833,8 +833,8 @@ static int __init gpio_init(void) printk(KERN_INFO "ETRAX 100LX GPIO driver v2.5, (c) 2001-2008 " "Axis Communications AB\n"); /* We call etrax_gpio_wake_up_check() from timer interrupt and - * from cpu_idle() in kernel/process.c - * The check in cpu_idle() reduces latency from ~15 ms to ~6 ms + * from default_idle() in kernel/process.c + * The check in default_idle() reduces latency from ~15 ms to ~6 ms * in some tests. */ res = request_irq(TIMER0_IRQ_NBR, gpio_poll_timer_interrupt, diff --git a/arch/cris/arch-v32/drivers/mach-fs/gpio.c b/arch/cris/arch-v32/drivers/mach-fs/gpio.c index 9e54273af0ca..009f4ee1bd09 100644 --- a/arch/cris/arch-v32/drivers/mach-fs/gpio.c +++ b/arch/cris/arch-v32/drivers/mach-fs/gpio.c @@ -958,11 +958,7 @@ gpio_init(void) printk(KERN_INFO "ETRAX FS GPIO driver v2.5, (c) 2003-2007 " "Axis Communications AB\n"); - /* We call etrax_gpio_wake_up_check() from timer interrupt and - * from cpu_idle() in kernel/process.c - * The check in cpu_idle() reduces latency from ~15 ms to ~6 ms - * in some tests. - */ + /* We call etrax_gpio_wake_up_check() from timer interrupt */ if (request_irq(TIMER0_INTR_VECT, gpio_poll_timer_interrupt, IRQF_SHARED, "gpio poll", &alarmlist)) printk(KERN_ERR "timer0 irq for gpio\n"); diff --git a/arch/cris/include/asm/unistd.h b/arch/cris/include/asm/unistd.h index 5cc7d1991e48..0f40fed1ba25 100644 --- a/arch/cris/include/asm/unistd.h +++ b/arch/cris/include/asm/unistd.h @@ -15,7 +15,6 @@ #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_UTIME diff --git a/arch/frv/include/asm/unistd.h b/arch/frv/include/asm/unistd.h index 70ec7293dce7..17b5df8fc28a 100644 --- a/arch/frv/include/asm/unistd.h +++ b/arch/frv/include/asm/unistd.h @@ -13,7 +13,6 @@ /* #define __ARCH_WANT_SYS_GETHOSTNAME */ #define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE -/* #define __ARCH_WANT_SYS_SGETMASK */ /* #define __ARCH_WANT_SYS_SIGNAL */ #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_UTIME diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 12c3afee0f6f..2f3abcf8f6bc 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -32,6 +32,7 @@ config IA64 select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP select GENERIC_IRQ_SHOW + select GENERIC_IRQ_LEGACY select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_IOMAP diff --git a/arch/ia64/include/asm/hw_irq.h b/arch/ia64/include/asm/hw_irq.h index a681d02cb324..029bab36cd91 100644 --- a/arch/ia64/include/asm/hw_irq.h +++ b/arch/ia64/include/asm/hw_irq.h @@ -132,7 +132,6 @@ extern int reserve_irq_vector (int vector); extern void __setup_vector_irq(int cpu); extern void ia64_send_ipi (int cpu, int vector, int delivery_mode, int redirect); extern void ia64_native_register_percpu_irq (ia64_vector vec, struct irqaction *action); -extern int check_irq_used (int irq); extern void destroy_and_reserve_irq (unsigned int irq); #if defined(CONFIG_SMP) && (defined(CONFIG_IA64_GENERIC) || defined(CONFIG_IA64_DIG)) diff --git a/arch/ia64/include/asm/irq.h b/arch/ia64/include/asm/irq.h index 91b920fd7d53..820667cbea7e 100644 --- a/arch/ia64/include/asm/irq.h +++ b/arch/ia64/include/asm/irq.h @@ -31,4 +31,7 @@ bool is_affinity_mask_valid(const struct cpumask *cpumask); #define is_affinity_mask_valid is_affinity_mask_valid +int create_irq(void); +void destroy_irq(unsigned int irq); + #endif /* _ASM_IA64_IRQ_H */ diff --git a/arch/ia64/include/asm/irq_remapping.h b/arch/ia64/include/asm/irq_remapping.h index a8687b1d8906..e3b3556e2e1b 100644 --- a/arch/ia64/include/asm/irq_remapping.h +++ b/arch/ia64/include/asm/irq_remapping.h @@ -1,4 +1,6 @@ #ifndef __IA64_INTR_REMAPPING_H #define __IA64_INTR_REMAPPING_H #define irq_remapping_enabled 0 +#define dmar_alloc_hwirq create_irq +#define dmar_free_hwirq destroy_irq #endif diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 3202aa74e0d6..6437ca21f61b 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -21,7 +21,8 @@ #define PENALTY_FOR_NODE_WITH_CPUS 255 /* - * Distance above which we begin to use zone reclaim + * Nodes within this distance are eligible for reclaim by zone_reclaim() when + * zone_reclaim_mode is enabled. */ #define RECLAIM_DISTANCE 15 diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index b942f4032d7a..2955f359e2a7 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -237,7 +237,7 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data) } #ifdef CONFIG_SYSCTL -static ctl_table kdump_ctl_table[] = { +static struct ctl_table kdump_ctl_table[] = { { .procname = "kdump_on_init", .data = &kdump_on_init, @@ -255,7 +255,7 @@ static ctl_table kdump_ctl_table[] = { { } }; -static ctl_table sys_table[] = { +static struct ctl_table sys_table[] = { { .procname = "kernel", .mode = 0555, diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index 19f107be734e..cd44a57c73be 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -735,7 +735,7 @@ iosapic_register_intr (unsigned int gsi, rte = find_rte(irq, gsi); if(iosapic_intr_info[irq].count == 0) { assign_irq_vector(irq); - dynamic_irq_init(irq); + irq_init_desc(irq); } else if (rte->refcnt != NO_REF_RTE) { rte->refcnt++; goto unlock_iosapic_lock; diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 0884f5ecbcc3..03ea78ed64a9 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -93,14 +93,6 @@ static int irq_status[NR_IRQS] = { [0 ... NR_IRQS -1] = IRQ_UNUSED }; -int check_irq_used(int irq) -{ - if (irq_status[irq] == IRQ_USED) - return 1; - - return -1; -} - static inline int find_unassigned_irq(void) { int irq; @@ -390,8 +382,7 @@ void destroy_and_reserve_irq(unsigned int irq) { unsigned long flags; - dynamic_irq_cleanup(irq); - + irq_init_desc(irq); spin_lock_irqsave(&vector_lock, flags); __clear_irq_vector(irq); irq_status[irq] = IRQ_RSVD; @@ -424,13 +415,13 @@ int create_irq(void) out: spin_unlock_irqrestore(&vector_lock, flags); if (irq >= 0) - dynamic_irq_init(irq); + irq_init_desc(irq); return irq; } void destroy_irq(unsigned int irq) { - dynamic_irq_cleanup(irq); + irq_init_desc(irq); clear_irq_vector(irq); } diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index d841c4bd6864..5845ffea67c3 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -521,7 +521,7 @@ static pmu_config_t *pmu_conf; pfm_sysctl_t pfm_sysctl; EXPORT_SYMBOL(pfm_sysctl); -static ctl_table pfm_ctl_table[]={ +static struct ctl_table pfm_ctl_table[] = { { .procname = "debug", .data = &pfm_sysctl.debug, @@ -552,7 +552,7 @@ static ctl_table pfm_ctl_table[]={ }, {} }; -static ctl_table pfm_sysctl_dir[] = { +static struct ctl_table pfm_sysctl_dir[] = { { .procname = "perfmon", .mode = 0555, @@ -560,7 +560,7 @@ static ctl_table pfm_sysctl_dir[] = { }, {} }; -static ctl_table pfm_sysctl_root[] = { +static struct ctl_table pfm_sysctl_root[] = { { .procname = "kernel", .mode = 0555, diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 68232db98baa..76069c18ee42 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -114,11 +114,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 0; -} - struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/m68k/include/asm/signal.h b/arch/m68k/include/asm/signal.h index 214320b50384..8c8ce5e1ee0e 100644 --- a/arch/m68k/include/asm/signal.h +++ b/arch/m68k/include/asm/signal.h @@ -60,15 +60,6 @@ static inline int __gen_sigismember(sigset_t *set, int _sig) __const_sigismember(set,sig) : \ __gen_sigismember(set,sig)) -static inline int sigfindinword(unsigned long word) -{ - asm ("bfffo %1{#0,#0},%0" - : "=d" (word) - : "d" (word & -word) - : "cc"); - return word ^ 31; -} - #endif /* !CONFIG_CPU_HAS_NO_BITFIELDS */ #ifndef __uClinux__ diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index 33afa56ad47a..1fcdd344c7ad 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -13,7 +13,6 @@ #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_UTIME diff --git a/arch/metag/kernel/setup.c b/arch/metag/kernel/setup.c index 129c7cdda1ce..31cf53d0eba2 100644 --- a/arch/metag/kernel/setup.c +++ b/arch/metag/kernel/setup.c @@ -105,10 +105,6 @@ extern char _heap_start[]; -#ifdef CONFIG_METAG_BUILTIN_DTB -extern u32 __dtb_start[]; -#endif - #ifdef CONFIG_DA_CONSOLE /* Our early channel based console driver */ extern struct console dash_console; diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c index 042431509b56..3c52fa6d0f8e 100644 --- a/arch/metag/mm/hugetlbpage.c +++ b/arch/metag/mm/hugetlbpage.c @@ -110,11 +110,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 1; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/microblaze/configs/mmu_defconfig b/arch/microblaze/configs/mmu_defconfig index deaf45ab6429..e2f6543b91e7 100644 --- a/arch/microblaze/configs/mmu_defconfig +++ b/arch/microblaze/configs/mmu_defconfig @@ -49,6 +49,7 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_UARTLITE=y CONFIG_SERIAL_UARTLITE_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set CONFIG_XILINX_HWICAP=y CONFIG_I2C=y diff --git a/arch/microblaze/configs/nommu_defconfig b/arch/microblaze/configs/nommu_defconfig index 10b5172283d7..a29ebd4a9fcb 100644 --- a/arch/microblaze/configs/nommu_defconfig +++ b/arch/microblaze/configs/nommu_defconfig @@ -58,6 +58,7 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_UARTLITE=y CONFIG_SERIAL_UARTLITE_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set CONFIG_XILINX_HWICAP=y CONFIG_I2C=y diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index c98ed95c0541..35b3ecaf25d5 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -2,6 +2,7 @@ generic-y += barrier.h generic-y += clkdev.h generic-y += cputime.h +generic-y += device.h generic-y += exec.h generic-y += hash.h generic-y += mcs_spinlock.h diff --git a/arch/microblaze/include/asm/device.h b/arch/microblaze/include/asm/device.h deleted file mode 100644 index 123b2fe72d01..000000000000 --- a/arch/microblaze/include/asm/device.h +++ /dev/null @@ -1,26 +0,0 @@ -/* - * Arch specific extensions to struct device - * - * This file is subject to the terms and conditions of the GNU General Public - * License v2. See the file "COPYING" in the main directory of this archive - * for more details. - */ - -#ifndef _ASM_MICROBLAZE_DEVICE_H -#define _ASM_MICROBLAZE_DEVICE_H - -struct device_node; - -struct dev_archdata { - /* DMA operations on that device */ - struct dma_map_ops *dma_ops; - void *dma_data; -}; - -struct pdev_archdata { - u64 dma_mask; -}; - -#endif /* _ASM_MICROBLAZE_DEVICE_H */ - - diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h index 46460f1c49c4..ab353723076a 100644 --- a/arch/microblaze/include/asm/dma-mapping.h +++ b/arch/microblaze/include/asm/dma-mapping.h @@ -35,16 +35,6 @@ #define __dma_alloc_coherent(dev, gfp, size, handle) NULL #define __dma_free_coherent(size, addr) ((void)0) -static inline unsigned long device_to_mask(struct device *dev) -{ - if (dev->dma_mask && *dev->dma_mask) - return *dev->dma_mask; - /* Assume devices without mask can take 32 bit addresses */ - return 0xfffffffful; -} - -extern struct dma_map_ops *dma_ops; - /* * Available generic sets of operations */ @@ -52,20 +42,7 @@ extern struct dma_map_ops dma_direct_ops; static inline struct dma_map_ops *get_dma_ops(struct device *dev) { - /* We don't handle the NULL dev case for ISA for now. We could - * do it via an out of line call but it is not needed for now. The - * only ISA DMA device we support is the floppy and we have a hack - * in the floppy driver directly to get a device for us. - */ - if (unlikely(!dev) || !dev->archdata.dma_ops) - return NULL; - - return dev->archdata.dma_ops; -} - -static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops) -{ - dev->archdata.dma_ops = ops; + return &dma_direct_ops; } static inline int dma_supported(struct device *dev, u64 mask) diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h index 1e4c3329f62e..433751b2a003 100644 --- a/arch/microblaze/include/asm/io.h +++ b/arch/microblaze/include/asm/io.h @@ -19,17 +19,14 @@ #ifndef CONFIG_PCI #define _IO_BASE 0 #define _ISA_MEM_BASE 0 -#define PCI_DRAM_OFFSET 0 #else #define _IO_BASE isa_io_base #define _ISA_MEM_BASE isa_mem_base -#define PCI_DRAM_OFFSET pci_dram_offset struct pci_dev; extern void pci_iounmap(struct pci_dev *dev, void __iomem *); #define pci_iounmap pci_iounmap extern unsigned long isa_io_base; -extern unsigned long pci_dram_offset; extern resource_size_t isa_mem_base; #endif diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h index 335524040fff..468aca8cec0d 100644 --- a/arch/microblaze/include/asm/pci.h +++ b/arch/microblaze/include/asm/pci.h @@ -45,14 +45,6 @@ struct pci_dev; #define pcibios_assign_all_busses() 0 #ifdef CONFIG_PCI -extern void set_pci_dma_ops(struct dma_map_ops *dma_ops); -extern struct dma_map_ops *get_pci_dma_ops(void); -#else /* CONFIG_PCI */ -#define set_pci_dma_ops(d) -#define get_pci_dma_ops() NULL -#endif - -#ifdef CONFIG_PCI static inline void pci_dma_burst_advice(struct pci_dev *pdev, enum pci_dma_burst_strategy *strat, unsigned long *strategy_parameter) diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h index b14232b6878f..fd56a8f66489 100644 --- a/arch/microblaze/include/asm/unistd.h +++ b/arch/microblaze/include/asm/unistd.h @@ -19,7 +19,6 @@ #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_UTIME diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index da68d00fd087..4633c36c1b32 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -13,23 +13,6 @@ #include <linux/export.h> #include <linux/bug.h> -/* - * Generic direct DMA implementation - * - * This implementation supports a per-device offset that can be applied if - * the address at which memory is visible to devices is not 0. Platform code - * can set archdata.dma_data to an unsigned long holding the offset. By - * default the offset is PCI_DRAM_OFFSET. - */ - -static unsigned long get_dma_direct_offset(struct device *dev) -{ - if (likely(dev)) - return (unsigned long)dev->archdata.dma_data; - - return PCI_DRAM_OFFSET; /* FIXME Not sure if is correct */ -} - #define NOT_COHERENT_CACHE static void *dma_direct_alloc_coherent(struct device *dev, size_t size, @@ -51,7 +34,7 @@ static void *dma_direct_alloc_coherent(struct device *dev, size_t size, return NULL; ret = page_address(page); memset(ret, 0, size); - *dma_handle = virt_to_phys(ret) + get_dma_direct_offset(dev); + *dma_handle = virt_to_phys(ret); return ret; #endif @@ -77,7 +60,7 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, /* FIXME this part of code is untested */ for_each_sg(sgl, sg, nents, i) { - sg->dma_address = sg_phys(sg) + get_dma_direct_offset(dev); + sg->dma_address = sg_phys(sg); __dma_sync(page_to_phys(sg_page(sg)) + sg->offset, sg->length, direction); } @@ -85,12 +68,6 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, return nents; } -static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) -{ -} - static int dma_direct_dma_supported(struct device *dev, u64 mask) { return 1; @@ -104,7 +81,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, struct dma_attrs *attrs) { __dma_sync(page_to_phys(page) + offset, size, direction); - return page_to_phys(page) + offset + get_dma_direct_offset(dev); + return page_to_phys(page) + offset; } static inline void dma_direct_unmap_page(struct device *dev, @@ -181,7 +158,6 @@ struct dma_map_ops dma_direct_ops = { .alloc = dma_direct_alloc_coherent, .free = dma_direct_free_coherent, .map_sg = dma_direct_map_sg, - .unmap_sg = dma_direct_unmap_sg, .dma_supported = dma_direct_dma_supported, .map_page = dma_direct_map_page, .unmap_page = dma_direct_unmap_page, diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S index 17645b2e2f07..4655ff342c64 100644 --- a/arch/microblaze/kernel/head.S +++ b/arch/microblaze/kernel/head.S @@ -205,7 +205,7 @@ GT4: /* r11 contains the rest - will be either 1 or 4 */ GT16: /* TLB0 is 16MB */ addik r9, r0, 0x1000000 /* means TLB0 is 16MB */ TLB1: - /* must be used r2 because of substract if failed */ + /* must be used r2 because of subtract if failed */ addik r2, r11, -0x0400000 bgei r2, GT20 /* size is greater than 16MB */ /* size is >16MB and <20MB */ diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c index abdfb10e7eca..68f099960ebc 100644 --- a/arch/microblaze/kernel/prom.c +++ b/arch/microblaze/kernel/prom.c @@ -43,13 +43,13 @@ #include <asm/pci-bridge.h> #ifdef CONFIG_EARLY_PRINTK -static char *stdout; +static const char *stdout; static int __init early_init_dt_scan_chosen_serial(unsigned long node, const char *uname, int depth, void *data) { - unsigned long l; - char *p; + int l; + const char *p; pr_debug("%s: depth: %d, uname: %s\n", __func__, depth, uname); @@ -80,7 +80,7 @@ static int __init early_init_dt_scan_chosen_serial(unsigned long node, (strncmp(p, "xlnx,opb-uartlite", 17) == 0) || (strncmp(p, "xlnx,axi-uartlite", 17) == 0) || (strncmp(p, "xlnx,mdm", 8) == 0)) { - unsigned int *addrp; + const unsigned int *addrp; *(u32 *)data = UARTLITE; @@ -114,34 +114,3 @@ void __init early_init_devtree(void *params) pr_debug(" <- early_init_devtree()\n"); } - -/******* - * - * New implementation of the OF "find" APIs, return a refcounted - * object, call of_node_put() when done. The device tree and list - * are protected by a rw_lock. - * - * Note that property management will need some locking as well, - * this isn't dealt with yet. - * - *******/ - -#if defined(CONFIG_DEBUG_FS) && defined(DEBUG) -static struct debugfs_blob_wrapper flat_dt_blob; - -static int __init export_flat_device_tree(void) -{ - struct dentry *d; - - flat_dt_blob.data = initial_boot_params; - flat_dt_blob.size = initial_boot_params->totalsize; - - d = debugfs_create_blob("flat-device-tree", S_IFREG | S_IRUSR, - of_debugfs_root, &flat_dt_blob); - if (!d) - return 1; - - return 0; -} -device_initcall(export_flat_device_tree); -#endif diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c index 67cc4b282cc1..ab5b488e1fde 100644 --- a/arch/microblaze/kernel/setup.c +++ b/arch/microblaze/kernel/setup.c @@ -71,13 +71,9 @@ void __init setup_arch(char **cmdline_p) xilinx_pci_init(); -#ifdef CONFIG_VT -#if defined(CONFIG_XILINX_CONSOLE) - conswitchp = &xil_con; -#elif defined(CONFIG_DUMMY_CONSOLE) +#if defined(CONFIG_DUMMY_CONSOLE) conswitchp = &dummy_con; #endif -#endif } #ifdef CONFIG_MTD_UCLINUX @@ -229,31 +225,3 @@ static int __init debugfs_tlb(void) device_initcall(debugfs_tlb); # endif #endif - -static int dflt_bus_notify(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - /* We are only intereted in device addition */ - if (action != BUS_NOTIFY_ADD_DEVICE) - return 0; - - set_dma_ops(dev, &dma_direct_ops); - - return NOTIFY_DONE; -} - -static struct notifier_block dflt_plat_bus_notifier = { - .notifier_call = dflt_bus_notify, - .priority = INT_MAX, -}; - -static int __init setup_bus_notifier(void) -{ - bus_register_notifier(&platform_bus_type, &dflt_plat_bus_notifier); - - return 0; -} - -arch_initcall(setup_bus_notifier); diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index a59de1bc1ce0..9037914f6985 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -47,24 +47,9 @@ static int global_phb_number; /* Global phb counter */ /* ISA Memory physical address */ resource_size_t isa_mem_base; -static struct dma_map_ops *pci_dma_ops = &dma_direct_ops; - unsigned long isa_io_base; -unsigned long pci_dram_offset; static int pci_bus_count; - -void set_pci_dma_ops(struct dma_map_ops *dma_ops) -{ - pci_dma_ops = dma_ops; -} - -struct dma_map_ops *get_pci_dma_ops(void) -{ - return pci_dma_ops; -} -EXPORT_SYMBOL(get_pci_dma_ops); - struct pci_controller *pcibios_alloc_controller(struct device_node *dev) { struct pci_controller *phb; @@ -866,10 +851,6 @@ void pcibios_setup_bus_devices(struct pci_bus *bus) */ set_dev_node(&dev->dev, pcibus_to_node(dev->bus)); - /* Hook up default DMA ops */ - set_dma_ops(&dev->dev, pci_dma_ops); - dev->dev.archdata.dma_data = (void *)PCI_DRAM_OFFSET; - /* Read default IRQs and fixup if necessary */ dev->irq = of_irq_parse_and_map_pci(dev, 0, 0); } diff --git a/arch/mips/Kbuild b/arch/mips/Kbuild index d2cfe45f332b..dd295335891a 100644 --- a/arch/mips/Kbuild +++ b/arch/mips/Kbuild @@ -16,7 +16,7 @@ obj- := $(platform-) obj-y += kernel/ obj-y += mm/ -obj-y += math-emu/ +obj-y += net/ ifdef CONFIG_KVM obj-y += kvm/ diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms index 6e239123d6fe..f5e18bf3275e 100644 --- a/arch/mips/Kbuild.platforms +++ b/arch/mips/Kbuild.platforms @@ -18,6 +18,7 @@ platforms += loongson1 platforms += mti-malta platforms += mti-sead3 platforms += netlogic +platforms += paravirt platforms += pmcs-msp71xx platforms += pnx833x platforms += ralink diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 5e0014e864f3..7a469acee33c 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -12,6 +12,7 @@ config MIPS select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK + select HAVE_BPF_JIT if !CPU_MICROMIPS select ARCH_HAVE_CUSTOM_GPIO_H select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST @@ -50,6 +51,8 @@ config MIPS select CLONE_BACKWARDS select HAVE_DEBUG_STACKOVERFLOW select HAVE_CC_STACKPROTECTOR + select CPU_PM if CPU_IDLE + select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST menu "Machine selection" @@ -83,6 +86,7 @@ config AR7 select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN + select SYS_SUPPORTS_MIPS16 select SYS_SUPPORTS_ZBOOT_UART16550 select ARCH_REQUIRE_GPIOLIB select VLYNQ @@ -106,6 +110,7 @@ config ATH79 select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN + select SYS_SUPPORTS_MIPS16 help Support for the Atheros AR71XX/AR724X/AR913X SoCs. @@ -122,6 +127,7 @@ config BCM47XX select NO_EXCEPT_FILL select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN + select SYS_SUPPORTS_MIPS16 select SYS_HAS_EARLY_PRINTK select USE_GENERIC_EARLY_PRINTK_8250 help @@ -168,9 +174,9 @@ config MACH_DECSTATION bool "DECstations" select BOOT_ELF32 select CEVT_DS1287 - select CEVT_R4K + select CEVT_R4K if CPU_R4X00 select CSRC_IOASIC - select CSRC_R4K + select CSRC_R4K if CPU_R4X00 select CPU_DADDI_WORKAROUNDS if 64BIT select CPU_R4000_WORKAROUNDS if 64BIT select CPU_R4400_WORKAROUNDS if 64BIT @@ -248,6 +254,7 @@ config LANTIQ select SYS_HAS_CPU_MIPS32_R2 select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_32BIT_KERNEL + select SYS_SUPPORTS_MIPS16 select SYS_SUPPORTS_MULTITHREADING select SYS_HAS_EARLY_PRINTK select ARCH_REQUIRE_GPIOLIB @@ -330,6 +337,7 @@ config MIPS_MALTA select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_MIPS_CMP select SYS_SUPPORTS_MIPS_CPS + select SYS_SUPPORTS_MIPS16 select SYS_SUPPORTS_MULTITHREADING select SYS_SUPPORTS_SMARTMIPS select SYS_SUPPORTS_ZBOOT @@ -361,6 +369,7 @@ config MIPS_SEAD3 select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_SMARTMIPS select SYS_SUPPORTS_MICROMIPS + select SYS_SUPPORTS_MIPS16 select USB_EHCI_BIG_ENDIAN_DESC select USB_EHCI_BIG_ENDIAN_MMIO select USE_OF @@ -380,6 +389,7 @@ config MACH_VR41XX select CEVT_R4K select CSRC_R4K select SYS_HAS_CPU_VR41XX + select SYS_SUPPORTS_MIPS16 select ARCH_REQUIRE_GPIOLIB config NXP_STB220 @@ -407,6 +417,7 @@ config PMC_MSP select SYS_HAS_CPU_MIPS32_R2 select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN + select SYS_SUPPORTS_MIPS16 select IRQ_CPU select SERIAL_8250 select SERIAL_8250_CONSOLE @@ -430,6 +441,7 @@ config RALINK select SYS_HAS_CPU_MIPS32_R2 select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN + select SYS_SUPPORTS_MIPS16 select SYS_HAS_EARLY_PRINTK select HAVE_MACH_CLKDEV select CLKDEV_LOOKUP @@ -674,7 +686,6 @@ config SNI_RM select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN - select USE_GENERIC_EARLY_PRINTK_8250 help The SNI RM200/300/400 are MIPS-based machines manufactured by Siemens Nixdorf Informationssysteme (SNI), parent company of Pyramid @@ -721,6 +732,11 @@ config CAVIUM_OCTEON_SOC select ZONE_DMA32 select HOLES_IN_ZONE select ARCH_REQUIRE_GPIOLIB + select LIBFDT + select USE_OF + select ARCH_SPARSEMEM_ENABLE + select SYS_SUPPORTS_SMP + select NR_CPUS_DEFAULT_16 help This option supports all of the Octeon reference boards from Cavium Networks. It builds a kernel that dynamically determines the Octeon @@ -789,6 +805,25 @@ config NLM_XLP_BOARD This board is based on Netlogic XLP Processor. Say Y here if you have a XLP based board. +config MIPS_PARAVIRT + bool "Para-Virtualized guest system" + select CEVT_R4K + select CSRC_R4K + select DMA_COHERENT + select SYS_SUPPORTS_64BIT_KERNEL + select SYS_SUPPORTS_32BIT_KERNEL + select SYS_SUPPORTS_BIG_ENDIAN + select SYS_SUPPORTS_SMP + select NR_CPUS_DEFAULT_4 + select SYS_HAS_EARLY_PRINTK + select SYS_HAS_CPU_MIPS32_R2 + select SYS_HAS_CPU_MIPS64_R2 + select SYS_HAS_CPU_CAVIUM_OCTEON + select HW_HAS_PCI + select SWAP_IO_SPACE + help + This option supports guest running under ???? + endchoice source "arch/mips/alchemy/Kconfig" @@ -809,6 +844,7 @@ source "arch/mips/cavium-octeon/Kconfig" source "arch/mips/loongson/Kconfig" source "arch/mips/loongson1/Kconfig" source "arch/mips/netlogic/Kconfig" +source "arch/mips/paravirt/Kconfig" endmenu @@ -1059,6 +1095,7 @@ config SOC_PNX833X select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_BIG_ENDIAN + select SYS_SUPPORTS_MIPS16 select CPU_MIPSR2_IRQ_VI config SOC_PNX8335 @@ -1398,16 +1435,11 @@ config CPU_SB1 config CPU_CAVIUM_OCTEON bool "Cavium Octeon processor" depends on SYS_HAS_CPU_CAVIUM_OCTEON - select ARCH_SPARSEMEM_ENABLE select CPU_HAS_PREFETCH select CPU_SUPPORTS_64BIT_KERNEL - select SYS_SUPPORTS_SMP - select NR_CPUS_DEFAULT_16 select WEAK_ORDERING select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_HUGEPAGES - select LIBFDT - select USE_OF select USB_EHCI_BIG_ENDIAN_MMIO select MIPS_L1_CACHE_SHIFT_7 help @@ -1659,6 +1691,12 @@ config SYS_HAS_CPU_XLR config SYS_HAS_CPU_XLP bool +config MIPS_MALTA_PM + depends on MIPS_MALTA + depends on PCI + bool + default y + # # CPU may reorder R->R, R->W, W->R, W->W # Reordering beyond LL and SC is handled in WEAK_REORDERING_BEYOND_LLSC @@ -1842,7 +1880,7 @@ config FORCE_MAX_ZONEORDER config CEVT_GIC bool "Use GIC global counter for clock events" - depends on IRQ_GIC && !(MIPS_SEAD3 || MIPS_MT_SMTC) + depends on IRQ_GIC && !MIPS_SEAD3 help Use the GIC global counter for the clock events. The R4K clock event driver is always present, so if the platform ends up not @@ -1895,19 +1933,8 @@ config CPU_R4K_CACHE_TLB bool default y if !(CPU_R3000 || CPU_R8000 || CPU_SB1 || CPU_TX39XX || CPU_CAVIUM_OCTEON) -choice - prompt "MIPS MT options" - -config MIPS_MT_DISABLED - bool "Disable multithreading support" - help - Use this option if your platform does not support the MT ASE - which is hardware multithreading support. On systems without - an MT-enabled processor, this will be the only option that is - available in this menu. - config MIPS_MT_SMP - bool "Use 1 TC on each available VPE for SMP" + bool "MIPS MT SMP support (1 TC on each available VPE)" depends on SYS_SUPPORTS_MULTITHREADING select CPU_MIPSR2_IRQ_VI select CPU_MIPSR2_IRQ_EI @@ -1926,26 +1953,6 @@ config MIPS_MT_SMP Intel Hyperthreading feature. For further information go to <http://www.imgtec.com/mips/mips-multithreading.asp>. -config MIPS_MT_SMTC - bool "Use all TCs on all VPEs for SMP (DEPRECATED)" - depends on CPU_MIPS32_R2 - depends on SYS_SUPPORTS_MULTITHREADING - depends on !MIPS_CPS - select CPU_MIPSR2_IRQ_VI - select CPU_MIPSR2_IRQ_EI - select MIPS_MT - select SMP - select SMP_UP - select SYS_SUPPORTS_SMP - select NR_CPUS_DEFAULT_8 - help - This is a kernel model which is known as SMTC. This is - supported on cores with the MT ASE and presents all TCs - available on all VPEs to support SMP. For further - information see <http://www.linux-mips.org/wiki/34K#SMTC>. - -endchoice - config MIPS_MT bool @@ -1967,7 +1974,7 @@ config SYS_SUPPORTS_MULTITHREADING config MIPS_MT_FPAFF bool "Dynamic FPU affinity for FP-intensive threads" default y - depends on MIPS_MT_SMP || MIPS_MT_SMTC + depends on MIPS_MT_SMP config MIPS_VPE_LOADER bool "VPE loader support." @@ -1989,29 +1996,6 @@ config MIPS_VPE_LOADER_MT default "y" depends on MIPS_VPE_LOADER && !MIPS_CMP -config MIPS_MT_SMTC_IM_BACKSTOP - bool "Use per-TC register bits as backstop for inhibited IM bits" - depends on MIPS_MT_SMTC - default n - help - To support multiple TC microthreads acting as "CPUs" within - a VPE, VPE-wide interrupt mask bits must be specially manipulated - during interrupt handling. To support legacy drivers and interrupt - controller management code, SMTC has a "backstop" to track and - if necessary restore the interrupt mask. This has some performance - impact on interrupt service overhead. - -config MIPS_MT_SMTC_IRQAFF - bool "Support IRQ affinity API" - depends on MIPS_MT_SMTC - default n - help - Enables SMP IRQ affinity API (/proc/irq/*/smp_affinity, etc.) - for SMTC Linux kernel. Requires platform support, of which - an example can be found in the MIPS kernel i8259 and Malta - platform code. Adds some overhead to interrupt dispatch, and - should be used only if you know what you are doing. - config MIPS_VPE_LOADER_TOM bool "Load VPE program into memory hidden from linux" depends on MIPS_VPE_LOADER @@ -2039,7 +2023,7 @@ config MIPS_VPE_APSP_API_MT config MIPS_CMP bool "MIPS CMP framework support (DEPRECATED)" - depends on SYS_SUPPORTS_MIPS_CMP && !MIPS_MT_SMTC + depends on SYS_SUPPORTS_MIPS_CMP select MIPS_GIC_IPI select SYNC_R4K select WEAK_ORDERING @@ -2057,9 +2041,11 @@ config MIPS_CPS depends on SYS_SUPPORTS_MIPS_CPS select MIPS_CM select MIPS_CPC + select MIPS_CPS_PM if HOTPLUG_CPU select MIPS_GIC_IPI select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) + select SYS_SUPPORTS_HOTPLUG_CPU select SYS_SUPPORTS_SMP select WEAK_ORDERING help @@ -2069,6 +2055,9 @@ config MIPS_CPS no external assistance. It is safe to enable this when hardware support is unavailable. +config MIPS_CPS_PM + bool + config MIPS_GIC_IPI bool @@ -2199,6 +2188,13 @@ config SYS_SUPPORTS_SMARTMIPS config SYS_SUPPORTS_MICROMIPS bool +config SYS_SUPPORTS_MIPS16 + bool + help + This option must be set if a kernel might be executed on a MIPS16- + enabled CPU even if MIPS16 is not actually being used. In other + words, it makes the kernel MIPS16-tolerant. + config CPU_SUPPORTS_MSA bool @@ -2239,7 +2235,7 @@ config NODES_SHIFT config HW_PERF_EVENTS bool "Enable hardware performance counter support for perf events" - depends on PERF_EVENTS && !MIPS_MT_SMTC && OPROFILE=n && (CPU_MIPS32 || CPU_MIPS64 || CPU_R10000 || CPU_SB1 || CPU_CAVIUM_OCTEON || CPU_XLP) + depends on PERF_EVENTS && OPROFILE=n && (CPU_MIPS32 || CPU_MIPS64 || CPU_R10000 || CPU_SB1 || CPU_CAVIUM_OCTEON || CPU_XLP) default y help Enable hardware performance counter support for perf events. If @@ -2297,8 +2293,8 @@ config NR_CPUS_DEFAULT_64 bool config NR_CPUS - int "Maximum number of CPUs (2-64)" - range 2 64 + int "Maximum number of CPUs (2-256)" + range 2 256 depends on SMP default "4" if NR_CPUS_DEFAULT_4 default "8" if NR_CPUS_DEFAULT_8 @@ -2671,12 +2667,16 @@ endmenu config MIPS_EXTERNAL_TIMER bool -if CPU_SUPPORTS_CPUFREQ && MIPS_EXTERNAL_TIMER menu "CPU Power Management" + +if CPU_SUPPORTS_CPUFREQ && MIPS_EXTERNAL_TIMER source "drivers/cpufreq/Kconfig" -endmenu endif +source "drivers/cpuidle/Kconfig" + +endmenu + source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug index 25de29211d76..3a2b775e8458 100644 --- a/arch/mips/Kconfig.debug +++ b/arch/mips/Kconfig.debug @@ -79,15 +79,6 @@ config CMDLINE_OVERRIDE Normally, you will choose 'N' here. -config SMTC_IDLE_HOOK_DEBUG - bool "Enable additional debug checks before going into CPU idle loop" - depends on DEBUG_KERNEL && MIPS_MT_SMTC - help - This option enables Enable additional debug checks before going into - CPU idle loop. For details on these checks, see - arch/mips/kernel/smtc.c. This debugging option result in significant - overhead so should be disabled in production kernels. - config SB1XXX_CORELIS bool "Corelis Debugger" depends on SIBYTE_SB1xxx_SOC diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 60a359cfa328..a8521de14791 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -120,7 +120,7 @@ cflags-$(CONFIG_SB1XXX_CORELIS) += $(call cc-option,-mno-sched-prolog) \ -fno-omit-frame-pointer ifeq ($(CONFIG_CPU_HAS_MSA),y) -toolchain-msa := $(call cc-option-yn,-mhard-float -mfp64 -mmsa) +toolchain-msa := $(call cc-option-yn,-mhard-float -mfp64 -Wa$(comma)-mmsa) cflags-$(toolchain-msa) += -DTOOLCHAIN_SUPPORTS_MSA endif @@ -251,6 +251,7 @@ OBJCOPYFLAGS += --remove-section=.reginfo head-y := arch/mips/kernel/head.o libs-y += arch/mips/lib/ +libs-y += arch/mips/math-emu/ # See arch/mips/Kbuild for content of core part of the kernel core-y += arch/mips/ diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c index bd5513650293..3fb814be0e91 100644 --- a/arch/mips/alchemy/board-xxs1500.c +++ b/arch/mips/alchemy/board-xxs1500.c @@ -49,7 +49,7 @@ void __init prom_init(void) prom_init_cmdline(); memsize_str = prom_getenv("memsize"); - if (!memsize_str || strict_strtoul(memsize_str, 0, &memsize)) + if (!memsize_str || kstrtoul(memsize_str, 0, &memsize)) memsize = 0x04000000; add_memory_region(0, memsize, BOOT_MEM_RAM); diff --git a/arch/mips/alchemy/common/setup.c b/arch/mips/alchemy/common/setup.c index 566a1743f685..8267e3c97721 100644 --- a/arch/mips/alchemy/common/setup.c +++ b/arch/mips/alchemy/common/setup.c @@ -67,6 +67,12 @@ void __init plat_mem_setup(void) case ALCHEMY_CPU_AU1500: case ALCHEMY_CPU_AU1100: coherentio = 0; + break; + case ALCHEMY_CPU_AU1200: + /* Au1200 AB USB does not support coherent memory */ + if (0 == (read_c0_prid() & PRID_REV_MASK)) + coherentio = 0; + break; } board_setup(); /* board specific setup */ diff --git a/arch/mips/alchemy/common/usb.c b/arch/mips/alchemy/common/usb.c index 2adc7edda49c..d193dbea84a1 100644 --- a/arch/mips/alchemy/common/usb.c +++ b/arch/mips/alchemy/common/usb.c @@ -355,47 +355,25 @@ static inline void __au1200_udc_control(void __iomem *base, int enable) } } -static inline int au1200_coherency_bug(void) -{ -#if defined(CONFIG_DMA_COHERENT) - /* Au1200 AB USB does not support coherent memory */ - if (!(read_c0_prid() & PRID_REV_MASK)) { - printk(KERN_INFO "Au1200 USB: this is chip revision AB !!\n"); - printk(KERN_INFO "Au1200 USB: update your board or re-configure" - " the kernel\n"); - return -ENODEV; - } -#endif - return 0; -} - static inline int au1200_usb_control(int block, int enable) { void __iomem *base = (void __iomem *)KSEG1ADDR(AU1200_USB_CTL_PHYS_ADDR); - int ret = 0; switch (block) { case ALCHEMY_USB_OHCI0: - ret = au1200_coherency_bug(); - if (ret && enable) - goto out; __au1200_ohci_control(base, enable); break; case ALCHEMY_USB_UDC0: __au1200_udc_control(base, enable); break; case ALCHEMY_USB_EHCI0: - ret = au1200_coherency_bug(); - if (ret && enable) - goto out; __au1200_ehci_control(base, enable); break; default: - ret = -ENODEV; + return -ENODEV; } -out: - return ret; + return 0; } diff --git a/arch/mips/alchemy/devboards/pm.c b/arch/mips/alchemy/devboards/pm.c index b86bff31d1d3..61e90fe9eab1 100644 --- a/arch/mips/alchemy/devboards/pm.c +++ b/arch/mips/alchemy/devboards/pm.c @@ -158,7 +158,7 @@ static ssize_t db1x_pmattr_store(struct kobject *kobj, int tmp; if (ATTRCMP(timer_timeout)) { - tmp = strict_strtoul(instr, 0, &l); + tmp = kstrtoul(instr, 0, &l); if (tmp) return tmp; @@ -181,7 +181,7 @@ static ssize_t db1x_pmattr_store(struct kobject *kobj, } } else if (ATTRCMP(wakemsk)) { - tmp = strict_strtoul(instr, 0, &l); + tmp = kstrtoul(instr, 0, &l); if (tmp) return tmp; diff --git a/arch/mips/bcm47xx/prom.c b/arch/mips/bcm47xx/prom.c index 0af808dfd1ca..1a03a2f43496 100644 --- a/arch/mips/bcm47xx/prom.c +++ b/arch/mips/bcm47xx/prom.c @@ -69,15 +69,18 @@ static __init void prom_init_mem(void) * BCM47XX uses 128MB for addressing the ram, if the system contains * less that that amount of ram it remaps the ram more often into the * available space. - * Accessing memory after 128MB will cause an exception. - * max contains the biggest possible address supported by the platform. - * If the method wants to try something above we assume 128MB ram. */ - off = (unsigned long)prom_init; - max = off | ((128 << 20) - 1); - for (mem = (1 << 20); mem < (128 << 20); mem += (1 << 20)) { - if ((off + mem) > max) { - mem = (128 << 20); + + /* Physical address, without mapping to any kernel segment */ + off = CPHYSADDR((unsigned long)prom_init); + + /* Accessing memory after 128 MiB will cause an exception */ + max = 128 << 20; + + for (mem = 1 << 20; mem < max; mem += 1 << 20) { + /* Loop condition may be not enough, off may be over 1 MiB */ + if (off + mem >= max) { + mem = max; printk(KERN_DEBUG "assume 128MB RAM\n"); break; } diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig index 227705d9d5ae..602866657938 100644 --- a/arch/mips/cavium-octeon/Kconfig +++ b/arch/mips/cavium-octeon/Kconfig @@ -10,6 +10,17 @@ config CAVIUM_CN63XXP1 non-CN63XXP1 hardware, so it is recommended to select "n" unless it is known the workarounds are needed. +config CAVIUM_OCTEON_CVMSEG_SIZE + int "Number of L1 cache lines reserved for CVMSEG memory" + range 0 54 + default 1 + help + CVMSEG LM is a segment that accesses portions of the dcache as a + local memory; the larger CVMSEG is, the smaller the cache is. + This selects the size of CVMSEG LM, which is in cache blocks. The + legally range is from zero to 54 cache blocks (i.e. CVMSEG LM is + between zero and 6192 bytes). + endif # CPU_CAVIUM_OCTEON if CAVIUM_OCTEON_SOC @@ -23,17 +34,6 @@ config CAVIUM_OCTEON_2ND_KERNEL with this option to be run at the same time as one built without this option. -config CAVIUM_OCTEON_CVMSEG_SIZE - int "Number of L1 cache lines reserved for CVMSEG memory" - range 0 54 - default 1 - help - CVMSEG LM is a segment that accesses portions of the dcache as a - local memory; the larger CVMSEG is, the smaller the cache is. - This selects the size of CVMSEG LM, which is in cache blocks. The - legally range is from zero to 54 cache blocks (i.e. CVMSEG LM is - between zero and 6192 bytes). - config CAVIUM_OCTEON_LOCK_L2 bool "Lock often used kernel code in the L2" default "y" @@ -86,7 +86,6 @@ config SWIOTLB select IOMMU_HELPER select NEED_SG_DMA_LENGTH - config OCTEON_ILM tristate "Module to measure interrupt latency using Octeon CIU Timer" help diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c index 8553ad5c72b6..7e5cf7a5e2f3 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c @@ -106,6 +106,158 @@ int cvmx_helper_ports_on_interface(int interface) EXPORT_SYMBOL_GPL(cvmx_helper_ports_on_interface); /** + * @INTERNAL + * Return interface mode for CN68xx. + */ +static cvmx_helper_interface_mode_t __cvmx_get_mode_cn68xx(int interface) +{ + union cvmx_mio_qlmx_cfg qlm_cfg; + switch (interface) { + case 0: + qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(0)); + /* QLM is disabled when QLM SPD is 15. */ + if (qlm_cfg.s.qlm_spd == 15) + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + + if (qlm_cfg.s.qlm_cfg == 2) + return CVMX_HELPER_INTERFACE_MODE_SGMII; + else if (qlm_cfg.s.qlm_cfg == 3) + return CVMX_HELPER_INTERFACE_MODE_XAUI; + else + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + case 2: + case 3: + case 4: + qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(interface)); + /* QLM is disabled when QLM SPD is 15. */ + if (qlm_cfg.s.qlm_spd == 15) + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + + if (qlm_cfg.s.qlm_cfg == 2) + return CVMX_HELPER_INTERFACE_MODE_SGMII; + else if (qlm_cfg.s.qlm_cfg == 3) + return CVMX_HELPER_INTERFACE_MODE_XAUI; + else + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + case 7: + qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(3)); + /* QLM is disabled when QLM SPD is 15. */ + if (qlm_cfg.s.qlm_spd == 15) { + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + } else if (qlm_cfg.s.qlm_cfg != 0) { + qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(1)); + if (qlm_cfg.s.qlm_cfg != 0) + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + } + return CVMX_HELPER_INTERFACE_MODE_NPI; + case 8: + return CVMX_HELPER_INTERFACE_MODE_LOOP; + default: + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + } +} + +/** + * @INTERNAL + * Return interface mode for an Octeon II + */ +static cvmx_helper_interface_mode_t __cvmx_get_mode_octeon2(int interface) +{ + union cvmx_gmxx_inf_mode mode; + + if (OCTEON_IS_MODEL(OCTEON_CN68XX)) + return __cvmx_get_mode_cn68xx(interface); + + if (interface == 2) + return CVMX_HELPER_INTERFACE_MODE_NPI; + + if (interface == 3) + return CVMX_HELPER_INTERFACE_MODE_LOOP; + + /* Only present in CN63XX & CN66XX Octeon model */ + if ((OCTEON_IS_MODEL(OCTEON_CN63XX) && + (interface == 4 || interface == 5)) || + (OCTEON_IS_MODEL(OCTEON_CN66XX) && + interface >= 4 && interface <= 7)) { + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + } + + if (OCTEON_IS_MODEL(OCTEON_CN66XX)) { + union cvmx_mio_qlmx_cfg mio_qlm_cfg; + + /* QLM2 is SGMII0 and QLM1 is SGMII1 */ + if (interface == 0) + mio_qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(2)); + else if (interface == 1) + mio_qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(1)); + else + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + + if (mio_qlm_cfg.s.qlm_spd == 15) + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + + if (mio_qlm_cfg.s.qlm_cfg == 9) + return CVMX_HELPER_INTERFACE_MODE_SGMII; + else if (mio_qlm_cfg.s.qlm_cfg == 11) + return CVMX_HELPER_INTERFACE_MODE_XAUI; + else + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + } else if (OCTEON_IS_MODEL(OCTEON_CN61XX)) { + union cvmx_mio_qlmx_cfg qlm_cfg; + + if (interface == 0) { + qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(2)); + if (qlm_cfg.s.qlm_cfg == 2) + return CVMX_HELPER_INTERFACE_MODE_SGMII; + else if (qlm_cfg.s.qlm_cfg == 3) + return CVMX_HELPER_INTERFACE_MODE_XAUI; + else + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + } else if (interface == 1) { + qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(0)); + if (qlm_cfg.s.qlm_cfg == 2) + return CVMX_HELPER_INTERFACE_MODE_SGMII; + else if (qlm_cfg.s.qlm_cfg == 3) + return CVMX_HELPER_INTERFACE_MODE_XAUI; + else + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + } + } else if (OCTEON_IS_MODEL(OCTEON_CNF71XX)) { + if (interface == 0) { + union cvmx_mio_qlmx_cfg qlm_cfg; + qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(0)); + if (qlm_cfg.s.qlm_cfg == 2) + return CVMX_HELPER_INTERFACE_MODE_SGMII; + } + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + } + + if (interface == 1 && OCTEON_IS_MODEL(OCTEON_CN63XX)) + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + + mode.u64 = cvmx_read_csr(CVMX_GMXX_INF_MODE(interface)); + + if (OCTEON_IS_MODEL(OCTEON_CN63XX)) { + switch (mode.cn63xx.mode) { + case 0: + return CVMX_HELPER_INTERFACE_MODE_SGMII; + case 1: + return CVMX_HELPER_INTERFACE_MODE_XAUI; + default: + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + } + } else { + if (!mode.s.en) + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + + if (mode.s.type) + return CVMX_HELPER_INTERFACE_MODE_GMII; + else + return CVMX_HELPER_INTERFACE_MODE_RGMII; + } +} + +/** * Get the operating mode of an interface. Depending on the Octeon * chip and configuration, this function returns an enumeration * of the type of packet I/O supported by an interface. @@ -118,6 +270,20 @@ EXPORT_SYMBOL_GPL(cvmx_helper_ports_on_interface); cvmx_helper_interface_mode_t cvmx_helper_interface_get_mode(int interface) { union cvmx_gmxx_inf_mode mode; + + if (interface < 0 || + interface >= cvmx_helper_get_number_of_interfaces()) + return CVMX_HELPER_INTERFACE_MODE_DISABLED; + + /* + * Octeon II models + */ + if (OCTEON_IS_MODEL(OCTEON_CN6XXX) || OCTEON_IS_MODEL(OCTEON_CNF71XX)) + return __cvmx_get_mode_octeon2(interface); + + /* + * Octeon and Octeon Plus models + */ if (interface == 2) return CVMX_HELPER_INTERFACE_MODE_NPI; diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 3aa5b46b2d40..1b82ac6921e0 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -1260,11 +1260,13 @@ static void __init octeon_irq_init_ciu(void) for (i = 0; i < 4; i++) octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_PCI_MSI0, 0, i + 40); + octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_TWSI, 0, 45); octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_RML, 0, 46); for (i = 0; i < 4; i++) octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_TIMER0, 0, i + 52); octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB0, 0, 56); + octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_TWSI2, 0, 59); /* CIU_1 */ for (i = 0; i < 16; i++) diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index 331b837cec57..008e9c8b8eac 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -729,17 +729,6 @@ void __init prom_init(void) octeon_write_lcd("Linux"); #endif -#ifdef CONFIG_CAVIUM_GDB - /* - * When debugging the linux kernel, force the cores to enter - * the debug exception handler to break in. - */ - if (octeon_get_boot_debug_flag()) { - cvmx_write_csr(CVMX_CIU_DINT, 1 << cvmx_get_core_num()); - cvmx_read_csr(CVMX_CIU_DINT); - } -#endif - octeon_setup_delays(); /* @@ -779,12 +768,6 @@ void __init prom_init(void) MAX_MEMORY = 32ull << 30; if (*p == '@') RESERVE_LOW_MEM = memparse(p + 1, &p); - } else if (strcmp(arg, "ecc_verbose") == 0) { -#ifdef CONFIG_CAVIUM_REPORT_SINGLE_BIT_ECC - __cvmx_interrupt_ecc_report_single_bit_errors = 1; - pr_notice("Reporting of single bit ECC errors is " - "turned on\n"); -#endif #ifdef CONFIG_KEXEC } else if (strncmp(arg, "crashkernel=", 12) == 0) { crashk_size = memparse(arg+12, &p); @@ -1053,36 +1036,26 @@ void prom_free_prom_memory(void) int octeon_prune_device_tree(void); extern const char __dtb_octeon_3xxx_begin; -extern const char __dtb_octeon_3xxx_end; extern const char __dtb_octeon_68xx_begin; -extern const char __dtb_octeon_68xx_end; void __init device_tree_init(void) { - int dt_size; - struct boot_param_header *fdt; + const void *fdt; bool do_prune; if (octeon_bootinfo->minor_version >= 3 && octeon_bootinfo->fdt_addr) { fdt = phys_to_virt(octeon_bootinfo->fdt_addr); if (fdt_check_header(fdt)) panic("Corrupt Device Tree passed to kernel."); - dt_size = be32_to_cpu(fdt->totalsize); do_prune = false; } else if (OCTEON_IS_MODEL(OCTEON_CN68XX)) { - fdt = (struct boot_param_header *)&__dtb_octeon_68xx_begin; - dt_size = &__dtb_octeon_68xx_end - &__dtb_octeon_68xx_begin; + fdt = &__dtb_octeon_68xx_begin; do_prune = true; } else { - fdt = (struct boot_param_header *)&__dtb_octeon_3xxx_begin; - dt_size = &__dtb_octeon_3xxx_end - &__dtb_octeon_3xxx_begin; + fdt = &__dtb_octeon_3xxx_begin; do_prune = true; } - /* Copy the default tree from init memory. */ - initial_boot_params = early_init_dt_alloc_memory_arch(dt_size, 8); - if (initial_boot_params == NULL) - panic("Could not allocate initial_boot_params"); - memcpy(initial_boot_params, fdt, dt_size); + initial_boot_params = (void *)fdt; if (do_prune) { octeon_prune_device_tree(); @@ -1090,7 +1063,7 @@ void __init device_tree_init(void) } else { pr_info("Using passed Device Tree.\n"); } - unflatten_device_tree(); + unflatten_and_copy_device_tree(); } static int __initdata disable_octeon_edac_p; diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 67a078ffc464..a7b3ae104d8c 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -218,15 +218,6 @@ void octeon_prepare_cpus(unsigned int max_cpus) */ static void octeon_smp_finish(void) { -#ifdef CONFIG_CAVIUM_GDB - unsigned long tmp; - /* Pulse MCD0 signal on Ctrl-C to stop all the cores. Also set the MCD0 - to be not masked by this core so we know the signal is received by - someone */ - asm volatile ("dmfc0 %0, $22\n" - "ori %0, %0, 0x9100\n" "dmtc0 %0, $22\n" : "=r" (tmp)); -#endif - octeon_user_io_init(); /* to generate the first CPU timer interrupt */ @@ -234,21 +225,6 @@ static void octeon_smp_finish(void) local_irq_enable(); } -/** - * Hook for after all CPUs are online - */ -static void octeon_cpus_done(void) -{ -#ifdef CONFIG_CAVIUM_GDB - unsigned long tmp; - /* Pulse MCD0 signal on Ctrl-C to stop all the cores. Also set the MCD0 - to be not masked by this core so we know the signal is received by - someone */ - asm volatile ("dmfc0 %0, $22\n" - "ori %0, %0, 0x9100\n" "dmtc0 %0, $22\n" : "=r" (tmp)); -#endif -} - #ifdef CONFIG_HOTPLUG_CPU /* State of each CPU. */ @@ -405,7 +381,6 @@ struct plat_smp_ops octeon_smp_ops = { .send_ipi_mask = octeon_send_ipi_mask, .init_secondary = octeon_init_secondary, .smp_finish = octeon_smp_finish, - .cpus_done = octeon_cpus_done, .boot_secondary = octeon_boot_secondary, .smp_setup = octeon_smp_setup, .prepare_cpus = octeon_prepare_cpus, diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig index e3a3836508ec..134879c1310a 100644 --- a/arch/mips/configs/ath79_defconfig +++ b/arch/mips/configs/ath79_defconfig @@ -46,7 +46,6 @@ CONFIG_MTD=y CONFIG_MTD_REDBOOT_PARTS=y CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-2 CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_JEDECPROBE=y @@ -54,7 +53,7 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_COMPLEX_MAPPINGS=y CONFIG_MTD_PHYSMAP=y CONFIG_MTD_M25P80=y -# CONFIG_M25PXX_USE_FAST_READ is not set +CONFIG_MTD_SPI_NOR=y CONFIG_NETDEVICES=y # CONFIG_NET_PACKET_ENGINE is not set CONFIG_ATH_COMMON=m diff --git a/arch/mips/configs/db1xxx_defconfig b/arch/mips/configs/db1xxx_defconfig index c99b6eeda90b..a64b30b96a0d 100644 --- a/arch/mips/configs/db1xxx_defconfig +++ b/arch/mips/configs/db1xxx_defconfig @@ -113,6 +113,7 @@ CONFIG_MTD_NAND=y CONFIG_MTD_NAND_ECC_BCH=y CONFIG_MTD_NAND_AU1550=y CONFIG_MTD_NAND_PLATFORM=y +CONFIG_MTD_SPI_NOR=y CONFIG_EEPROM_AT24=y CONFIG_EEPROM_AT25=y CONFIG_SCSI_TGT=y diff --git a/arch/mips/configs/maltasmtc_defconfig b/arch/mips/configs/maltasmtc_defconfig deleted file mode 100644 index eb316447588c..000000000000 --- a/arch/mips/configs/maltasmtc_defconfig +++ /dev/null @@ -1,196 +0,0 @@ -CONFIG_MIPS_MALTA=y -CONFIG_CPU_LITTLE_ENDIAN=y -CONFIG_CPU_MIPS32_R2=y -CONFIG_PAGE_SIZE_16KB=y -CONFIG_MIPS_MT_SMTC=y -# CONFIG_MIPS_MT_FPAFF is not set -CONFIG_NR_CPUS=9 -CONFIG_HZ_48=y -CONFIG_LOCALVERSION="smtc" -CONFIG_SYSVIPC=y -CONFIG_POSIX_MQUEUE=y -CONFIG_AUDIT=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=15 -CONFIG_SYSCTL_SYSCALL=y -CONFIG_EMBEDDED=y -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_MODULE_SRCVERSION_ALL=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_PCI=y -# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_XFRM_USER=m -CONFIG_NET_KEY=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_ADVANCED_ROUTER=y -CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_ROUTE_MULTIPATH=y -CONFIG_IP_ROUTE_VERBOSE=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_NET_IPIP=m -CONFIG_IP_MROUTE=y -CONFIG_IP_PIMSM_V1=y -CONFIG_IP_PIMSM_V2=y -CONFIG_SYN_COOKIES=y -CONFIG_INET_AH=m -CONFIG_INET_ESP=m -CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_IPV6_TUNNEL=m -CONFIG_BRIDGE=m -CONFIG_VLAN_8021Q=m -CONFIG_ATALK=m -CONFIG_DEV_APPLETALK=m -CONFIG_IPDDP=m -CONFIG_IPDDP_ENCAP=y -CONFIG_NET_SCHED=y -CONFIG_NET_SCH_CBQ=m -CONFIG_NET_SCH_HTB=m -CONFIG_NET_SCH_HFSC=m -CONFIG_NET_SCH_PRIO=m -CONFIG_NET_SCH_RED=m -CONFIG_NET_SCH_SFQ=m -CONFIG_NET_SCH_TEQL=m -CONFIG_NET_SCH_TBF=m -CONFIG_NET_SCH_GRED=m -CONFIG_NET_SCH_DSMARK=m -CONFIG_NET_SCH_NETEM=m -CONFIG_NET_SCH_INGRESS=m -CONFIG_NET_CLS_BASIC=m -CONFIG_NET_CLS_TCINDEX=m -CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_FW=m -CONFIG_NET_CLS_U32=m -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_RSVP6=m -CONFIG_NET_CLS_ACT=y -CONFIG_NET_ACT_POLICE=y -CONFIG_NET_CLS_IND=y -# CONFIG_WIRELESS is not set -CONFIG_DEVTMPFS=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_CRYPTOLOOP=m -CONFIG_IDE=y -# CONFIG_IDE_PROC_FS is not set -# CONFIG_IDEPCI_PCIBUS_ORDER is not set -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_PIIX=y -CONFIG_SCSI=y -CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_SG=y -# CONFIG_SCSI_LOWLEVEL is not set -CONFIG_NETDEVICES=y -# CONFIG_NET_VENDOR_3COM is not set -# CONFIG_NET_VENDOR_ADAPTEC is not set -# CONFIG_NET_VENDOR_ALTEON is not set -CONFIG_PCNET32=y -# CONFIG_NET_VENDOR_ATHEROS is not set -# CONFIG_NET_VENDOR_BROADCOM is not set -# CONFIG_NET_VENDOR_BROCADE is not set -# CONFIG_NET_VENDOR_CHELSIO is not set -# CONFIG_NET_VENDOR_CISCO is not set -# CONFIG_NET_VENDOR_DEC is not set -# CONFIG_NET_VENDOR_DLINK is not set -# CONFIG_NET_VENDOR_EMULEX is not set -# CONFIG_NET_VENDOR_EXAR is not set -# CONFIG_NET_VENDOR_HP is not set -# CONFIG_NET_VENDOR_INTEL is not set -# CONFIG_NET_VENDOR_MARVELL is not set -# CONFIG_NET_VENDOR_MELLANOX is not set -# CONFIG_NET_VENDOR_MICREL is not set -# CONFIG_NET_VENDOR_MYRI is not set -# CONFIG_NET_VENDOR_NATSEMI is not set -# CONFIG_NET_VENDOR_NVIDIA is not set -# CONFIG_NET_VENDOR_OKI is not set -# CONFIG_NET_PACKET_ENGINE is not set -# CONFIG_NET_VENDOR_QLOGIC is not set -# CONFIG_NET_VENDOR_REALTEK is not set -# CONFIG_NET_VENDOR_RDC is not set -# CONFIG_NET_VENDOR_SEEQ is not set -# CONFIG_NET_VENDOR_SILAN is not set -# CONFIG_NET_VENDOR_SIS is not set -# CONFIG_NET_VENDOR_SMSC is not set -# CONFIG_NET_VENDOR_STMICRO is not set -# CONFIG_NET_VENDOR_SUN is not set -# CONFIG_NET_VENDOR_TEHUTI is not set -# CONFIG_NET_VENDOR_TI is not set -# CONFIG_NET_VENDOR_TOSHIBA is not set -# CONFIG_NET_VENDOR_VIA is not set -# CONFIG_WLAN is not set -# CONFIG_VT is not set -CONFIG_LEGACY_PTY_COUNT=16 -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_HW_RANDOM=y -# CONFIG_HWMON is not set -CONFIG_VIDEO_OUTPUT_CONTROL=m -CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y -CONFIG_FB_MATROX=y -CONFIG_FB_MATROX_G=y -CONFIG_USB=y -CONFIG_USB_EHCI_HCD=y -# CONFIG_USB_EHCI_TT_NEWSCHED is not set -CONFIG_USB_UHCI_HCD=y -CONFIG_USB_STORAGE=y -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=y -CONFIG_LEDS_TRIGGERS=y -CONFIG_LEDS_TRIGGER_TIMER=y -CONFIG_LEDS_TRIGGER_IDE_DISK=y -CONFIG_LEDS_TRIGGER_HEARTBEAT=y -CONFIG_LEDS_TRIGGER_BACKLIGHT=y -CONFIG_LEDS_TRIGGER_DEFAULT_ON=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_CMOS=y -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set -CONFIG_XFS_FS=y -CONFIG_XFS_QUOTA=y -CONFIG_XFS_POSIX_ACL=y -CONFIG_QUOTA=y -CONFIG_QFMT_V2=y -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_NFS_FS=y -CONFIG_ROOT_NFS=y -CONFIG_CIFS=m -CONFIG_CIFS_WEAK_PW_HASH=y -CONFIG_CIFS_XATTR=y -CONFIG_CIFS_POSIX=y -CONFIG_NLS_CODEPAGE_437=m -CONFIG_NLS_ISO8859_1=m -# CONFIG_FTRACE is not set -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_HMAC=y -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set -# CONFIG_CRYPTO_HW is not set diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig index 10ef3bed5f43..f8a32315bb38 100644 --- a/arch/mips/configs/maltasmvp_defconfig +++ b/arch/mips/configs/maltasmvp_defconfig @@ -4,10 +4,9 @@ CONFIG_CPU_MIPS32_R2=y CONFIG_PAGE_SIZE_16KB=y CONFIG_MIPS_MT_SMP=y CONFIG_SCHED_SMT=y -CONFIG_MIPS_CMP=y +CONFIG_MIPS_CPS=y CONFIG_NR_CPUS=8 CONFIG_HZ_100=y -CONFIG_LOCALVERSION="cmp" CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig index 2d3002cba102..c83338a39917 100644 --- a/arch/mips/configs/maltasmvp_eva_defconfig +++ b/arch/mips/configs/maltasmvp_eva_defconfig @@ -5,10 +5,9 @@ CONFIG_CPU_MIPS32_3_5_FEATURES=y CONFIG_PAGE_SIZE_16KB=y CONFIG_MIPS_MT_SMP=y CONFIG_SCHED_SMT=y -CONFIG_MIPS_CMP=y +CONFIG_MIPS_CPS=y CONFIG_NR_CPUS=8 CONFIG_HZ_100=y -CONFIG_LOCALVERSION="cmp" CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y diff --git a/arch/mips/configs/mips_paravirt_defconfig b/arch/mips/configs/mips_paravirt_defconfig new file mode 100644 index 000000000000..84cfcb4bf2ea --- /dev/null +++ b/arch/mips/configs/mips_paravirt_defconfig @@ -0,0 +1,103 @@ +CONFIG_MIPS_PARAVIRT=y +CONFIG_CPU_MIPS64_R2=y +CONFIG_64BIT=y +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_SMP=y +CONFIG_HZ_1000=y +CONFIG_PREEMPT=y +CONFIG_SYSVIPC=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_BSD_PROCESS_ACCT_V3=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_RELAY=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_EXPERT=y +CONFIG_SLAB=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set +CONFIG_PCI=y +CONFIG_MIPS32_COMPAT=y +CONFIG_MIPS32_O32=y +CONFIG_MIPS32_N32=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_SYN_COOKIES=y +# CONFIG_INET_LRO is not set +CONFIG_IPV6=y +# CONFIG_WIRELESS is not set +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +# CONFIG_FW_LOADER is not set +CONFIG_BLK_DEV_LOOP=y +CONFIG_VIRTIO_BLK=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_NETDEVICES=y +CONFIG_VIRTIO_NET=y +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_SMSC is not set +# CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_WIZNET is not set +CONFIG_PHYLIB=y +CONFIG_MARVELL_PHY=y +CONFIG_BROADCOM_PHY=y +CONFIG_BCM87XX_PHY=y +# CONFIG_WLAN is not set +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +CONFIG_VIRTIO_CONSOLE=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_VIRTIO_MMIO=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_HUGETLBFS=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +CONFIG_NFS_V4=y +CONFIG_NFS_V4_1=y +CONFIG_ROOT_NFS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=y +CONFIG_NLS_UTF8=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_FS=y +CONFIG_MAGIC_SYSRQ=y +# CONFIG_SCHED_DEBUG is not set +# CONFIG_FTRACE is not set +CONFIG_CRYPTO_CBC=y +CONFIG_CRYPTO_HMAC=y +CONFIG_CRYPTO_MD5=y +CONFIG_CRYPTO_DES=y +# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/mips/configs/rt305x_defconfig b/arch/mips/configs/rt305x_defconfig index d1741bcf8949..d14ae2fa7d13 100644 --- a/arch/mips/configs/rt305x_defconfig +++ b/arch/mips/configs/rt305x_defconfig @@ -81,7 +81,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FIRMWARE_IN_KERNEL is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y @@ -89,6 +88,7 @@ CONFIG_MTD_COMPLEX_MAPPINGS=y CONFIG_MTD_PHYSMAP=y CONFIG_MTD_PHYSMAP_OF=y CONFIG_MTD_M25P80=y +CONFIG_MTD_SPI_NOR=y CONFIG_EEPROM_93CX6=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y diff --git a/arch/mips/dec/Makefile b/arch/mips/dec/Makefile index 3d5d2c56de8d..bd74e05c90b0 100644 --- a/arch/mips/dec/Makefile +++ b/arch/mips/dec/Makefile @@ -3,7 +3,7 @@ # obj-y := ecc-berr.o int-handler.o ioasic-irq.o kn01-berr.o \ - kn02-irq.o kn02xa-berr.o reset.o setup.o time.o + kn02-irq.o kn02xa-berr.o platform.o reset.o setup.o time.o obj-$(CONFIG_TC) += tc.o obj-$(CONFIG_CPU_HAS_WB) += wbflush.o diff --git a/arch/mips/dec/platform.c b/arch/mips/dec/platform.c new file mode 100644 index 000000000000..c7ac86af847a --- /dev/null +++ b/arch/mips/dec/platform.c @@ -0,0 +1,44 @@ +/* + * DEC platform devices. + * + * Copyright (c) 2014 Maciej W. Rozycki + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/ioport.h> +#include <linux/kernel.h> +#include <linux/mc146818rtc.h> +#include <linux/platform_device.h> + +static struct resource dec_rtc_resources[] = { + { + .name = "rtc", + .flags = IORESOURCE_MEM, + }, +}; + +static struct cmos_rtc_board_info dec_rtc_info = { + .flags = CMOS_RTC_FLAGS_NOFREQ, + .address_space = 64, +}; + +static struct platform_device dec_rtc_device = { + .name = "rtc_cmos", + .id = PLATFORM_DEVID_NONE, + .dev.platform_data = &dec_rtc_info, + .resource = dec_rtc_resources, + .num_resources = ARRAY_SIZE(dec_rtc_resources), +}; + +static int __init dec_add_devices(void) +{ + dec_rtc_resources[0].start = RTC_PORT(0); + dec_rtc_resources[0].end = RTC_PORT(0) + dec_kn_slot_size - 1; + return platform_device_register(&dec_rtc_device); +} + +device_initcall(dec_add_devices); diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c index 56e6e2c23683..41bbffd9cc0e 100644 --- a/arch/mips/dec/setup.c +++ b/arch/mips/dec/setup.c @@ -23,6 +23,7 @@ #include <asm/bootinfo.h> #include <asm/cpu.h> #include <asm/cpu-features.h> +#include <asm/cpu-type.h> #include <asm/irq.h> #include <asm/irq_cpu.h> #include <asm/mipsregs.h> @@ -748,6 +749,10 @@ void __init arch_init_irq(void) cpu_fpu_mask = 0; dec_interrupt[DEC_IRQ_FPU] = -1; } + /* Free the halt interrupt unused on R4k systems. */ + if (current_cpu_type() == CPU_R4000SC || + current_cpu_type() == CPU_R4400SC) + dec_interrupt[DEC_IRQ_HALT] = -1; /* Register board interrupts: FPU and cascade. */ if (dec_interrupt[DEC_IRQ_FPU] >= 0) diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index b464b8b1147a..935543f14538 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -17,26 +17,8 @@ #ifdef CONFIG_64BIT #include <asm/asmmacro-64.h> #endif -#ifdef CONFIG_MIPS_MT_SMTC -#include <asm/mipsmtregs.h> -#endif - -#ifdef CONFIG_MIPS_MT_SMTC - .macro local_irq_enable reg=t0 - mfc0 \reg, CP0_TCSTATUS - ori \reg, \reg, TCSTATUS_IXMT - xori \reg, \reg, TCSTATUS_IXMT - mtc0 \reg, CP0_TCSTATUS - _ehb - .endm - .macro local_irq_disable reg=t0 - mfc0 \reg, CP0_TCSTATUS - ori \reg, \reg, TCSTATUS_IXMT - mtc0 \reg, CP0_TCSTATUS - _ehb - .endm -#elif defined(CONFIG_CPU_MIPSR2) +#ifdef CONFIG_CPU_MIPSR2 .macro local_irq_enable reg=t0 ei irq_enable_hazard @@ -71,7 +53,7 @@ sw \reg, TI_PRE_COUNT($28) #endif .endm -#endif /* CONFIG_MIPS_MT_SMTC */ +#endif /* CONFIG_CPU_MIPSR2 */ .macro fpu_save_16even thread tmp=t0 cfc1 \tmp, fcr31 @@ -267,13 +249,35 @@ .set pop .endm #else + +#ifdef CONFIG_CPU_MICROMIPS +#define CFC_MSA_INSN 0x587e0056 +#define CTC_MSA_INSN 0x583e0816 +#define LDD_MSA_INSN 0x58000837 +#define STD_MSA_INSN 0x5800083f +#define COPY_UW_MSA_INSN 0x58f00056 +#define COPY_UD_MSA_INSN 0x58f80056 +#define INSERT_W_MSA_INSN 0x59300816 +#define INSERT_D_MSA_INSN 0x59380816 +#else +#define CFC_MSA_INSN 0x787e0059 +#define CTC_MSA_INSN 0x783e0819 +#define LDD_MSA_INSN 0x78000823 +#define STD_MSA_INSN 0x78000827 +#define COPY_UW_MSA_INSN 0x78f00059 +#define COPY_UD_MSA_INSN 0x78f80059 +#define INSERT_W_MSA_INSN 0x79300819 +#define INSERT_D_MSA_INSN 0x79380819 +#endif + /* * Temporary until all toolchains in use include MSA support. */ .macro cfcmsa rd, cs .set push .set noat - .word 0x787e0059 | (\cs << 11) + .insn + .word CFC_MSA_INSN | (\cs << 11) move \rd, $1 .set pop .endm @@ -282,7 +286,7 @@ .set push .set noat move $1, \rs - .word 0x783e0819 | (\cd << 6) + .word CTC_MSA_INSN | (\cd << 6) .set pop .endm @@ -290,7 +294,7 @@ .set push .set noat add $1, \base, \off - .word 0x78000823 | (\wd << 6) + .word LDD_MSA_INSN | (\wd << 6) .set pop .endm @@ -298,14 +302,15 @@ .set push .set noat add $1, \base, \off - .word 0x78000827 | (\wd << 6) + .word STD_MSA_INSN | (\wd << 6) .set pop .endm .macro copy_u_w rd, ws, n .set push .set noat - .word 0x78f00059 | (\n << 16) | (\ws << 11) + .insn + .word COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11) /* move triggers an assembler bug... */ or \rd, $1, zero .set pop @@ -314,7 +319,8 @@ .macro copy_u_d rd, ws, n .set push .set noat - .word 0x78f80059 | (\n << 16) | (\ws << 11) + .insn + .word COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11) /* move triggers an assembler bug... */ or \rd, $1, zero .set pop @@ -325,7 +331,7 @@ .set noat /* move triggers an assembler bug... */ or $1, \rs, zero - .word 0x79300819 | (\n << 16) | (\wd << 6) + .word INSERT_W_MSA_INSN | (\n << 16) | (\wd << 6) .set pop .endm @@ -334,7 +340,7 @@ .set noat /* move triggers an assembler bug... */ or $1, \rs, zero - .word 0x79380819 | (\n << 16) | (\wd << 6) + .word INSERT_D_MSA_INSN | (\n << 16) | (\wd << 6) .set pop .endm #endif diff --git a/arch/mips/include/asm/branch.h b/arch/mips/include/asm/branch.h index e28a3e0eb3cb..de781cf54bc7 100644 --- a/arch/mips/include/asm/branch.h +++ b/arch/mips/include/asm/branch.h @@ -8,6 +8,8 @@ #ifndef _ASM_BRANCH_H #define _ASM_BRANCH_H +#include <asm/cpu-features.h> +#include <asm/mipsregs.h> #include <asm/ptrace.h> #include <asm/inst.h> @@ -18,12 +20,40 @@ extern int __compute_return_epc_for_insn(struct pt_regs *regs, extern int __microMIPS_compute_return_epc(struct pt_regs *regs); extern int __MIPS16e_compute_return_epc(struct pt_regs *regs); +/* + * microMIPS bitfields + */ +#define MM_POOL32A_MINOR_MASK 0x3f +#define MM_POOL32A_MINOR_SHIFT 0x6 +#define MM_MIPS32_COND_FC 0x30 + +extern int __mm_isBranchInstr(struct pt_regs *regs, + struct mm_decoded_insn dec_insn, unsigned long *contpc); + +static inline int mm_isBranchInstr(struct pt_regs *regs, + struct mm_decoded_insn dec_insn, unsigned long *contpc) +{ + if (!cpu_has_mmips) + return 0; + + return __mm_isBranchInstr(regs, dec_insn, contpc); +} static inline int delay_slot(struct pt_regs *regs) { return regs->cp0_cause & CAUSEF_BD; } +static inline void clear_delay_slot(struct pt_regs *regs) +{ + regs->cp0_cause &= ~CAUSEF_BD; +} + +static inline void set_delay_slot(struct pt_regs *regs) +{ + regs->cp0_cause |= CAUSEF_BD; +} + static inline unsigned long exception_epc(struct pt_regs *regs) { if (likely(!delay_slot(regs))) diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index 69468ded2828..e08381a37f8b 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -113,6 +113,12 @@ unsigned long run_uncached(void *func); extern void *kmap_coherent(struct page *page, unsigned long addr); extern void kunmap_coherent(void); +extern void *kmap_noncoherent(struct page *page, unsigned long addr); + +static inline void kunmap_noncoherent(void) +{ + kunmap_coherent(); +} #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE static inline void flush_kernel_dcache_page(struct page *page) diff --git a/arch/mips/include/asm/cmp.h b/arch/mips/include/asm/cmp.h index 89a73fb93ae6..033d97303c85 100644 --- a/arch/mips/include/asm/cmp.h +++ b/arch/mips/include/asm/cmp.h @@ -10,7 +10,6 @@ extern void cmp_smp_setup(void); extern void cmp_smp_finish(void); extern void cmp_boot_secondary(int cpu, struct task_struct *t); extern void cmp_init_secondary(void); -extern void cmp_cpus_done(void); extern void cmp_prepare_cpus(unsigned int max_cpus); /* This is platform specific */ diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index f56cc975b92f..c7d8c997d93e 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -110,9 +110,15 @@ #ifndef cpu_has_smartmips #define cpu_has_smartmips (cpu_data[0].ases & MIPS_ASE_SMARTMIPS) #endif + #ifndef cpu_has_rixi -#define cpu_has_rixi (cpu_data[0].options & MIPS_CPU_RIXI) +# ifdef CONFIG_64BIT +# define cpu_has_rixi (cpu_data[0].options & MIPS_CPU_RIXI) +# else /* CONFIG_32BIT */ +# define cpu_has_rixi ((cpu_data[0].options & MIPS_CPU_RIXI) && !cpu_has_64bits) +# endif #endif + #ifndef cpu_has_mmips # ifdef CONFIG_SYS_SUPPORTS_MICROMIPS # define cpu_has_mmips (cpu_data[0].options & MIPS_CPU_MICROMIPS) @@ -120,6 +126,7 @@ # define cpu_has_mmips 0 # endif #endif + #ifndef cpu_has_vtag_icache #define cpu_has_vtag_icache (cpu_data[0].icache.flags & MIPS_CACHE_VTAG) #endif @@ -183,6 +190,17 @@ /* * Shortcuts ... */ +#define cpu_has_mips_2_3_4_5 (cpu_has_mips_2 | cpu_has_mips_3_4_5) +#define cpu_has_mips_3_4_5 (cpu_has_mips_3 | cpu_has_mips_4_5) +#define cpu_has_mips_4_5 (cpu_has_mips_4 | cpu_has_mips_5) + +#define cpu_has_mips_2_3_4_5_r (cpu_has_mips_2 | cpu_has_mips_3_4_5_r) +#define cpu_has_mips_3_4_5_r (cpu_has_mips_3 | cpu_has_mips_4_5_r) +#define cpu_has_mips_4_5_r (cpu_has_mips_4 | cpu_has_mips_5_r) +#define cpu_has_mips_5_r (cpu_has_mips_5 | cpu_has_mips_r) + +#define cpu_has_mips_4_5_r2 (cpu_has_mips_4_5 | cpu_has_mips_r2) + #define cpu_has_mips32 (cpu_has_mips32r1 | cpu_has_mips32r2) #define cpu_has_mips64 (cpu_has_mips64r1 | cpu_has_mips64r2) #define cpu_has_mips_r1 (cpu_has_mips32r1 | cpu_has_mips64r1) diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h index ff2707ab3295..47d5967ce7ef 100644 --- a/arch/mips/include/asm/cpu-info.h +++ b/arch/mips/include/asm/cpu-info.h @@ -65,18 +65,13 @@ struct cpuinfo_mips { #ifdef CONFIG_64BIT int vmbits; /* Virtual memory size in bits */ #endif -#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC) +#ifdef CONFIG_MIPS_MT_SMP /* - * In the MIPS MT "SMTC" model, each TC is considered - * to be a "CPU" for the purposes of scheduling, but - * exception resources, ASID spaces, etc, are common - * to all TCs within the same VPE. + * There is not necessarily a 1:1 mapping of VPE num to CPU number + * in particular on multi-core systems. */ int vpe_id; /* Virtual Processor number */ #endif -#ifdef CONFIG_MIPS_MT_SMTC - int tc_id; /* Thread Context number */ -#endif void *data; /* Additional data */ unsigned int watch_reg_count; /* Number that exist */ unsigned int watch_reg_use_cnt; /* Usable by ptrace */ @@ -117,7 +112,7 @@ struct proc_cpuinfo_notifier_args { unsigned long n; }; -#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC) +#ifdef CONFIG_MIPS_MT_SMP # define cpu_vpe_id(cpuinfo) ((cpuinfo)->vpe_id) #else # define cpu_vpe_id(cpuinfo) 0 diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index 721906130a57..b4e2bd87df50 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -155,9 +155,6 @@ static inline int __pure __get_cpu_type(const int cpu_type) case CPU_RM7000: case CPU_SR71000: #endif -#ifdef CONFIG_SYS_HAS_CPU_RM9000 - case CPU_RM9000: -#endif #ifdef CONFIG_SYS_HAS_CPU_SB1 case CPU_SB1: case CPU_SB1A: @@ -166,6 +163,7 @@ static inline int __pure __get_cpu_type(const int cpu_type) case CPU_CAVIUM_OCTEON: case CPU_CAVIUM_OCTEON_PLUS: case CPU_CAVIUM_OCTEON2: + case CPU_CAVIUM_OCTEON3: #endif #if defined(CONFIG_SYS_HAS_CPU_BMIPS32_3300) || \ diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 530eb8b3a68e..129d08701e91 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -201,6 +201,7 @@ #define PRID_IMP_NETLOGIC_XLP3XX 0x1100 #define PRID_IMP_NETLOGIC_XLP2XX 0x1200 #define PRID_IMP_NETLOGIC_XLP9XX 0x1500 +#define PRID_IMP_NETLOGIC_XLP5XX 0x1300 /* * Particular Revision values for bits 7:0 of the PRId register. @@ -281,7 +282,7 @@ enum cpu_type_enum { CPU_R4700, CPU_R5000, CPU_R5500, CPU_NEVADA, CPU_R5432, CPU_R10000, CPU_R12000, CPU_R14000, CPU_VR41XX, CPU_VR4111, CPU_VR4121, CPU_VR4122, CPU_VR4131, CPU_VR4133, CPU_VR4181, CPU_VR4181A, CPU_RM7000, - CPU_SR71000, CPU_RM9000, CPU_TX49XX, + CPU_SR71000, CPU_TX49XX, /* * R8000 class processors diff --git a/arch/mips/include/asm/dec/kn05.h b/arch/mips/include/asm/dec/kn05.h index 56d22dc8803a..8e14f677e5ef 100644 --- a/arch/mips/include/asm/dec/kn05.h +++ b/arch/mips/include/asm/dec/kn05.h @@ -49,12 +49,20 @@ #define KN4K_RES_15 (15*IOASIC_SLOT_SIZE) /* unused? */ /* + * MB ASIC interrupt bits. + */ +#define KN4K_MB_INR_MB 4 /* ??? */ +#define KN4K_MB_INR_MT 3 /* memory, I/O bus read/write errors */ +#define KN4K_MB_INR_RES_2 2 /* unused */ +#define KN4K_MB_INR_RTC 1 /* RTC */ +#define KN4K_MB_INR_TC 0 /* I/O ASIC cascade */ + +/* * Bits for the MB interrupt register. * The register appears read-only. */ -#define KN4K_MB_INT_TC (1<<0) /* TURBOchannel? */ -#define KN4K_MB_INT_RTC (1<<1) /* RTC? */ -#define KN4K_MB_INT_MT (1<<3) /* I/O ASIC cascade */ +#define KN4K_MB_INT_IRQ (0x1f<<0) /* CPU Int[4:0] status. */ +#define KN4K_MB_INT_IRQ_N(n) (1<<(n)) /* Individual status bits. */ /* * Bits for the MB control & status register. @@ -70,6 +78,7 @@ #define KN4K_MB_CSR_NC (1<<14) /* ??? */ #define KN4K_MB_CSR_EE (1<<15) /* (bus) Exception Enable? */ #define KN4K_MB_CSR_MSK (0x1f<<16) /* CPU Int[4:0] mask */ +#define KN4K_MB_CSR_MSK_N(n) (1<<((n)+16)) /* Individual mask bits. */ #define KN4K_MB_CSR_FW (1<<21) /* ??? */ #define KN4K_MB_CSR_W (1<<31) /* ??? */ diff --git a/arch/mips/include/asm/fixmap.h b/arch/mips/include/asm/fixmap.h index 8c012af2f451..6842ffafd1e7 100644 --- a/arch/mips/include/asm/fixmap.h +++ b/arch/mips/include/asm/fixmap.h @@ -48,11 +48,7 @@ enum fixed_addresses { #define FIX_N_COLOURS 8 FIX_CMAP_BEGIN, -#ifdef CONFIG_MIPS_MT_SMTC - FIX_CMAP_END = FIX_CMAP_BEGIN + (FIX_N_COLOURS * NR_CPUS * 2), -#else FIX_CMAP_END = FIX_CMAP_BEGIN + (FIX_N_COLOURS * 2), -#endif #ifdef CONFIG_HIGHMEM /* reserved pte's for temporary kernel mappings */ FIX_KMAP_BEGIN = FIX_CMAP_END + 1, diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index 4d86b72750c7..a939574f8293 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -17,6 +17,7 @@ #include <asm/mipsregs.h> #include <asm/cpu.h> #include <asm/cpu-features.h> +#include <asm/fpu_emulator.h> #include <asm/hazards.h> #include <asm/processor.h> #include <asm/current.h> @@ -28,7 +29,6 @@ struct sigcontext; struct sigcontext32; -extern void fpu_emulator_init_fpu(void); extern void _init_fpu(void); extern void _save_fp(struct task_struct *); extern void _restore_fp(struct task_struct *); @@ -156,15 +156,16 @@ static inline int init_fpu(void) int ret = 0; preempt_disable(); + if (cpu_has_fpu) { ret = __own_fpu(); if (!ret) _init_fpu(); - } else { + } else fpu_emulator_init_fpu(); - } preempt_enable(); + return ret; } diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h index 2abb587d5ab4..0195745b4b1b 100644 --- a/arch/mips/include/asm/fpu_emulator.h +++ b/arch/mips/include/asm/fpu_emulator.h @@ -23,9 +23,12 @@ #ifndef _ASM_FPU_EMULATOR_H #define _ASM_FPU_EMULATOR_H +#include <linux/sched.h> #include <asm/break.h> +#include <asm/thread_info.h> #include <asm/inst.h> #include <asm/local.h> +#include <asm/processor.h> #ifdef CONFIG_DEBUG_FS @@ -36,6 +39,11 @@ struct mips_fpu_emulator_stats { local_t cp1ops; local_t cp1xops; local_t errors; + local_t ieee754_inexact; + local_t ieee754_underflow; + local_t ieee754_overflow; + local_t ieee754_zerodiv; + local_t ieee754_invalidop; }; DECLARE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats); @@ -71,4 +79,17 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, */ #define BREAK_MATH (0x0000000d | (BRK_MEMU << 16)) +#define SIGNALLING_NAN 0x7ff800007ff80000LL + +static inline void fpu_emulator_init_fpu(void) +{ + struct task_struct *t = current; + int i; + + t->thread.fpu.fcr31 = 0; + + for (i = 0; i < 32; i++) + set_fpr64(&t->thread.fpu.fpr[i], 0, SIGNALLING_NAN); +} + #endif /* _ASM_FPU_EMULATOR_H */ diff --git a/arch/mips/include/asm/gic.h b/arch/mips/include/asm/gic.h index 082716690589..10f6a99f92c2 100644 --- a/arch/mips/include/asm/gic.h +++ b/arch/mips/include/asm/gic.h @@ -380,6 +380,7 @@ extern unsigned int gic_compare_int (void); extern cycle_t gic_read_count(void); extern cycle_t gic_read_compare(void); extern void gic_write_compare(cycle_t cnt); +extern void gic_write_cpu_compare(cycle_t cnt, int cpu); extern void gic_send_ipi(unsigned int intr); extern unsigned int plat_ipi_call_int_xlate(unsigned int); extern unsigned int plat_ipi_resched_int_xlate(unsigned int); diff --git a/arch/mips/include/asm/gio_device.h b/arch/mips/include/asm/gio_device.h index 0878701712f8..4be1a57cdbb0 100644 --- a/arch/mips/include/asm/gio_device.h +++ b/arch/mips/include/asm/gio_device.h @@ -50,7 +50,7 @@ static inline void gio_device_free(struct gio_device *dev) extern int gio_register_driver(struct gio_driver *); extern void gio_unregister_driver(struct gio_driver *); -#define gio_get_drvdata(_dev) drv_get_drvdata(&(_dev)->dev) -#define gio_set_drvdata(_dev, data) drv_set_drvdata(&(_dev)->dev, (data)) +#define gio_get_drvdata(_dev) dev_get_drvdata(&(_dev)->dev) +#define gio_set_drvdata(_dev, data) dev_set_drvdata(&(_dev)->dev, (data)) extern void gio_set_master(struct gio_device *); diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h index d192158886b1..d9f932de80e9 100644 --- a/arch/mips/include/asm/idle.h +++ b/arch/mips/include/asm/idle.h @@ -1,6 +1,7 @@ #ifndef __ASM_IDLE_H #define __ASM_IDLE_H +#include <linux/cpuidle.h> #include <linux/linkage.h> extern void (*cpu_wait)(void); @@ -20,4 +21,17 @@ static inline int address_is_in_r4k_wait_irqoff(unsigned long addr) addr < (unsigned long)__pastwait; } +extern int mips_cpuidle_wait_enter(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index); + +#define MIPS_CPUIDLE_WAIT_STATE {\ + .enter = mips_cpuidle_wait_enter,\ + .exit_latency = 1,\ + .target_residency = 1,\ + .power_usage = UINT_MAX,\ + .flags = CPUIDLE_FLAG_TIME_VALID,\ + .name = "wait",\ + .desc = "MIPS wait",\ +} + #endif /* __ASM_IDLE_H */ diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index 7bc2cdb35057..ae1f7b24dd1a 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -26,104 +26,8 @@ static inline int irq_canonicalize(int irq) #define irq_canonicalize(irq) (irq) /* Sane hardware, sane code ... */ #endif -#ifdef CONFIG_MIPS_MT_SMTC - -struct irqaction; - -extern unsigned long irq_hwmask[]; -extern int setup_irq_smtc(unsigned int irq, struct irqaction * new, - unsigned long hwmask); - -static inline void smtc_im_ack_irq(unsigned int irq) -{ - if (irq_hwmask[irq] & ST0_IM) - set_c0_status(irq_hwmask[irq] & ST0_IM); -} - -#else - -static inline void smtc_im_ack_irq(unsigned int irq) -{ -} - -#endif /* CONFIG_MIPS_MT_SMTC */ - -#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF -#include <linux/cpumask.h> - -extern int plat_set_irq_affinity(struct irq_data *d, - const struct cpumask *affinity, bool force); -extern void smtc_forward_irq(struct irq_data *d); - -/* - * IRQ affinity hook invoked at the beginning of interrupt dispatch - * if option is enabled. - * - * Up through Linux 2.6.22 (at least) cpumask operations are very - * inefficient on MIPS. Initial prototypes of SMTC IRQ affinity - * used a "fast path" per-IRQ-descriptor cache of affinity information - * to reduce latency. As there is a project afoot to optimize the - * cpumask implementations, this version is optimistically assuming - * that cpumask.h macro overhead is reasonable during interrupt dispatch. - */ -static inline int handle_on_other_cpu(unsigned int irq) -{ - struct irq_data *d = irq_get_irq_data(irq); - - if (cpumask_test_cpu(smp_processor_id(), d->affinity)) - return 0; - smtc_forward_irq(d); - return 1; -} - -#else /* Not doing SMTC affinity */ - -static inline int handle_on_other_cpu(unsigned int irq) { return 0; } - -#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ - -#ifdef CONFIG_MIPS_MT_SMTC_IM_BACKSTOP - -static inline void smtc_im_backstop(unsigned int irq) -{ - if (irq_hwmask[irq] & 0x0000ff00) - write_c0_tccontext(read_c0_tccontext() & - ~(irq_hwmask[irq] & 0x0000ff00)); -} - -/* - * Clear interrupt mask handling "backstop" if irq_hwmask - * entry so indicates. This implies that the ack() or end() - * functions will take over re-enabling the low-level mask. - * Otherwise it will be done on return from exception. - */ -static inline int smtc_handle_on_other_cpu(unsigned int irq) -{ - int ret = handle_on_other_cpu(irq); - - if (!ret) - smtc_im_backstop(irq); - return ret; -} - -#else - -static inline void smtc_im_backstop(unsigned int irq) { } -static inline int smtc_handle_on_other_cpu(unsigned int irq) -{ - return handle_on_other_cpu(irq); -} - -#endif - extern void do_IRQ(unsigned int irq); -#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF - -extern void do_IRQ_no_affinity(unsigned int irq); - -#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ - extern void arch_init_irq(void); extern void spurious_interrupt(void); diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h index 45c00951888b..0fa5fdcd1f01 100644 --- a/arch/mips/include/asm/irqflags.h +++ b/arch/mips/include/asm/irqflags.h @@ -17,7 +17,7 @@ #include <linux/stringify.h> #include <asm/hazards.h> -#if defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_MIPS_MT_SMTC) +#ifdef CONFIG_CPU_MIPSR2 static inline void arch_local_irq_disable(void) { @@ -118,30 +118,15 @@ void arch_local_irq_disable(void); unsigned long arch_local_irq_save(void); void arch_local_irq_restore(unsigned long flags); void __arch_local_irq_restore(unsigned long flags); -#endif /* if defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_MIPS_MT_SMTC) */ - - -extern void smtc_ipi_replay(void); +#endif /* CONFIG_CPU_MIPSR2 */ static inline void arch_local_irq_enable(void) { -#ifdef CONFIG_MIPS_MT_SMTC - /* - * SMTC kernel needs to do a software replay of queued - * IPIs, at the cost of call overhead on each local_irq_enable() - */ - smtc_ipi_replay(); -#endif __asm__ __volatile__( " .set push \n" " .set reorder \n" " .set noat \n" -#ifdef CONFIG_MIPS_MT_SMTC - " mfc0 $1, $2, 1 # SMTC - clear TCStatus.IXMT \n" - " ori $1, 0x400 \n" - " xori $1, 0x400 \n" - " mtc0 $1, $2, 1 \n" -#elif defined(CONFIG_CPU_MIPSR2) +#if defined(CONFIG_CPU_MIPSR2) " ei \n" #else " mfc0 $1,$12 \n" @@ -163,11 +148,7 @@ static inline unsigned long arch_local_save_flags(void) asm __volatile__( " .set push \n" " .set reorder \n" -#ifdef CONFIG_MIPS_MT_SMTC - " mfc0 %[flags], $2, 1 \n" -#else " mfc0 %[flags], $12 \n" -#endif " .set pop \n" : [flags] "=r" (flags)); @@ -177,14 +158,7 @@ static inline unsigned long arch_local_save_flags(void) static inline int arch_irqs_disabled_flags(unsigned long flags) { -#ifdef CONFIG_MIPS_MT_SMTC - /* - * SMTC model uses TCStatus.IXMT to disable interrupts for a thread/CPU - */ - return flags & 0x400; -#else return !(flags & 1); -#endif } #endif /* #ifndef __ASSEMBLY__ */ diff --git a/arch/mips/include/asm/kvm_para.h b/arch/mips/include/asm/kvm_para.h new file mode 100644 index 000000000000..5a9aa918abe6 --- /dev/null +++ b/arch/mips/include/asm/kvm_para.h @@ -0,0 +1,109 @@ +#ifndef _ASM_MIPS_KVM_PARA_H +#define _ASM_MIPS_KVM_PARA_H + +#include <uapi/asm/kvm_para.h> + +#define KVM_HYPERCALL ".word 0x42000028" + +/* + * Hypercalls for KVM. + * + * Hypercall number is passed in v0. + * Return value will be placed in v0. + * Up to 3 arguments are passed in a0, a1, and a2. + */ +static inline unsigned long kvm_hypercall0(unsigned long num) +{ + register unsigned long n asm("v0"); + register unsigned long r asm("v0"); + + n = num; + __asm__ __volatile__( + KVM_HYPERCALL + : "=r" (r) : "r" (n) : "memory" + ); + + return r; +} + +static inline unsigned long kvm_hypercall1(unsigned long num, + unsigned long arg0) +{ + register unsigned long n asm("v0"); + register unsigned long r asm("v0"); + register unsigned long a0 asm("a0"); + + n = num; + a0 = arg0; + __asm__ __volatile__( + KVM_HYPERCALL + : "=r" (r) : "r" (n), "r" (a0) : "memory" + ); + + return r; +} + +static inline unsigned long kvm_hypercall2(unsigned long num, + unsigned long arg0, unsigned long arg1) +{ + register unsigned long n asm("v0"); + register unsigned long r asm("v0"); + register unsigned long a0 asm("a0"); + register unsigned long a1 asm("a1"); + + n = num; + a0 = arg0; + a1 = arg1; + __asm__ __volatile__( + KVM_HYPERCALL + : "=r" (r) : "r" (n), "r" (a0), "r" (a1) : "memory" + ); + + return r; +} + +static inline unsigned long kvm_hypercall3(unsigned long num, + unsigned long arg0, unsigned long arg1, unsigned long arg2) +{ + register unsigned long n asm("v0"); + register unsigned long r asm("v0"); + register unsigned long a0 asm("a0"); + register unsigned long a1 asm("a1"); + register unsigned long a2 asm("a2"); + + n = num; + a0 = arg0; + a1 = arg1; + a2 = arg2; + __asm__ __volatile__( + KVM_HYPERCALL + : "=r" (r) : "r" (n), "r" (a0), "r" (a1), "r" (a2) : "memory" + ); + + return r; +} + +static inline bool kvm_check_and_clear_guest_paused(void) +{ + return false; +} + +static inline unsigned int kvm_arch_para_features(void) +{ + return 0; +} + +#ifdef CONFIG_MIPS_PARAVIRT +static inline bool kvm_para_available(void) +{ + return true; +} +#else +static inline bool kvm_para_available(void) +{ + return false; +} +#endif + + +#endif /* _ASM_MIPS_KVM_PARA_H */ diff --git a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h index 94ed063eec92..cf8022872892 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h @@ -22,7 +22,6 @@ #define cpu_has_3k_cache 0 #define cpu_has_4k_cache 0 #define cpu_has_tx39_cache 0 -#define cpu_has_fpu 0 #define cpu_has_counter 1 #define cpu_has_watch 1 #define cpu_has_divec 1 diff --git a/arch/mips/include/asm/mach-cavium-octeon/irq.h b/arch/mips/include/asm/mach-cavium-octeon/irq.h index 60fc4c347c44..cceae32a0732 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/irq.h +++ b/arch/mips/include/asm/mach-cavium-octeon/irq.h @@ -35,6 +35,8 @@ enum octeon_irq { OCTEON_IRQ_PCI_MSI2, OCTEON_IRQ_PCI_MSI3, + OCTEON_IRQ_TWSI, + OCTEON_IRQ_TWSI2, OCTEON_IRQ_RML, OCTEON_IRQ_TIMER0, OCTEON_IRQ_TIMER1, diff --git a/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h index 1bcb6421205e..1dfe47453ea4 100644 --- a/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h @@ -39,6 +39,10 @@ #define cpu_has_nofpuex 0 #define cpu_has_64bits 1 +#define cpu_has_mips_2 1 +#define cpu_has_mips_3 1 +#define cpu_has_mips_5 0 + #define cpu_has_mips32r1 0 #define cpu_has_mips32r2 0 #define cpu_has_mips64r1 0 diff --git a/arch/mips/include/asm/mach-jz4740/dma.h b/arch/mips/include/asm/mach-jz4740/dma.h index 509cd5828044..14ecc5313d2d 100644 --- a/arch/mips/include/asm/mach-jz4740/dma.h +++ b/arch/mips/include/asm/mach-jz4740/dma.h @@ -22,8 +22,6 @@ enum jz4740_dma_request_type { JZ4740_DMA_TYPE_UART_RECEIVE = 21, JZ4740_DMA_TYPE_SPI_TRANSMIT = 22, JZ4740_DMA_TYPE_SPI_RECEIVE = 23, - JZ4740_DMA_TYPE_AIC_TRANSMIT = 24, - JZ4740_DMA_TYPE_AIC_RECEIVE = 25, JZ4740_DMA_TYPE_MMC_TRANSMIT = 26, JZ4740_DMA_TYPE_MMC_RECEIVE = 27, JZ4740_DMA_TYPE_TCU = 28, diff --git a/arch/mips/include/asm/mach-malta/kernel-entry-init.h b/arch/mips/include/asm/mach-malta/kernel-entry-init.h index 7c5e17a17849..77eeda77e73c 100644 --- a/arch/mips/include/asm/mach-malta/kernel-entry-init.h +++ b/arch/mips/include/asm/mach-malta/kernel-entry-init.h @@ -80,36 +80,6 @@ .endm .macro kernel_entry_setup -#ifdef CONFIG_MIPS_MT_SMTC - mfc0 t0, CP0_CONFIG - bgez t0, 9f - mfc0 t0, CP0_CONFIG, 1 - bgez t0, 9f - mfc0 t0, CP0_CONFIG, 2 - bgez t0, 9f - mfc0 t0, CP0_CONFIG, 3 - and t0, 1<<2 - bnez t0, 0f -9: - /* Assume we came from YAMON... */ - PTR_LA v0, 0x9fc00534 /* YAMON print */ - lw v0, (v0) - move a0, zero - PTR_LA a1, nonmt_processor - jal v0 - - PTR_LA v0, 0x9fc00520 /* YAMON exit */ - lw v0, (v0) - li a0, 1 - jal v0 - -1: b 1b - - __INITDATA -nonmt_processor: - .asciz "SMTC kernel requires the MT ASE to run\n" - __FINIT -#endif #ifdef CONFIG_EVA sync diff --git a/arch/mips/include/asm/mach-malta/malta-pm.h b/arch/mips/include/asm/mach-malta/malta-pm.h new file mode 100644 index 000000000000..c2c2e201013d --- /dev/null +++ b/arch/mips/include/asm/mach-malta/malta-pm.h @@ -0,0 +1,37 @@ +/* + * Copyright (C) 2014 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __ASM_MIPS_MACH_MALTA_PM_H__ +#define __ASM_MIPS_MACH_MALTA_PM_H__ + +#include <asm/mips-boards/piix4.h> + +#ifdef CONFIG_MIPS_MALTA_PM + +/** + * mips_pm_suspend - enter a suspend state + * @state: the state to enter, one of PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_* + * + * Enters a suspend state via the Malta's PIIX4. If the state to be entered + * is one which loses context (eg. SOFF) then this function will never + * return. + */ +extern int mips_pm_suspend(unsigned state); + +#else /* !CONFIG_MIPS_MALTA_PM */ + +static inline int mips_pm_suspend(unsigned state) +{ + return -EINVAL; +} + +#endif /* !CONFIG_MIPS_MALTA_PM */ + +#endif /* __ASM_MIPS_MACH_MALTA_PM_H__ */ diff --git a/arch/mips/include/asm/mach-netlogic/topology.h b/arch/mips/include/asm/mach-netlogic/topology.h index 0da99fa11c38..ceeb1f5e7129 100644 --- a/arch/mips/include/asm/mach-netlogic/topology.h +++ b/arch/mips/include/asm/mach-netlogic/topology.h @@ -10,10 +10,12 @@ #include <asm/mach-netlogic/multi-node.h> +#ifdef CONFIG_SMP #define topology_physical_package_id(cpu) cpu_to_node(cpu) #define topology_core_id(cpu) (cpu_logical_map(cpu) / NLM_THREADS_PER_CORE) #define topology_thread_cpumask(cpu) (&cpu_sibling_map[cpu]) #define topology_core_cpumask(cpu) cpumask_of_node(cpu_to_node(cpu)) +#endif #include <asm-generic/topology.h> diff --git a/arch/mips/include/asm/mach-paravirt/cpu-feature-overrides.h b/arch/mips/include/asm/mach-paravirt/cpu-feature-overrides.h new file mode 100644 index 000000000000..725e1ed83f6a --- /dev/null +++ b/arch/mips/include/asm/mach-paravirt/cpu-feature-overrides.h @@ -0,0 +1,36 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2013 Cavium, Inc. + */ +#ifndef __ASM_MACH_PARAVIRT_CPU_FEATURE_OVERRIDES_H +#define __ASM_MACH_PARAVIRT_CPU_FEATURE_OVERRIDES_H + +#define cpu_has_4kex 1 +#define cpu_has_3k_cache 0 +#define cpu_has_tx39_cache 0 +#define cpu_has_counter 1 +#define cpu_has_llsc 1 +/* + * We Disable LL/SC on non SMP systems as it is faster to disable + * interrupts for atomic access than a LL/SC. + */ +#ifdef CONFIG_SMP +# define kernel_uses_llsc 1 +#else +# define kernel_uses_llsc 0 +#endif + +#ifdef CONFIG_CPU_CAVIUM_OCTEON +#define cpu_dcache_line_size() 128 +#define cpu_icache_line_size() 128 +#define cpu_has_octeon_cache 1 +#define cpu_has_4k_cache 0 +#else +#define cpu_has_octeon_cache 0 +#define cpu_has_4k_cache 1 +#endif + +#endif /* __ASM_MACH_PARAVIRT_CPU_FEATURE_OVERRIDES_H */ diff --git a/arch/mips/include/asm/mach-paravirt/irq.h b/arch/mips/include/asm/mach-paravirt/irq.h new file mode 100644 index 000000000000..9b4d35eca977 --- /dev/null +++ b/arch/mips/include/asm/mach-paravirt/irq.h @@ -0,0 +1,19 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2013 Cavium, Inc. + */ +#ifndef __ASM_MACH_PARAVIRT_IRQ_H__ +#define __ASM_MACH_PARAVIRT_IRQ_H__ + +#define NR_IRQS 64 +#define MIPS_CPU_IRQ_BASE 1 + +#define MIPS_IRQ_PCIA (MIPS_CPU_IRQ_BASE + 8) + +#define MIPS_IRQ_MBOX0 (MIPS_CPU_IRQ_BASE + 32) +#define MIPS_IRQ_MBOX1 (MIPS_CPU_IRQ_BASE + 33) + +#endif /* __ASM_MACH_PARAVIRT_IRQ_H__ */ diff --git a/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h new file mode 100644 index 000000000000..2f82bfa3a773 --- /dev/null +++ b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h @@ -0,0 +1,50 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2013 Cavium, Inc + */ +#ifndef __ASM_MACH_PARAVIRT_KERNEL_ENTRY_H +#define __ASM_MACH_PARAVIRT_KERNEL_ENTRY_H + +#define CP0_EBASE $15, 1 + + .macro kernel_entry_setup + mfc0 t0, CP0_EBASE + andi t0, t0, 0x3ff # CPUNum + beqz t0, 1f + # CPUs other than zero goto smp_bootstrap + j smp_bootstrap + +1: + .endm + +/* + * Do SMP slave processor setup necessary before we can safely execute + * C code. + */ + .macro smp_slave_setup + mfc0 t0, CP0_EBASE + andi t0, t0, 0x3ff # CPUNum + slti t1, t0, NR_CPUS + bnez t1, 1f +2: + di + wait + b 2b # Unknown CPU, loop forever. +1: + PTR_LA t1, paravirt_smp_sp + PTR_SLL t0, PTR_SCALESHIFT + PTR_ADDU t1, t1, t0 +3: + PTR_L sp, 0(t1) + beqz sp, 3b # Spin until told to proceed. + + PTR_LA t1, paravirt_smp_gp + PTR_ADDU t1, t1, t0 + sync + PTR_L gp, 0(t1) + .endm + +#endif /* __ASM_MACH_PARAVIRT_KERNEL_ENTRY_H */ diff --git a/arch/mips/include/asm/mach-paravirt/war.h b/arch/mips/include/asm/mach-paravirt/war.h new file mode 100644 index 000000000000..36d3afb98451 --- /dev/null +++ b/arch/mips/include/asm/mach-paravirt/war.h @@ -0,0 +1,25 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2002, 2004, 2007 by Ralf Baechle <ralf@linux-mips.org> + * Copyright (C) 2013 Cavium Networks <support@caviumnetworks.com> + */ +#ifndef __ASM_MIPS_MACH_PARAVIRT_WAR_H +#define __ASM_MIPS_MACH_PARAVIRT_WAR_H + +#define R4600_V1_INDEX_ICACHEOP_WAR 0 +#define R4600_V1_HIT_CACHEOP_WAR 0 +#define R4600_V2_HIT_CACHEOP_WAR 0 +#define R5432_CP0_INTERRUPT_WAR 0 +#define BCM1250_M3_WAR 0 +#define SIBYTE_1956_WAR 0 +#define MIPS4K_ICACHE_REFILL_WAR 0 +#define MIPS_CACHE_SYNC_WAR 0 +#define TX49XX_ICACHE_INDEX_INV_WAR 0 +#define ICACHE_REFILLS_WORKAROUND_WAR 0 +#define R10000_LLSC_WAR 0 +#define MIPS34K_MISSED_ITLB_WAR 0 + +#endif /* __ASM_MIPS_MACH_PARAVIRT_WAR_H */ diff --git a/arch/mips/include/asm/mach-pmcs-msp71xx/msp_usb.h b/arch/mips/include/asm/mach-pmcs-msp71xx/msp_usb.h index aa45e6a07126..fe1566f2913e 100644 --- a/arch/mips/include/asm/mach-pmcs-msp71xx/msp_usb.h +++ b/arch/mips/include/asm/mach-pmcs-msp71xx/msp_usb.h @@ -25,11 +25,7 @@ #ifndef MSP_USB_H_ #define MSP_USB_H_ -#ifdef CONFIG_MSP_HAS_DUAL_USB -#define NUM_USB_DEVS 2 -#else #define NUM_USB_DEVS 1 -#endif /* Register spaces for USB host 0 */ #define MSP_USB0_MAB_START (MSP_USB0_BASE + 0x0) diff --git a/arch/mips/include/asm/mach-ralink/war.h b/arch/mips/include/asm/mach-ralink/war.h index a7b712cf2d28..c074b5dc1f82 100644 --- a/arch/mips/include/asm/mach-ralink/war.h +++ b/arch/mips/include/asm/mach-ralink/war.h @@ -17,7 +17,6 @@ #define MIPS4K_ICACHE_REFILL_WAR 0 #define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 -#define RM9000_CDEX_SMP_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-sead3/kernel-entry-init.h b/arch/mips/include/asm/mach-sead3/kernel-entry-init.h index 3dfbd8e7947f..6cccd4d558d7 100644 --- a/arch/mips/include/asm/mach-sead3/kernel-entry-init.h +++ b/arch/mips/include/asm/mach-sead3/kernel-entry-init.h @@ -10,37 +10,6 @@ #define __ASM_MACH_MIPS_KERNEL_ENTRY_INIT_H .macro kernel_entry_setup -#ifdef CONFIG_MIPS_MT_SMTC - mfc0 t0, CP0_CONFIG - bgez t0, 9f - mfc0 t0, CP0_CONFIG, 1 - bgez t0, 9f - mfc0 t0, CP0_CONFIG, 2 - bgez t0, 9f - mfc0 t0, CP0_CONFIG, 3 - and t0, 1<<2 - bnez t0, 0f -9 : - /* Assume we came from YAMON... */ - PTR_LA v0, 0x9fc00534 /* YAMON print */ - lw v0, (v0) - move a0, zero - PTR_LA a1, nonmt_processor - jal v0 - - PTR_LA v0, 0x9fc00520 /* YAMON exit */ - lw v0, (v0) - li a0, 1 - jal v0 - -1 : b 1b - - __INITDATA -nonmt_processor : - .asciz "SMTC kernel requires the MT ASE to run\n" - __FINIT -0 : -#endif .endm /* diff --git a/arch/mips/include/asm/mips-boards/generic.h b/arch/mips/include/asm/mips-boards/generic.h index 48616816bcbc..c904c24550f6 100644 --- a/arch/mips/include/asm/mips-boards/generic.h +++ b/arch/mips/include/asm/mips-boards/generic.h @@ -67,10 +67,6 @@ extern int mips_revision_sconid; -#ifdef CONFIG_OF -extern struct boot_param_header __dtb_start; -#endif - #ifdef CONFIG_PCI extern void mips_pcibios_init(void); #else diff --git a/arch/mips/include/asm/mips-boards/piix4.h b/arch/mips/include/asm/mips-boards/piix4.h index 9cf54041d416..9e340be52a50 100644 --- a/arch/mips/include/asm/mips-boards/piix4.h +++ b/arch/mips/include/asm/mips-boards/piix4.h @@ -55,4 +55,16 @@ #define PIIX4_FUNC3_PMREGMISC 0x80 #define PIIX4_FUNC3_PMREGMISC_EN (1 << 0) +/* Power Management IO Space */ +#define PIIX4_FUNC3IO_PMSTS 0x00 +#define PIIX4_FUNC3IO_PMSTS_PWRBTN_STS (1 << 8) +#define PIIX4_FUNC3IO_PMCNTRL 0x04 +#define PIIX4_FUNC3IO_PMCNTRL_SUS_EN (1 << 13) +#define PIIX4_FUNC3IO_PMCNTRL_SUS_TYP (0x7 << 10) +#define PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_SOFF (0x0 << 10) +#define PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_STR (0x1 << 10) + +/* Data for magic special PCI cycle */ +#define PIIX4_SUSPEND_MAGIC 0x00120002 + #endif /* __ASM_MIPS_BOARDS_PIIX4_H */ diff --git a/arch/mips/include/asm/mips-cpc.h b/arch/mips/include/asm/mips-cpc.h index 988507e46d42..e139a534e0fd 100644 --- a/arch/mips/include/asm/mips-cpc.h +++ b/arch/mips/include/asm/mips-cpc.h @@ -72,7 +72,12 @@ static inline bool mips_cpc_present(void) #define MIPS_CPC_COCB_OFS 0x4000 /* Macros to ease the creation of register access functions */ -#define BUILD_CPC_R_(name, off) \ +#define BUILD_CPC_R_(name, off) \ +static inline u32 *addr_cpc_##name(void) \ +{ \ + return (u32 *)(mips_cpc_base + (off)); \ +} \ + \ static inline u32 read_cpc_##name(void) \ { \ return __raw_readl(mips_cpc_base + (off)); \ @@ -147,4 +152,31 @@ BUILD_CPC_Cx_RW(other, 0x10) #define CPC_Cx_OTHER_CORENUM_SHF 16 #define CPC_Cx_OTHER_CORENUM_MSK (_ULCAST_(0xff) << 16) +#ifdef CONFIG_MIPS_CPC + +/** + * mips_cpc_lock_other - lock access to another core + * core: the other core to be accessed + * + * Call before operating upon a core via the 'other' register region in + * order to prevent the region being moved during access. Must be followed + * by a call to mips_cpc_unlock_other. + */ +extern void mips_cpc_lock_other(unsigned int core); + +/** + * mips_cpc_unlock_other - unlock access to another core + * + * Call after operating upon another core via the 'other' register region. + * Must be called after mips_cpc_lock_other. + */ +extern void mips_cpc_unlock_other(void); + +#else /* !CONFIG_MIPS_CPC */ + +static inline void mips_cpc_lock_other(unsigned int core) { } +static inline void mips_cpc_unlock_other(void) { } + +#endif /* !CONFIG_MIPS_CPC */ + #endif /* __MIPS_ASM_MIPS_CPC_H__ */ diff --git a/arch/mips/include/asm/mips_mt.h b/arch/mips/include/asm/mips_mt.h index a3df0c3faa0e..f6ba004a7711 100644 --- a/arch/mips/include/asm/mips_mt.h +++ b/arch/mips/include/asm/mips_mt.h @@ -1,7 +1,6 @@ /* - * Definitions and decalrations for MIPS MT support - * that are common between SMTC, VSMP, and/or AP/SP - * kernel models. + * Definitions and decalrations for MIPS MT support that are common between + * the VSMP, and AP/SP kernel models. */ #ifndef __ASM_MIPS_MT_H #define __ASM_MIPS_MT_H diff --git a/arch/mips/include/asm/mipsmtregs.h b/arch/mips/include/asm/mipsmtregs.h index 6efa79a27b6a..5f8052ce43bf 100644 --- a/arch/mips/include/asm/mipsmtregs.h +++ b/arch/mips/include/asm/mipsmtregs.h @@ -36,6 +36,8 @@ #define read_c0_tcbind() __read_32bit_c0_register($2, 2) +#define write_c0_tchalt(val) __write_32bit_c0_register($2, 4, val) + #define read_c0_tccontext() __read_32bit_c0_register($2, 5) #define write_c0_tccontext(val) __write_32bit_c0_register($2, 5, val) diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 3e025b5311db..98e9754a4b6b 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -709,11 +709,18 @@ #ifndef __ASSEMBLY__ /* - * Macros for handling the ISA mode bit for microMIPS. + * Macros for handling the ISA mode bit for MIPS16 and microMIPS. */ +#if defined(CONFIG_SYS_SUPPORTS_MIPS16) || \ + defined(CONFIG_SYS_SUPPORTS_MICROMIPS) #define get_isa16_mode(x) ((x) & 0x1) #define msk_isa16_mode(x) ((x) & ~0x1) #define set_isa16_mode(x) do { (x) |= 0x1; } while(0) +#else +#define get_isa16_mode(x) 0 +#define msk_isa16_mode(x) (x) +#define set_isa16_mode(x) do { } while(0) +#endif /* * microMIPS instructions can be 16-bit or 32-bit in length. This @@ -1007,19 +1014,8 @@ do { \ #define write_c0_compare3(val) __write_32bit_c0_register($11, 7, val) #define read_c0_status() __read_32bit_c0_register($12, 0) -#ifdef CONFIG_MIPS_MT_SMTC -#define write_c0_status(val) \ -do { \ - __write_32bit_c0_register($12, 0, val); \ - __ehb(); \ -} while (0) -#else -/* - * Legacy non-SMTC code, which may be hazardous - * but which might not support EHB - */ + #define write_c0_status(val) __write_32bit_c0_register($12, 0, val) -#endif /* CONFIG_MIPS_MT_SMTC */ #define read_c0_cause() __read_32bit_c0_register($13, 0) #define write_c0_cause(val) __write_32bit_c0_register($13, 0, val) @@ -1743,11 +1739,6 @@ static inline void tlb_write_random(void) /* * Manipulate bits in a c0 register. */ -#ifndef CONFIG_MIPS_MT_SMTC -/* - * SMTC Linux requires shutting-down microthread scheduling - * during CP0 register read-modify-write sequences. - */ #define __BUILD_SET_C0(name) \ static inline unsigned int \ set_c0_##name(unsigned int set) \ @@ -1786,121 +1777,6 @@ change_c0_##name(unsigned int change, unsigned int val) \ return res; \ } -#else /* SMTC versions that manage MT scheduling */ - -#include <linux/irqflags.h> - -/* - * This is a duplicate of dmt() in mipsmtregs.h to avoid problems with - * header file recursion. - */ -static inline unsigned int __dmt(void) -{ - int res; - - __asm__ __volatile__( - " .set push \n" - " .set mips32r2 \n" - " .set noat \n" - " .word 0x41610BC1 # dmt $1 \n" - " ehb \n" - " move %0, $1 \n" - " .set pop \n" - : "=r" (res)); - - instruction_hazard(); - - return res; -} - -#define __VPECONTROL_TE_SHIFT 15 -#define __VPECONTROL_TE (1UL << __VPECONTROL_TE_SHIFT) - -#define __EMT_ENABLE __VPECONTROL_TE - -static inline void __emt(unsigned int previous) -{ - if ((previous & __EMT_ENABLE)) - __asm__ __volatile__( - " .set mips32r2 \n" - " .word 0x41600be1 # emt \n" - " ehb \n" - " .set mips0 \n"); -} - -static inline void __ehb(void) -{ - __asm__ __volatile__( - " .set mips32r2 \n" - " ehb \n" " .set mips0 \n"); -} - -/* - * Note that local_irq_save/restore affect TC-specific IXMT state, - * not Status.IE as in non-SMTC kernel. - */ - -#define __BUILD_SET_C0(name) \ -static inline unsigned int \ -set_c0_##name(unsigned int set) \ -{ \ - unsigned int res; \ - unsigned int new; \ - unsigned int omt; \ - unsigned long flags; \ - \ - local_irq_save(flags); \ - omt = __dmt(); \ - res = read_c0_##name(); \ - new = res | set; \ - write_c0_##name(new); \ - __emt(omt); \ - local_irq_restore(flags); \ - \ - return res; \ -} \ - \ -static inline unsigned int \ -clear_c0_##name(unsigned int clear) \ -{ \ - unsigned int res; \ - unsigned int new; \ - unsigned int omt; \ - unsigned long flags; \ - \ - local_irq_save(flags); \ - omt = __dmt(); \ - res = read_c0_##name(); \ - new = res & ~clear; \ - write_c0_##name(new); \ - __emt(omt); \ - local_irq_restore(flags); \ - \ - return res; \ -} \ - \ -static inline unsigned int \ -change_c0_##name(unsigned int change, unsigned int newbits) \ -{ \ - unsigned int res; \ - unsigned int new; \ - unsigned int omt; \ - unsigned long flags; \ - \ - local_irq_save(flags); \ - \ - omt = __dmt(); \ - res = read_c0_##name(); \ - new = res & ~change; \ - new |= (newbits & change); \ - write_c0_##name(new); \ - __emt(omt); \ - local_irq_restore(flags); \ - \ - return res; \ -} -#endif - __BUILD_SET_C0(status) __BUILD_SET_C0(cause) __BUILD_SET_C0(config) @@ -1916,6 +1792,15 @@ __BUILD_SET_C0(brcm_cmt_ctrl) __BUILD_SET_C0(brcm_config) __BUILD_SET_C0(brcm_mode) +/* + * Return low 10 bits of ebase. + * Note that under KVM (MIPSVZ) this returns vcpu id. + */ +static inline unsigned int get_ebase_cpunum(void) +{ + return read_c0_ebase() & 0x3ff; +} + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_MIPSREGS_H */ diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h index e277bbad2871..2e373da5f8e9 100644 --- a/arch/mips/include/asm/mmu_context.h +++ b/arch/mips/include/asm/mmu_context.h @@ -18,10 +18,6 @@ #include <asm/cacheflush.h> #include <asm/hazards.h> #include <asm/tlbflush.h> -#ifdef CONFIG_MIPS_MT_SMTC -#include <asm/mipsmtregs.h> -#include <asm/smtc.h> -#endif /* SMTC */ #include <asm-generic/mm_hooks.h> #define TLBMISS_HANDLER_SETUP_PGD(pgd) \ @@ -31,11 +27,15 @@ do { \ } while (0) #ifdef CONFIG_MIPS_PGD_C0_CONTEXT + +#define TLBMISS_HANDLER_RESTORE() \ + write_c0_xcontext((unsigned long) smp_processor_id() << \ + SMP_CPUID_REGSHIFT) + #define TLBMISS_HANDLER_SETUP() \ do { \ TLBMISS_HANDLER_SETUP_PGD(swapper_pg_dir); \ - write_c0_xcontext((unsigned long) smp_processor_id() << \ - SMP_CPUID_REGSHIFT); \ + TLBMISS_HANDLER_RESTORE(); \ } while (0) #else /* !CONFIG_MIPS_PGD_C0_CONTEXT: using pgd_current*/ @@ -47,9 +47,12 @@ do { \ */ extern unsigned long pgd_current[]; -#define TLBMISS_HANDLER_SETUP() \ +#define TLBMISS_HANDLER_RESTORE() \ write_c0_context((unsigned long) smp_processor_id() << \ - SMP_CPUID_REGSHIFT); \ + SMP_CPUID_REGSHIFT) + +#define TLBMISS_HANDLER_SETUP() \ + TLBMISS_HANDLER_RESTORE(); \ back_to_back_c0_hazard(); \ TLBMISS_HANDLER_SETUP_PGD(swapper_pg_dir) #endif /* CONFIG_MIPS_PGD_C0_CONTEXT*/ @@ -63,13 +66,6 @@ extern unsigned long pgd_current[]; #define ASID_INC 0x10 #define ASID_MASK 0xff0 -#elif defined(CONFIG_MIPS_MT_SMTC) - -#define ASID_INC 0x1 -extern unsigned long smtc_asid_mask; -#define ASID_MASK (smtc_asid_mask) -#define HW_ASID_MASK 0xff -/* End SMTC/34K debug hack */ #else /* FIXME: not correct for R6000 */ #define ASID_INC 0x1 @@ -92,7 +88,6 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) #define ASID_VERSION_MASK ((unsigned long)~(ASID_MASK|(ASID_MASK-1))) #define ASID_FIRST_VERSION ((unsigned long)(~ASID_VERSION_MASK) + 1) -#ifndef CONFIG_MIPS_MT_SMTC /* Normal, classic MIPS get_new_mmu_context */ static inline void get_new_mmu_context(struct mm_struct *mm, unsigned long cpu) @@ -115,12 +110,6 @@ get_new_mmu_context(struct mm_struct *mm, unsigned long cpu) cpu_context(cpu, mm) = asid_cache(cpu) = asid; } -#else /* CONFIG_MIPS_MT_SMTC */ - -#define get_new_mmu_context(mm, cpu) smtc_get_new_mmu_context((mm), (cpu)) - -#endif /* CONFIG_MIPS_MT_SMTC */ - /* * Initialize the context related info for a new mm_struct * instance. @@ -141,46 +130,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, { unsigned int cpu = smp_processor_id(); unsigned long flags; -#ifdef CONFIG_MIPS_MT_SMTC - unsigned long oldasid; - unsigned long mtflags; - int mytlb = (smtc_status & SMTC_TLB_SHARED) ? 0 : cpu_data[cpu].vpe_id; local_irq_save(flags); - mtflags = dvpe(); -#else /* Not SMTC */ - local_irq_save(flags); -#endif /* CONFIG_MIPS_MT_SMTC */ /* Check if our ASID is of an older version and thus invalid */ if ((cpu_context(cpu, next) ^ asid_cache(cpu)) & ASID_VERSION_MASK) get_new_mmu_context(next, cpu); -#ifdef CONFIG_MIPS_MT_SMTC - /* - * If the EntryHi ASID being replaced happens to be - * the value flagged at ASID recycling time as having - * an extended life, clear the bit showing it being - * in use by this "CPU", and if that's the last bit, - * free up the ASID value for use and flush any old - * instances of it from the TLB. - */ - oldasid = (read_c0_entryhi() & ASID_MASK); - if(smtc_live_asid[mytlb][oldasid]) { - smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu); - if(smtc_live_asid[mytlb][oldasid] == 0) - smtc_flush_tlb_asid(oldasid); - } - /* - * Tread softly on EntryHi, and so long as we support - * having ASID_MASK smaller than the hardware maximum, - * make sure no "soft" bits become "hard"... - */ - write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK) | - cpu_asid(cpu, next)); - ehb(); /* Make sure it propagates to TCStatus */ - evpe(mtflags); -#else write_c0_entryhi(cpu_asid(cpu, next)); -#endif /* CONFIG_MIPS_MT_SMTC */ TLBMISS_HANDLER_SETUP_PGD(next->pgd); /* @@ -213,34 +168,12 @@ activate_mm(struct mm_struct *prev, struct mm_struct *next) unsigned long flags; unsigned int cpu = smp_processor_id(); -#ifdef CONFIG_MIPS_MT_SMTC - unsigned long oldasid; - unsigned long mtflags; - int mytlb = (smtc_status & SMTC_TLB_SHARED) ? 0 : cpu_data[cpu].vpe_id; -#endif /* CONFIG_MIPS_MT_SMTC */ - local_irq_save(flags); /* Unconditionally get a new ASID. */ get_new_mmu_context(next, cpu); -#ifdef CONFIG_MIPS_MT_SMTC - /* See comments for similar code above */ - mtflags = dvpe(); - oldasid = read_c0_entryhi() & ASID_MASK; - if(smtc_live_asid[mytlb][oldasid]) { - smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu); - if(smtc_live_asid[mytlb][oldasid] == 0) - smtc_flush_tlb_asid(oldasid); - } - /* See comments for similar code above */ - write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK) | - cpu_asid(cpu, next)); - ehb(); /* Make sure it propagates to TCStatus */ - evpe(mtflags); -#else write_c0_entryhi(cpu_asid(cpu, next)); -#endif /* CONFIG_MIPS_MT_SMTC */ TLBMISS_HANDLER_SETUP_PGD(next->pgd); /* mark mmu ownership change */ @@ -258,48 +191,15 @@ static inline void drop_mmu_context(struct mm_struct *mm, unsigned cpu) { unsigned long flags; -#ifdef CONFIG_MIPS_MT_SMTC - unsigned long oldasid; - /* Can't use spinlock because called from TLB flush within DVPE */ - unsigned int prevvpe; - int mytlb = (smtc_status & SMTC_TLB_SHARED) ? 0 : cpu_data[cpu].vpe_id; -#endif /* CONFIG_MIPS_MT_SMTC */ local_irq_save(flags); if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { get_new_mmu_context(mm, cpu); -#ifdef CONFIG_MIPS_MT_SMTC - /* See comments for similar code above */ - prevvpe = dvpe(); - oldasid = (read_c0_entryhi() & ASID_MASK); - if (smtc_live_asid[mytlb][oldasid]) { - smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu); - if(smtc_live_asid[mytlb][oldasid] == 0) - smtc_flush_tlb_asid(oldasid); - } - /* See comments for similar code above */ - write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK) - | cpu_asid(cpu, mm)); - ehb(); /* Make sure it propagates to TCStatus */ - evpe(prevvpe); -#else /* not CONFIG_MIPS_MT_SMTC */ write_c0_entryhi(cpu_asid(cpu, mm)); -#endif /* CONFIG_MIPS_MT_SMTC */ } else { /* will get a new context next time */ -#ifndef CONFIG_MIPS_MT_SMTC cpu_context(cpu, mm) = 0; -#else /* SMTC */ - int i; - - /* SMTC shares the TLB (and ASIDs) across VPEs */ - for_each_online_cpu(i) { - if((smtc_status & SMTC_TLB_SHARED) - || (cpu_data[i].vpe_id == cpu_data[cpu].vpe_id)) - cpu_context(i, mm) = 0; - } -#endif /* CONFIG_MIPS_MT_SMTC */ } local_irq_restore(flags); } diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h index c2edae382d5d..800fe578dc99 100644 --- a/arch/mips/include/asm/module.h +++ b/arch/mips/include/asm/module.h @@ -144,13 +144,7 @@ search_module_dbetables(unsigned long addr) #define MODULE_KERNEL_TYPE "64BIT " #endif -#ifdef CONFIG_MIPS_MT_SMTC -#define MODULE_KERNEL_SMTC "MT_SMTC " -#else -#define MODULE_KERNEL_SMTC "" -#endif - #define MODULE_ARCH_VERMAGIC \ - MODULE_PROC_FAMILY MODULE_KERNEL_TYPE MODULE_KERNEL_SMTC + MODULE_PROC_FAMILY MODULE_KERNEL_TYPE #endif /* _ASM_MODULE_H */ diff --git a/arch/mips/include/asm/msa.h b/arch/mips/include/asm/msa.h index a2aba6c3ec05..538f6d482db8 100644 --- a/arch/mips/include/asm/msa.h +++ b/arch/mips/include/asm/msa.h @@ -84,7 +84,7 @@ static inline void write_msa_##name(unsigned int val) \ __asm__ __volatile__( \ " .set push\n" \ " .set msa\n" \ - " cfcmsa $" #cs ", %0\n" \ + " ctcmsa $" #cs ", %0\n" \ " .set pop\n" \ : : "r"(val)); \ } @@ -96,6 +96,13 @@ static inline void write_msa_##name(unsigned int val) \ * allow compilation with toolchains that do not support MSA. Once all * toolchains in use support MSA these can be removed. */ +#ifdef CONFIG_CPU_MICROMIPS +#define CFC_MSA_INSN 0x587e0056 +#define CTC_MSA_INSN 0x583e0816 +#else +#define CFC_MSA_INSN 0x787e0059 +#define CTC_MSA_INSN 0x783e0819 +#endif #define __BUILD_MSA_CTL_REG(name, cs) \ static inline unsigned int read_msa_##name(void) \ @@ -104,7 +111,8 @@ static inline unsigned int read_msa_##name(void) \ __asm__ __volatile__( \ " .set push\n" \ " .set noat\n" \ - " .word 0x787e0059 | (" #cs " << 11)\n" \ + " .insn\n" \ + " .word #CFC_MSA_INSN | (" #cs " << 11)\n" \ " move %0, $1\n" \ " .set pop\n" \ : "=r"(reg)); \ @@ -117,7 +125,8 @@ static inline void write_msa_##name(unsigned int val) \ " .set push\n" \ " .set noat\n" \ " move $1, %0\n" \ - " .word 0x783e0819 | (" #cs " << 6)\n" \ + " .insn\n" \ + " .word #CTC_MSA_INSN | (" #cs " << 6)\n" \ " .set pop\n" \ : : "r"(val)); \ } diff --git a/arch/mips/include/asm/netlogic/mips-extns.h b/arch/mips/include/asm/netlogic/mips-extns.h index de9aada6f4c1..06f1f75bfa9b 100644 --- a/arch/mips/include/asm/netlogic/mips-extns.h +++ b/arch/mips/include/asm/netlogic/mips-extns.h @@ -146,9 +146,10 @@ static inline int hard_smp_processor_id(void) static inline int nlm_nodeid(void) { - uint32_t prid = read_c0_prid(); + uint32_t prid = read_c0_prid() & PRID_IMP_MASK; - if ((prid & 0xff00) == PRID_IMP_NETLOGIC_XLP9XX) + if ((prid == PRID_IMP_NETLOGIC_XLP9XX) || + (prid == PRID_IMP_NETLOGIC_XLP5XX)) return (__read_32bit_c0_register($15, 1) >> 7) & 0x7; else return (__read_32bit_c0_register($15, 1) >> 5) & 0x3; diff --git a/arch/mips/include/asm/netlogic/xlp-hal/iomap.h b/arch/mips/include/asm/netlogic/xlp-hal/iomap.h index 1f23dfaa7167..805bfd21f33e 100644 --- a/arch/mips/include/asm/netlogic/xlp-hal/iomap.h +++ b/arch/mips/include/asm/netlogic/xlp-hal/iomap.h @@ -74,6 +74,8 @@ #define XLP_IO_USB_OHCI2_OFFSET(node) XLP_HDR_OFFSET(node, 0, 2, 4) #define XLP_IO_USB_OHCI3_OFFSET(node) XLP_HDR_OFFSET(node, 0, 2, 5) +#define XLP_IO_SATA_OFFSET(node) XLP_HDR_OFFSET(node, 0, 3, 2) + /* XLP2xx has an updated USB block */ #define XLP2XX_IO_USB_OFFSET(node, i) XLP_HDR_OFFSET(node, 0, 4, i) #define XLP2XX_IO_USB_XHCI0_OFFSET(node) XLP_HDR_OFFSET(node, 0, 4, 1) @@ -103,13 +105,11 @@ #define XLP_IO_SYS_OFFSET(node) XLP_HDR_OFFSET(node, 0, 6, 5) #define XLP_IO_JTAG_OFFSET(node) XLP_HDR_OFFSET(node, 0, 6, 6) +/* Flash */ #define XLP_IO_NOR_OFFSET(node) XLP_HDR_OFFSET(node, 0, 7, 0) #define XLP_IO_NAND_OFFSET(node) XLP_HDR_OFFSET(node, 0, 7, 1) #define XLP_IO_SPI_OFFSET(node) XLP_HDR_OFFSET(node, 0, 7, 2) -/* SD flash */ -#define XLP_IO_SD_OFFSET(node) XLP_HDR_OFFSET(node, 0, 7, 3) -#define XLP_IO_MMC_OFFSET(node, slot) \ - ((XLP_IO_SD_OFFSET(node))+(slot*0x100)+XLP_IO_PCI_HDRSZ) +#define XLP_IO_MMC_OFFSET(node) XLP_HDR_OFFSET(node, 0, 7, 3) /* Things have changed drastically in XLP 9XX */ #define XLP9XX_HDR_OFFSET(n, d, f) \ @@ -120,6 +120,8 @@ #define XLP9XX_IO_UART_OFFSET(node) XLP9XX_HDR_OFFSET(node, 2, 2) #define XLP9XX_IO_SYS_OFFSET(node) XLP9XX_HDR_OFFSET(node, 6, 0) #define XLP9XX_IO_FUSE_OFFSET(node) XLP9XX_HDR_OFFSET(node, 6, 1) +#define XLP9XX_IO_CLOCK_OFFSET(node) XLP9XX_HDR_OFFSET(node, 6, 2) +#define XLP9XX_IO_POWER_OFFSET(node) XLP9XX_HDR_OFFSET(node, 6, 3) #define XLP9XX_IO_JTAG_OFFSET(node) XLP9XX_HDR_OFFSET(node, 6, 4) #define XLP9XX_IO_PCIE_OFFSET(node, i) XLP9XX_HDR_OFFSET(node, 1, i) @@ -135,11 +137,11 @@ /* XLP9XX on-chip SATA controller */ #define XLP9XX_IO_SATA_OFFSET(node) XLP9XX_HDR_OFFSET(node, 3, 2) +/* Flash */ #define XLP9XX_IO_NOR_OFFSET(node) XLP9XX_HDR_OFFSET(node, 7, 0) #define XLP9XX_IO_NAND_OFFSET(node) XLP9XX_HDR_OFFSET(node, 7, 1) #define XLP9XX_IO_SPI_OFFSET(node) XLP9XX_HDR_OFFSET(node, 7, 2) -/* SD flash */ -#define XLP9XX_IO_MMCSD_OFFSET(node) XLP9XX_HDR_OFFSET(node, 7, 3) +#define XLP9XX_IO_MMC_OFFSET(node) XLP9XX_HDR_OFFSET(node, 7, 3) /* PCI config header register id's */ #define XLP_PCI_CFGREG0 0x00 @@ -186,8 +188,10 @@ #define PCI_DEVICE_ID_NLM_NOR 0x1015 #define PCI_DEVICE_ID_NLM_NAND 0x1016 #define PCI_DEVICE_ID_NLM_MMC 0x1018 -#define PCI_DEVICE_ID_NLM_XHCI 0x101d +#define PCI_DEVICE_ID_NLM_SATA 0x101A +#define PCI_DEVICE_ID_NLM_XHCI 0x101D +#define PCI_DEVICE_ID_XLP9XX_MMC 0x9018 #define PCI_DEVICE_ID_XLP9XX_SATA 0x901A #define PCI_DEVICE_ID_XLP9XX_XHCI 0x901D diff --git a/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h b/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h index d4deb87ad069..91540f41e1e4 100644 --- a/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h +++ b/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h @@ -69,6 +69,20 @@ #define PCIE_9XX_BYTE_SWAP_IO_BASE 0x25e #define PCIE_9XX_BYTE_SWAP_IO_LIM 0x25f +#define PCIE_9XX_BRIDGE_MSIX_ADDR_BASE 0x264 +#define PCIE_9XX_BRIDGE_MSIX_ADDR_LIMIT 0x265 +#define PCIE_9XX_MSI_STATUS 0x283 +#define PCIE_9XX_MSI_EN 0x284 +/* 128 MSIX vectors available in 9xx */ +#define PCIE_9XX_MSIX_STATUS0 0x286 +#define PCIE_9XX_MSIX_STATUSX(n) (n + 0x286) +#define PCIE_9XX_MSIX_VEC 0x296 +#define PCIE_9XX_MSIX_VECX(n) (n + 0x296) +#define PCIE_9XX_INT_STATUS0 0x397 +#define PCIE_9XX_INT_STATUS1 0x398 +#define PCIE_9XX_INT_EN0 0x399 +#define PCIE_9XX_INT_EN1 0x39a + /* other */ #define PCIE_NLINKS 4 diff --git a/arch/mips/include/asm/netlogic/xlp-hal/pic.h b/arch/mips/include/asm/netlogic/xlp-hal/pic.h index f10bf3bba58f..41cefe94f0c9 100644 --- a/arch/mips/include/asm/netlogic/xlp-hal/pic.h +++ b/arch/mips/include/asm/netlogic/xlp-hal/pic.h @@ -199,6 +199,10 @@ #define PIC_IRT_PCIE_LINK_3_INDEX 81 #define PIC_IRT_PCIE_LINK_INDEX(num) ((num) + PIC_IRT_PCIE_LINK_0_INDEX) +#define PIC_9XX_IRT_PCIE_LINK_0_INDEX 191 +#define PIC_9XX_IRT_PCIE_LINK_INDEX(num) \ + ((num) + PIC_9XX_IRT_PCIE_LINK_0_INDEX) + #define PIC_CLOCK_TIMER 7 #if !defined(LOCORE) && !defined(__ASSEMBLY__) diff --git a/arch/mips/include/asm/netlogic/xlp-hal/sys.h b/arch/mips/include/asm/netlogic/xlp-hal/sys.h index d9b107ffca93..bc7bddf25be9 100644 --- a/arch/mips/include/asm/netlogic/xlp-hal/sys.h +++ b/arch/mips/include/asm/netlogic/xlp-hal/sys.h @@ -118,6 +118,10 @@ #define SYS_SCRTCH3 0x4c /* PLL registers XLP2XX */ +#define SYS_CPU_PLL_CTRL0(core) (0x1c0 + (core * 4)) +#define SYS_CPU_PLL_CTRL1(core) (0x1c1 + (core * 4)) +#define SYS_CPU_PLL_CTRL2(core) (0x1c2 + (core * 4)) +#define SYS_CPU_PLL_CTRL3(core) (0x1c3 + (core * 4)) #define SYS_PLL_CTRL0 0x240 #define SYS_PLL_CTRL1 0x241 #define SYS_PLL_CTRL2 0x242 @@ -147,6 +151,32 @@ #define SYS_SYS_PLL_MEM_REQ 0x2a3 #define SYS_PLL_MEM_STAT 0x2a4 +/* PLL registers XLP9XX */ +#define SYS_9XX_CPU_PLL_CTRL0(core) (0xc0 + (core * 4)) +#define SYS_9XX_CPU_PLL_CTRL1(core) (0xc1 + (core * 4)) +#define SYS_9XX_CPU_PLL_CTRL2(core) (0xc2 + (core * 4)) +#define SYS_9XX_CPU_PLL_CTRL3(core) (0xc3 + (core * 4)) +#define SYS_9XX_DMC_PLL_CTRL0 0x140 +#define SYS_9XX_DMC_PLL_CTRL1 0x141 +#define SYS_9XX_DMC_PLL_CTRL2 0x142 +#define SYS_9XX_DMC_PLL_CTRL3 0x143 +#define SYS_9XX_PLL_CTRL0 0x144 +#define SYS_9XX_PLL_CTRL1 0x145 +#define SYS_9XX_PLL_CTRL2 0x146 +#define SYS_9XX_PLL_CTRL3 0x147 + +#define SYS_9XX_PLL_CTRL0_DEVX(x) (0x148 + (x) * 4) +#define SYS_9XX_PLL_CTRL1_DEVX(x) (0x149 + (x) * 4) +#define SYS_9XX_PLL_CTRL2_DEVX(x) (0x14a + (x) * 4) +#define SYS_9XX_PLL_CTRL3_DEVX(x) (0x14b + (x) * 4) + +#define SYS_9XX_CPU_PLL_CHG_CTRL 0x188 +#define SYS_9XX_PLL_CHG_CTRL 0x189 +#define SYS_9XX_CLK_DEV_DIS 0x18a +#define SYS_9XX_CLK_DEV_SEL 0x18b +#define SYS_9XX_CLK_DEV_DIV 0x18d +#define SYS_9XX_CLK_DEV_CHG 0x18f + /* Registers changed on 9XX */ #define SYS_9XX_POWER_ON_RESET_CFG 0x00 #define SYS_9XX_CHIP_RESET 0x01 @@ -170,6 +200,11 @@ #define nlm_get_fuse_regbase(node) \ (nlm_get_fuse_pcibase(node) + XLP_IO_PCI_HDRSZ) +#define nlm_get_clock_pcibase(node) \ + nlm_pcicfg_base(XLP9XX_IO_CLOCK_OFFSET(node)) +#define nlm_get_clock_regbase(node) \ + (nlm_get_clock_pcibase(node) + XLP_IO_PCI_HDRSZ) + unsigned int nlm_get_pic_frequency(int node); #endif #endif diff --git a/arch/mips/include/asm/netlogic/xlp-hal/xlp.h b/arch/mips/include/asm/netlogic/xlp-hal/xlp.h index 2b0c9599ebe5..a862b93223cc 100644 --- a/arch/mips/include/asm/netlogic/xlp-hal/xlp.h +++ b/arch/mips/include/asm/netlogic/xlp-hal/xlp.h @@ -58,6 +58,10 @@ #define PIC_I2C_1_IRQ 31 #define PIC_I2C_2_IRQ 32 #define PIC_I2C_3_IRQ 33 +#define PIC_SPI_IRQ 34 +#define PIC_NAND_IRQ 37 +#define PIC_SATA_IRQ 38 +#define PIC_GPIO_IRQ 39 #define PIC_PCIE_LINK_MSI_IRQ_BASE 44 /* 44 - 47 MSI IRQ */ #define PIC_PCIE_LINK_MSI_IRQ(i) (44 + (i)) @@ -66,8 +70,9 @@ #define PIC_PCIE_MSIX_IRQ_BASE 48 /* 48 - 51 MSI-X IRQ */ #define PIC_PCIE_MSIX_IRQ(i) (48 + (i)) -#define NLM_MSIX_VEC_BASE 96 /* 96 - 127 - MSIX mapped */ -#define NLM_MSI_VEC_BASE 128 /* 128 -255 - MSI mapped */ +/* XLP9xx and XLP8xx has 128 and 32 MSIX vectors respectively */ +#define NLM_MSIX_VEC_BASE 96 /* 96 - 223 - MSIX mapped */ +#define NLM_MSI_VEC_BASE 224 /* 224 -351 - MSI mapped */ #define NLM_PIC_INDIRECT_VEC_BASE 512 #define NLM_GPIO_VEC_BASE 768 @@ -95,17 +100,19 @@ void *xlp_dt_init(void *fdtp); static inline int cpu_is_xlpii(void) { - int chip = read_c0_prid() & 0xff00; + int chip = read_c0_prid() & PRID_IMP_MASK; return chip == PRID_IMP_NETLOGIC_XLP2XX || - chip == PRID_IMP_NETLOGIC_XLP9XX; + chip == PRID_IMP_NETLOGIC_XLP9XX || + chip == PRID_IMP_NETLOGIC_XLP5XX; } static inline int cpu_is_xlp9xx(void) { - int chip = read_c0_prid() & 0xff00; + int chip = read_c0_prid() & PRID_IMP_MASK; - return chip == PRID_IMP_NETLOGIC_XLP9XX; + return chip == PRID_IMP_NETLOGIC_XLP9XX || + chip == PRID_IMP_NETLOGIC_XLP5XX; } #endif /* !__ASSEMBLY__ */ #endif /* _ASM_NLM_XLP_H */ diff --git a/arch/mips/include/asm/nile4.h b/arch/mips/include/asm/nile4.h index 2e2436d0e94e..99e97f8bfbca 100644 --- a/arch/mips/include/asm/nile4.h +++ b/arch/mips/include/asm/nile4.h @@ -1,7 +1,7 @@ /* * asm-mips/nile4.h -- NEC Vrc-5074 Nile 4 definitions * - * Copyright (C) 2000 Geert Uytterhoeven <geert@sonycom.com> + * Copyright (C) 2000 Geert Uytterhoeven <geert@linux-m68k.org> * Sony Software Development Center Europe (SDCE), Brussels * * This file is based on the following documentation: diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h index f5d77b91537f..d781f9e66884 100644 --- a/arch/mips/include/asm/octeon/octeon.h +++ b/arch/mips/include/asm/octeon/octeon.h @@ -211,7 +211,6 @@ union octeon_cvmemctl { extern void octeon_write_lcd(const char *s); extern void octeon_check_cpu_bist(void); -extern int octeon_get_boot_debug_flag(void); extern int octeon_get_boot_uart(void); struct uart_port; diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 008324d1c261..539ddd148bbb 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -32,6 +32,8 @@ struct vm_area_struct; _page_cachable_default) #define PAGE_KERNEL __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \ _PAGE_GLOBAL | _page_cachable_default) +#define PAGE_KERNEL_NC __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \ + _PAGE_GLOBAL | _CACHE_CACHABLE_NONCOHERENT) #define PAGE_USERIO __pgprot(_PAGE_PRESENT | (cpu_has_rixi ? 0 : _PAGE_READ) | _PAGE_WRITE | \ _page_cachable_default) #define PAGE_KERNEL_UNCACHED __pgprot(_PAGE_PRESENT | __READABLE | \ diff --git a/arch/mips/include/asm/pm-cps.h b/arch/mips/include/asm/pm-cps.h new file mode 100644 index 000000000000..625eda53d571 --- /dev/null +++ b/arch/mips/include/asm/pm-cps.h @@ -0,0 +1,51 @@ +/* + * Copyright (C) 2014 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __MIPS_ASM_PM_CPS_H__ +#define __MIPS_ASM_PM_CPS_H__ + +/* + * The CM & CPC can only handle coherence & power control on a per-core basis, + * thus in an MT system the VPEs within each core are coupled and can only + * enter or exit states requiring CM or CPC assistance in unison. + */ +#ifdef CONFIG_MIPS_MT +# define coupled_coherence cpu_has_mipsmt +#else +# define coupled_coherence 0 +#endif + +/* Enumeration of possible PM states */ +enum cps_pm_state { + CPS_PM_NC_WAIT, /* MIPS wait instruction, non-coherent */ + CPS_PM_CLOCK_GATED, /* Core clock gated */ + CPS_PM_POWER_GATED, /* Core power gated */ + CPS_PM_STATE_COUNT, +}; + +/** + * cps_pm_support_state - determine whether the system supports a PM state + * @state: the state to test for support + * + * Returns true if the system supports the given state, otherwise false. + */ +extern bool cps_pm_support_state(enum cps_pm_state state); + +/** + * cps_pm_enter_state - enter a PM state + * @state: the state to enter + * + * Enter the given PM state. If coupled_coherence is non-zero then it is + * expected that this function be called at approximately the same time on + * each coupled CPU. Returns 0 on successful entry & exit, otherwise -errno. + */ +extern int cps_pm_enter_state(enum cps_pm_state state); + +#endif /* __MIPS_ASM_PM_CPS_H__ */ diff --git a/arch/mips/include/asm/pm.h b/arch/mips/include/asm/pm.h new file mode 100644 index 000000000000..7c03469e043f --- /dev/null +++ b/arch/mips/include/asm/pm.h @@ -0,0 +1,159 @@ +/* + * Copyright (C) 2014 Imagination Technologies Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * PM helper macros for CPU power off (e.g. Suspend-to-RAM). + */ + +#ifndef __ASM_PM_H +#define __ASM_PM_H + +#ifdef __ASSEMBLY__ + +#include <asm/asm-offsets.h> +#include <asm/asm.h> +#include <asm/mipsregs.h> +#include <asm/regdef.h> + +/* Save CPU state to stack for suspend to RAM */ +.macro SUSPEND_SAVE_REGS + subu sp, PT_SIZE + /* Call preserved GPRs */ + LONG_S $16, PT_R16(sp) + LONG_S $17, PT_R17(sp) + LONG_S $18, PT_R18(sp) + LONG_S $19, PT_R19(sp) + LONG_S $20, PT_R20(sp) + LONG_S $21, PT_R21(sp) + LONG_S $22, PT_R22(sp) + LONG_S $23, PT_R23(sp) + LONG_S $28, PT_R28(sp) + LONG_S $30, PT_R30(sp) + LONG_S $31, PT_R31(sp) + /* A couple of CP0 registers with space in pt_regs */ + mfc0 k0, CP0_STATUS + LONG_S k0, PT_STATUS(sp) +.endm + +/* Restore CPU state from stack after resume from RAM */ +.macro RESUME_RESTORE_REGS_RETURN + .set push + .set noreorder + /* A couple of CP0 registers with space in pt_regs */ + LONG_L k0, PT_STATUS(sp) + mtc0 k0, CP0_STATUS + /* Call preserved GPRs */ + LONG_L $16, PT_R16(sp) + LONG_L $17, PT_R17(sp) + LONG_L $18, PT_R18(sp) + LONG_L $19, PT_R19(sp) + LONG_L $20, PT_R20(sp) + LONG_L $21, PT_R21(sp) + LONG_L $22, PT_R22(sp) + LONG_L $23, PT_R23(sp) + LONG_L $28, PT_R28(sp) + LONG_L $30, PT_R30(sp) + LONG_L $31, PT_R31(sp) + /* Pop and return */ + jr ra + addiu sp, PT_SIZE + .set pop +.endm + +/* Get address of static suspend state into t1 */ +.macro LA_STATIC_SUSPEND + la t1, mips_static_suspend_state +.endm + +/* Save important CPU state for early restoration to global data */ +.macro SUSPEND_SAVE_STATIC +#ifdef CONFIG_EVA + /* + * Segment configuration is saved in global data where it can be easily + * reloaded without depending on the segment configuration. + */ + mfc0 k0, CP0_PAGEMASK, 2 /* SegCtl0 */ + LONG_S k0, SSS_SEGCTL0(t1) + mfc0 k0, CP0_PAGEMASK, 3 /* SegCtl1 */ + LONG_S k0, SSS_SEGCTL1(t1) + mfc0 k0, CP0_PAGEMASK, 4 /* SegCtl2 */ + LONG_S k0, SSS_SEGCTL2(t1) +#endif + /* save stack pointer (pointing to GPRs) */ + LONG_S sp, SSS_SP(t1) +.endm + +/* Restore important CPU state early from global data */ +.macro RESUME_RESTORE_STATIC +#ifdef CONFIG_EVA + /* + * Segment configuration must be restored prior to any access to + * allocated memory, as it may reside outside of the legacy kernel + * segments. + */ + LONG_L k0, SSS_SEGCTL0(t1) + mtc0 k0, CP0_PAGEMASK, 2 /* SegCtl0 */ + LONG_L k0, SSS_SEGCTL1(t1) + mtc0 k0, CP0_PAGEMASK, 3 /* SegCtl1 */ + LONG_L k0, SSS_SEGCTL2(t1) + mtc0 k0, CP0_PAGEMASK, 4 /* SegCtl2 */ + tlbw_use_hazard +#endif + /* restore stack pointer (pointing to GPRs) */ + LONG_L sp, SSS_SP(t1) +.endm + +/* flush caches to make sure context has reached memory */ +.macro SUSPEND_CACHE_FLUSH + .extern __wback_cache_all + .set push + .set noreorder + la t1, __wback_cache_all + LONG_L t0, 0(t1) + jalr t0 + nop + .set pop + .endm + +/* Save suspend state and flush data caches to RAM */ +.macro SUSPEND_SAVE + SUSPEND_SAVE_REGS + LA_STATIC_SUSPEND + SUSPEND_SAVE_STATIC + SUSPEND_CACHE_FLUSH +.endm + +/* Restore saved state after resume from RAM and return */ +.macro RESUME_RESTORE_RETURN + LA_STATIC_SUSPEND + RESUME_RESTORE_STATIC + RESUME_RESTORE_REGS_RETURN +.endm + +#else /* __ASSEMBLY__ */ + +/** + * struct mips_static_suspend_state - Core saved CPU state across S2R. + * @segctl: CP0 Segment control registers. + * @sp: Stack frame where GP register context is saved. + * + * This structure contains minimal CPU state that must be saved in static kernel + * data in order to be able to restore the rest of the state. This includes + * segmentation configuration in the case of EVA being enabled, as they must be + * restored prior to any kmalloc'd memory being referenced (even the stack + * pointer). + */ +struct mips_static_suspend_state { +#ifdef CONFIG_EVA + unsigned long segctl[3]; +#endif + unsigned long sp; +}; + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ASM_PM_HELPERS_H */ diff --git a/arch/mips/include/asm/prom.h b/arch/mips/include/asm/prom.h index ccd2b75f152c..a9494c0141fb 100644 --- a/arch/mips/include/asm/prom.h +++ b/arch/mips/include/asm/prom.h @@ -21,13 +21,13 @@ extern void device_tree_init(void); struct boot_param_header; -extern void __dt_setup_arch(struct boot_param_header *bph); +extern void __dt_setup_arch(void *bph); #define dt_setup_arch(sym) \ ({ \ - extern struct boot_param_header __dtb_##sym##_begin; \ + extern char __dtb_##sym##_begin[]; \ \ - __dt_setup_arch(&__dtb_##sym##_begin); \ + __dt_setup_arch(__dtb_##sym##_begin); \ }) #else /* CONFIG_OF */ diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index bf1ac8d35783..7e6e682aece3 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -39,9 +39,6 @@ struct pt_regs { unsigned long cp0_badvaddr; unsigned long cp0_cause; unsigned long cp0_epc; -#ifdef CONFIG_MIPS_MT_SMTC - unsigned long cp0_tcstatus; -#endif /* CONFIG_MIPS_MT_SMTC */ #ifdef CONFIG_CPU_CAVIUM_OCTEON unsigned long long mpl[3]; /* MTM{0,1,2} */ unsigned long long mtp[3]; /* MTP{0,1,2} */ diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h index ca64cbe44493..0b8bd28a0df1 100644 --- a/arch/mips/include/asm/r4kcache.h +++ b/arch/mips/include/asm/r4kcache.h @@ -43,11 +43,10 @@ : "i" (op), "R" (*(unsigned char *)(addr))) #ifdef CONFIG_MIPS_MT + /* - * Temporary hacks for SMTC debug. Optionally force single-threaded - * execution during I-cache flushes. + * Optionally force single-threaded execution during I-cache flushes. */ - #define PROTECT_CACHE_FLUSHES 1 #ifdef PROTECT_CACHE_FLUSHES @@ -524,6 +523,8 @@ __BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 32, __BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 64, ) __BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 64, ) __BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 64, ) +__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 128, ) +__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 128, ) __BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 128, ) __BUILD_BLAST_CACHE(inv_d, dcache, Index_Writeback_Inv_D, Hit_Invalidate_D, 16, ) diff --git a/arch/mips/include/asm/sgi/ip22.h b/arch/mips/include/asm/sgi/ip22.h index 8db1a3588cf2..87ec9eaa04e3 100644 --- a/arch/mips/include/asm/sgi/ip22.h +++ b/arch/mips/include/asm/sgi/ip22.h @@ -69,6 +69,8 @@ #define SGI_EISA_IRQ SGINT_LOCAL2 + 3 /* EISA interrupts */ #define SGI_KEYBD_IRQ SGINT_LOCAL2 + 4 /* keyboard */ #define SGI_SERIAL_IRQ SGINT_LOCAL2 + 5 /* onboard serial */ +#define SGI_GIOEXP0_IRQ (SGINT_LOCAL2 + 6) /* Indy GIO EXP0 */ +#define SGI_GIOEXP1_IRQ (SGINT_LOCAL2 + 7) /* Indy GIO EXP1 */ #define ip22_is_fullhouse() (sgioc->sysid & SGIOC_SYSID_FULLHOUSE) diff --git a/arch/mips/include/asm/smp-cps.h b/arch/mips/include/asm/smp-cps.h index d60d1a2180d1..a06a08a9afc6 100644 --- a/arch/mips/include/asm/smp-cps.h +++ b/arch/mips/include/asm/smp-cps.h @@ -13,17 +13,28 @@ #ifndef __ASSEMBLY__ -struct boot_config { - unsigned int core; - unsigned int vpe; +struct vpe_boot_config { unsigned long pc; unsigned long sp; unsigned long gp; }; -extern struct boot_config mips_cps_bootcfg; +struct core_boot_config { + atomic_t vpe_mask; + struct vpe_boot_config *vpe_config; +}; + +extern struct core_boot_config *mips_cps_core_bootcfg; extern void mips_cps_core_entry(void); +extern void mips_cps_core_init(void); + +extern struct vpe_boot_config *mips_cps_boot_vpes(void); + +extern bool mips_cps_smp_in_use(void); + +extern void mips_cps_pm_save(void); +extern void mips_cps_pm_restore(void); #else /* __ASSEMBLY__ */ diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h index 73d35b18fb64..6ba1fb8b11e2 100644 --- a/arch/mips/include/asm/smp-ops.h +++ b/arch/mips/include/asm/smp-ops.h @@ -26,7 +26,6 @@ struct plat_smp_ops { void (*send_ipi_mask)(const struct cpumask *mask, unsigned int action); void (*init_secondary)(void); void (*smp_finish)(void); - void (*cpus_done)(void); void (*boot_secondary)(int cpu, struct task_struct *idle); void (*smp_setup)(void); void (*prepare_cpus)(unsigned int max_cpus); diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index efa02acd3dd5..b037334fca22 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -46,6 +46,9 @@ extern int __cpu_logical_map[NR_CPUS]; extern volatile cpumask_t cpu_callin_map; +/* Mask of CPUs which are currently definitely operating coherently */ +extern cpumask_t cpu_coherent_mask; + extern void asmlinkage smp_bootstrap(void); /* diff --git a/arch/mips/include/asm/smtc.h b/arch/mips/include/asm/smtc.h deleted file mode 100644 index e56b439b7871..000000000000 --- a/arch/mips/include/asm/smtc.h +++ /dev/null @@ -1,78 +0,0 @@ -#ifndef _ASM_SMTC_MT_H -#define _ASM_SMTC_MT_H - -/* - * Definitions for SMTC multitasking on MIPS MT cores - */ - -#include <asm/mips_mt.h> -#include <asm/smtc_ipi.h> - -/* - * System-wide SMTC status information - */ - -extern unsigned int smtc_status; - -#define SMTC_TLB_SHARED 0x00000001 -#define SMTC_MTC_ACTIVE 0x00000002 - -/* - * TLB/ASID Management information - */ - -#define MAX_SMTC_TLBS 2 -#define MAX_SMTC_ASIDS 256 -#if NR_CPUS <= 8 -typedef char asiduse; -#else -#if NR_CPUS <= 16 -typedef short asiduse; -#else -typedef long asiduse; -#endif -#endif - -/* - * VPE Management information - */ - -#define MAX_SMTC_VPES MAX_SMTC_TLBS /* FIXME: May not always be true. */ - -extern asiduse smtc_live_asid[MAX_SMTC_TLBS][MAX_SMTC_ASIDS]; - -struct mm_struct; -struct task_struct; - -void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu); -void self_ipi(struct smtc_ipi *); -void smtc_flush_tlb_asid(unsigned long asid); -extern int smtc_build_cpu_map(int startslot); -extern void smtc_prepare_cpus(int cpus); -extern void smtc_smp_finish(void); -extern void smtc_boot_secondary(int cpu, struct task_struct *t); -extern void smtc_cpus_done(void); -extern void smtc_init_secondary(void); - - -/* - * Sharing the TLB between multiple VPEs means that the - * "random" index selection function is not allowed to - * select the current value of the Index register. To - * avoid additional TLB pressure, the Index registers - * are "parked" with an non-Valid value. - */ - -#define PARKED_INDEX ((unsigned int)0x80000000) - -/* - * Define low-level interrupt mask for IPIs, if necessary. - * By default, use SW interrupt 1, which requires no external - * hardware support, but which works only for single-core - * MIPS MT systems. - */ -#ifndef MIPS_CPU_IPI_IRQ -#define MIPS_CPU_IPI_IRQ 1 -#endif - -#endif /* _ASM_SMTC_MT_H */ diff --git a/arch/mips/include/asm/smtc_ipi.h b/arch/mips/include/asm/smtc_ipi.h deleted file mode 100644 index 15278dbd7e79..000000000000 --- a/arch/mips/include/asm/smtc_ipi.h +++ /dev/null @@ -1,129 +0,0 @@ -/* - * Definitions used in MIPS MT SMTC "Interprocessor Interrupt" code. - */ -#ifndef __ASM_SMTC_IPI_H -#define __ASM_SMTC_IPI_H - -#include <linux/spinlock.h> - -//#define SMTC_IPI_DEBUG - -#ifdef SMTC_IPI_DEBUG -#include <asm/mipsregs.h> -#include <asm/mipsmtregs.h> -#endif /* SMTC_IPI_DEBUG */ - -/* - * An IPI "message" - */ - -struct smtc_ipi { - struct smtc_ipi *flink; - int type; - void *arg; - int dest; -#ifdef SMTC_IPI_DEBUG - int sender; - long stamp; -#endif /* SMTC_IPI_DEBUG */ -}; - -/* - * Defined IPI Types - */ - -#define LINUX_SMP_IPI 1 -#define SMTC_CLOCK_TICK 2 -#define IRQ_AFFINITY_IPI 3 - -/* - * A queue of IPI messages - */ - -struct smtc_ipi_q { - struct smtc_ipi *head; - spinlock_t lock; - struct smtc_ipi *tail; - int depth; - int resched_flag; /* reschedule already queued */ -}; - -static inline void smtc_ipi_nq(struct smtc_ipi_q *q, struct smtc_ipi *p) -{ - unsigned long flags; - - spin_lock_irqsave(&q->lock, flags); - if (q->head == NULL) - q->head = q->tail = p; - else - q->tail->flink = p; - p->flink = NULL; - q->tail = p; - q->depth++; -#ifdef SMTC_IPI_DEBUG - p->sender = read_c0_tcbind(); - p->stamp = read_c0_count(); -#endif /* SMTC_IPI_DEBUG */ - spin_unlock_irqrestore(&q->lock, flags); -} - -static inline struct smtc_ipi *__smtc_ipi_dq(struct smtc_ipi_q *q) -{ - struct smtc_ipi *p; - - if (q->head == NULL) - p = NULL; - else { - p = q->head; - q->head = q->head->flink; - q->depth--; - /* Arguably unnecessary, but leaves queue cleaner */ - if (q->head == NULL) - q->tail = NULL; - } - - return p; -} - -static inline struct smtc_ipi *smtc_ipi_dq(struct smtc_ipi_q *q) -{ - unsigned long flags; - struct smtc_ipi *p; - - spin_lock_irqsave(&q->lock, flags); - p = __smtc_ipi_dq(q); - spin_unlock_irqrestore(&q->lock, flags); - - return p; -} - -static inline void smtc_ipi_req(struct smtc_ipi_q *q, struct smtc_ipi *p) -{ - unsigned long flags; - - spin_lock_irqsave(&q->lock, flags); - if (q->head == NULL) { - q->head = q->tail = p; - p->flink = NULL; - } else { - p->flink = q->head; - q->head = p; - } - q->depth++; - spin_unlock_irqrestore(&q->lock, flags); -} - -static inline int smtc_ipi_qdepth(struct smtc_ipi_q *q) -{ - unsigned long flags; - int retval; - - spin_lock_irqsave(&q->lock, flags); - retval = q->depth; - spin_unlock_irqrestore(&q->lock, flags); - return retval; -} - -extern void smtc_send_ipi(int cpu, int type, unsigned int action); - -#endif /* __ASM_SMTC_IPI_H */ diff --git a/arch/mips/include/asm/smtc_proc.h b/arch/mips/include/asm/smtc_proc.h deleted file mode 100644 index 25da651f1f5f..000000000000 --- a/arch/mips/include/asm/smtc_proc.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * Definitions for SMTC /proc entries - * Copyright(C) 2005 MIPS Technologies Inc. - */ -#ifndef __ASM_SMTC_PROC_H -#define __ASM_SMTC_PROC_H - -/* - * per-"CPU" statistics - */ - -struct smtc_cpu_proc { - unsigned long timerints; - unsigned long selfipis; -}; - -extern struct smtc_cpu_proc smtc_cpu_stats[NR_CPUS]; - -/* Count of number of recoveries of "stolen" FPU access rights on 34K */ - -extern atomic_t smtc_fpu_recoveries; - -#endif /* __ASM_SMTC_PROC_H */ diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h index d301e108d5b8..b188c797565c 100644 --- a/arch/mips/include/asm/stackframe.h +++ b/arch/mips/include/asm/stackframe.h @@ -19,22 +19,12 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> -/* - * For SMTC kernel, global IE should be left set, and interrupts - * controlled exclusively via IXMT. - */ -#ifdef CONFIG_MIPS_MT_SMTC -#define STATMASK 0x1e -#elif defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX) +#if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX) #define STATMASK 0x3f #else #define STATMASK 0x1f #endif -#ifdef CONFIG_MIPS_MT_SMTC -#include <asm/mipsmtregs.h> -#endif /* CONFIG_MIPS_MT_SMTC */ - .macro SAVE_AT .set push .set noat @@ -186,16 +176,6 @@ mfc0 v1, CP0_STATUS LONG_S $2, PT_R2(sp) LONG_S v1, PT_STATUS(sp) -#ifdef CONFIG_MIPS_MT_SMTC - /* - * Ideally, these instructions would be shuffled in - * to cover the pipeline delay. - */ - .set mips32 - mfc0 k0, CP0_TCSTATUS - .set mips0 - LONG_S k0, PT_TCSTATUS(sp) -#endif /* CONFIG_MIPS_MT_SMTC */ LONG_S $4, PT_R4(sp) mfc0 v1, CP0_CAUSE LONG_S $5, PT_R5(sp) @@ -321,36 +301,6 @@ .set push .set reorder .set noat -#ifdef CONFIG_MIPS_MT_SMTC - .set mips32r2 - /* - * We need to make sure the read-modify-write - * of Status below isn't perturbed by an interrupt - * or cross-TC access, so we need to do at least a DMT, - * protected by an interrupt-inhibit. But setting IXMT - * also creates a few-cycle window where an IPI could - * be queued and not be detected before potentially - * returning to a WAIT or user-mode loop. It must be - * replayed. - * - * We're in the middle of a context switch, and - * we can't dispatch it directly without trashing - * some registers, so we'll try to detect this unlikely - * case and program a software interrupt in the VPE, - * as would be done for a cross-VPE IPI. To accommodate - * the handling of that case, we're doing a DVPE instead - * of just a DMT here to protect against other threads. - * This is a lot of cruft to cover a tiny window. - * If you can find a better design, implement it! - * - */ - mfc0 v0, CP0_TCSTATUS - ori v0, TCSTATUS_IXMT - mtc0 v0, CP0_TCSTATUS - _ehb - DVPE 5 # dvpe a1 - jal mips_ihb -#endif /* CONFIG_MIPS_MT_SMTC */ mfc0 a0, CP0_STATUS ori a0, STATMASK xori a0, STATMASK @@ -362,59 +312,6 @@ and v0, v1 or v0, a0 mtc0 v0, CP0_STATUS -#ifdef CONFIG_MIPS_MT_SMTC -/* - * Only after EXL/ERL have been restored to status can we - * restore TCStatus.IXMT. - */ - LONG_L v1, PT_TCSTATUS(sp) - _ehb - mfc0 a0, CP0_TCSTATUS - andi v1, TCSTATUS_IXMT - bnez v1, 0f - -/* - * We'd like to detect any IPIs queued in the tiny window - * above and request an software interrupt to service them - * when we ERET. - * - * Computing the offset into the IPIQ array of the executing - * TC's IPI queue in-line would be tedious. We use part of - * the TCContext register to hold 16 bits of offset that we - * can add in-line to find the queue head. - */ - mfc0 v0, CP0_TCCONTEXT - la a2, IPIQ - srl v0, v0, 16 - addu a2, a2, v0 - LONG_L v0, 0(a2) - beqz v0, 0f -/* - * If we have a queue, provoke dispatch within the VPE by setting C_SW1 - */ - mfc0 v0, CP0_CAUSE - ori v0, v0, C_SW1 - mtc0 v0, CP0_CAUSE -0: - /* - * This test should really never branch but - * let's be prudent here. Having atomized - * the shared register modifications, we can - * now EVPE, and must do so before interrupts - * are potentially re-enabled. - */ - andi a1, a1, MVPCONTROL_EVP - beqz a1, 1f - evpe -1: - /* We know that TCStatua.IXMT should be set from above */ - xori a0, a0, TCSTATUS_IXMT - or a0, a0, v1 - mtc0 a0, CP0_TCSTATUS - _ehb - - .set mips0 -#endif /* CONFIG_MIPS_MT_SMTC */ LONG_L v1, PT_EPC(sp) MTC0 v1, CP0_EPC LONG_L $31, PT_R31(sp) @@ -467,33 +364,11 @@ * Set cp0 enable bit as sign that we're running on the kernel stack */ .macro CLI -#if !defined(CONFIG_MIPS_MT_SMTC) mfc0 t0, CP0_STATUS li t1, ST0_CU0 | STATMASK or t0, t1 xori t0, STATMASK mtc0 t0, CP0_STATUS -#else /* CONFIG_MIPS_MT_SMTC */ - /* - * For SMTC, we need to set privilege - * and disable interrupts only for the - * current TC, using the TCStatus register. - */ - mfc0 t0, CP0_TCSTATUS - /* Fortunately CU 0 is in the same place in both registers */ - /* Set TCU0, TMX, TKSU (for later inversion) and IXMT */ - li t1, ST0_CU0 | 0x08001c00 - or t0, t1 - /* Clear TKSU, leave IXMT */ - xori t0, 0x00001800 - mtc0 t0, CP0_TCSTATUS - _ehb - /* We need to leave the global IE bit set, but clear EXL...*/ - mfc0 t0, CP0_STATUS - ori t0, ST0_EXL | ST0_ERL - xori t0, ST0_EXL | ST0_ERL - mtc0 t0, CP0_STATUS -#endif /* CONFIG_MIPS_MT_SMTC */ irq_disable_hazard .endm @@ -502,35 +377,11 @@ * Set cp0 enable bit as sign that we're running on the kernel stack */ .macro STI -#if !defined(CONFIG_MIPS_MT_SMTC) mfc0 t0, CP0_STATUS li t1, ST0_CU0 | STATMASK or t0, t1 xori t0, STATMASK & ~1 mtc0 t0, CP0_STATUS -#else /* CONFIG_MIPS_MT_SMTC */ - /* - * For SMTC, we need to set privilege - * and enable interrupts only for the - * current TC, using the TCStatus register. - */ - _ehb - mfc0 t0, CP0_TCSTATUS - /* Fortunately CU 0 is in the same place in both registers */ - /* Set TCU0, TKSU (for later inversion) and IXMT */ - li t1, ST0_CU0 | 0x08001c00 - or t0, t1 - /* Clear TKSU *and* IXMT */ - xori t0, 0x00001c00 - mtc0 t0, CP0_TCSTATUS - _ehb - /* We need to leave the global IE bit set, but clear EXL...*/ - mfc0 t0, CP0_STATUS - ori t0, ST0_EXL - xori t0, ST0_EXL - mtc0 t0, CP0_STATUS - /* irq_enable_hazard below should expand to EHB for 24K/34K cpus */ -#endif /* CONFIG_MIPS_MT_SMTC */ irq_enable_hazard .endm @@ -540,32 +391,6 @@ * Set cp0 enable bit as sign that we're running on the kernel stack */ .macro KMODE -#ifdef CONFIG_MIPS_MT_SMTC - /* - * This gets baroque in SMTC. We want to - * protect the non-atomic clearing of EXL - * with DMT/EMT, but we don't want to take - * an interrupt while DMT is still in effect. - */ - - /* KMODE gets invoked from both reorder and noreorder code */ - .set push - .set mips32r2 - .set noreorder - mfc0 v0, CP0_TCSTATUS - andi v1, v0, TCSTATUS_IXMT - ori v0, TCSTATUS_IXMT - mtc0 v0, CP0_TCSTATUS - _ehb - DMT 2 # dmt v0 - /* - * We don't know a priori if ra is "live" - */ - move t0, ra - jal mips_ihb - nop /* delay slot */ - move ra, t0 -#endif /* CONFIG_MIPS_MT_SMTC */ mfc0 t0, CP0_STATUS li t1, ST0_CU0 | (STATMASK & ~1) #if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX) @@ -576,25 +401,6 @@ or t0, t1 xori t0, STATMASK & ~1 mtc0 t0, CP0_STATUS -#ifdef CONFIG_MIPS_MT_SMTC - _ehb - andi v0, v0, VPECONTROL_TE - beqz v0, 2f - nop /* delay slot */ - emt -2: - mfc0 v0, CP0_TCSTATUS - /* Clear IXMT, then OR in previous value */ - ori v0, TCSTATUS_IXMT - xori v0, TCSTATUS_IXMT - or v0, v1, v0 - mtc0 v0, CP0_TCSTATUS - /* - * irq_disable_hazard below should expand to EHB - * on 24K/34K CPUS - */ - .set pop -#endif /* CONFIG_MIPS_MT_SMTC */ irq_disable_hazard .endm diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index d2d961d6cb86..7de865805deb 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -159,11 +159,7 @@ static inline struct thread_info *current_thread_info(void) * We stash processor id into a COP0 register to retrieve it fast * at kernel exception entry. */ -#if defined(CONFIG_MIPS_MT_SMTC) -#define SMP_CPUID_REG 2, 2 /* TCBIND */ -#define ASM_SMP_CPUID_REG $2, 2 -#define SMP_CPUID_PTRSHIFT 19 -#elif defined(CONFIG_MIPS_PGD_C0_CONTEXT) +#if defined(CONFIG_MIPS_PGD_C0_CONTEXT) #define SMP_CPUID_REG 20, 0 /* XCONTEXT */ #define ASM_SMP_CPUID_REG $20 #define SMP_CPUID_PTRSHIFT 48 @@ -179,13 +175,8 @@ static inline struct thread_info *current_thread_info(void) #define SMP_CPUID_REGSHIFT (SMP_CPUID_PTRSHIFT + 2) #endif -#ifdef CONFIG_MIPS_MT_SMTC -#define ASM_CPUID_MFC0 mfc0 -#define UASM_i_CPUID_MFC0 uasm_i_mfc0 -#else #define ASM_CPUID_MFC0 MFC0 #define UASM_i_CPUID_MFC0 UASM_i_MFC0 -#endif #endif /* __KERNEL__ */ #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/mips/include/asm/time.h b/arch/mips/include/asm/time.h index 24f534a7fbc3..8f3047d611ee 100644 --- a/arch/mips/include/asm/time.h +++ b/arch/mips/include/asm/time.h @@ -52,14 +52,11 @@ extern int (*perf_irq)(void); */ extern unsigned int __weak get_c0_compare_int(void); extern int r4k_clockevent_init(void); -extern int smtc_clockevent_init(void); extern int gic_clockevent_init(void); static inline int mips_clockevent_init(void) { -#ifdef CONFIG_MIPS_MT_SMTC - return smtc_clockevent_init(); -#elif defined(CONFIG_CEVT_GIC) +#if defined(CONFIG_CEVT_GIC) return (gic_clockevent_init() | r4k_clockevent_init()); #elif defined(CONFIG_CEVT_R4K) return r4k_clockevent_init(); diff --git a/arch/mips/include/asm/timex.h b/arch/mips/include/asm/timex.h index c5424757da65..b05bb70a2e46 100644 --- a/arch/mips/include/asm/timex.h +++ b/arch/mips/include/asm/timex.h @@ -4,12 +4,16 @@ * for more details. * * Copyright (C) 1998, 1999, 2003 by Ralf Baechle + * Copyright (C) 2014 by Maciej W. Rozycki */ #ifndef _ASM_TIMEX_H #define _ASM_TIMEX_H #ifdef __KERNEL__ +#include <linux/compiler.h> + +#include <asm/cpu.h> #include <asm/cpu-features.h> #include <asm/mipsregs.h> #include <asm/cpu-type.h> @@ -45,29 +49,54 @@ typedef unsigned int cycles_t; * However for now the implementaton of this function doesn't get these * fine details right. */ -static inline cycles_t get_cycles(void) +static inline int can_use_mips_counter(unsigned int prid) { - switch (boot_cpu_type()) { - case CPU_R4400PC: - case CPU_R4400SC: - case CPU_R4400MC: - if ((read_c0_prid() & 0xff) >= 0x0050) - return read_c0_count(); - break; + int comp = (prid & PRID_COMP_MASK) != PRID_COMP_LEGACY; - case CPU_R4000PC: - case CPU_R4000SC: - case CPU_R4000MC: - break; + if (__builtin_constant_p(cpu_has_counter) && !cpu_has_counter) + return 0; + else if (__builtin_constant_p(cpu_has_mips_r) && cpu_has_mips_r) + return 1; + else if (likely(!__builtin_constant_p(cpu_has_mips_r) && comp)) + return 1; + /* Make sure we don't peek at cpu_data[0].options in the fast path! */ + if (!__builtin_constant_p(cpu_has_counter)) + asm volatile("" : "=m" (cpu_data[0].options)); + if (likely(cpu_has_counter && + prid >= (PRID_IMP_R4000 | PRID_REV_ENCODE_44(5, 0)))) + return 1; + else + return 0; +} - default: - if (cpu_has_counter) - return read_c0_count(); - break; - } +static inline cycles_t get_cycles(void) +{ + if (can_use_mips_counter(read_c0_prid())) + return read_c0_count(); + else + return 0; /* no usable counter */ +} + +/* + * Like get_cycles - but where c0_count is not available we desperately + * use c0_random in an attempt to get at least a little bit of entropy. + * + * R6000 and R6000A neither have a count register nor a random register. + * That leaves no entropy source in the CPU itself. + */ +static inline unsigned long random_get_entropy(void) +{ + unsigned int prid = read_c0_prid(); + unsigned int imp = prid & PRID_IMP_MASK; - return 0; /* no usable counter */ + if (can_use_mips_counter(prid)) + return read_c0_count(); + else if (likely(imp != PRID_IMP_R6000 && imp != PRID_IMP_R6000A)) + return read_c0_random(); + else + return 0; /* no usable register */ } +#define random_get_entropy random_get_entropy #endif /* __KERNEL__ */ diff --git a/arch/mips/include/asm/uasm.h b/arch/mips/include/asm/uasm.h index c33a9564fb41..f8d63b3b40b4 100644 --- a/arch/mips/include/asm/uasm.h +++ b/arch/mips/include/asm/uasm.h @@ -55,6 +55,9 @@ void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, unsigned int c) #define Ip_u2u1u3(op) \ void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, unsigned int c) +#define Ip_u3u2u1(op) \ +void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, unsigned int c) + #define Ip_u3u1u2(op) \ void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, unsigned int c) @@ -74,6 +77,9 @@ void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, unsigned int c, \ #define Ip_u1u2(op) \ void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b) +#define Ip_u2u1(op) \ +void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b) + #define Ip_u1s2(op) \ void ISAOPC(op)(u32 **buf, unsigned int a, signed int b) @@ -99,6 +105,7 @@ Ip_u2u1s3(_daddiu); Ip_u3u1u2(_daddu); Ip_u2u1msbu3(_dins); Ip_u2u1msbu3(_dinsm); +Ip_u1u2(_divu); Ip_u1u2u3(_dmfc0); Ip_u1u2u3(_dmtc0); Ip_u2u1u3(_drotr); @@ -114,16 +121,22 @@ Ip_u2u1msbu3(_ext); Ip_u2u1msbu3(_ins); Ip_u1(_j); Ip_u1(_jal); +Ip_u2u1(_jalr); Ip_u1(_jr); +Ip_u2s3u1(_lb); Ip_u2s3u1(_ld); Ip_u3u1u2(_ldx); +Ip_u2s3u1(_lh); Ip_u2s3u1(_ll); Ip_u2s3u1(_lld); Ip_u1s2(_lui); Ip_u2s3u1(_lw); Ip_u3u1u2(_lwx); Ip_u1u2u3(_mfc0); +Ip_u1(_mfhi); +Ip_u1(_mflo); Ip_u1u2u3(_mtc0); +Ip_u3u1u2(_mul); Ip_u3u1u2(_or); Ip_u2u1u3(_ori); Ip_u2s3u1(_pref); @@ -133,17 +146,25 @@ Ip_u2s3u1(_sc); Ip_u2s3u1(_scd); Ip_u2s3u1(_sd); Ip_u2u1u3(_sll); +Ip_u3u2u1(_sllv); +Ip_u2u1s3(_sltiu); +Ip_u3u1u2(_sltu); Ip_u2u1u3(_sra); Ip_u2u1u3(_srl); +Ip_u3u2u1(_srlv); Ip_u3u1u2(_subu); Ip_u2s3u1(_sw); +Ip_u1(_sync); Ip_u1(_syscall); Ip_0(_tlbp); Ip_0(_tlbr); Ip_0(_tlbwi); Ip_0(_tlbwr); +Ip_u1(_wait); +Ip_u2u1(_wsbh); Ip_u3u1u2(_xor); Ip_u2u1u3(_xori); +Ip_u2u1(_yield); /* Handle labels. */ @@ -264,6 +285,8 @@ void uasm_il_bbit0(u32 **p, struct uasm_reloc **r, unsigned int reg, unsigned int bit, int lid); void uasm_il_bbit1(u32 **p, struct uasm_reloc **r, unsigned int reg, unsigned int bit, int lid); +void uasm_il_beq(u32 **p, struct uasm_reloc **r, unsigned int r1, + unsigned int r2, int lid); void uasm_il_beqz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid); void uasm_il_beqzl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid); void uasm_il_bgezl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid); diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 413d6c612bec..e55813029d5a 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -29,7 +29,6 @@ #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_UTIME #define __ARCH_WANT_SYS_WAITPID #define __ARCH_WANT_SYS_SOCKETCALL diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild index be7196eacb88..96fe7395ed8d 100644 --- a/arch/mips/include/uapi/asm/Kbuild +++ b/arch/mips/include/uapi/asm/Kbuild @@ -4,6 +4,7 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h generic-y += ipcbuf.h +header-y += bitfield.h header-y += bitsperlong.h header-y += break.h header-y += byteorder.h diff --git a/arch/mips/include/uapi/asm/bitfield.h b/arch/mips/include/uapi/asm/bitfield.h new file mode 100644 index 000000000000..ad9861359cea --- /dev/null +++ b/arch/mips/include/uapi/asm/bitfield.h @@ -0,0 +1,29 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2014 by Ralf Baechle <ralf@linux-mips.org> + */ +#ifndef __UAPI_ASM_BITFIELD_H +#define __UAPI_ASM_BITFIELD_H + +/* + * * Damn ... bitfields depend from byteorder :-( + * */ +#ifdef __MIPSEB__ +#define __BITFIELD_FIELD(field, more) \ + field; \ + more + +#elif defined(__MIPSEL__) + +#define __BITFIELD_FIELD(field, more) \ + more \ + field; + +#else /* !defined (__MIPSEB__) && !defined (__MIPSEL__) */ +#error "MIPS but neither __MIPSEL__ nor __MIPSEB__?" +#endif + +#endif /* __UAPI_ASM_BITFIELD_H */ diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h index 3125797f2a88..4b7160259292 100644 --- a/arch/mips/include/uapi/asm/inst.h +++ b/arch/mips/include/uapi/asm/inst.h @@ -13,6 +13,8 @@ #ifndef _UAPI_ASM_INST_H #define _UAPI_ASM_INST_H +#include <asm/bitfield.h> + /* * Major opcodes; before MIPS IV cop1x was called cop3. */ @@ -74,16 +76,17 @@ enum spec2_op { enum spec3_op { ext_op, dextm_op, dextu_op, dext_op, ins_op, dinsm_op, dinsu_op, dins_op, - lx_op = 0x0a, lwle_op = 0x19, - lwre_op = 0x1a, cachee_op = 0x1b, - sbe_op = 0x1c, she_op = 0x1d, - sce_op = 0x1e, swe_op = 0x1f, - bshfl_op = 0x20, swle_op = 0x21, - swre_op = 0x22, prefe_op = 0x23, - dbshfl_op = 0x24, lbue_op = 0x28, - lhue_op = 0x29, lbe_op = 0x2c, - lhe_op = 0x2d, lle_op = 0x2e, - lwe_op = 0x2f, rdhwr_op = 0x3b + yield_op = 0x09, lx_op = 0x0a, + lwle_op = 0x19, lwre_op = 0x1a, + cachee_op = 0x1b, sbe_op = 0x1c, + she_op = 0x1d, sce_op = 0x1e, + swe_op = 0x1f, bshfl_op = 0x20, + swle_op = 0x21, swre_op = 0x22, + prefe_op = 0x23, dbshfl_op = 0x24, + lbue_op = 0x28, lhue_op = 0x29, + lbe_op = 0x2c, lhe_op = 0x2d, + lle_op = 0x2e, lwe_op = 0x2f, + rdhwr_op = 0x3b }; /* @@ -125,7 +128,8 @@ enum bcop_op { enum cop0_coi_func { tlbr_op = 0x01, tlbwi_op = 0x02, tlbwr_op = 0x06, tlbp_op = 0x08, - rfe_op = 0x10, eret_op = 0x18 + rfe_op = 0x10, eret_op = 0x18, + wait_op = 0x20, }; /* @@ -202,6 +206,16 @@ enum lx_func { }; /* + * BSHFL opcodes + */ +enum bshfl_func { + wsbh_op = 0x2, + dshd_op = 0x5, + seb_op = 0x10, + seh_op = 0x18, +}; + +/* * (microMIPS) Major opcodes. */ enum mm_major_op { @@ -244,17 +258,22 @@ enum mm_32i_minor_op { enum mm_32a_minor_op { mm_sll32_op = 0x000, mm_ins_op = 0x00c, + mm_sllv32_op = 0x010, mm_ext_op = 0x02c, mm_pool32axf_op = 0x03c, mm_srl32_op = 0x040, mm_sra_op = 0x080, + mm_srlv32_op = 0x090, mm_rotr_op = 0x0c0, mm_lwxs_op = 0x118, mm_addu32_op = 0x150, mm_subu32_op = 0x1d0, + mm_wsbh_op = 0x1ec, + mm_mul_op = 0x210, mm_and_op = 0x250, mm_or32_op = 0x290, mm_xor32_op = 0x310, + mm_sltu_op = 0x390, }; /* @@ -294,15 +313,20 @@ enum mm_32axf_minor_op { mm_mfc0_op = 0x003, mm_mtc0_op = 0x00b, mm_tlbp_op = 0x00d, + mm_mfhi32_op = 0x035, mm_jalr_op = 0x03c, mm_tlbr_op = 0x04d, + mm_mflo32_op = 0x075, mm_jalrhb_op = 0x07c, mm_tlbwi_op = 0x08d, mm_tlbwr_op = 0x0cd, mm_jalrs_op = 0x13c, mm_jalrshb_op = 0x17c, + mm_sync_op = 0x1ad, mm_syscall_op = 0x22d, + mm_wait_op = 0x24d, mm_eret_op = 0x3cd, + mm_divu_op = 0x5dc, }; /* @@ -480,24 +504,6 @@ enum MIPS6e_i8_func { */ #define MM_NOP16 0x0c00 -/* - * Damn ... bitfields depend from byteorder :-( - */ -#ifdef __MIPSEB__ -#define __BITFIELD_FIELD(field, more) \ - field; \ - more - -#elif defined(__MIPSEL__) - -#define __BITFIELD_FIELD(field, more) \ - more \ - field; - -#else /* !defined (__MIPSEB__) && !defined (__MIPSEL__) */ -#error "MIPS but neither __MIPSEL__ nor __MIPSEB__?" -#endif - struct j_format { __BITFIELD_FIELD(unsigned int opcode : 6, /* Jump format */ __BITFIELD_FIELD(unsigned int target : 26, diff --git a/arch/mips/include/uapi/asm/kvm_para.h b/arch/mips/include/uapi/asm/kvm_para.h index 14fab8f0b957..7e16d7c42e65 100644 --- a/arch/mips/include/uapi/asm/kvm_para.h +++ b/arch/mips/include/uapi/asm/kvm_para.h @@ -1 +1,5 @@ -#include <asm-generic/kvm_para.h> +#ifndef _UAPI_ASM_MIPS_KVM_PARA_H +#define _UAPI_ASM_MIPS_KVM_PARA_H + + +#endif /* _UAPI_ASM_MIPS_KVM_PARA_H */ diff --git a/arch/mips/include/uapi/asm/types.h b/arch/mips/include/uapi/asm/types.h index 7ac9d0baad84..f3dd9ff0cc0c 100644 --- a/arch/mips/include/uapi/asm/types.h +++ b/arch/mips/include/uapi/asm/types.h @@ -14,9 +14,12 @@ /* * We don't use int-l64.h for the kernel anymore but still use it for * userspace to avoid code changes. + * + * However, some user programs (e.g. perf) may not want this. They can + * flag __SANE_USERSPACE_TYPES__ to get int-ll64.h here. */ #ifndef __KERNEL__ -# if _MIPS_SZLONG == 64 +# if _MIPS_SZLONG == 64 && !defined(__SANE_USERSPACE_TYPES__) # include <asm-generic/int-l64.h> # else # include <asm-generic/int-ll64.h> diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c index c01900e5d078..088e92a79ae6 100644 --- a/arch/mips/jz4740/board-qi_lb60.c +++ b/arch/mips/jz4740/board-qi_lb60.c @@ -425,6 +425,15 @@ static struct platform_device qi_lb60_audio_device = { .id = -1, }; +static struct gpiod_lookup_table qi_lb60_audio_gpio_table = { + .dev_id = "qi-lb60-audio", + .table = { + GPIO_LOOKUP("Bank B", 29, "snd", 0), + GPIO_LOOKUP("Bank D", 4, "amp", 0), + { }, + }, +}; + static struct platform_device *jz_platform_devices[] __initdata = { &jz4740_udc_device, &jz4740_udc_xceiv_device, @@ -461,6 +470,8 @@ static int __init qi_lb60_init_platform_devices(void) jz4740_adc_device.dev.platform_data = &qi_lb60_battery_pdata; jz4740_mmc_device.dev.platform_data = &qi_lb60_mmc_pdata; + gpiod_add_lookup_table(&qi_lb60_audio_gpio_table); + jz4740_serial_device_register(); spi_register_board_info(qi_lb60_spi_board_info, diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 277dab301cea..008a2fed0584 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -17,7 +17,6 @@ endif obj-$(CONFIG_CEVT_BCM1480) += cevt-bcm1480.o obj-$(CONFIG_CEVT_R4K) += cevt-r4k.o -obj-$(CONFIG_MIPS_MT_SMTC) += cevt-smtc.o obj-$(CONFIG_CEVT_DS1287) += cevt-ds1287.o obj-$(CONFIG_CEVT_GIC) += cevt-gic.o obj-$(CONFIG_CEVT_GT641XX) += cevt-gt641xx.o @@ -42,7 +41,7 @@ obj-$(CONFIG_CPU_R4K_FPU) += r4k_fpu.o r4k_switch.o obj-$(CONFIG_CPU_R3000) += r2300_fpu.o r2300_switch.o obj-$(CONFIG_CPU_R6000) += r6000_fpu.o r4k_switch.o obj-$(CONFIG_CPU_TX39XX) += r2300_fpu.o r2300_switch.o -obj-$(CONFIG_CPU_CAVIUM_OCTEON) += octeon_switch.o +obj-$(CONFIG_CPU_CAVIUM_OCTEON) += r4k_fpu.o octeon_switch.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SMP_UP) += smp-up.o @@ -50,7 +49,6 @@ obj-$(CONFIG_CPU_BMIPS) += smp-bmips.o bmips_vec.o obj-$(CONFIG_MIPS_MT) += mips-mt.o obj-$(CONFIG_MIPS_MT_FPAFF) += mips-mt-fpaff.o -obj-$(CONFIG_MIPS_MT_SMTC) += smtc.o smtc-asm.o smtc-proc.o obj-$(CONFIG_MIPS_MT_SMP) += smp-mt.o obj-$(CONFIG_MIPS_CMP) += smp-cmp.o obj-$(CONFIG_MIPS_CPS) += smp-cps.o cps-vec.o @@ -107,6 +105,9 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_MIPS_CM) += mips-cm.o obj-$(CONFIG_MIPS_CPC) += mips-cpc.o +obj-$(CONFIG_CPU_PM) += pm.o +obj-$(CONFIG_MIPS_CPS_PM) += pm-cps.o + # # DSP ASE supported for MIPS32 or MIPS64 Release 2 cores only. It is not # safe to unconditionnaly use the assembler -mdsp / -mdspr2 switches diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index 0ea75c244b48..02f075df8f2e 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -14,6 +14,7 @@ #include <linux/mm.h> #include <linux/kbuild.h> #include <linux/suspend.h> +#include <asm/pm.h> #include <asm/ptrace.h> #include <asm/processor.h> #include <asm/smp-cps.h> @@ -64,9 +65,6 @@ void output_ptreg_defines(void) OFFSET(PT_BVADDR, pt_regs, cp0_badvaddr); OFFSET(PT_STATUS, pt_regs, cp0_status); OFFSET(PT_CAUSE, pt_regs, cp0_cause); -#ifdef CONFIG_MIPS_MT_SMTC - OFFSET(PT_TCSTATUS, pt_regs, cp0_tcstatus); -#endif /* CONFIG_MIPS_MT_SMTC */ #ifdef CONFIG_CPU_CAVIUM_OCTEON OFFSET(PT_MPL, pt_regs, mpl); OFFSET(PT_MTP, pt_regs, mtp); @@ -404,6 +402,20 @@ void output_pbe_defines(void) } #endif +#ifdef CONFIG_CPU_PM +void output_pm_defines(void) +{ + COMMENT(" PM offsets. "); +#ifdef CONFIG_EVA + OFFSET(SSS_SEGCTL0, mips_static_suspend_state, segctl[0]); + OFFSET(SSS_SEGCTL1, mips_static_suspend_state, segctl[1]); + OFFSET(SSS_SEGCTL2, mips_static_suspend_state, segctl[2]); +#endif + OFFSET(SSS_SP, mips_static_suspend_state, sp); + BLANK(); +} +#endif + void output_kvm_defines(void) { COMMENT(" KVM/MIPS Specfic offsets. "); @@ -472,10 +484,14 @@ void output_kvm_defines(void) void output_cps_defines(void) { COMMENT(" MIPS CPS offsets. "); - OFFSET(BOOTCFG_CORE, boot_config, core); - OFFSET(BOOTCFG_VPE, boot_config, vpe); - OFFSET(BOOTCFG_PC, boot_config, pc); - OFFSET(BOOTCFG_SP, boot_config, sp); - OFFSET(BOOTCFG_GP, boot_config, gp); + + OFFSET(COREBOOTCFG_VPEMASK, core_boot_config, vpe_mask); + OFFSET(COREBOOTCFG_VPECONFIG, core_boot_config, vpe_config); + DEFINE(COREBOOTCFG_SIZE, sizeof(struct core_boot_config)); + + OFFSET(VPEBOOTCFG_PC, vpe_boot_config, pc); + OFFSET(VPEBOOTCFG_SP, vpe_boot_config, sp); + OFFSET(VPEBOOTCFG_GP, vpe_boot_config, gp); + DEFINE(VPEBOOTCFG_SIZE, sizeof(struct vpe_boot_config)); } #endif diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index 76122ff5cb5e..7b2df224f041 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -48,6 +48,202 @@ int __isa_exception_epc(struct pt_regs *regs) return epc; } +/* (microMIPS) Convert 16-bit register encoding to 32-bit register encoding. */ +static const unsigned int reg16to32map[8] = {16, 17, 2, 3, 4, 5, 6, 7}; + +int __mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, + unsigned long *contpc) +{ + union mips_instruction insn = (union mips_instruction)dec_insn.insn; + int bc_false = 0; + unsigned int fcr31; + unsigned int bit; + + if (!cpu_has_mmips) + return 0; + + switch (insn.mm_i_format.opcode) { + case mm_pool32a_op: + if ((insn.mm_i_format.simmediate & MM_POOL32A_MINOR_MASK) == + mm_pool32axf_op) { + switch (insn.mm_i_format.simmediate >> + MM_POOL32A_MINOR_SHIFT) { + case mm_jalr_op: + case mm_jalrhb_op: + case mm_jalrs_op: + case mm_jalrshb_op: + if (insn.mm_i_format.rt != 0) /* Not mm_jr */ + regs->regs[insn.mm_i_format.rt] = + regs->cp0_epc + + dec_insn.pc_inc + + dec_insn.next_pc_inc; + *contpc = regs->regs[insn.mm_i_format.rs]; + return 1; + } + } + break; + case mm_pool32i_op: + switch (insn.mm_i_format.rt) { + case mm_bltzals_op: + case mm_bltzal_op: + regs->regs[31] = regs->cp0_epc + + dec_insn.pc_inc + + dec_insn.next_pc_inc; + /* Fall through */ + case mm_bltz_op: + if ((long)regs->regs[insn.mm_i_format.rs] < 0) + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + (insn.mm_i_format.simmediate << 1); + else + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + dec_insn.next_pc_inc; + return 1; + case mm_bgezals_op: + case mm_bgezal_op: + regs->regs[31] = regs->cp0_epc + + dec_insn.pc_inc + + dec_insn.next_pc_inc; + /* Fall through */ + case mm_bgez_op: + if ((long)regs->regs[insn.mm_i_format.rs] >= 0) + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + (insn.mm_i_format.simmediate << 1); + else + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + dec_insn.next_pc_inc; + return 1; + case mm_blez_op: + if ((long)regs->regs[insn.mm_i_format.rs] <= 0) + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + (insn.mm_i_format.simmediate << 1); + else + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + dec_insn.next_pc_inc; + return 1; + case mm_bgtz_op: + if ((long)regs->regs[insn.mm_i_format.rs] <= 0) + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + (insn.mm_i_format.simmediate << 1); + else + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + dec_insn.next_pc_inc; + return 1; + case mm_bc2f_op: + case mm_bc1f_op: + bc_false = 1; + /* Fall through */ + case mm_bc2t_op: + case mm_bc1t_op: + preempt_disable(); + if (is_fpu_owner()) + asm volatile("cfc1\t%0,$31" : "=r" (fcr31)); + else + fcr31 = current->thread.fpu.fcr31; + preempt_enable(); + + if (bc_false) + fcr31 = ~fcr31; + + bit = (insn.mm_i_format.rs >> 2); + bit += (bit != 0); + bit += 23; + if (fcr31 & (1 << bit)) + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + (insn.mm_i_format.simmediate << 1); + else + *contpc = regs->cp0_epc + + dec_insn.pc_inc + dec_insn.next_pc_inc; + return 1; + } + break; + case mm_pool16c_op: + switch (insn.mm_i_format.rt) { + case mm_jalr16_op: + case mm_jalrs16_op: + regs->regs[31] = regs->cp0_epc + + dec_insn.pc_inc + dec_insn.next_pc_inc; + /* Fall through */ + case mm_jr16_op: + *contpc = regs->regs[insn.mm_i_format.rs]; + return 1; + } + break; + case mm_beqz16_op: + if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] == 0) + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + (insn.mm_b1_format.simmediate << 1); + else + *contpc = regs->cp0_epc + + dec_insn.pc_inc + dec_insn.next_pc_inc; + return 1; + case mm_bnez16_op: + if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] != 0) + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + (insn.mm_b1_format.simmediate << 1); + else + *contpc = regs->cp0_epc + + dec_insn.pc_inc + dec_insn.next_pc_inc; + return 1; + case mm_b16_op: + *contpc = regs->cp0_epc + dec_insn.pc_inc + + (insn.mm_b0_format.simmediate << 1); + return 1; + case mm_beq32_op: + if (regs->regs[insn.mm_i_format.rs] == + regs->regs[insn.mm_i_format.rt]) + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + (insn.mm_i_format.simmediate << 1); + else + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + dec_insn.next_pc_inc; + return 1; + case mm_bne32_op: + if (regs->regs[insn.mm_i_format.rs] != + regs->regs[insn.mm_i_format.rt]) + *contpc = regs->cp0_epc + + dec_insn.pc_inc + + (insn.mm_i_format.simmediate << 1); + else + *contpc = regs->cp0_epc + + dec_insn.pc_inc + dec_insn.next_pc_inc; + return 1; + case mm_jalx32_op: + regs->regs[31] = regs->cp0_epc + + dec_insn.pc_inc + dec_insn.next_pc_inc; + *contpc = regs->cp0_epc + dec_insn.pc_inc; + *contpc >>= 28; + *contpc <<= 28; + *contpc |= (insn.j_format.target << 2); + return 1; + case mm_jals32_op: + case mm_jal32_op: + regs->regs[31] = regs->cp0_epc + + dec_insn.pc_inc + dec_insn.next_pc_inc; + /* Fall through */ + case mm_j32_op: + *contpc = regs->cp0_epc + dec_insn.pc_inc; + *contpc >>= 27; + *contpc <<= 27; + *contpc |= (insn.j_format.target << 1); + set_isa16_mode(*contpc); + return 1; + } + return 0; +} + /* * Compute return address and emulate branch in microMIPS mode after an * exception only. It does not handle compact branches/jumps and cannot @@ -366,7 +562,11 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case cop1_op: preempt_disable(); if (is_fpu_owner()) - asm volatile("cfc1\t%0,$31" : "=r" (fcr31)); + asm volatile( + ".set push\n" + "\t.set mips1\n" + "\tcfc1\t%0,$31\n" + "\t.set pop" : "=r" (fcr31)); else fcr31 = current->thread.fpu.fcr31; preempt_enable(); diff --git a/arch/mips/kernel/cevt-gic.c b/arch/mips/kernel/cevt-gic.c index 594cbbf16d62..6093716980b9 100644 --- a/arch/mips/kernel/cevt-gic.c +++ b/arch/mips/kernel/cevt-gic.c @@ -26,7 +26,7 @@ static int gic_next_event(unsigned long delta, struct clock_event_device *evt) cnt = gic_read_count(); cnt += (u64)delta; - gic_write_compare(cnt); + gic_write_cpu_compare(cnt, cpumask_first(evt->cpumask)); res = ((int)(gic_read_count() - cnt) >= 0) ? -ETIME : 0; return res; } @@ -73,7 +73,8 @@ int gic_clockevent_init(void) cd = &per_cpu(gic_clockevent_device, cpu); cd->name = "MIPS GIC"; - cd->features = CLOCK_EVT_FEAT_ONESHOT; + cd->features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_C3STOP; clockevent_set_clock(cd, gic_frequency); diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 50d3f5a8d6bb..bc127e22fdab 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -12,17 +12,10 @@ #include <linux/smp.h> #include <linux/irq.h> -#include <asm/smtc_ipi.h> #include <asm/time.h> #include <asm/cevt-r4k.h> #include <asm/gic.h> -/* - * The SMTC Kernel for the 34K, 1004K, et. al. replaces several - * of these routines with SMTC-specific variants. - */ - -#ifndef CONFIG_MIPS_MT_SMTC static int mips_next_event(unsigned long delta, struct clock_event_device *evt) { @@ -36,8 +29,6 @@ static int mips_next_event(unsigned long delta, return res; } -#endif /* CONFIG_MIPS_MT_SMTC */ - void mips_set_clock_mode(enum clock_event_mode mode, struct clock_event_device *evt) { @@ -47,7 +38,6 @@ void mips_set_clock_mode(enum clock_event_mode mode, DEFINE_PER_CPU(struct clock_event_device, mips_clockevent_device); int cp0_timer_irq_installed; -#ifndef CONFIG_MIPS_MT_SMTC irqreturn_t c0_compare_interrupt(int irq, void *dev_id) { const int r2 = cpu_has_mips_r2; @@ -72,9 +62,6 @@ irqreturn_t c0_compare_interrupt(int irq, void *dev_id) /* Clear Count/Compare Interrupt */ write_c0_compare(read_c0_compare()); cd = &per_cpu(mips_clockevent_device, cpu); -#ifdef CONFIG_CEVT_GIC - if (!gic_present) -#endif cd->event_handler(cd); } @@ -82,8 +69,6 @@ out: return IRQ_HANDLED; } -#endif /* Not CONFIG_MIPS_MT_SMTC */ - struct irqaction c0_compare_irqaction = { .handler = c0_compare_interrupt, .flags = IRQF_PERCPU | IRQF_TIMER, @@ -170,7 +155,6 @@ int c0_compare_int_usable(void) return 1; } -#ifndef CONFIG_MIPS_MT_SMTC int r4k_clockevent_init(void) { unsigned int cpu = smp_processor_id(); @@ -195,7 +179,9 @@ int r4k_clockevent_init(void) cd = &per_cpu(mips_clockevent_device, cpu); cd->name = "MIPS"; - cd->features = CLOCK_EVT_FEAT_ONESHOT; + cd->features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_C3STOP | + CLOCK_EVT_FEAT_PERCPU; clockevent_set_clock(cd, mips_hpt_frequency); @@ -210,9 +196,6 @@ int r4k_clockevent_init(void) cd->set_mode = mips_set_clock_mode; cd->event_handler = mips_event_handler; -#ifdef CONFIG_CEVT_GIC - if (!gic_present) -#endif clockevents_register_device(cd); if (cp0_timer_irq_installed) @@ -225,4 +208,3 @@ int r4k_clockevent_init(void) return 0; } -#endif /* Not CONFIG_MIPS_MT_SMTC */ diff --git a/arch/mips/kernel/cevt-smtc.c b/arch/mips/kernel/cevt-smtc.c deleted file mode 100644 index b6cf0a60d896..000000000000 --- a/arch/mips/kernel/cevt-smtc.c +++ /dev/null @@ -1,324 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2007 MIPS Technologies, Inc. - * Copyright (C) 2007 Ralf Baechle <ralf@linux-mips.org> - * Copyright (C) 2008 Kevin D. Kissell, Paralogos sarl - */ -#include <linux/clockchips.h> -#include <linux/interrupt.h> -#include <linux/percpu.h> -#include <linux/smp.h> -#include <linux/irq.h> - -#include <asm/smtc_ipi.h> -#include <asm/time.h> -#include <asm/cevt-r4k.h> - -/* - * Variant clock event timer support for SMTC on MIPS 34K, 1004K - * or other MIPS MT cores. - * - * Notes on SMTC Support: - * - * SMTC has multiple microthread TCs pretending to be Linux CPUs. - * But there's only one Count/Compare pair per VPE, and Compare - * interrupts are taken opportunisitically by available TCs - * bound to the VPE with the Count register. The new timer - * framework provides for global broadcasts, but we really - * want VPE-level multicasts for best behavior. So instead - * of invoking the high-level clock-event broadcast code, - * this version of SMTC support uses the historical SMTC - * multicast mechanisms "under the hood", appearing to the - * generic clock layer as if the interrupts are per-CPU. - * - * The approach taken here is to maintain a set of NR_CPUS - * virtual timers, and track which "CPU" needs to be alerted - * at each event. - * - * It's unlikely that we'll see a MIPS MT core with more than - * 2 VPEs, but we *know* that we won't need to handle more - * VPEs than we have "CPUs". So NCPUs arrays of NCPUs elements - * is always going to be overkill, but always going to be enough. - */ - -unsigned long smtc_nexttime[NR_CPUS][NR_CPUS]; -static int smtc_nextinvpe[NR_CPUS]; - -/* - * Timestamps stored are absolute values to be programmed - * into Count register. Valid timestamps will never be zero. - * If a Zero Count value is actually calculated, it is converted - * to be a 1, which will introduce 1 or two CPU cycles of error - * roughly once every four billion events, which at 1000 HZ means - * about once every 50 days. If that's actually a problem, one - * could alternate squashing 0 to 1 and to -1. - */ - -#define MAKEVALID(x) (((x) == 0L) ? 1L : (x)) -#define ISVALID(x) ((x) != 0L) - -/* - * Time comparison is subtle, as it's really truncated - * modular arithmetic. - */ - -#define IS_SOONER(a, b, reference) \ - (((a) - (unsigned long)(reference)) < ((b) - (unsigned long)(reference))) - -/* - * CATCHUP_INCREMENT, used when the function falls behind the counter. - * Could be an increasing function instead of a constant; - */ - -#define CATCHUP_INCREMENT 64 - -static int mips_next_event(unsigned long delta, - struct clock_event_device *evt) -{ - unsigned long flags; - unsigned int mtflags; - unsigned long timestamp, reference, previous; - unsigned long nextcomp = 0L; - int vpe = current_cpu_data.vpe_id; - int cpu = smp_processor_id(); - local_irq_save(flags); - mtflags = dmt(); - - /* - * Maintain the per-TC virtual timer - * and program the per-VPE shared Count register - * as appropriate here... - */ - reference = (unsigned long)read_c0_count(); - timestamp = MAKEVALID(reference + delta); - /* - * To really model the clock, we have to catch the case - * where the current next-in-VPE timestamp is the old - * timestamp for the calling CPE, but the new value is - * in fact later. In that case, we have to do a full - * scan and discover the new next-in-VPE CPU id and - * timestamp. - */ - previous = smtc_nexttime[vpe][cpu]; - if (cpu == smtc_nextinvpe[vpe] && ISVALID(previous) - && IS_SOONER(previous, timestamp, reference)) { - int i; - int soonest = cpu; - - /* - * Update timestamp array here, so that new - * value gets considered along with those of - * other virtual CPUs on the VPE. - */ - smtc_nexttime[vpe][cpu] = timestamp; - for_each_online_cpu(i) { - if (ISVALID(smtc_nexttime[vpe][i]) - && IS_SOONER(smtc_nexttime[vpe][i], - smtc_nexttime[vpe][soonest], reference)) { - soonest = i; - } - } - smtc_nextinvpe[vpe] = soonest; - nextcomp = smtc_nexttime[vpe][soonest]; - /* - * Otherwise, we don't have to process the whole array rank, - * we just have to see if the event horizon has gotten closer. - */ - } else { - if (!ISVALID(smtc_nexttime[vpe][smtc_nextinvpe[vpe]]) || - IS_SOONER(timestamp, - smtc_nexttime[vpe][smtc_nextinvpe[vpe]], reference)) { - smtc_nextinvpe[vpe] = cpu; - nextcomp = timestamp; - } - /* - * Since next-in-VPE may me the same as the executing - * virtual CPU, we update the array *after* checking - * its value. - */ - smtc_nexttime[vpe][cpu] = timestamp; - } - - /* - * It may be that, in fact, we don't need to update Compare, - * but if we do, we want to make sure we didn't fall into - * a crack just behind Count. - */ - if (ISVALID(nextcomp)) { - write_c0_compare(nextcomp); - ehb(); - /* - * We never return an error, we just make sure - * that we trigger the handlers as quickly as - * we can if we fell behind. - */ - while ((nextcomp - (unsigned long)read_c0_count()) - > (unsigned long)LONG_MAX) { - nextcomp += CATCHUP_INCREMENT; - write_c0_compare(nextcomp); - ehb(); - } - } - emt(mtflags); - local_irq_restore(flags); - return 0; -} - - -void smtc_distribute_timer(int vpe) -{ - unsigned long flags; - unsigned int mtflags; - int cpu; - struct clock_event_device *cd; - unsigned long nextstamp; - unsigned long reference; - - -repeat: - nextstamp = 0L; - for_each_online_cpu(cpu) { - /* - * Find virtual CPUs within the current VPE who have - * unserviced timer requests whose time is now past. - */ - local_irq_save(flags); - mtflags = dmt(); - if (cpu_data[cpu].vpe_id == vpe && - ISVALID(smtc_nexttime[vpe][cpu])) { - reference = (unsigned long)read_c0_count(); - if ((smtc_nexttime[vpe][cpu] - reference) - > (unsigned long)LONG_MAX) { - smtc_nexttime[vpe][cpu] = 0L; - emt(mtflags); - local_irq_restore(flags); - /* - * We don't send IPIs to ourself. - */ - if (cpu != smp_processor_id()) { - smtc_send_ipi(cpu, SMTC_CLOCK_TICK, 0); - } else { - cd = &per_cpu(mips_clockevent_device, cpu); - cd->event_handler(cd); - } - } else { - /* Local to VPE but Valid Time not yet reached. */ - if (!ISVALID(nextstamp) || - IS_SOONER(smtc_nexttime[vpe][cpu], nextstamp, - reference)) { - smtc_nextinvpe[vpe] = cpu; - nextstamp = smtc_nexttime[vpe][cpu]; - } - emt(mtflags); - local_irq_restore(flags); - } - } else { - emt(mtflags); - local_irq_restore(flags); - - } - } - /* Reprogram for interrupt at next soonest timestamp for VPE */ - if (ISVALID(nextstamp)) { - write_c0_compare(nextstamp); - ehb(); - if ((nextstamp - (unsigned long)read_c0_count()) - > (unsigned long)LONG_MAX) - goto repeat; - } -} - - -irqreturn_t c0_compare_interrupt(int irq, void *dev_id) -{ - int cpu = smp_processor_id(); - - /* If we're running SMTC, we've got MIPS MT and therefore MIPS32R2 */ - handle_perf_irq(1); - - if (read_c0_cause() & (1 << 30)) { - /* Clear Count/Compare Interrupt */ - write_c0_compare(read_c0_compare()); - smtc_distribute_timer(cpu_data[cpu].vpe_id); - } - return IRQ_HANDLED; -} - - -int smtc_clockevent_init(void) -{ - uint64_t mips_freq = mips_hpt_frequency; - unsigned int cpu = smp_processor_id(); - struct clock_event_device *cd; - unsigned int irq; - int i; - int j; - - if (!cpu_has_counter || !mips_hpt_frequency) - return -ENXIO; - if (cpu == 0) { - for (i = 0; i < num_possible_cpus(); i++) { - smtc_nextinvpe[i] = 0; - for (j = 0; j < num_possible_cpus(); j++) - smtc_nexttime[i][j] = 0L; - } - /* - * SMTC also can't have the usablility test - * run by secondary TCs once Compare is in use. - */ - if (!c0_compare_int_usable()) - return -ENXIO; - } - - /* - * With vectored interrupts things are getting platform specific. - * get_c0_compare_int is a hook to allow a platform to return the - * interrupt number of it's liking. - */ - irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq; - if (get_c0_compare_int) - irq = get_c0_compare_int(); - - cd = &per_cpu(mips_clockevent_device, cpu); - - cd->name = "MIPS"; - cd->features = CLOCK_EVT_FEAT_ONESHOT; - - /* Calculate the min / max delta */ - cd->mult = div_sc((unsigned long) mips_freq, NSEC_PER_SEC, 32); - cd->shift = 32; - cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd); - cd->min_delta_ns = clockevent_delta2ns(0x300, cd); - - cd->rating = 300; - cd->irq = irq; - cd->cpumask = cpumask_of(cpu); - cd->set_next_event = mips_next_event; - cd->set_mode = mips_set_clock_mode; - cd->event_handler = mips_event_handler; - - clockevents_register_device(cd); - - /* - * On SMTC we only want to do the data structure - * initialization and IRQ setup once. - */ - if (cpu) - return 0; - /* - * And we need the hwmask associated with the c0_compare - * vector to be initialized. - */ - irq_hwmask[irq] = (0x100 << cp0_compare_irq); - if (cp0_timer_irq_installed) - return 0; - - cp0_timer_irq_installed = 1; - - setup_irq(irq, &c0_compare_irqaction); - - return 0; -} diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index f7a46db4b161..6f4f739dad96 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -14,19 +14,43 @@ #include <asm/asmmacro.h> #include <asm/cacheops.h> #include <asm/mipsregs.h> +#include <asm/mipsmtregs.h> +#include <asm/pm.h> -#define GCR_CL_COHERENCE_OFS 0x2008 +#define GCR_CL_COHERENCE_OFS 0x2008 +#define GCR_CL_ID_OFS 0x2028 + +.extern mips_cm_base + +.set noreorder + + /* + * Set dest to non-zero if the core supports the MT ASE, else zero. If + * MT is not supported then branch to nomt. + */ + .macro has_mt dest, nomt + mfc0 \dest, CP0_CONFIG + bgez \dest, \nomt + mfc0 \dest, CP0_CONFIG, 1 + bgez \dest, \nomt + mfc0 \dest, CP0_CONFIG, 2 + bgez \dest, \nomt + mfc0 \dest, CP0_CONFIG, 3 + andi \dest, \dest, MIPS_CONF3_MT + beqz \dest, \nomt + .endm .section .text.cps-vec .balign 0x1000 -.set noreorder LEAF(mips_cps_core_entry) /* - * These first 8 bytes will be patched by cps_smp_setup to load the - * base address of the CM GCRs into register v1. + * These first 12 bytes will be patched by cps_smp_setup to load the + * base address of the CM GCRs into register v1 and the CCA to use into + * register s0. */ .quad 0 + .word 0 /* Check whether we're here due to an NMI */ mfc0 k0, CP0_STATUS @@ -117,10 +141,11 @@ icache_done: add a0, a0, t0 dcache_done: - /* Set Kseg0 cacheable, coherent, write-back, write-allocate */ + /* Set Kseg0 CCA to that in s0 */ mfc0 t0, CP0_CONFIG ori t0, 0x7 - xori t0, 0x2 + xori t0, 0x7 + or t0, t0, s0 mtc0 t0, CP0_CONFIG ehb @@ -134,21 +159,24 @@ dcache_done: jr t0 nop -1: /* We're up, cached & coherent */ + /* + * We're up, cached & coherent. Perform any further required core-level + * initialisation. + */ +1: jal mips_cps_core_init + nop /* - * TODO: We should check the VPE number we intended to boot here, and - * if non-zero we should start that VPE and stop this one. For - * the moment this doesn't matter since CPUs are brought up - * sequentially and in order, but once hotplug is implemented - * this will need revisiting. + * Boot any other VPEs within this core that should be online, and + * deactivate this VPE if it should be offline. */ + jal mips_cps_boot_vpes + nop /* Off we go! */ - la t0, mips_cps_bootcfg - lw t1, BOOTCFG_PC(t0) - lw gp, BOOTCFG_GP(t0) - lw sp, BOOTCFG_SP(t0) + lw t1, VPEBOOTCFG_PC(v0) + lw gp, VPEBOOTCFG_GP(v0) + lw sp, VPEBOOTCFG_SP(v0) jr t1 nop END(mips_cps_core_entry) @@ -189,3 +217,271 @@ LEAF(excep_ejtag) jr k0 nop END(excep_ejtag) + +LEAF(mips_cps_core_init) +#ifdef CONFIG_MIPS_MT + /* Check that the core implements the MT ASE */ + has_mt t0, 3f + nop + + .set push + .set mt + + /* Only allow 1 TC per VPE to execute... */ + dmt + + /* ...and for the moment only 1 VPE */ + dvpe + la t1, 1f + jr.hb t1 + nop + + /* Enter VPE configuration state */ +1: mfc0 t0, CP0_MVPCONTROL + ori t0, t0, MVPCONTROL_VPC + mtc0 t0, CP0_MVPCONTROL + + /* Retrieve the number of VPEs within the core */ + mfc0 t0, CP0_MVPCONF0 + srl t0, t0, MVPCONF0_PVPE_SHIFT + andi t0, t0, (MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT) + addi t7, t0, 1 + + /* If there's only 1, we're done */ + beqz t0, 2f + nop + + /* Loop through each VPE within this core */ + li t5, 1 + +1: /* Operate on the appropriate TC */ + mtc0 t5, CP0_VPECONTROL + ehb + + /* Bind TC to VPE (1:1 TC:VPE mapping) */ + mttc0 t5, CP0_TCBIND + + /* Set exclusive TC, non-active, master */ + li t0, VPECONF0_MVP + sll t1, t5, VPECONF0_XTC_SHIFT + or t0, t0, t1 + mttc0 t0, CP0_VPECONF0 + + /* Set TC non-active, non-allocatable */ + mttc0 zero, CP0_TCSTATUS + + /* Set TC halted */ + li t0, TCHALT_H + mttc0 t0, CP0_TCHALT + + /* Next VPE */ + addi t5, t5, 1 + slt t0, t5, t7 + bnez t0, 1b + nop + + /* Leave VPE configuration state */ +2: mfc0 t0, CP0_MVPCONTROL + xori t0, t0, MVPCONTROL_VPC + mtc0 t0, CP0_MVPCONTROL + +3: .set pop +#endif + jr ra + nop + END(mips_cps_core_init) + +LEAF(mips_cps_boot_vpes) + /* Retrieve CM base address */ + la t0, mips_cm_base + lw t0, 0(t0) + + /* Calculate a pointer to this cores struct core_boot_config */ + lw t0, GCR_CL_ID_OFS(t0) + li t1, COREBOOTCFG_SIZE + mul t0, t0, t1 + la t1, mips_cps_core_bootcfg + lw t1, 0(t1) + addu t0, t0, t1 + + /* Calculate this VPEs ID. If the core doesn't support MT use 0 */ + has_mt t6, 1f + li t9, 0 + + /* Find the number of VPEs present in the core */ + mfc0 t1, CP0_MVPCONF0 + srl t1, t1, MVPCONF0_PVPE_SHIFT + andi t1, t1, MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT + addi t1, t1, 1 + + /* Calculate a mask for the VPE ID from EBase.CPUNum */ + clz t1, t1 + li t2, 31 + subu t1, t2, t1 + li t2, 1 + sll t1, t2, t1 + addiu t1, t1, -1 + + /* Retrieve the VPE ID from EBase.CPUNum */ + mfc0 t9, $15, 1 + and t9, t9, t1 + +1: /* Calculate a pointer to this VPEs struct vpe_boot_config */ + li t1, VPEBOOTCFG_SIZE + mul v0, t9, t1 + lw t7, COREBOOTCFG_VPECONFIG(t0) + addu v0, v0, t7 + +#ifdef CONFIG_MIPS_MT + + /* If the core doesn't support MT then return */ + bnez t6, 1f + nop + jr ra + nop + + .set push + .set mt + +1: /* Enter VPE configuration state */ + dvpe + la t1, 1f + jr.hb t1 + nop +1: mfc0 t1, CP0_MVPCONTROL + ori t1, t1, MVPCONTROL_VPC + mtc0 t1, CP0_MVPCONTROL + ehb + + /* Loop through each VPE */ + lw t6, COREBOOTCFG_VPEMASK(t0) + move t8, t6 + li t5, 0 + + /* Check whether the VPE should be running. If not, skip it */ +1: andi t0, t6, 1 + beqz t0, 2f + nop + + /* Operate on the appropriate TC */ + mfc0 t0, CP0_VPECONTROL + ori t0, t0, VPECONTROL_TARGTC + xori t0, t0, VPECONTROL_TARGTC + or t0, t0, t5 + mtc0 t0, CP0_VPECONTROL + ehb + + /* Skip the VPE if its TC is not halted */ + mftc0 t0, CP0_TCHALT + beqz t0, 2f + nop + + /* Calculate a pointer to the VPEs struct vpe_boot_config */ + li t0, VPEBOOTCFG_SIZE + mul t0, t0, t5 + addu t0, t0, t7 + + /* Set the TC restart PC */ + lw t1, VPEBOOTCFG_PC(t0) + mttc0 t1, CP0_TCRESTART + + /* Set the TC stack pointer */ + lw t1, VPEBOOTCFG_SP(t0) + mttgpr t1, sp + + /* Set the TC global pointer */ + lw t1, VPEBOOTCFG_GP(t0) + mttgpr t1, gp + + /* Copy config from this VPE */ + mfc0 t0, CP0_CONFIG + mttc0 t0, CP0_CONFIG + + /* Ensure no software interrupts are pending */ + mttc0 zero, CP0_CAUSE + mttc0 zero, CP0_STATUS + + /* Set TC active, not interrupt exempt */ + mftc0 t0, CP0_TCSTATUS + li t1, ~TCSTATUS_IXMT + and t0, t0, t1 + ori t0, t0, TCSTATUS_A + mttc0 t0, CP0_TCSTATUS + + /* Clear the TC halt bit */ + mttc0 zero, CP0_TCHALT + + /* Set VPE active */ + mftc0 t0, CP0_VPECONF0 + ori t0, t0, VPECONF0_VPA + mttc0 t0, CP0_VPECONF0 + + /* Next VPE */ +2: srl t6, t6, 1 + addi t5, t5, 1 + bnez t6, 1b + nop + + /* Leave VPE configuration state */ + mfc0 t1, CP0_MVPCONTROL + xori t1, t1, MVPCONTROL_VPC + mtc0 t1, CP0_MVPCONTROL + ehb + evpe + + /* Check whether this VPE is meant to be running */ + li t0, 1 + sll t0, t0, t9 + and t0, t0, t8 + bnez t0, 2f + nop + + /* This VPE should be offline, halt the TC */ + li t0, TCHALT_H + mtc0 t0, CP0_TCHALT + la t0, 1f +1: jr.hb t0 + nop + +2: .set pop + +#endif /* CONFIG_MIPS_MT */ + + /* Return */ + jr ra + nop + END(mips_cps_boot_vpes) + +#if defined(CONFIG_MIPS_CPS_PM) && defined(CONFIG_CPU_PM) + + /* Calculate a pointer to this CPUs struct mips_static_suspend_state */ + .macro psstate dest + .set push + .set noat + lw $1, TI_CPU(gp) + sll $1, $1, LONGLOG + la \dest, __per_cpu_offset + addu $1, $1, \dest + lw $1, 0($1) + la \dest, cps_cpu_state + addu \dest, \dest, $1 + .set pop + .endm + +LEAF(mips_cps_pm_save) + /* Save CPU state */ + SUSPEND_SAVE_REGS + psstate t1 + SUSPEND_SAVE_STATIC + jr v0 + nop + END(mips_cps_pm_save) + +LEAF(mips_cps_pm_restore) + /* Restore CPU state */ + psstate t1 + RESUME_RESTORE_STATIC + RESUME_RESTORE_REGS_RETURN + END(mips_cps_pm_restore) + +#endif /* CONFIG_MIPS_CPS_PM && CONFIG_CPU_PM */ diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 6e8fb85ce7c3..d74f957c561e 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -62,7 +62,7 @@ static inline void check_errata(void) case CPU_34K: /* * Erratum "RPS May Cause Incorrect Instruction Execution" - * This code only handles VPE0, any SMP/SMTC/RTOS code + * This code only handles VPE0, any SMP/RTOS code * making use of VPE1 will be responsable for that VPE. */ if ((c->processor_id & PRID_REV_MASK) <= PRID_REV_34K_V1_0_2) @@ -423,7 +423,7 @@ static void decode_configs(struct cpuinfo_mips *c) #ifndef CONFIG_MIPS_CPS if (cpu_has_mips_r2) { - c->core = read_c0_ebase() & 0x3ff; + c->core = get_ebase_cpunum(); if (cpu_has_mipsmt) c->core >>= fls(core_nvpes()) - 1; } @@ -684,21 +684,6 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) */ c->tlbsize = (read_c0_info() & (1 << 29)) ? 64 : 48; break; - case PRID_IMP_RM9000: - c->cputype = CPU_RM9000; - __cpu_name[cpu] = "RM9000"; - set_isa(c, MIPS_CPU_ISA_IV); - c->options = R4K_OPTS | MIPS_CPU_FPU | MIPS_CPU_32FPR | - MIPS_CPU_LLSC; - /* - * Bit 29 in the info register of the RM9000 - * indicates if the TLB has 48 or 64 entries. - * - * 29 1 => 64 entry JTLB - * 0 => 48 entry JTLB - */ - c->tlbsize = (read_c0_info() & (1 << 29)) ? 64 : 48; - break; case PRID_IMP_R8000: c->cputype = CPU_R8000; __cpu_name[cpu] = "RM8000"; @@ -1041,6 +1026,7 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu) decode_configs(c); /* JZRISC does not implement the CP0 counter. */ c->options &= ~MIPS_CPU_COUNTER; + BUG_ON(!__builtin_constant_p(cpu_has_counter) || cpu_has_counter); switch (c->processor_id & PRID_IMP_MASK) { case PRID_IMP_JZRISC: c->cputype = CPU_JZRISC; @@ -1074,6 +1060,7 @@ static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu) switch (c->processor_id & PRID_IMP_MASK) { case PRID_IMP_NETLOGIC_XLP2XX: case PRID_IMP_NETLOGIC_XLP9XX: + case PRID_IMP_NETLOGIC_XLP5XX: c->cputype = CPU_XLP; __cpu_name[cpu] = "Broadcom XLPII"; break; diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S index e5786858cdb6..4353d323f017 100644 --- a/arch/mips/kernel/entry.S +++ b/arch/mips/kernel/entry.S @@ -16,9 +16,6 @@ #include <asm/isadep.h> #include <asm/thread_info.h> #include <asm/war.h> -#ifdef CONFIG_MIPS_MT_SMTC -#include <asm/mipsmtregs.h> -#endif #ifndef CONFIG_PREEMPT #define resume_kernel restore_all @@ -89,41 +86,6 @@ FEXPORT(syscall_exit) bnez t0, syscall_exit_work restore_all: # restore full frame -#ifdef CONFIG_MIPS_MT_SMTC -#ifdef CONFIG_MIPS_MT_SMTC_IM_BACKSTOP -/* Re-arm any temporarily masked interrupts not explicitly "acked" */ - mfc0 v0, CP0_TCSTATUS - ori v1, v0, TCSTATUS_IXMT - mtc0 v1, CP0_TCSTATUS - andi v0, TCSTATUS_IXMT - _ehb - mfc0 t0, CP0_TCCONTEXT - DMT 9 # dmt t1 - jal mips_ihb - mfc0 t2, CP0_STATUS - andi t3, t0, 0xff00 - or t2, t2, t3 - mtc0 t2, CP0_STATUS - _ehb - andi t1, t1, VPECONTROL_TE - beqz t1, 1f - EMT -1: - mfc0 v1, CP0_TCSTATUS - /* We set IXMT above, XOR should clear it here */ - xori v1, v1, TCSTATUS_IXMT - or v1, v0, v1 - mtc0 v1, CP0_TCSTATUS - _ehb - xor t0, t0, t3 - mtc0 t0, CP0_TCCONTEXT -#endif /* CONFIG_MIPS_MT_SMTC_IM_BACKSTOP */ -/* Detect and execute deferred IPI "interrupts" */ - LONG_L s0, TI_REGS($28) - LONG_S sp, TI_REGS($28) - jal deferred_smtc_ipi - LONG_S s0, TI_REGS($28) -#endif /* CONFIG_MIPS_MT_SMTC */ .set noat RESTORE_TEMP RESTORE_AT diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index a9ce3408be25..ac35e12cb1f3 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -21,20 +21,6 @@ #include <asm/war.h> #include <asm/thread_info.h> -#ifdef CONFIG_MIPS_MT_SMTC -#define PANIC_PIC(msg) \ - .set push; \ - .set nomicromips; \ - .set reorder; \ - PTR_LA a0,8f; \ - .set noat; \ - PTR_LA AT, panic; \ - jr AT; \ -9: b 9b; \ - .set pop; \ - TEXT(msg) -#endif - __INIT /* @@ -251,15 +237,6 @@ NESTED(except_vec_vi, 0, sp) SAVE_AT .set push .set noreorder -#ifdef CONFIG_MIPS_MT_SMTC - /* - * To keep from blindly blocking *all* interrupts - * during service by SMTC kernel, we also want to - * pass the IM value to be cleared. - */ -FEXPORT(except_vec_vi_mori) - ori a0, $0, 0 -#endif /* CONFIG_MIPS_MT_SMTC */ PTR_LA v1, except_vec_vi_handler FEXPORT(except_vec_vi_lui) lui v0, 0 /* Patched */ @@ -277,37 +254,10 @@ EXPORT(except_vec_vi_end) NESTED(except_vec_vi_handler, 0, sp) SAVE_TEMP SAVE_STATIC -#ifdef CONFIG_MIPS_MT_SMTC - /* - * SMTC has an interesting problem that interrupts are level-triggered, - * and the CLI macro will clear EXL, potentially causing a duplicate - * interrupt service invocation. So we need to clear the associated - * IM bit of Status prior to doing CLI, and restore it after the - * service routine has been invoked - we must assume that the - * service routine will have cleared the state, and any active - * level represents a new or otherwised unserviced event... - */ - mfc0 t1, CP0_STATUS - and t0, a0, t1 -#ifdef CONFIG_MIPS_MT_SMTC_IM_BACKSTOP - mfc0 t2, CP0_TCCONTEXT - or t2, t0, t2 - mtc0 t2, CP0_TCCONTEXT -#endif /* CONFIG_MIPS_MT_SMTC_IM_BACKSTOP */ - xor t1, t1, t0 - mtc0 t1, CP0_STATUS - _ehb -#endif /* CONFIG_MIPS_MT_SMTC */ CLI #ifdef CONFIG_TRACE_IRQFLAGS move s0, v0 -#ifdef CONFIG_MIPS_MT_SMTC - move s1, a0 -#endif TRACE_IRQS_OFF -#ifdef CONFIG_MIPS_MT_SMTC - move a0, s1 -#endif move v0, s0 #endif @@ -496,9 +446,6 @@ NESTED(nmi_handler, PT_SIZE, sp) .align 5 LEAF(handle_ri_rdhwr_vivt) -#ifdef CONFIG_MIPS_MT_SMTC - PANIC_PIC("handle_ri_rdhwr_vivt called") -#else .set push .set noat .set noreorder @@ -517,7 +464,6 @@ NESTED(nmi_handler, PT_SIZE, sp) .set pop bltz k1, handle_ri /* slow path */ /* fall thru */ -#endif END(handle_ri_rdhwr_vivt) LEAF(handle_ri_rdhwr) diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S index e712dcf18b2d..95afd663cd45 100644 --- a/arch/mips/kernel/head.S +++ b/arch/mips/kernel/head.S @@ -35,33 +35,12 @@ */ .macro setup_c0_status set clr .set push -#ifdef CONFIG_MIPS_MT_SMTC - /* - * For SMTC, we need to set privilege and disable interrupts only for - * the current TC, using the TCStatus register. - */ - mfc0 t0, CP0_TCSTATUS - /* Fortunately CU 0 is in the same place in both registers */ - /* Set TCU0, TMX, TKSU (for later inversion) and IXMT */ - li t1, ST0_CU0 | 0x08001c00 - or t0, t1 - /* Clear TKSU, leave IXMT */ - xori t0, 0x00001800 - mtc0 t0, CP0_TCSTATUS - _ehb - /* We need to leave the global IE bit set, but clear EXL...*/ - mfc0 t0, CP0_STATUS - or t0, ST0_CU0 | ST0_EXL | ST0_ERL | \set | \clr - xor t0, ST0_EXL | ST0_ERL | \clr - mtc0 t0, CP0_STATUS -#else mfc0 t0, CP0_STATUS or t0, ST0_CU0|\set|0x1f|\clr xor t0, 0x1f|\clr mtc0 t0, CP0_STATUS .set noreorder sll zero,3 # ehb -#endif .set pop .endm @@ -115,24 +94,6 @@ NESTED(kernel_entry, 16, sp) # kernel entry point jr t0 0: -#ifdef CONFIG_MIPS_MT_SMTC - /* - * In SMTC kernel, "CLI" is thread-specific, in TCStatus. - * We still need to enable interrupts globally in Status, - * and clear EXL/ERL. - * - * TCContext is used to track interrupt levels under - * service in SMTC kernel. Clear for boot TC before - * allowing any interrupts. - */ - mtc0 zero, CP0_TCCONTEXT - - mfc0 t0, CP0_STATUS - ori t0, t0, 0xff1f - xori t0, t0, 0x001e - mtc0 t0, CP0_STATUS -#endif /* CONFIG_MIPS_MT_SMTC */ - PTR_LA t0, __bss_start # clear .bss LONG_S zero, (t0) PTR_LA t1, __bss_stop - LONGSIZE @@ -164,25 +125,8 @@ NESTED(kernel_entry, 16, sp) # kernel entry point * function after setting up the stack and gp registers. */ NESTED(smp_bootstrap, 16, sp) -#ifdef CONFIG_MIPS_MT_SMTC - /* - * Read-modify-writes of Status must be atomic, and this - * is one case where CLI is invoked without EXL being - * necessarily set. The CLI and setup_c0_status will - * in fact be redundant for all but the first TC of - * each VPE being booted. - */ - DMT 10 # dmt t2 /* t0, t1 are used by CLI and setup_c0_status() */ - jal mips_ihb -#endif /* CONFIG_MIPS_MT_SMTC */ smp_slave_setup setup_c0_status_sec -#ifdef CONFIG_MIPS_MT_SMTC - andi t2, t2, VPECONTROL_TE - beqz t2, 2f - EMT # emt -2: -#endif /* CONFIG_MIPS_MT_SMTC */ j start_secondary END(smp_bootstrap) #endif /* CONFIG_SMP */ diff --git a/arch/mips/kernel/i8259.c b/arch/mips/kernel/i8259.c index 2b91fe80c436..50b364897dda 100644 --- a/arch/mips/kernel/i8259.c +++ b/arch/mips/kernel/i8259.c @@ -42,9 +42,6 @@ static struct irq_chip i8259A_chip = { .irq_disable = disable_8259A_irq, .irq_unmask = enable_8259A_irq, .irq_mask_ack = mask_and_ack_8259A, -#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF - .irq_set_affinity = plat_set_irq_affinity, -#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ }; /* @@ -180,7 +177,6 @@ handle_real_irq: outb(cached_master_mask, PIC_MASTER_IMR); outb(0x60+irq, PIC_MASTER_CMD); /* 'Specific EOI to master */ } - smtc_im_ack_irq(irq); raw_spin_unlock_irqrestore(&i8259A_lock, flags); return; diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index 837ff27950bc..09ce45980758 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -224,29 +224,26 @@ void __init check_wait(void) cpu_wait = r4k_wait; */ break; - case CPU_RM9000: - if ((c->processor_id & 0x00ff) >= 0x40) - cpu_wait = r4k_wait; - break; default: break; } } -static void smtc_idle_hook(void) -{ -#ifdef CONFIG_MIPS_MT_SMTC - void smtc_idle_loop_hook(void); - - smtc_idle_loop_hook(); -#endif -} - void arch_cpu_idle(void) { - smtc_idle_hook(); if (cpu_wait) cpu_wait(); else local_irq_enable(); } + +#ifdef CONFIG_CPU_IDLE + +int mips_cpuidle_wait_enter(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + arch_cpu_idle(); + return index; +} + +#endif diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c index 8520dad6d4e3..88e4c323382c 100644 --- a/arch/mips/kernel/irq-gic.c +++ b/arch/mips/kernel/irq-gic.c @@ -54,6 +54,21 @@ void gic_write_compare(cycle_t cnt) (int)(cnt & 0xffffffff)); } +void gic_write_cpu_compare(cycle_t cnt, int cpu) +{ + unsigned long flags; + + local_irq_save(flags); + + GICWRITE(GIC_REG(VPE_LOCAL, GIC_VPE_OTHER_ADDR), cpu); + GICWRITE(GIC_REG(VPE_OTHER, GIC_VPE_COMPARE_HI), + (int)(cnt >> 32)); + GICWRITE(GIC_REG(VPE_OTHER, GIC_VPE_COMPARE_LO), + (int)(cnt & 0xffffffff)); + + local_irq_restore(flags); +} + cycle_t gic_read_compare(void) { unsigned int hi, lo; diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c index fab40f7d2e03..4858642d543d 100644 --- a/arch/mips/kernel/irq-msc01.c +++ b/arch/mips/kernel/irq-msc01.c @@ -53,13 +53,9 @@ static inline void unmask_msc_irq(struct irq_data *d) */ static void level_mask_and_ack_msc_irq(struct irq_data *d) { - unsigned int irq = d->irq; - mask_msc_irq(d); if (!cpu_has_veic) MSCIC_WRITE(MSC01_IC_EOI, 0); - /* This actually needs to be a call into platform code */ - smtc_im_ack_irq(irq); } /* @@ -78,7 +74,6 @@ static void edge_mask_and_ack_msc_irq(struct irq_data *d) MSCIC_WRITE(MSC01_IC_SUP+irq*8, r | ~MSC01_IC_SUP_EDGE_BIT); MSCIC_WRITE(MSC01_IC_SUP+irq*8, r); } - smtc_im_ack_irq(irq); } /* diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c index 1818da4dbb85..d2bfbc2e8995 100644 --- a/arch/mips/kernel/irq.c +++ b/arch/mips/kernel/irq.c @@ -73,7 +73,6 @@ void free_irqno(unsigned int irq) */ void ack_bad_irq(unsigned int irq) { - smtc_im_ack_irq(irq); printk("unexpected IRQ # %d\n", irq); } @@ -142,23 +141,7 @@ void __irq_entry do_IRQ(unsigned int irq) { irq_enter(); check_stack_overflow(); - if (!smtc_handle_on_other_cpu(irq)) - generic_handle_irq(irq); - irq_exit(); -} - -#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF -/* - * To avoid inefficient and in some cases pathological re-checking of - * IRQ affinity, we have this variant that skips the affinity check. - */ - -void __irq_entry do_IRQ_no_affinity(unsigned int irq) -{ - irq_enter(); - smtc_im_backstop(irq); generic_handle_irq(irq); irq_exit(); } -#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c index c9dc67402969..ba473608a347 100644 --- a/arch/mips/kernel/mips-cpc.c +++ b/arch/mips/kernel/mips-cpc.c @@ -9,12 +9,18 @@ */ #include <linux/errno.h> +#include <linux/percpu.h> +#include <linux/spinlock.h> #include <asm/mips-cm.h> #include <asm/mips-cpc.h> void __iomem *mips_cpc_base; +static DEFINE_PER_CPU_ALIGNED(spinlock_t, cpc_core_lock); + +static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags); + phys_t __weak mips_cpc_phys_base(void) { u32 cpc_base; @@ -39,6 +45,10 @@ phys_t __weak mips_cpc_phys_base(void) int mips_cpc_probe(void) { phys_t addr; + unsigned cpu; + + for_each_possible_cpu(cpu) + spin_lock_init(&per_cpu(cpc_core_lock, cpu)); addr = mips_cpc_phys_base(); if (!addr) @@ -50,3 +60,21 @@ int mips_cpc_probe(void) return 0; } + +void mips_cpc_lock_other(unsigned int core) +{ + unsigned curr_core; + preempt_disable(); + curr_core = current_cpu_data.core; + spin_lock_irqsave(&per_cpu(cpc_core_lock, curr_core), + per_cpu(cpc_core_lock_flags, curr_core)); + write_cpc_cl_other(core << CPC_Cx_OTHER_CORENUM_SHF); +} + +void mips_cpc_unlock_other(void) +{ + unsigned curr_core = current_cpu_data.core; + spin_unlock_irqrestore(&per_cpu(cpc_core_lock, curr_core), + per_cpu(cpc_core_lock_flags, curr_core)); + preempt_enable(); +} diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c index cb098628aee8..362bb3707e62 100644 --- a/arch/mips/kernel/mips-mt-fpaff.c +++ b/arch/mips/kernel/mips-mt-fpaff.c @@ -1,5 +1,5 @@ /* - * General MIPS MT support routines, usable in AP/SP, SMVP, or SMTC kernels + * General MIPS MT support routines, usable in AP/SP and SMVP. * Copyright (C) 2005 Mips Technologies, Inc */ #include <linux/cpu.h> diff --git a/arch/mips/kernel/mips-mt.c b/arch/mips/kernel/mips-mt.c index 6ded9bd1489c..88b1ef5f868a 100644 --- a/arch/mips/kernel/mips-mt.c +++ b/arch/mips/kernel/mips-mt.c @@ -1,5 +1,5 @@ /* - * General MIPS MT support routines, usable in AP/SP, SMVP, or SMTC kernels + * General MIPS MT support routines, usable in AP/SP and SMVP. * Copyright (C) 2005 Mips Technologies, Inc */ @@ -57,9 +57,6 @@ void mips_mt_regdump(unsigned long mvpctl) int tc; unsigned long haltval; unsigned long tcstatval; -#ifdef CONFIG_MIPS_MT_SMTC - void smtc_soft_dump(void); -#endif /* CONFIG_MIPT_MT_SMTC */ local_irq_save(flags); vpflags = dvpe(); @@ -116,9 +113,6 @@ void mips_mt_regdump(unsigned long mvpctl) if (!haltval) write_tc_c0_tchalt(0); } -#ifdef CONFIG_MIPS_MT_SMTC - smtc_soft_dump(); -#endif /* CONFIG_MIPT_MT_SMTC */ printk("===========================\n"); evpe(vpflags); local_irq_restore(flags); @@ -295,21 +289,11 @@ void mips_mt_set_cpuoptions(void) void mt_cflush_lockdown(void) { -#ifdef CONFIG_MIPS_MT_SMTC - void smtc_cflush_lockdown(void); - - smtc_cflush_lockdown(); -#endif /* CONFIG_MIPS_MT_SMTC */ /* FILL IN VSMP and AP/SP VERSIONS HERE */ } void mt_cflush_release(void) { -#ifdef CONFIG_MIPS_MT_SMTC - void smtc_cflush_release(void); - - smtc_cflush_release(); -#endif /* CONFIG_MIPS_MT_SMTC */ /* FILL IN VSMP and AP/SP VERSIONS HERE */ } diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S index 029e002a4ea0..f6547680c81c 100644 --- a/arch/mips/kernel/octeon_switch.S +++ b/arch/mips/kernel/octeon_switch.S @@ -10,24 +10,12 @@ * Copyright (C) 2000 MIPS Technologies, Inc. * written by Carsten Langgaard, carstenl@mips.com */ -#include <asm/asm.h> -#include <asm/cachectl.h> -#include <asm/fpregdef.h> -#include <asm/mipsregs.h> -#include <asm/asm-offsets.h> -#include <asm/pgtable-bits.h> -#include <asm/regdef.h> -#include <asm/stackframe.h> -#include <asm/thread_info.h> - -#include <asm/asmmacro.h> - -/* - * Offset to the current process status flags, the first 32 bytes of the - * stack are not used. - */ -#define ST_OFF (_THREAD_SIZE - 32 - PT_SIZE + PT_STATUS) +#define USE_ALTERNATE_RESUME_IMPL 1 + .set push + .set arch=mips64r2 +#include "r4k_switch.S" + .set pop /* * task_struct *resume(task_struct *prev, task_struct *next, * struct thread_info *next_ti, int usedfpu) @@ -40,6 +28,61 @@ cpu_save_nonscratch a0 LONG_S ra, THREAD_REG31(a0) + /* + * check if we need to save FPU registers + */ + PTR_L t3, TASK_THREAD_INFO(a0) + LONG_L t0, TI_FLAGS(t3) + li t1, _TIF_USEDFPU + and t2, t0, t1 + beqz t2, 1f + nor t1, zero, t1 + + and t0, t0, t1 + LONG_S t0, TI_FLAGS(t3) + + /* + * clear saved user stack CU1 bit + */ + LONG_L t0, ST_OFF(t3) + li t1, ~ST0_CU1 + and t0, t0, t1 + LONG_S t0, ST_OFF(t3) + + .set push + .set arch=mips64r2 + fpu_save_double a0 t0 t1 # c0_status passed in t0 + # clobbers t1 + .set pop +1: + + /* check if we need to save COP2 registers */ + PTR_L t2, TASK_THREAD_INFO(a0) + LONG_L t0, ST_OFF(t2) + bbit0 t0, 30, 1f + + /* Disable COP2 in the stored process state */ + li t1, ST0_CU2 + xor t0, t1 + LONG_S t0, ST_OFF(t2) + + /* Enable COP2 so we can save it */ + mfc0 t0, CP0_STATUS + or t0, t1 + mtc0 t0, CP0_STATUS + + /* Save COP2 */ + daddu a0, THREAD_CP2 + jal octeon_cop2_save + dsubu a0, THREAD_CP2 + + /* Disable COP2 now that we are done */ + mfc0 t0, CP0_STATUS + li t1, ST0_CU2 + xor t0, t1 + mtc0 t0, CP0_STATUS + +1: #if CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0 /* Check if we need to store CVMSEG state */ mfc0 t0, $11,7 /* CvmMemCtl */ @@ -85,12 +128,7 @@ move $28, a2 cpu_restore_nonscratch a1 -#if (_THREAD_SIZE - 32) < 0x8000 - PTR_ADDIU t0, $28, _THREAD_SIZE - 32 -#else - PTR_LI t0, _THREAD_SIZE - 32 - PTR_ADDU t0, $28 -#endif + PTR_ADDU t0, $28, _THREAD_SIZE - 32 set_saved_sp t0, t1, t2 mfc0 t1, CP0_STATUS /* Do we really need this? */ diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c new file mode 100644 index 000000000000..5aa4c6f8cf83 --- /dev/null +++ b/arch/mips/kernel/pm-cps.c @@ -0,0 +1,716 @@ +/* + * Copyright (C) 2014 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/init.h> +#include <linux/percpu.h> +#include <linux/slab.h> + +#include <asm/asm-offsets.h> +#include <asm/cacheflush.h> +#include <asm/cacheops.h> +#include <asm/idle.h> +#include <asm/mips-cm.h> +#include <asm/mips-cpc.h> +#include <asm/mipsmtregs.h> +#include <asm/pm.h> +#include <asm/pm-cps.h> +#include <asm/smp-cps.h> +#include <asm/uasm.h> + +/* + * cps_nc_entry_fn - type of a generated non-coherent state entry function + * @online: the count of online coupled VPEs + * @nc_ready_count: pointer to a non-coherent mapping of the core ready_count + * + * The code entering & exiting non-coherent states is generated at runtime + * using uasm, in order to ensure that the compiler cannot insert a stray + * memory access at an unfortunate time and to allow the generation of optimal + * core-specific code particularly for cache routines. If coupled_coherence + * is non-zero and this is the entry function for the CPS_PM_NC_WAIT state, + * returns the number of VPEs that were in the wait state at the point this + * VPE left it. Returns garbage if coupled_coherence is zero or this is not + * the entry function for CPS_PM_NC_WAIT. + */ +typedef unsigned (*cps_nc_entry_fn)(unsigned online, u32 *nc_ready_count); + +/* + * The entry point of the generated non-coherent idle state entry/exit + * functions. Actually per-core rather than per-CPU. + */ +static DEFINE_PER_CPU_READ_MOSTLY(cps_nc_entry_fn[CPS_PM_STATE_COUNT], + nc_asm_enter); + +/* Bitmap indicating which states are supported by the system */ +DECLARE_BITMAP(state_support, CPS_PM_STATE_COUNT); + +/* + * Indicates the number of coupled VPEs ready to operate in a non-coherent + * state. Actually per-core rather than per-CPU. + */ +static DEFINE_PER_CPU_ALIGNED(u32*, ready_count); +static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc); + +/* Indicates online CPUs coupled with the current CPU */ +static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled); + +/* + * Used to synchronize entry to deep idle states. Actually per-core rather + * than per-CPU. + */ +static DEFINE_PER_CPU_ALIGNED(atomic_t, pm_barrier); + +/* Saved CPU state across the CPS_PM_POWER_GATED state */ +DEFINE_PER_CPU_ALIGNED(struct mips_static_suspend_state, cps_cpu_state); + +/* A somewhat arbitrary number of labels & relocs for uasm */ +static struct uasm_label labels[32] __initdata; +static struct uasm_reloc relocs[32] __initdata; + +/* CPU dependant sync types */ +static unsigned stype_intervention; +static unsigned stype_memory; +static unsigned stype_ordering; + +enum mips_reg { + zero, at, v0, v1, a0, a1, a2, a3, + t0, t1, t2, t3, t4, t5, t6, t7, + s0, s1, s2, s3, s4, s5, s6, s7, + t8, t9, k0, k1, gp, sp, fp, ra, +}; + +bool cps_pm_support_state(enum cps_pm_state state) +{ + return test_bit(state, state_support); +} + +static void coupled_barrier(atomic_t *a, unsigned online) +{ + /* + * This function is effectively the same as + * cpuidle_coupled_parallel_barrier, which can't be used here since + * there's no cpuidle device. + */ + + if (!coupled_coherence) + return; + + smp_mb__before_atomic_inc(); + atomic_inc(a); + + while (atomic_read(a) < online) + cpu_relax(); + + if (atomic_inc_return(a) == online * 2) { + atomic_set(a, 0); + return; + } + + while (atomic_read(a) > online) + cpu_relax(); +} + +int cps_pm_enter_state(enum cps_pm_state state) +{ + unsigned cpu = smp_processor_id(); + unsigned core = current_cpu_data.core; + unsigned online, left; + cpumask_t *coupled_mask = this_cpu_ptr(&online_coupled); + u32 *core_ready_count, *nc_core_ready_count; + void *nc_addr; + cps_nc_entry_fn entry; + struct core_boot_config *core_cfg; + struct vpe_boot_config *vpe_cfg; + + /* Check that there is an entry function for this state */ + entry = per_cpu(nc_asm_enter, core)[state]; + if (!entry) + return -EINVAL; + + /* Calculate which coupled CPUs (VPEs) are online */ +#ifdef CONFIG_MIPS_MT + if (cpu_online(cpu)) { + cpumask_and(coupled_mask, cpu_online_mask, + &cpu_sibling_map[cpu]); + online = cpumask_weight(coupled_mask); + cpumask_clear_cpu(cpu, coupled_mask); + } else +#endif + { + cpumask_clear(coupled_mask); + online = 1; + } + + /* Setup the VPE to run mips_cps_pm_restore when started again */ + if (config_enabled(CONFIG_CPU_PM) && state == CPS_PM_POWER_GATED) { + core_cfg = &mips_cps_core_bootcfg[core]; + vpe_cfg = &core_cfg->vpe_config[current_cpu_data.vpe_id]; + vpe_cfg->pc = (unsigned long)mips_cps_pm_restore; + vpe_cfg->gp = (unsigned long)current_thread_info(); + vpe_cfg->sp = 0; + } + + /* Indicate that this CPU might not be coherent */ + cpumask_clear_cpu(cpu, &cpu_coherent_mask); + smp_mb__after_clear_bit(); + + /* Create a non-coherent mapping of the core ready_count */ + core_ready_count = per_cpu(ready_count, core); + nc_addr = kmap_noncoherent(virt_to_page(core_ready_count), + (unsigned long)core_ready_count); + nc_addr += ((unsigned long)core_ready_count & ~PAGE_MASK); + nc_core_ready_count = nc_addr; + + /* Ensure ready_count is zero-initialised before the assembly runs */ + ACCESS_ONCE(*nc_core_ready_count) = 0; + coupled_barrier(&per_cpu(pm_barrier, core), online); + + /* Run the generated entry code */ + left = entry(online, nc_core_ready_count); + + /* Remove the non-coherent mapping of ready_count */ + kunmap_noncoherent(); + + /* Indicate that this CPU is definitely coherent */ + cpumask_set_cpu(cpu, &cpu_coherent_mask); + + /* + * If this VPE is the first to leave the non-coherent wait state then + * it needs to wake up any coupled VPEs still running their wait + * instruction so that they return to cpuidle, which can then complete + * coordination between the coupled VPEs & provide the governor with + * a chance to reflect on the length of time the VPEs were in the + * idle state. + */ + if (coupled_coherence && (state == CPS_PM_NC_WAIT) && (left == online)) + arch_send_call_function_ipi_mask(coupled_mask); + + return 0; +} + +static void __init cps_gen_cache_routine(u32 **pp, struct uasm_label **pl, + struct uasm_reloc **pr, + const struct cache_desc *cache, + unsigned op, int lbl) +{ + unsigned cache_size = cache->ways << cache->waybit; + unsigned i; + const unsigned unroll_lines = 32; + + /* If the cache isn't present this function has it easy */ + if (cache->flags & MIPS_CACHE_NOT_PRESENT) + return; + + /* Load base address */ + UASM_i_LA(pp, t0, (long)CKSEG0); + + /* Calculate end address */ + if (cache_size < 0x8000) + uasm_i_addiu(pp, t1, t0, cache_size); + else + UASM_i_LA(pp, t1, (long)(CKSEG0 + cache_size)); + + /* Start of cache op loop */ + uasm_build_label(pl, *pp, lbl); + + /* Generate the cache ops */ + for (i = 0; i < unroll_lines; i++) + uasm_i_cache(pp, op, i * cache->linesz, t0); + + /* Update the base address */ + uasm_i_addiu(pp, t0, t0, unroll_lines * cache->linesz); + + /* Loop if we haven't reached the end address yet */ + uasm_il_bne(pp, pr, t0, t1, lbl); + uasm_i_nop(pp); +} + +static int __init cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl, + struct uasm_reloc **pr, + const struct cpuinfo_mips *cpu_info, + int lbl) +{ + unsigned i, fsb_size = 8; + unsigned num_loads = (fsb_size * 3) / 2; + unsigned line_stride = 2; + unsigned line_size = cpu_info->dcache.linesz; + unsigned perf_counter, perf_event; + unsigned revision = cpu_info->processor_id & PRID_REV_MASK; + + /* + * Determine whether this CPU requires an FSB flush, and if so which + * performance counter/event reflect stalls due to a full FSB. + */ + switch (__get_cpu_type(cpu_info->cputype)) { + case CPU_INTERAPTIV: + perf_counter = 1; + perf_event = 51; + break; + + case CPU_PROAPTIV: + /* Newer proAptiv cores don't require this workaround */ + if (revision >= PRID_REV_ENCODE_332(1, 1, 0)) + return 0; + + /* On older ones it's unavailable */ + return -1; + + /* CPUs which do not require the workaround */ + case CPU_P5600: + return 0; + + default: + WARN_ONCE(1, "pm-cps: FSB flush unsupported for this CPU\n"); + return -1; + } + + /* + * Ensure that the fill/store buffer (FSB) is not holding the results + * of a prefetch, since if it is then the CPC sequencer may become + * stuck in the D3 (ClrBus) state whilst entering a low power state. + */ + + /* Preserve perf counter setup */ + uasm_i_mfc0(pp, t2, 25, (perf_counter * 2) + 0); /* PerfCtlN */ + uasm_i_mfc0(pp, t3, 25, (perf_counter * 2) + 1); /* PerfCntN */ + + /* Setup perf counter to count FSB full pipeline stalls */ + uasm_i_addiu(pp, t0, zero, (perf_event << 5) | 0xf); + uasm_i_mtc0(pp, t0, 25, (perf_counter * 2) + 0); /* PerfCtlN */ + uasm_i_ehb(pp); + uasm_i_mtc0(pp, zero, 25, (perf_counter * 2) + 1); /* PerfCntN */ + uasm_i_ehb(pp); + + /* Base address for loads */ + UASM_i_LA(pp, t0, (long)CKSEG0); + + /* Start of clear loop */ + uasm_build_label(pl, *pp, lbl); + + /* Perform some loads to fill the FSB */ + for (i = 0; i < num_loads; i++) + uasm_i_lw(pp, zero, i * line_size * line_stride, t0); + + /* + * Invalidate the new D-cache entries so that the cache will need + * refilling (via the FSB) if the loop is executed again. + */ + for (i = 0; i < num_loads; i++) { + uasm_i_cache(pp, Hit_Invalidate_D, + i * line_size * line_stride, t0); + uasm_i_cache(pp, Hit_Writeback_Inv_SD, + i * line_size * line_stride, t0); + } + + /* Completion barrier */ + uasm_i_sync(pp, stype_memory); + uasm_i_ehb(pp); + + /* Check whether the pipeline stalled due to the FSB being full */ + uasm_i_mfc0(pp, t1, 25, (perf_counter * 2) + 1); /* PerfCntN */ + + /* Loop if it didn't */ + uasm_il_beqz(pp, pr, t1, lbl); + uasm_i_nop(pp); + + /* Restore perf counter 1. The count may well now be wrong... */ + uasm_i_mtc0(pp, t2, 25, (perf_counter * 2) + 0); /* PerfCtlN */ + uasm_i_ehb(pp); + uasm_i_mtc0(pp, t3, 25, (perf_counter * 2) + 1); /* PerfCntN */ + uasm_i_ehb(pp); + + return 0; +} + +static void __init cps_gen_set_top_bit(u32 **pp, struct uasm_label **pl, + struct uasm_reloc **pr, + unsigned r_addr, int lbl) +{ + uasm_i_lui(pp, t0, uasm_rel_hi(0x80000000)); + uasm_build_label(pl, *pp, lbl); + uasm_i_ll(pp, t1, 0, r_addr); + uasm_i_or(pp, t1, t1, t0); + uasm_i_sc(pp, t1, 0, r_addr); + uasm_il_beqz(pp, pr, t1, lbl); + uasm_i_nop(pp); +} + +static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) +{ + struct uasm_label *l = labels; + struct uasm_reloc *r = relocs; + u32 *buf, *p; + const unsigned r_online = a0; + const unsigned r_nc_count = a1; + const unsigned r_pcohctl = t7; + const unsigned max_instrs = 256; + unsigned cpc_cmd; + int err; + enum { + lbl_incready = 1, + lbl_poll_cont, + lbl_secondary_hang, + lbl_disable_coherence, + lbl_flush_fsb, + lbl_invicache, + lbl_flushdcache, + lbl_hang, + lbl_set_cont, + lbl_secondary_cont, + lbl_decready, + }; + + /* Allocate a buffer to hold the generated code */ + p = buf = kcalloc(max_instrs, sizeof(u32), GFP_KERNEL); + if (!buf) + return NULL; + + /* Clear labels & relocs ready for (re)use */ + memset(labels, 0, sizeof(labels)); + memset(relocs, 0, sizeof(relocs)); + + if (config_enabled(CONFIG_CPU_PM) && state == CPS_PM_POWER_GATED) { + /* + * Save CPU state. Note the non-standard calling convention + * with the return address placed in v0 to avoid clobbering + * the ra register before it is saved. + */ + UASM_i_LA(&p, t0, (long)mips_cps_pm_save); + uasm_i_jalr(&p, v0, t0); + uasm_i_nop(&p); + } + + /* + * Load addresses of required CM & CPC registers. This is done early + * because they're needed in both the enable & disable coherence steps + * but in the coupled case the enable step will only run on one VPE. + */ + UASM_i_LA(&p, r_pcohctl, (long)addr_gcr_cl_coherence()); + + if (coupled_coherence) { + /* Increment ready_count */ + uasm_i_sync(&p, stype_ordering); + uasm_build_label(&l, p, lbl_incready); + uasm_i_ll(&p, t1, 0, r_nc_count); + uasm_i_addiu(&p, t2, t1, 1); + uasm_i_sc(&p, t2, 0, r_nc_count); + uasm_il_beqz(&p, &r, t2, lbl_incready); + uasm_i_addiu(&p, t1, t1, 1); + + /* Ordering barrier */ + uasm_i_sync(&p, stype_ordering); + + /* + * If this is the last VPE to become ready for non-coherence + * then it should branch below. + */ + uasm_il_beq(&p, &r, t1, r_online, lbl_disable_coherence); + uasm_i_nop(&p); + + if (state < CPS_PM_POWER_GATED) { + /* + * Otherwise this is not the last VPE to become ready + * for non-coherence. It needs to wait until coherence + * has been disabled before proceeding, which it will do + * by polling for the top bit of ready_count being set. + */ + uasm_i_addiu(&p, t1, zero, -1); + uasm_build_label(&l, p, lbl_poll_cont); + uasm_i_lw(&p, t0, 0, r_nc_count); + uasm_il_bltz(&p, &r, t0, lbl_secondary_cont); + uasm_i_ehb(&p); + uasm_i_yield(&p, zero, t1); + uasm_il_b(&p, &r, lbl_poll_cont); + uasm_i_nop(&p); + } else { + /* + * The core will lose power & this VPE will not continue + * so it can simply halt here. + */ + uasm_i_addiu(&p, t0, zero, TCHALT_H); + uasm_i_mtc0(&p, t0, 2, 4); + uasm_build_label(&l, p, lbl_secondary_hang); + uasm_il_b(&p, &r, lbl_secondary_hang); + uasm_i_nop(&p); + } + } + + /* + * This is the point of no return - this VPE will now proceed to + * disable coherence. At this point we *must* be sure that no other + * VPE within the core will interfere with the L1 dcache. + */ + uasm_build_label(&l, p, lbl_disable_coherence); + + /* Invalidate the L1 icache */ + cps_gen_cache_routine(&p, &l, &r, &cpu_data[cpu].icache, + Index_Invalidate_I, lbl_invicache); + + /* Writeback & invalidate the L1 dcache */ + cps_gen_cache_routine(&p, &l, &r, &cpu_data[cpu].dcache, + Index_Writeback_Inv_D, lbl_flushdcache); + + /* Completion barrier */ + uasm_i_sync(&p, stype_memory); + uasm_i_ehb(&p); + + /* + * Disable all but self interventions. The load from COHCTL is defined + * by the interAptiv & proAptiv SUMs as ensuring that the operation + * resulting from the preceeding store is complete. + */ + uasm_i_addiu(&p, t0, zero, 1 << cpu_data[cpu].core); + uasm_i_sw(&p, t0, 0, r_pcohctl); + uasm_i_lw(&p, t0, 0, r_pcohctl); + + /* Sync to ensure previous interventions are complete */ + uasm_i_sync(&p, stype_intervention); + uasm_i_ehb(&p); + + /* Disable coherence */ + uasm_i_sw(&p, zero, 0, r_pcohctl); + uasm_i_lw(&p, t0, 0, r_pcohctl); + + if (state >= CPS_PM_CLOCK_GATED) { + err = cps_gen_flush_fsb(&p, &l, &r, &cpu_data[cpu], + lbl_flush_fsb); + if (err) + goto out_err; + + /* Determine the CPC command to issue */ + switch (state) { + case CPS_PM_CLOCK_GATED: + cpc_cmd = CPC_Cx_CMD_CLOCKOFF; + break; + case CPS_PM_POWER_GATED: + cpc_cmd = CPC_Cx_CMD_PWRDOWN; + break; + default: + BUG(); + goto out_err; + } + + /* Issue the CPC command */ + UASM_i_LA(&p, t0, (long)addr_cpc_cl_cmd()); + uasm_i_addiu(&p, t1, zero, cpc_cmd); + uasm_i_sw(&p, t1, 0, t0); + + if (state == CPS_PM_POWER_GATED) { + /* If anything goes wrong just hang */ + uasm_build_label(&l, p, lbl_hang); + uasm_il_b(&p, &r, lbl_hang); + uasm_i_nop(&p); + + /* + * There's no point generating more code, the core is + * powered down & if powered back up will run from the + * reset vector not from here. + */ + goto gen_done; + } + + /* Completion barrier */ + uasm_i_sync(&p, stype_memory); + uasm_i_ehb(&p); + } + + if (state == CPS_PM_NC_WAIT) { + /* + * At this point it is safe for all VPEs to proceed with + * execution. This VPE will set the top bit of ready_count + * to indicate to the other VPEs that they may continue. + */ + if (coupled_coherence) + cps_gen_set_top_bit(&p, &l, &r, r_nc_count, + lbl_set_cont); + + /* + * VPEs which did not disable coherence will continue + * executing, after coherence has been disabled, from this + * point. + */ + uasm_build_label(&l, p, lbl_secondary_cont); + + /* Now perform our wait */ + uasm_i_wait(&p, 0); + } + + /* + * Re-enable coherence. Note that for CPS_PM_NC_WAIT all coupled VPEs + * will run this. The first will actually re-enable coherence & the + * rest will just be performing a rather unusual nop. + */ + uasm_i_addiu(&p, t0, zero, CM_GCR_Cx_COHERENCE_COHDOMAINEN_MSK); + uasm_i_sw(&p, t0, 0, r_pcohctl); + uasm_i_lw(&p, t0, 0, r_pcohctl); + + /* Completion barrier */ + uasm_i_sync(&p, stype_memory); + uasm_i_ehb(&p); + + if (coupled_coherence && (state == CPS_PM_NC_WAIT)) { + /* Decrement ready_count */ + uasm_build_label(&l, p, lbl_decready); + uasm_i_sync(&p, stype_ordering); + uasm_i_ll(&p, t1, 0, r_nc_count); + uasm_i_addiu(&p, t2, t1, -1); + uasm_i_sc(&p, t2, 0, r_nc_count); + uasm_il_beqz(&p, &r, t2, lbl_decready); + uasm_i_andi(&p, v0, t1, (1 << fls(smp_num_siblings)) - 1); + + /* Ordering barrier */ + uasm_i_sync(&p, stype_ordering); + } + + if (coupled_coherence && (state == CPS_PM_CLOCK_GATED)) { + /* + * At this point it is safe for all VPEs to proceed with + * execution. This VPE will set the top bit of ready_count + * to indicate to the other VPEs that they may continue. + */ + cps_gen_set_top_bit(&p, &l, &r, r_nc_count, lbl_set_cont); + + /* + * This core will be reliant upon another core sending a + * power-up command to the CPC in order to resume operation. + * Thus an arbitrary VPE can't trigger the core leaving the + * idle state and the one that disables coherence might as well + * be the one to re-enable it. The rest will continue from here + * after that has been done. + */ + uasm_build_label(&l, p, lbl_secondary_cont); + + /* Ordering barrier */ + uasm_i_sync(&p, stype_ordering); + } + + /* The core is coherent, time to return to C code */ + uasm_i_jr(&p, ra); + uasm_i_nop(&p); + +gen_done: + /* Ensure the code didn't exceed the resources allocated for it */ + BUG_ON((p - buf) > max_instrs); + BUG_ON((l - labels) > ARRAY_SIZE(labels)); + BUG_ON((r - relocs) > ARRAY_SIZE(relocs)); + + /* Patch branch offsets */ + uasm_resolve_relocs(relocs, labels); + + /* Flush the icache */ + local_flush_icache_range((unsigned long)buf, (unsigned long)p); + + return buf; +out_err: + kfree(buf); + return NULL; +} + +static int __init cps_gen_core_entries(unsigned cpu) +{ + enum cps_pm_state state; + unsigned core = cpu_data[cpu].core; + unsigned dlinesz = cpu_data[cpu].dcache.linesz; + void *entry_fn, *core_rc; + + for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) { + if (per_cpu(nc_asm_enter, core)[state]) + continue; + if (!test_bit(state, state_support)) + continue; + + entry_fn = cps_gen_entry_code(cpu, state); + if (!entry_fn) { + pr_err("Failed to generate core %u state %u entry\n", + core, state); + clear_bit(state, state_support); + } + + per_cpu(nc_asm_enter, core)[state] = entry_fn; + } + + if (!per_cpu(ready_count, core)) { + core_rc = kmalloc(dlinesz * 2, GFP_KERNEL); + if (!core_rc) { + pr_err("Failed allocate core %u ready_count\n", core); + return -ENOMEM; + } + per_cpu(ready_count_alloc, core) = core_rc; + + /* Ensure ready_count is aligned to a cacheline boundary */ + core_rc += dlinesz - 1; + core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1)); + per_cpu(ready_count, core) = core_rc; + } + + return 0; +} + +static int __init cps_pm_init(void) +{ + unsigned cpu; + int err; + + /* Detect appropriate sync types for the system */ + switch (current_cpu_data.cputype) { + case CPU_INTERAPTIV: + case CPU_PROAPTIV: + case CPU_M5150: + case CPU_P5600: + stype_intervention = 0x2; + stype_memory = 0x3; + stype_ordering = 0x10; + break; + + default: + pr_warn("Power management is using heavyweight sync 0\n"); + } + + /* A CM is required for all non-coherent states */ + if (!mips_cm_present()) { + pr_warn("pm-cps: no CM, non-coherent states unavailable\n"); + goto out; + } + + /* + * If interrupts were enabled whilst running a wait instruction on a + * non-coherent core then the VPE may end up processing interrupts + * whilst non-coherent. That would be bad. + */ + if (cpu_wait == r4k_wait_irqoff) + set_bit(CPS_PM_NC_WAIT, state_support); + else + pr_warn("pm-cps: non-coherent wait unavailable\n"); + + /* Detect whether a CPC is present */ + if (mips_cpc_present()) { + /* Detect whether clock gating is implemented */ + if (read_cpc_cl_stat_conf() & CPC_Cx_STAT_CONF_CLKGAT_IMPL_MSK) + set_bit(CPS_PM_CLOCK_GATED, state_support); + else + pr_warn("pm-cps: CPC does not support clock gating\n"); + + /* Power gating is available with CPS SMP & any CPC */ + if (mips_cps_smp_in_use()) + set_bit(CPS_PM_POWER_GATED, state_support); + else + pr_warn("pm-cps: CPS SMP not in use, power gating unavailable\n"); + } else { + pr_warn("pm-cps: no CPC, clock & power gating unavailable\n"); + } + + for_each_present_cpu(cpu) { + err = cps_gen_core_entries(cpu); + if (err) + return err; + } +out: + return 0; +} +arch_initcall(cps_pm_init); diff --git a/arch/mips/kernel/pm.c b/arch/mips/kernel/pm.c new file mode 100644 index 000000000000..fefdf39d3df3 --- /dev/null +++ b/arch/mips/kernel/pm.c @@ -0,0 +1,99 @@ +/* + * Copyright (C) 2014 Imagination Technologies Ltd. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * CPU PM notifiers for saving/restoring general CPU state. + */ + +#include <linux/cpu_pm.h> +#include <linux/init.h> + +#include <asm/dsp.h> +#include <asm/fpu.h> +#include <asm/mmu_context.h> +#include <asm/pm.h> +#include <asm/watch.h> + +/* Used by PM helper macros in asm/pm.h */ +struct mips_static_suspend_state mips_static_suspend_state; + +/** + * mips_cpu_save() - Save general CPU state. + * Ensures that general CPU context is saved, notably FPU and DSP. + */ +static int mips_cpu_save(void) +{ + /* Save FPU state */ + lose_fpu(1); + + /* Save DSP state */ + save_dsp(current); + + return 0; +} + +/** + * mips_cpu_restore() - Restore general CPU state. + * Restores important CPU context. + */ +static void mips_cpu_restore(void) +{ + unsigned int cpu = smp_processor_id(); + + /* Restore ASID */ + if (current->mm) + write_c0_entryhi(cpu_asid(cpu, current->mm)); + + /* Restore DSP state */ + restore_dsp(current); + + /* Restore UserLocal */ + if (cpu_has_userlocal) + write_c0_userlocal(current_thread_info()->tp_value); + + /* Restore watch registers */ + __restore_watch(); +} + +/** + * mips_pm_notifier() - Notifier for preserving general CPU context. + * @self: Notifier block. + * @cmd: CPU PM event. + * @v: Private data (unused). + * + * This is called when a CPU power management event occurs, and is used to + * ensure that important CPU context is preserved across a CPU power down. + */ +static int mips_pm_notifier(struct notifier_block *self, unsigned long cmd, + void *v) +{ + int ret; + + switch (cmd) { + case CPU_PM_ENTER: + ret = mips_cpu_save(); + if (ret) + return NOTIFY_STOP; + break; + case CPU_PM_ENTER_FAILED: + case CPU_PM_EXIT: + mips_cpu_restore(); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block mips_pm_notifier_block = { + .notifier_call = mips_pm_notifier, +}; + +static int __init mips_pm_init(void) +{ + return cpu_pm_register_notifier(&mips_pm_notifier_block); +} +arch_initcall(mips_pm_init); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 60e39dc7f1eb..0a1ec0f3beff 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -140,13 +140,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, */ childregs->cp0_status &= ~(ST0_CU2|ST0_CU1); -#ifdef CONFIG_MIPS_MT_SMTC - /* - * SMTC restores TCStatus after Status, and the CU bits - * are aliased there. - */ - childregs->cp0_tcstatus &= ~(ST0_CU2|ST0_CU1); -#endif clear_tsk_thread_flag(p, TIF_USEDFPU); #ifdef CONFIG_MIPS_MT_FPAFF diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c index 3c3b0df8f48d..5d39bb85bf35 100644 --- a/arch/mips/kernel/prom.c +++ b/arch/mips/kernel/prom.c @@ -47,7 +47,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)); } -void __init __dt_setup_arch(struct boot_param_header *bph) +void __init __dt_setup_arch(void *bph) { if (!early_init_dt_scan(bph)) return; diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S index abacac7c33ef..81ca3f70fe29 100644 --- a/arch/mips/kernel/r4k_switch.S +++ b/arch/mips/kernel/r4k_switch.S @@ -28,6 +28,7 @@ */ #define ST_OFF (_THREAD_SIZE - 32 - PT_SIZE + PT_STATUS) +#ifndef USE_ALTERNATE_RESUME_IMPL /* * task_struct *resume(task_struct *prev, task_struct *next, * struct thread_info *next_ti, s32 fp_save) @@ -87,18 +88,6 @@ PTR_ADDU t0, $28, _THREAD_SIZE - 32 set_saved_sp t0, t1, t2 -#ifdef CONFIG_MIPS_MT_SMTC - /* Read-modify-writes of Status must be atomic on a VPE */ - mfc0 t2, CP0_TCSTATUS - ori t1, t2, TCSTATUS_IXMT - mtc0 t1, CP0_TCSTATUS - andi t2, t2, TCSTATUS_IXMT - _ehb - DMT 8 # dmt t0 - move t1,ra - jal mips_ihb - move ra,t1 -#endif /* CONFIG_MIPS_MT_SMTC */ mfc0 t1, CP0_STATUS /* Do we really need this? */ li a3, 0xff01 and t1, a3 @@ -107,22 +96,12 @@ and a2, a3 or a2, t1 mtc0 a2, CP0_STATUS -#ifdef CONFIG_MIPS_MT_SMTC - _ehb - andi t0, t0, VPECONTROL_TE - beqz t0, 1f - emt -1: - mfc0 t1, CP0_TCSTATUS - xori t1, t1, TCSTATUS_IXMT - or t1, t1, t2 - mtc0 t1, CP0_TCSTATUS - _ehb -#endif /* CONFIG_MIPS_MT_SMTC */ move v0, a0 jr ra END(resume) +#endif /* USE_ALTERNATE_RESUME_IMPL */ + /* * Save a thread's fp context. */ @@ -176,19 +155,10 @@ LEAF(_restore_msa) #define FPU_DEFAULT 0x00000000 LEAF(_init_fpu) -#ifdef CONFIG_MIPS_MT_SMTC - /* Rather than manipulate per-VPE Status, set per-TC bit in TCStatus */ - mfc0 t0, CP0_TCSTATUS - /* Bit position is the same for Status, TCStatus */ - li t1, ST0_CU1 - or t0, t1 - mtc0 t0, CP0_TCSTATUS -#else /* Normal MIPS CU1 enable */ mfc0 t0, CP0_STATUS li t1, ST0_CU1 or t0, t1 mtc0 t0, CP0_STATUS -#endif /* CONFIG_MIPS_MT_SMTC */ enable_fpu_hazard li t1, FPU_DEFAULT diff --git a/arch/mips/kernel/rtlx-mt.c b/arch/mips/kernel/rtlx-mt.c index 9c1aca00fd54..5a66b975989e 100644 --- a/arch/mips/kernel/rtlx-mt.c +++ b/arch/mips/kernel/rtlx-mt.c @@ -36,7 +36,6 @@ static irqreturn_t rtlx_interrupt(int irq, void *dev_id) unsigned long flags; int i; - /* Ought not to be strictly necessary for SMTC builds */ local_irq_save(flags); vpeflags = dvpe(); set_c0_status(0x100 << MIPS_CPU_RTLX_IRQ); diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index ea4c2dc31692..df9e2bd9b2c2 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -281,13 +281,6 @@ static void bmips_smp_finish(void) } /* - * Runs on CPU0 after all CPUs have been booted - */ -static void bmips_cpus_done(void) -{ -} - -/* * BMIPS5000 raceless IPIs * * Each CPU has two inbound SW IRQs which are independent of all other CPUs. @@ -434,7 +427,6 @@ struct plat_smp_ops bmips43xx_smp_ops = { .boot_secondary = bmips_boot_secondary, .smp_finish = bmips_smp_finish, .init_secondary = bmips_init_secondary, - .cpus_done = bmips_cpus_done, .send_ipi_single = bmips43xx_send_ipi_single, .send_ipi_mask = bmips43xx_send_ipi_mask, #ifdef CONFIG_HOTPLUG_CPU @@ -449,7 +441,6 @@ struct plat_smp_ops bmips5000_smp_ops = { .boot_secondary = bmips_boot_secondary, .smp_finish = bmips_smp_finish, .init_secondary = bmips_init_secondary, - .cpus_done = bmips_cpus_done, .send_ipi_single = bmips5000_send_ipi_single, .send_ipi_mask = bmips5000_send_ipi_mask, #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c index 3ef55fb7ac03..fc8a51553426 100644 --- a/arch/mips/kernel/smp-cmp.c +++ b/arch/mips/kernel/smp-cmp.c @@ -49,14 +49,11 @@ static void cmp_init_secondary(void) /* Enable per-cpu interrupts: platform specific */ -#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC) +#ifdef CONFIG_MIPS_MT_SMP if (cpu_has_mipsmt) c->vpe_id = (read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & TCBIND_CURVPE; #endif -#ifdef CONFIG_MIPS_MT_SMTC - c->tc_id = (read_c0_tcbind() & TCBIND_CURTC) >> TCBIND_CURTC_SHIFT; -#endif } static void cmp_smp_finish(void) @@ -75,11 +72,6 @@ static void cmp_smp_finish(void) local_irq_enable(); } -static void cmp_cpus_done(void) -{ - pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__); -} - /* * Setup the PC, SP, and GP of a secondary processor and start it running * smp_bootstrap is the place to resume from @@ -135,10 +127,6 @@ void __init cmp_smp_setup(void) unsigned int mvpconf0 = read_c0_mvpconf0(); nvpe = ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1; -#elif defined(CONFIG_MIPS_MT_SMTC) - unsigned int mvpconf0 = read_c0_mvpconf0(); - - nvpe = ((mvpconf0 & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1; #endif smp_num_siblings = nvpe; } @@ -165,7 +153,6 @@ struct plat_smp_ops cmp_smp_ops = { .send_ipi_mask = gic_send_ipi_mask, .init_secondary = cmp_init_secondary, .smp_finish = cmp_smp_finish, - .cpus_done = cmp_cpus_done, .boot_secondary = cmp_boot_secondary, .smp_setup = cmp_smp_setup, .prepare_cpus = cmp_prepare_cpus, diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 536eec0d21b6..df0598d9bfdd 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -20,104 +20,43 @@ #include <asm/mips-cpc.h> #include <asm/mips_mt.h> #include <asm/mipsregs.h> +#include <asm/pm-cps.h> #include <asm/smp-cps.h> #include <asm/time.h> #include <asm/uasm.h> static DECLARE_BITMAP(core_power, NR_CPUS); -struct boot_config mips_cps_bootcfg; +struct core_boot_config *mips_cps_core_bootcfg; -static void init_core(void) +static unsigned core_vpe_count(unsigned core) { - unsigned int nvpes, t; - u32 mvpconf0, vpeconf0, vpecontrol, tcstatus, tcbind, status; + unsigned cfg; - if (!cpu_has_mipsmt) - return; - - /* Enter VPE configuration state */ - dvpe(); - set_c0_mvpcontrol(MVPCONTROL_VPC); - - /* Retrieve the count of VPEs in this core */ - mvpconf0 = read_c0_mvpconf0(); - nvpes = ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1; - smp_num_siblings = nvpes; - - for (t = 1; t < nvpes; t++) { - /* Use a 1:1 mapping of TC index to VPE index */ - settc(t); - - /* Bind 1 TC to this VPE */ - tcbind = read_tc_c0_tcbind(); - tcbind &= ~TCBIND_CURVPE; - tcbind |= t << TCBIND_CURVPE_SHIFT; - write_tc_c0_tcbind(tcbind); - - /* Set exclusive TC, non-active, master */ - vpeconf0 = read_vpe_c0_vpeconf0(); - vpeconf0 &= ~(VPECONF0_XTC | VPECONF0_VPA); - vpeconf0 |= t << VPECONF0_XTC_SHIFT; - vpeconf0 |= VPECONF0_MVP; - write_vpe_c0_vpeconf0(vpeconf0); - - /* Declare TC non-active, non-allocatable & interrupt exempt */ - tcstatus = read_tc_c0_tcstatus(); - tcstatus &= ~(TCSTATUS_A | TCSTATUS_DA); - tcstatus |= TCSTATUS_IXMT; - write_tc_c0_tcstatus(tcstatus); - - /* Halt the TC */ - write_tc_c0_tchalt(TCHALT_H); - - /* Allow only 1 TC to execute */ - vpecontrol = read_vpe_c0_vpecontrol(); - vpecontrol &= ~VPECONTROL_TE; - write_vpe_c0_vpecontrol(vpecontrol); - - /* Copy (most of) Status from VPE 0 */ - status = read_c0_status(); - status &= ~(ST0_IM | ST0_IE | ST0_KSU); - status |= ST0_CU0; - write_vpe_c0_status(status); - - /* Copy Config from VPE 0 */ - write_vpe_c0_config(read_c0_config()); - write_vpe_c0_config7(read_c0_config7()); - - /* Ensure no software interrupts are pending */ - write_vpe_c0_cause(0); - - /* Sync Count */ - write_vpe_c0_count(read_c0_count()); - } + if (!config_enabled(CONFIG_MIPS_MT_SMP) || !cpu_has_mipsmt) + return 1; - /* Leave VPE configuration state */ - clear_c0_mvpcontrol(MVPCONTROL_VPC); + write_gcr_cl_other(core << CM_GCR_Cx_OTHER_CORENUM_SHF); + cfg = read_gcr_co_config() & CM_GCR_Cx_CONFIG_PVPE_MSK; + return (cfg >> CM_GCR_Cx_CONFIG_PVPE_SHF) + 1; } static void __init cps_smp_setup(void) { unsigned int ncores, nvpes, core_vpes; int c, v; - u32 core_cfg, *entry_code; /* Detect & record VPE topology */ ncores = mips_cm_numcores(); pr_info("VPE topology "); for (c = nvpes = 0; c < ncores; c++) { - if (cpu_has_mipsmt && config_enabled(CONFIG_MIPS_MT_SMP)) { - write_gcr_cl_other(c << CM_GCR_Cx_OTHER_CORENUM_SHF); - core_cfg = read_gcr_co_config(); - core_vpes = ((core_cfg & CM_GCR_Cx_CONFIG_PVPE_MSK) >> - CM_GCR_Cx_CONFIG_PVPE_SHF) + 1; - } else { - core_vpes = 1; - } - + core_vpes = core_vpe_count(c); pr_cont("%c%u", c ? ',' : '{', core_vpes); + /* Use the number of VPEs in core 0 for smp_num_siblings */ + if (!c) + smp_num_siblings = core_vpes; + for (v = 0; v < min_t(int, core_vpes, NR_CPUS - nvpes); v++) { cpu_data[nvpes + v].core = c; #ifdef CONFIG_MIPS_MT_SMP @@ -137,19 +76,14 @@ static void __init cps_smp_setup(void) __cpu_logical_map[v] = v; } + /* Set a coherent default CCA (CWB) */ + change_c0_config(CONF_CM_CMASK, 0x5); + /* Core 0 is powered up (we're running on it) */ bitmap_set(core_power, 0, 1); - /* Disable MT - we only want to run 1 TC per VPE */ - if (cpu_has_mipsmt) - dmt(); - /* Initialise core 0 */ - init_core(); - - /* Patch the start of mips_cps_core_entry to provide the CM base */ - entry_code = (u32 *)&mips_cps_core_entry; - UASM_i_LA(&entry_code, 3, (long)mips_cm_base); + mips_cps_core_init(); /* Make core 0 coherent with everything */ write_gcr_cl_coherence(0xff); @@ -157,15 +91,99 @@ static void __init cps_smp_setup(void) static void __init cps_prepare_cpus(unsigned int max_cpus) { + unsigned ncores, core_vpes, c, cca; + bool cca_unsuitable; + u32 *entry_code; + mips_mt_set_cpuoptions(); + + /* Detect whether the CCA is unsuited to multi-core SMP */ + cca = read_c0_config() & CONF_CM_CMASK; + switch (cca) { + case 0x4: /* CWBE */ + case 0x5: /* CWB */ + /* The CCA is coherent, multi-core is fine */ + cca_unsuitable = false; + break; + + default: + /* CCA is not coherent, multi-core is not usable */ + cca_unsuitable = true; + } + + /* Warn the user if the CCA prevents multi-core */ + ncores = mips_cm_numcores(); + if (cca_unsuitable && ncores > 1) { + pr_warn("Using only one core due to unsuitable CCA 0x%x\n", + cca); + + for_each_present_cpu(c) { + if (cpu_data[c].core) + set_cpu_present(c, false); + } + } + + /* + * Patch the start of mips_cps_core_entry to provide: + * + * v0 = CM base address + * s0 = kseg0 CCA + */ + entry_code = (u32 *)&mips_cps_core_entry; + UASM_i_LA(&entry_code, 3, (long)mips_cm_base); + uasm_i_addiu(&entry_code, 16, 0, cca); + dma_cache_wback_inv((unsigned long)&mips_cps_core_entry, + (void *)entry_code - (void *)&mips_cps_core_entry); + + /* Allocate core boot configuration structs */ + mips_cps_core_bootcfg = kcalloc(ncores, sizeof(*mips_cps_core_bootcfg), + GFP_KERNEL); + if (!mips_cps_core_bootcfg) { + pr_err("Failed to allocate boot config for %u cores\n", ncores); + goto err_out; + } + + /* Allocate VPE boot configuration structs */ + for (c = 0; c < ncores; c++) { + core_vpes = core_vpe_count(c); + mips_cps_core_bootcfg[c].vpe_config = kcalloc(core_vpes, + sizeof(*mips_cps_core_bootcfg[c].vpe_config), + GFP_KERNEL); + if (!mips_cps_core_bootcfg[c].vpe_config) { + pr_err("Failed to allocate %u VPE boot configs\n", + core_vpes); + goto err_out; + } + } + + /* Mark this CPU as booted */ + atomic_set(&mips_cps_core_bootcfg[current_cpu_data.core].vpe_mask, + 1 << cpu_vpe_id(¤t_cpu_data)); + + return; +err_out: + /* Clean up allocations */ + if (mips_cps_core_bootcfg) { + for (c = 0; c < ncores; c++) + kfree(mips_cps_core_bootcfg[c].vpe_config); + kfree(mips_cps_core_bootcfg); + mips_cps_core_bootcfg = NULL; + } + + /* Effectively disable SMP by declaring CPUs not present */ + for_each_possible_cpu(c) { + if (c == 0) + continue; + set_cpu_present(c, false); + } } -static void boot_core(struct boot_config *cfg) +static void boot_core(unsigned core) { u32 access; /* Select the appropriate core */ - write_gcr_cl_other(cfg->core << CM_GCR_Cx_OTHER_CORENUM_SHF); + write_gcr_cl_other(core << CM_GCR_Cx_OTHER_CORENUM_SHF); /* Set its reset vector */ write_gcr_co_reset_base(CKSEG1ADDR((unsigned long)mips_cps_core_entry)); @@ -175,104 +193,74 @@ static void boot_core(struct boot_config *cfg) /* Ensure the core can access the GCRs */ access = read_gcr_access(); - access |= 1 << (CM_GCR_ACCESS_ACCESSEN_SHF + cfg->core); + access |= 1 << (CM_GCR_ACCESS_ACCESSEN_SHF + core); write_gcr_access(access); - /* Copy cfg */ - mips_cps_bootcfg = *cfg; - if (mips_cpc_present()) { - /* Select the appropriate core */ - write_cpc_cl_other(cfg->core << CPC_Cx_OTHER_CORENUM_SHF); - /* Reset the core */ + mips_cpc_lock_other(core); write_cpc_co_cmd(CPC_Cx_CMD_RESET); + mips_cpc_unlock_other(); } else { /* Take the core out of reset */ write_gcr_co_reset_release(0); } /* The core is now powered up */ - bitmap_set(core_power, cfg->core, 1); + bitmap_set(core_power, core, 1); } -static void boot_vpe(void *info) +static void remote_vpe_boot(void *dummy) { - struct boot_config *cfg = info; - u32 tcstatus, vpeconf0; - - /* Enter VPE configuration state */ - dvpe(); - set_c0_mvpcontrol(MVPCONTROL_VPC); - - settc(cfg->vpe); - - /* Set the TC restart PC */ - write_tc_c0_tcrestart((unsigned long)&smp_bootstrap); - - /* Activate the TC, allow interrupts */ - tcstatus = read_tc_c0_tcstatus(); - tcstatus &= ~TCSTATUS_IXMT; - tcstatus |= TCSTATUS_A; - write_tc_c0_tcstatus(tcstatus); - - /* Clear the TC halt bit */ - write_tc_c0_tchalt(0); - - /* Activate the VPE */ - vpeconf0 = read_vpe_c0_vpeconf0(); - vpeconf0 |= VPECONF0_VPA; - write_vpe_c0_vpeconf0(vpeconf0); - - /* Set the stack & global pointer registers */ - write_tc_gpr_sp(cfg->sp); - write_tc_gpr_gp(cfg->gp); - - /* Leave VPE configuration state */ - clear_c0_mvpcontrol(MVPCONTROL_VPC); - - /* Enable other VPEs to execute */ - evpe(EVPE_ENABLE); + mips_cps_boot_vpes(); } static void cps_boot_secondary(int cpu, struct task_struct *idle) { - struct boot_config cfg; + unsigned core = cpu_data[cpu].core; + unsigned vpe_id = cpu_vpe_id(&cpu_data[cpu]); + struct core_boot_config *core_cfg = &mips_cps_core_bootcfg[core]; + struct vpe_boot_config *vpe_cfg = &core_cfg->vpe_config[vpe_id]; unsigned int remote; int err; - cfg.core = cpu_data[cpu].core; - cfg.vpe = cpu_vpe_id(&cpu_data[cpu]); - cfg.pc = (unsigned long)&smp_bootstrap; - cfg.sp = __KSTK_TOS(idle); - cfg.gp = (unsigned long)task_thread_info(idle); + vpe_cfg->pc = (unsigned long)&smp_bootstrap; + vpe_cfg->sp = __KSTK_TOS(idle); + vpe_cfg->gp = (unsigned long)task_thread_info(idle); + + atomic_or(1 << cpu_vpe_id(&cpu_data[cpu]), &core_cfg->vpe_mask); - if (!test_bit(cfg.core, core_power)) { + preempt_disable(); + + if (!test_bit(core, core_power)) { /* Boot a VPE on a powered down core */ - boot_core(&cfg); - return; + boot_core(core); + goto out; } - if (cfg.core != current_cpu_data.core) { + if (core != current_cpu_data.core) { /* Boot a VPE on another powered up core */ for (remote = 0; remote < NR_CPUS; remote++) { - if (cpu_data[remote].core != cfg.core) + if (cpu_data[remote].core != core) continue; if (cpu_online(remote)) break; } BUG_ON(remote >= NR_CPUS); - err = smp_call_function_single(remote, boot_vpe, &cfg, 1); + err = smp_call_function_single(remote, remote_vpe_boot, + NULL, 1); if (err) panic("Failed to call remote CPU\n"); - return; + goto out; } BUG_ON(!cpu_has_mipsmt); /* Boot a VPE on this core */ - boot_vpe(&cfg); + mips_cps_boot_vpes(); +out: + preempt_enable(); } static void cps_init_secondary(void) @@ -281,10 +269,6 @@ static void cps_init_secondary(void) if (cpu_has_mipsmt) dmt(); - /* TODO: revisit this assumption once hotplug is implemented */ - if (cpu_vpe_id(¤t_cpu_data) == 0) - init_core(); - change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 | STATUSF_IP6 | STATUSF_IP7); } @@ -302,10 +286,148 @@ static void cps_smp_finish(void) local_irq_enable(); } -static void cps_cpus_done(void) +#ifdef CONFIG_HOTPLUG_CPU + +static int cps_cpu_disable(void) +{ + unsigned cpu = smp_processor_id(); + struct core_boot_config *core_cfg; + + if (!cpu) + return -EBUSY; + + if (!cps_pm_support_state(CPS_PM_POWER_GATED)) + return -EINVAL; + + core_cfg = &mips_cps_core_bootcfg[current_cpu_data.core]; + atomic_sub(1 << cpu_vpe_id(¤t_cpu_data), &core_cfg->vpe_mask); + smp_mb__after_atomic_dec(); + set_cpu_online(cpu, false); + cpu_clear(cpu, cpu_callin_map); + + return 0; +} + +static DECLARE_COMPLETION(cpu_death_chosen); +static unsigned cpu_death_sibling; +static enum { + CPU_DEATH_HALT, + CPU_DEATH_POWER, +} cpu_death; + +void play_dead(void) +{ + unsigned cpu, core; + + local_irq_disable(); + idle_task_exit(); + cpu = smp_processor_id(); + cpu_death = CPU_DEATH_POWER; + + if (cpu_has_mipsmt) { + core = cpu_data[cpu].core; + + /* Look for another online VPE within the core */ + for_each_online_cpu(cpu_death_sibling) { + if (cpu_data[cpu_death_sibling].core != core) + continue; + + /* + * There is an online VPE within the core. Just halt + * this TC and leave the core alone. + */ + cpu_death = CPU_DEATH_HALT; + break; + } + } + + /* This CPU has chosen its way out */ + complete(&cpu_death_chosen); + + if (cpu_death == CPU_DEATH_HALT) { + /* Halt this TC */ + write_c0_tchalt(TCHALT_H); + instruction_hazard(); + } else { + /* Power down the core */ + cps_pm_enter_state(CPS_PM_POWER_GATED); + } + + /* This should never be reached */ + panic("Failed to offline CPU %u", cpu); +} + +static void wait_for_sibling_halt(void *ptr_cpu) { + unsigned cpu = (unsigned)ptr_cpu; + unsigned vpe_id = cpu_data[cpu].vpe_id; + unsigned halted; + unsigned long flags; + + do { + local_irq_save(flags); + settc(vpe_id); + halted = read_tc_c0_tchalt(); + local_irq_restore(flags); + } while (!(halted & TCHALT_H)); +} + +static void cps_cpu_die(unsigned int cpu) +{ + unsigned core = cpu_data[cpu].core; + unsigned stat; + int err; + + /* Wait for the cpu to choose its way out */ + if (!wait_for_completion_timeout(&cpu_death_chosen, + msecs_to_jiffies(5000))) { + pr_err("CPU%u: didn't offline\n", cpu); + return; + } + + /* + * Now wait for the CPU to actually offline. Without doing this that + * offlining may race with one or more of: + * + * - Onlining the CPU again. + * - Powering down the core if another VPE within it is offlined. + * - A sibling VPE entering a non-coherent state. + * + * In the non-MT halt case (ie. infinite loop) the CPU is doing nothing + * with which we could race, so do nothing. + */ + if (cpu_death == CPU_DEATH_POWER) { + /* + * Wait for the core to enter a powered down or clock gated + * state, the latter happening when a JTAG probe is connected + * in which case the CPC will refuse to power down the core. + */ + do { + mips_cpc_lock_other(core); + stat = read_cpc_co_stat_conf(); + stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK; + mips_cpc_unlock_other(); + } while (stat != CPC_Cx_STAT_CONF_SEQSTATE_D0 && + stat != CPC_Cx_STAT_CONF_SEQSTATE_D2 && + stat != CPC_Cx_STAT_CONF_SEQSTATE_U2); + + /* Indicate the core is powered off */ + bitmap_clear(core_power, core, 1); + } else if (cpu_has_mipsmt) { + /* + * Have a CPU with access to the offlined CPUs registers wait + * for its TC to halt. + */ + err = smp_call_function_single(cpu_death_sibling, + wait_for_sibling_halt, + (void *)cpu, 1); + if (err) + panic("Failed to call remote sibling CPU\n"); + } } +#endif /* CONFIG_HOTPLUG_CPU */ + static struct plat_smp_ops cps_smp_ops = { .smp_setup = cps_smp_setup, .prepare_cpus = cps_prepare_cpus, @@ -314,9 +436,18 @@ static struct plat_smp_ops cps_smp_ops = { .smp_finish = cps_smp_finish, .send_ipi_single = gic_send_ipi_single, .send_ipi_mask = gic_send_ipi_mask, - .cpus_done = cps_cpus_done, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_disable = cps_cpu_disable, + .cpu_die = cps_cpu_die, +#endif }; +bool mips_cps_smp_in_use(void) +{ + extern struct plat_smp_ops *mp_ops; + return mp_ops == &cps_smp_ops; +} + int register_cps_smp_ops(void) { if (!mips_cm_present()) { diff --git a/arch/mips/kernel/smp-gic.c b/arch/mips/kernel/smp-gic.c index 3bb1f92ab525..3b21a96d1ccb 100644 --- a/arch/mips/kernel/smp-gic.c +++ b/arch/mips/kernel/smp-gic.c @@ -15,12 +15,14 @@ #include <linux/printk.h> #include <asm/gic.h> +#include <asm/mips-cpc.h> #include <asm/smp-ops.h> void gic_send_ipi_single(int cpu, unsigned int action) { unsigned long flags; unsigned int intr; + unsigned int core = cpu_data[cpu].core; pr_debug("CPU%d: %s cpu %d action %u status %08x\n", smp_processor_id(), __func__, cpu, action, read_c0_status()); @@ -41,6 +43,15 @@ void gic_send_ipi_single(int cpu, unsigned int action) } gic_send_ipi(intr); + + if (mips_cpc_present() && (core != current_cpu_data.core)) { + while (!cpumask_test_cpu(cpu, &cpu_coherent_mask)) { + mips_cpc_lock_other(core); + write_cpc_co_cmd(CPC_Cx_CMD_PWRUP); + mips_cpc_unlock_other(); + } + } + local_irq_restore(flags); } diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c index f8e13149604d..3babf6e4f894 100644 --- a/arch/mips/kernel/smp-mt.c +++ b/arch/mips/kernel/smp-mt.c @@ -183,10 +183,6 @@ static void vsmp_smp_finish(void) local_irq_enable(); } -static void vsmp_cpus_done(void) -{ -} - /* * Setup the PC, SP, and GP of a secondary processor and start it * running! @@ -287,7 +283,6 @@ struct plat_smp_ops vsmp_smp_ops = { .send_ipi_mask = vsmp_send_ipi_mask, .init_secondary = vsmp_init_secondary, .smp_finish = vsmp_smp_finish, - .cpus_done = vsmp_cpus_done, .boot_secondary = vsmp_boot_secondary, .smp_setup = vsmp_smp_setup, .prepare_cpus = vsmp_prepare_cpus, diff --git a/arch/mips/kernel/smp-up.c b/arch/mips/kernel/smp-up.c index 7fde3e4d978f..17878d71ef2b 100644 --- a/arch/mips/kernel/smp-up.c +++ b/arch/mips/kernel/smp-up.c @@ -36,11 +36,6 @@ static void up_smp_finish(void) { } -/* Hook for after all CPUs are online */ -static void up_cpus_done(void) -{ -} - /* * Firmware CPU startup hook */ @@ -73,7 +68,6 @@ struct plat_smp_ops up_smp_ops = { .send_ipi_mask = up_send_ipi_mask, .init_secondary = up_init_secondary, .smp_finish = up_smp_finish, - .cpus_done = up_cpus_done, .boot_secondary = up_boot_secondary, .smp_setup = up_smp_setup, .prepare_cpus = up_prepare_cpus, diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 0a022ee33b2a..9bad52ede903 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -43,10 +43,6 @@ #include <asm/time.h> #include <asm/setup.h> -#ifdef CONFIG_MIPS_MT_SMTC -#include <asm/mipsmtregs.h> -#endif /* CONFIG_MIPS_MT_SMTC */ - volatile cpumask_t cpu_callin_map; /* Bitmask of started secondaries */ int __cpu_number_map[NR_CPUS]; /* Map physical to logical */ @@ -66,6 +62,8 @@ EXPORT_SYMBOL(cpu_sibling_map); /* representing cpus for which sibling maps can be computed */ static cpumask_t cpu_sibling_setup_map; +cpumask_t cpu_coherent_mask; + static inline void set_cpu_sibling_map(int cpu) { int i; @@ -102,12 +100,6 @@ asmlinkage void start_secondary(void) { unsigned int cpu; -#ifdef CONFIG_MIPS_MT_SMTC - /* Only do cpu_probe for first TC of CPU */ - if ((read_c0_tcbind() & TCBIND_CURTC) != 0) - __cpu_name[smp_processor_id()] = __cpu_name[0]; - else -#endif /* CONFIG_MIPS_MT_SMTC */ cpu_probe(); cpu_report(); per_cpu_trap_init(false); @@ -124,6 +116,7 @@ asmlinkage void start_secondary(void) cpu = smp_processor_id(); cpu_data[cpu].udelay_val = loops_per_jiffy; + cpu_set(cpu, cpu_coherent_mask); notify_cpu_starting(cpu); set_cpu_online(cpu, true); @@ -173,7 +166,6 @@ void smp_send_stop(void) void __init smp_cpus_done(unsigned int max_cpus) { - mp_ops->cpus_done(); } /* called from main before smp_init() */ @@ -186,6 +178,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) #ifndef CONFIG_HOTPLUG_CPU init_cpu_present(cpu_possible_mask); #endif + cpumask_copy(&cpu_coherent_mask, cpu_possible_mask); } /* preload SMP state for boot cpu */ @@ -238,13 +231,10 @@ static void flush_tlb_mm_ipi(void *mm) * o collapses to normal function call on UP kernels * o collapses to normal function call on systems with a single shared * primary cache. - * o CONFIG_MIPS_MT_SMTC currently implies there is only one physical core. */ static inline void smp_on_other_tlbs(void (*func) (void *info), void *info) { -#ifndef CONFIG_MIPS_MT_SMTC smp_call_function(func, info, 1); -#endif } static inline void smp_on_each_tlb(void (*func) (void *info), void *info) @@ -404,3 +394,46 @@ void dump_send_ipi(void (*dump_ipi_callback)(void *)) } EXPORT_SYMBOL(dump_send_ipi); #endif + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST + +static DEFINE_PER_CPU(atomic_t, tick_broadcast_count); +static DEFINE_PER_CPU(struct call_single_data, tick_broadcast_csd); + +void tick_broadcast(const struct cpumask *mask) +{ + atomic_t *count; + struct call_single_data *csd; + int cpu; + + for_each_cpu(cpu, mask) { + count = &per_cpu(tick_broadcast_count, cpu); + csd = &per_cpu(tick_broadcast_csd, cpu); + + if (atomic_inc_return(count) == 1) + smp_call_function_single_async(cpu, csd); + } +} + +static void tick_broadcast_callee(void *info) +{ + int cpu = smp_processor_id(); + tick_receive_broadcast(); + atomic_set(&per_cpu(tick_broadcast_count, cpu), 0); +} + +static int __init tick_broadcast_init(void) +{ + struct call_single_data *csd; + int cpu; + + for (cpu = 0; cpu < NR_CPUS; cpu++) { + csd = &per_cpu(tick_broadcast_csd, cpu); + csd->func = tick_broadcast_callee; + } + + return 0; +} +early_initcall(tick_broadcast_init); + +#endif /* CONFIG_GENERIC_CLOCKEVENTS_BROADCAST */ diff --git a/arch/mips/kernel/smtc-asm.S b/arch/mips/kernel/smtc-asm.S deleted file mode 100644 index 2866863a39df..000000000000 --- a/arch/mips/kernel/smtc-asm.S +++ /dev/null @@ -1,133 +0,0 @@ -/* - * Assembly Language Functions for MIPS MT SMTC support - */ - -/* - * This file should be built into the kernel only if CONFIG_MIPS_MT_SMTC is set. */ - -#include <asm/regdef.h> -#include <asm/asmmacro.h> -#include <asm/stackframe.h> -#include <asm/irqflags.h> - -/* - * "Software Interrupt" linkage. - * - * This is invoked when an "Interrupt" is sent from one TC to another, - * where the TC to be interrupted is halted, has it's Restart address - * and Status values saved by the "remote control" thread, then modified - * to cause execution to begin here, in kenel mode. This code then - * disguises the TC state as that of an exception and transfers - * control to the general exception or vectored interrupt handler. - */ - .set noreorder - -/* -The __smtc_ipi_vector would use k0 and k1 as temporaries and -1) Set EXL (this is per-VPE, so this can't be done by proxy!) -2) Restore the K/CU and IXMT bits to the pre "exception" state - (EXL means no interrupts and access to the kernel map). -3) Set EPC to be the saved value of TCRestart. -4) Jump to the exception handler entry point passed by the sender. - -CAN WE PROVE THAT WE WON'T DO THIS IF INTS DISABLED?? -*/ - -/* - * Reviled and slandered vision: Set EXL and restore K/CU/IXMT - * state of pre-halt thread, then save everything and call - * thought some function pointer to imaginary_exception, which - * will parse a register value or memory message queue to - * deliver things like interprocessor interrupts. On return - * from that function, jump to the global ret_from_irq code - * to invoke the scheduler and return as appropriate. - */ - -#define PT_PADSLOT4 (PT_R0-8) -#define PT_PADSLOT5 (PT_R0-4) - - .text - .align 5 -FEXPORT(__smtc_ipi_vector) -#ifdef CONFIG_CPU_MICROMIPS - nop -#endif - .set noat - /* Disable thread scheduling to make Status update atomic */ - DMT 27 # dmt k1 - _ehb - /* Set EXL */ - mfc0 k0,CP0_STATUS - ori k0,k0,ST0_EXL - mtc0 k0,CP0_STATUS - _ehb - /* Thread scheduling now inhibited by EXL. Restore TE state. */ - andi k1,k1,VPECONTROL_TE - beqz k1,1f - emt -1: - /* - * The IPI sender has put some information on the anticipated - * kernel stack frame. If we were in user mode, this will be - * built above the saved kernel SP. If we were already in the - * kernel, it will be built above the current CPU SP. - * - * Were we in kernel mode, as indicated by CU0? - */ - sll k1,k0,3 - .set noreorder - bltz k1,2f - move k1,sp - .set reorder - /* - * If previously in user mode, set CU0 and use kernel stack. - */ - li k1,ST0_CU0 - or k1,k1,k0 - mtc0 k1,CP0_STATUS - _ehb - get_saved_sp - /* Interrupting TC will have pre-set values in slots in the new frame */ -2: subu k1,k1,PT_SIZE - /* Load TCStatus Value */ - lw k0,PT_TCSTATUS(k1) - /* Write it to TCStatus to restore CU/KSU/IXMT state */ - mtc0 k0,$2,1 - _ehb - lw k0,PT_EPC(k1) - mtc0 k0,CP0_EPC - /* Save all will redundantly recompute the SP, but use it for now */ - SAVE_ALL - CLI - TRACE_IRQS_OFF - /* Function to be invoked passed stack pad slot 5 */ - lw t0,PT_PADSLOT5(sp) - /* Argument from sender passed in stack pad slot 4 */ - lw a0,PT_PADSLOT4(sp) - LONG_L s0, TI_REGS($28) - LONG_S sp, TI_REGS($28) - PTR_LA ra, ret_from_irq - jr t0 - -/* - * Called from idle loop to provoke processing of queued IPIs - * First IPI message in queue passed as argument. - */ - -LEAF(self_ipi) - /* Before anything else, block interrupts */ - mfc0 t0,CP0_TCSTATUS - ori t1,t0,TCSTATUS_IXMT - mtc0 t1,CP0_TCSTATUS - _ehb - /* We know we're in kernel mode, so prepare stack frame */ - subu t1,sp,PT_SIZE - sw ra,PT_EPC(t1) - sw a0,PT_PADSLOT4(t1) - la t2,ipi_decode - sw t2,PT_PADSLOT5(t1) - /* Save pre-disable value of TCStatus */ - sw t0,PT_TCSTATUS(t1) - j __smtc_ipi_vector - nop -END(self_ipi) diff --git a/arch/mips/kernel/smtc-proc.c b/arch/mips/kernel/smtc-proc.c deleted file mode 100644 index 38635a996cbf..000000000000 --- a/arch/mips/kernel/smtc-proc.c +++ /dev/null @@ -1,102 +0,0 @@ -/* - * /proc hooks for SMTC kernel - * Copyright (C) 2005 Mips Technologies, Inc - */ - -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/cpumask.h> -#include <linux/interrupt.h> - -#include <asm/cpu.h> -#include <asm/processor.h> -#include <linux/atomic.h> -#include <asm/hardirq.h> -#include <asm/mmu_context.h> -#include <asm/mipsregs.h> -#include <asm/cacheflush.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> - -#include <asm/smtc_proc.h> - -/* - * /proc diagnostic and statistics hooks - */ - -/* - * Statistics gathered - */ -unsigned long selfipis[NR_CPUS]; - -struct smtc_cpu_proc smtc_cpu_stats[NR_CPUS]; - -atomic_t smtc_fpu_recoveries; - -static int smtc_proc_show(struct seq_file *m, void *v) -{ - int i; - extern unsigned long ebase; - - seq_printf(m, "SMTC Status Word: 0x%08x\n", smtc_status); - seq_printf(m, "Config7: 0x%08x\n", read_c0_config7()); - seq_printf(m, "EBASE: 0x%08lx\n", ebase); - seq_printf(m, "Counter Interrupts taken per CPU (TC)\n"); - for (i=0; i < NR_CPUS; i++) - seq_printf(m, "%d: %ld\n", i, smtc_cpu_stats[i].timerints); - seq_printf(m, "Self-IPIs by CPU:\n"); - for(i = 0; i < NR_CPUS; i++) - seq_printf(m, "%d: %ld\n", i, smtc_cpu_stats[i].selfipis); - seq_printf(m, "%d Recoveries of \"stolen\" FPU\n", - atomic_read(&smtc_fpu_recoveries)); - return 0; -} - -static int smtc_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, smtc_proc_show, NULL); -} - -static const struct file_operations smtc_proc_fops = { - .open = smtc_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -void init_smtc_stats(void) -{ - int i; - - for (i=0; i<NR_CPUS; i++) { - smtc_cpu_stats[i].timerints = 0; - smtc_cpu_stats[i].selfipis = 0; - } - - atomic_set(&smtc_fpu_recoveries, 0); - - proc_create("smtc", 0444, NULL, &smtc_proc_fops); -} - -static int proc_cpuinfo_chain_call(struct notifier_block *nfb, - unsigned long action_unused, void *data) -{ - struct proc_cpuinfo_notifier_args *pcn = data; - struct seq_file *m = pcn->m; - unsigned long n = pcn->n; - - if (!cpu_has_mipsmt) - return NOTIFY_OK; - - seq_printf(m, "VPE\t\t\t: %d\n", cpu_data[n].vpe_id); - seq_printf(m, "TC\t\t\t: %d\n", cpu_data[n].tc_id); - - return NOTIFY_OK; -} - -static int __init proc_cpuinfo_notifier_init(void) -{ - return proc_cpuinfo_notifier(proc_cpuinfo_chain_call, 0); -} - -subsys_initcall(proc_cpuinfo_notifier_init); diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c deleted file mode 100644 index c1681d65dd5c..000000000000 --- a/arch/mips/kernel/smtc.c +++ /dev/null @@ -1,1528 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * Copyright (C) 2004 Mips Technologies, Inc - * Copyright (C) 2008 Kevin D. Kissell - */ - -#include <linux/clockchips.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/smp.h> -#include <linux/cpumask.h> -#include <linux/interrupt.h> -#include <linux/kernel_stat.h> -#include <linux/module.h> -#include <linux/ftrace.h> -#include <linux/slab.h> - -#include <asm/cpu.h> -#include <asm/processor.h> -#include <linux/atomic.h> -#include <asm/hardirq.h> -#include <asm/hazards.h> -#include <asm/irq.h> -#include <asm/idle.h> -#include <asm/mmu_context.h> -#include <asm/mipsregs.h> -#include <asm/cacheflush.h> -#include <asm/time.h> -#include <asm/addrspace.h> -#include <asm/smtc.h> -#include <asm/smtc_proc.h> -#include <asm/setup.h> - -/* - * SMTC Kernel needs to manipulate low-level CPU interrupt mask - * in do_IRQ. These are passed in setup_irq_smtc() and stored - * in this table. - */ -unsigned long irq_hwmask[NR_IRQS]; - -#define LOCK_MT_PRA() \ - local_irq_save(flags); \ - mtflags = dmt() - -#define UNLOCK_MT_PRA() \ - emt(mtflags); \ - local_irq_restore(flags) - -#define LOCK_CORE_PRA() \ - local_irq_save(flags); \ - mtflags = dvpe() - -#define UNLOCK_CORE_PRA() \ - evpe(mtflags); \ - local_irq_restore(flags) - -/* - * Data structures purely associated with SMTC parallelism - */ - - -/* - * Table for tracking ASIDs whose lifetime is prolonged. - */ - -asiduse smtc_live_asid[MAX_SMTC_TLBS][MAX_SMTC_ASIDS]; - -/* - * Number of InterProcessor Interrupt (IPI) message buffers to allocate - */ - -#define IPIBUF_PER_CPU 4 - -struct smtc_ipi_q IPIQ[NR_CPUS]; -static struct smtc_ipi_q freeIPIq; - - -/* - * Number of FPU contexts for each VPE - */ - -static int smtc_nconf1[MAX_SMTC_VPES]; - - -/* Forward declarations */ - -void ipi_decode(struct smtc_ipi *); -static void post_direct_ipi(int cpu, struct smtc_ipi *pipi); -static void setup_cross_vpe_interrupts(unsigned int nvpe); -void init_smtc_stats(void); - -/* Global SMTC Status */ - -unsigned int smtc_status; - -/* Boot command line configuration overrides */ - -static int vpe0limit; -static int ipibuffers; -static int nostlb; -static int asidmask; -unsigned long smtc_asid_mask = 0xff; - -static int __init vpe0tcs(char *str) -{ - get_option(&str, &vpe0limit); - - return 1; -} - -static int __init ipibufs(char *str) -{ - get_option(&str, &ipibuffers); - return 1; -} - -static int __init stlb_disable(char *s) -{ - nostlb = 1; - return 1; -} - -static int __init asidmask_set(char *str) -{ - get_option(&str, &asidmask); - switch (asidmask) { - case 0x1: - case 0x3: - case 0x7: - case 0xf: - case 0x1f: - case 0x3f: - case 0x7f: - case 0xff: - smtc_asid_mask = (unsigned long)asidmask; - break; - default: - printk("ILLEGAL ASID mask 0x%x from command line\n", asidmask); - } - return 1; -} - -__setup("vpe0tcs=", vpe0tcs); -__setup("ipibufs=", ipibufs); -__setup("nostlb", stlb_disable); -__setup("asidmask=", asidmask_set); - -#ifdef CONFIG_SMTC_IDLE_HOOK_DEBUG - -static int hang_trig; - -static int __init hangtrig_enable(char *s) -{ - hang_trig = 1; - return 1; -} - - -__setup("hangtrig", hangtrig_enable); - -#define DEFAULT_BLOCKED_IPI_LIMIT 32 - -static int timerq_limit = DEFAULT_BLOCKED_IPI_LIMIT; - -static int __init tintq(char *str) -{ - get_option(&str, &timerq_limit); - return 1; -} - -__setup("tintq=", tintq); - -static int imstuckcount[MAX_SMTC_VPES][8]; -/* vpemask represents IM/IE bits of per-VPE Status registers, low-to-high */ -static int vpemask[MAX_SMTC_VPES][8] = { - {0, 0, 1, 0, 0, 0, 0, 1}, - {0, 0, 0, 0, 0, 0, 0, 1} -}; -int tcnoprog[NR_CPUS]; -static atomic_t idle_hook_initialized = ATOMIC_INIT(0); -static int clock_hang_reported[NR_CPUS]; - -#endif /* CONFIG_SMTC_IDLE_HOOK_DEBUG */ - -/* - * Configure shared TLB - VPC configuration bit must be set by caller - */ - -static void smtc_configure_tlb(void) -{ - int i, tlbsiz, vpes; - unsigned long mvpconf0; - unsigned long config1val; - - /* Set up ASID preservation table */ - for (vpes=0; vpes<MAX_SMTC_TLBS; vpes++) { - for(i = 0; i < MAX_SMTC_ASIDS; i++) { - smtc_live_asid[vpes][i] = 0; - } - } - mvpconf0 = read_c0_mvpconf0(); - - if ((vpes = ((mvpconf0 & MVPCONF0_PVPE) - >> MVPCONF0_PVPE_SHIFT) + 1) > 1) { - /* If we have multiple VPEs, try to share the TLB */ - if ((mvpconf0 & MVPCONF0_TLBS) && !nostlb) { - /* - * If TLB sizing is programmable, shared TLB - * size is the total available complement. - * Otherwise, we have to take the sum of all - * static VPE TLB entries. - */ - if ((tlbsiz = ((mvpconf0 & MVPCONF0_PTLBE) - >> MVPCONF0_PTLBE_SHIFT)) == 0) { - /* - * If there's more than one VPE, there had better - * be more than one TC, because we need one to bind - * to each VPE in turn to be able to read - * its configuration state! - */ - settc(1); - /* Stop the TC from doing anything foolish */ - write_tc_c0_tchalt(TCHALT_H); - mips_ihb(); - /* No need to un-Halt - that happens later anyway */ - for (i=0; i < vpes; i++) { - write_tc_c0_tcbind(i); - /* - * To be 100% sure we're really getting the right - * information, we exit the configuration state - * and do an IHB after each rebinding. - */ - write_c0_mvpcontrol( - read_c0_mvpcontrol() & ~ MVPCONTROL_VPC ); - mips_ihb(); - /* - * Only count if the MMU Type indicated is TLB - */ - if (((read_vpe_c0_config() & MIPS_CONF_MT) >> 7) == 1) { - config1val = read_vpe_c0_config1(); - tlbsiz += ((config1val >> 25) & 0x3f) + 1; - } - - /* Put core back in configuration state */ - write_c0_mvpcontrol( - read_c0_mvpcontrol() | MVPCONTROL_VPC ); - mips_ihb(); - } - } - write_c0_mvpcontrol(read_c0_mvpcontrol() | MVPCONTROL_STLB); - ehb(); - - /* - * Setup kernel data structures to use software total, - * rather than read the per-VPE Config1 value. The values - * for "CPU 0" gets copied to all the other CPUs as part - * of their initialization in smtc_cpu_setup(). - */ - - /* MIPS32 limits TLB indices to 64 */ - if (tlbsiz > 64) - tlbsiz = 64; - cpu_data[0].tlbsize = current_cpu_data.tlbsize = tlbsiz; - smtc_status |= SMTC_TLB_SHARED; - local_flush_tlb_all(); - - printk("TLB of %d entry pairs shared by %d VPEs\n", - tlbsiz, vpes); - } else { - printk("WARNING: TLB Not Sharable on SMTC Boot!\n"); - } - } -} - - -/* - * Incrementally build the CPU map out of constituent MIPS MT cores, - * using the specified available VPEs and TCs. Plaform code needs - * to ensure that each MIPS MT core invokes this routine on reset, - * one at a time(!). - * - * This version of the build_cpu_map and prepare_cpus routines assumes - * that *all* TCs of a MIPS MT core will be used for Linux, and that - * they will be spread across *all* available VPEs (to minimise the - * loss of efficiency due to exception service serialization). - * An improved version would pick up configuration information and - * possibly leave some TCs/VPEs as "slave" processors. - * - * Use c0_MVPConf0 to find out how many TCs are available, setting up - * cpu_possible_mask and the logical/physical mappings. - */ - -int __init smtc_build_cpu_map(int start_cpu_slot) -{ - int i, ntcs; - - /* - * The CPU map isn't actually used for anything at this point, - * so it's not clear what else we should do apart from set - * everything up so that "logical" = "physical". - */ - ntcs = ((read_c0_mvpconf0() & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1; - for (i=start_cpu_slot; i<NR_CPUS && i<ntcs; i++) { - set_cpu_possible(i, true); - __cpu_number_map[i] = i; - __cpu_logical_map[i] = i; - } -#ifdef CONFIG_MIPS_MT_FPAFF - /* Initialize map of CPUs with FPUs */ - cpus_clear(mt_fpu_cpumask); -#endif - - /* One of those TC's is the one booting, and not a secondary... */ - printk("%i available secondary CPU TC(s)\n", i - 1); - - return i; -} - -/* - * Common setup before any secondaries are started - * Make sure all CPUs are in a sensible state before we boot any of the - * secondaries. - * - * For MIPS MT "SMTC" operation, we set up all TCs, spread as evenly - * as possible across the available VPEs. - */ - -static void smtc_tc_setup(int vpe, int tc, int cpu) -{ - static int cp1contexts[MAX_SMTC_VPES]; - - /* - * Make a local copy of the available FPU contexts in order - * to keep track of TCs that can have one. - */ - if (tc == 1) - { - /* - * FIXME: Multi-core SMTC hasn't been tested and the - * maximum number of VPEs may change. - */ - cp1contexts[0] = smtc_nconf1[0] - 1; - cp1contexts[1] = smtc_nconf1[1]; - } - - settc(tc); - write_tc_c0_tchalt(TCHALT_H); - mips_ihb(); - write_tc_c0_tcstatus((read_tc_c0_tcstatus() - & ~(TCSTATUS_TKSU | TCSTATUS_DA | TCSTATUS_IXMT)) - | TCSTATUS_A); - /* - * TCContext gets an offset from the base of the IPIQ array - * to be used in low-level code to detect the presence of - * an active IPI queue. - */ - write_tc_c0_tccontext((sizeof(struct smtc_ipi_q) * cpu) << 16); - - /* Bind TC to VPE. */ - write_tc_c0_tcbind(vpe); - - /* In general, all TCs should have the same cpu_data indications. */ - memcpy(&cpu_data[cpu], &cpu_data[0], sizeof(struct cpuinfo_mips)); - - /* Check to see if there is a FPU context available for this TC. */ - if (!cp1contexts[vpe]) - cpu_data[cpu].options &= ~MIPS_CPU_FPU; - else - cp1contexts[vpe]--; - - /* Store the TC and VPE into the cpu_data structure. */ - cpu_data[cpu].vpe_id = vpe; - cpu_data[cpu].tc_id = tc; - - /* FIXME: Multi-core SMTC hasn't been tested, but be prepared. */ - cpu_data[cpu].core = (read_vpe_c0_ebase() >> 1) & 0xff; -} - -/* - * Tweak to get Count registers synced as closely as possible. The - * value seems good for 34K-class cores. - */ - -#define CP0_SKEW 8 - -void smtc_prepare_cpus(int cpus) -{ - int i, vpe, tc, ntc, nvpe, tcpervpe[NR_CPUS], slop, cpu; - unsigned long flags; - unsigned long val; - int nipi; - struct smtc_ipi *pipi; - - /* disable interrupts so we can disable MT */ - local_irq_save(flags); - /* disable MT so we can configure */ - dvpe(); - dmt(); - - spin_lock_init(&freeIPIq.lock); - - /* - * We probably don't have as many VPEs as we do SMP "CPUs", - * but it's possible - and in any case we'll never use more! - */ - for (i=0; i<NR_CPUS; i++) { - IPIQ[i].head = IPIQ[i].tail = NULL; - spin_lock_init(&IPIQ[i].lock); - IPIQ[i].depth = 0; - IPIQ[i].resched_flag = 0; /* No reschedules queued initially */ - } - - /* cpu_data index starts at zero */ - cpu = 0; - cpu_data[cpu].vpe_id = 0; - cpu_data[cpu].tc_id = 0; - cpu_data[cpu].core = (read_c0_ebase() >> 1) & 0xff; - cpu++; - - /* Report on boot-time options */ - mips_mt_set_cpuoptions(); - if (vpelimit > 0) - printk("Limit of %d VPEs set\n", vpelimit); - if (tclimit > 0) - printk("Limit of %d TCs set\n", tclimit); - if (nostlb) { - printk("Shared TLB Use Inhibited - UNSAFE for Multi-VPE Operation\n"); - } - if (asidmask) - printk("ASID mask value override to 0x%x\n", asidmask); - - /* Temporary */ -#ifdef CONFIG_SMTC_IDLE_HOOK_DEBUG - if (hang_trig) - printk("Logic Analyser Trigger on suspected TC hang\n"); -#endif /* CONFIG_SMTC_IDLE_HOOK_DEBUG */ - - /* Put MVPE's into 'configuration state' */ - write_c0_mvpcontrol( read_c0_mvpcontrol() | MVPCONTROL_VPC ); - - val = read_c0_mvpconf0(); - nvpe = ((val & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1; - if (vpelimit > 0 && nvpe > vpelimit) - nvpe = vpelimit; - ntc = ((val & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1; - if (ntc > NR_CPUS) - ntc = NR_CPUS; - if (tclimit > 0 && ntc > tclimit) - ntc = tclimit; - slop = ntc % nvpe; - for (i = 0; i < nvpe; i++) { - tcpervpe[i] = ntc / nvpe; - if (slop) { - if((slop - i) > 0) tcpervpe[i]++; - } - } - /* Handle command line override for VPE0 */ - if (vpe0limit > ntc) vpe0limit = ntc; - if (vpe0limit > 0) { - int slopslop; - if (vpe0limit < tcpervpe[0]) { - /* Reducing TC count - distribute to others */ - slop = tcpervpe[0] - vpe0limit; - slopslop = slop % (nvpe - 1); - tcpervpe[0] = vpe0limit; - for (i = 1; i < nvpe; i++) { - tcpervpe[i] += slop / (nvpe - 1); - if(slopslop && ((slopslop - (i - 1) > 0))) - tcpervpe[i]++; - } - } else if (vpe0limit > tcpervpe[0]) { - /* Increasing TC count - steal from others */ - slop = vpe0limit - tcpervpe[0]; - slopslop = slop % (nvpe - 1); - tcpervpe[0] = vpe0limit; - for (i = 1; i < nvpe; i++) { - tcpervpe[i] -= slop / (nvpe - 1); - if(slopslop && ((slopslop - (i - 1) > 0))) - tcpervpe[i]--; - } - } - } - - /* Set up shared TLB */ - smtc_configure_tlb(); - - for (tc = 0, vpe = 0 ; (vpe < nvpe) && (tc < ntc) ; vpe++) { - /* Get number of CP1 contexts for each VPE. */ - if (tc == 0) - { - /* - * Do not call settc() for TC0 or the FPU context - * value will be incorrect. Besides, we know that - * we are TC0 anyway. - */ - smtc_nconf1[0] = ((read_vpe_c0_vpeconf1() & - VPECONF1_NCP1) >> VPECONF1_NCP1_SHIFT); - if (nvpe == 2) - { - settc(1); - smtc_nconf1[1] = ((read_vpe_c0_vpeconf1() & - VPECONF1_NCP1) >> VPECONF1_NCP1_SHIFT); - settc(0); - } - } - if (tcpervpe[vpe] == 0) - continue; - if (vpe != 0) - printk(", "); - printk("VPE %d: TC", vpe); - for (i = 0; i < tcpervpe[vpe]; i++) { - /* - * TC 0 is bound to VPE 0 at reset, - * and is presumably executing this - * code. Leave it alone! - */ - if (tc != 0) { - smtc_tc_setup(vpe, tc, cpu); - if (vpe != 0) { - /* - * Set MVP bit (possibly again). Do it - * here to catch CPUs that have no TCs - * bound to the VPE at reset. In that - * case, a TC must be bound to the VPE - * before we can set VPEControl[MVP] - */ - write_vpe_c0_vpeconf0( - read_vpe_c0_vpeconf0() | - VPECONF0_MVP); - } - cpu++; - } - printk(" %d", tc); - tc++; - } - if (vpe != 0) { - /* - * Allow this VPE to control others. - */ - write_vpe_c0_vpeconf0(read_vpe_c0_vpeconf0() | - VPECONF0_MVP); - - /* - * Clear any stale software interrupts from VPE's Cause - */ - write_vpe_c0_cause(0); - - /* - * Clear ERL/EXL of VPEs other than 0 - * and set restricted interrupt enable/mask. - */ - write_vpe_c0_status((read_vpe_c0_status() - & ~(ST0_BEV | ST0_ERL | ST0_EXL | ST0_IM)) - | (STATUSF_IP0 | STATUSF_IP1 | STATUSF_IP7 - | ST0_IE)); - /* - * set config to be the same as vpe0, - * particularly kseg0 coherency alg - */ - write_vpe_c0_config(read_c0_config()); - /* Clear any pending timer interrupt */ - write_vpe_c0_compare(0); - /* Propagate Config7 */ - write_vpe_c0_config7(read_c0_config7()); - write_vpe_c0_count(read_c0_count() + CP0_SKEW); - ehb(); - } - /* enable multi-threading within VPE */ - write_vpe_c0_vpecontrol(read_vpe_c0_vpecontrol() | VPECONTROL_TE); - /* enable the VPE */ - write_vpe_c0_vpeconf0(read_vpe_c0_vpeconf0() | VPECONF0_VPA); - } - - /* - * Pull any physically present but unused TCs out of circulation. - */ - while (tc < (((val & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1)) { - set_cpu_possible(tc, false); - set_cpu_present(tc, false); - tc++; - } - - /* release config state */ - write_c0_mvpcontrol( read_c0_mvpcontrol() & ~ MVPCONTROL_VPC ); - - printk("\n"); - - /* Set up coprocessor affinity CPU mask(s) */ - -#ifdef CONFIG_MIPS_MT_FPAFF - for (tc = 0; tc < ntc; tc++) { - if (cpu_data[tc].options & MIPS_CPU_FPU) - cpu_set(tc, mt_fpu_cpumask); - } -#endif - - /* set up ipi interrupts... */ - - /* If we have multiple VPEs running, set up the cross-VPE interrupt */ - - setup_cross_vpe_interrupts(nvpe); - - /* Set up queue of free IPI "messages". */ - nipi = NR_CPUS * IPIBUF_PER_CPU; - if (ipibuffers > 0) - nipi = ipibuffers; - - pipi = kmalloc(nipi *sizeof(struct smtc_ipi), GFP_KERNEL); - if (pipi == NULL) - panic("kmalloc of IPI message buffers failed"); - else - printk("IPI buffer pool of %d buffers\n", nipi); - for (i = 0; i < nipi; i++) { - smtc_ipi_nq(&freeIPIq, pipi); - pipi++; - } - - /* Arm multithreading and enable other VPEs - but all TCs are Halted */ - emt(EMT_ENABLE); - evpe(EVPE_ENABLE); - local_irq_restore(flags); - /* Initialize SMTC /proc statistics/diagnostics */ - init_smtc_stats(); -} - - -/* - * Setup the PC, SP, and GP of a secondary processor and start it - * running! - * smp_bootstrap is the place to resume from - * __KSTK_TOS(idle) is apparently the stack pointer - * (unsigned long)idle->thread_info the gp - * - */ -void smtc_boot_secondary(int cpu, struct task_struct *idle) -{ - extern u32 kernelsp[NR_CPUS]; - unsigned long flags; - int mtflags; - - LOCK_MT_PRA(); - if (cpu_data[cpu].vpe_id != cpu_data[smp_processor_id()].vpe_id) { - dvpe(); - } - settc(cpu_data[cpu].tc_id); - - /* pc */ - write_tc_c0_tcrestart((unsigned long)&smp_bootstrap); - - /* stack pointer */ - kernelsp[cpu] = __KSTK_TOS(idle); - write_tc_gpr_sp(__KSTK_TOS(idle)); - - /* global pointer */ - write_tc_gpr_gp((unsigned long)task_thread_info(idle)); - - smtc_status |= SMTC_MTC_ACTIVE; - write_tc_c0_tchalt(0); - if (cpu_data[cpu].vpe_id != cpu_data[smp_processor_id()].vpe_id) { - evpe(EVPE_ENABLE); - } - UNLOCK_MT_PRA(); -} - -void smtc_init_secondary(void) -{ -} - -void smtc_smp_finish(void) -{ - int cpu = smp_processor_id(); - - /* - * Lowest-numbered CPU per VPE starts a clock tick. - * Like per_cpu_trap_init() hack, this assumes that - * SMTC init code assigns TCs consdecutively and - * in ascending order across available VPEs. - */ - if (cpu > 0 && (cpu_data[cpu].vpe_id != cpu_data[cpu - 1].vpe_id)) - write_c0_compare(read_c0_count() + mips_hpt_frequency/HZ); - - local_irq_enable(); - - printk("TC %d going on-line as CPU %d\n", - cpu_data[smp_processor_id()].tc_id, smp_processor_id()); -} - -void smtc_cpus_done(void) -{ -} - -/* - * Support for SMTC-optimized driver IRQ registration - */ - -/* - * SMTC Kernel needs to manipulate low-level CPU interrupt mask - * in do_IRQ. These are passed in setup_irq_smtc() and stored - * in this table. - */ - -int setup_irq_smtc(unsigned int irq, struct irqaction * new, - unsigned long hwmask) -{ -#ifdef CONFIG_SMTC_IDLE_HOOK_DEBUG - unsigned int vpe = current_cpu_data.vpe_id; - - vpemask[vpe][irq - MIPS_CPU_IRQ_BASE] = 1; -#endif - irq_hwmask[irq] = hwmask; - - return setup_irq(irq, new); -} - -#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF -/* - * Support for IRQ affinity to TCs - */ - -void smtc_set_irq_affinity(unsigned int irq, cpumask_t affinity) -{ - /* - * If a "fast path" cache of quickly decodable affinity state - * is maintained, this is where it gets done, on a call up - * from the platform affinity code. - */ -} - -void smtc_forward_irq(struct irq_data *d) -{ - unsigned int irq = d->irq; - int target; - - /* - * OK wise guy, now figure out how to get the IRQ - * to be serviced on an authorized "CPU". - * - * Ideally, to handle the situation where an IRQ has multiple - * eligible CPUS, we would maintain state per IRQ that would - * allow a fair distribution of service requests. Since the - * expected use model is any-or-only-one, for simplicity - * and efficiency, we just pick the easiest one to find. - */ - - target = cpumask_first(d->affinity); - - /* - * We depend on the platform code to have correctly processed - * IRQ affinity change requests to ensure that the IRQ affinity - * mask has been purged of bits corresponding to nonexistent and - * offline "CPUs", and to TCs bound to VPEs other than the VPE - * connected to the physical interrupt input for the interrupt - * in question. Otherwise we have a nasty problem with interrupt - * mask management. This is best handled in non-performance-critical - * platform IRQ affinity setting code, to minimize interrupt-time - * checks. - */ - - /* If no one is eligible, service locally */ - if (target >= NR_CPUS) - do_IRQ_no_affinity(irq); - else - smtc_send_ipi(target, IRQ_AFFINITY_IPI, irq); -} - -#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ - -/* - * IPI model for SMTC is tricky, because interrupts aren't TC-specific. - * Within a VPE one TC can interrupt another by different approaches. - * The easiest to get right would probably be to make all TCs except - * the target IXMT and set a software interrupt, but an IXMT-based - * scheme requires that a handler must run before a new IPI could - * be sent, which would break the "broadcast" loops in MIPS MT. - * A more gonzo approach within a VPE is to halt the TC, extract - * its Restart, Status, and a couple of GPRs, and program the Restart - * address to emulate an interrupt. - * - * Within a VPE, one can be confident that the target TC isn't in - * a critical EXL state when halted, since the write to the Halt - * register could not have issued on the writing thread if the - * halting thread had EXL set. So k0 and k1 of the target TC - * can be used by the injection code. Across VPEs, one can't - * be certain that the target TC isn't in a critical exception - * state. So we try a two-step process of sending a software - * interrupt to the target VPE, which either handles the event - * itself (if it was the target) or injects the event within - * the VPE. - */ - -static void smtc_ipi_qdump(void) -{ - int i; - struct smtc_ipi *temp; - - for (i = 0; i < NR_CPUS ;i++) { - pr_info("IPIQ[%d]: head = 0x%x, tail = 0x%x, depth = %d\n", - i, (unsigned)IPIQ[i].head, (unsigned)IPIQ[i].tail, - IPIQ[i].depth); - temp = IPIQ[i].head; - - while (temp != IPIQ[i].tail) { - pr_debug("%d %d %d: ", temp->type, temp->dest, - (int)temp->arg); -#ifdef SMTC_IPI_DEBUG - pr_debug("%u %lu\n", temp->sender, temp->stamp); -#else - pr_debug("\n"); -#endif - temp = temp->flink; - } - } -} - -/* - * The standard atomic.h primitives don't quite do what we want - * here: We need an atomic add-and-return-previous-value (which - * could be done with atomic_add_return and a decrement) and an - * atomic set/zero-and-return-previous-value (which can't really - * be done with the atomic.h primitives). And since this is - * MIPS MT, we can assume that we have LL/SC. - */ -static inline int atomic_postincrement(atomic_t *v) -{ - unsigned long result; - - unsigned long temp; - - __asm__ __volatile__( - "1: ll %0, %2 \n" - " addu %1, %0, 1 \n" - " sc %1, %2 \n" - " beqz %1, 1b \n" - __WEAK_LLSC_MB - : "=&r" (result), "=&r" (temp), "=m" (v->counter) - : "m" (v->counter) - : "memory"); - - return result; -} - -void smtc_send_ipi(int cpu, int type, unsigned int action) -{ - int tcstatus; - struct smtc_ipi *pipi; - unsigned long flags; - int mtflags; - unsigned long tcrestart; - int set_resched_flag = (type == LINUX_SMP_IPI && - action == SMP_RESCHEDULE_YOURSELF); - - if (cpu == smp_processor_id()) { - printk("Cannot Send IPI to self!\n"); - return; - } - if (set_resched_flag && IPIQ[cpu].resched_flag != 0) - return; /* There is a reschedule queued already */ - - /* Set up a descriptor, to be delivered either promptly or queued */ - pipi = smtc_ipi_dq(&freeIPIq); - if (pipi == NULL) { - bust_spinlocks(1); - mips_mt_regdump(dvpe()); - panic("IPI Msg. Buffers Depleted"); - } - pipi->type = type; - pipi->arg = (void *)action; - pipi->dest = cpu; - if (cpu_data[cpu].vpe_id != cpu_data[smp_processor_id()].vpe_id) { - /* If not on same VPE, enqueue and send cross-VPE interrupt */ - IPIQ[cpu].resched_flag |= set_resched_flag; - smtc_ipi_nq(&IPIQ[cpu], pipi); - LOCK_CORE_PRA(); - settc(cpu_data[cpu].tc_id); - write_vpe_c0_cause(read_vpe_c0_cause() | C_SW1); - UNLOCK_CORE_PRA(); - } else { - /* - * Not sufficient to do a LOCK_MT_PRA (dmt) here, - * since ASID shootdown on the other VPE may - * collide with this operation. - */ - LOCK_CORE_PRA(); - settc(cpu_data[cpu].tc_id); - /* Halt the targeted TC */ - write_tc_c0_tchalt(TCHALT_H); - mips_ihb(); - - /* - * Inspect TCStatus - if IXMT is set, we have to queue - * a message. Otherwise, we set up the "interrupt" - * of the other TC - */ - tcstatus = read_tc_c0_tcstatus(); - - if ((tcstatus & TCSTATUS_IXMT) != 0) { - /* - * If we're in the the irq-off version of the wait - * loop, we need to force exit from the wait and - * do a direct post of the IPI. - */ - if (cpu_wait == r4k_wait_irqoff) { - tcrestart = read_tc_c0_tcrestart(); - if (address_is_in_r4k_wait_irqoff(tcrestart)) { - write_tc_c0_tcrestart(__pastwait); - tcstatus &= ~TCSTATUS_IXMT; - write_tc_c0_tcstatus(tcstatus); - goto postdirect; - } - } - /* - * Otherwise we queue the message for the target TC - * to pick up when he does a local_irq_restore() - */ - write_tc_c0_tchalt(0); - UNLOCK_CORE_PRA(); - IPIQ[cpu].resched_flag |= set_resched_flag; - smtc_ipi_nq(&IPIQ[cpu], pipi); - } else { -postdirect: - post_direct_ipi(cpu, pipi); - write_tc_c0_tchalt(0); - UNLOCK_CORE_PRA(); - } - } -} - -/* - * Send IPI message to Halted TC, TargTC/TargVPE already having been set - */ -static void post_direct_ipi(int cpu, struct smtc_ipi *pipi) -{ - struct pt_regs *kstack; - unsigned long tcstatus; - unsigned long tcrestart; - extern u32 kernelsp[NR_CPUS]; - extern void __smtc_ipi_vector(void); -//printk("%s: on %d for %d\n", __func__, smp_processor_id(), cpu); - - /* Extract Status, EPC from halted TC */ - tcstatus = read_tc_c0_tcstatus(); - tcrestart = read_tc_c0_tcrestart(); - /* If TCRestart indicates a WAIT instruction, advance the PC */ - if ((tcrestart & 0x80000000) - && ((*(unsigned int *)tcrestart & 0xfe00003f) == 0x42000020)) { - tcrestart += 4; - } - /* - * Save on TC's future kernel stack - * - * CU bit of Status is indicator that TC was - * already running on a kernel stack... - */ - if (tcstatus & ST0_CU0) { - /* Note that this "- 1" is pointer arithmetic */ - kstack = ((struct pt_regs *)read_tc_gpr_sp()) - 1; - } else { - kstack = ((struct pt_regs *)kernelsp[cpu]) - 1; - } - - kstack->cp0_epc = (long)tcrestart; - /* Save TCStatus */ - kstack->cp0_tcstatus = tcstatus; - /* Pass token of operation to be performed kernel stack pad area */ - kstack->pad0[4] = (unsigned long)pipi; - /* Pass address of function to be called likewise */ - kstack->pad0[5] = (unsigned long)&ipi_decode; - /* Set interrupt exempt and kernel mode */ - tcstatus |= TCSTATUS_IXMT; - tcstatus &= ~TCSTATUS_TKSU; - write_tc_c0_tcstatus(tcstatus); - ehb(); - /* Set TC Restart address to be SMTC IPI vector */ - write_tc_c0_tcrestart(__smtc_ipi_vector); -} - -static void ipi_resched_interrupt(void) -{ - scheduler_ipi(); -} - -static void ipi_call_interrupt(void) -{ - /* Invoke generic function invocation code in smp.c */ - smp_call_function_interrupt(); -} - -DECLARE_PER_CPU(struct clock_event_device, mips_clockevent_device); - -static void __irq_entry smtc_clock_tick_interrupt(void) -{ - unsigned int cpu = smp_processor_id(); - struct clock_event_device *cd; - int irq = MIPS_CPU_IRQ_BASE + 1; - - irq_enter(); - kstat_incr_irq_this_cpu(irq); - cd = &per_cpu(mips_clockevent_device, cpu); - cd->event_handler(cd); - irq_exit(); -} - -void ipi_decode(struct smtc_ipi *pipi) -{ - void *arg_copy = pipi->arg; - int type_copy = pipi->type; - - smtc_ipi_nq(&freeIPIq, pipi); - - switch (type_copy) { - case SMTC_CLOCK_TICK: - smtc_clock_tick_interrupt(); - break; - - case LINUX_SMP_IPI: - switch ((int)arg_copy) { - case SMP_RESCHEDULE_YOURSELF: - ipi_resched_interrupt(); - break; - case SMP_CALL_FUNCTION: - ipi_call_interrupt(); - break; - default: - printk("Impossible SMTC IPI Argument %p\n", arg_copy); - break; - } - break; -#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF - case IRQ_AFFINITY_IPI: - /* - * Accept a "forwarded" interrupt that was initially - * taken by a TC who doesn't have affinity for the IRQ. - */ - do_IRQ_no_affinity((int)arg_copy); - break; -#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ - default: - printk("Impossible SMTC IPI Type 0x%x\n", type_copy); - break; - } -} - -/* - * Similar to smtc_ipi_replay(), but invoked from context restore, - * so it reuses the current exception frame rather than set up a - * new one with self_ipi. - */ - -void deferred_smtc_ipi(void) -{ - int cpu = smp_processor_id(); - - /* - * Test is not atomic, but much faster than a dequeue, - * and the vast majority of invocations will have a null queue. - * If irq_disabled when this was called, then any IPIs queued - * after we test last will be taken on the next irq_enable/restore. - * If interrupts were enabled, then any IPIs added after the - * last test will be taken directly. - */ - - while (IPIQ[cpu].head != NULL) { - struct smtc_ipi_q *q = &IPIQ[cpu]; - struct smtc_ipi *pipi; - unsigned long flags; - - /* - * It may be possible we'll come in with interrupts - * already enabled. - */ - local_irq_save(flags); - spin_lock(&q->lock); - pipi = __smtc_ipi_dq(q); - spin_unlock(&q->lock); - if (pipi != NULL) { - if (pipi->type == LINUX_SMP_IPI && - (int)pipi->arg == SMP_RESCHEDULE_YOURSELF) - IPIQ[cpu].resched_flag = 0; - ipi_decode(pipi); - } - /* - * The use of the __raw_local restore isn't - * as obviously necessary here as in smtc_ipi_replay(), - * but it's more efficient, given that we're already - * running down the IPI queue. - */ - __arch_local_irq_restore(flags); - } -} - -/* - * Cross-VPE interrupts in the SMTC prototype use "software interrupts" - * set via cross-VPE MTTR manipulation of the Cause register. It would be - * in some regards preferable to have external logic for "doorbell" hardware - * interrupts. - */ - -static int cpu_ipi_irq = MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_IRQ; - -static irqreturn_t ipi_interrupt(int irq, void *dev_idm) -{ - int my_vpe = cpu_data[smp_processor_id()].vpe_id; - int my_tc = cpu_data[smp_processor_id()].tc_id; - int cpu; - struct smtc_ipi *pipi; - unsigned long tcstatus; - int sent; - unsigned long flags; - unsigned int mtflags; - unsigned int vpflags; - - /* - * So long as cross-VPE interrupts are done via - * MFTR/MTTR read-modify-writes of Cause, we need - * to stop other VPEs whenever the local VPE does - * anything similar. - */ - local_irq_save(flags); - vpflags = dvpe(); - clear_c0_cause(0x100 << MIPS_CPU_IPI_IRQ); - set_c0_status(0x100 << MIPS_CPU_IPI_IRQ); - irq_enable_hazard(); - evpe(vpflags); - local_irq_restore(flags); - - /* - * Cross-VPE Interrupt handler: Try to directly deliver IPIs - * queued for TCs on this VPE other than the current one. - * Return-from-interrupt should cause us to drain the queue - * for the current TC, so we ought not to have to do it explicitly here. - */ - - for_each_online_cpu(cpu) { - if (cpu_data[cpu].vpe_id != my_vpe) - continue; - - pipi = smtc_ipi_dq(&IPIQ[cpu]); - if (pipi != NULL) { - if (cpu_data[cpu].tc_id != my_tc) { - sent = 0; - LOCK_MT_PRA(); - settc(cpu_data[cpu].tc_id); - write_tc_c0_tchalt(TCHALT_H); - mips_ihb(); - tcstatus = read_tc_c0_tcstatus(); - if ((tcstatus & TCSTATUS_IXMT) == 0) { - post_direct_ipi(cpu, pipi); - sent = 1; - } - write_tc_c0_tchalt(0); - UNLOCK_MT_PRA(); - if (!sent) { - smtc_ipi_req(&IPIQ[cpu], pipi); - } - } else { - /* - * ipi_decode() should be called - * with interrupts off - */ - local_irq_save(flags); - if (pipi->type == LINUX_SMP_IPI && - (int)pipi->arg == SMP_RESCHEDULE_YOURSELF) - IPIQ[cpu].resched_flag = 0; - ipi_decode(pipi); - local_irq_restore(flags); - } - } - } - - return IRQ_HANDLED; -} - -static void ipi_irq_dispatch(void) -{ - do_IRQ(cpu_ipi_irq); -} - -static struct irqaction irq_ipi = { - .handler = ipi_interrupt, - .flags = IRQF_PERCPU, - .name = "SMTC_IPI" -}; - -static void setup_cross_vpe_interrupts(unsigned int nvpe) -{ - if (nvpe < 1) - return; - - if (!cpu_has_vint) - panic("SMTC Kernel requires Vectored Interrupt support"); - - set_vi_handler(MIPS_CPU_IPI_IRQ, ipi_irq_dispatch); - - setup_irq_smtc(cpu_ipi_irq, &irq_ipi, (0x100 << MIPS_CPU_IPI_IRQ)); - - irq_set_handler(cpu_ipi_irq, handle_percpu_irq); -} - -/* - * SMTC-specific hacks invoked from elsewhere in the kernel. - */ - - /* - * smtc_ipi_replay is called from raw_local_irq_restore - */ - -void smtc_ipi_replay(void) -{ - unsigned int cpu = smp_processor_id(); - - /* - * To the extent that we've ever turned interrupts off, - * we may have accumulated deferred IPIs. This is subtle. - * we should be OK: If we pick up something and dispatch - * it here, that's great. If we see nothing, but concurrent - * with this operation, another TC sends us an IPI, IXMT - * is clear, and we'll handle it as a real pseudo-interrupt - * and not a pseudo-pseudo interrupt. The important thing - * is to do the last check for queued message *after* the - * re-enabling of interrupts. - */ - while (IPIQ[cpu].head != NULL) { - struct smtc_ipi_q *q = &IPIQ[cpu]; - struct smtc_ipi *pipi; - unsigned long flags; - - /* - * It's just possible we'll come in with interrupts - * already enabled. - */ - local_irq_save(flags); - - spin_lock(&q->lock); - pipi = __smtc_ipi_dq(q); - spin_unlock(&q->lock); - /* - ** But use a raw restore here to avoid recursion. - */ - __arch_local_irq_restore(flags); - - if (pipi) { - self_ipi(pipi); - smtc_cpu_stats[cpu].selfipis++; - } - } -} - -EXPORT_SYMBOL(smtc_ipi_replay); - -void smtc_idle_loop_hook(void) -{ -#ifdef CONFIG_SMTC_IDLE_HOOK_DEBUG - int im; - int flags; - int mtflags; - int bit; - int vpe; - int tc; - int hook_ntcs; - /* - * printk within DMT-protected regions can deadlock, - * so buffer diagnostic messages for later output. - */ - char *pdb_msg; - char id_ho_db_msg[768]; /* worst-case use should be less than 700 */ - - if (atomic_read(&idle_hook_initialized) == 0) { /* fast test */ - if (atomic_add_return(1, &idle_hook_initialized) == 1) { - int mvpconf0; - /* Tedious stuff to just do once */ - mvpconf0 = read_c0_mvpconf0(); - hook_ntcs = ((mvpconf0 & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1; - if (hook_ntcs > NR_CPUS) - hook_ntcs = NR_CPUS; - for (tc = 0; tc < hook_ntcs; tc++) { - tcnoprog[tc] = 0; - clock_hang_reported[tc] = 0; - } - for (vpe = 0; vpe < 2; vpe++) - for (im = 0; im < 8; im++) - imstuckcount[vpe][im] = 0; - printk("Idle loop test hook initialized for %d TCs\n", hook_ntcs); - atomic_set(&idle_hook_initialized, 1000); - } else { - /* Someone else is initializing in parallel - let 'em finish */ - while (atomic_read(&idle_hook_initialized) < 1000) - ; - } - } - - /* Have we stupidly left IXMT set somewhere? */ - if (read_c0_tcstatus() & 0x400) { - write_c0_tcstatus(read_c0_tcstatus() & ~0x400); - ehb(); - printk("Dangling IXMT in cpu_idle()\n"); - } - - /* Have we stupidly left an IM bit turned off? */ -#define IM_LIMIT 2000 - local_irq_save(flags); - mtflags = dmt(); - pdb_msg = &id_ho_db_msg[0]; - im = read_c0_status(); - vpe = current_cpu_data.vpe_id; - for (bit = 0; bit < 8; bit++) { - /* - * In current prototype, I/O interrupts - * are masked for VPE > 0 - */ - if (vpemask[vpe][bit]) { - if (!(im & (0x100 << bit))) - imstuckcount[vpe][bit]++; - else - imstuckcount[vpe][bit] = 0; - if (imstuckcount[vpe][bit] > IM_LIMIT) { - set_c0_status(0x100 << bit); - ehb(); - imstuckcount[vpe][bit] = 0; - pdb_msg += sprintf(pdb_msg, - "Dangling IM %d fixed for VPE %d\n", bit, - vpe); - } - } - } - - emt(mtflags); - local_irq_restore(flags); - if (pdb_msg != &id_ho_db_msg[0]) - printk("CPU%d: %s", smp_processor_id(), id_ho_db_msg); -#endif /* CONFIG_SMTC_IDLE_HOOK_DEBUG */ - - smtc_ipi_replay(); -} - -void smtc_soft_dump(void) -{ - int i; - - printk("Counter Interrupts taken per CPU (TC)\n"); - for (i=0; i < NR_CPUS; i++) { - printk("%d: %ld\n", i, smtc_cpu_stats[i].timerints); - } - printk("Self-IPI invocations:\n"); - for (i=0; i < NR_CPUS; i++) { - printk("%d: %ld\n", i, smtc_cpu_stats[i].selfipis); - } - smtc_ipi_qdump(); - printk("%d Recoveries of \"stolen\" FPU\n", - atomic_read(&smtc_fpu_recoveries)); -} - - -/* - * TLB management routines special to SMTC - */ - -void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu) -{ - unsigned long flags, mtflags, tcstat, prevhalt, asid; - int tlb, i; - - /* - * It would be nice to be able to use a spinlock here, - * but this is invoked from within TLB flush routines - * that protect themselves with DVPE, so if a lock is - * held by another TC, it'll never be freed. - * - * DVPE/DMT must not be done with interrupts enabled, - * so even so most callers will already have disabled - * them, let's be really careful... - */ - - local_irq_save(flags); - if (smtc_status & SMTC_TLB_SHARED) { - mtflags = dvpe(); - tlb = 0; - } else { - mtflags = dmt(); - tlb = cpu_data[cpu].vpe_id; - } - asid = asid_cache(cpu); - - do { - if (!((asid += ASID_INC) & ASID_MASK) ) { - if (cpu_has_vtag_icache) - flush_icache_all(); - /* Traverse all online CPUs (hack requires contiguous range) */ - for_each_online_cpu(i) { - /* - * We don't need to worry about our own CPU, nor those of - * CPUs who don't share our TLB. - */ - if ((i != smp_processor_id()) && - ((smtc_status & SMTC_TLB_SHARED) || - (cpu_data[i].vpe_id == cpu_data[cpu].vpe_id))) { - settc(cpu_data[i].tc_id); - prevhalt = read_tc_c0_tchalt() & TCHALT_H; - if (!prevhalt) { - write_tc_c0_tchalt(TCHALT_H); - mips_ihb(); - } - tcstat = read_tc_c0_tcstatus(); - smtc_live_asid[tlb][(tcstat & ASID_MASK)] |= (asiduse)(0x1 << i); - if (!prevhalt) - write_tc_c0_tchalt(0); - } - } - if (!asid) /* fix version if needed */ - asid = ASID_FIRST_VERSION; - local_flush_tlb_all(); /* start new asid cycle */ - } - } while (smtc_live_asid[tlb][(asid & ASID_MASK)]); - - /* - * SMTC shares the TLB within VPEs and possibly across all VPEs. - */ - for_each_online_cpu(i) { - if ((smtc_status & SMTC_TLB_SHARED) || - (cpu_data[i].vpe_id == cpu_data[cpu].vpe_id)) - cpu_context(i, mm) = asid_cache(i) = asid; - } - - if (smtc_status & SMTC_TLB_SHARED) - evpe(mtflags); - else - emt(mtflags); - local_irq_restore(flags); -} - -/* - * Invoked from macros defined in mmu_context.h - * which must already have disabled interrupts - * and done a DVPE or DMT as appropriate. - */ - -void smtc_flush_tlb_asid(unsigned long asid) -{ - int entry; - unsigned long ehi; - - entry = read_c0_wired(); - - /* Traverse all non-wired entries */ - while (entry < current_cpu_data.tlbsize) { - write_c0_index(entry); - ehb(); - tlb_read(); - ehb(); - ehi = read_c0_entryhi(); - if ((ehi & ASID_MASK) == asid) { - /* - * Invalidate only entries with specified ASID, - * makiing sure all entries differ. - */ - write_c0_entryhi(CKSEG0 + (entry << (PAGE_SHIFT + 1))); - write_c0_entrylo0(0); - write_c0_entrylo1(0); - mtc0_tlbw_hazard(); - tlb_write_indexed(); - } - entry++; - } - write_c0_index(PARKED_INDEX); - tlbw_use_hazard(); -} - -/* - * Support for single-threading cache flush operations. - */ - -static int halt_state_save[NR_CPUS]; - -/* - * To really, really be sure that nothing is being done - * by other TCs, halt them all. This code assumes that - * a DVPE has already been done, so while their Halted - * state is theoretically architecturally unstable, in - * practice, it's not going to change while we're looking - * at it. - */ - -void smtc_cflush_lockdown(void) -{ - int cpu; - - for_each_online_cpu(cpu) { - if (cpu != smp_processor_id()) { - settc(cpu_data[cpu].tc_id); - halt_state_save[cpu] = read_tc_c0_tchalt(); - write_tc_c0_tchalt(TCHALT_H); - } - } - mips_ihb(); -} - -/* It would be cheating to change the cpu_online states during a flush! */ - -void smtc_cflush_release(void) -{ - int cpu; - - /* - * Start with a hazard barrier to ensure - * that all CACHE ops have played through. - */ - mips_ihb(); - - for_each_online_cpu(cpu) { - if (cpu != smp_processor_id()) { - settc(cpu_data[cpu].tc_id); - write_tc_c0_tchalt(halt_state_save[cpu]); - } - } - mips_ihb(); -} diff --git a/arch/mips/kernel/sync-r4k.c b/arch/mips/kernel/sync-r4k.c index c24ad5f4b324..2242bdd4370e 100644 --- a/arch/mips/kernel/sync-r4k.c +++ b/arch/mips/kernel/sync-r4k.c @@ -6,8 +6,6 @@ * not have done anything significant (but they may have had interrupts * enabled briefly - prom_smp_finish() should not be responsible for enabling * interrupts...) - * - * FIXME: broken for SMTC */ #include <linux/kernel.h> @@ -33,14 +31,6 @@ void synchronise_count_master(int cpu) unsigned long flags; unsigned int initcount; -#ifdef CONFIG_MIPS_MT_SMTC - /* - * SMTC needs to synchronise per VPE, not per CPU - * ignore for now - */ - return; -#endif - printk(KERN_INFO "Synchronize counters for CPU %u: ", cpu); local_irq_save(flags); @@ -110,14 +100,6 @@ void synchronise_count_slave(int cpu) int i; unsigned int initcount; -#ifdef CONFIG_MIPS_MT_SMTC - /* - * SMTC needs to synchronise per VPE, not per CPU - * ignore for now - */ - return; -#endif - /* * Not every cpu is online at the time this gets called, * so we first wait for the master to say everyone is ready diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index dcb8e5d3bb8a..8d0170969e22 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -26,7 +26,6 @@ #include <asm/cpu-features.h> #include <asm/cpu-type.h> #include <asm/div64.h> -#include <asm/smtc_ipi.h> #include <asm/time.h> /* diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 8119ac2fdfc9..51706d6dd5b0 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -15,6 +15,7 @@ #include <linux/bug.h> #include <linux/compiler.h> #include <linux/context_tracking.h> +#include <linux/cpu_pm.h> #include <linux/kexec.h> #include <linux/init.h> #include <linux/kernel.h> @@ -370,9 +371,6 @@ void __noreturn die(const char *str, struct pt_regs *regs) { static int die_counter; int sig = SIGSEGV; -#ifdef CONFIG_MIPS_MT_SMTC - unsigned long dvpret; -#endif /* CONFIG_MIPS_MT_SMTC */ oops_enter(); @@ -382,13 +380,7 @@ void __noreturn die(const char *str, struct pt_regs *regs) console_verbose(); raw_spin_lock_irq(&die_lock); -#ifdef CONFIG_MIPS_MT_SMTC - dvpret = dvpe(); -#endif /* CONFIG_MIPS_MT_SMTC */ bust_spinlocks(1); -#ifdef CONFIG_MIPS_MT_SMTC - mips_mt_regdump(dvpret); -#endif /* CONFIG_MIPS_MT_SMTC */ printk("%s[#%d]:\n", str, ++die_counter); show_registers(regs); @@ -712,10 +704,12 @@ int process_fpemu_return(int sig, void __user *fault_addr) si.si_addr = fault_addr; si.si_signo = sig; if (sig == SIGSEGV) { + down_read(¤t->mm->mmap_sem); if (find_vma(current->mm, (unsigned long)fault_addr)) si.si_code = SEGV_ACCERR; else si.si_code = SEGV_MAPERR; + up_read(¤t->mm->mmap_sem); } else { si.si_code = BUS_ADRERR; } @@ -1759,19 +1753,6 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs) extern char rollback_except_vec_vi; char *vec_start = using_rollback_handler() ? &rollback_except_vec_vi : &except_vec_vi; -#ifdef CONFIG_MIPS_MT_SMTC - /* - * We need to provide the SMTC vectored interrupt handler - * not only with the address of the handler, but with the - * Status.IM bit to be masked before going there. - */ - extern char except_vec_vi_mori; -#if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN) - const int mori_offset = &except_vec_vi_mori - vec_start + 2; -#else - const int mori_offset = &except_vec_vi_mori - vec_start; -#endif -#endif /* CONFIG_MIPS_MT_SMTC */ #if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN) const int lui_offset = &except_vec_vi_lui - vec_start + 2; const int ori_offset = &except_vec_vi_ori - vec_start + 2; @@ -1795,12 +1776,6 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs) #else handler_len); #endif -#ifdef CONFIG_MIPS_MT_SMTC - BUG_ON(n > 7); /* Vector index %d exceeds SMTC maximum. */ - - h = (u16 *)(b + mori_offset); - *h = (0x100 << n); -#endif /* CONFIG_MIPS_MT_SMTC */ h = (u16 *)(b + lui_offset); *h = (handler >> 16) & 0xffff; h = (u16 *)(b + ori_offset); @@ -1865,32 +1840,16 @@ static int __init ulri_disable(char *s) } __setup("noulri", ulri_disable); -void per_cpu_trap_init(bool is_boot_cpu) +/* configure STATUS register */ +static void configure_status(void) { - unsigned int cpu = smp_processor_id(); - unsigned int status_set = ST0_CU0; - unsigned int hwrena = cpu_hwrena_impl_bits; -#ifdef CONFIG_MIPS_MT_SMTC - int secondaryTC = 0; - int bootTC = (cpu == 0); - - /* - * Only do per_cpu_trap_init() for first TC of Each VPE. - * Note that this hack assumes that the SMTC init code - * assigns TCs consecutively and in ascending order. - */ - - if (((read_c0_tcbind() & TCBIND_CURTC) != 0) && - ((read_c0_tcbind() & TCBIND_CURVPE) == cpu_data[cpu - 1].vpe_id)) - secondaryTC = 1; -#endif /* CONFIG_MIPS_MT_SMTC */ - /* * Disable coprocessors and select 32-bit or 64-bit addressing * and the 16/32 or 32/32 FPR register model. Reset the BEV * flag that some firmware may have left set and the TS bit (for * IP27). Set XX for ISA IV code to work. */ + unsigned int status_set = ST0_CU0; #ifdef CONFIG_64BIT status_set |= ST0_FR|ST0_KX|ST0_SX|ST0_UX; #endif @@ -1901,6 +1860,12 @@ void per_cpu_trap_init(bool is_boot_cpu) change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX, status_set); +} + +/* configure HWRENA register */ +static void configure_hwrena(void) +{ + unsigned int hwrena = cpu_hwrena_impl_bits; if (cpu_has_mips_r2) hwrena |= 0x0000000f; @@ -1910,11 +1875,10 @@ void per_cpu_trap_init(bool is_boot_cpu) if (hwrena) write_c0_hwrena(hwrena); +} -#ifdef CONFIG_MIPS_MT_SMTC - if (!secondaryTC) { -#endif /* CONFIG_MIPS_MT_SMTC */ - +static void configure_exception_vector(void) +{ if (cpu_has_veic || cpu_has_vint) { unsigned long sr = set_c0_status(ST0_BEV); write_c0_ebase(ebase); @@ -1930,6 +1894,16 @@ void per_cpu_trap_init(bool is_boot_cpu) } else set_c0_cause(CAUSEF_IV); } +} + +void per_cpu_trap_init(bool is_boot_cpu) +{ + unsigned int cpu = smp_processor_id(); + + configure_status(); + configure_hwrena(); + + configure_exception_vector(); /* * Before R2 both interrupt numbers were fixed to 7, so on R2 only: @@ -1949,10 +1923,6 @@ void per_cpu_trap_init(bool is_boot_cpu) cp0_perfcount_irq = -1; } -#ifdef CONFIG_MIPS_MT_SMTC - } -#endif /* CONFIG_MIPS_MT_SMTC */ - if (!cpu_data[cpu].asid_cache) cpu_data[cpu].asid_cache = ASID_FIRST_VERSION; @@ -1961,23 +1931,10 @@ void per_cpu_trap_init(bool is_boot_cpu) BUG_ON(current->mm); enter_lazy_tlb(&init_mm, current); -#ifdef CONFIG_MIPS_MT_SMTC - if (bootTC) { -#endif /* CONFIG_MIPS_MT_SMTC */ /* Boot CPU's cache setup in setup_arch(). */ if (!is_boot_cpu) cpu_cache_init(); tlb_init(); -#ifdef CONFIG_MIPS_MT_SMTC - } else if (!secondaryTC) { - /* - * First TC in non-boot VPE must do subset of tlb_init() - * for MMU countrol registers. - */ - write_c0_pagemask(PM_DEFAULT_MASK); - write_c0_wired(0); - } -#endif /* CONFIG_MIPS_MT_SMTC */ TLBMISS_HANDLER_SETUP(); } @@ -2185,3 +2142,32 @@ void __init trap_init(void) cu2_notifier(default_cu2_call, 0x80000000); /* Run last */ } + +static int trap_pm_notifier(struct notifier_block *self, unsigned long cmd, + void *v) +{ + switch (cmd) { + case CPU_PM_ENTER_FAILED: + case CPU_PM_EXIT: + configure_status(); + configure_hwrena(); + configure_exception_vector(); + + /* Restore register with CPU number for TLB handlers */ + TLBMISS_HANDLER_RESTORE(); + + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block trap_pm_notifier_block = { + .notifier_call = trap_pm_notifier, +}; + +static int __init trap_pm_init(void) +{ + return cpu_pm_register_notifier(&trap_pm_notifier_block); +} +arch_initcall(trap_pm_init); diff --git a/arch/mips/kernel/vpe-mt.c b/arch/mips/kernel/vpe-mt.c index 949ae0e17018..2e003b11a098 100644 --- a/arch/mips/kernel/vpe-mt.c +++ b/arch/mips/kernel/vpe-mt.c @@ -127,9 +127,8 @@ int vpe_run(struct vpe *v) clear_c0_mvpcontrol(MVPCONTROL_VPC); /* - * SMTC/SMVP kernels manage VPE enable independently, - * but uniprocessor kernels need to turn it on, even - * if that wasn't the pre-dvpe() state. + * SMVP kernels manage VPE enable independently, but uniprocessor + * kernels need to turn it on, even if that wasn't the pre-dvpe() state. */ #ifdef CONFIG_SMP evpe(vpeflags); @@ -454,12 +453,11 @@ int __init vpe_module_init(void) settc(tc); - /* Any TC that is bound to VPE0 gets left as is - in - * case we are running SMTC on VPE0. A TC that is bound - * to any other VPE gets bound to VPE0, ideally I'd like - * to make it homeless but it doesn't appear to let me - * bind a TC to a non-existent VPE. Which is perfectly - * reasonable. + /* + * A TC that is bound to any other VPE gets bound to + * VPE0, ideally I'd like to make it homeless but it + * doesn't appear to let me bind a TC to a non-existent + * VPE. Which is perfectly reasonable. * * The (un)bound state is visible to an EJTAG probe so * may notify GDB... diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index 85685e1cdb89..030568a70ac4 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -61,7 +61,7 @@ /* we have a cascade of 8 irqs */ #define MIPS_CPU_IRQ_CASCADE 8 -#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC) +#ifdef CONFIG_MIPS_MT_SMP int gic_present; #endif @@ -440,7 +440,7 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent) arch_init_ipiirq(MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_CALL_IRQ, &irq_call); #endif -#if !defined(CONFIG_MIPS_MT_SMP) && !defined(CONFIG_MIPS_MT_SMTC) +#ifndef CONFIG_MIPS_MT_SMP set_c0_status(IE_IRQ0 | IE_IRQ1 | IE_IRQ2 | IE_IRQ3 | IE_IRQ4 | IE_IRQ5); #else diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c index 19686c5bc5ed..7447d322d14e 100644 --- a/arch/mips/lantiq/prom.c +++ b/arch/mips/lantiq/prom.c @@ -71,23 +71,12 @@ void __init plat_mem_setup(void) * Load the builtin devicetree. This causes the chosen node to be * parsed resulting in our memory appearing */ - __dt_setup_arch(&__dtb_start); + __dt_setup_arch(__dtb_start); } void __init device_tree_init(void) { - unsigned long base, size; - - if (!initial_boot_params) - return; - - base = virt_to_phys((void *)initial_boot_params); - size = be32_to_cpu(initial_boot_params->totalsize); - - /* Before we do anything, lets reserve the dt blob */ - reserve_bootmem(base, size, BOOTMEM_DEFAULT); - - unflatten_device_tree(); + unflatten_and_copy_device_tree(); } void __init prom_init(void) diff --git a/arch/mips/lantiq/prom.h b/arch/mips/lantiq/prom.h index 8e07b5f28ef1..bfd2d58c1d69 100644 --- a/arch/mips/lantiq/prom.h +++ b/arch/mips/lantiq/prom.h @@ -26,6 +26,4 @@ struct ltq_soc_info { extern void ltq_soc_detect(struct ltq_soc_info *i); extern void ltq_soc_init(void); -extern struct boot_param_header __dtb_start; - #endif diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c index 705cfb7c1a74..21d27c6819a2 100644 --- a/arch/mips/lib/delay.c +++ b/arch/mips/lib/delay.c @@ -11,7 +11,9 @@ #include <linux/module.h> #include <linux/param.h> #include <linux/smp.h> +#include <linux/stringify.h> +#include <asm/asm.h> #include <asm/compiler.h> #include <asm/war.h> @@ -27,11 +29,7 @@ void __delay(unsigned long loops) " .set noreorder \n" " .align 3 \n" "1: bnez %0, 1b \n" -#if BITS_PER_LONG == 32 - " subu %0, %1 \n" -#else - " dsubu %0, %1 \n" -#endif + " " __stringify(LONG_SUBU) " %0, %1 \n" " .set reorder \n" : "=r" (loops) : GCC_DADDI_IMM_ASM() (1), "0" (loops)); diff --git a/arch/mips/lib/mips-atomic.c b/arch/mips/lib/mips-atomic.c index 6807f7172eaf..57bcdaf1f1c8 100644 --- a/arch/mips/lib/mips-atomic.c +++ b/arch/mips/lib/mips-atomic.c @@ -15,7 +15,7 @@ #include <linux/export.h> #include <linux/stringify.h> -#if !defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_MIPS_MT_SMTC) +#ifndef CONFIG_CPU_MIPSR2 /* * For cli() we have to insert nops to make sure that the new value @@ -42,12 +42,7 @@ notrace void arch_local_irq_disable(void) __asm__ __volatile__( " .set push \n" " .set noat \n" -#ifdef CONFIG_MIPS_MT_SMTC - " mfc0 $1, $2, 1 \n" - " ori $1, 0x400 \n" - " .set noreorder \n" - " mtc0 $1, $2, 1 \n" -#elif defined(CONFIG_CPU_MIPSR2) +#if defined(CONFIG_CPU_MIPSR2) /* see irqflags.h for inline function */ #else " mfc0 $1,$12 \n" @@ -77,13 +72,7 @@ notrace unsigned long arch_local_irq_save(void) " .set push \n" " .set reorder \n" " .set noat \n" -#ifdef CONFIG_MIPS_MT_SMTC - " mfc0 %[flags], $2, 1 \n" - " ori $1, %[flags], 0x400 \n" - " .set noreorder \n" - " mtc0 $1, $2, 1 \n" - " andi %[flags], %[flags], 0x400 \n" -#elif defined(CONFIG_CPU_MIPSR2) +#if defined(CONFIG_CPU_MIPSR2) /* see irqflags.h for inline function */ #else " mfc0 %[flags], $12 \n" @@ -108,29 +97,13 @@ notrace void arch_local_irq_restore(unsigned long flags) { unsigned long __tmp1; -#ifdef CONFIG_MIPS_MT_SMTC - /* - * SMTC kernel needs to do a software replay of queued - * IPIs, at the cost of branch and call overhead on each - * local_irq_restore() - */ - if (unlikely(!(flags & 0x0400))) - smtc_ipi_replay(); -#endif preempt_disable(); __asm__ __volatile__( " .set push \n" " .set noreorder \n" " .set noat \n" -#ifdef CONFIG_MIPS_MT_SMTC - " mfc0 $1, $2, 1 \n" - " andi %[flags], 0x400 \n" - " ori $1, 0x400 \n" - " xori $1, 0x400 \n" - " or %[flags], $1 \n" - " mtc0 %[flags], $2, 1 \n" -#elif defined(CONFIG_CPU_MIPSR2) && defined(CONFIG_IRQ_CPU) +#if defined(CONFIG_CPU_MIPSR2) && defined(CONFIG_IRQ_CPU) /* see irqflags.h for inline function */ #elif defined(CONFIG_CPU_MIPSR2) /* see irqflags.h for inline function */ @@ -163,14 +136,7 @@ notrace void __arch_local_irq_restore(unsigned long flags) " .set push \n" " .set noreorder \n" " .set noat \n" -#ifdef CONFIG_MIPS_MT_SMTC - " mfc0 $1, $2, 1 \n" - " andi %[flags], 0x400 \n" - " ori $1, 0x400 \n" - " xori $1, 0x400 \n" - " or %[flags], $1 \n" - " mtc0 %[flags], $2, 1 \n" -#elif defined(CONFIG_CPU_MIPSR2) && defined(CONFIG_IRQ_CPU) +#if defined(CONFIG_CPU_MIPSR2) && defined(CONFIG_IRQ_CPU) /* see irqflags.h for inline function */ #elif defined(CONFIG_CPU_MIPSR2) /* see irqflags.h for inline function */ @@ -192,4 +158,4 @@ notrace void __arch_local_irq_restore(unsigned long flags) } EXPORT_SYMBOL(__arch_local_irq_restore); -#endif /* !defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_MIPS_MT_SMTC) */ +#endif /* !CONFIG_CPU_MIPSR2 */ diff --git a/arch/mips/loongson/Kconfig b/arch/mips/loongson/Kconfig index 603d79a95f47..e6a86ccc4421 100644 --- a/arch/mips/loongson/Kconfig +++ b/arch/mips/loongson/Kconfig @@ -95,10 +95,11 @@ config CS5536 config CS5536_MFGPT bool "CS5536 MFGPT Timer" - depends on CS5536 + depends on CS5536 && !HIGH_RES_TIMERS select MIPS_EXTERNAL_TIMER help - This option enables the mfgpt0 timer of AMD CS5536. + This option enables the mfgpt0 timer of AMD CS5536. With this timer + switched on you can not use high resolution timers. If you want to enable the Loongson2 CPUFreq Driver, Please enable this option at first, otherwise, You will get wrong system time. diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c index c665fe16d4c9..1e8894020ea5 100644 --- a/arch/mips/loongson/loongson-3/smp.c +++ b/arch/mips/loongson/loongson-3/smp.c @@ -279,13 +279,6 @@ static void loongson3_boot_secondary(int cpu, struct task_struct *idle) loongson3_ipi_write64(startargs[0], (void *)(ipi_mailbox_buf[cpu]+0x0)); } -/* - * Final cleanup after all secondaries booted - */ -static void __init loongson3_cpus_done(void) -{ -} - #ifdef CONFIG_HOTPLUG_CPU static int loongson3_cpu_disable(void) @@ -432,7 +425,6 @@ struct plat_smp_ops loongson3_smp_ops = { .send_ipi_mask = loongson3_send_ipi_mask, .init_secondary = loongson3_init_secondary, .smp_finish = loongson3_smp_finish, - .cpus_done = loongson3_cpus_done, .boot_secondary = loongson3_boot_secondary, .smp_setup = loongson3_smp_setup, .prepare_cpus = loongson3_prepare_cpus, diff --git a/arch/mips/loongson1/Kconfig b/arch/mips/loongson1/Kconfig index fbf75f635798..e23c25d09963 100644 --- a/arch/mips/loongson1/Kconfig +++ b/arch/mips/loongson1/Kconfig @@ -14,6 +14,7 @@ config LOONGSON1_LS1B select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_HIGHMEM + select SYS_SUPPORTS_MIPS16 select SYS_HAS_EARLY_PRINTK select COMMON_CLK diff --git a/arch/mips/math-emu/Makefile b/arch/mips/math-emu/Makefile index 121a848a3594..619cfc1a2442 100644 --- a/arch/mips/math-emu/Makefile +++ b/arch/mips/math-emu/Makefile @@ -2,10 +2,12 @@ # Makefile for the Linux/MIPS kernel FPU emulation. # -obj-y := cp1emu.o ieee754m.o ieee754d.o ieee754dp.o ieee754sp.o ieee754.o \ - ieee754xcpt.o dp_frexp.o dp_modf.o dp_div.o dp_mul.o dp_sub.o \ - dp_add.o dp_fsp.o dp_cmp.o dp_logb.o dp_scalb.o dp_simple.o \ - dp_tint.o dp_fint.o dp_tlong.o dp_flong.o sp_frexp.o sp_modf.o \ - sp_div.o sp_mul.o sp_sub.o sp_add.o sp_fdp.o sp_cmp.o sp_logb.o \ - sp_scalb.o sp_simple.o sp_tint.o sp_fint.o sp_tlong.o sp_flong.o \ - dp_sqrt.o sp_sqrt.o kernel_linkage.o dsemul.o +obj-y += cp1emu.o ieee754dp.o ieee754sp.o ieee754.o dp_div.o dp_mul.o \ + dp_sub.o dp_add.o dp_fsp.o dp_cmp.o dp_simple.o dp_tint.o \ + dp_fint.o dp_tlong.o dp_flong.o sp_div.o sp_mul.o sp_sub.o \ + sp_add.o sp_fdp.o sp_cmp.o sp_simple.o sp_tint.o sp_fint.o \ + sp_tlong.o sp_flong.o dsemul.o + +lib-y += ieee754d.o dp_sqrt.o sp_sqrt.o + +obj-$(CONFIG_DEBUG_FS) += me-debugfs.o diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 7b3c9acae689..736c17a226e9 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -1,5 +1,5 @@ /* - * cp1emu.c: a MIPS coprocessor 1 (fpu) instruction emulator + * cp1emu.c: a MIPS coprocessor 1 (FPU) instruction emulator * * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. @@ -18,61 +18,46 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. * * A complete emulator for MIPS coprocessor 1 instructions. This is * required for #float(switch) or #float(trap), where it catches all * COP1 instructions via the "CoProcessor Unusable" exception. * * More surprisingly it is also required for #float(ieee), to help out - * the hardware fpu at the boundaries of the IEEE-754 representation + * the hardware FPU at the boundaries of the IEEE-754 representation * (denormalised values, infinities, underflow, etc). It is made * quite nasty because emulation of some non-COP1 instructions is * required, e.g. in branch delay slots. * - * Note if you know that you won't have an fpu, then you'll get much + * Note if you know that you won't have an FPU, then you'll get much * better performance by compiling with -msoft-float! */ #include <linux/sched.h> -#include <linux/module.h> #include <linux/debugfs.h> +#include <linux/kconfig.h> +#include <linux/percpu-defs.h> #include <linux/perf_event.h> +#include <asm/branch.h> #include <asm/inst.h> -#include <asm/bootinfo.h> -#include <asm/processor.h> #include <asm/ptrace.h> #include <asm/signal.h> -#include <asm/mipsregs.h> +#include <asm/uaccess.h> + +#include <asm/processor.h> #include <asm/fpu_emulator.h> #include <asm/fpu.h> -#include <asm/uaccess.h> -#include <asm/branch.h> #include "ieee754.h" -/* Strap kernel emulator for full MIPS IV emulation */ - -#ifdef __mips -#undef __mips -#endif -#define __mips 4 - /* Function which emulates a floating point instruction. */ static int fpu_emu(struct pt_regs *, struct mips_fpu_struct *, mips_instruction); -#if __mips >= 4 && __mips != 32 static int fpux_emu(struct pt_regs *, struct mips_fpu_struct *, mips_instruction, void *__user *); -#endif - -/* Further private data for which no space exists in mips_fpu_struct */ - -#ifdef CONFIG_DEBUG_FS -DEFINE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats); -#endif /* Control registers */ @@ -82,27 +67,6 @@ DEFINE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats); /* Determine rounding mode from the RM bits of the FCSR */ #define modeindex(v) ((v) & FPU_CSR_RM) -/* microMIPS bitfields */ -#define MM_POOL32A_MINOR_MASK 0x3f -#define MM_POOL32A_MINOR_SHIFT 0x6 -#define MM_MIPS32_COND_FC 0x30 - -/* Convert Mips rounding mode (0..3) to IEEE library modes. */ -static const unsigned char ieee_rm[4] = { - [FPU_CSR_RN] = IEEE754_RN, - [FPU_CSR_RZ] = IEEE754_RZ, - [FPU_CSR_RU] = IEEE754_RU, - [FPU_CSR_RD] = IEEE754_RD, -}; -/* Convert IEEE library modes to Mips rounding mode (0..3). */ -static const unsigned char mips_rm[4] = { - [IEEE754_RN] = FPU_CSR_RN, - [IEEE754_RZ] = FPU_CSR_RZ, - [IEEE754_RD] = FPU_CSR_RD, - [IEEE754_RU] = FPU_CSR_RU, -}; - -#if __mips >= 4 /* convert condition code register number to csr bit */ static const unsigned int fpucondbit[8] = { FPU_CSR_COND0, @@ -114,10 +78,6 @@ static const unsigned int fpucondbit[8] = { FPU_CSR_COND6, FPU_CSR_COND7 }; -#endif - -/* (microMIPS) Convert 16-bit register encoding to 32-bit register encoding. */ -static const unsigned int reg16to32map[8] = {16, 17, 2, 3, 4, 5, 6, 7}; /* (microMIPS) Convert certain microMIPS instructions to MIPS32 format. */ static const int sd_format[] = {16, 17, 0, 0, 0, 0, 0, 0}; @@ -466,199 +426,6 @@ static int microMIPS32_to_MIPS32(union mips_instruction *insn_ptr) return 0; } -int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, - unsigned long *contpc) -{ - union mips_instruction insn = (union mips_instruction)dec_insn.insn; - int bc_false = 0; - unsigned int fcr31; - unsigned int bit; - - if (!cpu_has_mmips) - return 0; - - switch (insn.mm_i_format.opcode) { - case mm_pool32a_op: - if ((insn.mm_i_format.simmediate & MM_POOL32A_MINOR_MASK) == - mm_pool32axf_op) { - switch (insn.mm_i_format.simmediate >> - MM_POOL32A_MINOR_SHIFT) { - case mm_jalr_op: - case mm_jalrhb_op: - case mm_jalrs_op: - case mm_jalrshb_op: - if (insn.mm_i_format.rt != 0) /* Not mm_jr */ - regs->regs[insn.mm_i_format.rt] = - regs->cp0_epc + - dec_insn.pc_inc + - dec_insn.next_pc_inc; - *contpc = regs->regs[insn.mm_i_format.rs]; - return 1; - } - } - break; - case mm_pool32i_op: - switch (insn.mm_i_format.rt) { - case mm_bltzals_op: - case mm_bltzal_op: - regs->regs[31] = regs->cp0_epc + - dec_insn.pc_inc + - dec_insn.next_pc_inc; - /* Fall through */ - case mm_bltz_op: - if ((long)regs->regs[insn.mm_i_format.rs] < 0) - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - (insn.mm_i_format.simmediate << 1); - else - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - dec_insn.next_pc_inc; - return 1; - case mm_bgezals_op: - case mm_bgezal_op: - regs->regs[31] = regs->cp0_epc + - dec_insn.pc_inc + - dec_insn.next_pc_inc; - /* Fall through */ - case mm_bgez_op: - if ((long)regs->regs[insn.mm_i_format.rs] >= 0) - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - (insn.mm_i_format.simmediate << 1); - else - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - dec_insn.next_pc_inc; - return 1; - case mm_blez_op: - if ((long)regs->regs[insn.mm_i_format.rs] <= 0) - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - (insn.mm_i_format.simmediate << 1); - else - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - dec_insn.next_pc_inc; - return 1; - case mm_bgtz_op: - if ((long)regs->regs[insn.mm_i_format.rs] <= 0) - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - (insn.mm_i_format.simmediate << 1); - else - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - dec_insn.next_pc_inc; - return 1; - case mm_bc2f_op: - case mm_bc1f_op: - bc_false = 1; - /* Fall through */ - case mm_bc2t_op: - case mm_bc1t_op: - preempt_disable(); - if (is_fpu_owner()) - asm volatile("cfc1\t%0,$31" : "=r" (fcr31)); - else - fcr31 = current->thread.fpu.fcr31; - preempt_enable(); - - if (bc_false) - fcr31 = ~fcr31; - - bit = (insn.mm_i_format.rs >> 2); - bit += (bit != 0); - bit += 23; - if (fcr31 & (1 << bit)) - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - (insn.mm_i_format.simmediate << 1); - else - *contpc = regs->cp0_epc + - dec_insn.pc_inc + dec_insn.next_pc_inc; - return 1; - } - break; - case mm_pool16c_op: - switch (insn.mm_i_format.rt) { - case mm_jalr16_op: - case mm_jalrs16_op: - regs->regs[31] = regs->cp0_epc + - dec_insn.pc_inc + dec_insn.next_pc_inc; - /* Fall through */ - case mm_jr16_op: - *contpc = regs->regs[insn.mm_i_format.rs]; - return 1; - } - break; - case mm_beqz16_op: - if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] == 0) - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - (insn.mm_b1_format.simmediate << 1); - else - *contpc = regs->cp0_epc + - dec_insn.pc_inc + dec_insn.next_pc_inc; - return 1; - case mm_bnez16_op: - if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] != 0) - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - (insn.mm_b1_format.simmediate << 1); - else - *contpc = regs->cp0_epc + - dec_insn.pc_inc + dec_insn.next_pc_inc; - return 1; - case mm_b16_op: - *contpc = regs->cp0_epc + dec_insn.pc_inc + - (insn.mm_b0_format.simmediate << 1); - return 1; - case mm_beq32_op: - if (regs->regs[insn.mm_i_format.rs] == - regs->regs[insn.mm_i_format.rt]) - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - (insn.mm_i_format.simmediate << 1); - else - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - dec_insn.next_pc_inc; - return 1; - case mm_bne32_op: - if (regs->regs[insn.mm_i_format.rs] != - regs->regs[insn.mm_i_format.rt]) - *contpc = regs->cp0_epc + - dec_insn.pc_inc + - (insn.mm_i_format.simmediate << 1); - else - *contpc = regs->cp0_epc + - dec_insn.pc_inc + dec_insn.next_pc_inc; - return 1; - case mm_jalx32_op: - regs->regs[31] = regs->cp0_epc + - dec_insn.pc_inc + dec_insn.next_pc_inc; - *contpc = regs->cp0_epc + dec_insn.pc_inc; - *contpc >>= 28; - *contpc <<= 28; - *contpc |= (insn.j_format.target << 2); - return 1; - case mm_jals32_op: - case mm_jal32_op: - regs->regs[31] = regs->cp0_epc + - dec_insn.pc_inc + dec_insn.next_pc_inc; - /* Fall through */ - case mm_j32_op: - *contpc = regs->cp0_epc + dec_insn.pc_inc; - *contpc >>= 27; - *contpc <<= 27; - *contpc |= (insn.j_format.target << 1); - set_isa16_mode(*contpc); - return 1; - } - return 0; -} - /* * Redundant with logic already in kernel/branch.c, * embedded in compute_return_epc. At some point, @@ -817,7 +584,11 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, if (insn.i_format.rs == bc_op) { preempt_disable(); if (is_fpu_owner()) - asm volatile("cfc1\t%0,$31" : "=r" (fcr31)); + asm volatile( + ".set push\n" + "\t.set mips1\n" + "\tcfc1\t%0,$31\n" + "\t.set pop" : "=r" (fcr31)); else fcr31 = current->thread.fpu.fcr31; preempt_enable(); @@ -867,23 +638,25 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, */ static inline int cop1_64bit(struct pt_regs *xcp) { -#if defined(CONFIG_64BIT) && !defined(CONFIG_MIPS32_O32) - return 1; -#elif defined(CONFIG_32BIT) && !defined(CONFIG_MIPS_O32_FP64_SUPPORT) - return 0; -#else + if (config_enabled(CONFIG_64BIT) && !config_enabled(CONFIG_MIPS32_O32)) + return 1; + else if (config_enabled(CONFIG_32BIT) && + !config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) + return 0; + return !test_thread_flag(TIF_32BIT_FPREGS); -#endif } -#define SIFROMREG(si, x) do { \ +#define SIFROMREG(si, x) \ +do { \ if (cop1_64bit(xcp)) \ (si) = get_fpr32(&ctx->fpr[x], 0); \ else \ (si) = get_fpr32(&ctx->fpr[(x) & ~1], (x) & 1); \ } while (0) -#define SITOREG(si, x) do { \ +#define SITOREG(si, x) \ +do { \ if (cop1_64bit(xcp)) { \ unsigned i; \ set_fpr32(&ctx->fpr[x], 0, si); \ @@ -896,17 +669,19 @@ static inline int cop1_64bit(struct pt_regs *xcp) #define SIFROMHREG(si, x) ((si) = get_fpr32(&ctx->fpr[x], 1)) -#define SITOHREG(si, x) do { \ +#define SITOHREG(si, x) \ +do { \ unsigned i; \ set_fpr32(&ctx->fpr[x], 1, si); \ for (i = 2; i < ARRAY_SIZE(ctx->fpr[x].val32); i++) \ set_fpr32(&ctx->fpr[x], i, 0); \ } while (0) -#define DIFROMREG(di, x) \ +#define DIFROMREG(di, x) \ ((di) = get_fpr64(&ctx->fpr[(x) & ~(cop1_64bit(xcp) == 0)], 0)) -#define DITOREG(di, x) do { \ +#define DITOREG(di, x) \ +do { \ unsigned fpr, i; \ fpr = (x) & ~(cop1_64bit(xcp) == 0); \ set_fpr64(&ctx->fpr[fpr], 0, di); \ @@ -927,23 +702,36 @@ static inline int cop1_64bit(struct pt_regs *xcp) static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, struct mm_decoded_insn dec_insn, void *__user *fault_addr) { - mips_instruction ir; unsigned long contpc = xcp->cp0_epc + dec_insn.pc_inc; - unsigned int cond; - int pc_inc; + unsigned int cond, cbit; + mips_instruction ir; + int likely, pc_inc; + u32 __user *wva; + u64 __user *dva; + u32 value; + u32 wval; + u64 dval; + int sig; + + /* + * These are giving gcc a gentle hint about what to expect in + * dec_inst in order to do better optimization. + */ + if (!cpu_has_mmips && dec_insn.micro_mips_mode) + unreachable(); /* XXX NEC Vr54xx bug workaround */ - if (xcp->cp0_cause & CAUSEF_BD) { + if (delay_slot(xcp)) { if (dec_insn.micro_mips_mode) { if (!mm_isBranchInstr(xcp, dec_insn, &contpc)) - xcp->cp0_cause &= ~CAUSEF_BD; + clear_delay_slot(xcp); } else { if (!isBranchInstr(xcp, dec_insn, &contpc)) - xcp->cp0_cause &= ~CAUSEF_BD; + clear_delay_slot(xcp); } } - if (xcp->cp0_cause & CAUSEF_BD) { + if (delay_slot(xcp)) { /* * The instruction to be emulated is in a branch delay slot * which means that we have to emulate the branch instruction @@ -985,96 +773,85 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, return SIGILL; } - emul: +emul: perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, xcp, 0); MIPS_FPU_EMU_INC_STATS(emulated); switch (MIPSInst_OPCODE(ir)) { - case ldc1_op:{ - u64 __user *va = (u64 __user *) (xcp->regs[MIPSInst_RS(ir)] + - MIPSInst_SIMM(ir)); - u64 val; - + case ldc1_op: + dva = (u64 __user *) (xcp->regs[MIPSInst_RS(ir)] + + MIPSInst_SIMM(ir)); MIPS_FPU_EMU_INC_STATS(loads); - if (!access_ok(VERIFY_READ, va, sizeof(u64))) { + if (!access_ok(VERIFY_READ, dva, sizeof(u64))) { MIPS_FPU_EMU_INC_STATS(errors); - *fault_addr = va; + *fault_addr = dva; return SIGBUS; } - if (__get_user(val, va)) { + if (__get_user(dval, dva)) { MIPS_FPU_EMU_INC_STATS(errors); - *fault_addr = va; + *fault_addr = dva; return SIGSEGV; } - DITOREG(val, MIPSInst_RT(ir)); + DITOREG(dval, MIPSInst_RT(ir)); break; - } - - case sdc1_op:{ - u64 __user *va = (u64 __user *) (xcp->regs[MIPSInst_RS(ir)] + - MIPSInst_SIMM(ir)); - u64 val; + case sdc1_op: + dva = (u64 __user *) (xcp->regs[MIPSInst_RS(ir)] + + MIPSInst_SIMM(ir)); MIPS_FPU_EMU_INC_STATS(stores); - DIFROMREG(val, MIPSInst_RT(ir)); - if (!access_ok(VERIFY_WRITE, va, sizeof(u64))) { + DIFROMREG(dval, MIPSInst_RT(ir)); + if (!access_ok(VERIFY_WRITE, dva, sizeof(u64))) { MIPS_FPU_EMU_INC_STATS(errors); - *fault_addr = va; + *fault_addr = dva; return SIGBUS; } - if (__put_user(val, va)) { + if (__put_user(dval, dva)) { MIPS_FPU_EMU_INC_STATS(errors); - *fault_addr = va; + *fault_addr = dva; return SIGSEGV; } break; - } - - case lwc1_op:{ - u32 __user *va = (u32 __user *) (xcp->regs[MIPSInst_RS(ir)] + - MIPSInst_SIMM(ir)); - u32 val; + case lwc1_op: + wva = (u32 __user *) (xcp->regs[MIPSInst_RS(ir)] + + MIPSInst_SIMM(ir)); MIPS_FPU_EMU_INC_STATS(loads); - if (!access_ok(VERIFY_READ, va, sizeof(u32))) { + if (!access_ok(VERIFY_READ, wva, sizeof(u32))) { MIPS_FPU_EMU_INC_STATS(errors); - *fault_addr = va; + *fault_addr = wva; return SIGBUS; } - if (__get_user(val, va)) { + if (__get_user(wval, wva)) { MIPS_FPU_EMU_INC_STATS(errors); - *fault_addr = va; + *fault_addr = wva; return SIGSEGV; } - SITOREG(val, MIPSInst_RT(ir)); + SITOREG(wval, MIPSInst_RT(ir)); break; - } - - case swc1_op:{ - u32 __user *va = (u32 __user *) (xcp->regs[MIPSInst_RS(ir)] + - MIPSInst_SIMM(ir)); - u32 val; + case swc1_op: + wva = (u32 __user *) (xcp->regs[MIPSInst_RS(ir)] + + MIPSInst_SIMM(ir)); MIPS_FPU_EMU_INC_STATS(stores); - SIFROMREG(val, MIPSInst_RT(ir)); - if (!access_ok(VERIFY_WRITE, va, sizeof(u32))) { + SIFROMREG(wval, MIPSInst_RT(ir)); + if (!access_ok(VERIFY_WRITE, wva, sizeof(u32))) { MIPS_FPU_EMU_INC_STATS(errors); - *fault_addr = va; + *fault_addr = wva; return SIGBUS; } - if (__put_user(val, va)) { + if (__put_user(wval, wva)) { MIPS_FPU_EMU_INC_STATS(errors); - *fault_addr = va; + *fault_addr = wva; return SIGSEGV; } break; - } case cop1_op: switch (MIPSInst_RS(ir)) { - -#if defined(__mips64) case dmfc_op: + if (!cpu_has_mips_3_4_5 && !cpu_has_mips64) + return SIGILL; + /* copregister fs -> gpr[rt] */ if (MIPSInst_RT(ir) != 0) { DIFROMREG(xcp->regs[MIPSInst_RT(ir)], @@ -1083,10 +860,12 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, break; case dmtc_op: + if (!cpu_has_mips_3_4_5 && !cpu_has_mips64) + return SIGILL; + /* copregister fs <- rt */ DITOREG(xcp->regs[MIPSInst_RT(ir)], MIPSInst_RD(ir)); break; -#endif case mfhc_op: if (!cpu_has_mips_r2) @@ -1120,19 +899,14 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, SITOREG(xcp->regs[MIPSInst_RT(ir)], MIPSInst_RD(ir)); break; - case cfc_op:{ + case cfc_op: /* cop control register rd -> gpr[rt] */ - u32 value; - if (MIPSInst_RD(ir) == FPCREG_CSR) { value = ctx->fcr31; - value = (value & ~FPU_CSR_RM) | - mips_rm[modeindex(value)]; -#ifdef CSRTRACE - printk("%p gpr[%d]<-csr=%08x\n", - (void *) (xcp->cp0_epc), - MIPSInst_RT(ir), value); -#endif + value = (value & ~FPU_CSR_RM) | modeindex(value); + pr_debug("%p gpr[%d]<-csr=%08x\n", + (void *) (xcp->cp0_epc), + MIPSInst_RT(ir), value); } else if (MIPSInst_RD(ir) == FPCREG_RID) value = 0; @@ -1141,12 +915,9 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (MIPSInst_RT(ir)) xcp->regs[MIPSInst_RT(ir)] = value; break; - } - case ctc_op:{ + case ctc_op: /* copregister rd <- rt */ - u32 value; - if (MIPSInst_RT(ir) == 0) value = 0; else @@ -1155,37 +926,33 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, /* we only have one writable control reg */ if (MIPSInst_RD(ir) == FPCREG_CSR) { -#ifdef CSRTRACE - printk("%p gpr[%d]->csr=%08x\n", - (void *) (xcp->cp0_epc), - MIPSInst_RT(ir), value); -#endif + pr_debug("%p gpr[%d]->csr=%08x\n", + (void *) (xcp->cp0_epc), + MIPSInst_RT(ir), value); /* * Don't write reserved bits, * and convert to ieee library modes */ - ctx->fcr31 = (value & - ~(FPU_CSR_RSVD | FPU_CSR_RM)) | - ieee_rm[modeindex(value)]; + ctx->fcr31 = (value & ~(FPU_CSR_RSVD | FPU_CSR_RM)) | + modeindex(value); } if ((ctx->fcr31 >> 5) & ctx->fcr31 & FPU_CSR_ALL_E) { return SIGFPE; } break; - } - case bc_op:{ - int likely = 0; - - if (xcp->cp0_cause & CAUSEF_BD) + case bc_op: + if (delay_slot(xcp)) return SIGILL; -#if __mips >= 4 - cond = ctx->fcr31 & fpucondbit[MIPSInst_RT(ir) >> 2]; -#else - cond = ctx->fcr31 & FPU_CSR_COND; -#endif + if (cpu_has_mips_4_5_r) + cbit = fpucondbit[MIPSInst_RT(ir) >> 2]; + else + cbit = FPU_CSR_COND; + cond = ctx->fcr31 & cbit; + + likely = 0; switch (MIPSInst_RT(ir) & 3) { case bcfl_op: likely = 1; @@ -1201,10 +968,10 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, return SIGILL; } - xcp->cp0_cause |= CAUSEF_BD; + set_delay_slot(xcp); if (cond) { - /* branch taken: emulate dslot - * instruction + /* + * Branch taken: emulate dslot instruction */ xcp->cp0_epc += dec_insn.pc_inc; @@ -1238,23 +1005,37 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, switch (MIPSInst_OPCODE(ir)) { case lwc1_op: + goto emul; + case swc1_op: -#if (__mips >= 2 || defined(__mips64)) + goto emul; + case ldc1_op: case sdc1_op: -#endif + if (cpu_has_mips_2_3_4_5 || + cpu_has_mips64) + goto emul; + + return SIGILL; + goto emul; + case cop1_op: -#if __mips >= 4 && __mips != 32 - case cop1x_op: -#endif - /* its one of ours */ goto emul; -#if __mips >= 4 + + case cop1x_op: + if (cpu_has_mips_4_5 || cpu_has_mips64) + /* its one of ours */ + goto emul; + + return SIGILL; + case spec_op: + if (!cpu_has_mips_4_5_r) + return SIGILL; + if (MIPSInst_FUNC(ir) == movc_op) goto emul; break; -#endif } /* @@ -1262,10 +1043,7 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, * instruction in the dslot */ return mips_dsemul(xcp, ir, contpc); - } - else { - /* branch not taken */ - if (likely) { + } else if (likely) { /* branch not taken */ /* * branch likely nullifies * dslot if not taken @@ -1277,34 +1055,31 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, * dslot as normal insn */ } - } break; - } default: if (!(MIPSInst_RS(ir) & 0x10)) return SIGILL; - { - int sig; - /* a real fpu computation instruction */ - if ((sig = fpu_emu(xcp, ctx, ir))) - return sig; - } + /* a real fpu computation instruction */ + if ((sig = fpu_emu(xcp, ctx, ir))) + return sig; } break; -#if __mips >= 4 && __mips != 32 - case cop1x_op:{ - int sig = fpux_emu(xcp, ctx, ir, fault_addr); + case cop1x_op: + if (!cpu_has_mips_4_5 && !cpu_has_mips64) + return SIGILL; + + sig = fpux_emu(xcp, ctx, ir, fault_addr); if (sig) return sig; break; - } -#endif -#if __mips >= 4 case spec_op: + if (!cpu_has_mips_4_5_r) + return SIGILL; + if (MIPSInst_FUNC(ir) != movc_op) return SIGILL; cond = fpucondbit[MIPSInst_RT(ir) >> 2]; @@ -1312,8 +1087,6 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, xcp->regs[MIPSInst_RD(ir)] = xcp->regs[MIPSInst_RS(ir)]; break; -#endif - default: sigill: return SIGILL; @@ -1321,7 +1094,7 @@ sigill: /* we did it !! */ xcp->cp0_epc = contpc; - xcp->cp0_cause &= ~CAUSEF_BD; + clear_delay_slot(xcp); return 0; } @@ -1342,44 +1115,42 @@ static const unsigned char cmptab[8] = { }; -#if __mips >= 4 && __mips != 32 - /* * Additional MIPS4 instructions */ -#define DEF3OP(name, p, f1, f2, f3) \ -static ieee754##p fpemu_##p##_##name(ieee754##p r, ieee754##p s, \ - ieee754##p t) \ -{ \ - struct _ieee754_csr ieee754_csr_save; \ - s = f1(s, t); \ - ieee754_csr_save = ieee754_csr; \ - s = f2(s, r); \ - ieee754_csr_save.cx |= ieee754_csr.cx; \ - ieee754_csr_save.sx |= ieee754_csr.sx; \ - s = f3(s); \ - ieee754_csr.cx |= ieee754_csr_save.cx; \ - ieee754_csr.sx |= ieee754_csr_save.sx; \ - return s; \ +#define DEF3OP(name, p, f1, f2, f3) \ +static union ieee754##p fpemu_##p##_##name(union ieee754##p r, \ + union ieee754##p s, union ieee754##p t) \ +{ \ + struct _ieee754_csr ieee754_csr_save; \ + s = f1(s, t); \ + ieee754_csr_save = ieee754_csr; \ + s = f2(s, r); \ + ieee754_csr_save.cx |= ieee754_csr.cx; \ + ieee754_csr_save.sx |= ieee754_csr.sx; \ + s = f3(s); \ + ieee754_csr.cx |= ieee754_csr_save.cx; \ + ieee754_csr.sx |= ieee754_csr_save.sx; \ + return s; \ } -static ieee754dp fpemu_dp_recip(ieee754dp d) +static union ieee754dp fpemu_dp_recip(union ieee754dp d) { return ieee754dp_div(ieee754dp_one(0), d); } -static ieee754dp fpemu_dp_rsqrt(ieee754dp d) +static union ieee754dp fpemu_dp_rsqrt(union ieee754dp d) { return ieee754dp_div(ieee754dp_one(0), ieee754dp_sqrt(d)); } -static ieee754sp fpemu_sp_recip(ieee754sp s) +static union ieee754sp fpemu_sp_recip(union ieee754sp s) { return ieee754sp_div(ieee754sp_one(0), s); } -static ieee754sp fpemu_sp_rsqrt(ieee754sp s) +static union ieee754sp fpemu_sp_rsqrt(union ieee754sp s) { return ieee754sp_div(ieee754sp_one(0), ieee754sp_sqrt(s)); } @@ -1403,8 +1174,8 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, switch (MIPSInst_FMA_FFMT(ir)) { case s_fmt:{ /* 0 */ - ieee754sp(*handler) (ieee754sp, ieee754sp, ieee754sp); - ieee754sp fd, fr, fs, ft; + union ieee754sp(*handler) (union ieee754sp, union ieee754sp, union ieee754sp); + union ieee754sp fd, fr, fs, ft; u32 __user *va; u32 val; @@ -1467,18 +1238,26 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, SPTOREG(fd, MIPSInst_FD(ir)); copcsr: - if (ieee754_cxtest(IEEE754_INEXACT)) + if (ieee754_cxtest(IEEE754_INEXACT)) { + MIPS_FPU_EMU_INC_STATS(ieee754_inexact); rcsr |= FPU_CSR_INE_X | FPU_CSR_INE_S; - if (ieee754_cxtest(IEEE754_UNDERFLOW)) + } + if (ieee754_cxtest(IEEE754_UNDERFLOW)) { + MIPS_FPU_EMU_INC_STATS(ieee754_underflow); rcsr |= FPU_CSR_UDF_X | FPU_CSR_UDF_S; - if (ieee754_cxtest(IEEE754_OVERFLOW)) + } + if (ieee754_cxtest(IEEE754_OVERFLOW)) { + MIPS_FPU_EMU_INC_STATS(ieee754_overflow); rcsr |= FPU_CSR_OVF_X | FPU_CSR_OVF_S; - if (ieee754_cxtest(IEEE754_INVALID_OPERATION)) + } + if (ieee754_cxtest(IEEE754_INVALID_OPERATION)) { + MIPS_FPU_EMU_INC_STATS(ieee754_invalidop); rcsr |= FPU_CSR_INV_X | FPU_CSR_INV_S; + } ctx->fcr31 = (ctx->fcr31 & ~FPU_CSR_ALL_X) | rcsr; if ((ctx->fcr31 >> 5) & ctx->fcr31 & FPU_CSR_ALL_E) { - /*printk ("SIGFPE: fpu csr = %08x\n", + /*printk ("SIGFPE: FPU csr = %08x\n", ctx->fcr31); */ return SIGFPE; } @@ -1492,8 +1271,8 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, } case d_fmt:{ /* 1 */ - ieee754dp(*handler) (ieee754dp, ieee754dp, ieee754dp); - ieee754dp fd, fr, fs, ft; + union ieee754dp(*handler) (union ieee754dp, union ieee754dp, union ieee754dp); + union ieee754dp fd, fr, fs, ft; u64 __user *va; u64 val; @@ -1574,7 +1353,6 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, return 0; } -#endif @@ -1586,23 +1364,25 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, { int rfmt; /* resulting format */ unsigned rcsr = 0; /* resulting csr */ + unsigned int oldrm; + unsigned int cbit; unsigned cond; union { - ieee754dp d; - ieee754sp s; + union ieee754dp d; + union ieee754sp s; int w; -#ifdef __mips64 s64 l; -#endif } rv; /* resulting value */ + u64 bits; MIPS_FPU_EMU_INC_STATS(cp1ops); switch (rfmt = (MIPSInst_FFMT(ir) & 0xf)) { - case s_fmt:{ /* 0 */ + case s_fmt: { /* 0 */ union { - ieee754sp(*b) (ieee754sp, ieee754sp); - ieee754sp(*u) (ieee754sp); + union ieee754sp(*b) (union ieee754sp, union ieee754sp); + union ieee754sp(*u) (union ieee754sp); } handler; + union ieee754sp fs, ft; switch (MIPSInst_FUNC(ir)) { /* binary ops */ @@ -1620,148 +1400,167 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, goto scopbop; /* unary ops */ -#if __mips >= 2 || defined(__mips64) case fsqrt_op: + if (!cpu_has_mips_4_5_r) + return SIGILL; + handler.u = ieee754sp_sqrt; goto scopuop; -#endif -#if __mips >= 4 && __mips != 32 + + /* + * Note that on some MIPS IV implementations such as the + * R5000 and R8000 the FSQRT and FRECIP instructions do not + * achieve full IEEE-754 accuracy - however this emulator does. + */ case frsqrt_op: + if (!cpu_has_mips_4_5_r2) + return SIGILL; + handler.u = fpemu_sp_rsqrt; goto scopuop; + case frecip_op: + if (!cpu_has_mips_4_5_r2) + return SIGILL; + handler.u = fpemu_sp_recip; goto scopuop; -#endif -#if __mips >= 4 + case fmovc_op: + if (!cpu_has_mips_4_5_r) + return SIGILL; + cond = fpucondbit[MIPSInst_FT(ir) >> 2]; if (((ctx->fcr31 & cond) != 0) != ((MIPSInst_FT(ir) & 1) != 0)) return 0; SPFROMREG(rv.s, MIPSInst_FS(ir)); break; + case fmovz_op: + if (!cpu_has_mips_4_5_r) + return SIGILL; + if (xcp->regs[MIPSInst_FT(ir)] != 0) return 0; SPFROMREG(rv.s, MIPSInst_FS(ir)); break; + case fmovn_op: + if (!cpu_has_mips_4_5_r) + return SIGILL; + if (xcp->regs[MIPSInst_FT(ir)] == 0) return 0; SPFROMREG(rv.s, MIPSInst_FS(ir)); break; -#endif + case fabs_op: handler.u = ieee754sp_abs; goto scopuop; + case fneg_op: handler.u = ieee754sp_neg; goto scopuop; + case fmov_op: /* an easy one */ SPFROMREG(rv.s, MIPSInst_FS(ir)); goto copcsr; /* binary op on handler */ - scopbop: - { - ieee754sp fs, ft; - - SPFROMREG(fs, MIPSInst_FS(ir)); - SPFROMREG(ft, MIPSInst_FT(ir)); - - rv.s = (*handler.b) (fs, ft); - goto copcsr; - } - scopuop: - { - ieee754sp fs; +scopbop: + SPFROMREG(fs, MIPSInst_FS(ir)); + SPFROMREG(ft, MIPSInst_FT(ir)); - SPFROMREG(fs, MIPSInst_FS(ir)); - rv.s = (*handler.u) (fs); - goto copcsr; - } - copcsr: - if (ieee754_cxtest(IEEE754_INEXACT)) + rv.s = (*handler.b) (fs, ft); + goto copcsr; +scopuop: + SPFROMREG(fs, MIPSInst_FS(ir)); + rv.s = (*handler.u) (fs); + goto copcsr; +copcsr: + if (ieee754_cxtest(IEEE754_INEXACT)) { + MIPS_FPU_EMU_INC_STATS(ieee754_inexact); rcsr |= FPU_CSR_INE_X | FPU_CSR_INE_S; - if (ieee754_cxtest(IEEE754_UNDERFLOW)) + } + if (ieee754_cxtest(IEEE754_UNDERFLOW)) { + MIPS_FPU_EMU_INC_STATS(ieee754_underflow); rcsr |= FPU_CSR_UDF_X | FPU_CSR_UDF_S; - if (ieee754_cxtest(IEEE754_OVERFLOW)) + } + if (ieee754_cxtest(IEEE754_OVERFLOW)) { + MIPS_FPU_EMU_INC_STATS(ieee754_overflow); rcsr |= FPU_CSR_OVF_X | FPU_CSR_OVF_S; - if (ieee754_cxtest(IEEE754_ZERO_DIVIDE)) + } + if (ieee754_cxtest(IEEE754_ZERO_DIVIDE)) { + MIPS_FPU_EMU_INC_STATS(ieee754_zerodiv); rcsr |= FPU_CSR_DIV_X | FPU_CSR_DIV_S; - if (ieee754_cxtest(IEEE754_INVALID_OPERATION)) + } + if (ieee754_cxtest(IEEE754_INVALID_OPERATION)) { + MIPS_FPU_EMU_INC_STATS(ieee754_invalidop); rcsr |= FPU_CSR_INV_X | FPU_CSR_INV_S; + } break; /* unary conv ops */ case fcvts_op: return SIGILL; /* not defined */ - case fcvtd_op:{ - ieee754sp fs; + case fcvtd_op: SPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fsp(fs); rfmt = d_fmt; goto copcsr; - } - case fcvtw_op:{ - ieee754sp fs; + case fcvtw_op: SPFROMREG(fs, MIPSInst_FS(ir)); rv.w = ieee754sp_tint(fs); rfmt = w_fmt; goto copcsr; - } -#if __mips >= 2 || defined(__mips64) case fround_op: case ftrunc_op: case fceil_op: - case ffloor_op:{ - unsigned int oldrm = ieee754_csr.rm; - ieee754sp fs; + case ffloor_op: + if (!cpu_has_mips_2_3_4_5 && !cpu_has_mips64) + return SIGILL; + oldrm = ieee754_csr.rm; SPFROMREG(fs, MIPSInst_FS(ir)); - ieee754_csr.rm = ieee_rm[modeindex(MIPSInst_FUNC(ir))]; + ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir)); rv.w = ieee754sp_tint(fs); ieee754_csr.rm = oldrm; rfmt = w_fmt; goto copcsr; - } -#endif /* __mips >= 2 */ -#if defined(__mips64) - case fcvtl_op:{ - ieee754sp fs; + case fcvtl_op: + if (!cpu_has_mips_3_4_5 && !cpu_has_mips64) + return SIGILL; SPFROMREG(fs, MIPSInst_FS(ir)); rv.l = ieee754sp_tlong(fs); rfmt = l_fmt; goto copcsr; - } case froundl_op: case ftruncl_op: case fceill_op: - case ffloorl_op:{ - unsigned int oldrm = ieee754_csr.rm; - ieee754sp fs; + case ffloorl_op: + if (!cpu_has_mips_3_4_5 && !cpu_has_mips64) + return SIGILL; + oldrm = ieee754_csr.rm; SPFROMREG(fs, MIPSInst_FS(ir)); - ieee754_csr.rm = ieee_rm[modeindex(MIPSInst_FUNC(ir))]; + ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir)); rv.l = ieee754sp_tlong(fs); ieee754_csr.rm = oldrm; rfmt = l_fmt; goto copcsr; - } -#endif /* defined(__mips64) */ default: if (MIPSInst_FUNC(ir) >= fcmp_op) { unsigned cmpop = MIPSInst_FUNC(ir) - fcmp_op; - ieee754sp fs, ft; + union ieee754sp fs, ft; SPFROMREG(fs, MIPSInst_FS(ir)); SPFROMREG(ft, MIPSInst_FT(ir)); @@ -1774,19 +1573,18 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, else goto copcsr; - } - else { + } else return SIGILL; - } break; } break; } - case d_fmt:{ + case d_fmt: { + union ieee754dp fs, ft; union { - ieee754dp(*b) (ieee754dp, ieee754dp); - ieee754dp(*u) (ieee754dp); + union ieee754dp(*b) (union ieee754dp, union ieee754dp); + union ieee754dp(*u) (union ieee754dp); } handler; switch (MIPSInst_FUNC(ir)) { @@ -1805,21 +1603,33 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, goto dcopbop; /* unary ops */ -#if __mips >= 2 || defined(__mips64) case fsqrt_op: + if (!cpu_has_mips_2_3_4_5_r) + return SIGILL; + handler.u = ieee754dp_sqrt; goto dcopuop; -#endif -#if __mips >= 4 && __mips != 32 + /* + * Note that on some MIPS IV implementations such as the + * R5000 and R8000 the FSQRT and FRECIP instructions do not + * achieve full IEEE-754 accuracy - however this emulator does. + */ case frsqrt_op: + if (!cpu_has_mips_4_5_r2) + return SIGILL; + handler.u = fpemu_dp_rsqrt; goto dcopuop; case frecip_op: + if (!cpu_has_mips_4_5_r2) + return SIGILL; + handler.u = fpemu_dp_recip; goto dcopuop; -#endif -#if __mips >= 4 case fmovc_op: + if (!cpu_has_mips_4_5_r) + return SIGILL; + cond = fpucondbit[MIPSInst_FT(ir) >> 2]; if (((ctx->fcr31 & cond) != 0) != ((MIPSInst_FT(ir) & 1) != 0)) @@ -1827,16 +1637,21 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, DPFROMREG(rv.d, MIPSInst_FS(ir)); break; case fmovz_op: + if (!cpu_has_mips_4_5_r) + return SIGILL; + if (xcp->regs[MIPSInst_FT(ir)] != 0) return 0; DPFROMREG(rv.d, MIPSInst_FS(ir)); break; case fmovn_op: + if (!cpu_has_mips_4_5_r) + return SIGILL; + if (xcp->regs[MIPSInst_FT(ir)] == 0) return 0; DPFROMREG(rv.d, MIPSInst_FS(ir)); break; -#endif case fabs_op: handler.u = ieee754dp_abs; goto dcopuop; @@ -1851,91 +1666,78 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, goto copcsr; /* binary op on handler */ - dcopbop:{ - ieee754dp fs, ft; - - DPFROMREG(fs, MIPSInst_FS(ir)); - DPFROMREG(ft, MIPSInst_FT(ir)); - - rv.d = (*handler.b) (fs, ft); - goto copcsr; - } - dcopuop:{ - ieee754dp fs; - - DPFROMREG(fs, MIPSInst_FS(ir)); - rv.d = (*handler.u) (fs); - goto copcsr; - } +dcopbop: + DPFROMREG(fs, MIPSInst_FS(ir)); + DPFROMREG(ft, MIPSInst_FT(ir)); - /* unary conv ops */ - case fcvts_op:{ - ieee754dp fs; + rv.d = (*handler.b) (fs, ft); + goto copcsr; +dcopuop: + DPFROMREG(fs, MIPSInst_FS(ir)); + rv.d = (*handler.u) (fs); + goto copcsr; + /* + * unary conv ops + */ + case fcvts_op: DPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fdp(fs); rfmt = s_fmt; goto copcsr; - } + case fcvtd_op: return SIGILL; /* not defined */ - case fcvtw_op:{ - ieee754dp fs; - + case fcvtw_op: DPFROMREG(fs, MIPSInst_FS(ir)); rv.w = ieee754dp_tint(fs); /* wrong */ rfmt = w_fmt; goto copcsr; - } -#if __mips >= 2 || defined(__mips64) case fround_op: case ftrunc_op: case fceil_op: - case ffloor_op:{ - unsigned int oldrm = ieee754_csr.rm; - ieee754dp fs; + case ffloor_op: + if (!cpu_has_mips_2_3_4_5_r) + return SIGILL; + oldrm = ieee754_csr.rm; DPFROMREG(fs, MIPSInst_FS(ir)); - ieee754_csr.rm = ieee_rm[modeindex(MIPSInst_FUNC(ir))]; + ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir)); rv.w = ieee754dp_tint(fs); ieee754_csr.rm = oldrm; rfmt = w_fmt; goto copcsr; - } -#endif -#if defined(__mips64) - case fcvtl_op:{ - ieee754dp fs; + case fcvtl_op: + if (!cpu_has_mips_3_4_5 && !cpu_has_mips64) + return SIGILL; DPFROMREG(fs, MIPSInst_FS(ir)); rv.l = ieee754dp_tlong(fs); rfmt = l_fmt; goto copcsr; - } case froundl_op: case ftruncl_op: case fceill_op: - case ffloorl_op:{ - unsigned int oldrm = ieee754_csr.rm; - ieee754dp fs; + case ffloorl_op: + if (!cpu_has_mips_3_4_5 && !cpu_has_mips64) + return SIGILL; + oldrm = ieee754_csr.rm; DPFROMREG(fs, MIPSInst_FS(ir)); - ieee754_csr.rm = ieee_rm[modeindex(MIPSInst_FUNC(ir))]; + ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir)); rv.l = ieee754dp_tlong(fs); ieee754_csr.rm = oldrm; rfmt = l_fmt; goto copcsr; - } -#endif /* __mips >= 3 */ default: if (MIPSInst_FUNC(ir) >= fcmp_op) { unsigned cmpop = MIPSInst_FUNC(ir) - fcmp_op; - ieee754dp fs, ft; + union ieee754dp fs, ft; DPFROMREG(fs, MIPSInst_FS(ir)); DPFROMREG(ft, MIPSInst_FT(ir)); @@ -1957,11 +1759,8 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, break; } break; - } - - case w_fmt:{ - ieee754sp fs; + case w_fmt: switch (MIPSInst_FUNC(ir)) { case fcvts_op: /* convert word to single precision real */ @@ -1981,9 +1780,11 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, break; } -#if defined(__mips64) - case l_fmt:{ - u64 bits; + case l_fmt: + + if (!cpu_has_mips_3_4_5 && !cpu_has_mips64) + return SIGILL; + DIFROMREG(bits, MIPSInst_FS(ir)); switch (MIPSInst_FUNC(ir)) { @@ -2001,8 +1802,6 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, return SIGILL; } break; - } -#endif default: return SIGILL; @@ -2017,7 +1816,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, */ ctx->fcr31 = (ctx->fcr31 & ~FPU_CSR_ALL_X) | rcsr; if ((ctx->fcr31 >> 5) & ctx->fcr31 & FPU_CSR_ALL_E) { - /*printk ("SIGFPE: fpu csr = %08x\n",ctx->fcr31); */ + /*printk ("SIGFPE: FPU csr = %08x\n",ctx->fcr31); */ return SIGFPE; } @@ -2025,18 +1824,18 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, * Now we can safely write the result back to the register file. */ switch (rfmt) { - case -1:{ -#if __mips >= 4 - cond = fpucondbit[MIPSInst_FD(ir) >> 2]; -#else - cond = FPU_CSR_COND; -#endif + case -1: + + if (cpu_has_mips_4_5_r) + cbit = fpucondbit[MIPSInst_RT(ir) >> 2]; + else + cbit = FPU_CSR_COND; if (rv.w) - ctx->fcr31 |= cond; + ctx->fcr31 |= cbit; else - ctx->fcr31 &= ~cond; + ctx->fcr31 &= ~cbit; break; - } + case d_fmt: DPTOREG(rv.d, MIPSInst_FD(ir)); break; @@ -2046,11 +1845,12 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, case w_fmt: SITOREG(rv.w, MIPSInst_FD(ir)); break; -#if defined(__mips64) case l_fmt: + if (!cpu_has_mips_3_4_5 && !cpu_has_mips64) + return SIGILL; + DITOREG(rv.l, MIPSInst_FD(ir)); break; -#endif default: return SIGILL; } @@ -2138,11 +1938,7 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, * ieee754_csr. But ieee754_csr.rm is ieee * library modes. (not mips rounding mode) */ - /* convert to ieee library modes */ - ieee754_csr.rm = ieee_rm[ieee754_csr.rm]; sig = cop1Emulate(xcp, ctx, dec_insn, fault_addr); - /* revert to mips rounding mode */ - ieee754_csr.rm = mips_rm[ieee754_csr.rm]; } if (has_fpu) @@ -2155,58 +1951,8 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, /* SIGILL indicates a non-fpu instruction */ if (sig == SIGILL && xcp->cp0_epc != oldepc) - /* but if epc has advanced, then ignore it */ + /* but if EPC has advanced, then ignore it */ sig = 0; return sig; } - -#ifdef CONFIG_DEBUG_FS - -static int fpuemu_stat_get(void *data, u64 *val) -{ - int cpu; - unsigned long sum = 0; - for_each_online_cpu(cpu) { - struct mips_fpu_emulator_stats *ps; - local_t *pv; - ps = &per_cpu(fpuemustats, cpu); - pv = (void *)ps + (unsigned long)data; - sum += local_read(pv); - } - *val = sum; - return 0; -} -DEFINE_SIMPLE_ATTRIBUTE(fops_fpuemu_stat, fpuemu_stat_get, NULL, "%llu\n"); - -extern struct dentry *mips_debugfs_dir; -static int __init debugfs_fpuemu(void) -{ - struct dentry *d, *dir; - - if (!mips_debugfs_dir) - return -ENODEV; - dir = debugfs_create_dir("fpuemustats", mips_debugfs_dir); - if (!dir) - return -ENOMEM; - -#define FPU_STAT_CREATE(M) \ - do { \ - d = debugfs_create_file(#M , S_IRUGO, dir, \ - (void *)offsetof(struct mips_fpu_emulator_stats, M), \ - &fops_fpuemu_stat); \ - if (!d) \ - return -ENOMEM; \ - } while (0) - - FPU_STAT_CREATE(emulated); - FPU_STAT_CREATE(loads); - FPU_STAT_CREATE(stores); - FPU_STAT_CREATE(cp1ops); - FPU_STAT_CREATE(cp1xops); - FPU_STAT_CREATE(errors); - - return 0; -} -__initcall(debugfs_fpuemu); -#endif diff --git a/arch/mips/math-emu/dp_add.c b/arch/mips/math-emu/dp_add.c index c57c8adc42c4..7f64577df984 100644 --- a/arch/mips/math-emu/dp_add.c +++ b/arch/mips/math-emu/dp_add.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,24 +16,22 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - * + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754dp.h" -ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y) +union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y) { + int s; + COMPXDP; COMPYDP; EXPLODEXDP; EXPLODEYDP; - CLEARCX; + ieee754_clearcx(); FLUSHXDP; FLUSHYDP; @@ -52,8 +48,8 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_nanxcpt(ieee754dp_indef(), "add", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_nanxcpt(ieee754dp_indef()); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): @@ -69,14 +65,14 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y) return x; - /* Infinity handling - */ - + /* + * Infinity handling + */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): if (xs == ys) return x; - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_xcpt(ieee754dp_indef(), "add", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_indef(); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): @@ -88,15 +84,14 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y) case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): return x; - /* Zero handling - */ - + /* + * Zero handling + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): if (xs == ys) return x; else - return ieee754dp_zero(ieee754_csr.rm == - IEEE754_RD); + return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): @@ -125,20 +120,24 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y) assert(xm & DP_HIDDEN_BIT); assert(ym & DP_HIDDEN_BIT); - /* provide guard,round and stick bit space */ + /* + * Provide guard,round and stick bit space. + */ xm <<= 3; ym <<= 3; if (xe > ye) { - /* have to shift y fraction right to align + /* + * Have to shift y fraction right to align. */ - int s = xe - ye; + s = xe - ye; ym = XDPSRS(ym, s); ye += s; } else if (ye > xe) { - /* have to shift x fraction right to align + /* + * Have to shift x fraction right to align. */ - int s = ye - xe; + s = ye - xe; xm = XDPSRS(xm, s); xe += s; } @@ -146,14 +145,15 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y) assert(xe <= DP_EMAX); if (xs == ys) { - /* generate 28 bit result of adding two 27 bit numbers - * leaving result in xm,xs,xe + /* + * Generate 28 bit result of adding two 27 bit numbers + * leaving result in xm, xs and xe. */ xm = xm + ym; xe = xe; xs = xs; - if (xm >> (DP_MBITS + 1 + 3)) { /* carry out */ + if (xm >> (DP_FBITS + 1 + 3)) { /* carry out */ xm = XDPSRS1(xm); xe++; } @@ -168,15 +168,16 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y) xs = ys; } if (xm == 0) - return ieee754dp_zero(ieee754_csr.rm == - IEEE754_RD); + return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD); - /* normalize to rounding precision */ - while ((xm >> (DP_MBITS + 3)) == 0) { + /* + * Normalize to rounding precision. + */ + while ((xm >> (DP_FBITS + 3)) == 0) { xm <<= 1; xe--; } - } - DPNORMRET2(xs, xe, xm, "add", x, y); + + return ieee754dp_format(xs, xe, xm); } diff --git a/arch/mips/math-emu/dp_cmp.c b/arch/mips/math-emu/dp_cmp.c index 0f32486b0ed9..30f95f6e9ac4 100644 --- a/arch/mips/math-emu/dp_cmp.c +++ b/arch/mips/math-emu/dp_cmp.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,16 +16,16 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754dp.h" -int ieee754dp_cmp(ieee754dp x, ieee754dp y, int cmp, int sig) +int ieee754dp_cmp(union ieee754dp x, union ieee754dp y, int cmp, int sig) { + s64 vx; + s64 vy; + COMPXDP; COMPYDP; @@ -35,21 +33,21 @@ int ieee754dp_cmp(ieee754dp x, ieee754dp y, int cmp, int sig) EXPLODEYDP; FLUSHXDP; FLUSHYDP; - CLEARCX; /* Even clear inexact flag here */ + ieee754_clearcx(); /* Even clear inexact flag here */ if (ieee754dp_isnan(x) || ieee754dp_isnan(y)) { if (sig || xc == IEEE754_CLASS_SNAN || yc == IEEE754_CLASS_SNAN) - SETCX(IEEE754_INVALID_OPERATION); + ieee754_setcx(IEEE754_INVALID_OPERATION); if (cmp & IEEE754_CUN) return 1; if (cmp & (IEEE754_CLT | IEEE754_CGT)) { - if (sig && SETANDTESTCX(IEEE754_INVALID_OPERATION)) - return ieee754si_xcpt(0, "fcmpf", x); + if (sig && ieee754_setandtestcx(IEEE754_INVALID_OPERATION)) + return 0; } return 0; } else { - s64 vx = x.bits; - s64 vy = y.bits; + vx = x.bits; + vy = y.bits; if (vx < 0) vx = -vx ^ DP_SIGN_BIT; diff --git a/arch/mips/math-emu/dp_div.c b/arch/mips/math-emu/dp_div.c index a1bce1b7c09c..bef0e55e5938 100644 --- a/arch/mips/math-emu/dp_div.c +++ b/arch/mips/math-emu/dp_div.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,23 +16,24 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754dp.h" -ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y) +union ieee754dp ieee754dp_div(union ieee754dp x, union ieee754dp y) { + u64 rm; + int re; + u64 bm; + COMPXDP; COMPYDP; EXPLODEXDP; EXPLODEYDP; - CLEARCX; + ieee754_clearcx(); FLUSHXDP; FLUSHYDP; @@ -51,8 +50,8 @@ ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_nanxcpt(ieee754dp_indef(), "div", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_nanxcpt(ieee754dp_indef()); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): @@ -68,12 +67,12 @@ ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y) return x; - /* Infinity handling - */ - + /* + * Infinity handling + */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_xcpt(ieee754dp_indef(), "div", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_indef(); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): @@ -85,17 +84,17 @@ ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y) case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): return ieee754dp_inf(xs ^ ys); - /* Zero handling - */ - + /* + * Zero handling + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_xcpt(ieee754dp_indef(), "div", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_indef(); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): - SETCX(IEEE754_ZERO_DIVIDE); - return ieee754dp_xcpt(ieee754dp_inf(xs ^ ys), "div", x, y); + ieee754_setcx(IEEE754_ZERO_DIVIDE); + return ieee754dp_inf(xs ^ ys); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM): @@ -122,35 +121,34 @@ ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y) xm <<= 3; ym <<= 3; - { - /* now the dirty work */ - - u64 rm = 0; - int re = xe - ye; - u64 bm; - - for (bm = DP_MBIT(DP_MBITS + 2); bm; bm >>= 1) { - if (xm >= ym) { - xm -= ym; - rm |= bm; - if (xm == 0) - break; - } - xm <<= 1; - } - rm <<= 1; - if (xm) - rm |= 1; /* have remainder, set sticky */ + /* now the dirty work */ - assert(rm); + rm = 0; + re = xe - ye; - /* normalise rm to rounding precision ? - */ - while ((rm >> (DP_MBITS + 3)) == 0) { - rm <<= 1; - re--; + for (bm = DP_MBIT(DP_FBITS + 2); bm; bm >>= 1) { + if (xm >= ym) { + xm -= ym; + rm |= bm; + if (xm == 0) + break; } + xm <<= 1; + } + + rm <<= 1; + if (xm) + rm |= 1; /* have remainder, set sticky */ - DPNORMRET2(xs == ys ? 0 : 1, re, rm, "div", x, y); + assert(rm); + + /* + * Normalise rm to rounding precision ? + */ + while ((rm >> (DP_FBITS + 3)) == 0) { + rm <<= 1; + re--; } + + return ieee754dp_format(xs == ys ? 0 : 1, re, rm); } diff --git a/arch/mips/math-emu/dp_fint.c b/arch/mips/math-emu/dp_fint.c index 88571288c9e0..10258f0afd69 100644 --- a/arch/mips/math-emu/dp_fint.c +++ b/arch/mips/math-emu/dp_fint.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,21 +16,18 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754dp.h" -ieee754dp ieee754dp_fint(int x) +union ieee754dp ieee754dp_fint(int x) { u64 xm; int xe; int xs; - CLEARCX; + ieee754_clearcx(); if (x == 0) return ieee754dp_zero(0); @@ -51,29 +46,11 @@ ieee754dp ieee754dp_fint(int x) xm = x; } -#if 1 /* normalize - result can never be inexact or overflow */ - xe = DP_MBITS; - while ((xm >> DP_MBITS) == 0) { + xe = DP_FBITS; + while ((xm >> DP_FBITS) == 0) { xm <<= 1; xe--; } return builddp(xs, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT); -#else - /* normalize */ - xe = DP_MBITS + 3; - while ((xm >> (DP_MBITS + 3)) == 0) { - xm <<= 1; - xe--; - } - DPNORMRET1(xs, xe, xm, "fint", x); -#endif -} - -ieee754dp ieee754dp_funs(unsigned int u) -{ - if ((int) u < 0) - return ieee754dp_add(ieee754dp_1e31(), - ieee754dp_fint(u & ~(1 << 31))); - return ieee754dp_fint(u); } diff --git a/arch/mips/math-emu/dp_flong.c b/arch/mips/math-emu/dp_flong.c index 14fc01ec742d..a267c2e39d78 100644 --- a/arch/mips/math-emu/dp_flong.c +++ b/arch/mips/math-emu/dp_flong.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,21 +16,18 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754dp.h" -ieee754dp ieee754dp_flong(s64 x) +union ieee754dp ieee754dp_flong(s64 x) { u64 xm; int xe; int xs; - CLEARCX; + ieee754_clearcx(); if (x == 0) return ieee754dp_zero(0); @@ -52,26 +47,19 @@ ieee754dp ieee754dp_flong(s64 x) } /* normalize */ - xe = DP_MBITS + 3; - if (xm >> (DP_MBITS + 1 + 3)) { + xe = DP_FBITS + 3; + if (xm >> (DP_FBITS + 1 + 3)) { /* shunt out overflow bits */ - while (xm >> (DP_MBITS + 1 + 3)) { + while (xm >> (DP_FBITS + 1 + 3)) { XDPSRSX1(); } } else { /* normalize in grs extended double precision */ - while ((xm >> (DP_MBITS + 3)) == 0) { + while ((xm >> (DP_FBITS + 3)) == 0) { xm <<= 1; xe--; } } - DPNORMRET1(xs, xe, xm, "dp_flong", x); -} -ieee754dp ieee754dp_fulong(u64 u) -{ - if ((s64) u < 0) - return ieee754dp_add(ieee754dp_1e63(), - ieee754dp_flong(u & ~(1ULL << 63))); - return ieee754dp_flong(u); + return ieee754dp_format(xs, xe, xm); } diff --git a/arch/mips/math-emu/dp_frexp.c b/arch/mips/math-emu/dp_frexp.c deleted file mode 100644 index cb15a5eaecbb..000000000000 --- a/arch/mips/math-emu/dp_frexp.c +++ /dev/null @@ -1,52 +0,0 @@ -/* IEEE754 floating point arithmetic - * double precision: common utilities - */ -/* - * MIPS floating point support - * Copyright (C) 1994-2000 Algorithmics Ltd. - * - * ######################################################################## - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - */ - - -#include "ieee754dp.h" - -/* close to ieeep754dp_logb -*/ -ieee754dp ieee754dp_frexp(ieee754dp x, int *eptr) -{ - COMPXDP; - CLEARCX; - EXPLODEXDP; - - switch (xc) { - case IEEE754_CLASS_SNAN: - case IEEE754_CLASS_QNAN: - case IEEE754_CLASS_INF: - case IEEE754_CLASS_ZERO: - *eptr = 0; - return x; - case IEEE754_CLASS_DNORM: - DPDNORMX; - break; - case IEEE754_CLASS_NORM: - break; - } - *eptr = xe + 1; - return builddp(xs, -1 + DP_EBIAS, xm & ~DP_HIDDEN_BIT); -} diff --git a/arch/mips/math-emu/dp_fsp.c b/arch/mips/math-emu/dp_fsp.c index daed6834dc15..ffb69c5830b0 100644 --- a/arch/mips/math-emu/dp_fsp.c +++ b/arch/mips/math-emu/dp_fsp.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,56 +16,58 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - +#include "ieee754sp.h" #include "ieee754dp.h" -ieee754dp ieee754dp_fsp(ieee754sp x) +union ieee754dp ieee754dp_fsp(union ieee754sp x) { COMPXSP; EXPLODEXSP; - CLEARCX; + ieee754_clearcx(); FLUSHXSP; switch (xc) { case IEEE754_CLASS_SNAN: - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_nanxcpt(ieee754dp_indef(), "fsp"); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_nanxcpt(ieee754dp_indef()); + case IEEE754_CLASS_QNAN: return ieee754dp_nanxcpt(builddp(xs, DP_EMAX + 1 + DP_EBIAS, ((u64) xm - << (DP_MBITS - - SP_MBITS))), "fsp", - x); + << (DP_FBITS - + SP_FBITS)))); case IEEE754_CLASS_INF: return ieee754dp_inf(xs); + case IEEE754_CLASS_ZERO: return ieee754dp_zero(xs); + case IEEE754_CLASS_DNORM: /* normalize */ - while ((xm >> SP_MBITS) == 0) { + while ((xm >> SP_FBITS) == 0) { xm <<= 1; xe--; } break; + case IEEE754_CLASS_NORM: break; } - /* CAN'T possibly overflow,underflow, or need rounding + /* + * Can't possibly overflow,underflow, or need rounding */ /* drop the hidden bit */ xm &= ~SP_HIDDEN_BIT; return builddp(xs, xe + DP_EBIAS, - (u64) xm << (DP_MBITS - SP_MBITS)); + (u64) xm << (DP_FBITS - SP_FBITS)); } diff --git a/arch/mips/math-emu/dp_logb.c b/arch/mips/math-emu/dp_logb.c deleted file mode 100644 index 151127e59f5c..000000000000 --- a/arch/mips/math-emu/dp_logb.c +++ /dev/null @@ -1,53 +0,0 @@ -/* IEEE754 floating point arithmetic - * double precision: common utilities - */ -/* - * MIPS floating point support - * Copyright (C) 1994-2000 Algorithmics Ltd. - * - * ######################################################################## - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - */ - - -#include "ieee754dp.h" - -ieee754dp ieee754dp_logb(ieee754dp x) -{ - COMPXDP; - - CLEARCX; - - EXPLODEXDP; - - switch (xc) { - case IEEE754_CLASS_SNAN: - return ieee754dp_nanxcpt(x, "logb", x); - case IEEE754_CLASS_QNAN: - return x; - case IEEE754_CLASS_INF: - return ieee754dp_inf(0); - case IEEE754_CLASS_ZERO: - return ieee754dp_inf(1); - case IEEE754_CLASS_DNORM: - DPDNORMX; - break; - case IEEE754_CLASS_NORM: - break; - } - return ieee754dp_fint(xe); -} diff --git a/arch/mips/math-emu/dp_modf.c b/arch/mips/math-emu/dp_modf.c deleted file mode 100644 index b01f9cf6d402..000000000000 --- a/arch/mips/math-emu/dp_modf.c +++ /dev/null @@ -1,79 +0,0 @@ -/* IEEE754 floating point arithmetic - * double precision: common utilities - */ -/* - * MIPS floating point support - * Copyright (C) 1994-2000 Algorithmics Ltd. - * - * ######################################################################## - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - */ - - -#include "ieee754dp.h" - -/* modf function is always exact for a finite number -*/ -ieee754dp ieee754dp_modf(ieee754dp x, ieee754dp *ip) -{ - COMPXDP; - - CLEARCX; - - EXPLODEXDP; - - switch (xc) { - case IEEE754_CLASS_SNAN: - case IEEE754_CLASS_QNAN: - case IEEE754_CLASS_INF: - case IEEE754_CLASS_ZERO: - *ip = x; - return x; - case IEEE754_CLASS_DNORM: - /* far to small */ - *ip = ieee754dp_zero(xs); - return x; - case IEEE754_CLASS_NORM: - break; - } - if (xe < 0) { - *ip = ieee754dp_zero(xs); - return x; - } - if (xe >= DP_MBITS) { - *ip = x; - return ieee754dp_zero(xs); - } - /* generate ipart mantissa by clearing bottom bits - */ - *ip = builddp(xs, xe + DP_EBIAS, - ((xm >> (DP_MBITS - xe)) << (DP_MBITS - xe)) & - ~DP_HIDDEN_BIT); - - /* generate fpart mantissa by clearing top bits - * and normalizing (must be able to normalize) - */ - xm = (xm << (64 - (DP_MBITS - xe))) >> (64 - (DP_MBITS - xe)); - if (xm == 0) - return ieee754dp_zero(xs); - - while ((xm >> DP_MBITS) == 0) { - xm <<= 1; - xe--; - } - return builddp(xs, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT); -} diff --git a/arch/mips/math-emu/dp_mul.c b/arch/mips/math-emu/dp_mul.c index 09175f461920..d3acdedb5b9d 100644 --- a/arch/mips/math-emu/dp_mul.c +++ b/arch/mips/math-emu/dp_mul.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,23 +16,32 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754dp.h" -ieee754dp ieee754dp_mul(ieee754dp x, ieee754dp y) +union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y) { + int re; + int rs; + u64 rm; + unsigned lxm; + unsigned hxm; + unsigned lym; + unsigned hym; + u64 lrm; + u64 hrm; + u64 t; + u64 at; + COMPXDP; COMPYDP; EXPLODEXDP; EXPLODEYDP; - CLEARCX; + ieee754_clearcx(); FLUSHXDP; FLUSHYDP; @@ -51,8 +58,8 @@ ieee754dp ieee754dp_mul(ieee754dp x, ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_nanxcpt(ieee754dp_indef(), "mul", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_nanxcpt(ieee754dp_indef()); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): @@ -68,12 +75,13 @@ ieee754dp ieee754dp_mul(ieee754dp x, ieee754dp y) return x; - /* Infinity handling */ - + /* + * Infinity handling + */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_xcpt(ieee754dp_indef(), "mul", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_indef(); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): @@ -107,70 +115,59 @@ ieee754dp ieee754dp_mul(ieee754dp x, ieee754dp y) /* rm = xm * ym, re = xe+ye basically */ assert(xm & DP_HIDDEN_BIT); assert(ym & DP_HIDDEN_BIT); - { - int re = xe + ye; - int rs = xs ^ ys; - u64 rm; - /* shunt to top of word */ - xm <<= 64 - (DP_MBITS + 1); - ym <<= 64 - (DP_MBITS + 1); + re = xe + ye; + rs = xs ^ ys; + + /* shunt to top of word */ + xm <<= 64 - (DP_FBITS + 1); + ym <<= 64 - (DP_FBITS + 1); - /* multiply 32bits xm,ym to give high 32bits rm with stickness - */ + /* + * Multiply 32 bits xm, ym to give high 32 bits rm with stickness. + */ - /* 32 * 32 => 64 */ + /* 32 * 32 => 64 */ #define DPXMULT(x, y) ((u64)(x) * (u64)y) - { - unsigned lxm = xm; - unsigned hxm = xm >> 32; - unsigned lym = ym; - unsigned hym = ym >> 32; - u64 lrm; - u64 hrm; - - lrm = DPXMULT(lxm, lym); - hrm = DPXMULT(hxm, hym); - - { - u64 t = DPXMULT(lxm, hym); - { - u64 at = - lrm + (t << 32); - hrm += at < lrm; - lrm = at; - } - hrm = hrm + (t >> 32); - } - - { - u64 t = DPXMULT(hxm, lym); - { - u64 at = - lrm + (t << 32); - hrm += at < lrm; - lrm = at; - } - hrm = hrm + (t >> 32); - } - rm = hrm | (lrm != 0); - } - - /* - * sticky shift down to normal rounding precision - */ - if ((s64) rm < 0) { - rm = - (rm >> (64 - (DP_MBITS + 1 + 3))) | - ((rm << (DP_MBITS + 1 + 3)) != 0); + lxm = xm; + hxm = xm >> 32; + lym = ym; + hym = ym >> 32; + + lrm = DPXMULT(lxm, lym); + hrm = DPXMULT(hxm, hym); + + t = DPXMULT(lxm, hym); + + at = lrm + (t << 32); + hrm += at < lrm; + lrm = at; + + hrm = hrm + (t >> 32); + + t = DPXMULT(hxm, lym); + + at = lrm + (t << 32); + hrm += at < lrm; + lrm = at; + + hrm = hrm + (t >> 32); + + rm = hrm | (lrm != 0); + + /* + * Sticky shift down to normal rounding precision. + */ + if ((s64) rm < 0) { + rm = (rm >> (64 - (DP_FBITS + 1 + 3))) | + ((rm << (DP_FBITS + 1 + 3)) != 0); re++; - } else { - rm = - (rm >> (64 - (DP_MBITS + 1 + 3 + 1))) | - ((rm << (DP_MBITS + 1 + 3 + 1)) != 0); - } - assert(rm & (DP_HIDDEN_BIT << 3)); - DPNORMRET2(rs, re, rm, "mul", x, y); + } else { + rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) | + ((rm << (DP_FBITS + 1 + 3 + 1)) != 0); } + assert(rm & (DP_HIDDEN_BIT << 3)); + + return ieee754dp_format(rs, re, rm); } diff --git a/arch/mips/math-emu/dp_scalb.c b/arch/mips/math-emu/dp_scalb.c deleted file mode 100644 index 6f5df438dda8..000000000000 --- a/arch/mips/math-emu/dp_scalb.c +++ /dev/null @@ -1,57 +0,0 @@ -/* IEEE754 floating point arithmetic - * double precision: common utilities - */ -/* - * MIPS floating point support - * Copyright (C) 1994-2000 Algorithmics Ltd. - * - * ######################################################################## - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - */ - - -#include "ieee754dp.h" - -ieee754dp ieee754dp_scalb(ieee754dp x, int n) -{ - COMPXDP; - - CLEARCX; - - EXPLODEXDP; - - switch (xc) { - case IEEE754_CLASS_SNAN: - return ieee754dp_nanxcpt(x, "scalb", x, n); - case IEEE754_CLASS_QNAN: - case IEEE754_CLASS_INF: - case IEEE754_CLASS_ZERO: - return x; - case IEEE754_CLASS_DNORM: - DPDNORMX; - break; - case IEEE754_CLASS_NORM: - break; - } - DPNORMRET2(xs, xe + n, xm << 3, "scalb", x, n); -} - - -ieee754dp ieee754dp_ldexp(ieee754dp x, int n) -{ - return ieee754dp_scalb(x, n); -} diff --git a/arch/mips/math-emu/dp_simple.c b/arch/mips/math-emu/dp_simple.c index 79ce2673a714..bccbe90efceb 100644 --- a/arch/mips/math-emu/dp_simple.c +++ b/arch/mips/math-emu/dp_simple.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,33 +16,17 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754dp.h" -int ieee754dp_finite(ieee754dp x) -{ - return DPBEXP(x) != DP_EMAX + 1 + DP_EBIAS; -} - -ieee754dp ieee754dp_copysign(ieee754dp x, ieee754dp y) -{ - CLEARCX; - DPSIGN(x) = DPSIGN(y); - return x; -} - - -ieee754dp ieee754dp_neg(ieee754dp x) +union ieee754dp ieee754dp_neg(union ieee754dp x) { COMPXDP; EXPLODEXDP; - CLEARCX; + ieee754_clearcx(); FLUSHXDP; /* @@ -55,30 +37,29 @@ ieee754dp ieee754dp_neg(ieee754dp x) DPSIGN(x) ^= 1; if (xc == IEEE754_CLASS_SNAN) { - ieee754dp y = ieee754dp_indef(); - SETCX(IEEE754_INVALID_OPERATION); + union ieee754dp y = ieee754dp_indef(); + ieee754_setcx(IEEE754_INVALID_OPERATION); DPSIGN(y) = DPSIGN(x); - return ieee754dp_nanxcpt(y, "neg"); + return ieee754dp_nanxcpt(y); } return x; } - -ieee754dp ieee754dp_abs(ieee754dp x) +union ieee754dp ieee754dp_abs(union ieee754dp x) { COMPXDP; EXPLODEXDP; - CLEARCX; + ieee754_clearcx(); FLUSHXDP; /* Clear sign ALWAYS, irrespective of NaN */ DPSIGN(x) = 0; if (xc == IEEE754_CLASS_SNAN) { - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_nanxcpt(ieee754dp_indef(), "abs"); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_nanxcpt(ieee754dp_indef()); } return x; diff --git a/arch/mips/math-emu/dp_sqrt.c b/arch/mips/math-emu/dp_sqrt.c index b874d60a942b..041bbb6124bb 100644 --- a/arch/mips/math-emu/dp_sqrt.c +++ b/arch/mips/math-emu/dp_sqrt.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,12 +16,9 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754dp.h" static const unsigned table[] = { @@ -34,44 +29,49 @@ static const unsigned table[] = { 1742, 661, 130 }; -ieee754dp ieee754dp_sqrt(ieee754dp x) +union ieee754dp ieee754dp_sqrt(union ieee754dp x) { struct _ieee754_csr oldcsr; - ieee754dp y, z, t; + union ieee754dp y, z, t; unsigned scalx, yh; COMPXDP; EXPLODEXDP; - CLEARCX; + ieee754_clearcx(); FLUSHXDP; /* x == INF or NAN? */ switch (xc) { case IEEE754_CLASS_QNAN: /* sqrt(Nan) = Nan */ - return ieee754dp_nanxcpt(x, "sqrt"); + return ieee754dp_nanxcpt(x); + case IEEE754_CLASS_SNAN: - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_nanxcpt(ieee754dp_indef(), "sqrt"); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_nanxcpt(ieee754dp_indef()); + case IEEE754_CLASS_ZERO: /* sqrt(0) = 0 */ return x; + case IEEE754_CLASS_INF: if (xs) { /* sqrt(-Inf) = Nan */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_nanxcpt(ieee754dp_indef(), "sqrt"); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_nanxcpt(ieee754dp_indef()); } /* sqrt(+Inf) = Inf */ return x; + case IEEE754_CLASS_DNORM: DPDNORMX; /* fall through */ + case IEEE754_CLASS_NORM: if (xs) { /* sqrt(-x) = Nan */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_nanxcpt(ieee754dp_indef(), "sqrt"); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_nanxcpt(ieee754dp_indef()); } break; } @@ -80,7 +80,7 @@ ieee754dp ieee754dp_sqrt(ieee754dp x) oldcsr = ieee754_csr; ieee754_csr.mx &= ~IEEE754_INEXACT; ieee754_csr.sx &= ~IEEE754_INEXACT; - ieee754_csr.rm = IEEE754_RN; + ieee754_csr.rm = FPU_CSR_RN; /* adjust exponent to prevent overflow */ scalx = 0; @@ -110,19 +110,19 @@ ieee754dp ieee754dp_sqrt(ieee754dp x) /* triple to almost 56 sig. bits: y ~= sqrt(x) to within 1 ulp */ /* t=y*y; z=t; pt[n0]+=0x00100000; t+=z; z=(x-z)*y; */ z = t = ieee754dp_mul(y, y); - t.parts.bexp += 0x001; + t.bexp += 0x001; t = ieee754dp_add(t, z); z = ieee754dp_mul(ieee754dp_sub(x, z), y); /* t=z/(t+x) ; pt[n0]+=0x00100000; y+=t; */ t = ieee754dp_div(z, ieee754dp_add(t, x)); - t.parts.bexp += 0x001; + t.bexp += 0x001; y = ieee754dp_add(y, t); /* twiddle last bit to force y correctly rounded */ /* set RZ, clear INEX flag */ - ieee754_csr.rm = IEEE754_RZ; + ieee754_csr.rm = FPU_CSR_RZ; ieee754_csr.sx &= ~IEEE754_INEXACT; /* t=x/y; ...chopped quotient, possibly inexact */ @@ -139,10 +139,10 @@ ieee754dp ieee754dp_sqrt(ieee754dp x) oldcsr.sx |= IEEE754_INEXACT; switch (oldcsr.rm) { - case IEEE754_RP: + case FPU_CSR_RU: y.bits += 1; /* drop through */ - case IEEE754_RN: + case FPU_CSR_RN: t.bits += 1; break; } @@ -155,7 +155,7 @@ ieee754dp ieee754dp_sqrt(ieee754dp x) } /* py[n0]=py[n0]+scalx; ...scale back y */ - y.parts.bexp += scalx; + y.bexp += scalx; /* restore rounding mode, possibly set inexact */ ieee754_csr = oldcsr; diff --git a/arch/mips/math-emu/dp_sub.c b/arch/mips/math-emu/dp_sub.c index 91e0a4b5cbc7..7a174029043a 100644 --- a/arch/mips/math-emu/dp_sub.c +++ b/arch/mips/math-emu/dp_sub.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,23 +16,22 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754dp.h" -ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y) +union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y) { + int s; + COMPXDP; COMPYDP; EXPLODEXDP; EXPLODEYDP; - CLEARCX; + ieee754_clearcx(); FLUSHXDP; FLUSHYDP; @@ -51,8 +48,8 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_nanxcpt(ieee754dp_indef(), "sub", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_nanxcpt(ieee754dp_indef()); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): @@ -68,14 +65,14 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y) return x; - /* Infinity handling - */ - + /* + * Infinity handling + */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): if (xs != ys) return x; - SETCX(IEEE754_INVALID_OPERATION); - return ieee754dp_xcpt(ieee754dp_indef(), "sub", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_indef(); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): @@ -87,15 +84,14 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y) case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): return x; - /* Zero handling - */ - + /* + * Zero handling + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): if (xs != ys) return x; else - return ieee754dp_zero(ieee754_csr.rm == - IEEE754_RD); + return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): @@ -136,15 +132,17 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y) ym <<= 3; if (xe > ye) { - /* have to shift y fraction right to align + /* + * Have to shift y fraction right to align */ - int s = xe - ye; + s = xe - ye; ym = XDPSRS(ym, s); ye += s; } else if (ye > xe) { - /* have to shift x fraction right to align + /* + * Have to shift x fraction right to align */ - int s = ye - xe; + s = ye - xe; xm = XDPSRS(xm, s); xe += s; } @@ -158,7 +156,7 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y) xe = xe; xs = xs; - if (xm >> (DP_MBITS + 1 + 3)) { /* carry out */ + if (xm >> (DP_FBITS + 1 + 3)) { /* carry out */ xm = XDPSRS1(xm); /* shift preserving sticky */ xe++; } @@ -173,7 +171,7 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y) xs = ys; } if (xm == 0) { - if (ieee754_csr.rm == IEEE754_RD) + if (ieee754_csr.rm == FPU_CSR_RD) return ieee754dp_zero(1); /* round negative inf. => sign = -1 */ else return ieee754dp_zero(0); /* other round modes => sign = 1 */ @@ -181,10 +179,11 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y) /* normalize to rounding precision */ - while ((xm >> (DP_MBITS + 3)) == 0) { + while ((xm >> (DP_FBITS + 3)) == 0) { xm <<= 1; xe--; } } - DPNORMRET2(xs, xe, xm, "sub", x, y); + + return ieee754dp_format(xs, xe, xm); } diff --git a/arch/mips/math-emu/dp_tint.c b/arch/mips/math-emu/dp_tint.c index 0ebe8598b94a..6ffc336c530e 100644 --- a/arch/mips/math-emu/dp_tint.c +++ b/arch/mips/math-emu/dp_tint.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,20 +16,21 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - -#include <linux/kernel.h> #include "ieee754dp.h" -int ieee754dp_tint(ieee754dp x) +int ieee754dp_tint(union ieee754dp x) { + u64 residue; + int round; + int sticky; + int odd; + COMPXDP; - CLEARCX; + ieee754_clearcx(); EXPLODEXDP; FLUSHXDP; @@ -40,10 +39,12 @@ int ieee754dp_tint(ieee754dp x) case IEEE754_CLASS_SNAN: case IEEE754_CLASS_QNAN: case IEEE754_CLASS_INF: - SETCX(IEEE754_INVALID_OPERATION); - return ieee754si_xcpt(ieee754si_indef(), "dp_tint", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754si_indef(); + case IEEE754_CLASS_ZERO: return 0; + case IEEE754_CLASS_DNORM: case IEEE754_CLASS_NORM: break; @@ -51,44 +52,39 @@ int ieee754dp_tint(ieee754dp x) if (xe > 31) { /* Set invalid. We will only use overflow for floating point overflow */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754si_xcpt(ieee754si_indef(), "dp_tint", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754si_indef(); } /* oh gawd */ - if (xe > DP_MBITS) { - xm <<= xe - DP_MBITS; - } else if (xe < DP_MBITS) { - u64 residue; - int round; - int sticky; - int odd; - + if (xe > DP_FBITS) { + xm <<= xe - DP_FBITS; + } else if (xe < DP_FBITS) { if (xe < -1) { residue = xm; round = 0; sticky = residue != 0; xm = 0; } else { - residue = xm << (64 - DP_MBITS + xe); + residue = xm << (64 - DP_FBITS + xe); round = (residue >> 63) != 0; sticky = (residue << 1) != 0; - xm >>= DP_MBITS - xe; + xm >>= DP_FBITS - xe; } /* Note: At this point upper 32 bits of xm are guaranteed to be zero */ odd = (xm & 0x1) != 0x0; switch (ieee754_csr.rm) { - case IEEE754_RN: + case FPU_CSR_RN: if (round && (sticky || odd)) xm++; break; - case IEEE754_RZ: + case FPU_CSR_RZ: break; - case IEEE754_RU: /* toward +Infinity */ + case FPU_CSR_RU: /* toward +Infinity */ if ((round || sticky) && !xs) xm++; break; - case IEEE754_RD: /* toward -Infinity */ + case FPU_CSR_RD: /* toward -Infinity */ if ((round || sticky) && xs) xm++; break; @@ -96,27 +92,14 @@ int ieee754dp_tint(ieee754dp x) /* look for valid corner case 0x80000000 */ if ((xm >> 31) != 0 && (xs == 0 || xm != 0x80000000)) { /* This can happen after rounding */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754si_xcpt(ieee754si_indef(), "dp_tint", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754si_indef(); } if (round || sticky) - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_INEXACT); } if (xs) return -xm; else return xm; } - - -unsigned int ieee754dp_tuns(ieee754dp x) -{ - ieee754dp hb = ieee754dp_1e31(); - - /* what if x < 0 ?? */ - if (ieee754dp_lt(x, hb)) - return (unsigned) ieee754dp_tint(x); - - return (unsigned) ieee754dp_tint(ieee754dp_sub(x, hb)) | - ((unsigned) 1 << 31); -} diff --git a/arch/mips/math-emu/dp_tlong.c b/arch/mips/math-emu/dp_tlong.c index 133ce2ba0012..9cdc145b75e0 100644 --- a/arch/mips/math-emu/dp_tlong.c +++ b/arch/mips/math-emu/dp_tlong.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,19 +16,21 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754dp.h" -s64 ieee754dp_tlong(ieee754dp x) +s64 ieee754dp_tlong(union ieee754dp x) { + u64 residue; + int round; + int sticky; + int odd; + COMPXDP; - CLEARCX; + ieee754_clearcx(); EXPLODEXDP; FLUSHXDP; @@ -39,10 +39,12 @@ s64 ieee754dp_tlong(ieee754dp x) case IEEE754_CLASS_SNAN: case IEEE754_CLASS_QNAN: case IEEE754_CLASS_INF: - SETCX(IEEE754_INVALID_OPERATION); - return ieee754di_xcpt(ieee754di_indef(), "dp_tlong", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754di_indef(); + case IEEE754_CLASS_ZERO: return 0; + case IEEE754_CLASS_DNORM: case IEEE754_CLASS_NORM: break; @@ -53,18 +55,13 @@ s64 ieee754dp_tlong(ieee754dp x) return -0x8000000000000000LL; /* Set invalid. We will only use overflow for floating point overflow */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754di_xcpt(ieee754di_indef(), "dp_tlong", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754di_indef(); } /* oh gawd */ - if (xe > DP_MBITS) { - xm <<= xe - DP_MBITS; - } else if (xe < DP_MBITS) { - u64 residue; - int round; - int sticky; - int odd; - + if (xe > DP_FBITS) { + xm <<= xe - DP_FBITS; + } else if (xe < DP_FBITS) { if (xe < -1) { residue = xm; round = 0; @@ -75,51 +72,38 @@ s64 ieee754dp_tlong(ieee754dp x) * so we do it in two steps. Be aware that xe * may be -1 */ residue = xm << (xe + 1); - residue <<= 63 - DP_MBITS; + residue <<= 63 - DP_FBITS; round = (residue >> 63) != 0; sticky = (residue << 1) != 0; - xm >>= DP_MBITS - xe; + xm >>= DP_FBITS - xe; } odd = (xm & 0x1) != 0x0; switch (ieee754_csr.rm) { - case IEEE754_RN: + case FPU_CSR_RN: if (round && (sticky || odd)) xm++; break; - case IEEE754_RZ: + case FPU_CSR_RZ: break; - case IEEE754_RU: /* toward +Infinity */ + case FPU_CSR_RU: /* toward +Infinity */ if ((round || sticky) && !xs) xm++; break; - case IEEE754_RD: /* toward -Infinity */ + case FPU_CSR_RD: /* toward -Infinity */ if ((round || sticky) && xs) xm++; break; } if ((xm >> 63) != 0) { /* This can happen after rounding */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754di_xcpt(ieee754di_indef(), "dp_tlong", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754di_indef(); } if (round || sticky) - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_INEXACT); } if (xs) return -xm; else return xm; } - - -u64 ieee754dp_tulong(ieee754dp x) -{ - ieee754dp hb = ieee754dp_1e63(); - - /* what if x < 0 ?? */ - if (ieee754dp_lt(x, hb)) - return (u64) ieee754dp_tlong(x); - - return (u64) ieee754dp_tlong(ieee754dp_sub(x, hb)) | - (1ULL << 63); -} diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c index 7ea622ab8dad..4f514f3724cb 100644 --- a/arch/mips/math-emu/dsemul.c +++ b/arch/mips/math-emu/dsemul.c @@ -1,30 +1,12 @@ -#include <linux/compiler.h> -#include <linux/mm.h> -#include <linux/signal.h> -#include <linux/smp.h> - -#include <asm/asm.h> -#include <asm/bootinfo.h> -#include <asm/byteorder.h> -#include <asm/cpu.h> -#include <asm/inst.h> -#include <asm/processor.h> -#include <asm/uaccess.h> #include <asm/branch.h> -#include <asm/mipsregs.h> #include <asm/cacheflush.h> - #include <asm/fpu_emulator.h> +#include <asm/inst.h> +#include <asm/mipsregs.h> +#include <asm/uaccess.h> #include "ieee754.h" -/* Strap kernel emulator for full MIPS IV emulation */ - -#ifdef __mips -#undef __mips -#endif -#define __mips 4 - /* * Emulate the arbritrary instruction ir at xcp->cp0_epc. Required when * we have to emulate the instruction in a COP1 branch delay slot. Do @@ -59,13 +41,11 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc) (ir == 0)) { /* NOP is easy */ regs->cp0_epc = cpc; - regs->cp0_cause &= ~CAUSEF_BD; + clear_delay_slot(regs); return 0; } -#ifdef DSEMUL_TRACE - printk("dsemul %lx %lx\n", regs->cp0_epc, cpc); -#endif + pr_debug("dsemul %lx %lx\n", regs->cp0_epc, cpc); /* * The strategy is to push the instruction onto the user stack @@ -167,9 +147,8 @@ int do_dsemulret(struct pt_regs *xcp) * emulating the branch delay instruction. */ -#ifdef DSEMUL_TRACE - printk("dsemulret\n"); -#endif + pr_debug("dsemulret\n"); + if (__get_user(epc, &fr->epc)) { /* Saved EPC */ /* This is not a good situation to be in */ force_sig(SIGBUS, current); diff --git a/arch/mips/math-emu/ieee754.c b/arch/mips/math-emu/ieee754.c index 0015cf1989da..53f1d2287084 100644 --- a/arch/mips/math-emu/ieee754.c +++ b/arch/mips/math-emu/ieee754.c @@ -10,8 +10,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -23,105 +21,69 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ +#include <linux/compiler.h> -#include "ieee754int.h" +#include "ieee754.h" #include "ieee754sp.h" #include "ieee754dp.h" -#define DP_EBIAS 1023 -#define DP_EMIN (-1022) -#define DP_EMAX 1023 - -#define SP_EBIAS 127 -#define SP_EMIN (-126) -#define SP_EMAX 127 - -/* special constants -*/ - - -#if (defined(BYTE_ORDER) && BYTE_ORDER == LITTLE_ENDIAN) || defined(__MIPSEL__) -#define SPSTR(s, b, m) {m, b, s} -#define DPSTR(s, b, mh, ml) {ml, mh, b, s} -#endif - -#ifdef __MIPSEB__ -#define SPSTR(s, b, m) {s, b, m} -#define DPSTR(s, b, mh, ml) {s, b, mh, ml} -#endif +/* + * Special constants + */ -const struct ieee754dp_konst __ieee754dp_spcvals[] = { - DPSTR(0, DP_EMIN - 1 + DP_EBIAS, 0, 0), /* + zero */ - DPSTR(1, DP_EMIN - 1 + DP_EBIAS, 0, 0), /* - zero */ - DPSTR(0, DP_EBIAS, 0, 0), /* + 1.0 */ - DPSTR(1, DP_EBIAS, 0, 0), /* - 1.0 */ - DPSTR(0, 3 + DP_EBIAS, 0x40000, 0), /* + 10.0 */ - DPSTR(1, 3 + DP_EBIAS, 0x40000, 0), /* - 10.0 */ - DPSTR(0, DP_EMAX + 1 + DP_EBIAS, 0, 0), /* + infinity */ - DPSTR(1, DP_EMAX + 1 + DP_EBIAS, 0, 0), /* - infinity */ - DPSTR(0, DP_EMAX+1+DP_EBIAS, 0x7FFFF, 0xFFFFFFFF), /* + indef quiet Nan */ - DPSTR(0, DP_EMAX + DP_EBIAS, 0xFFFFF, 0xFFFFFFFF), /* + max */ - DPSTR(1, DP_EMAX + DP_EBIAS, 0xFFFFF, 0xFFFFFFFF), /* - max */ - DPSTR(0, DP_EMIN + DP_EBIAS, 0, 0), /* + min normal */ - DPSTR(1, DP_EMIN + DP_EBIAS, 0, 0), /* - min normal */ - DPSTR(0, DP_EMIN - 1 + DP_EBIAS, 0, 1), /* + min denormal */ - DPSTR(1, DP_EMIN - 1 + DP_EBIAS, 0, 1), /* - min denormal */ - DPSTR(0, 31 + DP_EBIAS, 0, 0), /* + 1.0e31 */ - DPSTR(0, 63 + DP_EBIAS, 0, 0), /* + 1.0e63 */ -}; +#define DPCNST(s, b, m) \ +{ \ + .sign = (s), \ + .bexp = (b) + DP_EBIAS, \ + .mant = (m) \ +} -const struct ieee754sp_konst __ieee754sp_spcvals[] = { - SPSTR(0, SP_EMIN - 1 + SP_EBIAS, 0), /* + zero */ - SPSTR(1, SP_EMIN - 1 + SP_EBIAS, 0), /* - zero */ - SPSTR(0, SP_EBIAS, 0), /* + 1.0 */ - SPSTR(1, SP_EBIAS, 0), /* - 1.0 */ - SPSTR(0, 3 + SP_EBIAS, 0x200000), /* + 10.0 */ - SPSTR(1, 3 + SP_EBIAS, 0x200000), /* - 10.0 */ - SPSTR(0, SP_EMAX + 1 + SP_EBIAS, 0), /* + infinity */ - SPSTR(1, SP_EMAX + 1 + SP_EBIAS, 0), /* - infinity */ - SPSTR(0, SP_EMAX+1+SP_EBIAS, 0x3FFFFF), /* + indef quiet Nan */ - SPSTR(0, SP_EMAX + SP_EBIAS, 0x7FFFFF), /* + max normal */ - SPSTR(1, SP_EMAX + SP_EBIAS, 0x7FFFFF), /* - max normal */ - SPSTR(0, SP_EMIN + SP_EBIAS, 0), /* + min normal */ - SPSTR(1, SP_EMIN + SP_EBIAS, 0), /* - min normal */ - SPSTR(0, SP_EMIN - 1 + SP_EBIAS, 1), /* + min denormal */ - SPSTR(1, SP_EMIN - 1 + SP_EBIAS, 1), /* - min denormal */ - SPSTR(0, 31 + SP_EBIAS, 0), /* + 1.0e31 */ - SPSTR(0, 63 + SP_EBIAS, 0), /* + 1.0e63 */ +const union ieee754dp __ieee754dp_spcvals[] = { + DPCNST(0, DP_EMIN - 1, 0x0000000000000ULL), /* + zero */ + DPCNST(1, DP_EMIN - 1, 0x0000000000000ULL), /* - zero */ + DPCNST(0, 0, 0x0000000000000ULL), /* + 1.0 */ + DPCNST(1, 0, 0x0000000000000ULL), /* - 1.0 */ + DPCNST(0, 3, 0x4000000000000ULL), /* + 10.0 */ + DPCNST(1, 3, 0x4000000000000ULL), /* - 10.0 */ + DPCNST(0, DP_EMAX + 1, 0x0000000000000ULL), /* + infinity */ + DPCNST(1, DP_EMAX + 1, 0x0000000000000ULL), /* - infinity */ + DPCNST(0, DP_EMAX + 1, 0x7FFFFFFFFFFFFULL), /* + indef quiet Nan */ + DPCNST(0, DP_EMAX, 0xFFFFFFFFFFFFFULL), /* + max */ + DPCNST(1, DP_EMAX, 0xFFFFFFFFFFFFFULL), /* - max */ + DPCNST(0, DP_EMIN, 0x0000000000000ULL), /* + min normal */ + DPCNST(1, DP_EMIN, 0x0000000000000ULL), /* - min normal */ + DPCNST(0, DP_EMIN - 1, 0x0000000000001ULL), /* + min denormal */ + DPCNST(1, DP_EMIN - 1, 0x0000000000001ULL), /* - min denormal */ + DPCNST(0, 31, 0x0000000000000ULL), /* + 1.0e31 */ + DPCNST(0, 63, 0x0000000000000ULL), /* + 1.0e63 */ }; - -int ieee754si_xcpt(int r, const char *op, ...) -{ - struct ieee754xctx ax; - - if (!TSTX()) - return r; - ax.op = op; - ax.rt = IEEE754_RT_SI; - ax.rv.si = r; - va_start(ax.ap, op); - ieee754_xcpt(&ax); - va_end(ax.ap); - return ax.rv.si; +#define SPCNST(s, b, m) \ +{ \ + .sign = (s), \ + .bexp = (b) + SP_EBIAS, \ + .mant = (m) \ } -s64 ieee754di_xcpt(s64 r, const char *op, ...) -{ - struct ieee754xctx ax; - - if (!TSTX()) - return r; - ax.op = op; - ax.rt = IEEE754_RT_DI; - ax.rv.di = r; - va_start(ax.ap, op); - ieee754_xcpt(&ax); - va_end(ax.ap); - return ax.rv.di; -} +const union ieee754sp __ieee754sp_spcvals[] = { + SPCNST(0, SP_EMIN - 1, 0x000000), /* + zero */ + SPCNST(1, SP_EMIN - 1, 0x000000), /* - zero */ + SPCNST(0, 0, 0x000000), /* + 1.0 */ + SPCNST(1, 0, 0x000000), /* - 1.0 */ + SPCNST(0, 3, 0x200000), /* + 10.0 */ + SPCNST(1, 3, 0x200000), /* - 10.0 */ + SPCNST(0, SP_EMAX + 1, 0x000000), /* + infinity */ + SPCNST(1, SP_EMAX + 1, 0x000000), /* - infinity */ + SPCNST(0, SP_EMAX + 1, 0x3FFFFF), /* + indef quiet Nan */ + SPCNST(0, SP_EMAX, 0x7FFFFF), /* + max normal */ + SPCNST(1, SP_EMAX, 0x7FFFFF), /* - max normal */ + SPCNST(0, SP_EMIN, 0x000000), /* + min normal */ + SPCNST(1, SP_EMIN, 0x000000), /* - min normal */ + SPCNST(0, SP_EMIN - 1, 0x000001), /* + min denormal */ + SPCNST(1, SP_EMIN - 1, 0x000001), /* - min denormal */ + SPCNST(0, 31, 0x000000), /* + 1.0e31 */ + SPCNST(0, 63, 0x000000), /* + 1.0e63 */ +}; diff --git a/arch/mips/math-emu/ieee754.h b/arch/mips/math-emu/ieee754.h index 22796e012060..43c4fb522ac2 100644 --- a/arch/mips/math-emu/ieee754.h +++ b/arch/mips/math-emu/ieee754.h @@ -13,7 +13,7 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. * * Nov 7, 2000 * Modification to allow integration with Linux kernel @@ -24,186 +24,93 @@ #ifndef __ARCH_MIPS_MATH_EMU_IEEE754_H #define __ARCH_MIPS_MATH_EMU_IEEE754_H +#include <linux/compiler.h> #include <asm/byteorder.h> +#include <linux/kernel.h> #include <linux/types.h> #include <linux/sched.h> +#include <asm/bitfield.h> -/* - * Not very pretty, but the Linux kernel's normal va_list definition - * does not allow it to be used as a structure element, as it is here. - */ -#ifndef _STDARG_H -#include <stdarg.h> -#endif - -#ifdef __LITTLE_ENDIAN -struct ieee754dp_konst { - unsigned mantlo:32; - unsigned manthi:20; - unsigned bexp:11; - unsigned sign:1; -}; -struct ieee754sp_konst { - unsigned mant:23; - unsigned bexp:8; - unsigned sign:1; -}; - -typedef union _ieee754dp { - struct ieee754dp_konst oparts; +union ieee754dp { struct { - u64 mant:52; - unsigned int bexp:11; - unsigned int sign:1; - } parts; + __BITFIELD_FIELD(unsigned int sign:1, + __BITFIELD_FIELD(unsigned int bexp:11, + __BITFIELD_FIELD(u64 mant:52, + ;))) + }; u64 bits; - double d; -} ieee754dp; - -typedef union _ieee754sp { - struct ieee754sp_konst parts; - float f; - u32 bits; -} ieee754sp; -#endif - -#ifdef __BIG_ENDIAN -struct ieee754dp_konst { - unsigned sign:1; - unsigned bexp:11; - unsigned manthi:20; - unsigned mantlo:32; }; -typedef union _ieee754dp { - struct ieee754dp_konst oparts; +union ieee754sp { struct { - unsigned int sign:1; - unsigned int bexp:11; - u64 mant:52; - } parts; - double d; - u64 bits; -} ieee754dp; - -struct ieee754sp_konst { - unsigned sign:1; - unsigned bexp:8; - unsigned mant:23; -}; - -typedef union _ieee754sp { - struct ieee754sp_konst parts; - float f; + __BITFIELD_FIELD(unsigned sign:1, + __BITFIELD_FIELD(unsigned bexp:8, + __BITFIELD_FIELD(unsigned mant:23, + ;))) + }; u32 bits; -} ieee754sp; -#endif +}; /* * single precision (often aka float) */ -int ieee754sp_finite(ieee754sp x); -int ieee754sp_class(ieee754sp x); - -ieee754sp ieee754sp_abs(ieee754sp x); -ieee754sp ieee754sp_neg(ieee754sp x); -ieee754sp ieee754sp_scalb(ieee754sp x, int); -ieee754sp ieee754sp_logb(ieee754sp x); - -/* x with sign of y */ -ieee754sp ieee754sp_copysign(ieee754sp x, ieee754sp y); - -ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y); -ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y); -ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y); -ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y); - -ieee754sp ieee754sp_fint(int x); -ieee754sp ieee754sp_funs(unsigned x); -ieee754sp ieee754sp_flong(s64 x); -ieee754sp ieee754sp_fulong(u64 x); -ieee754sp ieee754sp_fdp(ieee754dp x); - -int ieee754sp_tint(ieee754sp x); -unsigned int ieee754sp_tuns(ieee754sp x); -s64 ieee754sp_tlong(ieee754sp x); -u64 ieee754sp_tulong(ieee754sp x); - -int ieee754sp_cmp(ieee754sp x, ieee754sp y, int cop, int sig); -/* - * basic sp math - */ -ieee754sp ieee754sp_modf(ieee754sp x, ieee754sp * ip); -ieee754sp ieee754sp_frexp(ieee754sp x, int *exp); -ieee754sp ieee754sp_ldexp(ieee754sp x, int exp); +int ieee754sp_class(union ieee754sp x); -ieee754sp ieee754sp_ceil(ieee754sp x); -ieee754sp ieee754sp_floor(ieee754sp x); -ieee754sp ieee754sp_trunc(ieee754sp x); +union ieee754sp ieee754sp_abs(union ieee754sp x); +union ieee754sp ieee754sp_neg(union ieee754sp x); -ieee754sp ieee754sp_sqrt(ieee754sp x); +union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y); +union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y); +union ieee754sp ieee754sp_mul(union ieee754sp x, union ieee754sp y); +union ieee754sp ieee754sp_div(union ieee754sp x, union ieee754sp y); -/* - * double precision (often aka double) -*/ -int ieee754dp_finite(ieee754dp x); -int ieee754dp_class(ieee754dp x); +union ieee754sp ieee754sp_fint(int x); +union ieee754sp ieee754sp_flong(s64 x); +union ieee754sp ieee754sp_fdp(union ieee754dp x); -/* x with sign of y */ -ieee754dp ieee754dp_copysign(ieee754dp x, ieee754dp y); +int ieee754sp_tint(union ieee754sp x); +s64 ieee754sp_tlong(union ieee754sp x); -ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y); -ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y); -ieee754dp ieee754dp_mul(ieee754dp x, ieee754dp y); -ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y); +int ieee754sp_cmp(union ieee754sp x, union ieee754sp y, int cop, int sig); -ieee754dp ieee754dp_abs(ieee754dp x); -ieee754dp ieee754dp_neg(ieee754dp x); -ieee754dp ieee754dp_scalb(ieee754dp x, int); +union ieee754sp ieee754sp_sqrt(union ieee754sp x); -/* return exponent as integer in floating point format - */ -ieee754dp ieee754dp_logb(ieee754dp x); +/* + * double precision (often aka double) +*/ +int ieee754dp_class(union ieee754dp x); -ieee754dp ieee754dp_fint(int x); -ieee754dp ieee754dp_funs(unsigned x); -ieee754dp ieee754dp_flong(s64 x); -ieee754dp ieee754dp_fulong(u64 x); -ieee754dp ieee754dp_fsp(ieee754sp x); +union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y); +union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y); +union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y); +union ieee754dp ieee754dp_div(union ieee754dp x, union ieee754dp y); -ieee754dp ieee754dp_ceil(ieee754dp x); -ieee754dp ieee754dp_floor(ieee754dp x); -ieee754dp ieee754dp_trunc(ieee754dp x); +union ieee754dp ieee754dp_abs(union ieee754dp x); +union ieee754dp ieee754dp_neg(union ieee754dp x); -int ieee754dp_tint(ieee754dp x); -unsigned int ieee754dp_tuns(ieee754dp x); -s64 ieee754dp_tlong(ieee754dp x); -u64 ieee754dp_tulong(ieee754dp x); +union ieee754dp ieee754dp_fint(int x); +union ieee754dp ieee754dp_flong(s64 x); +union ieee754dp ieee754dp_fsp(union ieee754sp x); -int ieee754dp_cmp(ieee754dp x, ieee754dp y, int cop, int sig); -/* - * basic sp math - */ -ieee754dp ieee754dp_modf(ieee754dp x, ieee754dp * ip); -ieee754dp ieee754dp_frexp(ieee754dp x, int *exp); -ieee754dp ieee754dp_ldexp(ieee754dp x, int exp); +int ieee754dp_tint(union ieee754dp x); +s64 ieee754dp_tlong(union ieee754dp x); -ieee754dp ieee754dp_ceil(ieee754dp x); -ieee754dp ieee754dp_floor(ieee754dp x); -ieee754dp ieee754dp_trunc(ieee754dp x); +int ieee754dp_cmp(union ieee754dp x, union ieee754dp y, int cop, int sig); -ieee754dp ieee754dp_sqrt(ieee754dp x); +union ieee754dp ieee754dp_sqrt(union ieee754dp x); /* 5 types of floating point number */ -#define IEEE754_CLASS_NORM 0x00 -#define IEEE754_CLASS_ZERO 0x01 -#define IEEE754_CLASS_DNORM 0x02 -#define IEEE754_CLASS_INF 0x03 -#define IEEE754_CLASS_SNAN 0x04 -#define IEEE754_CLASS_QNAN 0x05 +enum { + IEEE754_CLASS_NORM = 0x00, + IEEE754_CLASS_ZERO = 0x01, + IEEE754_CLASS_DNORM = 0x02, + IEEE754_CLASS_INF = 0x03, + IEEE754_CLASS_SNAN = 0x04, + IEEE754_CLASS_QNAN = 0x05, +}; /* exception numbers */ #define IEEE754_INEXACT 0x01 @@ -219,114 +126,84 @@ ieee754dp ieee754dp_sqrt(ieee754dp x); #define IEEE754_CGT 0x04 #define IEEE754_CUN 0x08 -/* rounding mode -*/ -#define IEEE754_RN 0 /* round to nearest */ -#define IEEE754_RZ 1 /* round toward zero */ -#define IEEE754_RD 2 /* round toward -Infinity */ -#define IEEE754_RU 3 /* round toward +Infinity */ - -/* other naming */ -#define IEEE754_RM IEEE754_RD -#define IEEE754_RP IEEE754_RU - /* "normal" comparisons */ -static inline int ieee754sp_eq(ieee754sp x, ieee754sp y) +static inline int ieee754sp_eq(union ieee754sp x, union ieee754sp y) { return ieee754sp_cmp(x, y, IEEE754_CEQ, 0); } -static inline int ieee754sp_ne(ieee754sp x, ieee754sp y) +static inline int ieee754sp_ne(union ieee754sp x, union ieee754sp y) { return ieee754sp_cmp(x, y, IEEE754_CLT | IEEE754_CGT | IEEE754_CUN, 0); } -static inline int ieee754sp_lt(ieee754sp x, ieee754sp y) +static inline int ieee754sp_lt(union ieee754sp x, union ieee754sp y) { return ieee754sp_cmp(x, y, IEEE754_CLT, 0); } -static inline int ieee754sp_le(ieee754sp x, ieee754sp y) +static inline int ieee754sp_le(union ieee754sp x, union ieee754sp y) { return ieee754sp_cmp(x, y, IEEE754_CLT | IEEE754_CEQ, 0); } -static inline int ieee754sp_gt(ieee754sp x, ieee754sp y) +static inline int ieee754sp_gt(union ieee754sp x, union ieee754sp y) { return ieee754sp_cmp(x, y, IEEE754_CGT, 0); } -static inline int ieee754sp_ge(ieee754sp x, ieee754sp y) +static inline int ieee754sp_ge(union ieee754sp x, union ieee754sp y) { return ieee754sp_cmp(x, y, IEEE754_CGT | IEEE754_CEQ, 0); } -static inline int ieee754dp_eq(ieee754dp x, ieee754dp y) +static inline int ieee754dp_eq(union ieee754dp x, union ieee754dp y) { return ieee754dp_cmp(x, y, IEEE754_CEQ, 0); } -static inline int ieee754dp_ne(ieee754dp x, ieee754dp y) +static inline int ieee754dp_ne(union ieee754dp x, union ieee754dp y) { return ieee754dp_cmp(x, y, IEEE754_CLT | IEEE754_CGT | IEEE754_CUN, 0); } -static inline int ieee754dp_lt(ieee754dp x, ieee754dp y) +static inline int ieee754dp_lt(union ieee754dp x, union ieee754dp y) { return ieee754dp_cmp(x, y, IEEE754_CLT, 0); } -static inline int ieee754dp_le(ieee754dp x, ieee754dp y) +static inline int ieee754dp_le(union ieee754dp x, union ieee754dp y) { return ieee754dp_cmp(x, y, IEEE754_CLT | IEEE754_CEQ, 0); } -static inline int ieee754dp_gt(ieee754dp x, ieee754dp y) +static inline int ieee754dp_gt(union ieee754dp x, union ieee754dp y) { return ieee754dp_cmp(x, y, IEEE754_CGT, 0); } -static inline int ieee754dp_ge(ieee754dp x, ieee754dp y) +static inline int ieee754dp_ge(union ieee754dp x, union ieee754dp y) { return ieee754dp_cmp(x, y, IEEE754_CGT | IEEE754_CEQ, 0); } - -/* - * Like strtod - */ -ieee754dp ieee754dp_fstr(const char *s, char **endp); -char *ieee754dp_tstr(ieee754dp x, int prec, int fmt, int af); - - /* * The control status register */ struct _ieee754_csr { -#ifdef __BIG_ENDIAN - unsigned pad0:7; - unsigned nod:1; /* set 1 for no denormalised numbers */ - unsigned c:1; /* condition */ - unsigned pad1:5; - unsigned cx:6; /* exceptions this operation */ - unsigned mx:5; /* exception enable mask */ - unsigned sx:5; /* exceptions total */ - unsigned rm:2; /* current rounding mode */ -#endif -#ifdef __LITTLE_ENDIAN - unsigned rm:2; /* current rounding mode */ - unsigned sx:5; /* exceptions total */ - unsigned mx:5; /* exception enable mask */ - unsigned cx:6; /* exceptions this operation */ - unsigned pad1:5; - unsigned c:1; /* condition */ - unsigned nod:1; /* set 1 for no denormalised numbers */ - unsigned pad0:7; -#endif + __BITFIELD_FIELD(unsigned pad0:7, + __BITFIELD_FIELD(unsigned nod:1, /* set 1 for no denormalised numbers */ + __BITFIELD_FIELD(unsigned c:1, /* condition */ + __BITFIELD_FIELD(unsigned pad1:5, + __BITFIELD_FIELD(unsigned cx:6, /* exceptions this operation */ + __BITFIELD_FIELD(unsigned mx:5, /* exception enable mask */ + __BITFIELD_FIELD(unsigned sx:5, /* exceptions total */ + __BITFIELD_FIELD(unsigned rm:2, /* current rounding mode */ + ;)))))))) }; #define ieee754_csr (*(struct _ieee754_csr *)(¤t->thread.fpu.fcr31)) @@ -377,8 +254,8 @@ static inline int ieee754_sxtest(unsigned n) } /* debugging */ -ieee754sp ieee754sp_dump(char *s, ieee754sp x); -ieee754dp ieee754dp_dump(char *s, ieee754dp x); +union ieee754sp ieee754sp_dump(char *s, union ieee754sp x); +union ieee754dp ieee754dp_dump(char *s, union ieee754dp x); #define IEEE754_SPCVAL_PZERO 0 #define IEEE754_SPCVAL_NZERO 1 @@ -398,10 +275,10 @@ ieee754dp ieee754dp_dump(char *s, ieee754dp x); #define IEEE754_SPCVAL_P1E31 15 /* + 1.0e31 */ #define IEEE754_SPCVAL_P1E63 16 /* + 1.0e63 */ -extern const struct ieee754dp_konst __ieee754dp_spcvals[]; -extern const struct ieee754sp_konst __ieee754sp_spcvals[]; -#define ieee754dp_spcvals ((const ieee754dp *)__ieee754dp_spcvals) -#define ieee754sp_spcvals ((const ieee754sp *)__ieee754sp_spcvals) +extern const union ieee754dp __ieee754dp_spcvals[]; +extern const union ieee754sp __ieee754sp_spcvals[]; +#define ieee754dp_spcvals ((const union ieee754dp *)__ieee754dp_spcvals) +#define ieee754sp_spcvals ((const union ieee754sp *)__ieee754sp_spcvals) /* * Return infinity with given sign @@ -431,28 +308,15 @@ extern const struct ieee754sp_konst __ieee754sp_spcvals[]; /* * Indefinite integer value */ -#define ieee754si_indef() INT_MAX -#ifdef LONG_LONG_MAX -#define ieee754di_indef() LONG_LONG_MAX -#else -#define ieee754di_indef() ((s64)(~0ULL>>1)) -#endif - -/* IEEE exception context, passed to handler */ -struct ieee754xctx { - const char *op; /* operation name */ - int rt; /* result type */ - union { - ieee754sp sp; /* single precision */ - ieee754dp dp; /* double precision */ -#ifdef IEEE854_XP - ieee754xp xp; /* extended precision */ -#endif - int si; /* standard signed integer (32bits) */ - s64 di; /* extended signed integer (64bits) */ - } rv; /* default result format implied by op */ - va_list ap; -}; +static inline int ieee754si_indef(void) +{ + return INT_MAX; +} + +static inline s64 ieee754di_indef(void) +{ + return S64_MAX; +} /* result types for xctx.rt */ #define IEEE754_RT_SP 0 @@ -461,8 +325,6 @@ struct ieee754xctx { #define IEEE754_RT_SI 3 #define IEEE754_RT_DI 4 -extern void ieee754_xcpt(struct ieee754xctx *xcp); - /* compat */ #define ieee754dp_fix(x) ieee754dp_tint(x) #define ieee754sp_fix(x) ieee754sp_tint(x) diff --git a/arch/mips/math-emu/ieee754d.c b/arch/mips/math-emu/ieee754d.c index 9599bdd32585..a04e8a7e5ac3 100644 --- a/arch/mips/math-emu/ieee754d.c +++ b/arch/mips/math-emu/ieee754d.c @@ -16,7 +16,7 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. * * Nov 7, 2000 * Modified to build and operate in Linux kernel environment. @@ -25,38 +25,13 @@ * Copyright (C) 2000 MIPS Technologies, Inc. All rights reserved. */ -#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/printk.h> #include "ieee754.h" +#include "ieee754sp.h" +#include "ieee754dp.h" -#define DP_EBIAS 1023 -#define DP_EMIN (-1022) -#define DP_EMAX 1023 -#define DP_FBITS 52 - -#define SP_EBIAS 127 -#define SP_EMIN (-126) -#define SP_EMAX 127 -#define SP_FBITS 23 - -#define DP_MBIT(x) ((u64)1 << (x)) -#define DP_HIDDEN_BIT DP_MBIT(DP_FBITS) -#define DP_SIGN_BIT DP_MBIT(63) - - -#define SP_MBIT(x) ((u32)1 << (x)) -#define SP_HIDDEN_BIT SP_MBIT(SP_FBITS) -#define SP_SIGN_BIT SP_MBIT(31) - - -#define SPSIGN(sp) (sp.parts.sign) -#define SPBEXP(sp) (sp.parts.bexp) -#define SPMANT(sp) (sp.parts.mant) - -#define DPSIGN(dp) (dp.parts.sign) -#define DPBEXP(dp) (dp.parts.bexp) -#define DPMANT(dp) (dp.parts.mant) - -ieee754dp ieee754dp_dump(char *m, ieee754dp x) +union ieee754dp ieee754dp_dump(char *m, union ieee754dp x) { int i; @@ -96,7 +71,7 @@ ieee754dp ieee754dp_dump(char *m, ieee754dp x) return x; } -ieee754sp ieee754sp_dump(char *m, ieee754sp x) +union ieee754sp ieee754sp_dump(char *m, union ieee754sp x) { int i; diff --git a/arch/mips/math-emu/ieee754dp.c b/arch/mips/math-emu/ieee754dp.c index 068e56be8de9..fd134675fc2e 100644 --- a/arch/mips/math-emu/ieee754dp.c +++ b/arch/mips/math-emu/ieee754dp.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,104 +16,68 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ +#include <linux/compiler.h> #include "ieee754dp.h" -int ieee754dp_class(ieee754dp x) +int ieee754dp_class(union ieee754dp x) { COMPXDP; EXPLODEXDP; return xc; } -int ieee754dp_isnan(ieee754dp x) +int ieee754dp_isnan(union ieee754dp x) { return ieee754dp_class(x) >= IEEE754_CLASS_SNAN; } -int ieee754dp_issnan(ieee754dp x) +static inline int ieee754dp_issnan(union ieee754dp x) { assert(ieee754dp_isnan(x)); - return ((DPMANT(x) & DP_MBIT(DP_MBITS-1)) == DP_MBIT(DP_MBITS-1)); + return ((DPMANT(x) & DP_MBIT(DP_FBITS-1)) == DP_MBIT(DP_FBITS-1)); } -ieee754dp ieee754dp_xcpt(ieee754dp r, const char *op, ...) -{ - struct ieee754xctx ax; - if (!TSTX()) - return r; - - ax.op = op; - ax.rt = IEEE754_RT_DP; - ax.rv.dp = r; - va_start(ax.ap, op); - ieee754_xcpt(&ax); - va_end(ax.ap); - return ax.rv.dp; -} - -ieee754dp ieee754dp_nanxcpt(ieee754dp r, const char *op, ...) +union ieee754dp __cold ieee754dp_nanxcpt(union ieee754dp r) { - struct ieee754xctx ax; - assert(ieee754dp_isnan(r)); if (!ieee754dp_issnan(r)) /* QNAN does not cause invalid op !! */ return r; - if (!SETANDTESTCX(IEEE754_INVALID_OPERATION)) { + if (!ieee754_setandtestcx(IEEE754_INVALID_OPERATION)) { /* not enabled convert to a quiet NaN */ - DPMANT(r) &= (~DP_MBIT(DP_MBITS-1)); + DPMANT(r) &= (~DP_MBIT(DP_FBITS-1)); if (ieee754dp_isnan(r)) return r; else return ieee754dp_indef(); } - ax.op = op; - ax.rt = 0; - ax.rv.dp = r; - va_start(ax.ap, op); - ieee754_xcpt(&ax); - va_end(ax.ap); - return ax.rv.dp; + return r; } -ieee754dp ieee754dp_bestnan(ieee754dp x, ieee754dp y) -{ - assert(ieee754dp_isnan(x)); - assert(ieee754dp_isnan(y)); - - if (DPMANT(x) > DPMANT(y)) - return x; - else - return y; -} - - -static u64 get_rounding(int sn, u64 xm) +static u64 ieee754dp_get_rounding(int sn, u64 xm) { /* inexact must round of 3 bits */ if (xm & (DP_MBIT(3) - 1)) { switch (ieee754_csr.rm) { - case IEEE754_RZ: + case FPU_CSR_RZ: break; - case IEEE754_RN: + case FPU_CSR_RN: xm += 0x3 + ((xm >> 3) & 1); /* xm += (xm&0x8)?0x4:0x3 */ break; - case IEEE754_RU: /* toward +Infinity */ + case FPU_CSR_RU: /* toward +Infinity */ if (!sn) /* ?? */ xm += 0x8; break; - case IEEE754_RD: /* toward -Infinity */ + case FPU_CSR_RD: /* toward -Infinity */ if (sn) /* ?? */ xm += 0x8; break; @@ -130,11 +92,11 @@ static u64 get_rounding(int sn, u64 xm) * xe is an unbiased exponent * xm is 3bit extended precision value. */ -ieee754dp ieee754dp_format(int sn, int xe, u64 xm) +union ieee754dp ieee754dp_format(int sn, int xe, u64 xm) { assert(xm); /* we don't gen exact zeros (probably should) */ - assert((xm >> (DP_MBITS + 1 + 3)) == 0); /* no execess */ + assert((xm >> (DP_FBITS + 1 + 3)) == 0); /* no execess */ assert(xm & (DP_HIDDEN_BIT << 3)); if (xe < DP_EMIN) { @@ -142,32 +104,32 @@ ieee754dp ieee754dp_format(int sn, int xe, u64 xm) int es = DP_EMIN - xe; if (ieee754_csr.nod) { - SETCX(IEEE754_UNDERFLOW); - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_UNDERFLOW); + ieee754_setcx(IEEE754_INEXACT); switch(ieee754_csr.rm) { - case IEEE754_RN: - case IEEE754_RZ: + case FPU_CSR_RN: + case FPU_CSR_RZ: return ieee754dp_zero(sn); - case IEEE754_RU: /* toward +Infinity */ - if(sn == 0) + case FPU_CSR_RU: /* toward +Infinity */ + if (sn == 0) return ieee754dp_min(0); else return ieee754dp_zero(1); - case IEEE754_RD: /* toward -Infinity */ - if(sn == 0) + case FPU_CSR_RD: /* toward -Infinity */ + if (sn == 0) return ieee754dp_zero(0); else return ieee754dp_min(1); } } - if (xe == DP_EMIN - 1 - && get_rounding(sn, xm) >> (DP_MBITS + 1 + 3)) + if (xe == DP_EMIN - 1 && + ieee754dp_get_rounding(sn, xm) >> (DP_FBITS + 1 + 3)) { /* Not tiny after rounding */ - SETCX(IEEE754_INEXACT); - xm = get_rounding(sn, xm); + ieee754_setcx(IEEE754_INEXACT); + xm = ieee754dp_get_rounding(sn, xm); xm >>= 1; /* Clear grs bits */ xm &= ~(DP_MBIT(3) - 1); @@ -183,17 +145,17 @@ ieee754dp ieee754dp_format(int sn, int xe, u64 xm) } } if (xm & (DP_MBIT(3) - 1)) { - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_INEXACT); if ((xm & (DP_HIDDEN_BIT << 3)) == 0) { - SETCX(IEEE754_UNDERFLOW); + ieee754_setcx(IEEE754_UNDERFLOW); } /* inexact must round of 3 bits */ - xm = get_rounding(sn, xm); + xm = ieee754dp_get_rounding(sn, xm); /* adjust exponent for rounding add overflowing */ - if (xm >> (DP_MBITS + 3 + 1)) { + if (xm >> (DP_FBITS + 3 + 1)) { /* add causes mantissa overflow */ xm >>= 1; xe++; @@ -202,24 +164,24 @@ ieee754dp ieee754dp_format(int sn, int xe, u64 xm) /* strip grs bits */ xm >>= 3; - assert((xm >> (DP_MBITS + 1)) == 0); /* no execess */ + assert((xm >> (DP_FBITS + 1)) == 0); /* no execess */ assert(xe >= DP_EMIN); if (xe > DP_EMAX) { - SETCX(IEEE754_OVERFLOW); - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_OVERFLOW); + ieee754_setcx(IEEE754_INEXACT); /* -O can be table indexed by (rm,sn) */ switch (ieee754_csr.rm) { - case IEEE754_RN: + case FPU_CSR_RN: return ieee754dp_inf(sn); - case IEEE754_RZ: + case FPU_CSR_RZ: return ieee754dp_max(sn); - case IEEE754_RU: /* toward +Infinity */ + case FPU_CSR_RU: /* toward +Infinity */ if (sn == 0) return ieee754dp_inf(0); else return ieee754dp_max(1); - case IEEE754_RD: /* toward -Infinity */ + case FPU_CSR_RD: /* toward -Infinity */ if (sn == 0) return ieee754dp_max(0); else @@ -232,10 +194,10 @@ ieee754dp ieee754dp_format(int sn, int xe, u64 xm) /* we underflow (tiny/zero) */ assert(xe == DP_EMIN); if (ieee754_csr.mx & IEEE754_UNDERFLOW) - SETCX(IEEE754_UNDERFLOW); + ieee754_setcx(IEEE754_UNDERFLOW); return builddp(sn, DP_EMIN - 1 + DP_EBIAS, xm); } else { - assert((xm >> (DP_MBITS + 1)) == 0); /* no execess */ + assert((xm >> (DP_FBITS + 1)) == 0); /* no execess */ assert(xm & DP_HIDDEN_BIT); return builddp(sn, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT); diff --git a/arch/mips/math-emu/ieee754dp.h b/arch/mips/math-emu/ieee754dp.h index f139c724c59a..61fd6fd31350 100644 --- a/arch/mips/math-emu/ieee754dp.h +++ b/arch/mips/math-emu/ieee754dp.h @@ -6,8 +6,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -19,64 +17,66 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ +#include <linux/compiler.h> #include "ieee754int.h" #define assert(expr) ((void)0) +#define DP_EBIAS 1023 +#define DP_EMIN (-1022) +#define DP_EMAX 1023 +#define DP_FBITS 52 +#define DP_MBITS 52 + +#define DP_MBIT(x) ((u64)1 << (x)) +#define DP_HIDDEN_BIT DP_MBIT(DP_FBITS) +#define DP_SIGN_BIT DP_MBIT(63) + +#define DPSIGN(dp) (dp.sign) +#define DPBEXP(dp) (dp.bexp) +#define DPMANT(dp) (dp.mant) + +static inline int ieee754dp_finite(union ieee754dp x) +{ + return DPBEXP(x) != DP_EMAX + 1 + DP_EBIAS; +} + /* 3bit extended double precision sticky right shift */ #define XDPSRS(v,rs) \ - ((rs > (DP_MBITS+3))?1:((v) >> (rs)) | ((v) << (64-(rs)) != 0)) + ((rs > (DP_FBITS+3))?1:((v) >> (rs)) | ((v) << (64-(rs)) != 0)) #define XDPSRSX1() \ - (xe++, (xm = (xm >> 1) | (xm & 1))) + (xe++, (xm = (xm >> 1) | (xm & 1))) #define XDPSRS1(v) \ - (((v) >> 1) | ((v) & 1)) + (((v) >> 1) | ((v) & 1)) /* convert denormal to normalized with extended exponent */ #define DPDNORMx(m,e) \ - while( (m >> DP_MBITS) == 0) { m <<= 1; e--; } + while ((m >> DP_FBITS) == 0) { m <<= 1; e--; } #define DPDNORMX DPDNORMx(xm, xe) #define DPDNORMY DPDNORMx(ym, ye) -static inline ieee754dp builddp(int s, int bx, u64 m) +static inline union ieee754dp builddp(int s, int bx, u64 m) { - ieee754dp r; + union ieee754dp r; assert((s) == 0 || (s) == 1); assert((bx) >= DP_EMIN - 1 + DP_EBIAS && (bx) <= DP_EMAX + 1 + DP_EBIAS); - assert(((m) >> DP_MBITS) == 0); + assert(((m) >> DP_FBITS) == 0); - r.parts.sign = s; - r.parts.bexp = bx; - r.parts.mant = m; - return r; -} + r.sign = s; + r.bexp = bx; + r.mant = m; -extern int ieee754dp_isnan(ieee754dp); -extern int ieee754dp_issnan(ieee754dp); -extern int ieee754si_xcpt(int, const char *, ...); -extern s64 ieee754di_xcpt(s64, const char *, ...); -extern ieee754dp ieee754dp_xcpt(ieee754dp, const char *, ...); -extern ieee754dp ieee754dp_nanxcpt(ieee754dp, const char *, ...); -extern ieee754dp ieee754dp_bestnan(ieee754dp, ieee754dp); -extern ieee754dp ieee754dp_format(int, int, u64); - - -#define DPNORMRET2(s, e, m, name, a0, a1) \ -{ \ - ieee754dp V = ieee754dp_format(s, e, m); \ - if(TSTX()) \ - return ieee754dp_xcpt(V, name, a0, a1); \ - else \ - return V; \ + return r; } -#define DPNORMRET1(s, e, m, name, a0) DPNORMRET2(s, e, m, name, a0, a0) +extern int ieee754dp_isnan(union ieee754dp); +extern union ieee754dp __cold ieee754dp_nanxcpt(union ieee754dp); +extern union ieee754dp ieee754dp_format(int, int, u64); diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h index 4b6c6fb35304..f0365bb86747 100644 --- a/arch/mips/math-emu/ieee754int.h +++ b/arch/mips/math-emu/ieee754int.h @@ -6,8 +6,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -19,146 +17,125 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - +#ifndef __IEEE754INT_H +#define __IEEE754INT_H #include "ieee754.h" -#define DP_EBIAS 1023 -#define DP_EMIN (-1022) -#define DP_EMAX 1023 -#define DP_MBITS 52 - -#define SP_EBIAS 127 -#define SP_EMIN (-126) -#define SP_EMAX 127 -#define SP_MBITS 23 - -#define DP_MBIT(x) ((u64)1 << (x)) -#define DP_HIDDEN_BIT DP_MBIT(DP_MBITS) -#define DP_SIGN_BIT DP_MBIT(63) - -#define SP_MBIT(x) ((u32)1 << (x)) -#define SP_HIDDEN_BIT SP_MBIT(SP_MBITS) -#define SP_SIGN_BIT SP_MBIT(31) - - -#define SPSIGN(sp) (sp.parts.sign) -#define SPBEXP(sp) (sp.parts.bexp) -#define SPMANT(sp) (sp.parts.mant) - -#define DPSIGN(dp) (dp.parts.sign) -#define DPBEXP(dp) (dp.parts.bexp) -#define DPMANT(dp) (dp.parts.mant) - #define CLPAIR(x, y) ((x)*6+(y)) -#define CLEARCX \ - (ieee754_csr.cx = 0) - -#define SETCX(x) \ - (ieee754_csr.cx |= (x), ieee754_csr.sx |= (x)) +static inline void ieee754_clearcx(void) +{ + ieee754_csr.cx = 0; +} -#define SETANDTESTCX(x) \ - (SETCX(x), ieee754_csr.mx & (x)) +static inline void ieee754_setcx(const unsigned int flags) +{ + ieee754_csr.cx |= flags; + ieee754_csr.sx |= flags; +} -#define TSTX() \ - (ieee754_csr.cx & ieee754_csr.mx) +static inline int ieee754_setandtestcx(const unsigned int x) +{ + ieee754_setcx(x); + return ieee754_csr.mx & x; +} #define COMPXSP \ - unsigned xm; int xe; int xs __maybe_unused; int xc + unsigned xm; int xe; int xs __maybe_unused; int xc #define COMPYSP \ - unsigned ym; int ye; int ys; int yc - -#define EXPLODESP(v, vc, vs, ve, vm) \ -{\ - vs = SPSIGN(v);\ - ve = SPBEXP(v);\ - vm = SPMANT(v);\ - if(ve == SP_EMAX+1+SP_EBIAS){\ - if(vm == 0)\ - vc = IEEE754_CLASS_INF;\ - else if(vm & SP_MBIT(SP_MBITS-1)) \ - vc = IEEE754_CLASS_SNAN;\ - else \ - vc = IEEE754_CLASS_QNAN;\ - } else if(ve == SP_EMIN-1+SP_EBIAS) {\ - if(vm) {\ - ve = SP_EMIN;\ - vc = IEEE754_CLASS_DNORM;\ - } else\ - vc = IEEE754_CLASS_ZERO;\ - } else {\ - ve -= SP_EBIAS;\ - vm |= SP_HIDDEN_BIT;\ - vc = IEEE754_CLASS_NORM;\ - }\ + unsigned ym; int ye; int ys; int yc + +#define EXPLODESP(v, vc, vs, ve, vm) \ +{ \ + vs = SPSIGN(v); \ + ve = SPBEXP(v); \ + vm = SPMANT(v); \ + if (ve == SP_EMAX+1+SP_EBIAS) { \ + if (vm == 0) \ + vc = IEEE754_CLASS_INF; \ + else if (vm & SP_MBIT(SP_FBITS-1)) \ + vc = IEEE754_CLASS_SNAN; \ + else \ + vc = IEEE754_CLASS_QNAN; \ + } else if (ve == SP_EMIN-1+SP_EBIAS) { \ + if (vm) { \ + ve = SP_EMIN; \ + vc = IEEE754_CLASS_DNORM; \ + } else \ + vc = IEEE754_CLASS_ZERO; \ + } else { \ + ve -= SP_EBIAS; \ + vm |= SP_HIDDEN_BIT; \ + vc = IEEE754_CLASS_NORM; \ + } \ } #define EXPLODEXSP EXPLODESP(x, xc, xs, xe, xm) #define EXPLODEYSP EXPLODESP(y, yc, ys, ye, ym) #define COMPXDP \ -u64 xm; int xe; int xs __maybe_unused; int xc + u64 xm; int xe; int xs __maybe_unused; int xc #define COMPYDP \ -u64 ym; int ye; int ys; int yc - -#define EXPLODEDP(v, vc, vs, ve, vm) \ -{\ - vm = DPMANT(v);\ - vs = DPSIGN(v);\ - ve = DPBEXP(v);\ - if(ve == DP_EMAX+1+DP_EBIAS){\ - if(vm == 0)\ - vc = IEEE754_CLASS_INF;\ - else if(vm & DP_MBIT(DP_MBITS-1)) \ - vc = IEEE754_CLASS_SNAN;\ - else \ - vc = IEEE754_CLASS_QNAN;\ - } else if(ve == DP_EMIN-1+DP_EBIAS) {\ - if(vm) {\ - ve = DP_EMIN;\ - vc = IEEE754_CLASS_DNORM;\ - } else\ - vc = IEEE754_CLASS_ZERO;\ - } else {\ - ve -= DP_EBIAS;\ - vm |= DP_HIDDEN_BIT;\ - vc = IEEE754_CLASS_NORM;\ - }\ + u64 ym; int ye; int ys; int yc + +#define EXPLODEDP(v, vc, vs, ve, vm) \ +{ \ + vm = DPMANT(v); \ + vs = DPSIGN(v); \ + ve = DPBEXP(v); \ + if (ve == DP_EMAX+1+DP_EBIAS) { \ + if (vm == 0) \ + vc = IEEE754_CLASS_INF; \ + else if (vm & DP_MBIT(DP_FBITS-1)) \ + vc = IEEE754_CLASS_SNAN; \ + else \ + vc = IEEE754_CLASS_QNAN; \ + } else if (ve == DP_EMIN-1+DP_EBIAS) { \ + if (vm) { \ + ve = DP_EMIN; \ + vc = IEEE754_CLASS_DNORM; \ + } else \ + vc = IEEE754_CLASS_ZERO; \ + } else { \ + ve -= DP_EBIAS; \ + vm |= DP_HIDDEN_BIT; \ + vc = IEEE754_CLASS_NORM; \ + } \ } #define EXPLODEXDP EXPLODEDP(x, xc, xs, xe, xm) #define EXPLODEYDP EXPLODEDP(y, yc, ys, ye, ym) -#define FLUSHDP(v, vc, vs, ve, vm) \ - if(vc==IEEE754_CLASS_DNORM) {\ - if(ieee754_csr.nod) {\ - SETCX(IEEE754_INEXACT);\ - vc = IEEE754_CLASS_ZERO;\ - ve = DP_EMIN-1+DP_EBIAS;\ - vm = 0;\ - v = ieee754dp_zero(vs);\ - }\ +#define FLUSHDP(v, vc, vs, ve, vm) \ + if (vc==IEEE754_CLASS_DNORM) { \ + if (ieee754_csr.nod) { \ + ieee754_setcx(IEEE754_INEXACT); \ + vc = IEEE754_CLASS_ZERO; \ + ve = DP_EMIN-1+DP_EBIAS; \ + vm = 0; \ + v = ieee754dp_zero(vs); \ + } \ } -#define FLUSHSP(v, vc, vs, ve, vm) \ - if(vc==IEEE754_CLASS_DNORM) {\ - if(ieee754_csr.nod) {\ - SETCX(IEEE754_INEXACT);\ - vc = IEEE754_CLASS_ZERO;\ - ve = SP_EMIN-1+SP_EBIAS;\ - vm = 0;\ - v = ieee754sp_zero(vs);\ - }\ +#define FLUSHSP(v, vc, vs, ve, vm) \ + if (vc==IEEE754_CLASS_DNORM) { \ + if (ieee754_csr.nod) { \ + ieee754_setcx(IEEE754_INEXACT); \ + vc = IEEE754_CLASS_ZERO; \ + ve = SP_EMIN-1+SP_EBIAS; \ + vm = 0; \ + v = ieee754sp_zero(vs); \ + } \ } #define FLUSHXDP FLUSHDP(x, xc, xs, xe, xm) #define FLUSHYDP FLUSHDP(y, yc, ys, ye, ym) #define FLUSHXSP FLUSHSP(x, xc, xs, xe, xm) #define FLUSHYSP FLUSHSP(y, yc, ys, ye, ym) + +#endif /* __IEEE754INT_H */ diff --git a/arch/mips/math-emu/ieee754m.c b/arch/mips/math-emu/ieee754m.c deleted file mode 100644 index 24190f3c9dd6..000000000000 --- a/arch/mips/math-emu/ieee754m.c +++ /dev/null @@ -1,55 +0,0 @@ -/* - * floor, trunc, ceil - */ -/* - * MIPS floating point support - * Copyright (C) 1994-2000 Algorithmics Ltd. - * - * ######################################################################## - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - */ - - -#include "ieee754.h" - -ieee754dp ieee754dp_floor(ieee754dp x) -{ - ieee754dp i; - - if (ieee754dp_lt(ieee754dp_modf(x, &i), ieee754dp_zero(0))) - return ieee754dp_sub(i, ieee754dp_one(0)); - else - return i; -} - -ieee754dp ieee754dp_ceil(ieee754dp x) -{ - ieee754dp i; - - if (ieee754dp_gt(ieee754dp_modf(x, &i), ieee754dp_zero(0))) - return ieee754dp_add(i, ieee754dp_one(0)); - else - return i; -} - -ieee754dp ieee754dp_trunc(ieee754dp x) -{ - ieee754dp i; - - (void) ieee754dp_modf(x, &i); - return i; -} diff --git a/arch/mips/math-emu/ieee754sp.c b/arch/mips/math-emu/ieee754sp.c index 15d1e36cfe64..d348efe91445 100644 --- a/arch/mips/math-emu/ieee754sp.c +++ b/arch/mips/math-emu/ieee754sp.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,105 +16,68 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ +#include <linux/compiler.h> #include "ieee754sp.h" -int ieee754sp_class(ieee754sp x) +int ieee754sp_class(union ieee754sp x) { COMPXSP; EXPLODEXSP; return xc; } -int ieee754sp_isnan(ieee754sp x) +int ieee754sp_isnan(union ieee754sp x) { return ieee754sp_class(x) >= IEEE754_CLASS_SNAN; } -int ieee754sp_issnan(ieee754sp x) +static inline int ieee754sp_issnan(union ieee754sp x) { assert(ieee754sp_isnan(x)); - return (SPMANT(x) & SP_MBIT(SP_MBITS-1)); + return (SPMANT(x) & SP_MBIT(SP_FBITS-1)); } -ieee754sp ieee754sp_xcpt(ieee754sp r, const char *op, ...) -{ - struct ieee754xctx ax; - - if (!TSTX()) - return r; - - ax.op = op; - ax.rt = IEEE754_RT_SP; - ax.rv.sp = r; - va_start(ax.ap, op); - ieee754_xcpt(&ax); - va_end(ax.ap); - return ax.rv.sp; -} - -ieee754sp ieee754sp_nanxcpt(ieee754sp r, const char *op, ...) +union ieee754sp __cold ieee754sp_nanxcpt(union ieee754sp r) { - struct ieee754xctx ax; - assert(ieee754sp_isnan(r)); if (!ieee754sp_issnan(r)) /* QNAN does not cause invalid op !! */ return r; - if (!SETANDTESTCX(IEEE754_INVALID_OPERATION)) { + if (!ieee754_setandtestcx(IEEE754_INVALID_OPERATION)) { /* not enabled convert to a quiet NaN */ - SPMANT(r) &= (~SP_MBIT(SP_MBITS-1)); + SPMANT(r) &= (~SP_MBIT(SP_FBITS-1)); if (ieee754sp_isnan(r)) return r; else return ieee754sp_indef(); } - ax.op = op; - ax.rt = 0; - ax.rv.sp = r; - va_start(ax.ap, op); - ieee754_xcpt(&ax); - va_end(ax.ap); - return ax.rv.sp; -} - -ieee754sp ieee754sp_bestnan(ieee754sp x, ieee754sp y) -{ - assert(ieee754sp_isnan(x)); - assert(ieee754sp_isnan(y)); - - if (SPMANT(x) > SPMANT(y)) - return x; - else - return y; + return r; } - -static unsigned get_rounding(int sn, unsigned xm) +static unsigned ieee754sp_get_rounding(int sn, unsigned xm) { /* inexact must round of 3 bits */ if (xm & (SP_MBIT(3) - 1)) { switch (ieee754_csr.rm) { - case IEEE754_RZ: + case FPU_CSR_RZ: break; - case IEEE754_RN: + case FPU_CSR_RN: xm += 0x3 + ((xm >> 3) & 1); /* xm += (xm&0x8)?0x4:0x3 */ break; - case IEEE754_RU: /* toward +Infinity */ + case FPU_CSR_RU: /* toward +Infinity */ if (!sn) /* ?? */ xm += 0x8; break; - case IEEE754_RD: /* toward -Infinity */ + case FPU_CSR_RD: /* toward -Infinity */ if (sn) /* ?? */ xm += 0x8; break; @@ -131,11 +92,11 @@ static unsigned get_rounding(int sn, unsigned xm) * xe is an unbiased exponent * xm is 3bit extended precision value. */ -ieee754sp ieee754sp_format(int sn, int xe, unsigned xm) +union ieee754sp ieee754sp_format(int sn, int xe, unsigned xm) { assert(xm); /* we don't gen exact zeros (probably should) */ - assert((xm >> (SP_MBITS + 1 + 3)) == 0); /* no execess */ + assert((xm >> (SP_FBITS + 1 + 3)) == 0); /* no execess */ assert(xm & (SP_HIDDEN_BIT << 3)); if (xe < SP_EMIN) { @@ -143,38 +104,37 @@ ieee754sp ieee754sp_format(int sn, int xe, unsigned xm) int es = SP_EMIN - xe; if (ieee754_csr.nod) { - SETCX(IEEE754_UNDERFLOW); - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_UNDERFLOW); + ieee754_setcx(IEEE754_INEXACT); switch(ieee754_csr.rm) { - case IEEE754_RN: - case IEEE754_RZ: + case FPU_CSR_RN: + case FPU_CSR_RZ: return ieee754sp_zero(sn); - case IEEE754_RU: /* toward +Infinity */ - if(sn == 0) + case FPU_CSR_RU: /* toward +Infinity */ + if (sn == 0) return ieee754sp_min(0); else return ieee754sp_zero(1); - case IEEE754_RD: /* toward -Infinity */ - if(sn == 0) + case FPU_CSR_RD: /* toward -Infinity */ + if (sn == 0) return ieee754sp_zero(0); else return ieee754sp_min(1); } } - if (xe == SP_EMIN - 1 - && get_rounding(sn, xm) >> (SP_MBITS + 1 + 3)) + if (xe == SP_EMIN - 1 && + ieee754sp_get_rounding(sn, xm) >> (SP_FBITS + 1 + 3)) { /* Not tiny after rounding */ - SETCX(IEEE754_INEXACT); - xm = get_rounding(sn, xm); + ieee754_setcx(IEEE754_INEXACT); + xm = ieee754sp_get_rounding(sn, xm); xm >>= 1; /* Clear grs bits */ xm &= ~(SP_MBIT(3) - 1); xe++; - } - else { + } else { /* sticky right shift es bits */ SPXSRSXn(es); @@ -183,17 +143,17 @@ ieee754sp ieee754sp_format(int sn, int xe, unsigned xm) } } if (xm & (SP_MBIT(3) - 1)) { - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_INEXACT); if ((xm & (SP_HIDDEN_BIT << 3)) == 0) { - SETCX(IEEE754_UNDERFLOW); + ieee754_setcx(IEEE754_UNDERFLOW); } /* inexact must round of 3 bits */ - xm = get_rounding(sn, xm); + xm = ieee754sp_get_rounding(sn, xm); /* adjust exponent for rounding add overflowing */ - if (xm >> (SP_MBITS + 1 + 3)) { + if (xm >> (SP_FBITS + 1 + 3)) { /* add causes mantissa overflow */ xm >>= 1; xe++; @@ -202,24 +162,24 @@ ieee754sp ieee754sp_format(int sn, int xe, unsigned xm) /* strip grs bits */ xm >>= 3; - assert((xm >> (SP_MBITS + 1)) == 0); /* no execess */ + assert((xm >> (SP_FBITS + 1)) == 0); /* no execess */ assert(xe >= SP_EMIN); if (xe > SP_EMAX) { - SETCX(IEEE754_OVERFLOW); - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_OVERFLOW); + ieee754_setcx(IEEE754_INEXACT); /* -O can be table indexed by (rm,sn) */ switch (ieee754_csr.rm) { - case IEEE754_RN: + case FPU_CSR_RN: return ieee754sp_inf(sn); - case IEEE754_RZ: + case FPU_CSR_RZ: return ieee754sp_max(sn); - case IEEE754_RU: /* toward +Infinity */ + case FPU_CSR_RU: /* toward +Infinity */ if (sn == 0) return ieee754sp_inf(0); else return ieee754sp_max(1); - case IEEE754_RD: /* toward -Infinity */ + case FPU_CSR_RD: /* toward -Infinity */ if (sn == 0) return ieee754sp_max(0); else @@ -232,10 +192,10 @@ ieee754sp ieee754sp_format(int sn, int xe, unsigned xm) /* we underflow (tiny/zero) */ assert(xe == SP_EMIN); if (ieee754_csr.mx & IEEE754_UNDERFLOW) - SETCX(IEEE754_UNDERFLOW); + ieee754_setcx(IEEE754_UNDERFLOW); return buildsp(sn, SP_EMIN - 1 + SP_EBIAS, xm); } else { - assert((xm >> (SP_MBITS + 1)) == 0); /* no execess */ + assert((xm >> (SP_FBITS + 1)) == 0); /* no execess */ assert(xm & SP_HIDDEN_BIT); return buildsp(sn, xe + SP_EBIAS, xm & ~SP_HIDDEN_BIT); diff --git a/arch/mips/math-emu/ieee754sp.h b/arch/mips/math-emu/ieee754sp.h index 754fd54649b5..ad268e332318 100644 --- a/arch/mips/math-emu/ieee754sp.h +++ b/arch/mips/math-emu/ieee754sp.h @@ -6,8 +6,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -19,70 +17,71 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ +#include <linux/compiler.h> #include "ieee754int.h" #define assert(expr) ((void)0) +#define SP_EBIAS 127 +#define SP_EMIN (-126) +#define SP_EMAX 127 +#define SP_FBITS 23 +#define SP_MBITS 23 + +#define SP_MBIT(x) ((u32)1 << (x)) +#define SP_HIDDEN_BIT SP_MBIT(SP_FBITS) +#define SP_SIGN_BIT SP_MBIT(31) + +#define SPSIGN(sp) (sp.sign) +#define SPBEXP(sp) (sp.bexp) +#define SPMANT(sp) (sp.mant) + +static inline int ieee754sp_finite(union ieee754sp x) +{ + return SPBEXP(x) != SP_EMAX + 1 + SP_EBIAS; +} + /* 3bit extended single precision sticky right shift */ -#define SPXSRSXn(rs) \ - (xe += rs, \ - xm = (rs > (SP_MBITS+3))?1:((xm) >> (rs)) | ((xm) << (32-(rs)) != 0)) +#define SPXSRSXn(rs) \ + (xe += rs, \ + xm = (rs > (SP_FBITS+3))?1:((xm) >> (rs)) | ((xm) << (32-(rs)) != 0)) #define SPXSRSX1() \ - (xe++, (xm = (xm >> 1) | (xm & 1))) + (xe++, (xm = (xm >> 1) | (xm & 1))) -#define SPXSRSYn(rs) \ - (ye+=rs, \ - ym = (rs > (SP_MBITS+3))?1:((ym) >> (rs)) | ((ym) << (32-(rs)) != 0)) +#define SPXSRSYn(rs) \ + (ye+=rs, \ + ym = (rs > (SP_FBITS+3))?1:((ym) >> (rs)) | ((ym) << (32-(rs)) != 0)) #define SPXSRSY1() \ - (ye++, (ym = (ym >> 1) | (ym & 1))) + (ye++, (ym = (ym >> 1) | (ym & 1))) /* convert denormal to normalized with extended exponent */ #define SPDNORMx(m,e) \ - while( (m >> SP_MBITS) == 0) { m <<= 1; e--; } + while ((m >> SP_FBITS) == 0) { m <<= 1; e--; } #define SPDNORMX SPDNORMx(xm, xe) #define SPDNORMY SPDNORMx(ym, ye) -static inline ieee754sp buildsp(int s, int bx, unsigned m) +static inline union ieee754sp buildsp(int s, int bx, unsigned m) { - ieee754sp r; + union ieee754sp r; assert((s) == 0 || (s) == 1); assert((bx) >= SP_EMIN - 1 + SP_EBIAS && (bx) <= SP_EMAX + 1 + SP_EBIAS); - assert(((m) >> SP_MBITS) == 0); + assert(((m) >> SP_FBITS) == 0); - r.parts.sign = s; - r.parts.bexp = bx; - r.parts.mant = m; + r.sign = s; + r.bexp = bx; + r.mant = m; return r; } -extern int ieee754sp_isnan(ieee754sp); -extern int ieee754sp_issnan(ieee754sp); -extern int ieee754si_xcpt(int, const char *, ...); -extern s64 ieee754di_xcpt(s64, const char *, ...); -extern ieee754sp ieee754sp_xcpt(ieee754sp, const char *, ...); -extern ieee754sp ieee754sp_nanxcpt(ieee754sp, const char *, ...); -extern ieee754sp ieee754sp_bestnan(ieee754sp, ieee754sp); -extern ieee754sp ieee754sp_format(int, int, unsigned); - - -#define SPNORMRET2(s, e, m, name, a0, a1) \ -{ \ - ieee754sp V = ieee754sp_format(s, e, m); \ - if(TSTX()) \ - return ieee754sp_xcpt(V, name, a0, a1); \ - else \ - return V; \ -} - -#define SPNORMRET1(s, e, m, name, a0) SPNORMRET2(s, e, m, name, a0, a0) +extern int ieee754sp_isnan(union ieee754sp); +extern union ieee754sp __cold ieee754sp_nanxcpt(union ieee754sp); +extern union ieee754sp ieee754sp_format(int, int, unsigned); diff --git a/arch/mips/math-emu/ieee754xcpt.c b/arch/mips/math-emu/ieee754xcpt.c deleted file mode 100644 index 967167116ae8..000000000000 --- a/arch/mips/math-emu/ieee754xcpt.c +++ /dev/null @@ -1,47 +0,0 @@ -/* - * MIPS floating point support - * Copyright (C) 1994-2000 Algorithmics Ltd. - * - * ######################################################################## - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - */ - -/************************************************************************** - * Nov 7, 2000 - * Added preprocessor hacks to map to Linux kernel diagnostics. - * - * Kevin D. Kissell, kevink@mips.com and Carsten Langgaard, carstenl@mips.com - * Copyright (C) 2000 MIPS Technologies, Inc. All rights reserved. - *************************************************************************/ - -#include <linux/kernel.h> -#include "ieee754.h" - -/* - * Very naff exception handler (you can plug in your own and - * override this). - */ - -static const char *const rtnames[] = { - "sp", "dp", "xp", "si", "di" -}; - -void ieee754_xcpt(struct ieee754xctx *xcp) -{ - printk(KERN_DEBUG "floating point exception in \"%s\", type=%s\n", - xcp->op, rtnames[xcp->rt]); -} diff --git a/arch/mips/math-emu/kernel_linkage.c b/arch/mips/math-emu/kernel_linkage.c deleted file mode 100644 index eb58a85b3157..000000000000 --- a/arch/mips/math-emu/kernel_linkage.c +++ /dev/null @@ -1,45 +0,0 @@ -/* - * Kevin D. Kissell, kevink@mips and Carsten Langgaard, carstenl@mips.com - * Copyright (C) 2000 MIPS Technologies, Inc. All rights reserved. - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * Routines corresponding to Linux kernel FP context - * manipulation primitives for the Algorithmics MIPS - * FPU Emulator - */ -#include <linux/sched.h> -#include <asm/processor.h> -#include <asm/signal.h> -#include <asm/uaccess.h> - -#include <asm/fpu.h> -#include <asm/fpu_emulator.h> - -#define SIGNALLING_NAN 0x7ff800007ff80000LL - -void fpu_emulator_init_fpu(void) -{ - static int first = 1; - int i; - - if (first) { - first = 0; - printk("Algorithmics/MIPS FPU Emulator v1.5\n"); - } - - current->thread.fpu.fcr31 = 0; - for (i = 0; i < 32; i++) - set_fpr64(¤t->thread.fpu.fpr[i], 0, SIGNALLING_NAN); -} diff --git a/arch/mips/math-emu/me-debugfs.c b/arch/mips/math-emu/me-debugfs.c new file mode 100644 index 000000000000..becdd63e14a9 --- /dev/null +++ b/arch/mips/math-emu/me-debugfs.c @@ -0,0 +1,67 @@ +#include <linux/cpumask.h> +#include <linux/debugfs.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/percpu.h> +#include <linux/types.h> +#include <asm/fpu_emulator.h> +#include <asm/local.h> + +DEFINE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats); + +static int fpuemu_stat_get(void *data, u64 *val) +{ + int cpu; + unsigned long sum = 0; + + for_each_online_cpu(cpu) { + struct mips_fpu_emulator_stats *ps; + local_t *pv; + + ps = &per_cpu(fpuemustats, cpu); + pv = (void *)ps + (unsigned long)data; + sum += local_read(pv); + } + *val = sum; + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(fops_fpuemu_stat, fpuemu_stat_get, NULL, "%llu\n"); + +extern struct dentry *mips_debugfs_dir; +static int __init debugfs_fpuemu(void) +{ + struct dentry *d, *dir; + + if (!mips_debugfs_dir) + return -ENODEV; + dir = debugfs_create_dir("fpuemustats", mips_debugfs_dir); + if (!dir) + return -ENOMEM; + +#define FPU_EMU_STAT_OFFSET(m) \ + offsetof(struct mips_fpu_emulator_stats, m) + +#define FPU_STAT_CREATE(m) \ +do { \ + d = debugfs_create_file(#m , S_IRUGO, dir, \ + (void *)FPU_EMU_STAT_OFFSET(m), \ + &fops_fpuemu_stat); \ + if (!d) \ + return -ENOMEM; \ +} while (0) + + FPU_STAT_CREATE(emulated); + FPU_STAT_CREATE(loads); + FPU_STAT_CREATE(stores); + FPU_STAT_CREATE(cp1ops); + FPU_STAT_CREATE(cp1xops); + FPU_STAT_CREATE(errors); + FPU_STAT_CREATE(ieee754_inexact); + FPU_STAT_CREATE(ieee754_underflow); + FPU_STAT_CREATE(ieee754_overflow); + FPU_STAT_CREATE(ieee754_zerodiv); + FPU_STAT_CREATE(ieee754_invalidop); + + return 0; +} +__initcall(debugfs_fpuemu); diff --git a/arch/mips/math-emu/sp_add.c b/arch/mips/math-emu/sp_add.c index c446e64637e2..2d84d460cb67 100644 --- a/arch/mips/math-emu/sp_add.c +++ b/arch/mips/math-emu/sp_add.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,23 +16,22 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" -ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y) +union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y) { + int s; + COMPXSP; COMPYSP; EXPLODEXSP; EXPLODEYSP; - CLEARCX; + ieee754_clearcx(); FLUSHXSP; FLUSHYSP; @@ -51,8 +48,8 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_nanxcpt(ieee754sp_indef(), "add", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_nanxcpt(ieee754sp_indef()); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): @@ -68,14 +65,14 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y) return x; - /* Infinity handling - */ - + /* + * Infinity handling + */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): if (xs == ys) return x; - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_xcpt(ieee754sp_indef(), "add", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_indef(); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): @@ -87,15 +84,14 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y) case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): return x; - /* Zero handling - */ - + /* + * Zero handling + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): if (xs == ys) return x; else - return ieee754sp_zero(ieee754_csr.rm == - IEEE754_RD); + return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): @@ -108,6 +104,8 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* FALL THROUGH */ + case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; break; @@ -122,33 +120,38 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y) assert(xm & SP_HIDDEN_BIT); assert(ym & SP_HIDDEN_BIT); - /* provide guard,round and stick bit space */ + /* + * Provide guard, round and stick bit space. + */ xm <<= 3; ym <<= 3; if (xe > ye) { - /* have to shift y fraction right to align + /* + * Have to shift y fraction right to align. */ - int s = xe - ye; + s = xe - ye; SPXSRSYn(s); } else if (ye > xe) { - /* have to shift x fraction right to align + /* + * Have to shift x fraction right to align. */ - int s = ye - xe; + s = ye - xe; SPXSRSXn(s); } assert(xe == ye); assert(xe <= SP_EMAX); if (xs == ys) { - /* generate 28 bit result of adding two 27 bit numbers - * leaving result in xm,xs,xe + /* + * Generate 28 bit result of adding two 27 bit numbers + * leaving result in xm, xs and xe. */ xm = xm + ym; xe = xe; xs = xs; - if (xm >> (SP_MBITS + 1 + 3)) { /* carry out */ + if (xm >> (SP_FBITS + 1 + 3)) { /* carry out */ SPXSRSX1(); } } else { @@ -162,15 +165,16 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y) xs = ys; } if (xm == 0) - return ieee754sp_zero(ieee754_csr.rm == - IEEE754_RD); + return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD); - /* normalize in extended single precision */ - while ((xm >> (SP_MBITS + 3)) == 0) { + /* + * Normalize in extended single precision + */ + while ((xm >> (SP_FBITS + 3)) == 0) { xm <<= 1; xe--; } - } - SPNORMRET2(xs, xe, xm, "add", x, y); + + return ieee754sp_format(xs, xe, xm); } diff --git a/arch/mips/math-emu/sp_cmp.c b/arch/mips/math-emu/sp_cmp.c index 716cf37e2465..addbccb2f556 100644 --- a/arch/mips/math-emu/sp_cmp.c +++ b/arch/mips/math-emu/sp_cmp.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,16 +16,16 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" -int ieee754sp_cmp(ieee754sp x, ieee754sp y, int cmp, int sig) +int ieee754sp_cmp(union ieee754sp x, union ieee754sp y, int cmp, int sig) { + int vx; + int vy; + COMPXSP; COMPYSP; @@ -35,21 +33,21 @@ int ieee754sp_cmp(ieee754sp x, ieee754sp y, int cmp, int sig) EXPLODEYSP; FLUSHXSP; FLUSHYSP; - CLEARCX; /* Even clear inexact flag here */ + ieee754_clearcx(); /* Even clear inexact flag here */ if (ieee754sp_isnan(x) || ieee754sp_isnan(y)) { if (sig || xc == IEEE754_CLASS_SNAN || yc == IEEE754_CLASS_SNAN) - SETCX(IEEE754_INVALID_OPERATION); + ieee754_setcx(IEEE754_INVALID_OPERATION); if (cmp & IEEE754_CUN) return 1; if (cmp & (IEEE754_CLT | IEEE754_CGT)) { - if (sig && SETANDTESTCX(IEEE754_INVALID_OPERATION)) - return ieee754si_xcpt(0, "fcmpf", x); + if (sig && ieee754_setandtestcx(IEEE754_INVALID_OPERATION)) + return 0; } return 0; } else { - int vx = x.bits; - int vy = y.bits; + vx = x.bits; + vy = y.bits; if (vx < 0) vx = -vx ^ SP_SIGN_BIT; diff --git a/arch/mips/math-emu/sp_div.c b/arch/mips/math-emu/sp_div.c index d7747928c954..721f317aa877 100644 --- a/arch/mips/math-emu/sp_div.c +++ b/arch/mips/math-emu/sp_div.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,23 +16,24 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" -ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y) +union ieee754sp ieee754sp_div(union ieee754sp x, union ieee754sp y) { + unsigned rm; + int re; + unsigned bm; + COMPXSP; COMPYSP; EXPLODEXSP; EXPLODEYSP; - CLEARCX; + ieee754_clearcx(); FLUSHXSP; FLUSHYSP; @@ -51,8 +50,8 @@ ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_nanxcpt(ieee754sp_indef(), "div", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_nanxcpt(ieee754sp_indef()); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): @@ -68,12 +67,12 @@ ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y) return x; - /* Infinity handling - */ - + /* + * Infinity handling + */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_xcpt(ieee754sp_indef(), "div", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_indef(); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): @@ -85,17 +84,17 @@ ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y) case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): return ieee754sp_inf(xs ^ ys); - /* Zero handling - */ - + /* + * Zero handling + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_xcpt(ieee754sp_indef(), "div", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_indef(); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): - SETCX(IEEE754_ZERO_DIVIDE); - return ieee754sp_xcpt(ieee754sp_inf(xs ^ ys), "div", x, y); + ieee754_setcx(IEEE754_ZERO_DIVIDE); + return ieee754sp_inf(xs ^ ys); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM): @@ -122,35 +121,33 @@ ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y) xm <<= 3; ym <<= 3; - { - /* now the dirty work */ - - unsigned rm = 0; - int re = xe - ye; - unsigned bm; - - for (bm = SP_MBIT(SP_MBITS + 2); bm; bm >>= 1) { - if (xm >= ym) { - xm -= ym; - rm |= bm; - if (xm == 0) - break; - } - xm <<= 1; - } - rm <<= 1; - if (xm) - rm |= 1; /* have remainder, set sticky */ + /* now the dirty work */ - assert(rm); + rm = 0; + re = xe - ye; - /* normalise rm to rounding precision ? - */ - while ((rm >> (SP_MBITS + 3)) == 0) { - rm <<= 1; - re--; + for (bm = SP_MBIT(SP_FBITS + 2); bm; bm >>= 1) { + if (xm >= ym) { + xm -= ym; + rm |= bm; + if (xm == 0) + break; } + xm <<= 1; + } + + rm <<= 1; + if (xm) + rm |= 1; /* have remainder, set sticky */ - SPNORMRET2(xs == ys ? 0 : 1, re, rm, "div", x, y); + assert(rm); + + /* normalise rm to rounding precision ? + */ + while ((rm >> (SP_FBITS + 3)) == 0) { + rm <<= 1; + re--; } + + return ieee754sp_format(xs == ys ? 0 : 1, re, rm); } diff --git a/arch/mips/math-emu/sp_fdp.c b/arch/mips/math-emu/sp_fdp.c index e1515aae0166..1b266fb16973 100644 --- a/arch/mips/math-emu/sp_fdp.c +++ b/arch/mips/math-emu/sp_fdp.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,59 +16,61 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" +#include "ieee754dp.h" -ieee754sp ieee754sp_fdp(ieee754dp x) +union ieee754sp ieee754sp_fdp(union ieee754dp x) { + u32 rm; + COMPXDP; - ieee754sp nan; + union ieee754sp nan; EXPLODEXDP; - CLEARCX; + ieee754_clearcx(); FLUSHXDP; switch (xc) { case IEEE754_CLASS_SNAN: - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_nanxcpt(ieee754sp_indef(), "fdp"); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_nanxcpt(ieee754sp_indef()); + case IEEE754_CLASS_QNAN: nan = buildsp(xs, SP_EMAX + 1 + SP_EBIAS, (u32) - (xm >> (DP_MBITS - SP_MBITS))); + (xm >> (DP_FBITS - SP_FBITS))); if (!ieee754sp_isnan(nan)) nan = ieee754sp_indef(); - return ieee754sp_nanxcpt(nan, "fdp", x); + return ieee754sp_nanxcpt(nan); + case IEEE754_CLASS_INF: return ieee754sp_inf(xs); + case IEEE754_CLASS_ZERO: return ieee754sp_zero(xs); + case IEEE754_CLASS_DNORM: /* can't possibly be sp representable */ - SETCX(IEEE754_UNDERFLOW); - SETCX(IEEE754_INEXACT); - if ((ieee754_csr.rm == IEEE754_RU && !xs) || - (ieee754_csr.rm == IEEE754_RD && xs)) - return ieee754sp_xcpt(ieee754sp_mind(xs), "fdp", x); - return ieee754sp_xcpt(ieee754sp_zero(xs), "fdp", x); + ieee754_setcx(IEEE754_UNDERFLOW); + ieee754_setcx(IEEE754_INEXACT); + if ((ieee754_csr.rm == FPU_CSR_RU && !xs) || + (ieee754_csr.rm == FPU_CSR_RD && xs)) + return ieee754sp_mind(xs); + return ieee754sp_zero(xs); + case IEEE754_CLASS_NORM: break; } - { - u32 rm; - - /* convert from DP_MBITS to SP_MBITS+3 with sticky right shift - */ - rm = (xm >> (DP_MBITS - (SP_MBITS + 3))) | - ((xm << (64 - (DP_MBITS - (SP_MBITS + 3)))) != 0); + /* + * Convert from DP_FBITS to SP_FBITS+3 with sticky right shift. + */ + rm = (xm >> (DP_FBITS - (SP_FBITS + 3))) | + ((xm << (64 - (DP_FBITS - (SP_FBITS + 3)))) != 0); - SPNORMRET1(xs, xe, rm, "fdp", x); - } + return ieee754sp_format(xs, xe, rm); } diff --git a/arch/mips/math-emu/sp_fint.c b/arch/mips/math-emu/sp_fint.c index 9694d6c016cb..d5d8495b2cc4 100644 --- a/arch/mips/math-emu/sp_fint.c +++ b/arch/mips/math-emu/sp_fint.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,21 +16,18 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" -ieee754sp ieee754sp_fint(int x) +union ieee754sp ieee754sp_fint(int x) { unsigned xm; int xe; int xs; - CLEARCX; + ieee754_clearcx(); if (x == 0) return ieee754sp_zero(0); @@ -50,30 +45,21 @@ ieee754sp ieee754sp_fint(int x) } else { xm = x; } - xe = SP_MBITS + 3; + xe = SP_FBITS + 3; - if (xm >> (SP_MBITS + 1 + 3)) { + if (xm >> (SP_FBITS + 1 + 3)) { /* shunt out overflow bits */ - while (xm >> (SP_MBITS + 1 + 3)) { + while (xm >> (SP_FBITS + 1 + 3)) { SPXSRSX1(); } } else { /* normalize in grs extended single precision */ - while ((xm >> (SP_MBITS + 3)) == 0) { + while ((xm >> (SP_FBITS + 3)) == 0) { xm <<= 1; xe--; } } - SPNORMRET1(xs, xe, xm, "fint", x); -} - - -ieee754sp ieee754sp_funs(unsigned int u) -{ - if ((int) u < 0) - return ieee754sp_add(ieee754sp_1e31(), - ieee754sp_fint(u & ~(1 << 31))); - return ieee754sp_fint(u); + return ieee754sp_format(xs, xe, xm); } diff --git a/arch/mips/math-emu/sp_flong.c b/arch/mips/math-emu/sp_flong.c index 16a651f29865..012e30ce7589 100644 --- a/arch/mips/math-emu/sp_flong.c +++ b/arch/mips/math-emu/sp_flong.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,21 +16,18 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" -ieee754sp ieee754sp_flong(s64 x) +union ieee754sp ieee754sp_flong(s64 x) { u64 xm; /* <--- need 64-bit mantissa temp */ int xe; int xs; - CLEARCX; + ieee754_clearcx(); if (x == 0) return ieee754sp_zero(0); @@ -50,29 +45,20 @@ ieee754sp ieee754sp_flong(s64 x) } else { xm = x; } - xe = SP_MBITS + 3; + xe = SP_FBITS + 3; - if (xm >> (SP_MBITS + 1 + 3)) { + if (xm >> (SP_FBITS + 1 + 3)) { /* shunt out overflow bits */ - while (xm >> (SP_MBITS + 1 + 3)) { + while (xm >> (SP_FBITS + 1 + 3)) { SPXSRSX1(); } } else { /* normalize in grs extended single precision */ - while ((xm >> (SP_MBITS + 3)) == 0) { + while ((xm >> (SP_FBITS + 3)) == 0) { xm <<= 1; xe--; } } - SPNORMRET1(xs, xe, xm, "sp_flong", x); -} - - -ieee754sp ieee754sp_fulong(u64 u) -{ - if ((s64) u < 0) - return ieee754sp_add(ieee754sp_1e63(), - ieee754sp_flong(u & ~(1ULL << 63))); - return ieee754sp_flong(u); + return ieee754sp_format(xs, xe, xm); } diff --git a/arch/mips/math-emu/sp_frexp.c b/arch/mips/math-emu/sp_frexp.c deleted file mode 100644 index 5bc993c30044..000000000000 --- a/arch/mips/math-emu/sp_frexp.c +++ /dev/null @@ -1,52 +0,0 @@ -/* IEEE754 floating point arithmetic - * single precision - */ -/* - * MIPS floating point support - * Copyright (C) 1994-2000 Algorithmics Ltd. - * - * ######################################################################## - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - */ - - -#include "ieee754sp.h" - -/* close to ieeep754sp_logb -*/ -ieee754sp ieee754sp_frexp(ieee754sp x, int *eptr) -{ - COMPXSP; - CLEARCX; - EXPLODEXSP; - - switch (xc) { - case IEEE754_CLASS_SNAN: - case IEEE754_CLASS_QNAN: - case IEEE754_CLASS_INF: - case IEEE754_CLASS_ZERO: - *eptr = 0; - return x; - case IEEE754_CLASS_DNORM: - SPDNORMX; - break; - case IEEE754_CLASS_NORM: - break; - } - *eptr = xe + 1; - return buildsp(xs, -1 + SP_EBIAS, xm & ~SP_HIDDEN_BIT); -} diff --git a/arch/mips/math-emu/sp_logb.c b/arch/mips/math-emu/sp_logb.c deleted file mode 100644 index 9c14e0c75bd2..000000000000 --- a/arch/mips/math-emu/sp_logb.c +++ /dev/null @@ -1,53 +0,0 @@ -/* IEEE754 floating point arithmetic - * single precision - */ -/* - * MIPS floating point support - * Copyright (C) 1994-2000 Algorithmics Ltd. - * - * ######################################################################## - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - */ - - -#include "ieee754sp.h" - -ieee754sp ieee754sp_logb(ieee754sp x) -{ - COMPXSP; - - CLEARCX; - - EXPLODEXSP; - - switch (xc) { - case IEEE754_CLASS_SNAN: - return ieee754sp_nanxcpt(x, "logb", x); - case IEEE754_CLASS_QNAN: - return x; - case IEEE754_CLASS_INF: - return ieee754sp_inf(0); - case IEEE754_CLASS_ZERO: - return ieee754sp_inf(1); - case IEEE754_CLASS_DNORM: - SPDNORMX; - break; - case IEEE754_CLASS_NORM: - break; - } - return ieee754sp_fint(xe); -} diff --git a/arch/mips/math-emu/sp_modf.c b/arch/mips/math-emu/sp_modf.c deleted file mode 100644 index 25a0fbaa0556..000000000000 --- a/arch/mips/math-emu/sp_modf.c +++ /dev/null @@ -1,79 +0,0 @@ -/* IEEE754 floating point arithmetic - * single precision - */ -/* - * MIPS floating point support - * Copyright (C) 1994-2000 Algorithmics Ltd. - * - * ######################################################################## - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - */ - - -#include "ieee754sp.h" - -/* modf function is always exact for a finite number -*/ -ieee754sp ieee754sp_modf(ieee754sp x, ieee754sp *ip) -{ - COMPXSP; - - CLEARCX; - - EXPLODEXSP; - - switch (xc) { - case IEEE754_CLASS_SNAN: - case IEEE754_CLASS_QNAN: - case IEEE754_CLASS_INF: - case IEEE754_CLASS_ZERO: - *ip = x; - return x; - case IEEE754_CLASS_DNORM: - /* far to small */ - *ip = ieee754sp_zero(xs); - return x; - case IEEE754_CLASS_NORM: - break; - } - if (xe < 0) { - *ip = ieee754sp_zero(xs); - return x; - } - if (xe >= SP_MBITS) { - *ip = x; - return ieee754sp_zero(xs); - } - /* generate ipart mantissa by clearing bottom bits - */ - *ip = buildsp(xs, xe + SP_EBIAS, - ((xm >> (SP_MBITS - xe)) << (SP_MBITS - xe)) & - ~SP_HIDDEN_BIT); - - /* generate fpart mantissa by clearing top bits - * and normalizing (must be able to normalize) - */ - xm = (xm << (32 - (SP_MBITS - xe))) >> (32 - (SP_MBITS - xe)); - if (xm == 0) - return ieee754sp_zero(xs); - - while ((xm >> SP_MBITS) == 0) { - xm <<= 1; - xe--; - } - return buildsp(xs, xe + SP_EBIAS, xm & ~SP_HIDDEN_BIT); -} diff --git a/arch/mips/math-emu/sp_mul.c b/arch/mips/math-emu/sp_mul.c index fa4675cf2aad..890c13a2965e 100644 --- a/arch/mips/math-emu/sp_mul.c +++ b/arch/mips/math-emu/sp_mul.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,23 +16,32 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" -ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y) +union ieee754sp ieee754sp_mul(union ieee754sp x, union ieee754sp y) { + int re; + int rs; + unsigned rm; + unsigned short lxm; + unsigned short hxm; + unsigned short lym; + unsigned short hym; + unsigned lrm; + unsigned hrm; + unsigned t; + unsigned at; + COMPXSP; COMPYSP; EXPLODEXSP; EXPLODEYSP; - CLEARCX; + ieee754_clearcx(); FLUSHXSP; FLUSHYSP; @@ -51,8 +58,8 @@ ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_nanxcpt(ieee754sp_indef(), "mul", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_nanxcpt(ieee754sp_indef()); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): @@ -68,12 +75,13 @@ ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y) return x; - /* Infinity handling */ - + /* + * Infinity handling + */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_xcpt(ieee754sp_indef(), "mul", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_indef(); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): @@ -108,63 +116,50 @@ ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y) assert(xm & SP_HIDDEN_BIT); assert(ym & SP_HIDDEN_BIT); - { - int re = xe + ye; - int rs = xs ^ ys; - unsigned rm; - - /* shunt to top of word */ - xm <<= 32 - (SP_MBITS + 1); - ym <<= 32 - (SP_MBITS + 1); - - /* multiply 32bits xm,ym to give high 32bits rm with stickness - */ - { - unsigned short lxm = xm & 0xffff; - unsigned short hxm = xm >> 16; - unsigned short lym = ym & 0xffff; - unsigned short hym = ym >> 16; - unsigned lrm; - unsigned hrm; - - lrm = lxm * lym; /* 16 * 16 => 32 */ - hrm = hxm * hym; /* 16 * 16 => 32 */ - - { - unsigned t = lxm * hym; /* 16 * 16 => 32 */ - { - unsigned at = lrm + (t << 16); - hrm += at < lrm; - lrm = at; - } - hrm = hrm + (t >> 16); - } - - { - unsigned t = hxm * lym; /* 16 * 16 => 32 */ - { - unsigned at = lrm + (t << 16); - hrm += at < lrm; - lrm = at; - } - hrm = hrm + (t >> 16); - } - rm = hrm | (lrm != 0); - } - - /* - * sticky shift down to normal rounding precision - */ - if ((int) rm < 0) { - rm = (rm >> (32 - (SP_MBITS + 1 + 3))) | - ((rm << (SP_MBITS + 1 + 3)) != 0); - re++; - } else { - rm = (rm >> (32 - (SP_MBITS + 1 + 3 + 1))) | - ((rm << (SP_MBITS + 1 + 3 + 1)) != 0); - } - assert(rm & (SP_HIDDEN_BIT << 3)); - - SPNORMRET2(rs, re, rm, "mul", x, y); + re = xe + ye; + rs = xs ^ ys; + + /* shunt to top of word */ + xm <<= 32 - (SP_FBITS + 1); + ym <<= 32 - (SP_FBITS + 1); + + /* + * Multiply 32 bits xm, ym to give high 32 bits rm with stickness. + */ + lxm = xm & 0xffff; + hxm = xm >> 16; + lym = ym & 0xffff; + hym = ym >> 16; + + lrm = lxm * lym; /* 16 * 16 => 32 */ + hrm = hxm * hym; /* 16 * 16 => 32 */ + + t = lxm * hym; /* 16 * 16 => 32 */ + at = lrm + (t << 16); + hrm += at < lrm; + lrm = at; + hrm = hrm + (t >> 16); + + t = hxm * lym; /* 16 * 16 => 32 */ + at = lrm + (t << 16); + hrm += at < lrm; + lrm = at; + hrm = hrm + (t >> 16); + + rm = hrm | (lrm != 0); + + /* + * Sticky shift down to normal rounding precision. + */ + if ((int) rm < 0) { + rm = (rm >> (32 - (SP_FBITS + 1 + 3))) | + ((rm << (SP_FBITS + 1 + 3)) != 0); + re++; + } else { + rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) | + ((rm << (SP_FBITS + 1 + 3 + 1)) != 0); } + assert(rm & (SP_HIDDEN_BIT << 3)); + + return ieee754sp_format(rs, re, rm); } diff --git a/arch/mips/math-emu/sp_scalb.c b/arch/mips/math-emu/sp_scalb.c deleted file mode 100644 index dd76196984c8..000000000000 --- a/arch/mips/math-emu/sp_scalb.c +++ /dev/null @@ -1,57 +0,0 @@ -/* IEEE754 floating point arithmetic - * single precision - */ -/* - * MIPS floating point support - * Copyright (C) 1994-2000 Algorithmics Ltd. - * - * ######################################################################## - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License (Version 2) as - * published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## - */ - - -#include "ieee754sp.h" - -ieee754sp ieee754sp_scalb(ieee754sp x, int n) -{ - COMPXSP; - - CLEARCX; - - EXPLODEXSP; - - switch (xc) { - case IEEE754_CLASS_SNAN: - return ieee754sp_nanxcpt(x, "scalb", x, n); - case IEEE754_CLASS_QNAN: - case IEEE754_CLASS_INF: - case IEEE754_CLASS_ZERO: - return x; - case IEEE754_CLASS_DNORM: - SPDNORMX; - break; - case IEEE754_CLASS_NORM: - break; - } - SPNORMRET2(xs, xe + n, xm << 3, "scalb", x, n); -} - - -ieee754sp ieee754sp_ldexp(ieee754sp x, int n) -{ - return ieee754sp_scalb(x, n); -} diff --git a/arch/mips/math-emu/sp_simple.c b/arch/mips/math-emu/sp_simple.c index ae4fcfafd853..f1ffaa9a17e0 100644 --- a/arch/mips/math-emu/sp_simple.c +++ b/arch/mips/math-emu/sp_simple.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,33 +16,17 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" -int ieee754sp_finite(ieee754sp x) -{ - return SPBEXP(x) != SP_EMAX + 1 + SP_EBIAS; -} - -ieee754sp ieee754sp_copysign(ieee754sp x, ieee754sp y) -{ - CLEARCX; - SPSIGN(x) = SPSIGN(y); - return x; -} - - -ieee754sp ieee754sp_neg(ieee754sp x) +union ieee754sp ieee754sp_neg(union ieee754sp x) { COMPXSP; EXPLODEXSP; - CLEARCX; + ieee754_clearcx(); FLUSHXSP; /* @@ -55,30 +37,29 @@ ieee754sp ieee754sp_neg(ieee754sp x) SPSIGN(x) ^= 1; if (xc == IEEE754_CLASS_SNAN) { - ieee754sp y = ieee754sp_indef(); - SETCX(IEEE754_INVALID_OPERATION); + union ieee754sp y = ieee754sp_indef(); + ieee754_setcx(IEEE754_INVALID_OPERATION); SPSIGN(y) = SPSIGN(x); - return ieee754sp_nanxcpt(y, "neg"); + return ieee754sp_nanxcpt(y); } return x; } - -ieee754sp ieee754sp_abs(ieee754sp x) +union ieee754sp ieee754sp_abs(union ieee754sp x) { COMPXSP; EXPLODEXSP; - CLEARCX; + ieee754_clearcx(); FLUSHXSP; /* Clear sign ALWAYS, irrespective of NaN */ SPSIGN(x) = 0; if (xc == IEEE754_CLASS_SNAN) { - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_nanxcpt(ieee754sp_indef(), "abs"); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_nanxcpt(ieee754sp_indef()); } return x; diff --git a/arch/mips/math-emu/sp_sqrt.c b/arch/mips/math-emu/sp_sqrt.c index fed20175f5fb..b7c098a86f95 100644 --- a/arch/mips/math-emu/sp_sqrt.c +++ b/arch/mips/math-emu/sp_sqrt.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,15 +16,12 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" -ieee754sp ieee754sp_sqrt(ieee754sp x) +union ieee754sp ieee754sp_sqrt(union ieee754sp x) { int ix, s, q, m, t, i; unsigned int r; @@ -35,34 +30,38 @@ ieee754sp ieee754sp_sqrt(ieee754sp x) /* take care of Inf and NaN */ EXPLODEXSP; - CLEARCX; + ieee754_clearcx(); FLUSHXSP; /* x == INF or NAN? */ switch (xc) { case IEEE754_CLASS_QNAN: /* sqrt(Nan) = Nan */ - return ieee754sp_nanxcpt(x, "sqrt"); + return ieee754sp_nanxcpt(x); + case IEEE754_CLASS_SNAN: - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_nanxcpt(ieee754sp_indef(), "sqrt"); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_nanxcpt(ieee754sp_indef()); + case IEEE754_CLASS_ZERO: /* sqrt(0) = 0 */ return x; + case IEEE754_CLASS_INF: if (xs) { /* sqrt(-Inf) = Nan */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_nanxcpt(ieee754sp_indef(), "sqrt"); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_nanxcpt(ieee754sp_indef()); } /* sqrt(+Inf) = Inf */ return x; + case IEEE754_CLASS_DNORM: case IEEE754_CLASS_NORM: if (xs) { /* sqrt(-x) = Nan */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_nanxcpt(ieee754sp_indef(), "sqrt"); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_nanxcpt(ieee754sp_indef()); } break; } @@ -99,12 +98,12 @@ ieee754sp ieee754sp_sqrt(ieee754sp x) } if (ix != 0) { - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_INEXACT); switch (ieee754_csr.rm) { - case IEEE754_RP: + case FPU_CSR_RU: q += 2; break; - case IEEE754_RN: + case FPU_CSR_RN: q += (q & 1); break; } diff --git a/arch/mips/math-emu/sp_sub.c b/arch/mips/math-emu/sp_sub.c index e595c6f3d0bb..8592e49032b8 100644 --- a/arch/mips/math-emu/sp_sub.c +++ b/arch/mips/math-emu/sp_sub.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,23 +16,22 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" -ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y) +union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y) { + int s; + COMPXSP; COMPYSP; EXPLODEXSP; EXPLODEYSP; - CLEARCX; + ieee754_clearcx(); FLUSHXSP; FLUSHYSP; @@ -51,8 +48,8 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_nanxcpt(ieee754sp_indef(), "sub", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_nanxcpt(ieee754sp_indef()); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): @@ -68,14 +65,14 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y) return x; - /* Infinity handling - */ - + /* + * Infinity handling + */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): if (xs != ys) return x; - SETCX(IEEE754_INVALID_OPERATION); - return ieee754sp_xcpt(ieee754sp_indef(), "sub", x, y); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_indef(); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): @@ -87,15 +84,14 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y) case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): return x; - /* Zero handling - */ - + /* + * Zero handling + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): if (xs != ys) return x; else - return ieee754sp_zero(ieee754_csr.rm == - IEEE754_RD); + return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD); case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): @@ -104,7 +100,7 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y) case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM): /* quick fix up */ - DPSIGN(y) ^= 1; + SPSIGN(y) ^= 1; return y; case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): @@ -133,14 +129,16 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y) ym <<= 3; if (xe > ye) { - /* have to shift y fraction right to align + /* + * have to shift y fraction right to align */ - int s = xe - ye; + s = xe - ye; SPXSRSYn(s); } else if (ye > xe) { - /* have to shift x fraction right to align + /* + * have to shift x fraction right to align */ - int s = ye - xe; + s = ye - xe; SPXSRSXn(s); } assert(xe == ye); @@ -153,7 +151,7 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y) xe = xe; xs = xs; - if (xm >> (SP_MBITS + 1 + 3)) { /* carry out */ + if (xm >> (SP_FBITS + 1 + 3)) { /* carry out */ SPXSRSX1(); /* shift preserving sticky */ } } else { @@ -167,17 +165,18 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y) xs = ys; } if (xm == 0) { - if (ieee754_csr.rm == IEEE754_RD) + if (ieee754_csr.rm == FPU_CSR_RD) return ieee754sp_zero(1); /* round negative inf. => sign = -1 */ else return ieee754sp_zero(0); /* other round modes => sign = 1 */ } /* normalize to rounding precision */ - while ((xm >> (SP_MBITS + 3)) == 0) { + while ((xm >> (SP_FBITS + 3)) == 0) { xm <<= 1; xe--; } } - SPNORMRET2(xs, xe, xm, "sub", x, y); + + return ieee754sp_format(xs, xe, xm); } diff --git a/arch/mips/math-emu/sp_tint.c b/arch/mips/math-emu/sp_tint.c index 0fe9acc7716e..091299a31798 100644 --- a/arch/mips/math-emu/sp_tint.c +++ b/arch/mips/math-emu/sp_tint.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,20 +16,21 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - -#include <linux/kernel.h> #include "ieee754sp.h" -int ieee754sp_tint(ieee754sp x) +int ieee754sp_tint(union ieee754sp x) { + u32 residue; + int round; + int sticky; + int odd; + COMPXSP; - CLEARCX; + ieee754_clearcx(); EXPLODEXSP; FLUSHXSP; @@ -40,10 +39,12 @@ int ieee754sp_tint(ieee754sp x) case IEEE754_CLASS_SNAN: case IEEE754_CLASS_QNAN: case IEEE754_CLASS_INF: - SETCX(IEEE754_INVALID_OPERATION); - return ieee754si_xcpt(ieee754si_indef(), "sp_tint", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754si_indef(); + case IEEE754_CLASS_ZERO: return 0; + case IEEE754_CLASS_DNORM: case IEEE754_CLASS_NORM: break; @@ -54,18 +55,13 @@ int ieee754sp_tint(ieee754sp x) return -0x80000000; /* Set invalid. We will only use overflow for floating point overflow */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754si_xcpt(ieee754si_indef(), "sp_tint", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754si_indef(); } /* oh gawd */ - if (xe > SP_MBITS) { - xm <<= xe - SP_MBITS; + if (xe > SP_FBITS) { + xm <<= xe - SP_FBITS; } else { - u32 residue; - int round; - int sticky; - int odd; - if (xe < -1) { residue = xm; round = 0; @@ -76,51 +72,38 @@ int ieee754sp_tint(ieee754sp x) * so we do it in two steps. Be aware that xe * may be -1 */ residue = xm << (xe + 1); - residue <<= 31 - SP_MBITS; + residue <<= 31 - SP_FBITS; round = (residue >> 31) != 0; sticky = (residue << 1) != 0; - xm >>= SP_MBITS - xe; + xm >>= SP_FBITS - xe; } odd = (xm & 0x1) != 0x0; switch (ieee754_csr.rm) { - case IEEE754_RN: + case FPU_CSR_RN: if (round && (sticky || odd)) xm++; break; - case IEEE754_RZ: + case FPU_CSR_RZ: break; - case IEEE754_RU: /* toward +Infinity */ + case FPU_CSR_RU: /* toward +Infinity */ if ((round || sticky) && !xs) xm++; break; - case IEEE754_RD: /* toward -Infinity */ + case FPU_CSR_RD: /* toward -Infinity */ if ((round || sticky) && xs) xm++; break; } if ((xm >> 31) != 0) { /* This can happen after rounding */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754si_xcpt(ieee754si_indef(), "sp_tint", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754si_indef(); } if (round || sticky) - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_INEXACT); } if (xs) return -xm; else return xm; } - - -unsigned int ieee754sp_tuns(ieee754sp x) -{ - ieee754sp hb = ieee754sp_1e31(); - - /* what if x < 0 ?? */ - if (ieee754sp_lt(x, hb)) - return (unsigned) ieee754sp_tint(x); - - return (unsigned) ieee754sp_tint(ieee754sp_sub(x, hb)) | - ((unsigned) 1 << 31); -} diff --git a/arch/mips/math-emu/sp_tlong.c b/arch/mips/math-emu/sp_tlong.c index d0ca6e22be29..9f3c742c1cea 100644 --- a/arch/mips/math-emu/sp_tlong.c +++ b/arch/mips/math-emu/sp_tlong.c @@ -5,8 +5,6 @@ * MIPS floating point support * Copyright (C) 1994-2000 Algorithmics Ltd. * - * ######################################################################## - * * This program is free software; you can distribute it and/or modify it * under the terms of the GNU General Public License (Version 2) as * published by the Free Software Foundation. @@ -18,19 +16,22 @@ * * You should have received a copy of the GNU General Public License along * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. - * - * ######################################################################## + * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. */ - #include "ieee754sp.h" +#include "ieee754dp.h" -s64 ieee754sp_tlong(ieee754sp x) +s64 ieee754sp_tlong(union ieee754sp x) { + u32 residue; + int round; + int sticky; + int odd; + COMPXDP; /* <-- need 64-bit mantissa tmp */ - CLEARCX; + ieee754_clearcx(); EXPLODEXSP; FLUSHXSP; @@ -39,10 +40,12 @@ s64 ieee754sp_tlong(ieee754sp x) case IEEE754_CLASS_SNAN: case IEEE754_CLASS_QNAN: case IEEE754_CLASS_INF: - SETCX(IEEE754_INVALID_OPERATION); - return ieee754di_xcpt(ieee754di_indef(), "sp_tlong", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754di_indef(); + case IEEE754_CLASS_ZERO: return 0; + case IEEE754_CLASS_DNORM: case IEEE754_CLASS_NORM: break; @@ -53,69 +56,51 @@ s64 ieee754sp_tlong(ieee754sp x) return -0x8000000000000000LL; /* Set invalid. We will only use overflow for floating point overflow */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754di_xcpt(ieee754di_indef(), "sp_tlong", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754di_indef(); } /* oh gawd */ - if (xe > SP_MBITS) { - xm <<= xe - SP_MBITS; - } else if (xe < SP_MBITS) { - u32 residue; - int round; - int sticky; - int odd; - + if (xe > SP_FBITS) { + xm <<= xe - SP_FBITS; + } else if (xe < SP_FBITS) { if (xe < -1) { residue = xm; round = 0; sticky = residue != 0; xm = 0; } else { - residue = xm << (32 - SP_MBITS + xe); + residue = xm << (32 - SP_FBITS + xe); round = (residue >> 31) != 0; sticky = (residue << 1) != 0; - xm >>= SP_MBITS - xe; + xm >>= SP_FBITS - xe; } odd = (xm & 0x1) != 0x0; switch (ieee754_csr.rm) { - case IEEE754_RN: + case FPU_CSR_RN: if (round && (sticky || odd)) xm++; break; - case IEEE754_RZ: + case FPU_CSR_RZ: break; - case IEEE754_RU: /* toward +Infinity */ + case FPU_CSR_RU: /* toward +Infinity */ if ((round || sticky) && !xs) xm++; break; - case IEEE754_RD: /* toward -Infinity */ + case FPU_CSR_RD: /* toward -Infinity */ if ((round || sticky) && xs) xm++; break; } if ((xm >> 63) != 0) { /* This can happen after rounding */ - SETCX(IEEE754_INVALID_OPERATION); - return ieee754di_xcpt(ieee754di_indef(), "sp_tlong", x); + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754di_indef(); } if (round || sticky) - SETCX(IEEE754_INEXACT); + ieee754_setcx(IEEE754_INEXACT); } if (xs) return -xm; else return xm; } - - -u64 ieee754sp_tulong(ieee754sp x) -{ - ieee754sp hb = ieee754sp_1e63(); - - /* what if x < 0 ?? */ - if (ieee754sp_lt(x, hb)) - return (u64) ieee754sp_tlong(x); - - return (u64) ieee754sp_tlong(ieee754sp_sub(x, hb)) | - (1ULL << 63); -} diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c index f41a5c5b0865..05b1d7cf9514 100644 --- a/arch/mips/mm/c-octeon.c +++ b/arch/mips/mm/c-octeon.c @@ -137,8 +137,10 @@ static void octeon_flush_cache_sigtramp(unsigned long addr) { struct vm_area_struct *vma; + down_read(¤t->mm->mmap_sem); vma = find_vma(current->mm, addr); octeon_flush_icache_all_cores(vma); + up_read(¤t->mm->mmap_sem); } diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 1c74a6ad072a..f2e8302fa70f 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -7,6 +7,7 @@ * Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002 Ralf Baechle (ralf@gnu.org) * Copyright (C) 1999, 2000 Silicon Graphics, Inc. */ +#include <linux/cpu_pm.h> #include <linux/hardirq.h> #include <linux/init.h> #include <linux/highmem.h> @@ -50,7 +51,7 @@ static inline void r4k_on_each_cpu(void (*func) (void *info), void *info) { preempt_disable(); -#if !defined(CONFIG_MIPS_MT_SMP) && !defined(CONFIG_MIPS_MT_SMTC) +#ifndef CONFIG_MIPS_MT_SMP smp_call_function(func, info, 1); #endif func(info); @@ -105,22 +106,37 @@ static inline void r4k_blast_dcache_page_dc32(unsigned long addr) static inline void r4k_blast_dcache_page_dc64(unsigned long addr) { - R4600_HIT_CACHEOP_WAR_IMPL; blast_dcache64_page(addr); } +static inline void r4k_blast_dcache_page_dc128(unsigned long addr) +{ + blast_dcache128_page(addr); +} + static void r4k_blast_dcache_page_setup(void) { unsigned long dc_lsize = cpu_dcache_line_size(); - if (dc_lsize == 0) + switch (dc_lsize) { + case 0: r4k_blast_dcache_page = (void *)cache_noop; - else if (dc_lsize == 16) + break; + case 16: r4k_blast_dcache_page = blast_dcache16_page; - else if (dc_lsize == 32) + break; + case 32: r4k_blast_dcache_page = r4k_blast_dcache_page_dc32; - else if (dc_lsize == 64) + break; + case 64: r4k_blast_dcache_page = r4k_blast_dcache_page_dc64; + break; + case 128: + r4k_blast_dcache_page = r4k_blast_dcache_page_dc128; + break; + default: + break; + } } #ifndef CONFIG_EVA @@ -159,6 +175,8 @@ static void r4k_blast_dcache_page_indexed_setup(void) r4k_blast_dcache_page_indexed = blast_dcache32_page_indexed; else if (dc_lsize == 64) r4k_blast_dcache_page_indexed = blast_dcache64_page_indexed; + else if (dc_lsize == 128) + r4k_blast_dcache_page_indexed = blast_dcache128_page_indexed; } void (* r4k_blast_dcache)(void); @@ -176,6 +194,8 @@ static void r4k_blast_dcache_setup(void) r4k_blast_dcache = blast_dcache32; else if (dc_lsize == 64) r4k_blast_dcache = blast_dcache64; + else if (dc_lsize == 128) + r4k_blast_dcache = blast_dcache128; } /* force code alignment (used for TX49XX_ICACHE_INDEX_INV_WAR) */ @@ -265,6 +285,8 @@ static void r4k_blast_icache_page_setup(void) r4k_blast_icache_page = blast_icache32_page; else if (ic_lsize == 64) r4k_blast_icache_page = blast_icache64_page; + else if (ic_lsize == 128) + r4k_blast_icache_page = blast_icache128_page; } #ifndef CONFIG_EVA @@ -338,6 +360,8 @@ static void r4k_blast_icache_setup(void) r4k_blast_icache = blast_icache32; } else if (ic_lsize == 64) r4k_blast_icache = blast_icache64; + else if (ic_lsize == 128) + r4k_blast_icache = blast_icache128; } static void (* r4k_blast_scache_page)(unsigned long addr); @@ -428,7 +452,7 @@ static void r4k___flush_cache_all(void) static inline int has_valid_asid(const struct mm_struct *mm) { -#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC) +#ifdef CONFIG_MIPS_MT_SMP int i; for_each_online_cpu(i) @@ -1094,6 +1118,21 @@ static void probe_pcache(void) c->dcache.waybit = 0; break; + case CPU_CAVIUM_OCTEON3: + /* For now lie about the number of ways. */ + c->icache.linesz = 128; + c->icache.sets = 16; + c->icache.ways = 8; + c->icache.flags |= MIPS_CACHE_VTAG; + icache_size = c->icache.sets * c->icache.ways * c->icache.linesz; + + c->dcache.linesz = 128; + c->dcache.ways = 8; + c->dcache.sets = 8; + dcache_size = c->dcache.sets * c->dcache.ways * c->dcache.linesz; + c->options |= MIPS_CPU_PREFETCH; + break; + default: if (!(config & MIPS_CONF_M)) panic("Don't know how to probe P-caches on this cpu."); @@ -1414,6 +1453,7 @@ static void setup_scache(void) loongson3_sc_init(); return; + case CPU_CAVIUM_OCTEON3: case CPU_XLP: /* don't need to worry about L2, fully coherent */ return; @@ -1644,3 +1684,26 @@ void r4k_cache_init(void) coherency_setup(); board_cache_error_setup = r4k_cache_error_setup; } + +static int r4k_cache_pm_notifier(struct notifier_block *self, unsigned long cmd, + void *v) +{ + switch (cmd) { + case CPU_PM_ENTER_FAILED: + case CPU_PM_EXIT: + coherency_setup(); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block r4k_cache_pm_notifier_block = { + .notifier_call = r4k_cache_pm_notifier, +}; + +int __init r4k_cache_init_pm(void) +{ + return cpu_pm_register_notifier(&r4k_cache_pm_notifier_block); +} +arch_initcall(r4k_cache_init_pm); diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c index 77e0ae036e7c..4ec8ee10d371 100644 --- a/arch/mips/mm/hugetlbpage.c +++ b/arch/mips/mm/hugetlbpage.c @@ -84,11 +84,6 @@ int pud_huge(pud_t pud) return (pud_val(pud) & _PAGE_HUGE) != 0; } -int pmd_huge_support(void) -{ - return 1; -} - struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 4fc74c78265a..6e4413330e36 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -44,27 +44,6 @@ #include <asm/tlb.h> #include <asm/fixmap.h> -/* Atomicity and interruptability */ -#ifdef CONFIG_MIPS_MT_SMTC - -#include <asm/mipsmtregs.h> - -#define ENTER_CRITICAL(flags) \ - { \ - unsigned int mvpflags; \ - local_irq_save(flags);\ - mvpflags = dvpe() -#define EXIT_CRITICAL(flags) \ - evpe(mvpflags); \ - local_irq_restore(flags); \ - } -#else - -#define ENTER_CRITICAL(flags) local_irq_save(flags) -#define EXIT_CRITICAL(flags) local_irq_restore(flags) - -#endif /* CONFIG_MIPS_MT_SMTC */ - /* * We have up to 8 empty zeroed pages so we can map one of the right colour * when needed. This is necessary only on R4000 / R4400 SC and MC versions @@ -100,21 +79,7 @@ void setup_zero_pages(void) zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK; } -#ifdef CONFIG_MIPS_MT_SMTC -static pte_t *kmap_coherent_pte; -static void __init kmap_coherent_init(void) -{ - unsigned long vaddr; - - /* cache the first coherent kmap pte */ - vaddr = __fix_to_virt(FIX_CMAP_BEGIN); - kmap_coherent_pte = kmap_get_fixmap_pte(vaddr); -} -#else -static inline void kmap_coherent_init(void) {} -#endif - -void *kmap_coherent(struct page *page, unsigned long addr) +static void *__kmap_pgprot(struct page *page, unsigned long addr, pgprot_t prot) { enum fixed_addresses idx; unsigned long vaddr, flags, entrylo; @@ -126,58 +91,48 @@ void *kmap_coherent(struct page *page, unsigned long addr) pagefault_disable(); idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1); -#ifdef CONFIG_MIPS_MT_SMTC - idx += FIX_N_COLOURS * smp_processor_id() + - (in_interrupt() ? (FIX_N_COLOURS * NR_CPUS) : 0); -#else idx += in_interrupt() ? FIX_N_COLOURS : 0; -#endif vaddr = __fix_to_virt(FIX_CMAP_END - idx); - pte = mk_pte(page, PAGE_KERNEL); + pte = mk_pte(page, prot); #if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32) entrylo = pte.pte_high; #else entrylo = pte_to_entrylo(pte_val(pte)); #endif - ENTER_CRITICAL(flags); + local_irq_save(flags); old_ctx = read_c0_entryhi(); write_c0_entryhi(vaddr & (PAGE_MASK << 1)); write_c0_entrylo0(entrylo); write_c0_entrylo1(entrylo); -#ifdef CONFIG_MIPS_MT_SMTC - set_pte(kmap_coherent_pte - (FIX_CMAP_END - idx), pte); - /* preload TLB instead of local_flush_tlb_one() */ - mtc0_tlbw_hazard(); - tlb_probe(); - tlb_probe_hazard(); - tlbidx = read_c0_index(); - mtc0_tlbw_hazard(); - if (tlbidx < 0) - tlb_write_random(); - else - tlb_write_indexed(); -#else tlbidx = read_c0_wired(); write_c0_wired(tlbidx + 1); write_c0_index(tlbidx); mtc0_tlbw_hazard(); tlb_write_indexed(); -#endif tlbw_use_hazard(); write_c0_entryhi(old_ctx); - EXIT_CRITICAL(flags); + local_irq_restore(flags); return (void*) vaddr; } +void *kmap_coherent(struct page *page, unsigned long addr) +{ + return __kmap_pgprot(page, addr, PAGE_KERNEL); +} + +void *kmap_noncoherent(struct page *page, unsigned long addr) +{ + return __kmap_pgprot(page, addr, PAGE_KERNEL_NC); +} + void kunmap_coherent(void) { -#ifndef CONFIG_MIPS_MT_SMTC unsigned int wired; unsigned long flags, old_ctx; - ENTER_CRITICAL(flags); + local_irq_save(flags); old_ctx = read_c0_entryhi(); wired = read_c0_wired() - 1; write_c0_wired(wired); @@ -189,8 +144,7 @@ void kunmap_coherent(void) tlb_write_indexed(); tlbw_use_hazard(); write_c0_entryhi(old_ctx); - EXIT_CRITICAL(flags); -#endif + local_irq_restore(flags); pagefault_enable(); } @@ -256,7 +210,7 @@ EXPORT_SYMBOL_GPL(copy_from_user_page); void __init fixrange_init(unsigned long start, unsigned long end, pgd_t *pgd_base) { -#if defined(CONFIG_HIGHMEM) || defined(CONFIG_MIPS_MT_SMTC) +#ifdef CONFIG_HIGHMEM pgd_t *pgd; pud_t *pud; pmd_t *pmd; @@ -327,8 +281,6 @@ void __init paging_init(void) #ifdef CONFIG_HIGHMEM kmap_init(); #endif - kmap_coherent_init(); - #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; #endif diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index eeaf50f5df2b..3914e27456f2 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -8,6 +8,7 @@ * Carsten Langgaard, carstenl@mips.com * Copyright (C) 2002 MIPS Technologies, Inc. All rights reserved. */ +#include <linux/cpu_pm.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/smp.h> @@ -25,28 +26,6 @@ extern void build_tlb_refill_handler(void); -/* Atomicity and interruptability */ -#ifdef CONFIG_MIPS_MT_SMTC - -#include <asm/smtc.h> -#include <asm/mipsmtregs.h> - -#define ENTER_CRITICAL(flags) \ - { \ - unsigned int mvpflags; \ - local_irq_save(flags);\ - mvpflags = dvpe() -#define EXIT_CRITICAL(flags) \ - evpe(mvpflags); \ - local_irq_restore(flags); \ - } -#else - -#define ENTER_CRITICAL(flags) local_irq_save(flags) -#define EXIT_CRITICAL(flags) local_irq_restore(flags) - -#endif /* CONFIG_MIPS_MT_SMTC */ - /* * LOONGSON2/3 has a 4 entry itlb which is a subset of dtlb, * unfortunately, itlb is not totally transparent to software. @@ -75,7 +54,7 @@ void local_flush_tlb_all(void) unsigned long old_ctx; int entry, ftlbhighset; - ENTER_CRITICAL(flags); + local_irq_save(flags); /* Save old context and create impossible VPN2 value */ old_ctx = read_c0_entryhi(); write_c0_entrylo0(0); @@ -112,7 +91,7 @@ void local_flush_tlb_all(void) tlbw_use_hazard(); write_c0_entryhi(old_ctx); flush_itlb(); - EXIT_CRITICAL(flags); + local_irq_restore(flags); } EXPORT_SYMBOL(local_flush_tlb_all); @@ -142,7 +121,7 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, if (cpu_context(cpu, mm) != 0) { unsigned long size, flags; - ENTER_CRITICAL(flags); + local_irq_save(flags); start = round_down(start, PAGE_SIZE << 1); end = round_up(end, PAGE_SIZE << 1); size = (end - start) >> (PAGE_SHIFT + 1); @@ -176,7 +155,7 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, drop_mmu_context(mm, cpu); } flush_itlb(); - EXIT_CRITICAL(flags); + local_irq_restore(flags); } } @@ -184,7 +163,7 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) { unsigned long size, flags; - ENTER_CRITICAL(flags); + local_irq_save(flags); size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT; size = (size + 1) >> 1; if (size <= (current_cpu_data.tlbsizeftlbsets ? @@ -220,7 +199,7 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) local_flush_tlb_all(); } flush_itlb(); - EXIT_CRITICAL(flags); + local_irq_restore(flags); } void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page) @@ -233,7 +212,7 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page) newpid = cpu_asid(cpu, vma->vm_mm); page &= (PAGE_MASK << 1); - ENTER_CRITICAL(flags); + local_irq_save(flags); oldpid = read_c0_entryhi(); write_c0_entryhi(page | newpid); mtc0_tlbw_hazard(); @@ -253,7 +232,7 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page) finish: write_c0_entryhi(oldpid); flush_itlb_vm(vma); - EXIT_CRITICAL(flags); + local_irq_restore(flags); } } @@ -266,7 +245,7 @@ void local_flush_tlb_one(unsigned long page) unsigned long flags; int oldpid, idx; - ENTER_CRITICAL(flags); + local_irq_save(flags); oldpid = read_c0_entryhi(); page &= (PAGE_MASK << 1); write_c0_entryhi(page); @@ -285,7 +264,7 @@ void local_flush_tlb_one(unsigned long page) } write_c0_entryhi(oldpid); flush_itlb(); - EXIT_CRITICAL(flags); + local_irq_restore(flags); } /* @@ -308,7 +287,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte) if (current->active_mm != vma->vm_mm) return; - ENTER_CRITICAL(flags); + local_irq_save(flags); pid = read_c0_entryhi() & ASID_MASK; address &= (PAGE_MASK << 1); @@ -358,7 +337,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte) } tlbw_use_hazard(); flush_itlb_vm(vma); - EXIT_CRITICAL(flags); + local_irq_restore(flags); } void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1, @@ -369,7 +348,7 @@ void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1, unsigned long old_pagemask; unsigned long old_ctx; - ENTER_CRITICAL(flags); + local_irq_save(flags); /* Save old context and create impossible VPN2 value */ old_ctx = read_c0_entryhi(); old_pagemask = read_c0_pagemask(); @@ -389,7 +368,7 @@ void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1, tlbw_use_hazard(); /* What is the hazard here? */ write_c0_pagemask(old_pagemask); local_flush_tlb_all(); - EXIT_CRITICAL(flags); + local_irq_restore(flags); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -399,13 +378,13 @@ int __init has_transparent_hugepage(void) unsigned int mask; unsigned long flags; - ENTER_CRITICAL(flags); + local_irq_save(flags); write_c0_pagemask(PM_HUGE_MASK); back_to_back_c0_hazard(); mask = read_c0_pagemask(); write_c0_pagemask(PM_DEFAULT_MASK); - EXIT_CRITICAL(flags); + local_irq_restore(flags); return mask == PM_HUGE_MASK; } @@ -421,7 +400,10 @@ static int __init set_ntlb(char *str) __setup("ntlb=", set_ntlb); -void tlb_init(void) +/* + * Configure TLB (for init or after a CPU has been powered off). + */ +static void r4k_tlb_configure(void) { /* * You should never change this register: @@ -453,6 +435,11 @@ void tlb_init(void) local_flush_tlb_all(); /* Did I tell you that ARC SUCKS? */ +} + +void tlb_init(void) +{ + r4k_tlb_configure(); if (ntlb) { if (ntlb > 1 && ntlb <= current_cpu_data.tlbsize) { @@ -466,3 +453,26 @@ void tlb_init(void) build_tlb_refill_handler(); } + +static int r4k_tlb_pm_notifier(struct notifier_block *self, unsigned long cmd, + void *v) +{ + switch (cmd) { + case CPU_PM_ENTER_FAILED: + case CPU_PM_EXIT: + r4k_tlb_configure(); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block r4k_tlb_pm_notifier_block = { + .notifier_call = r4k_tlb_pm_notifier, +}; + +static int __init r4k_tlb_init_pm(void) +{ + return cpu_pm_register_notifier(&r4k_tlb_pm_notifier_block); +} +arch_initcall(r4k_tlb_init_pm); diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index f99ec587b151..e80e10bafc83 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -1256,7 +1256,7 @@ static void build_r4000_tlb_refill_handler(void) memset(relocs, 0, sizeof(relocs)); memset(final_handler, 0, sizeof(final_handler)); - if ((scratch_reg >= 0 || scratchpad_available()) && use_bbit_insns()) { + if (IS_ENABLED(CONFIG_64BIT) && (scratch_reg >= 0 || scratchpad_available()) && use_bbit_insns()) { htlb_info = build_fast_tlb_refill_handler(&p, &l, &r, K0, K1, scratch_reg); vmalloc_mode = refill_scratch; diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c index b8d580ca02e5..775c2800cba2 100644 --- a/arch/mips/mm/uasm-micromips.c +++ b/arch/mips/mm/uasm-micromips.c @@ -63,6 +63,7 @@ static struct insn insn_table_MM[] = { { insn_cache, M(mm_pool32b_op, 0, 0, mm_cache_func, 0, 0), RT | RS | SIMM }, { insn_daddu, 0, 0 }, { insn_daddiu, 0, 0 }, + { insn_divu, M(mm_pool32a_op, 0, 0, 0, mm_divu_op, mm_pool32axf_op), RT | RS }, { insn_dmfc0, 0, 0 }, { insn_dmtc0, 0, 0 }, { insn_dsll, 0, 0 }, @@ -78,14 +79,20 @@ static struct insn insn_table_MM[] = { { insn_ext, M(mm_pool32a_op, 0, 0, 0, 0, mm_ext_op), RT | RS | RD | RE }, { insn_j, M(mm_j32_op, 0, 0, 0, 0, 0), JIMM }, { insn_jal, M(mm_jal32_op, 0, 0, 0, 0, 0), JIMM }, + { insn_jalr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RT | RS }, { insn_jr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS }, + { insn_lb, M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, { insn_ld, 0, 0 }, + { insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM }, { insn_ll, M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM }, { insn_lld, 0, 0 }, { insn_lui, M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM }, { insn_lw, M(mm_lw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, { insn_mfc0, M(mm_pool32a_op, 0, 0, 0, mm_mfc0_op, mm_pool32axf_op), RT | RS | RD }, + { insn_mfhi, M(mm_pool32a_op, 0, 0, 0, mm_mfhi32_op, mm_pool32axf_op), RS }, + { insn_mflo, M(mm_pool32a_op, 0, 0, 0, mm_mflo32_op, mm_pool32axf_op), RS }, { insn_mtc0, M(mm_pool32a_op, 0, 0, 0, mm_mtc0_op, mm_pool32axf_op), RT | RS | RD }, + { insn_mul, M(mm_pool32a_op, 0, 0, 0, 0, mm_mul_op), RT | RS | RD }, { insn_or, M(mm_pool32a_op, 0, 0, 0, 0, mm_or32_op), RT | RS | RD }, { insn_ori, M(mm_ori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM }, { insn_pref, M(mm_pool32c_op, 0, 0, (mm_pref_func << 1), 0, 0), RT | RS | SIMM }, @@ -94,15 +101,22 @@ static struct insn insn_table_MM[] = { { insn_scd, 0, 0 }, { insn_sd, 0, 0 }, { insn_sll, M(mm_pool32a_op, 0, 0, 0, 0, mm_sll32_op), RT | RS | RD }, + { insn_sllv, M(mm_pool32a_op, 0, 0, 0, 0, mm_sllv32_op), RT | RS | RD }, + { insn_sltiu, M(mm_sltiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, + { insn_sltu, M(mm_pool32a_op, 0, 0, 0, 0, mm_sltu_op), RT | RS | RD }, { insn_sra, M(mm_pool32a_op, 0, 0, 0, 0, mm_sra_op), RT | RS | RD }, { insn_srl, M(mm_pool32a_op, 0, 0, 0, 0, mm_srl32_op), RT | RS | RD }, + { insn_srlv, M(mm_pool32a_op, 0, 0, 0, 0, mm_srlv32_op), RT | RS | RD }, { insn_rotr, M(mm_pool32a_op, 0, 0, 0, 0, mm_rotr_op), RT | RS | RD }, { insn_subu, M(mm_pool32a_op, 0, 0, 0, 0, mm_subu32_op), RT | RS | RD }, { insn_sw, M(mm_sw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, + { insn_sync, M(mm_pool32a_op, 0, 0, 0, mm_sync_op, mm_pool32axf_op), RS }, { insn_tlbp, M(mm_pool32a_op, 0, 0, 0, mm_tlbp_op, mm_pool32axf_op), 0 }, { insn_tlbr, M(mm_pool32a_op, 0, 0, 0, mm_tlbr_op, mm_pool32axf_op), 0 }, { insn_tlbwi, M(mm_pool32a_op, 0, 0, 0, mm_tlbwi_op, mm_pool32axf_op), 0 }, { insn_tlbwr, M(mm_pool32a_op, 0, 0, 0, mm_tlbwr_op, mm_pool32axf_op), 0 }, + { insn_wait, M(mm_pool32a_op, 0, 0, 0, mm_wait_op, mm_pool32axf_op), SCIMM }, + { insn_wsbh, M(mm_pool32a_op, 0, 0, 0, mm_wsbh_op, mm_pool32axf_op), RT | RS }, { insn_xor, M(mm_pool32a_op, 0, 0, 0, 0, mm_xor32_op), RT | RS | RD }, { insn_xori, M(mm_xori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM }, { insn_dins, 0, 0 }, diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c index 3abd609518c9..38792c2364f5 100644 --- a/arch/mips/mm/uasm-mips.c +++ b/arch/mips/mm/uasm-mips.c @@ -67,6 +67,7 @@ static struct insn insn_table[] = { { insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD }, { insn_dinsm, M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE }, { insn_dins, M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE }, + { insn_divu, M(spec_op, 0, 0, 0, 0, divu_op), RS | RT }, { insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET}, { insn_dmtc0, M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET}, { insn_drotr32, M(spec_op, 1, 0, 0, 0, dsrl32_op), RT | RD | RE }, @@ -82,17 +83,23 @@ static struct insn insn_table[] = { { insn_ins, M(spec3_op, 0, 0, 0, 0, ins_op), RS | RT | RD | RE }, { insn_j, M(j_op, 0, 0, 0, 0, 0), JIMM }, { insn_jal, M(jal_op, 0, 0, 0, 0, 0), JIMM }, + { insn_jalr, M(spec_op, 0, 0, 0, 0, jalr_op), RS | RD }, { insn_j, M(j_op, 0, 0, 0, 0, 0), JIMM }, { insn_jr, M(spec_op, 0, 0, 0, 0, jr_op), RS }, + { insn_lb, M(lb_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, { insn_ld, M(ld_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, { insn_ldx, M(spec3_op, 0, 0, 0, ldx_op, lx_op), RS | RT | RD }, + { insn_lh, M(lw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, { insn_lld, M(lld_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, { insn_ll, M(ll_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, { insn_lui, M(lui_op, 0, 0, 0, 0, 0), RT | SIMM }, { insn_lw, M(lw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, { insn_lwx, M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD }, { insn_mfc0, M(cop0_op, mfc_op, 0, 0, 0, 0), RT | RD | SET}, + { insn_mfhi, M(spec_op, 0, 0, 0, 0, mfhi_op), RD }, + { insn_mflo, M(spec_op, 0, 0, 0, 0, mflo_op), RD }, { insn_mtc0, M(cop0_op, mtc_op, 0, 0, 0, 0), RT | RD | SET}, + { insn_mul, M(spec2_op, 0, 0, 0, 0, mul_op), RS | RT | RD}, { insn_ori, M(ori_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, { insn_or, M(spec_op, 0, 0, 0, 0, or_op), RS | RT | RD }, { insn_pref, M(pref_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, @@ -102,17 +109,25 @@ static struct insn insn_table[] = { { insn_sc, M(sc_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, { insn_sd, M(sd_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, { insn_sll, M(spec_op, 0, 0, 0, 0, sll_op), RT | RD | RE }, + { insn_sllv, M(spec_op, 0, 0, 0, 0, sllv_op), RS | RT | RD }, + { insn_sltiu, M(sltiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_sltu, M(spec_op, 0, 0, 0, 0, sltu_op), RS | RT | RD }, { insn_sra, M(spec_op, 0, 0, 0, 0, sra_op), RT | RD | RE }, { insn_srl, M(spec_op, 0, 0, 0, 0, srl_op), RT | RD | RE }, + { insn_srlv, M(spec_op, 0, 0, 0, 0, srlv_op), RS | RT | RD }, { insn_subu, M(spec_op, 0, 0, 0, 0, subu_op), RS | RT | RD }, { insn_sw, M(sw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + { insn_sync, M(spec_op, 0, 0, 0, 0, sync_op), RE }, { insn_syscall, M(spec_op, 0, 0, 0, 0, syscall_op), SCIMM}, { insn_tlbp, M(cop0_op, cop_op, 0, 0, 0, tlbp_op), 0 }, { insn_tlbr, M(cop0_op, cop_op, 0, 0, 0, tlbr_op), 0 }, { insn_tlbwi, M(cop0_op, cop_op, 0, 0, 0, tlbwi_op), 0 }, { insn_tlbwr, M(cop0_op, cop_op, 0, 0, 0, tlbwr_op), 0 }, + { insn_wait, M(cop0_op, cop_op, 0, 0, 0, wait_op), SCIMM }, + { insn_wsbh, M(spec3_op, 0, 0, 0, wsbh_op, bshfl_op), RT | RD }, { insn_xori, M(xori_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, { insn_xor, M(spec_op, 0, 0, 0, 0, xor_op), RS | RT | RD }, + { insn_yield, M(spec3_op, 0, 0, 0, 0, yield_op), RS | RD }, { insn_invalid, 0, 0 } }; diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c index b9d14b6c7f58..00515805fe41 100644 --- a/arch/mips/mm/uasm.c +++ b/arch/mips/mm/uasm.c @@ -47,14 +47,16 @@ enum opcode { insn_addiu, insn_addu, insn_and, insn_andi, insn_bbit0, insn_bbit1, insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl, insn_bne, insn_cache, insn_daddiu, insn_daddu, insn_dins, insn_dinsm, - insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll, + insn_divu, insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll, insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32, insn_dsubu, insn_eret, - insn_ext, insn_ins, insn_j, insn_jal, insn_jr, insn_ld, insn_ldx, - insn_ll, insn_lld, insn_lui, insn_lw, insn_lwx, insn_mfc0, insn_mtc0, + insn_ext, insn_ins, insn_j, insn_jal, insn_jalr, insn_jr, insn_lb, + insn_ld, insn_ldx, insn_lh, insn_ll, insn_lld, insn_lui, insn_lw, + insn_lwx, insn_mfc0, insn_mfhi, insn_mflo, insn_mtc0, insn_mul, insn_or, insn_ori, insn_pref, insn_rfe, insn_rotr, insn_sc, insn_scd, - insn_sd, insn_sll, insn_sra, insn_srl, insn_subu, insn_sw, - insn_syscall, insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_xor, - insn_xori, + insn_sd, insn_sll, insn_sllv, insn_sltiu, insn_sltu, insn_sra, + insn_srl, insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall, + insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh, + insn_xor, insn_xori, insn_yield, }; struct insn { @@ -144,6 +146,13 @@ Ip_u2u1u3(op) \ } \ UASM_EXPORT_SYMBOL(uasm_i##op); +#define I_u3u2u1(op) \ +Ip_u3u2u1(op) \ +{ \ + build_insn(buf, insn##op, c, b, a); \ +} \ +UASM_EXPORT_SYMBOL(uasm_i##op); + #define I_u3u1u2(op) \ Ip_u3u1u2(op) \ { \ @@ -200,6 +209,13 @@ Ip_u1u2(op) \ } \ UASM_EXPORT_SYMBOL(uasm_i##op); +#define I_u2u1(op) \ +Ip_u1u2(op) \ +{ \ + build_insn(buf, insn##op, b, a); \ +} \ +UASM_EXPORT_SYMBOL(uasm_i##op); + #define I_u1s2(op) \ Ip_u1s2(op) \ { \ @@ -237,6 +253,7 @@ I_u1u2u3(_dmfc0) I_u1u2u3(_dmtc0) I_u2u1s3(_daddiu) I_u3u1u2(_daddu) +I_u1u2(_divu) I_u2u1u3(_dsll) I_u2u1u3(_dsll32) I_u2u1u3(_dsra) @@ -250,14 +267,20 @@ I_u2u1msbdu3(_ext) I_u2u1msbu3(_ins) I_u1(_j) I_u1(_jal) +I_u2u1(_jalr) I_u1(_jr) +I_u2s3u1(_lb) I_u2s3u1(_ld) +I_u2s3u1(_lh) I_u2s3u1(_ll) I_u2s3u1(_lld) I_u1s2(_lui) I_u2s3u1(_lw) I_u1u2u3(_mfc0) +I_u1(_mfhi) +I_u1(_mflo) I_u1u2u3(_mtc0) +I_u3u1u2(_mul) I_u2u1u3(_ori) I_u3u1u2(_or) I_0(_rfe) @@ -265,17 +288,25 @@ I_u2s3u1(_sc) I_u2s3u1(_scd) I_u2s3u1(_sd) I_u2u1u3(_sll) +I_u3u2u1(_sllv) +I_u2u1s3(_sltiu) +I_u3u1u2(_sltu) I_u2u1u3(_sra) I_u2u1u3(_srl) +I_u3u2u1(_srlv) I_u2u1u3(_rotr) I_u3u1u2(_subu) I_u2s3u1(_sw) +I_u1(_sync) I_0(_tlbp) I_0(_tlbr) I_0(_tlbwi) I_0(_tlbwr) +I_u1(_wait); +I_u2u1(_wsbh) I_u3u1u2(_xor) I_u2u1u3(_xori) +I_u2u1(_yield) I_u2u1msbu3(_dins); I_u2u1msb32u3(_dinsm); I_u1(_syscall); @@ -469,6 +500,14 @@ void ISAFUNC(uasm_il_b)(u32 **p, struct uasm_reloc **r, int lid) } UASM_EXPORT_SYMBOL(ISAFUNC(uasm_il_b)); +void ISAFUNC(uasm_il_beq)(u32 **p, struct uasm_reloc **r, unsigned int r1, + unsigned int r2, int lid) +{ + uasm_r_mips_pc16(r, *p, lid); + ISAFUNC(uasm_i_beq)(p, r1, r2, 0); +} +UASM_EXPORT_SYMBOL(ISAFUNC(uasm_il_beq)); + void ISAFUNC(uasm_il_beqz)(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid) { diff --git a/arch/mips/mti-malta/Makefile b/arch/mips/mti-malta/Makefile index eae0ba3876d9..b9510ea8db56 100644 --- a/arch/mips/mti-malta/Makefile +++ b/arch/mips/mti-malta/Makefile @@ -9,5 +9,4 @@ obj-y := malta-amon.o malta-display.o malta-init.o \ malta-int.o malta-memory.o malta-platform.o \ malta-reset.o malta-setup.o malta-time.o -# FIXME FIXME FIXME -obj-$(CONFIG_MIPS_MT_SMTC) += malta-smtc.o +obj-$(CONFIG_MIPS_MALTA_PM) += malta-pm.o diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c index 4f9e44d358b7..0f60256d3784 100644 --- a/arch/mips/mti-malta/malta-init.c +++ b/arch/mips/mti-malta/malta-init.c @@ -116,8 +116,6 @@ phys_t mips_cpc_default_phys_base(void) return CPC_BASE_ADDR; } -extern struct plat_smp_ops msmtc_smp_ops; - void __init prom_init(void) { mips_display_message("LINUX"); @@ -304,8 +302,4 @@ mips_pci_controller: return; if (!register_vsmp_smp_ops()) return; - -#ifdef CONFIG_MIPS_MT_SMTC - register_smp_ops(&msmtc_smp_ops); -#endif } diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index b71ee809191a..ecc2785f7858 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -504,28 +504,9 @@ void __init arch_init_irq(void) } else if (cpu_has_vint) { set_vi_handler(MIPSCPU_INT_I8259A, malta_hw0_irqdispatch); set_vi_handler(MIPSCPU_INT_COREHI, corehi_irqdispatch); -#ifdef CONFIG_MIPS_MT_SMTC - setup_irq_smtc(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_I8259A, &i8259irq, - (0x100 << MIPSCPU_INT_I8259A)); - setup_irq_smtc(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_COREHI, - &corehi_irqaction, (0x100 << MIPSCPU_INT_COREHI)); - /* - * Temporary hack to ensure that the subsidiary device - * interrupts coing in via the i8259A, but associated - * with low IRQ numbers, will restore the Status.IM - * value associated with the i8259A. - */ - { - int i; - - for (i = 0; i < 16; i++) - irq_hwmask[i] = (0x100 << MIPSCPU_INT_I8259A); - } -#else /* Not SMTC */ setup_irq(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_I8259A, &i8259irq); setup_irq(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_COREHI, &corehi_irqaction); -#endif /* CONFIG_MIPS_MT_SMTC */ } else { setup_irq(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_I8259A, &i8259irq); setup_irq(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_COREHI, diff --git a/arch/mips/mti-malta/malta-memory.c b/arch/mips/mti-malta/malta-memory.c index f2364e419682..6d9773096750 100644 --- a/arch/mips/mti-malta/malta-memory.c +++ b/arch/mips/mti-malta/malta-memory.c @@ -26,8 +26,8 @@ unsigned long physical_memsize = 0L; fw_memblock_t * __init fw_getmdesc(int eva) { - char *memsize_str, *ememsize_str __maybe_unused = NULL, *ptr; - unsigned long memsize = 0, ememsize __maybe_unused = 0; + char *memsize_str, *ememsize_str = NULL, *ptr; + unsigned long memsize = 0, ememsize = 0; static char cmdline[COMMAND_LINE_SIZE] __initdata; int tmp; diff --git a/arch/mips/mti-malta/malta-pm.c b/arch/mips/mti-malta/malta-pm.c new file mode 100644 index 000000000000..c1e456c01a44 --- /dev/null +++ b/arch/mips/mti-malta/malta-pm.c @@ -0,0 +1,96 @@ +/* + * Copyright (C) 2014 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/pci.h> + +#include <asm/mach-malta/malta-pm.h> + +static struct pci_bus *pm_pci_bus; +static resource_size_t pm_io_offset; + +int mips_pm_suspend(unsigned state) +{ + int spec_devid; + u16 sts; + + if (!pm_pci_bus || !pm_io_offset) + return -ENODEV; + + /* Ensure the power button status is clear */ + while (1) { + sts = inw(pm_io_offset + PIIX4_FUNC3IO_PMSTS); + if (!(sts & PIIX4_FUNC3IO_PMSTS_PWRBTN_STS)) + break; + outw(sts, pm_io_offset + PIIX4_FUNC3IO_PMSTS); + } + + /* Enable entry to suspend */ + outw(state | PIIX4_FUNC3IO_PMCNTRL_SUS_EN, + pm_io_offset + PIIX4_FUNC3IO_PMCNTRL); + + /* If the special cycle occurs too soon this doesn't work... */ + mdelay(10); + + /* + * The PIIX4 will enter the suspend state only after seeing a special + * cycle with the correct magic data on the PCI bus. Generate that + * cycle now. + */ + spec_devid = PCI_DEVID(0, PCI_DEVFN(0x1f, 0x7)); + pci_bus_write_config_dword(pm_pci_bus, spec_devid, 0, + PIIX4_SUSPEND_MAGIC); + + /* Give the system some time to power down */ + mdelay(1000); + + return 0; +} + +static int __init malta_pm_setup(void) +{ + struct pci_dev *dev; + int res, io_region = PCI_BRIDGE_RESOURCES; + + /* Find a reference to the PCI bus */ + pm_pci_bus = pci_find_next_bus(NULL); + if (!pm_pci_bus) { + pr_warn("malta-pm: failed to find reference to PCI bus\n"); + return -ENODEV; + } + + /* Find the PIIX4 PM device */ + dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82371AB_3, PCI_ANY_ID, + PCI_ANY_ID, NULL); + if (!dev) { + pr_warn("malta-pm: failed to find PIIX4 PM\n"); + return -ENODEV; + } + + /* Request access to the PIIX4 PM IO registers */ + res = pci_request_region(dev, io_region, "PIIX4 PM IO registers"); + if (res) { + pr_warn("malta-pm: failed to request PM IO registers (%d)\n", + res); + pci_dev_put(dev); + return -ENODEV; + } + + /* Find the offset to the PIIX4 PM IO registers */ + pm_io_offset = pci_resource_start(dev, io_region); + + pci_dev_put(dev); + return 0; +} + +late_initcall(malta_pm_setup); diff --git a/arch/mips/mti-malta/malta-reset.c b/arch/mips/mti-malta/malta-reset.c index d627d4b2b47f..2fd2cc2c5034 100644 --- a/arch/mips/mti-malta/malta-reset.c +++ b/arch/mips/mti-malta/malta-reset.c @@ -10,6 +10,7 @@ #include <linux/pm.h> #include <asm/reboot.h> +#include <asm/mach-malta/malta-pm.h> #define SOFTRES_REG 0x1f000500 #define GORESET 0x42 @@ -24,17 +25,22 @@ static void mips_machine_restart(char *command) static void mips_machine_halt(void) { - unsigned int __iomem *softres_reg = - ioremap(SOFTRES_REG, sizeof(unsigned int)); + while (true); +} - __raw_writel(GORESET, softres_reg); +static void mips_machine_power_off(void) +{ + mips_pm_suspend(PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_SOFF); + + pr_info("Failed to power down, resetting\n"); + mips_machine_restart(NULL); } static int __init mips_reboot_setup(void) { _machine_restart = mips_machine_restart; _machine_halt = mips_machine_halt; - pm_power_off = mips_machine_halt; + pm_power_off = mips_machine_power_off; return 0; } diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index bf621516afff..db7c9e5826a6 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -77,11 +77,7 @@ const char *get_system_type(void) return "MIPS Malta"; } -#if defined(CONFIG_MIPS_MT_SMTC) -const char display_string[] = " SMTC LINUX ON MALTA "; -#else const char display_string[] = " LINUX ON MALTA "; -#endif /* CONFIG_MIPS_MT_SMTC */ #ifdef CONFIG_BLK_DEV_FD static void __init fd_activate(void) diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c deleted file mode 100644 index c4849904f013..000000000000 --- a/arch/mips/mti-malta/malta-smtc.c +++ /dev/null @@ -1,162 +0,0 @@ -/* - * Malta Platform-specific hooks for SMP operation - */ -#include <linux/irq.h> -#include <linux/init.h> - -#include <asm/mipsregs.h> -#include <asm/mipsmtregs.h> -#include <asm/smtc.h> -#include <asm/smtc_ipi.h> - -/* VPE/SMP Prototype implements platform interfaces directly */ - -/* - * Cause the specified action to be performed on a targeted "CPU" - */ - -static void msmtc_send_ipi_single(int cpu, unsigned int action) -{ - /* "CPU" may be TC of same VPE, VPE of same CPU, or different CPU */ - smtc_send_ipi(cpu, LINUX_SMP_IPI, action); -} - -static void msmtc_send_ipi_mask(const struct cpumask *mask, unsigned int action) -{ - unsigned int i; - - for_each_cpu(i, mask) - msmtc_send_ipi_single(i, action); -} - -/* - * Post-config but pre-boot cleanup entry point - */ -static void msmtc_init_secondary(void) -{ - int myvpe; - - /* Don't enable Malta I/O interrupts (IP2) for secondary VPEs */ - myvpe = read_c0_tcbind() & TCBIND_CURVPE; - if (myvpe != 0) { - /* Ideally, this should be done only once per VPE, but... */ - clear_c0_status(ST0_IM); - set_c0_status((0x100 << cp0_compare_irq) - | (0x100 << MIPS_CPU_IPI_IRQ)); - if (cp0_perfcount_irq >= 0) - set_c0_status(0x100 << cp0_perfcount_irq); - } - - smtc_init_secondary(); -} - -/* - * Platform "CPU" startup hook - */ -static void msmtc_boot_secondary(int cpu, struct task_struct *idle) -{ - smtc_boot_secondary(cpu, idle); -} - -/* - * SMP initialization finalization entry point - */ -static void msmtc_smp_finish(void) -{ - smtc_smp_finish(); -} - -/* - * Hook for after all CPUs are online - */ - -static void msmtc_cpus_done(void) -{ -} - -/* - * Platform SMP pre-initialization - * - * As noted above, we can assume a single CPU for now - * but it may be multithreaded. - */ - -static void __init msmtc_smp_setup(void) -{ - /* - * we won't get the definitive value until - * we've run smtc_prepare_cpus later, but - * we would appear to need an upper bound now. - */ - smp_num_siblings = smtc_build_cpu_map(0); -} - -static void __init msmtc_prepare_cpus(unsigned int max_cpus) -{ - smtc_prepare_cpus(max_cpus); -} - -struct plat_smp_ops msmtc_smp_ops = { - .send_ipi_single = msmtc_send_ipi_single, - .send_ipi_mask = msmtc_send_ipi_mask, - .init_secondary = msmtc_init_secondary, - .smp_finish = msmtc_smp_finish, - .cpus_done = msmtc_cpus_done, - .boot_secondary = msmtc_boot_secondary, - .smp_setup = msmtc_smp_setup, - .prepare_cpus = msmtc_prepare_cpus, -}; - -#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF -/* - * IRQ affinity hook - */ - - -int plat_set_irq_affinity(struct irq_data *d, const struct cpumask *affinity, - bool force) -{ - cpumask_t tmask; - int cpu = 0; - void smtc_set_irq_affinity(unsigned int irq, cpumask_t aff); - - /* - * On the legacy Malta development board, all I/O interrupts - * are routed through the 8259 and combined in a single signal - * to the CPU daughterboard, and on the CoreFPGA2/3 34K models, - * that signal is brought to IP2 of both VPEs. To avoid racing - * concurrent interrupt service events, IP2 is enabled only on - * one VPE, by convention VPE0. So long as no bits are ever - * cleared in the affinity mask, there will never be any - * interrupt forwarding. But as soon as a program or operator - * sets affinity for one of the related IRQs, we need to make - * sure that we don't ever try to forward across the VPE boundary, - * at least not until we engineer a system where the interrupt - * _ack() or _end() function can somehow know that it corresponds - * to an interrupt taken on another VPE, and perform the appropriate - * restoration of Status.IM state using MFTR/MTTR instead of the - * normal local behavior. We also ensure that no attempt will - * be made to forward to an offline "CPU". - */ - - cpumask_copy(&tmask, affinity); - for_each_cpu(cpu, affinity) { - if ((cpu_data[cpu].vpe_id != 0) || !cpu_online(cpu)) - cpu_clear(cpu, tmask); - } - cpumask_copy(d->affinity, &tmask); - - if (cpus_empty(tmask)) - /* - * We could restore a default mask here, but the - * runtime code can anyway deal with the null set - */ - printk(KERN_WARNING - "IRQ affinity leaves no legal CPU for IRQ %d\n", d->irq); - - /* Do any generic SMTC IRQ affinity setup */ - smtc_set_irq_affinity(d->irq, tmask); - - return IRQ_SET_MASK_OK_NOCOPY; -} -#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ diff --git a/arch/mips/mti-sead3/sead3-pic32-i2c-drv.c b/arch/mips/mti-sead3/sead3-pic32-i2c-drv.c index b921e5ec507c..80fe194cfa53 100644 --- a/arch/mips/mti-sead3/sead3-pic32-i2c-drv.c +++ b/arch/mips/mti-sead3/sead3-pic32-i2c-drv.c @@ -312,16 +312,13 @@ static int i2c_platform_probe(struct platform_device *pdev) pr_debug("i2c_platform_probe\n"); r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!r) { - ret = -ENODEV; - goto out; - } + if (!r) + return -ENODEV; - priv = kzalloc(sizeof(struct i2c_platform_data), GFP_KERNEL); - if (!priv) { - ret = -ENOMEM; - goto out; - } + priv = devm_kzalloc(&pdev->dev, sizeof(struct i2c_platform_data), + GFP_KERNEL); + if (!priv) + return -ENOMEM; /* FIXME: need to allocate resource in PIC32 space */ #if 0 @@ -330,10 +327,8 @@ static int i2c_platform_probe(struct platform_device *pdev) #else priv->base = r->start; #endif - if (!priv->base) { - ret = -EBUSY; - goto out_mem; - } + if (!priv->base) + return -EBUSY; priv->xfer_timeout = 200; priv->ack_timeout = 200; @@ -348,17 +343,13 @@ static int i2c_platform_probe(struct platform_device *pdev) i2c_platform_setup(priv); ret = i2c_add_numbered_adapter(&priv->adap); - if (ret == 0) { - platform_set_drvdata(pdev, priv); - return 0; + if (ret) { + i2c_platform_disable(priv); + return ret; } - i2c_platform_disable(priv); - -out_mem: - kfree(priv); -out: - return ret; + platform_set_drvdata(pdev, priv); + return 0; } static int i2c_platform_remove(struct platform_device *pdev) @@ -369,7 +360,6 @@ static int i2c_platform_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); i2c_del_adapter(&priv->adap); i2c_platform_disable(priv); - kfree(priv); return 0; } diff --git a/arch/mips/mti-sead3/sead3-setup.c b/arch/mips/mti-sead3/sead3-setup.c index bf7fe48bf2f9..e43f4801a245 100644 --- a/arch/mips/mti-sead3/sead3-setup.c +++ b/arch/mips/mti-sead3/sead3-setup.c @@ -69,17 +69,17 @@ static void __init parse_memsize_param(void) if (!memsize) return; - offset = fdt_path_offset(&__dtb_start, "/memory"); + offset = fdt_path_offset(__dtb_start, "/memory"); if (offset > 0) { uint64_t new_value; /* * reg contains 2 32-bits BE values, offset and size. We just * want to replace the size value without affecting the offset */ - prop_value = fdt_getprop(&__dtb_start, offset, "reg", &prop_len); + prop_value = fdt_getprop(__dtb_start, offset, "reg", &prop_len); new_value = be64_to_cpu(*prop_value); new_value = (new_value & ~0xffffffffllu) | memsize; - fdt_setprop_inplace_u64(&__dtb_start, offset, "reg", new_value); + fdt_setprop_inplace_u64(__dtb_start, offset, "reg", new_value); } } @@ -92,7 +92,7 @@ void __init plat_mem_setup(void) * Load the builtin devicetree. This causes the chosen node to be * parsed resulting in our memory appearing */ - __dt_setup_arch(&__dtb_start); + __dt_setup_arch(__dtb_start); } void __init device_tree_init(void) diff --git a/arch/mips/net/Makefile b/arch/mips/net/Makefile new file mode 100644 index 000000000000..ae74b3a91f5c --- /dev/null +++ b/arch/mips/net/Makefile @@ -0,0 +1,3 @@ +# MIPS networking code + +obj-$(CONFIG_BPF_JIT) += bpf_jit.o diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c new file mode 100644 index 000000000000..a67b9753330b --- /dev/null +++ b/arch/mips/net/bpf_jit.c @@ -0,0 +1,1399 @@ +/* + * Just-In-Time compiler for BPF filters on MIPS + * + * Copyright (c) 2014 Imagination Technologies Ltd. + * Author: Markos Chandras <markos.chandras@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License. + */ + +#include <linux/bitops.h> +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/filter.h> +#include <linux/if_vlan.h> +#include <linux/kconfig.h> +#include <linux/moduleloader.h> +#include <linux/netdevice.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <asm/bitops.h> +#include <asm/cacheflush.h> +#include <asm/cpu-features.h> +#include <asm/uasm.h> + +#include "bpf_jit.h" + +/* ABI + * + * s0 1st scratch register + * s1 2nd scratch register + * s2 offset register + * s3 BPF register A + * s4 BPF register X + * s5 *skb + * s6 *scratch memory + * + * On entry (*bpf_func)(*skb, *filter) + * a0 = MIPS_R_A0 = skb; + * a1 = MIPS_R_A1 = filter; + * + * Stack + * ... + * M[15] + * M[14] + * M[13] + * ... + * M[0] <-- r_M + * saved reg k-1 + * saved reg k-2 + * ... + * saved reg 0 <-- r_sp + * <no argument area> + * + * Packet layout + * + * <--------------------- len ------------------------> + * <--skb-len(r_skb_hl)-->< ----- skb->data_len ------> + * ---------------------------------------------------- + * | skb->data | + * ---------------------------------------------------- + */ + +#define RSIZE (sizeof(unsigned long)) +#define ptr typeof(unsigned long) + +/* ABI specific return values */ +#ifdef CONFIG_32BIT /* O32 */ +#ifdef CONFIG_CPU_LITTLE_ENDIAN +#define r_err MIPS_R_V1 +#define r_val MIPS_R_V0 +#else /* CONFIG_CPU_LITTLE_ENDIAN */ +#define r_err MIPS_R_V0 +#define r_val MIPS_R_V1 +#endif +#else /* N64 */ +#define r_err MIPS_R_V0 +#define r_val MIPS_R_V0 +#endif + +#define r_ret MIPS_R_V0 + +/* + * Use 2 scratch registers to avoid pipeline interlocks. + * There is no overhead during epilogue and prologue since + * any of the $s0-$s6 registers will only be preserved if + * they are going to actually be used. + */ +#define r_s0 MIPS_R_S0 /* scratch reg 1 */ +#define r_s1 MIPS_R_S1 /* scratch reg 2 */ +#define r_off MIPS_R_S2 +#define r_A MIPS_R_S3 +#define r_X MIPS_R_S4 +#define r_skb MIPS_R_S5 +#define r_M MIPS_R_S6 +#define r_tmp_imm MIPS_R_T6 /* No need to preserve this */ +#define r_tmp MIPS_R_T7 /* No need to preserve this */ +#define r_zero MIPS_R_ZERO +#define r_sp MIPS_R_SP +#define r_ra MIPS_R_RA + +#define SCRATCH_OFF(k) (4 * (k)) + +/* JIT flags */ +#define SEEN_CALL (1 << BPF_MEMWORDS) +#define SEEN_SREG_SFT (BPF_MEMWORDS + 1) +#define SEEN_SREG_BASE (1 << SEEN_SREG_SFT) +#define SEEN_SREG(x) (SEEN_SREG_BASE << (x)) +#define SEEN_S0 SEEN_SREG(0) +#define SEEN_S1 SEEN_SREG(1) +#define SEEN_OFF SEEN_SREG(2) +#define SEEN_A SEEN_SREG(3) +#define SEEN_X SEEN_SREG(4) +#define SEEN_SKB SEEN_SREG(5) +#define SEEN_MEM SEEN_SREG(6) + +/* Arguments used by JIT */ +#define ARGS_USED_BY_JIT 2 /* only applicable to 64-bit */ + +#define FLAG_NEED_X_RESET (1 << 0) + +#define SBIT(x) (1 << (x)) /* Signed version of BIT() */ + +/** + * struct jit_ctx - JIT context + * @skf: The sk_filter + * @prologue_bytes: Number of bytes for prologue + * @idx: Instruction index + * @flags: JIT flags + * @offsets: Instruction offsets + * @target: Memory location for the compiled filter + */ +struct jit_ctx { + const struct sk_filter *skf; + unsigned int prologue_bytes; + u32 idx; + u32 flags; + u32 *offsets; + u32 *target; +}; + + +static inline int optimize_div(u32 *k) +{ + /* power of 2 divides can be implemented with right shift */ + if (!(*k & (*k-1))) { + *k = ilog2(*k); + return 1; + } + + return 0; +} + +/* Simply emit the instruction if the JIT memory space has been allocated */ +#define emit_instr(ctx, func, ...) \ +do { \ + if ((ctx)->target != NULL) { \ + u32 *p = &(ctx)->target[ctx->idx]; \ + uasm_i_##func(&p, ##__VA_ARGS__); \ + } \ + (ctx)->idx++; \ +} while (0) + +/* Determine if immediate is within the 16-bit signed range */ +static inline bool is_range16(s32 imm) +{ + if (imm >= SBIT(15) || imm < -SBIT(15)) + return true; + return false; +} + +static inline void emit_addu(unsigned int dst, unsigned int src1, + unsigned int src2, struct jit_ctx *ctx) +{ + emit_instr(ctx, addu, dst, src1, src2); +} + +static inline void emit_nop(struct jit_ctx *ctx) +{ + emit_instr(ctx, nop); +} + +/* Load a u32 immediate to a register */ +static inline void emit_load_imm(unsigned int dst, u32 imm, struct jit_ctx *ctx) +{ + if (ctx->target != NULL) { + /* addiu can only handle s16 */ + if (is_range16(imm)) { + u32 *p = &ctx->target[ctx->idx]; + uasm_i_lui(&p, r_tmp_imm, (s32)imm >> 16); + p = &ctx->target[ctx->idx + 1]; + uasm_i_ori(&p, dst, r_tmp_imm, imm & 0xffff); + } else { + u32 *p = &ctx->target[ctx->idx]; + uasm_i_addiu(&p, dst, r_zero, imm); + } + } + ctx->idx++; + + if (is_range16(imm)) + ctx->idx++; +} + +static inline void emit_or(unsigned int dst, unsigned int src1, + unsigned int src2, struct jit_ctx *ctx) +{ + emit_instr(ctx, or, dst, src1, src2); +} + +static inline void emit_ori(unsigned int dst, unsigned src, u32 imm, + struct jit_ctx *ctx) +{ + if (imm >= BIT(16)) { + emit_load_imm(r_tmp, imm, ctx); + emit_or(dst, src, r_tmp, ctx); + } else { + emit_instr(ctx, ori, dst, src, imm); + } +} + + +static inline void emit_daddu(unsigned int dst, unsigned int src1, + unsigned int src2, struct jit_ctx *ctx) +{ + emit_instr(ctx, daddu, dst, src1, src2); +} + +static inline void emit_daddiu(unsigned int dst, unsigned int src, + int imm, struct jit_ctx *ctx) +{ + /* + * Only used for stack, so the imm is relatively small + * and it fits in 15-bits + */ + emit_instr(ctx, daddiu, dst, src, imm); +} + +static inline void emit_addiu(unsigned int dst, unsigned int src, + u32 imm, struct jit_ctx *ctx) +{ + if (is_range16(imm)) { + emit_load_imm(r_tmp, imm, ctx); + emit_addu(dst, r_tmp, src, ctx); + } else { + emit_instr(ctx, addiu, dst, src, imm); + } +} + +static inline void emit_and(unsigned int dst, unsigned int src1, + unsigned int src2, struct jit_ctx *ctx) +{ + emit_instr(ctx, and, dst, src1, src2); +} + +static inline void emit_andi(unsigned int dst, unsigned int src, + u32 imm, struct jit_ctx *ctx) +{ + /* If imm does not fit in u16 then load it to register */ + if (imm >= BIT(16)) { + emit_load_imm(r_tmp, imm, ctx); + emit_and(dst, src, r_tmp, ctx); + } else { + emit_instr(ctx, andi, dst, src, imm); + } +} + +static inline void emit_xor(unsigned int dst, unsigned int src1, + unsigned int src2, struct jit_ctx *ctx) +{ + emit_instr(ctx, xor, dst, src1, src2); +} + +static inline void emit_xori(ptr dst, ptr src, u32 imm, struct jit_ctx *ctx) +{ + /* If imm does not fit in u16 then load it to register */ + if (imm >= BIT(16)) { + emit_load_imm(r_tmp, imm, ctx); + emit_xor(dst, src, r_tmp, ctx); + } else { + emit_instr(ctx, xori, dst, src, imm); + } +} + +static inline void emit_stack_offset(int offset, struct jit_ctx *ctx) +{ + if (config_enabled(CONFIG_64BIT)) + emit_instr(ctx, daddiu, r_sp, r_sp, offset); + else + emit_instr(ctx, addiu, r_sp, r_sp, offset); + +} + +static inline void emit_subu(unsigned int dst, unsigned int src1, + unsigned int src2, struct jit_ctx *ctx) +{ + emit_instr(ctx, subu, dst, src1, src2); +} + +static inline void emit_neg(unsigned int reg, struct jit_ctx *ctx) +{ + emit_subu(reg, r_zero, reg, ctx); +} + +static inline void emit_sllv(unsigned int dst, unsigned int src, + unsigned int sa, struct jit_ctx *ctx) +{ + emit_instr(ctx, sllv, dst, src, sa); +} + +static inline void emit_sll(unsigned int dst, unsigned int src, + unsigned int sa, struct jit_ctx *ctx) +{ + /* sa is 5-bits long */ + BUG_ON(sa >= BIT(5)); + emit_instr(ctx, sll, dst, src, sa); +} + +static inline void emit_srlv(unsigned int dst, unsigned int src, + unsigned int sa, struct jit_ctx *ctx) +{ + emit_instr(ctx, srlv, dst, src, sa); +} + +static inline void emit_srl(unsigned int dst, unsigned int src, + unsigned int sa, struct jit_ctx *ctx) +{ + /* sa is 5-bits long */ + BUG_ON(sa >= BIT(5)); + emit_instr(ctx, srl, dst, src, sa); +} + +static inline void emit_sltu(unsigned int dst, unsigned int src1, + unsigned int src2, struct jit_ctx *ctx) +{ + emit_instr(ctx, sltu, dst, src1, src2); +} + +static inline void emit_sltiu(unsigned dst, unsigned int src, + unsigned int imm, struct jit_ctx *ctx) +{ + /* 16 bit immediate */ + if (is_range16((s32)imm)) { + emit_load_imm(r_tmp, imm, ctx); + emit_sltu(dst, src, r_tmp, ctx); + } else { + emit_instr(ctx, sltiu, dst, src, imm); + } + +} + +/* Store register on the stack */ +static inline void emit_store_stack_reg(ptr reg, ptr base, + unsigned int offset, + struct jit_ctx *ctx) +{ + if (config_enabled(CONFIG_64BIT)) + emit_instr(ctx, sd, reg, offset, base); + else + emit_instr(ctx, sw, reg, offset, base); +} + +static inline void emit_store(ptr reg, ptr base, unsigned int offset, + struct jit_ctx *ctx) +{ + emit_instr(ctx, sw, reg, offset, base); +} + +static inline void emit_load_stack_reg(ptr reg, ptr base, + unsigned int offset, + struct jit_ctx *ctx) +{ + if (config_enabled(CONFIG_64BIT)) + emit_instr(ctx, ld, reg, offset, base); + else + emit_instr(ctx, lw, reg, offset, base); +} + +static inline void emit_load(unsigned int reg, unsigned int base, + unsigned int offset, struct jit_ctx *ctx) +{ + emit_instr(ctx, lw, reg, offset, base); +} + +static inline void emit_load_byte(unsigned int reg, unsigned int base, + unsigned int offset, struct jit_ctx *ctx) +{ + emit_instr(ctx, lb, reg, offset, base); +} + +static inline void emit_half_load(unsigned int reg, unsigned int base, + unsigned int offset, struct jit_ctx *ctx) +{ + emit_instr(ctx, lh, reg, offset, base); +} + +static inline void emit_mul(unsigned int dst, unsigned int src1, + unsigned int src2, struct jit_ctx *ctx) +{ + emit_instr(ctx, mul, dst, src1, src2); +} + +static inline void emit_div(unsigned int dst, unsigned int src, + struct jit_ctx *ctx) +{ + if (ctx->target != NULL) { + u32 *p = &ctx->target[ctx->idx]; + uasm_i_divu(&p, dst, src); + p = &ctx->target[ctx->idx + 1]; + uasm_i_mfhi(&p, dst); + } + ctx->idx += 2; /* 2 insts */ +} + +static inline void emit_mod(unsigned int dst, unsigned int src, + struct jit_ctx *ctx) +{ + if (ctx->target != NULL) { + u32 *p = &ctx->target[ctx->idx]; + uasm_i_divu(&p, dst, src); + p = &ctx->target[ctx->idx + 1]; + uasm_i_mflo(&p, dst); + } + ctx->idx += 2; /* 2 insts */ +} + +static inline void emit_dsll(unsigned int dst, unsigned int src, + unsigned int sa, struct jit_ctx *ctx) +{ + emit_instr(ctx, dsll, dst, src, sa); +} + +static inline void emit_dsrl32(unsigned int dst, unsigned int src, + unsigned int sa, struct jit_ctx *ctx) +{ + emit_instr(ctx, dsrl32, dst, src, sa); +} + +static inline void emit_wsbh(unsigned int dst, unsigned int src, + struct jit_ctx *ctx) +{ + emit_instr(ctx, wsbh, dst, src); +} + +/* load a function pointer to register */ +static inline void emit_load_func(unsigned int reg, ptr imm, + struct jit_ctx *ctx) +{ + if (config_enabled(CONFIG_64BIT)) { + /* At this point imm is always 64-bit */ + emit_load_imm(r_tmp, (u64)imm >> 32, ctx); + emit_dsll(r_tmp_imm, r_tmp, 16, ctx); /* left shift by 16 */ + emit_ori(r_tmp, r_tmp_imm, (imm >> 16) & 0xffff, ctx); + emit_dsll(r_tmp_imm, r_tmp, 16, ctx); /* left shift by 16 */ + emit_ori(reg, r_tmp_imm, imm & 0xffff, ctx); + } else { + emit_load_imm(reg, imm, ctx); + } +} + +/* Move to real MIPS register */ +static inline void emit_reg_move(ptr dst, ptr src, struct jit_ctx *ctx) +{ + if (config_enabled(CONFIG_64BIT)) + emit_daddu(dst, src, r_zero, ctx); + else + emit_addu(dst, src, r_zero, ctx); +} + +/* Move to JIT (32-bit) register */ +static inline void emit_jit_reg_move(ptr dst, ptr src, struct jit_ctx *ctx) +{ + emit_addu(dst, src, r_zero, ctx); +} + +/* Compute the immediate value for PC-relative branches. */ +static inline u32 b_imm(unsigned int tgt, struct jit_ctx *ctx) +{ + if (ctx->target == NULL) + return 0; + + /* + * We want a pc-relative branch. We only do forward branches + * so tgt is always after pc. tgt is the instruction offset + * we want to jump to. + + * Branch on MIPS: + * I: target_offset <- sign_extend(offset) + * I+1: PC += target_offset (delay slot) + * + * ctx->idx currently points to the branch instruction + * but the offset is added to the delay slot so we need + * to subtract 4. + */ + return ctx->offsets[tgt] - + (ctx->idx * 4 - ctx->prologue_bytes) - 4; +} + +static inline void emit_bcond(int cond, unsigned int reg1, unsigned int reg2, + unsigned int imm, struct jit_ctx *ctx) +{ + if (ctx->target != NULL) { + u32 *p = &ctx->target[ctx->idx]; + + switch (cond) { + case MIPS_COND_EQ: + uasm_i_beq(&p, reg1, reg2, imm); + break; + case MIPS_COND_NE: + uasm_i_bne(&p, reg1, reg2, imm); + break; + case MIPS_COND_ALL: + uasm_i_b(&p, imm); + break; + default: + pr_warn("%s: Unhandled branch conditional: %d\n", + __func__, cond); + } + } + ctx->idx++; +} + +static inline void emit_b(unsigned int imm, struct jit_ctx *ctx) +{ + emit_bcond(MIPS_COND_ALL, r_zero, r_zero, imm, ctx); +} + +static inline void emit_jalr(unsigned int link, unsigned int reg, + struct jit_ctx *ctx) +{ + emit_instr(ctx, jalr, link, reg); +} + +static inline void emit_jr(unsigned int reg, struct jit_ctx *ctx) +{ + emit_instr(ctx, jr, reg); +} + +static inline u16 align_sp(unsigned int num) +{ + /* Double word alignment for 32-bit, quadword for 64-bit */ + unsigned int align = config_enabled(CONFIG_64BIT) ? 16 : 8; + num = (num + (align - 1)) & -align; + return num; +} + +static inline void update_on_xread(struct jit_ctx *ctx) +{ + if (!(ctx->flags & SEEN_X)) + ctx->flags |= FLAG_NEED_X_RESET; + + ctx->flags |= SEEN_X; +} + +static bool is_load_to_a(u16 inst) +{ + switch (inst) { + case BPF_S_LD_W_LEN: + case BPF_S_LD_W_ABS: + case BPF_S_LD_H_ABS: + case BPF_S_LD_B_ABS: + case BPF_S_ANC_CPU: + case BPF_S_ANC_IFINDEX: + case BPF_S_ANC_MARK: + case BPF_S_ANC_PROTOCOL: + case BPF_S_ANC_RXHASH: + case BPF_S_ANC_VLAN_TAG: + case BPF_S_ANC_VLAN_TAG_PRESENT: + case BPF_S_ANC_QUEUE: + return true; + default: + return false; + } +} + +static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset) +{ + int i = 0, real_off = 0; + u32 sflags, tmp_flags; + + /* Adjust the stack pointer */ + emit_stack_offset(-align_sp(offset), ctx); + + if (ctx->flags & SEEN_CALL) { + /* Argument save area */ + if (config_enabled(CONFIG_64BIT)) + /* Bottom of current frame */ + real_off = align_sp(offset) - RSIZE; + else + /* Top of previous frame */ + real_off = align_sp(offset) + RSIZE; + emit_store_stack_reg(MIPS_R_A0, r_sp, real_off, ctx); + emit_store_stack_reg(MIPS_R_A1, r_sp, real_off + RSIZE, ctx); + + real_off = 0; + } + + tmp_flags = sflags = ctx->flags >> SEEN_SREG_SFT; + /* sflags is essentially a bitmap */ + while (tmp_flags) { + if ((sflags >> i) & 0x1) { + emit_store_stack_reg(MIPS_R_S0 + i, r_sp, real_off, + ctx); + real_off += RSIZE; + } + i++; + tmp_flags >>= 1; + } + + /* save return address */ + if (ctx->flags & SEEN_CALL) { + emit_store_stack_reg(r_ra, r_sp, real_off, ctx); + real_off += RSIZE; + } + + /* Setup r_M leaving the alignment gap if necessary */ + if (ctx->flags & SEEN_MEM) { + if (real_off % (RSIZE * 2)) + real_off += RSIZE; + emit_addiu(r_M, r_sp, real_off, ctx); + } +} + +static void restore_bpf_jit_regs(struct jit_ctx *ctx, + unsigned int offset) +{ + int i, real_off = 0; + u32 sflags, tmp_flags; + + if (ctx->flags & SEEN_CALL) { + if (config_enabled(CONFIG_64BIT)) + /* Bottom of current frame */ + real_off = align_sp(offset) - RSIZE; + else + /* Top of previous frame */ + real_off = align_sp(offset) + RSIZE; + emit_load_stack_reg(MIPS_R_A0, r_sp, real_off, ctx); + emit_load_stack_reg(MIPS_R_A1, r_sp, real_off + RSIZE, ctx); + + real_off = 0; + } + + tmp_flags = sflags = ctx->flags >> SEEN_SREG_SFT; + /* sflags is a bitmap */ + i = 0; + while (tmp_flags) { + if ((sflags >> i) & 0x1) { + emit_load_stack_reg(MIPS_R_S0 + i, r_sp, real_off, + ctx); + real_off += RSIZE; + } + i++; + tmp_flags >>= 1; + } + + /* restore return address */ + if (ctx->flags & SEEN_CALL) + emit_load_stack_reg(r_ra, r_sp, real_off, ctx); + + /* Restore the sp and discard the scrach memory */ + emit_stack_offset(align_sp(offset), ctx); +} + +static unsigned int get_stack_depth(struct jit_ctx *ctx) +{ + int sp_off = 0; + + + /* How may s* regs do we need to preserved? */ + sp_off += hweight32(ctx->flags >> SEEN_SREG_SFT) * RSIZE; + + if (ctx->flags & SEEN_MEM) + sp_off += 4 * BPF_MEMWORDS; /* BPF_MEMWORDS are 32-bit */ + + if (ctx->flags & SEEN_CALL) + /* + * The JIT code make calls to external functions using 2 + * arguments. Therefore, for o32 we don't need to allocate + * space because we don't care if the argumetns are lost + * across calls. We do need however to preserve incoming + * arguments but the space is already allocated for us by + * the caller. On the other hand, for n64, we need to allocate + * this space ourselves. We need to preserve $ra as well. + */ + sp_off += config_enabled(CONFIG_64BIT) ? + (ARGS_USED_BY_JIT + 1) * RSIZE : RSIZE; + + /* + * Subtract the bytes for the last registers since we only care about + * the location on the stack pointer. + */ + return sp_off - RSIZE; +} + +static void build_prologue(struct jit_ctx *ctx) +{ + u16 first_inst = ctx->skf->insns[0].code; + int sp_off; + + /* Calculate the total offset for the stack pointer */ + sp_off = get_stack_depth(ctx); + save_bpf_jit_regs(ctx, sp_off); + + if (ctx->flags & SEEN_SKB) + emit_reg_move(r_skb, MIPS_R_A0, ctx); + + if (ctx->flags & FLAG_NEED_X_RESET) + emit_jit_reg_move(r_X, r_zero, ctx); + + /* Do not leak kernel data to userspace */ + if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst))) + emit_jit_reg_move(r_A, r_zero, ctx); +} + +static void build_epilogue(struct jit_ctx *ctx) +{ + unsigned int sp_off; + + /* Calculate the total offset for the stack pointer */ + + sp_off = get_stack_depth(ctx); + restore_bpf_jit_regs(ctx, sp_off); + + /* Return */ + emit_jr(r_ra, ctx); + emit_nop(ctx); +} + +static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset) +{ + u8 ret; + int err; + + err = skb_copy_bits(skb, offset, &ret, 1); + + return (u64)err << 32 | ret; +} + +static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset) +{ + u16 ret; + int err; + + err = skb_copy_bits(skb, offset, &ret, 2); + + return (u64)err << 32 | ntohs(ret); +} + +static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset) +{ + u32 ret; + int err; + + err = skb_copy_bits(skb, offset, &ret, 4); + + return (u64)err << 32 | ntohl(ret); +} + +#define PKT_TYPE_MAX 7 +static int pkt_type_offset(void) +{ + struct sk_buff skb_probe = { + .pkt_type = ~0, + }; + char *ct = (char *)&skb_probe; + unsigned int off; + + for (off = 0; off < sizeof(struct sk_buff); off++) { + if (ct[off] == PKT_TYPE_MAX) + return off; + } + pr_err_once("Please fix pkt_type_offset(), as pkt_type couldn't be found\n"); + return -1; +} + +static int build_body(struct jit_ctx *ctx) +{ + void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w}; + const struct sk_filter *prog = ctx->skf; + const struct sock_filter *inst; + unsigned int i, off, load_order, condt; + u32 k, b_off __maybe_unused; + + for (i = 0; i < prog->len; i++) { + inst = &(prog->insns[i]); + pr_debug("%s: code->0x%02x, jt->0x%x, jf->0x%x, k->0x%x\n", + __func__, inst->code, inst->jt, inst->jf, inst->k); + k = inst->k; + + if (ctx->target == NULL) + ctx->offsets[i] = ctx->idx * 4; + + switch (inst->code) { + case BPF_S_LD_IMM: + /* A <- k ==> li r_A, k */ + ctx->flags |= SEEN_A; + emit_load_imm(r_A, k, ctx); + break; + case BPF_S_LD_W_LEN: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); + /* A <- len ==> lw r_A, offset(skb) */ + ctx->flags |= SEEN_SKB | SEEN_A; + off = offsetof(struct sk_buff, len); + emit_load(r_A, r_skb, off, ctx); + break; + case BPF_S_LD_MEM: + /* A <- M[k] ==> lw r_A, offset(M) */ + ctx->flags |= SEEN_MEM | SEEN_A; + emit_load(r_A, r_M, SCRATCH_OFF(k), ctx); + break; + case BPF_S_LD_W_ABS: + /* A <- P[k:4] */ + load_order = 2; + goto load; + case BPF_S_LD_H_ABS: + /* A <- P[k:2] */ + load_order = 1; + goto load; + case BPF_S_LD_B_ABS: + /* A <- P[k:1] */ + load_order = 0; +load: + emit_load_imm(r_off, k, ctx); +load_common: + ctx->flags |= SEEN_CALL | SEEN_OFF | SEEN_S0 | + SEEN_SKB | SEEN_A; + + emit_load_func(r_s0, (ptr)load_func[load_order], + ctx); + emit_reg_move(MIPS_R_A0, r_skb, ctx); + emit_jalr(MIPS_R_RA, r_s0, ctx); + /* Load second argument to delay slot */ + emit_reg_move(MIPS_R_A1, r_off, ctx); + /* Check the error value */ + if (config_enabled(CONFIG_64BIT)) { + /* Get error code from the top 32-bits */ + emit_dsrl32(r_s0, r_val, 0, ctx); + /* Branch to 3 instructions ahead */ + emit_bcond(MIPS_COND_NE, r_s0, r_zero, 3 << 2, + ctx); + } else { + /* Branch to 3 instructions ahead */ + emit_bcond(MIPS_COND_NE, r_err, r_zero, 3 << 2, + ctx); + } + emit_nop(ctx); + /* We are good */ + emit_b(b_imm(i + 1, ctx), ctx); + emit_jit_reg_move(r_A, r_val, ctx); + /* Return with error */ + emit_b(b_imm(prog->len, ctx), ctx); + emit_reg_move(r_ret, r_zero, ctx); + break; + case BPF_S_LD_W_IND: + /* A <- P[X + k:4] */ + load_order = 2; + goto load_ind; + case BPF_S_LD_H_IND: + /* A <- P[X + k:2] */ + load_order = 1; + goto load_ind; + case BPF_S_LD_B_IND: + /* A <- P[X + k:1] */ + load_order = 0; +load_ind: + update_on_xread(ctx); + ctx->flags |= SEEN_OFF | SEEN_X; + emit_addiu(r_off, r_X, k, ctx); + goto load_common; + case BPF_S_LDX_IMM: + /* X <- k */ + ctx->flags |= SEEN_X; + emit_load_imm(r_X, k, ctx); + break; + case BPF_S_LDX_MEM: + /* X <- M[k] */ + ctx->flags |= SEEN_X | SEEN_MEM; + emit_load(r_X, r_M, SCRATCH_OFF(k), ctx); + break; + case BPF_S_LDX_W_LEN: + /* X <- len */ + ctx->flags |= SEEN_X | SEEN_SKB; + off = offsetof(struct sk_buff, len); + emit_load(r_X, r_skb, off, ctx); + break; + case BPF_S_LDX_B_MSH: + /* X <- 4 * (P[k:1] & 0xf) */ + ctx->flags |= SEEN_X | SEEN_CALL | SEEN_S0 | SEEN_SKB; + /* Load offset to a1 */ + emit_load_func(r_s0, (ptr)jit_get_skb_b, ctx); + /* + * This may emit two instructions so it may not fit + * in the delay slot. So use a0 in the delay slot. + */ + emit_load_imm(MIPS_R_A1, k, ctx); + emit_jalr(MIPS_R_RA, r_s0, ctx); + emit_reg_move(MIPS_R_A0, r_skb, ctx); /* delay slot */ + /* Check the error value */ + if (config_enabled(CONFIG_64BIT)) { + /* Top 32-bits of $v0 on 64-bit */ + emit_dsrl32(r_s0, r_val, 0, ctx); + emit_bcond(MIPS_COND_NE, r_s0, r_zero, + 3 << 2, ctx); + } else { + emit_bcond(MIPS_COND_NE, r_err, r_zero, + 3 << 2, ctx); + } + /* No need for delay slot */ + /* We are good */ + /* X <- P[1:K] & 0xf */ + emit_andi(r_X, r_val, 0xf, ctx); + /* X << 2 */ + emit_b(b_imm(i + 1, ctx), ctx); + emit_sll(r_X, r_X, 2, ctx); /* delay slot */ + /* Return with error */ + emit_b(b_imm(prog->len, ctx), ctx); + emit_load_imm(r_ret, 0, ctx); /* delay slot */ + break; + case BPF_S_ST: + /* M[k] <- A */ + ctx->flags |= SEEN_MEM | SEEN_A; + emit_store(r_A, r_M, SCRATCH_OFF(k), ctx); + break; + case BPF_S_STX: + /* M[k] <- X */ + ctx->flags |= SEEN_MEM | SEEN_X; + emit_store(r_X, r_M, SCRATCH_OFF(k), ctx); + break; + case BPF_S_ALU_ADD_K: + /* A += K */ + ctx->flags |= SEEN_A; + emit_addiu(r_A, r_A, k, ctx); + break; + case BPF_S_ALU_ADD_X: + /* A += X */ + ctx->flags |= SEEN_A | SEEN_X; + emit_addu(r_A, r_A, r_X, ctx); + break; + case BPF_S_ALU_SUB_K: + /* A -= K */ + ctx->flags |= SEEN_A; + emit_addiu(r_A, r_A, -k, ctx); + break; + case BPF_S_ALU_SUB_X: + /* A -= X */ + ctx->flags |= SEEN_A | SEEN_X; + emit_subu(r_A, r_A, r_X, ctx); + break; + case BPF_S_ALU_MUL_K: + /* A *= K */ + /* Load K to scratch register before MUL */ + ctx->flags |= SEEN_A | SEEN_S0; + emit_load_imm(r_s0, k, ctx); + emit_mul(r_A, r_A, r_s0, ctx); + break; + case BPF_S_ALU_MUL_X: + /* A *= X */ + update_on_xread(ctx); + ctx->flags |= SEEN_A | SEEN_X; + emit_mul(r_A, r_A, r_X, ctx); + break; + case BPF_S_ALU_DIV_K: + /* A /= k */ + if (k == 1) + break; + if (optimize_div(&k)) { + ctx->flags |= SEEN_A; + emit_srl(r_A, r_A, k, ctx); + break; + } + ctx->flags |= SEEN_A | SEEN_S0; + emit_load_imm(r_s0, k, ctx); + emit_div(r_A, r_s0, ctx); + break; + case BPF_S_ALU_MOD_K: + /* A %= k */ + if (k == 1 || optimize_div(&k)) { + ctx->flags |= SEEN_A; + emit_jit_reg_move(r_A, r_zero, ctx); + } else { + ctx->flags |= SEEN_A | SEEN_S0; + emit_load_imm(r_s0, k, ctx); + emit_mod(r_A, r_s0, ctx); + } + break; + case BPF_S_ALU_DIV_X: + /* A /= X */ + update_on_xread(ctx); + ctx->flags |= SEEN_X | SEEN_A; + /* Check if r_X is zero */ + emit_bcond(MIPS_COND_EQ, r_X, r_zero, + b_imm(prog->len, ctx), ctx); + emit_load_imm(r_val, 0, ctx); /* delay slot */ + emit_div(r_A, r_X, ctx); + break; + case BPF_S_ALU_MOD_X: + /* A %= X */ + update_on_xread(ctx); + ctx->flags |= SEEN_X | SEEN_A; + /* Check if r_X is zero */ + emit_bcond(MIPS_COND_EQ, r_X, r_zero, + b_imm(prog->len, ctx), ctx); + emit_load_imm(r_val, 0, ctx); /* delay slot */ + emit_mod(r_A, r_X, ctx); + break; + case BPF_S_ALU_OR_K: + /* A |= K */ + ctx->flags |= SEEN_A; + emit_ori(r_A, r_A, k, ctx); + break; + case BPF_S_ALU_OR_X: + /* A |= X */ + update_on_xread(ctx); + ctx->flags |= SEEN_A; + emit_ori(r_A, r_A, r_X, ctx); + break; + case BPF_S_ALU_XOR_K: + /* A ^= k */ + ctx->flags |= SEEN_A; + emit_xori(r_A, r_A, k, ctx); + break; + case BPF_S_ANC_ALU_XOR_X: + case BPF_S_ALU_XOR_X: + /* A ^= X */ + update_on_xread(ctx); + ctx->flags |= SEEN_A; + emit_xor(r_A, r_A, r_X, ctx); + break; + case BPF_S_ALU_AND_K: + /* A &= K */ + ctx->flags |= SEEN_A; + emit_andi(r_A, r_A, k, ctx); + break; + case BPF_S_ALU_AND_X: + /* A &= X */ + update_on_xread(ctx); + ctx->flags |= SEEN_A | SEEN_X; + emit_and(r_A, r_A, r_X, ctx); + break; + case BPF_S_ALU_LSH_K: + /* A <<= K */ + ctx->flags |= SEEN_A; + emit_sll(r_A, r_A, k, ctx); + break; + case BPF_S_ALU_LSH_X: + /* A <<= X */ + ctx->flags |= SEEN_A | SEEN_X; + update_on_xread(ctx); + emit_sllv(r_A, r_A, r_X, ctx); + break; + case BPF_S_ALU_RSH_K: + /* A >>= K */ + ctx->flags |= SEEN_A; + emit_srl(r_A, r_A, k, ctx); + break; + case BPF_S_ALU_RSH_X: + ctx->flags |= SEEN_A | SEEN_X; + update_on_xread(ctx); + emit_srlv(r_A, r_A, r_X, ctx); + break; + case BPF_S_ALU_NEG: + /* A = -A */ + ctx->flags |= SEEN_A; + emit_neg(r_A, ctx); + break; + case BPF_S_JMP_JA: + /* pc += K */ + emit_b(b_imm(i + k + 1, ctx), ctx); + emit_nop(ctx); + break; + case BPF_S_JMP_JEQ_K: + /* pc += ( A == K ) ? pc->jt : pc->jf */ + condt = MIPS_COND_EQ | MIPS_COND_K; + goto jmp_cmp; + case BPF_S_JMP_JEQ_X: + ctx->flags |= SEEN_X; + /* pc += ( A == X ) ? pc->jt : pc->jf */ + condt = MIPS_COND_EQ | MIPS_COND_X; + goto jmp_cmp; + case BPF_S_JMP_JGE_K: + /* pc += ( A >= K ) ? pc->jt : pc->jf */ + condt = MIPS_COND_GE | MIPS_COND_K; + goto jmp_cmp; + case BPF_S_JMP_JGE_X: + ctx->flags |= SEEN_X; + /* pc += ( A >= X ) ? pc->jt : pc->jf */ + condt = MIPS_COND_GE | MIPS_COND_X; + goto jmp_cmp; + case BPF_S_JMP_JGT_K: + /* pc += ( A > K ) ? pc->jt : pc->jf */ + condt = MIPS_COND_GT | MIPS_COND_K; + goto jmp_cmp; + case BPF_S_JMP_JGT_X: + ctx->flags |= SEEN_X; + /* pc += ( A > X ) ? pc->jt : pc->jf */ + condt = MIPS_COND_GT | MIPS_COND_X; +jmp_cmp: + /* Greater or Equal */ + if ((condt & MIPS_COND_GE) || + (condt & MIPS_COND_GT)) { + if (condt & MIPS_COND_K) { /* K */ + ctx->flags |= SEEN_S0 | SEEN_A; + emit_sltiu(r_s0, r_A, k, ctx); + } else { /* X */ + ctx->flags |= SEEN_S0 | SEEN_A | + SEEN_X; + emit_sltu(r_s0, r_A, r_X, ctx); + } + /* A < (K|X) ? r_scrach = 1 */ + b_off = b_imm(i + inst->jf + 1, ctx); + emit_bcond(MIPS_COND_GT, r_s0, r_zero, b_off, + ctx); + emit_nop(ctx); + /* A > (K|X) ? scratch = 0 */ + if (condt & MIPS_COND_GT) { + /* Checking for equality */ + ctx->flags |= SEEN_S0 | SEEN_A | SEEN_X; + if (condt & MIPS_COND_K) + emit_load_imm(r_s0, k, ctx); + else + emit_jit_reg_move(r_s0, r_X, + ctx); + b_off = b_imm(i + inst->jf + 1, ctx); + emit_bcond(MIPS_COND_EQ, r_A, r_s0, + b_off, ctx); + emit_nop(ctx); + /* Finally, A > K|X */ + b_off = b_imm(i + inst->jt + 1, ctx); + emit_b(b_off, ctx); + emit_nop(ctx); + } else { + /* A >= (K|X) so jump */ + b_off = b_imm(i + inst->jt + 1, ctx); + emit_b(b_off, ctx); + emit_nop(ctx); + } + } else { + /* A == K|X */ + if (condt & MIPS_COND_K) { /* K */ + ctx->flags |= SEEN_S0 | SEEN_A; + emit_load_imm(r_s0, k, ctx); + /* jump true */ + b_off = b_imm(i + inst->jt + 1, ctx); + emit_bcond(MIPS_COND_EQ, r_A, r_s0, + b_off, ctx); + emit_nop(ctx); + /* jump false */ + b_off = b_imm(i + inst->jf + 1, + ctx); + emit_bcond(MIPS_COND_NE, r_A, r_s0, + b_off, ctx); + emit_nop(ctx); + } else { /* X */ + /* jump true */ + ctx->flags |= SEEN_A | SEEN_X; + b_off = b_imm(i + inst->jt + 1, + ctx); + emit_bcond(MIPS_COND_EQ, r_A, r_X, + b_off, ctx); + emit_nop(ctx); + /* jump false */ + b_off = b_imm(i + inst->jf + 1, ctx); + emit_bcond(MIPS_COND_NE, r_A, r_X, + b_off, ctx); + emit_nop(ctx); + } + } + break; + case BPF_S_JMP_JSET_K: + ctx->flags |= SEEN_S0 | SEEN_S1 | SEEN_A; + /* pc += (A & K) ? pc -> jt : pc -> jf */ + emit_load_imm(r_s1, k, ctx); + emit_and(r_s0, r_A, r_s1, ctx); + /* jump true */ + b_off = b_imm(i + inst->jt + 1, ctx); + emit_bcond(MIPS_COND_NE, r_s0, r_zero, b_off, ctx); + emit_nop(ctx); + /* jump false */ + b_off = b_imm(i + inst->jf + 1, ctx); + emit_b(b_off, ctx); + emit_nop(ctx); + break; + case BPF_S_JMP_JSET_X: + ctx->flags |= SEEN_S0 | SEEN_X | SEEN_A; + /* pc += (A & X) ? pc -> jt : pc -> jf */ + emit_and(r_s0, r_A, r_X, ctx); + /* jump true */ + b_off = b_imm(i + inst->jt + 1, ctx); + emit_bcond(MIPS_COND_NE, r_s0, r_zero, b_off, ctx); + emit_nop(ctx); + /* jump false */ + b_off = b_imm(i + inst->jf + 1, ctx); + emit_b(b_off, ctx); + emit_nop(ctx); + break; + case BPF_S_RET_A: + ctx->flags |= SEEN_A; + if (i != prog->len - 1) + /* + * If this is not the last instruction + * then jump to the epilogue + */ + emit_b(b_imm(prog->len, ctx), ctx); + emit_reg_move(r_ret, r_A, ctx); /* delay slot */ + break; + case BPF_S_RET_K: + /* + * It can emit two instructions so it does not fit on + * the delay slot. + */ + emit_load_imm(r_ret, k, ctx); + if (i != prog->len - 1) { + /* + * If this is not the last instruction + * then jump to the epilogue + */ + emit_b(b_imm(prog->len, ctx), ctx); + emit_nop(ctx); + } + break; + case BPF_S_MISC_TAX: + /* X = A */ + ctx->flags |= SEEN_X | SEEN_A; + emit_jit_reg_move(r_X, r_A, ctx); + break; + case BPF_S_MISC_TXA: + /* A = X */ + ctx->flags |= SEEN_A | SEEN_X; + update_on_xread(ctx); + emit_jit_reg_move(r_A, r_X, ctx); + break; + /* AUX */ + case BPF_S_ANC_PROTOCOL: + /* A = ntohs(skb->protocol */ + ctx->flags |= SEEN_SKB | SEEN_OFF | SEEN_A; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + protocol) != 2); + off = offsetof(struct sk_buff, protocol); + emit_half_load(r_A, r_skb, off, ctx); +#ifdef CONFIG_CPU_LITTLE_ENDIAN + /* This needs little endian fixup */ + if (cpu_has_mips_r2) { + /* R2 and later have the wsbh instruction */ + emit_wsbh(r_A, r_A, ctx); + } else { + /* Get first byte */ + emit_andi(r_tmp_imm, r_A, 0xff, ctx); + /* Shift it */ + emit_sll(r_tmp, r_tmp_imm, 8, ctx); + /* Get second byte */ + emit_srl(r_tmp_imm, r_A, 8, ctx); + emit_andi(r_tmp_imm, r_tmp_imm, 0xff, ctx); + /* Put everyting together in r_A */ + emit_or(r_A, r_tmp, r_tmp_imm, ctx); + } +#endif + break; + case BPF_S_ANC_CPU: + ctx->flags |= SEEN_A | SEEN_OFF; + /* A = current_thread_info()->cpu */ + BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, + cpu) != 4); + off = offsetof(struct thread_info, cpu); + /* $28/gp points to the thread_info struct */ + emit_load(r_A, 28, off, ctx); + break; + case BPF_S_ANC_IFINDEX: + /* A = skb->dev->ifindex */ + ctx->flags |= SEEN_SKB | SEEN_A | SEEN_S0; + off = offsetof(struct sk_buff, dev); + emit_load(r_s0, r_skb, off, ctx); + /* error (0) in the delay slot */ + emit_bcond(MIPS_COND_EQ, r_s0, r_zero, + b_imm(prog->len, ctx), ctx); + emit_reg_move(r_ret, r_zero, ctx); + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, + ifindex) != 4); + off = offsetof(struct net_device, ifindex); + emit_load(r_A, r_s0, off, ctx); + break; + case BPF_S_ANC_MARK: + ctx->flags |= SEEN_SKB | SEEN_A; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + off = offsetof(struct sk_buff, mark); + emit_load(r_A, r_skb, off, ctx); + break; + case BPF_S_ANC_RXHASH: + ctx->flags |= SEEN_SKB | SEEN_A; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + off = offsetof(struct sk_buff, hash); + emit_load(r_A, r_skb, off, ctx); + break; + case BPF_S_ANC_VLAN_TAG: + case BPF_S_ANC_VLAN_TAG_PRESENT: + ctx->flags |= SEEN_SKB | SEEN_S0 | SEEN_A; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + vlan_tci) != 2); + off = offsetof(struct sk_buff, vlan_tci); + emit_half_load(r_s0, r_skb, off, ctx); + if (inst->code == BPF_S_ANC_VLAN_TAG) + emit_and(r_A, r_s0, VLAN_VID_MASK, ctx); + else + emit_and(r_A, r_s0, VLAN_TAG_PRESENT, ctx); + break; + case BPF_S_ANC_PKTTYPE: + off = pkt_type_offset(); + + if (off < 0) + return -1; + emit_load_byte(r_tmp, r_skb, off, ctx); + /* Keep only the last 3 bits */ + emit_andi(r_A, r_tmp, PKT_TYPE_MAX, ctx); + break; + case BPF_S_ANC_QUEUE: + ctx->flags |= SEEN_SKB | SEEN_A; + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + queue_mapping) != 2); + BUILD_BUG_ON(offsetof(struct sk_buff, + queue_mapping) > 0xff); + off = offsetof(struct sk_buff, queue_mapping); + emit_half_load(r_A, r_skb, off, ctx); + break; + default: + pr_warn("%s: Unhandled opcode: 0x%02x\n", __FILE__, + inst->code); + return -1; + } + } + + /* compute offsets only during the first pass */ + if (ctx->target == NULL) + ctx->offsets[i] = ctx->idx * 4; + + return 0; +} + +int bpf_jit_enable __read_mostly; + +void bpf_jit_compile(struct sk_filter *fp) +{ + struct jit_ctx ctx; + unsigned int alloc_size, tmp_idx; + + if (!bpf_jit_enable) + return; + + memset(&ctx, 0, sizeof(ctx)); + + ctx.offsets = kcalloc(fp->len, sizeof(*ctx.offsets), GFP_KERNEL); + if (ctx.offsets == NULL) + return; + + ctx.skf = fp; + + if (build_body(&ctx)) + goto out; + + tmp_idx = ctx.idx; + build_prologue(&ctx); + ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4; + /* just to complete the ctx.idx count */ + build_epilogue(&ctx); + + alloc_size = 4 * ctx.idx; + ctx.target = module_alloc(alloc_size); + if (ctx.target == NULL) + goto out; + + /* Clean it */ + memset(ctx.target, 0, alloc_size); + + ctx.idx = 0; + + /* Generate the actual JIT code */ + build_prologue(&ctx); + build_body(&ctx); + build_epilogue(&ctx); + + /* Update the icache */ + flush_icache_range((ptr)ctx.target, (ptr)(ctx.target + ctx.idx)); + + if (bpf_jit_enable > 1) + /* Dump JIT code */ + bpf_jit_dump(fp->len, alloc_size, 2, ctx.target); + + fp->bpf_func = (void *)ctx.target; + fp->jited = 1; + +out: + kfree(ctx.offsets); +} + +void bpf_jit_free(struct sk_filter *fp) +{ + if (fp->jited) + module_free(NULL, fp->bpf_func); + kfree(fp); +} diff --git a/arch/mips/net/bpf_jit.h b/arch/mips/net/bpf_jit.h new file mode 100644 index 000000000000..3a5751b4335a --- /dev/null +++ b/arch/mips/net/bpf_jit.h @@ -0,0 +1,44 @@ +/* + * Just-In-Time compiler for BPF filters on MIPS + * + * Copyright (c) 2014 Imagination Technologies Ltd. + * Author: Markos Chandras <markos.chandras@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License. + */ + +#ifndef BPF_JIT_MIPS_OP_H +#define BPF_JIT_MIPS_OP_H + +/* Registers used by JIT */ +#define MIPS_R_ZERO 0 +#define MIPS_R_V0 2 +#define MIPS_R_V1 3 +#define MIPS_R_A0 4 +#define MIPS_R_A1 5 +#define MIPS_R_T6 14 +#define MIPS_R_T7 15 +#define MIPS_R_S0 16 +#define MIPS_R_S1 17 +#define MIPS_R_S2 18 +#define MIPS_R_S3 19 +#define MIPS_R_S4 20 +#define MIPS_R_S5 21 +#define MIPS_R_S6 22 +#define MIPS_R_S7 23 +#define MIPS_R_SP 29 +#define MIPS_R_RA 31 + +/* Conditional codes */ +#define MIPS_COND_EQ 0x1 +#define MIPS_COND_GE (0x1 << 1) +#define MIPS_COND_GT (0x1 << 2) +#define MIPS_COND_NE (0x1 << 3) +#define MIPS_COND_ALL (0x1 << 4) +/* Conditionals on X register or K immediate */ +#define MIPS_COND_X (0x1 << 5) +#define MIPS_COND_K (0x1 << 6) + +#endif /* BPF_JIT_MIPS_OP_H */ diff --git a/arch/mips/netlogic/common/irq.c b/arch/mips/netlogic/common/irq.c index 5afc4b7fce0f..c100b9afa0ab 100644 --- a/arch/mips/netlogic/common/irq.c +++ b/arch/mips/netlogic/common/irq.c @@ -203,6 +203,8 @@ void nlm_set_pic_extra_ack(int node, int irq, void (*xack)(struct irq_data *)) xirq = nlm_irq_to_xirq(node, irq); pic_data = irq_get_handler_data(xirq); + if (WARN_ON(!pic_data)) + return; pic_data->extra_ack = xack; } diff --git a/arch/mips/netlogic/common/reset.S b/arch/mips/netlogic/common/reset.S index b231fe1e7a09..701c4bcb9e47 100644 --- a/arch/mips/netlogic/common/reset.S +++ b/arch/mips/netlogic/common/reset.S @@ -35,6 +35,7 @@ #include <asm/asm.h> #include <asm/asm-offsets.h> +#include <asm/cpu.h> #include <asm/cacheops.h> #include <asm/regdef.h> #include <asm/mipsregs.h> @@ -74,13 +75,25 @@ .endm /* + * Allow access to physical mem >64G by enabling ELPA in PAGEGRAIN + * register. This is needed before going to C code since the SP can + * in this region. Called from all HW threads. + */ +.macro xlp_early_mmu_init + mfc0 t0, CP0_PAGEMASK, 1 + li t1, (1 << 29) /* ELPA bit */ + or t0, t1 + mtc0 t0, CP0_PAGEMASK, 1 +.endm + +/* * L1D cache has to be flushed before enabling threads in XLP. * On XLP8xx/XLP3xx, we do a low level flush using processor control * registers. On XLPII CPUs, usual cache instructions work. */ .macro xlp_flush_l1_dcache mfc0 t0, CP0_EBASE, 0 - andi t0, t0, 0xff00 + andi t0, t0, PRID_IMP_MASK slt t1, t0, 0x1200 beqz t1, 15f nop @@ -159,11 +172,15 @@ FEXPORT(nlm_reset_entry) 1: /* Entry point on core wakeup */ mfc0 t0, CP0_EBASE, 0 /* processor ID */ - andi t0, 0xff00 + andi t0, PRID_IMP_MASK li t1, 0x1500 /* XLP 9xx */ beq t0, t1, 2f /* does not need to set coherent */ nop + li t1, 0x1300 /* XLP 5xx */ + beq t0, t1, 2f /* does not need to set coherent */ + nop + /* set bit in SYS coherent register for the core */ mfc0 t0, CP0_EBASE, 1 mfc0 t1, CP0_EBASE, 1 @@ -197,6 +214,9 @@ FEXPORT(nlm_reset_entry) EXPORT(nlm_boot_siblings) /* core L1D flush before enable threads */ xlp_flush_l1_dcache + /* save ra and sp, will be used later (only for boot cpu) */ + dmtc0 ra, $22, 6 + dmtc0 sp, $22, 7 /* Enable hw threads by writing to MAP_THREADMODE of the core */ li t0, CKSEG1ADDR(RESET_DATA_PHYS) lw t1, BOOT_THREAD_MODE(t0) /* t1 <- thread mode */ @@ -225,6 +245,8 @@ EXPORT(nlm_boot_siblings) #endif mtc0 t1, CP0_STATUS + xlp_early_mmu_init + /* mark CPU ready */ li t3, CKSEG1ADDR(RESET_DATA_PHYS) ADDIU t1, t3, BOOT_CPU_READY @@ -238,14 +260,12 @@ EXPORT(nlm_boot_siblings) nop /* - * For the boot CPU, we have to restore registers and - * return + * For the boot CPU, we have to restore ra and sp and return, rest + * of the registers will be restored by the caller */ -4: dmfc0 t0, $4, 2 /* restore SP from UserLocal */ - li t1, 0xfadebeef - dmtc0 t1, $4, 2 /* restore SP from UserLocal */ - PTR_SUBU sp, t0, PT_SIZE - RESTORE_ALL +4: + dmfc0 ra, $22, 6 + dmfc0 sp, $22, 7 jr ra nop EXPORT(nlm_reset_entry_end) @@ -253,6 +273,7 @@ EXPORT(nlm_reset_entry_end) LEAF(nlm_init_boot_cpu) #ifdef CONFIG_CPU_XLP xlp_config_lsu + xlp_early_mmu_init #endif jr ra nop diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c index 6baae15cc7b1..4fde7ac76cc9 100644 --- a/arch/mips/netlogic/common/smp.c +++ b/arch/mips/netlogic/common/smp.c @@ -135,10 +135,6 @@ void nlm_smp_finish(void) local_irq_enable(); } -void nlm_cpus_done(void) -{ -} - /* * Boot all other cpus in the system, initialize them, and bring them into * the boot function @@ -198,7 +194,7 @@ void __init nlm_smp_setup(void) cpumask_scnprintf(buf, ARRAY_SIZE(buf), cpu_possible_mask); pr_info("Possible CPU mask: %s\n", buf); - /* check with the cores we have worken up */ + /* check with the cores we have woken up */ for (ncore = 0, i = 0; i < NLM_NR_NODES; i++) ncore += hweight32(nlm_get_node(i)->coremask); @@ -213,6 +209,7 @@ static int nlm_parse_cpumask(cpumask_t *wakeup_mask) { uint32_t core0_thr_mask, core_thr_mask; int threadmode, i, j; + char buf[64]; core0_thr_mask = 0; for (i = 0; i < NLM_THREADS_PER_CORE; i++) @@ -247,8 +244,8 @@ static int nlm_parse_cpumask(cpumask_t *wakeup_mask) return threadmode; unsupp: - panic("Unsupported CPU mask %lx", - (unsigned long)cpumask_bits(wakeup_mask)[0]); + cpumask_scnprintf(buf, ARRAY_SIZE(buf), wakeup_mask); + panic("Unsupported CPU mask %s", buf); return 0; } @@ -277,7 +274,6 @@ struct plat_smp_ops nlm_smp_ops = { .send_ipi_mask = nlm_send_ipi_mask, .init_secondary = nlm_init_secondary, .smp_finish = nlm_smp_finish, - .cpus_done = nlm_cpus_done, .boot_secondary = nlm_boot_secondary, .smp_setup = nlm_smp_setup, .prepare_cpus = nlm_prepare_cpus, diff --git a/arch/mips/netlogic/common/smpboot.S b/arch/mips/netlogic/common/smpboot.S index 8597657c27fc..805355b0bd05 100644 --- a/arch/mips/netlogic/common/smpboot.S +++ b/arch/mips/netlogic/common/smpboot.S @@ -54,8 +54,9 @@ .set noat .set arch=xlr /* for mfcr/mtcr, XLR is sufficient */ -FEXPORT(xlp_boot_core0_siblings) /* "Master" cpu starts from here */ - dmtc0 sp, $4, 2 /* SP saved in UserLocal */ +/* Called by the boot cpu to wake up its sibling threads */ +NESTED(xlp_boot_core0_siblings, PT_SIZE, sp) + /* CPU register contents lost when enabling threads, save them first */ SAVE_ALL sync /* find the location to which nlm_boot_siblings was relocated */ @@ -65,9 +66,12 @@ FEXPORT(xlp_boot_core0_siblings) /* "Master" cpu starts from here */ dsubu t2, t1 daddu t2, t0 /* call it */ - jr t2 + jalr t2 nop - /* not reached */ + RESTORE_ALL + jr ra + nop +END(xlp_boot_core0_siblings) NESTED(nlm_boot_secondary_cpus, 16, sp) /* Initialize CP0 Status */ diff --git a/arch/mips/netlogic/common/time.c b/arch/mips/netlogic/common/time.c index 13391b8a6031..0c0a1a606f73 100644 --- a/arch/mips/netlogic/common/time.c +++ b/arch/mips/netlogic/common/time.c @@ -82,6 +82,7 @@ static struct clocksource csrc_pic = { static void nlm_init_pic_timer(void) { uint64_t picbase = nlm_get_node(0)->picbase; + u32 picfreq; nlm_pic_set_timer(picbase, PIC_CLOCK_TIMER, ~0ULL, 0, 0); if (current_cpu_data.cputype == CPU_XLR) { @@ -92,7 +93,9 @@ static void nlm_init_pic_timer(void) csrc_pic.read = nlm_get_pic_timer; } csrc_pic.rating = 1000; - clocksource_register_hz(&csrc_pic, pic_timer_freq()); + picfreq = pic_timer_freq(); + clocksource_register_hz(&csrc_pic, picfreq); + pr_info("PIC clock source added, frequency %d\n", picfreq); } void __init plat_time_init(void) diff --git a/arch/mips/netlogic/dts/xlp_gvp.dts b/arch/mips/netlogic/dts/xlp_gvp.dts index 047d27f54487..bb4ecd1d47fc 100644 --- a/arch/mips/netlogic/dts/xlp_gvp.dts +++ b/arch/mips/netlogic/dts/xlp_gvp.dts @@ -26,11 +26,12 @@ interrupt-parent = <&pic>; interrupts = <17>; }; - pic: pic@4000 { - interrupt-controller; + pic: pic@110000 { + compatible = "netlogic,xlp-pic"; #address-cells = <0>; #interrupt-cells = <1>; reg = <0 0x110000 0x200>; + interrupt-controller; }; nor_flash@1,0 { diff --git a/arch/mips/netlogic/xlp/Makefile b/arch/mips/netlogic/xlp/Makefile index ed9a93c04650..be358a8050c5 100644 --- a/arch/mips/netlogic/xlp/Makefile +++ b/arch/mips/netlogic/xlp/Makefile @@ -2,3 +2,5 @@ obj-y += setup.o nlm_hal.o cop2-ex.o dt.o obj-$(CONFIG_SMP) += wakeup.o obj-$(CONFIG_USB) += usb-init.o obj-$(CONFIG_USB) += usb-init-xlp2.o +obj-$(CONFIG_SATA_AHCI) += ahci-init.o +obj-$(CONFIG_SATA_AHCI) += ahci-init-xlp2.o diff --git a/arch/mips/netlogic/xlp/ahci-init-xlp2.c b/arch/mips/netlogic/xlp/ahci-init-xlp2.c new file mode 100644 index 000000000000..c83dbf3689e2 --- /dev/null +++ b/arch/mips/netlogic/xlp/ahci-init-xlp2.c @@ -0,0 +1,377 @@ +/* + * Copyright (c) 2003-2014 Broadcom Corporation + * All Rights Reserved + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the Broadcom + * license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR + * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE + * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN + * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/dma-mapping.h> +#include <linux/kernel.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/irq.h> +#include <linux/bitops.h> +#include <linux/pci_ids.h> +#include <linux/nodemask.h> + +#include <asm/cpu.h> +#include <asm/mipsregs.h> + +#include <asm/netlogic/common.h> +#include <asm/netlogic/haldefs.h> +#include <asm/netlogic/mips-extns.h> +#include <asm/netlogic/xlp-hal/xlp.h> +#include <asm/netlogic/xlp-hal/iomap.h> + +#define SATA_CTL 0x0 +#define SATA_STATUS 0x1 /* Status Reg */ +#define SATA_INT 0x2 /* Interrupt Reg */ +#define SATA_INT_MASK 0x3 /* Interrupt Mask Reg */ +#define SATA_BIU_TIMEOUT 0x4 +#define AXIWRSPERRLOG 0x5 +#define AXIRDSPERRLOG 0x6 +#define BiuTimeoutLow 0x7 +#define BiuTimeoutHi 0x8 +#define BiuSlvErLow 0x9 +#define BiuSlvErHi 0xa +#define IO_CONFIG_SWAP_DIS 0xb +#define CR_REG_TIMER 0xc +#define CORE_ID 0xd +#define AXI_SLAVE_OPT1 0xe +#define PHY_MEM_ACCESS 0xf +#define PHY0_CNTRL 0x10 +#define PHY0_STAT 0x11 +#define PHY0_RX_ALIGN 0x12 +#define PHY0_RX_EQ_LO 0x13 +#define PHY0_RX_EQ_HI 0x14 +#define PHY0_BIST_LOOP 0x15 +#define PHY1_CNTRL 0x16 +#define PHY1_STAT 0x17 +#define PHY1_RX_ALIGN 0x18 +#define PHY1_RX_EQ_LO 0x19 +#define PHY1_RX_EQ_HI 0x1a +#define PHY1_BIST_LOOP 0x1b +#define RdExBase 0x1c +#define RdExLimit 0x1d +#define CacheAllocBase 0x1e +#define CacheAllocLimit 0x1f +#define BiuSlaveCmdGstNum 0x20 + +/*SATA_CTL Bits */ +#define SATA_RST_N BIT(0) /* Active low reset sata_core phy */ +#define SataCtlReserve0 BIT(1) +#define M_CSYSREQ BIT(2) /* AXI master low power, not used */ +#define S_CSYSREQ BIT(3) /* AXI slave low power, not used */ +#define P0_CP_DET BIT(8) /* Reserved, bring in from pad */ +#define P0_MP_SW BIT(9) /* Mech Switch */ +#define P0_DISABLE BIT(10) /* disable p0 */ +#define P0_ACT_LED_EN BIT(11) /* Active LED enable */ +#define P0_IRST_HARD_SYNTH BIT(12) /* PHY hard synth reset */ +#define P0_IRST_HARD_TXRX BIT(13) /* PHY lane hard reset */ +#define P0_IRST_POR BIT(14) /* PHY power on reset*/ +#define P0_IPDTXL BIT(15) /* PHY Tx lane dis/power down */ +#define P0_IPDRXL BIT(16) /* PHY Rx lane dis/power down */ +#define P0_IPDIPDMSYNTH BIT(17) /* PHY synthesizer dis/porwer down */ +#define P0_CP_POD_EN BIT(18) /* CP_POD enable */ +#define P0_AT_BYPASS BIT(19) /* P0 address translation by pass */ +#define P1_CP_DET BIT(20) /* Reserved,Cold Detect */ +#define P1_MP_SW BIT(21) /* Mech Switch */ +#define P1_DISABLE BIT(22) /* disable p1 */ +#define P1_ACT_LED_EN BIT(23) /* Active LED enable */ +#define P1_IRST_HARD_SYNTH BIT(24) /* PHY hard synth reset */ +#define P1_IRST_HARD_TXRX BIT(25) /* PHY lane hard reset */ +#define P1_IRST_POR BIT(26) /* PHY power on reset*/ +#define P1_IPDTXL BIT(27) /* PHY Tx lane dis/porwer down */ +#define P1_IPDRXL BIT(28) /* PHY Rx lane dis/porwer down */ +#define P1_IPDIPDMSYNTH BIT(29) /* PHY synthesizer dis/porwer down */ +#define P1_CP_POD_EN BIT(30) +#define P1_AT_BYPASS BIT(31) /* P1 address translation by pass */ + +/* Status register */ +#define M_CACTIVE BIT(0) /* m_cactive, not used */ +#define S_CACTIVE BIT(1) /* s_cactive, not used */ +#define P0_PHY_READY BIT(8) /* phy is ready */ +#define P0_CP_POD BIT(9) /* Cold PowerOn */ +#define P0_SLUMBER BIT(10) /* power mode slumber */ +#define P0_PATIAL BIT(11) /* power mode patial */ +#define P0_PHY_SIG_DET BIT(12) /* phy dignal detect */ +#define P0_PHY_CALI BIT(13) /* phy calibration done */ +#define P1_PHY_READY BIT(16) /* phy is ready */ +#define P1_CP_POD BIT(17) /* Cold PowerOn */ +#define P1_SLUMBER BIT(18) /* power mode slumber */ +#define P1_PATIAL BIT(19) /* power mode patial */ +#define P1_PHY_SIG_DET BIT(20) /* phy dignal detect */ +#define P1_PHY_CALI BIT(21) /* phy calibration done */ + +/* SATA CR_REG_TIMER bits */ +#define CR_TIME_SCALE (0x1000 << 0) + +/* SATA PHY specific registers start and end address */ +#define RXCDRCALFOSC0 0x0065 +#define CALDUTY 0x006e +#define RXDPIF 0x8065 +#define PPMDRIFTMAX_HI 0x80A4 + +#define nlm_read_sata_reg(b, r) nlm_read_reg(b, r) +#define nlm_write_sata_reg(b, r, v) nlm_write_reg(b, r, v) +#define nlm_get_sata_pcibase(node) \ + nlm_pcicfg_base(XLP9XX_IO_SATA_OFFSET(node)) +#define nlm_get_sata_regbase(node) \ + (nlm_get_sata_pcibase(node) + 0x100) + +/* SATA PHY config for register block 1 0x0065 .. 0x006e */ +static const u8 sata_phy_config1[] = { + 0xC9, 0xC9, 0x07, 0x07, 0x18, 0x18, 0x01, 0x01, 0x22, 0x00 +}; + +/* SATA PHY config for register block 2 0x0x8065 .. 0x0x80A4 */ +static const u8 sata_phy_config2[] = { + 0xAA, 0x00, 0x4C, 0xC9, 0xC9, 0x07, 0x07, 0x18, + 0x18, 0x05, 0x0C, 0x10, 0x00, 0x10, 0x00, 0xFF, + 0xCF, 0xF7, 0xE1, 0xF5, 0xFD, 0xFD, 0xFF, 0xFF, + 0xFF, 0xFF, 0xE3, 0xE7, 0xDB, 0xF5, 0xFD, 0xFD, + 0xF5, 0xF5, 0xFF, 0xFF, 0xE3, 0xE7, 0xDB, 0xF5, + 0xFD, 0xFD, 0xF5, 0xF5, 0xFF, 0xFF, 0xFF, 0xF5, + 0x3F, 0x00, 0x32, 0x00, 0x03, 0x01, 0x05, 0x05, + 0x04, 0x00, 0x00, 0x08, 0x04, 0x00, 0x00, 0x04, +}; + +const int sata_phy_debug = 0; /* set to verify PHY writes */ + +static void sata_clear_glue_reg(u64 regbase, u32 off, u32 bit) +{ + u32 reg_val; + + reg_val = nlm_read_sata_reg(regbase, off); + nlm_write_sata_reg(regbase, off, (reg_val & ~bit)); +} + +static void sata_set_glue_reg(u64 regbase, u32 off, u32 bit) +{ + u32 reg_val; + + reg_val = nlm_read_sata_reg(regbase, off); + nlm_write_sata_reg(regbase, off, (reg_val | bit)); +} + +static void write_phy_reg(u64 regbase, u32 addr, u32 physel, u8 data) +{ + nlm_write_sata_reg(regbase, PHY_MEM_ACCESS, + (1u << 31) | (physel << 24) | (data << 16) | addr); + udelay(850); +} + +static u8 read_phy_reg(u64 regbase, u32 addr, u32 physel) +{ + u32 val; + + nlm_write_sata_reg(regbase, PHY_MEM_ACCESS, + (0 << 31) | (physel << 24) | (0 << 16) | addr); + udelay(850); + val = nlm_read_sata_reg(regbase, PHY_MEM_ACCESS); + return (val >> 16) & 0xff; +} + +static void config_sata_phy(u64 regbase) +{ + u32 port, i, reg; + + for (port = 0; port < 2; port++) { + for (i = 0, reg = RXCDRCALFOSC0; reg <= CALDUTY; reg++, i++) + write_phy_reg(regbase, reg, port, sata_phy_config1[i]); + + for (i = 0, reg = RXDPIF; reg <= PPMDRIFTMAX_HI; reg++, i++) + write_phy_reg(regbase, reg, port, sata_phy_config2[i]); + } +} + +static void check_phy_register(u64 regbase, u32 addr, u32 physel, u8 xdata) +{ + u8 data; + + data = read_phy_reg(regbase, addr, physel); + pr_info("PHY read addr = 0x%x physel = %d data = 0x%x %s\n", + addr, physel, data, data == xdata ? "TRUE" : "FALSE"); +} + +static void verify_sata_phy_config(u64 regbase) +{ + u32 port, i, reg; + + for (port = 0; port < 2; port++) { + for (i = 0, reg = RXCDRCALFOSC0; reg <= CALDUTY; reg++, i++) + check_phy_register(regbase, reg, port, + sata_phy_config1[i]); + + for (i = 0, reg = RXDPIF; reg <= PPMDRIFTMAX_HI; reg++, i++) + check_phy_register(regbase, reg, port, + sata_phy_config2[i]); + } +} + +static void nlm_sata_firmware_init(int node) +{ + u32 reg_val; + u64 regbase; + int n; + + pr_info("Initializing XLP9XX On-chip AHCI...\n"); + regbase = nlm_get_sata_regbase(node); + + /* Reset port0 */ + sata_clear_glue_reg(regbase, SATA_CTL, P0_IRST_POR); + sata_clear_glue_reg(regbase, SATA_CTL, P0_IRST_HARD_TXRX); + sata_clear_glue_reg(regbase, SATA_CTL, P0_IRST_HARD_SYNTH); + sata_clear_glue_reg(regbase, SATA_CTL, P0_IPDTXL); + sata_clear_glue_reg(regbase, SATA_CTL, P0_IPDRXL); + sata_clear_glue_reg(regbase, SATA_CTL, P0_IPDIPDMSYNTH); + + /* port1 */ + sata_clear_glue_reg(regbase, SATA_CTL, P1_IRST_POR); + sata_clear_glue_reg(regbase, SATA_CTL, P1_IRST_HARD_TXRX); + sata_clear_glue_reg(regbase, SATA_CTL, P1_IRST_HARD_SYNTH); + sata_clear_glue_reg(regbase, SATA_CTL, P1_IPDTXL); + sata_clear_glue_reg(regbase, SATA_CTL, P1_IPDRXL); + sata_clear_glue_reg(regbase, SATA_CTL, P1_IPDIPDMSYNTH); + udelay(300); + + /* Set PHY */ + sata_set_glue_reg(regbase, SATA_CTL, P0_IPDTXL); + sata_set_glue_reg(regbase, SATA_CTL, P0_IPDRXL); + sata_set_glue_reg(regbase, SATA_CTL, P0_IPDIPDMSYNTH); + sata_set_glue_reg(regbase, SATA_CTL, P1_IPDTXL); + sata_set_glue_reg(regbase, SATA_CTL, P1_IPDRXL); + sata_set_glue_reg(regbase, SATA_CTL, P1_IPDIPDMSYNTH); + + udelay(1000); + sata_set_glue_reg(regbase, SATA_CTL, P0_IRST_POR); + udelay(1000); + sata_set_glue_reg(regbase, SATA_CTL, P1_IRST_POR); + udelay(1000); + + /* setup PHY */ + config_sata_phy(regbase); + if (sata_phy_debug) + verify_sata_phy_config(regbase); + + udelay(1000); + sata_set_glue_reg(regbase, SATA_CTL, P0_IRST_HARD_TXRX); + sata_set_glue_reg(regbase, SATA_CTL, P0_IRST_HARD_SYNTH); + sata_set_glue_reg(regbase, SATA_CTL, P1_IRST_HARD_TXRX); + sata_set_glue_reg(regbase, SATA_CTL, P1_IRST_HARD_SYNTH); + udelay(300); + + /* Override reset in serial PHY mode */ + sata_set_glue_reg(regbase, CR_REG_TIMER, CR_TIME_SCALE); + /* Set reset SATA */ + sata_set_glue_reg(regbase, SATA_CTL, SATA_RST_N); + sata_set_glue_reg(regbase, SATA_CTL, M_CSYSREQ); + sata_set_glue_reg(regbase, SATA_CTL, S_CSYSREQ); + + pr_debug("Waiting for PHYs to come up.\n"); + n = 10000; + do { + reg_val = nlm_read_sata_reg(regbase, SATA_STATUS); + if ((reg_val & P1_PHY_READY) && (reg_val & P0_PHY_READY)) + break; + udelay(10); + } while (--n > 0); + + if (reg_val & P0_PHY_READY) + pr_info("PHY0 is up.\n"); + else + pr_info("PHY0 is down.\n"); + if (reg_val & P1_PHY_READY) + pr_info("PHY1 is up.\n"); + else + pr_info("PHY1 is down.\n"); + + pr_info("XLP AHCI Init Done.\n"); +} + +static int __init nlm_ahci_init(void) +{ + int node; + + if (!cpu_is_xlp9xx()) + return 0; + for (node = 0; node < NLM_NR_NODES; node++) + if (nlm_node_present(node)) + nlm_sata_firmware_init(node); + return 0; +} + +static void nlm_sata_intr_ack(struct irq_data *data) +{ + u64 regbase; + u32 val; + int node; + + node = data->irq / NLM_IRQS_PER_NODE; + regbase = nlm_get_sata_regbase(node); + val = nlm_read_sata_reg(regbase, SATA_INT); + sata_set_glue_reg(regbase, SATA_INT, val); +} + +static void nlm_sata_fixup_bar(struct pci_dev *dev) +{ + dev->resource[5] = dev->resource[0]; + memset(&dev->resource[0], 0, sizeof(dev->resource[0])); +} + +static void nlm_sata_fixup_final(struct pci_dev *dev) +{ + u32 val; + u64 regbase; + int node; + + /* Find end bridge function to find node */ + node = xlp_socdev_to_node(dev); + regbase = nlm_get_sata_regbase(node); + + /* clear pending interrupts and then enable them */ + val = nlm_read_sata_reg(regbase, SATA_INT); + sata_set_glue_reg(regbase, SATA_INT, val); + + /* Enable only the core interrupt */ + sata_set_glue_reg(regbase, SATA_INT_MASK, 0x1); + + dev->irq = nlm_irq_to_xirq(node, PIC_SATA_IRQ); + nlm_set_pic_extra_ack(node, PIC_SATA_IRQ, nlm_sata_intr_ack); +} + +arch_initcall(nlm_ahci_init); + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_XLP9XX_SATA, + nlm_sata_fixup_bar); + +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_XLP9XX_SATA, + nlm_sata_fixup_final); diff --git a/arch/mips/netlogic/xlp/ahci-init.c b/arch/mips/netlogic/xlp/ahci-init.c new file mode 100644 index 000000000000..a9d0fae02103 --- /dev/null +++ b/arch/mips/netlogic/xlp/ahci-init.c @@ -0,0 +1,209 @@ +/* + * Copyright (c) 2003-2014 Broadcom Corporation + * All Rights Reserved + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the Broadcom + * license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR + * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE + * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN + * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/dma-mapping.h> +#include <linux/kernel.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/irq.h> +#include <linux/bitops.h> + +#include <asm/cpu.h> +#include <asm/mipsregs.h> + +#include <asm/netlogic/haldefs.h> +#include <asm/netlogic/xlp-hal/xlp.h> +#include <asm/netlogic/common.h> +#include <asm/netlogic/xlp-hal/iomap.h> +#include <asm/netlogic/mips-extns.h> + +#define SATA_CTL 0x0 +#define SATA_STATUS 0x1 /* Status Reg */ +#define SATA_INT 0x2 /* Interrupt Reg */ +#define SATA_INT_MASK 0x3 /* Interrupt Mask Reg */ +#define SATA_CR_REG_TIMER 0x4 /* PHY Conrol Timer Reg */ +#define SATA_CORE_ID 0x5 /* Core ID Reg */ +#define SATA_AXI_SLAVE_OPT1 0x6 /* AXI Slave Options Reg */ +#define SATA_PHY_LOS_LEV 0x7 /* PHY LOS Level Reg */ +#define SATA_PHY_MULTI 0x8 /* PHY Multiplier Reg */ +#define SATA_PHY_CLK_SEL 0x9 /* Clock Select Reg */ +#define SATA_PHY_AMP1_GEN1 0xa /* PHY Transmit Amplitude Reg 1 */ +#define SATA_PHY_AMP1_GEN2 0xb /* PHY Transmit Amplitude Reg 2 */ +#define SATA_PHY_AMP1_GEN3 0xc /* PHY Transmit Amplitude Reg 3 */ +#define SATA_PHY_PRE1 0xd /* PHY Transmit Preemphasis Reg 1 */ +#define SATA_PHY_PRE2 0xe /* PHY Transmit Preemphasis Reg 2 */ +#define SATA_PHY_PRE3 0xf /* PHY Transmit Preemphasis Reg 3 */ +#define SATA_SPDMODE 0x10 /* Speed Mode Reg */ +#define SATA_REFCLK 0x11 /* Reference Clock Control Reg */ +#define SATA_BYTE_SWAP_DIS 0x12 /* byte swap disable */ + +/*SATA_CTL Bits */ +#define SATA_RST_N BIT(0) +#define PHY0_RESET_N BIT(16) +#define PHY1_RESET_N BIT(17) +#define PHY2_RESET_N BIT(18) +#define PHY3_RESET_N BIT(19) +#define M_CSYSREQ BIT(2) +#define S_CSYSREQ BIT(3) + +/*SATA_STATUS Bits */ +#define P0_PHY_READY BIT(4) +#define P1_PHY_READY BIT(5) +#define P2_PHY_READY BIT(6) +#define P3_PHY_READY BIT(7) + +#define nlm_read_sata_reg(b, r) nlm_read_reg(b, r) +#define nlm_write_sata_reg(b, r, v) nlm_write_reg(b, r, v) +#define nlm_get_sata_pcibase(node) \ + nlm_pcicfg_base(XLP_IO_SATA_OFFSET(node)) +/* SATA device specific configuration registers are starts at 0x900 offset */ +#define nlm_get_sata_regbase(node) \ + (nlm_get_sata_pcibase(node) + 0x900) + +static void sata_clear_glue_reg(uint64_t regbase, uint32_t off, uint32_t bit) +{ + uint32_t reg_val; + + reg_val = nlm_read_sata_reg(regbase, off); + nlm_write_sata_reg(regbase, off, (reg_val & ~bit)); +} + +static void sata_set_glue_reg(uint64_t regbase, uint32_t off, uint32_t bit) +{ + uint32_t reg_val; + + reg_val = nlm_read_sata_reg(regbase, off); + nlm_write_sata_reg(regbase, off, (reg_val | bit)); +} + +static void nlm_sata_firmware_init(int node) +{ + uint32_t reg_val; + uint64_t regbase; + int i; + + pr_info("XLP AHCI Initialization started.\n"); + regbase = nlm_get_sata_regbase(node); + + /* Reset SATA */ + sata_clear_glue_reg(regbase, SATA_CTL, SATA_RST_N); + /* Reset PHY */ + sata_clear_glue_reg(regbase, SATA_CTL, + (PHY3_RESET_N | PHY2_RESET_N + | PHY1_RESET_N | PHY0_RESET_N)); + + /* Set SATA */ + sata_set_glue_reg(regbase, SATA_CTL, SATA_RST_N); + /* Set PHY */ + sata_set_glue_reg(regbase, SATA_CTL, + (PHY3_RESET_N | PHY2_RESET_N + | PHY1_RESET_N | PHY0_RESET_N)); + + pr_debug("Waiting for PHYs to come up.\n"); + i = 0; + do { + reg_val = nlm_read_sata_reg(regbase, SATA_STATUS); + i++; + } while (((reg_val & 0xF0) != 0xF0) && (i < 10000)); + + for (i = 0; i < 4; i++) { + if (reg_val & (P0_PHY_READY << i)) + pr_info("PHY%d is up.\n", i); + else + pr_info("PHY%d is down.\n", i); + } + + pr_info("XLP AHCI init done.\n"); +} + +static int __init nlm_ahci_init(void) +{ + int node = 0; + int chip = read_c0_prid() & PRID_REV_MASK; + + if (chip == PRID_IMP_NETLOGIC_XLP3XX) + nlm_sata_firmware_init(node); + return 0; +} + +static void nlm_sata_intr_ack(struct irq_data *data) +{ + uint32_t val = 0; + uint64_t regbase; + + regbase = nlm_get_sata_regbase(nlm_nodeid()); + val = nlm_read_sata_reg(regbase, SATA_INT); + sata_set_glue_reg(regbase, SATA_INT, val); +} + +static void nlm_sata_fixup_bar(struct pci_dev *dev) +{ + /* + * The AHCI resource is in BAR 0, move it to + * BAR 5, where it is expected + */ + dev->resource[5] = dev->resource[0]; + memset(&dev->resource[0], 0, sizeof(dev->resource[0])); +} + +static void nlm_sata_fixup_final(struct pci_dev *dev) +{ + uint32_t val; + uint64_t regbase; + int node = 0; /* XLP3XX does not support multi-node */ + + regbase = nlm_get_sata_regbase(node); + + /* clear pending interrupts and then enable them */ + val = nlm_read_sata_reg(regbase, SATA_INT); + sata_set_glue_reg(regbase, SATA_INT, val); + + /* Mask the core interrupt. If all the interrupts + * are enabled there are spurious interrupt flow + * happening, to avoid only enable core interrupt + * mask. + */ + sata_set_glue_reg(regbase, SATA_INT_MASK, 0x1); + + dev->irq = PIC_SATA_IRQ; + nlm_set_pic_extra_ack(node, PIC_SATA_IRQ, nlm_sata_intr_ack); +} + +arch_initcall(nlm_ahci_init); + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_NETLOGIC, PCI_DEVICE_ID_NLM_SATA, + nlm_sata_fixup_bar); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_NETLOGIC, PCI_DEVICE_ID_NLM_SATA, + nlm_sata_fixup_final); diff --git a/arch/mips/netlogic/xlp/dt.c b/arch/mips/netlogic/xlp/dt.c index 5754097b9cde..7cc46032b28e 100644 --- a/arch/mips/netlogic/xlp/dt.c +++ b/arch/mips/netlogic/xlp/dt.c @@ -42,15 +42,16 @@ #include <asm/prom.h> extern u32 __dtb_xlp_evp_begin[], __dtb_xlp_svp_begin[], - __dtb_xlp_fvp_begin[], __dtb_xlp_gvp_begin[], __dtb_start[]; + __dtb_xlp_fvp_begin[], __dtb_xlp_gvp_begin[]; static void *xlp_fdt_blob; void __init *xlp_dt_init(void *fdtp) { if (!fdtp) { - switch (current_cpu_data.processor_id & 0xff00) { + switch (current_cpu_data.processor_id & PRID_IMP_MASK) { #ifdef CONFIG_DT_XLP_GVP case PRID_IMP_NETLOGIC_XLP9XX: + case PRID_IMP_NETLOGIC_XLP5XX: fdtp = __dtb_xlp_gvp_begin; break; #endif @@ -87,22 +88,7 @@ void __init xlp_early_init_devtree(void) void __init device_tree_init(void) { - unsigned long base, size; - struct boot_param_header *fdtp = xlp_fdt_blob; - - if (!fdtp) - return; - - base = virt_to_phys(fdtp); - size = be32_to_cpu(fdtp->totalsize); - - /* Before we do anything, lets reserve the dt blob */ - reserve_bootmem(base, size, BOOTMEM_DEFAULT); - - unflatten_device_tree(); - - /* free the space reserved for the dt blob */ - free_bootmem(base, size); + unflatten_and_copy_device_tree(); } static struct of_device_id __initdata xlp_ids[] = { diff --git a/arch/mips/netlogic/xlp/nlm_hal.c b/arch/mips/netlogic/xlp/nlm_hal.c index 997cd9ee10de..bc24beb3a426 100644 --- a/arch/mips/netlogic/xlp/nlm_hal.c +++ b/arch/mips/netlogic/xlp/nlm_hal.c @@ -54,6 +54,8 @@ void nlm_node_init(int node) struct nlm_soc_info *nodep; nodep = nlm_get_node(node); + if (node == 0) + nodep->coremask = 1; /* node 0, boot cpu */ nodep->sysbase = nlm_get_sys_regbase(node); nodep->picbase = nlm_get_pic_regbase(node); nodep->ebase = read_c0_ebase() & (~((1 << 12) - 1)); @@ -64,31 +66,39 @@ void nlm_node_init(int node) spin_lock_init(&nodep->piclock); } -int nlm_irq_to_irt(int irq) +static int xlp9xx_irq_to_irt(int irq) +{ + switch (irq) { + case PIC_GPIO_IRQ: + return 12; + case PIC_9XX_XHCI_0_IRQ: + return 114; + case PIC_9XX_XHCI_1_IRQ: + return 115; + case PIC_UART_0_IRQ: + return 133; + case PIC_UART_1_IRQ: + return 134; + case PIC_SATA_IRQ: + return 143; + case PIC_SPI_IRQ: + return 152; + case PIC_MMC_IRQ: + return 153; + case PIC_PCIE_LINK_LEGACY_IRQ(0): + case PIC_PCIE_LINK_LEGACY_IRQ(1): + case PIC_PCIE_LINK_LEGACY_IRQ(2): + case PIC_PCIE_LINK_LEGACY_IRQ(3): + return 191 + irq - PIC_PCIE_LINK_LEGACY_IRQ_BASE; + } + return -1; +} + +static int xlp_irq_to_irt(int irq) { uint64_t pcibase; int devoff, irt; - /* bypass for 9xx */ - if (cpu_is_xlp9xx()) { - switch (irq) { - case PIC_9XX_XHCI_0_IRQ: - return 114; - case PIC_9XX_XHCI_1_IRQ: - return 115; - case PIC_UART_0_IRQ: - return 133; - case PIC_UART_1_IRQ: - return 134; - case PIC_PCIE_LINK_LEGACY_IRQ(0): - case PIC_PCIE_LINK_LEGACY_IRQ(1): - case PIC_PCIE_LINK_LEGACY_IRQ(2): - case PIC_PCIE_LINK_LEGACY_IRQ(3): - return 191 + irq - PIC_PCIE_LINK_LEGACY_IRQ_BASE; - } - return -1; - } - devoff = 0; switch (irq) { case PIC_UART_0_IRQ: @@ -98,7 +108,7 @@ int nlm_irq_to_irt(int irq) devoff = XLP_IO_UART1_OFFSET(0); break; case PIC_MMC_IRQ: - devoff = XLP_IO_SD_OFFSET(0); + devoff = XLP_IO_MMC_OFFSET(0); break; case PIC_I2C_0_IRQ: /* I2C will be fixed up */ case PIC_I2C_1_IRQ: @@ -109,6 +119,18 @@ int nlm_irq_to_irt(int irq) else devoff = XLP_IO_I2C0_OFFSET(0); break; + case PIC_SATA_IRQ: + devoff = XLP_IO_SATA_OFFSET(0); + break; + case PIC_GPIO_IRQ: + devoff = XLP_IO_GPIO_OFFSET(0); + break; + case PIC_NAND_IRQ: + devoff = XLP_IO_NAND_OFFSET(0); + break; + case PIC_SPI_IRQ: + devoff = XLP_IO_SPI_OFFSET(0); + break; default: if (cpu_is_xlpii()) { switch (irq) { @@ -164,61 +186,123 @@ int nlm_irq_to_irt(int irq) /* HW bug, PCI IRT entries are bad on early silicon, fix */ irt = PIC_IRT_PCIE_LINK_INDEX(irq - PIC_PCIE_LINK_LEGACY_IRQ_BASE); - } else if (irq >= PIC_PCIE_LINK_MSI_IRQ(0) && - irq <= PIC_PCIE_LINK_MSI_IRQ(3)) { - irt = -2; - } else if (irq >= PIC_PCIE_MSIX_IRQ(0) && - irq <= PIC_PCIE_MSIX_IRQ(3)) { - irt = -2; } else { irt = -1; } return irt; } -unsigned int nlm_get_core_frequency(int node, int core) +int nlm_irq_to_irt(int irq) { - unsigned int pll_divf, pll_divr, dfs_div, ext_div; - unsigned int rstval, dfsval, denom; - uint64_t num, sysbase; + /* return -2 for irqs without 1-1 mapping */ + if (irq >= PIC_PCIE_LINK_MSI_IRQ(0) && irq <= PIC_PCIE_LINK_MSI_IRQ(3)) + return -2; + if (irq >= PIC_PCIE_MSIX_IRQ(0) && irq <= PIC_PCIE_MSIX_IRQ(3)) + return -2; - sysbase = nlm_get_node(node)->sysbase; if (cpu_is_xlp9xx()) - rstval = nlm_read_sys_reg(sysbase, SYS_9XX_POWER_ON_RESET_CFG); + return xlp9xx_irq_to_irt(irq); else - rstval = nlm_read_sys_reg(sysbase, SYS_POWER_ON_RESET_CFG); - if (cpu_is_xlpii()) { - num = 1000000ULL * (400 * 3 + 100 * (rstval >> 26)); - denom = 3; + return xlp_irq_to_irt(irq); +} + +static unsigned int nlm_xlp2_get_core_frequency(int node, int core) +{ + unsigned int pll_post_div, ctrl_val0, ctrl_val1, denom; + uint64_t num, sysbase, clockbase; + + if (cpu_is_xlp9xx()) { + clockbase = nlm_get_clock_regbase(node); + ctrl_val0 = nlm_read_sys_reg(clockbase, + SYS_9XX_CPU_PLL_CTRL0(core)); + ctrl_val1 = nlm_read_sys_reg(clockbase, + SYS_9XX_CPU_PLL_CTRL1(core)); } else { - dfsval = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIV_VALUE); - pll_divf = ((rstval >> 10) & 0x7f) + 1; - pll_divr = ((rstval >> 8) & 0x3) + 1; - ext_div = ((rstval >> 30) & 0x3) + 1; - dfs_div = ((dfsval >> (core * 4)) & 0xf) + 1; - - num = 800000000ULL * pll_divf; - denom = 3 * pll_divr * ext_div * dfs_div; + sysbase = nlm_get_node(node)->sysbase; + ctrl_val0 = nlm_read_sys_reg(sysbase, + SYS_CPU_PLL_CTRL0(core)); + ctrl_val1 = nlm_read_sys_reg(sysbase, + SYS_CPU_PLL_CTRL1(core)); + } + + /* Find PLL post divider value */ + switch ((ctrl_val0 >> 24) & 0x7) { + case 1: + pll_post_div = 2; + break; + case 3: + pll_post_div = 4; + break; + case 7: + pll_post_div = 8; + break; + case 6: + pll_post_div = 16; + break; + case 0: + default: + pll_post_div = 1; + break; } + + num = 1000000ULL * (400 * 3 + 100 * (ctrl_val1 & 0x3f)); + denom = 3 * pll_post_div; do_div(num, denom); + return (unsigned int)num; } -/* Calculate Frequency to the PIC from PLL. - * freq_out = ( ref_freq/2 * (6 + ctrl2[7:0]) + ctrl2[20:8]/2^13 ) / - * ((2^ctrl0[7:5]) * Table(ctrl0[26:24])) +static unsigned int nlm_xlp_get_core_frequency(int node, int core) +{ + unsigned int pll_divf, pll_divr, dfs_div, ext_div; + unsigned int rstval, dfsval, denom; + uint64_t num, sysbase; + + sysbase = nlm_get_node(node)->sysbase; + rstval = nlm_read_sys_reg(sysbase, SYS_POWER_ON_RESET_CFG); + dfsval = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIV_VALUE); + pll_divf = ((rstval >> 10) & 0x7f) + 1; + pll_divr = ((rstval >> 8) & 0x3) + 1; + ext_div = ((rstval >> 30) & 0x3) + 1; + dfs_div = ((dfsval >> (core * 4)) & 0xf) + 1; + + num = 800000000ULL * pll_divf; + denom = 3 * pll_divr * ext_div * dfs_div; + do_div(num, denom); + + return (unsigned int)num; +} + +unsigned int nlm_get_core_frequency(int node, int core) +{ + if (cpu_is_xlpii()) + return nlm_xlp2_get_core_frequency(node, core); + else + return nlm_xlp_get_core_frequency(node, core); +} + +/* + * Calculate PIC frequency from PLL registers. + * freq_out = (ref_freq/2 * (6 + ctrl2[7:0]) + ctrl2[20:8]/2^13) / + * ((2^ctrl0[7:5]) * Table(ctrl0[26:24])) */ -static unsigned int nlm_2xx_get_pic_frequency(int node) +static unsigned int nlm_xlp2_get_pic_frequency(int node) { - u32 ctrl_val0, ctrl_val2, vco_post_div, pll_post_div; + u32 ctrl_val0, ctrl_val2, vco_post_div, pll_post_div, cpu_xlp9xx; u32 mdiv, fdiv, pll_out_freq_den, reg_select, ref_div, pic_div; - u64 ref_clk, sysbase, pll_out_freq_num, ref_clk_select; + u64 sysbase, pll_out_freq_num, ref_clk_select, clockbase, ref_clk; sysbase = nlm_get_node(node)->sysbase; + clockbase = nlm_get_clock_regbase(node); + cpu_xlp9xx = cpu_is_xlp9xx(); /* Find ref_clk_base */ - ref_clk_select = - (nlm_read_sys_reg(sysbase, SYS_POWER_ON_RESET_CFG) >> 18) & 0x3; + if (cpu_xlp9xx) + ref_clk_select = (nlm_read_sys_reg(sysbase, + SYS_9XX_POWER_ON_RESET_CFG) >> 18) & 0x3; + else + ref_clk_select = (nlm_read_sys_reg(sysbase, + SYS_POWER_ON_RESET_CFG) >> 18) & 0x3; switch (ref_clk_select) { case 0: ref_clk = 200000000ULL; @@ -239,30 +323,70 @@ static unsigned int nlm_2xx_get_pic_frequency(int node) } /* Find the clock source PLL device for PIC */ - reg_select = (nlm_read_sys_reg(sysbase, SYS_CLK_DEV_SEL) >> 22) & 0x3; - switch (reg_select) { - case 0: - ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0); - ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2); - break; - case 1: - ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(0)); - ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(0)); - break; - case 2: - ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(1)); - ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(1)); - break; - case 3: - ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(2)); - ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(2)); - break; + if (cpu_xlp9xx) { + reg_select = nlm_read_sys_reg(clockbase, + SYS_9XX_CLK_DEV_SEL) & 0x3; + switch (reg_select) { + case 0: + ctrl_val0 = nlm_read_sys_reg(clockbase, + SYS_9XX_PLL_CTRL0); + ctrl_val2 = nlm_read_sys_reg(clockbase, + SYS_9XX_PLL_CTRL2); + break; + case 1: + ctrl_val0 = nlm_read_sys_reg(clockbase, + SYS_9XX_PLL_CTRL0_DEVX(0)); + ctrl_val2 = nlm_read_sys_reg(clockbase, + SYS_9XX_PLL_CTRL2_DEVX(0)); + break; + case 2: + ctrl_val0 = nlm_read_sys_reg(clockbase, + SYS_9XX_PLL_CTRL0_DEVX(1)); + ctrl_val2 = nlm_read_sys_reg(clockbase, + SYS_9XX_PLL_CTRL2_DEVX(1)); + break; + case 3: + ctrl_val0 = nlm_read_sys_reg(clockbase, + SYS_9XX_PLL_CTRL0_DEVX(2)); + ctrl_val2 = nlm_read_sys_reg(clockbase, + SYS_9XX_PLL_CTRL2_DEVX(2)); + break; + } + } else { + reg_select = (nlm_read_sys_reg(sysbase, + SYS_CLK_DEV_SEL) >> 22) & 0x3; + switch (reg_select) { + case 0: + ctrl_val0 = nlm_read_sys_reg(sysbase, + SYS_PLL_CTRL0); + ctrl_val2 = nlm_read_sys_reg(sysbase, + SYS_PLL_CTRL2); + break; + case 1: + ctrl_val0 = nlm_read_sys_reg(sysbase, + SYS_PLL_CTRL0_DEVX(0)); + ctrl_val2 = nlm_read_sys_reg(sysbase, + SYS_PLL_CTRL2_DEVX(0)); + break; + case 2: + ctrl_val0 = nlm_read_sys_reg(sysbase, + SYS_PLL_CTRL0_DEVX(1)); + ctrl_val2 = nlm_read_sys_reg(sysbase, + SYS_PLL_CTRL2_DEVX(1)); + break; + case 3: + ctrl_val0 = nlm_read_sys_reg(sysbase, + SYS_PLL_CTRL0_DEVX(2)); + ctrl_val2 = nlm_read_sys_reg(sysbase, + SYS_PLL_CTRL2_DEVX(2)); + break; + } } vco_post_div = (ctrl_val0 >> 5) & 0x7; pll_post_div = (ctrl_val0 >> 24) & 0x7; mdiv = ctrl_val2 & 0xff; - fdiv = (ctrl_val2 >> 8) & 0xfff; + fdiv = (ctrl_val2 >> 8) & 0x1fff; /* Find PLL post divider value */ switch (pll_post_div) { @@ -292,7 +416,12 @@ static unsigned int nlm_2xx_get_pic_frequency(int node) do_div(pll_out_freq_num, pll_out_freq_den); /* PIC post divider, which happens after PLL */ - pic_div = (nlm_read_sys_reg(sysbase, SYS_CLK_DEV_DIV) >> 22) & 0x3; + if (cpu_xlp9xx) + pic_div = nlm_read_sys_reg(clockbase, + SYS_9XX_CLK_DEV_DIV) & 0x3; + else + pic_div = (nlm_read_sys_reg(sysbase, + SYS_CLK_DEV_DIV) >> 22) & 0x3; do_div(pll_out_freq_num, 1 << pic_div); return pll_out_freq_num; @@ -300,12 +429,8 @@ static unsigned int nlm_2xx_get_pic_frequency(int node) unsigned int nlm_get_pic_frequency(int node) { - /* TODO Has to calculate freq as like 2xx */ - if (cpu_is_xlp9xx()) - return 250000000; - if (cpu_is_xlpii()) - return nlm_2xx_get_pic_frequency(node); + return nlm_xlp2_get_pic_frequency(node); else return 133333333; } diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c index 8c60a2dd9ef6..4fdd9fd29d1d 100644 --- a/arch/mips/netlogic/xlp/setup.c +++ b/arch/mips/netlogic/xlp/setup.c @@ -121,8 +121,9 @@ void __init plat_mem_setup(void) const char *get_system_type(void) { - switch (read_c0_prid() & 0xff00) { + switch (read_c0_prid() & PRID_IMP_MASK) { case PRID_IMP_NETLOGIC_XLP9XX: + case PRID_IMP_NETLOGIC_XLP5XX: case PRID_IMP_NETLOGIC_XLP2XX: return "Broadcom XLPII Series"; default: diff --git a/arch/mips/netlogic/xlp/wakeup.c b/arch/mips/netlogic/xlp/wakeup.c index 9a92617a2af5..e5f44d2605a8 100644 --- a/arch/mips/netlogic/xlp/wakeup.c +++ b/arch/mips/netlogic/xlp/wakeup.c @@ -135,11 +135,19 @@ static void xlp_enable_secondary_cores(const cpumask_t *wakeup_mask) if (cpu_is_xlp9xx()) { fusebase = nlm_get_fuse_regbase(n); fusemask = nlm_read_reg(fusebase, FUSE_9XX_DEVCFG6); - mask = 0xfffff; + switch (read_c0_prid() & PRID_IMP_MASK) { + case PRID_IMP_NETLOGIC_XLP5XX: + mask = 0xff; + break; + case PRID_IMP_NETLOGIC_XLP9XX: + default: + mask = 0xfffff; + break; + } } else { fusemask = nlm_read_sys_reg(nodep->sysbase, SYS_EFUSE_DEVICE_CFG_STATUS0); - switch (read_c0_prid() & 0xff00) { + switch (read_c0_prid() & PRID_IMP_MASK) { case PRID_IMP_NETLOGIC_XLP3XX: mask = 0xf; break; @@ -159,10 +167,6 @@ static void xlp_enable_secondary_cores(const cpumask_t *wakeup_mask) */ syscoremask = (1 << hweight32(~fusemask & mask)) - 1; - /* The boot cpu */ - if (n == 0) - nodep->coremask = 1; - pr_info("Node %d - SYS/FUSE coremask %x\n", n, syscoremask); for (core = 0; core < nlm_cores_per_node(); core++) { /* we will be on node 0 core 0 */ diff --git a/arch/mips/paravirt/Kconfig b/arch/mips/paravirt/Kconfig new file mode 100644 index 000000000000..ecae5861b601 --- /dev/null +++ b/arch/mips/paravirt/Kconfig @@ -0,0 +1,6 @@ +if MIPS_PARAVIRT + +config MIPS_PCI_VIRTIO + def_bool y + +endif # MIPS_PARAVIRT diff --git a/arch/mips/paravirt/Makefile b/arch/mips/paravirt/Makefile new file mode 100644 index 000000000000..5023af733a35 --- /dev/null +++ b/arch/mips/paravirt/Makefile @@ -0,0 +1,14 @@ +# +# Makefile for MIPS para-virtualized specific kernel interface routines +# under Linux. +# +# This file is subject to the terms and conditions of the GNU General Public +# License. See the file "COPYING" in the main directory of this archive +# for more details. +# +# Copyright (C) 2013 Cavium, Inc. +# + +obj-y := setup.o serial.o paravirt-irq.o + +obj-$(CONFIG_SMP) += paravirt-smp.o diff --git a/arch/mips/paravirt/Platform b/arch/mips/paravirt/Platform new file mode 100644 index 000000000000..7e76ef25ea17 --- /dev/null +++ b/arch/mips/paravirt/Platform @@ -0,0 +1,8 @@ +# +# Generic para-virtualized guest. +# +platform-$(CONFIG_MIPS_PARAVIRT) += paravirt/ +cflags-$(CONFIG_MIPS_PARAVIRT) += \ + -I$(srctree)/arch/mips/include/asm/mach-paravirt + +load-$(CONFIG_MIPS_PARAVIRT) = 0xffffffff80010000 diff --git a/arch/mips/paravirt/paravirt-irq.c b/arch/mips/paravirt/paravirt-irq.c new file mode 100644 index 000000000000..8987b06c9de9 --- /dev/null +++ b/arch/mips/paravirt/paravirt-irq.c @@ -0,0 +1,368 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2013 Cavium, Inc. + */ + +#include <linux/interrupt.h> +#include <linux/cpumask.h> +#include <linux/kernel.h> +#include <linux/mutex.h> + +#include <asm/io.h> + +#define MBOX_BITS_PER_CPU 2 + +static int cpunum_for_cpu(int cpu) +{ +#ifdef CONFIG_SMP + return cpu_logical_map(cpu); +#else + return get_ebase_cpunum(); +#endif +} + +struct core_chip_data { + struct mutex core_irq_mutex; + bool current_en; + bool desired_en; + u8 bit; +}; + +static struct core_chip_data irq_core_chip_data[8]; + +static void irq_core_ack(struct irq_data *data) +{ + struct core_chip_data *cd = irq_data_get_irq_chip_data(data); + unsigned int bit = cd->bit; + + /* + * We don't need to disable IRQs to make these atomic since + * they are already disabled earlier in the low level + * interrupt code. + */ + clear_c0_status(0x100 << bit); + /* The two user interrupts must be cleared manually. */ + if (bit < 2) + clear_c0_cause(0x100 << bit); +} + +static void irq_core_eoi(struct irq_data *data) +{ + struct core_chip_data *cd = irq_data_get_irq_chip_data(data); + + /* + * We don't need to disable IRQs to make these atomic since + * they are already disabled earlier in the low level + * interrupt code. + */ + set_c0_status(0x100 << cd->bit); +} + +static void irq_core_set_enable_local(void *arg) +{ + struct irq_data *data = arg; + struct core_chip_data *cd = irq_data_get_irq_chip_data(data); + unsigned int mask = 0x100 << cd->bit; + + /* + * Interrupts are already disabled, so these are atomic. + */ + if (cd->desired_en) + set_c0_status(mask); + else + clear_c0_status(mask); + +} + +static void irq_core_disable(struct irq_data *data) +{ + struct core_chip_data *cd = irq_data_get_irq_chip_data(data); + cd->desired_en = false; +} + +static void irq_core_enable(struct irq_data *data) +{ + struct core_chip_data *cd = irq_data_get_irq_chip_data(data); + cd->desired_en = true; +} + +static void irq_core_bus_lock(struct irq_data *data) +{ + struct core_chip_data *cd = irq_data_get_irq_chip_data(data); + + mutex_lock(&cd->core_irq_mutex); +} + +static void irq_core_bus_sync_unlock(struct irq_data *data) +{ + struct core_chip_data *cd = irq_data_get_irq_chip_data(data); + + if (cd->desired_en != cd->current_en) { + on_each_cpu(irq_core_set_enable_local, data, 1); + cd->current_en = cd->desired_en; + } + + mutex_unlock(&cd->core_irq_mutex); +} + +static struct irq_chip irq_chip_core = { + .name = "Core", + .irq_enable = irq_core_enable, + .irq_disable = irq_core_disable, + .irq_ack = irq_core_ack, + .irq_eoi = irq_core_eoi, + .irq_bus_lock = irq_core_bus_lock, + .irq_bus_sync_unlock = irq_core_bus_sync_unlock, + + .irq_cpu_online = irq_core_eoi, + .irq_cpu_offline = irq_core_ack, + .flags = IRQCHIP_ONOFFLINE_ENABLED, +}; + +static void __init irq_init_core(void) +{ + int i; + int irq; + struct core_chip_data *cd; + + /* Start with a clean slate */ + clear_c0_status(ST0_IM); + clear_c0_cause(CAUSEF_IP0 | CAUSEF_IP1); + + for (i = 0; i < ARRAY_SIZE(irq_core_chip_data); i++) { + cd = irq_core_chip_data + i; + cd->current_en = false; + cd->desired_en = false; + cd->bit = i; + mutex_init(&cd->core_irq_mutex); + + irq = MIPS_CPU_IRQ_BASE + i; + + switch (i) { + case 0: /* SW0 */ + case 1: /* SW1 */ + case 5: /* IP5 */ + case 6: /* IP6 */ + case 7: /* IP7 */ + irq_set_chip_data(irq, cd); + irq_set_chip_and_handler(irq, &irq_chip_core, + handle_percpu_irq); + break; + default: + break; + } + } +} + +static void __iomem *mips_irq_chip; +#define MIPS_IRQ_CHIP_NUM_BITS 0 +#define MIPS_IRQ_CHIP_REGS 8 + +static int mips_irq_cpu_stride; +static int mips_irq_chip_reg_raw; +static int mips_irq_chip_reg_src; +static int mips_irq_chip_reg_en; +static int mips_irq_chip_reg_raw_w1s; +static int mips_irq_chip_reg_raw_w1c; +static int mips_irq_chip_reg_en_w1s; +static int mips_irq_chip_reg_en_w1c; + +static void irq_pci_enable(struct irq_data *data) +{ + u32 mask = 1u << data->irq; + + __raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_en_w1s); +} + +static void irq_pci_disable(struct irq_data *data) +{ + u32 mask = 1u << data->irq; + + __raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_en_w1c); +} + +static void irq_pci_ack(struct irq_data *data) +{ +} + +static void irq_pci_mask(struct irq_data *data) +{ + u32 mask = 1u << data->irq; + + __raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_en_w1c); +} + +static void irq_pci_unmask(struct irq_data *data) +{ + u32 mask = 1u << data->irq; + + __raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_en_w1s); +} + +static struct irq_chip irq_chip_pci = { + .name = "PCI", + .irq_enable = irq_pci_enable, + .irq_disable = irq_pci_disable, + .irq_ack = irq_pci_ack, + .irq_mask = irq_pci_mask, + .irq_unmask = irq_pci_unmask, +}; + +static void irq_mbox_all(struct irq_data *data, void __iomem *base) +{ + int cpu; + unsigned int mbox = data->irq - MIPS_IRQ_MBOX0; + u32 mask; + + WARN_ON(mbox >= MBOX_BITS_PER_CPU); + + for_each_online_cpu(cpu) { + unsigned int cpuid = cpunum_for_cpu(cpu); + mask = 1 << (cpuid * MBOX_BITS_PER_CPU + mbox); + __raw_writel(mask, base + (cpuid * mips_irq_cpu_stride)); + } +} + +static void irq_mbox_enable(struct irq_data *data) +{ + irq_mbox_all(data, mips_irq_chip + mips_irq_chip_reg_en_w1s + sizeof(u32)); +} + +static void irq_mbox_disable(struct irq_data *data) +{ + irq_mbox_all(data, mips_irq_chip + mips_irq_chip_reg_en_w1c + sizeof(u32)); +} + +static void irq_mbox_ack(struct irq_data *data) +{ + u32 mask; + unsigned int mbox = data->irq - MIPS_IRQ_MBOX0; + + WARN_ON(mbox >= MBOX_BITS_PER_CPU); + + mask = 1 << (get_ebase_cpunum() * MBOX_BITS_PER_CPU + mbox); + __raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_raw_w1c + sizeof(u32)); +} + +void irq_mbox_ipi(int cpu, unsigned int actions) +{ + unsigned int cpuid = cpunum_for_cpu(cpu); + u32 mask; + + WARN_ON(actions >= (1 << MBOX_BITS_PER_CPU)); + + mask = actions << (cpuid * MBOX_BITS_PER_CPU); + __raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_raw_w1s + sizeof(u32)); +} + +static void irq_mbox_cpu_onoffline(struct irq_data *data, void __iomem *base) +{ + unsigned int mbox = data->irq - MIPS_IRQ_MBOX0; + unsigned int cpuid = get_ebase_cpunum(); + u32 mask; + + WARN_ON(mbox >= MBOX_BITS_PER_CPU); + + mask = 1 << (cpuid * MBOX_BITS_PER_CPU + mbox); + __raw_writel(mask, base + (cpuid * mips_irq_cpu_stride)); + +} + +static void irq_mbox_cpu_online(struct irq_data *data) +{ + irq_mbox_cpu_onoffline(data, mips_irq_chip + mips_irq_chip_reg_en_w1s + sizeof(u32)); +} + +static void irq_mbox_cpu_offline(struct irq_data *data) +{ + irq_mbox_cpu_onoffline(data, mips_irq_chip + mips_irq_chip_reg_en_w1c + sizeof(u32)); +} + +static struct irq_chip irq_chip_mbox = { + .name = "MBOX", + .irq_enable = irq_mbox_enable, + .irq_disable = irq_mbox_disable, + .irq_ack = irq_mbox_ack, + .irq_cpu_online = irq_mbox_cpu_online, + .irq_cpu_offline = irq_mbox_cpu_offline, + .flags = IRQCHIP_ONOFFLINE_ENABLED, +}; + +static void __init irq_pci_init(void) +{ + int i, stride; + u32 num_bits; + + mips_irq_chip = ioremap(0x1e010000, 4096); + + num_bits = __raw_readl(mips_irq_chip + MIPS_IRQ_CHIP_NUM_BITS); + stride = 8 * (1 + ((num_bits - 1) / 64)); + + + pr_notice("mips_irq_chip: %u bits, reg stride: %d\n", num_bits, stride); + mips_irq_chip_reg_raw = MIPS_IRQ_CHIP_REGS + 0 * stride; + mips_irq_chip_reg_raw_w1s = MIPS_IRQ_CHIP_REGS + 1 * stride; + mips_irq_chip_reg_raw_w1c = MIPS_IRQ_CHIP_REGS + 2 * stride; + mips_irq_chip_reg_src = MIPS_IRQ_CHIP_REGS + 3 * stride; + mips_irq_chip_reg_en = MIPS_IRQ_CHIP_REGS + 4 * stride; + mips_irq_chip_reg_en_w1s = MIPS_IRQ_CHIP_REGS + 5 * stride; + mips_irq_chip_reg_en_w1c = MIPS_IRQ_CHIP_REGS + 6 * stride; + mips_irq_cpu_stride = stride * 4; + + for (i = 0; i < 4; i++) + irq_set_chip_and_handler(i + MIPS_IRQ_PCIA, &irq_chip_pci, handle_level_irq); + + for (i = 0; i < 2; i++) + irq_set_chip_and_handler(i + MIPS_IRQ_MBOX0, &irq_chip_mbox, handle_percpu_irq); + + + set_c0_status(STATUSF_IP2); +} + +static void irq_pci_dispatch(void) +{ + unsigned int cpuid = get_ebase_cpunum(); + u32 en; + + en = __raw_readl(mips_irq_chip + mips_irq_chip_reg_src + + (cpuid * mips_irq_cpu_stride)); + + if (!en) { + en = __raw_readl(mips_irq_chip + mips_irq_chip_reg_src + (cpuid * mips_irq_cpu_stride) + sizeof(u32)); + en = (en >> (2 * cpuid)) & 3; + + if (!en) + spurious_interrupt(); + else + do_IRQ(__ffs(en) + MIPS_IRQ_MBOX0); /* MBOX type */ + } else { + do_IRQ(__ffs(en)); + } +} + + +void __init arch_init_irq(void) +{ + irq_init_core(); + irq_pci_init(); +} + +asmlinkage void plat_irq_dispatch(void) +{ + unsigned int pending = read_c0_cause() & read_c0_status() & ST0_IM; + int ip; + + if (unlikely(!pending)) { + spurious_interrupt(); + return; + } + + ip = ffs(pending) - 1 - STATUSB_IP0; + if (ip == 2) + irq_pci_dispatch(); + else + do_IRQ(MIPS_CPU_IRQ_BASE + ip); +} diff --git a/arch/mips/paravirt/paravirt-smp.c b/arch/mips/paravirt/paravirt-smp.c new file mode 100644 index 000000000000..0164b0c48352 --- /dev/null +++ b/arch/mips/paravirt/paravirt-smp.c @@ -0,0 +1,143 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2013 Cavium, Inc. + */ + +#include <linux/interrupt.h> +#include <linux/cpumask.h> +#include <linux/kernel.h> +#include <linux/sched.h> + +#include <asm/mipsregs.h> +#include <asm/setup.h> +#include <asm/time.h> +#include <asm/smp.h> + +/* + * Writing the sp releases the CPU, so writes must be ordered, gp + * first, then sp. + */ +unsigned long paravirt_smp_sp[NR_CPUS]; +unsigned long paravirt_smp_gp[NR_CPUS]; + +static int numcpus = 1; + +static int __init set_numcpus(char *str) +{ + int newval; + + if (get_option(&str, &newval)) { + if (newval < 1 || newval >= NR_CPUS) + goto bad; + numcpus = newval; + return 0; + } +bad: + return -EINVAL; +} +early_param("numcpus", set_numcpus); + + +static void paravirt_smp_setup(void) +{ + int id; + unsigned int cpunum = get_ebase_cpunum(); + + if (WARN_ON(cpunum >= NR_CPUS)) + return; + + /* The present CPUs are initially just the boot cpu (CPU 0). */ + for (id = 0; id < NR_CPUS; id++) { + set_cpu_possible(id, id == 0); + set_cpu_present(id, id == 0); + } + __cpu_number_map[cpunum] = 0; + __cpu_logical_map[0] = cpunum; + + for (id = 0; id < numcpus; id++) { + set_cpu_possible(id, true); + set_cpu_present(id, true); + __cpu_number_map[id] = id; + __cpu_logical_map[id] = id; + } +} + +void irq_mbox_ipi(int cpu, unsigned int actions); +static void paravirt_send_ipi_single(int cpu, unsigned int action) +{ + irq_mbox_ipi(cpu, action); +} + +static void paravirt_send_ipi_mask(const struct cpumask *mask, unsigned int action) +{ + unsigned int cpu; + + for_each_cpu_mask(cpu, *mask) + paravirt_send_ipi_single(cpu, action); +} + +static void paravirt_init_secondary(void) +{ + unsigned int sr; + + sr = set_c0_status(ST0_BEV); + write_c0_ebase((u32)ebase); + + sr |= STATUSF_IP2; /* Interrupt controller on IP2 */ + write_c0_status(sr); + + irq_cpu_online(); +} + +static void paravirt_smp_finish(void) +{ + /* to generate the first CPU timer interrupt */ + write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ); + local_irq_enable(); +} + +static void paravirt_boot_secondary(int cpu, struct task_struct *idle) +{ + paravirt_smp_gp[cpu] = (unsigned long)task_thread_info(idle); + smp_wmb(); + paravirt_smp_sp[cpu] = __KSTK_TOS(idle); +} + +static irqreturn_t paravirt_reched_interrupt(int irq, void *dev_id) +{ + scheduler_ipi(); + return IRQ_HANDLED; +} + +static irqreturn_t paravirt_function_interrupt(int irq, void *dev_id) +{ + smp_call_function_interrupt(); + return IRQ_HANDLED; +} + +static void paravirt_prepare_cpus(unsigned int max_cpus) +{ + if (request_irq(MIPS_IRQ_MBOX0, paravirt_reched_interrupt, + IRQF_PERCPU | IRQF_NO_THREAD, "Scheduler", + paravirt_reched_interrupt)) { + panic("Cannot request_irq for SchedulerIPI"); + } + if (request_irq(MIPS_IRQ_MBOX1, paravirt_function_interrupt, + IRQF_PERCPU | IRQF_NO_THREAD, "SMP-Call", + paravirt_function_interrupt)) { + panic("Cannot request_irq for SMP-Call"); + } +} + +struct plat_smp_ops paravirt_smp_ops = { + .send_ipi_single = paravirt_send_ipi_single, + .send_ipi_mask = paravirt_send_ipi_mask, + .init_secondary = paravirt_init_secondary, + .smp_finish = paravirt_smp_finish, + .boot_secondary = paravirt_boot_secondary, + .smp_setup = paravirt_smp_setup, + .prepare_cpus = paravirt_prepare_cpus, +}; diff --git a/arch/mips/paravirt/serial.c b/arch/mips/paravirt/serial.c new file mode 100644 index 000000000000..02b665c02272 --- /dev/null +++ b/arch/mips/paravirt/serial.c @@ -0,0 +1,40 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2013 Cavium, Inc. + */ + +#include <linux/kernel.h> +#include <linux/virtio_console.h> +#include <linux/kvm_para.h> + +/* + * Emit one character to the boot console. + */ +int prom_putchar(char c) +{ + kvm_hypercall3(KVM_HC_MIPS_CONSOLE_OUTPUT, 0 /* port 0 */, + (unsigned long)&c, 1 /* len == 1 */); + + return 1; +} + +#ifdef CONFIG_VIRTIO_CONSOLE +static int paravirt_put_chars(u32 vtermno, const char *buf, int count) +{ + kvm_hypercall3(KVM_HC_MIPS_CONSOLE_OUTPUT, vtermno, + (unsigned long)buf, count); + + return count; +} + +static int __init paravirt_cons_init(void) +{ + virtio_cons_early_init(paravirt_put_chars); + return 0; +} +core_initcall(paravirt_cons_init); + +#endif diff --git a/arch/mips/paravirt/setup.c b/arch/mips/paravirt/setup.c new file mode 100644 index 000000000000..cb8448b373a7 --- /dev/null +++ b/arch/mips/paravirt/setup.c @@ -0,0 +1,67 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2013 Cavium, Inc. + */ + +#include <linux/kernel.h> +#include <linux/kvm_para.h> + +#include <asm/reboot.h> +#include <asm/bootinfo.h> +#include <asm/smp-ops.h> +#include <asm/time.h> + +extern struct plat_smp_ops paravirt_smp_ops; + +const char *get_system_type(void) +{ + return "MIPS Para-Virtualized Guest"; +} + +void __init plat_time_init(void) +{ + mips_hpt_frequency = kvm_hypercall0(KVM_HC_MIPS_GET_CLOCK_FREQ); + + preset_lpj = mips_hpt_frequency / (2 * HZ); +} + +static void pv_machine_halt(void) +{ + kvm_hypercall0(KVM_HC_MIPS_EXIT_VM); +} + +/* + * Early entry point for arch setup + */ +void __init prom_init(void) +{ + int i; + int argc = fw_arg0; + char **argv = (char **)fw_arg1; + +#ifdef CONFIG_32BIT + set_io_port_base(KSEG1ADDR(0x1e000000)); +#else /* CONFIG_64BIT */ + set_io_port_base(PHYS_TO_XKSEG_UNCACHED(0x1e000000)); +#endif + + for (i = 0; i < argc; i++) { + strlcat(arcs_cmdline, argv[i], COMMAND_LINE_SIZE); + if (i < argc - 1) + strlcat(arcs_cmdline, " ", COMMAND_LINE_SIZE); + } + _machine_halt = pv_machine_halt; + register_smp_ops(¶virt_smp_ops); +} + +void __init plat_mem_setup(void) +{ + /* Do nothing, the "mem=???" parser handles our memory. */ +} + +void __init prom_free_prom_memory(void) +{ +} diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile index d61138a177cc..ff8a5539b363 100644 --- a/arch/mips/pci/Makefile +++ b/arch/mips/pci/Makefile @@ -21,7 +21,7 @@ obj-$(CONFIG_BCM63XX) += pci-bcm63xx.o fixup-bcm63xx.o \ obj-$(CONFIG_MIPS_ALCHEMY) += pci-alchemy.o obj-$(CONFIG_SOC_AR71XX) += pci-ar71xx.o obj-$(CONFIG_PCI_AR724X) += pci-ar724x.o - +obj-$(CONFIG_MIPS_PCI_VIRTIO) += pci-virtio-guest.o # # These are still pretty much in the old state, watch, go blind. # diff --git a/arch/mips/pci/fixup-malta.c b/arch/mips/pci/fixup-malta.c index 2f9e52a1a750..40e920c653cc 100644 --- a/arch/mips/pci/fixup-malta.c +++ b/arch/mips/pci/fixup-malta.c @@ -68,6 +68,7 @@ static void malta_piix_func0_fixup(struct pci_dev *pdev) { unsigned char reg_val; u32 reg_val32; + u16 reg_val16; /* PIIX PIRQC[A:D] irq mappings */ static int piixirqmap[PIIX4_FUNC0_PIRQRC_IRQ_ROUTING_MAX] = { 0, 0, 0, 3, @@ -107,6 +108,11 @@ static void malta_piix_func0_fixup(struct pci_dev *pdev) pci_read_config_byte(pdev, PIIX4_FUNC0_SERIRQC, ®_val); reg_val |= PIIX4_FUNC0_SERIRQC_EN | PIIX4_FUNC0_SERIRQC_CONT; pci_write_config_byte(pdev, PIIX4_FUNC0_SERIRQC, reg_val); + + /* Enable response to special cycles */ + pci_read_config_word(pdev, PCI_COMMAND, ®_val16); + pci_write_config_word(pdev, PCI_COMMAND, + reg_val16 | PCI_COMMAND_SPECIAL); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_0, diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c index 2b91b0e61566..ab0c5d14c6f7 100644 --- a/arch/mips/pci/msi-octeon.c +++ b/arch/mips/pci/msi-octeon.c @@ -15,6 +15,7 @@ #include <asm/octeon/cvmx-npi-defs.h> #include <asm/octeon/cvmx-pci-defs.h> #include <asm/octeon/cvmx-npei-defs.h> +#include <asm/octeon/cvmx-sli-defs.h> #include <asm/octeon/cvmx-pexp-defs.h> #include <asm/octeon/pci-octeon.h> @@ -162,6 +163,11 @@ msi_irq_allocated: msg.address_lo = (0 + CVMX_NPEI_PCIE_MSI_RCV) & 0xffffffff; msg.address_hi = (0 + CVMX_NPEI_PCIE_MSI_RCV) >> 32; break; + case OCTEON_DMA_BAR_TYPE_PCIE2: + /* When using PCIe2, Bar 0 is based at 0 */ + msg.address_lo = (0 + CVMX_SLI_PCIE_MSI_RCV) & 0xffffffff; + msg.address_hi = (0 + CVMX_SLI_PCIE_MSI_RCV) >> 32; + break; default: panic("arch_setup_msi_irq: Invalid octeon_dma_bar_type"); } diff --git a/arch/mips/pci/msi-xlp.c b/arch/mips/pci/msi-xlp.c index afd8405e0188..fa374fe3746b 100644 --- a/arch/mips/pci/msi-xlp.c +++ b/arch/mips/pci/msi-xlp.c @@ -56,8 +56,8 @@ #include <asm/netlogic/xlp-hal/bridge.h> #define XLP_MSIVEC_PER_LINK 32 -#define XLP_MSIXVEC_TOTAL 32 -#define XLP_MSIXVEC_PER_LINK 8 +#define XLP_MSIXVEC_TOTAL (cpu_is_xlp9xx() ? 128 : 32) +#define XLP_MSIXVEC_PER_LINK (cpu_is_xlp9xx() ? 32 : 8) /* 128 MSI irqs per node, mapped starting at NLM_MSI_VEC_BASE */ static inline int nlm_link_msiirq(int link, int msivec) @@ -65,35 +65,44 @@ static inline int nlm_link_msiirq(int link, int msivec) return NLM_MSI_VEC_BASE + link * XLP_MSIVEC_PER_LINK + msivec; } +/* get the link MSI vector from irq number */ static inline int nlm_irq_msivec(int irq) { - return irq % XLP_MSIVEC_PER_LINK; + return (irq - NLM_MSI_VEC_BASE) % XLP_MSIVEC_PER_LINK; } +/* get the link from the irq number */ static inline int nlm_irq_msilink(int irq) { - return (irq % (XLP_MSIVEC_PER_LINK * PCIE_NLINKS)) / - XLP_MSIVEC_PER_LINK; + int total_msivec = XLP_MSIVEC_PER_LINK * PCIE_NLINKS; + + return ((irq - NLM_MSI_VEC_BASE) % total_msivec) / + XLP_MSIVEC_PER_LINK; } /* - * Only 32 MSI-X vectors are possible because there are only 32 PIC - * interrupts for MSI. We split them statically and use 8 MSI-X vectors - * per link - this keeps the allocation and lookup simple. + * For XLP 8xx/4xx/3xx/2xx, only 32 MSI-X vectors are possible because + * there are only 32 PIC interrupts for MSI. We split them statically + * and use 8 MSI-X vectors per link - this keeps the allocation and + * lookup simple. + * On XLP 9xx, there are 32 vectors per link, and the interrupts are + * not routed thru PIC, so we can use all 128 MSI-X vectors. */ static inline int nlm_link_msixirq(int link, int bit) { return NLM_MSIX_VEC_BASE + link * XLP_MSIXVEC_PER_LINK + bit; } +/* get the link MSI vector from irq number */ static inline int nlm_irq_msixvec(int irq) { - return irq % XLP_MSIXVEC_TOTAL; /* works when given xirq */ + return (irq - NLM_MSIX_VEC_BASE) % XLP_MSIXVEC_TOTAL; } -static inline int nlm_irq_msixlink(int irq) +/* get the link from MSIX vec */ +static inline int nlm_irq_msixlink(int msixvec) { - return nlm_irq_msixvec(irq) / XLP_MSIXVEC_PER_LINK; + return msixvec / XLP_MSIXVEC_PER_LINK; } /* @@ -129,7 +138,11 @@ static void xlp_msi_enable(struct irq_data *d) vec = nlm_irq_msivec(d->irq); spin_lock_irqsave(&md->msi_lock, flags); md->msi_enabled_mask |= 1u << vec; - nlm_write_reg(md->lnkbase, PCIE_MSI_EN, md->msi_enabled_mask); + if (cpu_is_xlp9xx()) + nlm_write_reg(md->lnkbase, PCIE_9XX_MSI_EN, + md->msi_enabled_mask); + else + nlm_write_reg(md->lnkbase, PCIE_MSI_EN, md->msi_enabled_mask); spin_unlock_irqrestore(&md->msi_lock, flags); } @@ -142,7 +155,11 @@ static void xlp_msi_disable(struct irq_data *d) vec = nlm_irq_msivec(d->irq); spin_lock_irqsave(&md->msi_lock, flags); md->msi_enabled_mask &= ~(1u << vec); - nlm_write_reg(md->lnkbase, PCIE_MSI_EN, md->msi_enabled_mask); + if (cpu_is_xlp9xx()) + nlm_write_reg(md->lnkbase, PCIE_9XX_MSI_EN, + md->msi_enabled_mask); + else + nlm_write_reg(md->lnkbase, PCIE_MSI_EN, md->msi_enabled_mask); spin_unlock_irqrestore(&md->msi_lock, flags); } @@ -156,11 +173,18 @@ static void xlp_msi_mask_ack(struct irq_data *d) xlp_msi_disable(d); /* Ack MSI on bridge */ - nlm_write_reg(md->lnkbase, PCIE_MSI_STATUS, 1u << vec); + if (cpu_is_xlp9xx()) + nlm_write_reg(md->lnkbase, PCIE_9XX_MSI_STATUS, 1u << vec); + else + nlm_write_reg(md->lnkbase, PCIE_MSI_STATUS, 1u << vec); /* Ack at eirr and PIC */ ack_c0_eirr(PIC_PCIE_LINK_MSI_IRQ(link)); - nlm_pic_ack(md->node->picbase, PIC_IRT_PCIE_LINK_INDEX(link)); + if (cpu_is_xlp9xx()) + nlm_pic_ack(md->node->picbase, + PIC_9XX_IRT_PCIE_LINK_INDEX(link)); + else + nlm_pic_ack(md->node->picbase, PIC_IRT_PCIE_LINK_INDEX(link)); } static struct irq_chip xlp_msi_chip = { @@ -172,30 +196,45 @@ static struct irq_chip xlp_msi_chip = { }; /* - * The MSI-X interrupt handling is different from MSI, there are 32 - * MSI-X interrupts generated by the PIC and each of these correspond - * to a MSI-X vector (0-31) that can be assigned. + * XLP8XX/4XX/3XX/2XX: + * The MSI-X interrupt handling is different from MSI, there are 32 MSI-X + * interrupts generated by the PIC and each of these correspond to a MSI-X + * vector (0-31) that can be assigned. + * + * We divide the MSI-X vectors to 8 per link and do a per-link allocation * - * We divide the MSI-X vectors to 8 per link and do a per-link - * allocation + * XLP9XX: + * 32 MSI-X vectors are available per link, and the interrupts are not routed + * thru the PIC. PIC ack not needed. * * Enable and disable done using standard MSI functions. */ static void xlp_msix_mask_ack(struct irq_data *d) { - struct xlp_msi_data *md = irq_data_get_irq_handler_data(d); + struct xlp_msi_data *md; int link, msixvec; + uint32_t status_reg, bit; msixvec = nlm_irq_msixvec(d->irq); - link = nlm_irq_msixlink(d->irq); + link = nlm_irq_msixlink(msixvec); mask_msi_irq(d); + md = irq_data_get_irq_handler_data(d); /* Ack MSI on bridge */ - nlm_write_reg(md->lnkbase, PCIE_MSIX_STATUS, 1u << msixvec); + if (cpu_is_xlp9xx()) { + status_reg = PCIE_9XX_MSIX_STATUSX(link); + bit = msixvec % XLP_MSIXVEC_PER_LINK; + } else { + status_reg = PCIE_MSIX_STATUS; + bit = msixvec; + } + nlm_write_reg(md->lnkbase, status_reg, 1u << bit); /* Ack at eirr and PIC */ ack_c0_eirr(PIC_PCIE_MSIX_IRQ(link)); - nlm_pic_ack(md->node->picbase, PIC_IRT_PCIE_MSIX_INDEX(msixvec)); + if (!cpu_is_xlp9xx()) + nlm_pic_ack(md->node->picbase, + PIC_IRT_PCIE_MSIX_INDEX(msixvec)); } static struct irq_chip xlp_msix_chip = { @@ -206,14 +245,8 @@ static struct irq_chip xlp_msix_chip = { .irq_unmask = unmask_msi_irq, }; -void destroy_irq(unsigned int irq) -{ - /* nothing to do yet */ -} - void arch_teardown_msi_irq(unsigned int irq) { - destroy_irq(irq); } /* @@ -225,10 +258,18 @@ static void xlp_config_link_msi(uint64_t lnkbase, int lirq, uint64_t msiaddr) { u32 val; - val = nlm_read_reg(lnkbase, PCIE_INT_EN0); - if ((val & 0x200) == 0) { - val |= 0x200; /* MSI Interrupt enable */ - nlm_write_reg(lnkbase, PCIE_INT_EN0, val); + if (cpu_is_xlp9xx()) { + val = nlm_read_reg(lnkbase, PCIE_9XX_INT_EN0); + if ((val & 0x200) == 0) { + val |= 0x200; /* MSI Interrupt enable */ + nlm_write_reg(lnkbase, PCIE_9XX_INT_EN0, val); + } + } else { + val = nlm_read_reg(lnkbase, PCIE_INT_EN0); + if ((val & 0x200) == 0) { + val |= 0x200; + nlm_write_reg(lnkbase, PCIE_INT_EN0, val); + } } val = nlm_read_reg(lnkbase, 0x1); /* CMD */ @@ -275,9 +316,12 @@ static int xlp_setup_msi(uint64_t lnkbase, int node, int link, spin_lock_irqsave(&md->msi_lock, flags); if (md->msi_alloc_mask == 0) { - /* switch the link IRQ to MSI range */ xlp_config_link_msi(lnkbase, lirq, msiaddr); - irt = PIC_IRT_PCIE_LINK_INDEX(link); + /* switch the link IRQ to MSI range */ + if (cpu_is_xlp9xx()) + irt = PIC_9XX_IRT_PCIE_LINK_INDEX(link); + else + irt = PIC_IRT_PCIE_LINK_INDEX(link); nlm_setup_pic_irq(node, lirq, lirq, irt); nlm_pic_init_irt(nlm_get_node(node)->picbase, irt, lirq, node * nlm_threads_per_node(), 1 /*en */); @@ -298,10 +342,8 @@ static int xlp_setup_msi(uint64_t lnkbase, int node, int link, xirq = xirq + msivec; /* msi mapped to global irq space */ ret = irq_set_msi_desc(xirq, desc); - if (ret < 0) { - destroy_irq(xirq); + if (ret < 0) return ret; - } write_msi_msg(xirq, &msg); return 0; @@ -319,10 +361,19 @@ static void xlp_config_link_msix(uint64_t lnkbase, int lirq, uint64_t msixaddr) val |= 0x80000000U; nlm_write_reg(lnkbase, 0x2C, val); } - val = nlm_read_reg(lnkbase, PCIE_INT_EN0); - if ((val & 0x200) == 0) { - val |= 0x200; /* MSI Interrupt enable */ - nlm_write_reg(lnkbase, PCIE_INT_EN0, val); + + if (cpu_is_xlp9xx()) { + val = nlm_read_reg(lnkbase, PCIE_9XX_INT_EN0); + if ((val & 0x200) == 0) { + val |= 0x200; /* MSI Interrupt enable */ + nlm_write_reg(lnkbase, PCIE_9XX_INT_EN0, val); + } + } else { + val = nlm_read_reg(lnkbase, PCIE_INT_EN0); + if ((val & 0x200) == 0) { + val |= 0x200; /* MSI Interrupt enable */ + nlm_write_reg(lnkbase, PCIE_INT_EN0, val); + } } val = nlm_read_reg(lnkbase, 0x1); /* CMD */ @@ -337,10 +388,19 @@ static void xlp_config_link_msix(uint64_t lnkbase, int lirq, uint64_t msixaddr) val |= (1 << 8) | lirq; nlm_write_pci_reg(lnkbase, 0xf, val); - /* MSI-X addresses */ - nlm_write_reg(lnkbase, PCIE_BRIDGE_MSIX_ADDR_BASE, msixaddr >> 8); - nlm_write_reg(lnkbase, PCIE_BRIDGE_MSIX_ADDR_LIMIT, - (msixaddr + MSI_ADDR_SZ) >> 8); + if (cpu_is_xlp9xx()) { + /* MSI-X addresses */ + nlm_write_reg(lnkbase, PCIE_9XX_BRIDGE_MSIX_ADDR_BASE, + msixaddr >> 8); + nlm_write_reg(lnkbase, PCIE_9XX_BRIDGE_MSIX_ADDR_LIMIT, + (msixaddr + MSI_ADDR_SZ) >> 8); + } else { + /* MSI-X addresses */ + nlm_write_reg(lnkbase, PCIE_BRIDGE_MSIX_ADDR_BASE, + msixaddr >> 8); + nlm_write_reg(lnkbase, PCIE_BRIDGE_MSIX_ADDR_LIMIT, + (msixaddr + MSI_ADDR_SZ) >> 8); + } } /* @@ -377,6 +437,7 @@ static int xlp_setup_msix(uint64_t lnkbase, int node, int link, xirq += t; msixvec = nlm_irq_msixvec(xirq); + msg.address_hi = msixaddr >> 32; msg.address_lo = msixaddr & 0xffffffff; msg.data = 0xc00 | msixvec; @@ -417,7 +478,7 @@ void __init xlp_init_node_msi_irqs(int node, int link) { struct nlm_soc_info *nodep; struct xlp_msi_data *md; - int irq, i, irt, msixvec; + int irq, i, irt, msixvec, val; pr_info("[%d %d] Init node PCI IRT\n", node, link); nodep = nlm_get_node(node); @@ -438,19 +499,28 @@ void __init xlp_init_node_msi_irqs(int node, int link) irq_set_handler_data(i, md); } - for (i = 0; i < XLP_MSIXVEC_PER_LINK; i++) { - /* Initialize MSI-X irts to generate one interrupt per link */ - msixvec = link * XLP_MSIXVEC_PER_LINK + i; - irt = PIC_IRT_PCIE_MSIX_INDEX(msixvec); - nlm_pic_init_irt(nodep->picbase, irt, PIC_PCIE_MSIX_IRQ(link), - node * nlm_threads_per_node(), 1 /* enable */); + for (i = 0; i < XLP_MSIXVEC_PER_LINK ; i++) { + if (cpu_is_xlp9xx()) { + val = ((node * nlm_threads_per_node()) << 7 | + PIC_PCIE_MSIX_IRQ(link) << 1 | 0 << 0); + nlm_write_pcie_reg(md->lnkbase, PCIE_9XX_MSIX_VECX(i + + (link * XLP_MSIXVEC_PER_LINK)), val); + } else { + /* Initialize MSI-X irts to generate one interrupt + * per link + */ + msixvec = link * XLP_MSIXVEC_PER_LINK + i; + irt = PIC_IRT_PCIE_MSIX_INDEX(msixvec); + nlm_pic_init_irt(nodep->picbase, irt, + PIC_PCIE_MSIX_IRQ(link), + node * nlm_threads_per_node(), 1); + } /* Initialize MSI-X extended irq space for the link */ irq = nlm_irq_to_xirq(node, nlm_link_msixirq(link, i)); irq_set_chip_and_handler(irq, &xlp_msix_chip, handle_level_irq); irq_set_handler_data(irq, md); } - } void nlm_dispatch_msi(int node, int lirq) @@ -462,7 +532,11 @@ void nlm_dispatch_msi(int node, int lirq) link = lirq - PIC_PCIE_LINK_MSI_IRQ_BASE; irqbase = nlm_irq_to_xirq(node, nlm_link_msiirq(link, 0)); md = irq_get_handler_data(irqbase); - status = nlm_read_reg(md->lnkbase, PCIE_MSI_STATUS) & + if (cpu_is_xlp9xx()) + status = nlm_read_reg(md->lnkbase, PCIE_9XX_MSI_STATUS) & + md->msi_enabled_mask; + else + status = nlm_read_reg(md->lnkbase, PCIE_MSI_STATUS) & md->msi_enabled_mask; while (status) { i = __ffs(status); @@ -480,10 +554,14 @@ void nlm_dispatch_msix(int node, int lirq) link = lirq - PIC_PCIE_MSIX_IRQ_BASE; irqbase = nlm_irq_to_xirq(node, nlm_link_msixirq(link, 0)); md = irq_get_handler_data(irqbase); - status = nlm_read_reg(md->lnkbase, PCIE_MSIX_STATUS); + if (cpu_is_xlp9xx()) + status = nlm_read_reg(md->lnkbase, PCIE_9XX_MSIX_STATUSX(link)); + else + status = nlm_read_reg(md->lnkbase, PCIE_MSIX_STATUS); /* narrow it down to the MSI-x vectors for our link */ - status = (status >> (link * XLP_MSIXVEC_PER_LINK)) & + if (!cpu_is_xlp9xx()) + status = (status >> (link * XLP_MSIXVEC_PER_LINK)) & ((1 << XLP_MSIXVEC_PER_LINK) - 1); while (status) { diff --git a/arch/mips/pci/ops-pmcmsp.c b/arch/mips/pci/ops-pmcmsp.c index 3d27800edba2..50034f985be1 100644 --- a/arch/mips/pci/ops-pmcmsp.c +++ b/arch/mips/pci/ops-pmcmsp.c @@ -7,7 +7,7 @@ * Author: Jun Sun, jsun@mvista.com or jsun@junsun.net * * Much of the code is derived from the original DDB5074 port by - * Geert Uytterhoeven <geert@sonycom.com> + * Geert Uytterhoeven <geert@linux-m68k.org> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the diff --git a/arch/mips/pci/ops-tx3927.c b/arch/mips/pci/ops-tx3927.c index 02d64f77e967..d35dc9c9ab9d 100644 --- a/arch/mips/pci/ops-tx3927.c +++ b/arch/mips/pci/ops-tx3927.c @@ -11,7 +11,7 @@ * Define the pci_ops for TX3927. * * Much of the code is derived from the original DDB5074 port by - * Geert Uytterhoeven <geert@sonycom.com> + * Geert Uytterhoeven <geert@linux-m68k.org> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the diff --git a/arch/mips/pci/ops-tx4927.c b/arch/mips/pci/ops-tx4927.c index 3d5df514d024..0e046d82e4e3 100644 --- a/arch/mips/pci/ops-tx4927.c +++ b/arch/mips/pci/ops-tx4927.c @@ -202,17 +202,20 @@ char *tx4927_pcibios_setup(char *str) unsigned long val; if (!strncmp(str, "trdyto=", 7)) { - if (strict_strtoul(str + 7, 0, &val) == 0) + u8 val = 0; + if (kstrtou8(str + 7, 0, &val) == 0) tx4927_pci_opts.trdyto = val; return NULL; } if (!strncmp(str, "retryto=", 8)) { - if (strict_strtoul(str + 8, 0, &val) == 0) + u8 val = 0; + if (kstrtou8(str + 8, 0, &val) == 0) tx4927_pci_opts.retryto = val; return NULL; } if (!strncmp(str, "gbwc=", 5)) { - if (strict_strtoul(str + 5, 0, &val) == 0) + u16 val; + if (kstrtou16(str + 5, 0, &val) == 0) tx4927_pci_opts.gbwc = val; return NULL; } diff --git a/arch/mips/pci/pci-virtio-guest.c b/arch/mips/pci/pci-virtio-guest.c new file mode 100644 index 000000000000..40a078bc4617 --- /dev/null +++ b/arch/mips/pci/pci-virtio-guest.c @@ -0,0 +1,131 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2013 Cavium, Inc. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/pci.h> + +#include <uapi/asm/bitfield.h> +#include <asm/byteorder.h> +#include <asm/io.h> + +#define PCI_CONFIG_ADDRESS 0xcf8 +#define PCI_CONFIG_DATA 0xcfc + +union pci_config_address { + struct { + __BITFIELD_FIELD(unsigned enable_bit : 1, /* 31 */ + __BITFIELD_FIELD(unsigned reserved : 7, /* 30 .. 24 */ + __BITFIELD_FIELD(unsigned bus_number : 8, /* 23 .. 16 */ + __BITFIELD_FIELD(unsigned devfn_number : 8, /* 15 .. 8 */ + __BITFIELD_FIELD(unsigned register_number : 8, /* 7 .. 0 */ + ))))); + }; + u32 w; +}; + +int pcibios_plat_dev_init(struct pci_dev *dev) +{ + return 0; +} + +int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +{ + return ((pin + slot) % 4)+ MIPS_IRQ_PCIA; +} + +static void pci_virtio_guest_write_config_addr(struct pci_bus *bus, + unsigned int devfn, int reg) +{ + union pci_config_address pca = { .w = 0 }; + + pca.register_number = reg; + pca.devfn_number = devfn; + pca.bus_number = bus->number; + pca.enable_bit = 1; + + outl(pca.w, PCI_CONFIG_ADDRESS); +} + +static int pci_virtio_guest_write_config(struct pci_bus *bus, + unsigned int devfn, int reg, int size, u32 val) +{ + pci_virtio_guest_write_config_addr(bus, devfn, reg); + + switch (size) { + case 1: + outb(val, PCI_CONFIG_DATA + (reg & 3)); + break; + case 2: + outw(val, PCI_CONFIG_DATA + (reg & 2)); + break; + case 4: + outl(val, PCI_CONFIG_DATA); + break; + } + + return PCIBIOS_SUCCESSFUL; +} + +static int pci_virtio_guest_read_config(struct pci_bus *bus, unsigned int devfn, + int reg, int size, u32 *val) +{ + pci_virtio_guest_write_config_addr(bus, devfn, reg); + + switch (size) { + case 1: + *val = inb(PCI_CONFIG_DATA + (reg & 3)); + break; + case 2: + *val = inw(PCI_CONFIG_DATA + (reg & 2)); + break; + case 4: + *val = inl(PCI_CONFIG_DATA); + break; + } + return PCIBIOS_SUCCESSFUL; +} + +static struct pci_ops pci_virtio_guest_ops = { + .read = pci_virtio_guest_read_config, + .write = pci_virtio_guest_write_config, +}; + +static struct resource pci_virtio_guest_mem_resource = { + .name = "Virtio MEM", + .flags = IORESOURCE_MEM, + .start = 0x10000000, + .end = 0x1dffffff +}; + +static struct resource pci_virtio_guest_io_resource = { + .name = "Virtio IO", + .flags = IORESOURCE_IO, + .start = 0, + .end = 0xffff +}; + +static struct pci_controller pci_virtio_guest_controller = { + .pci_ops = &pci_virtio_guest_ops, + .mem_resource = &pci_virtio_guest_mem_resource, + .io_resource = &pci_virtio_guest_io_resource, +}; + +static int __init pci_virtio_guest_setup(void) +{ + pr_err("pci_virtio_guest_setup\n"); + + /* Virtio comes pre-assigned */ + pci_set_flags(PCI_PROBE_ONLY); + + pci_virtio_guest_controller.io_map_base = mips_io_port_base; + register_pci_controller(&pci_virtio_guest_controller); + return 0; +} +arch_initcall(pci_virtio_guest_setup); diff --git a/arch/mips/pci/pci-xlr.c b/arch/mips/pci/pci-xlr.c index 4427abbd48b5..0dde80332d3a 100644 --- a/arch/mips/pci/pci-xlr.c +++ b/arch/mips/pci/pci-xlr.c @@ -214,14 +214,8 @@ static int get_irq_vector(const struct pci_dev *dev) } #ifdef CONFIG_PCI_MSI -void destroy_irq(unsigned int irq) -{ - /* nothing to do yet */ -} - void arch_teardown_msi_irq(unsigned int irq) { - destroy_irq(irq); } int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc) @@ -263,10 +257,8 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc) MSI_DATA_DELIVERY_FIXED; ret = irq_set_msi_desc(irq, desc); - if (ret < 0) { - destroy_irq(irq); + if (ret < 0) return ret; - } write_msi_msg(irq, &msg); return 0; diff --git a/arch/mips/pmcs-msp71xx/Makefile b/arch/mips/pmcs-msp71xx/Makefile index 9201c8b3858d..d4f7220f2485 100644 --- a/arch/mips/pmcs-msp71xx/Makefile +++ b/arch/mips/pmcs-msp71xx/Makefile @@ -10,4 +10,3 @@ obj-$(CONFIG_PCI) += msp_pci.o obj-$(CONFIG_MSP_HAS_MAC) += msp_eth.o obj-$(CONFIG_MSP_HAS_USB) += msp_usb.o obj-$(CONFIG_MIPS_MT_SMP) += msp_smp.o -obj-$(CONFIG_MIPS_MT_SMTC) += msp_smtc.o diff --git a/arch/mips/pmcs-msp71xx/msp_eth.c b/arch/mips/pmcs-msp71xx/msp_eth.c index c584df393de2..15679b427f44 100644 --- a/arch/mips/pmcs-msp71xx/msp_eth.c +++ b/arch/mips/pmcs-msp71xx/msp_eth.c @@ -38,73 +38,6 @@ #define MSP_ETHERNET_GPIO1 15 #define MSP_ETHERNET_GPIO2 16 -#ifdef CONFIG_MSP_HAS_TSMAC -#define MSP_TSMAC_SIZE 0x10020 -#define MSP_TSMAC_ID "pmc_tsmac" - -static struct resource msp_tsmac0_resources[] = { - [0] = { - .start = MSP_MAC0_BASE, - .end = MSP_MAC0_BASE + MSP_TSMAC_SIZE - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = MSP_INT_MAC0, - .end = MSP_INT_MAC0, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource msp_tsmac1_resources[] = { - [0] = { - .start = MSP_MAC1_BASE, - .end = MSP_MAC1_BASE + MSP_TSMAC_SIZE - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = MSP_INT_MAC1, - .end = MSP_INT_MAC1, - .flags = IORESOURCE_IRQ, - }, -}; -static struct resource msp_tsmac2_resources[] = { - [0] = { - .start = MSP_MAC2_BASE, - .end = MSP_MAC2_BASE + MSP_TSMAC_SIZE - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = MSP_INT_SAR, - .end = MSP_INT_SAR, - .flags = IORESOURCE_IRQ, - }, -}; - - -static struct platform_device tsmac_device[] = { - [0] = { - .name = MSP_TSMAC_ID, - .id = 0, - .num_resources = ARRAY_SIZE(msp_tsmac0_resources), - .resource = msp_tsmac0_resources, - }, - [1] = { - .name = MSP_TSMAC_ID, - .id = 1, - .num_resources = ARRAY_SIZE(msp_tsmac1_resources), - .resource = msp_tsmac1_resources, - }, - [2] = { - .name = MSP_TSMAC_ID, - .id = 2, - .num_resources = ARRAY_SIZE(msp_tsmac2_resources), - .resource = msp_tsmac2_resources, - }, -}; -#define msp_eth_devs tsmac_device - -#else -/* If it is not TSMAC assume MSP_ETH (100Mbps) */ #define MSP_ETH_ID "pmc_mspeth" #define MSP_ETH_SIZE 0xE0 static struct resource msp_eth0_resources[] = { @@ -152,7 +85,6 @@ static struct platform_device mspeth_device[] = { }; #define msp_eth_devs mspeth_device -#endif int __init msp_eth_setup(void) { int i, ret = 0; @@ -161,14 +93,6 @@ int __init msp_eth_setup(void) msp_gpio_pin_mode(MSP_GPIO_OUTPUT, MSP_ETHERNET_GPIO0); msp_gpio_pin_hi(MSP_ETHERNET_GPIO0); -#ifdef CONFIG_MSP_HAS_TSMAC - /* 3 phys on boards with TSMAC */ - msp_gpio_pin_mode(MSP_GPIO_OUTPUT, MSP_ETHERNET_GPIO1); - msp_gpio_pin_hi(MSP_ETHERNET_GPIO1); - - msp_gpio_pin_mode(MSP_GPIO_OUTPUT, MSP_ETHERNET_GPIO2); - msp_gpio_pin_hi(MSP_ETHERNET_GPIO2); -#endif for (i = 0; i < ARRAY_SIZE(msp_eth_devs); i++) { ret = platform_device_register(&msp_eth_devs[i]); printk(KERN_INFO "device: %d, return value = %d\n", i, ret); diff --git a/arch/mips/pmcs-msp71xx/msp_irq.c b/arch/mips/pmcs-msp71xx/msp_irq.c index 9da5619c00a5..941744aabb51 100644 --- a/arch/mips/pmcs-msp71xx/msp_irq.c +++ b/arch/mips/pmcs-msp71xx/msp_irq.c @@ -32,7 +32,7 @@ extern void msp_vsmp_int_init(void); /* vectored interrupt implementation */ -/* SW0/1 interrupts are used for SMP/SMTC */ +/* SW0/1 interrupts are used for SMP */ static inline void mac0_int_dispatch(void) { do_IRQ(MSP_INT_MAC0); } static inline void mac1_int_dispatch(void) { do_IRQ(MSP_INT_MAC1); } static inline void mac2_int_dispatch(void) { do_IRQ(MSP_INT_SAR); } @@ -138,14 +138,6 @@ void __init arch_init_irq(void) set_vi_handler(MSP_INT_SEC, sec_int_dispatch); #ifdef CONFIG_MIPS_MT_SMP msp_vsmp_int_init(); -#elif defined CONFIG_MIPS_MT_SMTC - /*Set hwmask for all platform devices */ - irq_hwmask[MSP_INT_MAC0] = C_IRQ0; - irq_hwmask[MSP_INT_MAC1] = C_IRQ1; - irq_hwmask[MSP_INT_USB] = C_IRQ2; - irq_hwmask[MSP_INT_SAR] = C_IRQ3; - irq_hwmask[MSP_INT_SEC] = C_IRQ5; - #endif /* CONFIG_MIPS_MT_SMP */ #endif /* CONFIG_MIPS_MT */ /* setup the cascaded interrupts */ @@ -153,8 +145,10 @@ void __init arch_init_irq(void) setup_irq(MSP_INT_PER, &per_cascade_msp); #else - /* setup the 2nd-level SLP register based interrupt controller */ - /* VSMP /SMTC support support is not enabled for SLP */ + /* + * Setup the 2nd-level SLP register based interrupt controller. + * VSMP support support is not enabled for SLP. + */ msp_slp_irq_init(); /* setup the cascaded SLP/PER interrupts */ diff --git a/arch/mips/pmcs-msp71xx/msp_irq_cic.c b/arch/mips/pmcs-msp71xx/msp_irq_cic.c index e49b499f66db..b8df2f7b3328 100644 --- a/arch/mips/pmcs-msp71xx/msp_irq_cic.c +++ b/arch/mips/pmcs-msp71xx/msp_irq_cic.c @@ -120,10 +120,9 @@ static void msp_cic_irq_ack(struct irq_data *d) * hurt for the others */ *CIC_STS_REG = (1 << (d->irq - MSP_CIC_INTBASE)); - smtc_im_ack_irq(d->irq); } -/*Note: Limiting to VSMP . Not tested in SMTC */ +/* Note: Limiting to VSMP. */ #ifdef CONFIG_MIPS_MT_SMP static int msp_cic_irq_set_affinity(struct irq_data *d, @@ -183,10 +182,6 @@ void __init msp_cic_irq_init(void) for (i = MSP_CIC_INTBASE ; i < MSP_CIC_INTBASE + 32 ; i++) { irq_set_chip_and_handler(i, &msp_cic_irq_controller, handle_level_irq); -#ifdef CONFIG_MIPS_MT_SMTC - /* Mask of CIC interrupt */ - irq_hwmask[i] = C_IRQ4; -#endif } /* Initialize the PER interrupt sub-system */ diff --git a/arch/mips/pmcs-msp71xx/msp_irq_per.c b/arch/mips/pmcs-msp71xx/msp_irq_per.c index d1fd530479d4..a111836bcec2 100644 --- a/arch/mips/pmcs-msp71xx/msp_irq_per.c +++ b/arch/mips/pmcs-msp71xx/msp_irq_per.c @@ -113,9 +113,6 @@ void __init msp_per_irq_init(void) /* initialize all the IRQ descriptors */ for (i = MSP_PER_INTBASE; i < MSP_PER_INTBASE + 32; i++) { irq_set_chip(i, &msp_per_irq_controller); -#ifdef CONFIG_MIPS_MT_SMTC - irq_hwmask[i] = C_IRQ4; -#endif } } diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c index 7e980767679c..4f925e06c414 100644 --- a/arch/mips/pmcs-msp71xx/msp_setup.c +++ b/arch/mips/pmcs-msp71xx/msp_setup.c @@ -27,7 +27,6 @@ #endif extern void msp_serial_setup(void); -extern void pmctwiled_setup(void); #if defined(CONFIG_PMC_MSP7120_EVAL) || \ defined(CONFIG_PMC_MSP7120_GW) || \ @@ -148,8 +147,6 @@ void __init plat_mem_setup(void) pm_power_off = msp_power_off; } -extern struct plat_smp_ops msp_smtc_smp_ops; - void __init prom_init(void) { unsigned long family; @@ -230,17 +227,5 @@ void __init prom_init(void) */ msp_serial_setup(); - if (register_vsmp_smp_ops()) { -#ifdef CONFIG_MIPS_MT_SMTC - register_smp_ops(&msp_smtc_smp_ops); -#endif - } - -#ifdef CONFIG_PMCTWILED - /* - * Setup LED states before the subsys_initcall loads other - * dependent drivers/modules. - */ - pmctwiled_setup(); -#endif + register_vsmp_smp_ops(); } diff --git a/arch/mips/pmcs-msp71xx/msp_smtc.c b/arch/mips/pmcs-msp71xx/msp_smtc.c deleted file mode 100644 index 6b5607fce279..000000000000 --- a/arch/mips/pmcs-msp71xx/msp_smtc.c +++ /dev/null @@ -1,104 +0,0 @@ -/* - * MSP71xx Platform-specific hooks for SMP operation - */ -#include <linux/irq.h> -#include <linux/init.h> - -#include <asm/mipsmtregs.h> -#include <asm/mipsregs.h> -#include <asm/smtc.h> -#include <asm/smtc_ipi.h> - -/* VPE/SMP Prototype implements platform interfaces directly */ - -/* - * Cause the specified action to be performed on a targeted "CPU" - */ - -static void msp_smtc_send_ipi_single(int cpu, unsigned int action) -{ - /* "CPU" may be TC of same VPE, VPE of same CPU, or different CPU */ - smtc_send_ipi(cpu, LINUX_SMP_IPI, action); -} - -static void msp_smtc_send_ipi_mask(const struct cpumask *mask, - unsigned int action) -{ - unsigned int i; - - for_each_cpu(i, mask) - msp_smtc_send_ipi_single(i, action); -} - -/* - * Post-config but pre-boot cleanup entry point - */ -static void msp_smtc_init_secondary(void) -{ - int myvpe; - - /* Don't enable Malta I/O interrupts (IP2) for secondary VPEs */ - myvpe = read_c0_tcbind() & TCBIND_CURVPE; - if (myvpe > 0) - change_c0_status(ST0_IM, STATUSF_IP0 | STATUSF_IP1 | - STATUSF_IP6 | STATUSF_IP7); - smtc_init_secondary(); -} - -/* - * Platform "CPU" startup hook - */ -static void msp_smtc_boot_secondary(int cpu, struct task_struct *idle) -{ - smtc_boot_secondary(cpu, idle); -} - -/* - * SMP initialization finalization entry point - */ -static void msp_smtc_smp_finish(void) -{ - smtc_smp_finish(); -} - -/* - * Hook for after all CPUs are online - */ - -static void msp_smtc_cpus_done(void) -{ -} - -/* - * Platform SMP pre-initialization - * - * As noted above, we can assume a single CPU for now - * but it may be multithreaded. - */ - -static void __init msp_smtc_smp_setup(void) -{ - /* - * we won't get the definitive value until - * we've run smtc_prepare_cpus later, but - */ - - if (read_c0_config3() & (1 << 2)) - smp_num_siblings = smtc_build_cpu_map(0); -} - -static void __init msp_smtc_prepare_cpus(unsigned int max_cpus) -{ - smtc_prepare_cpus(max_cpus); -} - -struct plat_smp_ops msp_smtc_smp_ops = { - .send_ipi_single = msp_smtc_send_ipi_single, - .send_ipi_mask = msp_smtc_send_ipi_mask, - .init_secondary = msp_smtc_init_secondary, - .smp_finish = msp_smtc_smp_finish, - .cpus_done = msp_smtc_cpus_done, - .boot_secondary = msp_smtc_boot_secondary, - .smp_setup = msp_smtc_smp_setup, - .prepare_cpus = msp_smtc_prepare_cpus, -}; diff --git a/arch/mips/pmcs-msp71xx/msp_usb.c b/arch/mips/pmcs-msp71xx/msp_usb.c index 4dab915696e7..c87c5f810cd1 100644 --- a/arch/mips/pmcs-msp71xx/msp_usb.c +++ b/arch/mips/pmcs-msp71xx/msp_usb.c @@ -75,47 +75,6 @@ static struct mspusb_device msp_usbhost0_device = { .resource = msp_usbhost0_resources, }, }; - -/* MSP7140/MSP82XX has two USB2 hosts. */ -#ifdef CONFIG_MSP_HAS_DUAL_USB -static u64 msp_usbhost1_dma_mask = 0xffffffffUL; - -static struct resource msp_usbhost1_resources[] = { - [0] = { /* EHCI-HS operational and capabilities registers */ - .start = MSP_USB1_HS_START, - .end = MSP_USB1_HS_END, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = MSP_INT_USB, - .end = MSP_INT_USB, - .flags = IORESOURCE_IRQ, - }, - [2] = { /* MSBus-to-AMBA bridge register space */ - .start = MSP_USB1_MAB_START, - .end = MSP_USB1_MAB_END, - .flags = IORESOURCE_MEM, - }, - [3] = { /* Identification and general hardware parameters */ - .start = MSP_USB1_ID_START, - .end = MSP_USB1_ID_END, - .flags = IORESOURCE_MEM, - }, -}; - -static struct mspusb_device msp_usbhost1_device = { - .dev = { - .name = "pmcmsp-ehci", - .id = 1, - .dev = { - .dma_mask = &msp_usbhost1_dma_mask, - .coherent_dma_mask = 0xffffffffUL, - }, - .num_resources = ARRAY_SIZE(msp_usbhost1_resources), - .resource = msp_usbhost1_resources, - }, -}; -#endif /* CONFIG_MSP_HAS_DUAL_USB */ #endif /* CONFIG_USB_EHCI_HCD */ #if defined(CONFIG_USB_GADGET) @@ -157,46 +116,6 @@ static struct mspusb_device msp_usbdev0_device = { .resource = msp_usbdev0_resources, }, }; - -#ifdef CONFIG_MSP_HAS_DUAL_USB -static struct resource msp_usbdev1_resources[] = { - [0] = { /* EHCI-HS operational and capabilities registers */ - .start = MSP_USB1_HS_START, - .end = MSP_USB1_HS_END, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = MSP_INT_USB, - .end = MSP_INT_USB, - .flags = IORESOURCE_IRQ, - }, - [2] = { /* MSBus-to-AMBA bridge register space */ - .start = MSP_USB1_MAB_START, - .end = MSP_USB1_MAB_END, - .flags = IORESOURCE_MEM, - }, - [3] = { /* Identification and general hardware parameters */ - .start = MSP_USB1_ID_START, - .end = MSP_USB1_ID_END, - .flags = IORESOURCE_MEM, - }, -}; - -/* This may need to be converted to a mspusb_device, too. */ -static struct mspusb_device msp_usbdev1_device = { - .dev = { - .name = "msp71xx_udc", - .id = 0, - .dev = { - .dma_mask = &msp_usbdev_dma_mask, - .coherent_dma_mask = 0xffffffffUL, - }, - .num_resources = ARRAY_SIZE(msp_usbdev1_resources), - .resource = msp_usbdev1_resources, - }, -}; - -#endif /* CONFIG_MSP_HAS_DUAL_USB */ #endif /* CONFIG_USB_GADGET */ static int __init msp_usb_setup(void) @@ -231,10 +150,6 @@ static int __init msp_usb_setup(void) #if defined(CONFIG_USB_EHCI_HCD) msp_devs[0] = &msp_usbhost0_device.dev; ppfinit("platform add USB HOST done %s.\n", msp_devs[0]->name); -#ifdef CONFIG_MSP_HAS_DUAL_USB - msp_devs[1] = &msp_usbhost1_device.dev; - ppfinit("platform add USB HOST done %s.\n", msp_devs[1]->name); -#endif #else ppfinit("%s: echi_hcd not supported\n", __FILE__); #endif /* CONFIG_USB_EHCI_HCD */ @@ -244,11 +159,6 @@ static int __init msp_usb_setup(void) msp_devs[0] = &msp_usbdev0_device.dev; ppfinit("platform add USB DEVICE done %s.\n" , msp_devs[0]->name); -#ifdef CONFIG_MSP_HAS_DUAL_USB - msp_devs[1] = &msp_usbdev1_device.dev; - ppfinit("platform add USB DEVICE done %s.\n" - , msp_devs[1]->name); -#endif #else ppfinit("%s: usb_gadget not supported\n", __FILE__); #endif /* CONFIG_USB_GADGET */ diff --git a/arch/mips/pnx833x/common/platform.c b/arch/mips/pnx833x/common/platform.c index 2b7e837dc2e2..b4b774bc3178 100644 --- a/arch/mips/pnx833x/common/platform.c +++ b/arch/mips/pnx833x/common/platform.c @@ -33,11 +33,6 @@ #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> -#ifdef CONFIG_I2C_PNX0105 -/* Until i2c driver available in kernel.*/ -#include <linux/i2c-pnx0105.h> -#endif - #include <irq.h> #include <irq-mapping.h> #include <pnx833x.h> @@ -134,70 +129,6 @@ static struct platform_device pnx833x_usb_ehci_device = { .resource = pnx833x_usb_ehci_resources, }; -#ifdef CONFIG_I2C_PNX0105 -static struct resource pnx833x_i2c0_resources[] = { - { - .start = PNX833X_I2C0_PORTS_START, - .end = PNX833X_I2C0_PORTS_END, - .flags = IORESOURCE_MEM, - }, - { - .start = PNX833X_PIC_I2C0_INT, - .end = PNX833X_PIC_I2C0_INT, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource pnx833x_i2c1_resources[] = { - { - .start = PNX833X_I2C1_PORTS_START, - .end = PNX833X_I2C1_PORTS_END, - .flags = IORESOURCE_MEM, - }, - { - .start = PNX833X_PIC_I2C1_INT, - .end = PNX833X_PIC_I2C1_INT, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct i2c_pnx0105_dev pnx833x_i2c_dev[] = { - { - .base = PNX833X_I2C0_PORTS_START, - .irq = -1, /* should be PNX833X_PIC_I2C0_INT but polling is faster */ - .clock = 6, /* 0 == 400 kHz, 4 == 100 kHz(Maximum HDMI), 6 = 50kHz(Preferred HDCP) */ - .bus_addr = 0, /* no slave support */ - }, - { - .base = PNX833X_I2C1_PORTS_START, - .irq = -1, /* on high freq, polling is faster */ - /*.irq = PNX833X_PIC_I2C1_INT,*/ - .clock = 4, /* 0 == 400 kHz, 4 == 100 kHz. 100 kHz seems a safe default for now */ - .bus_addr = 0, /* no slave support */ - }, -}; - -static struct platform_device pnx833x_i2c0_device = { - .name = "i2c-pnx0105", - .id = 0, - .dev = { - .platform_data = &pnx833x_i2c_dev[0], - }, - .num_resources = ARRAY_SIZE(pnx833x_i2c0_resources), - .resource = pnx833x_i2c0_resources, -}; - -static struct platform_device pnx833x_i2c1_device = { - .name = "i2c-pnx0105", - .id = 1, - .dev = { - .platform_data = &pnx833x_i2c_dev[1], - }, - .num_resources = ARRAY_SIZE(pnx833x_i2c1_resources), - .resource = pnx833x_i2c1_resources, -}; -#endif - static u64 ethernet_dmamask = DMA_BIT_MASK(32); static struct resource pnx833x_ethernet_resources[] = { @@ -294,10 +225,6 @@ static struct platform_device pnx833x_flash_nand = { static struct platform_device *pnx833x_platform_devices[] __initdata = { &pnx833x_uart_device, &pnx833x_usb_ehci_device, -#ifdef CONFIG_I2C_PNX0105 - &pnx833x_i2c0_device, - &pnx833x_i2c1_device, -#endif &pnx833x_ethernet_device, &pnx833x_sata_device, &pnx833x_flash_nand, diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index eccc5526155e..251395210e23 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -28,8 +28,6 @@ __iomem void *rt_sysc_membase; __iomem void *rt_memc_membase; -extern struct boot_param_header __dtb_start; - __iomem void *plat_of_remap_node(const char *node) { struct resource res; @@ -52,30 +50,7 @@ __iomem void *plat_of_remap_node(const char *node) void __init device_tree_init(void) { - unsigned long base, size; - void *fdt_copy; - - if (!initial_boot_params) - return; - - base = virt_to_phys((void *)initial_boot_params); - size = be32_to_cpu(initial_boot_params->totalsize); - - /* Before we do anything, lets reserve the dt blob */ - reserve_bootmem(base, size, BOOTMEM_DEFAULT); - - /* The strings in the flattened tree are referenced directly by the - * device tree, so copy the flattened device tree from init memory - * to regular memory. - */ - fdt_copy = alloc_bootmem(size); - memcpy(fdt_copy, initial_boot_params, size); - initial_boot_params = fdt_copy; - - unflatten_device_tree(); - - /* free the space reserved for the dt blob */ - free_bootmem(base, size); + unflatten_and_copy_device_tree(); } void __init plat_mem_setup(void) @@ -86,7 +61,7 @@ void __init plat_mem_setup(void) * Load the builtin devicetree. This causes the chosen node to be * parsed resulting in our memory appearing */ - __dt_setup_arch(&__dtb_start); + __dt_setup_arch(__dtb_start); if (soc_info.mem_size) add_memory_region(soc_info.mem_base, soc_info.mem_size * SZ_1M, diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c index ab0e379dc7e0..8e52446286ca 100644 --- a/arch/mips/sgi-ip22/ip22-gio.c +++ b/arch/mips/sgi-ip22/ip22-gio.c @@ -19,6 +19,9 @@ static struct { } gio_name_table[] = { { .name = "SGI Impact", .id = 0x10 }, { .name = "Phobos G160", .id = 0x35 }, + { .name = "Phobos G130", .id = 0x36 }, + { .name = "Phobos G100", .id = 0x37 }, + { .name = "Set Engineering GFE", .id = 0x38 }, /* fake IDs */ { .name = "SGI Newport", .id = 0x7e }, { .name = "SGI GR2/GR3", .id = 0x7f }, @@ -293,7 +296,16 @@ static int ip22_gio_id(unsigned long addr, u32 *res) * data matches */ ptr8 = (void *)CKSEG1ADDR(addr + 3); - get_dbe(tmp8, ptr8); + if (get_dbe(tmp8, ptr8)) { + /* + * 32bit access worked, but 8bit doesn't + * so we don't see phantom reads on + * a pipelined bus, but a real card which + * doesn't support 8 bit reads + */ + *res = tmp32; + return 1; + } ptr16 = (void *)CKSEG1ADDR(addr + 2); get_dbe(tmp16, ptr16); if (tmp8 == (tmp16 & 0xff) && @@ -324,7 +336,7 @@ static int ip22_is_gr2(unsigned long addr) } -static void ip22_check_gio(int slotno, unsigned long addr) +static void ip22_check_gio(int slotno, unsigned long addr, int irq) { const char *name = "Unknown"; struct gio_device *gio_dev; @@ -338,9 +350,9 @@ static void ip22_check_gio(int slotno, unsigned long addr) else { if (!ip22_gio_id(addr, &tmp)) { /* - * no GIO signature at start address of slot, but - * Newport doesn't have one, so let's check usea - * status register + * no GIO signature at start address of slot + * since Newport doesn't have one, we check if + * user status register is readable */ if (ip22_gio_id(addr + NEWPORT_USTATUS_OFFS, &tmp)) tmp = 0x7e; @@ -369,6 +381,7 @@ static void ip22_check_gio(int slotno, unsigned long addr) gio_dev->resource.start = addr; gio_dev->resource.end = addr + 0x3fffff; gio_dev->resource.flags = IORESOURCE_MEM; + gio_dev->irq = irq; dev_set_name(&gio_dev->dev, "%d", slotno); gio_device_register(gio_dev); } else @@ -408,16 +421,17 @@ int __init ip22_gio_init(void) request_resource(&iomem_resource, &gio_bus_resource); printk(KERN_INFO "GIO: Probing bus...\n"); - if (ip22_is_fullhouse() || - !get_dbe(pbdma, (unsigned int *)&hpc3c1->pbdma[1])) { - /* Indigo2 and ChallengeS */ - ip22_check_gio(0, GIO_SLOT_GFX_BASE); - ip22_check_gio(1, GIO_SLOT_EXP0_BASE); + if (ip22_is_fullhouse()) { + /* Indigo2 */ + ip22_check_gio(0, GIO_SLOT_GFX_BASE, SGI_GIO_1_IRQ); + ip22_check_gio(1, GIO_SLOT_EXP0_BASE, SGI_GIO_1_IRQ); } else { - /* Indy */ - ip22_check_gio(0, GIO_SLOT_GFX_BASE); - ip22_check_gio(1, GIO_SLOT_EXP0_BASE); - ip22_check_gio(2, GIO_SLOT_EXP1_BASE); + /* Indy/Challenge S */ + if (get_dbe(pbdma, (unsigned int *)&hpc3c1->pbdma[1])) + ip22_check_gio(0, GIO_SLOT_GFX_BASE, + SGI_GIO_0_IRQ); + ip22_check_gio(1, GIO_SLOT_EXP0_BASE, SGI_GIOEXP0_IRQ); + ip22_check_gio(2, GIO_SLOT_EXP1_BASE, SGI_GIOEXP1_IRQ); } } else device_unregister(&gio_bus); diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c index 58b40ae59335..c66889fc4913 100644 --- a/arch/mips/sgi-ip22/ip22-int.c +++ b/arch/mips/sgi-ip22/ip22-int.c @@ -119,9 +119,14 @@ static void indy_local0_irqdispatch(void) } else irq = lc0msk_to_irqnr[mask]; - /* if irq == 0, then the interrupt has already been cleared */ + /* + * workaround for INT2 bug; if irq == 0, INT2 has seen a fifo full + * irq, but failed to latch it into status register + */ if (irq) do_IRQ(irq); + else + do_IRQ(SGINT_LOCAL0 + 0); } static void indy_local1_irqdispatch(void) diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c index f4ea8aa79ba2..f9ae6a8fa7c7 100644 --- a/arch/mips/sgi-ip27/ip27-smp.c +++ b/arch/mips/sgi-ip27/ip27-smp.c @@ -186,10 +186,6 @@ static void ip27_smp_finish(void) local_irq_enable(); } -static void __init ip27_cpus_done(void) -{ -} - /* * Launch a slave into smp_bootstrap(). It doesn't take an argument, and we * set sp to the kernel stack of the newly created idle process, gp to the proc @@ -236,7 +232,6 @@ struct plat_smp_ops ip27_smp_ops = { .send_ipi_mask = ip27_send_ipi_mask, .init_secondary = ip27_init_secondary, .smp_finish = ip27_smp_finish, - .cpus_done = ip27_cpus_done, .boot_secondary = ip27_boot_secondary, .smp_setup = ip27_smp_setup, .prepare_cpus = ip27_prepare_cpus, diff --git a/arch/mips/sibyte/bcm1480/irq.c b/arch/mips/sibyte/bcm1480/irq.c index 59cfe2659771..373fbbc8425c 100644 --- a/arch/mips/sibyte/bcm1480/irq.c +++ b/arch/mips/sibyte/bcm1480/irq.c @@ -347,19 +347,8 @@ asmlinkage void plat_irq_dispatch(void) unsigned int cpu = smp_processor_id(); unsigned int pending; -#ifdef CONFIG_SIBYTE_BCM1480_PROF - /* Set compare to count to silence count/compare timer interrupts */ - write_c0_compare(read_c0_count()); -#endif - pending = read_c0_cause() & read_c0_status(); -#ifdef CONFIG_SIBYTE_BCM1480_PROF - if (pending & CAUSEF_IP7) /* Cpu performance counter interrupt */ - sbprof_cpu_intr(); - else -#endif - if (pending & CAUSEF_IP4) do_IRQ(K_BCM1480_INT_TIMER_0 + cpu); #ifdef CONFIG_SMP diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c index 70d9182b26f1..af7d44edd9a8 100644 --- a/arch/mips/sibyte/bcm1480/smp.c +++ b/arch/mips/sibyte/bcm1480/smp.c @@ -115,13 +115,6 @@ static void bcm1480_smp_finish(void) } /* - * Final cleanup after all secondaries booted - */ -static void bcm1480_cpus_done(void) -{ -} - -/* * Setup the PC, SP, and GP of a secondary processor and start it * running! */ @@ -170,7 +163,6 @@ struct plat_smp_ops bcm1480_smp_ops = { .send_ipi_mask = bcm1480_send_ipi_mask, .init_secondary = bcm1480_init_secondary, .smp_finish = bcm1480_smp_finish, - .cpus_done = bcm1480_cpus_done, .boot_secondary = bcm1480_boot_secondary, .smp_setup = bcm1480_smp_setup, .prepare_cpus = bcm1480_prepare_cpus, diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c index db976117dd4d..c0c4b3f88a08 100644 --- a/arch/mips/sibyte/sb1250/smp.c +++ b/arch/mips/sibyte/sb1250/smp.c @@ -103,13 +103,6 @@ static void sb1250_smp_finish(void) } /* - * Final cleanup after all secondaries booted - */ -static void sb1250_cpus_done(void) -{ -} - -/* * Setup the PC, SP, and GP of a secondary processor and start it * running! */ @@ -158,7 +151,6 @@ struct plat_smp_ops sb_smp_ops = { .send_ipi_mask = sb1250_send_ipi_mask, .init_secondary = sb1250_init_secondary, .smp_finish = sb1250_smp_finish, - .cpus_done = sb1250_cpus_done, .boot_secondary = sb1250_boot_secondary, .smp_setup = sb1250_smp_setup, .prepare_cpus = sb1250_prepare_cpus, diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c index 2b0b83c171e0..dd2cf25b5ae5 100644 --- a/arch/mips/txx9/generic/setup.c +++ b/arch/mips/txx9/generic/setup.c @@ -309,8 +309,8 @@ static void __init preprocess_cmdline(void) txx9_board_vec = find_board_byname(str + 6); continue; } else if (strncmp(str, "masterclk=", 10) == 0) { - unsigned long val; - if (strict_strtoul(str + 10, 10, &val) == 0) + unsigned int val; + if (kstrtouint(str + 10, 10, &val) == 0) txx9_master_clock = val; continue; } else if (strcmp(str, "icdisable") == 0) { diff --git a/arch/mn10300/include/asm/unistd.h b/arch/mn10300/include/asm/unistd.h index 9d4e2d1ef90e..0522468f488b 100644 --- a/arch/mn10300/include/asm/unistd.h +++ b/arch/mn10300/include/asm/unistd.h @@ -26,7 +26,6 @@ #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_UTIME diff --git a/arch/openrisc/kernel/vmlinux.h b/arch/openrisc/kernel/vmlinux.h index 70b9ce41835c..bbcdf21b0b35 100644 --- a/arch/openrisc/kernel/vmlinux.h +++ b/arch/openrisc/kernel/vmlinux.h @@ -5,6 +5,4 @@ extern char __initrd_start, __initrd_end; #endif -extern u32 __dtb_start[]; - #endif diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h index 72c0fafaa039..544ed8ef87eb 100644 --- a/arch/parisc/include/asm/ftrace.h +++ b/arch/parisc/include/asm/ftrace.h @@ -24,15 +24,7 @@ extern void return_to_handler(void); extern unsigned long return_address(unsigned int); -#define HAVE_ARCH_CALLER_ADDR - -#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -#define CALLER_ADDR1 return_address(1) -#define CALLER_ADDR2 return_address(2) -#define CALLER_ADDR3 return_address(3) -#define CALLER_ADDR4 return_address(4) -#define CALLER_ADDR5 return_address(5) -#define CALLER_ADDR6 return_address(6) +#define ftrace_return_address(n) return_address(n) #endif /* __ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/unistd.h b/arch/parisc/include/asm/unistd.h index 74d835820ee7..5f4c68daa261 100644 --- a/arch/parisc/include/asm/unistd.h +++ b/arch/parisc/include/asm/unistd.h @@ -145,7 +145,6 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5) \ #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_COMPAT_SYS_TIME diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e0998997943b..bd6dd6ed3a9f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -453,6 +453,14 @@ config NODES_SHIFT default "4" depends on NEED_MULTIPLE_NODES +config USE_PERCPU_NUMA_NODE_ID + def_bool y + depends on NUMA + +config HAVE_MEMORYLESS_NODES + def_bool y + depends on NUMA + config ARCH_SELECT_MEMORY_MODEL def_bool y depends on PPC64 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index ce4c68a4a823..5687e299d0a5 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -113,8 +113,13 @@ else endif endif -CFLAGS-$(CONFIG_PPC64) := -mtraceback=no -mcall-aixdesc -CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) +CFLAGS-$(CONFIG_PPC64) := -mtraceback=no +ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) +CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,-mcall-aixdesc) +AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2) +else +CFLAGS-$(CONFIG_PPC64) += -mcall-aixdesc +endif CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,-mminimal-toc) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) CFLAGS-$(CONFIG_PPC32) := -ffixed-r2 $(MULTIPLEWORD) @@ -153,7 +158,7 @@ CFLAGS-$(CONFIG_TUNE_CELL) += $(call cc-option,-mtune=cell) asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1) KBUILD_CPPFLAGS += -Iarch/$(ARCH) $(asinstr) -KBUILD_AFLAGS += -Iarch/$(ARCH) +KBUILD_AFLAGS += -Iarch/$(ARCH) $(AFLAGS-y) KBUILD_CFLAGS += -msoft-float -pipe -Iarch/$(ARCH) $(CFLAGS-y) CPP = $(CC) -E $(KBUILD_CFLAGS) @@ -161,6 +166,11 @@ CHECKFLAGS += -m$(CONFIG_WORD_SIZE) -D__powerpc__ -D__powerpc$(CONFIG_WORD_SIZE) KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o +ifeq ($(CONFIG_476FPE_ERR46),y) + KBUILD_LDFLAGS_MODULE += --ppc476-workaround \ + -T $(srctree)/arch/powerpc/platforms/44x/ppc476_modules.lds +endif + # No AltiVec or VSX instructions when building kernel KBUILD_CFLAGS += $(call cc-option,-mno-altivec) KBUILD_CFLAGS += $(call cc-option,-mno-vsx) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index a1f8c7f1ec60..426dce7ae7c4 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -22,8 +22,14 @@ all: $(obj)/zImage BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -Os -msoft-float -pipe \ -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ - -isystem $(shell $(CROSS32CC) -print-file-name=include) \ - -mbig-endian + -isystem $(shell $(CROSS32CC) -print-file-name=include) +ifdef CONFIG_PPC64_BOOT_WRAPPER +BOOTCFLAGS += -m64 +endif +ifdef CONFIG_CPU_BIG_ENDIAN +BOOTCFLAGS += -mbig-endian +endif + BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc ifdef CONFIG_DEBUG_INFO @@ -47,6 +53,7 @@ $(obj)/cuboot-acadia.o: BOOTCFLAGS += -mcpu=405 $(obj)/treeboot-walnut.o: BOOTCFLAGS += -mcpu=405 $(obj)/treeboot-iss4xx.o: BOOTCFLAGS += -mcpu=405 $(obj)/treeboot-currituck.o: BOOTCFLAGS += -mcpu=405 +$(obj)/treeboot-akebono.o: BOOTCFLAGS += -mcpu=405 $(obj)/virtex405-head.o: BOOTAFLAGS += -mcpu=405 @@ -86,6 +93,7 @@ src-plat-$(CONFIG_44x) += treeboot-ebony.c cuboot-ebony.c treeboot-bamboo.c \ cuboot-taishan.c cuboot-katmai.c \ cuboot-warp.c cuboot-yosemite.c \ treeboot-iss4xx.c treeboot-currituck.c \ + treeboot-akebono.c \ simpleboot.c fixed-head.S virtex.c src-plat-$(CONFIG_8xx) += cuboot-8xx.c fixed-head.S ep88xc.c redboot-8xx.c src-plat-$(CONFIG_PPC_MPC52xx) += cuboot-52xx.c @@ -99,6 +107,11 @@ src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c cuboot-mpc7448hpc2.c \ src-plat-$(CONFIG_AMIGAONE) += cuboot-amigaone.c src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c +src-plat-$(CONFIG_PPC_PSERIES) += pseries-head.S +src-plat-$(CONFIG_PPC_POWERNV) += pseries-head.S +src-plat-$(CONFIG_PPC_IBM_CELL_BLADE) += pseries-head.S +src-plat-$(CONFIG_PPC_CELLEB) += pseries-head.S +src-plat-$(CONFIG_PPC_CELL_QPACE) += pseries-head.S src-wlib := $(sort $(src-wlib-y)) src-plat := $(sort $(src-plat-y)) @@ -137,7 +150,11 @@ $(addprefix $(obj)/,$(libfdt) $(libfdtheader)): $(obj)/%: $(srctree)/scripts/dtc $(obj)/empty.c: @touch $@ -$(obj)/zImage.lds $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds: $(obj)/%: $(srctree)/$(src)/%.S +$(obj)/zImage.lds: $(obj)/%: $(srctree)/$(src)/%.S + $(CROSS32CC) $(cpp_flags) -E -Wp,-MD,$(depfile) -P -Upowerpc \ + -D__ASSEMBLY__ -DLINKER_SCRIPT -o $@ $< + +$(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(srctree)/$(src)/%.S @cp $< $@ clean-files := $(zlib) $(zlibheader) $(zliblinuxheader) \ @@ -235,6 +252,7 @@ image-$(CONFIG_YOSEMITE) += cuImage.yosemite image-$(CONFIG_ISS4xx) += treeImage.iss4xx \ treeImage.iss4xx-mpic image-$(CONFIG_CURRITUCK) += treeImage.currituck +image-$(CONFIG_AKEBONO) += treeImage.akebono # Board ports in arch/powerpc/platform/8xx/Kconfig image-$(CONFIG_MPC86XADS) += cuImage.mpc866ads diff --git a/arch/powerpc/boot/addnote.c b/arch/powerpc/boot/addnote.c index 349b5530d2c4..9d9f6f334d3c 100644 --- a/arch/powerpc/boot/addnote.c +++ b/arch/powerpc/boot/addnote.c @@ -6,6 +6,8 @@ * * Copyright 2000 Paul Mackerras. * + * Adapted for 64 bit little endian images by Andrew Tauferner. + * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version @@ -55,36 +57,61 @@ unsigned int rpanote[N_RPA_DESCR] = { #define ROUNDUP(len) (((len) + 3) & ~3) -unsigned char buf[512]; +unsigned char buf[1024]; +#define ELFDATA2LSB 1 +#define ELFDATA2MSB 2 +static int e_data = ELFDATA2MSB; +#define ELFCLASS32 1 +#define ELFCLASS64 2 +static int e_class = ELFCLASS32; #define GET_16BE(off) ((buf[off] << 8) + (buf[(off)+1])) -#define GET_32BE(off) ((GET_16BE(off) << 16) + GET_16BE((off)+2)) - -#define PUT_16BE(off, v) (buf[off] = ((v) >> 8) & 0xff, \ - buf[(off) + 1] = (v) & 0xff) -#define PUT_32BE(off, v) (PUT_16BE((off), (v) >> 16), \ - PUT_16BE((off) + 2, (v))) +#define GET_32BE(off) ((GET_16BE(off) << 16U) + GET_16BE((off)+2U)) +#define GET_64BE(off) ((((unsigned long long)GET_32BE(off)) << 32ULL) + \ + ((unsigned long long)GET_32BE((off)+4ULL))) +#define PUT_16BE(off, v)(buf[off] = ((v) >> 8) & 0xff, \ + buf[(off) + 1] = (v) & 0xff) +#define PUT_32BE(off, v)(PUT_16BE((off), (v) >> 16L), PUT_16BE((off) + 2, (v))) +#define PUT_64BE(off, v)((PUT_32BE((off), (v) >> 32L), \ + PUT_32BE((off) + 4, (v)))) + +#define GET_16LE(off) ((buf[off]) + (buf[(off)+1] << 8)) +#define GET_32LE(off) (GET_16LE(off) + (GET_16LE((off)+2U) << 16U)) +#define GET_64LE(off) ((unsigned long long)GET_32LE(off) + \ + (((unsigned long long)GET_32LE((off)+4ULL)) << 32ULL)) +#define PUT_16LE(off, v) (buf[off] = (v) & 0xff, \ + buf[(off) + 1] = ((v) >> 8) & 0xff) +#define PUT_32LE(off, v) (PUT_16LE((off), (v)), PUT_16LE((off) + 2, (v) >> 16L)) +#define PUT_64LE(off, v) (PUT_32LE((off), (v)), PUT_32LE((off) + 4, (v) >> 32L)) + +#define GET_16(off) (e_data == ELFDATA2MSB ? GET_16BE(off) : GET_16LE(off)) +#define GET_32(off) (e_data == ELFDATA2MSB ? GET_32BE(off) : GET_32LE(off)) +#define GET_64(off) (e_data == ELFDATA2MSB ? GET_64BE(off) : GET_64LE(off)) +#define PUT_16(off, v) (e_data == ELFDATA2MSB ? PUT_16BE(off, v) : \ + PUT_16LE(off, v)) +#define PUT_32(off, v) (e_data == ELFDATA2MSB ? PUT_32BE(off, v) : \ + PUT_32LE(off, v)) +#define PUT_64(off, v) (e_data == ELFDATA2MSB ? PUT_64BE(off, v) : \ + PUT_64LE(off, v)) /* Structure of an ELF file */ #define E_IDENT 0 /* ELF header */ -#define E_PHOFF 28 -#define E_PHENTSIZE 42 -#define E_PHNUM 44 -#define E_HSIZE 52 /* size of ELF header */ +#define E_PHOFF (e_class == ELFCLASS32 ? 28 : 32) +#define E_PHENTSIZE (e_class == ELFCLASS32 ? 42 : 54) +#define E_PHNUM (e_class == ELFCLASS32 ? 44 : 56) +#define E_HSIZE (e_class == ELFCLASS32 ? 52 : 64) #define EI_MAGIC 0 /* offsets in E_IDENT area */ #define EI_CLASS 4 #define EI_DATA 5 #define PH_TYPE 0 /* ELF program header */ -#define PH_OFFSET 4 -#define PH_FILESZ 16 -#define PH_HSIZE 32 /* size of program header */ +#define PH_OFFSET (e_class == ELFCLASS32 ? 4 : 8) +#define PH_FILESZ (e_class == ELFCLASS32 ? 16 : 32) +#define PH_HSIZE (e_class == ELFCLASS32 ? 32 : 56) #define PT_NOTE 4 /* Program header type = note */ -#define ELFCLASS32 1 -#define ELFDATA2MSB 2 unsigned char elf_magic[4] = { 0x7f, 'E', 'L', 'F' }; @@ -92,8 +119,8 @@ int main(int ac, char **av) { int fd, n, i; - int ph, ps, np; - int nnote, nnote2, ns; + unsigned long ph, ps, np; + long nnote, nnote2, ns; if (ac != 2) { fprintf(stderr, "Usage: %s elf-file\n", av[0]); @@ -114,26 +141,27 @@ main(int ac, char **av) exit(1); } - if (n < E_HSIZE || memcmp(&buf[E_IDENT+EI_MAGIC], elf_magic, 4) != 0) + if (memcmp(&buf[E_IDENT+EI_MAGIC], elf_magic, 4) != 0) + goto notelf; + e_class = buf[E_IDENT+EI_CLASS]; + if (e_class != ELFCLASS32 && e_class != ELFCLASS64) + goto notelf; + e_data = buf[E_IDENT+EI_DATA]; + if (e_data != ELFDATA2MSB && e_data != ELFDATA2LSB) + goto notelf; + if (n < E_HSIZE) goto notelf; - if (buf[E_IDENT+EI_CLASS] != ELFCLASS32 - || buf[E_IDENT+EI_DATA] != ELFDATA2MSB) { - fprintf(stderr, "%s is not a big-endian 32-bit ELF image\n", - av[1]); - exit(1); - } - - ph = GET_32BE(E_PHOFF); - ps = GET_16BE(E_PHENTSIZE); - np = GET_16BE(E_PHNUM); + ph = (e_class == ELFCLASS32 ? GET_32(E_PHOFF) : GET_64(E_PHOFF)); + ps = GET_16(E_PHENTSIZE); + np = GET_16(E_PHNUM); if (ph < E_HSIZE || ps < PH_HSIZE || np < 1) goto notelf; if (ph + (np + 2) * ps + nnote + nnote2 > n) goto nospace; for (i = 0; i < np; ++i) { - if (GET_32BE(ph + PH_TYPE) == PT_NOTE) { + if (GET_32(ph + PH_TYPE) == PT_NOTE) { fprintf(stderr, "%s already has a note entry\n", av[1]); exit(0); @@ -148,15 +176,22 @@ main(int ac, char **av) /* fill in the program header entry */ ns = ph + 2 * ps; - PUT_32BE(ph + PH_TYPE, PT_NOTE); - PUT_32BE(ph + PH_OFFSET, ns); - PUT_32BE(ph + PH_FILESZ, nnote); + PUT_32(ph + PH_TYPE, PT_NOTE); + if (e_class == ELFCLASS32) + PUT_32(ph + PH_OFFSET, ns); + else + PUT_64(ph + PH_OFFSET, ns); + + if (e_class == ELFCLASS32) + PUT_32(ph + PH_FILESZ, nnote); + else + PUT_64(ph + PH_FILESZ, nnote); /* fill in the note area we point to */ /* XXX we should probably make this a proper section */ - PUT_32BE(ns, strlen(arch) + 1); - PUT_32BE(ns + 4, N_DESCR * 4); - PUT_32BE(ns + 8, 0x1275); + PUT_32(ns, strlen(arch) + 1); + PUT_32(ns + 4, N_DESCR * 4); + PUT_32(ns + 8, 0x1275); strcpy((char *) &buf[ns + 12], arch); ns += 12 + strlen(arch) + 1; for (i = 0; i < N_DESCR; ++i, ns += 4) @@ -164,21 +199,28 @@ main(int ac, char **av) /* fill in the second program header entry and the RPA note area */ ph += ps; - PUT_32BE(ph + PH_TYPE, PT_NOTE); - PUT_32BE(ph + PH_OFFSET, ns); - PUT_32BE(ph + PH_FILESZ, nnote2); + PUT_32(ph + PH_TYPE, PT_NOTE); + if (e_class == ELFCLASS32) + PUT_32(ph + PH_OFFSET, ns); + else + PUT_64(ph + PH_OFFSET, ns); + + if (e_class == ELFCLASS32) + PUT_32(ph + PH_FILESZ, nnote); + else + PUT_64(ph + PH_FILESZ, nnote2); /* fill in the note area we point to */ - PUT_32BE(ns, strlen(rpaname) + 1); - PUT_32BE(ns + 4, sizeof(rpanote)); - PUT_32BE(ns + 8, 0x12759999); + PUT_32(ns, strlen(rpaname) + 1); + PUT_32(ns + 4, sizeof(rpanote)); + PUT_32(ns + 8, 0x12759999); strcpy((char *) &buf[ns + 12], rpaname); ns += 12 + ROUNDUP(strlen(rpaname) + 1); for (i = 0; i < N_RPA_DESCR; ++i, ns += 4) PUT_32BE(ns, rpanote[i]); /* Update the number of program headers */ - PUT_16BE(E_PHNUM, np + 2); + PUT_16(E_PHNUM, np + 2); /* write back */ lseek(fd, (long) 0, SEEK_SET); diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S index 0f7428a37efb..14de4f8778a7 100644 --- a/arch/powerpc/boot/crt0.S +++ b/arch/powerpc/boot/crt0.S @@ -1,17 +1,20 @@ /* * Copyright (C) Paul Mackerras 1997. * + * Adapted for 64 bit LE PowerPC by Andrew Tauferner + * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * NOTE: this code runs in 32 bit mode, is position-independent, - * and is packaged as ELF32. */ #include "ppc_asm.h" +RELA = 7 +RELACOUNT = 0x6ffffff9 + .text /* A procedure descriptor used when booting this as a COFF file. * When making COFF, this comes first in the link and we're @@ -21,6 +24,20 @@ _zimage_start_opd: .long 0x500000, 0, 0, 0 +#ifdef __powerpc64__ +.balign 8 +p_start: .llong _start +p_etext: .llong _etext +p_bss_start: .llong __bss_start +p_end: .llong _end + +p_toc: .llong __toc_start + 0x8000 - p_base +p_dyn: .llong __dynamic_start - p_base +p_rela: .llong __rela_dyn_start - p_base +p_prom: .llong 0 + .weak _platform_stack_top +p_pstack: .llong _platform_stack_top +#else p_start: .long _start p_etext: .long _etext p_bss_start: .long __bss_start @@ -28,6 +45,7 @@ p_end: .long _end .weak _platform_stack_top p_pstack: .long _platform_stack_top +#endif .weak _zimage_start .globl _zimage_start @@ -38,6 +56,7 @@ _zimage_start_lib: and the address where we're running. */ bl .+4 p_base: mflr r10 /* r10 now points to runtime addr of p_base */ +#ifndef __powerpc64__ /* grab the link address of the dynamic section in r11 */ addis r11,r10,(_GLOBAL_OFFSET_TABLE_-p_base)@ha lwz r11,(_GLOBAL_OFFSET_TABLE_-p_base)@l(r11) @@ -51,8 +70,6 @@ p_base: mflr r10 /* r10 now points to runtime addr of p_base */ /* The dynamic section contains a series of tagged entries. * We need the RELA and RELACOUNT entries. */ -RELA = 7 -RELACOUNT = 0x6ffffff9 li r9,0 li r0,0 9: lwz r8,0(r12) /* get tag */ @@ -120,9 +137,164 @@ RELACOUNT = 0x6ffffff9 li r0,0 stwu r0,-16(r1) /* establish a stack frame */ 6: +#else /* __powerpc64__ */ + /* Save the prom pointer at p_prom. */ + std r5,(p_prom-p_base)(r10) + + /* Set r2 to the TOC. */ + ld r2,(p_toc-p_base)(r10) + add r2,r2,r10 + + /* Grab the link address of the dynamic section in r11. */ + ld r11,-32768(r2) + cmpwi r11,0 + beq 3f /* if not linked -pie then no dynamic section */ + + ld r11,(p_dyn-p_base)(r10) + add r11,r11,r10 + ld r9,(p_rela-p_base)(r10) + add r9,r9,r10 + li r7,0 + li r8,0 +9: ld r6,0(r11) /* get tag */ + cmpdi r6,0 + beq 12f /* end of list */ + cmpdi r6,RELA + bne 10f + ld r7,8(r11) /* get RELA pointer in r7 */ + b 11f +10: addis r6,r6,(-RELACOUNT)@ha + cmpdi r6,RELACOUNT@l + bne 11f + ld r8,8(r11) /* get RELACOUNT value in r8 */ +11: addi r11,r11,16 + b 9b +12: + cmpdi r7,0 /* check we have both RELA and RELACOUNT */ + cmpdi cr1,r8,0 + beq 3f + beq cr1,3f + + /* Calcuate the runtime offset. */ + subf r7,r7,r9 + + /* Run through the list of relocations and process the + * R_PPC64_RELATIVE ones. */ + mtctr r8 +13: ld r0,8(r9) /* ELF64_R_TYPE(reloc->r_info) */ + cmpdi r0,22 /* R_PPC64_RELATIVE */ + bne 3f + ld r6,0(r9) /* reloc->r_offset */ + ld r0,16(r9) /* reloc->r_addend */ + add r0,r0,r7 + stdx r0,r7,r6 + addi r9,r9,24 + bdnz 13b + + /* Do a cache flush for our text, in case the loader didn't */ +3: ld r9,p_start-p_base(r10) /* note: these are relocated now */ + ld r8,p_etext-p_base(r10) +4: dcbf r0,r9 + icbi r0,r9 + addi r9,r9,0x20 + cmpld cr0,r9,r8 + blt 4b + sync + isync + + /* Clear the BSS */ + ld r9,p_bss_start-p_base(r10) + ld r8,p_end-p_base(r10) + li r0,0 +5: std r0,0(r9) + addi r9,r9,8 + cmpld cr0,r9,r8 + blt 5b + + /* Possibly set up a custom stack */ + ld r8,p_pstack-p_base(r10) + cmpdi r8,0 + beq 6f + ld r1,0(r8) + li r0,0 + stdu r0,-16(r1) /* establish a stack frame */ +6: +#endif /* __powerpc64__ */ /* Call platform_init() */ bl platform_init /* Call start */ b start + +#ifdef __powerpc64__ + +#define PROM_FRAME_SIZE 512 +#define SAVE_GPR(n, base) std n,8*(n)(base) +#define REST_GPR(n, base) ld n,8*(n)(base) +#define SAVE_2GPRS(n, base) SAVE_GPR(n, base); SAVE_GPR(n+1, base) +#define SAVE_4GPRS(n, base) SAVE_2GPRS(n, base); SAVE_2GPRS(n+2, base) +#define SAVE_8GPRS(n, base) SAVE_4GPRS(n, base); SAVE_4GPRS(n+4, base) +#define SAVE_10GPRS(n, base) SAVE_8GPRS(n, base); SAVE_2GPRS(n+8, base) +#define REST_2GPRS(n, base) REST_GPR(n, base); REST_GPR(n+1, base) +#define REST_4GPRS(n, base) REST_2GPRS(n, base); REST_2GPRS(n+2, base) +#define REST_8GPRS(n, base) REST_4GPRS(n, base); REST_4GPRS(n+4, base) +#define REST_10GPRS(n, base) REST_8GPRS(n, base); REST_2GPRS(n+8, base) + +/* prom handles the jump into and return from firmware. The prom args pointer + is loaded in r3. */ +.globl prom +prom: + mflr r0 + std r0,16(r1) + stdu r1,-PROM_FRAME_SIZE(r1) /* Save SP and create stack space */ + + SAVE_GPR(2, r1) + SAVE_GPR(13, r1) + SAVE_8GPRS(14, r1) + SAVE_10GPRS(22, r1) + mfcr r10 + std r10,8*32(r1) + mfmsr r10 + std r10,8*33(r1) + + /* remove MSR_LE from msr but keep MSR_SF */ + mfmsr r10 + rldicr r10,r10,0,62 + mtsrr1 r10 + + /* Load FW address, set LR to label 1, and jump to FW */ + bl 0f +0: mflr r10 + addi r11,r10,(1f-0b) + mtlr r11 + + ld r10,(p_prom-0b)(r10) + mtsrr0 r10 + + rfid + +1: /* Return from OF */ + FIXUP_ENDIAN + + /* Restore registers and return. */ + rldicl r1,r1,0,32 + + /* Restore the MSR (back to 64 bits) */ + ld r10,8*(33)(r1) + mtmsr r10 + isync + + /* Restore other registers */ + REST_GPR(2, r1) + REST_GPR(13, r1) + REST_8GPRS(14, r1) + REST_10GPRS(22, r1) + ld r10,8*32(r1) + mtcr r10 + + addi r1,r1,PROM_FRAME_SIZE + ld r0,16(r1) + mtlr r0 + blr +#endif diff --git a/arch/powerpc/boot/dcr.h b/arch/powerpc/boot/dcr.h index cc73f7a95e26..bf8f4ede1928 100644 --- a/arch/powerpc/boot/dcr.h +++ b/arch/powerpc/boot/dcr.h @@ -15,6 +15,10 @@ asm volatile("mfdcrx %0,%1" : "=r"(rval) : "r"(rn)); \ rval; \ }) +#define mtdcrx(rn, val) \ + ({ \ + asm volatile("mtdcrx %0,%1" : : "r"(rn), "r" (val)); \ + }) /* 440GP/440GX SDRAM controller DCRs */ #define DCRN_SDRAM0_CFGADDR 0x010 diff --git a/arch/powerpc/boot/dts/akebono.dts b/arch/powerpc/boot/dts/akebono.dts new file mode 100644 index 000000000000..f92ecfed3d2f --- /dev/null +++ b/arch/powerpc/boot/dts/akebono.dts @@ -0,0 +1,415 @@ +/* + * Device Tree Source for IBM Embedded PPC 476 Platform + * + * Copyright © 2013 Tony Breeds IBM Corporation + * Copyright © 2013 Alistair Popple IBM Corporation + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without + * any warranty of any kind, whether express or implied. + */ + +/dts-v1/; + +/memreserve/ 0x01f00000 0x00100000; // spin table + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "ibm,akebono"; + compatible = "ibm,akebono", "ibm,476gtr"; + dcr-parent = <&{/cpus/cpu@0}>; + + aliases { + serial0 = &UART0; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + model = "PowerPC,476"; + reg = <0>; + clock-frequency = <1600000000>; // 1.6 GHz + timebase-frequency = <100000000>; // 100Mhz + i-cache-line-size = <32>; + d-cache-line-size = <32>; + i-cache-size = <32768>; + d-cache-size = <32768>; + dcr-controller; + dcr-access-method = "native"; + status = "ok"; + }; + cpu@1 { + device_type = "cpu"; + model = "PowerPC,476"; + reg = <1>; + clock-frequency = <1600000000>; // 1.6 GHz + timebase-frequency = <100000000>; // 100Mhz + i-cache-line-size = <32>; + d-cache-line-size = <32>; + i-cache-size = <32768>; + d-cache-size = <32768>; + dcr-controller; + dcr-access-method = "native"; + status = "disabled"; + enable-method = "spin-table"; + cpu-release-addr = <0x0 0x01f00000>; + }; + }; + + memory { + device_type = "memory"; + reg = <0x0 0x0 0x0 0x0>; // filled in by zImage + }; + + MPIC: interrupt-controller { + compatible = "chrp,open-pic"; + interrupt-controller; + dcr-reg = <0xffc00000 0x00040000>; + #address-cells = <0>; + #size-cells = <0>; + #interrupt-cells = <2>; + single-cpu-affinity; + }; + + plb { + compatible = "ibm,plb6"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + clock-frequency = <200000000>; // 200Mhz + + HSTA0: hsta@310000e0000 { + compatible = "ibm,476gtr-hsta-msi", "ibm,hsta-msi"; + reg = <0x310 0x000e0000 0x0 0xf0>; + interrupt-parent = <&MPIC>; + interrupts = <108 0 + 109 0 + 110 0 + 111 0 + 112 0 + 113 0 + 114 0 + 115 0 + 116 0 + 117 0 + 118 0 + 119 0 + 120 0 + 121 0 + 122 0 + 123 0>; + }; + + MAL0: mcmal { + compatible = "ibm,mcmal-476gtr", "ibm,mcmal2"; + dcr-reg = <0xc0000000 0x062>; + num-tx-chans = <1>; + num-rx-chans = <1>; + #address-cells = <0>; + #size-cells = <0>; + interrupt-parent = <&MPIC>; + interrupts = < /*TXEOB*/ 77 0x4 + /*RXEOB*/ 78 0x4 + /*SERR*/ 76 0x4 + /*TXDE*/ 79 0x4 + /*RXDE*/ 80 0x4>; + }; + + SATA0: sata@30000010000 { + compatible = "ibm,476gtr-ahci"; + reg = <0x300 0x00010000 0x0 0x10000>; + interrupt-parent = <&MPIC>; + interrupts = <93 2>; + }; + + EHCI0: ehci@30010000000 { + compatible = "ibm,476gtr-ehci", "generic-ehci"; + reg = <0x300 0x10000000 0x0 0x10000>; + interrupt-parent = <&MPIC>; + interrupts = <85 2>; + }; + + SD0: sd@30000000000 { + compatible = "ibm,476gtr-sdhci", "generic-sdhci"; + reg = <0x300 0x00000000 0x0 0x10000>; + interrupts = <91 2>; + interrupt-parent = <&MPIC>; + }; + + OHCI0: ohci@30010010000 { + compatible = "ibm,476gtr-ohci", "generic-ohci"; + reg = <0x300 0x10010000 0x0 0x10000>; + interrupt-parent = <&MPIC>; + interrupts = <89 1>; + }; + + OHCI1: ohci@30010020000 { + compatible = "ibm,476gtr-ohci", "generic-ohci"; + reg = <0x300 0x10020000 0x0 0x10000>; + interrupt-parent = <&MPIC>; + interrupts = <88 1>; + }; + + POB0: opb { + compatible = "ibm,opb-4xx", "ibm,opb"; + #address-cells = <1>; + #size-cells = <1>; + /* Wish there was a nicer way of specifying a full + * 32-bit range + */ + ranges = <0x00000000 0x0000033f 0x00000000 0x80000000 + 0x80000000 0x0000033f 0x80000000 0x80000000>; + clock-frequency = <100000000>; + + RGMII0: emac-rgmii-wol@50004 { + compatible = "ibm,rgmii-wol-476gtr", "ibm,rgmii-wol"; + reg = <0x50004 0x00000008>; + has-mdio; + }; + + EMAC0: ethernet@30000 { + device_type = "network"; + compatible = "ibm,emac-476gtr", "ibm,emac4sync"; + interrupt-parent = <&EMAC0>; + interrupts = <0x0 0x1>; + #interrupt-cells = <1>; + #address-cells = <0>; + #size-cells = <0>; + interrupt-map = </*Status*/ 0x0 &MPIC 81 0x4 + /*Wake*/ 0x1 &MPIC 82 0x4>; + reg = <0x30000 0x78>; + + /* local-mac-address will normally be added by + * the wrapper. If your device doesn't support + * passing data to the wrapper (in the form + * local-mac-addr=<hwaddr>) then you will need + * to set it manually here. */ + //local-mac-address = [000000000000]; + + mal-device = <&MAL0>; + mal-tx-channel = <0>; + mal-rx-channel = <0>; + cell-index = <0>; + max-frame-size = <9000>; + rx-fifo-size = <4096>; + tx-fifo-size = <2048>; + rx-fifo-size-gige = <16384>; + phy-mode = "rgmii"; + phy-map = <0x00000000>; + rgmii-wol-device = <&RGMII0>; + has-inverted-stacr-oc; + has-new-stacr-staopc; + }; + + UART0: serial@10000 { + device_type = "serial"; + compatible = "ns16750", "ns16550"; + reg = <0x10000 0x00000008>; + virtual-reg = <0xe8010000>; + clock-frequency = <1851851>; + current-speed = <38400>; + interrupt-parent = <&MPIC>; + interrupts = <39 2>; + }; + + IIC0: i2c@00000000 { + compatible = "ibm,iic-476gtr", "ibm,iic"; + reg = <0x0 0x00000020>; + interrupt-parent = <&MPIC>; + interrupts = <37 2>; + #address-cells = <1>; + #size-cells = <0>; + rtc@68 { + compatible = "stm,m41t80", "m41st85"; + reg = <0x68>; + }; + }; + + IIC1: i2c@00000100 { + compatible = "ibm,iic-476gtr", "ibm,iic"; + reg = <0x100 0x00000020>; + interrupt-parent = <&MPIC>; + interrupts = <38 2>; + #address-cells = <1>; + #size-cells = <0>; + avr@58 { + compatible = "ibm,akebono-avr"; + reg = <0x58>; + }; + }; + + FPGA0: fpga@ebc00000 { + compatible = "ibm,akebono-fpga"; + reg = <0xebc00000 0x8>; + }; + }; + + PCIE0: pciex@10100000000 { + device_type = "pci"; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + compatible = "ibm,plb-pciex-476fpe", "ibm,plb-pciex"; + primary; + port = <0x0>; /* port number */ + reg = <0x00000101 0x00000000 0x0 0x10000000 /* Config space access */ + 0x00000100 0x00000000 0x0 0x00001000>; /* UTL Registers space access */ + dcr-reg = <0xc0 0x20>; + +// pci_space < pci_addr > < cpu_addr > < size > + ranges = <0x02000000 0x00000000 0x80000000 0x00000110 0x80000000 0x0 0x80000000 + 0x01000000 0x0 0x0 0x00000140 0x0 0x0 0x00010000>; + + /* Inbound starting at 0x0 to 0x40000000000. In order to use MSI + * PCI devices must be able to write to the HSTA module. + */ + dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x400 0x0>; + + /* This drives busses 0 to 0xf */ + bus-range = <0x0 0xf>; + + /* Legacy interrupts (note the weird polarity, the bridge seems + * to invert PCIe legacy interrupts). + * We are de-swizzling here because the numbers are actually for + * port of the root complex virtual P2P bridge. But I want + * to avoid putting a node for it in the tree, so the numbers + * below are basically de-swizzled numbers. + * The real slot is on idsel 0, so the swizzling is 1:1 + */ + interrupt-map-mask = <0x0 0x0 0x0 0x7>; + interrupt-map = < + 0x0 0x0 0x0 0x1 &MPIC 45 0x2 /* int A */ + 0x0 0x0 0x0 0x2 &MPIC 46 0x2 /* int B */ + 0x0 0x0 0x0 0x3 &MPIC 47 0x2 /* int C */ + 0x0 0x0 0x0 0x4 &MPIC 48 0x2 /* int D */>; + }; + + PCIE1: pciex@20100000000 { + device_type = "pci"; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + compatible = "ibm,plb-pciex-476fpe", "ibm,plb-pciex"; + primary; + port = <0x1>; /* port number */ + reg = <0x00000201 0x00000000 0x0 0x10000000 /* Config space access */ + 0x00000200 0x00000000 0x0 0x00001000>; /* UTL Registers space access */ + dcr-reg = <0x100 0x20>; + +// pci_space < pci_addr > < cpu_addr > < size > + ranges = <0x02000000 0x00000000 0x80000000 0x00000210 0x80000000 0x0 0x80000000 + 0x01000000 0x0 0x0 0x00000240 0x0 0x0 0x00010000>; + + /* Inbound starting at 0x0 to 0x40000000000. In order to use MSI + * PCI devices must be able to write to the HSTA module. + */ + dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x400 0x0>; + + /* This drives busses 0 to 0xf */ + bus-range = <0x0 0xf>; + + /* Legacy interrupts (note the weird polarity, the bridge seems + * to invert PCIe legacy interrupts). + * We are de-swizzling here because the numbers are actually for + * port of the root complex virtual P2P bridge. But I want + * to avoid putting a node for it in the tree, so the numbers + * below are basically de-swizzled numbers. + * The real slot is on idsel 0, so the swizzling is 1:1 + */ + interrupt-map-mask = <0x0 0x0 0x0 0x7>; + interrupt-map = < + 0x0 0x0 0x0 0x1 &MPIC 53 0x2 /* int A */ + 0x0 0x0 0x0 0x2 &MPIC 54 0x2 /* int B */ + 0x0 0x0 0x0 0x3 &MPIC 55 0x2 /* int C */ + 0x0 0x0 0x0 0x4 &MPIC 56 0x2 /* int D */>; + }; + + PCIE2: pciex@18100000000 { + device_type = "pci"; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + compatible = "ibm,plb-pciex-476fpe", "ibm,plb-pciex"; + primary; + port = <0x2>; /* port number */ + reg = <0x00000181 0x00000000 0x0 0x10000000 /* Config space access */ + 0x00000180 0x00000000 0x0 0x00001000>; /* UTL Registers space access */ + dcr-reg = <0xe0 0x20>; + +// pci_space < pci_addr > < cpu_addr > < size > + ranges = <0x02000000 0x00000000 0x80000000 0x00000190 0x80000000 0x0 0x80000000 + 0x01000000 0x0 0x0 0x000001c0 0x0 0x0 0x00010000>; + + /* Inbound starting at 0x0 to 0x40000000000. In order to use MSI + * PCI devices must be able to write to the HSTA module. + */ + dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x400 0x0>; + + /* This drives busses 0 to 0xf */ + bus-range = <0x0 0xf>; + + /* Legacy interrupts (note the weird polarity, the bridge seems + * to invert PCIe legacy interrupts). + * We are de-swizzling here because the numbers are actually for + * port of the root complex virtual P2P bridge. But I want + * to avoid putting a node for it in the tree, so the numbers + * below are basically de-swizzled numbers. + * The real slot is on idsel 0, so the swizzling is 1:1 + */ + interrupt-map-mask = <0x0 0x0 0x0 0x7>; + interrupt-map = < + 0x0 0x0 0x0 0x1 &MPIC 61 0x2 /* int A */ + 0x0 0x0 0x0 0x2 &MPIC 62 0x2 /* int B */ + 0x0 0x0 0x0 0x3 &MPIC 63 0x2 /* int C */ + 0x0 0x0 0x0 0x4 &MPIC 64 0x2 /* int D */>; + }; + + PCIE3: pciex@28100000000 { + device_type = "pci"; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + compatible = "ibm,plb-pciex-476fpe", "ibm,plb-pciex"; + primary; + port = <0x3>; /* port number */ + reg = <0x00000281 0x00000000 0x0 0x10000000 /* Config space access */ + 0x00000280 0x00000000 0x0 0x00001000>; /* UTL Registers space access */ + dcr-reg = <0x120 0x20>; + +// pci_space < pci_addr > < cpu_addr > < size > + ranges = <0x02000000 0x00000000 0x80000000 0x00000290 0x80000000 0x0 0x80000000 + 0x01000000 0x0 0x0 0x000002c0 0x0 0x0 0x00010000>; + + /* Inbound starting at 0x0 to 0x40000000000. In order to use MSI + * PCI devices must be able to write to the HSTA module. + */ + dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x400 0x0>; + + /* This drives busses 0 to 0xf */ + bus-range = <0x0 0xf>; + + /* Legacy interrupts (note the weird polarity, the bridge seems + * to invert PCIe legacy interrupts). + * We are de-swizzling here because the numbers are actually for + * port of the root complex virtual P2P bridge. But I want + * to avoid putting a node for it in the tree, so the numbers + * below are basically de-swizzled numbers. + * The real slot is on idsel 0, so the swizzling is 1:1 + */ + interrupt-map-mask = <0x0 0x0 0x0 0x7>; + interrupt-map = < + 0x0 0x0 0x0 0x1 &MPIC 69 0x2 /* int A */ + 0x0 0x0 0x0 0x2 &MPIC 70 0x2 /* int B */ + 0x0 0x0 0x0 0x3 &MPIC 71 0x2 /* int C */ + 0x0 0x0 0x0 0x4 &MPIC 72 0x2 /* int D */>; + }; + }; + + chosen { + linux,stdout-path = &UART0; + }; +}; diff --git a/arch/powerpc/boot/dts/b4860emu.dts b/arch/powerpc/boot/dts/b4860emu.dts index 7290021f2dfc..85646b4f96e1 100644 --- a/arch/powerpc/boot/dts/b4860emu.dts +++ b/arch/powerpc/boot/dts/b4860emu.dts @@ -61,21 +61,25 @@ device_type = "cpu"; reg = <0 1>; next-level-cache = <&L2>; + fsl,portid-mapping = <0x80000000>; }; cpu1: PowerPC,e6500@2 { device_type = "cpu"; reg = <2 3>; next-level-cache = <&L2>; + fsl,portid-mapping = <0x80000000>; }; cpu2: PowerPC,e6500@4 { device_type = "cpu"; reg = <4 5>; next-level-cache = <&L2>; + fsl,portid-mapping = <0x80000000>; }; cpu3: PowerPC,e6500@6 { device_type = "cpu"; reg = <6 7>; next-level-cache = <&L2>; + fsl,portid-mapping = <0x80000000>; }; }; }; @@ -157,7 +161,7 @@ }; corenet-cf@18000 { - compatible = "fsl,b4-corenet-cf"; + compatible = "fsl,corenet2-cf", "fsl,corenet-cf"; reg = <0x18000 0x1000>; interrupts = <16 2 1 0>; fsl,ccf-num-csdids = <32>; @@ -167,6 +171,7 @@ iommu@20000 { compatible = "fsl,pamu-v1.0", "fsl,pamu"; reg = <0x20000 0x4000>; + fsl,portid-mapping = <0x8000>; #address-cells = <1>; #size-cells = <1>; interrupts = < diff --git a/arch/powerpc/boot/dts/bsc9132qds.dts b/arch/powerpc/boot/dts/bsc9132qds.dts new file mode 100644 index 000000000000..6cab1062bc74 --- /dev/null +++ b/arch/powerpc/boot/dts/bsc9132qds.dts @@ -0,0 +1,35 @@ +/* + * BSC9132 QDS Device Tree Source + * + * Copyright 2014 Freescale Semiconductor Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +/include/ "fsl/bsc9132si-pre.dtsi" + +/ { + model = "fsl,bsc9132qds"; + compatible = "fsl,bsc9132qds"; + + memory { + device_type = "memory"; + }; + + ifc: ifc@ff71e000 { + /* NOR, NAND Flash on board */ + ranges = <0x0 0x0 0x0 0x88000000 0x08000000 + 0x1 0x0 0x0 0xff800000 0x00010000>; + reg = <0x0 0xff71e000 0x0 0x2000>; + }; + + soc: soc@ff700000 { + ranges = <0x0 0x0 0xff700000 0x100000>; + }; +}; + +/include/ "bsc9132qds.dtsi" +/include/ "fsl/bsc9132si-post.dtsi" diff --git a/arch/powerpc/boot/dts/bsc9132qds.dtsi b/arch/powerpc/boot/dts/bsc9132qds.dtsi new file mode 100644 index 000000000000..af8e88830221 --- /dev/null +++ b/arch/powerpc/boot/dts/bsc9132qds.dtsi @@ -0,0 +1,101 @@ +/* + * BSC9132 QDS Device Tree Source stub (no addresses or top-level ranges) + * + * Copyright 2014 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +&ifc { + nor@0,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "cfi-flash"; + reg = <0x0 0x0 0x8000000>; + bank-width = <2>; + device-width = <1>; + }; + + nand@1,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,ifc-nand"; + reg = <0x1 0x0 0x4000>; + }; +}; + +&soc { + spi@7000 { + flash@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "spansion,s25sl12801"; + reg = <0>; + spi-max-frequency = <30000000>; + }; + }; + + i2c@3000 { + fpga: fpga@66 { + compatible = "fsl,bsc9132qds-fpga", "fsl,fpga-qixis-i2c"; + reg = <0x66>; + }; + }; + + usb@22000 { + phy_type = "ulpi"; + }; + + mdio@24000 { + phy0: ethernet-phy@0 { + reg = <0x0>; + }; + + phy1: ethernet-phy@1 { + reg = <0x1>; + }; + + tbi0: tbi-phy@11 { + reg = <0x1f>; + device_type = "tbi-phy"; + }; + }; + + enet0: ethernet@b0000 { + phy-handle = <&phy0>; + tbi-handle = <&tbi0>; + phy-connection-type = "sgmii"; + }; + + enet1: ethernet@b1000 { + phy-handle = <&phy1>; + tbi-handle = <&tbi0>; + phy-connection-type = "sgmii"; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi index 60566f9927be..d67894459ac8 100644 --- a/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi @@ -76,10 +76,6 @@ compatible = "fsl,b4420-l3-cache-controller", "cache"; }; - corenet-cf@18000 { - compatible = "fsl,b4420-corenet-cf"; - }; - guts: global-utilities@e0000 { compatible = "fsl,b4420-device-config", "fsl,qoriq-device-config-2.0"; }; diff --git a/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi index 2419731c2c54..338af7e39dd9 100644 --- a/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi @@ -66,12 +66,14 @@ reg = <0 1>; clocks = <&mux0>; next-level-cache = <&L2>; + fsl,portid-mapping = <0x80000000>; }; cpu1: PowerPC,e6500@2 { device_type = "cpu"; reg = <2 3>; clocks = <&mux0>; next-level-cache = <&L2>; + fsl,portid-mapping = <0x80000000>; }; }; }; diff --git a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi index cbc354b05117..582381dba1d7 100644 --- a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi @@ -120,10 +120,6 @@ compatible = "fsl,b4860-l3-cache-controller", "cache"; }; - corenet-cf@18000 { - compatible = "fsl,b4860-corenet-cf"; - }; - guts: global-utilities@e0000 { compatible = "fsl,b4860-device-config", "fsl,qoriq-device-config-2.0"; }; diff --git a/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi index 142ac862cacf..1948f73fd26b 100644 --- a/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi @@ -66,24 +66,28 @@ reg = <0 1>; clocks = <&mux0>; next-level-cache = <&L2>; + fsl,portid-mapping = <0x80000000>; }; cpu1: PowerPC,e6500@2 { device_type = "cpu"; reg = <2 3>; clocks = <&mux0>; next-level-cache = <&L2>; + fsl,portid-mapping = <0x80000000>; }; cpu2: PowerPC,e6500@4 { device_type = "cpu"; reg = <4 5>; clocks = <&mux0>; next-level-cache = <&L2>; + fsl,portid-mapping = <0x80000000>; }; cpu3: PowerPC,e6500@6 { device_type = "cpu"; reg = <6 7>; clocks = <&mux0>; next-level-cache = <&L2>; + fsl,portid-mapping = <0x80000000>; }; }; }; diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi index 4f6e48277c46..1a54ba71f685 100644 --- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi @@ -158,7 +158,7 @@ }; corenet-cf@18000 { - compatible = "fsl,b4-corenet-cf"; + compatible = "fsl,corenet2-cf", "fsl,corenet-cf"; reg = <0x18000 0x1000>; interrupts = <16 2 1 0>; fsl,ccf-num-csdids = <32>; @@ -168,6 +168,7 @@ iommu@20000 { compatible = "fsl,pamu-v1.0", "fsl,pamu"; reg = <0x20000 0x4000>; + fsl,portid-mapping = <0x8000>; #address-cells = <1>; #size-cells = <1>; interrupts = < diff --git a/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi new file mode 100644 index 000000000000..c72307198140 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi @@ -0,0 +1,185 @@ +/* + * BSC9132 Silicon/SoC Device Tree Source (post include) + * + * Copyright 2014 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +&ifc { + #address-cells = <2>; + #size-cells = <1>; + compatible = "fsl,ifc", "simple-bus"; + /* FIXME: Test whether interrupts are split */ + interrupts = <16 2 0 0 20 2 0 0>; +}; + +&soc { + #address-cells = <1>; + #size-cells = <1>; + device_type = "soc"; + compatible = "fsl,bsc9132-immr", "simple-bus"; + bus-frequency = <0>; // Filled out by uboot. + + ecm-law@0 { + compatible = "fsl,ecm-law"; + reg = <0x0 0x1000>; + fsl,num-laws = <12>; + }; + + ecm@1000 { + compatible = "fsl,bsc9132-ecm", "fsl,ecm"; + reg = <0x1000 0x1000>; + interrupts = <16 2 0 0>; + }; + + memory-controller@2000 { + compatible = "fsl,bsc9132-memory-controller"; + reg = <0x2000 0x1000>; + interrupts = <16 2 1 8>; + }; + +/include/ "pq3-i2c-0.dtsi" + i2c@3000 { + interrupts = <17 2 0 0>; + }; + +/include/ "pq3-i2c-1.dtsi" + i2c@3100 { + interrupts = <17 2 0 0>; + }; + +/include/ "pq3-duart-0.dtsi" + serial0: serial@4500 { + interrupts = <18 2 0 0>; + }; + + serial1: serial@4600 { + interrupts = <18 2 0 0 >; + }; +/include/ "pq3-espi-0.dtsi" + spi0: spi@7000 { + fsl,espi-num-chipselects = <1>; + interrupts = <22 0x2 0 0>; + }; + +/include/ "pq3-gpio-0.dtsi" + gpio-controller@f000 { + interrupts = <19 0x2 0 0>; + }; + + L2: l2-cache-controller@20000 { + compatible = "fsl,bsc9132-l2-cache-controller"; + reg = <0x20000 0x1000>; + cache-line-size = <32>; // 32 bytes + cache-size = <0x40000>; // L2,256K + interrupts = <16 2 1 0>; + }; + +/include/ "pq3-dma-0.dtsi" + +dma@21300 { + + dma-channel@0 { + interrupts = <62 2 0 0>; + }; + + dma-channel@80 { + interrupts = <63 2 0 0>; + }; + + dma-channel@100 { + interrupts = <64 2 0 0>; + }; + + dma-channel@180 { + interrupts = <65 2 0 0>; + }; +}; + +/include/ "pq3-usb2-dr-0.dtsi" +usb@22000 { + compatible = "fsl-usb2-dr","fsl-usb2-dr-v2.2"; + interrupts = <40 0x2 0 0>; +}; + +/include/ "pq3-esdhc-0.dtsi" + sdhc@2e000 { + fsl,sdhci-auto-cmd12; + interrupts = <41 0x2 0 0>; + }; + +/include/ "pq3-sec4.4-0.dtsi" +crypto@30000 { + interrupts = <57 2 0 0>; + + sec_jr0: jr@1000 { + interrupts = <58 2 0 0>; + }; + + sec_jr1: jr@2000 { + interrupts = <59 2 0 0>; + }; + + sec_jr2: jr@3000 { + interrupts = <60 2 0 0>; + }; + + sec_jr3: jr@4000 { + interrupts = <61 2 0 0>; + }; +}; + +/include/ "pq3-mpic.dtsi" +/include/ "pq3-mpic-timer-B.dtsi" + +/include/ "pq3-etsec2-0.dtsi" +enet0: ethernet@b0000 { + queue-group@b0000 { + fsl,rx-bit-map = <0xff>; + fsl,tx-bit-map = <0xff>; + interrupts = <26 2 0 0 27 2 0 0 28 2 0 0>; + }; +}; + +/include/ "pq3-etsec2-1.dtsi" +enet1: ethernet@b1000 { + queue-group@b1000 { + fsl,rx-bit-map = <0xff>; + fsl,tx-bit-map = <0xff>; + interrupts = <33 2 0 0 34 2 0 0 35 2 0 0>; + }; +}; + +global-utilities@e0000 { + compatible = "fsl,bsc9132-guts"; + reg = <0xe0000 0x1000>; + fsl,has-rstcr; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi b/arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi new file mode 100644 index 000000000000..301a9dba5790 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi @@ -0,0 +1,66 @@ +/* + * BSC9132 Silicon/SoC Device Tree Source (pre include) + * + * Copyright 2014 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/dts-v1/; + +/include/ "e500v2_power_isa.dtsi" + +/ { + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; + + aliases { + serial0 = &serial0; + ethernet0 = &enet0; + ethernet1 = &enet1; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: PowerPC,e500v2@0 { + device_type = "cpu"; + reg = <0x0>; + next-level-cache = <&L2>; + }; + + cpu1: PowerPC,e500v2@1 { + device_type = "cpu"; + reg = <0x1>; + next-level-cache = <&L2>; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi index e2987a33083c..5290df83ff30 100644 --- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi @@ -246,7 +246,7 @@ }; corenet-cf@18000 { - compatible = "fsl,corenet-cf"; + compatible = "fsl,corenet1-cf", "fsl,corenet-cf"; reg = <0x18000 0x1000>; interrupts = <16 2 1 31>; fsl,ccf-num-csdids = <32>; @@ -262,6 +262,7 @@ interrupts = < 24 2 0 0 16 2 1 30>; + fsl,portid-mapping = <0x0f000000>; pamu0: pamu@0 { reg = <0 0x1000>; diff --git a/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi index 22f3b14517de..b1ea147f2995 100644 --- a/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi @@ -83,6 +83,7 @@ reg = <0>; clocks = <&mux0>; next-level-cache = <&L2_0>; + fsl,portid-mapping = <0x80000000>; L2_0: l2-cache { next-level-cache = <&cpc>; }; @@ -92,6 +93,7 @@ reg = <1>; clocks = <&mux1>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x40000000>; L2_1: l2-cache { next-level-cache = <&cpc>; }; @@ -101,6 +103,7 @@ reg = <2>; clocks = <&mux2>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x20000000>; L2_2: l2-cache { next-level-cache = <&cpc>; }; @@ -110,6 +113,7 @@ reg = <3>; clocks = <&mux3>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x10000000>; L2_3: l2-cache { next-level-cache = <&cpc>; }; diff --git a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi index 7af6d45fd998..cd63cb1b1042 100644 --- a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi @@ -273,7 +273,7 @@ }; corenet-cf@18000 { - compatible = "fsl,corenet-cf"; + compatible = "fsl,corenet1-cf", "fsl,corenet-cf"; reg = <0x18000 0x1000>; interrupts = <16 2 1 31>; fsl,ccf-num-csdids = <32>; @@ -289,6 +289,7 @@ interrupts = < 24 2 0 0 16 2 1 30>; + fsl,portid-mapping = <0x0f000000>; pamu0: pamu@0 { reg = <0 0x1000>; diff --git a/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi index 468e8be8ac6f..dc5f4b362c24 100644 --- a/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi @@ -84,6 +84,7 @@ reg = <0>; clocks = <&mux0>; next-level-cache = <&L2_0>; + fsl,portid-mapping = <0x80000000>; L2_0: l2-cache { next-level-cache = <&cpc>; }; @@ -93,6 +94,7 @@ reg = <1>; clocks = <&mux1>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x40000000>; L2_1: l2-cache { next-level-cache = <&cpc>; }; @@ -102,6 +104,7 @@ reg = <2>; clocks = <&mux2>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x20000000>; L2_2: l2-cache { next-level-cache = <&cpc>; }; @@ -111,6 +114,7 @@ reg = <3>; clocks = <&mux3>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x10000000>; L2_3: l2-cache { next-level-cache = <&cpc>; }; diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi index 2415e1f1d3fa..12947ccddf25 100644 --- a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi @@ -281,7 +281,7 @@ }; corenet-cf@18000 { - compatible = "fsl,corenet-cf"; + compatible = "fsl,corenet1-cf", "fsl,corenet-cf"; reg = <0x18000 0x1000>; interrupts = <16 2 1 31>; fsl,ccf-num-csdids = <32>; @@ -297,6 +297,7 @@ interrupts = < 24 2 0 0 16 2 1 30>; + fsl,portid-mapping = <0x00f80000>; pamu0: pamu@0 { reg = <0 0x1000>; diff --git a/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi index 0040b5a5379e..38bde0958672 100644 --- a/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi @@ -83,6 +83,7 @@ reg = <0>; clocks = <&mux0>; next-level-cache = <&L2_0>; + fsl,portid-mapping = <0x80000000>; L2_0: l2-cache { next-level-cache = <&cpc>; }; @@ -92,6 +93,7 @@ reg = <1>; clocks = <&mux1>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x40000000>; L2_1: l2-cache { next-level-cache = <&cpc>; }; @@ -101,6 +103,7 @@ reg = <2>; clocks = <&mux2>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x20000000>; L2_2: l2-cache { next-level-cache = <&cpc>; }; @@ -110,6 +113,7 @@ reg = <3>; clocks = <&mux3>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x10000000>; L2_3: l2-cache { next-level-cache = <&cpc>; }; @@ -119,6 +123,7 @@ reg = <4>; clocks = <&mux4>; next-level-cache = <&L2_4>; + fsl,portid-mapping = <0x08000000>; L2_4: l2-cache { next-level-cache = <&cpc>; }; @@ -128,6 +133,7 @@ reg = <5>; clocks = <&mux5>; next-level-cache = <&L2_5>; + fsl,portid-mapping = <0x04000000>; L2_5: l2-cache { next-level-cache = <&cpc>; }; @@ -137,6 +143,7 @@ reg = <6>; clocks = <&mux6>; next-level-cache = <&L2_6>; + fsl,portid-mapping = <0x02000000>; L2_6: l2-cache { next-level-cache = <&cpc>; }; @@ -146,6 +153,7 @@ reg = <7>; clocks = <&mux7>; next-level-cache = <&L2_7>; + fsl,portid-mapping = <0x01000000>; L2_7: l2-cache { next-level-cache = <&cpc>; }; diff --git a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi index 2985de4ad6be..4c4a2b0436b2 100644 --- a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi @@ -278,7 +278,7 @@ }; corenet-cf@18000 { - compatible = "fsl,corenet-cf"; + compatible = "fsl,corenet1-cf", "fsl,corenet-cf"; reg = <0x18000 0x1000>; interrupts = <16 2 1 31>; fsl,ccf-num-csdids = <32>; @@ -294,6 +294,7 @@ interrupts = < 24 2 0 0 16 2 1 30>; + fsl,portid-mapping = <0x3c000000>; pamu0: pamu@0 { reg = <0 0x1000>; diff --git a/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi index fe1a2e6613b4..1cc61e126e4c 100644 --- a/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi @@ -90,6 +90,7 @@ reg = <0>; clocks = <&mux0>; next-level-cache = <&L2_0>; + fsl,portid-mapping = <0x80000000>; L2_0: l2-cache { next-level-cache = <&cpc>; }; @@ -99,6 +100,7 @@ reg = <1>; clocks = <&mux1>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x40000000>; L2_1: l2-cache { next-level-cache = <&cpc>; }; diff --git a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi index 546a899efe20..67296fdd9698 100644 --- a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi @@ -233,7 +233,7 @@ }; corenet-cf@18000 { - compatible = "fsl,corenet-cf"; + compatible = "fsl,corenet1-cf", "fsl,corenet-cf"; reg = <0x18000 0x1000>; interrupts = <16 2 1 31>; fsl,ccf-num-csdids = <32>; @@ -248,6 +248,7 @@ #size-cells = <1>; interrupts = <24 2 0 0 16 2 1 30>; + fsl,portid-mapping = <0x0f800000>; pamu0: pamu@0 { reg = <0 0x1000>; diff --git a/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi index 3674686687cb..b048a2be05a8 100644 --- a/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi @@ -83,6 +83,7 @@ reg = <0>; clocks = <&mux0>; next-level-cache = <&L2_0>; + fsl,portid-mapping = <0x80000000>; L2_0: l2-cache { next-level-cache = <&cpc>; }; @@ -92,6 +93,7 @@ reg = <1>; clocks = <&mux1>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x40000000>; L2_1: l2-cache { next-level-cache = <&cpc>; }; @@ -101,6 +103,7 @@ reg = <2>; clocks = <&mux2>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x20000000>; L2_2: l2-cache { next-level-cache = <&cpc>; }; @@ -110,6 +113,7 @@ reg = <3>; clocks = <&mux3>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x10000000>; L2_3: l2-cache { next-level-cache = <&cpc>; }; diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi new file mode 100644 index 000000000000..12e597eea3c8 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi @@ -0,0 +1,430 @@ +/* + * T1040 Silicon/SoC Device Tree Source (post include) + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +&ifc { + #address-cells = <2>; + #size-cells = <1>; + compatible = "fsl,ifc", "simple-bus"; + interrupts = <25 2 0 0>; +}; + +&pci0 { + compatible = "fsl,t1040-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie"; + device_type = "pci"; + #size-cells = <2>; + #address-cells = <3>; + bus-range = <0x0 0xff>; + interrupts = <20 2 0 0>; + fsl,iommu-parent = <&pamu0>; + pcie@0 { + reg = <0 0 0 0 0>; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + device_type = "pci"; + interrupts = <20 2 0 0>; + interrupt-map-mask = <0xf800 0 0 7>; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 40 1 0 0 + 0000 0 0 2 &mpic 1 1 0 0 + 0000 0 0 3 &mpic 2 1 0 0 + 0000 0 0 4 &mpic 3 1 0 0 + >; + }; +}; + +&pci1 { + compatible = "fsl,t1040-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie"; + device_type = "pci"; + #size-cells = <2>; + #address-cells = <3>; + bus-range = <0 0xff>; + interrupts = <21 2 0 0>; + fsl,iommu-parent = <&pamu0>; + pcie@0 { + reg = <0 0 0 0 0>; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + device_type = "pci"; + interrupts = <21 2 0 0>; + interrupt-map-mask = <0xf800 0 0 7>; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 41 1 0 0 + 0000 0 0 2 &mpic 5 1 0 0 + 0000 0 0 3 &mpic 6 1 0 0 + 0000 0 0 4 &mpic 7 1 0 0 + >; + }; +}; + +&pci2 { + compatible = "fsl,t1040-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie"; + device_type = "pci"; + #size-cells = <2>; + #address-cells = <3>; + bus-range = <0x0 0xff>; + interrupts = <22 2 0 0>; + fsl,iommu-parent = <&pamu0>; + pcie@0 { + reg = <0 0 0 0 0>; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + device_type = "pci"; + interrupts = <22 2 0 0>; + interrupt-map-mask = <0xf800 0 0 7>; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 42 1 0 0 + 0000 0 0 2 &mpic 9 1 0 0 + 0000 0 0 3 &mpic 10 1 0 0 + 0000 0 0 4 &mpic 11 1 0 0 + >; + }; +}; + +&pci3 { + compatible = "fsl,t1040-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie"; + device_type = "pci"; + #size-cells = <2>; + #address-cells = <3>; + bus-range = <0x0 0xff>; + interrupts = <23 2 0 0>; + fsl,iommu-parent = <&pamu0>; + pcie@0 { + reg = <0 0 0 0 0>; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + device_type = "pci"; + interrupts = <23 2 0 0>; + interrupt-map-mask = <0xf800 0 0 7>; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 43 1 0 0 + 0000 0 0 2 &mpic 0 1 0 0 + 0000 0 0 3 &mpic 4 1 0 0 + 0000 0 0 4 &mpic 8 1 0 0 + >; + }; +}; + +&dcsr { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,dcsr", "simple-bus"; + + dcsr-epu@0 { + compatible = "fsl,t1040-dcsr-epu", "fsl,dcsr-epu"; + interrupts = <52 2 0 0 + 84 2 0 0 + 85 2 0 0>; + reg = <0x0 0x1000>; + }; + dcsr-npc { + compatible = "fsl,t1040-dcsr-cnpc", "fsl,dcsr-cnpc"; + reg = <0x1000 0x1000 0x1002000 0x10000>; + }; + dcsr-nxc@2000 { + compatible = "fsl,dcsr-nxc"; + reg = <0x2000 0x1000>; + }; + dcsr-corenet { + compatible = "fsl,dcsr-corenet"; + reg = <0x8000 0x1000 0x1A000 0x1000>; + }; + dcsr-dpaa@9000 { + compatible = "fsl,t1040-dcsr-dpaa", "fsl,dcsr-dpaa"; + reg = <0x9000 0x1000>; + }; + dcsr-ocn@11000 { + compatible = "fsl,t1040-dcsr-ocn", "fsl,dcsr-ocn"; + reg = <0x11000 0x1000>; + }; + dcsr-ddr@12000 { + compatible = "fsl,dcsr-ddr"; + dev-handle = <&ddr1>; + reg = <0x12000 0x1000>; + }; + dcsr-nal@18000 { + compatible = "fsl,t1040-dcsr-nal", "fsl,dcsr-nal"; + reg = <0x18000 0x1000>; + }; + dcsr-rcpm@22000 { + compatible = "fsl,t1040-dcsr-rcpm", "fsl,dcsr-rcpm"; + reg = <0x22000 0x1000>; + }; + dcsr-snpc@30000 { + compatible = "fsl,t1040-dcsr-snpc", "fsl,dcsr-snpc"; + reg = <0x30000 0x1000 0x1022000 0x10000>; + }; + dcsr-snpc@31000 { + compatible = "fsl,t1040-dcsr-snpc", "fsl,dcsr-snpc"; + reg = <0x31000 0x1000 0x1042000 0x10000>; + }; + dcsr-cpu-sb-proxy@100000 { + compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu0>; + reg = <0x100000 0x1000 0x101000 0x1000>; + }; + dcsr-cpu-sb-proxy@108000 { + compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu1>; + reg = <0x108000 0x1000 0x109000 0x1000>; + }; + dcsr-cpu-sb-proxy@110000 { + compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu2>; + reg = <0x110000 0x1000 0x111000 0x1000>; + }; + dcsr-cpu-sb-proxy@118000 { + compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; + cpu-handle = <&cpu3>; + reg = <0x118000 0x1000 0x119000 0x1000>; + }; +}; + +&soc { + #address-cells = <1>; + #size-cells = <1>; + device_type = "soc"; + compatible = "simple-bus"; + + soc-sram-error { + compatible = "fsl,soc-sram-error"; + interrupts = <16 2 1 29>; + }; + + corenet-law@0 { + compatible = "fsl,corenet-law"; + reg = <0x0 0x1000>; + fsl,num-laws = <16>; + }; + + ddr1: memory-controller@8000 { + compatible = "fsl,qoriq-memory-controller-v5.0", + "fsl,qoriq-memory-controller"; + reg = <0x8000 0x1000>; + interrupts = <16 2 1 23>; + }; + + cpc: l3-cache-controller@10000 { + compatible = "fsl,t1040-l3-cache-controller", "cache"; + reg = <0x10000 0x1000>; + interrupts = <16 2 1 27>; + }; + + corenet-cf@18000 { + compatible = "fsl,corenet2-cf", "fsl,corenet-cf"; + reg = <0x18000 0x1000>; + interrupts = <16 2 1 31>; + fsl,ccf-num-csdids = <32>; + fsl,ccf-num-snoopids = <32>; + }; + + iommu@20000 { + compatible = "fsl,pamu-v1.0", "fsl,pamu"; + reg = <0x20000 0x1000>; + ranges = <0 0x20000 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + interrupts = < + 24 2 0 0 + 16 2 1 30>; + pamu0: pamu@0 { + reg = <0 0x1000>; + fsl,primary-cache-geometry = <128 1>; + fsl,secondary-cache-geometry = <16 2>; + }; + }; + +/include/ "qoriq-mpic.dtsi" + + guts: global-utilities@e0000 { + compatible = "fsl,t1040-device-config", "fsl,qoriq-device-config-2.0"; + reg = <0xe0000 0xe00>; + fsl,has-rstcr; + fsl,liodn-bits = <12>; + }; + + clockgen: global-utilities@e1000 { + compatible = "fsl,t1040-clockgen", "fsl,qoriq-clockgen-2.0"; + ranges = <0x0 0xe1000 0x1000>; + reg = <0xe1000 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + + sysclk: sysclk { + #clock-cells = <0>; + compatible = "fsl,qoriq-sysclk-2.0"; + clock-output-names = "sysclk", "fixed-clock"; + }; + + + pll0: pll0@800 { + #clock-cells = <1>; + reg = <0x800 4>; + compatible = "fsl,qoriq-core-pll-2.0"; + clocks = <&sysclk>; + clock-output-names = "pll0", "pll0-div2", "pll0-div4"; + }; + + pll1: pll1@820 { + #clock-cells = <1>; + reg = <0x820 4>; + compatible = "fsl,qoriq-core-pll-2.0"; + clocks = <&sysclk>; + clock-output-names = "pll1", "pll1-div2", "pll1-div4"; + }; + + mux0: mux0@0 { + #clock-cells = <0>; + reg = <0x0 4>; + compatible = "fsl,qoriq-core-mux-2.0"; + clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, + <&pll1 0>, <&pll1 1>, <&pll1 2>; + clock-names = "pll0", "pll0-div2", "pll1-div4", + "pll1", "pll1-div2", "pll1-div4"; + clock-output-names = "cmux0"; + }; + + mux1: mux1@20 { + #clock-cells = <0>; + reg = <0x20 4>; + compatible = "fsl,qoriq-core-mux-2.0"; + clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, + <&pll1 0>, <&pll1 1>, <&pll1 2>; + clock-names = "pll0", "pll0-div2", "pll1-div4", + "pll1", "pll1-div2", "pll1-div4"; + clock-output-names = "cmux1"; + }; + + mux2: mux2@40 { + #clock-cells = <0>; + reg = <0x40 4>; + compatible = "fsl,qoriq-core-mux-2.0"; + clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, + <&pll1 0>, <&pll1 1>, <&pll1 2>; + clock-names = "pll0", "pll0-div2", "pll1-div4", + "pll1", "pll1-div2", "pll1-div4"; + clock-output-names = "cmux2"; + }; + + mux3: mux3@60 { + #clock-cells = <0>; + reg = <0x60 4>; + compatible = "fsl,qoriq-core-mux-2.0"; + clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>, + <&pll1 0>, <&pll1 1>, <&pll1 2>; + clock-names = "pll0_0", "pll0_1", "pll0_2", + "pll1_0", "pll1_1", "pll1_2"; + clock-output-names = "cmux3"; + }; + }; + + rcpm: global-utilities@e2000 { + compatible = "fsl,t1040-rcpm", "fsl,qoriq-rcpm-2.0"; + reg = <0xe2000 0x1000>; + }; + + sfp: sfp@e8000 { + compatible = "fsl,t1040-sfp"; + reg = <0xe8000 0x1000>; + }; + + serdes: serdes@ea000 { + compatible = "fsl,t1040-serdes"; + reg = <0xea000 0x4000>; + }; + +/include/ "elo3-dma-0.dtsi" +/include/ "elo3-dma-1.dtsi" +/include/ "qoriq-espi-0.dtsi" + spi@110000 { + fsl,espi-num-chipselects = <4>; + }; + +/include/ "qoriq-esdhc-0.dtsi" + sdhc@114000 { + compatible = "fsl,t1040-esdhc", "fsl,esdhc"; + fsl,iommu-parent = <&pamu0>; + fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */ + sdhci,auto-cmd12; + }; +/include/ "qoriq-i2c-0.dtsi" +/include/ "qoriq-i2c-1.dtsi" +/include/ "qoriq-duart-0.dtsi" +/include/ "qoriq-duart-1.dtsi" +/include/ "qoriq-gpio-0.dtsi" +/include/ "qoriq-gpio-1.dtsi" +/include/ "qoriq-gpio-2.dtsi" +/include/ "qoriq-gpio-3.dtsi" +/include/ "qoriq-usb2-mph-0.dtsi" + usb0: usb@210000 { + compatible = "fsl-usb2-mph-v2.4", "fsl-usb2-mph"; + fsl,iommu-parent = <&pamu0>; + fsl,liodn-reg = <&guts 0x520>; /* USB1LIODNR */ + phy_type = "utmi"; + port0; + }; +/include/ "qoriq-usb2-dr-0.dtsi" + usb1: usb@211000 { + compatible = "fsl-usb2-dr-v2.4", "fsl-usb2-dr"; + fsl,iommu-parent = <&pamu0>; + fsl,liodn-reg = <&guts 0x524>; /* USB2LIODNR */ + dr_mode = "host"; + phy_type = "utmi"; + }; + + display@180000 { + compatible = "fsl,t1040-diu", "fsl,diu"; + reg = <0x180000 1000>; + interrupts = <74 2 0 0>; + }; + +/include/ "qoriq-sata2-0.dtsi" + sata@220000 { + fsl,iommu-parent = <&pamu0>; + fsl,liodn-reg = <&guts 0x550>; /* SATA1LIODNR */ + }; +/include/ "qoriq-sata2-1.dtsi" + sata@221000 { + fsl,iommu-parent = <&pamu0>; + fsl,liodn-reg = <&guts 0x554>; /* SATA2LIODNR */ + }; +/include/ "qoriq-sec5.0-0.dtsi" +}; diff --git a/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi new file mode 100644 index 000000000000..319b74f29724 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi @@ -0,0 +1,37 @@ +/* + * T1042 Silicon/SoC Device Tree Source (post include) + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/include/ "t1040si-post.dtsi" + +/* Place holder for ethernet related device tree nodes */ diff --git a/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi new file mode 100644 index 000000000000..bbb7025ca9c2 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi @@ -0,0 +1,104 @@ +/* + * T1040/T1042 Silicon/SoC Device Tree Source (pre include) + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/dts-v1/; + +/include/ "e5500_power_isa.dtsi" + +/ { + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; + + aliases { + ccsr = &soc; + dcsr = &dcsr; + + serial0 = &serial0; + serial1 = &serial1; + serial2 = &serial2; + serial3 = &serial3; + pci0 = &pci0; + pci1 = &pci1; + pci2 = &pci2; + pci3 = &pci3; + usb0 = &usb0; + usb1 = &usb1; + sdhc = &sdhc; + + crypto = &crypto; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: PowerPC,e5500@0 { + device_type = "cpu"; + reg = <0>; + clocks = <&mux0>; + next-level-cache = <&L2_1>; + L2_1: l2-cache { + next-level-cache = <&cpc>; + }; + }; + cpu1: PowerPC,e5500@1 { + device_type = "cpu"; + reg = <1>; + clocks = <&mux1>; + next-level-cache = <&L2_2>; + L2_2: l2-cache { + next-level-cache = <&cpc>; + }; + }; + cpu2: PowerPC,e5500@2 { + device_type = "cpu"; + reg = <2>; + clocks = <&mux2>; + next-level-cache = <&L2_3>; + L2_3: l2-cache { + next-level-cache = <&cpc>; + }; + }; + cpu3: PowerPC,e5500@3 { + device_type = "cpu"; + reg = <3>; + clocks = <&mux3>; + next-level-cache = <&L2_4>; + L2_4: l2-cache { + next-level-cache = <&cpc>; + }; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi index f99d74ff11b4..793669baa13e 100644 --- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi @@ -343,7 +343,7 @@ }; corenet-cf@18000 { - compatible = "fsl,corenet-cf"; + compatible = "fsl,corenet2-cf", "fsl,corenet-cf"; reg = <0x18000 0x1000>; interrupts = <16 2 1 31>; fsl,ccf-num-csdids = <32>; @@ -353,6 +353,7 @@ iommu@20000 { compatible = "fsl,pamu-v1.0", "fsl,pamu"; reg = <0x20000 0x6000>; + fsl,portid-mapping = <0x8000>; interrupts = < 24 2 0 0 16 2 1 30>; diff --git a/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi index 0b8ccc5b4a46..d2f157edbe81 100644 --- a/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi @@ -69,72 +69,84 @@ reg = <0 1>; clocks = <&mux0>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x80000000>; }; cpu1: PowerPC,e6500@2 { device_type = "cpu"; reg = <2 3>; clocks = <&mux0>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x80000000>; }; cpu2: PowerPC,e6500@4 { device_type = "cpu"; reg = <4 5>; clocks = <&mux0>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x80000000>; }; cpu3: PowerPC,e6500@6 { device_type = "cpu"; reg = <6 7>; clocks = <&mux0>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x80000000>; }; cpu4: PowerPC,e6500@8 { device_type = "cpu"; reg = <8 9>; clocks = <&mux1>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x40000000>; }; cpu5: PowerPC,e6500@10 { device_type = "cpu"; reg = <10 11>; clocks = <&mux1>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x40000000>; }; cpu6: PowerPC,e6500@12 { device_type = "cpu"; reg = <12 13>; clocks = <&mux1>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x40000000>; }; cpu7: PowerPC,e6500@14 { device_type = "cpu"; reg = <14 15>; clocks = <&mux1>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x40000000>; }; cpu8: PowerPC,e6500@16 { device_type = "cpu"; reg = <16 17>; clocks = <&mux2>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x20000000>; }; cpu9: PowerPC,e6500@18 { device_type = "cpu"; reg = <18 19>; clocks = <&mux2>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x20000000>; }; cpu10: PowerPC,e6500@20 { device_type = "cpu"; reg = <20 21>; clocks = <&mux2>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x20000000>; }; cpu11: PowerPC,e6500@22 { device_type = "cpu"; reg = <22 23>; clocks = <&mux2>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x20000000>; }; }; }; diff --git a/arch/powerpc/boot/dts/kmcoge4.dts b/arch/powerpc/boot/dts/kmcoge4.dts new file mode 100644 index 000000000000..89b4119f3b19 --- /dev/null +++ b/arch/powerpc/boot/dts/kmcoge4.dts @@ -0,0 +1,152 @@ +/* + * Keymile kmcoge4 Device Tree Source, based on the P2041RDB DTS + * + * (C) Copyright 2014 + * Valentin Longchamp, Keymile AG, valentin.longchamp@keymile.com + * + * Copyright 2011 Freescale Semiconductor Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +/include/ "fsl/p2041si-pre.dtsi" + +/ { + model = "keymile,kmcoge4"; + compatible = "keymile,kmcoge4", "keymile,kmp204x"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; + + memory { + device_type = "memory"; + }; + + dcsr: dcsr@f00000000 { + ranges = <0x00000000 0xf 0x00000000 0x01008000>; + }; + + soc: soc@ffe000000 { + ranges = <0x00000000 0xf 0xfe000000 0x1000000>; + reg = <0xf 0xfe000000 0 0x00001000>; + spi@110000 { + flash@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "spansion,s25fl256s1"; + reg = <0>; + spi-max-frequency = <20000000>; /* input clock */ + }; + + network_clock@1 { + compatible = "zarlink,zl30343"; + reg = <1>; + spi-max-frequency = <8000000>; + }; + + flash@2 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "micron,m25p32"; + reg = <2>; + spi-max-frequency = <15000000>; + }; + }; + + i2c@119000 { + status = "disabled"; + }; + + i2c@119100 { + status = "disabled"; + }; + + usb0: usb@210000 { + status = "disabled"; + }; + + usb1: usb@211000 { + status = "disabled"; + }; + + sata@220000 { + status = "disabled"; + }; + + sata@221000 { + status = "disabled"; + }; + }; + + rio: rapidio@ffe0c0000 { + status = "disabled"; + }; + + lbc: localbus@ffe124000 { + reg = <0xf 0xfe124000 0 0x1000>; + ranges = <0 0 0xf 0xffa00000 0x00040000 /* LB 0 */ + 1 0 0xf 0xfb000000 0x00010000 /* LB 1 */ + 2 0 0xf 0xd0000000 0x10000000 /* LB 2 */ + 3 0 0xf 0xe0000000 0x10000000>; /* LB 3 */ + + nand@0,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,elbc-fcm-nand"; + reg = <0 0 0x40000>; + }; + + board-control@1,0 { + compatible = "keymile,qriox"; + reg = <1 0 0x80>; + }; + + chassis-mgmt@3,0 { + compatible = "keymile,bfticu"; + interrupt-controller; + #interrupt-cells = <2>; + reg = <3 0 0x100>; + interrupt-parent = <&mpic>; + interrupts = <6 1 0 0>; + }; + }; + + pci0: pcie@ffe200000 { + reg = <0xf 0xfe200000 0 0x1000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000 + 0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x20000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; + + pci1: pcie@ffe201000 { + status = "disabled"; + }; + + pci2: pcie@ffe202000 { + reg = <0xf 0xfe202000 0 0x1000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x20000000 + 0x01000000 0 0x00000000 0xf 0xf8010000 0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x20000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; +}; + +/include/ "fsl/p2041si-post.dtsi" diff --git a/arch/powerpc/boot/dts/mpc8308_p1m.dts b/arch/powerpc/boot/dts/mpc8308_p1m.dts index 651e4f55acdb..57f86cdf9f36 100644 --- a/arch/powerpc/boot/dts/mpc8308_p1m.dts +++ b/arch/powerpc/boot/dts/mpc8308_p1m.dts @@ -296,7 +296,7 @@ }; dma@2c000 { - compatible = "fsl,mpc8308-dma", "fsl,mpc5121-dma"; + compatible = "fsl,mpc8308-dma"; reg = <0x2c000 0x1800>; interrupts = <3 0x8 94 0x8>; diff --git a/arch/powerpc/boot/dts/mpc8308rdb.dts b/arch/powerpc/boot/dts/mpc8308rdb.dts index 9ce45f2efd34..d0211f0413c6 100644 --- a/arch/powerpc/boot/dts/mpc8308rdb.dts +++ b/arch/powerpc/boot/dts/mpc8308rdb.dts @@ -265,7 +265,7 @@ }; dma@2c000 { - compatible = "fsl,mpc8308-dma", "fsl,mpc5121-dma"; + compatible = "fsl,mpc8308-dma"; reg = <0x2c000 0x1800>; interrupts = <3 0x8 94 0x8>; diff --git a/arch/powerpc/boot/dts/oca4080.dts b/arch/powerpc/boot/dts/oca4080.dts new file mode 100644 index 000000000000..3d4c751d1608 --- /dev/null +++ b/arch/powerpc/boot/dts/oca4080.dts @@ -0,0 +1,118 @@ +/* + * OCA4080 Device Tree Source + * + * Copyright 2014 Prodrive Technologies B.V. + * + * Based on: + * P4080DS Device Tree Source + * Copyright 2009-2011 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/include/ "fsl/p4080si-pre.dtsi" + +/ { + model = "fsl,OCA4080"; + compatible = "fsl,OCA4080"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; + + memory { + device_type = "memory"; + }; + + dcsr: dcsr@f00000000 { + ranges = <0x00000000 0xf 0x00000000 0x01008000>; + }; + + soc: soc@ffe000000 { + ranges = <0x00000000 0xf 0xfe000000 0x1000000>; + reg = <0xf 0xfe000000 0 0x00001000>; + + i2c@118000 { + status = "disabled"; + }; + + i2c@118100 { + status = "disabled"; + }; + + i2c@119000 { + status = "disabled"; + }; + + i2c@119100 { + status = "disabled"; + }; + + usb0: usb@210000 { + status = "disabled"; + }; + + usb1: usb@211000 { + status = "disabled"; + }; + }; + + rio: rapidio@ffe0c0000 { + reg = <0xf 0xfe0c0000 0 0x11000>; + + port1 { + ranges = <0 0 0xc 0x20000000 0 0x10000000>; + }; + }; + + lbc: localbus@ffe124000 { + reg = <0xf 0xfe124000 0 0x1000>; + ranges = <0 0 0xf 0xef800000 0x800000>; + + flash@0,0 { + compatible = "cfi-flash"; + reg = <0 0 0x00800000>; + bank-width = <2>; + device-width = <2>; + }; + }; + + pci0: pcie@ffe200000 { + status = "disabled"; + }; + + pci1: pcie@ffe201000 { + status = "disabled"; + }; + + pci2: pcie@ffe202000 { + status = "disabled"; + }; +}; + +/include/ "fsl/p4080si-post.dtsi" diff --git a/arch/powerpc/boot/dts/p1023rds.dts b/arch/powerpc/boot/dts/p1023rds.dts deleted file mode 100644 index beb6cb12e59d..000000000000 --- a/arch/powerpc/boot/dts/p1023rds.dts +++ /dev/null @@ -1,219 +0,0 @@ -/* - * P1023 RDS Device Tree Source - * - * Copyright 2010-2011 Freescale Semiconductor Inc. - * - * Author: Roy Zang <tie-fei.zang@freescale.com> - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -/include/ "fsl/p1023si-pre.dtsi" - -/ { - model = "fsl,P1023"; - compatible = "fsl,P1023RDS"; - #address-cells = <2>; - #size-cells = <2>; - interrupt-parent = <&mpic>; - - memory { - device_type = "memory"; - }; - - soc: soc@ff600000 { - ranges = <0x0 0x0 0xff600000 0x200000>; - - i2c@3000 { - rtc@68 { - compatible = "dallas,ds1374"; - reg = <0x68>; - }; - }; - - spi@7000 { - fsl_dataflash@0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "atmel,at45db081d"; - reg = <0>; - spi-max-frequency = <40000000>; /* input clock */ - partition@u-boot { - /* 512KB for u-boot Bootloader Image */ - label = "u-boot-spi"; - reg = <0x00000000 0x00080000>; - read-only; - }; - partition@dtb { - /* 512KB for DTB Image */ - label = "dtb-spi"; - reg = <0x00080000 0x00080000>; - read-only; - }; - }; - }; - - usb@22000 { - dr_mode = "host"; - phy_type = "ulpi"; - }; - }; - - lbc: localbus@ff605000 { - reg = <0 0xff605000 0 0x1000>; - - /* NOR Flash, BCSR */ - ranges = <0x0 0x0 0x0 0xee000000 0x02000000 - 0x1 0x0 0x0 0xe0000000 0x00008000>; - - nor@0,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "cfi-flash"; - reg = <0x0 0x0 0x02000000>; - bank-width = <2>; - device-width = <1>; - partition@0 { - label = "ramdisk"; - reg = <0x00000000 0x01c00000>; - }; - partition@1c00000 { - label = "kernel"; - reg = <0x01c00000 0x002e0000>; - }; - partiton@1ee0000 { - label = "dtb"; - reg = <0x01ee0000 0x00020000>; - }; - partition@1f00000 { - label = "firmware"; - reg = <0x01f00000 0x00080000>; - read-only; - }; - partition@1f80000 { - label = "u-boot"; - reg = <0x01f80000 0x00080000>; - read-only; - }; - }; - - fpga@1,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,p1023rds-fpga"; - reg = <1 0 0x8000>; - ranges = <0 1 0 0x8000>; - - bcsr@20 { - compatible = "fsl,p1023rds-bcsr"; - reg = <0x20 0x20>; - }; - }; - }; - - pci0: pcie@ff60a000 { - reg = <0 0xff60a000 0 0x1000>; - ranges = <0x2000000 0x0 0xc0000000 0 0xc0000000 0x0 0x20000000 - 0x1000000 0x0 0x00000000 0 0xffc20000 0x0 0x10000>; - pcie@0 { - /* IRQ[0:3] are pulled up on board, set to active-low */ - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = < - /* IDSEL 0x0 */ - 0000 0 0 1 &mpic 0 1 0 0 - 0000 0 0 2 &mpic 1 1 0 0 - 0000 0 0 3 &mpic 2 1 0 0 - 0000 0 0 4 &mpic 3 1 0 0 - >; - ranges = <0x2000000 0x0 0xc0000000 - 0x2000000 0x0 0xc0000000 - 0x0 0x20000000 - - 0x1000000 0x0 0x0 - 0x1000000 0x0 0x0 - 0x0 0x100000>; - }; - }; - - board_pci1: pci1: pcie@ff609000 { - reg = <0 0xff609000 0 0x1000>; - ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000 - 0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>; - pcie@0 { - /* - * IRQ[4:6] only for PCIe, set to active-high, - * IRQ[7] is pulled up on board, set to active-low - */ - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = < - /* IDSEL 0x0 */ - 0000 0 0 1 &mpic 4 2 0 0 - 0000 0 0 2 &mpic 5 2 0 0 - 0000 0 0 3 &mpic 6 2 0 0 - 0000 0 0 4 &mpic 7 1 0 0 - >; - ranges = <0x2000000 0x0 0xa0000000 - 0x2000000 0x0 0xa0000000 - 0x0 0x20000000 - - 0x1000000 0x0 0x0 - 0x1000000 0x0 0x0 - 0x0 0x100000>; - }; - }; - - pci2: pcie@ff60b000 { - reg = <0 0xff60b000 0 0x1000>; - ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x20000000 - 0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>; - pcie@0 { - /* - * IRQ[8:10] are pulled up on board, set to active-low - * IRQ[11] only for PCIe, set to active-high, - */ - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = < - /* IDSEL 0x0 */ - 0000 0 0 1 &mpic 8 1 0 0 - 0000 0 0 2 &mpic 9 1 0 0 - 0000 0 0 3 &mpic 10 1 0 0 - 0000 0 0 4 &mpic 11 2 0 0 - >; - ranges = <0x2000000 0x0 0x80000000 - 0x2000000 0x0 0x80000000 - 0x0 0x20000000 - - 0x1000000 0x0 0x0 - 0x1000000 0x0 0x0 - 0x0 0x100000>; - }; - }; -}; - -/include/ "fsl/p1023si-post.dtsi" diff --git a/arch/powerpc/boot/dts/t1040qds.dts b/arch/powerpc/boot/dts/t1040qds.dts new file mode 100644 index 000000000000..973c29c2f56e --- /dev/null +++ b/arch/powerpc/boot/dts/t1040qds.dts @@ -0,0 +1,46 @@ +/* + * T1040QDS Device Tree Source + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/include/ "fsl/t104xsi-pre.dtsi" +/include/ "t104xqds.dtsi" + +/ { + model = "fsl,T1040QDS"; + compatible = "fsl,T1040QDS"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; +}; + +/include/ "fsl/t1040si-post.dtsi" diff --git a/arch/powerpc/boot/dts/t1042qds.dts b/arch/powerpc/boot/dts/t1042qds.dts new file mode 100644 index 000000000000..45bd03752154 --- /dev/null +++ b/arch/powerpc/boot/dts/t1042qds.dts @@ -0,0 +1,46 @@ +/* + * T1042QDS Device Tree Source + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/include/ "fsl/t104xsi-pre.dtsi" +/include/ "t104xqds.dtsi" + +/ { + model = "fsl,T1042QDS"; + compatible = "fsl,T1042QDS"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; +}; + +/include/ "fsl/t1042si-post.dtsi" diff --git a/arch/powerpc/boot/dts/t104xqds.dtsi b/arch/powerpc/boot/dts/t104xqds.dtsi new file mode 100644 index 000000000000..234f4b596c5b --- /dev/null +++ b/arch/powerpc/boot/dts/t104xqds.dtsi @@ -0,0 +1,166 @@ +/* + * T104xQDS Device Tree Source + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/ { + model = "fsl,T1040QDS"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&mpic>; + + ifc: localbus@ffe124000 { + reg = <0xf 0xfe124000 0 0x2000>; + ranges = <0 0 0xf 0xe8000000 0x08000000 + 2 0 0xf 0xff800000 0x00010000 + 3 0 0xf 0xffdf0000 0x00008000>; + + nor@0,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "cfi-flash"; + reg = <0x0 0x0 0x8000000>; + + bank-width = <2>; + device-width = <1>; + }; + + nand@2,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,ifc-nand"; + reg = <0x2 0x0 0x10000>; + }; + + board-control@3,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,fpga-qixis"; + reg = <3 0 0x300>; + }; + }; + + memory { + device_type = "memory"; + }; + + dcsr: dcsr@f00000000 { + ranges = <0x00000000 0xf 0x00000000 0x01072000>; + }; + + soc: soc@ffe000000 { + ranges = <0x00000000 0xf 0xfe000000 0x1000000>; + reg = <0xf 0xfe000000 0 0x00001000>; + + spi@110000 { + flash@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "micron,n25q128a11"; + reg = <0>; + spi-max-frequency = <10000000>; /* input clock */ + }; + }; + + i2c@118000 { + pca9547@77 { + compatible = "philips,pca9547"; + reg = <0x77>; + }; + rtc@68 { + compatible = "dallas,ds3232"; + reg = <0x68>; + interrupts = <0x1 0x1 0 0>; + }; + }; + }; + + pci0: pcie@ffe240000 { + reg = <0xf 0xfe240000 0 0x10000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x10000000 + 0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x10000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; + + pci1: pcie@ffe250000 { + reg = <0xf 0xfe250000 0 0x10000>; + ranges = <0x02000000 0x0 0xe0000000 0xc 0x10000000 0x0 0x10000000 + 0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x10000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; + + pci2: pcie@ffe260000 { + reg = <0xf 0xfe260000 0 0x10000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000 + 0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x10000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; + + pci3: pcie@ffe270000 { + reg = <0xf 0xfe270000 0 0x10000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x30000000 0 0x10000000 + 0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x10000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/t4240emu.dts b/arch/powerpc/boot/dts/t4240emu.dts index ee24ab335598..bc12127a03fb 100644 --- a/arch/powerpc/boot/dts/t4240emu.dts +++ b/arch/powerpc/boot/dts/t4240emu.dts @@ -60,63 +60,75 @@ device_type = "cpu"; reg = <0 1>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x80000000>; }; cpu1: PowerPC,e6500@2 { device_type = "cpu"; reg = <2 3>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x80000000>; }; cpu2: PowerPC,e6500@4 { device_type = "cpu"; reg = <4 5>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x80000000>; }; cpu3: PowerPC,e6500@6 { device_type = "cpu"; reg = <6 7>; next-level-cache = <&L2_1>; + fsl,portid-mapping = <0x80000000>; }; cpu4: PowerPC,e6500@8 { device_type = "cpu"; reg = <8 9>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x40000000>; }; cpu5: PowerPC,e6500@10 { device_type = "cpu"; reg = <10 11>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x40000000>; }; cpu6: PowerPC,e6500@12 { device_type = "cpu"; reg = <12 13>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x40000000>; }; cpu7: PowerPC,e6500@14 { device_type = "cpu"; reg = <14 15>; next-level-cache = <&L2_2>; + fsl,portid-mapping = <0x40000000>; }; cpu8: PowerPC,e6500@16 { device_type = "cpu"; reg = <16 17>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x20000000>; }; cpu9: PowerPC,e6500@18 { device_type = "cpu"; reg = <18 19>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x20000000>; }; cpu10: PowerPC,e6500@20 { device_type = "cpu"; reg = <20 21>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x20000000>; }; cpu11: PowerPC,e6500@22 { device_type = "cpu"; reg = <22 23>; next-level-cache = <&L2_3>; + fsl,portid-mapping = <0x20000000>; }; }; }; @@ -213,7 +225,7 @@ }; corenet-cf@18000 { - compatible = "fsl,corenet-cf"; + compatible = "fsl,corenet2-cf", "fsl,corenet-cf"; reg = <0x18000 0x1000>; interrupts = <16 2 1 31>; fsl,ccf-num-csdids = <32>; @@ -223,6 +235,7 @@ iommu@20000 { compatible = "fsl,pamu-v1.0", "fsl,pamu"; reg = <0x20000 0x6000>; + fsl,portid-mapping = <0x8000>; interrupts = < 24 2 0 0 16 2 1 30>; diff --git a/arch/powerpc/boot/elf_util.c b/arch/powerpc/boot/elf_util.c index 1567a0c0f05c..316552dea4d8 100644 --- a/arch/powerpc/boot/elf_util.c +++ b/arch/powerpc/boot/elf_util.c @@ -26,7 +26,11 @@ int parse_elf64(void *hdr, struct elf_info *info) elf64->e_ident[EI_MAG2] == ELFMAG2 && elf64->e_ident[EI_MAG3] == ELFMAG3 && elf64->e_ident[EI_CLASS] == ELFCLASS64 && +#ifdef __LITTLE_ENDIAN__ + elf64->e_ident[EI_DATA] == ELFDATA2LSB && +#else elf64->e_ident[EI_DATA] == ELFDATA2MSB && +#endif (elf64->e_type == ET_EXEC || elf64->e_type == ET_DYN) && elf64->e_machine == EM_PPC64)) diff --git a/arch/powerpc/boot/of.c b/arch/powerpc/boot/of.c index 62e2f43ec1df..7ca910cb2fc6 100644 --- a/arch/powerpc/boot/of.c +++ b/arch/powerpc/boot/of.c @@ -40,8 +40,8 @@ static void *of_try_claim(unsigned long size) #ifdef DEBUG printf(" trying: 0x%08lx\n\r", claim_base); #endif - addr = (unsigned long)of_claim(claim_base, size, 0); - if ((void *)addr != (void *)-1) + addr = (unsigned long) of_claim(claim_base, size, 0); + if (addr != PROM_ERROR) break; } if (addr == 0) diff --git a/arch/powerpc/boot/of.h b/arch/powerpc/boot/of.h index e4c68f7391c5..c8c1750aba0c 100644 --- a/arch/powerpc/boot/of.h +++ b/arch/powerpc/boot/of.h @@ -1,12 +1,15 @@ #ifndef _PPC_BOOT_OF_H_ #define _PPC_BOOT_OF_H_ +#include "swab.h" + typedef void *phandle; -typedef void *ihandle; +typedef u32 ihandle; void of_init(void *promptr); int of_call_prom(const char *service, int nargs, int nret, ...); -void *of_claim(unsigned long virt, unsigned long size, unsigned long align); +unsigned int of_claim(unsigned long virt, unsigned long size, + unsigned long align); void *of_vmlinux_alloc(unsigned long size); void of_exit(void); void *of_finddevice(const char *name); @@ -18,4 +21,16 @@ int of_setprop(const void *phandle, const char *name, const void *buf, /* Console functions */ void of_console_init(void); +typedef u32 __be32; + +#ifdef __LITTLE_ENDIAN__ +#define cpu_to_be32(x) swab32(x) +#define be32_to_cpu(x) swab32(x) +#else +#define cpu_to_be32(x) (x) +#define be32_to_cpu(x) (x) +#endif + +#define PROM_ERROR (-1u) + #endif /* _PPC_BOOT_OF_H_ */ diff --git a/arch/powerpc/boot/ofconsole.c b/arch/powerpc/boot/ofconsole.c index ce0e02424453..8b754702460a 100644 --- a/arch/powerpc/boot/ofconsole.c +++ b/arch/powerpc/boot/ofconsole.c @@ -18,7 +18,7 @@ #include "of.h" -static void *of_stdout_handle; +static unsigned int of_stdout_handle; static int of_console_open(void) { @@ -27,8 +27,10 @@ static int of_console_open(void) if (((devp = of_finddevice("/chosen")) != NULL) && (of_getprop(devp, "stdout", &of_stdout_handle, sizeof(of_stdout_handle)) - == sizeof(of_stdout_handle))) + == sizeof(of_stdout_handle))) { + of_stdout_handle = be32_to_cpu(of_stdout_handle); return 0; + } return -1; } diff --git a/arch/powerpc/boot/oflib.c b/arch/powerpc/boot/oflib.c index b0ec9cf3eaaf..46c98a47d949 100644 --- a/arch/powerpc/boot/oflib.c +++ b/arch/powerpc/boot/oflib.c @@ -16,74 +16,83 @@ #include "of.h" +typedef u32 prom_arg_t; + +/* The following structure is used to communicate with open firmware. + * All arguments in and out are in big endian format. */ +struct prom_args { + __be32 service; /* Address of service name string. */ + __be32 nargs; /* Number of input arguments. */ + __be32 nret; /* Number of output arguments. */ + __be32 args[10]; /* Input/output arguments. */ +}; + +#ifdef __powerpc64__ +extern int prom(void *); +#else static int (*prom) (void *); +#endif void of_init(void *promptr) { +#ifndef __powerpc64__ prom = (int (*)(void *))promptr; +#endif } +#define ADDR(x) (u32)(unsigned long)(x) + int of_call_prom(const char *service, int nargs, int nret, ...) { int i; - struct prom_args { - const char *service; - int nargs; - int nret; - unsigned int args[12]; - } args; + struct prom_args args; va_list list; - args.service = service; - args.nargs = nargs; - args.nret = nret; + args.service = cpu_to_be32(ADDR(service)); + args.nargs = cpu_to_be32(nargs); + args.nret = cpu_to_be32(nret); va_start(list, nret); for (i = 0; i < nargs; i++) - args.args[i] = va_arg(list, unsigned int); + args.args[i] = cpu_to_be32(va_arg(list, prom_arg_t)); va_end(list); for (i = 0; i < nret; i++) args.args[nargs+i] = 0; if (prom(&args) < 0) - return -1; + return PROM_ERROR; - return (nret > 0)? args.args[nargs]: 0; + return (nret > 0) ? be32_to_cpu(args.args[nargs]) : 0; } static int of_call_prom_ret(const char *service, int nargs, int nret, - unsigned int *rets, ...) + prom_arg_t *rets, ...) { int i; - struct prom_args { - const char *service; - int nargs; - int nret; - unsigned int args[12]; - } args; + struct prom_args args; va_list list; - args.service = service; - args.nargs = nargs; - args.nret = nret; + args.service = cpu_to_be32(ADDR(service)); + args.nargs = cpu_to_be32(nargs); + args.nret = cpu_to_be32(nret); va_start(list, rets); for (i = 0; i < nargs; i++) - args.args[i] = va_arg(list, unsigned int); + args.args[i] = cpu_to_be32(va_arg(list, prom_arg_t)); va_end(list); for (i = 0; i < nret; i++) args.args[nargs+i] = 0; if (prom(&args) < 0) - return -1; + return PROM_ERROR; - if (rets != (void *) 0) + if (rets != NULL) for (i = 1; i < nret; ++i) - rets[i-1] = args.args[nargs+i]; + rets[i-1] = be32_to_cpu(args.args[nargs+i]); - return (nret > 0)? args.args[nargs]: 0; + return (nret > 0) ? be32_to_cpu(args.args[nargs]) : 0; } /* returns true if s2 is a prefix of s1 */ @@ -103,7 +112,7 @@ static int string_match(const char *s1, const char *s2) */ static int need_map = -1; static ihandle chosen_mmu; -static phandle memory; +static ihandle memory; static int check_of_version(void) { @@ -132,10 +141,10 @@ static int check_of_version(void) printf("no mmu\n"); return 0; } - memory = (ihandle) of_call_prom("open", 1, 1, "/memory"); - if (memory == (ihandle) -1) { - memory = (ihandle) of_call_prom("open", 1, 1, "/memory@0"); - if (memory == (ihandle) -1) { + memory = of_call_prom("open", 1, 1, "/memory"); + if (memory == PROM_ERROR) { + memory = of_call_prom("open", 1, 1, "/memory@0"); + if (memory == PROM_ERROR) { printf("no memory node\n"); return 0; } @@ -144,40 +153,41 @@ static int check_of_version(void) return 1; } -void *of_claim(unsigned long virt, unsigned long size, unsigned long align) +unsigned int of_claim(unsigned long virt, unsigned long size, + unsigned long align) { int ret; - unsigned int result; + prom_arg_t result; if (need_map < 0) need_map = check_of_version(); if (align || !need_map) - return (void *) of_call_prom("claim", 3, 1, virt, size, align); + return of_call_prom("claim", 3, 1, virt, size, align); ret = of_call_prom_ret("call-method", 5, 2, &result, "claim", memory, align, size, virt); if (ret != 0 || result == -1) - return (void *) -1; + return -1; ret = of_call_prom_ret("call-method", 5, 2, &result, "claim", chosen_mmu, align, size, virt); /* 0x12 == coherent + read/write */ ret = of_call_prom("call-method", 6, 1, "map", chosen_mmu, 0x12, size, virt, virt); - return (void *) virt; + return virt; } void *of_vmlinux_alloc(unsigned long size) { unsigned long start = (unsigned long)_start, end = (unsigned long)_end; - void *addr; + unsigned long addr; void *p; /* With some older POWER4 firmware we need to claim the area the kernel * will reside in. Newer firmwares don't need this so we just ignore * the return value. */ - addr = of_claim(start, end - start, 0); - printf("Trying to claim from 0x%lx to 0x%lx (0x%lx) got %p\r\n", + addr = (unsigned long) of_claim(start, end - start, 0); + printf("Trying to claim from 0x%lx to 0x%lx (0x%lx) got %lx\r\n", start, end, end - start, addr); p = malloc(size); @@ -197,7 +207,7 @@ void of_exit(void) */ void *of_finddevice(const char *name) { - return (phandle) of_call_prom("finddevice", 1, 1, name); + return (void *) (unsigned long) of_call_prom("finddevice", 1, 1, name); } int of_getprop(const void *phandle, const char *name, void *buf, diff --git a/arch/powerpc/boot/ppc_asm.h b/arch/powerpc/boot/ppc_asm.h index eb0e98be69e0..35ea60c1f070 100644 --- a/arch/powerpc/boot/ppc_asm.h +++ b/arch/powerpc/boot/ppc_asm.h @@ -62,4 +62,16 @@ #define SPRN_TBRL 268 #define SPRN_TBRU 269 +#define FIXUP_ENDIAN \ + tdi 0, 0, 0x48; /* Reverse endian of b . + 8 */ \ + b $+36; /* Skip trampoline if endian is good */ \ + .long 0x05009f42; /* bcl 20,31,$+4 */ \ + .long 0xa602487d; /* mflr r10 */ \ + .long 0x1c004a39; /* addi r10,r10,28 */ \ + .long 0xa600607d; /* mfmsr r11 */ \ + .long 0x01006b69; /* xori r11,r11,1 */ \ + .long 0xa6035a7d; /* mtsrr0 r10 */ \ + .long 0xa6037b7d; /* mtsrr1 r11 */ \ + .long 0x2400004c /* rfid */ + #endif /* _PPC64_PPC_ASM_H */ diff --git a/arch/powerpc/boot/pseries-head.S b/arch/powerpc/boot/pseries-head.S new file mode 100644 index 000000000000..6ef6e02e80f9 --- /dev/null +++ b/arch/powerpc/boot/pseries-head.S @@ -0,0 +1,8 @@ +#include "ppc_asm.h" + + .text + + .globl _zimage_start +_zimage_start: + FIXUP_ENDIAN + b _zimage_start_lib diff --git a/arch/powerpc/boot/stdio.c b/arch/powerpc/boot/stdio.c index 5b57800bbc67..a701261b1781 100644 --- a/arch/powerpc/boot/stdio.c +++ b/arch/powerpc/boot/stdio.c @@ -21,6 +21,18 @@ size_t strnlen(const char * s, size_t count) return sc - s; } +#ifdef __powerpc64__ + +# define do_div(n, base) ({ \ + unsigned int __base = (base); \ + unsigned int __rem; \ + __rem = ((unsigned long long)(n)) % __base; \ + (n) = ((unsigned long long)(n)) / __base; \ + __rem; \ +}) + +#else + extern unsigned int __div64_32(unsigned long long *dividend, unsigned int divisor); @@ -39,6 +51,8 @@ extern unsigned int __div64_32(unsigned long long *dividend, __rem; \ }) +#endif /* __powerpc64__ */ + static int skip_atoi(const char **s) { int i, c; diff --git a/arch/powerpc/boot/swab.h b/arch/powerpc/boot/swab.h new file mode 100644 index 000000000000..d0e1431084ca --- /dev/null +++ b/arch/powerpc/boot/swab.h @@ -0,0 +1,29 @@ +#ifndef _PPC_BOOT_SWAB_H_ +#define _PPC_BOOT_SWAB_H_ + +static inline u16 swab16(u16 x) +{ + return ((x & (u16)0x00ffU) << 8) | + ((x & (u16)0xff00U) >> 8); +} + +static inline u32 swab32(u32 x) +{ + return ((x & (u32)0x000000ffUL) << 24) | + ((x & (u32)0x0000ff00UL) << 8) | + ((x & (u32)0x00ff0000UL) >> 8) | + ((x & (u32)0xff000000UL) >> 24); +} + +static inline u64 swab64(u64 x) +{ + return (u64)((x & (u64)0x00000000000000ffULL) << 56) | + (u64)((x & (u64)0x000000000000ff00ULL) << 40) | + (u64)((x & (u64)0x0000000000ff0000ULL) << 24) | + (u64)((x & (u64)0x00000000ff000000ULL) << 8) | + (u64)((x & (u64)0x000000ff00000000ULL) >> 8) | + (u64)((x & (u64)0x0000ff0000000000ULL) >> 24) | + (u64)((x & (u64)0x00ff000000000000ULL) >> 40) | + (u64)((x & (u64)0xff00000000000000ULL) >> 56); +} +#endif /* _PPC_BOOT_SWAB_H_ */ diff --git a/arch/powerpc/boot/treeboot-akebono.c b/arch/powerpc/boot/treeboot-akebono.c new file mode 100644 index 000000000000..b73174c34fe4 --- /dev/null +++ b/arch/powerpc/boot/treeboot-akebono.c @@ -0,0 +1,163 @@ +/* + * Copyright © 2013 Tony Breeds IBM Corporation + * Copyright © 2013 Alistair Popple IBM Corporation + * + * Based on earlier code: + * Copyright (C) Paul Mackerras 1997. + * + * Matt Porter <mporter@kernel.crashing.org> + * Copyright 2002-2005 MontaVista Software Inc. + * + * Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net> + * Copyright (c) 2003, 2004 Zultys Technologies + * + * Copyright 2007 David Gibson, IBM Corporation. + * Copyright 2010 Ben. Herrenschmidt, IBM Corporation. + * Copyright © 2011 David Kleikamp IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <stdarg.h> +#include <stddef.h> +#include "types.h" +#include "elf.h" +#include "string.h" +#include "stdlib.h" +#include "stdio.h" +#include "page.h" +#include "ops.h" +#include "reg.h" +#include "io.h" +#include "dcr.h" +#include "4xx.h" +#include "44x.h" +#include "libfdt.h" + +BSS_STACK(4096); + +#define SPRN_PIR 0x11E /* Processor Indentification Register */ +#define USERDATA_LEN 256 /* Length of userdata passed in by PIBS */ +#define MAX_RANKS 0x4 +#define DDR3_MR0CF 0x80010011U +#define CCTL0_MCO2 0x8000080FU +#define CCTL0_MCO3 0x80000810U +#define CCTL0_MCO4 0x80000811U +#define CCTL0_MCO5 0x80000812U +#define CCTL0_MCO6 0x80000813U + +static unsigned long long ibm_akebono_memsize; +static long long unsigned mac_addr; + +static unsigned long long ibm_akebono_detect_memsize(void) +{ + u32 reg; + unsigned i; + unsigned long long memsize = 0; + + for (i = 0; i < MAX_RANKS; i++) { + reg = mfdcrx(DDR3_MR0CF + i); + + if (!(reg & 1)) + continue; + + reg &= 0x0000f000; + reg >>= 12; + memsize += (0x800000ULL << reg); + } + + return memsize; +} + +static void ibm_akebono_fixups(void) +{ + void *emac; + u32 reg; + + dt_fixup_memory(0x0ULL, ibm_akebono_memsize); + + /* Fixup the SD timeout frequency */ + mtdcrx(CCTL0_MCO4, 0x1); + + /* Disable SD high-speed mode (which seems to be broken) */ + reg = mfdcrx(CCTL0_MCO2) & ~0x2; + mtdcrx(CCTL0_MCO2, reg); + + /* Set the MAC address */ + emac = finddevice("/plb/opb/ethernet"); + if (emac > 0) { + if (mac_addr) + setprop(emac, "local-mac-address", + ((u8 *) &mac_addr) + 2 , 6); + } +} + +void platform_init(char *userdata) +{ + unsigned long end_of_ram, avail_ram; + u32 pir_reg; + int node, size; + const u32 *timebase; + int len, i, userdata_len; + char *end; + + userdata[USERDATA_LEN - 1] = '\0'; + userdata_len = strlen(userdata); + for (i = 0; i < userdata_len - 15; i++) { + if (strncmp(&userdata[i], "local-mac-addr=", 15) == 0) { + if (i > 0 && userdata[i - 1] != ' ') { + /* We've only found a substring ending + * with local-mac-addr so this isn't + * our mac address. */ + continue; + } + + mac_addr = strtoull(&userdata[i + 15], &end, 16); + + /* Remove the "local-mac-addr=<...>" from the kernel + * command line, including the tailing space if + * present. */ + if (*end == ' ') + end++; + + len = ((int) end) - ((int) &userdata[i]); + memmove(&userdata[i], end, + userdata_len - (len + i) + 1); + break; + } + } + + loader_info.cmdline = userdata; + loader_info.cmdline_len = 256; + + ibm_akebono_memsize = ibm_akebono_detect_memsize(); + if (ibm_akebono_memsize >> 32) + end_of_ram = ~0UL; + else + end_of_ram = ibm_akebono_memsize; + avail_ram = end_of_ram - (unsigned long)_end; + + simple_alloc_init(_end, avail_ram, 128, 64); + platform_ops.fixups = ibm_akebono_fixups; + platform_ops.exit = ibm44x_dbcr_reset; + pir_reg = mfspr(SPRN_PIR); + + /* Make sure FDT blob is sane */ + if (fdt_check_header(_dtb_start) != 0) + fatal("Invalid device tree blob\n"); + + node = fdt_node_offset_by_prop_value(_dtb_start, -1, "device_type", + "cpu", sizeof("cpu")); + if (!node) + fatal("Cannot find cpu node\n"); + timebase = fdt_getprop(_dtb_start, node, "timebase-frequency", &size); + if (timebase && (size == 4)) + timebase_period_ns = 1000000000 / *timebase; + + fdt_set_boot_cpuid_phys(_dtb_start, pir_reg); + fdt_init(_dtb_start); + + serial_console_init(); +} diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S index 6636b1d7821b..243b8497d58b 100644 --- a/arch/powerpc/boot/util.S +++ b/arch/powerpc/boot/util.S @@ -45,7 +45,7 @@ udelay: mfspr r4,SPRN_PVR srwi r4,r4,16 cmpwi 0,r4,1 /* 601 ? */ - bne .udelay_not_601 + bne .Ludelay_not_601 00: li r0,86 /* Instructions / microsecond? */ mtctr r0 10: addi r0,r0,0 /* NOP */ @@ -54,7 +54,7 @@ udelay: bne 00b blr -.udelay_not_601: +.Ludelay_not_601: mulli r4,r3,1000 /* nanoseconds */ /* Change r4 to be the number of ticks using: * (nanoseconds + (timebase_period_ns - 1 )) / timebase_period_ns diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index d27a25518b01..ae0f88ec4a32 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -40,6 +40,7 @@ cacheit= binary= gzip=.gz pie= +format= # cross-compilation prefix CROSS= @@ -136,6 +137,14 @@ if [ -z "$kernel" ]; then kernel=vmlinux fi +elfformat="`${CROSS}objdump -p "$kernel" | grep 'file format' | awk '{print $4}'`" +case "$elfformat" in + elf64-powerpcle) format=elf64lppc ;; + elf64-powerpc) format=elf32ppc ;; + elf32-powerpc) format=elf32ppc ;; +esac + + platformo=$object/"$platform".o lds=$object/zImage.lds ext=strip @@ -152,8 +161,12 @@ of) make_space=n ;; pseries) - platformo="$object/of.o $object/epapr.o" + platformo="$object/pseries-head.o $object/of.o $object/epapr.o" link_address='0x4000000' + if [ "$format" != "elf32ppc" ]; then + link_address= + pie=-pie + fi make_space=n ;; maple) @@ -257,6 +270,9 @@ gamecube|wii) treeboot-currituck) link_address='0x1000000' ;; +treeboot-akebono) + link_address='0x1000000' + ;; treeboot-iss4xx-mpic) platformo="$object/treeboot-iss4xx.o" ;; @@ -379,7 +395,7 @@ if [ "$platform" != "miboot" ]; then if [ -n "$link_address" ] ; then text_start="-Ttext $link_address" fi - ${CROSS}ld -m elf32ppc -T $lds $text_start $pie -o "$ofile" \ + ${CROSS}ld -m $format -T $lds $text_start $pie -o "$ofile" \ $platformo $tmp $object/wrapper.a rm $tmp fi diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S index 2bd8731f1365..861e72109df2 100644 --- a/arch/powerpc/boot/zImage.lds.S +++ b/arch/powerpc/boot/zImage.lds.S @@ -1,4 +1,10 @@ +#include <asm-generic/vmlinux.lds.h> + +#ifdef CONFIG_PPC64_BOOT_WRAPPER +OUTPUT_ARCH(powerpc:common64) +#else OUTPUT_ARCH(powerpc:common) +#endif ENTRY(_zimage_start) EXTERN(_zimage_start) SECTIONS @@ -16,7 +22,9 @@ SECTIONS *(.rodata*) *(.data*) *(.sdata*) +#ifndef CONFIG_PPC64_BOOT_WRAPPER *(.got2) +#endif } .dynsym : { *(.dynsym) } .dynstr : { *(.dynstr) } @@ -27,7 +35,13 @@ SECTIONS } .hash : { *(.hash) } .interp : { *(.interp) } - .rela.dyn : { *(.rela*) } + .rela.dyn : + { +#ifdef CONFIG_PPC64_BOOT_WRAPPER + __rela_dyn_start = .; +#endif + *(.rela*) + } . = ALIGN(8); .kernel:dtb : @@ -53,6 +67,15 @@ SECTIONS _initrd_end = .; } +#ifdef CONFIG_PPC64_BOOT_WRAPPER + .got : + { + __toc_start = .; + *(.got) + *(.toc) + } +#endif + . = ALIGN(4096); .bss : { diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig new file mode 100644 index 000000000000..7e2530cd9d30 --- /dev/null +++ b/arch/powerpc/configs/44x/akebono_defconfig @@ -0,0 +1,148 @@ +CONFIG_44x=y +CONFIG_SMP=y +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_BLK_DEV_INITRD=y +CONFIG_RD_BZIP2=y +CONFIG_RD_LZMA=y +CONFIG_RD_XZ=y +CONFIG_EXPERT=y +CONFIG_KALLSYMS_ALL=y +# CONFIG_SLUB_CPU_PARTIAL is not set +CONFIG_PROFILING=y +CONFIG_OPROFILE=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_POWERNV_MSI is not set +CONFIG_PPC_47x=y +# CONFIG_EBONY is not set +CONFIG_AKEBONO=y +CONFIG_HIGHMEM=y +CONFIG_HZ_100=y +CONFIG_IRQ_ALL_CPUS=y +# CONFIG_COMPACTION is not set +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="" +# CONFIG_SUSPEND is not set +CONFIG_PCI_MSI=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +# CONFIG_IPV6 is not set +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_CONNECTOR=y +CONFIG_MTD=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_JEDECPROBE=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_PROC_DEVICETREE=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=35000 +# CONFIG_SCSI_PROC_FS is not set +CONFIG_BLK_DEV_SD=y +# CONFIG_SCSI_LOWLEVEL is not set +# CONFIG_SATA_PMP is not set +# CONFIG_ATA_SFF is not set +# CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_ADAPTEC is not set +# CONFIG_NET_VENDOR_ALTEON is not set +# CONFIG_NET_VENDOR_AMD is not set +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ATHEROS is not set +# CONFIG_NET_CADENCE is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_BROCADE is not set +# CONFIG_NET_VENDOR_CHELSIO is not set +# CONFIG_NET_VENDOR_CISCO is not set +# CONFIG_NET_VENDOR_DEC is not set +# CONFIG_NET_VENDOR_DLINK is not set +# CONFIG_NET_VENDOR_EMULEX is not set +# CONFIG_NET_VENDOR_EXAR is not set +# CONFIG_NET_VENDOR_HP is not set +CONFIG_IBM_EMAC=y +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MELLANOX is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MYRI is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_NVIDIA is not set +# CONFIG_NET_VENDOR_OKI is not set +# CONFIG_NET_VENDOR_QLOGIC is not set +# CONFIG_NET_VENDOR_REALTEK is not set +# CONFIG_NET_VENDOR_RDC is not set +# CONFIG_NET_VENDOR_SEEQ is not set +# CONFIG_NET_VENDOR_SILAN is not set +# CONFIG_NET_VENDOR_SIS is not set +# CONFIG_NET_VENDOR_SMSC is not set +# CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SUN is not set +# CONFIG_NET_VENDOR_TEHUTI is not set +# CONFIG_NET_VENDOR_TI is not set +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_XILINX is not set +# CONFIG_KEYBOARD_ATKBD is not set +# CONFIG_MOUSE_PS2 is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +CONFIG_SERIAL_8250=y +# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_EXTENDED=y +CONFIG_SERIAL_8250_SHARE_IRQ=y +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +CONFIG_I2C_CHARDEV=y +# CONFIG_HWMON is not set +CONFIG_THERMAL=y +# CONFIG_USB_DEFAULT_PERSIST is not set +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_OHCI_HCD=y +# CONFIG_USB_OHCI_HCD_PCI is not set +CONFIG_USB_STORAGE=y +CONFIG_MMC=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_M41T80=y +CONFIG_EXT2_FS=y +CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y +# CONFIG_DNOTIFY is not set +# CONFIG_INOTIFY_USER is not set +CONFIG_VFAT_FS=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_CRAMFS=y +# CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_NLS_DEFAULT="n" +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_FS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_XMON=y +CONFIG_XMON_DEFAULT=y +CONFIG_PPC_EARLY_DEBUG=y +CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW=0x00010000 +CONFIG_PPC_EARLY_DEBUG_44x_PHYSHIGH=0x33f +CONFIG_CRYPTO_PCBC=y +CONFIG_CRYPTO_MD5=y +CONFIG_CRYPTO_SHA1_PPC=y +CONFIG_CRYPTO_DES=y +# CONFIG_CRYPTO_ANSI_CPRNG is not set +# CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/85xx/kmp204x_defconfig b/arch/powerpc/configs/85xx/kmp204x_defconfig new file mode 100644 index 000000000000..e9a81e5ba273 --- /dev/null +++ b/arch/powerpc/configs/85xx/kmp204x_defconfig @@ -0,0 +1,225 @@ +CONFIG_PPC_85xx=y +CONFIG_SMP=y +CONFIG_NR_CPUS=8 +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_CGROUPS=y +CONFIG_CGROUP_SCHED=y +CONFIG_RELAY=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +CONFIG_SLAB=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_MODVERSIONS=y +# CONFIG_BLK_DEV_BSG is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_MAC_PARTITION=y +CONFIG_CORENET_GENERIC=y +CONFIG_MPIC_MSGR=y +CONFIG_HIGHMEM=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_BINFMT_MISC=m +CONFIG_KEXEC=y +CONFIG_FORCE_MAX_ZONEORDER=13 +CONFIG_PCI=y +CONFIG_PCIEPORTBUS=y +# CONFIG_PCIEASPM is not set +CONFIG_PCI_MSI=y +CONFIG_ADVANCED_OPTIONS=y +CONFIG_LOWMEM_SIZE_BOOL=y +CONFIG_LOWMEM_SIZE=0x20000000 +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_XFRM_SUB_POLICY=y +CONFIG_XFRM_STATISTICS=y +CONFIG_NET_KEY=y +CONFIG_NET_KEY_MIGRATE=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_NET_IPIP=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_INET_AH=y +CONFIG_INET_ESP=y +CONFIG_INET_IPCOMP=y +# CONFIG_INET_LRO is not set +CONFIG_IPV6=y +CONFIG_IP_SCTP=m +CONFIG_TIPC=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_CBQ=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_SCH_HFSC=y +CONFIG_NET_SCH_PRIO=y +CONFIG_NET_SCH_MULTIQ=y +CONFIG_NET_SCH_RED=y +CONFIG_NET_SCH_SFQ=y +CONFIG_NET_SCH_TEQL=y +CONFIG_NET_SCH_TBF=y +CONFIG_NET_SCH_GRED=y +CONFIG_NET_CLS_BASIC=y +CONFIG_NET_CLS_TCINDEX=y +CONFIG_NET_CLS_U32=y +CONFIG_CLS_U32_PERF=y +CONFIG_CLS_U32_MARK=y +CONFIG_NET_CLS_FLOW=y +CONFIG_NET_CLS_CGROUP=y +CONFIG_UEVENT_HELPER_PATH="/sbin/mdev" +CONFIG_DEVTMPFS=y +CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_MTD_M25P80=y +CONFIG_MTD_PHRAM=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_ECC_BCH=y +CONFIG_MTD_NAND_FSL_ELBC=y +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_GLUEBI=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=2 +CONFIG_BLK_DEV_RAM_SIZE=2048 +CONFIG_EEPROM_AT24=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_CHR_DEV_ST=y +CONFIG_BLK_DEV_SR=y +CONFIG_CHR_DEV_SG=y +CONFIG_SCSI_MULTI_LUN=y +CONFIG_SCSI_LOGGING=y +CONFIG_SCSI_SYM53C8XX_2=y +CONFIG_NETDEVICES=y +# CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_ADAPTEC is not set +# CONFIG_NET_VENDOR_ALTEON is not set +# CONFIG_NET_VENDOR_AMD is not set +# CONFIG_NET_VENDOR_ATHEROS is not set +# CONFIG_NET_CADENCE is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_BROCADE is not set +# CONFIG_NET_VENDOR_CHELSIO is not set +# CONFIG_NET_VENDOR_CISCO is not set +# CONFIG_NET_VENDOR_DEC is not set +# CONFIG_NET_VENDOR_DLINK is not set +# CONFIG_NET_VENDOR_EMULEX is not set +# CONFIG_NET_VENDOR_EXAR is not set +CONFIG_FSL_PQ_MDIO=y +CONFIG_FSL_XGMAC_MDIO=y +# CONFIG_NET_VENDOR_HP is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MELLANOX is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROCHIP is not set +# CONFIG_NET_VENDOR_MYRI is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_NVIDIA is not set +# CONFIG_NET_VENDOR_OKI is not set +# CONFIG_NET_PACKET_ENGINE is not set +# CONFIG_NET_VENDOR_QLOGIC is not set +# CONFIG_NET_VENDOR_REALTEK is not set +# CONFIG_NET_VENDOR_RDC is not set +# CONFIG_NET_VENDOR_SEEQ is not set +# CONFIG_NET_VENDOR_SILAN is not set +# CONFIG_NET_VENDOR_SIS is not set +# CONFIG_NET_VENDOR_SMSC is not set +# CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SUN is not set +# CONFIG_NET_VENDOR_TEHUTI is not set +# CONFIG_NET_VENDOR_TI is not set +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_XILINX is not set +CONFIG_MARVELL_PHY=y +CONFIG_VITESSE_PHY=y +CONFIG_FIXED_PHY=y +# CONFIG_WLAN is not set +# CONFIG_INPUT_MOUSEDEV is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +CONFIG_SERIO_LIBPS2=y +# CONFIG_LEGACY_PTYS is not set +CONFIG_PPC_EPAPR_HV_BYTECHAN=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_MANY_PORTS=y +CONFIG_SERIAL_8250_DETECT_IRQ=y +CONFIG_SERIAL_8250_RSA=y +CONFIG_NVRAM=y +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=y +CONFIG_I2C_MUX=y +CONFIG_I2C_MUX_PCA954x=y +CONFIG_I2C_MPC=y +CONFIG_SPI=y +CONFIG_SPI_FSL_SPI=y +CONFIG_SPI_FSL_ESPI=y +CONFIG_SPI_SPIDEV=m +CONFIG_PTP_1588_CLOCK=y +# CONFIG_HWMON is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_EDAC=y +CONFIG_EDAC_MM_EDAC=y +CONFIG_EDAC_MPC85XX=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_DS3232=y +CONFIG_RTC_DRV_CMOS=y +CONFIG_UIO=y +CONFIG_STAGING=y +# CONFIG_NET_VENDOR_SILICOM is not set +CONFIG_CLK_PPC_CORENET=y +CONFIG_EXT2_FS=y +CONFIG_NTFS_FS=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_UBIFS_FS=y +CONFIG_CRAMFS=y +CONFIG_SQUASHFS=y +CONFIG_SQUASHFS_XZ=y +CONFIG_NFS_FS=y +CONFIG_NFS_V4=y +CONFIG_ROOT_NFS=y +CONFIG_NLS_ISO8859_1=y +CONFIG_NLS_UTF8=m +CONFIG_CRC_ITU_T=m +CONFIG_DEBUG_INFO=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_SHIRQ=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_SCHEDSTATS=y +CONFIG_RCU_TRACE=y +CONFIG_UPROBE_EVENT=y +CONFIG_CRYPTO_NULL=y +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_MD4=y +CONFIG_CRYPTO_SHA256=y +CONFIG_CRYPTO_SHA512=y +# CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DEV_FSL_CAAM=y diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig index bbd794deb6eb..c19ff057d0f9 100644 --- a/arch/powerpc/configs/corenet32_smp_defconfig +++ b/arch/powerpc/configs/corenet32_smp_defconfig @@ -72,6 +72,7 @@ CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP_OF=y CONFIG_MTD_M25P80=y diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig index 19f0fbe5ba4b..55765c8cb08f 100644 --- a/arch/powerpc/configs/mpc85xx_defconfig +++ b/arch/powerpc/configs/mpc85xx_defconfig @@ -32,7 +32,6 @@ CONFIG_P1010_RDB=y CONFIG_P1022_DS=y CONFIG_P1022_RDK=y CONFIG_P1023_RDB=y -CONFIG_P1023_RDS=y CONFIG_SOCRATES=y CONFIG_KSI8560=y CONFIG_XES_MPC85xx=y diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig index 062312e1fe1a..5c6ecdc0f70e 100644 --- a/arch/powerpc/configs/mpc85xx_smp_defconfig +++ b/arch/powerpc/configs/mpc85xx_smp_defconfig @@ -35,7 +35,6 @@ CONFIG_P1010_RDB=y CONFIG_P1022_DS=y CONFIG_P1022_RDK=y CONFIG_P1023_RDB=y -CONFIG_P1023_RDS=y CONFIG_SOCRATES=y CONFIG_KSI8560=y CONFIG_XES_MPC85xx=y diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 97e02f985df8..37991e154ef8 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -42,15 +42,47 @@ void __patch_exception(int exc, unsigned long addr); } while (0) #endif +#define OP_RT_RA_MASK 0xffff0000UL +#define LIS_R2 0x3c020000UL +#define ADDIS_R2_R12 0x3c4c0000UL +#define ADDI_R2_R2 0x38420000UL + static inline unsigned long ppc_function_entry(void *func) { -#ifdef CONFIG_PPC64 +#if defined(CONFIG_PPC64) +#if defined(_CALL_ELF) && _CALL_ELF == 2 + u32 *insn = func; + + /* + * A PPC64 ABIv2 function may have a local and a global entry + * point. We need to use the local entry point when patching + * functions, so identify and step over the global entry point + * sequence. + * + * The global entry point sequence is always of the form: + * + * addis r2,r12,XXXX + * addi r2,r2,XXXX + * + * A linker optimisation may convert the addis to lis: + * + * lis r2,XXXX + * addi r2,r2,XXXX + */ + if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) || + ((*insn & OP_RT_RA_MASK) == LIS_R2)) && + ((*(insn+1) & OP_RT_RA_MASK) == ADDI_R2_R2)) + return (unsigned long)(insn + 2); + else + return (unsigned long)func; +#else /* - * On PPC64 the function pointer actually points to the function's - * descriptor. The first entry in the descriptor is the address - * of the function text. + * On PPC64 ABIv1 the function pointer actually points to the + * function's descriptor. The first entry in the descriptor is the + * address of the function text. */ return ((func_descr_t *)func)->entry; +#endif #else return (unsigned long)func; #endif diff --git a/arch/powerpc/include/asm/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h index b6f5a33b8ee2..40014921ffff 100644 --- a/arch/powerpc/include/asm/context_tracking.h +++ b/arch/powerpc/include/asm/context_tracking.h @@ -2,9 +2,9 @@ #define _ASM_POWERPC_CONTEXT_TRACKING_H #ifdef CONFIG_CONTEXT_TRACKING -#define SCHEDULE_USER bl .schedule_user +#define SCHEDULE_USER bl schedule_user #else -#define SCHEDULE_USER bl .schedule +#define SCHEDULE_USER bl schedule #endif #endif diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index ac3eedb9b74a..2bf8e9307be9 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -18,10 +18,12 @@ #ifdef CONFIG_SMP extern int threads_per_core; +extern int threads_per_subcore; extern int threads_shift; extern cpumask_t threads_core_mask; #else #define threads_per_core 1 +#define threads_per_subcore 1 #define threads_shift 0 #define threads_core_mask (CPU_MASK_CPU0) #endif @@ -74,6 +76,11 @@ static inline int cpu_thread_in_core(int cpu) return cpu & (threads_per_core - 1); } +static inline int cpu_thread_in_subcore(int cpu) +{ + return cpu & (threads_per_subcore - 1); +} + static inline int cpu_first_thread_sibling(int cpu) { return cpu & ~(threads_per_core - 1); diff --git a/arch/powerpc/include/asm/dcr-mmio.h b/arch/powerpc/include/asm/dcr-mmio.h index acd491dbd45a..93a68b28e695 100644 --- a/arch/powerpc/include/asm/dcr-mmio.h +++ b/arch/powerpc/include/asm/dcr-mmio.h @@ -51,10 +51,6 @@ static inline void dcr_write_mmio(dcr_host_mmio_t host, out_be32(host.token + ((host.base + dcr_n) * host.stride), value); } -extern u64 of_translate_dcr_address(struct device_node *dev, - unsigned int dcr_n, - unsigned int *stride); - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_DCR_MMIO_H */ diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h index d2516308ed1e..a954e4975049 100644 --- a/arch/powerpc/include/asm/debug.h +++ b/arch/powerpc/include/asm/debug.h @@ -46,7 +46,8 @@ static inline int debugger_break_match(struct pt_regs *regs) { return 0; } static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; } #endif -int set_breakpoint(struct arch_hw_breakpoint *brk); +void set_breakpoint(struct arch_hw_breakpoint *brk); +void __set_breakpoint(struct arch_hw_breakpoint *brk); #ifdef CONFIG_PPC_ADV_DEBUG_REGS extern void do_send_trap(struct pt_regs *regs, unsigned long address, unsigned long error_code, int signal_code, int brkpt); diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index d4dd41fb951b..b76f58c124ca 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -32,6 +32,22 @@ struct device_node; #ifdef CONFIG_EEH +/* EEH subsystem flags */ +#define EEH_ENABLED 0x1 /* EEH enabled */ +#define EEH_FORCE_DISABLED 0x2 /* EEH disabled */ +#define EEH_PROBE_MODE_DEV 0x4 /* From PCI device */ +#define EEH_PROBE_MODE_DEVTREE 0x8 /* From device tree */ + +/* + * Delay for PE reset, all in ms + * + * PCI specification has reset hold time of 100 milliseconds. + * We have 250 milliseconds here. The PCI bus settlement time + * is specified as 1.5 seconds and we have 1.8 seconds. + */ +#define EEH_PE_RST_HOLD_TIME 250 +#define EEH_PE_RST_SETTLE_TIME 1800 + /* * The struct is used to trace PE related EEH functionality. * In theory, there will have one instance of the struct to @@ -53,7 +69,7 @@ struct device_node; #define EEH_PE_ISOLATED (1 << 0) /* Isolated PE */ #define EEH_PE_RECOVERING (1 << 1) /* Recovering PE */ -#define EEH_PE_PHB_DEAD (1 << 2) /* Dead PHB */ +#define EEH_PE_RESET (1 << 2) /* PE reset in progress */ #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ @@ -92,6 +108,7 @@ struct eeh_pe { #define EEH_DEV_NO_HANDLER (1 << 8) /* No error handler */ #define EEH_DEV_SYSFS (1 << 9) /* Sysfs created */ +#define EEH_DEV_REMOVED (1 << 10) /* Removed permanently */ struct eeh_dev { int mode; /* EEH mode */ @@ -99,7 +116,9 @@ struct eeh_dev { int config_addr; /* Config address */ int pe_config_addr; /* PE config address */ u32 config_space[16]; /* Saved PCI config space */ - u8 pcie_cap; /* Saved PCIe capability */ + int pcix_cap; /* Saved PCIx capability */ + int pcie_cap; /* Saved PCIe capability */ + int aer_cap; /* Saved AER capability */ struct eeh_pe *pe; /* Associated PE */ struct list_head list; /* Form link list in the PE */ struct pci_controller *phb; /* Associated PHB */ @@ -171,37 +190,40 @@ struct eeh_ops { int (*restore_config)(struct device_node *dn); }; +extern int eeh_subsystem_flags; extern struct eeh_ops *eeh_ops; -extern bool eeh_subsystem_enabled; extern raw_spinlock_t confirm_error_lock; -extern int eeh_probe_mode; static inline bool eeh_enabled(void) { - return eeh_subsystem_enabled; + if ((eeh_subsystem_flags & EEH_FORCE_DISABLED) || + !(eeh_subsystem_flags & EEH_ENABLED)) + return false; + + return true; } static inline void eeh_set_enable(bool mode) { - eeh_subsystem_enabled = mode; + if (mode) + eeh_subsystem_flags |= EEH_ENABLED; + else + eeh_subsystem_flags &= ~EEH_ENABLED; } -#define EEH_PROBE_MODE_DEV (1<<0) /* From PCI device */ -#define EEH_PROBE_MODE_DEVTREE (1<<1) /* From device tree */ - static inline void eeh_probe_mode_set(int flag) { - eeh_probe_mode = flag; + eeh_subsystem_flags |= flag; } static inline int eeh_probe_mode_devtree(void) { - return (eeh_probe_mode == EEH_PROBE_MODE_DEVTREE); + return (eeh_subsystem_flags & EEH_PROBE_MODE_DEVTREE); } static inline int eeh_probe_mode_dev(void) { - return (eeh_probe_mode == EEH_PROBE_MODE_DEV); + return (eeh_subsystem_flags & EEH_PROBE_MODE_DEV); } static inline void eeh_serialize_lock(unsigned long *flags) diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index 935b5e7a1436..888d8f3f2524 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -90,6 +90,8 @@ typedef elf_vrregset_t elf_fpxregset_t; do { \ if (((ex).e_flags & 0x3) == 2) \ set_thread_flag(TIF_ELF2ABI); \ + else \ + clear_thread_flag(TIF_ELF2ABI); \ if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ set_thread_flag(TIF_32BIT); \ else \ diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h index a563d9afd179..a8b52b61043f 100644 --- a/arch/powerpc/include/asm/exception-64e.h +++ b/arch/powerpc/include/asm/exception-64e.h @@ -174,10 +174,10 @@ exc_##label##_book3e: mtlr r16; #define TLB_MISS_STATS_D(name) \ addi r9,r13,MMSTAT_DSTATS+name; \ - bl .tlb_stat_inc; + bl tlb_stat_inc; #define TLB_MISS_STATS_I(name) \ addi r9,r13,MMSTAT_ISTATS+name; \ - bl .tlb_stat_inc; + bl tlb_stat_inc; #define TLB_MISS_STATS_X(name) \ ld r8,PACA_EXTLB+EX_TLB_ESR(r13); \ cmpdi cr2,r8,-1; \ @@ -185,7 +185,7 @@ exc_##label##_book3e: addi r9,r13,MMSTAT_DSTATS+name; \ b 62f; \ 61: addi r9,r13,MMSTAT_ISTATS+name; \ -62: bl .tlb_stat_inc; +62: bl tlb_stat_inc; #define TLB_MISS_STATS_SAVE_INFO \ std r14,EX_TLB_ESR(r12); /* save ESR */ #define TLB_MISS_STATS_SAVE_INFO_BOLTED \ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index aeaa56cd9b54..8f35cd7d59cc 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -517,7 +517,7 @@ label##_relon_hv: \ #define DISABLE_INTS RECONCILE_IRQ_STATE(r10,r11) #define ADD_NVGPRS \ - bl .save_nvgprs + bl save_nvgprs #define RUNLATCH_ON \ BEGIN_FTR_SECTION \ diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index 169d039ed402..e3661872fbea 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -61,6 +61,7 @@ struct dyn_arch_ftrace { #endif #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__) +#if !defined(_CALL_ELF) || _CALL_ELF != 2 #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) { @@ -72,6 +73,7 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name */ return !strcmp(sym + 4, name + 3); } +#endif #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 && !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_FTRACE */ diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index eb0f4ac75c4c..ac6432d9be46 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -79,7 +79,7 @@ static inline void hw_breakpoint_disable(void) brk.address = 0; brk.type = 0; brk.len = 0; - set_breakpoint(&brk); + __set_breakpoint(&brk); } extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/irqflags.h b/arch/powerpc/include/asm/irqflags.h index f51a5580bfd0..e20eb95429a8 100644 --- a/arch/powerpc/include/asm/irqflags.h +++ b/arch/powerpc/include/asm/irqflags.h @@ -20,9 +20,9 @@ */ #define TRACE_WITH_FRAME_BUFFER(func) \ mflr r0; \ - stdu r1, -32(r1); \ + stdu r1, -STACK_FRAME_OVERHEAD(r1); \ std r0, 16(r1); \ - stdu r1, -32(r1); \ + stdu r1, -STACK_FRAME_OVERHEAD(r1); \ bl func; \ ld r1, 0(r1); \ ld r1, 0(r1); @@ -36,8 +36,8 @@ * have to call a C function so call a wrapper that saves all the * C-clobbered registers. */ -#define TRACE_ENABLE_INTS TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_on) -#define TRACE_DISABLE_INTS TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_off) +#define TRACE_ENABLE_INTS TRACE_WITH_FRAME_BUFFER(trace_hardirqs_on) +#define TRACE_DISABLE_INTS TRACE_WITH_FRAME_BUFFER(trace_hardirqs_off) /* * This is used by assembly code to soft-disable interrupts first and diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 7b6feab6fd26..af15d4d8d604 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -30,6 +30,7 @@ #include <linux/ptrace.h> #include <linux/percpu.h> #include <asm/probes.h> +#include <asm/code-patching.h> #define __ARCH_WANT_KPROBES_INSN_SLOT @@ -56,9 +57,9 @@ typedef ppc_opcode_t kprobe_opcode_t; if ((colon = strchr(name, ':')) != NULL) { \ colon++; \ if (*colon != '\0' && *colon != '.') \ - addr = *(kprobe_opcode_t **)addr; \ + addr = (kprobe_opcode_t *)ppc_function_entry(addr); \ } else if (name[0] != '.') \ - addr = *(kprobe_opcode_t **)addr; \ + addr = (kprobe_opcode_t *)ppc_function_entry(addr); \ } else { \ char dot_name[KSYM_NAME_LEN]; \ dot_name[0] = '.'; \ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 4a7cc453be0b..9c89cdd067a6 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -337,6 +337,10 @@ static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) vcpu->kvm->arch.kvm_ops->fast_vcpu_kick(vcpu); } +extern void kvm_hv_vm_activated(void); +extern void kvm_hv_vm_deactivated(void); +extern bool kvm_hv_mode_active(void); + #else static inline void __init kvm_cma_reserve(void) {} @@ -356,6 +360,9 @@ static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) { kvm_vcpu_kick(vcpu); } + +static inline bool kvm_hv_mode_active(void) { return false; } + #endif #ifdef CONFIG_KVM_XICS diff --git a/arch/powerpc/include/asm/linkage.h b/arch/powerpc/include/asm/linkage.h index b36f650a13ff..e3ad5c72724a 100644 --- a/arch/powerpc/include/asm/linkage.h +++ b/arch/powerpc/include/asm/linkage.h @@ -2,6 +2,7 @@ #define _ASM_POWERPC_LINKAGE_H #ifdef CONFIG_PPC64 +#if !defined(_CALL_ELF) || _CALL_ELF != 2 #define cond_syscall(x) \ asm ("\t.weak " #x "\n\t.set " #x ", sys_ni_syscall\n" \ "\t.weak ." #x "\n\t.set ." #x ", .sys_ni_syscall\n") @@ -9,5 +10,6 @@ asm ("\t.globl " #alias "\n\t.set " #alias ", " #name "\n" \ "\t.globl ." #alias "\n\t.set ." #alias ", ." #name) #endif +#endif #endif /* _ASM_POWERPC_LINKAGE_H */ diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 5b6c03f1058f..f92b0b54e921 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -98,6 +98,9 @@ struct machdep_calls { void (*iommu_save)(void); void (*iommu_restore)(void); #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE + unsigned long (*memory_block_size)(void); +#endif #endif /* CONFIG_PPC64 */ void (*pci_dma_dev_setup)(struct pci_dev *dev); @@ -113,6 +116,8 @@ struct machdep_calls { /* Optional, may be NULL. */ void (*show_cpuinfo)(struct seq_file *m); void (*show_percpuinfo)(struct seq_file *m, int i); + /* Returns the current operating frequency of "cpu" in Hz */ + unsigned long (*get_proc_freq)(unsigned int cpu); void (*init_IRQ)(void); @@ -241,6 +246,9 @@ struct machdep_calls { /* Called during PCI resource reassignment */ resource_size_t (*pcibios_window_alignment)(struct pci_bus *, unsigned long type); + /* Reset the secondary bus of bridge */ + void (*pcibios_reset_secondary_bus)(struct pci_dev *dev); + /* Called to shutdown machine specific hardware not already controlled * by other drivers. */ diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 49fa55bfbac4..dcfcad139bcc 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -35,6 +35,7 @@ struct mod_arch_specific { #ifdef __powerpc64__ unsigned int stubs_section; /* Index of stubs section in module */ unsigned int toc_section; /* What section is the TOC? */ + bool toc_fixed; /* Have we fixed up .TOC.? */ #ifdef CONFIG_DYNAMIC_FTRACE unsigned long toc; unsigned long tramp; @@ -77,6 +78,9 @@ struct mod_arch_specific { # endif /* MODULE */ #endif +bool is_module_trampoline(u32 *insns); +int module_trampoline_target(struct module *mod, u32 *trampoline, + unsigned long *target); struct exception_table_entry; void sort_ex_table(struct exception_table_entry *start, diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 66ad7a74116f..cb15cbb51600 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -154,6 +154,7 @@ extern int opal_enter_rtas(struct rtas_args *args, #define OPAL_LPC_READ 67 #define OPAL_LPC_WRITE 68 #define OPAL_RETURN_CPU 69 +#define OPAL_REINIT_CPUS 70 #define OPAL_ELOG_READ 71 #define OPAL_ELOG_WRITE 72 #define OPAL_ELOG_ACK 73 @@ -509,7 +510,7 @@ enum OpalMemErr_DynErrType { struct OpalMemoryErrorData { enum OpalMemErr_Version version:8; /* 0x00 */ enum OpalMemErrType type:8; /* 0x01 */ - uint16_t flags; /* 0x02 */ + __be16 flags; /* 0x02 */ uint8_t reserved_1[4]; /* 0x04 */ union { @@ -517,15 +518,15 @@ struct OpalMemoryErrorData { struct { enum OpalMemErr_ResilErrType resil_err_type:8; uint8_t reserved_1[7]; - uint64_t physical_address_start; - uint64_t physical_address_end; + __be64 physical_address_start; + __be64 physical_address_end; } resilience; /* Dynamic memory deallocation error info */ struct { enum OpalMemErr_DynErrType dyn_err_type:8; uint8_t reserved_1[7]; - uint64_t physical_address_start; - uint64_t physical_address_end; + __be64 physical_address_start; + __be64 physical_address_end; } dyn_dealloc; } u; }; @@ -725,6 +726,11 @@ struct OpalIoPhb3ErrorData { uint64_t pestB[OPAL_PHB3_NUM_PEST_REGS]; }; +enum { + OPAL_REINIT_CPUS_HILE_BE = (1 << 0), + OPAL_REINIT_CPUS_HILE_LE = (1 << 1), +}; + typedef struct oppanel_line { const char * line; uint64_t line_len; @@ -849,6 +855,7 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe, uint16_t *pci_error_type, uint16_t *severity); int64_t opal_pci_poll(uint64_t phb_id); int64_t opal_return_cpu(void); +int64_t opal_reinit_cpus(uint64_t flags); int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val); int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val); @@ -916,6 +923,7 @@ extern void opal_get_rtc_time(struct rtc_time *tm); extern unsigned long opal_get_boot_time(void); extern void opal_nvram_init(void); extern void opal_flash_init(void); +extern void opal_flash_term_callback(void); extern int opal_elog_init(void); extern void opal_platform_dump_init(void); extern void opal_sys_param_init(void); diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 8e956a0b6e85..bb0bd25f20d0 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -92,7 +92,10 @@ struct paca_struct { struct slb_shadow *slb_shadow_ptr; struct dtl_entry *dispatch_log; struct dtl_entry *dispatch_log_end; +#endif /* CONFIG_PPC_STD_MMU_64 */ + u64 dscr_default; /* per-CPU default DSCR */ +#ifdef CONFIG_PPC_STD_MMU_64 /* * Now, starting in cacheline 2, the exception save areas */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 3ebb188c3ff5..d98c1ecc3266 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -44,6 +44,12 @@ static inline int pte_present(pte_t pte) return pte_val(pte) & (_PAGE_PRESENT | _PAGE_NUMA); } +#define pte_present_nonuma pte_present_nonuma +static inline int pte_present_nonuma(pte_t pte) +{ + return pte_val(pte) & (_PAGE_PRESENT); +} + #define pte_numa pte_numa static inline int pte_numa(pte_t pte) { diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index ed57fa7920c8..db1e2b8eff3c 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -58,6 +58,7 @@ int rtas_write_config(struct pci_dn *, int where, int size, u32 val); int rtas_read_config(struct pci_dn *, int where, int size, u32 *val); void eeh_pe_state_mark(struct eeh_pe *pe, int state); void eeh_pe_state_clear(struct eeh_pe *pe, int state); +void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode); void eeh_sysfs_add_device(struct pci_dev *pdev); void eeh_sysfs_remove_device(struct pci_dev *pdev); diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index cded7c1278ef..9ea266eae33e 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -57,7 +57,7 @@ BEGIN_FW_FTR_SECTION; \ LDX_BE r10,0,r10; /* get log write index */ \ cmpd cr1,r11,r10; \ beq+ cr1,33f; \ - bl .accumulate_stolen_time; \ + bl accumulate_stolen_time; \ ld r12,_MSR(r1); \ andi. r10,r12,MSR_PR; /* Restore cr0 (coming from user) */ \ 33: \ @@ -189,57 +189,53 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #define __STK_REG(i) (112 + ((i)-14)*8) #define STK_REG(i) __STK_REG(__REG_##i) +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define STK_GOT 24 +#define __STK_PARAM(i) (32 + ((i)-3)*8) +#else +#define STK_GOT 40 #define __STK_PARAM(i) (48 + ((i)-3)*8) +#endif #define STK_PARAM(i) __STK_PARAM(__REG_##i) -#define XGLUE(a,b) a##b -#define GLUE(a,b) XGLUE(a,b) +#if defined(_CALL_ELF) && _CALL_ELF == 2 #define _GLOBAL(name) \ .section ".text"; \ .align 2 ; \ + .type name,@function; \ .globl name; \ - .globl GLUE(.,name); \ - .section ".opd","aw"; \ -name: \ - .quad GLUE(.,name); \ - .quad .TOC.@tocbase; \ - .quad 0; \ - .previous; \ - .type GLUE(.,name),@function; \ -GLUE(.,name): +name: -#define _INIT_GLOBAL(name) \ - __REF; \ +#define _GLOBAL_TOC(name) \ + .section ".text"; \ .align 2 ; \ + .type name,@function; \ .globl name; \ - .globl GLUE(.,name); \ - .section ".opd","aw"; \ name: \ - .quad GLUE(.,name); \ - .quad .TOC.@tocbase; \ - .quad 0; \ - .previous; \ - .type GLUE(.,name),@function; \ -GLUE(.,name): +0: addis r2,r12,(.TOC.-0b)@ha; \ + addi r2,r2,(.TOC.-0b)@l; \ + .localentry name,.-name #define _KPROBE(name) \ .section ".kprobes.text","a"; \ .align 2 ; \ + .type name,@function; \ .globl name; \ - .globl GLUE(.,name); \ - .section ".opd","aw"; \ -name: \ - .quad GLUE(.,name); \ - .quad .TOC.@tocbase; \ - .quad 0; \ - .previous; \ - .type GLUE(.,name),@function; \ -GLUE(.,name): +name: + +#define DOTSYM(a) a + +#else + +#define XGLUE(a,b) a##b +#define GLUE(a,b) XGLUE(a,b) -#define _STATIC(name) \ +#define _GLOBAL(name) \ .section ".text"; \ .align 2 ; \ + .globl name; \ + .globl GLUE(.,name); \ .section ".opd","aw"; \ name: \ .quad GLUE(.,name); \ @@ -249,9 +245,13 @@ name: \ .type GLUE(.,name),@function; \ GLUE(.,name): -#define _INIT_STATIC(name) \ - __REF; \ +#define _GLOBAL_TOC(name) _GLOBAL(name) + +#define _KPROBE(name) \ + .section ".kprobes.text","a"; \ .align 2 ; \ + .globl name; \ + .globl GLUE(.,name); \ .section ".opd","aw"; \ name: \ .quad GLUE(.,name); \ @@ -261,6 +261,10 @@ name: \ .type GLUE(.,name),@function; \ GLUE(.,name): +#define DOTSYM(a) GLUE(.,a) + +#endif + #else /* 32-bit */ #define _ENTRY(n) \ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index d660dc36831a..6d59072e13a7 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -449,7 +449,7 @@ extern unsigned long cpuidle_disable; enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; extern int powersave_nap; /* set if nap mode can be used in idle loop */ -extern void power7_nap(void); +extern void power7_nap(int check_irq); extern void power7_sleep(void); extern void flush_instruction_cache(void); extern void hard_reset_now(void); diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index d977b9b78696..74b79f07f041 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -26,6 +26,45 @@ #include <linux/of_irq.h> #include <linux/platform_device.h> +#define OF_DT_BEGIN_NODE 0x1 /* Start of node, full name */ +#define OF_DT_END_NODE 0x2 /* End node */ +#define OF_DT_PROP 0x3 /* Property: name off, size, + * content */ +#define OF_DT_NOP 0x4 /* nop */ +#define OF_DT_END 0x9 + +#define OF_DT_VERSION 0x10 + +/* + * This is what gets passed to the kernel by prom_init or kexec + * + * The dt struct contains the device tree structure, full pathes and + * property contents. The dt strings contain a separate block with just + * the strings for the property names, and is fully page aligned and + * self contained in a page, so that it can be kept around by the kernel, + * each property name appears only once in this page (cheap compression) + * + * the mem_rsvmap contains a map of reserved ranges of physical memory, + * passing it here instead of in the device-tree itself greatly simplifies + * the job of everybody. It's just a list of u64 pairs (base/size) that + * ends when size is 0 + */ +struct boot_param_header { + __be32 magic; /* magic word OF_DT_HEADER */ + __be32 totalsize; /* total size of DT block */ + __be32 off_dt_struct; /* offset to structure */ + __be32 off_dt_strings; /* offset to strings */ + __be32 off_mem_rsvmap; /* offset to memory reserve map */ + __be32 version; /* format version */ + __be32 last_comp_version; /* last compatible version */ + /* version 2 fields below */ + __be32 boot_cpuid_phys; /* Physical CPU id we're booting on */ + /* version 3 fields below */ + __be32 dt_strings_size; /* size of the DT strings block */ + /* version 17 fields below */ + __be32 dt_struct_size; /* size of the DT structure block */ +}; + /* * OF address retreival & translation */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 4852bcf270f3..bffd89d27301 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -215,6 +215,7 @@ #define SPRN_TEXASR 0x82 /* Transaction EXception & Summary */ #define TEXASR_FS __MASK(63-36) /* Transaction Failure Summary */ #define SPRN_TEXASRU 0x83 /* '' '' '' Upper 32 */ +#define TEXASR_FS __MASK(63-36) /* TEXASR Failure Summary */ #define SPRN_TFHAR 0x80 /* Transaction Failure Handler Addr */ #define SPRN_CTRLF 0x088 #define SPRN_CTRLT 0x098 @@ -224,6 +225,7 @@ #define CTRL_TE 0x00c00000 /* thread enable */ #define CTRL_RUNLATCH 0x1 #define SPRN_DAWR 0xB4 +#define SPRN_RPR 0xBA /* Relative Priority Register */ #define SPRN_CIABR 0xBB #define CIABR_PRIV 0x3 #define CIABR_PRIV_USER 1 @@ -272,8 +274,10 @@ #define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */ #define SPRN_IC 0x350 /* Virtual Instruction Count */ #define SPRN_VTB 0x351 /* Virtual Time Base */ +#define SPRN_LDBAR 0x352 /* LD Base Address Register */ #define SPRN_PMICR 0x354 /* Power Management Idle Control Reg */ #define SPRN_PMSR 0x355 /* Power Management Status Reg */ +#define SPRN_PMMAR 0x356 /* Power Management Memory Activity Register */ #define SPRN_PMCR 0x374 /* Power Management Control Register */ /* HFSCR and FSCR bit numbers are the same */ @@ -433,6 +437,12 @@ #define HID0_BTCD (1<<1) /* Branch target cache disable */ #define HID0_NOPDST (1<<1) /* No-op dst, dstt, etc. instr. */ #define HID0_NOPTI (1<<0) /* No-op dcbt and dcbst instr. */ +/* POWER8 HID0 bits */ +#define HID0_POWER8_4LPARMODE __MASK(61) +#define HID0_POWER8_2LPARMODE __MASK(57) +#define HID0_POWER8_1TO2LPAR __MASK(52) +#define HID0_POWER8_1TO4LPAR __MASK(51) +#define HID0_POWER8_DYNLPARDIS __MASK(48) #define SPRN_HID1 0x3F1 /* Hardware Implementation Register 1 */ #ifdef CONFIG_6xx diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 521790330672..a5e930aca804 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -50,6 +50,7 @@ static inline int overlaps_kvm_tmp(unsigned long start, unsigned long end) #endif } +#if !defined(_CALL_ELF) || _CALL_ELF != 2 #undef dereference_function_descriptor static inline void *dereference_function_descriptor(void *ptr) { @@ -60,6 +61,7 @@ static inline void *dereference_function_descriptor(void *ptr) ptr = p; return ptr; } +#endif #endif diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index ff51046b6466..5a6614a7f0b2 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -68,14 +68,6 @@ void generic_mach_cpu_die(void); void generic_set_cpu_dead(unsigned int cpu); void generic_set_cpu_up(unsigned int cpu); int generic_check_cpu_restart(unsigned int cpu); - -extern void inhibit_secondary_onlining(void); -extern void uninhibit_secondary_onlining(void); - -#else /* HOTPLUG_CPU */ -static inline void inhibit_secondary_onlining(void) {} -static inline void uninhibit_secondary_onlining(void) {} - #endif #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index 0dffad6bcc84..e40010abcaf1 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -10,9 +10,7 @@ #define __HAVE_ARCH_STRNCMP #define __HAVE_ARCH_STRCAT #define __HAVE_ARCH_MEMSET -#ifdef __BIG_ENDIAN__ #define __HAVE_ARCH_MEMCPY -#endif #define __HAVE_ARCH_MEMMOVE #define __HAVE_ARCH_MEMCMP #define __HAVE_ARCH_MEMCHR @@ -24,9 +22,7 @@ extern int strcmp(const char *,const char *); extern int strncmp(const char *, const char *, __kernel_size_t); extern char * strcat(char *, const char *); extern void * memset(void *,int,__kernel_size_t); -#ifdef __BIG_ENDIAN__ extern void * memcpy(void *,const void *,__kernel_size_t); -#endif extern void * memmove(void *,const void *,__kernel_size_t); extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index ea4dc3a89c1f..babbeca6850f 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -62,7 +62,7 @@ COMPAT_SYS_SPU(fcntl) SYSCALL(ni_syscall) SYSCALL_SPU(setpgid) SYSCALL(ni_syscall) -SYSX(sys_ni_syscall,sys_olduname, sys_olduname) +SYSX(sys_ni_syscall,sys_olduname,sys_olduname) SYSCALL_SPU(umask) SYSCALL_SPU(chroot) COMPAT_SYS(ustat) @@ -190,7 +190,7 @@ SYSCALL_SPU(getcwd) SYSCALL_SPU(capget) SYSCALL_SPU(capset) COMPAT_SYS(sigaltstack) -COMPAT_SYS_SPU(sendfile) +SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile) SYSCALL(ni_syscall) SYSCALL(ni_syscall) PPC_SYS(vfork) @@ -258,7 +258,7 @@ SYSCALL_SPU(tgkill) COMPAT_SYS_SPU(utimes) COMPAT_SYS_SPU(statfs64) COMPAT_SYS_SPU(fstatfs64) -SYSX(sys_ni_syscall, ppc_fadvise64_64, ppc_fadvise64_64) +SYSX(sys_ni_syscall,ppc_fadvise64_64,ppc_fadvise64_64) PPC_SYS_SPU(rtas) OLDSYS(debug_setcontext) SYSCALL(ni_syscall) @@ -295,7 +295,7 @@ SYSCALL_SPU(mkdirat) SYSCALL_SPU(mknodat) SYSCALL_SPU(fchownat) COMPAT_SYS_SPU(futimesat) -SYSX_SPU(sys_newfstatat, sys_fstatat64, sys_fstatat64) +SYSX_SPU(sys_newfstatat,sys_fstatat64,sys_fstatat64) SYSCALL_SPU(unlinkat) SYSCALL_SPU(renameat) SYSCALL_SPU(linkat) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index c9202151079f..5f1048eaa5b6 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -9,30 +9,13 @@ struct device_node; #ifdef CONFIG_NUMA /* - * Before going off node we want the VM to try and reclaim from the local - * node. It does this if the remote distance is larger than RECLAIM_DISTANCE. - * With the default REMOTE_DISTANCE of 20 and the default RECLAIM_DISTANCE of - * 20, we never reclaim and go off node straight away. - * - * To fix this we choose a smaller value of RECLAIM_DISTANCE. + * If zone_reclaim_mode is enabled, a RECLAIM_DISTANCE of 10 will mean that + * all zones on all nodes will be eligible for zone_reclaim(). */ #define RECLAIM_DISTANCE 10 #include <asm/mmzone.h> -static inline int cpu_to_node(int cpu) -{ - int nid; - - nid = numa_cpu_lookup_table[cpu]; - - /* - * During early boot, the numa-cpu lookup table might not have been - * setup for all CPUs yet. In such cases, default to node 0. - */ - return (nid < 0) ? 0 : nid; -} - #define parent_node(node) (node) #define cpumask_of_node(node) ((node) == -1 ? \ diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 9b892bbd9d84..5ce5552ab9f5 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -29,7 +29,6 @@ #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_UTIME diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild index 48be855ef37b..7a3f795ac218 100644 --- a/arch/powerpc/include/uapi/asm/Kbuild +++ b/arch/powerpc/include/uapi/asm/Kbuild @@ -15,7 +15,6 @@ header-y += ioctls.h header-y += ipcbuf.h header-y += kvm.h header-y += kvm_para.h -header-y += linkage.h header-y += mman.h header-y += msgbuf.h header-y += nvram.h diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 7e39c9146a71..59dad113897b 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -291,9 +291,17 @@ do { \ #define R_PPC64_DTPREL16_HIGHERA 104 /* half16 (sym+add)@dtprel@highera */ #define R_PPC64_DTPREL16_HIGHEST 105 /* half16 (sym+add)@dtprel@highest */ #define R_PPC64_DTPREL16_HIGHESTA 106 /* half16 (sym+add)@dtprel@highesta */ +#define R_PPC64_TLSGD 107 +#define R_PPC64_TLSLD 108 +#define R_PPC64_TOCSAVE 109 + +#define R_PPC64_REL16 249 +#define R_PPC64_REL16_LO 250 +#define R_PPC64_REL16_HI 251 +#define R_PPC64_REL16_HA 252 /* Keep this the last entry. */ -#define R_PPC64_NUM 107 +#define R_PPC64_NUM 253 /* There's actually a third entry here, but it's unused */ struct ppc64_opd_entry diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index fcc9a89a4695..fab19ec25597 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -2,6 +2,7 @@ # Makefile for the linux kernel. # +CFLAGS_prom.o = -I$(src)/../../../scripts/dtc/libfdt CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 93e1465c8496..f5995a912213 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -248,6 +248,7 @@ int main(void) #endif DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); + DEFINE(PACA_DSCR, offsetof(struct paca_struct, dscr_default)); DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime)); DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user)); DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time)); diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index cc2d8962e090..4f1393d20079 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -94,12 +94,12 @@ _GLOBAL(setup_altivec_idle) _GLOBAL(__setup_cpu_e6500) mflr r6 #ifdef CONFIG_PPC64 - bl .setup_altivec_ivors + bl setup_altivec_ivors /* Touch IVOR42 only if the CPU supports E.HV category */ mfspr r10,SPRN_MMUCFG rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f - bl .setup_lrat_ivor + bl setup_lrat_ivor 1: #endif bl setup_pw20_idle @@ -164,15 +164,15 @@ _GLOBAL(__setup_cpu_e5500) #ifdef CONFIG_PPC_BOOK3E_64 _GLOBAL(__restore_cpu_e6500) mflr r5 - bl .setup_altivec_ivors + bl setup_altivec_ivors /* Touch IVOR42 only if the CPU supports E.HV category */ mfspr r10,SPRN_MMUCFG rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f - bl .setup_lrat_ivor + bl setup_lrat_ivor 1: - bl .setup_pw20_idle - bl .setup_altivec_idle + bl setup_pw20_idle + bl setup_altivec_idle bl __restore_cpu_e5500 mtlr r5 blr @@ -181,9 +181,9 @@ _GLOBAL(__restore_cpu_e5500) mflr r4 bl __e500_icache_setup bl __e500_dcache_setup - bl .__setup_base_ivors - bl .setup_perfmon_ivor - bl .setup_doorbell_ivors + bl __setup_base_ivors + bl setup_perfmon_ivor + bl setup_doorbell_ivors /* * We only want to touch IVOR38-41 if we're running on hardware * that supports category E.HV. The architectural way to determine @@ -192,7 +192,7 @@ _GLOBAL(__restore_cpu_e5500) mfspr r10,SPRN_MMUCFG rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f - bl .setup_ehv_ivors + bl setup_ehv_ivors 1: mtlr r4 blr @@ -201,9 +201,9 @@ _GLOBAL(__setup_cpu_e5500) mflr r5 bl __e500_icache_setup bl __e500_dcache_setup - bl .__setup_base_ivors - bl .setup_perfmon_ivor - bl .setup_doorbell_ivors + bl __setup_base_ivors + bl setup_perfmon_ivor + bl setup_doorbell_ivors /* * We only want to touch IVOR38-41 if we're running on hardware * that supports category E.HV. The architectural way to determine @@ -212,7 +212,7 @@ _GLOBAL(__setup_cpu_e5500) mfspr r10,SPRN_MMUCFG rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f - bl .setup_ehv_ivors + bl setup_ehv_ivors b 2f 1: ld r10,CPU_SPEC_FEATURES(r4) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index e7b76a6bf150..7051ea3101b9 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -22,6 +22,7 @@ */ #include <linux/delay.h> +#include <linux/debugfs.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/list.h> @@ -35,6 +36,7 @@ #include <linux/of.h> #include <linux/atomic.h> +#include <asm/debug.h> #include <asm/eeh.h> #include <asm/eeh_event.h> #include <asm/io.h> @@ -87,22 +89,21 @@ /* Time to wait for a PCI slot to report status, in milliseconds */ #define PCI_BUS_RESET_WAIT_MSEC (5*60*1000) -/* Platform dependent EEH operations */ -struct eeh_ops *eeh_ops = NULL; - -bool eeh_subsystem_enabled = false; -EXPORT_SYMBOL(eeh_subsystem_enabled); - /* - * EEH probe mode support. The intention is to support multiple - * platforms for EEH. Some platforms like pSeries do PCI emunation - * based on device tree. However, other platforms like powernv probe - * PCI devices from hardware. The flag is used to distinguish that. - * In addition, struct eeh_ops::probe would be invoked for particular - * OF node or PCI device so that the corresponding PE would be created - * there. + * EEH probe mode support, which is part of the flags, + * is to support multiple platforms for EEH. Some platforms + * like pSeries do PCI emunation based on device tree. + * However, other platforms like powernv probe PCI devices + * from hardware. The flag is used to distinguish that. + * In addition, struct eeh_ops::probe would be invoked for + * particular OF node or PCI device so that the corresponding + * PE would be created there. */ -int eeh_probe_mode; +int eeh_subsystem_flags; +EXPORT_SYMBOL(eeh_subsystem_flags); + +/* Platform dependent EEH operations */ +struct eeh_ops *eeh_ops = NULL; /* Lock to avoid races due to multiple reports of an error */ DEFINE_RAW_SPINLOCK(confirm_error_lock); @@ -133,6 +134,15 @@ static struct eeh_stats eeh_stats; #define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE) +static int __init eeh_setup(char *str) +{ + if (!strcmp(str, "off")) + eeh_subsystem_flags |= EEH_FORCE_DISABLED; + + return 1; +} +__setup("eeh=", eeh_setup); + /** * eeh_gather_pci_data - Copy assorted PCI config space registers to buff * @edev: device to report data for @@ -145,73 +155,67 @@ static struct eeh_stats eeh_stats; static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) { struct device_node *dn = eeh_dev_to_of_node(edev); - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); u32 cfg; int cap, i; int n = 0; n += scnprintf(buf+n, len-n, "%s\n", dn->full_name); - printk(KERN_WARNING "EEH: of node=%s\n", dn->full_name); + pr_warn("EEH: of node=%s\n", dn->full_name); eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg); n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg); - printk(KERN_WARNING "EEH: PCI device/vendor: %08x\n", cfg); + pr_warn("EEH: PCI device/vendor: %08x\n", cfg); eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg); n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI cmd/status register: %08x\n", cfg); - - if (!dev) { - printk(KERN_WARNING "EEH: no PCI device for this of node\n"); - return n; - } + pr_warn("EEH: PCI cmd/status register: %08x\n", cfg); /* Gather bridge-specific registers */ - if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) { + if (edev->mode & EEH_DEV_BRIDGE) { eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg); n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg); - printk(KERN_WARNING "EEH: Bridge secondary status: %04x\n", cfg); + pr_warn("EEH: Bridge secondary status: %04x\n", cfg); eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg); n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg); - printk(KERN_WARNING "EEH: Bridge control: %04x\n", cfg); + pr_warn("EEH: Bridge control: %04x\n", cfg); } /* Dump out the PCI-X command and status regs */ - cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); + cap = edev->pcix_cap; if (cap) { eeh_ops->read_config(dn, cap, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI-X cmd: %08x\n", cfg); + pr_warn("EEH: PCI-X cmd: %08x\n", cfg); eeh_ops->read_config(dn, cap+4, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI-X status: %08x\n", cfg); + pr_warn("EEH: PCI-X status: %08x\n", cfg); } - /* If PCI-E capable, dump PCI-E cap 10, and the AER */ - if (pci_is_pcie(dev)) { + /* If PCI-E capable, dump PCI-E cap 10 */ + cap = edev->pcie_cap; + if (cap) { n += scnprintf(buf+n, len-n, "pci-e cap10:\n"); - printk(KERN_WARNING - "EEH: PCI-E capabilities and status follow:\n"); + pr_warn("EEH: PCI-E capabilities and status follow:\n"); for (i=0; i<=8; i++) { - eeh_ops->read_config(dn, dev->pcie_cap+4*i, 4, &cfg); + eeh_ops->read_config(dn, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - printk(KERN_WARNING "EEH: PCI-E %02x: %08x\n", i, cfg); + pr_warn("EEH: PCI-E %02x: %08x\n", i, cfg); } + } - cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); - if (cap) { - n += scnprintf(buf+n, len-n, "pci-e AER:\n"); - printk(KERN_WARNING - "EEH: PCI-E AER capability register set follows:\n"); - - for (i=0; i<14; i++) { - eeh_ops->read_config(dn, cap+4*i, 4, &cfg); - n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - printk(KERN_WARNING "EEH: PCI-E AER %02x: %08x\n", i, cfg); - } + /* If AER capable, dump it */ + cap = edev->aer_cap; + if (cap) { + n += scnprintf(buf+n, len-n, "pci-e AER:\n"); + pr_warn("EEH: PCI-E AER capability register set follows:\n"); + + for (i=0; i<14; i++) { + eeh_ops->read_config(dn, cap+4*i, 4, &cfg); + n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); + pr_warn("EEH: PCI-E AER %02x: %08x\n", i, cfg); } } @@ -232,21 +236,19 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity) { size_t loglen = 0; struct eeh_dev *edev, *tmp; - bool valid_cfg_log = true; /* * When the PHB is fenced or dead, it's pointless to collect * the data from PCI config space because it should return * 0xFF's. For ER, we still retrieve the data from the PCI * config space. + * + * For pHyp, we have to enable IO for log retrieval. Otherwise, + * 0xFF's is always returned from PCI config space. */ - if (eeh_probe_mode_dev() && - (pe->type & EEH_PE_PHB) && - (pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD))) - valid_cfg_log = false; - - if (valid_cfg_log) { - eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); + if (!(pe->type & EEH_PE_PHB)) { + if (eeh_probe_mode_devtree()) + eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); @@ -309,7 +311,7 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) /* If the PHB has been in problematic state */ eeh_serialize_lock(&flags); - if (phb_pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)) { + if (phb_pe->state & EEH_PE_ISOLATED) { ret = 0; goto out; } @@ -515,16 +517,42 @@ EXPORT_SYMBOL(eeh_check_failure); */ int eeh_pci_enable(struct eeh_pe *pe, int function) { - int rc; + int rc, flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); + + /* + * pHyp doesn't allow to enable IO or DMA on unfrozen PE. + * Also, it's pointless to enable them on unfrozen PE. So + * we have the check here. + */ + if (function == EEH_OPT_THAW_MMIO || + function == EEH_OPT_THAW_DMA) { + rc = eeh_ops->get_state(pe, NULL); + if (rc < 0) + return rc; + + /* Needn't to enable or already enabled */ + if ((rc == EEH_STATE_NOT_SUPPORT) || + ((rc & flags) == flags)) + return 0; + } rc = eeh_ops->set_option(pe, function); if (rc) - pr_warning("%s: Unexpected state change %d on PHB#%d-PE#%x, err=%d\n", - __func__, function, pe->phb->global_number, pe->addr, rc); + pr_warn("%s: Unexpected state change %d on " + "PHB#%d-PE#%x, err=%d\n", + __func__, function, pe->phb->global_number, + pe->addr, rc); rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if (rc > 0 && (rc & EEH_STATE_MMIO_ENABLED) && - (function == EEH_OPT_THAW_MMIO)) + if (rc <= 0) + return rc; + + if ((function == EEH_OPT_THAW_MMIO) && + (rc & EEH_STATE_MMIO_ENABLED)) + return 0; + + if ((function == EEH_OPT_THAW_DMA) && + (rc & EEH_STATE_DMA_ENABLED)) return 0; return rc; @@ -612,26 +640,7 @@ static void eeh_reset_pe_once(struct eeh_pe *pe) else eeh_ops->reset(pe, EEH_RESET_HOT); - /* The PCI bus requires that the reset be held high for at least - * a 100 milliseconds. We wait a bit longer 'just in case'. - */ -#define PCI_BUS_RST_HOLD_TIME_MSEC 250 - msleep(PCI_BUS_RST_HOLD_TIME_MSEC); - - /* We might get hit with another EEH freeze as soon as the - * pci slot reset line is dropped. Make sure we don't miss - * these, and clear the flag now. - */ - eeh_pe_state_clear(pe, EEH_PE_ISOLATED); - eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); - - /* After a PCI slot has been reset, the PCI Express spec requires - * a 1.5 second idle time for the bus to stabilize, before starting - * up traffic. - */ -#define PCI_BUS_SETTLE_TIME_MSEC 1800 - msleep(PCI_BUS_SETTLE_TIME_MSEC); } /** @@ -651,6 +660,10 @@ int eeh_reset_pe(struct eeh_pe *pe) for (i=0; i<3; i++) { eeh_reset_pe_once(pe); + /* + * EEH_PE_ISOLATED is expected to be removed after + * BAR restore. + */ rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); if ((rc & flags) == flags) return 0; @@ -826,8 +839,8 @@ int eeh_init(void) &hose_list, list_node) pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL); } else { - pr_warning("%s: Invalid probe mode %d\n", - __func__, eeh_probe_mode); + pr_warn("%s: Invalid probe mode %x", + __func__, eeh_subsystem_flags); return -EINVAL; } @@ -1102,10 +1115,45 @@ static const struct file_operations proc_eeh_operations = { .release = single_release, }; +#ifdef CONFIG_DEBUG_FS +static int eeh_enable_dbgfs_set(void *data, u64 val) +{ + if (val) + eeh_subsystem_flags &= ~EEH_FORCE_DISABLED; + else + eeh_subsystem_flags |= EEH_FORCE_DISABLED; + + /* Notify the backend */ + if (eeh_ops->post_init) + eeh_ops->post_init(); + + return 0; +} + +static int eeh_enable_dbgfs_get(void *data, u64 *val) +{ + if (eeh_enabled()) + *val = 0x1ul; + else + *val = 0x0ul; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get, + eeh_enable_dbgfs_set, "0x%llx\n"); +#endif + static int __init eeh_init_proc(void) { - if (machine_is(pseries) || machine_is(powernv)) + if (machine_is(pseries) || machine_is(powernv)) { proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations); +#ifdef CONFIG_DEBUG_FS + debugfs_create_file("eeh_enable", 0600, + powerpc_debugfs_root, NULL, + &eeh_enable_dbgfs_ops); +#endif + } + return 0; } __initcall(eeh_init_proc); diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index bb61ca58ca6d..7100a5b96e70 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -171,6 +171,15 @@ static void eeh_enable_irq(struct pci_dev *dev) } } +static bool eeh_dev_removed(struct eeh_dev *edev) +{ + /* EEH device removed ? */ + if (!edev || (edev->mode & EEH_DEV_REMOVED)) + return true; + + return false; +} + /** * eeh_report_error - Report pci error to each device driver * @data: eeh device @@ -187,10 +196,8 @@ static void *eeh_report_error(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - /* We might not have the associated PCI device, - * then we should continue for next one. - */ - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_frozen; driver = eeh_pcid_get(dev); @@ -230,6 +237,9 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; + if (!dev || eeh_dev_removed(edev)) + return NULL; + driver = eeh_pcid_get(dev); if (!driver) return NULL; @@ -267,7 +277,8 @@ static void *eeh_report_reset(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_normal; driver = eeh_pcid_get(dev); @@ -307,7 +318,8 @@ static void *eeh_report_resume(void *data, void *userdata) struct pci_dev *dev = eeh_dev_to_pci_dev(edev); struct pci_driver *driver; - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_normal; driver = eeh_pcid_get(dev); @@ -343,7 +355,8 @@ static void *eeh_report_failure(void *data, void *userdata) struct pci_dev *dev = eeh_dev_to_pci_dev(edev); struct pci_driver *driver; - if (!dev) return NULL; + if (!dev || eeh_dev_removed(edev)) + return NULL; dev->error_state = pci_channel_io_perm_failure; driver = eeh_pcid_get(dev); @@ -380,6 +393,16 @@ static void *eeh_rmv_device(void *data, void *userdata) if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)) return NULL; + /* + * We rely on count-based pcibios_release_device() to + * detach permanently offlined PEs. Unfortunately, that's + * not reliable enough. We might have the permanently + * offlined PEs attached, but we needn't take care of + * them and their child devices. + */ + if (eeh_dev_removed(edev)) + return NULL; + driver = eeh_pcid_get(dev); if (driver) { eeh_pcid_put(dev); @@ -417,6 +440,36 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) return NULL; } +/* + * Explicitly clear PE's frozen state for PowerNV where + * we have frozen PE until BAR restore is completed. It's + * harmless to clear it for pSeries. To be consistent with + * PE reset (for 3 times), we try to clear the frozen state + * for 3 times as well. + */ +static int eeh_clear_pe_frozen_state(struct eeh_pe *pe) +{ + int i, rc; + + for (i = 0; i < 3; i++) { + rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); + if (rc) + continue; + rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA); + if (!rc) + break; + } + + /* The PE has been isolated, clear it */ + if (rc) + pr_warn("%s: Can't clear frozen PHB#%x-PE#%x (%d)\n", + __func__, pe->phb->global_number, pe->addr, rc); + else + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); + + return rc; +} + /** * eeh_reset_device - Perform actual reset of a pci slot * @pe: EEH PE @@ -451,19 +504,33 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed); } - /* Reset the pci controller. (Asserts RST#; resets config space). + /* + * Reset the pci controller. (Asserts RST#; resets config space). * Reconfigure bridges and devices. Don't try to bring the system * up if the reset failed for some reason. + * + * During the reset, it's very dangerous to have uncontrolled PCI + * config accesses. So we prefer to block them. However, controlled + * PCI config accesses initiated from EEH itself are allowed. */ + eeh_pe_state_mark(pe, EEH_PE_RESET); rc = eeh_reset_pe(pe); - if (rc) + if (rc) { + eeh_pe_state_clear(pe, EEH_PE_RESET); return rc; + } pci_lock_rescan_remove(); /* Restore PE */ eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); + eeh_pe_state_clear(pe, EEH_PE_RESET); + + /* Clear frozen state */ + rc = eeh_clear_pe_frozen_state(pe); + if (rc) + return rc; /* Give the system 5 seconds to finish running the user-space * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, @@ -573,7 +640,6 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) result = PCI_ERS_RESULT_NEED_RESET; } else { pr_info("EEH: Notify device drivers to resume I/O\n"); - result = PCI_ERS_RESULT_NONE; eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result); } } @@ -585,10 +651,17 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) if (rc < 0) goto hard_fail; - if (rc) + if (rc) { result = PCI_ERS_RESULT_NEED_RESET; - else + } else { + /* + * We didn't do PE reset for the case. The PE + * is still in frozen state. Clear it before + * resuming the PE. + */ + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); result = PCI_ERS_RESULT_RECOVERED; + } } /* If any device has a hard failure, then shut off everything. */ @@ -650,8 +723,17 @@ perm_error: /* Notify all devices that they're about to go down. */ eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); - /* Shut down the device drivers for good. */ + /* Mark the PE to be removed permanently */ + pe->freeze_count = EEH_MAX_ALLOWED_FREEZES + 1; + + /* + * Shut down the device drivers for good. We mark + * all removed devices correctly to avoid access + * the their PCI config any more. + */ if (frozen_bus) { + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + pci_lock_rescan_remove(); pcibios_remove_pci_devices(frozen_bus); pci_unlock_rescan_remove(); @@ -682,8 +764,7 @@ static void eeh_handle_special_event(void) phb_pe = eeh_phb_pe_get(hose); if (!phb_pe) continue; - eeh_pe_state_mark(phb_pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED); } eeh_serialize_unlock(flags); @@ -699,8 +780,7 @@ static void eeh_handle_special_event(void) eeh_remove_event(pe); if (rc == EEH_NEXT_ERR_DEAD_PHB) - eeh_pe_state_mark(pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); else eeh_pe_state_mark(pe, EEH_PE_ISOLATED | EEH_PE_RECOVERING); @@ -724,12 +804,14 @@ static void eeh_handle_special_event(void) if (rc == EEH_NEXT_ERR_FROZEN_PE || rc == EEH_NEXT_ERR_FENCED_PHB) { eeh_handle_normal_event(pe); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING); } else { pci_lock_rescan_remove(); list_for_each_entry(hose, &hose_list, list_node) { phb_pe = eeh_phb_pe_get(hose); if (!phb_pe || - !(phb_pe->state & EEH_PE_PHB_DEAD)) + !(phb_pe->state & EEH_PE_ISOLATED) || + (phb_pe->state & EEH_PE_RECOVERING)) continue; /* Notify all devices to be down */ diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index f0c353fa655a..995c2a284630 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -503,13 +503,17 @@ static void *__eeh_pe_state_mark(void *data, void *flag) struct eeh_dev *edev, *tmp; struct pci_dev *pdev; - /* - * Mark the PE with the indicated state. Also, - * the associated PCI device will be put into - * I/O frozen state to avoid I/O accesses from - * the PCI device driver. - */ + /* Keep the state of permanently removed PE intact */ + if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) && + (state & (EEH_PE_ISOLATED | EEH_PE_RECOVERING))) + return NULL; + pe->state |= state; + + /* Offline PCI devices if applicable */ + if (state != EEH_PE_ISOLATED) + return NULL; + eeh_pe_for_each_dev(pe, edev, tmp) { pdev = eeh_dev_to_pci_dev(edev); if (pdev) @@ -532,6 +536,27 @@ void eeh_pe_state_mark(struct eeh_pe *pe, int state) eeh_pe_traverse(pe, __eeh_pe_state_mark, &state); } +static void *__eeh_pe_dev_mode_mark(void *data, void *flag) +{ + struct eeh_dev *edev = data; + int mode = *((int *)flag); + + edev->mode |= mode; + + return NULL; +} + +/** + * eeh_pe_dev_state_mark - Mark state for all device under the PE + * @pe: EEH PE + * + * Mark specific state for all child devices of the PE. + */ +void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode) +{ + eeh_pe_dev_traverse(pe, __eeh_pe_dev_mode_mark, &mode); +} + /** * __eeh_pe_state_clear - Clear state for the PE * @data: EEH PE @@ -546,8 +571,16 @@ static void *__eeh_pe_state_clear(void *data, void *flag) struct eeh_pe *pe = (struct eeh_pe *)data; int state = *((int *)flag); + /* Keep the state of permanently removed PE intact */ + if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) && + (state & EEH_PE_ISOLATED)) + return NULL; + pe->state &= ~state; - pe->check_count = 0; + + /* Clear check count since last isolation */ + if (state & EEH_PE_ISOLATED) + pe->check_count = 0; return NULL; } diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index 5d753d4f2c75..e2595ba4b720 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -59,6 +59,9 @@ void eeh_sysfs_add_device(struct pci_dev *pdev) struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); int rc=0; + if (!eeh_enabled()) + return; + if (edev && (edev->mode & EEH_DEV_SYSFS)) return; diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 662c6dd98072..911d45366f59 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -39,8 +39,8 @@ * System calls. */ .section ".toc","aw" -.SYS_CALL_TABLE: - .tc .sys_call_table[TC],.sys_call_table +SYS_CALL_TABLE: + .tc sys_call_table[TC],sys_call_table /* This value is used to mark exception frames on the stack. */ exception_marker: @@ -106,7 +106,7 @@ BEGIN_FW_FTR_SECTION LDX_BE r10,0,r10 /* get log write index */ cmpd cr1,r11,r10 beq+ cr1,33f - bl .accumulate_stolen_time + bl accumulate_stolen_time REST_GPR(0,r1) REST_4GPRS(3,r1) REST_2GPRS(7,r1) @@ -143,7 +143,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) std r10,SOFTE(r1) #ifdef SHOW_SYSCALLS - bl .do_show_syscall + bl do_show_syscall REST_GPR(0,r1) REST_4GPRS(3,r1) REST_2GPRS(7,r1) @@ -162,7 +162,7 @@ system_call: /* label this so stack traces look sane */ * Need to vector to 32 Bit or default sys_call_table here, * based on caller's run-mode / personality. */ - ld r11,.SYS_CALL_TABLE@toc(2) + ld r11,SYS_CALL_TABLE@toc(2) andi. r10,r10,_TIF_32BIT beq 15f addi r11,r11,8 /* use 32-bit syscall entries */ @@ -174,14 +174,14 @@ system_call: /* label this so stack traces look sane */ clrldi r8,r8,32 15: slwi r0,r0,4 - ldx r10,r11,r0 /* Fetch system call handler [ptr] */ - mtctr r10 + ldx r12,r11,r0 /* Fetch system call handler [ptr] */ + mtctr r12 bctrl /* Call handler */ syscall_exit: std r3,RESULT(r1) #ifdef SHOW_SYSCALLS - bl .do_show_syscall_exit + bl do_show_syscall_exit ld r3,RESULT(r1) #endif CURRENT_THREAD_INFO(r12, r1) @@ -248,9 +248,9 @@ syscall_error: /* Traced system call support */ syscall_dotrace: - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_syscall_trace_enter + bl do_syscall_trace_enter /* * Restore argument registers possibly just changed. * We use the return value of do_syscall_trace_enter @@ -308,7 +308,7 @@ syscall_exit_work: 4: /* Anything else left to do? */ SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */ andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) - beq .ret_from_except_lite + beq ret_from_except_lite /* Re-enable interrupts */ #ifdef CONFIG_PPC_BOOK3E @@ -319,10 +319,10 @@ syscall_exit_work: mtmsrd r10,1 #endif /* CONFIG_PPC_BOOK3E */ - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_syscall_trace_leave - b .ret_from_except + bl do_syscall_trace_leave + b ret_from_except /* Save non-volatile GPRs, if not already saved. */ _GLOBAL(save_nvgprs) @@ -345,52 +345,48 @@ _GLOBAL(save_nvgprs) */ _GLOBAL(ppc_fork) - bl .save_nvgprs - bl .sys_fork + bl save_nvgprs + bl sys_fork b syscall_exit _GLOBAL(ppc_vfork) - bl .save_nvgprs - bl .sys_vfork + bl save_nvgprs + bl sys_vfork b syscall_exit _GLOBAL(ppc_clone) - bl .save_nvgprs - bl .sys_clone + bl save_nvgprs + bl sys_clone b syscall_exit _GLOBAL(ppc32_swapcontext) - bl .save_nvgprs - bl .compat_sys_swapcontext + bl save_nvgprs + bl compat_sys_swapcontext b syscall_exit _GLOBAL(ppc64_swapcontext) - bl .save_nvgprs - bl .sys_swapcontext + bl save_nvgprs + bl sys_swapcontext b syscall_exit _GLOBAL(ret_from_fork) - bl .schedule_tail + bl schedule_tail REST_NVGPRS(r1) li r3,0 b syscall_exit _GLOBAL(ret_from_kernel_thread) - bl .schedule_tail + bl schedule_tail REST_NVGPRS(r1) - ld r14, 0(r14) mtlr r14 mr r3,r15 +#if defined(_CALL_ELF) && _CALL_ELF == 2 + mr r12,r14 +#endif blrl li r3,0 b syscall_exit - .section ".toc","aw" -DSCR_DEFAULT: - .tc dscr_default[TC],dscr_default - - .section ".text" - /* * This routine switches between two different tasks. The process * state of one is saved on its kernel stack. Then the state @@ -575,11 +571,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #ifdef CONFIG_PPC64 BEGIN_FTR_SECTION lwz r6,THREAD_DSCR_INHERIT(r4) - ld r7,DSCR_DEFAULT@toc(2) ld r0,THREAD_DSCR(r4) cmpwi r6,0 bne 1f - ld r0,0(r7) + ld r0,PACA_DSCR(r13) 1: BEGIN_FTR_SECTION_NESTED(70) mfspr r8, SPRN_FSCR @@ -611,7 +606,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR) _GLOBAL(ret_from_except) ld r11,_TRAP(r1) andi. r0,r11,1 - bne .ret_from_except_lite + bne ret_from_except_lite REST_NVGPRS(r1) _GLOBAL(ret_from_except_lite) @@ -661,23 +656,23 @@ _GLOBAL(ret_from_except_lite) #endif 1: andi. r0,r4,_TIF_NEED_RESCHED beq 2f - bl .restore_interrupts + bl restore_interrupts SCHEDULE_USER - b .ret_from_except_lite + b ret_from_except_lite 2: #ifdef CONFIG_PPC_TRANSACTIONAL_MEM andi. r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM bne 3f /* only restore TM if nothing else to do */ addi r3,r1,STACK_FRAME_OVERHEAD - bl .restore_tm_state + bl restore_tm_state b restore 3: #endif - bl .save_nvgprs - bl .restore_interrupts + bl save_nvgprs + bl restore_interrupts addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_notify_resume - b .ret_from_except + bl do_notify_resume + b ret_from_except resume_kernel: /* check current_thread_info, _TIF_EMULATE_STACK_STORE */ @@ -730,7 +725,7 @@ resume_kernel: * sure we are soft-disabled first and reconcile irq state. */ RECONCILE_IRQ_STATE(r3,r4) -1: bl .preempt_schedule_irq +1: bl preempt_schedule_irq /* Re-test flags and eventually loop */ CURRENT_THREAD_INFO(r9, r1) @@ -792,7 +787,7 @@ restore_no_replay: */ do_restore: #ifdef CONFIG_PPC_BOOK3E - b .exception_return_book3e + b exception_return_book3e #else /* * Clear the reservation. If we know the CPU tracks the address of @@ -907,7 +902,7 @@ restore_check_irq_replay: * * Still, this might be useful for things like hash_page */ - bl .__check_irq_replay + bl __check_irq_replay cmpwi cr0,r3,0 beq restore_no_replay @@ -928,13 +923,13 @@ restore_check_irq_replay: cmpwi cr0,r3,0x500 bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; - bl .do_IRQ - b .ret_from_except + bl do_IRQ + b ret_from_except 1: cmpwi cr0,r3,0x900 bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; - bl .timer_interrupt - b .ret_from_except + bl timer_interrupt + b ret_from_except #ifdef CONFIG_PPC_DOORBELL 1: #ifdef CONFIG_PPC_BOOK3E @@ -948,14 +943,14 @@ restore_check_irq_replay: #endif /* CONFIG_PPC_BOOK3E */ bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; - bl .doorbell_exception - b .ret_from_except + bl doorbell_exception + b ret_from_except #endif /* CONFIG_PPC_DOORBELL */ -1: b .ret_from_except /* What else to do here ? */ +1: b ret_from_except /* What else to do here ? */ unrecov_restore: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b unrecov_restore #ifdef CONFIG_PPC_RTAS @@ -1021,7 +1016,7 @@ _GLOBAL(enter_rtas) std r6,PACASAVEDMSR(r13) /* Setup our real return addr */ - LOAD_REG_ADDR(r4,.rtas_return_loc) + LOAD_REG_ADDR(r4,rtas_return_loc) clrldi r4,r4,2 /* convert to realmode address */ mtlr r4 @@ -1045,7 +1040,7 @@ _GLOBAL(enter_rtas) rfid b . /* prevent speculative execution */ -_STATIC(rtas_return_loc) +rtas_return_loc: FIXUP_ENDIAN /* relocation is off at this point */ @@ -1054,7 +1049,7 @@ _STATIC(rtas_return_loc) bcl 20,31,$+4 0: mflr r3 - ld r3,(1f-0b)(r3) /* get &.rtas_restore_regs */ + ld r3,(1f-0b)(r3) /* get &rtas_restore_regs */ mfmsr r6 li r0,MSR_RI @@ -1071,9 +1066,9 @@ _STATIC(rtas_return_loc) b . /* prevent speculative execution */ .align 3 -1: .llong .rtas_restore_regs +1: .llong rtas_restore_regs -_STATIC(rtas_restore_regs) +rtas_restore_regs: /* relocation is on at this point */ REST_GPR(2, r1) /* Restore the TOC */ REST_GPR(13, r1) /* Restore paca */ @@ -1173,7 +1168,7 @@ _GLOBAL(mcount) _GLOBAL(_mcount) blr -_GLOBAL(ftrace_caller) +_GLOBAL_TOC(ftrace_caller) /* Taken from output of objdump from lib64/glibc */ mflr r3 ld r11, 0(r1) @@ -1197,10 +1192,7 @@ _GLOBAL(ftrace_graph_stub) _GLOBAL(ftrace_stub) blr #else -_GLOBAL(mcount) - blr - -_GLOBAL(_mcount) +_GLOBAL_TOC(_mcount) /* Taken from output of objdump from lib64/glibc */ mflr r3 ld r11, 0(r1) @@ -1238,7 +1230,7 @@ _GLOBAL(ftrace_graph_caller) ld r11, 112(r1) addi r3, r11, 16 - bl .prepare_ftrace_return + bl prepare_ftrace_return nop ld r0, 128(r1) @@ -1254,7 +1246,7 @@ _GLOBAL(return_to_handler) mr r31, r1 stdu r1, -112(r1) - bl .ftrace_return_to_handler + bl ftrace_return_to_handler nop /* return value has real return address */ @@ -1284,7 +1276,7 @@ _GLOBAL(mod_return_to_handler) */ ld r2, PACATOC(r13) - bl .ftrace_return_to_handler + bl ftrace_return_to_handler nop /* return value has real return address */ diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c index d9b79358b833..59e4ba74975d 100644 --- a/arch/powerpc/kernel/epapr_paravirt.c +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -30,13 +30,14 @@ extern u32 epapr_ev_idle_start[]; #endif bool epapr_paravirt_enabled; +static bool __maybe_unused epapr_has_idle; static int __init early_init_dt_scan_epapr(unsigned long node, const char *uname, int depth, void *data) { const u32 *insts; - unsigned long len; + int len; int i; insts = of_get_flat_dt_prop(node, "hcall-instructions", &len); @@ -56,7 +57,7 @@ static int __init early_init_dt_scan_epapr(unsigned long node, #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) if (of_get_flat_dt_prop(node, "has-idle", NULL)) - ppc_md.power_save = epapr_ev_idle; + epapr_has_idle = true; #endif epapr_paravirt_enabled = true; @@ -71,3 +72,14 @@ int __init epapr_paravirt_early_init(void) return 0; } +static int __init epapr_idle_init(void) +{ +#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) + if (epapr_has_idle) + ppc_md.power_save = epapr_ev_idle; +#endif + + return 0; +} + +postcore_initcall(epapr_idle_init); diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index c1bee3ce9d1f..771b4e92e5d9 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -499,7 +499,7 @@ exc_##n##_bad_stack: \ CHECK_NAPPING(); \ addi r3,r1,STACK_FRAME_OVERHEAD; \ bl hdlr; \ - b .ret_from_except_lite; + b ret_from_except_lite; /* This value is used to mark exception frames on the stack. */ .section ".toc","aw" @@ -550,11 +550,11 @@ interrupt_end_book3e: CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL, PROLOG_ADDITION_NONE) EXCEPTION_COMMON_CRIT(0x100) - bl .save_nvgprs + bl save_nvgprs bl special_reg_save CHECK_NAPPING(); addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception + bl unknown_exception b ret_from_crit_except /* Machine Check Interrupt */ @@ -562,11 +562,11 @@ interrupt_end_book3e: MC_EXCEPTION_PROLOG(0x000, BOOKE_INTERRUPT_MACHINE_CHECK, PROLOG_ADDITION_NONE) EXCEPTION_COMMON_MC(0x000) - bl .save_nvgprs + bl save_nvgprs bl special_reg_save CHECK_NAPPING(); addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_exception + bl machine_check_exception b ret_from_mc_except /* Data Storage Interrupt */ @@ -591,7 +591,7 @@ interrupt_end_book3e: /* External Input Interrupt */ MASKABLE_EXCEPTION(0x500, BOOKE_INTERRUPT_EXTERNAL, - external_input, .do_IRQ, ACK_NONE) + external_input, do_IRQ, ACK_NONE) /* Alignment */ START_EXCEPTION(alignment); @@ -612,9 +612,9 @@ interrupt_end_book3e: std r14,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXGEN+EX_R14(r13) - bl .save_nvgprs - bl .program_check_exception - b .ret_from_except + bl save_nvgprs + bl program_check_exception + b ret_from_except /* Floating Point Unavailable Interrupt */ START_EXCEPTION(fp_unavailable); @@ -625,13 +625,13 @@ interrupt_end_book3e: ld r12,_MSR(r1) andi. r0,r12,MSR_PR; beq- 1f - bl .load_up_fpu + bl load_up_fpu b fast_exception_return 1: INTS_DISABLE - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_fp_unavailable_exception - b .ret_from_except + bl kernel_fp_unavailable_exception + b ret_from_except /* Altivec Unavailable Interrupt */ START_EXCEPTION(altivec_unavailable); @@ -644,16 +644,16 @@ BEGIN_FTR_SECTION ld r12,_MSR(r1) andi. r0,r12,MSR_PR; beq- 1f - bl .load_up_altivec + bl load_up_altivec b fast_exception_return 1: END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif INTS_DISABLE - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .altivec_unavailable_exception - b .ret_from_except + bl altivec_unavailable_exception + b ret_from_except /* AltiVec Assist */ START_EXCEPTION(altivec_assist); @@ -662,39 +662,39 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x220) INTS_DISABLE - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION - bl .altivec_assist_exception + bl altivec_assist_exception END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #else - bl .unknown_exception + bl unknown_exception #endif - b .ret_from_except + b ret_from_except /* Decrementer Interrupt */ MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER, - decrementer, .timer_interrupt, ACK_DEC) + decrementer, timer_interrupt, ACK_DEC) /* Fixed Interval Timer Interrupt */ MASKABLE_EXCEPTION(0x980, BOOKE_INTERRUPT_FIT, - fixed_interval, .unknown_exception, ACK_FIT) + fixed_interval, unknown_exception, ACK_FIT) /* Watchdog Timer Interrupt */ START_EXCEPTION(watchdog); CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG, PROLOG_ADDITION_NONE) EXCEPTION_COMMON_CRIT(0x9f0) - bl .save_nvgprs + bl save_nvgprs bl special_reg_save CHECK_NAPPING(); addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_BOOKE_WDT - bl .WatchdogException + bl WatchdogException #else - bl .unknown_exception + bl unknown_exception #endif b ret_from_crit_except @@ -712,10 +712,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0xf20) INTS_DISABLE - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* Debug exception as a critical interrupt*/ START_EXCEPTION(debug_crit); @@ -774,9 +774,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mr r4,r14 ld r14,PACA_EXCRIT+EX_R14(r13) ld r15,PACA_EXCRIT+EX_R15(r13) - bl .save_nvgprs - bl .DebugException - b .ret_from_except + bl save_nvgprs + bl DebugException + b ret_from_except kernel_dbg_exc: b . /* NYI */ @@ -839,9 +839,9 @@ kernel_dbg_exc: mr r4,r14 ld r14,PACA_EXDBG+EX_R14(r13) ld r15,PACA_EXDBG+EX_R15(r13) - bl .save_nvgprs - bl .DebugException - b .ret_from_except + bl save_nvgprs + bl DebugException + b ret_from_except START_EXCEPTION(perfmon); NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR, @@ -850,23 +850,23 @@ kernel_dbg_exc: INTS_DISABLE CHECK_NAPPING() addi r3,r1,STACK_FRAME_OVERHEAD - bl .performance_monitor_exception - b .ret_from_except_lite + bl performance_monitor_exception + b ret_from_except_lite /* Doorbell interrupt */ MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL, - doorbell, .doorbell_exception, ACK_NONE) + doorbell, doorbell_exception, ACK_NONE) /* Doorbell critical Interrupt */ START_EXCEPTION(doorbell_crit); CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL, PROLOG_ADDITION_NONE) EXCEPTION_COMMON_CRIT(0x2a0) - bl .save_nvgprs + bl save_nvgprs bl special_reg_save CHECK_NAPPING(); addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception + bl unknown_exception b ret_from_crit_except /* @@ -878,21 +878,21 @@ kernel_dbg_exc: PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x2c0) addi r3,r1,STACK_FRAME_OVERHEAD - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* Guest Doorbell critical Interrupt */ START_EXCEPTION(guest_doorbell_crit); CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT, PROLOG_ADDITION_NONE) EXCEPTION_COMMON_CRIT(0x2e0) - bl .save_nvgprs + bl save_nvgprs bl special_reg_save CHECK_NAPPING(); addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception + bl unknown_exception b ret_from_crit_except /* Hypervisor call */ @@ -901,10 +901,10 @@ kernel_dbg_exc: PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x310) addi r3,r1,STACK_FRAME_OVERHEAD - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* Embedded Hypervisor priviledged */ START_EXCEPTION(ehpriv); @@ -912,10 +912,10 @@ kernel_dbg_exc: PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x320) addi r3,r1,STACK_FRAME_OVERHEAD - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* LRAT Error interrupt */ START_EXCEPTION(lrat_error); @@ -1014,16 +1014,16 @@ storage_fault_common: mr r5,r15 ld r14,PACA_EXGEN+EX_R14(r13) ld r15,PACA_EXGEN+EX_R15(r13) - bl .do_page_fault + bl do_page_fault cmpdi r3,0 bne- 1f - b .ret_from_except_lite -1: bl .save_nvgprs + b ret_from_except_lite +1: bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD ld r4,_DAR(r1) - bl .bad_page_fault - b .ret_from_except + bl bad_page_fault + b ret_from_except /* * Alignment exception doesn't fit entirely in the 0x100 bytes so it @@ -1035,10 +1035,10 @@ alignment_more: addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXGEN+EX_R14(r13) ld r15,PACA_EXGEN+EX_R15(r13) - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .alignment_exception - b .ret_from_except + bl alignment_exception + b ret_from_except /* * We branch here from entry_64.S for the last stage of the exception @@ -1172,7 +1172,7 @@ bad_stack_book3e: std r12,0(r11) ld r2,PACATOC(r13) 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_bad_stack + bl kernel_bad_stack b 1b /* @@ -1521,13 +1521,13 @@ _GLOBAL(start_initialization_book3e) * and always use AS 0, so we just set it up to match our link * address and never use 0 based addresses. */ - bl .initial_tlb_book3e + bl initial_tlb_book3e /* Init global core bits */ - bl .init_core_book3e + bl init_core_book3e /* Init per-thread bits */ - bl .init_thread_book3e + bl init_thread_book3e /* Return to common init code */ tovirt(r28,r28) @@ -1548,7 +1548,7 @@ _GLOBAL(start_initialization_book3e) */ _GLOBAL(book3e_secondary_core_init_tlb_set) li r4,1 - b .generic_secondary_smp_init + b generic_secondary_smp_init _GLOBAL(book3e_secondary_core_init) mflr r28 @@ -1558,18 +1558,18 @@ _GLOBAL(book3e_secondary_core_init) bne 2f /* Setup TLB for this core */ - bl .initial_tlb_book3e + bl initial_tlb_book3e /* We can return from the above running at a different * address, so recalculate r2 (TOC) */ - bl .relative_toc + bl relative_toc /* Init global core bits */ -2: bl .init_core_book3e +2: bl init_core_book3e /* Init per-thread bits */ -3: bl .init_thread_book3e +3: bl init_thread_book3e /* Return to common init code at proper virtual address. * @@ -1596,14 +1596,14 @@ _GLOBAL(book3e_secondary_thread_init) mflr r28 b 3b -_STATIC(init_core_book3e) +init_core_book3e: /* Establish the interrupt vector base */ LOAD_REG_IMMEDIATE(r3, interrupt_base_book3e) mtspr SPRN_IVPR,r3 sync blr -_STATIC(init_thread_book3e) +init_thread_book3e: lis r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h mtspr SPRN_EPCR,r3 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 3afd3915921a..20f11eb4dff7 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -132,12 +132,12 @@ BEGIN_FTR_SECTION #endif beq cr1,2f - b .power7_wakeup_noloss -2: b .power7_wakeup_loss + b power7_wakeup_noloss +2: b power7_wakeup_loss /* Fast Sleep wakeup on PowerNV */ 8: GET_PACA(r13) - b .power7_wakeup_tb_loss + b power7_wakeup_tb_loss 9: END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) @@ -211,16 +211,16 @@ data_access_slb_pSeries: #endif /* __DISABLED__ */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else /* - * We can't just use a direct branch to .slb_miss_realmode + * We can't just use a direct branch to slb_miss_realmode * because the distance from here to there depends on where * the kernel ends up being put. */ mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -243,11 +243,11 @@ instruction_access_slb_pSeries: #endif /* __DISABLED__ */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -524,7 +524,7 @@ do_stab_bolted_pSeries: std r12,PACA_EXSLB+EX_R12(r13) GET_SCRATCH0(r10) std r10,PACA_EXSLB+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD) + EXCEPTION_PROLOG_PSERIES_1(do_stab_bolted, EXC_STD) KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) @@ -769,38 +769,38 @@ kvmppc_skip_Hinterrupt: /*** Common interrupt handlers ***/ - STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception) + STD_EXCEPTION_COMMON(0x100, system_reset, system_reset_exception) STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ) - STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt) - STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt) + STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, timer_interrupt) + STD_EXCEPTION_COMMON(0x980, hdecrementer, hdec_interrupt) #ifdef CONFIG_PPC_DOORBELL - STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .doorbell_exception) + STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, doorbell_exception) #else - STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .unknown_exception) + STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, unknown_exception) #endif - STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception) - STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception) - STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception) - STD_EXCEPTION_COMMON(0xe40, emulation_assist, .emulation_assist_interrupt) - STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception) + STD_EXCEPTION_COMMON(0xb00, trap_0b, unknown_exception) + STD_EXCEPTION_COMMON(0xd00, single_step, single_step_exception) + STD_EXCEPTION_COMMON(0xe00, trap_0e, unknown_exception) + STD_EXCEPTION_COMMON(0xe40, emulation_assist, emulation_assist_interrupt) + STD_EXCEPTION_COMMON(0xe60, hmi_exception, unknown_exception) #ifdef CONFIG_PPC_DOORBELL - STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .doorbell_exception) + STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, doorbell_exception) #else - STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .unknown_exception) + STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception) #endif - STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, .performance_monitor_exception) - STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) - STD_EXCEPTION_COMMON(0x1502, denorm, .unknown_exception) + STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, performance_monitor_exception) + STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, instruction_breakpoint_exception) + STD_EXCEPTION_COMMON(0x1502, denorm, unknown_exception) #ifdef CONFIG_ALTIVEC - STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception) + STD_EXCEPTION_COMMON(0x1700, altivec_assist, altivec_assist_exception) #else - STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception) + STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception) #endif #ifdef CONFIG_CBE_RAS - STD_EXCEPTION_COMMON(0x1200, cbe_system_error, .cbe_system_error_exception) - STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, .cbe_maintenance_exception) - STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception) + STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception) + STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception) + STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception) #endif /* CONFIG_CBE_RAS */ /* @@ -829,16 +829,16 @@ data_access_slb_relon_pSeries: mfspr r3,SPRN_DAR mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else /* - * We can't just use a direct branch to .slb_miss_realmode + * We can't just use a direct branch to slb_miss_realmode * because the distance from here to there depends on where * the kernel ends up being put. */ mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -854,11 +854,11 @@ instruction_access_slb_relon_pSeries: mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE - b .slb_miss_realmode + b slb_miss_realmode #else mfctr r11 ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, .slb_miss_realmode) + LOAD_HANDLER(r10, slb_miss_realmode) mtctr r10 bctr #endif @@ -966,7 +966,7 @@ system_call_entry: b system_call_common ppc64_runlatch_on_trampoline: - b .__ppc64_runlatch_on + b __ppc64_runlatch_on /* * Here we have detected that the kernel stack pointer is bad. @@ -1025,7 +1025,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) std r12,RESULT(r1) std r11,STACK_FRAME_OVERHEAD-16(r1) 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_bad_stack + bl kernel_bad_stack b 1b /* @@ -1046,7 +1046,7 @@ data_access_common: ld r3,PACA_EXGEN+EX_DAR(r13) lwz r4,PACA_EXGEN+EX_DSISR(r13) li r5,0x300 - b .do_hash_page /* Try to handle as hpte fault */ + b do_hash_page /* Try to handle as hpte fault */ .align 7 .globl h_data_storage_common @@ -1056,11 +1056,11 @@ h_data_storage_common: mfspr r10,SPRN_HDSISR stw r10,PACA_EXGEN+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except .align 7 .globl instruction_access_common @@ -1071,9 +1071,9 @@ instruction_access_common: ld r3,_NIP(r1) andis. r4,r12,0x5820 li r5,0x400 - b .do_hash_page /* Try to handle as hpte fault */ + b do_hash_page /* Try to handle as hpte fault */ - STD_EXCEPTION_COMMON(0xe20, h_instr_storage, .unknown_exception) + STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception) /* * Here is the common SLB miss user that is used when going to virtual @@ -1088,7 +1088,7 @@ slb_miss_user_common: stw r9,PACA_EXGEN+EX_CCR(r13) std r10,PACA_EXGEN+EX_LR(r13) std r11,PACA_EXGEN+EX_SRR0(r13) - bl .slb_allocate_user + bl slb_allocate_user ld r10,PACA_EXGEN+EX_LR(r13) ld r3,PACA_EXGEN+EX_R3(r13) @@ -1131,9 +1131,9 @@ slb_miss_fault: unrecov_user_slb: EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN) DISABLE_INTS - bl .save_nvgprs + bl save_nvgprs 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b 1b #endif /* __DISABLED__ */ @@ -1158,10 +1158,10 @@ machine_check_common: lwz r4,PACA_EXGEN+EX_DSISR(r13) std r3,_DAR(r1) std r4,_DSISR(r1) - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_exception - b .ret_from_except + bl machine_check_exception + b ret_from_except .align 7 .globl alignment_common @@ -1175,31 +1175,31 @@ alignment_common: lwz r4,PACA_EXGEN+EX_DSISR(r13) std r3,_DAR(r1) std r4,_DSISR(r1) - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .alignment_exception - b .ret_from_except + bl alignment_exception + b ret_from_except .align 7 .globl program_check_common program_check_common: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .program_check_exception - b .ret_from_except + bl program_check_exception + b ret_from_except .align 7 .globl fp_unavailable_common fp_unavailable_common: EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) bne 1f /* if from user, just load it up */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .kernel_fp_unavailable_exception + bl kernel_fp_unavailable_exception BUG_OPCODE 1: #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -1211,15 +1211,15 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif - bl .load_up_fpu + bl load_up_fpu b fast_exception_return #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .fp_unavailable_tm - b .ret_from_except + bl fp_unavailable_tm + b ret_from_except #endif .align 7 .globl altivec_unavailable_common @@ -1237,24 +1237,24 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) #endif - bl .load_up_altivec + bl load_up_altivec b fast_exception_return #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .altivec_unavailable_tm - b .ret_from_except + bl altivec_unavailable_tm + b ret_from_except #endif 1: END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .altivec_unavailable_exception - b .ret_from_except + bl altivec_unavailable_exception + b ret_from_except .align 7 .globl vsx_unavailable_common @@ -1272,26 +1272,26 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) #endif - b .load_up_vsx + b load_up_vsx #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .vsx_unavailable_tm - b .ret_from_except + bl vsx_unavailable_tm + b ret_from_except #endif 1: END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif - bl .save_nvgprs + bl save_nvgprs DISABLE_INTS addi r3,r1,STACK_FRAME_OVERHEAD - bl .vsx_unavailable_exception - b .ret_from_except + bl vsx_unavailable_exception + b ret_from_except - STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception) - STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception) + STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception) + STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception) .align 7 .globl __end_handlers @@ -1386,9 +1386,9 @@ _GLOBAL(opal_mc_secondary_handler) machine_check_handle_early: std r0,GPR0(r1) /* Save r0 */ EXCEPTION_PROLOG_COMMON_3(0x200) - bl .save_nvgprs + bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_early + bl machine_check_early ld r12,_MSR(r1) #ifdef CONFIG_PPC_P7_NAP /* @@ -1408,11 +1408,11 @@ machine_check_handle_early: /* Supervisor state loss */ li r0,1 stb r0,PACA_NAPSTATELOST(r13) -3: bl .machine_check_queue_event +3: bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) - b .power7_enter_nap_mode + b power7_enter_nap_mode 4: #endif /* @@ -1444,7 +1444,7 @@ machine_check_handle_early: andi. r11,r12,MSR_RI bne 2f 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b 1b 2: /* @@ -1452,7 +1452,7 @@ machine_check_handle_early: * Queue up the MCE event so that we can log it later, while * returning from kernel or opal call. */ - bl .machine_check_queue_event + bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP rfid 9: @@ -1468,7 +1468,7 @@ machine_check_handle_early: * r3 is saved in paca->slb_r3 * We assume we aren't going to take any exceptions during this procedure. */ -_GLOBAL(slb_miss_realmode) +slb_miss_realmode: mflr r10 #ifdef CONFIG_RELOCATABLE mtctr r11 @@ -1477,7 +1477,7 @@ _GLOBAL(slb_miss_realmode) stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ - bl .slb_allocate_realmode + bl slb_allocate_realmode /* All done -- return from exception. */ @@ -1517,9 +1517,9 @@ _GLOBAL(slb_miss_realmode) unrecov_slb: EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) DISABLE_INTS - bl .save_nvgprs + bl save_nvgprs 1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception + bl unrecoverable_exception b 1b @@ -1536,7 +1536,7 @@ power4_fixup_nap: * Hash table stuff */ .align 7 -_STATIC(do_hash_page) +do_hash_page: std r3,_DAR(r1) std r4,_DSISR(r1) @@ -1573,7 +1573,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) * * at return r3 = 0 for success, 1 for page fault, negative for error */ - bl .hash_page /* build HPTE if possible */ + bl hash_page /* build HPTE if possible */ cmpdi r3,0 /* see if hash_page succeeded */ /* Success */ @@ -1587,35 +1587,35 @@ handle_page_fault: 11: ld r4,_DAR(r1) ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_page_fault + bl do_page_fault cmpdi r3,0 beq+ 12f - bl .save_nvgprs + bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD lwz r4,_DAR(r1) - bl .bad_page_fault - b .ret_from_except + bl bad_page_fault + b ret_from_except /* We have a data breakpoint exception - handle it */ handle_dabr_fault: - bl .save_nvgprs + bl save_nvgprs ld r4,_DAR(r1) ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_break -12: b .ret_from_except_lite + bl do_break +12: b ret_from_except_lite /* We have a page fault that hash_page could handle but HV refused * the PTE insertion */ -13: bl .save_nvgprs +13: bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD ld r4,_DAR(r1) - bl .low_hash_fault - b .ret_from_except + bl low_hash_fault + b ret_from_except /* * We come here as a result of a DSI at a point where we don't want @@ -1624,16 +1624,16 @@ handle_dabr_fault: * were soft-disabled. We want to invoke the exception handler for * the access, or panic if there isn't a handler. */ -77: bl .save_nvgprs +77: bl save_nvgprs mr r4,r3 addi r3,r1,STACK_FRAME_OVERHEAD li r5,SIGSEGV - bl .bad_page_fault - b .ret_from_except + bl bad_page_fault + b ret_from_except /* here we have a segment miss */ do_ste_alloc: - bl .ste_allocate /* try to insert stab entry */ + bl ste_allocate /* try to insert stab entry */ cmpdi r3,0 bne- handle_page_fault b fast_exception_return @@ -1646,7 +1646,7 @@ do_ste_alloc: * We assume (DAR >> 60) == 0xc. */ .align 7 -_GLOBAL(do_stab_bolted) +do_stab_bolted: stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */ mfspr r11,SPRN_DAR /* ea */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 2230fd0ca3e4..742694c1d852 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -55,9 +55,9 @@ int crash_mem_ranges; int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname, int depth, void *data) { - __be32 *sections; + const __be32 *sections; int i, num_sections; - unsigned long size; + int size; const int *token; if (depth != 1 || strcmp(uname, "rtas") != 0) @@ -69,7 +69,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, */ token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL); if (!token) - return 0; + return 1; fw_dump.fadump_supported = 1; fw_dump.ibm_configure_kernel_dump = *token; @@ -92,7 +92,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, &size); if (!sections) - return 0; + return 1; num_sections = size / (3 * sizeof(u32)); @@ -110,6 +110,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, break; } } + return 1; } @@ -645,7 +646,7 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) } /* Lower 4 bytes of reg_value contains logical cpu id */ cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK; - if (!cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) { + if (fdh && !cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) { SKIP_TO_NEXT_CPU(reg_entry); continue; } @@ -662,9 +663,11 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) } fadump_final_note(note_buf); - pr_debug("Updating elfcore header (%llx) with cpu notes\n", + if (fdh) { + pr_debug("Updating elfcore header (%llx) with cpu notes\n", fdh->elfcorehdr_addr); - fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr)); + fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr)); + } return 0; error_out: diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 6a014c763cc7..f202d0731b06 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -105,11 +105,9 @@ __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { unsigned int op; - unsigned int jmp[5]; unsigned long ptr; unsigned long ip = rec->ip; - unsigned long tramp; - int offset; + void *tramp; /* read where this goes */ if (probe_kernel_read(&op, (void *)ip, sizeof(int))) @@ -122,96 +120,41 @@ __ftrace_make_nop(struct module *mod, } /* lets find where the pointer goes */ - tramp = find_bl_target(ip, op); - - /* - * On PPC64 the trampoline looks like: - * 0x3d, 0x82, 0x00, 0x00, addis r12,r2, <high> - * 0x39, 0x8c, 0x00, 0x00, addi r12,r12, <low> - * Where the bytes 2,3,6 and 7 make up the 32bit offset - * to the TOC that holds the pointer. - * to jump to. - * 0xf8, 0x41, 0x00, 0x28, std r2,40(r1) - * 0xe9, 0x6c, 0x00, 0x20, ld r11,32(r12) - * The actually address is 32 bytes from the offset - * into the TOC. - * 0xe8, 0x4c, 0x00, 0x28, ld r2,40(r12) - */ - - pr_devel("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc); - - /* Find where the trampoline jumps to */ - if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { - printk(KERN_ERR "Failed to read %lx\n", tramp); - return -EFAULT; - } + tramp = (void *)find_bl_target(ip, op); - pr_devel(" %08x %08x", jmp[0], jmp[1]); + pr_devel("ip:%lx jumps to %p", ip, tramp); - /* verify that this is what we expect it to be */ - if (((jmp[0] & 0xffff0000) != 0x3d820000) || - ((jmp[1] & 0xffff0000) != 0x398c0000) || - (jmp[2] != 0xf8410028) || - (jmp[3] != 0xe96c0020) || - (jmp[4] != 0xe84c0028)) { + if (!is_module_trampoline(tramp)) { printk(KERN_ERR "Not a trampoline\n"); return -EINVAL; } - /* The bottom half is signed extended */ - offset = ((unsigned)((unsigned short)jmp[0]) << 16) + - (int)((short)jmp[1]); - - pr_devel(" %x ", offset); - - /* get the address this jumps too */ - tramp = mod->arch.toc + offset + 32; - pr_devel("toc: %lx", tramp); - - if (probe_kernel_read(jmp, (void *)tramp, 8)) { - printk(KERN_ERR "Failed to read %lx\n", tramp); + if (module_trampoline_target(mod, tramp, &ptr)) { + printk(KERN_ERR "Failed to get trampoline target\n"); return -EFAULT; } - pr_devel(" %08x %08x\n", jmp[0], jmp[1]); - -#ifdef __LITTLE_ENDIAN__ - ptr = ((unsigned long)jmp[1] << 32) + jmp[0]; -#else - ptr = ((unsigned long)jmp[0] << 32) + jmp[1]; -#endif + pr_devel("trampoline target %lx", ptr); /* This should match what was called */ if (ptr != ppc_function_entry((void *)addr)) { - printk(KERN_ERR "addr does not match %lx\n", ptr); + printk(KERN_ERR "addr %lx does not match expected %lx\n", + ptr, ppc_function_entry((void *)addr)); return -EINVAL; } /* - * We want to nop the line, but the next line is - * 0xe8, 0x41, 0x00, 0x28 ld r2,40(r1) - * This needs to be turned to a nop too. - */ - if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) - return -EFAULT; - - if (op != 0xe8410028) { - printk(KERN_ERR "Next line is not ld! (%08x)\n", op); - return -EINVAL; - } - - /* - * Milton Miller pointed out that we can not blindly do nops. - * If a task was preempted when calling a trace function, - * the nops will remove the way to restore the TOC in r2 - * and the r2 TOC will get corrupted. - */ - - /* - * Replace: - * bl <tramp> <==== will be replaced with "b 1f" - * ld r2,40(r1) - * 1: + * Our original call site looks like: + * + * bl <tramp> + * ld r2,XX(r1) + * + * Milton Miller pointed out that we can not simply nop the branch. + * If a task was preempted when calling a trace function, the nops + * will remove the way to restore the TOC in r2 and the r2 TOC will + * get corrupted. + * + * Use a b +8 to jump over the load. */ op = 0x48000008; /* b +8 */ @@ -349,19 +292,24 @@ static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { unsigned int op[2]; - unsigned long ip = rec->ip; + void *ip = (void *)rec->ip; /* read where this goes */ - if (probe_kernel_read(op, (void *)ip, MCOUNT_INSN_SIZE * 2)) + if (probe_kernel_read(op, ip, sizeof(op))) return -EFAULT; /* - * It should be pointing to two nops or - * b +8; ld r2,40(r1) + * We expect to see: + * + * b +8 + * ld r2,XX(r1) + * + * The load offset is different depending on the ABI. For simplicity + * just mask it out when doing the compare. */ - if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) && - ((op[0] != PPC_INST_NOP) || (op[1] != PPC_INST_NOP))) { - printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]); + if ((op[0] != 0x48000008) || ((op[1] & 0xffff00000) != 0xe8410000)) { + printk(KERN_ERR "Unexpected call sequence: %x %x\n", + op[0], op[1]); return -EINVAL; } @@ -371,23 +319,16 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return -EINVAL; } - /* create the branch to the trampoline */ - op[0] = create_branch((unsigned int *)ip, - rec->arch.mod->arch.tramp, BRANCH_SET_LINK); - if (!op[0]) { - printk(KERN_ERR "REL24 out of range!\n"); + /* Ensure branch is within 24 bits */ + if (create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + printk(KERN_ERR "Branch out of range"); return -EINVAL; } - /* ld r2,40(r1) */ - op[1] = 0xe8410028; - - pr_devel("write to %lx\n", rec->ip); - - if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2)) - return -EPERM; - - flush_icache_range(ip, ip + 8); + if (patch_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + printk(KERN_ERR "REL24 out of range!\n"); + return -EINVAL; + } return 0; } diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index b7363bd42452..a95145d7f61b 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -70,16 +70,15 @@ _GLOBAL(__start) /* NOP this out unconditionally */ BEGIN_FTR_SECTION FIXUP_ENDIAN - b .__start_initialization_multiplatform + b __start_initialization_multiplatform END_FTR_SECTION(0, 1) /* Catch branch to 0 in real mode */ trap - /* Secondary processors spin on this value until it becomes nonzero. - * When it does it contains the real address of the descriptor - * of the function that the cpu should jump to to continue - * initialization. + /* Secondary processors spin on this value until it becomes non-zero. + * When non-zero, it contains the real address of the function the cpu + * should jump to. */ .balign 8 .globl __secondary_hold_spinloop @@ -140,16 +139,15 @@ __secondary_hold: tovirt(r26,r26) #endif /* All secondary cpus wait here until told to start. */ -100: ld r4,__secondary_hold_spinloop-_stext(r26) - cmpdi 0,r4,0 +100: ld r12,__secondary_hold_spinloop-_stext(r26) + cmpdi 0,r12,0 beq 100b #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) #ifdef CONFIG_PPC_BOOK3E - tovirt(r4,r4) + tovirt(r12,r12) #endif - ld r4,0(r4) /* deref function descriptor */ - mtctr r4 + mtctr r12 mr r3,r24 /* * it may be the case that other platforms have r4 right to @@ -186,16 +184,16 @@ _GLOBAL(generic_secondary_thread_init) mr r24,r3 /* turn on 64-bit mode */ - bl .enable_64b_mode + bl enable_64b_mode /* get a valid TOC pointer, wherever we're mapped at */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) #ifdef CONFIG_PPC_BOOK3E /* Book3E initialization */ mr r3,r24 - bl .book3e_secondary_thread_init + bl book3e_secondary_thread_init #endif b generic_secondary_common_init @@ -214,17 +212,17 @@ _GLOBAL(generic_secondary_smp_init) mr r25,r4 /* turn on 64-bit mode */ - bl .enable_64b_mode + bl enable_64b_mode /* get a valid TOC pointer, wherever we're mapped at */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) #ifdef CONFIG_PPC_BOOK3E /* Book3E initialization */ mr r3,r24 mr r4,r25 - bl .book3e_secondary_core_init + bl book3e_secondary_core_init #endif generic_secondary_common_init: @@ -236,7 +234,7 @@ generic_secondary_common_init: ld r13,0(r13) /* Get base vaddr of paca array */ #ifndef CONFIG_SMP addi r13,r13,PACA_SIZE /* know r13 if used accidentally */ - b .kexec_wait /* wait for next kernel if !SMP */ + b kexec_wait /* wait for next kernel if !SMP */ #else LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */ lwz r7,0(r7) /* also the max paca allocated */ @@ -250,7 +248,7 @@ generic_secondary_common_init: blt 1b mr r3,r24 /* not found, copy phys to r3 */ - b .kexec_wait /* next kernel might do better */ + b kexec_wait /* next kernel might do better */ 2: SET_PACA(r13) #ifdef CONFIG_PPC_BOOK3E @@ -264,11 +262,13 @@ generic_secondary_common_init: /* See if we need to call a cpu state restore handler */ LOAD_REG_ADDR(r23, cur_cpu_spec) ld r23,0(r23) - ld r23,CPU_SPEC_RESTORE(r23) - cmpdi 0,r23,0 + ld r12,CPU_SPEC_RESTORE(r23) + cmpdi 0,r12,0 beq 3f - ld r23,0(r23) - mtctr r23 +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + ld r12,0(r12) +#endif + mtctr r12 bctrl 3: LOAD_REG_ADDR(r3, spinning_secondaries) /* Decrement spinning_secondaries */ @@ -299,7 +299,7 @@ generic_secondary_common_init: * Assumes we're mapped EA == RA if the MMU is on. */ #ifdef CONFIG_PPC_BOOK3S -_STATIC(__mmu_off) +__mmu_off: mfmsr r3 andi. r0,r3,MSR_IR|MSR_DR beqlr @@ -324,12 +324,12 @@ _STATIC(__mmu_off) * DT block, r4 is a physical pointer to the kernel itself * */ -_GLOBAL(__start_initialization_multiplatform) +__start_initialization_multiplatform: /* Make sure we are running in 64 bits mode */ - bl .enable_64b_mode + bl enable_64b_mode /* Get TOC pointer (current runtime address) */ - bl .relative_toc + bl relative_toc /* find out where we are now */ bcl 20,31,$+4 @@ -342,7 +342,7 @@ _GLOBAL(__start_initialization_multiplatform) */ cmpldi cr0,r5,0 beq 1f - b .__boot_from_prom /* yes -> prom */ + b __boot_from_prom /* yes -> prom */ 1: /* Save parameters */ mr r31,r3 @@ -354,8 +354,8 @@ _GLOBAL(__start_initialization_multiplatform) #endif #ifdef CONFIG_PPC_BOOK3E - bl .start_initialization_book3e - b .__after_prom_start + bl start_initialization_book3e + b __after_prom_start #else /* Setup some critical 970 SPRs before switching MMU off */ mfspr r0,SPRN_PVR @@ -368,15 +368,15 @@ _GLOBAL(__start_initialization_multiplatform) beq 1f cmpwi r0,0x45 /* 970GX */ bne 2f -1: bl .__cpu_preinit_ppc970 +1: bl __cpu_preinit_ppc970 2: /* Switch off MMU if not already off */ - bl .__mmu_off - b .__after_prom_start + bl __mmu_off + b __after_prom_start #endif /* CONFIG_PPC_BOOK3E */ -_INIT_STATIC(__boot_from_prom) +__boot_from_prom: #ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE /* Save parameters */ mr r31,r3 @@ -395,7 +395,7 @@ _INIT_STATIC(__boot_from_prom) #ifdef CONFIG_RELOCATABLE /* Relocate code for where we are now */ mr r3,r26 - bl .relocate + bl relocate #endif /* Restore parameters */ @@ -407,14 +407,14 @@ _INIT_STATIC(__boot_from_prom) /* Do all of the interaction with OF client interface */ mr r8,r26 - bl .prom_init + bl prom_init #endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */ /* We never return. We also hit that trap if trying to boot * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */ trap -_STATIC(__after_prom_start) +__after_prom_start: #ifdef CONFIG_RELOCATABLE /* process relocations for the final address of the kernel */ lis r25,PAGE_OFFSET@highest /* compute virtual base of kernel */ @@ -424,7 +424,7 @@ _STATIC(__after_prom_start) bne 1f add r25,r25,r26 1: mr r3,r25 - bl .relocate + bl relocate #endif /* @@ -464,12 +464,12 @@ _STATIC(__after_prom_start) lis r5,(copy_to_here - _stext)@ha addi r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */ - bl .copy_and_flush /* copy the first n bytes */ + bl copy_and_flush /* copy the first n bytes */ /* this includes the code being */ /* executed here. */ addis r8,r3,(4f - _stext)@ha /* Jump to the copy of this code */ - addi r8,r8,(4f - _stext)@l /* that we just made */ - mtctr r8 + addi r12,r8,(4f - _stext)@l /* that we just made */ + mtctr r12 bctr .balign 8 @@ -478,9 +478,9 @@ p_end: .llong _end - _stext 4: /* Now copy the rest of the kernel up to _end */ addis r5,r26,(p_end - _stext)@ha ld r5,(p_end - _stext)@l(r5) /* get _end */ -5: bl .copy_and_flush /* copy the rest */ +5: bl copy_and_flush /* copy the rest */ -9: b .start_here_multiplatform +9: b start_here_multiplatform /* * Copy routine used to copy the kernel to start at physical address 0 @@ -544,7 +544,7 @@ __secondary_start_pmac_0: _GLOBAL(pmac_secondary_start) /* turn on 64-bit mode */ - bl .enable_64b_mode + bl enable_64b_mode li r0,0 mfspr r3,SPRN_HID4 @@ -556,11 +556,11 @@ _GLOBAL(pmac_secondary_start) slbia /* get TOC pointer (real address) */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) /* Copy some CPU settings from CPU 0 */ - bl .__restore_cpu_ppc970 + bl __restore_cpu_ppc970 /* pSeries do that early though I don't think we really need it */ mfmsr r3 @@ -619,7 +619,7 @@ __secondary_start: std r14,PACAKSAVE(r13) /* Do early setup for that CPU (stab, slb, hash table pointer) */ - bl .early_setup_secondary + bl early_setup_secondary /* * setup the new stack pointer, but *don't* use this until @@ -639,7 +639,7 @@ __secondary_start: stb r0,PACAIRQHAPPENED(r13) /* enable MMU and jump to start_secondary */ - LOAD_REG_ADDR(r3, .start_secondary_prolog) + LOAD_REG_ADDR(r3, start_secondary_prolog) LOAD_REG_IMMEDIATE(r4, MSR_KERNEL) mtspr SPRN_SRR0,r3 @@ -652,11 +652,11 @@ __secondary_start: * zero the stack back-chain pointer and get the TOC virtual address * before going into C code. */ -_GLOBAL(start_secondary_prolog) +start_secondary_prolog: ld r2,PACATOC(r13) li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ - bl .start_secondary + bl start_secondary b . /* * Reset stack pointer and call start_secondary @@ -667,14 +667,14 @@ _GLOBAL(start_secondary_resume) ld r1,PACAKSAVE(r13) /* Reload kernel stack pointer */ li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ - bl .start_secondary + bl start_secondary b . #endif /* * This subroutine clobbers r11 and r12 */ -_GLOBAL(enable_64b_mode) +enable_64b_mode: mfmsr r11 /* grab the current MSR */ #ifdef CONFIG_PPC_BOOK3E oris r11,r11,0x8000 /* CM bit set, we'll set ICM later */ @@ -715,9 +715,9 @@ p_toc: .llong __toc_start + 0x8000 - 0b /* * This is where the main kernel code starts. */ -_INIT_STATIC(start_here_multiplatform) +start_here_multiplatform: /* set up the TOC */ - bl .relative_toc + bl relative_toc tovirt(r2,r2) /* Clear out the BSS. It may have been done in prom_init, @@ -776,9 +776,9 @@ _INIT_STATIC(start_here_multiplatform) /* Restore parameters passed from prom_init/kexec */ mr r3,r31 - bl .early_setup /* also sets r13 and SPRG_PACA */ + bl early_setup /* also sets r13 and SPRG_PACA */ - LOAD_REG_ADDR(r3, .start_here_common) + LOAD_REG_ADDR(r3, start_here_common) ld r4,PACAKMSR(r13) mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 @@ -786,7 +786,8 @@ _INIT_STATIC(start_here_multiplatform) b . /* prevent speculative execution */ /* This is where all platforms converge execution */ -_INIT_GLOBAL(start_here_common) + +start_here_common: /* relocation is on at this point */ std r1,PACAKSAVE(r13) @@ -794,7 +795,7 @@ _INIT_GLOBAL(start_here_common) ld r2,PACATOC(r13) /* Do more system initializations in virtual mode */ - bl .setup_system + bl setup_system /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) @@ -805,7 +806,7 @@ _INIT_GLOBAL(start_here_common) stb r0,PACAIRQHAPPENED(r13) /* Generic kernel entry */ - bl .start_kernel + bl start_kernel /* Not reached */ BUG_OPCODE diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index b0a1792279bb..0bb5918faaaf 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -72,7 +72,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) * If so, DABR will be populated in single_step_dabr_instruction(). */ if (current->thread.last_hit_ubp != bp) - set_breakpoint(info); + __set_breakpoint(info); return 0; } @@ -198,7 +198,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) info = counter_arch_bp(tsk->thread.last_hit_ubp); regs->msr &= ~MSR_SE; - set_breakpoint(info); + __set_breakpoint(info); tsk->thread.last_hit_ubp = NULL; } @@ -284,7 +284,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ)) perf_bp_event(bp, regs); - set_breakpoint(info); + __set_breakpoint(info); out: rcu_read_unlock(); return rc; @@ -316,7 +316,7 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ)) perf_bp_event(bp, regs); - set_breakpoint(info); + __set_breakpoint(info); current->thread.last_hit_ubp = NULL; /* diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S index bfb73cc209ce..48c21acef915 100644 --- a/arch/powerpc/kernel/idle_book3e.S +++ b/arch/powerpc/kernel/idle_book3e.S @@ -43,7 +43,7 @@ _GLOBAL(\name) */ #ifdef CONFIG_TRACE_IRQFLAGS stdu r1,-128(r1) - bl .trace_hardirqs_on + bl trace_hardirqs_on addi r1,r1,128 #endif li r0,1 diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S index e3edaa189911..f57a19348bdd 100644 --- a/arch/powerpc/kernel/idle_power4.S +++ b/arch/powerpc/kernel/idle_power4.S @@ -46,7 +46,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP) mflr r0 std r0,16(r1) stdu r1,-128(r1) - bl .trace_hardirqs_on + bl trace_hardirqs_on addi r1,r1,128 ld r0,16(r1) mtlr r0 diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index c3ab86975614..2480256272d4 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -39,6 +39,10 @@ * Pass requested state in r3: * 0 - nap * 1 - sleep + * + * To check IRQ_HAPPENED in r4 + * 0 - don't check + * 1 - check */ _GLOBAL(power7_powersave_common) /* Use r3 to pass state nap/sleep/winkle */ @@ -58,7 +62,7 @@ _GLOBAL(power7_powersave_common) /* Make sure FPU, VSX etc... are flushed as we may lose * state when going to nap mode */ - bl .discard_lazy_cpu_state + bl discard_lazy_cpu_state #endif /* CONFIG_SMP */ /* Hard disable interrupts */ @@ -71,6 +75,8 @@ _GLOBAL(power7_powersave_common) lbz r0,PACAIRQHAPPENED(r13) cmpwi cr0,r0,0 beq 1f + cmpwi cr0,r4,0 + beq 1f addi r1,r1,INT_FRAME_SIZE ld r0,16(r1) mtlr r0 @@ -114,15 +120,18 @@ _GLOBAL(power7_idle) lwz r4,ADDROFF(powersave_nap)(r3) cmpwi 0,r4,0 beqlr + li r3, 1 /* fall through */ _GLOBAL(power7_nap) + mr r4,r3 li r3,0 b power7_powersave_common /* No return */ _GLOBAL(power7_sleep) li r3,1 + li r4,0 b power7_powersave_common /* No return */ @@ -168,7 +177,7 @@ _GLOBAL(power7_wakeup_loss) _GLOBAL(power7_wakeup_noloss) lbz r0,PACA_NAPSTATELOST(r13) cmpwi r0,0 - bne .power7_wakeup_loss + bne power7_wakeup_loss ld r1,PACAR1(r13) ld r4,_MSR(r1) ld r5,_NIP(r1) diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index ca1cd7459c4a..248ee7e5bebd 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -304,7 +304,7 @@ void notrace restore_interrupts(void) * being re-enabled and generally sanitized the lazy irq state, * and in the latter case it will leave with interrupts hard * disabled and marked as such, so the local_irq_enable() call - * in cpu_idle() will properly re-enable everything. + * in arch_cpu_idle() will properly re-enable everything. */ bool prep_irq_for_idle(void) { diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 40bd7bd4e19a..936258881c98 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -48,6 +48,9 @@ static struct of_device_id legacy_serial_parents[] __initdata = { static unsigned int legacy_serial_count; static int legacy_serial_console = -1; +static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | + UPF_SHARE_IRQ | UPF_FIXED_PORT; + static unsigned int tsi_serial_in(struct uart_port *p, int offset) { unsigned int tmp; @@ -71,8 +74,9 @@ static int __init add_legacy_port(struct device_node *np, int want_index, phys_addr_t taddr, unsigned long irq, upf_t flags, int irq_check_parent) { - const __be32 *clk, *spd; + const __be32 *clk, *spd, *rs; u32 clock = BASE_BAUD * 16; + u32 shift = 0; int index; /* get clock freq. if present */ @@ -83,6 +87,11 @@ static int __init add_legacy_port(struct device_node *np, int want_index, /* get default speed if present */ spd = of_get_property(np, "current-speed", NULL); + /* get register shift if present */ + rs = of_get_property(np, "reg-shift", NULL); + if (rs && *rs) + shift = be32_to_cpup(rs); + /* If we have a location index, then try to use it */ if (want_index >= 0 && want_index < MAX_LEGACY_SERIAL_PORTS) index = want_index; @@ -126,6 +135,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index, legacy_serial_ports[index].uartclk = clock; legacy_serial_ports[index].irq = irq; legacy_serial_ports[index].flags = flags; + legacy_serial_ports[index].regshift = shift; legacy_serial_infos[index].taddr = taddr; legacy_serial_infos[index].np = of_node_get(np); legacy_serial_infos[index].clock = clock; @@ -153,8 +163,6 @@ static int __init add_legacy_soc_port(struct device_node *np, { u64 addr; const __be32 *addrp; - upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ - | UPF_FIXED_PORT; struct device_node *tsi = of_get_parent(np); /* We only support ports that have a clock frequency properly @@ -163,9 +171,8 @@ static int __init add_legacy_soc_port(struct device_node *np, if (of_get_property(np, "clock-frequency", NULL) == NULL) return -1; - /* if reg-shift or offset, don't try to use it */ - if ((of_get_property(np, "reg-shift", NULL) != NULL) || - (of_get_property(np, "reg-offset", NULL) != NULL)) + /* if reg-offset don't try to use it */ + if ((of_get_property(np, "reg-offset", NULL) != NULL)) return -1; /* if rtas uses this device, don't try to use it as well */ @@ -185,9 +192,11 @@ static int __init add_legacy_soc_port(struct device_node *np, * IO port value. It will be fixed up later along with the irq */ if (tsi && !strcmp(tsi->type, "tsi-bridge")) - return add_legacy_port(np, -1, UPIO_TSI, addr, addr, NO_IRQ, flags, 0); + return add_legacy_port(np, -1, UPIO_TSI, addr, addr, + NO_IRQ, legacy_port_flags, 0); else - return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags, 0); + return add_legacy_port(np, -1, UPIO_MEM, addr, addr, + NO_IRQ, legacy_port_flags, 0); } static int __init add_legacy_isa_port(struct device_node *np, @@ -233,7 +242,7 @@ static int __init add_legacy_isa_port(struct device_node *np, /* Add port, irq will be dealt with later */ return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]), - taddr, NO_IRQ, UPF_BOOT_AUTOCONF, 0); + taddr, NO_IRQ, legacy_port_flags, 0); } @@ -306,7 +315,7 @@ static int __init add_legacy_pci_port(struct device_node *np, * IO port value. It will be fixed up later along with the irq */ return add_legacy_port(np, index, iotype, base, addr, NO_IRQ, - UPF_BOOT_AUTOCONF, np != pci_dev); + legacy_port_flags, np != pci_dev); } #endif @@ -315,17 +324,20 @@ static void __init setup_legacy_serial_console(int console) struct legacy_serial_info *info = &legacy_serial_infos[console]; struct plat_serial8250_port *port = &legacy_serial_ports[console]; void __iomem *addr; + unsigned int stride; + + stride = 1 << port->regshift; /* Check if a translated MMIO address has been found */ if (info->taddr) { addr = ioremap(info->taddr, 0x1000); if (addr == NULL) return; - udbg_uart_init_mmio(addr, 1); + udbg_uart_init_mmio(addr, stride); } else { /* Check if it's PIO and we support untranslated PIO */ if (port->iotype == UPIO_PORT && isa_io_special) - udbg_uart_init_pio(port->iobase, 1); + udbg_uart_init_pio(port->iobase, stride); else return; } diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 3d0249599d52..4e314b90c75d 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -34,7 +34,7 @@ _GLOBAL(call_do_softirq) std r0,16(r1) stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3) mr r1,r3 - bl .__do_softirq + bl __do_softirq ld r1,0(r1) ld r0,16(r1) mtlr r0 @@ -45,7 +45,7 @@ _GLOBAL(call_do_irq) std r0,16(r1) stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4) mr r1,r4 - bl .__do_irq + bl __do_irq ld r1,0(r1) ld r0,16(r1) mtlr r0 @@ -506,7 +506,7 @@ _GLOBAL(kexec_smp_wait) stb r4,PACAKEXECSTATE(r13) SYNC - b .kexec_wait + b kexec_wait /* * switch to real mode (turn mmu off) @@ -576,7 +576,7 @@ _GLOBAL(kexec_sequence) /* copy dest pages, flush whole dest image */ mr r3,r29 - bl .kexec_copy_flush /* (image) */ + bl kexec_copy_flush /* (image) */ /* turn off mmu */ bl real_mode @@ -586,7 +586,7 @@ _GLOBAL(kexec_sequence) mr r4,r30 /* start, aka phys mem offset */ li r5,0x100 li r6,0 - bl .copy_and_flush /* (dest, src, copy limit, start offset) */ + bl copy_and_flush /* (dest, src, copy limit, start offset) */ 1: /* assume normal blr return */ /* release other cpus to the new kernel secondary start at 0x60 */ @@ -595,8 +595,12 @@ _GLOBAL(kexec_sequence) stw r6,kexec_flag-1b(5) /* clear out hardware hash page table and tlb */ - ld r5,0(r27) /* deref function descriptor */ - mtctr r5 +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + ld r12,0(r27) /* deref function descriptor */ +#else + mr r12,r27 +#endif + mtctr r12 bctrl /* ppc_md.hpte_clear_all(void); */ /* @@ -630,3 +634,31 @@ _GLOBAL(kexec_sequence) li r5,0 blr /* image->start(physid, image->start, 0); */ #endif /* CONFIG_KEXEC */ + +#ifdef CONFIG_MODULES +#if defined(_CALL_ELF) && _CALL_ELF == 2 + +#ifdef CONFIG_MODVERSIONS +.weak __crc_TOC. +.section "___kcrctab+TOC.","a" +.globl __kcrctab_TOC. +__kcrctab_TOC.: + .llong __crc_TOC. +#endif + +/* + * Export a fake .TOC. since both modpost and depmod will complain otherwise. + * Both modpost and depmod strip the leading . so we do the same here. + */ +.section "__ksymtab_strings","a" +__kstrtab_TOC.: + .asciz "TOC." + +.section "___ksymtab+TOC.","a" +/* This symbol name is important: it's used by modpost to find exported syms */ +.globl __ksymtab_TOC. +__ksymtab_TOC.: + .llong 0 /* .value */ + .llong __kstrtab_TOC. +#endif /* ELFv2 */ +#endif /* MODULES */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 12664c130d73..077d2ce6c5a7 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -22,6 +22,7 @@ #include <linux/vmalloc.h> #include <linux/ftrace.h> #include <linux/bug.h> +#include <linux/uaccess.h> #include <asm/module.h> #include <asm/firmware.h> #include <asm/code-patching.h> @@ -41,46 +42,170 @@ #define DEBUGP(fmt , ...) #endif +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define R2_STACK_OFFSET 24 + +/* An address is simply the address of the function. */ +typedef unsigned long func_desc_t; + +static func_desc_t func_desc(unsigned long addr) +{ + return addr; +} +static unsigned long func_addr(unsigned long addr) +{ + return addr; +} +static unsigned long stub_func_addr(func_desc_t func) +{ + return func; +} + +/* PowerPC64 specific values for the Elf64_Sym st_other field. */ +#define STO_PPC64_LOCAL_BIT 5 +#define STO_PPC64_LOCAL_MASK (7 << STO_PPC64_LOCAL_BIT) +#define PPC64_LOCAL_ENTRY_OFFSET(other) \ + (((1 << (((other) & STO_PPC64_LOCAL_MASK) >> STO_PPC64_LOCAL_BIT)) >> 2) << 2) + +static unsigned int local_entry_offset(const Elf64_Sym *sym) +{ + /* sym->st_other indicates offset to local entry point + * (otherwise it will assume r12 is the address of the start + * of function and try to derive r2 from it). */ + return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other); +} +#else +#define R2_STACK_OFFSET 40 + +/* An address is address of the OPD entry, which contains address of fn. */ +typedef struct ppc64_opd_entry func_desc_t; + +static func_desc_t func_desc(unsigned long addr) +{ + return *(struct ppc64_opd_entry *)addr; +} +static unsigned long func_addr(unsigned long addr) +{ + return func_desc(addr).funcaddr; +} +static unsigned long stub_func_addr(func_desc_t func) +{ + return func.funcaddr; +} +static unsigned int local_entry_offset(const Elf64_Sym *sym) +{ + return 0; +} +#endif + /* Like PPC32, we need little trampolines to do > 24-bit jumps (into the kernel itself). But on PPC64, these need to be used for every jump, actually, to reset r2 (TOC+0x8000). */ struct ppc64_stub_entry { - /* 28 byte jump instruction sequence (7 instructions) */ - unsigned char jump[28]; - unsigned char unused[4]; + /* 28 byte jump instruction sequence (7 instructions). We only + * need 6 instructions on ABIv2 but we always allocate 7 so + * so we don't have to modify the trampoline load instruction. */ + u32 jump[7]; + u32 unused; /* Data for the above code */ - struct ppc64_opd_entry opd; + func_desc_t funcdata; }; -/* We use a stub to fix up r2 (TOC ptr) and to jump to the (external) - function which may be more than 24-bits away. We could simply - patch the new r2 value and function pointer into the stub, but it's - significantly shorter to put these values at the end of the stub - code, and patch the stub address (32-bits relative to the TOC ptr, - r2) into the stub. */ -static struct ppc64_stub_entry ppc64_stub = -{ .jump = { -#ifdef __LITTLE_ENDIAN__ - 0x00, 0x00, 0x82, 0x3d, /* addis r12,r2, <high> */ - 0x00, 0x00, 0x8c, 0x39, /* addi r12,r12, <low> */ - /* Save current r2 value in magic place on the stack. */ - 0x28, 0x00, 0x41, 0xf8, /* std r2,40(r1) */ - 0x20, 0x00, 0x6c, 0xe9, /* ld r11,32(r12) */ - 0x28, 0x00, 0x4c, 0xe8, /* ld r2,40(r12) */ - 0xa6, 0x03, 0x69, 0x7d, /* mtctr r11 */ - 0x20, 0x04, 0x80, 0x4e /* bctr */ -#else - 0x3d, 0x82, 0x00, 0x00, /* addis r12,r2, <high> */ - 0x39, 0x8c, 0x00, 0x00, /* addi r12,r12, <low> */ +/* + * PPC64 uses 24 bit jumps, but we need to jump into other modules or + * the kernel which may be further. So we jump to a stub. + * + * For ELFv1 we need to use this to set up the new r2 value (aka TOC + * pointer). For ELFv2 it's the callee's responsibility to set up the + * new r2, but for both we need to save the old r2. + * + * We could simply patch the new r2 value and function pointer into + * the stub, but it's significantly shorter to put these values at the + * end of the stub code, and patch the stub address (32-bits relative + * to the TOC ptr, r2) into the stub. + */ + +static u32 ppc64_stub_insns[] = { + 0x3d620000, /* addis r11,r2, <high> */ + 0x396b0000, /* addi r11,r11, <low> */ /* Save current r2 value in magic place on the stack. */ - 0xf8, 0x41, 0x00, 0x28, /* std r2,40(r1) */ - 0xe9, 0x6c, 0x00, 0x20, /* ld r11,32(r12) */ - 0xe8, 0x4c, 0x00, 0x28, /* ld r2,40(r12) */ - 0x7d, 0x69, 0x03, 0xa6, /* mtctr r11 */ - 0x4e, 0x80, 0x04, 0x20 /* bctr */ + 0xf8410000|R2_STACK_OFFSET, /* std r2,R2_STACK_OFFSET(r1) */ + 0xe98b0020, /* ld r12,32(r11) */ +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + /* Set up new r2 from function descriptor */ + 0xe84b0028, /* ld r2,40(r11) */ +#endif + 0x7d8903a6, /* mtctr r12 */ + 0x4e800420 /* bctr */ +}; + +#ifdef CONFIG_DYNAMIC_FTRACE + +static u32 ppc64_stub_mask[] = { + 0xffff0000, + 0xffff0000, + 0xffffffff, + 0xffffffff, +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + 0xffffffff, +#endif + 0xffffffff, + 0xffffffff +}; + +bool is_module_trampoline(u32 *p) +{ + unsigned int i; + u32 insns[ARRAY_SIZE(ppc64_stub_insns)]; + + BUILD_BUG_ON(sizeof(ppc64_stub_insns) != sizeof(ppc64_stub_mask)); + + if (probe_kernel_read(insns, p, sizeof(insns))) + return -EFAULT; + + for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) { + u32 insna = insns[i]; + u32 insnb = ppc64_stub_insns[i]; + u32 mask = ppc64_stub_mask[i]; + + if ((insna & mask) != (insnb & mask)) + return false; + } + + return true; +} + +int module_trampoline_target(struct module *mod, u32 *trampoline, + unsigned long *target) +{ + u32 buf[2]; + u16 upper, lower; + long offset; + void *toc_entry; + + if (probe_kernel_read(buf, trampoline, sizeof(buf))) + return -EFAULT; + + upper = buf[0] & 0xffff; + lower = buf[1] & 0xffff; + + /* perform the addis/addi, both signed */ + offset = ((short)upper << 16) + (short)lower; + + /* + * Now get the address this trampoline jumps to. This + * is always 32 bytes into our trampoline stub. + */ + toc_entry = (void *)mod->arch.toc + offset + 32; + + if (probe_kernel_read(target, toc_entry, sizeof(*target))) + return -EFAULT; + + return 0; +} + #endif -} }; /* Count how many different 24-bit relocations (different symbol, different addend) */ @@ -183,6 +308,7 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, return relocs * sizeof(struct ppc64_stub_entry); } +/* Still needed for ELFv2, for .TOC. */ static void dedotify_versions(struct modversion_info *vers, unsigned long size) { @@ -193,7 +319,7 @@ static void dedotify_versions(struct modversion_info *vers, memmove(vers->name, vers->name+1, strlen(vers->name)); } -/* Undefined symbols which refer to .funcname, hack to funcname */ +/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) { unsigned int i; @@ -207,6 +333,24 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) } } +static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex) +{ + unsigned int i, numsyms; + Elf64_Sym *syms; + + syms = (Elf64_Sym *)sechdrs[symindex].sh_addr; + numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym); + + for (i = 1; i < numsyms; i++) { + if (syms[i].st_shndx == SHN_UNDEF + && strcmp(strtab + syms[i].st_name, "TOC.") == 0) + return &syms[i]; + } + return NULL; +} + int module_frob_arch_sections(Elf64_Ehdr *hdr, Elf64_Shdr *sechdrs, char *secstrings, @@ -271,21 +415,12 @@ static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me) /* Patch stub to reference function and correct r2 value. */ static inline int create_stub(Elf64_Shdr *sechdrs, struct ppc64_stub_entry *entry, - struct ppc64_opd_entry *opd, + unsigned long addr, struct module *me) { - Elf64_Half *loc1, *loc2; long reladdr; - *entry = ppc64_stub; - -#ifdef __LITTLE_ENDIAN__ - loc1 = (Elf64_Half *)&entry->jump[0]; - loc2 = (Elf64_Half *)&entry->jump[4]; -#else - loc1 = (Elf64_Half *)&entry->jump[2]; - loc2 = (Elf64_Half *)&entry->jump[6]; -#endif + memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns)); /* Stub uses address relative to r2. */ reladdr = (unsigned long)entry - my_r2(sechdrs, me); @@ -296,35 +431,33 @@ static inline int create_stub(Elf64_Shdr *sechdrs, } DEBUGP("Stub %p get data from reladdr %li\n", entry, reladdr); - *loc1 = PPC_HA(reladdr); - *loc2 = PPC_LO(reladdr); - entry->opd.funcaddr = opd->funcaddr; - entry->opd.r2 = opd->r2; + entry->jump[0] |= PPC_HA(reladdr); + entry->jump[1] |= PPC_LO(reladdr); + entry->funcdata = func_desc(addr); return 1; } -/* Create stub to jump to function described in this OPD: we need the +/* Create stub to jump to function described in this OPD/ptr: we need the stub to set up the TOC ptr (r2) for the function. */ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs, - unsigned long opdaddr, + unsigned long addr, struct module *me) { struct ppc64_stub_entry *stubs; - struct ppc64_opd_entry *opd = (void *)opdaddr; unsigned int i, num_stubs; num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stubs); /* Find this stub, or if that fails, the next avail. entry */ stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr; - for (i = 0; stubs[i].opd.funcaddr; i++) { + for (i = 0; stub_func_addr(stubs[i].funcdata); i++) { BUG_ON(i >= num_stubs); - if (stubs[i].opd.funcaddr == opd->funcaddr) + if (stub_func_addr(stubs[i].funcdata) == func_addr(addr)) return (unsigned long)&stubs[i]; } - if (!create_stub(sechdrs, &stubs[i], opd, me)) + if (!create_stub(sechdrs, &stubs[i], addr, me)) return 0; return (unsigned long)&stubs[i]; @@ -339,7 +472,8 @@ static int restore_r2(u32 *instruction, struct module *me) me->name, *instruction); return 0; } - *instruction = 0xe8410028; /* ld r2,40(r1) */ + /* ld r2,R2_STACK_OFFSET(r1) */ + *instruction = 0xe8410000 | R2_STACK_OFFSET; return 1; } @@ -357,6 +491,17 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, DEBUGP("Applying ADD relocate section %u to %u\n", relsec, sechdrs[relsec].sh_info); + + /* First time we're called, we can fix up .TOC. */ + if (!me->arch.toc_fixed) { + sym = find_dot_toc(sechdrs, strtab, symindex); + /* It's theoretically possible that a module doesn't want a + * .TOC. so don't fail it just for that. */ + if (sym) + sym->st_value = my_r2(sechdrs, me); + me->arch.toc_fixed = true; + } + for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) { /* This is where to make the change */ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr @@ -453,7 +598,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, return -ENOENT; if (!restore_r2((u32 *)location + 1, me)) return -ENOEXEC; - } + } else + value += local_entry_offset(sym); /* Convert value to relative */ value -= (unsigned long)location; @@ -474,6 +620,31 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, *location = value - (unsigned long)location; break; + case R_PPC64_TOCSAVE: + /* + * Marker reloc indicates we don't have to save r2. + * That would only save us one instruction, so ignore + * it. + */ + break; + + case R_PPC64_REL16_HA: + /* Subtract location pointer */ + value -= (unsigned long)location; + value = ((value + 0x8000) >> 16); + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + + case R_PPC64_REL16_LO: + /* Subtract location pointer */ + value -= (unsigned long)location; + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + default: printk("%s: Unknown ADD relocation: %lu\n", me->name, diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 24d342e91790..b49c72fd7f16 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/delay.h> #include <linux/export.h> #include <linux/of_address.h> #include <linux/of_pci.h> @@ -120,6 +121,25 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus, return 1; } +void pcibios_reset_secondary_bus(struct pci_dev *dev) +{ + u16 ctrl; + + if (ppc_md.pcibios_reset_secondary_bus) { + ppc_md.pcibios_reset_secondary_bus(dev); + return; + } + + pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl); + ctrl |= PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + msleep(2); + + ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + ssleep(1); +} + static resource_size_t pcibios_io_size(const struct pci_controller *hose) { #ifdef CONFIG_PPC64 @@ -646,60 +666,36 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, void pci_process_bridge_OF_ranges(struct pci_controller *hose, struct device_node *dev, int primary) { - const __be32 *ranges; - int rlen; - int pna = of_n_addr_cells(dev); - int np = pna + 5; int memno = 0; - u32 pci_space; - unsigned long long pci_addr, cpu_addr, pci_next, cpu_next, size; struct resource *res; + struct of_pci_range range; + struct of_pci_range_parser parser; printk(KERN_INFO "PCI host bridge %s %s ranges:\n", dev->full_name, primary ? "(primary)" : ""); - /* Get ranges property */ - ranges = of_get_property(dev, "ranges", &rlen); - if (ranges == NULL) + /* Check for ranges property */ + if (of_pci_range_parser_init(&parser, dev)) return; /* Parse it */ - while ((rlen -= np * 4) >= 0) { - /* Read next ranges element */ - pci_space = of_read_number(ranges, 1); - pci_addr = of_read_number(ranges + 1, 2); - cpu_addr = of_translate_address(dev, ranges + 3); - size = of_read_number(ranges + pna + 3, 2); - ranges += np; - + for_each_of_pci_range(&parser, &range) { /* If we failed translation or got a zero-sized region * (some FW try to feed us with non sensical zero sized regions * such as power3 which look like some kind of attempt at exposing * the VGA memory hole) */ - if (cpu_addr == OF_BAD_ADDR || size == 0) + if (range.cpu_addr == OF_BAD_ADDR || range.size == 0) continue; - /* Now consume following elements while they are contiguous */ - for (; rlen >= np * sizeof(u32); - ranges += np, rlen -= np * 4) { - if (of_read_number(ranges, 1) != pci_space) - break; - pci_next = of_read_number(ranges + 1, 2); - cpu_next = of_translate_address(dev, ranges + 3); - if (pci_next != pci_addr + size || - cpu_next != cpu_addr + size) - break; - size += of_read_number(ranges + pna + 3, 2); - } - /* Act based on address space type */ res = NULL; - switch ((pci_space >> 24) & 0x3) { - case 1: /* PCI IO space */ + switch (range.flags & IORESOURCE_TYPE_BITS) { + case IORESOURCE_IO: printk(KERN_INFO " IO 0x%016llx..0x%016llx -> 0x%016llx\n", - cpu_addr, cpu_addr + size - 1, pci_addr); + range.cpu_addr, range.cpu_addr + range.size - 1, + range.pci_addr); /* We support only one IO range */ if (hose->pci_io_size) { @@ -709,11 +705,12 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, } #ifdef CONFIG_PPC32 /* On 32 bits, limit I/O space to 16MB */ - if (size > 0x01000000) - size = 0x01000000; + if (range.size > 0x01000000) + range.size = 0x01000000; /* 32 bits needs to map IOs here */ - hose->io_base_virt = ioremap(cpu_addr, size); + hose->io_base_virt = ioremap(range.cpu_addr, + range.size); /* Expect trouble if pci_addr is not 0 */ if (primary) @@ -723,20 +720,20 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, /* pci_io_size and io_base_phys always represent IO * space starting at 0 so we factor in pci_addr */ - hose->pci_io_size = pci_addr + size; - hose->io_base_phys = cpu_addr - pci_addr; + hose->pci_io_size = range.pci_addr + range.size; + hose->io_base_phys = range.cpu_addr - range.pci_addr; /* Build resource */ res = &hose->io_resource; - res->flags = IORESOURCE_IO; - res->start = pci_addr; + range.cpu_addr = range.pci_addr; break; - case 2: /* PCI Memory space */ - case 3: /* PCI 64 bits Memory space */ + case IORESOURCE_MEM: printk(KERN_INFO " MEM 0x%016llx..0x%016llx -> 0x%016llx %s\n", - cpu_addr, cpu_addr + size - 1, pci_addr, - (pci_space & 0x40000000) ? "Prefetch" : ""); + range.cpu_addr, range.cpu_addr + range.size - 1, + range.pci_addr, + (range.pci_space & 0x40000000) ? + "Prefetch" : ""); /* We support only 3 memory ranges */ if (memno >= 3) { @@ -745,28 +742,21 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, continue; } /* Handles ISA memory hole space here */ - if (pci_addr == 0) { + if (range.pci_addr == 0) { if (primary || isa_mem_base == 0) - isa_mem_base = cpu_addr; - hose->isa_mem_phys = cpu_addr; - hose->isa_mem_size = size; + isa_mem_base = range.cpu_addr; + hose->isa_mem_phys = range.cpu_addr; + hose->isa_mem_size = range.size; } /* Build resource */ - hose->mem_offset[memno] = cpu_addr - pci_addr; + hose->mem_offset[memno] = range.cpu_addr - + range.pci_addr; res = &hose->mem_resources[memno++]; - res->flags = IORESOURCE_MEM; - if (pci_space & 0x40000000) - res->flags |= IORESOURCE_PREFETCH; - res->start = cpu_addr; break; } if (res != NULL) { - res->name = dev->full_name; - res->end = res->start + size - 1; - res->parent = NULL; - res->sibling = NULL; - res->child = NULL; + of_pci_range_to_resource(&range, dev, res); } } } diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 059e244484fe..44562aa97f16 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -304,6 +304,9 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus, struct pci_dev *dev = NULL; const __be32 *reg; int reglen, devfn; +#ifdef CONFIG_EEH + struct eeh_dev *edev = of_node_to_eeh_dev(dn); +#endif pr_debug(" * %s\n", dn->full_name); if (!of_device_is_available(dn)) @@ -321,6 +324,12 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus, return dev; } + /* Device removed permanently ? */ +#ifdef CONFIG_EEH + if (edev && (edev->mode & EEH_DEV_REMOVED)) + return NULL; +#endif + /* create a new pci_dev for this device */ dev = of_create_pci_dev(dn, bus, devfn); if (!dev) diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 450850a49dce..48d17d6fca5b 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -155,9 +155,7 @@ EXPORT_SYMBOL(__cmpdi2); #endif long long __bswapdi2(long long); EXPORT_SYMBOL(__bswapdi2); -#ifdef __BIG_ENDIAN__ EXPORT_SYMBOL(memcpy); -#endif EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memcmp); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 31d021506d21..8a1edbe26b8f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -54,6 +54,7 @@ #ifdef CONFIG_PPC64 #include <asm/firmware.h> #endif +#include <asm/code-patching.h> #include <linux/kprobes.h> #include <linux/kdebug.h> @@ -495,14 +496,21 @@ static inline int set_dawr(struct arch_hw_breakpoint *brk) return 0; } -int set_breakpoint(struct arch_hw_breakpoint *brk) +void __set_breakpoint(struct arch_hw_breakpoint *brk) { __get_cpu_var(current_brk) = *brk; if (cpu_has_feature(CPU_FTR_DAWR)) - return set_dawr(brk); + set_dawr(brk); + else + set_dabr(brk); +} - return set_dabr(brk); +void set_breakpoint(struct arch_hw_breakpoint *brk) +{ + preempt_disable(); + __set_breakpoint(brk); + preempt_enable(); } #ifdef CONFIG_PPC64 @@ -834,7 +842,7 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifndef CONFIG_HAVE_HW_BREAKPOINT if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk))) - set_breakpoint(&new->thread.hw_brk); + __set_breakpoint(&new->thread.hw_brk); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif @@ -1108,7 +1116,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, struct thread_info *ti = (void *)task_stack_page(p); memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); - childregs->gpr[14] = usp; /* function */ + /* function */ + if (usp) + childregs->gpr[14] = ppc_function_entry((void *)usp); #ifdef CONFIG_PPC64 clear_tsk_thread_flag(p, TIF_32BIT); childregs->softe = 1; @@ -1187,17 +1197,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, if (cpu_has_feature(CPU_FTR_HAS_PPR)) p->thread.ppr = INIT_PPR; #endif - /* - * The PPC64 ABI makes use of a TOC to contain function - * pointers. The function (ret_from_except) is actually a pointer - * to the TOC entry. The first entry is a pointer to the actual - * function. - */ -#ifdef CONFIG_PPC64 - kregs->nip = *((unsigned long *)f); -#else - kregs->nip = (unsigned long)f; -#endif + kregs->nip = ppc_function_entry(f); return 0; } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 668aa4791fd7..613a860a203c 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -29,11 +29,11 @@ #include <linux/bitops.h> #include <linux/export.h> #include <linux/kexec.h> -#include <linux/debugfs.h> #include <linux/irq.h> #include <linux/memblock.h> #include <linux/of.h> #include <linux/of_fdt.h> +#include <linux/libfdt.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -118,14 +118,14 @@ static void __init move_device_tree(void) DBG("-> move_device_tree\n"); start = __pa(initial_boot_params); - size = be32_to_cpu(initial_boot_params->totalsize); + size = fdt_totalsize(initial_boot_params); if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) || overlaps_crashkernel(start, size) || overlaps_initrd(start, size)) { p = __va(memblock_alloc(size, PAGE_SIZE)); memcpy(p, initial_boot_params, size); - initial_boot_params = (struct boot_param_header *)p; + initial_boot_params = p; DBG("Moved device tree to 0x%p\n", p); } @@ -163,7 +163,7 @@ static struct ibm_pa_feature { {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, }; -static void __init scan_features(unsigned long node, unsigned char *ftrs, +static void __init scan_features(unsigned long node, const unsigned char *ftrs, unsigned long tablelen, struct ibm_pa_feature *fp, unsigned long ft_size) @@ -202,8 +202,8 @@ static void __init scan_features(unsigned long node, unsigned char *ftrs, static void __init check_cpu_pa_features(unsigned long node) { - unsigned char *pa_ftrs; - unsigned long tablelen; + const unsigned char *pa_ftrs; + int tablelen; pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen); if (pa_ftrs == NULL) @@ -216,7 +216,7 @@ static void __init check_cpu_pa_features(unsigned long node) #ifdef CONFIG_PPC_STD_MMU_64 static void __init check_cpu_slb_size(unsigned long node) { - __be32 *slb_size_ptr; + const __be32 *slb_size_ptr; slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL); if (slb_size_ptr != NULL) { @@ -257,7 +257,7 @@ static struct feature_property { static inline void identical_pvr_fixup(unsigned long node) { unsigned int pvr; - char *model = of_get_flat_dt_prop(node, "model", NULL); + const char *model = of_get_flat_dt_prop(node, "model", NULL); /* * Since 440GR(x)/440EP(x) processors have the same pvr, @@ -295,11 +295,11 @@ static int __init early_init_dt_scan_cpus(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); const __be32 *prop; const __be32 *intserv; int i, nthreads; - unsigned long len; + int len; int found = -1; int found_thread = 0; @@ -325,9 +325,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node, * version 2 of the kexec param format adds the phys cpuid of * booted proc. */ - if (be32_to_cpu(initial_boot_params->version) >= 2) { + if (fdt_version(initial_boot_params) >= 2) { if (be32_to_cpu(intserv[i]) == - be32_to_cpu(initial_boot_params->boot_cpuid_phys)) { + fdt_boot_cpuid_phys(initial_boot_params)) { found = boot_cpu_count; found_thread = i; } @@ -392,7 +392,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node, int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname, int depth, void *data) { - unsigned long *lprop; /* All these set by kernel, so no need to convert endian */ + const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */ /* Use common scan routine to determine if this is the chosen node */ if (early_init_dt_scan_chosen(node, uname, depth, data) == 0) @@ -443,8 +443,9 @@ int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname, */ static int __init early_init_dt_scan_drconf_memory(unsigned long node) { - __be32 *dm, *ls, *usm; - unsigned long l, n, flags; + const __be32 *dm, *ls, *usm; + int l; + unsigned long n, flags; u64 base, size, memblock_size; unsigned int is_kexec_kdump = 0, rngs; @@ -564,9 +565,12 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) static void __init early_reserve_mem_dt(void) { - unsigned long i, len, dt_root; + unsigned long i, dt_root; + int len; const __be32 *prop; + early_init_fdt_scan_reserved_mem(); + dt_root = of_get_flat_dt_root(); prop = of_get_flat_dt_prop(dt_root, "reserved-ranges", &len); @@ -589,24 +593,14 @@ static void __init early_reserve_mem_dt(void) memblock_reserve(base, size); } } - - early_init_fdt_scan_reserved_mem(); } static void __init early_reserve_mem(void) { - u64 base, size; __be64 *reserve_map; - unsigned long self_base; - unsigned long self_size; reserve_map = (__be64 *)(((unsigned long)initial_boot_params) + - be32_to_cpu(initial_boot_params->off_mem_rsvmap)); - - /* before we do anything, lets reserve the dt blob */ - self_base = __pa((unsigned long)initial_boot_params); - self_size = be32_to_cpu(initial_boot_params->totalsize); - memblock_reserve(self_base, self_size); + fdt_off_mem_rsvmap(initial_boot_params)); /* Look for the new "reserved-regions" property in the DT */ early_reserve_mem_dt(); @@ -636,26 +630,12 @@ static void __init early_reserve_mem(void) size_32 = be32_to_cpup(reserve_map_32++); if (size_32 == 0) break; - /* skip if the reservation is for the blob */ - if (base_32 == self_base && size_32 == self_size) - continue; DBG("reserving: %x -> %x\n", base_32, size_32); memblock_reserve(base_32, size_32); } return; } #endif - DBG("Processing reserve map\n"); - - /* Handle the reserve map in the fdt blob if it exists */ - while (1) { - base = be64_to_cpup(reserve_map++); - size = be64_to_cpup(reserve_map++); - if (size == 0) - break; - DBG("reserving: %llx -> %llx\n", base, size); - memblock_reserve(base, size); - } } void __init early_init_devtree(void *params) @@ -922,23 +902,3 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { return (int)phys_id == get_hard_smp_processor_id(cpu); } - -#if defined(CONFIG_DEBUG_FS) && defined(DEBUG) -static struct debugfs_blob_wrapper flat_dt_blob; - -static int __init export_flat_device_tree(void) -{ - struct dentry *d; - - flat_dt_blob.data = initial_boot_params; - flat_dt_blob.size = be32_to_cpu(initial_boot_params->totalsize); - - d = debugfs_create_blob("flat-device-tree", S_IFREG | S_IRUSR, - powerpc_debugfs_root, &flat_dt_blob); - if (!d) - return 1; - - return 0; -} -__initcall(export_flat_device_tree); -#endif diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index b0c263da219a..77aa1e95e904 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -23,7 +23,7 @@ strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224 reloc_got2 kernstart_addr memstart_addr linux_banner _stext opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry boot_command_line __prom_init_toc_start __prom_init_toc_end -btext_setup_display" +btext_setup_display TOC." NM="$1" OBJ="$2" diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 8cd5ed049b5d..8b4c857c1421 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1142,7 +1142,7 @@ void __init rtas_initialize(void) int __init early_init_dt_scan_rtas(unsigned long node, const char *uname, int depth, void *data) { - u32 *basep, *entryp, *sizep; + const u32 *basep, *entryp, *sizep; if (depth != 1 || strcmp(uname, "rtas") != 0) return 0; diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 7d4c7172f38e..c168337aef9d 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -80,10 +80,6 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val) if (ret) return PCIBIOS_DEVICE_NOT_FOUND; - if (returnval == EEH_IO_ERROR_VALUE(size) && - eeh_dev_check_failure(of_node_to_eeh_dev(pdn->node))) - return PCIBIOS_DEVICE_NOT_FOUND; - return PCIBIOS_SUCCESSFUL; } @@ -92,18 +88,39 @@ static int rtas_pci_read_config(struct pci_bus *bus, int where, int size, u32 *val) { struct device_node *busdn, *dn; - - busdn = pci_bus_to_OF_node(bus); + struct pci_dn *pdn; + bool found = false; +#ifdef CONFIG_EEH + struct eeh_dev *edev; +#endif + int ret; /* Search only direct children of the bus */ + *val = 0xFFFFFFFF; + busdn = pci_bus_to_OF_node(bus); for (dn = busdn->child; dn; dn = dn->sibling) { - struct pci_dn *pdn = PCI_DN(dn); + pdn = PCI_DN(dn); if (pdn && pdn->devfn == devfn - && of_device_is_available(dn)) - return rtas_read_config(pdn, where, size, val); + && of_device_is_available(dn)) { + found = true; + break; + } } - return PCIBIOS_DEVICE_NOT_FOUND; + if (!found) + return PCIBIOS_DEVICE_NOT_FOUND; +#ifdef CONFIG_EEH + edev = of_node_to_eeh_dev(dn); + if (edev && edev->pe && edev->pe->state & EEH_PE_RESET) + return PCIBIOS_DEVICE_NOT_FOUND; +#endif + + ret = rtas_read_config(pdn, where, size, val); + if (*val == EEH_IO_ERROR_VALUE(size) && + eeh_dev_check_failure(of_node_to_eeh_dev(dn))) + return PCIBIOS_DEVICE_NOT_FOUND; + + return ret; } int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val) @@ -136,17 +153,34 @@ static int rtas_pci_write_config(struct pci_bus *bus, int where, int size, u32 val) { struct device_node *busdn, *dn; - - busdn = pci_bus_to_OF_node(bus); + struct pci_dn *pdn; + bool found = false; +#ifdef CONFIG_EEH + struct eeh_dev *edev; +#endif + int ret; /* Search only direct children of the bus */ + busdn = pci_bus_to_OF_node(bus); for (dn = busdn->child; dn; dn = dn->sibling) { - struct pci_dn *pdn = PCI_DN(dn); + pdn = PCI_DN(dn); if (pdn && pdn->devfn == devfn - && of_device_is_available(dn)) - return rtas_write_config(pdn, where, size, val); + && of_device_is_available(dn)) { + found = true; + break; + } } - return PCIBIOS_DEVICE_NOT_FOUND; + + if (!found) + return PCIBIOS_DEVICE_NOT_FOUND; +#ifdef CONFIG_EEH + edev = of_node_to_eeh_dev(dn); + if (edev && edev->pe && (edev->pe->state & EEH_PE_RESET)) + return PCIBIOS_DEVICE_NOT_FOUND; +#endif + ret = rtas_write_config(pdn, where, size, val); + + return ret; } static struct pci_ops rtas_pci_ops = { diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 79b7612ac6fa..d4d418376f99 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -212,6 +212,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long cpu_id = (unsigned long)v - 1; unsigned int pvr; + unsigned long proc_freq; unsigned short maj; unsigned short min; @@ -263,12 +264,19 @@ static int show_cpuinfo(struct seq_file *m, void *v) #endif /* CONFIG_TAU */ /* - * Assume here that all clock rates are the same in a - * smp system. -- Cort + * Platforms that have variable clock rates, should implement + * the method ppc_md.get_proc_freq() that reports the clock + * rate of a given cpu. The rest can use ppc_proc_freq to + * report the clock rate that is same across all cpus. */ - if (ppc_proc_freq) + if (ppc_md.get_proc_freq) + proc_freq = ppc_md.get_proc_freq(cpu_id); + else + proc_freq = ppc_proc_freq; + + if (proc_freq) seq_printf(m, "clock\t\t: %lu.%06luMHz\n", - ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); + proc_freq / 1000000, proc_freq % 1000000); if (ppc_md.show_percpuinfo != NULL) ppc_md.show_percpuinfo(m, cpu_id); @@ -382,9 +390,10 @@ void __init check_for_initrd(void) #ifdef CONFIG_SMP -int threads_per_core, threads_shift; +int threads_per_core, threads_per_subcore, threads_shift; cpumask_t threads_core_mask; EXPORT_SYMBOL_GPL(threads_per_core); +EXPORT_SYMBOL_GPL(threads_per_subcore); EXPORT_SYMBOL_GPL(threads_shift); EXPORT_SYMBOL_GPL(threads_core_mask); @@ -393,6 +402,7 @@ static void __init cpu_init_thread_core_maps(int tpc) int i; threads_per_core = tpc; + threads_per_subcore = tpc; cpumask_clear(&threads_core_mask); /* This implementation only supports power of 2 number of threads @@ -718,33 +728,6 @@ static int powerpc_debugfs_init(void) arch_initcall(powerpc_debugfs_init); #endif -#ifdef CONFIG_BOOKE_WDT -extern u32 booke_wdt_enabled; -extern u32 booke_wdt_period; - -/* Checks wdt=x and wdt_period=xx command-line option */ -notrace int __init early_parse_wdt(char *p) -{ - if (p && strncmp(p, "0", 1) != 0) - booke_wdt_enabled = 1; - - return 0; -} -early_param("wdt", early_parse_wdt); - -int __init early_parse_wdt_period(char *p) -{ - unsigned long ret; - if (p) { - if (!kstrtol(p, 0, &ret)) - booke_wdt_period = ret; - } - - return 0; -} -early_param("wdt_period", early_parse_wdt_period); -#endif /* CONFIG_BOOKE_WDT */ - void ppc_printk_progress(char *s, unsigned short hex) { pr_info("%s\n", s); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index fbe24377eda3..ee082d771178 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -36,6 +36,7 @@ #include <linux/lockdep.h> #include <linux/memblock.h> #include <linux/hugetlb.h> +#include <linux/memory.h> #include <asm/io.h> #include <asm/kdump.h> @@ -341,7 +342,7 @@ void smp_release_cpus(void) ptr = (unsigned long *)((unsigned long)&__secondary_hold_spinloop - PHYSICAL_START); - *ptr = __pa(generic_secondary_smp_init); + *ptr = ppc_function_entry(generic_secondary_smp_init); /* And wait a bit for them to catch up */ for (i = 0; i < 100000; i++) { @@ -780,6 +781,15 @@ void __init setup_per_cpu_areas(void) } #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +unsigned long memory_block_size_bytes(void) +{ + if (ppc_md.memory_block_size) + return ppc_md.memory_block_size(); + + return MIN_MEMORY_BLOCK_SIZE; +} +#endif #if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO) struct ppc_pci_io ppc_pci_io; diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 8fc4177ed65a..1c794cef2883 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -134,7 +134,7 @@ static int do_signal(struct pt_regs *regs) */ if (current->thread.hw_brk.address && current->thread.hw_brk.type) - set_breakpoint(¤t->thread.hw_brk); + __set_breakpoint(¤t->thread.hw_brk); #endif /* Re-enable the breakpoints for the signal stack */ thread_change_pc(current, regs); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 10ffffef0414..7753af2d2613 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -36,6 +36,7 @@ #include <linux/atomic.h> #include <asm/irq.h> #include <asm/hw_irq.h> +#include <asm/kvm_ppc.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/prom.h> @@ -390,6 +391,7 @@ void smp_prepare_boot_cpu(void) #ifdef CONFIG_PPC64 paca[boot_cpuid].__current = current; #endif + set_numa_node(numa_cpu_lookup_table[boot_cpuid]); current_set[boot_cpuid] = task_thread_info(current); } @@ -457,38 +459,9 @@ int generic_check_cpu_restart(unsigned int cpu) return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE; } -static atomic_t secondary_inhibit_count; - -/* - * Don't allow secondary CPU threads to come online - */ -void inhibit_secondary_onlining(void) +static bool secondaries_inhibited(void) { - /* - * This makes secondary_inhibit_count stable during cpu - * online/offline operations. - */ - get_online_cpus(); - - atomic_inc(&secondary_inhibit_count); - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(inhibit_secondary_onlining); - -/* - * Allow secondary CPU threads to come online again - */ -void uninhibit_secondary_onlining(void) -{ - get_online_cpus(); - atomic_dec(&secondary_inhibit_count); - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(uninhibit_secondary_onlining); - -static int secondaries_inhibited(void) -{ - return atomic_read(&secondary_inhibit_count); + return kvm_hv_mode_active(); } #else /* HOTPLUG_CPU */ @@ -517,7 +490,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) * Don't allow secondary threads to come online if inhibited */ if (threads_per_core > 1 && secondaries_inhibited() && - cpu % threads_per_core != 0) + cpu_thread_in_subcore(cpu)) return -EBUSY; if (smp_ops == NULL || @@ -750,6 +723,12 @@ void start_secondary(void *unused) } traverse_core_siblings(cpu, true); + /* + * numa_node_id() works after this. + */ + set_numa_node(numa_cpu_lookup_table[cpu]); + set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); + smp_wmb(); notify_cpu_starting(cpu); set_cpu_online(cpu, true); diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index d90d4b7810d6..67fd2fd2620a 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -404,7 +404,7 @@ void ppc_enable_pmcs(void) } EXPORT_SYMBOL(ppc_enable_pmcs); -#define __SYSFS_SPRSETUP(NAME, ADDRESS, EXTRA) \ +#define __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, EXTRA) \ static void read_##NAME(void *val) \ { \ *(unsigned long *)val = mfspr(ADDRESS); \ @@ -413,7 +413,9 @@ static void write_##NAME(void *val) \ { \ EXTRA; \ mtspr(ADDRESS, *(unsigned long *)val); \ -} \ +} + +#define __SYSFS_SPRSETUP_SHOW_STORE(NAME) \ static ssize_t show_##NAME(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ @@ -436,10 +438,15 @@ static ssize_t __used \ return count; \ } -#define SYSFS_PMCSETUP(NAME, ADDRESS) \ - __SYSFS_SPRSETUP(NAME, ADDRESS, ppc_enable_pmcs()) -#define SYSFS_SPRSETUP(NAME, ADDRESS) \ - __SYSFS_SPRSETUP(NAME, ADDRESS, ) +#define SYSFS_PMCSETUP(NAME, ADDRESS) \ + __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ppc_enable_pmcs()) \ + __SYSFS_SPRSETUP_SHOW_STORE(NAME) +#define SYSFS_SPRSETUP(NAME, ADDRESS) \ + __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ) \ + __SYSFS_SPRSETUP_SHOW_STORE(NAME) + +#define SYSFS_SPRSETUP_SHOW_STORE(NAME) \ + __SYSFS_SPRSETUP_SHOW_STORE(NAME) /* Let's define all possible registers, we'll only hook up the ones * that are implemented on the current processor @@ -477,7 +484,6 @@ SYSFS_PMCSETUP(pmc8, SPRN_PMC8); SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); SYSFS_SPRSETUP(purr, SPRN_PURR); SYSFS_SPRSETUP(spurr, SPRN_SPURR); -SYSFS_SPRSETUP(dscr, SPRN_DSCR); SYSFS_SPRSETUP(pir, SPRN_PIR); /* @@ -487,12 +493,27 @@ SYSFS_SPRSETUP(pir, SPRN_PIR); */ static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra); static DEVICE_ATTR(spurr, 0400, show_spurr, NULL); -static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr); static DEVICE_ATTR(purr, 0400, show_purr, store_purr); static DEVICE_ATTR(pir, 0400, show_pir, NULL); -unsigned long dscr_default = 0; -EXPORT_SYMBOL(dscr_default); +static unsigned long dscr_default; + +static void read_dscr(void *val) +{ + *(unsigned long *)val = get_paca()->dscr_default; +} + +static void write_dscr(void *val) +{ + get_paca()->dscr_default = *(unsigned long *)val; + if (!current->thread.dscr_inherit) { + current->thread.dscr = *(unsigned long *)val; + mtspr(SPRN_DSCR, *(unsigned long *)val); + } +} + +SYSFS_SPRSETUP_SHOW_STORE(dscr); +static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr); static void add_write_permission_dev_attr(struct device_attribute *attr) { @@ -505,14 +526,6 @@ static ssize_t show_dscr_default(struct device *dev, return sprintf(buf, "%lx\n", dscr_default); } -static void update_dscr(void *dummy) -{ - if (!current->thread.dscr_inherit) { - current->thread.dscr = dscr_default; - mtspr(SPRN_DSCR, dscr_default); - } -} - static ssize_t __used store_dscr_default(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -525,7 +538,7 @@ static ssize_t __used store_dscr_default(struct device *dev, return -EINVAL; dscr_default = val; - on_each_cpu(update_dscr, NULL, 1); + on_each_cpu(write_dscr, &val, 1); return count; } diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 93219c34af32..895c50ca943c 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -17,12 +17,12 @@ #include <asm/ppc_asm.h> #ifdef CONFIG_PPC64 -#define SYSCALL(func) .llong .sys_##func,.sys_##func -#define COMPAT_SYS(func) .llong .sys_##func,.compat_sys_##func -#define PPC_SYS(func) .llong .ppc_##func,.ppc_##func -#define OLDSYS(func) .llong .sys_ni_syscall,.sys_ni_syscall -#define SYS32ONLY(func) .llong .sys_ni_syscall,.compat_sys_##func -#define SYSX(f, f3264, f32) .llong .f,.f3264 +#define SYSCALL(func) .llong DOTSYM(sys_##func),DOTSYM(sys_##func) +#define COMPAT_SYS(func) .llong DOTSYM(sys_##func),DOTSYM(compat_sys_##func) +#define PPC_SYS(func) .llong DOTSYM(ppc_##func),DOTSYM(ppc_##func) +#define OLDSYS(func) .llong DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall) +#define SYS32ONLY(func) .llong DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func) +#define SYSX(f, f3264, f32) .llong DOTSYM(f),DOTSYM(f3264) #else #define SYSCALL(func) .long sys_##func #define COMPAT_SYS(func) .long sys_##func @@ -36,6 +36,8 @@ #define PPC_SYS_SPU(func) PPC_SYS(func) #define SYSX_SPU(f, f3264, f32) SYSX(f, f3264, f32) +.section .rodata,"a" + #ifdef CONFIG_PPC64 #define sys_sigpending sys_ni_syscall #define sys_old_getrlimit sys_ni_syscall @@ -43,5 +45,7 @@ .p2align 3 #endif -_GLOBAL(sys_call_table) +.globl sys_call_table +sys_call_table: + #include <asm/systbl.h> diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 03567c05950a..2a324f4cb1b9 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -10,6 +10,7 @@ #include <asm/ppc-opcode.h> #include <asm/ptrace.h> #include <asm/reg.h> +#include <asm/bug.h> #ifdef CONFIG_VSX /* See fpu.S, this is borrowed from there */ @@ -41,7 +42,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ /* Stack frame offsets for local variables. */ #define TM_FRAME_L0 TM_FRAME_SIZE-16 #define TM_FRAME_L1 TM_FRAME_SIZE-8 -#define STACK_PARAM(x) (48+((x)*8)) /* In order to access the TM SPRs, TM must be enabled. So, do so: */ @@ -78,12 +78,6 @@ _GLOBAL(tm_abort) TABORT(R3) blr - .section ".toc","aw" -DSCR_DEFAULT: - .tc dscr_default[TC],dscr_default - - .section ".text" - /* void tm_reclaim(struct thread_struct *thread, * unsigned long orig_msr, * uint8_t cause) @@ -108,12 +102,12 @@ _GLOBAL(tm_reclaim) mflr r0 stw r6, 8(r1) std r0, 16(r1) - std r2, 40(r1) + std r2, STK_GOT(r1) stdu r1, -TM_FRAME_SIZE(r1) /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */ - std r3, STACK_PARAM(0)(r1) + std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) /* We need to setup MSR for VSX register save instructions. Here we @@ -175,6 +169,13 @@ dont_backup_vec: stfd fr0,FPSTATE_FPSCR(r7) dont_backup_fp: + /* Do sanity check on MSR to make sure we are suspended */ + li r7, (MSR_TS_S)@higher + srdi r6, r14, 32 + and r6, r6, r7 +1: tdeqi r6, 0 + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + /* The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. @@ -202,7 +203,7 @@ dont_backup_fp: /* Now get some more GPRS free */ std r7, GPR7(r1) /* Temporary stash */ std r12, GPR12(r1) /* '' '' '' */ - ld r12, STACK_PARAM(0)(r1) /* Param 0, thread_struct * */ + ld r12, STK_PARAM(R3)(r1) /* Param 0, thread_struct * */ std r11, THREAD_TM_PPR(r12) /* Store PPR and free r11 */ @@ -289,11 +290,10 @@ dont_backup_fp: ld r0, 16(r1) mtcr r4 mtlr r0 - ld r2, 40(r1) + ld r2, STK_GOT(r1) - /* Load system default DSCR */ - ld r4, DSCR_DEFAULT@toc(r2) - ld r0, 0(r4) + /* Load CPU's default DSCR */ + ld r0, PACA_DSCR(r13) mtspr SPRN_DSCR, r0 blr @@ -312,7 +312,7 @@ _GLOBAL(__tm_recheckpoint) mflr r0 stw r5, 8(r1) std r0, 16(r1) - std r2, 40(r1) + std r2, STK_GOT(r1) stdu r1, -TM_FRAME_SIZE(r1) /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. @@ -320,8 +320,6 @@ _GLOBAL(__tm_recheckpoint) */ SAVE_NVGPRS(r1) - std r1, PACAR1(r13) - /* Load complete register state from ts_ckpt* registers */ addi r7, r3, PT_CKPT_REGS /* Thread's ckpt_regs */ @@ -385,12 +383,10 @@ restore_gprs: /* ******************** CR,LR,CCR,MSR ********** */ ld r4, _CTR(r7) ld r5, _LINK(r7) - ld r6, _CCR(r7) ld r8, _XER(r7) mtctr r4 mtlr r5 - mtcr r6 mtxer r8 /* ******************** TAR ******************** */ @@ -406,7 +402,8 @@ restore_gprs: li r4, 0 mtmsrd r4, 1 - REST_4GPRS(0, r7) /* GPR0-3 */ + REST_GPR(0, r7) /* GPR0 */ + REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ REST_4GPRS(8, r7) /* GPR8-11 */ REST_2GPRS(12, r7) /* GPR12-13 */ @@ -418,6 +415,31 @@ restore_gprs: mtspr SPRN_DSCR, r5 mtspr SPRN_PPR, r6 + /* Do final sanity check on TEXASR to make sure FS is set. Do this + * here before we load up the userspace r1 so any bugs we hit will get + * a call chain */ + mfspr r5, SPRN_TEXASR + srdi r5, r5, 16 + li r6, (TEXASR_FS)@h + and r6, r6, r5 +1: tdeqi r6, 0 + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + + /* Do final sanity check on MSR to make sure we are not transactional + * or suspended + */ + mfmsr r6 + li r5, (MSR_TS_MASK)@higher + srdi r6, r6, 32 + and r6, r6, r5 +1: tdnei r6, 0 + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + + /* Restore CR */ + ld r6, _CCR(r7) + mtcr r6 + + REST_GPR(1, r7) /* GPR1 */ REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) ld r7, GPR7(r7) @@ -448,11 +470,10 @@ restore_gprs: ld r0, 16(r1) mtcr r4 mtlr r0 - ld r2, 40(r1) + ld r2, STK_GOT(r1) - /* Load system default DSCR */ - ld r4, DSCR_DEFAULT@toc(r2) - ld r0, 0(r4) + /* Load CPU's default DSCR */ + ld r0, PACA_DSCR(r13) mtspr SPRN_DSCR, r0 blr diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index aba05bbb3e74..7a12edbb61e7 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1236,7 +1236,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, int core; struct kvmppc_vcore *vcore; - core = id / threads_per_core; + core = id / threads_per_subcore; if (core >= KVM_MAX_VCORES) goto out; @@ -1286,7 +1286,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, init_waitqueue_head(&vcore->wq); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; - vcore->first_vcpuid = core * threads_per_core; + vcore->first_vcpuid = core * threads_per_subcore; vcore->kvm = kvm; } kvm->arch.vcores[core] = vcore; @@ -1476,16 +1476,19 @@ static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc) static int on_primary_thread(void) { int cpu = smp_processor_id(); - int thr = cpu_thread_in_core(cpu); + int thr; - if (thr) + /* Are we on a primary subcore? */ + if (cpu_thread_in_subcore(cpu)) return 0; - while (++thr < threads_per_core) + + thr = 0; + while (++thr < threads_per_subcore) if (cpu_online(cpu + thr)) return 0; /* Grab all hw threads so they can't go into the kernel */ - for (thr = 1; thr < threads_per_core; ++thr) { + for (thr = 1; thr < threads_per_subcore; ++thr) { if (kvmppc_grab_hwthread(cpu + thr)) { /* Couldn't grab one; let the others go */ do { @@ -1544,15 +1547,18 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) } /* - * Make sure we are running on thread 0, and that - * secondary threads are offline. + * Make sure we are running on primary threads, and that secondary + * threads are offline. Also check if the number of threads in this + * guest are greater than the current system threads per guest. */ - if (threads_per_core > 1 && !on_primary_thread()) { + if ((threads_per_core > 1) && + ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) { list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) vcpu->arch.ret = -EBUSY; goto out; } + vc->pcpu = smp_processor_id(); list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { kvmppc_start_thread(vcpu); @@ -1580,7 +1586,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) /* wait for secondary threads to finish writing their state to memory */ if (vc->nap_count < vc->n_woken) kvmppc_wait_for_nap(vc); - for (i = 0; i < threads_per_core; ++i) + for (i = 0; i < threads_per_subcore; ++i) kvmppc_release_hwthread(vc->pcpu + i); /* prevent other vcpu threads from doing kvmppc_start_thread() now */ vc->vcore_state = VCORE_EXITING; @@ -2305,10 +2311,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) spin_lock_init(&kvm->arch.slot_phys_lock); /* - * Don't allow secondary CPU threads to come online - * while any KVM VMs exist. + * Track that we now have a HV mode VM active. This blocks secondary + * CPU threads from coming online. */ - inhibit_secondary_onlining(); + kvm_hv_vm_activated(); return 0; } @@ -2324,7 +2330,7 @@ static void kvmppc_free_vcores(struct kvm *kvm) static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) { - uninhibit_secondary_onlining(); + kvm_hv_vm_deactivated(); kvmppc_free_vcores(kvm); if (kvm->arch.rma) { diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 8cd0daebb82d..7cde8a665205 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -6,6 +6,7 @@ * published by the Free Software Foundation. */ +#include <linux/cpu.h> #include <linux/kvm_host.h> #include <linux/preempt.h> #include <linux/export.h> @@ -181,3 +182,33 @@ void __init kvm_cma_reserve(void) kvm_cma_declare_contiguous(selected_size, align_size); } } + +/* + * When running HV mode KVM we need to block certain operations while KVM VMs + * exist in the system. We use a counter of VMs to track this. + * + * One of the operations we need to block is onlining of secondaries, so we + * protect hv_vm_count with get/put_online_cpus(). + */ +static atomic_t hv_vm_count; + +void kvm_hv_vm_activated(void) +{ + get_online_cpus(); + atomic_inc(&hv_vm_count); + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(kvm_hv_vm_activated); + +void kvm_hv_vm_deactivated(void) +{ + get_online_cpus(); + atomic_dec(&hv_vm_count); + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(kvm_hv_vm_deactivated); + +bool kvm_hv_mode_active(void) +{ + return atomic_read(&hv_vm_count) != 0; +} diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index e18e3cfc32de..8c86422a1e37 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -171,7 +171,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) #endif /* CONFIG_SMP */ /* Jump to partition switch code */ - bl .kvmppc_hv_entry_trampoline + bl kvmppc_hv_entry_trampoline nop /* diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 974793435a2e..77356fd25ccc 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -292,8 +292,7 @@ kvm_start_guest: beq kvm_no_guest /* Set HSTATE_DSCR(r13) to something sensible */ - LOAD_REG_ADDR(r6, dscr_default) - ld r6, 0(r6) + ld r6, PACA_DSCR(r13) std r6, HSTATE_DSCR(r13) bl kvmppc_hv_entry @@ -1799,7 +1798,7 @@ kvmppc_hdsi: /* Search the hash table. */ mr r3, r9 /* vcpu pointer */ li r7, 1 /* data fault */ - bl .kvmppc_hpte_hv_fault + bl kvmppc_hpte_hv_fault ld r9, HSTATE_KVM_VCPU(r13) ld r10, VCPU_PC(r9) ld r11, VCPU_MSR(r9) @@ -1873,7 +1872,7 @@ kvmppc_hisi: mr r4, r10 mr r6, r11 li r7, 0 /* instruction fault */ - bl .kvmppc_hpte_hv_fault + bl kvmppc_hpte_hv_fault ld r9, HSTATE_KVM_VCPU(r13) ld r10, VCPU_PC(r9) ld r11, VCPU_MSR(r9) @@ -1947,16 +1946,16 @@ hcall_real_fallback: .globl hcall_real_table hcall_real_table: .long 0 /* 0 - unused */ - .long .kvmppc_h_remove - hcall_real_table - .long .kvmppc_h_enter - hcall_real_table - .long .kvmppc_h_read - hcall_real_table + .long DOTSYM(kvmppc_h_remove) - hcall_real_table + .long DOTSYM(kvmppc_h_enter) - hcall_real_table + .long DOTSYM(kvmppc_h_read) - hcall_real_table .long 0 /* 0x10 - H_CLEAR_MOD */ .long 0 /* 0x14 - H_CLEAR_REF */ - .long .kvmppc_h_protect - hcall_real_table - .long .kvmppc_h_get_tce - hcall_real_table - .long .kvmppc_h_put_tce - hcall_real_table + .long DOTSYM(kvmppc_h_protect) - hcall_real_table + .long DOTSYM(kvmppc_h_get_tce) - hcall_real_table + .long DOTSYM(kvmppc_h_put_tce) - hcall_real_table .long 0 /* 0x24 - H_SET_SPRG0 */ - .long .kvmppc_h_set_dabr - hcall_real_table + .long DOTSYM(kvmppc_h_set_dabr) - hcall_real_table .long 0 /* 0x2c */ .long 0 /* 0x30 */ .long 0 /* 0x34 */ @@ -1972,11 +1971,11 @@ hcall_real_table: .long 0 /* 0x5c */ .long 0 /* 0x60 */ #ifdef CONFIG_KVM_XICS - .long .kvmppc_rm_h_eoi - hcall_real_table - .long .kvmppc_rm_h_cppr - hcall_real_table - .long .kvmppc_rm_h_ipi - hcall_real_table + .long DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table + .long DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table + .long DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table .long 0 /* 0x70 - H_IPOLL */ - .long .kvmppc_rm_h_xirr - hcall_real_table + .long DOTSYM(kvmppc_rm_h_xirr) - hcall_real_table #else .long 0 /* 0x64 - H_EOI */ .long 0 /* 0x68 - H_CPPR */ @@ -2010,7 +2009,7 @@ hcall_real_table: .long 0 /* 0xd4 */ .long 0 /* 0xd8 */ .long 0 /* 0xdc */ - .long .kvmppc_h_cede - hcall_real_table + .long DOTSYM(kvmppc_h_cede) - hcall_real_table .long 0 /* 0xe4 */ .long 0 /* 0xe8 */ .long 0 /* 0xec */ @@ -2027,11 +2026,11 @@ hcall_real_table: .long 0 /* 0x118 */ .long 0 /* 0x11c */ .long 0 /* 0x120 */ - .long .kvmppc_h_bulk_remove - hcall_real_table + .long DOTSYM(kvmppc_h_bulk_remove) - hcall_real_table .long 0 /* 0x128 */ .long 0 /* 0x12c */ .long 0 /* 0x130 */ - .long .kvmppc_h_set_xdabr - hcall_real_table + .long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table hcall_real_table_end: ignore_hdec: @@ -2256,7 +2255,7 @@ kvm_cede_exit: /* Try to handle a machine check in real mode */ machine_check_realmode: mr r3, r9 /* get vcpu pointer */ - bl .kvmppc_realmode_machine_check + bl kvmppc_realmode_machine_check nop cmpdi r3, 0 /* continue exiting from guest? */ ld r9, HSTATE_KVM_VCPU(r13) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index bab20f410443..61c738ab1283 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -426,7 +426,7 @@ int kvm_dev_ioctl_check_extension(long ext) #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE case KVM_CAP_PPC_SMT: if (hv_enabled) - r = threads_per_core; + r = threads_per_subcore; else r = 0; break; diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 95a20e17dbff..59fa2de9546d 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -23,9 +23,7 @@ obj-y += checksum_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_PPC64) += checksum_wrappers_64.o endif -ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),) obj-$(CONFIG_PPC64) += memcpy_power7.o memcpy_64.o -endif obj-$(CONFIG_PPC_EMULATE_SSTEP) += sstep.o ldstfp.o diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 9f9434a85264..a3c4dc4defdd 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -16,11 +16,11 @@ PPC64_CACHES: .tc ppc64_caches[TC],ppc64_caches .section ".text" -_GLOBAL(copy_page) +_GLOBAL_TOC(copy_page) BEGIN_FTR_SECTION lis r5,PAGE_SIZE@h FTR_SECTION_ELSE - b .copypage_power7 + b copypage_power7 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) ori r5,r5,PAGE_SIZE@l BEGIN_FTR_SECTION diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S index 395c594722a2..d7dafb3777ac 100644 --- a/arch/powerpc/lib/copypage_power7.S +++ b/arch/powerpc/lib/copypage_power7.S @@ -56,15 +56,15 @@ _GLOBAL(copypage_power7) #ifdef CONFIG_ALTIVEC mflr r0 - std r3,48(r1) - std r4,56(r1) + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl .enter_vmx_copy + bl enter_vmx_copy cmpwi r3,0 ld r0,STACKFRAMESIZE+16(r1) - ld r3,STACKFRAMESIZE+48(r1) - ld r4,STACKFRAMESIZE+56(r1) + ld r3,STK_REG(R31)(r1) + ld r4,STK_REG(R30)(r1) mtlr r0 li r0,(PAGE_SIZE/128) @@ -103,7 +103,7 @@ _GLOBAL(copypage_power7) addi r3,r3,128 bdnz 1b - b .exit_vmx_copy /* tail call optimise */ + b exit_vmx_copy /* tail call optimise */ #else li r0,(PAGE_SIZE/128) diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S index 596a285c0755..0860ee46013c 100644 --- a/arch/powerpc/lib/copyuser_64.S +++ b/arch/powerpc/lib/copyuser_64.S @@ -18,7 +18,7 @@ #endif .align 7 -_GLOBAL(__copy_tofrom_user) +_GLOBAL_TOC(__copy_tofrom_user) BEGIN_FTR_SECTION nop FTR_SECTION_ELSE diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index e8e9c36dc784..c46c876ac96a 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -66,7 +66,7 @@ ld r15,STK_REG(R15)(r1) ld r14,STK_REG(R14)(r1) .Ldo_err3: - bl .exit_vmx_usercopy + bl exit_vmx_usercopy ld r0,STACKFRAMESIZE+16(r1) mtlr r0 b .Lexit @@ -85,9 +85,9 @@ .Lexit: addi r1,r1,STACKFRAMESIZE .Ldo_err1: - ld r3,48(r1) - ld r4,56(r1) - ld r5,64(r1) + ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + ld r4,-STACKFRAMESIZE+STK_REG(R30)(r1) + ld r5,-STACKFRAMESIZE+STK_REG(R29)(r1) b __copy_tofrom_user_base @@ -96,18 +96,18 @@ _GLOBAL(__copy_tofrom_user_power7) cmpldi r5,16 cmpldi cr1,r5,4096 - std r3,48(r1) - std r4,56(r1) - std r5,64(r1) + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) + std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) blt .Lshort_copy bgt cr1,.Lvmx_copy #else cmpldi r5,16 - std r3,48(r1) - std r4,56(r1) - std r5,64(r1) + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) + std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) blt .Lshort_copy #endif @@ -295,12 +295,12 @@ err1; stb r0,0(r3) mflr r0 std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl .enter_vmx_usercopy + bl enter_vmx_usercopy cmpwi cr1,r3,0 ld r0,STACKFRAMESIZE+16(r1) - ld r3,STACKFRAMESIZE+48(r1) - ld r4,STACKFRAMESIZE+56(r1) - ld r5,STACKFRAMESIZE+64(r1) + ld r3,STK_REG(R31)(r1) + ld r4,STK_REG(R30)(r1) + ld r5,STK_REG(R29)(r1) mtlr r0 /* @@ -514,7 +514,7 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b .exit_vmx_usercopy /* tail call optimise */ + b exit_vmx_usercopy /* tail call optimise */ .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -717,5 +717,5 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b .exit_vmx_usercopy /* tail call optimise */ + b exit_vmx_usercopy /* tail call optimise */ #endif /* CONFiG_ALTIVEC */ diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S index 9b96ff2ecd4d..19e66001a4f9 100644 --- a/arch/powerpc/lib/hweight_64.S +++ b/arch/powerpc/lib/hweight_64.S @@ -24,7 +24,7 @@ _GLOBAL(__arch_hweight8) BEGIN_FTR_SECTION - b .__sw_hweight8 + b __sw_hweight8 nop nop FTR_SECTION_ELSE @@ -35,7 +35,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB) _GLOBAL(__arch_hweight16) BEGIN_FTR_SECTION - b .__sw_hweight16 + b __sw_hweight16 nop nop nop @@ -57,7 +57,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB) _GLOBAL(__arch_hweight32) BEGIN_FTR_SECTION - b .__sw_hweight32 + b __sw_hweight32 nop nop nop @@ -82,7 +82,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB) _GLOBAL(__arch_hweight64) BEGIN_FTR_SECTION - b .__sw_hweight64 + b __sw_hweight64 nop nop nop diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S index f4fcb0bc6563..0738f96befbf 100644 --- a/arch/powerpc/lib/mem_64.S +++ b/arch/powerpc/lib/mem_64.S @@ -79,8 +79,8 @@ _GLOBAL(memset) _GLOBAL(memmove) cmplw 0,r3,r4 - bgt .backwards_memcpy - b .memcpy + bgt backwards_memcpy + b memcpy _GLOBAL(backwards_memcpy) rlwinm. r7,r5,32-3,3,31 /* r0 = r5 >> 3 */ diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S index 72ad055168a3..32a06ec395d2 100644 --- a/arch/powerpc/lib/memcpy_64.S +++ b/arch/powerpc/lib/memcpy_64.S @@ -10,14 +10,29 @@ #include <asm/ppc_asm.h> .align 7 -_GLOBAL(memcpy) +_GLOBAL_TOC(memcpy) BEGIN_FTR_SECTION - std r3,48(r1) /* save destination pointer for return value */ +#ifdef __LITTLE_ENDIAN__ + cmpdi cr7,r5,0 +#else + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) /* save destination pointer for return value */ +#endif FTR_SECTION_ELSE #ifndef SELFTEST b memcpy_power7 #endif ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) +#ifdef __LITTLE_ENDIAN__ + /* dumb little-endian memcpy that will get replaced at runtime */ + addi r9,r3,-1 + addi r4,r4,-1 + beqlr cr7 + mtctr r5 +1: lbzu r10,1(r4) + stbu r10,1(r9) + bdnz 1b + blr +#else PPC_MTOCRF(0x01,r5) cmpldi cr1,r5,16 neg r6,r3 # LS 3 bits = # bytes to 8-byte dest bdry @@ -73,7 +88,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) 2: bf cr7*4+3,3f lbz r9,8(r4) stb r9,0(r3) -3: ld r3,48(r1) /* return dest pointer */ +3: ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) /* return dest pointer */ blr .Lsrc_unaligned: @@ -156,7 +171,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) 2: bf cr7*4+3,3f rotldi r9,r9,8 stb r9,0(r3) -3: ld r3,48(r1) /* return dest pointer */ +3: ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) /* return dest pointer */ blr .Ldst_unaligned: @@ -201,5 +216,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) 3: bf cr7*4+3,4f lbz r0,0(r4) stb r0,0(r3) -4: ld r3,48(r1) /* return dest pointer */ +4: ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) /* return dest pointer */ blr +#endif diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S index e4177dbea6bd..2ff5c142f87b 100644 --- a/arch/powerpc/lib/memcpy_power7.S +++ b/arch/powerpc/lib/memcpy_power7.S @@ -33,14 +33,14 @@ _GLOBAL(memcpy_power7) cmpldi r5,16 cmpldi cr1,r5,4096 - std r3,48(r1) + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) blt .Lshort_copy bgt cr1,.Lvmx_copy #else cmpldi r5,16 - std r3,48(r1) + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) blt .Lshort_copy #endif @@ -216,7 +216,7 @@ _GLOBAL(memcpy_power7) lbz r0,0(r4) stb r0,0(r3) -15: ld r3,48(r1) +15: ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) blr .Lunwind_stack_nonvmx_copy: @@ -226,16 +226,16 @@ _GLOBAL(memcpy_power7) #ifdef CONFIG_ALTIVEC .Lvmx_copy: mflr r0 - std r4,56(r1) - std r5,64(r1) + std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) + std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl .enter_vmx_copy + bl enter_vmx_copy cmpwi cr1,r3,0 ld r0,STACKFRAMESIZE+16(r1) - ld r3,STACKFRAMESIZE+48(r1) - ld r4,STACKFRAMESIZE+56(r1) - ld r5,STACKFRAMESIZE+64(r1) + ld r3,STK_REG(R31)(r1) + ld r4,STK_REG(R30)(r1) + ld r5,STK_REG(R29)(r1) mtlr r0 /* @@ -447,8 +447,8 @@ _GLOBAL(memcpy_power7) stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - ld r3,48(r1) - b .exit_vmx_copy /* tail call optimise */ + ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + b exit_vmx_copy /* tail call optimise */ .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -651,6 +651,6 @@ _GLOBAL(memcpy_power7) stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - ld r3,48(r1) - b .exit_vmx_copy /* tail call optimise */ + ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + b exit_vmx_copy /* tail call optimise */ #endif /* CONFiG_ALTIVEC */ diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S index 3b1e48049faf..7bd9549a90a2 100644 --- a/arch/powerpc/lib/string_64.S +++ b/arch/powerpc/lib/string_64.S @@ -77,7 +77,7 @@ err3; stb r0,0(r3) mr r3,r4 blr -_GLOBAL(__clear_user) +_GLOBAL_TOC(__clear_user) cmpdi r4,32 neg r6,r3 li r0,0 diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index 1136d26a95ae..057cbbb4c576 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -159,7 +159,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) BEGIN_FTR_SECTION mr r4,r30 mr r5,r7 - bl .hash_page_do_lazy_icache + bl hash_page_do_lazy_icache END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) /* At this point, r3 contains new PP bits, save them in @@ -201,7 +201,8 @@ htab_insert_pte: li r8,MMU_PAGE_4K /* page size */ li r9,MMU_PAGE_4K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(htab_call_hpte_insert1) +.globl htab_call_hpte_insert1 +htab_call_hpte_insert1: bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0 bge htab_pte_insert_ok /* Insertion successful */ @@ -225,7 +226,8 @@ _GLOBAL(htab_call_hpte_insert1) li r8,MMU_PAGE_4K /* page size */ li r9,MMU_PAGE_4K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(htab_call_hpte_insert2) +.globl htab_call_hpte_insert2 +htab_call_hpte_insert2: bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0 bge+ htab_pte_insert_ok /* Insertion successful */ @@ -242,7 +244,8 @@ _GLOBAL(htab_call_hpte_insert2) 2: and r0,r5,r27 rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ /* Call ppc_md.hpte_remove */ -_GLOBAL(htab_call_hpte_remove) +.globl htab_call_hpte_remove +htab_call_hpte_remove: bl . /* Patched by htab_finish_init() */ /* Try all again */ @@ -296,7 +299,8 @@ htab_modify_pte: li r7,MMU_PAGE_4K /* actual page size */ ld r8,STK_PARAM(R9)(r1) /* segment size */ ld r9,STK_PARAM(R8)(r1) /* get "local" param */ -_GLOBAL(htab_call_hpte_updatepp) +.globl htab_call_hpte_updatepp +htab_call_hpte_updatepp: bl . /* Patched by htab_finish_init() */ /* if we failed because typically the HPTE wasn't really here @@ -471,7 +475,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) BEGIN_FTR_SECTION mr r4,r30 mr r5,r7 - bl .hash_page_do_lazy_icache + bl hash_page_do_lazy_icache END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) /* At this point, r3 contains new PP bits, save them in @@ -526,7 +530,8 @@ htab_special_pfn: li r8,MMU_PAGE_4K /* page size */ li r9,MMU_PAGE_4K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(htab_call_hpte_insert1) +.globl htab_call_hpte_insert1 +htab_call_hpte_insert1: bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 bge htab_pte_insert_ok /* Insertion successful */ @@ -554,7 +559,8 @@ _GLOBAL(htab_call_hpte_insert1) li r8,MMU_PAGE_4K /* page size */ li r9,MMU_PAGE_4K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(htab_call_hpte_insert2) +.globl htab_call_hpte_insert2 +htab_call_hpte_insert2: bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 bge+ htab_pte_insert_ok /* Insertion successful */ @@ -571,7 +577,8 @@ _GLOBAL(htab_call_hpte_insert2) 2: and r0,r5,r27 rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ /* Call ppc_md.hpte_remove */ -_GLOBAL(htab_call_hpte_remove) +.globl htab_call_hpte_remove +htab_call_hpte_remove: bl . /* patched by htab_finish_init() */ /* Try all again */ @@ -588,7 +595,7 @@ htab_inval_old_hpte: li r6,MMU_PAGE_64K /* psize */ ld r7,STK_PARAM(R9)(r1) /* ssize */ ld r8,STK_PARAM(R8)(r1) /* local */ - bl .flush_hash_page + bl flush_hash_page /* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */ lis r0,_PAGE_HPTE_SUB@h ori r0,r0,_PAGE_HPTE_SUB@l @@ -660,7 +667,8 @@ htab_modify_pte: li r7,MMU_PAGE_4K /* actual page size */ ld r8,STK_PARAM(R9)(r1) /* segment size */ ld r9,STK_PARAM(R8)(r1) /* get "local" param */ -_GLOBAL(htab_call_hpte_updatepp) +.globl htab_call_hpte_updatepp +htab_call_hpte_updatepp: bl . /* patched by htab_finish_init() */ /* if we failed because typically the HPTE wasn't really here @@ -812,7 +820,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) BEGIN_FTR_SECTION mr r4,r30 mr r5,r7 - bl .hash_page_do_lazy_icache + bl hash_page_do_lazy_icache END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) /* At this point, r3 contains new PP bits, save them in @@ -857,7 +865,8 @@ ht64_insert_pte: li r8,MMU_PAGE_64K li r9,MMU_PAGE_64K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(ht64_call_hpte_insert1) +.globl ht64_call_hpte_insert1 +ht64_call_hpte_insert1: bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 bge ht64_pte_insert_ok /* Insertion successful */ @@ -881,7 +890,8 @@ _GLOBAL(ht64_call_hpte_insert1) li r8,MMU_PAGE_64K li r9,MMU_PAGE_64K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(ht64_call_hpte_insert2) +.globl ht64_call_hpte_insert2 +ht64_call_hpte_insert2: bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 bge+ ht64_pte_insert_ok /* Insertion successful */ @@ -898,7 +908,8 @@ _GLOBAL(ht64_call_hpte_insert2) 2: and r0,r5,r27 rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ /* Call ppc_md.hpte_remove */ -_GLOBAL(ht64_call_hpte_remove) +.globl ht64_call_hpte_remove +ht64_call_hpte_remove: bl . /* patched by htab_finish_init() */ /* Try all again */ @@ -952,7 +963,8 @@ ht64_modify_pte: li r7,MMU_PAGE_64K /* actual page size */ ld r8,STK_PARAM(R9)(r1) /* segment size */ ld r9,STK_PARAM(R8)(r1) /* get "local" param */ -_GLOBAL(ht64_call_hpte_updatepp) +.globl ht64_call_hpte_updatepp +ht64_call_hpte_updatepp: bl . /* patched by htab_finish_init() */ /* if we failed because typically the HPTE wasn't really here diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 06ba83b036d3..88fdd9d25077 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -269,9 +269,9 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); - __be32 *prop; - unsigned long size = 0; + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be32 *prop; + int size = 0; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) @@ -324,9 +324,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); - __be32 *prop; - unsigned long size = 0; + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be32 *prop; + int size = 0; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) @@ -406,9 +406,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, static int __init htab_dt_scan_hugepage_blocks(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); - __be64 *addr_prop; - __be32 *page_count_prop; + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be64 *addr_prop; + const __be32 *page_count_prop; unsigned int expected_pages; long unsigned int phys_addr; long unsigned int block_size; @@ -449,6 +449,24 @@ static void mmu_psize_set_default_penc(void) mmu_psize_defs[bpsize].penc[apsize] = -1; } +#ifdef CONFIG_PPC_64K_PAGES + +static bool might_have_hea(void) +{ + /* + * The HEA ethernet adapter requires awareness of the + * GX bus. Without that awareness we can easily assume + * we will never see an HEA ethernet device. + */ +#ifdef CONFIG_IBMEBUS + return !cpu_has_feature(CPU_FTR_ARCH_207S); +#else + return false; +#endif +} + +#endif /* #ifdef CONFIG_PPC_64K_PAGES */ + static void __init htab_init_page_sizes(void) { int rc; @@ -503,10 +521,11 @@ static void __init htab_init_page_sizes(void) mmu_linear_psize = MMU_PAGE_64K; if (mmu_has_feature(MMU_FTR_CI_LARGE_PAGE)) { /* - * Don't use 64k pages for ioremap on pSeries, since - * that would stop us accessing the HEA ethernet. + * When running on pSeries using 64k pages for ioremap + * would stop us accessing the HEA ethernet. So if we + * have the chance of ever seeing one, stay at 4k. */ - if (!machine_is(pseries)) + if (!might_have_hea() || !machine_is(pseries)) mmu_io_psize = MMU_PAGE_64K; } else mmu_ci_restrictions = 1; @@ -550,8 +569,8 @@ static int __init htab_dt_scan_pftsize(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); - __be32 *prop; + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be32 *prop; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) @@ -607,47 +626,43 @@ int remove_section_mapping(unsigned long start, unsigned long end) } #endif /* CONFIG_MEMORY_HOTPLUG */ -#define FUNCTION_TEXT(A) ((*(unsigned long *)(A))) +extern u32 htab_call_hpte_insert1[]; +extern u32 htab_call_hpte_insert2[]; +extern u32 htab_call_hpte_remove[]; +extern u32 htab_call_hpte_updatepp[]; +extern u32 ht64_call_hpte_insert1[]; +extern u32 ht64_call_hpte_insert2[]; +extern u32 ht64_call_hpte_remove[]; +extern u32 ht64_call_hpte_updatepp[]; static void __init htab_finish_init(void) { - extern unsigned int *htab_call_hpte_insert1; - extern unsigned int *htab_call_hpte_insert2; - extern unsigned int *htab_call_hpte_remove; - extern unsigned int *htab_call_hpte_updatepp; - #ifdef CONFIG_PPC_HAS_HASH_64K - extern unsigned int *ht64_call_hpte_insert1; - extern unsigned int *ht64_call_hpte_insert2; - extern unsigned int *ht64_call_hpte_remove; - extern unsigned int *ht64_call_hpte_updatepp; - patch_branch(ht64_call_hpte_insert1, - FUNCTION_TEXT(ppc_md.hpte_insert), + ppc_function_entry(ppc_md.hpte_insert), BRANCH_SET_LINK); patch_branch(ht64_call_hpte_insert2, - FUNCTION_TEXT(ppc_md.hpte_insert), + ppc_function_entry(ppc_md.hpte_insert), BRANCH_SET_LINK); patch_branch(ht64_call_hpte_remove, - FUNCTION_TEXT(ppc_md.hpte_remove), + ppc_function_entry(ppc_md.hpte_remove), BRANCH_SET_LINK); patch_branch(ht64_call_hpte_updatepp, - FUNCTION_TEXT(ppc_md.hpte_updatepp), + ppc_function_entry(ppc_md.hpte_updatepp), BRANCH_SET_LINK); - #endif /* CONFIG_PPC_HAS_HASH_64K */ patch_branch(htab_call_hpte_insert1, - FUNCTION_TEXT(ppc_md.hpte_insert), + ppc_function_entry(ppc_md.hpte_insert), BRANCH_SET_LINK); patch_branch(htab_call_hpte_insert2, - FUNCTION_TEXT(ppc_md.hpte_insert), + ppc_function_entry(ppc_md.hpte_insert), BRANCH_SET_LINK); patch_branch(htab_call_hpte_remove, - FUNCTION_TEXT(ppc_md.hpte_remove), + ppc_function_entry(ppc_md.hpte_remove), BRANCH_SET_LINK); patch_branch(htab_call_hpte_updatepp, - FUNCTION_TEXT(ppc_md.hpte_updatepp), + ppc_function_entry(ppc_md.hpte_updatepp), BRANCH_SET_LINK); } @@ -964,6 +979,22 @@ void hash_failure_debug(unsigned long ea, unsigned long access, trap, vsid, ssize, psize, lpsize, pte); } +static void check_paca_psize(unsigned long ea, struct mm_struct *mm, + int psize, bool user_region) +{ + if (user_region) { + if (psize != get_paca_psize(ea)) { + get_paca()->context = mm->context; + slb_flush_and_rebolt(); + } + } else if (get_paca()->vmalloc_sllp != + mmu_psize_defs[mmu_vmalloc_psize].sllp) { + get_paca()->vmalloc_sllp = + mmu_psize_defs[mmu_vmalloc_psize].sllp; + slb_vmalloc_update(); + } +} + /* Result code is: * 0 - handled * 1 - normal page fault @@ -1085,6 +1116,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) WARN_ON(1); } #endif + check_paca_psize(ea, mm, psize, user_region); + goto bail; } @@ -1125,17 +1158,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) #endif } } - if (user_region) { - if (psize != get_paca_psize(ea)) { - get_paca()->context = mm->context; - slb_flush_and_rebolt(); - } - } else if (get_paca()->vmalloc_sllp != - mmu_psize_defs[mmu_vmalloc_psize].sllp) { - get_paca()->vmalloc_sllp = - mmu_psize_defs[mmu_vmalloc_psize].sllp; - slb_vmalloc_update(); - } + + check_paca_psize(ea, mm, psize, user_region); #endif /* CONFIG_PPC_64K_PAGES */ #ifdef CONFIG_PPC_HAS_HASH_64K diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index eb923654ba80..7e70ae968e5f 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -86,11 +86,6 @@ int pgd_huge(pgd_t pgd) */ return ((pgd_val(pgd) & 0x3) != 0x0); } - -int pmd_huge_support(void) -{ - return 1; -} #else int pmd_huge(pmd_t pmd) { @@ -106,11 +101,6 @@ int pgd_huge(pgd_t pgd) { return 0; } - -int pmd_huge_support(void) -{ - return 0; -} #endif pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index 964a5f61488a..0399a6702958 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -256,10 +256,14 @@ static inline void patch_slb_encoding(unsigned int *insn_addr, patch_instruction(insn_addr, insn); } +extern u32 slb_compare_rr_to_size[]; +extern u32 slb_miss_kernel_load_linear[]; +extern u32 slb_miss_kernel_load_io[]; +extern u32 slb_compare_rr_to_size[]; +extern u32 slb_miss_kernel_load_vmemmap[]; + void slb_set_size(u16 size) { - extern unsigned int *slb_compare_rr_to_size; - if (mmu_slb_size == size) return; @@ -272,11 +276,7 @@ void slb_initialize(void) unsigned long linear_llp, vmalloc_llp, io_llp; unsigned long lflags, vflags; static int slb_encoding_inited; - extern unsigned int *slb_miss_kernel_load_linear; - extern unsigned int *slb_miss_kernel_load_io; - extern unsigned int *slb_compare_rr_to_size; #ifdef CONFIG_SPARSEMEM_VMEMMAP - extern unsigned int *slb_miss_kernel_load_vmemmap; unsigned long vmemmap_llp; #endif diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index 17aa6dfceb34..736d18b3cefd 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -35,7 +35,7 @@ _GLOBAL(slb_allocate_realmode) * check for bad kernel/user address * (ea & ~REGION_MASK) >= PGTABLE_RANGE */ - rldicr. r9,r3,4,(63 - 46 - 4) + rldicr. r9,r3,4,(63 - PGTABLE_EADDR_SIZE - 4) bne- 8f srdi r9,r3,60 /* get region */ @@ -59,7 +59,8 @@ _GLOBAL(slb_allocate_realmode) /* Linear mapping encoding bits, the "li" instruction below will * be patched by the kernel at boot */ -_GLOBAL(slb_miss_kernel_load_linear) +.globl slb_miss_kernel_load_linear +slb_miss_kernel_load_linear: li r11,0 /* * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 @@ -79,7 +80,8 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) /* Check virtual memmap region. To be patches at kernel boot */ cmpldi cr0,r9,0xf bne 1f -_GLOBAL(slb_miss_kernel_load_vmemmap) +.globl slb_miss_kernel_load_vmemmap +slb_miss_kernel_load_vmemmap: li r11,0 b 6f 1: @@ -95,7 +97,8 @@ _GLOBAL(slb_miss_kernel_load_vmemmap) b 6f 5: /* IO mapping */ - _GLOBAL(slb_miss_kernel_load_io) +.globl slb_miss_kernel_load_io +slb_miss_kernel_load_io: li r11,0 6: /* @@ -250,7 +253,8 @@ slb_finish_load: 7: ld r10,PACASTABRR(r13) addi r10,r10,1 /* This gets soft patched on boot. */ -_GLOBAL(slb_compare_rr_to_size) +.globl slb_compare_rr_to_size +slb_compare_rr_to_size: cmpldi r10,0 blt+ 4f diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index ae3d5b799b90..92cb18d52ea8 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -596,8 +596,13 @@ static void __early_init_mmu(int boot_cpu) /* XXX This should be decided at runtime based on supported * page sizes in the TLB, but for now let's assume 16M is * always there and a good fit (which it probably is) + * + * Freescale booke only supports 4K pages in TLB0, so use that. */ - mmu_vmemmap_psize = MMU_PAGE_16M; + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) + mmu_vmemmap_psize = MMU_PAGE_4K; + else + mmu_vmemmap_psize = MMU_PAGE_16M; /* XXX This code only checks for TLB 0 capabilities and doesn't * check what page size combos are supported by the HW. It diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index dc1a264ec6e6..4d88f6a19058 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -199,6 +199,34 @@ config CURRITUCK help This option enables support for the IBM Currituck (476fpe) evaluation board +config AKEBONO + bool "IBM Akebono (476gtr) Support" + depends on PPC_47x + default n + select SWIOTLB + select 476FPE + select PPC4xx_PCI_EXPRESS + select PCI_MSI + select PPC4xx_HSTA_MSI + select I2C + select I2C_IBM_IIC + select NETDEVICES + select ETHERNET + select NET_VENDOR_IBM + select IBM_EMAC_EMAC4 + select IBM_EMAC_RGMII_WOL + select USB + select USB_OHCI_HCD_PLATFORM + select USB_EHCI_HCD_PLATFORM + select MMC_SDHCI + select MMC_SDHCI_PLTFM + select MMC_SDHCI_OF_476GTR + select ATA + select SATA_AHCI_PLATFORM + help + This option enables support for the IBM Akebono (476gtr) evaluation board + + config ICON bool "Icon" depends on 44x @@ -323,6 +351,20 @@ config APM821xx select IBM_EMAC_EMAC4 select IBM_EMAC_TAH +config 476FPE_ERR46 + depends on 476FPE + bool "Enable linker work around for PPC476FPE errata #46" + help + This option enables a work around for an icache bug on 476 + that can cause execution of stale instructions when falling + through pages (IBM errata #46). It requires a recent version + of binutils which supports the --ppc476-workaround option. + + The work around enables the appropriate linker options and + ensures that all module output sections are aligned to 4K + page boundaries. The work around is only required when + building modules. + # 44x errata/workaround config symbols, selected by the CPU models above config IBM440EP_ERR42 bool diff --git a/arch/powerpc/platforms/44x/Makefile b/arch/powerpc/platforms/44x/Makefile index d03833abec09..26d35b5941f7 100644 --- a/arch/powerpc/platforms/44x/Makefile +++ b/arch/powerpc/platforms/44x/Makefile @@ -10,4 +10,5 @@ obj-$(CONFIG_XILINX_VIRTEX_5_FXT) += virtex.o obj-$(CONFIG_XILINX_ML510) += virtex_ml510.o obj-$(CONFIG_ISS4xx) += iss4xx.o obj-$(CONFIG_CANYONLANDS)+= canyonlands.o -obj-$(CONFIG_CURRITUCK) += currituck.o +obj-$(CONFIG_CURRITUCK) += ppc476.o +obj-$(CONFIG_AKEBONO) += ppc476.o diff --git a/arch/powerpc/platforms/44x/currituck.c b/arch/powerpc/platforms/44x/ppc476.c index 7f1b71a01c6a..33986c1a05da 100644 --- a/arch/powerpc/platforms/44x/currituck.c +++ b/arch/powerpc/platforms/44x/ppc476.c @@ -1,7 +1,8 @@ /* - * Currituck board specific routines + * PowerPC 476FPE board specific routines * - * Copyright © 2011 Tony Breeds IBM Corporation + * Copyright © 2013 Tony Breeds IBM Corporation + * Copyright © 2013 Alistair Popple IBM Corporation * * Based on earlier code: * Matt Porter <mporter@kernel.crashing.org> @@ -35,8 +36,9 @@ #include <asm/mmu.h> #include <linux/pci.h> +#include <linux/i2c.h> -static __initdata struct of_device_id ppc47x_of_bus[] = { +static struct of_device_id ppc47x_of_bus[] __initdata = { { .compatible = "ibm,plb4", }, { .compatible = "ibm,plb6", }, { .compatible = "ibm,opb", }, @@ -55,15 +57,69 @@ static void quirk_ppc_currituck_usb_fixup(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(0x1033, 0x0035, quirk_ppc_currituck_usb_fixup); +/* Akebono has an AVR microcontroller attached to the I2C bus + * which is used to power off/reset the system. */ + +/* AVR I2C Commands */ +#define AVR_PWRCTL_CMD (0x26) + +/* Flags for the power control I2C commands */ +#define AVR_PWRCTL_PWROFF (0x01) +#define AVR_PWRCTL_RESET (0x02) + +static struct i2c_client *avr_i2c_client; +static void avr_halt_system(int pwrctl_flags) +{ + /* Request the AVR to reset the system */ + i2c_smbus_write_byte_data(avr_i2c_client, + AVR_PWRCTL_CMD, pwrctl_flags); + + /* Wait for system to be reset */ + while (1) + ; +} + +static void avr_power_off_system(void) +{ + avr_halt_system(AVR_PWRCTL_PWROFF); +} + +static void avr_reset_system(char *cmd) +{ + avr_halt_system(AVR_PWRCTL_RESET); +} + +static int avr_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + avr_i2c_client = client; + ppc_md.restart = avr_reset_system; + ppc_md.power_off = avr_power_off_system; + return 0; +} + +static const struct i2c_device_id avr_id[] = { + { "akebono-avr", 0 }, + { } +}; + +static struct i2c_driver avr_driver = { + .driver = { + .name = "akebono-avr", + }, + .probe = avr_probe, + .id_table = avr_id, +}; + static int __init ppc47x_device_probe(void) { + i2c_add_driver(&avr_driver); of_platform_bus_probe(NULL, ppc47x_of_bus, NULL); return 0; } machine_device_initcall(ppc47x, ppc47x_device_probe); -/* We can have either UICs or MPICs */ static void __init ppc47x_init_irq(void) { struct device_node *np; @@ -157,43 +213,36 @@ static void __init ppc47x_setup_arch(void) { /* No need to check the DMA config as we /know/ our windows are all of - * RAM. Lets hope that doesn't change */ + * RAM. Lets hope that doesn't change */ swiotlb_detect_4g(); ppc47x_smp_init(); } -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init ppc47x_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (!of_flat_dt_is_compatible(root, "ibm,currituck")) - return 0; - - return 1; -} - static int board_rev = -1; static int __init ppc47x_get_board_rev(void) { - u8 fpga_reg0; - void *fpga; - struct device_node *np; + int reg; + u8 *fpga; + struct device_node *np = NULL; + + if (of_machine_is_compatible("ibm,currituck")) { + np = of_find_compatible_node(NULL, NULL, "ibm,currituck-fpga"); + reg = 0; + } else if (of_machine_is_compatible("ibm,akebono")) { + np = of_find_compatible_node(NULL, NULL, "ibm,akebono-fpga"); + reg = 2; + } - np = of_find_compatible_node(NULL, NULL, "ibm,currituck-fpga"); if (!np) goto fail; - fpga = of_iomap(np, 0); + fpga = (u8 *) of_iomap(np, 0); of_node_put(np); if (!fpga) goto fail; - fpga_reg0 = ioread8(fpga); - board_rev = fpga_reg0 & 0x03; + board_rev = ioread8(fpga + reg) & 0x03; pr_info("%s: Found board revision %d\n", __func__, board_rev); iounmap(fpga); return 0; @@ -208,7 +257,7 @@ machine_arch_initcall(ppc47x, ppc47x_get_board_rev); static void ppc47x_pci_irq_fixup(struct pci_dev *dev) { if (dev->vendor == 0x1033 && (dev->device == 0x0035 || - dev->device == 0x00e0)) { + dev->device == 0x00e0)) { if (board_rev == 0) { dev->irq = irq_create_mapping(NULL, 47); pr_info("%s: Mapping irq %d\n", __func__, dev->irq); @@ -221,13 +270,30 @@ static void ppc47x_pci_irq_fixup(struct pci_dev *dev) } } +/* + * Called very early, MMU is off, device-tree isn't unflattened + */ +static int __init ppc47x_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + if (of_flat_dt_is_compatible(root, "ibm,akebono")) + return 1; + + if (of_flat_dt_is_compatible(root, "ibm,currituck")) { + ppc_md.pci_irq_fixup = ppc47x_pci_irq_fixup; + return 1; + } + + return 0; +} + define_machine(ppc47x) { .name = "PowerPC 47x", .probe = ppc47x_probe, .progress = udbg_progress, .init_IRQ = ppc47x_init_irq, .setup_arch = ppc47x_setup_arch, - .pci_irq_fixup = ppc47x_pci_irq_fixup, .restart = ppc4xx_reset_system, .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/44x/ppc476_modules.lds b/arch/powerpc/platforms/44x/ppc476_modules.lds new file mode 100644 index 000000000000..9fec5d34ba8e --- /dev/null +++ b/arch/powerpc/platforms/44x/ppc476_modules.lds @@ -0,0 +1,15 @@ +SECTIONS +{ + .text : ALIGN(4096) + { + *(.text .text.* .fixup) + } + .init.text : ALIGN(4096) + { + *(.init.text .init.text.*) + } + .exit.text : ALIGN(4096) + { + *(.exit.text .exit.text.*) + } +} diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c index 18c104820198..6e19b0ad5d26 100644 --- a/arch/powerpc/platforms/52xx/efika.c +++ b/arch/powerpc/platforms/52xx/efika.c @@ -199,8 +199,8 @@ static void __init efika_setup_arch(void) static int __init efika_probe(void) { - char *model = of_get_flat_dt_prop(of_get_flat_dt_root(), - "model", NULL); + const char *model = of_get_flat_dt_prop(of_get_flat_dt_root(), + "model", NULL); if (model == NULL) return 0; diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index c17aae80e7ff..f442120e0033 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -38,6 +38,15 @@ config C293_PCIE help This option enables support for the C293PCIE board +config BSC9132_QDS + bool "Freescale BSC9132QDS" + select DEFAULT_UIMAGE + help + This option enables support for the Freescale BSC9132 QDS board. + BSC9132 is a heterogeneous SoC containing dual e500v2 powerpc cores + and dual StarCore SC3850 DSP cores. + Manufacturer : Freescale Semiconductor, Inc + config MPC8540_ADS bool "Freescale MPC8540 ADS" select DEFAULT_UIMAGE @@ -117,11 +126,11 @@ config P1022_RDK This option enables support for the Freescale / iVeia P1022RDK reference board. -config P1023_RDS - bool "Freescale P1023 RDS/RDB" +config P1023_RDB + bool "Freescale P1023 RDB" select DEFAULT_UIMAGE help - This option enables support for the P1023 RDS and RDB boards + This option enables support for the P1023 RDB board. config TWR_P102x bool "Freescale TWR-P102x" @@ -263,11 +272,11 @@ config CORENET_GENERIC help This option enables support for the FSL CoreNet based boards. For 32bit kernel, the following boards are supported: - P2041 RDB, P3041 DS and P4080 DS + P2041 RDB, P3041 DS, P4080 DS, kmcoge4, and OCA4080 For 64bit kernel, the following boards are supported: T4240 QDS and B4 QDS The following boards are supported for both 32bit and 64bit kernel: - P5020 DS and P5040 DS + P5020 DS, P5040 DS and T104xQDS endif # FSL_SOC_BOOKE diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile index 25cebe74ac46..730326046625 100644 --- a/arch/powerpc/platforms/85xx/Makefile +++ b/arch/powerpc/platforms/85xx/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_SMP) += smp.o obj-y += common.o obj-$(CONFIG_BSC9131_RDB) += bsc913x_rdb.o +obj-$(CONFIG_BSC9132_QDS) += bsc913x_qds.o obj-$(CONFIG_C293_PCIE) += c293pcie.o obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o @@ -17,7 +18,7 @@ obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o obj-$(CONFIG_P1010_RDB) += p1010rdb.o obj-$(CONFIG_P1022_DS) += p1022_ds.o obj-$(CONFIG_P1022_RDK) += p1022_rdk.o -obj-$(CONFIG_P1023_RDS) += p1023_rds.o +obj-$(CONFIG_P1023_RDB) += p1023_rdb.o obj-$(CONFIG_TWR_P102x) += twr_p102x.o obj-$(CONFIG_CORENET_GENERIC) += corenet_generic.o obj-$(CONFIG_STX_GP3) += stx_gp3.o diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c new file mode 100644 index 000000000000..f0927e58af25 --- /dev/null +++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c @@ -0,0 +1,74 @@ +/* + * BSC913xQDS Board Setup + * + * Author: + * Harninder Rai <harninder.rai@freescale.com> + * Priyanka Jain <Priyanka.Jain@freescale.com> + * + * Copyright 2014 Freescale Semiconductor Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <asm/mpic.h> +#include <sysdev/fsl_soc.h> +#include <asm/udbg.h> + +#include "mpc85xx.h" +#include "smp.h" + +void __init bsc913x_qds_pic_init(void) +{ + struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | + MPIC_SINGLE_DEST_CPU, + 0, 256, " OpenPIC "); + + if (!mpic) + pr_err("bsc913x: Failed to allocate MPIC structure\n"); + else + mpic_init(mpic); +} + +/* + * Setup the architecture + */ +static void __init bsc913x_qds_setup_arch(void) +{ + if (ppc_md.progress) + ppc_md.progress("bsc913x_qds_setup_arch()", 0); + +#if defined(CONFIG_SMP) + mpc85xx_smp_init(); +#endif + + pr_info("bsc913x board from Freescale Semiconductor\n"); +} + +machine_device_initcall(bsc9132_qds, mpc85xx_common_publish_devices); + +/* + * Called very early, device-tree isn't unflattened + */ + +static int __init bsc9132_qds_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + return of_flat_dt_is_compatible(root, "fsl,bsc9132qds"); +} + +define_machine(bsc9132_qds) { + .name = "BSC9132 QDS", + .probe = bsc9132_qds_probe, + .setup_arch = bsc913x_qds_setup_arch, + .init_IRQ = bsc913x_qds_pic_init, + .get_irq = mpic_get_irq, + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +}; diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index 8e4b1e1a4911..5db1e117fdde 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -67,7 +67,7 @@ void __init corenet_gen_setup_arch(void) swiotlb_detect_4g(); - pr_info("%s board from Freescale Semiconductor\n", ppc_md.name); + pr_info("%s board\n", ppc_md.name); mpc85xx_qe_init(); } @@ -115,6 +115,7 @@ int __init corenet_gen_publish_devices(void) static const char * const boards[] __initconst = { "fsl,P2041RDB", "fsl,P3041DS", + "fsl,OCA4080", "fsl,P4080DS", "fsl,P5020DS", "fsl,P5040DS", @@ -122,12 +123,16 @@ static const char * const boards[] __initconst = { "fsl,B4860QDS", "fsl,B4420QDS", "fsl,B4220QDS", + "fsl,T1040QDS", + "fsl,T1042QDS", + "keymile,kmcoge4", NULL }; static const char * const hv_boards[] __initconst = { "fsl,P2041RDB-hv", "fsl,P3041DS-hv", + "fsl,OCA4080-hv", "fsl,P4080DS-hv", "fsl,P5020DS-hv", "fsl,P5040DS-hv", @@ -135,6 +140,8 @@ static const char * const hv_boards[] __initconst = { "fsl,B4860QDS-hv", "fsl,B4420QDS-hv", "fsl,B4220QDS-hv", + "fsl,T1040QDS-hv", + "fsl,T1042QDS-hv", NULL }; diff --git a/arch/powerpc/platforms/85xx/p1023_rds.c b/arch/powerpc/platforms/85xx/p1023_rdb.c index 0e614007acfb..d5b7509825de 100644 --- a/arch/powerpc/platforms/85xx/p1023_rds.c +++ b/arch/powerpc/platforms/85xx/p1023_rdb.c @@ -4,7 +4,7 @@ * Author: Roy Zang <tie-fei.zang@freescale.com> * * Description: - * P1023 RDS Board Setup + * P1023 RDB Board Setup * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -41,12 +41,12 @@ * Setup the architecture * */ -static void __init mpc85xx_rds_setup_arch(void) +static void __init mpc85xx_rdb_setup_arch(void) { struct device_node *np; if (ppc_md.progress) - ppc_md.progress("p1023_rds_setup_arch()", 0); + ppc_md.progress("p1023_rdb_setup_arch()", 0); /* Map BCSR area */ np = of_find_node_by_name(NULL, "bcsr"); @@ -85,10 +85,9 @@ static void __init mpc85xx_rds_setup_arch(void) fsl_pci_assign_primary(); } -machine_arch_initcall(p1023_rds, mpc85xx_common_publish_devices); machine_arch_initcall(p1023_rdb, mpc85xx_common_publish_devices); -static void __init mpc85xx_rds_pic_init(void) +static void __init mpc85xx_rdb_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU, @@ -99,14 +98,6 @@ static void __init mpc85xx_rds_pic_init(void) mpic_init(mpic); } -static int __init p1023_rds_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); - - return of_flat_dt_is_compatible(root, "fsl,P1023RDS"); - -} - static int __init p1023_rdb_probe(void) { unsigned long root = of_get_flat_dt_root(); @@ -115,26 +106,11 @@ static int __init p1023_rdb_probe(void) } -define_machine(p1023_rds) { - .name = "P1023 RDS", - .probe = p1023_rds_probe, - .setup_arch = mpc85xx_rds_setup_arch, - .init_IRQ = mpc85xx_rds_pic_init, - .get_irq = mpic_get_irq, - .restart = fsl_rstcr_restart, - .calibrate_decr = generic_calibrate_decr, - .progress = udbg_progress, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, - .pcibios_fixup_phb = fsl_pcibios_fixup_phb, -#endif -}; - define_machine(p1023_rdb) { .name = "P1023 RDB", .probe = p1023_rdb_probe, - .setup_arch = mpc85xx_rds_setup_arch, - .init_IRQ = mpc85xx_rds_pic_init, + .setup_arch = mpc85xx_rdb_setup_arch, + .init_IRQ = mpc85xx_rdb_pic_init, .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, .calibrate_decr = generic_calibrate_decr, diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 6382098d6f8d..ba093f553678 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -27,6 +27,7 @@ #include <asm/cacheflush.h> #include <asm/dbell.h> #include <asm/fsl_guts.h> +#include <asm/code-patching.h> #include <sysdev/fsl_soc.h> #include <sysdev/mpic.h> @@ -267,7 +268,7 @@ out: flush_spin_table(spin_table); out_be32(&spin_table->pir, hw_cpu); out_be64((u64 *)(&spin_table->addr_h), - __pa((u64)*((unsigned long long *)generic_secondary_smp_init))); + __pa(ppc_function_entry(generic_secondary_smp_init))); flush_spin_table(spin_table); #endif diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index d9e2b19b7c8d..43b65ad1970a 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -422,6 +422,7 @@ config CPU_BIG_ENDIAN config CPU_LITTLE_ENDIAN bool "Build little endian kernel" + select PPC64_BOOT_WRAPPER help Build a little endian kernel. @@ -430,3 +431,7 @@ config CPU_LITTLE_ENDIAN little endian powerpc. endchoice + +config PPC64_BOOT_WRAPPER + def_bool n + depends on CPU_LITTLE_ENDIAN diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c index 90745eaa45fe..c8017a7bcabd 100644 --- a/arch/powerpc/platforms/cell/smp.c +++ b/arch/powerpc/platforms/cell/smp.c @@ -40,6 +40,7 @@ #include <asm/firmware.h> #include <asm/rtas.h> #include <asm/cputhreads.h> +#include <asm/code-patching.h> #include "interrupt.h" #include <asm/udbg.h> @@ -70,8 +71,8 @@ static cpumask_t of_spin_map; static inline int smp_startup_cpu(unsigned int lcpu) { int status; - unsigned long start_here = __pa((u32)*((unsigned long *) - generic_secondary_smp_init)); + unsigned long start_here = + __pa(ppc_function_entry(generic_secondary_smp_init)); unsigned int pcpu; int start_cpu; diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index c665d7de6c99..7044fd36197b 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -574,8 +574,8 @@ chrp_init2(void) static int __init chrp_probe(void) { - char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(), - "device_type", NULL); + const char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(), + "device_type", NULL); if (dtype == NULL) return 0; if (strcmp(dtype, "chrp")) diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig index 2a7024d8d8b1..a25f496c2ef9 100644 --- a/arch/powerpc/platforms/embedded6xx/Kconfig +++ b/arch/powerpc/platforms/embedded6xx/Kconfig @@ -65,6 +65,7 @@ config MVME5100 select PPC_INDIRECT_PCI select PPC_I8259 select PPC_NATIVE + select PPC_UDBG_16550 help This option enables support for the Motorola (now Emerson) MVME5100 board. diff --git a/arch/powerpc/platforms/pasemi/powersave.S b/arch/powerpc/platforms/pasemi/powersave.S index 56f45adcd089..81ab555aa491 100644 --- a/arch/powerpc/platforms/pasemi/powersave.S +++ b/arch/powerpc/platforms/pasemi/powersave.S @@ -66,7 +66,7 @@ sleep_common: std r3, 48(r1) /* Only do power savings when in astate 0 */ - bl .check_astate + bl check_astate cmpwi r3,0 bne 1f diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 63cebb9b4d45..4ad0d345bc96 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -1,7 +1,7 @@ obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o opal-async.o obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o -obj-y += opal-msglog.o +obj-y += opal-msglog.o subcore.o subcore-asm.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 5b51079f3e3b..753f08e36dfa 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -42,11 +42,19 @@ static int ioda_eeh_event(struct notifier_block *nb, { uint64_t changed_evts = (uint64_t)change; - /* We simply send special EEH event */ - if ((changed_evts & OPAL_EVENT_PCI_ERROR) && - (events & OPAL_EVENT_PCI_ERROR) && - eeh_enabled()) + /* + * We simply send special EEH event if EEH has + * been enabled, or clear pending events in + * case that we enable EEH soon + */ + if (!(changed_evts & OPAL_EVENT_PCI_ERROR) || + !(events & OPAL_EVENT_PCI_ERROR)) + return 0; + + if (eeh_enabled()) eeh_send_failure_event(NULL); + else + opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); return 0; } @@ -141,7 +149,9 @@ static int ioda_eeh_post_init(struct pci_controller *hose) } #ifdef CONFIG_DEBUG_FS - if (phb->dbgfs) { + if (!phb->has_dbgfs && phb->dbgfs) { + phb->has_dbgfs = 1; + debugfs_create_file("err_injct_outbound", 0600, phb->dbgfs, hose, &ioda_eeh_outb_dbgfs_ops); @@ -154,7 +164,14 @@ static int ioda_eeh_post_init(struct pci_controller *hose) } #endif - phb->eeh_state |= PNV_EEH_STATE_ENABLED; + /* If EEH is enabled, we're going to rely on that. + * Otherwise, we restore to conventional mechanism + * to clear frozen PE during PCI config access. + */ + if (eeh_enabled()) + phb->flags |= PNV_PHB_FLAG_EEH; + else + phb->flags &= ~PNV_PHB_FLAG_EEH; return 0; } @@ -268,6 +285,21 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) return EEH_STATE_NOT_SUPPORT; } + /* + * If we're in middle of PE reset, return normal + * state to keep EEH core going. For PHB reset, we + * still expect to have fenced PHB cleared with + * PHB reset. + */ + if (!(pe->type & EEH_PE_PHB) && + (pe->state & EEH_PE_RESET)) { + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + return result; + } + /* Retrieve PE status through OPAL */ pe_no = pe->addr; ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, @@ -347,52 +379,6 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) return result; } -static int ioda_eeh_pe_clear(struct eeh_pe *pe) -{ - struct pci_controller *hose; - struct pnv_phb *phb; - u32 pe_no; - u8 fstate; - u16 pcierr; - s64 ret; - - pe_no = pe->addr; - hose = pe->phb; - phb = pe->phb->private_data; - - /* Clear the EEH error on the PE */ - ret = opal_pci_eeh_freeze_clear(phb->opal_id, - pe_no, OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); - if (ret) { - pr_err("%s: Failed to clear EEH error for " - "PHB#%x-PE#%x, err=%lld\n", - __func__, hose->global_number, pe_no, ret); - return -EIO; - } - - /* - * Read the PE state back and verify that the frozen - * state has been removed. - */ - ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, - &fstate, &pcierr, NULL); - if (ret) { - pr_err("%s: Failed to get EEH status on " - "PHB#%x-PE#%x\n, err=%lld\n", - __func__, hose->global_number, pe_no, ret); - return -EIO; - } - - if (fstate != OPAL_EEH_STOPPED_NOT_FROZEN) { - pr_err("%s: Frozen state not cleared on " - "PHB#%x-PE#%x, sts=%x\n", - __func__, hose->global_number, pe_no, fstate); - return -EIO; - } - - return 0; -} - static s64 ioda_eeh_phb_poll(struct pnv_phb *phb) { s64 rc = OPAL_HARDWARE; @@ -402,13 +388,16 @@ static s64 ioda_eeh_phb_poll(struct pnv_phb *phb) if (rc <= 0) break; - msleep(rc); + if (system_state < SYSTEM_RUNNING) + udelay(1000 * rc); + else + msleep(rc); } return rc; } -static int ioda_eeh_phb_reset(struct pci_controller *hose, int option) +int ioda_eeh_phb_reset(struct pci_controller *hose, int option) { struct pnv_phb *phb = hose->private_data; s64 rc = OPAL_HARDWARE; @@ -431,9 +420,17 @@ static int ioda_eeh_phb_reset(struct pci_controller *hose, int option) /* * Poll state of the PHB until the request is done - * successfully. + * successfully. The PHB reset is usually PHB complete + * reset followed by hot reset on root bus. So we also + * need the PCI bus settlement delay. */ rc = ioda_eeh_phb_poll(phb); + if (option == EEH_RESET_DEACTIVATE) { + if (system_state < SYSTEM_RUNNING) + udelay(1000 * EEH_PE_RST_SETTLE_TIME); + else + msleep(EEH_PE_RST_SETTLE_TIME); + } out: if (rc != OPAL_SUCCESS) return -EIO; @@ -471,6 +468,8 @@ static int ioda_eeh_root_reset(struct pci_controller *hose, int option) /* Poll state of the PHB until the request is done */ rc = ioda_eeh_phb_poll(phb); + if (option == EEH_RESET_DEACTIVATE) + msleep(EEH_PE_RST_SETTLE_TIME); out: if (rc != OPAL_SUCCESS) return -EIO; @@ -478,32 +477,71 @@ out: return 0; } -static int ioda_eeh_bridge_reset(struct pci_controller *hose, - struct pci_dev *dev, int option) +static int ioda_eeh_bridge_reset(struct pci_dev *dev, int option) + { - u16 ctrl; + struct device_node *dn = pci_device_to_OF_node(dev); + struct eeh_dev *edev = of_node_to_eeh_dev(dn); + int aer = edev ? edev->aer_cap : 0; + u32 ctrl; - pr_debug("%s: Reset device %04x:%02x:%02x.%01x with option %d\n", - __func__, hose->global_number, dev->bus->number, - PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn), option); + pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n", + __func__, pci_domain_nr(dev->bus), + dev->bus->number, option); switch (option) { case EEH_RESET_FUNDAMENTAL: case EEH_RESET_HOT: - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl); + /* Don't report linkDown event */ + if (aer) { + eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK, + 4, &ctrl); + ctrl |= PCI_ERR_UNC_SURPDN; + eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK, + 4, ctrl); + } + + eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); ctrl |= PCI_BRIDGE_CTL_BUS_RESET; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); + msleep(EEH_PE_RST_HOLD_TIME); + break; case EEH_RESET_DEACTIVATE: - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl); + eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); + msleep(EEH_PE_RST_SETTLE_TIME); + + /* Continue reporting linkDown event */ + if (aer) { + eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK, + 4, &ctrl); + ctrl &= ~PCI_ERR_UNC_SURPDN; + eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK, + 4, ctrl); + } + break; } return 0; } +void pnv_pci_reset_secondary_bus(struct pci_dev *dev) +{ + struct pci_controller *hose; + + if (pci_is_root_bus(dev->bus)) { + hose = pci_bus_to_host(dev->bus); + ioda_eeh_root_reset(hose, EEH_RESET_HOT); + ioda_eeh_root_reset(hose, EEH_RESET_DEACTIVATE); + } else { + ioda_eeh_bridge_reset(dev, EEH_RESET_HOT); + ioda_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE); + } +} + /** * ioda_eeh_reset - Reset the indicated PE * @pe: EEH PE @@ -523,27 +561,18 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option) int ret; /* - * Anyway, we have to clear the problematic state for the - * corresponding PE. However, we needn't do it if the PE - * is PHB associated. That means the PHB is having fatal - * errors and it needs reset. Further more, the AIB interface - * isn't reliable any more. - */ - if (!(pe->type & EEH_PE_PHB) && - (option == EEH_RESET_HOT || - option == EEH_RESET_FUNDAMENTAL)) { - ret = ioda_eeh_pe_clear(pe); - if (ret) - return -EIO; - } - - /* - * The rules applied to reset, either fundamental or hot reset: + * For PHB reset, we always have complete reset. For those PEs whose + * primary bus derived from root complex (root bus) or root port + * (usually bus#1), we apply hot or fundamental reset on the root port. + * For other PEs, we always have hot reset on the PE primary bus. * - * We always reset the direct upstream bridge of the PE. If the - * direct upstream bridge isn't root bridge, we always take hot - * reset no matter what option (fundamental or hot) is. Otherwise, - * we should do the reset according to the required option. + * Here, we have different design to pHyp, which always clear the + * frozen state during PE reset. However, the good idea here from + * benh is to keep frozen state before we get PE reset done completely + * (until BAR restore). With the frozen state, HW drops illegal IO + * or MMIO access, which can incur recrusive frozen PE during PE + * reset. The side effect is that EEH core has to clear the frozen + * state explicitly after BAR restore. */ if (pe->type & EEH_PE_PHB) { ret = ioda_eeh_phb_reset(hose, option); @@ -553,7 +582,7 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option) pci_is_root_bus(bus->parent)) ret = ioda_eeh_root_reset(hose, option); else - ret = ioda_eeh_bridge_reset(hose, bus->self, option); + ret = ioda_eeh_bridge_reset(bus->self, option); } return ret; @@ -640,22 +669,6 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose) } } -static int ioda_eeh_get_phb_pe(struct pci_controller *hose, - struct eeh_pe **pe) -{ - struct eeh_pe *phb_pe; - - phb_pe = eeh_phb_pe_get(hose); - if (!phb_pe) { - pr_warning("%s Can't find PE for PHB#%d\n", - __func__, hose->global_number); - return -EEXIST; - } - - *pe = phb_pe; - return 0; -} - static int ioda_eeh_get_pe(struct pci_controller *hose, u16 pe_no, struct eeh_pe **pe) { @@ -663,7 +676,8 @@ static int ioda_eeh_get_pe(struct pci_controller *hose, struct eeh_dev dev; /* Find the PHB PE */ - if (ioda_eeh_get_phb_pe(hose, &phb_pe)) + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe) return -EEXIST; /* Find the PE according to PE# */ @@ -691,6 +705,7 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) { struct pci_controller *hose; struct pnv_phb *phb; + struct eeh_pe *phb_pe; u64 frozen_pe_no; u16 err_type, severity; long rc; @@ -707,10 +722,12 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) list_for_each_entry(hose, &hose_list, list_node) { /* * If the subordinate PCI buses of the PHB has been - * removed, we needn't take care of it any more. + * removed or is exactly under error recovery, we + * needn't take care of it any more. */ phb = hose->private_data; - if (phb->eeh_state & PNV_EEH_STATE_REMOVED) + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED)) continue; rc = opal_pci_next_error(phb->opal_id, @@ -743,12 +760,6 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) switch (err_type) { case OPAL_EEH_IOC_ERROR: if (severity == OPAL_EEH_SEV_IOC_DEAD) { - list_for_each_entry(hose, &hose_list, - list_node) { - phb = hose->private_data; - phb->eeh_state |= PNV_EEH_STATE_REMOVED; - } - pr_err("EEH: dead IOC detected\n"); ret = EEH_NEXT_ERR_DEAD_IOC; } else if (severity == OPAL_EEH_SEV_INF) { @@ -761,17 +772,12 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) break; case OPAL_EEH_PHB_ERROR: if (severity == OPAL_EEH_SEV_PHB_DEAD) { - if (ioda_eeh_get_phb_pe(hose, pe)) - break; - + *pe = phb_pe; pr_err("EEH: dead PHB#%x detected\n", hose->global_number); - phb->eeh_state |= PNV_EEH_STATE_REMOVED; ret = EEH_NEXT_ERR_DEAD_PHB; } else if (severity == OPAL_EEH_SEV_PHB_FENCED) { - if (ioda_eeh_get_phb_pe(hose, pe)) - break; - + *pe = phb_pe; pr_err("EEH: fenced PHB#%x detected\n", hose->global_number); ret = EEH_NEXT_ERR_FENCED_PHB; @@ -789,17 +795,21 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) * If we can't find the corresponding PE, the * PEEV / PEST would be messy. So we force an * fenced PHB so that it can be recovered. + * + * If the PE has been marked as isolated, that + * should have been removed permanently or in + * progress with recovery. We needn't report + * it again. */ if (ioda_eeh_get_pe(hose, frozen_pe_no, pe)) { - if (!ioda_eeh_get_phb_pe(hose, pe)) { - pr_err("EEH: Escalated fenced PHB#%x " - "detected for PE#%llx\n", - hose->global_number, - frozen_pe_no); - ret = EEH_NEXT_ERR_FENCED_PHB; - } else { - ret = EEH_NEXT_ERR_NONE; - } + *pe = phb_pe; + pr_err("EEH: Escalated fenced PHB#%x " + "detected for PE#%llx\n", + hose->global_number, + frozen_pe_no); + ret = EEH_NEXT_ERR_FENCED_PHB; + } else if ((*pe)->state & EEH_PE_ISOLATED) { + ret = EEH_NEXT_ERR_NONE; } else { pr_err("EEH: Frozen PE#%x on PHB#%x detected\n", (*pe)->addr, (*pe)->phb->global_number); diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index a59788e83b8b..56a206f32f77 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -126,6 +126,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) edev->mode &= 0xFFFFFF00; if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) edev->mode |= EEH_DEV_BRIDGE; + edev->pcix_cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); if (pci_is_pcie(dev)) { edev->pcie_cap = pci_pcie_cap(dev); @@ -133,6 +134,9 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) edev->mode |= EEH_DEV_ROOT_PORT; else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM) edev->mode |= EEH_DEV_DS_PORT; + + edev->aer_cap = pci_find_ext_capability(dev, + PCI_EXT_CAP_ID_ERR); } edev->config_addr = ((dev->bus->number << 8) | dev->devfn); diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index dc487ff04704..5c21d9c07f45 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -20,6 +20,7 @@ #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> +#include <linux/delay.h> #include <asm/opal.h> @@ -130,7 +131,8 @@ static inline void opal_flash_validate(void) { long ret; void *buf = validate_flash_data.buf; - __be32 size, result; + __be32 size = cpu_to_be32(validate_flash_data.buf_size); + __be32 result; ret = opal_validate_flash(__pa(buf), &size, &result); @@ -290,11 +292,6 @@ static int opal_flash_update(int op) /* First entry address */ addr = __pa(list); - pr_alert("FLASH: Image is %u bytes\n", image_data.size); - pr_alert("FLASH: Image update requested\n"); - pr_alert("FLASH: Image will be updated during system reboot\n"); - pr_alert("FLASH: This will take several minutes. Do not power off!\n"); - flash: rc = opal_update_flash(addr); @@ -302,6 +299,47 @@ invalid_img: return rc; } +/* Return CPUs to OPAL before starting FW update */ +static void flash_return_cpu(void *info) +{ + int cpu = smp_processor_id(); + + if (!cpu_online(cpu)) + return; + + /* Disable IRQ */ + hard_irq_disable(); + + /* Return the CPU to OPAL */ + opal_return_cpu(); +} + +/* This gets called just before system reboots */ +void opal_flash_term_callback(void) +{ + struct cpumask mask; + + if (update_flash_data.status != FLASH_IMG_READY) + return; + + pr_alert("FLASH: Flashing new firmware\n"); + pr_alert("FLASH: Image is %u bytes\n", image_data.size); + pr_alert("FLASH: Performing flash and reboot/shutdown\n"); + pr_alert("FLASH: This will take several minutes. Do not power off!\n"); + + /* Small delay to help getting the above message out */ + msleep(500); + + /* Return secondary CPUs to firmware */ + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + if (!cpumask_empty(&mask)) + smp_call_function_many(&mask, + flash_return_cpu, NULL, false); + /* Hard disable interrupts */ + hard_irq_disable(); +} + /* * Show candidate image status */ diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c index 79d83cad3d67..f04b4d8aca5a 100644 --- a/arch/powerpc/platforms/powernv/opal-lpc.c +++ b/arch/powerpc/platforms/powernv/opal-lpc.c @@ -12,12 +12,17 @@ #include <linux/kernel.h> #include <linux/of.h> #include <linux/bug.h> +#include <linux/debugfs.h> +#include <linux/io.h> +#include <linux/slab.h> #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/xics.h> #include <asm/opal.h> #include <asm/prom.h> +#include <asm/uaccess.h> +#include <asm/debug.h> static int opal_lpc_chip_id = -1; @@ -176,6 +181,152 @@ static const struct ppc_pci_io opal_lpc_io = { .outsl = opal_lpc_outsl, }; +#ifdef CONFIG_DEBUG_FS +struct lpc_debugfs_entry { + enum OpalLPCAddressType lpc_type; +}; + +static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct lpc_debugfs_entry *lpc = filp->private_data; + u32 data, pos, len, todo; + int rc; + + if (!access_ok(VERIFY_WRITE, ubuf, count)) + return -EFAULT; + + todo = count; + while (todo) { + pos = *ppos; + + /* + * Select access size based on count and alignment and + * access type. IO and MEM only support byte acceses, + * FW supports all 3. + */ + len = 1; + if (lpc->lpc_type == OPAL_LPC_FW) { + if (todo > 3 && (pos & 3) == 0) + len = 4; + else if (todo > 1 && (pos & 1) == 0) + len = 2; + } + rc = opal_lpc_read(opal_lpc_chip_id, lpc->lpc_type, pos, + &data, len); + if (rc) + return -ENXIO; + switch(len) { + case 4: + rc = __put_user((u32)data, (u32 __user *)ubuf); + break; + case 2: + rc = __put_user((u16)data, (u16 __user *)ubuf); + break; + default: + rc = __put_user((u8)data, (u8 __user *)ubuf); + break; + } + if (rc) + return -EFAULT; + *ppos += len; + ubuf += len; + todo -= len; + } + + return count; +} + +static ssize_t lpc_debug_write(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct lpc_debugfs_entry *lpc = filp->private_data; + u32 data, pos, len, todo; + int rc; + + if (!access_ok(VERIFY_READ, ubuf, count)) + return -EFAULT; + + todo = count; + while (todo) { + pos = *ppos; + + /* + * Select access size based on count and alignment and + * access type. IO and MEM only support byte acceses, + * FW supports all 3. + */ + len = 1; + if (lpc->lpc_type == OPAL_LPC_FW) { + if (todo > 3 && (pos & 3) == 0) + len = 4; + else if (todo > 1 && (pos & 1) == 0) + len = 2; + } + switch(len) { + case 4: + rc = __get_user(data, (u32 __user *)ubuf); + break; + case 2: + rc = __get_user(data, (u16 __user *)ubuf); + break; + default: + rc = __get_user(data, (u8 __user *)ubuf); + break; + } + if (rc) + return -EFAULT; + + rc = opal_lpc_write(opal_lpc_chip_id, lpc->lpc_type, pos, + data, len); + if (rc) + return -ENXIO; + *ppos += len; + ubuf += len; + todo -= len; + } + + return count; +} + +static const struct file_operations lpc_fops = { + .read = lpc_debug_read, + .write = lpc_debug_write, + .open = simple_open, + .llseek = default_llseek, +}; + +static int opal_lpc_debugfs_create_type(struct dentry *folder, + const char *fname, + enum OpalLPCAddressType type) +{ + struct lpc_debugfs_entry *entry; + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + entry->lpc_type = type; + debugfs_create_file(fname, 0600, folder, entry, &lpc_fops); + return 0; +} + +static int opal_lpc_init_debugfs(void) +{ + struct dentry *root; + int rc = 0; + + if (opal_lpc_chip_id < 0) + return -ENODEV; + + root = debugfs_create_dir("lpc", powerpc_debugfs_root); + + rc |= opal_lpc_debugfs_create_type(root, "io", OPAL_LPC_IO); + rc |= opal_lpc_debugfs_create_type(root, "mem", OPAL_LPC_MEM); + rc |= opal_lpc_debugfs_create_type(root, "fw", OPAL_LPC_FW); + return rc; +} +device_initcall(opal_lpc_init_debugfs); +#endif /* CONFIG_DEBUG_FS */ + void opal_lpc_init(void) { struct device_node *np; diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c index ec4132239cdf..b17a34b695ef 100644 --- a/arch/powerpc/platforms/powernv/opal-memory-errors.c +++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c @@ -47,12 +47,12 @@ static void handle_memory_error_event(struct OpalMemoryErrorData *merr_evt) __func__, merr_evt->type); switch (merr_evt->type) { case OPAL_MEM_ERR_TYPE_RESILIENCE: - paddr_start = merr_evt->u.resilience.physical_address_start; - paddr_end = merr_evt->u.resilience.physical_address_end; + paddr_start = be64_to_cpu(merr_evt->u.resilience.physical_address_start); + paddr_end = be64_to_cpu(merr_evt->u.resilience.physical_address_end); break; case OPAL_MEM_ERR_TYPE_DYN_DALLOC: - paddr_start = merr_evt->u.dyn_dealloc.physical_address_start; - paddr_end = merr_evt->u.dyn_dealloc.physical_address_end; + paddr_start = be64_to_cpu(merr_evt->u.dyn_dealloc.physical_address_start); + paddr_end = be64_to_cpu(merr_evt->u.dyn_dealloc.physical_address_end); break; default: return; diff --git a/arch/powerpc/platforms/powernv/opal-takeover.S b/arch/powerpc/platforms/powernv/opal-takeover.S index 3cd262897c27..11a3169ee583 100644 --- a/arch/powerpc/platforms/powernv/opal-takeover.S +++ b/arch/powerpc/platforms/powernv/opal-takeover.S @@ -21,11 +21,13 @@ _GLOBAL(opal_query_takeover) mfcr r0 stw r0,8(r1) + stdu r1,-STACKFRAMESIZE(r1) std r3,STK_PARAM(R3)(r1) std r4,STK_PARAM(R4)(r1) li r3,H_HAL_TAKEOVER li r4,H_HAL_TAKEOVER_QUERY_MAGIC HVSC + addi r1,r1,STACKFRAMESIZE ld r10,STK_PARAM(R3)(r1) std r4,0(r10) ld r10,STK_PARAM(R4)(r1) diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index f531ffe35b3e..4abbff22a61f 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -32,7 +32,7 @@ std r12,PACASAVEDMSR(r13); \ andc r12,r12,r0; \ mtmsrd r12,1; \ - LOAD_REG_ADDR(r0,.opal_return); \ + LOAD_REG_ADDR(r0,opal_return); \ mtlr r0; \ li r0,MSR_DR|MSR_IR|MSR_LE;\ andc r12,r12,r0; \ @@ -44,7 +44,7 @@ mtspr SPRN_HSRR0,r12; \ hrfid -_STATIC(opal_return) +opal_return: /* * Fixup endian on OPAL return... we should be able to simplify * this by instead converting the below trampoline to a set of @@ -124,6 +124,7 @@ OPAL_CALL(opal_xscom_write, OPAL_XSCOM_WRITE); OPAL_CALL(opal_lpc_read, OPAL_LPC_READ); OPAL_CALL(opal_lpc_write, OPAL_LPC_WRITE); OPAL_CALL(opal_return_cpu, OPAL_RETURN_CPU); +OPAL_CALL(opal_reinit_cpus, OPAL_REINIT_CPUS); OPAL_CALL(opal_read_elog, OPAL_ELOG_READ); OPAL_CALL(opal_send_ack_elog, OPAL_ELOG_ACK); OPAL_CALL(opal_get_elog_size, OPAL_ELOG_SIZE); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 360ad80c754c..199975613fe9 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -57,11 +57,26 @@ static DEFINE_SPINLOCK(opal_notifier_lock); static uint64_t last_notified_mask = 0x0ul; static atomic_t opal_notifier_hold = ATOMIC_INIT(0); +static void opal_reinit_cores(void) +{ + /* Do the actual re-init, This will clobber all FPRs, VRs, etc... + * + * It will preserve non volatile GPRs and HSPRG0/1. It will + * also restore HIDs and other SPRs to their original value + * but it might clobber a bunch. + */ +#ifdef __BIG_ENDIAN__ + opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE); +#else + opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_LE); +#endif +} + int __init early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data) { const void *basep, *entryp, *sizep; - unsigned long basesz, entrysz, runtimesz; + int basesz, entrysz, runtimesz; if (depth != 1 || strcmp(uname, "ibm,opal") != 0) return 0; @@ -77,11 +92,11 @@ int __init early_init_dt_scan_opal(unsigned long node, opal.entry = of_read_number(entryp, entrysz/4); opal.size = of_read_number(sizep, runtimesz/4); - pr_debug("OPAL Base = 0x%llx (basep=%p basesz=%ld)\n", + pr_debug("OPAL Base = 0x%llx (basep=%p basesz=%d)\n", opal.base, basep, basesz); - pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%ld)\n", + pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%d)\n", opal.entry, entryp, entrysz); - pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%ld)\n", + pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%d)\n", opal.size, sizep, runtimesz); powerpc_firmware_features |= FW_FEATURE_OPAL; @@ -96,13 +111,20 @@ int __init early_init_dt_scan_opal(unsigned long node, printk("OPAL V1 detected !\n"); } + /* Reinit all cores with the right endian */ + opal_reinit_cores(); + + /* Restore some bits */ + if (cur_cpu_spec->cpu_restore) + cur_cpu_spec->cpu_restore(); + return 1; } int __init early_init_dt_scan_recoverable_ranges(unsigned long node, const char *uname, int depth, void *data) { - unsigned long i, psize, size; + int i, psize, size; const __be32 *prop; if (depth != 1 || strcmp(uname, "ibm,opal") != 0) @@ -359,7 +381,7 @@ int opal_get_chars(uint32_t vtermno, char *buf, int count) if ((be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_INPUT) == 0) return 0; len = cpu_to_be64(count); - rc = opal_console_read(vtermno, &len, buf); + rc = opal_console_read(vtermno, &len, buf); if (rc == OPAL_SUCCESS) return be64_to_cpu(len); return 0; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 98824aa99173..de19edeaa7a7 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/pci.h> +#include <linux/crash_dump.h> #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/string.h> @@ -663,15 +664,15 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, * errors, and on the first pass the data will be a relative * bus number, print that out instead. */ - tbl->it_busno = 0; pe->tce_inval_reg_phys = be64_to_cpup(swinvp); tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys, 8); - tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE | - TCE_PCI_SWINV_PAIR; + tbl->it_type |= (TCE_PCI_SWINV_CREATE | + TCE_PCI_SWINV_FREE | + TCE_PCI_SWINV_PAIR); } iommu_init_table(tbl, phb->hose->node); - iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number); + iommu_register_group(tbl, phb->hose->global_number, pe->pe_number); if (pe->pdev) set_iommu_table_base_and_group(&pe->pdev->dev, tbl); @@ -793,14 +794,13 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, * errors, and on the first pass the data will be a relative * bus number, print that out instead. */ - tbl->it_busno = 0; pe->tce_inval_reg_phys = be64_to_cpup(swinvp); tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys, 8); - tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE; + tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE); } iommu_init_table(tbl, phb->hose->node); - iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number); + iommu_register_group(tbl, phb->hose->global_number, pe->pe_number); if (pe->pdev) set_iommu_table_base_and_group(&pe->pdev->dev, tbl); @@ -1386,12 +1386,24 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, ppc_md.pcibios_fixup = pnv_pci_ioda_fixup; ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook; ppc_md.pcibios_window_alignment = pnv_pci_window_alignment; + ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus; pci_add_flags(PCI_REASSIGN_ALL_RSRC); /* Reset IODA tables to a clean state */ rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET); if (rc) pr_warning(" OPAL Error %ld performing IODA table reset !\n", rc); + + /* If we're running in kdump kerenl, the previous kerenl never + * shutdown PCI devices correctly. We already got IODA table + * cleaned out. So we have to issue PHB reset to stop all PCI + * transactions from previous kerenl. + */ + if (is_kdump_kernel()) { + pr_info(" Issue PHB reset ...\n"); + ioda_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL); + ioda_eeh_phb_reset(hose, OPAL_DEASSERT_RESET); + } } void __init pnv_pci_init_ioda2_phb(struct device_node *np) diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 8518817dcdfd..eefbfcc3fd8c 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -131,65 +131,60 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose, int i; data = (struct OpalIoP7IOCPhbErrorData *)common; - pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n", + pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n", hose->global_number, common->version); if (data->brdgCtl) - pr_info(" brdgCtl: %08x\n", + pr_info("brdgCtl: %08x\n", data->brdgCtl); if (data->portStatusReg || data->rootCmplxStatus || data->busAgentStatus) - pr_info(" UtlSts: %08x %08x %08x\n", + pr_info("UtlSts: %08x %08x %08x\n", data->portStatusReg, data->rootCmplxStatus, data->busAgentStatus); if (data->deviceStatus || data->slotStatus || data->linkStatus || data->devCmdStatus || data->devSecStatus) - pr_info(" RootSts: %08x %08x %08x %08x %08x\n", + pr_info("RootSts: %08x %08x %08x %08x %08x\n", data->deviceStatus, data->slotStatus, data->linkStatus, data->devCmdStatus, data->devSecStatus); if (data->rootErrorStatus || data->uncorrErrorStatus || data->corrErrorStatus) - pr_info(" RootErrSts: %08x %08x %08x\n", + pr_info("RootErrSts: %08x %08x %08x\n", data->rootErrorStatus, data->uncorrErrorStatus, data->corrErrorStatus); if (data->tlpHdr1 || data->tlpHdr2 || data->tlpHdr3 || data->tlpHdr4) - pr_info(" RootErrLog: %08x %08x %08x %08x\n", + pr_info("RootErrLog: %08x %08x %08x %08x\n", data->tlpHdr1, data->tlpHdr2, data->tlpHdr3, data->tlpHdr4); if (data->sourceId || data->errorClass || data->correlator) - pr_info(" RootErrLog1: %08x %016llx %016llx\n", + pr_info("RootErrLog1: %08x %016llx %016llx\n", data->sourceId, data->errorClass, data->correlator); if (data->p7iocPlssr || data->p7iocCsr) - pr_info(" PhbSts: %016llx %016llx\n", + pr_info("PhbSts: %016llx %016llx\n", data->p7iocPlssr, data->p7iocCsr); - if (data->lemFir || data->lemErrorMask || - data->lemWOF) - pr_info(" Lem: %016llx %016llx %016llx\n", + if (data->lemFir) + pr_info("Lem: %016llx %016llx %016llx\n", data->lemFir, data->lemErrorMask, data->lemWOF); - if (data->phbErrorStatus || data->phbFirstErrorStatus || - data->phbErrorLog0 || data->phbErrorLog1) - pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n", + if (data->phbErrorStatus) + pr_info("PhbErr: %016llx %016llx %016llx %016llx\n", data->phbErrorStatus, data->phbFirstErrorStatus, data->phbErrorLog0, data->phbErrorLog1); - if (data->mmioErrorStatus || data->mmioFirstErrorStatus || - data->mmioErrorLog0 || data->mmioErrorLog1) - pr_info(" OutErr: %016llx %016llx %016llx %016llx\n", + if (data->mmioErrorStatus) + pr_info("OutErr: %016llx %016llx %016llx %016llx\n", data->mmioErrorStatus, data->mmioFirstErrorStatus, data->mmioErrorLog0, data->mmioErrorLog1); - if (data->dma0ErrorStatus || data->dma0FirstErrorStatus || - data->dma0ErrorLog0 || data->dma0ErrorLog1) - pr_info(" InAErr: %016llx %016llx %016llx %016llx\n", + if (data->dma0ErrorStatus) + pr_info("InAErr: %016llx %016llx %016llx %016llx\n", data->dma0ErrorStatus, data->dma0FirstErrorStatus, data->dma0ErrorLog0, data->dma0ErrorLog1); - if (data->dma1ErrorStatus || data->dma1FirstErrorStatus || - data->dma1ErrorLog0 || data->dma1ErrorLog1) - pr_info(" InBErr: %016llx %016llx %016llx %016llx\n", + if (data->dma1ErrorStatus) + pr_info("InBErr: %016llx %016llx %016llx %016llx\n", data->dma1ErrorStatus, data->dma1FirstErrorStatus, data->dma1ErrorLog0, data->dma1ErrorLog1); @@ -198,7 +193,7 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose, (data->pestB[i] >> 63) == 0) continue; - pr_info(" PE[%3d] A/B: %016llx %016llx\n", + pr_info("PE[%3d] A/B: %016llx %016llx\n", i, data->pestA[i], data->pestB[i]); } } @@ -210,69 +205,63 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose, int i; data = (struct OpalIoPhb3ErrorData*)common; - pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n", + pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n", hose->global_number, common->version); if (data->brdgCtl) - pr_info(" brdgCtl: %08x\n", + pr_info("brdgCtl: %08x\n", data->brdgCtl); if (data->portStatusReg || data->rootCmplxStatus || data->busAgentStatus) - pr_info(" UtlSts: %08x %08x %08x\n", + pr_info("UtlSts: %08x %08x %08x\n", data->portStatusReg, data->rootCmplxStatus, data->busAgentStatus); if (data->deviceStatus || data->slotStatus || data->linkStatus || data->devCmdStatus || data->devSecStatus) - pr_info(" RootSts: %08x %08x %08x %08x %08x\n", + pr_info("RootSts: %08x %08x %08x %08x %08x\n", data->deviceStatus, data->slotStatus, data->linkStatus, data->devCmdStatus, data->devSecStatus); if (data->rootErrorStatus || data->uncorrErrorStatus || data->corrErrorStatus) - pr_info(" RootErrSts: %08x %08x %08x\n", + pr_info("RootErrSts: %08x %08x %08x\n", data->rootErrorStatus, data->uncorrErrorStatus, data->corrErrorStatus); if (data->tlpHdr1 || data->tlpHdr2 || data->tlpHdr3 || data->tlpHdr4) - pr_info(" RootErrLog: %08x %08x %08x %08x\n", + pr_info("RootErrLog: %08x %08x %08x %08x\n", data->tlpHdr1, data->tlpHdr2, data->tlpHdr3, data->tlpHdr4); if (data->sourceId || data->errorClass || data->correlator) - pr_info(" RootErrLog1: %08x %016llx %016llx\n", + pr_info("RootErrLog1: %08x %016llx %016llx\n", data->sourceId, data->errorClass, data->correlator); - if (data->nFir || data->nFirMask || - data->nFirWOF) - pr_info(" nFir: %016llx %016llx %016llx\n", + if (data->nFir) + pr_info("nFir: %016llx %016llx %016llx\n", data->nFir, data->nFirMask, data->nFirWOF); if (data->phbPlssr || data->phbCsr) - pr_info(" PhbSts: %016llx %016llx\n", + pr_info("PhbSts: %016llx %016llx\n", data->phbPlssr, data->phbCsr); - if (data->lemFir || data->lemErrorMask || - data->lemWOF) - pr_info(" Lem: %016llx %016llx %016llx\n", + if (data->lemFir) + pr_info("Lem: %016llx %016llx %016llx\n", data->lemFir, data->lemErrorMask, data->lemWOF); - if (data->phbErrorStatus || data->phbFirstErrorStatus || - data->phbErrorLog0 || data->phbErrorLog1) - pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n", + if (data->phbErrorStatus) + pr_info("PhbErr: %016llx %016llx %016llx %016llx\n", data->phbErrorStatus, data->phbFirstErrorStatus, data->phbErrorLog0, data->phbErrorLog1); - if (data->mmioErrorStatus || data->mmioFirstErrorStatus || - data->mmioErrorLog0 || data->mmioErrorLog1) - pr_info(" OutErr: %016llx %016llx %016llx %016llx\n", + if (data->mmioErrorStatus) + pr_info("OutErr: %016llx %016llx %016llx %016llx\n", data->mmioErrorStatus, data->mmioFirstErrorStatus, data->mmioErrorLog0, data->mmioErrorLog1); - if (data->dma0ErrorStatus || data->dma0FirstErrorStatus || - data->dma0ErrorLog0 || data->dma0ErrorLog1) - pr_info(" InAErr: %016llx %016llx %016llx %016llx\n", + if (data->dma0ErrorStatus) + pr_info("InAErr: %016llx %016llx %016llx %016llx\n", data->dma0ErrorStatus, data->dma0FirstErrorStatus, data->dma0ErrorLog0, data->dma0ErrorLog1); - if (data->dma1ErrorStatus || data->dma1FirstErrorStatus || - data->dma1ErrorLog0 || data->dma1ErrorLog1) - pr_info(" InBErr: %016llx %016llx %016llx %016llx\n", + if (data->dma1ErrorStatus) + pr_info("InBErr: %016llx %016llx %016llx %016llx\n", data->dma1ErrorStatus, data->dma1FirstErrorStatus, data->dma1ErrorLog0, data->dma1ErrorLog1); @@ -281,7 +270,7 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose, (data->pestB[i] >> 63) == 0) continue; - pr_info(" PE[%3d] A/B: %016llx %016llx\n", + pr_info("PE[%3d] A/B: %016llx %016llx\n", i, data->pestA[i], data->pestB[i]); } } @@ -384,9 +373,6 @@ int pnv_pci_cfg_read(struct device_node *dn, struct pci_dn *pdn = PCI_DN(dn); struct pnv_phb *phb = pdn->phb->private_data; u32 bdfn = (pdn->busno << 8) | pdn->devfn; -#ifdef CONFIG_EEH - struct eeh_pe *phb_pe = NULL; -#endif s64 rc; switch (size) { @@ -412,31 +398,9 @@ int pnv_pci_cfg_read(struct device_node *dn, default: return PCIBIOS_FUNC_NOT_SUPPORTED; } + cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n", __func__, pdn->busno, pdn->devfn, where, size, *val); - - /* - * Check if the specified PE has been put into frozen - * state. On the other hand, we needn't do that while - * the PHB has been put into frozen state because of - * PHB-fatal errors. - */ -#ifdef CONFIG_EEH - phb_pe = eeh_phb_pe_get(pdn->phb); - if (phb_pe && (phb_pe->state & EEH_PE_ISOLATED)) - return PCIBIOS_SUCCESSFUL; - - if (phb->eeh_state & PNV_EEH_STATE_ENABLED) { - if (*val == EEH_IO_ERROR_VALUE(size) && - eeh_dev_check_failure(of_node_to_eeh_dev(dn))) - return PCIBIOS_DEVICE_NOT_FOUND; - } else { - pnv_pci_config_check_eeh(phb, dn); - } -#else - pnv_pci_config_check_eeh(phb, dn); -#endif - return PCIBIOS_SUCCESSFUL; } @@ -463,33 +427,74 @@ int pnv_pci_cfg_write(struct device_node *dn, return PCIBIOS_FUNC_NOT_SUPPORTED; } - /* Check if the PHB got frozen due to an error (no response) */ -#ifdef CONFIG_EEH - if (!(phb->eeh_state & PNV_EEH_STATE_ENABLED)) - pnv_pci_config_check_eeh(phb, dn); -#else - pnv_pci_config_check_eeh(phb, dn); -#endif - return PCIBIOS_SUCCESSFUL; } +#if CONFIG_EEH +static bool pnv_pci_cfg_check(struct pci_controller *hose, + struct device_node *dn) +{ + struct eeh_dev *edev = NULL; + struct pnv_phb *phb = hose->private_data; + + /* EEH not enabled ? */ + if (!(phb->flags & PNV_PHB_FLAG_EEH)) + return true; + + /* PE reset or device removed ? */ + edev = of_node_to_eeh_dev(dn); + if (edev) { + if (edev->pe && + (edev->pe->state & EEH_PE_RESET)) + return false; + + if (edev->mode & EEH_DEV_REMOVED) + return false; + } + + return true; +} +#else +static inline pnv_pci_cfg_check(struct pci_controller *hose, + struct device_node *dn) +{ + return true; +} +#endif /* CONFIG_EEH */ + static int pnv_pci_read_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { struct device_node *dn, *busdn = pci_bus_to_OF_node(bus); struct pci_dn *pdn; + struct pnv_phb *phb; + bool found = false; + int ret; + *val = 0xFFFFFFFF; for (dn = busdn->child; dn; dn = dn->sibling) { pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn) - return pnv_pci_cfg_read(dn, where, size, val); + if (pdn && pdn->devfn == devfn) { + phb = pdn->phb->private_data; + found = true; + break; + } } - *val = 0xFFFFFFFF; - return PCIBIOS_DEVICE_NOT_FOUND; + if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + return PCIBIOS_DEVICE_NOT_FOUND; + ret = pnv_pci_cfg_read(dn, where, size, val); + if (phb->flags & PNV_PHB_FLAG_EEH) { + if (*val == EEH_IO_ERROR_VALUE(size) && + eeh_dev_check_failure(of_node_to_eeh_dev(dn))) + return PCIBIOS_DEVICE_NOT_FOUND; + } else { + pnv_pci_config_check_eeh(phb, dn); + } + + return ret; } static int pnv_pci_write_config(struct pci_bus *bus, @@ -498,14 +503,27 @@ static int pnv_pci_write_config(struct pci_bus *bus, { struct device_node *dn, *busdn = pci_bus_to_OF_node(bus); struct pci_dn *pdn; + struct pnv_phb *phb; + bool found = false; + int ret; for (dn = busdn->child; dn; dn = dn->sibling) { pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn) - return pnv_pci_cfg_write(dn, where, size, val); + if (pdn && pdn->devfn == devfn) { + phb = pdn->phb->private_data; + found = true; + break; + } } - return PCIBIOS_DEVICE_NOT_FOUND; + if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + ret = pnv_pci_cfg_write(dn, where, size, val); + if (!(phb->flags & PNV_PHB_FLAG_EEH)) + pnv_pci_config_check_eeh(phb, dn); + + return ret; } struct pci_ops pnv_pci_ops = { diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index cde169442775..676232c34328 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -81,28 +81,27 @@ struct pnv_eeh_ops { int (*configure_bridge)(struct eeh_pe *pe); int (*next_error)(struct eeh_pe **pe); }; - -#define PNV_EEH_STATE_ENABLED (1 << 0) /* EEH enabled */ -#define PNV_EEH_STATE_REMOVED (1 << 1) /* PHB removed */ - #endif /* CONFIG_EEH */ +#define PNV_PHB_FLAG_EEH (1 << 0) + struct pnv_phb { struct pci_controller *hose; enum pnv_phb_type type; enum pnv_phb_model model; u64 hub_id; u64 opal_id; + int flags; void __iomem *regs; int initialized; spinlock_t lock; #ifdef CONFIG_EEH struct pnv_eeh_ops *eeh_ops; - int eeh_state; #endif #ifdef CONFIG_DEBUG_FS + int has_dbgfs; struct dentry *dbgfs; #endif @@ -205,5 +204,7 @@ extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, __be64 *startp, __be64 *endp, bool rm); +extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); +extern int ioda_eeh_phb_reset(struct pci_controller *hose, int option); #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 0051e108ef0f..75501bfede7f 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -25,4 +25,6 @@ static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) extern void pnv_lpc_init(void); +bool cpu_core_split_required(void); + #endif /* _POWERNV_H */ diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 8723d32632f5..8c16a5f96728 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -27,6 +27,7 @@ #include <linux/interrupt.h> #include <linux/bug.h> #include <linux/pci.h> +#include <linux/cpufreq.h> #include <asm/machdep.h> #include <asm/firmware.h> @@ -98,11 +99,32 @@ static void pnv_show_cpuinfo(struct seq_file *m) of_node_put(root); } +static void pnv_prepare_going_down(void) +{ + /* + * Disable all notifiers from OPAL, we can't + * service interrupts anymore anyway + */ + opal_notifier_disable(); + + /* Soft disable interrupts */ + local_irq_disable(); + + /* + * Return secondary CPUs to firwmare if a flash update + * is pending otherwise we will get all sort of error + * messages about CPU being stuck etc.. This will also + * have the side effect of hard disabling interrupts so + * past this point, the kernel is effectively dead. + */ + opal_flash_term_callback(); +} + static void __noreturn pnv_restart(char *cmd) { long rc = OPAL_BUSY; - opal_notifier_disable(); + pnv_prepare_going_down(); while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_cec_reboot(); @@ -119,7 +141,7 @@ static void __noreturn pnv_power_off(void) { long rc = OPAL_BUSY; - opal_notifier_disable(); + pnv_prepare_going_down(); while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_cec_power_down(0); @@ -222,6 +244,13 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) } #endif /* CONFIG_KEXEC */ +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +static unsigned long pnv_memory_block_size(void) +{ + return 256UL * 1024 * 1024; +} +#endif + static void __init pnv_setup_machdep_opal(void) { ppc_md.get_boot_time = opal_get_boot_time; @@ -269,6 +298,25 @@ static int __init pnv_probe(void) return 1; } +/* + * Returns the cpu frequency for 'cpu' in Hz. This is used by + * /proc/cpuinfo + */ +unsigned long pnv_get_proc_freq(unsigned int cpu) +{ + unsigned long ret_freq; + + ret_freq = cpufreq_quick_get(cpu) * 1000ul; + + /* + * If the backend cpufreq driver does not exist, + * then fallback to old way of reporting the clockrate. + */ + if (!ret_freq) + ret_freq = ppc_proc_freq; + return ret_freq; +} + define_machine(powernv) { .name = "PowerNV", .probe = pnv_probe, @@ -276,6 +324,7 @@ define_machine(powernv) { .setup_arch = pnv_setup_arch, .init_IRQ = pnv_init_IRQ, .show_cpuinfo = pnv_show_cpuinfo, + .get_proc_freq = pnv_get_proc_freq, .progress = pnv_progress, .machine_shutdown = pnv_shutdown, .power_save = power7_idle, @@ -284,4 +333,7 @@ define_machine(powernv) { #ifdef CONFIG_KEXEC .kexec_cpu_down = pnv_kexec_cpu_down, #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE + .memory_block_size = pnv_memory_block_size, +#endif }; diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index bf5fcd452168..0062a43a2e0d 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -31,6 +31,7 @@ #include <asm/xics.h> #include <asm/opal.h> #include <asm/runlatch.h> +#include <asm/code-patching.h> #include "powernv.h" @@ -50,8 +51,8 @@ static void pnv_smp_setup_cpu(int cpu) int pnv_smp_kick_cpu(int nr) { unsigned int pcpu = get_hard_smp_processor_id(nr); - unsigned long start_here = __pa(*((unsigned long *) - generic_secondary_smp_init)); + unsigned long start_here = + __pa(ppc_function_entry(generic_secondary_smp_init)); long rc; BUG_ON(nr < 0 || nr >= NR_CPUS); @@ -158,17 +159,19 @@ static void pnv_smp_cpu_kill_self(void) mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); while (!generic_check_cpu_restart(cpu)) { ppc64_runlatch_off(); - power7_nap(); + power7_nap(1); ppc64_runlatch_on(); - if (!generic_check_cpu_restart(cpu)) { + + /* Reenable IRQs briefly to clear the IPI that woke us */ + local_irq_enable(); + local_irq_disable(); + mb(); + + if (cpu_core_split_required()) + continue; + + if (!generic_check_cpu_restart(cpu)) DBG("CPU%d Unexpected exit while offline !\n", cpu); - /* We may be getting an IPI, so we re-enable - * interrupts to process it, it will be ignored - * since we aren't online (hopefully) - */ - local_irq_enable(); - local_irq_disable(); - } } mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1); DBG("CPU%d coming online...\n", cpu); diff --git a/arch/powerpc/platforms/powernv/subcore-asm.S b/arch/powerpc/platforms/powernv/subcore-asm.S new file mode 100644 index 000000000000..39bb24aa8f34 --- /dev/null +++ b/arch/powerpc/platforms/powernv/subcore-asm.S @@ -0,0 +1,95 @@ +/* + * Copyright 2013, Michael (Ellerman|Neuling), IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <asm/asm-offsets.h> +#include <asm/ppc_asm.h> +#include <asm/reg.h> + +#include "subcore.h" + + +_GLOBAL(split_core_secondary_loop) + /* + * r3 = u8 *state, used throughout the routine + * r4 = temp + * r5 = temp + * .. + * r12 = MSR + */ + mfmsr r12 + + /* Disable interrupts so SRR0/1 don't get trashed */ + li r4,0 + ori r4,r4,MSR_EE|MSR_SE|MSR_BE|MSR_RI + andc r4,r12,r4 + sync + mtmsrd r4 + + /* Switch to real mode and leave interrupts off */ + li r5, MSR_IR|MSR_DR + andc r5, r4, r5 + + LOAD_REG_ADDR(r4, real_mode) + + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r5 + rfid + b . /* prevent speculative execution */ + +real_mode: + /* Grab values from unsplit SPRs */ + mfspr r6, SPRN_LDBAR + mfspr r7, SPRN_PMMAR + mfspr r8, SPRN_PMCR + mfspr r9, SPRN_RPR + mfspr r10, SPRN_SDR1 + + /* Order reading the SPRs vs telling the primary we are ready to split */ + sync + + /* Tell thread 0 we are in real mode */ + li r4, SYNC_STEP_REAL_MODE + stb r4, 0(r3) + + li r5, (HID0_POWER8_4LPARMODE | HID0_POWER8_2LPARMODE)@highest + sldi r5, r5, 48 + + /* Loop until we see the split happen in HID0 */ +1: mfspr r4, SPRN_HID0 + and. r4, r4, r5 + beq 1b + + /* + * We only need to initialise the below regs once for each subcore, + * but it's simpler and harmless to do it on each thread. + */ + + /* Make sure various SPRS have sane values */ + li r4, 0 + mtspr SPRN_LPID, r4 + mtspr SPRN_PCR, r4 + mtspr SPRN_HDEC, r4 + + /* Restore SPR values now we are split */ + mtspr SPRN_LDBAR, r6 + mtspr SPRN_PMMAR, r7 + mtspr SPRN_PMCR, r8 + mtspr SPRN_RPR, r9 + mtspr SPRN_SDR1, r10 + + LOAD_REG_ADDR(r5, virtual_mode) + + /* Get out of real mode */ + mtspr SPRN_SRR0,r5 + mtspr SPRN_SRR1,r12 + rfid + b . /* prevent speculative execution */ + +virtual_mode: + blr diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c new file mode 100644 index 000000000000..894ecb3eb596 --- /dev/null +++ b/arch/powerpc/platforms/powernv/subcore.c @@ -0,0 +1,392 @@ +/* + * Copyright 2013, Michael (Ellerman|Neuling), IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) "powernv: " fmt + +#include <linux/kernel.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/gfp.h> +#include <linux/smp.h> +#include <linux/stop_machine.h> + +#include <asm/cputhreads.h> +#include <asm/kvm_ppc.h> +#include <asm/machdep.h> +#include <asm/opal.h> +#include <asm/smp.h> + +#include "subcore.h" + + +/* + * Split/unsplit procedure: + * + * A core can be in one of three states, unsplit, 2-way split, and 4-way split. + * + * The mapping to subcores_per_core is simple: + * + * State | subcores_per_core + * ------------|------------------ + * Unsplit | 1 + * 2-way split | 2 + * 4-way split | 4 + * + * The core is split along thread boundaries, the mapping between subcores and + * threads is as follows: + * + * Unsplit: + * ---------------------------- + * Subcore | 0 | + * ---------------------------- + * Thread | 0 1 2 3 4 5 6 7 | + * ---------------------------- + * + * 2-way split: + * ------------------------------------- + * Subcore | 0 | 1 | + * ------------------------------------- + * Thread | 0 1 2 3 | 4 5 6 7 | + * ------------------------------------- + * + * 4-way split: + * ----------------------------------------- + * Subcore | 0 | 1 | 2 | 3 | + * ----------------------------------------- + * Thread | 0 1 | 2 3 | 4 5 | 6 7 | + * ----------------------------------------- + * + * + * Transitions + * ----------- + * + * It is not possible to transition between either of the split states, the + * core must first be unsplit. The legal transitions are: + * + * ----------- --------------- + * | | <----> | 2-way split | + * | | --------------- + * | Unsplit | + * | | --------------- + * | | <----> | 4-way split | + * ----------- --------------- + * + * Unsplitting + * ----------- + * + * Unsplitting is the simpler procedure. It requires thread 0 to request the + * unsplit while all other threads NAP. + * + * Thread 0 clears HID0_POWER8_DYNLPARDIS (Dynamic LPAR Disable). This tells + * the hardware that if all threads except 0 are napping, the hardware should + * unsplit the core. + * + * Non-zero threads are sent to a NAP loop, they don't exit the loop until they + * see the core unsplit. + * + * Core 0 spins waiting for the hardware to see all the other threads napping + * and perform the unsplit. + * + * Once thread 0 sees the unsplit, it IPIs the secondary threads to wake them + * out of NAP. They will then see the core unsplit and exit the NAP loop. + * + * Splitting + * --------- + * + * The basic splitting procedure is fairly straight forward. However it is + * complicated by the fact that after the split occurs, the newly created + * subcores are not in a fully initialised state. + * + * Most notably the subcores do not have the correct value for SDR1, which + * means they must not be running in virtual mode when the split occurs. The + * subcores have separate timebases SPRs but these are pre-synchronised by + * opal. + * + * To begin with secondary threads are sent to an assembly routine. There they + * switch to real mode, so they are immune to the uninitialised SDR1 value. + * Once in real mode they indicate that they are in real mode, and spin waiting + * to see the core split. + * + * Thread 0 waits to see that all secondaries are in real mode, and then begins + * the splitting procedure. It firstly sets HID0_POWER8_DYNLPARDIS, which + * prevents the hardware from unsplitting. Then it sets the appropriate HID bit + * to request the split, and spins waiting to see that the split has happened. + * + * Concurrently the secondaries will notice the split. When they do they set up + * their SPRs, notably SDR1, and then they can return to virtual mode and exit + * the procedure. + */ + +/* Initialised at boot by subcore_init() */ +static int subcores_per_core; + +/* + * Used to communicate to offline cpus that we want them to pop out of the + * offline loop and do a split or unsplit. + * + * 0 - no split happening + * 1 - unsplit in progress + * 2 - split to 2 in progress + * 4 - split to 4 in progress + */ +static int new_split_mode; + +static cpumask_var_t cpu_offline_mask; + +struct split_state { + u8 step; + u8 master; +}; + +static DEFINE_PER_CPU(struct split_state, split_state); + +static void wait_for_sync_step(int step) +{ + int i, cpu = smp_processor_id(); + + for (i = cpu + 1; i < cpu + threads_per_core; i++) + while(per_cpu(split_state, i).step < step) + barrier(); + + /* Order the wait loop vs any subsequent loads/stores. */ + mb(); +} + +static void unsplit_core(void) +{ + u64 hid0, mask; + int i, cpu; + + mask = HID0_POWER8_2LPARMODE | HID0_POWER8_4LPARMODE; + + cpu = smp_processor_id(); + if (cpu_thread_in_core(cpu) != 0) { + while (mfspr(SPRN_HID0) & mask) + power7_nap(0); + + per_cpu(split_state, cpu).step = SYNC_STEP_UNSPLIT; + return; + } + + hid0 = mfspr(SPRN_HID0); + hid0 &= ~HID0_POWER8_DYNLPARDIS; + mtspr(SPRN_HID0, hid0); + + while (mfspr(SPRN_HID0) & mask) + cpu_relax(); + + /* Wake secondaries out of NAP */ + for (i = cpu + 1; i < cpu + threads_per_core; i++) + smp_send_reschedule(i); + + wait_for_sync_step(SYNC_STEP_UNSPLIT); +} + +static void split_core(int new_mode) +{ + struct { u64 value; u64 mask; } split_parms[2] = { + { HID0_POWER8_1TO2LPAR, HID0_POWER8_2LPARMODE }, + { HID0_POWER8_1TO4LPAR, HID0_POWER8_4LPARMODE } + }; + int i, cpu; + u64 hid0; + + /* Convert new_mode (2 or 4) into an index into our parms array */ + i = (new_mode >> 1) - 1; + BUG_ON(i < 0 || i > 1); + + cpu = smp_processor_id(); + if (cpu_thread_in_core(cpu) != 0) { + split_core_secondary_loop(&per_cpu(split_state, cpu).step); + return; + } + + wait_for_sync_step(SYNC_STEP_REAL_MODE); + + /* Write new mode */ + hid0 = mfspr(SPRN_HID0); + hid0 |= HID0_POWER8_DYNLPARDIS | split_parms[i].value; + mtspr(SPRN_HID0, hid0); + + /* Wait for it to happen */ + while (!(mfspr(SPRN_HID0) & split_parms[i].mask)) + cpu_relax(); +} + +static void cpu_do_split(int new_mode) +{ + /* + * At boot subcores_per_core will be 0, so we will always unsplit at + * boot. In the usual case where the core is already unsplit it's a + * nop, and this just ensures the kernel's notion of the mode is + * consistent with the hardware. + */ + if (subcores_per_core != 1) + unsplit_core(); + + if (new_mode != 1) + split_core(new_mode); + + mb(); + per_cpu(split_state, smp_processor_id()).step = SYNC_STEP_FINISHED; +} + +bool cpu_core_split_required(void) +{ + smp_rmb(); + + if (!new_split_mode) + return false; + + cpu_do_split(new_split_mode); + + return true; +} + +static int cpu_update_split_mode(void *data) +{ + int cpu, new_mode = *(int *)data; + + if (this_cpu_ptr(&split_state)->master) { + new_split_mode = new_mode; + smp_wmb(); + + cpumask_andnot(cpu_offline_mask, cpu_present_mask, + cpu_online_mask); + + /* This should work even though the cpu is offline */ + for_each_cpu(cpu, cpu_offline_mask) + smp_send_reschedule(cpu); + } + + cpu_do_split(new_mode); + + if (this_cpu_ptr(&split_state)->master) { + /* Wait for all cpus to finish before we touch subcores_per_core */ + for_each_present_cpu(cpu) { + if (cpu >= setup_max_cpus) + break; + + while(per_cpu(split_state, cpu).step < SYNC_STEP_FINISHED) + barrier(); + } + + new_split_mode = 0; + + /* Make the new mode public */ + subcores_per_core = new_mode; + threads_per_subcore = threads_per_core / subcores_per_core; + + /* Make sure the new mode is written before we exit */ + mb(); + } + + return 0; +} + +static int set_subcores_per_core(int new_mode) +{ + struct split_state *state; + int cpu; + + if (kvm_hv_mode_active()) { + pr_err("Unable to change split core mode while KVM active.\n"); + return -EBUSY; + } + + /* + * We are only called at boot, or from the sysfs write. If that ever + * changes we'll need a lock here. + */ + BUG_ON(new_mode < 1 || new_mode > 4 || new_mode == 3); + + for_each_present_cpu(cpu) { + state = &per_cpu(split_state, cpu); + state->step = SYNC_STEP_INITIAL; + state->master = 0; + } + + get_online_cpus(); + + /* This cpu will update the globals before exiting stop machine */ + this_cpu_ptr(&split_state)->master = 1; + + /* Ensure state is consistent before we call the other cpus */ + mb(); + + stop_machine(cpu_update_split_mode, &new_mode, cpu_online_mask); + + put_online_cpus(); + + return 0; +} + +static ssize_t __used store_subcores_per_core(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + unsigned long val; + int rc; + + /* We are serialised by the attribute lock */ + + rc = sscanf(buf, "%lx", &val); + if (rc != 1) + return -EINVAL; + + switch (val) { + case 1: + case 2: + case 4: + if (subcores_per_core == val) + /* Nothing to do */ + goto out; + break; + default: + return -EINVAL; + } + + rc = set_subcores_per_core(val); + if (rc) + return rc; + +out: + return count; +} + +static ssize_t show_subcores_per_core(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%x\n", subcores_per_core); +} + +static DEVICE_ATTR(subcores_per_core, 0644, + show_subcores_per_core, store_subcores_per_core); + +static int subcore_init(void) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return 0; + + /* + * We need all threads in a core to be present to split/unsplit so + * continue only if max_cpus are aligned to threads_per_core. + */ + if (setup_max_cpus % threads_per_core) + return 0; + + BUG_ON(!alloc_cpumask_var(&cpu_offline_mask, GFP_KERNEL)); + + set_subcores_per_core(1); + + return device_create_file(cpu_subsys.dev_root, + &dev_attr_subcores_per_core); +} +machine_device_initcall(powernv, subcore_init); diff --git a/arch/powerpc/platforms/powernv/subcore.h b/arch/powerpc/platforms/powernv/subcore.h new file mode 100644 index 000000000000..148abc91debf --- /dev/null +++ b/arch/powerpc/platforms/powernv/subcore.h @@ -0,0 +1,18 @@ +/* + * Copyright 2013, Michael Ellerman, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +/* These are ordered and tested with <= */ +#define SYNC_STEP_INITIAL 0 +#define SYNC_STEP_UNSPLIT 1 /* Set by secondary when it sees unsplit */ +#define SYNC_STEP_REAL_MODE 2 /* Set by secondary when in real mode */ +#define SYNC_STEP_FINISHED 3 /* Set by secondary when split/unsplit is done */ + +#ifndef __ASSEMBLY__ +void split_core_secondary_loop(u8 *state); +#endif diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 8a8f0472d98f..0bec0c02c5e7 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -175,6 +175,36 @@ static int pseries_eeh_find_cap(struct device_node *dn, int cap) return 0; } +static int pseries_eeh_find_ecap(struct device_node *dn, int cap) +{ + struct pci_dn *pdn = PCI_DN(dn); + struct eeh_dev *edev = of_node_to_eeh_dev(dn); + u32 header; + int pos = 256; + int ttl = (4096 - 256) / 8; + + if (!edev || !edev->pcie_cap) + return 0; + if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + return 0; + else if (!header) + return 0; + + while (ttl-- > 0) { + if (PCI_EXT_CAP_ID(header) == cap && pos) + return pos; + + pos = PCI_EXT_CAP_NEXT(header); + if (pos < 256) + break; + + if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + break; + } + + return 0; +} + /** * pseries_eeh_of_probe - EEH probe on the given device * @dn: OF node @@ -220,7 +250,9 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) * or PCIe switch downstream port. */ edev->class_code = class_code; + edev->pcix_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_PCIX); edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP); + edev->aer_cap = pseries_eeh_find_ecap(dn, PCI_EXT_CAP_ID_ERR); edev->mode &= 0xFFFFFF00; if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; @@ -464,6 +496,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *state) } else { result = EEH_STATE_NOT_SUPPORT; } + break; default: result = EEH_STATE_NOT_SUPPORT; } @@ -499,11 +532,19 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option) /* If fundamental-reset not supported, try hot-reset */ if (option == EEH_RESET_FUNDAMENTAL && ret == -8) { + option = EEH_RESET_HOT; ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), EEH_RESET_HOT); + BUID_LO(pe->phb->buid), option); } + /* We need reset hold or settlement delay */ + if (option == EEH_RESET_FUNDAMENTAL || + option == EEH_RESET_HOT) + msleep(EEH_PE_RST_HOLD_TIME); + else + msleep(EEH_PE_RST_SETTLE_TIME); + return ret; } diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 7f75c94af822..7995135170a3 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -21,7 +21,7 @@ #include <asm/prom.h> #include <asm/sparsemem.h> -static unsigned long get_memblock_size(void) +unsigned long pseries_memory_block_size(void) { struct device_node *np; unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; @@ -64,17 +64,6 @@ static unsigned long get_memblock_size(void) return memblock_size; } -/* WARNING: This is going to override the generic definition whenever - * pseries is built-in regardless of what platform is active at boot - * time. This is fine for now as this is the only "option" and it - * should work everywhere. If not, we'll have to turn this into a - * ppc_md. callback - */ -unsigned long memory_block_size_bytes(void) -{ - return get_memblock_size(); -} - #ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memory(u64 start, u64 size) { @@ -105,7 +94,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz if (!pfn_valid(start_pfn)) goto out; - block_sz = memory_block_size_bytes(); + block_sz = pseries_memory_block_size(); sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; nid = memory_add_physaddr_to_nid(base); @@ -201,7 +190,7 @@ static int pseries_update_drconf_memory(struct of_prop_reconfig *pr) u32 *p; int i, rc = -EINVAL; - memblock_size = get_memblock_size(); + memblock_size = pseries_memory_block_size(); if (!memblock_size) return -EINVAL; diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 444fe7759e55..99ecf0a5a929 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -49,7 +49,7 @@ END_FTR_SECTION(0, 1); \ std r0,16(r1); \ addi r4,r1,STK_PARAM(FIRST_REG); \ stdu r1,-STACK_FRAME_OVERHEAD(r1); \ - bl .__trace_hcall_entry; \ + bl __trace_hcall_entry; \ addi r1,r1,STACK_FRAME_OVERHEAD; \ ld r0,16(r1); \ ld r3,STK_PARAM(R3)(r1); \ @@ -83,7 +83,7 @@ END_FTR_SECTION(0, 1); \ mr r3,r6; \ std r0,16(r1); \ stdu r1,-STACK_FRAME_OVERHEAD(r1); \ - bl .__trace_hcall_exit; \ + bl __trace_hcall_exit; \ addi r1,r1,STACK_FRAME_OVERHEAD; \ ld r0,16(r1); \ ld r3,STK_PARAM(R3)(r1); \ @@ -106,7 +106,7 @@ END_FTR_SECTION(0, 1); \ .text -_GLOBAL(plpar_hcall_norets) +_GLOBAL_TOC(plpar_hcall_norets) HMT_MEDIUM mfcr r0 @@ -122,7 +122,7 @@ _GLOBAL(plpar_hcall_norets) mtcrf 0xff,r0 blr /* return r3 = status */ -_GLOBAL(plpar_hcall) +_GLOBAL_TOC(plpar_hcall) HMT_MEDIUM mfcr r0 @@ -188,7 +188,7 @@ _GLOBAL(plpar_hcall_raw) blr /* return r3 = status */ -_GLOBAL(plpar_hcall9) +_GLOBAL_TOC(plpar_hcall9) HMT_MEDIUM mfcr r0 diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 99219530ea4a..361add62abf1 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -64,4 +64,6 @@ extern int dlpar_detach_node(struct device_node *); struct pci_host_bridge; int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); +unsigned long pseries_memory_block_size(void); + #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 2db8cc691bf4..f2f40e64658f 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -510,7 +510,11 @@ static void __init pSeries_setup_arch(void) static int __init pSeries_init_panel(void) { /* Manually leave the kernel version on the panel. */ +#ifdef __BIG_ENDIAN__ ppc_md.progress("Linux ppc64\n", 0); +#else + ppc_md.progress("Linux ppc64le\n", 0); +#endif ppc_md.progress(init_utsname()->version, 0); return 0; @@ -665,7 +669,7 @@ static int __init pseries_probe_fw_features(unsigned long node, void *data) { const char *prop; - unsigned long len; + int len; static int hypertas_found; static int vec5_found; @@ -698,7 +702,7 @@ static int __init pseries_probe_fw_features(unsigned long node, static int __init pSeries_probe(void) { unsigned long root = of_get_flat_dt_root(); - char *dtype = of_get_flat_dt_prop(root, "device_type", NULL); + const char *dtype = of_get_flat_dt_prop(root, "device_type", NULL); if (dtype == NULL) return 0; @@ -806,4 +810,7 @@ define_machine(pseries) { #ifdef CONFIG_KEXEC .machine_kexec = pSeries_machine_kexec, #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE + .memory_block_size = pseries_memory_block_size, +#endif }; diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 24f58cb0a543..a3555b10c1a5 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -44,6 +44,7 @@ #include <asm/xics.h> #include <asm/dbell.h> #include <asm/plpar_wrappers.h> +#include <asm/code-patching.h> #include "pseries.h" #include "offline_states.h" @@ -96,8 +97,8 @@ int smp_query_cpu_stopped(unsigned int pcpu) static inline int smp_startup_cpu(unsigned int lcpu) { int status; - unsigned long start_here = __pa((u32)*((unsigned long *) - generic_secondary_smp_init)); + unsigned long start_here = + __pa(ppc_function_entry(generic_secondary_smp_init)); unsigned int pcpu; int start_cpu; diff --git a/arch/powerpc/platforms/wsp/scom_smp.c b/arch/powerpc/platforms/wsp/scom_smp.c index 268bc899c1f7..8c79ce016cf1 100644 --- a/arch/powerpc/platforms/wsp/scom_smp.c +++ b/arch/powerpc/platforms/wsp/scom_smp.c @@ -20,6 +20,7 @@ #include <asm/reg_a2.h> #include <asm/scom.h> #include <asm/udbg.h> +#include <asm/code-patching.h> #include "wsp.h" @@ -405,7 +406,7 @@ int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, struct device_node *np) goto fail; } - start_here = *(unsigned long *)(core_setup ? generic_secondary_smp_init + start_here = ppc_function_entry(core_setup ? generic_secondary_smp_init : generic_secondary_thread_init); pr_devel("CPU%d entry point at 0x%lx...\n", lcpu, start_here); diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig index 7baa70d6dc01..a19332a38715 100644 --- a/arch/powerpc/sysdev/Kconfig +++ b/arch/powerpc/sysdev/Kconfig @@ -7,6 +7,12 @@ config PPC4xx_PCI_EXPRESS depends on PCI && 4xx default n +config PPC4xx_HSTA_MSI + bool + depends on PCI_MSI + depends on PCI && 4xx + default n + config PPC4xx_MSI bool depends on PCI_MSI diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index afbcc37aa094..f7cb2a1b01fa 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -45,6 +45,7 @@ obj-$(CONFIG_OF_RTC) += of_rtc.o ifeq ($(CONFIG_PCI),y) obj-$(CONFIG_4xx) += ppc4xx_pci.o endif +obj-$(CONFIG_PPC4xx_HSTA_MSI) += ppc4xx_hsta_msi.o obj-$(CONFIG_PPC4xx_MSI) += ppc4xx_msi.o obj-$(CONFIG_PPC4xx_CPM) += ppc4xx_cpm.o obj-$(CONFIG_PPC4xx_GPIO) += ppc4xx_gpio.o diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c index 1bd0eba4d355..e9056e438575 100644 --- a/arch/powerpc/sysdev/dcr.c +++ b/arch/powerpc/sysdev/dcr.c @@ -152,9 +152,9 @@ EXPORT_SYMBOL_GPL(dcr_resource_len); #ifdef CONFIG_PPC_DCR_MMIO -u64 of_translate_dcr_address(struct device_node *dev, - unsigned int dcr_n, - unsigned int *out_stride) +static u64 of_translate_dcr_address(struct device_node *dev, + unsigned int dcr_n, + unsigned int *out_stride) { struct device_node *dp; const u32 *p; diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 3f415e252ea5..4bd091a05583 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -1150,8 +1150,7 @@ static int fsl_pci_pme_probe(struct pci_controller *hose) pci = hose->private_data; /* Enable PTOD, ENL23D & EXL23D */ - out_be32(&pci->pex_pme_mes_disr, 0); - setbits32(&pci->pex_pme_mes_disr, + clrbits32(&pci->pex_pme_mes_disr, PME_DISR_EN_PTOD | PME_DISR_EN_ENL23D | PME_DISR_EN_EXL23D); out_be32(&pci->pex_pme_mes_ier, 0); diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index cf2b0840a672..c04b718307c8 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -391,8 +391,10 @@ int fsl_rio_setup(struct platform_device *dev) ops->get_inb_message = fsl_get_inb_message; rmu_node = of_parse_phandle(dev->dev.of_node, "fsl,srio-rmu-handle", 0); - if (!rmu_node) + if (!rmu_node) { + dev_err(&dev->dev, "No valid fsl,srio-rmu-handle property\n"); goto err_rmu; + } rc = of_address_to_resource(rmu_node, 0, &rmu_regs); if (rc) { dev_err(&dev->dev, "Can't get %s property 'reg'\n", @@ -413,6 +415,7 @@ int fsl_rio_setup(struct platform_device *dev) /*set up doobell node*/ np = of_find_compatible_node(NULL, NULL, "fsl,srio-dbell-unit"); if (!np) { + dev_err(&dev->dev, "No fsl,srio-dbell-unit node\n"); rc = -ENODEV; goto err_dbell; } @@ -441,6 +444,7 @@ int fsl_rio_setup(struct platform_device *dev) /*set up port write node*/ np = of_find_compatible_node(NULL, NULL, "fsl,srio-port-write-unit"); if (!np) { + dev_err(&dev->dev, "No fsl,srio-port-write-unit node\n"); rc = -ENODEV; goto err_pw; } @@ -633,14 +637,18 @@ int fsl_rio_setup(struct platform_device *dev) return 0; err: kfree(pw); + pw = NULL; err_pw: kfree(dbell); + dbell = NULL; err_dbell: iounmap(rmu_regs_win); + rmu_regs_win = NULL; err_rmu: kfree(ops); err_ops: iounmap(rio_regs_win); + rio_regs_win = NULL; err_rio_regs: return rc; } diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c index 00e224a1048c..b48197ae44d0 100644 --- a/arch/powerpc/sysdev/fsl_rmu.c +++ b/arch/powerpc/sysdev/fsl_rmu.c @@ -881,9 +881,9 @@ fsl_open_inb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entries) rc = request_irq(IRQ_RIO_RX(mport), fsl_rio_rx_handler, 0, "msg_rx", (void *)mport); if (rc < 0) { - dma_free_coherent(priv->dev, RIO_MSG_BUFFER_SIZE, - rmu->msg_tx_ring.virt_buffer[i], - rmu->msg_tx_ring.phys_buffer[i]); + dma_free_coherent(priv->dev, + rmu->msg_rx_ring.size * RIO_MAX_MSG_SIZE, + rmu->msg_rx_ring.virt, rmu->msg_rx_ring.phys); goto out; } diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 8209744b2829..be33c9768ea1 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -1588,10 +1588,6 @@ void __init mpic_init(struct mpic *mpic) num_timers = 8; } - /* FSL mpic error interrupt intialization */ - if (mpic->flags & MPIC_FSL_HAS_EIMR) - mpic_err_int_init(mpic, MPIC_FSL_ERR_INT); - /* Initialize timers to our reserved vectors and mask them for now */ for (i = 0; i < num_timers; i++) { unsigned int offset = mpic_tm_offset(mpic, i); @@ -1675,6 +1671,10 @@ void __init mpic_init(struct mpic *mpic) irq_set_chained_handler(virq, &mpic_cascade); } } + + /* FSL mpic error interrupt intialization */ + if (mpic->flags & MPIC_FSL_HAS_EIMR) + mpic_err_int_init(mpic, MPIC_FSL_ERR_INT); } void __init mpic_set_clk_ratio(struct mpic *mpic, u32 clock_ratio) diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c new file mode 100644 index 000000000000..11c888416f0a --- /dev/null +++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c @@ -0,0 +1,215 @@ +/* + * MSI support for PPC4xx SoCs using High Speed Transfer Assist (HSTA) for + * generation of the interrupt. + * + * Copyright © 2013 Alistair Popple <alistair@popple.id.au> IBM Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/interrupt.h> +#include <linux/msi.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/semaphore.h> +#include <asm/msi_bitmap.h> + +struct ppc4xx_hsta_msi { + struct device *dev; + + /* The ioremapped HSTA MSI IO space */ + u32 __iomem *data; + + /* Physical address of HSTA MSI IO space */ + u64 address; + struct msi_bitmap bmp; + + /* An array mapping offsets to hardware IRQs */ + int *irq_map; + + /* Number of hwirqs supported */ + int irq_count; +}; +static struct ppc4xx_hsta_msi ppc4xx_hsta_msi; + +static int hsta_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + struct msi_msg msg; + struct msi_desc *entry; + int irq, hwirq; + u64 addr; + + list_for_each_entry(entry, &dev->msi_list, list) { + irq = msi_bitmap_alloc_hwirqs(&ppc4xx_hsta_msi.bmp, 1); + if (irq < 0) { + pr_debug("%s: Failed to allocate msi interrupt\n", + __func__); + return irq; + } + + hwirq = ppc4xx_hsta_msi.irq_map[irq]; + if (hwirq == NO_IRQ) { + pr_err("%s: Failed mapping irq %d\n", __func__, irq); + return -EINVAL; + } + + /* + * HSTA generates interrupts on writes to 128-bit aligned + * addresses. + */ + addr = ppc4xx_hsta_msi.address + irq*0x10; + msg.address_hi = upper_32_bits(addr); + msg.address_lo = lower_32_bits(addr); + + /* Data is not used by the HSTA. */ + msg.data = 0; + + pr_debug("%s: Setup irq %d (0x%0llx)\n", __func__, hwirq, + (((u64) msg.address_hi) << 32) | msg.address_lo); + + if (irq_set_msi_desc(hwirq, entry)) { + pr_err( + "%s: Invalid hwirq %d specified in device tree\n", + __func__, hwirq); + msi_bitmap_free_hwirqs(&ppc4xx_hsta_msi.bmp, irq, 1); + return -EINVAL; + } + write_msi_msg(hwirq, &msg); + } + + return 0; +} + +static int hsta_find_hwirq_offset(int hwirq) +{ + int irq; + + /* Find the offset given the hwirq */ + for (irq = 0; irq < ppc4xx_hsta_msi.irq_count; irq++) + if (ppc4xx_hsta_msi.irq_map[irq] == hwirq) + return irq; + + return -EINVAL; +} + +static void hsta_teardown_msi_irqs(struct pci_dev *dev) +{ + struct msi_desc *entry; + int irq; + + list_for_each_entry(entry, &dev->msi_list, list) { + if (entry->irq == NO_IRQ) + continue; + + irq = hsta_find_hwirq_offset(entry->irq); + + /* entry->irq should always be in irq_map */ + BUG_ON(irq < 0); + irq_set_msi_desc(entry->irq, NULL); + msi_bitmap_free_hwirqs(&ppc4xx_hsta_msi.bmp, irq, 1); + pr_debug("%s: Teardown IRQ %u (index %u)\n", __func__, + entry->irq, irq); + } +} + +static int hsta_msi_check_device(struct pci_dev *pdev, int nvec, int type) +{ + /* We don't support MSI-X */ + if (type == PCI_CAP_ID_MSIX) { + pr_debug("%s: MSI-X not supported.\n", __func__); + return -EINVAL; + } + + return 0; +} + +static int hsta_msi_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct resource *mem; + int irq, ret, irq_count; + + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (IS_ERR(mem)) { + dev_err(dev, "Unable to get mmio space\n"); + return -EINVAL; + } + + irq_count = of_irq_count(dev->of_node); + if (!irq_count) { + dev_err(dev, "Unable to find IRQ range\n"); + return -EINVAL; + } + + ppc4xx_hsta_msi.dev = dev; + ppc4xx_hsta_msi.address = mem->start; + ppc4xx_hsta_msi.data = ioremap(mem->start, resource_size(mem)); + ppc4xx_hsta_msi.irq_count = irq_count; + if (IS_ERR(ppc4xx_hsta_msi.data)) { + dev_err(dev, "Unable to map memory\n"); + return -ENOMEM; + } + + ret = msi_bitmap_alloc(&ppc4xx_hsta_msi.bmp, irq_count, dev->of_node); + if (ret) + goto out; + + ppc4xx_hsta_msi.irq_map = kmalloc(sizeof(int) * irq_count, GFP_KERNEL); + if (IS_ERR(ppc4xx_hsta_msi.irq_map)) { + ret = -ENOMEM; + goto out1; + } + + /* Setup a mapping from irq offsets to hardware irq numbers */ + for (irq = 0; irq < irq_count; irq++) { + ppc4xx_hsta_msi.irq_map[irq] = + irq_of_parse_and_map(dev->of_node, irq); + if (ppc4xx_hsta_msi.irq_map[irq] == NO_IRQ) { + dev_err(dev, "Unable to map IRQ\n"); + ret = -EINVAL; + goto out2; + } + } + + ppc_md.setup_msi_irqs = hsta_setup_msi_irqs; + ppc_md.teardown_msi_irqs = hsta_teardown_msi_irqs; + ppc_md.msi_check_device = hsta_msi_check_device; + return 0; + +out2: + kfree(ppc4xx_hsta_msi.irq_map); + +out1: + msi_bitmap_free(&ppc4xx_hsta_msi.bmp); + +out: + iounmap(ppc4xx_hsta_msi.data); + return ret; +} + +static const struct of_device_id hsta_msi_ids[] = { + { + .compatible = "ibm,hsta-msi", + }, + {} +}; + +static struct platform_driver hsta_msi_driver = { + .probe = hsta_msi_probe, + .driver = { + .name = "hsta-msi", + .owner = THIS_MODULE, + .of_match_table = hsta_msi_ids, + }, +}; + +static int hsta_msi_init(void) +{ + return platform_driver_register(&hsta_msi_driver); +} +subsys_initcall(hsta_msi_init); diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c index 4914fd3f41ec..df6e2fc4ff92 100644 --- a/arch/powerpc/sysdev/ppc4xx_pci.c +++ b/arch/powerpc/sysdev/ppc4xx_pci.c @@ -176,8 +176,12 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose, return -ENXIO; } - /* Check that we are fully contained within 32 bits space */ - if (res->end > 0xffffffff) { + /* Check that we are fully contained within 32 bits space if we are not + * running on a 460sx or 476fpe which have 64 bit bus addresses. + */ + if (res->end > 0xffffffff && + !(of_device_is_compatible(hose->dn, "ibm,plb-pciex-460sx") + || of_device_is_compatible(hose->dn, "ibm,plb-pciex-476fpe"))) { printk(KERN_ERR "%s: dma-ranges outside of 32 bits space\n", hose->dn->full_name); return -ENXIO; @@ -1440,7 +1444,8 @@ static int __init ppc4xx_pciex_check_core_init(struct device_node *np) ppc4xx_pciex_hwops = &ppc405ex_pcie_hwops; #endif #ifdef CONFIG_476FPE - if (of_device_is_compatible(np, "ibm,plb-pciex-476fpe")) + if (of_device_is_compatible(np, "ibm,plb-pciex-476fpe") + || of_device_is_compatible(np, "ibm,plb-pciex-476gtr")) ppc4xx_pciex_hwops = &ppc_476fpe_pcie_hwops; #endif if (ppc4xx_pciex_hwops == NULL) { @@ -1751,7 +1756,10 @@ static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port *port, dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL, sa | DCRO_PEGPL_460SX_OMR1MSKL_UOT | DCRO_PEGPL_OMRxMSKL_VAL); - else if (of_device_is_compatible(port->node, "ibm,plb-pciex-476fpe")) + else if (of_device_is_compatible( + port->node, "ibm,plb-pciex-476fpe") || + of_device_is_compatible( + port->node, "ibm,plb-pciex-476gtr")) dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL, sa | DCRO_PEGPL_476FPE_OMR1MSKL_UOT | DCRO_PEGPL_OMRxMSKL_VAL); @@ -1881,7 +1889,10 @@ static void __init ppc4xx_configure_pciex_PIMs(struct ppc4xx_pciex_port *port, sa |= PCI_BASE_ADDRESS_MEM_PREFETCH; if (of_device_is_compatible(port->node, "ibm,plb-pciex-460sx") || - of_device_is_compatible(port->node, "ibm,plb-pciex-476fpe")) + of_device_is_compatible( + port->node, "ibm,plb-pciex-476fpe") || + of_device_is_compatible( + port->node, "ibm,plb-pciex-476gtr")) sa |= PCI_BASE_ADDRESS_MEM_TYPE_64; out_le32(mbase + PECFG_BAR0HMPA, RES_TO_U32_HIGH(sa)); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 08504e75b2c7..d199bfa2f1fa 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -419,7 +419,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) get_output_lock(); excprint(regs); if (bp) { - printf("cpu 0x%x stopped at breakpoint 0x%x (", + printf("cpu 0x%x stopped at breakpoint 0x%lx (", cpu, BP_NUM(bp)); xmon_print_symbol(regs->nip, " ", ")\n"); } @@ -513,7 +513,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) excprint(regs); bp = at_breakpoint(regs->nip); if (bp) { - printf("Stopped at breakpoint %x (", BP_NUM(bp)); + printf("Stopped at breakpoint %lx (", BP_NUM(bp)); xmon_print_symbol(regs->nip, " ", ")\n"); } if (unrecoverable_excp(regs)) @@ -759,7 +759,7 @@ static void insert_cpu_bpts(void) brk.address = dabr.address; brk.type = (dabr.enabled & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL; brk.len = 8; - set_breakpoint(&brk); + __set_breakpoint(&brk); } if (iabr && cpu_has_feature(CPU_FTR_IABR)) mtspr(SPRN_IABR, iabr->address @@ -997,14 +997,14 @@ static int cpu_cmd(void) last_cpu = cpu; } else { if (last_cpu != first_cpu) - printf("-%lx", last_cpu); + printf("-0x%lx", last_cpu); last_cpu = first_cpu = cpu; - printf(" %lx", cpu); + printf(" 0x%lx", cpu); } } } if (last_cpu != first_cpu) - printf("-%lx", last_cpu); + printf("-0x%lx", last_cpu); printf("\n"); return 0; } @@ -1024,7 +1024,7 @@ static int cpu_cmd(void) /* take control back */ mb(); xmon_owner = smp_processor_id(); - printf("cpu %u didn't take control\n", cpu); + printf("cpu 0x%x didn't take control\n", cpu); return 0; } barrier(); @@ -1086,7 +1086,7 @@ csum(void) fcs = 0xffff; for (i = 0; i < ncsum; ++i) { if (mread(adrs+i, &v, 1) == 0) { - printf("csum stopped at %x\n", adrs+i); + printf("csum stopped at "REG"\n", adrs+i); break; } fcs = FCS(fcs, v); @@ -1202,12 +1202,12 @@ bpt_cmds(void) /* assume a breakpoint address */ bp = at_breakpoint(a); if (bp == NULL) { - printf("No breakpoint at %x\n", a); + printf("No breakpoint at %lx\n", a); break; } } - printf("Cleared breakpoint %x (", BP_NUM(bp)); + printf("Cleared breakpoint %lx (", BP_NUM(bp)); xmon_print_symbol(bp->address, " ", ")\n"); bp->enabled = 0; break; @@ -1746,7 +1746,7 @@ mwrite(unsigned long adrs, void *buf, int size) __delay(200); n = size; } else { - printf("*** Error writing address %x\n", adrs + n); + printf("*** Error writing address "REG"\n", adrs + n); } catch_memory_errors = 0; return n; @@ -2435,7 +2435,7 @@ static void proccall(void) ret = func(args[0], args[1], args[2], args[3], args[4], args[5], args[6], args[7]); sync(); - printf("return value is %x\n", ret); + printf("return value is 0x%lx\n", ret); } else { printf("*** %x exception occurred\n", fault_except); } @@ -2700,7 +2700,7 @@ static void dump_slb(void) unsigned long esid,vsid,valid; unsigned long llp; - printf("SLB contents of cpu %x\n", smp_processor_id()); + printf("SLB contents of cpu 0x%x\n", smp_processor_id()); for (i = 0; i < mmu_slb_size; i++) { asm volatile("slbmfee %0,%1" : "=r" (esid) : "r" (i)); @@ -2732,7 +2732,7 @@ static void dump_stab(void) int i; unsigned long *tmp = (unsigned long *)local_paca->stab_addr; - printf("Segment table contents of cpu %x\n", smp_processor_id()); + printf("Segment table contents of cpu 0x%x\n", smp_processor_id()); for (i = 0; i < PAGE_SIZE/16; i++) { unsigned long a, b; diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index c7463aa0014b..99b0b09646ca 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -92,7 +92,6 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = { void __init init_IRQ(void) { - irq_reserve_irqs(0, THIN_INTERRUPT); init_cio_interrupts(); init_airq_interrupts(); init_ext_interrupts(); @@ -151,9 +150,9 @@ out: return 0; } -int arch_show_interrupts(struct seq_file *p, int prec) +unsigned int arch_dynirq_lower_bound(unsigned int from) { - return 0; + return from < THIN_INTERRUPT ? THIN_INTERRUPT : from; } /* diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 0727a55d87d9..0ff66a7e29bb 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -220,11 +220,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 1; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmdp, int write) { diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index bdf02570d1df..9ddc51eeb8d6 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -401,11 +401,11 @@ static void zpci_irq_handler(struct airq_struct *airq) int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) { struct zpci_dev *zdev = get_zdev(pdev); - unsigned int hwirq, irq, msi_vecs; + unsigned int hwirq, msi_vecs; unsigned long aisb; struct msi_desc *msi; struct msi_msg msg; - int rc; + int rc, irq; if (type == PCI_CAP_ID_MSI && nvec > 1) return 1; @@ -433,7 +433,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) list_for_each_entry(msi, &pdev->msi_list, list) { rc = -EIO; irq = irq_alloc_desc(0); /* Alloc irq on node 0 */ - if (irq == NO_IRQ) + if (irq < 0) goto out_msi; rc = irq_set_msi_desc(irq, msi); if (rc) diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h index 13e9966464c2..e79fb6ebaa42 100644 --- a/arch/sh/include/asm/ftrace.h +++ b/arch/sh/include/asm/ftrace.h @@ -40,15 +40,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) /* arch/sh/kernel/return_address.c */ extern void *return_address(unsigned int); -#define HAVE_ARCH_CALLER_ADDR - -#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -#define CALLER_ADDR1 ((unsigned long)return_address(1)) -#define CALLER_ADDR2 ((unsigned long)return_address(2)) -#define CALLER_ADDR3 ((unsigned long)return_address(3)) -#define CALLER_ADDR4 ((unsigned long)return_address(4)) -#define CALLER_ADDR5 ((unsigned long)return_address(5)) -#define CALLER_ADDR6 ((unsigned long)return_address(6)) +#define ftrace_return_address(n) return_address(n) #endif /* __ASSEMBLY__ */ diff --git a/arch/sh/include/asm/unistd.h b/arch/sh/include/asm/unistd.h index e77816c4b9bc..126fe8340b22 100644 --- a/arch/sh/include/asm/unistd.h +++ b/arch/sh/include/asm/unistd.h @@ -11,7 +11,6 @@ # define __ARCH_WANT_SYS_GETHOSTNAME # define __ARCH_WANT_SYS_IPC # define __ARCH_WANT_SYS_PAUSE -# define __ARCH_WANT_SYS_SGETMASK # define __ARCH_WANT_SYS_SIGNAL # define __ARCH_WANT_SYS_TIME # define __ARCH_WANT_SYS_UTIME diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c index f9173766ec4b..2197fc584186 100644 --- a/arch/sh/kernel/hw_breakpoint.c +++ b/arch/sh/kernel/hw_breakpoint.c @@ -52,7 +52,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) int i; for (i = 0; i < sh_ubc->num_events; i++) { - struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]); + struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]); if (!*slot) { *slot = bp; @@ -84,7 +84,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) int i; for (i = 0; i < sh_ubc->num_events; i++) { - struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]); + struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]); if (*slot == bp) { *slot = NULL; diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index 42b46e61a2d5..83acbf3f6de8 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -102,7 +102,7 @@ int __kprobes kprobe_handle_illslot(unsigned long pc) void __kprobes arch_remove_kprobe(struct kprobe *p) { - struct kprobe *saved = &__get_cpu_var(saved_next_opcode); + struct kprobe *saved = this_cpu_ptr(&saved_next_opcode); if (saved->addr) { arch_disarm_kprobe(p); @@ -111,7 +111,7 @@ void __kprobes arch_remove_kprobe(struct kprobe *p) saved->addr = NULL; saved->opcode = 0; - saved = &__get_cpu_var(saved_next_opcode2); + saved = this_cpu_ptr(&saved_next_opcode2); if (saved->addr) { arch_disarm_kprobe(saved); @@ -129,14 +129,14 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; } static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = p; + __this_cpu_write(current_kprobe, p); } /* @@ -146,15 +146,15 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, */ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) { - __get_cpu_var(saved_current_opcode).addr = (kprobe_opcode_t *)regs->pc; + __this_cpu_write(saved_current_opcode.addr, (kprobe_opcode_t *)regs->pc); if (p != NULL) { struct kprobe *op1, *op2; arch_disarm_kprobe(p); - op1 = &__get_cpu_var(saved_next_opcode); - op2 = &__get_cpu_var(saved_next_opcode2); + op1 = this_cpu_ptr(&saved_next_opcode); + op2 = this_cpu_ptr(&saved_next_opcode2); if (OPCODE_JSR(p->opcode) || OPCODE_JMP(p->opcode)) { unsigned int reg_nr = ((p->opcode >> 8) & 0x000F); @@ -249,7 +249,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) kcb->kprobe_status = KPROBE_REENTER; return 1; } else { - p = __get_cpu_var(current_kprobe); + p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { goto ss_probe; } @@ -336,9 +336,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) continue; if (ri->rp && ri->rp->handler) { - __get_cpu_var(current_kprobe) = &ri->rp->kp; + __this_cpu_write(current_kprobe, &ri->rp->kp); ri->rp->handler(ri, regs); - __get_cpu_var(current_kprobe) = NULL; + __this_cpu_write(current_kprobe, NULL); } orig_ret_address = (unsigned long)ri->ret_addr; @@ -383,19 +383,19 @@ static int __kprobes post_kprobe_handler(struct pt_regs *regs) cur->post_handler(cur, regs, 0); } - p = &__get_cpu_var(saved_next_opcode); + p = this_cpu_ptr(&saved_next_opcode); if (p->addr) { arch_disarm_kprobe(p); p->addr = NULL; p->opcode = 0; - addr = __get_cpu_var(saved_current_opcode).addr; - __get_cpu_var(saved_current_opcode).addr = NULL; + addr = __this_cpu_read(saved_current_opcode.addr); + __this_cpu_write(saved_current_opcode.addr, NULL); p = get_kprobe(addr); arch_arm_kprobe(p); - p = &__get_cpu_var(saved_next_opcode2); + p = this_cpu_ptr(&saved_next_opcode2); if (p->addr) { arch_disarm_kprobe(p); p->addr = NULL; @@ -511,7 +511,7 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, if (kprobe_handler(args->regs)) { ret = NOTIFY_STOP; } else { - p = __get_cpu_var(current_kprobe); + p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, args->regs)) ret = NOTIFY_STOP; diff --git a/arch/sh/kernel/localtimer.c b/arch/sh/kernel/localtimer.c index 8bfc6dfa8b94..b880a7e2ace7 100644 --- a/arch/sh/kernel/localtimer.c +++ b/arch/sh/kernel/localtimer.c @@ -32,7 +32,7 @@ static DEFINE_PER_CPU(struct clock_event_device, local_clockevent); */ void local_timer_interrupt(void) { - struct clock_event_device *clk = &__get_cpu_var(local_clockevent); + struct clock_event_device *clk = this_cpu_ptr(&local_clockevent); irq_enter(); clk->event_handler(clk); diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index b9cefebda55c..02331672b6db 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -227,7 +227,7 @@ again: static void sh_pmu_stop(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; @@ -245,7 +245,7 @@ static void sh_pmu_stop(struct perf_event *event, int flags) static void sh_pmu_start(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; @@ -262,7 +262,7 @@ static void sh_pmu_start(struct perf_event *event, int flags) static void sh_pmu_del(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); sh_pmu_stop(event, PERF_EF_UPDATE); __clear_bit(event->hw.idx, cpuc->used_mask); @@ -272,7 +272,7 @@ static void sh_pmu_del(struct perf_event *event, int flags) static int sh_pmu_add(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; int ret = -EAGAIN; diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index 86a7936a980b..fc5acfc93c92 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -111,7 +111,7 @@ void play_dead_common(void) irq_ctx_exit(raw_smp_processor_id()); mb(); - __get_cpu_var(cpu_state) = CPU_DEAD; + __this_cpu_write(cpu_state, CPU_DEAD); local_irq_disable(); } diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index 0d676a41081e..d7762349ea48 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -83,11 +83,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 0; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h index dfa53fdd5cbc..0aac1e8f2968 100644 --- a/arch/sparc/include/asm/unistd.h +++ b/arch/sparc/include/asm/unistd.h @@ -25,7 +25,6 @@ #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME #define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_UTIME diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 9bd9ce80bf77..d329537739c6 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -231,11 +231,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 0; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 85258ca43ff5..4f3006b600e3 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -125,6 +125,8 @@ config HVC_TILE config TILEGX bool "Building for TILE-Gx (64-bit) processor" + select SPARSE_IRQ + select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_FUNCTION_GRAPH_TRACER diff --git a/arch/tile/include/asm/irq.h b/arch/tile/include/asm/irq.h index 33cff9a3058b..1fe86911838b 100644 --- a/arch/tile/include/asm/irq.h +++ b/arch/tile/include/asm/irq.h @@ -18,10 +18,12 @@ #include <linux/hardirq.h> /* The hypervisor interface provides 32 IRQs. */ -#define NR_IRQS 32 +#define NR_IRQS 32 /* IRQ numbers used for linux IPIs. */ -#define IRQ_RESCHEDULE 0 +#define IRQ_RESCHEDULE 0 +/* Interrupts for dynamic allocation start at 1. Let the core allocate irq0 */ +#define NR_IRQS_LEGACY 1 #define irq_canonicalize(irq) (irq) diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h index d767ff9f59b9..48e4fd0f38e4 100644 --- a/arch/tile/include/asm/thread_info.h +++ b/arch/tile/include/asm/thread_info.h @@ -94,7 +94,7 @@ register unsigned long stack_pointer __asm__("sp"); /* Sit on a nap instruction until interrupted. */ extern void smp_nap(void); -/* Enable interrupts racelessly and nap forever: helper for cpu_idle(). */ +/* Enable interrupts racelessly and nap forever: helper for arch_cpu_idle(). */ extern void _cpu_idle(void); #else /* __ASSEMBLY__ */ diff --git a/arch/tile/kernel/irq.c b/arch/tile/kernel/irq.c index 906a76bdb31d..637f2ffaa5f5 100644 --- a/arch/tile/kernel/irq.c +++ b/arch/tile/kernel/irq.c @@ -54,13 +54,6 @@ static DEFINE_PER_CPU(unsigned long, irq_disable_mask) */ static DEFINE_PER_CPU(int, irq_depth); -/* State for allocating IRQs on Gx. */ -#if CHIP_HAS_IPI() -static unsigned long available_irqs = ((1UL << NR_IRQS) - 1) & - (~(1UL << IRQ_RESCHEDULE)); -static DEFINE_SPINLOCK(available_irqs_lock); -#endif - #if CHIP_HAS_IPI() /* Use SPRs to manipulate device interrupts. */ #define mask_irqs(irq_mask) __insn_mtspr(SPR_IPI_MASK_SET_K, irq_mask) @@ -278,38 +271,11 @@ int arch_show_interrupts(struct seq_file *p, int prec) return 0; } -/* - * Generic, controller-independent functions: - */ - #if CHIP_HAS_IPI() -int create_irq(void) +int arch_setup_hwirq(unsigned int irq, int node) { - unsigned long flags; - int result; - - spin_lock_irqsave(&available_irqs_lock, flags); - if (available_irqs == 0) - result = -ENOMEM; - else { - result = __ffs(available_irqs); - available_irqs &= ~(1UL << result); - dynamic_irq_init(result); - } - spin_unlock_irqrestore(&available_irqs_lock, flags); - - return result; + return irq >= NR_IRQS ? -EINVAL : 0; } -EXPORT_SYMBOL(create_irq); -void destroy_irq(unsigned int irq) -{ - unsigned long flags; - - spin_lock_irqsave(&available_irqs_lock, flags); - available_irqs |= (1UL << irq); - dynamic_irq_cleanup(irq); - spin_unlock_irqrestore(&available_irqs_lock, flags); -} -EXPORT_SYMBOL(destroy_irq); +void arch_teardown_hwirq(unsigned int irq) { } #endif diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c index 077b7bc437e5..e39f9c542807 100644 --- a/arch/tile/kernel/pci_gx.c +++ b/arch/tile/kernel/pci_gx.c @@ -350,10 +350,9 @@ static int tile_init_irqs(struct pci_controller *controller) int cpu; /* Ask the kernel to allocate an IRQ. */ - irq = create_irq(); - if (irq < 0) { + irq = irq_alloc_hwirq(-1); + if (!irq) { pr_err("PCI: no free irq vectors, failed for %d\n", i); - goto free_irqs; } controller->irq_intx_table[i] = irq; @@ -382,7 +381,7 @@ static int tile_init_irqs(struct pci_controller *controller) free_irqs: for (j = 0; j < i; j++) - destroy_irq(controller->irq_intx_table[j]); + irq_free_hwirq(controller->irq_intx_table[j]); return -1; } @@ -1500,9 +1499,9 @@ int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) int irq; int ret; - irq = create_irq(); - if (irq < 0) - return irq; + irq = irq_alloc_hwirq(-1); + if (!irq) + return -ENOSPC; /* * Since we use a 64-bit Mem-Map to accept the MSI write, we fail @@ -1601,11 +1600,11 @@ hv_msi_config_failure: /* Free mem-map */ msi_mem_map_alloc_failure: is_64_failure: - destroy_irq(irq); + irq_free_hwirq(irq); return ret; } void arch_teardown_msi_irq(unsigned int irq) { - destroy_irq(irq); + irq_free_hwirq(irq); } diff --git a/arch/tile/kernel/proc.c b/arch/tile/kernel/proc.c index 681100c59fda..6829a9508649 100644 --- a/arch/tile/kernel/proc.c +++ b/arch/tile/kernel/proc.c @@ -113,7 +113,7 @@ arch_initcall(proc_tile_init); * Support /proc/sys/tile directory */ -static ctl_table unaligned_subtable[] = { +static struct ctl_table unaligned_subtable[] = { { .procname = "enabled", .data = &unaligned_fixup, @@ -138,7 +138,7 @@ static ctl_table unaligned_subtable[] = { {} }; -static ctl_table unaligned_table[] = { +static struct ctl_table unaligned_table[] = { { .procname = "unaligned_fixup", .mode = 0555, diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index 74c91729a62a..112ababa9e55 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -228,13 +228,10 @@ early_param("isolnodes", setup_isolnodes); #if defined(CONFIG_PCI) && !defined(__tilegx__) static int __init setup_pci_reserve(char* str) { - unsigned long mb; - - if (str == NULL || strict_strtoul(str, 0, &mb) != 0 || - mb > 3 * 1024) + if (str == NULL || kstrtouint(str, 0, &pci_reserve_mb) != 0 || + pci_reserve_mb > 3 * 1024) return -EINVAL; - pci_reserve_mb = mb; pr_info("Reserving %dMB for PCIE root complex mappings\n", pci_reserve_mb); return 0; @@ -691,7 +688,7 @@ static void __init setup_bootmem_allocator(void) /* Reserve any memory excluded by "memmap" arguments. */ for (i = 0; i < memmap_nr; ++i) { struct memmap_entry *m = &memmap_map[i]; - reserve_bootmem(m->addr, m->size, 0); + reserve_bootmem(m->addr, m->size, BOOTMEM_DEFAULT); } #ifdef CONFIG_BLK_DEV_INITRD @@ -715,7 +712,8 @@ static void __init setup_bootmem_allocator(void) #ifdef CONFIG_KEXEC if (crashk_res.start != crashk_res.end) - reserve_bootmem(crashk_res.start, resource_size(&crashk_res), 0); + reserve_bootmem(crashk_res.start, resource_size(&crashk_res), + BOOTMEM_DEFAULT); #endif } diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c index 2d1dbf38a9ab..d1d026f01267 100644 --- a/arch/tile/kernel/signal.c +++ b/arch/tile/kernel/signal.c @@ -321,14 +321,13 @@ int show_unhandled_signals = 1; static int __init crashinfo(char *str) { - unsigned long val; const char *word; if (*str == '\0') - val = 2; - else if (*str != '=' || strict_strtoul(++str, 0, &val) != 0) + show_unhandled_signals = 2; + else if (*str != '=' || kstrtoint(++str, 0, &show_unhandled_signals) != 0) return 0; - show_unhandled_signals = val; + switch (show_unhandled_signals) { case 0: word = "No"; diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c index 6b603d556ca6..f3ceb6308e42 100644 --- a/arch/tile/kernel/traps.c +++ b/arch/tile/kernel/traps.c @@ -42,10 +42,9 @@ static int __init setup_unaligned_fixup(char *str) * will still parse the instruction, then fire a SIGBUS with * the correct address from inside the single_step code. */ - long val; - if (strict_strtol(str, 0, &val) != 0) + if (kstrtoint(str, 0, &unaligned_fixup) != 0) return 0; - unaligned_fixup = val; + pr_info("Fixups for unaligned data accesses are %s\n", unaligned_fixup >= 0 ? (unaligned_fixup ? "enabled" : "disabled") : diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c index b030b4e78845..c02ea2a45f67 100644 --- a/arch/tile/kernel/unaligned.c +++ b/arch/tile/kernel/unaligned.c @@ -182,18 +182,7 @@ static void find_regs(tilegx_bundle_bits bundle, uint64_t *rd, uint64_t *ra, int i; uint64_t reg; uint64_t reg_map = 0, alias_reg_map = 0, map; - bool alias; - - *ra = -1; - *rb = -1; - - if (rd) - *rd = -1; - - *clob1 = -1; - *clob2 = -1; - *clob3 = -1; - alias = false; + bool alias = false; /* * Parse fault bundle, find potential used registers and mark @@ -569,7 +558,7 @@ void jit_bundle_gen(struct pt_regs *regs, tilegx_bundle_bits bundle, tilegx_bundle_bits bundle_2 = 0; /* If bundle_2_enable = false, bundle_2 is fnop/nop operation. */ bool bundle_2_enable = true; - uint64_t ra, rb, rd = -1, clob1, clob2, clob3; + uint64_t ra = -1, rb = -1, rd = -1, clob1 = -1, clob2 = -1, clob3 = -1; /* * Indicate if the unalign access * instruction's registers hit with diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c index 004ba568d93f..33294fdc402e 100644 --- a/arch/tile/mm/homecache.c +++ b/arch/tile/mm/homecache.c @@ -417,7 +417,7 @@ void __homecache_free_pages(struct page *page, unsigned int order) if (put_page_testzero(page)) { homecache_change_page_home(page, order, PAGE_HOME_HASH); if (order == 0) { - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); } else { init_page_count(page); __free_pages(page, order); diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c index 0cb3bbaa580c..e514899e1100 100644 --- a/arch/tile/mm/hugetlbpage.c +++ b/arch/tile/mm/hugetlbpage.c @@ -166,11 +166,6 @@ int pud_huge(pud_t pud) return !!(pud_val(pud) & _PAGE_HUGE_PAGE); } -int pmd_huge_support(void) -{ - return 1; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c index 0fa1acfac79a..bfb3127b4df9 100644 --- a/arch/tile/mm/init.c +++ b/arch/tile/mm/init.c @@ -273,9 +273,9 @@ static pgprot_t __init init_pgprot(ulong address) /* * Otherwise we just hand out consecutive cpus. To avoid * requiring this function to hold state, we just walk forward from - * _sdata by PAGE_SIZE, skipping the readonly and init data, to reach - * the requested address, while walking cpu home around kdata_mask. - * This is typically no more than a dozen or so iterations. + * __end_rodata by PAGE_SIZE, skipping the readonly and init data, to + * reach the requested address, while walking cpu home around + * kdata_mask. This is typically no more than a dozen or so iterations. */ page = (((ulong)__end_rodata) + PAGE_SIZE - 1) & PAGE_MASK; BUG_ON(address < page || address >= (ulong)_end); @@ -912,7 +912,7 @@ static long __write_once initfree = 1; static int __init set_initfree(char *str) { long val; - if (strict_strtol(str, 0, &val) == 0) { + if (kstrtol(str, 0, &val) == 0) { initfree = val; pr_info("initfree: %s free init pages\n", initfree ? "will" : "won't"); diff --git a/arch/unicore32/mm/ioremap.c b/arch/unicore32/mm/ioremap.c index 13068ee22f33..bf012b2b71a9 100644 --- a/arch/unicore32/mm/ioremap.c +++ b/arch/unicore32/mm/ioremap.c @@ -144,11 +144,11 @@ void __iomem *__uc32_ioremap_pfn_caller(unsigned long pfn, * Don't allow RAM to be mapped */ if (pfn_valid(pfn)) { - printk(KERN_WARNING "BUG: Your driver calls ioremap() on\n" + WARN(1, "BUG: Your driver calls ioremap() on\n" "system memory. This leads to architecturally\n" "unpredictable behaviour, and ioremap() will fail in\n" "the next kernel release. Please fix your driver.\n"); - WARN_ON(1); + return NULL; } type = get_mem_type(mtype); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7d5feb5908dd..b660088c220d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -26,7 +26,7 @@ config X86 select ARCH_MIGHT_HAVE_PC_SERIO select HAVE_AOUT if X86_32 select HAVE_UNSTABLE_SCHED_CLOCK - select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_SUPPORTS_INT128 if X86_64 select ARCH_WANTS_PROT_NUMA_PROT_NONE select HAVE_IDE @@ -41,7 +41,7 @@ config X86 select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS - select HAVE_DMA_CONTIGUOUS if !SWIOTLB + select HAVE_DMA_CONTIGUOUS select HAVE_KRETPROBES select GENERIC_EARLY_IOREMAP select HAVE_OPTPROBES @@ -105,7 +105,7 @@ config X86 select HAVE_ARCH_SECCOMP_FILTER select BUILDTIME_EXTABLE_SORT select GENERIC_CMOS_UPDATE - select HAVE_ARCH_SOFT_DIRTY + select HAVE_ARCH_SOFT_DIRTY if X86_64 select CLOCKSOURCE_WATCHDOG select GENERIC_CLOCKEVENTS select ARCH_CLOCKSOURCE_DATA @@ -833,6 +833,7 @@ config X86_LOCAL_APIC config X86_IO_APIC def_bool y depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI + select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS bool "Reroute for broken boot IRQs" @@ -911,10 +912,27 @@ config VM86 default y depends on X86_32 ---help--- - This option is required by programs like DOSEMU to run 16-bit legacy - code on X86 processors. It also may be needed by software like - XFree86 to initialize some video cards via BIOS. Disabling this - option saves about 6k. + This option is required by programs like DOSEMU to run + 16-bit real mode legacy code on x86 processors. It also may + be needed by software like XFree86 to initialize some video + cards via BIOS. Disabling this option saves about 6K. + +config X86_16BIT + bool "Enable support for 16-bit segments" if EXPERT + default y + ---help--- + This option is required by programs like Wine to run 16-bit + protected mode legacy code on x86 processors. Disabling + this option saves about 300 bytes on i386, or around 6K text + plus 16K runtime memory on x86-64, + +config X86_ESPFIX32 + def_bool y + depends on X86_16BIT && X86_32 + +config X86_ESPFIX64 + def_bool y + depends on X86_16BIT && X86_64 config TOSHIBA tristate "Toshiba Laptop support" @@ -1873,6 +1891,10 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK def_bool y depends on X86_64 || X86_PAE +config ARCH_ENABLE_HUGEPAGE_MIGRATION + def_bool y + depends on X86_64 && HUGETLB_PAGE && MIGRATION + menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 4703a6c4b8e3..0331d765c2bb 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1087,8 +1087,7 @@ struct boot_params *make_boot_params(struct efi_config *c) hdr->type_of_loader = 0x21; /* Convert unicode cmdline to ascii */ - cmdline_ptr = efi_convert_cmdline_to_ascii(sys_table, image, - &options_size); + cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); if (!cmdline_ptr) goto fail; hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 0d558ee899ae..2884e0c3e8a5 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -452,7 +452,7 @@ efi32_config: .global efi64_config efi64_config: .fill 11,8,0 - .quad efi_call6 + .quad efi_call .byte 1 #endif /* CONFIG_EFI_STUB */ diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 0ca9a5c362bc..84c223479e3c 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -375,8 +375,7 @@ xloadflags: # define XLF0 0 #endif -#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64) && \ - !defined(CONFIG_EFI_MIXED) +#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64) /* kernel/boot_param/ramdisk could be loaded above 4g */ # define XLF1 XLF_CAN_BE_LOADED_ABOVE_4G #else diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S index 185fad49d86f..5d1e0075ac24 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_asm.S +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -92,7 +92,7 @@ __clmul_gf128mul_ble: ret ENDPROC(__clmul_gf128mul_ble) -/* void clmul_ghash_mul(char *dst, const be128 *shash) */ +/* void clmul_ghash_mul(char *dst, const u128 *shash) */ ENTRY(clmul_ghash_mul) movups (%rdi), DATA movups (%rsi), SHASH @@ -106,7 +106,7 @@ ENDPROC(clmul_ghash_mul) /* * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, - * const be128 *shash); + * const u128 *shash); */ ENTRY(clmul_ghash_update) cmp $16, %rdx diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index d785cf2c529c..88bb7ba8b175 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -25,17 +25,17 @@ #define GHASH_BLOCK_SIZE 16 #define GHASH_DIGEST_SIZE 16 -void clmul_ghash_mul(char *dst, const be128 *shash); +void clmul_ghash_mul(char *dst, const u128 *shash); void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, - const be128 *shash); + const u128 *shash); struct ghash_async_ctx { struct cryptd_ahash *cryptd_tfm; }; struct ghash_ctx { - be128 shash; + u128 shash; }; struct ghash_desc_ctx { @@ -68,11 +68,11 @@ static int ghash_setkey(struct crypto_shash *tfm, a = be64_to_cpu(x->a); b = be64_to_cpu(x->b); - ctx->shash.a = (__be64)((b << 1) | (a >> 63)); - ctx->shash.b = (__be64)((a << 1) | (b >> 63)); + ctx->shash.a = (b << 1) | (a >> 63); + ctx->shash.b = (a << 1) | (b >> 63); if (a >> 63) - ctx->shash.b ^= cpu_to_be64(0xc2); + ctx->shash.b ^= ((u64)0xc2) << 56; return 0; } diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 220675795e08..f9e181aaba97 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -383,8 +383,8 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, } else { /* Return stub is in 32bit vsyscall page */ if (current->mm->context.vdso) - restorer = VDSO32_SYMBOL(current->mm->context.vdso, - sigreturn); + restorer = current->mm->context.vdso + + selected_vdso32->sym___kernel_sigreturn; else restorer = &frame->retcode; } @@ -462,8 +462,8 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; else - restorer = VDSO32_SYMBOL(current->mm->context.vdso, - rt_sigreturn); + restorer = current->mm->context.vdso + + selected_vdso32->sym___kernel_rt_sigreturn; put_user_ex(ptr_to_compat(restorer), &frame->pretcode); /* diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 0869434eaf72..1eb5f6433ad8 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_EFI_H #define _ASM_X86_EFI_H +#include <asm/i387.h> /* * We map the EFI regions needed for runtime services non-contiguously, * with preserved alignment on virtual addresses starting from -4G down @@ -27,91 +28,58 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); -#define efi_call_phys0(f) efi_call_phys(f) -#define efi_call_phys1(f, a1) efi_call_phys(f, a1) -#define efi_call_phys2(f, a1, a2) efi_call_phys(f, a1, a2) -#define efi_call_phys3(f, a1, a2, a3) efi_call_phys(f, a1, a2, a3) -#define efi_call_phys4(f, a1, a2, a3, a4) \ - efi_call_phys(f, a1, a2, a3, a4) -#define efi_call_phys5(f, a1, a2, a3, a4, a5) \ - efi_call_phys(f, a1, a2, a3, a4, a5) -#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6) \ - efi_call_phys(f, a1, a2, a3, a4, a5, a6) /* * Wrap all the virtual calls in a way that forces the parameters on the stack. */ +/* Use this macro if your virtual returns a non-void value */ #define efi_call_virt(f, args...) \ - ((efi_##f##_t __attribute__((regparm(0)))*)efi.systab->runtime->f)(args) - -#define efi_call_virt0(f) efi_call_virt(f) -#define efi_call_virt1(f, a1) efi_call_virt(f, a1) -#define efi_call_virt2(f, a1, a2) efi_call_virt(f, a1, a2) -#define efi_call_virt3(f, a1, a2, a3) efi_call_virt(f, a1, a2, a3) -#define efi_call_virt4(f, a1, a2, a3, a4) \ - efi_call_virt(f, a1, a2, a3, a4) -#define efi_call_virt5(f, a1, a2, a3, a4, a5) \ - efi_call_virt(f, a1, a2, a3, a4, a5) -#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ - efi_call_virt(f, a1, a2, a3, a4, a5, a6) +({ \ + efi_status_t __s; \ + kernel_fpu_begin(); \ + __s = ((efi_##f##_t __attribute__((regparm(0)))*) \ + efi.systab->runtime->f)(args); \ + kernel_fpu_end(); \ + __s; \ +}) + +/* Use this macro if your virtual call does not return any value */ +#define __efi_call_virt(f, args...) \ +({ \ + kernel_fpu_begin(); \ + ((efi_##f##_t __attribute__((regparm(0)))*) \ + efi.systab->runtime->f)(args); \ + kernel_fpu_end(); \ +}) #define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) #else /* !CONFIG_X86_32 */ -extern u64 efi_call0(void *fp); -extern u64 efi_call1(void *fp, u64 arg1); -extern u64 efi_call2(void *fp, u64 arg1, u64 arg2); -extern u64 efi_call3(void *fp, u64 arg1, u64 arg2, u64 arg3); -extern u64 efi_call4(void *fp, u64 arg1, u64 arg2, u64 arg3, u64 arg4); -extern u64 efi_call5(void *fp, u64 arg1, u64 arg2, u64 arg3, - u64 arg4, u64 arg5); -extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3, - u64 arg4, u64 arg5, u64 arg6); - -#define efi_call_phys0(f) \ - efi_call0((f)) -#define efi_call_phys1(f, a1) \ - efi_call1((f), (u64)(a1)) -#define efi_call_phys2(f, a1, a2) \ - efi_call2((f), (u64)(a1), (u64)(a2)) -#define efi_call_phys3(f, a1, a2, a3) \ - efi_call3((f), (u64)(a1), (u64)(a2), (u64)(a3)) -#define efi_call_phys4(f, a1, a2, a3, a4) \ - efi_call4((f), (u64)(a1), (u64)(a2), (u64)(a3), \ - (u64)(a4)) -#define efi_call_phys5(f, a1, a2, a3, a4, a5) \ - efi_call5((f), (u64)(a1), (u64)(a2), (u64)(a3), \ - (u64)(a4), (u64)(a5)) -#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6) \ - efi_call6((f), (u64)(a1), (u64)(a2), (u64)(a3), \ - (u64)(a4), (u64)(a5), (u64)(a6)) - -#define _efi_call_virtX(x, f, ...) \ +#define EFI_LOADER_SIGNATURE "EL64" + +extern u64 asmlinkage efi_call(void *fp, ...); + +#define efi_call_phys(f, args...) efi_call((f), args) + +#define efi_call_virt(f, ...) \ ({ \ efi_status_t __s; \ \ efi_sync_low_kernel_mappings(); \ preempt_disable(); \ - __s = efi_call##x((void *)efi.systab->runtime->f, __VA_ARGS__); \ + __kernel_fpu_begin(); \ + __s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__); \ + __kernel_fpu_end(); \ preempt_enable(); \ __s; \ }) -#define efi_call_virt0(f) \ - _efi_call_virtX(0, f) -#define efi_call_virt1(f, a1) \ - _efi_call_virtX(1, f, (u64)(a1)) -#define efi_call_virt2(f, a1, a2) \ - _efi_call_virtX(2, f, (u64)(a1), (u64)(a2)) -#define efi_call_virt3(f, a1, a2, a3) \ - _efi_call_virtX(3, f, (u64)(a1), (u64)(a2), (u64)(a3)) -#define efi_call_virt4(f, a1, a2, a3, a4) \ - _efi_call_virtX(4, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4)) -#define efi_call_virt5(f, a1, a2, a3, a4, a5) \ - _efi_call_virtX(5, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5)) -#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ - _efi_call_virtX(6, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) +/* + * All X86_64 virt calls return non-void values. Thus, use non-void call for + * virt calls that would be void on X86_32. + */ +#define __efi_call_virt(f, args...) efi_call_virt(f, args) extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 2c71182d30ef..1a055c81d864 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -75,7 +75,12 @@ typedef struct user_fxsr_struct elf_fpxregset_t; #include <asm/vdso.h> -extern unsigned int vdso_enabled; +#ifdef CONFIG_X86_64 +extern unsigned int vdso64_enabled; +#endif +#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +extern unsigned int vdso32_enabled; +#endif /* * This is used to ensure we don't load something for the wrong architecture. @@ -269,9 +274,9 @@ extern int force_personality32; struct task_struct; -#define ARCH_DLINFO_IA32(vdso_enabled) \ +#define ARCH_DLINFO_IA32 \ do { \ - if (vdso_enabled) { \ + if (vdso32_enabled) { \ NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \ } \ @@ -281,7 +286,7 @@ do { \ #define STACK_RND_MASK (0x7ff) -#define ARCH_DLINFO ARCH_DLINFO_IA32(vdso_enabled) +#define ARCH_DLINFO ARCH_DLINFO_IA32 /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ @@ -292,16 +297,17 @@ do { \ #define ARCH_DLINFO \ do { \ - if (vdso_enabled) \ + if (vdso64_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ - (unsigned long)current->mm->context.vdso); \ + (unsigned long __force)current->mm->context.vdso); \ } while (0) +/* As a historical oddity, the x32 and x86_64 vDSOs are controlled together. */ #define ARCH_DLINFO_X32 \ do { \ - if (vdso_enabled) \ + if (vdso64_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ - (unsigned long)current->mm->context.vdso); \ + (unsigned long __force)current->mm->context.vdso); \ } while (0) #define AT_SYSINFO 32 @@ -310,7 +316,7 @@ do { \ if (test_thread_flag(TIF_X32)) \ ARCH_DLINFO_X32; \ else \ - ARCH_DLINFO_IA32(sysctl_vsyscall32) + ARCH_DLINFO_IA32 #define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000) @@ -319,18 +325,17 @@ else \ #define VDSO_CURRENT_BASE ((unsigned long)current->mm->context.vdso) #define VDSO_ENTRY \ - ((unsigned long)VDSO32_SYMBOL(VDSO_CURRENT_BASE, vsyscall)) + ((unsigned long)current->mm->context.vdso + \ + selected_vdso32->sym___kernel_vsyscall) struct linux_binprm; #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 extern int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); -extern int x32_setup_additional_pages(struct linux_binprm *bprm, - int uses_interp); - -extern int syscall32_setup_pages(struct linux_binprm *, int exstack); -#define compat_arch_setup_additional_pages syscall32_setup_pages +extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); +#define compat_arch_setup_additional_pages compat_arch_setup_additional_pages extern unsigned long arch_randomize_brk(struct mm_struct *mm); #define arch_randomize_brk arch_randomize_brk diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h new file mode 100644 index 000000000000..99efebb2f69d --- /dev/null +++ b/arch/x86/include/asm/espfix.h @@ -0,0 +1,16 @@ +#ifndef _ASM_X86_ESPFIX_H +#define _ASM_X86_ESPFIX_H + +#ifdef CONFIG_X86_64 + +#include <asm/percpu.h> + +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +extern void init_espfix_bsp(void); +extern void init_espfix_ap(void); + +#endif /* CONFIG_X86_64 */ + +#endif /* _ASM_X86_ESPFIX_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 43f482a0db37..b0910f97a3ea 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -24,7 +24,7 @@ #include <linux/threads.h> #include <asm/kmap_types.h> #else -#include <asm/vsyscall.h> +#include <uapi/asm/vsyscall.h> #endif /* @@ -41,7 +41,8 @@ extern unsigned long __FIXADDR_TOP; #define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) #else -#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE) +#define FIXADDR_TOP (round_up(VSYSCALL_ADDR + PAGE_SIZE, 1<<PMD_SHIFT) - \ + PAGE_SIZE) #endif @@ -68,11 +69,7 @@ enum fixed_addresses { #ifdef CONFIG_X86_32 FIX_HOLE, #else - VSYSCALL_LAST_PAGE, - VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE - + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1, - VVAR_PAGE, - VSYSCALL_HPET, + VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT, #ifdef CONFIG_PARAVIRT_CLOCK PVCLOCK_FIXMAP_BEGIN, PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index cea1c76d49bf..115e3689cd53 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -87,22 +87,22 @@ static inline int is_x32_frame(void) static __always_inline __pure bool use_eager_fpu(void) { - return static_cpu_has(X86_FEATURE_EAGER_FPU); + return static_cpu_has_safe(X86_FEATURE_EAGER_FPU); } static __always_inline __pure bool use_xsaveopt(void) { - return static_cpu_has(X86_FEATURE_XSAVEOPT); + return static_cpu_has_safe(X86_FEATURE_XSAVEOPT); } static __always_inline __pure bool use_xsave(void) { - return static_cpu_has(X86_FEATURE_XSAVE); + return static_cpu_has_safe(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { - return static_cpu_has(X86_FEATURE_FXSR); + return static_cpu_has_safe(X86_FEATURE_FXSR); } static inline void fx_finit(struct i387_fxsave_struct *fx) @@ -293,7 +293,7 @@ static inline int restore_fpu_checking(struct task_struct *tsk) /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is pending. Clear the x87 state here by setting it to fixed values. "m" is a random variable that should be in L1 */ - if (unlikely(static_cpu_has(X86_FEATURE_FXSAVE_LEAK))) { + if (unlikely(static_cpu_has_safe(X86_FEATURE_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" "emms\n\t" diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 459e50a424d1..90f97b4b9347 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -168,8 +168,6 @@ extern int save_ioapic_entries(void); extern void mask_ioapic_entries(void); extern int restore_ioapic_entries(void); -extern int get_nr_irqs_gsi(void); - extern void setup_ioapic_ids_from_mpc(void); extern void setup_ioapic_ids_from_mpc_nocheck(void); diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index d806b228d2c0..b7747c4c2cf2 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -103,4 +103,7 @@ static inline bool setup_remapped_irq(int irq, } #endif /* CONFIG_IRQ_REMAP */ +#define dmar_alloc_hwirq() irq_alloc_hwirq(-1) +#define dmar_free_hwirq irq_free_hwirq + #endif /* __X86_IRQ_REMAPPING_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 6e4ce2df87cf..958b90f761e5 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -176,8 +176,6 @@ int mce_available(struct cpuinfo_x86 *c); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); -extern atomic_t mce_entry; - typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS); DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 5f55e6962769..876e74e8eec7 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -18,7 +18,7 @@ typedef struct { #endif struct mutex lock; - void *vdso; + void __user *vdso; } mm_context_t; #ifdef CONFIG_SMP diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 0d193e234647..206a87fdd22d 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -62,66 +62,14 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi return ((value >> rightshift) & mask) << leftshift; } -#ifdef CONFIG_MEM_SOFT_DIRTY - -/* - * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE, _PAGE_BIT_SOFT_DIRTY and - * _PAGE_BIT_PROTNONE are taken, split up the 28 bits of offset - * into this range. - */ -#define PTE_FILE_MAX_BITS 28 -#define PTE_FILE_SHIFT1 (_PAGE_BIT_PRESENT + 1) -#define PTE_FILE_SHIFT2 (_PAGE_BIT_FILE + 1) -#define PTE_FILE_SHIFT3 (_PAGE_BIT_PROTNONE + 1) -#define PTE_FILE_SHIFT4 (_PAGE_BIT_SOFT_DIRTY + 1) -#define PTE_FILE_BITS1 (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1) -#define PTE_FILE_BITS2 (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1) -#define PTE_FILE_BITS3 (PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1) - -#define PTE_FILE_MASK1 ((1U << PTE_FILE_BITS1) - 1) -#define PTE_FILE_MASK2 ((1U << PTE_FILE_BITS2) - 1) -#define PTE_FILE_MASK3 ((1U << PTE_FILE_BITS3) - 1) - -#define PTE_FILE_LSHIFT2 (PTE_FILE_BITS1) -#define PTE_FILE_LSHIFT3 (PTE_FILE_BITS1 + PTE_FILE_BITS2) -#define PTE_FILE_LSHIFT4 (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3) - -static __always_inline pgoff_t pte_to_pgoff(pte_t pte) -{ - return (pgoff_t) - (pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1, 0) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2, PTE_FILE_LSHIFT2) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT3, PTE_FILE_MASK3, PTE_FILE_LSHIFT3) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT4, -1UL, PTE_FILE_LSHIFT4)); -} - -static __always_inline pte_t pgoff_to_pte(pgoff_t off) -{ - return (pte_t){ - .pte_low = - pte_bitop(off, 0, PTE_FILE_MASK1, PTE_FILE_SHIFT1) + - pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2, PTE_FILE_SHIFT2) + - pte_bitop(off, PTE_FILE_LSHIFT3, PTE_FILE_MASK3, PTE_FILE_SHIFT3) + - pte_bitop(off, PTE_FILE_LSHIFT4, -1UL, PTE_FILE_SHIFT4) + - _PAGE_FILE, - }; -} - -#else /* CONFIG_MEM_SOFT_DIRTY */ - /* * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken, * split up the 29 bits of offset into this range. */ #define PTE_FILE_MAX_BITS 29 #define PTE_FILE_SHIFT1 (_PAGE_BIT_PRESENT + 1) -#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define PTE_FILE_SHIFT2 (_PAGE_BIT_FILE + 1) #define PTE_FILE_SHIFT3 (_PAGE_BIT_PROTNONE + 1) -#else -#define PTE_FILE_SHIFT2 (_PAGE_BIT_PROTNONE + 1) -#define PTE_FILE_SHIFT3 (_PAGE_BIT_FILE + 1) -#endif #define PTE_FILE_BITS1 (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1) #define PTE_FILE_BITS2 (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1) @@ -150,16 +98,9 @@ static __always_inline pte_t pgoff_to_pte(pgoff_t off) }; } -#endif /* CONFIG_MEM_SOFT_DIRTY */ - /* Encode and de-code a swap entry */ -#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1) #define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) -#else -#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1) -#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1) -#endif #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index b459ddf27d64..0ec056012618 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -131,7 +131,8 @@ static inline int pte_exec(pte_t pte) static inline int pte_special(pte_t pte) { - return pte_flags(pte) & _PAGE_SPECIAL; + return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) == + (_PAGE_PRESENT|_PAGE_SPECIAL); } static inline unsigned long pte_pfn(pte_t pte) @@ -296,6 +297,7 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT); } +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SOFT_DIRTY; @@ -331,6 +333,8 @@ static inline int pte_file_soft_dirty(pte_t pte) return pte_flags(pte) & _PAGE_SOFT_DIRTY; } +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. @@ -452,6 +456,12 @@ static inline int pte_present(pte_t a) _PAGE_NUMA); } +#define pte_present_nonuma pte_present_nonuma +static inline int pte_present_nonuma(pte_t a) +{ + return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); +} + #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { @@ -858,23 +868,25 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, { } +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); } static inline int pte_swp_soft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); } +#endif #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index e22c1dbf7feb..5be9063545d2 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -143,12 +143,12 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define pte_unmap(pte) ((void)(pte))/* NOP */ /* Encode and de-code a swap entry */ -#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1) -#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) +#ifdef CONFIG_NUMA_BALANCING +/* Automatic NUMA balancing needs to be distinguishable from swap entries */ +#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 2) #else -#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1) -#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1) +#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) #endif #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index c883bf726398..7166e25ecb57 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t; #define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) #define MODULES_END _AC(0xffffffffff000000, UL) #define MODULES_LEN (MODULES_END - MODULES_VADDR) +#define ESPFIX_PGD_ENTRY _AC(-2, UL) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT) #define EARLY_DYNAMIC_PAGE_TABLES 64 diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index eb3d44945133..f216963760e5 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -16,15 +16,26 @@ #define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */ #define _PAGE_BIT_PAT 7 /* on 4KB pages */ #define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ -#define _PAGE_BIT_UNUSED1 9 /* available for programmer */ -#define _PAGE_BIT_IOMAP 10 /* flag used to indicate IO mapping */ -#define _PAGE_BIT_HIDDEN 11 /* hidden by kmemcheck */ +#define _PAGE_BIT_SOFTW1 9 /* available for programmer */ +#define _PAGE_BIT_SOFTW2 10 /* " */ +#define _PAGE_BIT_SOFTW3 11 /* " */ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ -#define _PAGE_BIT_SPECIAL _PAGE_BIT_UNUSED1 -#define _PAGE_BIT_CPA_TEST _PAGE_BIT_UNUSED1 -#define _PAGE_BIT_SPLITTING _PAGE_BIT_UNUSED1 /* only valid on a PSE pmd */ +#define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 +#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 +#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ +#define _PAGE_BIT_IOMAP _PAGE_BIT_SOFTW2 /* flag used to indicate IO mapping */ +#define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ +#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ #define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ +/* + * Swap offsets on configurations that allow automatic NUMA balancing use the + * bits after _PAGE_BIT_GLOBAL. To uniquely distinguish NUMA hinting PTEs from + * swap entries, we use the first bit after _PAGE_BIT_GLOBAL and shrink the + * maximum possible swap space from 16TB to 8TB. + */ +#define _PAGE_BIT_NUMA (_PAGE_BIT_GLOBAL+1) + /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ #define _PAGE_BIT_PROTNONE _PAGE_BIT_GLOBAL @@ -40,7 +51,7 @@ #define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY) #define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE) #define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) -#define _PAGE_UNUSED1 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1) +#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) #define _PAGE_IOMAP (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP) #define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) @@ -61,8 +72,6 @@ * they do not conflict with each other. */ -#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_HIDDEN - #ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY) #else @@ -70,6 +79,21 @@ #endif /* + * _PAGE_NUMA distinguishes between a numa hinting minor fault and a page + * that is not present. The hinting fault gathers numa placement statistics + * (see pte_numa()). The bit is always zero when the PTE is not present. + * + * The bit picked must be always zero when the pmd is present and not + * present, so that we don't lose information when we set it while + * atomically clearing the present bit. + */ +#ifdef CONFIG_NUMA_BALANCING +#define _PAGE_NUMA (_AT(pteval_t, 1) << _PAGE_BIT_NUMA) +#else +#define _PAGE_NUMA (_AT(pteval_t, 0)) +#endif + +/* * Tracking soft dirty bit when a page goes to a swap is tricky. * We need a bit which can be stored in pte _and_ not conflict * with swap entry format. On x86 bits 6 and 7 are *not* involved @@ -94,26 +118,6 @@ #define _PAGE_FILE (_AT(pteval_t, 1) << _PAGE_BIT_FILE) #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) -/* - * _PAGE_NUMA indicates that this page will trigger a numa hinting - * minor page fault to gather numa placement statistics (see - * pte_numa()). The bit picked (8) is within the range between - * _PAGE_FILE (6) and _PAGE_PROTNONE (8) bits. Therefore, it doesn't - * require changes to the swp entry format because that bit is always - * zero when the pte is not present. - * - * The bit picked must be always zero when the pmd is present and not - * present, so that we don't lose information when we set it while - * atomically clearing the present bit. - * - * Because we shared the same bit (8) with _PAGE_PROTNONE this can be - * interpreted as _PAGE_NUMA only in places that _PAGE_PROTNONE - * couldn't reach, like handle_mm_fault() (see access_error in - * arch/x86/mm/fault.c, the vma protection must not be PROT_NONE for - * handle_mm_fault() to be invoked). - */ -#define _PAGE_NUMA _PAGE_PROTNONE - #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ _PAGE_ACCESSED | _PAGE_DIRTY) #define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ @@ -122,8 +126,8 @@ /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY) -#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) + _PAGE_SOFT_DIRTY | _PAGE_NUMA) +#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA) #define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT) #define _PAGE_CACHE_WB (0) diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 6fd3fd769796..a90f8972dad5 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -12,8 +12,6 @@ void ia32_syscall(void); void ia32_cstar_target(void); void ia32_sysenter_target(void); -void syscall32_cpu_init(void); - void x86_configure_nx(void); void x86_report_nx(void); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 9264f04a4c55..ff4e7b236e21 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -59,6 +59,8 @@ static inline void x86_ce4100_early_setup(void) { } #ifndef _SETUP +#include <asm/espfix.h> + /* * This is set up by the setup-routine at boot-time */ diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 35e67a457182..31eab867e6d3 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -92,12 +92,6 @@ static inline int __gen_sigismember(sigset_t *set, int _sig) ? __const_sigismember((set), (sig)) \ : __gen_sigismember((set), (sig))) -static inline int sigfindinword(unsigned long word) -{ - asm("bsfl %1,%0" : "=r"(word) : "rm"(word) : "cc"); - return word; -} - struct pt_regs; #else /* __i386__ */ diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index 977f1761a25d..ab05d73e2bb7 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -29,4 +29,11 @@ static inline void pci_swiotlb_late_init(void) static inline void dma_mark_clean(void *addr, size_t size) {} +extern void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs); +extern void x86_swiotlb_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + struct dma_attrs *attrs); + #endif /* _ASM_X86_SWIOTLB_H */ diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 3f556c6a0157..2b19caa4081c 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -41,7 +41,6 @@ # define __ARCH_WANT_SYS_OLD_GETRLIMIT # define __ARCH_WANT_SYS_OLD_UNAME # define __ARCH_WANT_SYS_PAUSE -# define __ARCH_WANT_SYS_SGETMASK # define __ARCH_WANT_SYS_SIGNAL # define __ARCH_WANT_SYS_SIGPENDING # define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index d1dc55404ff1..30be253dd283 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -3,63 +3,51 @@ #include <asm/page_types.h> #include <linux/linkage.h> +#include <linux/init.h> -#ifdef __ASSEMBLER__ +#ifndef __ASSEMBLER__ -#define DEFINE_VDSO_IMAGE(symname, filename) \ -__PAGE_ALIGNED_DATA ; \ - .globl symname##_start, symname##_end ; \ - .align PAGE_SIZE ; \ - symname##_start: ; \ - .incbin filename ; \ - symname##_end: ; \ - .align PAGE_SIZE /* extra data here leaks to userspace. */ ; \ - \ -.previous ; \ - \ - .globl symname##_pages ; \ - .bss ; \ - .align 8 ; \ - .type symname##_pages, @object ; \ - symname##_pages: ; \ - .zero (symname##_end - symname##_start + PAGE_SIZE - 1) / PAGE_SIZE * (BITS_PER_LONG / 8) ; \ - .size symname##_pages, .-symname##_pages +#include <linux/mm_types.h> -#else +struct vdso_image { + void *data; + unsigned long size; /* Always a multiple of PAGE_SIZE */ -#define DECLARE_VDSO_IMAGE(symname) \ - extern char symname##_start[], symname##_end[]; \ - extern struct page *symname##_pages[] + /* text_mapping.pages is big enough for data/size page pointers */ + struct vm_special_mapping text_mapping; -#if defined CONFIG_X86_32 || defined CONFIG_COMPAT + unsigned long alt, alt_len; -#include <asm/vdso32.h> + unsigned long sym_end_mapping; /* Total size of the mapping */ -DECLARE_VDSO_IMAGE(vdso32_int80); -#ifdef CONFIG_COMPAT -DECLARE_VDSO_IMAGE(vdso32_syscall); + unsigned long sym_vvar_page; + unsigned long sym_hpet_page; + unsigned long sym_VDSO32_NOTE_MASK; + unsigned long sym___kernel_sigreturn; + unsigned long sym___kernel_rt_sigreturn; + unsigned long sym___kernel_vsyscall; + unsigned long sym_VDSO32_SYSENTER_RETURN; +}; + +#ifdef CONFIG_X86_64 +extern const struct vdso_image vdso_image_64; +#endif + +#ifdef CONFIG_X86_X32 +extern const struct vdso_image vdso_image_x32; #endif -DECLARE_VDSO_IMAGE(vdso32_sysenter); -/* - * Given a pointer to the vDSO image, find the pointer to VDSO32_name - * as that symbol is defined in the vDSO sources or linker script. - */ -#define VDSO32_SYMBOL(base, name) \ -({ \ - extern const char VDSO32_##name[]; \ - (void __user *)(VDSO32_##name + (unsigned long)(base)); \ -}) +#if defined CONFIG_X86_32 || defined CONFIG_COMPAT +extern const struct vdso_image vdso_image_32_int80; +#ifdef CONFIG_COMPAT +extern const struct vdso_image vdso_image_32_syscall; #endif +extern const struct vdso_image vdso_image_32_sysenter; -/* - * These symbols are defined with the addresses in the vsyscall page. - * See vsyscall-sigreturn.S. - */ -extern void __user __kernel_sigreturn; -extern void __user __kernel_rt_sigreturn; +extern const struct vdso_image *selected_vdso32; +#endif -void __init patch_vdso32(void *vdso, size_t len); +extern void __init init_vdso_image(const struct vdso_image *image); #endif /* __ASSEMBLER__ */ diff --git a/arch/x86/include/asm/vdso32.h b/arch/x86/include/asm/vdso32.h deleted file mode 100644 index 7efb7018406e..000000000000 --- a/arch/x86/include/asm/vdso32.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_X86_VDSO32_H -#define _ASM_X86_VDSO32_H - -#define VDSO_BASE_PAGE 0 -#define VDSO_VVAR_PAGE 1 -#define VDSO_HPET_PAGE 2 -#define VDSO_PAGES 3 -#define VDSO_PREV_PAGES 2 -#define VDSO_OFFSET(x) ((x) * PAGE_SIZE) - -#endif diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h index 081d909bc495..5d2b9ad2c6d2 100644 --- a/arch/x86/include/asm/vvar.h +++ b/arch/x86/include/asm/vvar.h @@ -29,31 +29,13 @@ #else -#ifdef BUILD_VDSO32 +extern char __vvar_page; #define DECLARE_VVAR(offset, type, name) \ extern type vvar_ ## name __attribute__((visibility("hidden"))); #define VVAR(name) (vvar_ ## name) -#else - -extern char __vvar_page; - -/* Base address of vvars. This is not ABI. */ -#ifdef CONFIG_X86_64 -#define VVAR_ADDRESS (-10*1024*1024 - 4096) -#else -#define VVAR_ADDRESS (&__vvar_page) -#endif - -#define DECLARE_VVAR(offset, type, name) \ - static type const * const vvaraddr_ ## name = \ - (void *)(VVAR_ADDRESS + (offset)); - -#define VVAR(name) (*vvaraddr_ ## name) -#endif - #define DEFINE_VVAR(type, name) \ type name \ __attribute__((section(".vvar_" #name), aligned(16))) __visible diff --git a/arch/x86/include/uapi/asm/vsyscall.h b/arch/x86/include/uapi/asm/vsyscall.h index 85dc1b3825ab..b97dd6e263d2 100644 --- a/arch/x86/include/uapi/asm/vsyscall.h +++ b/arch/x86/include/uapi/asm/vsyscall.h @@ -7,11 +7,6 @@ enum vsyscall_num { __NR_vgetcpu, }; -#define VSYSCALL_START (-10UL << 20) -#define VSYSCALL_SIZE 1024 -#define VSYSCALL_END (-2UL << 20) -#define VSYSCALL_MAPPED_PAGES 1 -#define VSYSCALL_ADDR(vsyscall_nr) (VSYSCALL_START+VSYSCALL_SIZE*(vsyscall_nr)) - +#define VSYSCALL_ADDR (-10UL << 20) #endif /* _UAPI_ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f4d96000d33a..047f9ff2e36c 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -26,9 +26,11 @@ obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o obj-$(CONFIG_X86_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o +obj-$(CONFIG_X86_64) += mcount_64.o obj-y += syscall_$(BITS).o vsyscall_gtod.o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index b574b295a2f9..8e3842fc8bea 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -512,7 +512,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, struct dma_attrs *attrs) { gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL); - free_pages((unsigned long)vaddr, get_order(size)); + dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); } static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 992060e09897..9d0a9795a0f8 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -206,9 +206,6 @@ int __init arch_early_irq_init(void) count = ARRAY_SIZE(irq_cfgx); node = cpu_to_node(0); - /* Make sure the legacy interrupts are marked in the bitmap */ - irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs); - for (i = 0; i < count; i++) { irq_set_chip_data(i, &cfg[i]); zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node); @@ -281,18 +278,6 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) return cfg; } -static int alloc_irqs_from(unsigned int from, unsigned int count, int node) -{ - return irq_alloc_descs_from(from, count, node); -} - -static void free_irq_at(unsigned int at, struct irq_cfg *cfg) -{ - free_irq_cfg(at, cfg); - irq_free_desc(at); -} - - struct io_apic { unsigned int index; unsigned int unused[3]; @@ -2916,98 +2901,39 @@ static int __init ioapic_init_ops(void) device_initcall(ioapic_init_ops); /* - * Dynamic irq allocate and deallocation + * Dynamic irq allocate and deallocation. Should be replaced by irq domains! */ -unsigned int __create_irqs(unsigned int from, unsigned int count, int node) +int arch_setup_hwirq(unsigned int irq, int node) { - struct irq_cfg **cfg; + struct irq_cfg *cfg; unsigned long flags; - int irq, i; - - if (from < nr_irqs_gsi) - from = nr_irqs_gsi; + int ret; - cfg = kzalloc_node(count * sizeof(cfg[0]), GFP_KERNEL, node); + cfg = alloc_irq_cfg(irq, node); if (!cfg) - return 0; - - irq = alloc_irqs_from(from, count, node); - if (irq < 0) - goto out_cfgs; - - for (i = 0; i < count; i++) { - cfg[i] = alloc_irq_cfg(irq + i, node); - if (!cfg[i]) - goto out_irqs; - } + return -ENOMEM; raw_spin_lock_irqsave(&vector_lock, flags); - for (i = 0; i < count; i++) - if (__assign_irq_vector(irq + i, cfg[i], apic->target_cpus())) - goto out_vecs; - raw_spin_unlock_irqrestore(&vector_lock, flags); - - for (i = 0; i < count; i++) { - irq_set_chip_data(irq + i, cfg[i]); - irq_clear_status_flags(irq + i, IRQ_NOREQUEST); - } - - kfree(cfg); - return irq; - -out_vecs: - for (i--; i >= 0; i--) - __clear_irq_vector(irq + i, cfg[i]); + ret = __assign_irq_vector(irq, cfg, apic->target_cpus()); raw_spin_unlock_irqrestore(&vector_lock, flags); -out_irqs: - for (i = 0; i < count; i++) - free_irq_at(irq + i, cfg[i]); -out_cfgs: - kfree(cfg); - return 0; -} -unsigned int create_irq_nr(unsigned int from, int node) -{ - return __create_irqs(from, 1, node); -} - -int create_irq(void) -{ - int node = cpu_to_node(0); - unsigned int irq_want; - int irq; - - irq_want = nr_irqs_gsi; - irq = create_irq_nr(irq_want, node); - - if (irq == 0) - irq = -1; - - return irq; + if (!ret) + irq_set_chip_data(irq, cfg); + else + free_irq_cfg(irq, cfg); + return ret; } -void destroy_irq(unsigned int irq) +void arch_teardown_hwirq(unsigned int irq) { struct irq_cfg *cfg = irq_get_chip_data(irq); unsigned long flags; - irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE); - free_remapped_irq(irq); - raw_spin_lock_irqsave(&vector_lock, flags); __clear_irq_vector(irq, cfg); raw_spin_unlock_irqrestore(&vector_lock, flags); - free_irq_at(irq, cfg); -} - -void destroy_irqs(unsigned int irq, unsigned int count) -{ - unsigned int i; - - for (i = 0; i < count; i++) - destroy_irq(irq + i); + free_irq_cfg(irq, cfg); } /* @@ -3136,8 +3062,8 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - unsigned int irq, irq_want; struct msi_desc *msidesc; + unsigned int irq; int node, ret; /* Multiple MSI vectors only supported with interrupt remapping */ @@ -3145,28 +3071,25 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 1; node = dev_to_node(&dev->dev); - irq_want = nr_irqs_gsi; + list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = create_irq_nr(irq_want, node); - if (irq == 0) + irq = irq_alloc_hwirq(node); + if (!irq) return -ENOSPC; - irq_want = irq + 1; - ret = setup_msi_irq(dev, msidesc, irq, 0); - if (ret < 0) - goto error; + if (ret < 0) { + irq_free_hwirq(irq); + return ret; + } + } return 0; - -error: - destroy_irq(irq); - return ret; } void native_teardown_msi_irq(unsigned int irq) { - destroy_irq(irq); + irq_free_hwirq(irq); } #ifdef CONFIG_DMAR_TABLE @@ -3420,11 +3343,6 @@ static void __init probe_nr_irqs_gsi(void) printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi); } -int get_nr_irqs_gsi(void) -{ - return nr_irqs_gsi; -} - unsigned int arch_dynirq_lower_bound(unsigned int from) { return from < nr_irqs_gsi ? nr_irqs_gsi : from; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a135239badb7..2cbbf88d8f2c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -20,6 +20,7 @@ #include <asm/processor.h> #include <asm/debugreg.h> #include <asm/sections.h> +#include <asm/vsyscall.h> #include <linux/topology.h> #include <linux/cpumask.h> #include <asm/pgtable.h> @@ -953,6 +954,38 @@ static void vgetcpu_set_mode(void) else vgetcpu_mode = VGETCPU_LSL; } + +/* May not be __init: called during resume */ +static void syscall32_cpu_init(void) +{ + /* Load these always in case some future AMD CPU supports + SYSENTER from compat mode too. */ + wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); + + wrmsrl(MSR_CSTAR, ia32_cstar_target); +} +#endif + +#ifdef CONFIG_X86_32 +void enable_sep_cpu(void) +{ + int cpu = get_cpu(); + struct tss_struct *tss = &per_cpu(init_tss, cpu); + + if (!boot_cpu_has(X86_FEATURE_SEP)) { + put_cpu(); + return; + } + + tss->x86_tss.ss1 = __KERNEL_CS; + tss->x86_tss.sp1 = sizeof(struct tss_struct) + (unsigned long) tss; + wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0); + wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0); + wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) ia32_sysenter_target, 0); + put_cpu(); +} #endif void __init identify_boot_cpu(void) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 6cc800381d14..bb92f38153b2 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -60,8 +60,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define SPINUNIT 100 /* 100ns */ -atomic_t mce_entry; - DEFINE_PER_CPU(unsigned, mce_exception_count); struct mce_bank *mce_banks __read_mostly; @@ -1040,8 +1038,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); char *msg = "Unknown"; - atomic_inc(&mce_entry); - this_cpu_inc(mce_exception_count); if (!cfg->banks) @@ -1171,7 +1167,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) mce_report_event(regs); mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); out: - atomic_dec(&mce_entry); sync_core(); } EXPORT_SYMBOL_GPL(do_machine_check); diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index d35078ea1446..7db54b5d5f86 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -206,23 +206,21 @@ static void __init dtb_apic_setup(void) static void __init x86_flattree_get_config(void) { u32 size, map_len; - struct boot_param_header *dt; + void *dt; if (!initial_dtb) return; - map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), - (u64)sizeof(struct boot_param_header)); + map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128); - dt = early_memremap(initial_dtb, map_len); - size = be32_to_cpu(dt->totalsize); + initial_boot_params = dt = early_memremap(initial_dtb, map_len); + size = of_get_flat_dt_size(); if (map_len < size) { early_iounmap(dt, map_len); - dt = early_memremap(initial_dtb, size); + initial_boot_params = dt = early_memremap(initial_dtb, size); map_len = size; } - initial_boot_params = dt; unflatten_and_copy_device_tree(); early_iounmap(dt, map_len); } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6cda0baeac9d..2e1a6853e00c 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -419,7 +419,7 @@ static size_t __init gen6_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } -static size_t gen8_stolen_size(int num, int slot, int func) +static size_t __init gen8_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; @@ -429,48 +429,73 @@ static size_t gen8_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } +static size_t __init chv_stolen_size(int num, int slot, int func) +{ + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); + gmch_ctrl >>= SNB_GMCH_GMS_SHIFT; + gmch_ctrl &= SNB_GMCH_GMS_MASK; + + /* + * 0x0 to 0x10: 32MB increments starting at 0MB + * 0x11 to 0x16: 4MB increments starting at 8MB + * 0x17 to 0x1d: 4MB increments start at 36MB + */ + if (gmch_ctrl < 0x11) + return gmch_ctrl << 25; + else if (gmch_ctrl < 0x17) + return (gmch_ctrl - 0x11 + 2) << 22; + else + return (gmch_ctrl - 0x17 + 9) << 22; +} struct intel_stolen_funcs { size_t (*size)(int num, int slot, int func); u32 (*base)(int num, int slot, int func, size_t size); }; -static const struct intel_stolen_funcs i830_stolen_funcs = { +static const struct intel_stolen_funcs i830_stolen_funcs __initconst = { .base = i830_stolen_base, .size = i830_stolen_size, }; -static const struct intel_stolen_funcs i845_stolen_funcs = { +static const struct intel_stolen_funcs i845_stolen_funcs __initconst = { .base = i845_stolen_base, .size = i830_stolen_size, }; -static const struct intel_stolen_funcs i85x_stolen_funcs = { +static const struct intel_stolen_funcs i85x_stolen_funcs __initconst = { .base = i85x_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs i865_stolen_funcs = { +static const struct intel_stolen_funcs i865_stolen_funcs __initconst = { .base = i865_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs gen3_stolen_funcs = { +static const struct intel_stolen_funcs gen3_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs gen6_stolen_funcs = { +static const struct intel_stolen_funcs gen6_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen6_stolen_size, }; -static const struct intel_stolen_funcs gen8_stolen_funcs = { +static const struct intel_stolen_funcs gen8_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen8_stolen_size, }; -static struct pci_device_id intel_stolen_ids[] __initdata = { +static const struct intel_stolen_funcs chv_stolen_funcs __initconst = { + .base = intel_stolen_base, + .size = chv_stolen_size, +}; + +static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_I830_IDS(&i830_stolen_funcs), INTEL_I845G_IDS(&i845_stolen_funcs), INTEL_I85X_IDS(&i85x_stolen_funcs), @@ -496,7 +521,8 @@ static struct pci_device_id intel_stolen_ids[] __initdata = { INTEL_HSW_D_IDS(&gen6_stolen_funcs), INTEL_HSW_M_IDS(&gen6_stolen_funcs), INTEL_BDW_M_IDS(&gen8_stolen_funcs), - INTEL_BDW_D_IDS(&gen8_stolen_funcs) + INTEL_BDW_D_IDS(&gen8_stolen_funcs), + INTEL_CHV_IDS(&chv_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index a2a4f4697889..98313ffaae6a 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -527,6 +527,7 @@ syscall_exit: restore_all: TRACE_IRQS_IRET restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS # Warning: PT_OLDSS(%esp) contains the wrong/random values if we # are returning to the kernel. @@ -537,6 +538,7 @@ restore_all_notrace: cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax CFI_REMEMBER_STATE je ldt_ss # returning to user-space with LDT SS +#endif restore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code irq_return: @@ -549,13 +551,9 @@ ENTRY(iret_exc) .previous _ASM_EXTABLE(irq_return,iret_exc) +#ifdef CONFIG_X86_ESPFIX32 CFI_RESTORE_STATE ldt_ss: - larl PT_OLDSS(%esp), %eax - jnz restore_nocheck - testl $0x00400000, %eax # returning to 32bit stack? - jnz restore_nocheck # allright, normal return - #ifdef CONFIG_PARAVIRT /* * The kernel can't run on a non-flat stack if paravirt mode @@ -597,6 +595,7 @@ ldt_ss: lss (%esp), %esp /* switch to espfix segment */ CFI_ADJUST_CFA_OFFSET -8 jmp restore_nocheck +#endif CFI_ENDPROC ENDPROC(system_call) @@ -704,6 +703,7 @@ END(syscall_badsys) * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. */ +#ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ @@ -713,8 +713,10 @@ END(syscall_badsys) pushl_cfi %eax lss (%esp), %esp /* switch to the normal stack segment */ CFI_ADJUST_CFA_OFFSET -8 +#endif .endm .macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax @@ -725,6 +727,7 @@ END(syscall_badsys) /* switch to normal stack */ FIXUP_ESPFIX_STACK 27: +#endif .endm /* @@ -1355,11 +1358,13 @@ END(debug) ENTRY(nmi) RING0_INT_FRAME ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax popl_cfi %eax je nmi_espfix_stack +#endif cmpl $ia32_sysenter_target,(%esp) je nmi_stack_fixup pushl_cfi %eax @@ -1399,6 +1404,7 @@ nmi_debug_stack_check: FIX_STACK 24, nmi_stack_correct, 1 jmp nmi_stack_correct +#ifdef CONFIG_X86_ESPFIX32 nmi_espfix_stack: /* We have a RING0_INT_FRAME here. * @@ -1420,6 +1426,7 @@ nmi_espfix_stack: lss 12+4(%esp), %esp # back to espfix stack CFI_ADJUST_CFA_OFFSET -24 jmp irq_return +#endif CFI_ENDPROC END(nmi) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index be846d2468f7..48a2644a082a 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -53,11 +53,11 @@ #include <asm/page_types.h> #include <asm/irqflags.h> #include <asm/paravirt.h> -#include <asm/ftrace.h> #include <asm/percpu.h> #include <asm/asm.h> #include <asm/context_tracking.h> #include <asm/smap.h> +#include <asm/pgtable_types.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -69,209 +69,6 @@ .code64 .section .entry.text, "ax" -#ifdef CONFIG_FUNCTION_TRACER - -#ifdef CC_USING_FENTRY -# define function_hook __fentry__ -#else -# define function_hook mcount -#endif - -#ifdef CONFIG_DYNAMIC_FTRACE - -ENTRY(function_hook) - retq -END(function_hook) - -/* skip is set if stack has been adjusted */ -.macro ftrace_caller_setup skip=0 - MCOUNT_SAVE_FRAME \skip - - /* Load the ftrace_ops into the 3rd parameter */ - movq function_trace_op(%rip), %rdx - - /* Load ip into the first parameter */ - movq RIP(%rsp), %rdi - subq $MCOUNT_INSN_SIZE, %rdi - /* Load the parent_ip into the second parameter */ -#ifdef CC_USING_FENTRY - movq SS+16(%rsp), %rsi -#else - movq 8(%rbp), %rsi -#endif -.endm - -ENTRY(ftrace_caller) - /* Check if tracing was disabled (quick check) */ - cmpl $0, function_trace_stop - jne ftrace_stub - - ftrace_caller_setup - /* regs go into 4th parameter (but make it NULL) */ - movq $0, %rcx - -GLOBAL(ftrace_call) - call ftrace_stub - - MCOUNT_RESTORE_FRAME -ftrace_return: - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -GLOBAL(ftrace_graph_call) - jmp ftrace_stub -#endif - -GLOBAL(ftrace_stub) - retq -END(ftrace_caller) - -ENTRY(ftrace_regs_caller) - /* Save the current flags before compare (in SS location)*/ - pushfq - - /* Check if tracing was disabled (quick check) */ - cmpl $0, function_trace_stop - jne ftrace_restore_flags - - /* skip=8 to skip flags saved in SS */ - ftrace_caller_setup 8 - - /* Save the rest of pt_regs */ - movq %r15, R15(%rsp) - movq %r14, R14(%rsp) - movq %r13, R13(%rsp) - movq %r12, R12(%rsp) - movq %r11, R11(%rsp) - movq %r10, R10(%rsp) - movq %rbp, RBP(%rsp) - movq %rbx, RBX(%rsp) - /* Copy saved flags */ - movq SS(%rsp), %rcx - movq %rcx, EFLAGS(%rsp) - /* Kernel segments */ - movq $__KERNEL_DS, %rcx - movq %rcx, SS(%rsp) - movq $__KERNEL_CS, %rcx - movq %rcx, CS(%rsp) - /* Stack - skipping return address */ - leaq SS+16(%rsp), %rcx - movq %rcx, RSP(%rsp) - - /* regs go into 4th parameter */ - leaq (%rsp), %rcx - -GLOBAL(ftrace_regs_call) - call ftrace_stub - - /* Copy flags back to SS, to restore them */ - movq EFLAGS(%rsp), %rax - movq %rax, SS(%rsp) - - /* Handlers can change the RIP */ - movq RIP(%rsp), %rax - movq %rax, SS+8(%rsp) - - /* restore the rest of pt_regs */ - movq R15(%rsp), %r15 - movq R14(%rsp), %r14 - movq R13(%rsp), %r13 - movq R12(%rsp), %r12 - movq R10(%rsp), %r10 - movq RBP(%rsp), %rbp - movq RBX(%rsp), %rbx - - /* skip=8 to skip flags saved in SS */ - MCOUNT_RESTORE_FRAME 8 - - /* Restore flags */ - popfq - - jmp ftrace_return -ftrace_restore_flags: - popfq - jmp ftrace_stub - -END(ftrace_regs_caller) - - -#else /* ! CONFIG_DYNAMIC_FTRACE */ - -ENTRY(function_hook) - cmpl $0, function_trace_stop - jne ftrace_stub - - cmpq $ftrace_stub, ftrace_trace_function - jnz trace - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - cmpq $ftrace_stub, ftrace_graph_return - jnz ftrace_graph_caller - - cmpq $ftrace_graph_entry_stub, ftrace_graph_entry - jnz ftrace_graph_caller -#endif - -GLOBAL(ftrace_stub) - retq - -trace: - MCOUNT_SAVE_FRAME - - movq RIP(%rsp), %rdi -#ifdef CC_USING_FENTRY - movq SS+16(%rsp), %rsi -#else - movq 8(%rbp), %rsi -#endif - subq $MCOUNT_INSN_SIZE, %rdi - - call *ftrace_trace_function - - MCOUNT_RESTORE_FRAME - - jmp ftrace_stub -END(function_hook) -#endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_FUNCTION_TRACER */ - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) - MCOUNT_SAVE_FRAME - -#ifdef CC_USING_FENTRY - leaq SS+16(%rsp), %rdi - movq $0, %rdx /* No framepointers needed */ -#else - leaq 8(%rbp), %rdi - movq (%rbp), %rdx -#endif - movq RIP(%rsp), %rsi - subq $MCOUNT_INSN_SIZE, %rsi - - call prepare_ftrace_return - - MCOUNT_RESTORE_FRAME - - retq -END(ftrace_graph_caller) - -GLOBAL(return_to_handler) - subq $24, %rsp - - /* Save the return values */ - movq %rax, (%rsp) - movq %rdx, 8(%rsp) - movq %rbp, %rdi - - call ftrace_return_to_handler - - movq %rax, %rdi - movq 8(%rsp), %rdx - movq (%rsp), %rax - addq $24, %rsp - jmp *%rdi -#endif - #ifndef CONFIG_PREEMPT #define retint_kernel retint_restore_args @@ -1040,8 +837,18 @@ restore_args: RESTORE_ARGS 1,8,1 irq_return: + /* + * Are we returning to a stack segment from the LDT? Note: in + * 64-bit mode SS:RSP on the exception stack is always valid. + */ +#ifdef CONFIG_X86_ESPFIX64 + testb $4,(SS-RIP)(%rsp) + jnz irq_return_ldt +#endif + +irq_return_iret: INTERRUPT_RETURN - _ASM_EXTABLE(irq_return, bad_iret) + _ASM_EXTABLE(irq_return_iret, bad_iret) #ifdef CONFIG_PARAVIRT ENTRY(native_iret) @@ -1049,6 +856,32 @@ ENTRY(native_iret) _ASM_EXTABLE(native_iret, bad_iret) #endif +#ifdef CONFIG_X86_ESPFIX64 +irq_return_ldt: + pushq_cfi %rax + pushq_cfi %rdi + SWAPGS + movq PER_CPU_VAR(espfix_waddr),%rdi + movq %rax,(0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp),%rax /* RIP */ + movq %rax,(1*8)(%rdi) + movq (3*8)(%rsp),%rax /* CS */ + movq %rax,(2*8)(%rdi) + movq (4*8)(%rsp),%rax /* RFLAGS */ + movq %rax,(3*8)(%rdi) + movq (6*8)(%rsp),%rax /* SS */ + movq %rax,(5*8)(%rdi) + movq (5*8)(%rsp),%rax /* RSP */ + movq %rax,(4*8)(%rdi) + andl $0xffff0000,%eax + popq_cfi %rdi + orq PER_CPU_VAR(espfix_stack),%rax + SWAPGS + movq %rax,%rsp + popq_cfi %rax + jmp irq_return_iret +#endif + .section .fixup,"ax" bad_iret: /* @@ -1110,9 +943,45 @@ ENTRY(retint_kernel) call preempt_schedule_irq jmp exit_intr #endif - CFI_ENDPROC END(common_interrupt) + + /* + * If IRET takes a fault on the espfix stack, then we + * end up promoting it to a doublefault. In that case, + * modify the stack to make it look like we just entered + * the #GP handler from user space, similar to bad_iret. + */ +#ifdef CONFIG_X86_ESPFIX64 + ALIGN +__do_double_fault: + XCPT_FRAME 1 RDI+8 + movq RSP(%rdi),%rax /* Trap on the espfix stack? */ + sarq $PGDIR_SHIFT,%rax + cmpl $ESPFIX_PGD_ENTRY,%eax + jne do_double_fault /* No, just deliver the fault */ + cmpl $__KERNEL_CS,CS(%rdi) + jne do_double_fault + movq RIP(%rdi),%rax + cmpq $irq_return_iret,%rax +#ifdef CONFIG_PARAVIRT + je 1f + cmpq $native_iret,%rax +#endif + jne do_double_fault /* This shouldn't happen... */ +1: + movq PER_CPU_VAR(kernel_stack),%rax + subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */ + movq %rax,RSP(%rdi) + movq $0,(%rax) /* Missing (lost) #GP error code */ + movq $general_protection,RIP(%rdi) + retq + CFI_ENDPROC +END(__do_double_fault) +#else +# define __do_double_fault do_double_fault +#endif + /* * End of kprobes section */ @@ -1289,7 +1158,7 @@ idtentry overflow do_overflow has_error_code=0 idtentry bounds do_bounds has_error_code=0 idtentry invalid_op do_invalid_op has_error_code=0 idtentry device_not_available do_device_not_available has_error_code=0 -idtentry double_fault do_double_fault has_error_code=1 paranoid=1 +idtentry double_fault __do_double_fault has_error_code=1 paranoid=1 idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 idtentry invalid_TSS do_invalid_TSS has_error_code=1 idtentry segment_not_present do_segment_not_present has_error_code=1 @@ -1576,7 +1445,7 @@ error_sti: */ error_kernelspace: incl %ebx - leaq irq_return(%rip),%rcx + leaq irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) je error_swapgs movl %ecx,%eax /* zero extend */ diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c new file mode 100644 index 000000000000..6afbb16e9b79 --- /dev/null +++ b/arch/x86/kernel/espfix_64.c @@ -0,0 +1,209 @@ +/* ----------------------------------------------------------------------- * + * + * Copyright 2014 Intel Corporation; author: H. Peter Anvin + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * ----------------------------------------------------------------------- */ + +/* + * The IRET instruction, when returning to a 16-bit segment, only + * restores the bottom 16 bits of the user space stack pointer. This + * causes some 16-bit software to break, but it also leaks kernel state + * to user space. + * + * This works around this by creating percpu "ministacks", each of which + * is mapped 2^16 times 64K apart. When we detect that the return SS is + * on the LDT, we copy the IRET frame to the ministack and use the + * relevant alias to return to userspace. The ministacks are mapped + * readonly, so if the IRET fault we promote #GP to #DF which is an IST + * vector and thus has its own stack; we then do the fixup in the #DF + * handler. + * + * This file sets up the ministacks and the related page tables. The + * actual ministack invocation is in entry_64.S. + */ + +#include <linux/init.h> +#include <linux/init_task.h> +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/gfp.h> +#include <linux/random.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/setup.h> +#include <asm/espfix.h> + +/* + * Note: we only need 6*8 = 48 bytes for the espfix stack, but round + * it up to a cache line to avoid unnecessary sharing. + */ +#define ESPFIX_STACK_SIZE (8*8UL) +#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) + +/* There is address space for how many espfix pages? */ +#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16)) + +#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) +#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS +# error "Need more than one PGD for the ESPFIX hack" +#endif + +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) + +/* This contains the *bottom* address of the espfix stack */ +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +/* Initialization mutex - should this be a spinlock? */ +static DEFINE_MUTEX(espfix_init_mutex); + +/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */ +#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE) +static void *espfix_pages[ESPFIX_MAX_PAGES]; + +static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD] + __aligned(PAGE_SIZE); + +static unsigned int page_random, slot_random; + +/* + * This returns the bottom address of the espfix stack for a specific CPU. + * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case + * we have to account for some amount of padding at the end of each page. + */ +static inline unsigned long espfix_base_addr(unsigned int cpu) +{ + unsigned long page, slot; + unsigned long addr; + + page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random; + slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE; + addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE); + addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16); + addr += ESPFIX_BASE_ADDR; + return addr; +} + +#define PTE_STRIDE (65536/PAGE_SIZE) +#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE) +#define ESPFIX_PMD_CLONES PTRS_PER_PMD +#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES)) + +#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX) + +static void init_espfix_random(void) +{ + unsigned long rand; + + /* + * This is run before the entropy pools are initialized, + * but this is hopefully better than nothing. + */ + if (!arch_get_random_long(&rand)) { + /* The constant is an arbitrary large prime */ + rdtscll(rand); + rand *= 0xc345c6b72fd16123UL; + } + + slot_random = rand % ESPFIX_STACKS_PER_PAGE; + page_random = (rand / ESPFIX_STACKS_PER_PAGE) + & (ESPFIX_PAGE_SPACE - 1); +} + +void __init init_espfix_bsp(void) +{ + pgd_t *pgd_p; + pteval_t ptemask; + + ptemask = __supported_pte_mask; + + /* Install the espfix pud into the kernel page directory */ + pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + + /* Randomize the locations */ + init_espfix_random(); + + /* The rest is the same as for any other processor */ + init_espfix_ap(); +} + +void init_espfix_ap(void) +{ + unsigned int cpu, page; + unsigned long addr; + pud_t pud, *pud_p; + pmd_t pmd, *pmd_p; + pte_t pte, *pte_p; + int n; + void *stack_page; + pteval_t ptemask; + + /* We only have to do this once... */ + if (likely(this_cpu_read(espfix_stack))) + return; /* Already initialized */ + + cpu = smp_processor_id(); + addr = espfix_base_addr(cpu); + page = cpu/ESPFIX_STACKS_PER_PAGE; + + /* Did another CPU already set this up? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (likely(stack_page)) + goto done; + + mutex_lock(&espfix_init_mutex); + + /* Did we race on the lock? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (stack_page) + goto unlock_done; + + ptemask = __supported_pte_mask; + + pud_p = &espfix_pud_page[pud_index(addr)]; + pud = *pud_p; + if (!pud_present(pud)) { + pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); + pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PUD_CLONES; n++) + set_pud(&pud_p[n], pud); + } + + pmd_p = pmd_offset(&pud, addr); + pmd = *pmd_p; + if (!pmd_present(pmd)) { + pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); + pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PMD_CLONES; n++) + set_pmd(&pmd_p[n], pmd); + } + + pte_p = pte_offset_kernel(&pmd, addr); + stack_page = (void *)__get_free_page(GFP_KERNEL); + pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); + paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PTE_CLONES; n++) + set_pte(&pte_p[n*PTE_STRIDE], pte); + + /* Job is done for this CPU and any CPU which shares this page */ + ACCESS_ONCE(espfix_pages[page]) = stack_page; + +unlock_done: + mutex_unlock(&espfix_init_mutex); +done: + this_cpu_write(espfix_stack, addr); + this_cpu_write(espfix_waddr, (unsigned long)stack_page + + (addr & ~PAGE_MASK)); +} diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 52819e816f87..cbc4a91b131e 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -297,16 +297,7 @@ int ftrace_int3_handler(struct pt_regs *regs) static int ftrace_write(unsigned long ip, const char *val, int size) { - /* - * On x86_64, kernel text mappings are mapped read-only with - * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead - * of the kernel text mapping to modify the kernel text. - * - * For 32bit kernels, these mappings are same and we can use - * kernel identity mapping to modify code. - */ - if (within(ip, (unsigned long)_text, (unsigned long)_etext)) - ip = (unsigned long)__va(__pa_symbol(ip)); + ip = text_ip_addr(ip); if (probe_kernel_write((void *)ip, val, size)) return -EPERM; @@ -349,40 +340,14 @@ static int add_brk_on_nop(struct dyn_ftrace *rec) return add_break(rec->ip, old); } -/* - * If the record has the FTRACE_FL_REGS set, that means that it - * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS - * is not not set, then it wants to convert to the normal callback. - */ -static unsigned long get_ftrace_addr(struct dyn_ftrace *rec) -{ - if (rec->flags & FTRACE_FL_REGS) - return (unsigned long)FTRACE_REGS_ADDR; - else - return (unsigned long)FTRACE_ADDR; -} - -/* - * The FTRACE_FL_REGS_EN is set when the record already points to - * a function that saves all the regs. Basically the '_EN' version - * represents the current state of the function. - */ -static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec) -{ - if (rec->flags & FTRACE_FL_REGS_EN) - return (unsigned long)FTRACE_REGS_ADDR; - else - return (unsigned long)FTRACE_ADDR; -} - static int add_breakpoints(struct dyn_ftrace *rec, int enable) { unsigned long ftrace_addr; int ret; - ret = ftrace_test_record(rec, enable); + ftrace_addr = ftrace_get_addr_curr(rec); - ftrace_addr = get_ftrace_addr(rec); + ret = ftrace_test_record(rec, enable); switch (ret) { case FTRACE_UPDATE_IGNORE: @@ -392,10 +357,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) /* converting nop to call */ return add_brk_on_nop(rec); - case FTRACE_UPDATE_MODIFY_CALL_REGS: case FTRACE_UPDATE_MODIFY_CALL: - ftrace_addr = get_ftrace_old_addr(rec); - /* fall through */ case FTRACE_UPDATE_MAKE_NOP: /* converting a call to a nop */ return add_brk_on_call(rec, ftrace_addr); @@ -440,14 +402,14 @@ static int remove_breakpoint(struct dyn_ftrace *rec) * If not, don't touch the breakpoint, we make just create * a disaster. */ - ftrace_addr = get_ftrace_addr(rec); + ftrace_addr = ftrace_get_addr_new(rec); nop = ftrace_call_replace(ip, ftrace_addr); if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) goto update; /* Check both ftrace_addr and ftrace_old_addr */ - ftrace_addr = get_ftrace_old_addr(rec); + ftrace_addr = ftrace_get_addr_curr(rec); nop = ftrace_call_replace(ip, ftrace_addr); if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) @@ -491,13 +453,12 @@ static int add_update(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = get_ftrace_addr(rec); + ftrace_addr = ftrace_get_addr_new(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; - case FTRACE_UPDATE_MODIFY_CALL_REGS: case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ @@ -538,13 +499,12 @@ static int finish_update(struct dyn_ftrace *rec, int enable) ret = ftrace_update_record(rec, enable); - ftrace_addr = get_ftrace_addr(rec); + ftrace_addr = ftrace_get_addr_new(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; - case FTRACE_UPDATE_MODIFY_CALL_REGS: case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ @@ -621,8 +581,8 @@ void ftrace_replace_code(int enable) return; remove_breakpoints: + pr_warn("Failed on %s (%d):\n", report, count); ftrace_bug(ret, rec ? rec->ip : 0); - printk(KERN_WARNING "Failed on %s (%d):\n", report, count); for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); /* diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 068054f4bf20..eda1a865641e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -172,7 +172,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) */ load_ucode_bsp(); - if (console_loglevel == 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) early_printk("Kernel alive\n"); clear_page(init_level4_pgt); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 4177bfbc80b0..319bcb9372fe 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -74,9 +74,6 @@ static inline void hpet_writel(unsigned int d, unsigned int a) static inline void hpet_set_mapping(void) { hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE); -#ifdef CONFIG_X86_64 - __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VVAR_NOCACHE); -#endif } static inline void hpet_clear_mapping(void) @@ -479,7 +476,7 @@ static int hpet_msi_next_event(unsigned long delta, static int hpet_setup_msi_irq(unsigned int irq) { if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) { - destroy_irq(irq); + irq_free_hwirq(irq); return -EINVAL; } return 0; @@ -487,9 +484,8 @@ static int hpet_setup_msi_irq(unsigned int irq) static int hpet_assign_irq(struct hpet_dev *dev) { - unsigned int irq; + unsigned int irq = irq_alloc_hwirq(-1); - irq = create_irq_nr(0, -1); if (!irq) return -EINVAL; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 283a76a9cc40..11ccfb0a63e7 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -17,6 +17,7 @@ #include <asm/idle.h> #include <asm/mce.h> #include <asm/hw_irq.h> +#include <asm/desc.h> #define CREATE_TRACE_POINTS #include <asm/trace/irq_vectors.h> @@ -334,10 +335,17 @@ int check_irq_vectors_for_cpu_disable(void) for_each_online_cpu(cpu) { if (cpu == this_cpu) continue; - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; - vector++) { - if (per_cpu(vector_irq, cpu)[vector] < 0) - count++; + /* + * We scan from FIRST_EXTERNAL_VECTOR to first system + * vector. If the vector is marked in the used vectors + * bitmap or an irq is assigned to it, we don't count + * it as available. + */ + for (vector = FIRST_EXTERNAL_VECTOR; + vector < first_system_vector; vector++) { + if (!test_bit(vector, used_vectors) && + per_cpu(vector_irq, cpu)[vector] < 0) + count++; } } diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index dcbbaa165bde..c37886d759cc 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -20,8 +20,6 @@ #include <asm/mmu_context.h> #include <asm/syscalls.h> -int sysctl_ldt16 = 0; - #ifdef CONFIG_SMP static void flush_ldt(void *current_mm) { @@ -231,16 +229,10 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } } - /* - * On x86-64 we do not support 16-bit segments due to - * IRET leaking the high bits of the kernel stack address. - */ -#ifdef CONFIG_X86_64 - if (!ldt_info.seg_32bit && !sysctl_ldt16) { + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { error = -EINVAL; goto out_unlock; } -#endif fill_ldt(&ldt, &ldt_info); if (oldmode) diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S new file mode 100644 index 000000000000..c050a0153168 --- /dev/null +++ b/arch/x86/kernel/mcount_64.S @@ -0,0 +1,217 @@ +/* + * linux/arch/x86_64/mcount_64.S + * + * Copyright (C) 2014 Steven Rostedt, Red Hat Inc + */ + +#include <linux/linkage.h> +#include <asm/ptrace.h> +#include <asm/ftrace.h> + + + .code64 + .section .entry.text, "ax" + + +#ifdef CONFIG_FUNCTION_TRACER + +#ifdef CC_USING_FENTRY +# define function_hook __fentry__ +#else +# define function_hook mcount +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE + +ENTRY(function_hook) + retq +END(function_hook) + +/* skip is set if stack has been adjusted */ +.macro ftrace_caller_setup skip=0 + MCOUNT_SAVE_FRAME \skip + + /* Load the ftrace_ops into the 3rd parameter */ + movq function_trace_op(%rip), %rdx + + /* Load ip into the first parameter */ + movq RIP(%rsp), %rdi + subq $MCOUNT_INSN_SIZE, %rdi + /* Load the parent_ip into the second parameter */ +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else + movq 8(%rbp), %rsi +#endif +.endm + +ENTRY(ftrace_caller) + /* Check if tracing was disabled (quick check) */ + cmpl $0, function_trace_stop + jne ftrace_stub + + ftrace_caller_setup + /* regs go into 4th parameter (but make it NULL) */ + movq $0, %rcx + +GLOBAL(ftrace_call) + call ftrace_stub + + MCOUNT_RESTORE_FRAME +ftrace_return: + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +GLOBAL(ftrace_graph_call) + jmp ftrace_stub +#endif + +GLOBAL(ftrace_stub) + retq +END(ftrace_caller) + +ENTRY(ftrace_regs_caller) + /* Save the current flags before compare (in SS location)*/ + pushfq + + /* Check if tracing was disabled (quick check) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* skip=8 to skip flags saved in SS */ + ftrace_caller_setup 8 + + /* Save the rest of pt_regs */ + movq %r15, R15(%rsp) + movq %r14, R14(%rsp) + movq %r13, R13(%rsp) + movq %r12, R12(%rsp) + movq %r11, R11(%rsp) + movq %r10, R10(%rsp) + movq %rbp, RBP(%rsp) + movq %rbx, RBX(%rsp) + /* Copy saved flags */ + movq SS(%rsp), %rcx + movq %rcx, EFLAGS(%rsp) + /* Kernel segments */ + movq $__KERNEL_DS, %rcx + movq %rcx, SS(%rsp) + movq $__KERNEL_CS, %rcx + movq %rcx, CS(%rsp) + /* Stack - skipping return address */ + leaq SS+16(%rsp), %rcx + movq %rcx, RSP(%rsp) + + /* regs go into 4th parameter */ + leaq (%rsp), %rcx + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + /* Copy flags back to SS, to restore them */ + movq EFLAGS(%rsp), %rax + movq %rax, SS(%rsp) + + /* Handlers can change the RIP */ + movq RIP(%rsp), %rax + movq %rax, SS+8(%rsp) + + /* restore the rest of pt_regs */ + movq R15(%rsp), %r15 + movq R14(%rsp), %r14 + movq R13(%rsp), %r13 + movq R12(%rsp), %r12 + movq R10(%rsp), %r10 + movq RBP(%rsp), %rbp + movq RBX(%rsp), %rbx + + /* skip=8 to skip flags saved in SS */ + MCOUNT_RESTORE_FRAME 8 + + /* Restore flags */ + popfq + + jmp ftrace_return +ftrace_restore_flags: + popfq + jmp ftrace_stub + +END(ftrace_regs_caller) + + +#else /* ! CONFIG_DYNAMIC_FTRACE */ + +ENTRY(function_hook) + cmpl $0, function_trace_stop + jne ftrace_stub + + cmpq $ftrace_stub, ftrace_trace_function + jnz trace + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + cmpq $ftrace_stub, ftrace_graph_return + jnz ftrace_graph_caller + + cmpq $ftrace_graph_entry_stub, ftrace_graph_entry + jnz ftrace_graph_caller +#endif + +GLOBAL(ftrace_stub) + retq + +trace: + MCOUNT_SAVE_FRAME + + movq RIP(%rsp), %rdi +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else + movq 8(%rbp), %rsi +#endif + subq $MCOUNT_INSN_SIZE, %rdi + + call *ftrace_trace_function + + MCOUNT_RESTORE_FRAME + + jmp ftrace_stub +END(function_hook) +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + MCOUNT_SAVE_FRAME + +#ifdef CC_USING_FENTRY + leaq SS+16(%rsp), %rdi + movq $0, %rdx /* No framepointers needed */ +#else + leaq 8(%rbp), %rdi + movq (%rbp), %rdx +#endif + movq RIP(%rsp), %rsi + subq $MCOUNT_INSN_SIZE, %rsi + + call prepare_ftrace_return + + MCOUNT_RESTORE_FRAME + + retq +END(ftrace_graph_caller) + +GLOBAL(return_to_handler) + subq $24, %rsp + + /* Save the return values */ + movq %rax, (%rsp) + movq %rdx, 8(%rsp) + movq %rbp, %rdi + + call ftrace_return_to_handler + + movq %rax, %rdi + movq 8(%rsp), %rdx + movq (%rsp), %rax + addq $24, %rsp + jmp *%rdi +#endif diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index f7d0672481fd..a25e202bb319 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -97,12 +97,17 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_mask = dma_alloc_coherent_mask(dev, flag); - flag |= __GFP_ZERO; + flag &= ~__GFP_ZERO; again: page = NULL; /* CMA can be used only in the context which permits sleeping */ - if (flag & __GFP_WAIT) + if (flag & __GFP_WAIT) { page = dma_alloc_from_contiguous(dev, count, get_order(size)); + if (page && page_to_phys(page) + size > dma_mask) { + dma_release_from_contiguous(dev, page, count); + page = NULL; + } + } /* fallback */ if (!page) page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); @@ -120,7 +125,7 @@ again: return NULL; } - + memset(page_address(page), 0, size); *dma_addr = addr; return page_address(page); } diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 6c483ba98b9c..77dd0ad58be4 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -14,7 +14,7 @@ #include <asm/iommu_table.h> int swiotlb __read_mostly; -static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, +void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags, struct dma_attrs *attrs) { @@ -28,11 +28,14 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); } -static void x86_swiotlb_free_coherent(struct device *dev, size_t size, +void x86_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, struct dma_attrs *attrs) { - swiotlb_free_coherent(dev, size, vaddr, dma_addr); + if (is_swiotlb_buffer(dma_to_phys(dev, dma_addr))) + swiotlb_free_coherent(dev, size, vaddr, dma_addr); + else + dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); } static struct dma_map_ops swiotlb_dma_ops = { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 09c76d265550..78a0e6298922 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1119,7 +1119,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); memblock_set_current_limit(get_max_mapped()); - dma_contiguous_reserve(0); + dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); /* * NOTE: On x86-32, only from this point on, fixmaps are ready for use. diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 9e5de6813e1f..a0da58db43a8 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -298,7 +298,8 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, } if (current->mm->context.vdso) - restorer = VDSO32_SYMBOL(current->mm->context.vdso, sigreturn); + restorer = current->mm->context.vdso + + selected_vdso32->sym___kernel_sigreturn; else restorer = &frame->retcode; if (ksig->ka.sa.sa_flags & SA_RESTORER) @@ -361,7 +362,8 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. */ - restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); + restorer = current->mm->context.vdso + + selected_vdso32->sym___kernel_sigreturn; if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; put_user_ex(restorer, &frame->pretcode); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 34826934d4a7..5492798930ef 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -244,6 +244,13 @@ static void notrace start_secondary(void *unused) check_tsc_sync_target(); /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(); +#endif + + /* * We need to hold vector_lock so there the set of online cpus * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. @@ -859,9 +866,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) /* was set by cpu_init() */ cpumask_clear_cpu(cpu, cpu_initialized_mask); - - set_cpu_present(cpu, false); - per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; } /* mark "stuck" area as not stuck */ @@ -921,7 +925,7 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) err = do_boot_cpu(apicid, cpu, tidle); if (err) { - pr_debug("do_boot_cpu failed %d\n", err); + pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); return -EIO; } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 8b3b3eb3cead..ea5b5709aa76 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -91,7 +91,7 @@ static int addr_to_vsyscall_nr(unsigned long addr) { int nr; - if ((addr & ~0xC00UL) != VSYSCALL_START) + if ((addr & ~0xC00UL) != VSYSCALL_ADDR) return -EINVAL; nr = (addr & 0xC00UL) >> 10; @@ -330,24 +330,17 @@ void __init map_vsyscall(void) { extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); - unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page); - __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall, + __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, vsyscall_mode == NATIVE ? PAGE_KERNEL_VSYSCALL : PAGE_KERNEL_VVAR); - BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) != - (unsigned long)VSYSCALL_START); - - __set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR); - BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) != - (unsigned long)VVAR_ADDRESS); + BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != + (unsigned long)VSYSCALL_ADDR); } static int __init vsyscall_init(void) { - BUG_ON(VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE)); - cpu_notifier_register_begin(); on_each_cpu(cpu_vsyscall_init, NULL, 1); diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 20621d753d5f..167ffcac16ed 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -30,12 +30,14 @@ struct pg_state { unsigned long start_address; unsigned long current_address; const struct addr_marker *marker; + unsigned long lines; bool to_dmesg; }; struct addr_marker { unsigned long start_address; const char *name; + unsigned long max_lines; }; /* indices for address_markers; keep sync'd w/ address_markers below */ @@ -46,6 +48,7 @@ enum address_markers_idx { LOW_KERNEL_NR, VMALLOC_START_NR, VMEMMAP_START_NR, + ESPFIX_START_NR, HIGH_KERNEL_NR, MODULES_VADDR_NR, MODULES_END_NR, @@ -68,6 +71,7 @@ static struct addr_marker address_markers[] = { { PAGE_OFFSET, "Low Kernel Mapping" }, { VMALLOC_START, "vmalloc() Area" }, { VMEMMAP_START, "Vmemmap" }, + { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, { __START_KERNEL_map, "High Kernel Mapping" }, { MODULES_VADDR, "Modules" }, { MODULES_END, "End Modules" }, @@ -182,7 +186,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, pgprot_t new_prot, int level) { pgprotval_t prot, cur; - static const char units[] = "KMGTPE"; + static const char units[] = "BKMGTPE"; /* * If we have a "break" in the series, we need to flush the state that @@ -197,6 +201,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->current_prot = new_prot; st->level = level; st->marker = address_markers; + st->lines = 0; pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", st->marker->name); } else if (prot != cur || level != st->level || @@ -208,17 +213,24 @@ static void note_page(struct seq_file *m, struct pg_state *st, /* * Now print the actual finished series */ - pt_dump_seq_printf(m, st->to_dmesg, "0x%0*lx-0x%0*lx ", - width, st->start_address, - width, st->current_address); - - delta = (st->current_address - st->start_address) >> 10; - while (!(delta & 1023) && unit[1]) { - delta >>= 10; - unit++; + if (!st->marker->max_lines || + st->lines < st->marker->max_lines) { + pt_dump_seq_printf(m, st->to_dmesg, + "0x%0*lx-0x%0*lx ", + width, st->start_address, + width, st->current_address); + + delta = st->current_address - st->start_address; + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ", + delta, *unit); + printk_prot(m, st->current_prot, st->level, + st->to_dmesg); } - pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ", delta, *unit); - printk_prot(m, st->current_prot, st->level, st->to_dmesg); + st->lines++; /* * We print markers for special areas of address space, @@ -226,7 +238,17 @@ static void note_page(struct seq_file *m, struct pg_state *st, * This helps in the interpretation. */ if (st->current_address >= st->marker[1].start_address) { + if (st->marker->max_lines && + st->lines > st->marker->max_lines) { + unsigned long nskip = + st->lines - st->marker->max_lines; + pt_dump_seq_printf(m, st->to_dmesg, + "... %lu entr%s skipped ... \n", + nskip, + nskip == 1 ? "y" : "ies"); + } st->marker++; + st->lines = 0; pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", st->marker->name); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8e5722992677..858b47b5221b 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -18,7 +18,8 @@ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/pgalloc.h> /* pgd_*(), ... */ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ -#include <asm/fixmap.h> /* VSYSCALL_START */ +#include <asm/fixmap.h> /* VSYSCALL_ADDR */ +#include <asm/vsyscall.h> /* emulate_vsyscall */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -771,7 +772,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, * emulation. */ if (unlikely((error_code & PF_INSTR) && - ((address & ~0xfff) == VSYSCALL_START))) { + ((address & ~0xfff) == VSYSCALL_ADDR))) { if (emulate_vsyscall(regs, address)) return; } diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8c9f647ff9e1..8b977ebf9388 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { return NULL; } - -int pmd_huge_support(void) -{ - return 0; -} #else struct page * @@ -80,11 +75,6 @@ int pud_huge(pud_t pud) { return !!(pud_val(pud) & _PAGE_PSE); } - -int pmd_huge_support(void) -{ - return 1; -} #endif #ifdef CONFIG_HUGETLB_PAGE diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f35c66c5959a..df1a9927ad29 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1055,8 +1055,8 @@ void __init mem_init(void) after_bootmem = 1; /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, - VSYSCALL_END - VSYSCALL_START, KCORE_OTHER); + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, + PAGE_SIZE, KCORE_OTHER); mem_init_print_info(NULL); } @@ -1185,11 +1185,19 @@ int kern_addr_valid(unsigned long addr) * covers the 64bit vsyscall page now. 32bit has a real VMA now and does * not need special handling anymore: */ +static const char *gate_vma_name(struct vm_area_struct *vma) +{ + return "[vsyscall]"; +} +static struct vm_operations_struct gate_vma_ops = { + .name = gate_vma_name, +}; static struct vm_area_struct gate_vma = { - .vm_start = VSYSCALL_START, - .vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE), + .vm_start = VSYSCALL_ADDR, + .vm_end = VSYSCALL_ADDR + PAGE_SIZE, .vm_page_prot = PAGE_READONLY_EXEC, - .vm_flags = VM_READ | VM_EXEC + .vm_flags = VM_READ | VM_EXEC, + .vm_ops = &gate_vma_ops, }; struct vm_area_struct *get_gate_vma(struct mm_struct *mm) @@ -1218,29 +1226,46 @@ int in_gate_area(struct mm_struct *mm, unsigned long addr) */ int in_gate_area_no_mm(unsigned long addr) { - return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END); + return (addr & PAGE_MASK) == VSYSCALL_ADDR; } -const char *arch_vma_name(struct vm_area_struct *vma) +static unsigned long probe_memory_block_size(void) { - if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) - return "[vdso]"; - if (vma == &gate_vma) - return "[vsyscall]"; - return NULL; -} + /* start from 2g */ + unsigned long bz = 1UL<<31; #ifdef CONFIG_X86_UV -unsigned long memory_block_size_bytes(void) -{ if (is_uv_system()) { printk(KERN_INFO "UV: memory block size 2GB\n"); return 2UL * 1024 * 1024 * 1024; } - return MIN_MEMORY_BLOCK_SIZE; -} #endif + /* less than 64g installed */ + if ((max_pfn << PAGE_SHIFT) < (16UL << 32)) + return MIN_MEMORY_BLOCK_SIZE; + + /* get the tail size */ + while (bz > MIN_MEMORY_BLOCK_SIZE) { + if (!((max_pfn << PAGE_SHIFT) & (bz - 1))) + break; + bz >>= 1; + } + + printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20); + + return bz; +} + +static unsigned long memory_block_size_probed; +unsigned long memory_block_size_bytes(void) +{ + if (!memory_block_size_probed) + memory_block_size_probed = probe_memory_block_size(); + + return memory_block_size_probed; +} + #ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Initialise the sparsemem vmemmap using huge-pages at the PMD level. diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index bc7527e109c8..baff1da354e0 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -367,6 +367,12 @@ void __init early_ioremap_init(void) { pmd_t *pmd; +#ifdef CONFIG_X86_64 + BUILD_BUG_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1)); +#else + WARN_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1)); +#endif + early_ioremap_setup(); pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 1d045f9c390f..a32b706c401a 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -559,7 +559,7 @@ static void __init numa_clear_kernel_node_hotplug(void) int i, nid; nodemask_t numa_kernel_nodes = NODE_MASK_NONE; unsigned long start, end; - struct memblock_type *type = &memblock.reserved; + struct memblock_region *r; /* * At this time, all memory regions reserved by memblock are @@ -573,8 +573,8 @@ static void __init numa_clear_kernel_node_hotplug(void) } /* Mark all kernel nodes. */ - for (i = 0; i < type->cnt; i++) - node_set(type->regions[i].nid, numa_kernel_nodes); + for_each_memblock(reserved, r) + node_set(r->nid, numa_kernel_nodes); /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ for (i = 0; i < numa_meminfo.nr_blks; i++) { diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 461bc8289024..6629f397b467 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -35,7 +35,7 @@ enum { static int pte_testbit(pte_t pte) { - return pte_flags(pte) & _PAGE_UNUSED1; + return pte_flags(pte) & _PAGE_SOFTW1; } struct split_state { diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 0004ac72dbdd..6fb6927f9e76 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -456,9 +456,9 @@ void __init reserve_top_address(unsigned long reserve) { #ifdef CONFIG_X86_32 BUG_ON(fixmaps_set > 0); - printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", - (int)-reserve); - __FIXADDR_TOP = -reserve - PAGE_SIZE; + __FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE; + printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n", + -reserve, __FIXADDR_TOP + PAGE_SIZE); #endif } diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 9d8a509c9730..5ceda85b8687 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -173,9 +173,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev, { void *vaddr; - vaddr = dma_generic_alloc_coherent(dev, size, dma_handle, flags, attrs); - if (!vaddr) - vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, flags); + vaddr = x86_swiotlb_alloc_coherent(dev, size, dma_handle, flags, attrs); *dma_handle = p2a(*dma_handle, to_pci_dev(dev)); return vaddr; } @@ -183,7 +181,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev, /* We have our own dma_ops: the same as swiotlb but from alloc (above) */ static struct dma_map_ops sta2x11_dma_ops = { .alloc = sta2x11_swiotlb_alloc_coherent, - .free = swiotlb_free_coherent, + .free = x86_swiotlb_free_coherent, .map_page = swiotlb_map_page, .unmap_page = swiotlb_unmap_page, .map_sg = swiotlb_map_sg_attrs, diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 3781dd39e8bd..87fc96bcc13c 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -110,7 +110,7 @@ static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) efi_status_t status; spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt2(get_time, tm, tc); + status = efi_call_virt(get_time, tm, tc); spin_unlock_irqrestore(&rtc_lock, flags); return status; } @@ -121,7 +121,7 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm) efi_status_t status; spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt1(set_time, tm); + status = efi_call_virt(set_time, tm); spin_unlock_irqrestore(&rtc_lock, flags); return status; } @@ -134,8 +134,7 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled, efi_status_t status; spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt3(get_wakeup_time, - enabled, pending, tm); + status = efi_call_virt(get_wakeup_time, enabled, pending, tm); spin_unlock_irqrestore(&rtc_lock, flags); return status; } @@ -146,8 +145,7 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) efi_status_t status; spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt2(set_wakeup_time, - enabled, tm); + status = efi_call_virt(set_wakeup_time, enabled, tm); spin_unlock_irqrestore(&rtc_lock, flags); return status; } @@ -158,17 +156,17 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name, unsigned long *data_size, void *data) { - return efi_call_virt5(get_variable, - name, vendor, attr, - data_size, data); + return efi_call_virt(get_variable, + name, vendor, attr, + data_size, data); } static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { - return efi_call_virt3(get_next_variable, - name_size, name, vendor); + return efi_call_virt(get_next_variable, + name_size, name, vendor); } static efi_status_t virt_efi_set_variable(efi_char16_t *name, @@ -177,9 +175,9 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, unsigned long data_size, void *data) { - return efi_call_virt5(set_variable, - name, vendor, attr, - data_size, data); + return efi_call_virt(set_variable, + name, vendor, attr, + data_size, data); } static efi_status_t virt_efi_query_variable_info(u32 attr, @@ -190,13 +188,13 @@ static efi_status_t virt_efi_query_variable_info(u32 attr, if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) return EFI_UNSUPPORTED; - return efi_call_virt4(query_variable_info, attr, storage_space, - remaining_space, max_variable_size); + return efi_call_virt(query_variable_info, attr, storage_space, + remaining_space, max_variable_size); } static efi_status_t virt_efi_get_next_high_mono_count(u32 *count) { - return efi_call_virt1(get_next_high_mono_count, count); + return efi_call_virt(get_next_high_mono_count, count); } static void virt_efi_reset_system(int reset_type, @@ -204,8 +202,8 @@ static void virt_efi_reset_system(int reset_type, unsigned long data_size, efi_char16_t *data) { - efi_call_virt4(reset_system, reset_type, status, - data_size, data); + __efi_call_virt(reset_system, reset_type, status, + data_size, data); } static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules, @@ -215,7 +213,7 @@ static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules, if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) return EFI_UNSUPPORTED; - return efi_call_virt3(update_capsule, capsules, count, sg_list); + return efi_call_virt(update_capsule, capsules, count, sg_list); } static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules, @@ -226,8 +224,8 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules, if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) return EFI_UNSUPPORTED; - return efi_call_virt4(query_capsule_caps, capsules, count, max_size, - reset_type); + return efi_call_virt(query_capsule_caps, capsules, count, max_size, + reset_type); } static efi_status_t __init phys_efi_set_virtual_address_map( @@ -239,9 +237,9 @@ static efi_status_t __init phys_efi_set_virtual_address_map( efi_status_t status; efi_call_phys_prelog(); - status = efi_call_phys4(efi_phys.set_virtual_address_map, - memory_map_size, descriptor_size, - descriptor_version, virtual_map); + status = efi_call_phys(efi_phys.set_virtual_address_map, + memory_map_size, descriptor_size, + descriptor_version, virtual_map); efi_call_phys_epilog(); return status; } @@ -919,6 +917,9 @@ static void __init save_runtime_map(void) void *tmp, *p, *q = NULL; int count = 0; + if (efi_enabled(EFI_OLD_MEMMAP)) + return; + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index e0984ef0374b..5fcda7272550 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -73,84 +73,7 @@ 2: .endm -ENTRY(efi_call0) - SAVE_XMM - subq $32, %rsp - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $32, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call0) - -ENTRY(efi_call1) - SAVE_XMM - subq $32, %rsp - mov %rsi, %rcx - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $32, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call1) - -ENTRY(efi_call2) - SAVE_XMM - subq $32, %rsp - mov %rsi, %rcx - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $32, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call2) - -ENTRY(efi_call3) - SAVE_XMM - subq $32, %rsp - mov %rcx, %r8 - mov %rsi, %rcx - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $32, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call3) - -ENTRY(efi_call4) - SAVE_XMM - subq $32, %rsp - mov %r8, %r9 - mov %rcx, %r8 - mov %rsi, %rcx - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $32, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call4) - -ENTRY(efi_call5) - SAVE_XMM - subq $48, %rsp - mov %r9, 32(%rsp) - mov %r8, %r9 - mov %rcx, %r8 - mov %rsi, %rcx - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $48, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call5) - -ENTRY(efi_call6) +ENTRY(efi_call) SAVE_XMM mov (%rsp), %rax mov 8(%rax), %rax @@ -166,7 +89,7 @@ ENTRY(efi_call6) addq $48, %rsp RESTORE_XMM ret -ENDPROC(efi_call6) +ENDPROC(efi_call) #ifdef CONFIG_EFI_MIXED diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile index 097e7a7940d8..af9307f2cc28 100644 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ b/arch/x86/platform/intel-mid/device_libs/Makefile @@ -20,3 +20,4 @@ obj-$(subst m,y,$(CONFIG_DRM_MEDFIELD)) += platform_tc35876x.o obj-$(subst m,y,$(CONFIG_SERIAL_MRST_MAX3110)) += platform_max3111.o # MISC Devices obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o +obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_wdt.o diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c new file mode 100644 index 000000000000..973cf3bfa9fd --- /dev/null +++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c @@ -0,0 +1,72 @@ +/* + * platform_wdt.c: Watchdog platform library file + * + * (C) Copyright 2014 Intel Corporation + * Author: David Cohen <david.a.cohen@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/platform_device.h> +#include <linux/platform_data/intel-mid_wdt.h> +#include <asm/intel-mid.h> +#include <asm/io_apic.h> + +#define TANGIER_EXT_TIMER0_MSI 15 + +static struct platform_device wdt_dev = { + .name = "intel_mid_wdt", + .id = -1, +}; + +static int tangier_probe(struct platform_device *pdev) +{ + int ioapic; + int irq; + struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data; + struct io_apic_irq_attr irq_attr = { 0 }; + + if (!pdata) + return -EINVAL; + + irq = pdata->irq; + ioapic = mp_find_ioapic(irq); + if (ioapic >= 0) { + int ret; + irq_attr.ioapic = ioapic; + irq_attr.ioapic_pin = irq; + irq_attr.trigger = 1; + /* irq_attr.polarity = 0; -> Active high */ + ret = io_apic_set_pci_routing(NULL, irq, &irq_attr); + if (ret) + return ret; + } else { + dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n", + irq); + return -EINVAL; + } + + return 0; +} + +static struct intel_mid_wdt_pdata tangier_pdata = { + .irq = TANGIER_EXT_TIMER0_MSI, + .probe = tangier_probe, +}; + +static int __init register_mid_wdt(void) +{ + if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) { + wdt_dev.dev.platform_data = &tangier_pdata; + return platform_device_register(&wdt_dev); + } + + return -ENODEV; +} + +rootfs_initcall(register_mid_wdt); diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 766612137a62..1584cbed0dce 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -39,7 +39,7 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5) */ return BIOS_STATUS_UNIMPLEMENTED; - ret = efi_call6((void *)__va(tab->function), (u64)which, + ret = efi_call((void *)__va(tab->function), (u64)which, a1, a2, a3, a4, a5); return ret; } diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index acf7752da952..b233681af4de 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -238,11 +238,9 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, unsigned long mmr_offset, int limit) { - int irq, ret; + int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade)); - irq = create_irq_nr(NR_IRQS_LEGACY, uv_blade_to_memory_nid(mmr_blade)); - - if (irq <= 0) + if (!irq) return -EBUSY; ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset, @@ -250,7 +248,7 @@ int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, if (ret == irq) uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade); else - destroy_irq(irq); + irq_free_hwirq(irq); return ret; } @@ -285,6 +283,6 @@ void uv_teardown_irq(unsigned int irq) n = n->rb_right; } spin_unlock_irqrestore(&uv_irq_lock, irqflags); - destroy_irq(irq); + irq_free_hwirq(irq); } EXPORT_SYMBOL_GPL(uv_teardown_irq); diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index be27da60dc8f..c89c93320c12 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -85,7 +85,7 @@ static cpumask_var_t uv_nmi_cpu_mask; * Default is all stack dumps go to the console and buffer. * Lower level to send to log buffer only. */ -static int uv_nmi_loglevel = 7; +static int uv_nmi_loglevel = CONSOLE_LOGLEVEL_DEFAULT; module_param_named(dump_loglevel, uv_nmi_loglevel, int, 0644); /* diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 04376ac3d9ef..ec255a1646d2 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -212,10 +212,10 @@ 203 common sched_setaffinity sys_sched_setaffinity 204 common sched_getaffinity sys_sched_getaffinity 205 64 set_thread_area -206 common io_setup sys_io_setup +206 64 io_setup sys_io_setup 207 common io_destroy sys_io_destroy 208 common io_getevents sys_io_getevents -209 common io_submit sys_io_submit +209 64 io_submit sys_io_submit 210 common io_cancel sys_io_cancel 211 64 get_thread_area 212 common lookup_dcookie sys_lookup_dcookie @@ -359,3 +359,5 @@ 540 x32 process_vm_writev compat_sys_process_vm_writev 541 x32 setsockopt compat_sys_setsockopt 542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index af91901babb8..916cda4cd5b4 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -12,7 +12,7 @@ #include <asm/page.h> #include <linux/init.h> -unsigned int __read_mostly vdso_enabled = 1; +static unsigned int __read_mostly vdso_enabled = 1; unsigned long um_vdso_addr; extern unsigned long task_size; diff --git a/arch/x86/vdso/.gitignore b/arch/x86/vdso/.gitignore index 3282874bc61d..aae8ffdd5880 100644 --- a/arch/x86/vdso/.gitignore +++ b/arch/x86/vdso/.gitignore @@ -1,8 +1,7 @@ vdso.lds -vdso-syms.lds vdsox32.lds -vdsox32-syms.lds -vdso32-syms.lds vdso32-syscall-syms.lds vdso32-sysenter-syms.lds vdso32-int80-syms.lds +vdso-image-*.c +vdso2c diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index c580d1210ffe..9769df094035 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -24,15 +24,30 @@ vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y)) # files to link into kernel obj-y += vma.o -obj-$(VDSO64-y) += vdso.o -obj-$(VDSOX32-y) += vdsox32.o -obj-$(VDSO32-y) += vdso32.o vdso32-setup.o + +# vDSO images to build +vdso_img-$(VDSO64-y) += 64 +vdso_img-$(VDSOX32-y) += x32 +vdso_img-$(VDSO32-y) += 32-int80 +vdso_img-$(CONFIG_COMPAT) += 32-syscall +vdso_img-$(VDSO32-y) += 32-sysenter + +obj-$(VDSO32-y) += vdso32-setup.o vobjs := $(foreach F,$(vobj64s),$(obj)/$F) $(obj)/vdso.o: $(obj)/vdso.so -targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y) +targets += vdso.lds $(vobjs-y) + +# Build the vDSO image C files and link them in. +vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o) +vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c) +vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg) +obj-y += $(vdso_img_objs) +targets += $(vdso_img_cfiles) +targets += $(vdso_img_sodbg) +.SECONDARY: $(vdso_img-y:%=$(obj)/vdso-image-%.c) export CPPFLAGS_vdso.lds += -P -C @@ -41,14 +56,19 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \ $(DISABLE_LTO) -$(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so - -$(obj)/vdso.so.dbg: $(src)/vdso.lds $(vobjs) FORCE +$(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso) -$(obj)/%.so: OBJCOPYFLAGS := -S -$(obj)/%.so: $(obj)/%.so.dbg FORCE - $(call if_changed,objcopy) +HOST_EXTRACFLAGS += -I$(srctree)/tools/include +hostprogs-y += vdso2c + +quiet_cmd_vdso2c = VDSO2C $@ +define cmd_vdso2c + $(obj)/vdso2c $< $@ +endef + +$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso2c FORCE + $(call if_changed,vdso2c) # # Don't omit frame pointers for ease of userspace debugging, but do @@ -68,22 +88,6 @@ CFLAGS_REMOVE_vclock_gettime.o = -pg CFLAGS_REMOVE_vgetcpu.o = -pg CFLAGS_REMOVE_vvar.o = -pg -targets += vdso-syms.lds -obj-$(VDSO64-y) += vdso-syms.lds - -# -# Match symbols in the DSO that look like VDSO*; produce a file of constants. -# -sed-vdsosym := -e 's/^00*/0/' \ - -e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p' -quiet_cmd_vdsosym = VDSOSYM $@ -define cmd_vdsosym - $(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ -endef - -$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE - $(call if_changed,vdsosym) - # # X32 processes use x32 vDSO to access 64bit kernel data. # @@ -94,9 +98,6 @@ $(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE # so that it can reach 64bit address space with 64bit pointers. # -targets += vdsox32-syms.lds -obj-$(VDSOX32-y) += vdsox32-syms.lds - CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds) VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \ -Wl,-soname=linux-vdso.so.1 \ @@ -113,9 +114,7 @@ quiet_cmd_x32 = X32 $@ $(obj)/%-x32.o: $(obj)/%.o FORCE $(call if_changed,x32) -targets += vdsox32.so vdsox32.so.dbg vdsox32.lds $(vobjx32s-y) - -$(obj)/vdsox32.o: $(src)/vdsox32.S $(obj)/vdsox32.so +targets += vdsox32.lds $(vobjx32s-y) $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE $(call if_changed,vdso) @@ -123,7 +122,6 @@ $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE # # Build multiple 32-bit vDSO images to choose from at boot time. # -obj-$(VDSO32-y) += vdso32-syms.lds vdso32.so-$(VDSO32-y) += int80 vdso32.so-$(CONFIG_COMPAT) += syscall vdso32.so-$(VDSO32-y) += sysenter @@ -138,10 +136,8 @@ VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1 override obj-dirs = $(dir $(obj)) $(obj)/vdso32/ targets += vdso32/vdso32.lds -targets += $(vdso32-images) $(vdso32-images:=.dbg) targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o) - -extra-y += $(vdso32-images) +targets += vdso32/vclock_gettime.o $(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%) @@ -166,27 +162,6 @@ $(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \ $(obj)/vdso32/%.o $(call if_changed,vdso) -# Make vdso32-*-syms.lds from each image, and then make sure they match. -# The only difference should be that some do not define VDSO32_SYSENTER_RETURN. - -targets += vdso32-syms.lds $(vdso32.so-y:%=vdso32-%-syms.lds) - -quiet_cmd_vdso32sym = VDSOSYM $@ -define cmd_vdso32sym - if LC_ALL=C sort -u $(filter-out FORCE,$^) > $(@D)/.tmp_$(@F) && \ - $(foreach H,$(filter-out FORCE,$^),\ - if grep -q VDSO32_SYSENTER_RETURN $H; \ - then diff -u $(@D)/.tmp_$(@F) $H; \ - else sed /VDSO32_SYSENTER_RETURN/d $(@D)/.tmp_$(@F) | \ - diff -u - $H; fi &&) : ;\ - then mv -f $(@D)/.tmp_$(@F) $@; \ - else rm -f $(@D)/.tmp_$(@F); exit 1; \ - fi -endef - -$(obj)/vdso32-syms.lds: $(vdso32.so-y:%=$(obj)/vdso32-%-syms.lds) FORCE - $(call if_changed,vdso32sym) - # # The DSO images are built using a special linker script. # @@ -197,7 +172,7 @@ quiet_cmd_vdso = VDSO $@ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \ - $(LTO_CFLAGS) + -Wl,-Bsymbolic $(LTO_CFLAGS) GCOV_PROFILE := n # diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 16d686171e9a..b2e4f493e5b0 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -30,9 +30,12 @@ extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); extern time_t __vdso_time(time_t *t); #ifdef CONFIG_HPET_TIMER -static inline u32 read_hpet_counter(const volatile void *addr) +extern u8 hpet_page + __attribute__((visibility("hidden"))); + +static notrace cycle_t vread_hpet(void) { - return *(const volatile u32 *) (addr + HPET_COUNTER); + return *(const volatile u32 *)(&hpet_page + HPET_COUNTER); } #endif @@ -43,11 +46,6 @@ static inline u32 read_hpet_counter(const volatile void *addr) #include <asm/fixmap.h> #include <asm/pvclock.h> -static notrace cycle_t vread_hpet(void) -{ - return read_hpet_counter((const void *)fix_to_virt(VSYSCALL_HPET)); -} - notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; @@ -137,16 +135,6 @@ static notrace cycle_t vread_pvclock(int *mode) #else -extern u8 hpet_page - __attribute__((visibility("hidden"))); - -#ifdef CONFIG_HPET_TIMER -static notrace cycle_t vread_hpet(void) -{ - return read_hpet_counter((const void *)(&hpet_page)); -} -#endif - notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; @@ -154,7 +142,7 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) asm( "mov %%ebx, %%edx \n" "mov %2, %%ebx \n" - "call VDSO32_vsyscall \n" + "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" : "=a" (ret) : "0" (__NR_clock_gettime), "g" (clock), "c" (ts) @@ -169,7 +157,7 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) asm( "mov %%ebx, %%edx \n" "mov %2, %%ebx \n" - "call VDSO32_vsyscall \n" + "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" : "=a" (ret) : "0" (__NR_gettimeofday), "g" (tv), "c" (tz) diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S index 9df017ab2285..2ec72f651ebf 100644 --- a/arch/x86/vdso/vdso-layout.lds.S +++ b/arch/x86/vdso/vdso-layout.lds.S @@ -1,3 +1,5 @@ +#include <asm/vdso.h> + /* * Linker script for vDSO. This is an ELF shared object prelinked to * its virtual address, and with only one read-only segment. @@ -6,20 +8,6 @@ SECTIONS { -#ifdef BUILD_VDSO32 -#include <asm/vdso32.h> - - hpet_page = . - VDSO_OFFSET(VDSO_HPET_PAGE); - - vvar = . - VDSO_OFFSET(VDSO_VVAR_PAGE); - - /* Place all vvars at the offsets in asm/vvar.h. */ -#define EMIT_VVAR(name, offset) vvar_ ## name = vvar + offset; -#define __VVAR_KERNEL_LDS -#include <asm/vvar.h> -#undef __VVAR_KERNEL_LDS -#undef EMIT_VVAR -#endif . = SIZEOF_HEADERS; .hash : { *(.hash) } :text @@ -60,10 +48,30 @@ SECTIONS .text : { *(.text*) } :text =0x90909090, /* - * The comma above works around a bug in gold: - * https://sourceware.org/bugzilla/show_bug.cgi?id=16804 + * The remainder of the vDSO consists of special pages that are + * shared between the kernel and userspace. It needs to be at the + * end so that it doesn't overlap the mapping of the actual + * vDSO image. */ + . = ALIGN(PAGE_SIZE); + vvar_page = .; + + /* Place all vvars at the offsets in asm/vvar.h. */ +#define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset; +#define __VVAR_KERNEL_LDS +#include <asm/vvar.h> +#undef __VVAR_KERNEL_LDS +#undef EMIT_VVAR + + . = vvar_page + PAGE_SIZE; + + hpet_page = .; + . = . + PAGE_SIZE; + + . = ALIGN(PAGE_SIZE); + end_mapping = .; + /DISCARD/ : { *(.discard) *(.discard.*) diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S deleted file mode 100644 index be3f23b09af5..000000000000 --- a/arch/x86/vdso/vdso.S +++ /dev/null @@ -1,3 +0,0 @@ -#include <asm/vdso.h> - -DEFINE_VDSO_IMAGE(vdso, "arch/x86/vdso/vdso.so") diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/vdso/vdso.lds.S index b96b2677cad8..75e3404c83b1 100644 --- a/arch/x86/vdso/vdso.lds.S +++ b/arch/x86/vdso/vdso.lds.S @@ -1,14 +1,11 @@ /* * Linker script for 64-bit vDSO. * We #include the file to define the layout details. - * Here we only choose the prelinked virtual address. * * This file defines the version script giving the user-exported symbols in - * the DSO. We can define local symbols here called VDSO* to make their - * values visible using the asm-x86/vdso.h macros from the kernel proper. + * the DSO. */ -#define VDSO_PRELINK 0xffffffffff700000 #include "vdso-layout.lds.S" /* @@ -28,5 +25,3 @@ VERSION { local: *; }; } - -VDSO64_PRELINK = VDSO_PRELINK; diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/vdso/vdso2c.c new file mode 100644 index 000000000000..450ac6eaf613 --- /dev/null +++ b/arch/x86/vdso/vdso2c.c @@ -0,0 +1,175 @@ +#include <inttypes.h> +#include <stdint.h> +#include <unistd.h> +#include <stdarg.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <fcntl.h> +#include <err.h> + +#include <sys/mman.h> +#include <sys/types.h> + +#include <tools/le_byteshift.h> + +#include <linux/elf.h> +#include <linux/types.h> + +const char *outfilename; + +/* Symbols that we need in vdso2c. */ +enum { + sym_vvar_page, + sym_hpet_page, + sym_end_mapping, +}; + +const int special_pages[] = { + sym_vvar_page, + sym_hpet_page, +}; + +char const * const required_syms[] = { + [sym_vvar_page] = "vvar_page", + [sym_hpet_page] = "hpet_page", + [sym_end_mapping] = "end_mapping", + "VDSO32_NOTE_MASK", + "VDSO32_SYSENTER_RETURN", + "__kernel_vsyscall", + "__kernel_sigreturn", + "__kernel_rt_sigreturn", +}; + +__attribute__((format(printf, 1, 2))) __attribute__((noreturn)) +static void fail(const char *format, ...) +{ + va_list ap; + va_start(ap, format); + fprintf(stderr, "Error: "); + vfprintf(stderr, format, ap); + unlink(outfilename); + exit(1); + va_end(ap); +} + +/* + * Evil macros to do a little-endian read. + */ +#define GLE(x, bits, ifnot) \ + __builtin_choose_expr( \ + (sizeof(*(x)) == bits/8), \ + (__typeof__(*(x)))get_unaligned_le##bits(x), ifnot) + +extern void bad_get_le(void); +#define LAST_LE(x) \ + __builtin_choose_expr(sizeof(*(x)) == 1, *(x), bad_get_le()) + +#define GET_LE(x) \ + GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_LE(x)))) + +#define NSYMS (sizeof(required_syms) / sizeof(required_syms[0])) + +#define BITS 64 +#define GOFUNC go64 +#define Elf_Ehdr Elf64_Ehdr +#define Elf_Shdr Elf64_Shdr +#define Elf_Phdr Elf64_Phdr +#define Elf_Sym Elf64_Sym +#define Elf_Dyn Elf64_Dyn +#include "vdso2c.h" +#undef BITS +#undef GOFUNC +#undef Elf_Ehdr +#undef Elf_Shdr +#undef Elf_Phdr +#undef Elf_Sym +#undef Elf_Dyn + +#define BITS 32 +#define GOFUNC go32 +#define Elf_Ehdr Elf32_Ehdr +#define Elf_Shdr Elf32_Shdr +#define Elf_Phdr Elf32_Phdr +#define Elf_Sym Elf32_Sym +#define Elf_Dyn Elf32_Dyn +#include "vdso2c.h" +#undef BITS +#undef GOFUNC +#undef Elf_Ehdr +#undef Elf_Shdr +#undef Elf_Phdr +#undef Elf_Sym +#undef Elf_Dyn + +static void go(void *addr, size_t len, FILE *outfile, const char *name) +{ + Elf64_Ehdr *hdr = (Elf64_Ehdr *)addr; + + if (hdr->e_ident[EI_CLASS] == ELFCLASS64) { + go64(addr, len, outfile, name); + } else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) { + go32(addr, len, outfile, name); + } else { + fail("unknown ELF class\n"); + } +} + +int main(int argc, char **argv) +{ + int fd; + off_t len; + void *addr; + FILE *outfile; + char *name, *tmp; + int namelen; + + if (argc != 3) { + printf("Usage: vdso2c INPUT OUTPUT\n"); + return 1; + } + + /* + * Figure out the struct name. If we're writing to a .so file, + * generate raw output insted. + */ + name = strdup(argv[2]); + namelen = strlen(name); + if (namelen >= 3 && !strcmp(name + namelen - 3, ".so")) { + name = NULL; + } else { + tmp = strrchr(name, '/'); + if (tmp) + name = tmp + 1; + tmp = strchr(name, '.'); + if (tmp) + *tmp = '\0'; + for (tmp = name; *tmp; tmp++) + if (*tmp == '-') + *tmp = '_'; + } + + fd = open(argv[1], O_RDONLY); + if (fd == -1) + err(1, "%s", argv[1]); + + len = lseek(fd, 0, SEEK_END); + if (len == (off_t)-1) + err(1, "lseek"); + + addr = mmap(NULL, len, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + if (addr == MAP_FAILED) + err(1, "mmap"); + + outfilename = argv[2]; + outfile = fopen(outfilename, "w"); + if (!outfile) + err(1, "%s", argv[2]); + + go(addr, (size_t)len, outfile, name); + + munmap(addr, len); + fclose(outfile); + + return 0; +} diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h new file mode 100644 index 000000000000..8a074637a576 --- /dev/null +++ b/arch/x86/vdso/vdso2c.h @@ -0,0 +1,163 @@ +/* + * This file is included twice from vdso2c.c. It generates code for 32-bit + * and 64-bit vDSOs. We need both for 64-bit builds, since 32-bit vDSOs + * are built for 32-bit userspace. + */ + +static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name) +{ + int found_load = 0; + unsigned long load_size = -1; /* Work around bogus warning */ + unsigned long data_size; + Elf_Ehdr *hdr = (Elf_Ehdr *)addr; + int i; + unsigned long j; + Elf_Shdr *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr, + *alt_sec = NULL; + Elf_Dyn *dyn = 0, *dyn_end = 0; + const char *secstrings; + uint64_t syms[NSYMS] = {}; + + Elf_Phdr *pt = (Elf_Phdr *)(addr + GET_LE(&hdr->e_phoff)); + + /* Walk the segment table. */ + for (i = 0; i < GET_LE(&hdr->e_phnum); i++) { + if (GET_LE(&pt[i].p_type) == PT_LOAD) { + if (found_load) + fail("multiple PT_LOAD segs\n"); + + if (GET_LE(&pt[i].p_offset) != 0 || + GET_LE(&pt[i].p_vaddr) != 0) + fail("PT_LOAD in wrong place\n"); + + if (GET_LE(&pt[i].p_memsz) != GET_LE(&pt[i].p_filesz)) + fail("cannot handle memsz != filesz\n"); + + load_size = GET_LE(&pt[i].p_memsz); + found_load = 1; + } else if (GET_LE(&pt[i].p_type) == PT_DYNAMIC) { + dyn = addr + GET_LE(&pt[i].p_offset); + dyn_end = addr + GET_LE(&pt[i].p_offset) + + GET_LE(&pt[i].p_memsz); + } + } + if (!found_load) + fail("no PT_LOAD seg\n"); + data_size = (load_size + 4095) / 4096 * 4096; + + /* Walk the dynamic table */ + for (i = 0; dyn + i < dyn_end && + GET_LE(&dyn[i].d_tag) != DT_NULL; i++) { + typeof(dyn[i].d_tag) tag = GET_LE(&dyn[i].d_tag); + if (tag == DT_REL || tag == DT_RELSZ || + tag == DT_RELENT || tag == DT_TEXTREL) + fail("vdso image contains dynamic relocations\n"); + } + + /* Walk the section table */ + secstrings_hdr = addr + GET_LE(&hdr->e_shoff) + + GET_LE(&hdr->e_shentsize)*GET_LE(&hdr->e_shstrndx); + secstrings = addr + GET_LE(&secstrings_hdr->sh_offset); + for (i = 0; i < GET_LE(&hdr->e_shnum); i++) { + Elf_Shdr *sh = addr + GET_LE(&hdr->e_shoff) + + GET_LE(&hdr->e_shentsize) * i; + if (GET_LE(&sh->sh_type) == SHT_SYMTAB) + symtab_hdr = sh; + + if (!strcmp(secstrings + GET_LE(&sh->sh_name), + ".altinstructions")) + alt_sec = sh; + } + + if (!symtab_hdr) + fail("no symbol table\n"); + + strtab_hdr = addr + GET_LE(&hdr->e_shoff) + + GET_LE(&hdr->e_shentsize) * GET_LE(&symtab_hdr->sh_link); + + /* Walk the symbol table */ + for (i = 0; + i < GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize); + i++) { + int k; + Elf_Sym *sym = addr + GET_LE(&symtab_hdr->sh_offset) + + GET_LE(&symtab_hdr->sh_entsize) * i; + const char *name = addr + GET_LE(&strtab_hdr->sh_offset) + + GET_LE(&sym->st_name); + for (k = 0; k < NSYMS; k++) { + if (!strcmp(name, required_syms[k])) { + if (syms[k]) { + fail("duplicate symbol %s\n", + required_syms[k]); + } + syms[k] = GET_LE(&sym->st_value); + } + } + } + + /* Validate mapping addresses. */ + for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) { + if (!syms[i]) + continue; /* The mapping isn't used; ignore it. */ + + if (syms[i] % 4096) + fail("%s must be a multiple of 4096\n", + required_syms[i]); + if (syms[i] < data_size) + fail("%s must be after the text mapping\n", + required_syms[i]); + if (syms[sym_end_mapping] < syms[i] + 4096) + fail("%s overruns end_mapping\n", required_syms[i]); + } + if (syms[sym_end_mapping] % 4096) + fail("end_mapping must be a multiple of 4096\n"); + + /* Remove sections. */ + hdr->e_shoff = 0; + hdr->e_shentsize = 0; + hdr->e_shnum = 0; + hdr->e_shstrndx = htole16(SHN_UNDEF); + + if (!name) { + fwrite(addr, load_size, 1, outfile); + return; + } + + fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n"); + fprintf(outfile, "#include <linux/linkage.h>\n"); + fprintf(outfile, "#include <asm/page_types.h>\n"); + fprintf(outfile, "#include <asm/vdso.h>\n"); + fprintf(outfile, "\n"); + fprintf(outfile, + "static unsigned char raw_data[%lu] __page_aligned_data = {", + data_size); + for (j = 0; j < load_size; j++) { + if (j % 10 == 0) + fprintf(outfile, "\n\t"); + fprintf(outfile, "0x%02X, ", (int)((unsigned char *)addr)[j]); + } + fprintf(outfile, "\n};\n\n"); + + fprintf(outfile, "static struct page *pages[%lu];\n\n", + data_size / 4096); + + fprintf(outfile, "const struct vdso_image %s = {\n", name); + fprintf(outfile, "\t.data = raw_data,\n"); + fprintf(outfile, "\t.size = %lu,\n", data_size); + fprintf(outfile, "\t.text_mapping = {\n"); + fprintf(outfile, "\t\t.name = \"[vdso]\",\n"); + fprintf(outfile, "\t\t.pages = pages,\n"); + fprintf(outfile, "\t},\n"); + if (alt_sec) { + fprintf(outfile, "\t.alt = %lu,\n", + (unsigned long)GET_LE(&alt_sec->sh_offset)); + fprintf(outfile, "\t.alt_len = %lu,\n", + (unsigned long)GET_LE(&alt_sec->sh_size)); + } + for (i = 0; i < NSYMS; i++) { + if (syms[i]) + fprintf(outfile, "\t.sym_%s = 0x%" PRIx64 ",\n", + required_syms[i], syms[i]); + } + fprintf(outfile, "};\n"); +} diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index e1f220e3ca68..e4f7781ee162 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -8,27 +8,12 @@ #include <linux/init.h> #include <linux/smp.h> -#include <linux/thread_info.h> -#include <linux/sched.h> -#include <linux/gfp.h> -#include <linux/string.h> -#include <linux/elf.h> -#include <linux/mm.h> -#include <linux/err.h> -#include <linux/module.h> -#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/mm_types.h> #include <asm/cpufeature.h> -#include <asm/msr.h> -#include <asm/pgtable.h> -#include <asm/unistd.h> -#include <asm/elf.h> -#include <asm/tlbflush.h> +#include <asm/processor.h> #include <asm/vdso.h> -#include <asm/proto.h> -#include <asm/fixmap.h> -#include <asm/hpet.h> -#include <asm/vvar.h> #ifdef CONFIG_COMPAT_VDSO #define VDSO_DEFAULT 0 @@ -36,23 +21,17 @@ #define VDSO_DEFAULT 1 #endif -#ifdef CONFIG_X86_64 -#define vdso_enabled sysctl_vsyscall32 -#define arch_setup_additional_pages syscall32_setup_pages -extern int sysctl_ldt16; -#endif - /* * Should the kernel map a VDSO page into processes and pass its * address down to glibc upon exec()? */ -unsigned int __read_mostly vdso_enabled = VDSO_DEFAULT; +unsigned int __read_mostly vdso32_enabled = VDSO_DEFAULT; -static int __init vdso_setup(char *s) +static int __init vdso32_setup(char *s) { - vdso_enabled = simple_strtoul(s, NULL, 0); + vdso32_enabled = simple_strtoul(s, NULL, 0); - if (vdso_enabled > 1) + if (vdso32_enabled > 1) pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n"); return 1; @@ -63,177 +42,45 @@ static int __init vdso_setup(char *s) * behavior on both 64-bit and 32-bit kernels. * On 32-bit kernels, vdso=[012] means the same thing. */ -__setup("vdso32=", vdso_setup); +__setup("vdso32=", vdso32_setup); #ifdef CONFIG_X86_32 -__setup_param("vdso=", vdso32_setup, vdso_setup, 0); - -EXPORT_SYMBOL_GPL(vdso_enabled); +__setup_param("vdso=", vdso_setup, vdso32_setup, 0); #endif -static struct page **vdso32_pages; -static unsigned vdso32_size; - #ifdef CONFIG_X86_64 #define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SYSENTER32)) #define vdso32_syscall() (boot_cpu_has(X86_FEATURE_SYSCALL32)) -/* May not be __init: called during resume */ -void syscall32_cpu_init(void) -{ - /* Load these always in case some future AMD CPU supports - SYSENTER from compat mode too. */ - wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); - wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); - - wrmsrl(MSR_CSTAR, ia32_cstar_target); -} - #else /* CONFIG_X86_32 */ #define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SEP)) #define vdso32_syscall() (0) -void enable_sep_cpu(void) -{ - int cpu = get_cpu(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); - - if (!boot_cpu_has(X86_FEATURE_SEP)) { - put_cpu(); - return; - } - - tss->x86_tss.ss1 = __KERNEL_CS; - tss->x86_tss.sp1 = sizeof(struct tss_struct) + (unsigned long) tss; - wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0); - wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0); - wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) ia32_sysenter_target, 0); - put_cpu(); -} - #endif /* CONFIG_X86_64 */ +#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +const struct vdso_image *selected_vdso32; +#endif + int __init sysenter_setup(void) { - char *vdso32_start, *vdso32_end; - int npages, i; - #ifdef CONFIG_COMPAT - if (vdso32_syscall()) { - vdso32_start = vdso32_syscall_start; - vdso32_end = vdso32_syscall_end; - vdso32_pages = vdso32_syscall_pages; - } else + if (vdso32_syscall()) + selected_vdso32 = &vdso_image_32_syscall; + else #endif - if (vdso32_sysenter()) { - vdso32_start = vdso32_sysenter_start; - vdso32_end = vdso32_sysenter_end; - vdso32_pages = vdso32_sysenter_pages; - } else { - vdso32_start = vdso32_int80_start; - vdso32_end = vdso32_int80_end; - vdso32_pages = vdso32_int80_pages; - } - - npages = ((vdso32_end - vdso32_start) + PAGE_SIZE - 1) / PAGE_SIZE; - vdso32_size = npages << PAGE_SHIFT; - for (i = 0; i < npages; i++) - vdso32_pages[i] = virt_to_page(vdso32_start + i*PAGE_SIZE); + if (vdso32_sysenter()) + selected_vdso32 = &vdso_image_32_sysenter; + else + selected_vdso32 = &vdso_image_32_int80; - patch_vdso32(vdso32_start, vdso32_size); + init_vdso_image(selected_vdso32); return 0; } -/* Setup a VMA at program startup for the vsyscall page */ -int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) -{ - struct mm_struct *mm = current->mm; - unsigned long addr; - int ret = 0; - struct vm_area_struct *vma; - -#ifdef CONFIG_X86_X32_ABI - if (test_thread_flag(TIF_X32)) - return x32_setup_additional_pages(bprm, uses_interp); -#endif - - if (vdso_enabled != 1) /* Other values all mean "disabled" */ - return 0; - - down_write(&mm->mmap_sem); - - addr = get_unmapped_area(NULL, 0, vdso32_size + VDSO_OFFSET(VDSO_PREV_PAGES), 0, 0); - if (IS_ERR_VALUE(addr)) { - ret = addr; - goto up_fail; - } - - addr += VDSO_OFFSET(VDSO_PREV_PAGES); - - current->mm->context.vdso = (void *)addr; - - /* - * MAYWRITE to allow gdb to COW and set breakpoints - */ - ret = install_special_mapping(mm, - addr, - vdso32_size, - VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - vdso32_pages); - - if (ret) - goto up_fail; - - vma = _install_special_mapping(mm, - addr - VDSO_OFFSET(VDSO_PREV_PAGES), - VDSO_OFFSET(VDSO_PREV_PAGES), - VM_READ, - NULL); - - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto up_fail; - } - - ret = remap_pfn_range(vma, - addr - VDSO_OFFSET(VDSO_VVAR_PAGE), - __pa_symbol(&__vvar_page) >> PAGE_SHIFT, - PAGE_SIZE, - PAGE_READONLY); - - if (ret) - goto up_fail; - -#ifdef CONFIG_HPET_TIMER - if (hpet_address) { - ret = io_remap_pfn_range(vma, - addr - VDSO_OFFSET(VDSO_HPET_PAGE), - hpet_address >> PAGE_SHIFT, - PAGE_SIZE, - pgprot_noncached(PAGE_READONLY)); - - if (ret) - goto up_fail; - } -#endif - - current_thread_info()->sysenter_return = - VDSO32_SYMBOL(addr, SYSENTER_RETURN); - - up_fail: - if (ret) - current->mm->context.vdso = NULL; - - up_write(&mm->mmap_sem); - - return ret; -} - #ifdef CONFIG_X86_64 subsys_initcall(sysenter_setup); @@ -245,14 +92,7 @@ subsys_initcall(sysenter_setup); static struct ctl_table abi_table2[] = { { .procname = "vsyscall32", - .data = &sysctl_vsyscall32, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "ldt16", - .data = &sysctl_ldt16, + .data = &vdso32_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -279,13 +119,6 @@ __initcall(ia32_binfmt_init); #else /* CONFIG_X86_32 */ -const char *arch_vma_name(struct vm_area_struct *vma) -{ - if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) - return "[vdso]"; - return NULL; -} - struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { return NULL; diff --git a/arch/x86/vdso/vdso32.S b/arch/x86/vdso/vdso32.S deleted file mode 100644 index 018bcd9f97b4..000000000000 --- a/arch/x86/vdso/vdso32.S +++ /dev/null @@ -1,9 +0,0 @@ -#include <asm/vdso.h> - -DEFINE_VDSO_IMAGE(vdso32_int80, "arch/x86/vdso/vdso32-int80.so") - -#ifdef CONFIG_COMPAT -DEFINE_VDSO_IMAGE(vdso32_syscall, "arch/x86/vdso/vdso32-syscall.so") -#endif - -DEFINE_VDSO_IMAGE(vdso32_sysenter, "arch/x86/vdso/vdso32-sysenter.so") diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/vdso/vdso32/vdso32.lds.S index aadb8b9994cd..31056cf294bf 100644 --- a/arch/x86/vdso/vdso32/vdso32.lds.S +++ b/arch/x86/vdso/vdso32/vdso32.lds.S @@ -1,17 +1,14 @@ /* * Linker script for 32-bit vDSO. * We #include the file to define the layout details. - * Here we only choose the prelinked virtual address. * * This file defines the version script giving the user-exported symbols in - * the DSO. We can define local symbols here called VDSO* to make their - * values visible using the asm-x86/vdso.h macros from the kernel proper. + * the DSO. */ #include <asm/page.h> #define BUILD_VDSO32 -#define VDSO_PRELINK 0 #include "../vdso-layout.lds.S" @@ -38,13 +35,3 @@ VERSION local: *; }; } - -/* - * Symbols we define here called VDSO* get their values into vdso32-syms.h. - */ -VDSO32_vsyscall = __kernel_vsyscall; -VDSO32_sigreturn = __kernel_sigreturn; -VDSO32_rt_sigreturn = __kernel_rt_sigreturn; -VDSO32_clock_gettime = clock_gettime; -VDSO32_gettimeofday = gettimeofday; -VDSO32_time = time; diff --git a/arch/x86/vdso/vdsox32.S b/arch/x86/vdso/vdsox32.S deleted file mode 100644 index f4aa34e7f370..000000000000 --- a/arch/x86/vdso/vdsox32.S +++ /dev/null @@ -1,3 +0,0 @@ -#include <asm/vdso.h> - -DEFINE_VDSO_IMAGE(vdsox32, "arch/x86/vdso/vdsox32.so") diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/vdso/vdsox32.lds.S index 62272aa2ae0a..46b991b578a8 100644 --- a/arch/x86/vdso/vdsox32.lds.S +++ b/arch/x86/vdso/vdsox32.lds.S @@ -1,14 +1,11 @@ /* * Linker script for x32 vDSO. * We #include the file to define the layout details. - * Here we only choose the prelinked virtual address. * * This file defines the version script giving the user-exported symbols in - * the DSO. We can define local symbols here called VDSO* to make their - * values visible using the asm-x86/vdso.h macros from the kernel proper. + * the DSO. */ -#define VDSO_PRELINK 0 #include "vdso-layout.lds.S" /* @@ -24,5 +21,3 @@ VERSION { local: *; }; } - -VDSOX32_PRELINK = VDSO_PRELINK; diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 1ad102613127..e1513c47872a 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -15,115 +15,51 @@ #include <asm/proto.h> #include <asm/vdso.h> #include <asm/page.h> +#include <asm/hpet.h> #if defined(CONFIG_X86_64) -unsigned int __read_mostly vdso_enabled = 1; +unsigned int __read_mostly vdso64_enabled = 1; -DECLARE_VDSO_IMAGE(vdso); extern unsigned short vdso_sync_cpuid; -static unsigned vdso_size; - -#ifdef CONFIG_X86_X32_ABI -DECLARE_VDSO_IMAGE(vdsox32); -static unsigned vdsox32_size; -#endif #endif -#if defined(CONFIG_X86_32) || defined(CONFIG_X86_X32_ABI) || \ - defined(CONFIG_COMPAT) -void __init patch_vdso32(void *vdso, size_t len) +void __init init_vdso_image(const struct vdso_image *image) { - Elf32_Ehdr *hdr = vdso; - Elf32_Shdr *sechdrs, *alt_sec = 0; - char *secstrings; - void *alt_data; int i; + int npages = (image->size) / PAGE_SIZE; - BUG_ON(len < sizeof(Elf32_Ehdr)); - BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0); - - sechdrs = (void *)hdr + hdr->e_shoff; - secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; - - for (i = 1; i < hdr->e_shnum; i++) { - Elf32_Shdr *shdr = &sechdrs[i]; - if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) { - alt_sec = shdr; - goto found; - } - } - - /* If we get here, it's probably a bug. */ - pr_warning("patch_vdso32: .altinstructions not found\n"); - return; /* nothing to patch */ + BUG_ON(image->size % PAGE_SIZE != 0); + for (i = 0; i < npages; i++) + image->text_mapping.pages[i] = + virt_to_page(image->data + i*PAGE_SIZE); -found: - alt_data = (void *)hdr + alt_sec->sh_offset; - apply_alternatives(alt_data, alt_data + alt_sec->sh_size); + apply_alternatives((struct alt_instr *)(image->data + image->alt), + (struct alt_instr *)(image->data + image->alt + + image->alt_len)); } -#endif #if defined(CONFIG_X86_64) -static void __init patch_vdso64(void *vdso, size_t len) -{ - Elf64_Ehdr *hdr = vdso; - Elf64_Shdr *sechdrs, *alt_sec = 0; - char *secstrings; - void *alt_data; - int i; - - BUG_ON(len < sizeof(Elf64_Ehdr)); - BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0); - - sechdrs = (void *)hdr + hdr->e_shoff; - secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; - - for (i = 1; i < hdr->e_shnum; i++) { - Elf64_Shdr *shdr = &sechdrs[i]; - if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) { - alt_sec = shdr; - goto found; - } - } - - /* If we get here, it's probably a bug. */ - pr_warning("patch_vdso64: .altinstructions not found\n"); - return; /* nothing to patch */ - -found: - alt_data = (void *)hdr + alt_sec->sh_offset; - apply_alternatives(alt_data, alt_data + alt_sec->sh_size); -} - static int __init init_vdso(void) { - int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE; - int i; - - patch_vdso64(vdso_start, vdso_end - vdso_start); - - vdso_size = npages << PAGE_SHIFT; - for (i = 0; i < npages; i++) - vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE); + init_vdso_image(&vdso_image_64); #ifdef CONFIG_X86_X32_ABI - patch_vdso32(vdsox32_start, vdsox32_end - vdsox32_start); - npages = (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE; - vdsox32_size = npages << PAGE_SHIFT; - for (i = 0; i < npages; i++) - vdsox32_pages[i] = virt_to_page(vdsox32_start + i*PAGE_SIZE); + init_vdso_image(&vdso_image_x32); #endif return 0; } subsys_initcall(init_vdso); +#endif struct linux_binprm; /* Put the vdso above the (randomized) stack with another randomized offset. This way there is no hole in the middle of address space. To save memory make sure it is still in the same PTE as the stack top. - This doesn't give that many random bits */ + This doesn't give that many random bits. + + Only used for the 64-bit and x32 vdsos. */ static unsigned long vdso_addr(unsigned long start, unsigned len) { unsigned long addr, end; @@ -149,61 +85,149 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) return addr; } -/* Setup a VMA at program startup for the vsyscall page. - Not called for compat tasks */ -static int setup_additional_pages(struct linux_binprm *bprm, - int uses_interp, - struct page **pages, - unsigned size) +static int map_vdso(const struct vdso_image *image, bool calculate_addr) { struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; unsigned long addr; - int ret; - - if (!vdso_enabled) - return 0; + int ret = 0; + static struct page *no_pages[] = {NULL}; + static struct vm_special_mapping vvar_mapping = { + .name = "[vvar]", + .pages = no_pages, + }; + + if (calculate_addr) { + addr = vdso_addr(current->mm->start_stack, + image->sym_end_mapping); + } else { + addr = 0; + } down_write(&mm->mmap_sem); - addr = vdso_addr(mm->start_stack, size); - addr = get_unmapped_area(NULL, addr, size, 0, 0); + + addr = get_unmapped_area(NULL, addr, image->sym_end_mapping, 0, 0); if (IS_ERR_VALUE(addr)) { ret = addr; goto up_fail; } - current->mm->context.vdso = (void *)addr; + current->mm->context.vdso = (void __user *)addr; - ret = install_special_mapping(mm, addr, size, - VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - pages); - if (ret) { - current->mm->context.vdso = NULL; + /* + * MAYWRITE to allow gdb to COW and set breakpoints + */ + vma = _install_special_mapping(mm, + addr, + image->size, + VM_READ|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + &image->text_mapping); + + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); goto up_fail; } + vma = _install_special_mapping(mm, + addr + image->size, + image->sym_end_mapping - image->size, + VM_READ, + &vvar_mapping); + + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto up_fail; + } + + if (image->sym_vvar_page) + ret = remap_pfn_range(vma, + addr + image->sym_vvar_page, + __pa_symbol(&__vvar_page) >> PAGE_SHIFT, + PAGE_SIZE, + PAGE_READONLY); + + if (ret) + goto up_fail; + +#ifdef CONFIG_HPET_TIMER + if (hpet_address && image->sym_hpet_page) { + ret = io_remap_pfn_range(vma, + addr + image->sym_hpet_page, + hpet_address >> PAGE_SHIFT, + PAGE_SIZE, + pgprot_noncached(PAGE_READONLY)); + + if (ret) + goto up_fail; + } +#endif + up_fail: + if (ret) + current->mm->context.vdso = NULL; + up_write(&mm->mmap_sem); return ret; } +#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +static int load_vdso32(void) +{ + int ret; + + if (vdso32_enabled != 1) /* Other values all mean "disabled" */ + return 0; + + ret = map_vdso(selected_vdso32, false); + if (ret) + return ret; + + if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN) + current_thread_info()->sysenter_return = + current->mm->context.vdso + + selected_vdso32->sym_VDSO32_SYSENTER_RETURN; + + return 0; +} +#endif + +#ifdef CONFIG_X86_64 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - return setup_additional_pages(bprm, uses_interp, vdso_pages, - vdso_size); + if (!vdso64_enabled) + return 0; + + return map_vdso(&vdso_image_64, true); } +#ifdef CONFIG_COMPAT +int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp) +{ #ifdef CONFIG_X86_X32_ABI -int x32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) + if (test_thread_flag(TIF_X32)) { + if (!vdso64_enabled) + return 0; + + return map_vdso(&vdso_image_x32, true); + } +#endif + + return load_vdso32(); +} +#endif +#else +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - return setup_additional_pages(bprm, uses_interp, vdsox32_pages, - vdsox32_size); + return load_vdso32(); } #endif +#ifdef CONFIG_X86_64 static __init int vdso_setup(char *s) { - vdso_enabled = simple_strtoul(s, NULL, 0); + vdso64_enabled = simple_strtoul(s, NULL, 0); return 0; } __setup("vdso=", vdso_setup); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 6f6e15d28466..e8a1201c3293 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1494,7 +1494,7 @@ static int xen_pgd_alloc(struct mm_struct *mm) page->private = (unsigned long)user_pgd; if (user_pgd != NULL) { - user_pgd[pgd_index(VSYSCALL_START)] = + user_pgd[pgd_index(VSYSCALL_ADDR)] = __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); ret = 0; } @@ -2062,8 +2062,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) case FIX_KMAP_BEGIN ... FIX_KMAP_END: # endif #else - case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE: - case VVAR_PAGE: + case VSYSCALL_PAGE: #endif case FIX_TEXT_POKE0: case FIX_TEXT_POKE1: @@ -2104,8 +2103,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #ifdef CONFIG_X86_64 /* Replicate changes to map the vsyscall page into the user pagetable vsyscall mapping. */ - if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) || - idx == VVAR_PAGE) { + if (idx == VSYSCALL_PAGE) { unsigned long vaddr = __fix_to_virt(idx); set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte); } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 210426a26cc0..821a11ada590 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -525,10 +525,17 @@ char * __init xen_memory_setup(void) static void __init fiddle_vdso(void) { #ifdef CONFIG_X86_32 + /* + * This could be called before selected_vdso32 is initialized, so + * just fiddle with both possible images. vdso_image_32_syscall + * can't be selected, since it only exists on 64-bit systems. + */ u32 *mask; - mask = VDSO32_SYMBOL(&vdso32_int80_start, NOTE_MASK); + mask = vdso_image_32_int80.data + + vdso_image_32_int80.sym_VDSO32_NOTE_MASK; *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT; - mask = VDSO32_SYMBOL(&vdso32_sysenter_start, NOTE_MASK); + mask = vdso_image_32_sysenter.data + + vdso_image_32_sysenter.sym_VDSO32_NOTE_MASK; *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT; #endif } diff --git a/arch/xtensa/include/asm/ftrace.h b/arch/xtensa/include/asm/ftrace.h index 736b9d214d80..6c6d9a9f185f 100644 --- a/arch/xtensa/include/asm/ftrace.h +++ b/arch/xtensa/include/asm/ftrace.h @@ -12,24 +12,18 @@ #include <asm/processor.h> -#define HAVE_ARCH_CALLER_ADDR #ifndef __ASSEMBLY__ -#define CALLER_ADDR0 ({ unsigned long a0, a1; \ +#define ftrace_return_address0 ({ unsigned long a0, a1; \ __asm__ __volatile__ ( \ "mov %0, a0\n" \ "mov %1, a1\n" \ : "=r"(a0), "=r"(a1)); \ MAKE_PC_FROM_RA(a0, a1); }) + #ifdef CONFIG_FRAME_POINTER extern unsigned long return_address(unsigned level); -#define CALLER_ADDR1 return_address(1) -#define CALLER_ADDR2 return_address(2) -#define CALLER_ADDR3 return_address(3) -#else /* CONFIG_FRAME_POINTER */ -#define CALLER_ADDR1 (0) -#define CALLER_ADDR2 (0) -#define CALLER_ADDR3 (0) -#endif /* CONFIG_FRAME_POINTER */ +#define ftrace_return_address(n) return_address(n) +#endif #endif /* __ASSEMBLY__ */ #ifdef CONFIG_FUNCTION_TRACER diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 9757bb74e532..06370ccea9e9 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -74,7 +74,6 @@ extern int initrd_below_start_ok; #endif #ifdef CONFIG_OF -extern u32 __dtb_start[]; void *dtb_start = __dtb_start; #endif @@ -199,7 +198,7 @@ static int __init xtensa_dt_io_area(unsigned long node, const char *uname, int depth, void *data) { const __be32 *ranges; - unsigned long len; + int len; if (depth > 1) return 0; |