diff options
200 files changed, 2345 insertions, 1350 deletions
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index 2f813d644c69..18b7dc929234 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -99,7 +99,7 @@ Description: this file, the suspend image will be as small as possible. Reading from this file will display the current image size - limit, which is set to 500 MB by default. + limit, which is set to around 2/5 of available RAM by default. What: /sys/power/pm_trace Date: August 2006 diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst index 8f1d3de449b5..ac6f5c597a56 100644 --- a/Documentation/admin-guide/pm/intel_pstate.rst +++ b/Documentation/admin-guide/pm/intel_pstate.rst @@ -465,6 +465,13 @@ Next, the following policy attributes have special meaning if policy for the time interval between the last two invocations of the driver's utilization update callback by the CPU scheduler for that CPU. +One more policy attribute is present if the `HWP feature is enabled in the +processor <Active Mode With HWP_>`_: + +``base_frequency`` + Shows the base frequency of the CPU. Any frequency above this will be + in the turbo frequency range. + The meaning of these attributes in the `passive mode <Passive Mode_>`_ is the same as for other scaling drivers. diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt index cc87adf44c0a..236d1fb13640 100644 --- a/Documentation/power/swsusp.txt +++ b/Documentation/power/swsusp.txt @@ -56,7 +56,7 @@ If you want to limit the suspend image size to N bytes, do echo N > /sys/power/image_size -before suspend (it is limited to 500 MB by default). +before suspend (it is limited to around 2/5 of available RAM by default). . The resume process checks for the presence of the resume device, if found, it then checks the contents for the hibernation image signature. diff --git a/MAINTAINERS b/MAINTAINERS index 48a65c3a4189..6ac000cc006d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9657,7 +9657,8 @@ MIPS/LOONGSON2 ARCHITECTURE M: Jiaxun Yang <jiaxun.yang@flygoat.com> L: linux-mips@linux-mips.org S: Maintained -F: arch/mips/loongson64/*{2e/2f}* +F: arch/mips/loongson64/fuloong-2e/ +F: arch/mips/loongson64/lemote-2f/ F: arch/mips/include/asm/mach-loongson64/ F: drivers/*/*loongson2* F: drivers/*/*/*loongson2* @@ -9864,7 +9865,7 @@ M: Peter Rosin <peda@axentia.se> S: Maintained F: Documentation/ABI/testing/sysfs-class-mux* F: Documentation/devicetree/bindings/mux/ -F: include/linux/dt-bindings/mux/ +F: include/dt-bindings/mux/ F: include/linux/mux/ F: drivers/mux/ @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = -rc8 NAME = Merciless Moray # *DOCUMENTATION* @@ -483,13 +483,15 @@ endif ifeq ($(cc-name),clang) ifneq ($(CROSS_COMPILE),) CLANG_TARGET := --target=$(notdir $(CROSS_COMPILE:%-=%)) -GCC_TOOLCHAIN := $(realpath $(dir $(shell which $(LD)))/..) +GCC_TOOLCHAIN_DIR := $(dir $(shell which $(LD))) +CLANG_PREFIX := --prefix=$(GCC_TOOLCHAIN_DIR) +GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..) endif ifneq ($(GCC_TOOLCHAIN),) CLANG_GCC_TC := --gcc-toolchain=$(GCC_TOOLCHAIN) endif -KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) -KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) +KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) $(CLANG_PREFIX) +KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) $(CLANG_PREFIX) KBUILD_CFLAGS += $(call cc-option, -no-integrated-as) KBUILD_AFLAGS += $(call cc-option, -no-integrated-as) endif diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index b4441b0764d7..a045f3086047 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -149,7 +149,7 @@ config ARC_CPU_770 Support for ARC770 core introduced with Rel 4.10 (Summer 2011) This core has a bunch of cool new features: -MMU-v3: Variable Page Sz (4k, 8k, 16k), bigger J-TLB (128x4) - Shared Address Spaces (for sharing TLB entires in MMU) + Shared Address Spaces (for sharing TLB entries in MMU) -Caches: New Prog Model, Region Flush -Insns: endian swap, load-locked/store-conditional, time-stamp-ctr diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 99cce77ab98f..644815c0516e 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -6,33 +6,11 @@ # published by the Free Software Foundation. # -ifeq ($(CROSS_COMPILE),) -ifndef CONFIG_CPU_BIG_ENDIAN -CROSS_COMPILE := arc-linux- -else -CROSS_COMPILE := arceb-linux- -endif -endif - KBUILD_DEFCONFIG := nsim_700_defconfig cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__ cflags-$(CONFIG_ISA_ARCOMPACT) += -mA7 -cflags-$(CONFIG_ISA_ARCV2) += -mcpu=archs - -is_700 = $(shell $(CC) -dM -E - < /dev/null | grep -q "ARC700" && echo 1 || echo 0) - -ifdef CONFIG_ISA_ARCOMPACT -ifeq ($(is_700), 0) - $(error Toolchain not configured for ARCompact builds) -endif -endif - -ifdef CONFIG_ISA_ARCV2 -ifeq ($(is_700), 1) - $(error Toolchain not configured for ARCv2 builds) -endif -endif +cflags-$(CONFIG_ISA_ARCV2) += -mcpu=hs38 ifdef CONFIG_ARC_CURR_IN_REG # For a global register defintion, make sure it gets passed to every file @@ -79,7 +57,7 @@ cflags-$(disable_small_data) += -mno-sdata -fcall-used-gp cflags-$(CONFIG_CPU_BIG_ENDIAN) += -mbig-endian ldflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB -LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) +LIBGCC = $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel KBUILD_CFLAGS_MODULE += -mlong-calls -mno-millicode diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 4674541eba3f..8ce6e7235915 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -241,6 +241,26 @@ int copy_thread(unsigned long clone_flags, task_thread_info(current)->thr_ptr; } + + /* + * setup usermode thread pointer #1: + * when child is picked by scheduler, __switch_to() uses @c_callee to + * populate usermode callee regs: this works (despite being in a kernel + * function) since special return path for child @ret_from_fork() + * ensures those regs are not clobbered all the way to RTIE to usermode + */ + c_callee->r25 = task_thread_info(p)->thr_ptr; + +#ifdef CONFIG_ARC_CURR_IN_REG + /* + * setup usermode thread pointer #2: + * however for this special use of r25 in kernel, __switch_to() sets + * r25 for kernel needs and only in the final return path is usermode + * r25 setup, from pt_regs->user_r25. So set that up as well + */ + c_regs->user_r25 = c_callee->r25; +#endif + return 0; } diff --git a/arch/arm/boot/dts/imx53-qsb-common.dtsi b/arch/arm/boot/dts/imx53-qsb-common.dtsi index 7423d462d1e4..50dde84b72ed 100644 --- a/arch/arm/boot/dts/imx53-qsb-common.dtsi +++ b/arch/arm/boot/dts/imx53-qsb-common.dtsi @@ -123,6 +123,17 @@ }; }; +&cpu0 { + /* CPU rated to 1GHz, not 1.2GHz as per the default settings */ + operating-points = < + /* kHz uV */ + 166666 850000 + 400000 900000 + 800000 1050000 + 1000000 1200000 + >; +}; + &esdhc1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_esdhc1>; diff --git a/arch/arm/kernel/vmlinux.lds.h b/arch/arm/kernel/vmlinux.lds.h index ae5fdff18406..8247bc15addc 100644 --- a/arch/arm/kernel/vmlinux.lds.h +++ b/arch/arm/kernel/vmlinux.lds.h @@ -49,6 +49,8 @@ #define ARM_DISCARD \ *(.ARM.exidx.exit.text) \ *(.ARM.extab.exit.text) \ + *(.ARM.exidx.text.exit) \ + *(.ARM.extab.text.exit) \ ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text)) \ ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text)) \ ARM_EXIT_DISCARD(EXIT_TEXT) \ diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 450c7a4fbc8a..cb094e55dc5f 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -478,15 +478,15 @@ static const struct coproc_reg cp15_regs[] = { /* ICC_SGI1R */ { CRm64(12), Op1( 0), is64, access_gic_sgi}, - /* ICC_ASGI1R */ - { CRm64(12), Op1( 1), is64, access_gic_sgi}, - /* ICC_SGI0R */ - { CRm64(12), Op1( 2), is64, access_gic_sgi}, /* VBAR: swapped by interrupt.S. */ { CRn(12), CRm( 0), Op1( 0), Op2( 0), is32, NULL, reset_val, c12_VBAR, 0x00000000 }, + /* ICC_ASGI1R */ + { CRm64(12), Op1( 1), is64, access_gic_sgi}, + /* ICC_SGI0R */ + { CRm64(12), Op1( 2), is64, access_gic_sgi}, /* ICC_SRE */ { CRn(12), CRm(12), Op1( 0), Op2(5), is32, access_gic_sre }, diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 8e38d5267f22..e213f8e867f6 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -966,6 +966,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event, return 0; } +static int armv8pmu_filter_match(struct perf_event *event) +{ + unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT; + return evtype != ARMV8_PMUV3_PERFCTR_CHAIN; +} + static void armv8pmu_reset(void *info) { struct arm_pmu *cpu_pmu = (struct arm_pmu *)info; @@ -1114,6 +1120,7 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->stop = armv8pmu_stop, cpu_pmu->reset = armv8pmu_reset, cpu_pmu->set_event_filter = armv8pmu_set_event_filter; + cpu_pmu->filter_match = armv8pmu_filter_match; return 0; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 5b4fac434c84..b3354ff94e79 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -64,6 +64,9 @@ #include <asm/xen/hypervisor.h> #include <asm/mmu_context.h> +static int num_standard_resources; +static struct resource *standard_resources; + phys_addr_t __fdt_pointer __initdata; /* @@ -206,14 +209,19 @@ static void __init request_standard_resources(void) { struct memblock_region *region; struct resource *res; + unsigned long i = 0; kernel_code.start = __pa_symbol(_text); kernel_code.end = __pa_symbol(__init_begin - 1); kernel_data.start = __pa_symbol(_sdata); kernel_data.end = __pa_symbol(_end - 1); + num_standard_resources = memblock.memory.cnt; + standard_resources = alloc_bootmem_low(num_standard_resources * + sizeof(*standard_resources)); + for_each_memblock(memory, region) { - res = alloc_bootmem_low(sizeof(*res)); + res = &standard_resources[i++]; if (memblock_is_nomap(region)) { res->name = "reserved"; res->flags = IORESOURCE_MEM; @@ -243,36 +251,26 @@ static void __init request_standard_resources(void) static int __init reserve_memblock_reserved_regions(void) { - phys_addr_t start, end, roundup_end = 0; - struct resource *mem, *res; - u64 i; - - for_each_reserved_mem_region(i, &start, &end) { - if (end <= roundup_end) - continue; /* done already */ - - start = __pfn_to_phys(PFN_DOWN(start)); - end = __pfn_to_phys(PFN_UP(end)) - 1; - roundup_end = end; - - res = kzalloc(sizeof(*res), GFP_ATOMIC); - if (WARN_ON(!res)) - return -ENOMEM; - res->start = start; - res->end = end; - res->name = "reserved"; - res->flags = IORESOURCE_MEM; - - mem = request_resource_conflict(&iomem_resource, res); - /* - * We expected memblock_reserve() regions to conflict with - * memory created by request_standard_resources(). - */ - if (WARN_ON_ONCE(!mem)) + u64 i, j; + + for (i = 0; i < num_standard_resources; ++i) { + struct resource *mem = &standard_resources[i]; + phys_addr_t r_start, r_end, mem_size = resource_size(mem); + + if (!memblock_is_region_reserved(mem->start, mem_size)) continue; - kfree(res); - reserve_region_with_split(mem, start, end, "reserved"); + for_each_reserved_mem_region(j, &r_start, &r_end) { + resource_size_t start, end; + + start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start); + end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end); + + if (start > mem->end || end < mem->start) + continue; + + reserve_region_with_split(mem, start, end, "reserved"); + } } return 0; diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index b2fa62922d88..49d6046ca1d0 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -13,6 +13,7 @@ #include <linux/atomic.h> #include <linux/cpumask.h> +#include <linux/sizes.h> #include <linux/threads.h> #include <asm/cachectl.h> @@ -80,11 +81,10 @@ extern unsigned int vced_count, vcei_count; #endif -/* - * One page above the stack is used for branch delay slot "emulation". - * See dsemul.c for details. - */ -#define STACK_TOP ((TASK_SIZE & PAGE_MASK) - PAGE_SIZE) +#define VDSO_RANDOMIZE_SIZE (TASK_IS_32BIT_ADDR ? SZ_1M : SZ_256M) + +extern unsigned long mips_stack_top(void); +#define STACK_TOP mips_stack_top() /* * This decides where the kernel will search for a free chunk of vm diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 8fc69891e117..d4f7fd4550e1 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -32,6 +32,7 @@ #include <linux/nmi.h> #include <linux/cpu.h> +#include <asm/abi.h> #include <asm/asm.h> #include <asm/bootinfo.h> #include <asm/cpu.h> @@ -39,6 +40,7 @@ #include <asm/dsp.h> #include <asm/fpu.h> #include <asm/irq.h> +#include <asm/mips-cps.h> #include <asm/msa.h> #include <asm/pgtable.h> #include <asm/mipsregs.h> @@ -645,6 +647,29 @@ out: return pc; } +unsigned long mips_stack_top(void) +{ + unsigned long top = TASK_SIZE & PAGE_MASK; + + /* One page for branch delay slot "emulation" */ + top -= PAGE_SIZE; + + /* Space for the VDSO, data page & GIC user page */ + top -= PAGE_ALIGN(current->thread.abi->vdso->size); + top -= PAGE_SIZE; + top -= mips_gic_present() ? PAGE_SIZE : 0; + + /* Space for cache colour alignment */ + if (cpu_has_dc_aliases) + top -= shm_align_mask + 1; + + /* Space to randomize the VDSO base */ + if (current->flags & PF_RANDOMIZE) + top -= VDSO_RANDOMIZE_SIZE; + + return top; +} + /* * Don't forget that the stack pointer must be aligned on a 8 bytes * boundary for 32-bits ABI and 16 bytes for 64-bits ABI. diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index c71d1eb7da59..8aaaa42f91ed 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -846,6 +846,34 @@ static void __init arch_mem_init(char **cmdline_p) struct memblock_region *reg; extern void plat_mem_setup(void); + /* + * Initialize boot_command_line to an innocuous but non-empty string in + * order to prevent early_init_dt_scan_chosen() from copying + * CONFIG_CMDLINE into it without our knowledge. We handle + * CONFIG_CMDLINE ourselves below & don't want to duplicate its + * content because repeating arguments can be problematic. + */ + strlcpy(boot_command_line, " ", COMMAND_LINE_SIZE); + + /* call board setup routine */ + plat_mem_setup(); + + /* + * Make sure all kernel memory is in the maps. The "UP" and + * "DOWN" are opposite for initdata since if it crosses over + * into another memory section you don't want that to be + * freed when the initdata is freed. + */ + arch_mem_addpart(PFN_DOWN(__pa_symbol(&_text)) << PAGE_SHIFT, + PFN_UP(__pa_symbol(&_edata)) << PAGE_SHIFT, + BOOT_MEM_RAM); + arch_mem_addpart(PFN_UP(__pa_symbol(&__init_begin)) << PAGE_SHIFT, + PFN_DOWN(__pa_symbol(&__init_end)) << PAGE_SHIFT, + BOOT_MEM_INIT_RAM); + + pr_info("Determined physical RAM map:\n"); + print_memory_map(); + #if defined(CONFIG_CMDLINE_BOOL) && defined(CONFIG_CMDLINE_OVERRIDE) strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); #else @@ -873,26 +901,6 @@ static void __init arch_mem_init(char **cmdline_p) } #endif #endif - - /* call board setup routine */ - plat_mem_setup(); - - /* - * Make sure all kernel memory is in the maps. The "UP" and - * "DOWN" are opposite for initdata since if it crosses over - * into another memory section you don't want that to be - * freed when the initdata is freed. - */ - arch_mem_addpart(PFN_DOWN(__pa_symbol(&_text)) << PAGE_SHIFT, - PFN_UP(__pa_symbol(&_edata)) << PAGE_SHIFT, - BOOT_MEM_RAM); - arch_mem_addpart(PFN_UP(__pa_symbol(&__init_begin)) << PAGE_SHIFT, - PFN_DOWN(__pa_symbol(&__init_end)) << PAGE_SHIFT, - BOOT_MEM_INIT_RAM); - - pr_info("Determined physical RAM map:\n"); - print_memory_map(); - strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 8f845f6e5f42..48a9c6b90e07 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -15,6 +15,7 @@ #include <linux/ioport.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/random.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/timekeeper_internal.h> @@ -97,6 +98,21 @@ void update_vsyscall_tz(void) } } +static unsigned long vdso_base(void) +{ + unsigned long base; + + /* Skip the delay slot emulation page */ + base = STACK_TOP + PAGE_SIZE; + + if (current->flags & PF_RANDOMIZE) { + base += get_random_int() & (VDSO_RANDOMIZE_SIZE - 1); + base = PAGE_ALIGN(base); + } + + return base; +} + int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mips_vdso_image *image = current->thread.abi->vdso; @@ -137,7 +153,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (cpu_has_dc_aliases) size += shm_align_mask + 1; - base = get_unmapped_area(NULL, 0, size, 0, 0); + base = get_unmapped_area(NULL, vdso_base(), size, 0, 0); if (IS_ERR_VALUE(base)) { ret = base; goto out; diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S index 3a6f34ef5ffc..069acec3df9f 100644 --- a/arch/mips/lib/memset.S +++ b/arch/mips/lib/memset.S @@ -280,9 +280,11 @@ * unset_bytes = end_addr - current_addr + 1 * a2 = t1 - a0 + 1 */ + .set reorder PTR_SUBU a2, t1, a0 + PTR_ADDIU a2, 1 jr ra - PTR_ADDIU a2, 1 + .set noreorder .endm diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 2fdc865ca374..2a2486526d1f 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -114,7 +114,7 @@ */ #define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ _PAGE_ACCESSED | H_PAGE_THP_HUGE | _PAGE_PTE | \ - _PAGE_SOFT_DIRTY) + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) /* * user access blocked by key */ @@ -132,7 +132,7 @@ */ #define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \ - _PAGE_SOFT_DIRTY) + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) #define H_PTE_PKEY (H_PTE_PKEY_BIT0 | H_PTE_PKEY_BIT1 | H_PTE_PKEY_BIT2 | \ H_PTE_PKEY_BIT3 | H_PTE_PKEY_BIT4) diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 3cae9168f63c..e44a8d7959f5 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -108,7 +108,8 @@ int sclp_early_get_core_info(struct sclp_core_info *info); void sclp_early_get_ipl_info(struct sclp_ipl_info *info); void sclp_early_detect(void); void sclp_early_printk(const char *s); -void __sclp_early_printk(const char *s, unsigned int len); +void sclp_early_printk_force(const char *s); +void __sclp_early_printk(const char *s, unsigned int len, unsigned int force); int _sclp_get_core_info(struct sclp_core_info *info); int sclp_core_configure(u8 core); diff --git a/arch/s390/kernel/early_printk.c b/arch/s390/kernel/early_printk.c index 9431784d7796..40c1dfec944e 100644 --- a/arch/s390/kernel/early_printk.c +++ b/arch/s390/kernel/early_printk.c @@ -10,7 +10,7 @@ static void sclp_early_write(struct console *con, const char *s, unsigned int len) { - __sclp_early_printk(s, len); + __sclp_early_printk(s, len, 0); } static struct console sclp_early_console = { diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S index a049a7b9d6e8..c1a080b11ae9 100644 --- a/arch/s390/kernel/swsusp.S +++ b/arch/s390/kernel/swsusp.S @@ -198,12 +198,10 @@ pgm_check_entry: /* Suspend CPU not available -> panic */ larl %r15,init_thread_union - ahi %r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER) + aghi %r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER) + aghi %r15,-STACK_FRAME_OVERHEAD larl %r2,.Lpanic_string - lghi %r1,0 - sam31 - sigp %r1,%r0,SIGP_SET_ARCHITECTURE - brasl %r14,sclp_early_printk + brasl %r14,sclp_early_printk_force larl %r3,.Ldisabled_wait_31 lpsw 0(%r3) 4: diff --git a/arch/sparc/kernel/auxio_64.c b/arch/sparc/kernel/auxio_64.c index 4e8f56c3793c..cc42225c20f3 100644 --- a/arch/sparc/kernel/auxio_64.c +++ b/arch/sparc/kernel/auxio_64.c @@ -115,8 +115,8 @@ static int auxio_probe(struct platform_device *dev) auxio_devtype = AUXIO_TYPE_SBUS; size = 1; } else { - printk("auxio: Unknown parent bus type [%s]\n", - dp->parent->name); + printk("auxio: Unknown parent bus type [%pOFn]\n", + dp->parent); return -ENODEV; } auxio_register = of_ioremap(&dev->resource[0], 0, size, "auxio"); diff --git a/arch/sparc/kernel/kgdb_32.c b/arch/sparc/kernel/kgdb_32.c index 5868fc333ea8..639c8e54530a 100644 --- a/arch/sparc/kernel/kgdb_32.c +++ b/arch/sparc/kernel/kgdb_32.c @@ -122,7 +122,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, linux_regs->pc = addr; linux_regs->npc = addr + 4; } - /* fallthru */ + /* fall through */ case 'D': case 'k': diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c index d5f7dc6323d5..a68bbddbdba4 100644 --- a/arch/sparc/kernel/kgdb_64.c +++ b/arch/sparc/kernel/kgdb_64.c @@ -148,7 +148,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, linux_regs->tpc = addr; linux_regs->tnpc = addr + 4; } - /* fallthru */ + /* fall through */ case 'D': case 'k': diff --git a/arch/sparc/kernel/power.c b/arch/sparc/kernel/power.c index 92627abce311..d941875dd718 100644 --- a/arch/sparc/kernel/power.c +++ b/arch/sparc/kernel/power.c @@ -41,8 +41,8 @@ static int power_probe(struct platform_device *op) power_reg = of_ioremap(res, 0, 0x4, "power"); - printk(KERN_INFO "%s: Control reg at %llx\n", - op->dev.of_node->name, res->start); + printk(KERN_INFO "%pOFn: Control reg at %llx\n", + op->dev.of_node, res->start); if (has_button_interrupt(irq, op->dev.of_node)) { if (request_irq(irq, diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c index b51cbb9e87dc..17c87d29ff20 100644 --- a/arch/sparc/kernel/prom_32.c +++ b/arch/sparc/kernel/prom_32.c @@ -68,8 +68,8 @@ static void __init sparc32_path_component(struct device_node *dp, char *tmp_buf) return; regs = rprop->value; - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, regs->which_io, regs->phys_addr); } @@ -84,8 +84,8 @@ static void __init sbus_path_component(struct device_node *dp, char *tmp_buf) return; regs = prop->value; - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, regs->which_io, regs->phys_addr); } @@ -104,13 +104,13 @@ static void __init pci_path_component(struct device_node *dp, char *tmp_buf) regs = prop->value; devfn = (regs->phys_hi >> 8) & 0xff; if (devfn & 0x07) { - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, devfn >> 3, devfn & 0x07); } else { - sprintf(tmp_buf, "%s@%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x", + dp, devfn >> 3); } } @@ -127,8 +127,8 @@ static void __init ebus_path_component(struct device_node *dp, char *tmp_buf) regs = prop->value; - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, regs->which_io, regs->phys_addr); } @@ -167,8 +167,8 @@ static void __init ambapp_path_component(struct device_node *dp, char *tmp_buf) return; device = prop->value; - sprintf(tmp_buf, "%s:%d:%d@%x,%x", - dp->name, *vendor, *device, + sprintf(tmp_buf, "%pOFn:%d:%d@%x,%x", + dp, *vendor, *device, *intr, reg0); } @@ -201,7 +201,7 @@ char * __init build_path_component(struct device_node *dp) tmp_buf[0] = '\0'; __build_path_component(dp, tmp_buf); if (tmp_buf[0] == '\0') - strcpy(tmp_buf, dp->name); + snprintf(tmp_buf, sizeof(tmp_buf), "%pOFn", dp); n = prom_early_alloc(strlen(tmp_buf) + 1); strcpy(n, tmp_buf); diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index baeaeed64993..6220411ce8fc 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -82,8 +82,8 @@ static void __init sun4v_path_component(struct device_node *dp, char *tmp_buf) regs = rprop->value; if (!of_node_is_root(dp->parent)) { - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, (unsigned int) (regs->phys_addr >> 32UL), (unsigned int) (regs->phys_addr & 0xffffffffUL)); return; @@ -97,17 +97,17 @@ static void __init sun4v_path_component(struct device_node *dp, char *tmp_buf) const char *prefix = (type == 0) ? "m" : "i"; if (low_bits) - sprintf(tmp_buf, "%s@%s%x,%x", - dp->name, prefix, + sprintf(tmp_buf, "%pOFn@%s%x,%x", + dp, prefix, high_bits, low_bits); else - sprintf(tmp_buf, "%s@%s%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%s%x", + dp, prefix, high_bits); } else if (type == 12) { - sprintf(tmp_buf, "%s@%x", - dp->name, high_bits); + sprintf(tmp_buf, "%pOFn@%x", + dp, high_bits); } } @@ -122,8 +122,8 @@ static void __init sun4u_path_component(struct device_node *dp, char *tmp_buf) regs = prop->value; if (!of_node_is_root(dp->parent)) { - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, (unsigned int) (regs->phys_addr >> 32UL), (unsigned int) (regs->phys_addr & 0xffffffffUL)); return; @@ -138,8 +138,8 @@ static void __init sun4u_path_component(struct device_node *dp, char *tmp_buf) if (tlb_type >= cheetah) mask = 0x7fffff; - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, *(u32 *)prop->value, (unsigned int) (regs->phys_addr & mask)); } @@ -156,8 +156,8 @@ static void __init sbus_path_component(struct device_node *dp, char *tmp_buf) return; regs = prop->value; - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, regs->which_io, regs->phys_addr); } @@ -176,13 +176,13 @@ static void __init pci_path_component(struct device_node *dp, char *tmp_buf) regs = prop->value; devfn = (regs->phys_hi >> 8) & 0xff; if (devfn & 0x07) { - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, devfn >> 3, devfn & 0x07); } else { - sprintf(tmp_buf, "%s@%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x", + dp, devfn >> 3); } } @@ -203,8 +203,8 @@ static void __init upa_path_component(struct device_node *dp, char *tmp_buf) if (!prop) return; - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, *(u32 *) prop->value, (unsigned int) (regs->phys_addr & 0xffffffffUL)); } @@ -221,7 +221,7 @@ static void __init vdev_path_component(struct device_node *dp, char *tmp_buf) regs = prop->value; - sprintf(tmp_buf, "%s@%x", dp->name, *regs); + sprintf(tmp_buf, "%pOFn@%x", dp, *regs); } /* "name@addrhi,addrlo" */ @@ -236,8 +236,8 @@ static void __init ebus_path_component(struct device_node *dp, char *tmp_buf) regs = prop->value; - sprintf(tmp_buf, "%s@%x,%x", - dp->name, + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, (unsigned int) (regs->phys_addr >> 32UL), (unsigned int) (regs->phys_addr & 0xffffffffUL)); } @@ -257,8 +257,8 @@ static void __init i2c_path_component(struct device_node *dp, char *tmp_buf) /* This actually isn't right... should look at the #address-cells * property of the i2c bus node etc. etc. */ - sprintf(tmp_buf, "%s@%x,%x", - dp->name, regs[0], regs[1]); + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, regs[0], regs[1]); } /* "name@reg0[,reg1]" */ @@ -274,11 +274,11 @@ static void __init usb_path_component(struct device_node *dp, char *tmp_buf) regs = prop->value; if (prop->length == sizeof(u32) || regs[1] == 1) { - sprintf(tmp_buf, "%s@%x", - dp->name, regs[0]); + sprintf(tmp_buf, "%pOFn@%x", + dp, regs[0]); } else { - sprintf(tmp_buf, "%s@%x,%x", - dp->name, regs[0], regs[1]); + sprintf(tmp_buf, "%pOFn@%x,%x", + dp, regs[0], regs[1]); } } @@ -295,11 +295,11 @@ static void __init ieee1394_path_component(struct device_node *dp, char *tmp_buf regs = prop->value; if (regs[2] || regs[3]) { - sprintf(tmp_buf, "%s@%08x%08x,%04x%08x", - dp->name, regs[0], regs[1], regs[2], regs[3]); + sprintf(tmp_buf, "%pOFn@%08x%08x,%04x%08x", + dp, regs[0], regs[1], regs[2], regs[3]); } else { - sprintf(tmp_buf, "%s@%08x%08x", - dp->name, regs[0], regs[1]); + sprintf(tmp_buf, "%pOFn@%08x%08x", + dp, regs[0], regs[1]); } } @@ -361,7 +361,7 @@ char * __init build_path_component(struct device_node *dp) tmp_buf[0] = '\0'; __build_path_component(dp, tmp_buf); if (tmp_buf[0] == '\0') - strcpy(tmp_buf, dp->name); + snprintf(tmp_buf, sizeof(tmp_buf), "%pOFn", dp); n = prom_early_alloc(strlen(tmp_buf) + 1); strcpy(n, tmp_buf); diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c index 635d67ffc9a3..7db5aabe9708 100644 --- a/arch/sparc/kernel/viohs.c +++ b/arch/sparc/kernel/viohs.c @@ -180,11 +180,17 @@ static int send_dreg(struct vio_driver_state *vio) struct vio_dring_register pkt; char all[sizeof(struct vio_dring_register) + (sizeof(struct ldc_trans_cookie) * - dr->ncookies)]; + VIO_MAX_RING_COOKIES)]; } u; + size_t bytes = sizeof(struct vio_dring_register) + + (sizeof(struct ldc_trans_cookie) * + dr->ncookies); int i; - memset(&u, 0, sizeof(u)); + if (WARN_ON(bytes > sizeof(u))) + return -EINVAL; + + memset(&u, 0, bytes); init_tag(&u.pkt.tag, VIO_TYPE_CTRL, VIO_SUBTYPE_INFO, VIO_DRING_REG); u.pkt.dring_ident = 0; u.pkt.num_descr = dr->num_entries; @@ -206,7 +212,7 @@ static int send_dreg(struct vio_driver_state *vio) (unsigned long long) u.pkt.cookies[i].cookie_size); } - return send_ctrl(vio, &u.pkt.tag, sizeof(u)); + return send_ctrl(vio, &u.pkt.tag, bytes); } static int send_rdx(struct vio_driver_state *vio) diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index dd0b5a92ffd0..dc85570d8839 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -31,23 +31,21 @@ obj-y += $(vdso_img_objs) targets += $(vdso_img_cfiles) targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so) -export CPPFLAGS_vdso.lds += -P -C +CPPFLAGS_vdso.lds += -P -C VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ -Wl,--no-undefined \ -Wl,-z,max-page-size=8192 -Wl,-z,common-page-size=8192 \ $(DISABLE_LTO) -$(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE +$(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso) HOST_EXTRACFLAGS += -I$(srctree)/tools/include hostprogs-y += vdso2c quiet_cmd_vdso2c = VDSO2C $@ -define cmd_vdso2c - $(obj)/vdso2c $< $(<:%.dbg=%) $@ -endef + cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE $(call if_changed,vdso2c) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1a0be022f91d..e8de5de1057f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2422,7 +2422,7 @@ menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER def_bool y - depends on X86_64 && HIBERNATION + depends on HIBERNATION source "kernel/power/Kconfig" diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index b64acb08a62b..106b7d0e2dae 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -124,7 +124,7 @@ */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY) + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) /* diff --git a/arch/x86/include/asm/suspend.h b/arch/x86/include/asm/suspend.h index ecffe81ff65c..a892494ca5e4 100644 --- a/arch/x86/include/asm/suspend.h +++ b/arch/x86/include/asm/suspend.h @@ -4,3 +4,11 @@ #else # include <asm/suspend_64.h> #endif +extern unsigned long restore_jump_address __visible; +extern unsigned long jump_address_phys; +extern unsigned long restore_cr3 __visible; +extern unsigned long temp_pgt __visible; +extern unsigned long relocated_restore_code __visible; +extern int relocate_restore_code(void); +/* Defined in hibernate_asm_32/64.S */ +extern asmlinkage __visible int restore_image(void); diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 8be6afb58471..fdbd9d7b7bca 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -32,4 +32,8 @@ struct saved_context { unsigned long return_address; } __attribute__((packed)); +/* routines for saving/restoring kernel state */ +extern char core_restore_code[]; +extern char restore_registers[]; + #endif /* _ASM_X86_SUSPEND_32_H */ diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 285eb3ec4200..3736f6dc9545 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -529,14 +529,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - u32 _cbm, int closid, bool exclusive); + unsigned long cbm, int closid, bool exclusive); unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, - u32 cbm); + unsigned long cbm); enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); int rdtgroup_tasks_assigned(struct rdtgroup *r); int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm); bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d); int rdt_pseudo_lock_init(void); void rdt_pseudo_lock_release(void); diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c index 40f3903ae5d9..f8c260d522ca 100644 --- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -797,25 +797,27 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) /** * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked * @d: RDT domain - * @_cbm: CBM to test + * @cbm: CBM to test * - * @d represents a cache instance and @_cbm a capacity bitmask that is - * considered for it. Determine if @_cbm overlaps with any existing + * @d represents a cache instance and @cbm a capacity bitmask that is + * considered for it. Determine if @cbm overlaps with any existing * pseudo-locked region on @d. * - * Return: true if @_cbm overlaps with pseudo-locked region on @d, false + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * + * Return: true if @cbm overlaps with pseudo-locked region on @d, false * otherwise. */ -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm) +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm) { - unsigned long *cbm = (unsigned long *)&_cbm; - unsigned long *cbm_b; unsigned int cbm_len; + unsigned long cbm_b; if (d->plr) { cbm_len = d->plr->r->cache.cbm_len; - cbm_b = (unsigned long *)&d->plr->cbm; - if (bitmap_intersects(cbm, cbm_b, cbm_len)) + cbm_b = d->plr->cbm; + if (bitmap_intersects(&cbm, &cbm_b, cbm_len)) return true; } return false; diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 1b8e86a5d5e1..b140c68bc14b 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -975,33 +975,34 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, * is false then overlaps with any resource group or hardware entities * will be considered. * + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * * Return: false if CBM does not overlap, true if it does. */ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - u32 _cbm, int closid, bool exclusive) + unsigned long cbm, int closid, bool exclusive) { - unsigned long *cbm = (unsigned long *)&_cbm; - unsigned long *ctrl_b; enum rdtgrp_mode mode; + unsigned long ctrl_b; u32 *ctrl; int i; /* Check for any overlap with regions used by hardware directly */ if (!exclusive) { - if (bitmap_intersects(cbm, - (unsigned long *)&r->cache.shareable_bits, - r->cache.cbm_len)) + ctrl_b = r->cache.shareable_bits; + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) return true; } /* Check for overlap with other resource groups */ ctrl = d->ctrl_val; for (i = 0; i < closids_supported(); i++, ctrl++) { - ctrl_b = (unsigned long *)ctrl; + ctrl_b = *ctrl; mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && mode != RDT_MODE_PSEUDO_LOCKSETUP) { - if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) { + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) { if (exclusive) { if (mode == RDT_MODE_EXCLUSIVE) return true; @@ -1138,15 +1139,18 @@ out: * computed by first dividing the total cache size by the CBM length to * determine how many bytes each bit in the bitmask represents. The result * is multiplied with the number of bits set in the bitmask. + * + * @cbm is unsigned long, even if only 32 bits are used to make the + * bitmap functions work correctly. */ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, - struct rdt_domain *d, u32 cbm) + struct rdt_domain *d, unsigned long cbm) { struct cpu_cacheinfo *ci; unsigned int size = 0; int num_b, i; - num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len); + num_b = bitmap_weight(&cbm, r->cache.cbm_len); ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask)); for (i = 0; i < ci->num_leaves; i++) { if (ci->info_list[i].level == r->cache_level) { @@ -2353,6 +2357,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) u32 used_b = 0, unused_b = 0; u32 closid = rdtgrp->closid; struct rdt_resource *r; + unsigned long tmp_cbm; enum rdtgrp_mode mode; struct rdt_domain *d; int i, ret; @@ -2390,9 +2395,14 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) * modify the CBM based on system availability. */ cbm_ensure_valid(&d->new_ctrl, r); - if (bitmap_weight((unsigned long *) &d->new_ctrl, - r->cache.cbm_len) < - r->cache.min_cbm_bits) { + /* + * Assign the u32 CBM to an unsigned long to ensure + * that bitmap_weight() does not access out-of-bound + * memory. + */ + tmp_cbm = d->new_ctrl; + if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < + r->cache.min_cbm_bits) { rdt_last_cmd_printf("no space on %s:%d\n", r->name, d->id); return -ENOSPC; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b4866badb235..90ecc108bc8a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1251,7 +1251,7 @@ void __init setup_arch(char **cmdline_p) x86_init.hyper.guest_late_init(); e820__reserve_resources(); - e820__register_nosave_regions(max_low_pfn); + e820__register_nosave_regions(max_pfn); x86_init.resources.reserve_resources(); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d96092b35936..61ccfb13899e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -436,14 +436,18 @@ static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) static inline bool svm_sev_enabled(void) { - return max_sev_asid; + return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0; } static inline bool sev_guest(struct kvm *kvm) { +#ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return sev->active; +#else + return false; +#endif } static inline int sev_get_asid(struct kvm *kvm) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 612fd17be635..e665aa7167cf 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1572,8 +1572,12 @@ static int vmx_hv_remote_flush_tlb(struct kvm *kvm) goto out; } + /* + * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs the address of the + * base of EPT PML4 table, strip off EPT configuration information. + */ ret = hyperv_flush_guest_mapping( - to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer); + to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer & PAGE_MASK); out: spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 089e78c4effd..59274e2c1ac4 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -115,6 +115,8 @@ static inline void pgd_list_del(pgd_t *pgd) #define UNSHARED_PTRS_PER_PGD \ (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD) +#define MAX_UNSHARED_PTRS_PER_PGD \ + max_t(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD) static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm) @@ -181,6 +183,7 @@ static void pgd_dtor(pgd_t *pgd) * and initialize the kernel pmds here. */ #define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD +#define MAX_PREALLOCATED_PMDS MAX_UNSHARED_PTRS_PER_PGD /* * We allocate separate PMDs for the kernel part of the user page-table @@ -189,6 +192,7 @@ static void pgd_dtor(pgd_t *pgd) */ #define PREALLOCATED_USER_PMDS (static_cpu_has(X86_FEATURE_PTI) ? \ KERNEL_PGD_PTRS : 0) +#define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) { @@ -210,7 +214,9 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) /* No need to prepopulate any pagetable entries in non-PAE modes. */ #define PREALLOCATED_PMDS 0 +#define MAX_PREALLOCATED_PMDS 0 #define PREALLOCATED_USER_PMDS 0 +#define MAX_PREALLOCATED_USER_PMDS 0 #endif /* CONFIG_X86_PAE */ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) @@ -428,8 +434,8 @@ static inline void _pgd_free(pgd_t *pgd) pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; - pmd_t *u_pmds[PREALLOCATED_USER_PMDS]; - pmd_t *pmds[PREALLOCATED_PMDS]; + pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS]; + pmd_t *pmds[MAX_PREALLOCATED_PMDS]; pgd = _pgd_alloc(); diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index a4701389562c..37923d715741 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -7,4 +7,4 @@ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_cpu.o := $(nostackp) obj-$(CONFIG_PM_SLEEP) += cpu.o -obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o +obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o hibernate.o diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c new file mode 100644 index 000000000000..bcddf09b5aa3 --- /dev/null +++ b/arch/x86/power/hibernate.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hibernation support for x86 + * + * Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl> + * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz> + * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org> + */ +#include <linux/gfp.h> +#include <linux/smp.h> +#include <linux/suspend.h> +#include <linux/scatterlist.h> +#include <linux/kdebug.h> + +#include <crypto/hash.h> + +#include <asm/e820/api.h> +#include <asm/init.h> +#include <asm/proto.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/mtrr.h> +#include <asm/sections.h> +#include <asm/suspend.h> +#include <asm/tlbflush.h> + +/* + * Address to jump to in the last phase of restore in order to get to the image + * kernel's text (this value is passed in the image header). + */ +unsigned long restore_jump_address __visible; +unsigned long jump_address_phys; + +/* + * Value of the cr3 register from before the hibernation (this value is passed + * in the image header). + */ +unsigned long restore_cr3 __visible; +unsigned long temp_pgt __visible; +unsigned long relocated_restore_code __visible; + +/** + * pfn_is_nosave - check if given pfn is in the 'nosave' section + */ +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn; + unsigned long nosave_end_pfn; + + nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT; + nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT; + + return pfn >= nosave_begin_pfn && pfn < nosave_end_pfn; +} + + +#define MD5_DIGEST_SIZE 16 + +struct restore_data_record { + unsigned long jump_address; + unsigned long jump_address_phys; + unsigned long cr3; + unsigned long magic; + u8 e820_digest[MD5_DIGEST_SIZE]; +}; + +#if IS_BUILTIN(CONFIG_CRYPTO_MD5) +/** + * get_e820_md5 - calculate md5 according to given e820 table + * + * @table: the e820 table to be calculated + * @buf: the md5 result to be stored to + */ +static int get_e820_md5(struct e820_table *table, void *buf) +{ + struct crypto_shash *tfm; + struct shash_desc *desc; + int size; + int ret = 0; + + tfm = crypto_alloc_shash("md5", 0, 0); + if (IS_ERR(tfm)) + return -ENOMEM; + + desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm), + GFP_KERNEL); + if (!desc) { + ret = -ENOMEM; + goto free_tfm; + } + + desc->tfm = tfm; + desc->flags = 0; + + size = offsetof(struct e820_table, entries) + + sizeof(struct e820_entry) * table->nr_entries; + + if (crypto_shash_digest(desc, (u8 *)table, size, buf)) + ret = -EINVAL; + + kzfree(desc); + +free_tfm: + crypto_free_shash(tfm); + return ret; +} + +static int hibernation_e820_save(void *buf) +{ + return get_e820_md5(e820_table_firmware, buf); +} + +static bool hibernation_e820_mismatch(void *buf) +{ + int ret; + u8 result[MD5_DIGEST_SIZE]; + + memset(result, 0, MD5_DIGEST_SIZE); + /* If there is no digest in suspend kernel, let it go. */ + if (!memcmp(result, buf, MD5_DIGEST_SIZE)) + return false; + + ret = get_e820_md5(e820_table_firmware, result); + if (ret) + return true; + + return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false; +} +#else +static int hibernation_e820_save(void *buf) +{ + return 0; +} + +static bool hibernation_e820_mismatch(void *buf) +{ + /* If md5 is not builtin for restore kernel, let it go. */ + return false; +} +#endif + +#ifdef CONFIG_X86_64 +#define RESTORE_MAGIC 0x23456789ABCDEF01UL +#else +#define RESTORE_MAGIC 0x12345678UL +#endif + +/** + * arch_hibernation_header_save - populate the architecture specific part + * of a hibernation image header + * @addr: address to save the data at + */ +int arch_hibernation_header_save(void *addr, unsigned int max_size) +{ + struct restore_data_record *rdr = addr; + + if (max_size < sizeof(struct restore_data_record)) + return -EOVERFLOW; + rdr->magic = RESTORE_MAGIC; + rdr->jump_address = (unsigned long)restore_registers; + rdr->jump_address_phys = __pa_symbol(restore_registers); + + /* + * The restore code fixes up CR3 and CR4 in the following sequence: + * + * [in hibernation asm] + * 1. CR3 <= temporary page tables + * 2. CR4 <= mmu_cr4_features (from the kernel that restores us) + * 3. CR3 <= rdr->cr3 + * 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel) + * [in restore_processor_state()] + * 5. CR4 <= saved CR4 + * 6. CR3 <= saved CR3 + * + * Our mmu_cr4_features has CR4.PCIDE=0, and toggling + * CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so + * rdr->cr3 needs to point to valid page tables but must not + * have any of the PCID bits set. + */ + rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK; + + return hibernation_e820_save(rdr->e820_digest); +} + +/** + * arch_hibernation_header_restore - read the architecture specific data + * from the hibernation image header + * @addr: address to read the data from + */ +int arch_hibernation_header_restore(void *addr) +{ + struct restore_data_record *rdr = addr; + + if (rdr->magic != RESTORE_MAGIC) { + pr_crit("Unrecognized hibernate image header format!\n"); + return -EINVAL; + } + + restore_jump_address = rdr->jump_address; + jump_address_phys = rdr->jump_address_phys; + restore_cr3 = rdr->cr3; + + if (hibernation_e820_mismatch(rdr->e820_digest)) { + pr_crit("Hibernate inconsistent memory map detected!\n"); + return -ENODEV; + } + + return 0; +} + +int relocate_restore_code(void) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + relocated_restore_code = get_safe_page(GFP_ATOMIC); + if (!relocated_restore_code) + return -ENOMEM; + + memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE); + + /* Make the page containing the relocated code executable */ + pgd = (pgd_t *)__va(read_cr3_pa()) + + pgd_index(relocated_restore_code); + p4d = p4d_offset(pgd, relocated_restore_code); + if (p4d_large(*p4d)) { + set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX)); + goto out; + } + pud = pud_offset(p4d, relocated_restore_code); + if (pud_large(*pud)) { + set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); + goto out; + } + pmd = pmd_offset(pud, relocated_restore_code); + if (pmd_large(*pmd)) { + set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); + goto out; + } + pte = pte_offset_kernel(pmd, relocated_restore_code); + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); +out: + __flush_tlb_all(); + return 0; +} diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index afc4ed7b1578..15695e30f982 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -14,9 +14,7 @@ #include <asm/pgtable.h> #include <asm/mmzone.h> #include <asm/sections.h> - -/* Defined in hibernate_asm_32.S */ -extern int restore_image(void); +#include <asm/suspend.h> /* Pointer to the temporary resume page tables */ pgd_t *resume_pg_dir; @@ -145,6 +143,32 @@ static inline void resume_init_first_level_page_table(pgd_t *pg_dir) #endif } +static int set_up_temporary_text_mapping(pgd_t *pgd_base) +{ + pgd_t *pgd; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_base + pgd_index(restore_jump_address); + + pmd = resume_one_md_table_init(pgd); + if (!pmd) + return -ENOMEM; + + if (boot_cpu_has(X86_FEATURE_PSE)) { + set_pmd(pmd + pmd_index(restore_jump_address), + __pmd((jump_address_phys & PMD_MASK) | pgprot_val(PAGE_KERNEL_LARGE_EXEC))); + } else { + pte = resume_one_page_table_init(pmd); + if (!pte) + return -ENOMEM; + set_pte(pte + pte_index(restore_jump_address), + __pte((jump_address_phys & PAGE_MASK) | pgprot_val(PAGE_KERNEL_EXEC))); + } + + return 0; +} + asmlinkage int swsusp_arch_resume(void) { int error; @@ -154,22 +178,22 @@ asmlinkage int swsusp_arch_resume(void) return -ENOMEM; resume_init_first_level_page_table(resume_pg_dir); + + error = set_up_temporary_text_mapping(resume_pg_dir); + if (error) + return error; + error = resume_physical_mapping_init(resume_pg_dir); if (error) return error; + temp_pgt = __pa(resume_pg_dir); + + error = relocate_restore_code(); + if (error) + return error; + /* We have got enough memory and from now on we cannot recover */ restore_image(); return 0; } - -/* - * pfn_is_nosave - check if given pfn is in the 'nosave' section - */ - -int pfn_is_nosave(unsigned long pfn) -{ - unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT; - unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT; - return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn); -} diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index f8e3b668d20b..239f424ccb29 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -26,26 +26,6 @@ #include <asm/suspend.h> #include <asm/tlbflush.h> -/* Defined in hibernate_asm_64.S */ -extern asmlinkage __visible int restore_image(void); - -/* - * Address to jump to in the last phase of restore in order to get to the image - * kernel's text (this value is passed in the image header). - */ -unsigned long restore_jump_address __visible; -unsigned long jump_address_phys; - -/* - * Value of the cr3 register from before the hibernation (this value is passed - * in the image header). - */ -unsigned long restore_cr3 __visible; - -unsigned long temp_level4_pgt __visible; - -unsigned long relocated_restore_code __visible; - static int set_up_temporary_text_mapping(pgd_t *pgd) { pmd_t *pmd; @@ -141,46 +121,7 @@ static int set_up_temporary_mappings(void) return result; } - temp_level4_pgt = __pa(pgd); - return 0; -} - -static int relocate_restore_code(void) -{ - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - relocated_restore_code = get_safe_page(GFP_ATOMIC); - if (!relocated_restore_code) - return -ENOMEM; - - memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE); - - /* Make the page containing the relocated code executable */ - pgd = (pgd_t *)__va(read_cr3_pa()) + - pgd_index(relocated_restore_code); - p4d = p4d_offset(pgd, relocated_restore_code); - if (p4d_large(*p4d)) { - set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX)); - goto out; - } - pud = pud_offset(p4d, relocated_restore_code); - if (pud_large(*pud)) { - set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); - goto out; - } - pmd = pmd_offset(pud, relocated_restore_code); - if (pmd_large(*pmd)) { - set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); - goto out; - } - pte = pte_offset_kernel(pmd, relocated_restore_code); - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); -out: - __flush_tlb_all(); + temp_pgt = __pa(pgd); return 0; } @@ -200,166 +141,3 @@ asmlinkage int swsusp_arch_resume(void) restore_image(); return 0; } - -/* - * pfn_is_nosave - check if given pfn is in the 'nosave' section - */ - -int pfn_is_nosave(unsigned long pfn) -{ - unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT; - unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT; - return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn); -} - -#define MD5_DIGEST_SIZE 16 - -struct restore_data_record { - unsigned long jump_address; - unsigned long jump_address_phys; - unsigned long cr3; - unsigned long magic; - u8 e820_digest[MD5_DIGEST_SIZE]; -}; - -#define RESTORE_MAGIC 0x23456789ABCDEF01UL - -#if IS_BUILTIN(CONFIG_CRYPTO_MD5) -/** - * get_e820_md5 - calculate md5 according to given e820 table - * - * @table: the e820 table to be calculated - * @buf: the md5 result to be stored to - */ -static int get_e820_md5(struct e820_table *table, void *buf) -{ - struct crypto_shash *tfm; - struct shash_desc *desc; - int size; - int ret = 0; - - tfm = crypto_alloc_shash("md5", 0, 0); - if (IS_ERR(tfm)) - return -ENOMEM; - - desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm), - GFP_KERNEL); - if (!desc) { - ret = -ENOMEM; - goto free_tfm; - } - - desc->tfm = tfm; - desc->flags = 0; - - size = offsetof(struct e820_table, entries) + - sizeof(struct e820_entry) * table->nr_entries; - - if (crypto_shash_digest(desc, (u8 *)table, size, buf)) - ret = -EINVAL; - - kzfree(desc); - -free_tfm: - crypto_free_shash(tfm); - return ret; -} - -static void hibernation_e820_save(void *buf) -{ - get_e820_md5(e820_table_firmware, buf); -} - -static bool hibernation_e820_mismatch(void *buf) -{ - int ret; - u8 result[MD5_DIGEST_SIZE]; - - memset(result, 0, MD5_DIGEST_SIZE); - /* If there is no digest in suspend kernel, let it go. */ - if (!memcmp(result, buf, MD5_DIGEST_SIZE)) - return false; - - ret = get_e820_md5(e820_table_firmware, result); - if (ret) - return true; - - return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false; -} -#else -static void hibernation_e820_save(void *buf) -{ -} - -static bool hibernation_e820_mismatch(void *buf) -{ - /* If md5 is not builtin for restore kernel, let it go. */ - return false; -} -#endif - -/** - * arch_hibernation_header_save - populate the architecture specific part - * of a hibernation image header - * @addr: address to save the data at - */ -int arch_hibernation_header_save(void *addr, unsigned int max_size) -{ - struct restore_data_record *rdr = addr; - - if (max_size < sizeof(struct restore_data_record)) - return -EOVERFLOW; - rdr->jump_address = (unsigned long)restore_registers; - rdr->jump_address_phys = __pa_symbol(restore_registers); - - /* - * The restore code fixes up CR3 and CR4 in the following sequence: - * - * [in hibernation asm] - * 1. CR3 <= temporary page tables - * 2. CR4 <= mmu_cr4_features (from the kernel that restores us) - * 3. CR3 <= rdr->cr3 - * 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel) - * [in restore_processor_state()] - * 5. CR4 <= saved CR4 - * 6. CR3 <= saved CR3 - * - * Our mmu_cr4_features has CR4.PCIDE=0, and toggling - * CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so - * rdr->cr3 needs to point to valid page tables but must not - * have any of the PCID bits set. - */ - rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK; - - rdr->magic = RESTORE_MAGIC; - - hibernation_e820_save(rdr->e820_digest); - - return 0; -} - -/** - * arch_hibernation_header_restore - read the architecture specific data - * from the hibernation image header - * @addr: address to read the data from - */ -int arch_hibernation_header_restore(void *addr) -{ - struct restore_data_record *rdr = addr; - - restore_jump_address = rdr->jump_address; - jump_address_phys = rdr->jump_address_phys; - restore_cr3 = rdr->cr3; - - if (rdr->magic != RESTORE_MAGIC) { - pr_crit("Unrecognized hibernate image header format!\n"); - return -EINVAL; - } - - if (hibernation_e820_mismatch(rdr->e820_digest)) { - pr_crit("Hibernate inconsistent memory map detected!\n"); - return -ENODEV; - } - - return 0; -} diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S index 6e56815e13a0..6fe383002125 100644 --- a/arch/x86/power/hibernate_asm_32.S +++ b/arch/x86/power/hibernate_asm_32.S @@ -12,6 +12,7 @@ #include <asm/page_types.h> #include <asm/asm-offsets.h> #include <asm/processor-flags.h> +#include <asm/frame.h> .text @@ -24,13 +25,30 @@ ENTRY(swsusp_arch_suspend) pushfl popl saved_context_eflags + /* save cr3 */ + movl %cr3, %eax + movl %eax, restore_cr3 + + FRAME_BEGIN call swsusp_save + FRAME_END ret +ENDPROC(swsusp_arch_suspend) ENTRY(restore_image) + /* prepare to jump to the image kernel */ + movl restore_jump_address, %ebx + movl restore_cr3, %ebp + movl mmu_cr4_features, %ecx - movl resume_pg_dir, %eax - subl $__PAGE_OFFSET, %eax + + /* jump to relocated restore code */ + movl relocated_restore_code, %eax + jmpl *%eax + +/* code below has been relocated to a safe page */ +ENTRY(core_restore_code) + movl temp_pgt, %eax movl %eax, %cr3 jecxz 1f # cr4 Pentium and higher, skip if zero @@ -49,7 +67,7 @@ copy_loop: movl pbe_address(%edx), %esi movl pbe_orig_address(%edx), %edi - movl $1024, %ecx + movl $(PAGE_SIZE >> 2), %ecx rep movsl @@ -58,10 +76,13 @@ copy_loop: .p2align 4,,7 done: + jmpl *%ebx + + /* code below belongs to the image kernel */ + .align PAGE_SIZE +ENTRY(restore_registers) /* go back to the original page tables */ - movl $swapper_pg_dir, %eax - subl $__PAGE_OFFSET, %eax - movl %eax, %cr3 + movl %ebp, %cr3 movl mmu_cr4_features, %ecx jecxz 1f # cr4 Pentium and higher, skip if zero movl %ecx, %cr4; # turn PGE back on @@ -82,4 +103,8 @@ done: xorl %eax, %eax + /* tell the hibernation core that we've just restored the memory */ + movl %eax, in_suspend + ret +ENDPROC(restore_registers) diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index fd369a6e9ff8..3008baa2fa95 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -59,7 +59,7 @@ ENTRY(restore_image) movq restore_cr3(%rip), %r9 /* prepare to switch to temporary page tables */ - movq temp_level4_pgt(%rip), %rax + movq temp_pgt(%rip), %rax movq mmu_cr4_features(%rip), %rbx /* prepare to copy image data to their original locations */ diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 8e20a0677dcf..8ac93fcbaa2e 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -310,6 +310,7 @@ static void scale_up(struct rq_wb *rwb) rq_depth_scale_up(&rwb->rq_depth); calc_wb_limits(rwb); rwb->unknown_cnt = 0; + rwb_wake_all(rwb); rwb_trace_step(rwb, "scale up"); } @@ -318,7 +319,6 @@ static void scale_down(struct rq_wb *rwb, bool hard_throttle) rq_depth_scale_down(&rwb->rq_depth, hard_throttle); calc_wb_limits(rwb); rwb->unknown_cnt = 0; - rwb_wake_all(rwb); rwb_trace_step(rwb, "scale down"); } diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c index cf4fc0161164..e43cb71b6972 100644 --- a/drivers/acpi/acpi_lpit.c +++ b/drivers/acpi/acpi_lpit.c @@ -117,11 +117,17 @@ static void lpit_update_residency(struct lpit_residency_info *info, if (!info->iomem_addr) return; + if (!(acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0)) + return; + /* Silently fail, if cpuidle attribute group is not present */ sysfs_add_file_to_group(&cpu_subsys.dev_root->kobj, &dev_attr_low_power_idle_system_residency_us.attr, "cpuidle"); } else if (info->gaddr.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) { + if (!(acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0)) + return; + /* Silently fail, if cpuidle attribute group is not present */ sysfs_add_file_to_group(&cpu_subsys.dev_root->kobj, &dev_attr_low_power_idle_cpu_residency_us.attr, diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index d9ce4b162e2c..217a782c3e55 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1061,9 +1061,9 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps) { struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum); struct cpc_register_resource *highest_reg, *lowest_reg, - *lowest_non_linear_reg, *nominal_reg, + *lowest_non_linear_reg, *nominal_reg, *guaranteed_reg, *low_freq_reg = NULL, *nom_freq_reg = NULL; - u64 high, low, nom, min_nonlinear, low_f = 0, nom_f = 0; + u64 high, low, guaranteed, nom, min_nonlinear, low_f = 0, nom_f = 0; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum); struct cppc_pcc_data *pcc_ss_data = NULL; int ret = 0, regs_in_pcc = 0; @@ -1079,6 +1079,7 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps) nominal_reg = &cpc_desc->cpc_regs[NOMINAL_PERF]; low_freq_reg = &cpc_desc->cpc_regs[LOWEST_FREQ]; nom_freq_reg = &cpc_desc->cpc_regs[NOMINAL_FREQ]; + guaranteed_reg = &cpc_desc->cpc_regs[GUARANTEED_PERF]; /* Are any of the regs PCC ?*/ if (CPC_IN_PCC(highest_reg) || CPC_IN_PCC(lowest_reg) || @@ -1107,6 +1108,9 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps) cpc_read(cpunum, nominal_reg, &nom); perf_caps->nominal_perf = nom; + cpc_read(cpunum, guaranteed_reg, &guaranteed); + perf_caps->guaranteed_perf = guaranteed; + cpc_read(cpunum, lowest_non_linear_reg, &min_nonlinear); perf_caps->lowest_nonlinear_perf = min_nonlinear; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 4b5714199490..7f38a92b444a 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -467,6 +467,10 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on, return -EAGAIN; } + /* Default to shallowest state. */ + if (!genpd->gov) + genpd->state_idx = 0; + if (genpd->power_off) { int ret; @@ -1687,6 +1691,8 @@ int pm_genpd_init(struct generic_pm_domain *genpd, ret = genpd_set_default_power_state(genpd); if (ret) return ret; + } else if (!gov) { + pr_warn("%s : no governor for states\n", genpd->name); } device_initialize(&genpd->dev); @@ -2478,8 +2484,8 @@ static int genpd_iterate_idle_states(struct device_node *dn, * * Returns the device states parsed from the OF node. The memory for the states * is allocated by this function and is the responsibility of the caller to - * free the memory after use. If no domain idle states is found it returns - * -EINVAL and in case of errors, a negative error code. + * free the memory after use. If any or zero compatible domain idle states is + * found it returns 0 and in case of errors, a negative error code is returned. */ int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n) @@ -2488,8 +2494,14 @@ int of_genpd_parse_idle_states(struct device_node *dn, int ret; ret = genpd_iterate_idle_states(dn, NULL); - if (ret <= 0) - return ret < 0 ? ret : -EINVAL; + if (ret < 0) + return ret; + + if (!ret) { + *states = NULL; + *n = 0; + return 0; + } st = kcalloc(ret, sizeof(*st), GFP_KERNEL); if (!st) diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index e182f6019f68..2fee65886d50 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -1322,7 +1322,7 @@ static int qca_init_regulators(struct qca_power *qca, { int i; - qca->vreg_bulk = devm_kzalloc(qca->dev, num_vregs * + qca->vreg_bulk = devm_kcalloc(qca->dev, num_vregs, sizeof(struct regulator_bulk_data), GFP_KERNEL); if (!qca->vreg_bulk) diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 30f302149730..fd25c21cee72 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -428,7 +428,7 @@ MODULE_LICENSE("GPL"); late_initcall(cppc_cpufreq_init); -static const struct acpi_device_id cppc_acpi_ids[] = { +static const struct acpi_device_id cppc_acpi_ids[] __used = { {ACPI_PROCESSOR_DEVICE_HID, }, {} }; diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index fe14c57de6ca..b1c5468dca16 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -58,6 +58,7 @@ static const struct of_device_id whitelist[] __initconst = { { .compatible = "renesas,r8a73a4", }, { .compatible = "renesas,r8a7740", }, { .compatible = "renesas,r8a7743", }, + { .compatible = "renesas,r8a7744", }, { .compatible = "renesas,r8a7745", }, { .compatible = "renesas,r8a7778", }, { .compatible = "renesas,r8a7779", }, @@ -78,7 +79,10 @@ static const struct of_device_id whitelist[] __initconst = { { .compatible = "rockchip,rk3328", }, { .compatible = "rockchip,rk3366", }, { .compatible = "rockchip,rk3368", }, - { .compatible = "rockchip,rk3399", }, + { .compatible = "rockchip,rk3399", + .data = &(struct cpufreq_dt_platform_data) + { .have_governor_per_policy = true, }, + }, { .compatible = "st-ericsson,u8500", }, { .compatible = "st-ericsson,u8540", }, diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 0a9ebf00be46..e58bfcb1169e 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -32,6 +32,7 @@ struct private_data { struct device *cpu_dev; struct thermal_cooling_device *cdev; const char *reg_name; + bool have_static_opps; }; static struct freq_attr *cpufreq_dt_attr[] = { @@ -204,6 +205,15 @@ static int cpufreq_init(struct cpufreq_policy *policy) } } + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + ret = -ENOMEM; + goto out_put_regulator; + } + + priv->reg_name = name; + priv->opp_table = opp_table; + /* * Initialize OPP tables for all policy->cpus. They will be shared by * all CPUs which have marked their CPUs shared with OPP bindings. @@ -214,7 +224,8 @@ static int cpufreq_init(struct cpufreq_policy *policy) * * OPPs might be populated at runtime, don't check for error here */ - dev_pm_opp_of_cpumask_add_table(policy->cpus); + if (!dev_pm_opp_of_cpumask_add_table(policy->cpus)) + priv->have_static_opps = true; /* * But we need OPP table to function so if it is not there let's @@ -240,19 +251,10 @@ static int cpufreq_init(struct cpufreq_policy *policy) __func__, ret); } - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) { - ret = -ENOMEM; - goto out_free_opp; - } - - priv->reg_name = name; - priv->opp_table = opp_table; - ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table); if (ret) { dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret); - goto out_free_priv; + goto out_free_opp; } priv->cpu_dev = cpu_dev; @@ -282,10 +284,11 @@ static int cpufreq_init(struct cpufreq_policy *policy) out_free_cpufreq_table: dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table); -out_free_priv: - kfree(priv); out_free_opp: - dev_pm_opp_of_cpumask_remove_table(policy->cpus); + if (priv->have_static_opps) + dev_pm_opp_of_cpumask_remove_table(policy->cpus); + kfree(priv); +out_put_regulator: if (name) dev_pm_opp_put_regulators(opp_table); out_put_clk: @@ -300,7 +303,8 @@ static int cpufreq_exit(struct cpufreq_policy *policy) cpufreq_cooling_unregister(priv->cdev); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); - dev_pm_opp_of_cpumask_remove_table(policy->related_cpus); + if (priv->have_static_opps) + dev_pm_opp_of_cpumask_remove_table(policy->related_cpus); if (priv->reg_name) dev_pm_opp_put_regulators(priv->opp_table); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index f53fb41efb7b..7aa3dcad2175 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -403,7 +403,7 @@ EXPORT_SYMBOL_GPL(cpufreq_freq_transition_begin); void cpufreq_freq_transition_end(struct cpufreq_policy *policy, struct cpufreq_freqs *freqs, int transition_failed) { - if (unlikely(WARN_ON(!policy->transition_ongoing))) + if (WARN_ON(!policy->transition_ongoing)) return; cpufreq_notify_post_transition(policy, freqs, transition_failed); diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index f20f20a77d4d..4268f87e99fc 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -80,8 +80,10 @@ static unsigned int cs_dbs_update(struct cpufreq_policy *policy) * changed in the meantime, so fall back to current frequency in that * case. */ - if (requested_freq > policy->max || requested_freq < policy->min) + if (requested_freq > policy->max || requested_freq < policy->min) { requested_freq = policy->cur; + dbs_info->requested_freq = requested_freq; + } freq_step = get_freq_step(cs_tuners, policy); @@ -92,7 +94,7 @@ static unsigned int cs_dbs_update(struct cpufreq_policy *policy) if (policy_dbs->idle_periods < UINT_MAX) { unsigned int freq_steps = policy_dbs->idle_periods * freq_step; - if (requested_freq > freq_steps) + if (requested_freq > policy->min + freq_steps) requested_freq -= freq_steps; else requested_freq = policy->min; diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index b2ff423ad7f8..8cfee0ab804b 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -12,6 +12,7 @@ #include <linux/cpu_cooling.h> #include <linux/err.h> #include <linux/module.h> +#include <linux/nvmem-consumer.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/pm_opp.h> @@ -290,20 +291,32 @@ put_node: #define OCOTP_CFG3_6ULL_SPEED_792MHZ 0x2 #define OCOTP_CFG3_6ULL_SPEED_900MHZ 0x3 -static void imx6ul_opp_check_speed_grading(struct device *dev) +static int imx6ul_opp_check_speed_grading(struct device *dev) { - struct device_node *np; - void __iomem *base; u32 val; + int ret = 0; - np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-ocotp"); - if (!np) - return; + if (of_find_property(dev->of_node, "nvmem-cells", NULL)) { + ret = nvmem_cell_read_u32(dev, "speed_grade", &val); + if (ret) + return ret; + } else { + struct device_node *np; + void __iomem *base; + + np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-ocotp"); + if (!np) + return -ENOENT; + + base = of_iomap(np, 0); + of_node_put(np); + if (!base) { + dev_err(dev, "failed to map ocotp\n"); + return -EFAULT; + } - base = of_iomap(np, 0); - if (!base) { - dev_err(dev, "failed to map ocotp\n"); - goto put_node; + val = readl_relaxed(base + OCOTP_CFG3); + iounmap(base); } /* @@ -314,7 +327,6 @@ static void imx6ul_opp_check_speed_grading(struct device *dev) * 2b'11: 900000000Hz on i.MX6ULL only; * We need to set the max speed of ARM according to fuse map. */ - val = readl_relaxed(base + OCOTP_CFG3); val >>= OCOTP_CFG3_SPEED_SHIFT; val &= 0x3; @@ -334,9 +346,7 @@ static void imx6ul_opp_check_speed_grading(struct device *dev) dev_warn(dev, "failed to disable 900MHz OPP\n"); } - iounmap(base); -put_node: - of_node_put(np); + return ret; } static int imx6q_cpufreq_probe(struct platform_device *pdev) @@ -394,10 +404,18 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev) } if (of_machine_is_compatible("fsl,imx6ul") || - of_machine_is_compatible("fsl,imx6ull")) - imx6ul_opp_check_speed_grading(cpu_dev); - else + of_machine_is_compatible("fsl,imx6ull")) { + ret = imx6ul_opp_check_speed_grading(cpu_dev); + if (ret == -EPROBE_DEFER) + return ret; + if (ret) { + dev_err(cpu_dev, "failed to read ocotp: %d\n", + ret); + return ret; + } + } else { imx6q_opp_check_speed_grading(cpu_dev); + } /* Because we have added the OPPs here, we must free them */ free_opp = true; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b6a1aadaff9f..2a99e2fd9412 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -373,10 +373,28 @@ static void intel_pstate_set_itmt_prio(int cpu) } } } + +static int intel_pstate_get_cppc_guranteed(int cpu) +{ + struct cppc_perf_caps cppc_perf; + int ret; + + ret = cppc_get_perf_caps(cpu, &cppc_perf); + if (ret) + return ret; + + return cppc_perf.guaranteed_perf; +} + #else static void intel_pstate_set_itmt_prio(int cpu) { } + +static int intel_pstate_get_cppc_guranteed(int cpu) +{ + return -ENOTSUPP; +} #endif static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) @@ -699,9 +717,29 @@ static ssize_t show_energy_performance_preference( cpufreq_freq_attr_rw(energy_performance_preference); +static ssize_t show_base_frequency(struct cpufreq_policy *policy, char *buf) +{ + struct cpudata *cpu; + u64 cap; + int ratio; + + ratio = intel_pstate_get_cppc_guranteed(policy->cpu); + if (ratio <= 0) { + rdmsrl_on_cpu(policy->cpu, MSR_HWP_CAPABILITIES, &cap); + ratio = HWP_GUARANTEED_PERF(cap); + } + + cpu = all_cpu_data[policy->cpu]; + + return sprintf(buf, "%d\n", ratio * cpu->pstate.scaling); +} + +cpufreq_freq_attr_ro(base_frequency); + static struct freq_attr *hwp_cpufreq_attrs[] = { &energy_performance_preference, &energy_performance_available_preferences, + &base_frequency, NULL, }; diff --git a/drivers/cpufreq/mvebu-cpufreq.c b/drivers/cpufreq/mvebu-cpufreq.c index 31513bd42705..6d33a639f902 100644 --- a/drivers/cpufreq/mvebu-cpufreq.c +++ b/drivers/cpufreq/mvebu-cpufreq.c @@ -84,9 +84,10 @@ static int __init armada_xp_pmsu_cpufreq_init(void) ret = dev_pm_opp_add(cpu_dev, clk_get_rate(clk) / 2, 0); if (ret) { + dev_pm_opp_remove(cpu_dev, clk_get_rate(clk)); clk_put(clk); dev_err(cpu_dev, "Failed to register OPPs\n"); - goto opp_register_failed; + return ret; } ret = dev_pm_opp_set_sharing_cpus(cpu_dev, @@ -99,11 +100,5 @@ static int __init armada_xp_pmsu_cpufreq_init(void) platform_device_register_simple("cpufreq-dt", -1, NULL, 0); return 0; - -opp_register_failed: - /* As registering has failed remove all the opp for all cpus */ - dev_pm_opp_cpumask_remove_table(cpu_possible_mask); - - return ret; } device_initcall(armada_xp_pmsu_cpufreq_init); diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c index 5d31c2db12a3..dbecd7667db2 100644 --- a/drivers/cpufreq/s5pv210-cpufreq.c +++ b/drivers/cpufreq/s5pv210-cpufreq.c @@ -611,8 +611,8 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev) for_each_compatible_node(np, NULL, "samsung,s5pv210-dmc") { id = of_alias_get_id(np, "dmc"); if (id < 0 || id >= ARRAY_SIZE(dmc_base)) { - pr_err("%s: failed to get alias of dmc node '%s'\n", - __func__, np->name); + pr_err("%s: failed to get alias of dmc node '%pOFn'\n", + __func__, np); of_node_put(np); return id; } diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 1f59966573aa..f1e09022b819 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -121,7 +121,7 @@ static struct cpufreq_frequency_table *init_vhint_table( void *virt; virt = dma_alloc_coherent(bpmp->dev, sizeof(*data), &phys, - GFP_KERNEL | GFP_DMA32); + GFP_KERNEL); if (!virt) return ERR_PTR(-ENOMEM); diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 6df894d65d9e..4a97446f66d8 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -247,17 +247,17 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, if (!cpuidle_state_is_coupled(drv, index)) local_irq_enable(); - diff = ktime_us_delta(time_end, time_start); - if (diff > INT_MAX) - diff = INT_MAX; - - dev->last_residency = (int) diff; - if (entered_state >= 0) { - /* Update cpuidle counters */ - /* This can be moved to within driver enter routine + /* + * Update cpuidle counters + * This can be moved to within driver enter routine, * but that results in multiple copies of same code. */ + diff = ktime_us_delta(time_end, time_start); + if (diff > INT_MAX) + diff = INT_MAX; + + dev->last_residency = (int)diff; dev->states_usage[entered_state].time += dev->last_residency; dev->states_usage[entered_state].usage++; } else { diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c index 704880a6612a..f0dddc66af26 100644 --- a/drivers/cpuidle/governors/ladder.c +++ b/drivers/cpuidle/governors/ladder.c @@ -80,7 +80,7 @@ static int ladder_select_state(struct cpuidle_driver *drv, last_state = &ldev->states[last_idx]; - last_residency = cpuidle_get_last_residency(dev) - drv->states[last_idx].exit_latency; + last_residency = dev->last_residency - drv->states[last_idx].exit_latency; /* consider promotion */ if (last_idx < drv->state_count - 1 && diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index e26a40971b26..575a68f31761 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -124,7 +124,6 @@ struct menu_device { int tick_wakeup; unsigned int next_timer_us; - unsigned int predicted_us; unsigned int bucket; unsigned int correction_factor[BUCKETS]; unsigned int intervals[INTERVALS]; @@ -197,10 +196,11 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev); * of points is below a threshold. If it is... then use the * average of these 8 points as the estimated value. */ -static unsigned int get_typical_interval(struct menu_device *data) +static unsigned int get_typical_interval(struct menu_device *data, + unsigned int predicted_us) { int i, divisor; - unsigned int max, thresh, avg; + unsigned int min, max, thresh, avg; uint64_t sum, variance; thresh = UINT_MAX; /* Discard outliers above this value */ @@ -208,6 +208,7 @@ static unsigned int get_typical_interval(struct menu_device *data) again: /* First calculate the average of past intervals */ + min = UINT_MAX; max = 0; sum = 0; divisor = 0; @@ -218,8 +219,19 @@ again: divisor++; if (value > max) max = value; + + if (value < min) + min = value; } } + + /* + * If the result of the computation is going to be discarded anyway, + * avoid the computation altogether. + */ + if (min >= predicted_us) + return UINT_MAX; + if (divisor == INTERVALS) avg = sum >> INTERVAL_SHIFT; else @@ -286,10 +298,9 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, struct menu_device *data = this_cpu_ptr(&menu_devices); int latency_req = cpuidle_governor_latency_req(dev->cpu); int i; - int first_idx; int idx; unsigned int interactivity_req; - unsigned int expected_interval; + unsigned int predicted_us; unsigned long nr_iowaiters, cpu_load; ktime_t delta_next; @@ -298,50 +309,36 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, data->needs_update = 0; } - /* Special case when user has set very strict latency requirement */ - if (unlikely(latency_req == 0)) { - *stop_tick = false; - return 0; - } - /* determine the expected residency time, round up */ data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next)); get_iowait_load(&nr_iowaiters, &cpu_load); data->bucket = which_bucket(data->next_timer_us, nr_iowaiters); + if (unlikely(drv->state_count <= 1 || latency_req == 0) || + ((data->next_timer_us < drv->states[1].target_residency || + latency_req < drv->states[1].exit_latency) && + !drv->states[0].disabled && !dev->states_usage[0].disable)) { + /* + * In this case state[0] will be used no matter what, so return + * it right away and keep the tick running. + */ + *stop_tick = false; + return 0; + } + /* * Force the result of multiplication to be 64 bits even if both * operands are 32 bits. * Make sure to round up for half microseconds. */ - data->predicted_us = DIV_ROUND_CLOSEST_ULL((uint64_t)data->next_timer_us * + predicted_us = DIV_ROUND_CLOSEST_ULL((uint64_t)data->next_timer_us * data->correction_factor[data->bucket], RESOLUTION * DECAY); - - expected_interval = get_typical_interval(data); - expected_interval = min(expected_interval, data->next_timer_us); - - first_idx = 0; - if (drv->states[0].flags & CPUIDLE_FLAG_POLLING) { - struct cpuidle_state *s = &drv->states[1]; - unsigned int polling_threshold; - - /* - * Default to a physical idle state, not to busy polling, unless - * a timer is going to trigger really really soon. - */ - polling_threshold = max_t(unsigned int, 20, s->target_residency); - if (data->next_timer_us > polling_threshold && - latency_req > s->exit_latency && !s->disabled && - !dev->states_usage[1].disable) - first_idx = 1; - } - /* * Use the lowest expected idle interval to pick the idle state. */ - data->predicted_us = min(data->predicted_us, expected_interval); + predicted_us = min(predicted_us, get_typical_interval(data, predicted_us)); if (tick_nohz_tick_stopped()) { /* @@ -352,34 +349,46 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * the known time till the closest timer event for the idle * state selection. */ - if (data->predicted_us < TICK_USEC) - data->predicted_us = ktime_to_us(delta_next); + if (predicted_us < TICK_USEC) + predicted_us = ktime_to_us(delta_next); } else { /* * Use the performance multiplier and the user-configurable * latency_req to determine the maximum exit latency. */ - interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load); + interactivity_req = predicted_us / performance_multiplier(nr_iowaiters, cpu_load); if (latency_req > interactivity_req) latency_req = interactivity_req; } - expected_interval = data->predicted_us; /* * Find the idle state with the lowest power while satisfying * our constraints. */ idx = -1; - for (i = first_idx; i < drv->state_count; i++) { + for (i = 0; i < drv->state_count; i++) { struct cpuidle_state *s = &drv->states[i]; struct cpuidle_state_usage *su = &dev->states_usage[i]; if (s->disabled || su->disable) continue; + if (idx == -1) idx = i; /* first enabled state */ - if (s->target_residency > data->predicted_us) { - if (data->predicted_us < TICK_USEC) + + if (s->target_residency > predicted_us) { + /* + * Use a physical idle state, not busy polling, unless + * a timer is going to trigger soon enough. + */ + if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) && + s->exit_latency <= latency_req && + s->target_residency <= data->next_timer_us) { + predicted_us = s->target_residency; + idx = i; + break; + } + if (predicted_us < TICK_USEC) break; if (!tick_nohz_tick_stopped()) { @@ -389,7 +398,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * tick in that case and let the governor run * again in the next iteration of the loop. */ - expected_interval = drv->states[idx].target_residency; + predicted_us = drv->states[idx].target_residency; break; } @@ -403,7 +412,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, s->target_residency <= ktime_to_us(delta_next)) idx = i; - goto out; + return idx; } if (s->exit_latency > latency_req) { /* @@ -412,7 +421,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * expected idle duration so that the tick is retained * as long as that target residency is low enough. */ - expected_interval = drv->states[idx].target_residency; + predicted_us = drv->states[idx].target_residency; break; } idx = i; @@ -426,7 +435,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * expected idle duration is shorter than the tick period length. */ if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) || - expected_interval < TICK_USEC) && !tick_nohz_tick_stopped()) { + predicted_us < TICK_USEC) && !tick_nohz_tick_stopped()) { unsigned int delta_next_us = ktime_to_us(delta_next); *stop_tick = false; @@ -450,10 +459,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, } } -out: - data->last_state_idx = idx; - - return data->last_state_idx; + return idx; } /** @@ -512,9 +518,19 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * duration predictor do a better job next time. */ measured_us = 9 * MAX_INTERESTING / 10; + } else if ((drv->states[last_idx].flags & CPUIDLE_FLAG_POLLING) && + dev->poll_time_limit) { + /* + * The CPU exited the "polling" state due to a time limit, so + * the idle duration prediction leading to the selection of that + * state was inaccurate. If a better prediction had been made, + * the CPU might have been woken up from idle by the next timer. + * Assume that to be the case. + */ + measured_us = data->next_timer_us; } else { /* measured value */ - measured_us = cpuidle_get_last_residency(dev); + measured_us = dev->last_residency; /* Deduct exit latency */ if (measured_us > 2 * target->exit_latency) diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index 3f86d23c592e..85792d371add 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -9,7 +9,6 @@ #include <linux/sched/clock.h> #include <linux/sched/idle.h> -#define POLL_IDLE_TIME_LIMIT (TICK_NSEC / 16) #define POLL_IDLE_RELAX_COUNT 200 static int __cpuidle poll_idle(struct cpuidle_device *dev, @@ -17,8 +16,11 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev, { u64 time_start = local_clock(); + dev->poll_time_limit = false; + local_irq_enable(); if (!current_set_polling_and_test()) { + u64 limit = (u64)drv->states[1].target_residency * NSEC_PER_USEC; unsigned int loop_count = 0; while (!need_resched()) { @@ -27,8 +29,10 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev, continue; loop_count = 0; - if (local_clock() - time_start > POLL_IDLE_TIME_LIMIT) + if (local_clock() - time_start > limit) { + dev->poll_time_limit = true; break; + } } } current_clr_polling(); diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c index 7e71043457a6..86c699c14f84 100644 --- a/drivers/crypto/inside-secure/safexcel.c +++ b/drivers/crypto/inside-secure/safexcel.c @@ -1044,7 +1044,8 @@ static int safexcel_probe(struct platform_device *pdev) safexcel_configure(priv); - priv->ring = devm_kzalloc(dev, priv->config.rings * sizeof(*priv->ring), + priv->ring = devm_kcalloc(dev, priv->config.rings, + sizeof(*priv->ring), GFP_KERNEL); if (!priv->ring) { ret = -ENOMEM; @@ -1063,8 +1064,9 @@ static int safexcel_probe(struct platform_device *pdev) if (ret) goto err_reg_clk; - priv->ring[i].rdr_req = devm_kzalloc(dev, - sizeof(priv->ring[i].rdr_req) * EIP197_DEFAULT_RING_SIZE, + priv->ring[i].rdr_req = devm_kcalloc(dev, + EIP197_DEFAULT_RING_SIZE, + sizeof(priv->ring[i].rdr_req), GFP_KERNEL); if (!priv->ring[i].rdr_req) { ret = -ENOMEM; diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 4c49bb1330b5..141413067b5c 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -11,6 +11,7 @@ */ #include <linux/kernel.h> +#include <linux/kmod.h> #include <linux/sched.h> #include <linux/errno.h> #include <linux/err.h> @@ -28,9 +29,6 @@ #include <linux/of.h> #include "governor.h" -#define MAX(a,b) ((a > b) ? a : b) -#define MIN(a,b) ((a < b) ? a : b) - static struct class *devfreq_class; /* @@ -221,6 +219,49 @@ static struct devfreq_governor *find_devfreq_governor(const char *name) return ERR_PTR(-ENODEV); } +/** + * try_then_request_governor() - Try to find the governor and request the + * module if is not found. + * @name: name of the governor + * + * Search the list of devfreq governors and request the module and try again + * if is not found. This can happen when both drivers (the governor driver + * and the driver that call devfreq_add_device) are built as modules. + * devfreq_list_lock should be held by the caller. Returns the matched + * governor's pointer. + */ +static struct devfreq_governor *try_then_request_governor(const char *name) +{ + struct devfreq_governor *governor; + int err = 0; + + if (IS_ERR_OR_NULL(name)) { + pr_err("DEVFREQ: %s: Invalid parameters\n", __func__); + return ERR_PTR(-EINVAL); + } + WARN(!mutex_is_locked(&devfreq_list_lock), + "devfreq_list_lock must be locked."); + + governor = find_devfreq_governor(name); + if (IS_ERR(governor)) { + mutex_unlock(&devfreq_list_lock); + + if (!strncmp(name, DEVFREQ_GOV_SIMPLE_ONDEMAND, + DEVFREQ_NAME_LEN)) + err = request_module("governor_%s", "simpleondemand"); + else + err = request_module("governor_%s", name); + /* Restore previous state before return */ + mutex_lock(&devfreq_list_lock); + if (err) + return NULL; + + governor = find_devfreq_governor(name); + } + + return governor; +} + static int devfreq_notify_transition(struct devfreq *devfreq, struct devfreq_freqs *freqs, unsigned int state) { @@ -280,14 +321,14 @@ int update_devfreq(struct devfreq *devfreq) * max_freq * min_freq */ - max_freq = MIN(devfreq->scaling_max_freq, devfreq->max_freq); - min_freq = MAX(devfreq->scaling_min_freq, devfreq->min_freq); + max_freq = min(devfreq->scaling_max_freq, devfreq->max_freq); + min_freq = max(devfreq->scaling_min_freq, devfreq->min_freq); - if (min_freq && freq < min_freq) { + if (freq < min_freq) { freq = min_freq; flags &= ~DEVFREQ_FLAG_LEAST_UPPER_BOUND; /* Use GLB */ } - if (max_freq && freq > max_freq) { + if (freq > max_freq) { freq = max_freq; flags |= DEVFREQ_FLAG_LEAST_UPPER_BOUND; /* Use LUB */ } @@ -534,10 +575,6 @@ static void devfreq_dev_release(struct device *dev) list_del(&devfreq->node); mutex_unlock(&devfreq_list_lock); - if (devfreq->governor) - devfreq->governor->event_handler(devfreq, - DEVFREQ_GOV_STOP, NULL); - if (devfreq->profile->exit) devfreq->profile->exit(devfreq->dev.parent); @@ -646,9 +683,8 @@ struct devfreq *devfreq_add_device(struct device *dev, mutex_unlock(&devfreq->lock); mutex_lock(&devfreq_list_lock); - list_add(&devfreq->node, &devfreq_list); - governor = find_devfreq_governor(devfreq->governor_name); + governor = try_then_request_governor(devfreq->governor_name); if (IS_ERR(governor)) { dev_err(dev, "%s: Unable to find governor for the device\n", __func__); @@ -664,19 +700,20 @@ struct devfreq *devfreq_add_device(struct device *dev, __func__); goto err_init; } + + list_add(&devfreq->node, &devfreq_list); + mutex_unlock(&devfreq_list_lock); return devfreq; err_init: - list_del(&devfreq->node); mutex_unlock(&devfreq_list_lock); - device_unregister(&devfreq->dev); + devfreq_remove_device(devfreq); devfreq = NULL; err_dev: - if (devfreq) - kfree(devfreq); + kfree(devfreq); err_out: return ERR_PTR(err); } @@ -693,6 +730,9 @@ int devfreq_remove_device(struct devfreq *devfreq) if (!devfreq) return -EINVAL; + if (devfreq->governor) + devfreq->governor->event_handler(devfreq, + DEVFREQ_GOV_STOP, NULL); device_unregister(&devfreq->dev); return 0; @@ -991,7 +1031,7 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr, return -EINVAL; mutex_lock(&devfreq_list_lock); - governor = find_devfreq_governor(str_governor); + governor = try_then_request_governor(str_governor); if (IS_ERR(governor)) { ret = PTR_ERR(governor); goto out; @@ -1126,17 +1166,26 @@ static ssize_t min_freq_store(struct device *dev, struct device_attribute *attr, struct devfreq *df = to_devfreq(dev); unsigned long value; int ret; - unsigned long max; ret = sscanf(buf, "%lu", &value); if (ret != 1) return -EINVAL; mutex_lock(&df->lock); - max = df->max_freq; - if (value && max && value > max) { - ret = -EINVAL; - goto unlock; + + if (value) { + if (value > df->max_freq) { + ret = -EINVAL; + goto unlock; + } + } else { + unsigned long *freq_table = df->profile->freq_table; + + /* Get minimum frequency according to sorting order */ + if (freq_table[0] < freq_table[df->profile->max_state - 1]) + value = freq_table[0]; + else + value = freq_table[df->profile->max_state - 1]; } df->min_freq = value; @@ -1152,7 +1201,7 @@ static ssize_t min_freq_show(struct device *dev, struct device_attribute *attr, { struct devfreq *df = to_devfreq(dev); - return sprintf(buf, "%lu\n", MAX(df->scaling_min_freq, df->min_freq)); + return sprintf(buf, "%lu\n", max(df->scaling_min_freq, df->min_freq)); } static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr, @@ -1161,17 +1210,26 @@ static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr, struct devfreq *df = to_devfreq(dev); unsigned long value; int ret; - unsigned long min; ret = sscanf(buf, "%lu", &value); if (ret != 1) return -EINVAL; mutex_lock(&df->lock); - min = df->min_freq; - if (value && min && value < min) { - ret = -EINVAL; - goto unlock; + + if (value) { + if (value < df->min_freq) { + ret = -EINVAL; + goto unlock; + } + } else { + unsigned long *freq_table = df->profile->freq_table; + + /* Get maximum frequency according to sorting order */ + if (freq_table[0] < freq_table[df->profile->max_state - 1]) + value = freq_table[df->profile->max_state - 1]; + else + value = freq_table[0]; } df->max_freq = value; @@ -1188,7 +1246,7 @@ static ssize_t max_freq_show(struct device *dev, struct device_attribute *attr, { struct devfreq *df = to_devfreq(dev); - return sprintf(buf, "%lu\n", MIN(df->scaling_max_freq, df->max_freq)); + return sprintf(buf, "%lu\n", min(df->scaling_max_freq, df->max_freq)); } static DEVICE_ATTR_RW(max_freq); diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c index a9c64f0d3284..c61de0bdf053 100644 --- a/drivers/devfreq/event/exynos-ppmu.c +++ b/drivers/devfreq/event/exynos-ppmu.c @@ -535,8 +535,8 @@ static int of_get_devfreq_events(struct device_node *np, if (i == ARRAY_SIZE(ppmu_events)) { dev_warn(dev, - "don't know how to configure events : %s\n", - node->name); + "don't know how to configure events : %pOFn\n", + node); continue; } diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h index cfc50a61a90d..f53339ca610f 100644 --- a/drivers/devfreq/governor.h +++ b/drivers/devfreq/governor.h @@ -25,6 +25,9 @@ #define DEVFREQ_GOV_SUSPEND 0x4 #define DEVFREQ_GOV_RESUME 0x5 +#define DEVFREQ_MIN_FREQ 0 +#define DEVFREQ_MAX_FREQ ULONG_MAX + /** * struct devfreq_governor - Devfreq policy governor * @node: list node - contains registered devfreq governors @@ -54,9 +57,6 @@ struct devfreq_governor { unsigned int event, void *data); }; -/* Caution: devfreq->lock must be locked before calling update_devfreq */ -extern int update_devfreq(struct devfreq *devfreq); - extern void devfreq_monitor_start(struct devfreq *devfreq); extern void devfreq_monitor_stop(struct devfreq *devfreq); extern void devfreq_monitor_suspend(struct devfreq *devfreq); diff --git a/drivers/devfreq/governor_performance.c b/drivers/devfreq/governor_performance.c index 4d23ecfbd948..ded429fd51be 100644 --- a/drivers/devfreq/governor_performance.c +++ b/drivers/devfreq/governor_performance.c @@ -20,10 +20,7 @@ static int devfreq_performance_func(struct devfreq *df, * target callback should be able to get floor value as * said in devfreq.h */ - if (!df->max_freq) - *freq = UINT_MAX; - else - *freq = df->max_freq; + *freq = DEVFREQ_MAX_FREQ; return 0; } diff --git a/drivers/devfreq/governor_powersave.c b/drivers/devfreq/governor_powersave.c index 0c42f23249ef..9e8897f5ac42 100644 --- a/drivers/devfreq/governor_powersave.c +++ b/drivers/devfreq/governor_powersave.c @@ -20,7 +20,7 @@ static int devfreq_powersave_func(struct devfreq *df, * target callback should be able to get ceiling value as * said in devfreq.h */ - *freq = df->min_freq; + *freq = DEVFREQ_MIN_FREQ; return 0; } diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c index 28e0f2de7100..c0417f0e081e 100644 --- a/drivers/devfreq/governor_simpleondemand.c +++ b/drivers/devfreq/governor_simpleondemand.c @@ -27,7 +27,6 @@ static int devfreq_simple_ondemand_func(struct devfreq *df, unsigned int dfso_upthreshold = DFSO_UPTHRESHOLD; unsigned int dfso_downdifferential = DFSO_DOWNDIFFERENCTIAL; struct devfreq_simple_ondemand_data *data = df->data; - unsigned long max = (df->max_freq) ? df->max_freq : UINT_MAX; err = devfreq_update_stats(df); if (err) @@ -47,7 +46,7 @@ static int devfreq_simple_ondemand_func(struct devfreq *df, /* Assume MAX if it is going to be divided by zero */ if (stat->total_time == 0) { - *freq = max; + *freq = DEVFREQ_MAX_FREQ; return 0; } @@ -60,13 +59,13 @@ static int devfreq_simple_ondemand_func(struct devfreq *df, /* Set MAX if it's busy enough */ if (stat->busy_time * 100 > stat->total_time * dfso_upthreshold) { - *freq = max; + *freq = DEVFREQ_MAX_FREQ; return 0; } /* Set MAX if we do not know the initial frequency */ if (stat->current_frequency == 0) { - *freq = max; + *freq = DEVFREQ_MAX_FREQ; return 0; } @@ -85,11 +84,6 @@ static int devfreq_simple_ondemand_func(struct devfreq *df, b = div_u64(b, (dfso_upthreshold - dfso_downdifferential / 2)); *freq = (unsigned long) b; - if (df->min_freq && *freq < df->min_freq) - *freq = df->min_freq; - if (df->max_freq && *freq > df->max_freq) - *freq = df->max_freq; - return 0; } diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c index 080607c3f34d..378d84c011df 100644 --- a/drivers/devfreq/governor_userspace.c +++ b/drivers/devfreq/governor_userspace.c @@ -26,19 +26,11 @@ static int devfreq_userspace_func(struct devfreq *df, unsigned long *freq) { struct userspace_data *data = df->data; - if (data->valid) { - unsigned long adjusted_freq = data->user_frequency; - - if (df->max_freq && adjusted_freq > df->max_freq) - adjusted_freq = df->max_freq; - - if (df->min_freq && adjusted_freq < df->min_freq) - adjusted_freq = df->min_freq; - - *freq = adjusted_freq; - } else { + if (data->valid) + *freq = data->user_frequency; + else *freq = df->previous_freq; /* No user freq specified yet */ - } + return 0; } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index a57300c1d649..25187403e3ac 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1682,7 +1682,8 @@ static void gpiochip_set_cascaded_irqchip(struct gpio_chip *gpiochip, irq_set_chained_handler_and_data(parent_irq, parent_handler, gpiochip); - gpiochip->irq.parents = &parent_irq; + gpiochip->irq.parent_irq = parent_irq; + gpiochip->irq.parents = &gpiochip->irq.parent_irq; gpiochip->irq.num_parents = 1; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 0b976dfd04df..92ecb9bf982c 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -600,7 +600,7 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, } mtk_crtc->layer_nr = mtk_ddp_comp_layer_nr(mtk_crtc->ddp_comp[0]); - mtk_crtc->planes = devm_kzalloc(dev, mtk_crtc->layer_nr * + mtk_crtc->planes = devm_kcalloc(dev, mtk_crtc->layer_nr, sizeof(struct drm_plane), GFP_KERNEL); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c index 790d39f816dc..b557687b1964 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c @@ -153,8 +153,8 @@ int msm_dss_parse_clock(struct platform_device *pdev, return 0; } - mp->clk_config = devm_kzalloc(&pdev->dev, - sizeof(struct dss_clk) * num_clk, + mp->clk_config = devm_kcalloc(&pdev->dev, + num_clk, sizeof(struct dss_clk), GFP_KERNEL); if (!mp->clk_config) return -ENOMEM; diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 5691dfa1db6f..041e7daf8a33 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -900,9 +900,22 @@ static enum drm_connector_status nv50_mstc_detect(struct drm_connector *connector, bool force) { struct nv50_mstc *mstc = nv50_mstc(connector); + enum drm_connector_status conn_status; + int ret; + if (!mstc->port) return connector_status_disconnected; - return drm_dp_mst_detect_port(connector, mstc->port->mgr, mstc->port); + + ret = pm_runtime_get_sync(connector->dev->dev); + if (ret < 0 && ret != -EACCES) + return connector_status_disconnected; + + conn_status = drm_dp_mst_detect_port(connector, mstc->port->mgr, + mstc->port); + + pm_runtime_mark_last_busy(connector->dev->dev); + pm_runtime_put_autosuspend(connector->dev->dev); + return conn_status; } static void diff --git a/drivers/hwmon/npcm750-pwm-fan.c b/drivers/hwmon/npcm750-pwm-fan.c index 8474d601aa63..b998f9fbed41 100644 --- a/drivers/hwmon/npcm750-pwm-fan.c +++ b/drivers/hwmon/npcm750-pwm-fan.c @@ -908,7 +908,7 @@ static int npcm7xx_en_pwm_fan(struct device *dev, if (fan_cnt < 1) return -EINVAL; - fan_ch = devm_kzalloc(dev, sizeof(*fan_ch) * fan_cnt, GFP_KERNEL); + fan_ch = devm_kcalloc(dev, fan_cnt, sizeof(*fan_ch), GFP_KERNEL); if (!fan_ch) return -ENOMEM; diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 9ee9a15e7134..9200e349f29e 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -2270,7 +2270,7 @@ EXPORT_SYMBOL(i2c_put_adapter); * * Return: NULL if a DMA safe buffer was not obtained. Use msg->buf with PIO. * Or a valid pointer to be used with DMA. After use, release it by - * calling i2c_release_dma_safe_msg_buf(). + * calling i2c_put_dma_safe_msg_buf(). * * This function must only be called from process context! */ diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index b2ccce5fb071..791b8a366e6e 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1066,46 +1066,43 @@ static const struct idle_cpu idle_cpu_dnv = { .disable_promotion_to_c1e = true, }; -#define ICPU(model, cpu) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&cpu } - static const struct x86_cpu_id intel_idle_ids[] __initconst = { - ICPU(INTEL_FAM6_NEHALEM_EP, idle_cpu_nehalem), - ICPU(INTEL_FAM6_NEHALEM, idle_cpu_nehalem), - ICPU(INTEL_FAM6_NEHALEM_G, idle_cpu_nehalem), - ICPU(INTEL_FAM6_WESTMERE, idle_cpu_nehalem), - ICPU(INTEL_FAM6_WESTMERE_EP, idle_cpu_nehalem), - ICPU(INTEL_FAM6_NEHALEM_EX, idle_cpu_nehalem), - ICPU(INTEL_FAM6_ATOM_PINEVIEW, idle_cpu_atom), - ICPU(INTEL_FAM6_ATOM_LINCROFT, idle_cpu_lincroft), - ICPU(INTEL_FAM6_WESTMERE_EX, idle_cpu_nehalem), - ICPU(INTEL_FAM6_SANDYBRIDGE, idle_cpu_snb), - ICPU(INTEL_FAM6_SANDYBRIDGE_X, idle_cpu_snb), - ICPU(INTEL_FAM6_ATOM_CEDARVIEW, idle_cpu_atom), - ICPU(INTEL_FAM6_ATOM_SILVERMONT1, idle_cpu_byt), - ICPU(INTEL_FAM6_ATOM_MERRIFIELD, idle_cpu_tangier), - ICPU(INTEL_FAM6_ATOM_AIRMONT, idle_cpu_cht), - ICPU(INTEL_FAM6_IVYBRIDGE, idle_cpu_ivb), - ICPU(INTEL_FAM6_IVYBRIDGE_X, idle_cpu_ivt), - ICPU(INTEL_FAM6_HASWELL_CORE, idle_cpu_hsw), - ICPU(INTEL_FAM6_HASWELL_X, idle_cpu_hsw), - ICPU(INTEL_FAM6_HASWELL_ULT, idle_cpu_hsw), - ICPU(INTEL_FAM6_HASWELL_GT3E, idle_cpu_hsw), - ICPU(INTEL_FAM6_ATOM_SILVERMONT2, idle_cpu_avn), - ICPU(INTEL_FAM6_BROADWELL_CORE, idle_cpu_bdw), - ICPU(INTEL_FAM6_BROADWELL_GT3E, idle_cpu_bdw), - ICPU(INTEL_FAM6_BROADWELL_X, idle_cpu_bdw), - ICPU(INTEL_FAM6_BROADWELL_XEON_D, idle_cpu_bdw), - ICPU(INTEL_FAM6_SKYLAKE_MOBILE, idle_cpu_skl), - ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, idle_cpu_skl), - ICPU(INTEL_FAM6_KABYLAKE_MOBILE, idle_cpu_skl), - ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, idle_cpu_skl), - ICPU(INTEL_FAM6_SKYLAKE_X, idle_cpu_skx), - ICPU(INTEL_FAM6_XEON_PHI_KNL, idle_cpu_knl), - ICPU(INTEL_FAM6_XEON_PHI_KNM, idle_cpu_knl), - ICPU(INTEL_FAM6_ATOM_GOLDMONT, idle_cpu_bxt), - ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE, idle_cpu_bxt), - ICPU(INTEL_FAM6_ATOM_DENVERTON, idle_cpu_dnv), + INTEL_CPU_FAM6(NEHALEM_EP, idle_cpu_nehalem), + INTEL_CPU_FAM6(NEHALEM, idle_cpu_nehalem), + INTEL_CPU_FAM6(NEHALEM_G, idle_cpu_nehalem), + INTEL_CPU_FAM6(WESTMERE, idle_cpu_nehalem), + INTEL_CPU_FAM6(WESTMERE_EP, idle_cpu_nehalem), + INTEL_CPU_FAM6(NEHALEM_EX, idle_cpu_nehalem), + INTEL_CPU_FAM6(ATOM_PINEVIEW, idle_cpu_atom), + INTEL_CPU_FAM6(ATOM_LINCROFT, idle_cpu_lincroft), + INTEL_CPU_FAM6(WESTMERE_EX, idle_cpu_nehalem), + INTEL_CPU_FAM6(SANDYBRIDGE, idle_cpu_snb), + INTEL_CPU_FAM6(SANDYBRIDGE_X, idle_cpu_snb), + INTEL_CPU_FAM6(ATOM_CEDARVIEW, idle_cpu_atom), + INTEL_CPU_FAM6(ATOM_SILVERMONT1, idle_cpu_byt), + INTEL_CPU_FAM6(ATOM_MERRIFIELD, idle_cpu_tangier), + INTEL_CPU_FAM6(ATOM_AIRMONT, idle_cpu_cht), + INTEL_CPU_FAM6(IVYBRIDGE, idle_cpu_ivb), + INTEL_CPU_FAM6(IVYBRIDGE_X, idle_cpu_ivt), + INTEL_CPU_FAM6(HASWELL_CORE, idle_cpu_hsw), + INTEL_CPU_FAM6(HASWELL_X, idle_cpu_hsw), + INTEL_CPU_FAM6(HASWELL_ULT, idle_cpu_hsw), + INTEL_CPU_FAM6(HASWELL_GT3E, idle_cpu_hsw), + INTEL_CPU_FAM6(ATOM_SILVERMONT2, idle_cpu_avn), + INTEL_CPU_FAM6(BROADWELL_CORE, idle_cpu_bdw), + INTEL_CPU_FAM6(BROADWELL_GT3E, idle_cpu_bdw), + INTEL_CPU_FAM6(BROADWELL_X, idle_cpu_bdw), + INTEL_CPU_FAM6(BROADWELL_XEON_D, idle_cpu_bdw), + INTEL_CPU_FAM6(SKYLAKE_MOBILE, idle_cpu_skl), + INTEL_CPU_FAM6(SKYLAKE_DESKTOP, idle_cpu_skl), + INTEL_CPU_FAM6(KABYLAKE_MOBILE, idle_cpu_skl), + INTEL_CPU_FAM6(KABYLAKE_DESKTOP, idle_cpu_skl), + INTEL_CPU_FAM6(SKYLAKE_X, idle_cpu_skx), + INTEL_CPU_FAM6(XEON_PHI_KNL, idle_cpu_knl), + INTEL_CPU_FAM6(XEON_PHI_KNM, idle_cpu_knl), + INTEL_CPU_FAM6(ATOM_GOLDMONT, idle_cpu_bxt), + INTEL_CPU_FAM6(ATOM_GEMINI_LAKE, idle_cpu_bxt), + INTEL_CPU_FAM6(ATOM_DENVERTON, idle_cpu_dnv), {} }; diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 9fb1d9cb9401..e22314837645 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -544,6 +544,9 @@ void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) int shrink = 0; int c; + if (!mr->allocated_from_cache) + return; + c = order2idx(dev, mr->order); if (c < 0 || c >= MAX_MR_CACHE_ENTRIES) { mlx5_ib_warn(dev, "order %d, cache index %d\n", mr->order, c); @@ -1647,18 +1650,19 @@ static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) umem = NULL; } #endif - clean_mr(dev, mr); + /* + * We should unregister the DMA address from the HCA before + * remove the DMA mapping. + */ + mlx5_mr_cache_free(dev, mr); if (umem) { ib_umem_release(umem); atomic_sub(npages, &dev->mdev->priv.reg_pages); } - if (!mr->allocated_from_cache) kfree(mr); - else - mlx5_mr_cache_free(dev, mr); } int mlx5_ib_dereg_mr(struct ib_mr *ibmr) diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index 370206f987f9..f48369d6f3a0 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -564,6 +564,7 @@ static ssize_t evdev_write(struct file *file, const char __user *buffer, input_inject_event(&evdev->handle, event.type, event.code, event.value); + cond_resched(); } out: diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index cd620e009bad..d4b9db487b16 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -231,6 +231,7 @@ static const struct xpad_device { { 0x0e6f, 0x0246, "Rock Candy Gamepad for Xbox One 2015", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x02ab, "PDP Controller for Xbox One", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x02a4, "PDP Wired Controller for Xbox One - Stealth Series", 0, XTYPE_XBOXONE }, + { 0x0e6f, 0x02a6, "PDP Wired Controller for Xbox One - Camo Series", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x0301, "Logic3 Controller", 0, XTYPE_XBOX360 }, { 0x0e6f, 0x0346, "Rock Candy Gamepad for Xbox One 2016", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x0401, "Logic3 Controller", 0, XTYPE_XBOX360 }, @@ -530,6 +531,8 @@ static const struct xboxone_init_packet xboxone_init_packets[] = { XBOXONE_INIT_PKT(0x0e6f, 0x02ab, xboxone_pdp_init2), XBOXONE_INIT_PKT(0x0e6f, 0x02a4, xboxone_pdp_init1), XBOXONE_INIT_PKT(0x0e6f, 0x02a4, xboxone_pdp_init2), + XBOXONE_INIT_PKT(0x0e6f, 0x02a6, xboxone_pdp_init1), + XBOXONE_INIT_PKT(0x0e6f, 0x02a6, xboxone_pdp_init2), XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init), XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumblebegin_init), XBOXONE_INIT_PKT(0x24c6, 0x543a, xboxone_rumblebegin_init), diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index eb14ddf69346..8ec483e8688b 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -598,6 +598,7 @@ static ssize_t uinput_inject_events(struct uinput_device *udev, input_event(udev->dev, ev.type, ev.code, ev.value); bytes += input_event_size(); + cond_resched(); } return bytes; diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c index e08228061bcd..412fa71245af 100644 --- a/drivers/input/mousedev.c +++ b/drivers/input/mousedev.c @@ -707,6 +707,7 @@ static ssize_t mousedev_write(struct file *file, const char __user *buffer, mousedev_generate_response(client, c); spin_unlock_irq(&client->packet_lock); + cond_resched(); } kill_fasync(&client->fasync, SIGIO, POLL_IN); diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index b8bc71569349..95a78ccbd847 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -1395,15 +1395,26 @@ static void __init i8042_register_ports(void) for (i = 0; i < I8042_NUM_PORTS; i++) { struct serio *serio = i8042_ports[i].serio; - if (serio) { - printk(KERN_INFO "serio: %s at %#lx,%#lx irq %d\n", - serio->name, - (unsigned long) I8042_DATA_REG, - (unsigned long) I8042_COMMAND_REG, - i8042_ports[i].irq); - serio_register_port(serio); - device_set_wakeup_capable(&serio->dev, true); - } + if (!serio) + continue; + + printk(KERN_INFO "serio: %s at %#lx,%#lx irq %d\n", + serio->name, + (unsigned long) I8042_DATA_REG, + (unsigned long) I8042_COMMAND_REG, + i8042_ports[i].irq); + serio_register_port(serio); + device_set_wakeup_capable(&serio->dev, true); + + /* + * On platforms using suspend-to-idle, allow the keyboard to + * wake up the system from sleep by enabling keyboard wakeups + * by default. This is consistent with keyboard wakeup + * behavior on many platforms using suspend-to-RAM (ACPI S3) + * by default. + */ + if (pm_suspend_via_s2idle() && i == I8042_KBD_PORT_NO) + device_set_wakeup_enable(&serio->dev, true); } } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index e13d991e9fb5..b29a8327eed1 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3484,14 +3484,13 @@ static int __init dm_cache_init(void) int r; migration_cache = KMEM_CACHE(dm_cache_migration, 0); - if (!migration_cache) { - dm_unregister_target(&cache_target); + if (!migration_cache) return -ENOMEM; - } r = dm_register_target(&cache_target); if (r) { DMERR("cache target registration failed: %d", r); + kmem_cache_destroy(migration_cache); return r; } diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 21d126a5078c..32aabe27b37c 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -467,7 +467,9 @@ static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_ static struct target_type flakey_target = { .name = "flakey", .version = {1, 5, 0}, +#ifdef CONFIG_BLK_DEV_ZONED .features = DM_TARGET_ZONED_HM, +#endif .module = THIS_MODULE, .ctr = flakey_ctr, .dtr = flakey_dtr, diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 89ccb64342de..e1fa6baf4e8e 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -3462,7 +3462,8 @@ try_smaller_buffer: r = -ENOMEM; goto bad; } - ic->recalc_tags = kvmalloc((RECALC_SECTORS >> ic->sb->log2_sectors_per_block) * ic->tag_size, GFP_KERNEL); + ic->recalc_tags = kvmalloc_array(RECALC_SECTORS >> ic->sb->log2_sectors_per_block, + ic->tag_size, GFP_KERNEL); if (!ic->recalc_tags) { ti->error = "Cannot allocate tags for recalculating"; r = -ENOMEM; diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index d10964d41fd7..2f7c44a006c4 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -102,6 +102,7 @@ static int linear_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } +#ifdef CONFIG_BLK_DEV_ZONED static int linear_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *error) { @@ -112,6 +113,7 @@ static int linear_end_io(struct dm_target *ti, struct bio *bio, return DM_ENDIO_DONE; } +#endif static void linear_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) @@ -208,12 +210,16 @@ static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, static struct target_type linear_target = { .name = "linear", .version = {1, 4, 0}, +#ifdef CONFIG_BLK_DEV_ZONED + .end_io = linear_end_io, .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM, +#else + .features = DM_TARGET_PASSES_INTEGRITY, +#endif .module = THIS_MODULE, .ctr = linear_ctr, .dtr = linear_dtr, .map = linear_map, - .end_io = linear_end_io, .status = linear_status, .prepare_ioctl = linear_prepare_ioctl, .iterate_devices = linear_iterate_devices, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 20f7e4ef5342..45abb54037fc 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1155,12 +1155,14 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) EXPORT_SYMBOL_GPL(dm_accept_partial_bio); /* - * The zone descriptors obtained with a zone report indicate - * zone positions within the target device. The zone descriptors - * must be remapped to match their position within the dm device. - * A target may call dm_remap_zone_report after completion of a - * REQ_OP_ZONE_REPORT bio to remap the zone descriptors obtained - * from the target device mapping to the dm device. + * The zone descriptors obtained with a zone report indicate zone positions + * within the target backing device, regardless of that device is a partition + * and regardless of the target mapping start sector on the device or partition. + * The zone descriptors start sector and write pointer position must be adjusted + * to match their relative position within the dm device. + * A target may call dm_remap_zone_report() after completion of a + * REQ_OP_ZONE_REPORT bio to remap the zone descriptors obtained from the + * backing device. */ void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start) { @@ -1171,6 +1173,7 @@ void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start) struct blk_zone *zone; unsigned int nr_rep = 0; unsigned int ofst; + sector_t part_offset; struct bio_vec bvec; struct bvec_iter iter; void *addr; @@ -1179,6 +1182,15 @@ void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start) return; /* + * bio sector was incremented by the request size on completion. Taking + * into account the original request sector, the target start offset on + * the backing device and the target mapping offset (ti->begin), the + * start sector of the backing device. The partition offset is always 0 + * if the target uses a whole device. + */ + part_offset = bio->bi_iter.bi_sector + ti->begin - (start + bio_end_sector(report_bio)); + + /* * Remap the start sector of the reported zones. For sequential zones, * also remap the write pointer position. */ @@ -1195,6 +1207,7 @@ void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start) /* Set zones start sector */ while (hdr->nr_zones && ofst < bvec.bv_len) { zone = addr + ofst; + zone->start -= part_offset; if (zone->start >= start + ti->len) { hdr->nr_zones = 0; break; @@ -1206,7 +1219,7 @@ void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start) else if (zone->cond == BLK_ZONE_COND_EMPTY) zone->wp = zone->start; else - zone->wp = zone->wp + ti->begin - start; + zone->wp = zone->wp + ti->begin - start - part_offset; } ofst += sizeof(struct blk_zone); hdr->nr_zones--; diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index a0b9102c4c6e..e201ccb3fda4 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1371,6 +1371,16 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq, if (brq->data.blocks > 1) { /* + * Some SD cards in SPI mode return a CRC error or even lock up + * completely when trying to read the last block using a + * multiblock read command. + */ + if (mmc_host_is_spi(card->host) && (rq_data_dir(req) == READ) && + (blk_rq_pos(req) + blk_rq_sectors(req) == + get_capacity(md->disk))) + brq->data.blocks--; + + /* * After a read error, we redo the request one sector * at a time in order to accurately determine which * sectors can be read successfully. diff --git a/drivers/mux/adgs1408.c b/drivers/mux/adgs1408.c index 0f7cf54e3234..89096f10f4c4 100644 --- a/drivers/mux/adgs1408.c +++ b/drivers/mux/adgs1408.c @@ -128,4 +128,4 @@ module_spi_driver(adgs1408_driver); MODULE_AUTHOR("Mircea Caprioru <mircea.caprioru@analog.com>"); MODULE_DESCRIPTION("Analog Devices ADGS1408 MUX driver"); -MODULE_LICENSE("GPL v2"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index e0066adcd2f3..fc8b48adf38b 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -703,7 +703,6 @@ static int bcm_sf2_sw_suspend(struct dsa_switch *ds) static int bcm_sf2_sw_resume(struct dsa_switch *ds) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - unsigned int port; int ret; ret = bcm_sf2_sw_rst(priv); @@ -715,14 +714,7 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds) if (priv->hw_params.num_gphy == 1) bcm_sf2_gphy_enable_set(ds, true); - for (port = 0; port < DSA_MAX_PORTS; port++) { - if (dsa_is_user_port(ds, port)) - bcm_sf2_port_setup(ds, port, NULL); - else if (dsa_is_cpu_port(ds, port)) - bcm_sf2_imp_setup(ds, port); - } - - bcm_sf2_enable_acb(ds); + ds->ops->setup(ds); return 0; } @@ -1173,10 +1165,10 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev) { struct bcm_sf2_priv *priv = platform_get_drvdata(pdev); - /* Disable all ports and interrupts */ priv->wol_ports_mask = 0; - bcm_sf2_sw_suspend(priv->dev->ds); dsa_unregister_switch(priv->dev->ds); + /* Disable all ports and interrupts */ + bcm_sf2_sw_suspend(priv->dev->ds); bcm_sf2_mdio_unregister(priv); return 0; diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index 1c682b76190f..2b3ff0c20155 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -245,11 +245,11 @@ static inline void ena_com_rx_set_flags(struct ena_com_rx_ctx *ena_rx_ctx, (cdesc->status & ENA_ETH_IO_RX_CDESC_BASE_L4_PROTO_IDX_MASK) >> ENA_ETH_IO_RX_CDESC_BASE_L4_PROTO_IDX_SHIFT; ena_rx_ctx->l3_csum_err = - (cdesc->status & ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM_ERR_MASK) >> - ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM_ERR_SHIFT; + !!((cdesc->status & ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM_ERR_MASK) >> + ENA_ETH_IO_RX_CDESC_BASE_L3_CSUM_ERR_SHIFT); ena_rx_ctx->l4_csum_err = - (cdesc->status & ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_ERR_MASK) >> - ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_ERR_SHIFT; + !!((cdesc->status & ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_ERR_MASK) >> + ENA_ETH_IO_RX_CDESC_BASE_L4_CSUM_ERR_SHIFT); ena_rx_ctx->hash = cdesc->hash; ena_rx_ctx->frag = (cdesc->status & ENA_ETH_IO_RX_CDESC_BASE_IPV4_FRAG_MASK) >> diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 25621a218f20..d906293ce07d 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1575,8 +1575,6 @@ static int ena_up_complete(struct ena_adapter *adapter) if (rc) return rc; - ena_init_napi(adapter); - ena_change_mtu(adapter->netdev, adapter->netdev->mtu); ena_refill_all_rx_bufs(adapter); @@ -1730,6 +1728,13 @@ static int ena_up(struct ena_adapter *adapter) ena_setup_io_intr(adapter); + /* napi poll functions should be initialized before running + * request_irq(), to handle a rare condition where there is a pending + * interrupt, causing the ISR to fire immediately while the poll + * function wasn't set yet, causing a null dereference + */ + ena_init_napi(adapter); + rc = ena_request_io_irq(adapter); if (rc) goto err_req_irq; @@ -2619,7 +2624,11 @@ err_disable_msix: ena_free_mgmnt_irq(adapter); ena_disable_msix(adapter); err_device_destroy: + ena_com_abort_admin_commands(ena_dev); + ena_com_wait_for_abort_completion(ena_dev); ena_com_admin_destroy(ena_dev); + ena_com_mmio_reg_read_request_destroy(ena_dev); + ena_com_dev_reset(ena_dev, ENA_REGS_RESET_DRIVER_INVALID_STATE); err: clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags); @@ -3099,15 +3108,8 @@ err_rss_init: static void ena_release_bars(struct ena_com_dev *ena_dev, struct pci_dev *pdev) { - int release_bars; - - if (ena_dev->mem_bar) - devm_iounmap(&pdev->dev, ena_dev->mem_bar); - - if (ena_dev->reg_bar) - devm_iounmap(&pdev->dev, ena_dev->reg_bar); + int release_bars = pci_select_bars(pdev, IORESOURCE_MEM) & ENA_BAR_MASK; - release_bars = pci_select_bars(pdev, IORESOURCE_MEM) & ENA_BAR_MASK; pci_release_selected_regions(pdev, release_bars); } diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index d2d59444f562..6a046030e873 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -260,47 +260,34 @@ static const struct devlink_param mlx4_devlink_params[] = { NULL, NULL, NULL), }; -static void mlx4_devlink_set_init_value(struct devlink *devlink, u32 param_id, - union devlink_param_value init_val) -{ - struct mlx4_priv *priv = devlink_priv(devlink); - struct mlx4_dev *dev = &priv->dev; - int err; - - err = devlink_param_driverinit_value_set(devlink, param_id, init_val); - if (err) - mlx4_warn(dev, - "devlink set parameter %u value failed (err = %d)", - param_id, err); -} - static void mlx4_devlink_set_params_init_values(struct devlink *devlink) { union devlink_param_value value; value.vbool = !!mlx4_internal_err_reset; - mlx4_devlink_set_init_value(devlink, - DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, - value); + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, + value); value.vu32 = 1UL << log_num_mac; - mlx4_devlink_set_init_value(devlink, - DEVLINK_PARAM_GENERIC_ID_MAX_MACS, value); + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + value); value.vbool = enable_64b_cqe_eqe; - mlx4_devlink_set_init_value(devlink, - MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE, - value); + devlink_param_driverinit_value_set(devlink, + MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE, + value); value.vbool = enable_4k_uar; - mlx4_devlink_set_init_value(devlink, - MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR, - value); + devlink_param_driverinit_value_set(devlink, + MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR, + value); value.vbool = false; - mlx4_devlink_set_init_value(devlink, - DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT, - value); + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT, + value); } static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev, diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 9a5e2969df61..3a5e6160bf0d 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4282,8 +4282,8 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) RTL_W32(tp, RxConfig, RX_FIFO_THRESH | RX_DMA_BURST); break; case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_24: - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: + case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_36: + case RTL_GIGA_MAC_VER_38: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST); break; case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 7aa5ebb6766c..4289ccb26e4e 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -735,8 +735,11 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget) u16 idx = dring->tail; struct netsec_de *de = dring->vaddr + (DESC_SZ * idx); - if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD)) + if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD)) { + /* reading the register clears the irq */ + netsec_read(priv, NETSEC_REG_NRM_RX_PKTCNT); break; + } /* This barrier is needed to keep us from reading * any other fields out of the netsec_de until we have diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 6e13b8832bc7..fd8bb998ae52 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -163,8 +163,6 @@ static const enum gpiod_flags gpio_flags[] = { /* Give this long for the PHY to reset. */ #define T_PHY_RESET_MS 50 -static DEFINE_MUTEX(sfp_mutex); - struct sff_data { unsigned int gpios; bool (*module_supported)(const struct sfp_eeprom_id *id); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 533b6fb8d923..72a55b6b4211 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1241,6 +1241,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x0b3c, 0xc00b, 4)}, /* Olivetti Olicard 500 */ {QMI_FIXED_INTF(0x1e2d, 0x0060, 4)}, /* Cinterion PLxx */ {QMI_FIXED_INTF(0x1e2d, 0x0053, 4)}, /* Cinterion PHxx,PXxx */ + {QMI_FIXED_INTF(0x1e2d, 0x0063, 10)}, /* Cinterion ALASxx (1 RmNet) */ {QMI_FIXED_INTF(0x1e2d, 0x0082, 4)}, /* Cinterion PHxx,PXxx (2 RmNet) */ {QMI_FIXED_INTF(0x1e2d, 0x0082, 5)}, /* Cinterion PHxx,PXxx (2 RmNet) */ {QMI_FIXED_INTF(0x1e2d, 0x0083, 4)}, /* Cinterion PHxx,PXxx (1 RmNet + USB Audio)*/ diff --git a/drivers/net/wireless/marvell/libertas/if_sdio.c b/drivers/net/wireless/marvell/libertas/if_sdio.c index 43743c26c071..39bf85d0ade0 100644 --- a/drivers/net/wireless/marvell/libertas/if_sdio.c +++ b/drivers/net/wireless/marvell/libertas/if_sdio.c @@ -1317,6 +1317,10 @@ static int if_sdio_suspend(struct device *dev) if (priv->wol_criteria == EHS_REMOVE_WAKEUP) { dev_info(dev, "Suspend without wake params -- powering down card\n"); if (priv->fw_ready) { + ret = lbs_suspend(priv); + if (ret) + return ret; + priv->power_up_on_resume = true; if_sdio_power_off(card); } diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index 7780b07543bb..79e59f2379a2 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -258,7 +258,7 @@ int mt76u_buf_alloc(struct mt76_dev *dev, struct mt76u_buf *buf, if (!buf->urb) return -ENOMEM; - buf->urb->sg = devm_kzalloc(dev->dev, nsgs * sizeof(*buf->urb->sg), + buf->urb->sg = devm_kcalloc(dev->dev, nsgs, sizeof(*buf->urb->sg), gfp); if (!buf->urb->sg) return -ENOMEM; @@ -464,8 +464,8 @@ static int mt76u_alloc_rx(struct mt76_dev *dev) int i, err, nsgs; spin_lock_init(&q->lock); - q->entry = devm_kzalloc(dev->dev, - MT_NUM_RX_ENTRIES * sizeof(*q->entry), + q->entry = devm_kcalloc(dev->dev, + MT_NUM_RX_ENTRIES, sizeof(*q->entry), GFP_KERNEL); if (!q->entry) return -ENOMEM; @@ -717,8 +717,8 @@ static int mt76u_alloc_tx(struct mt76_dev *dev) INIT_LIST_HEAD(&q->swq); q->hw_idx = q2hwq(i); - q->entry = devm_kzalloc(dev->dev, - MT_NUM_TX_ENTRIES * sizeof(*q->entry), + q->entry = devm_kcalloc(dev->dev, + MT_NUM_TX_ENTRIES, sizeof(*q->entry), GFP_KERNEL); if (!q->entry) return -ENOMEM; diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 722537e14848..41b49716ac75 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -771,6 +771,9 @@ static void __init of_unittest_parse_interrupts(void) struct of_phandle_args args; int i, rc; + if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) + return; + np = of_find_node_by_path("/testcase-data/interrupts/interrupts0"); if (!np) { pr_err("missing testcase data\n"); @@ -845,6 +848,9 @@ static void __init of_unittest_parse_interrupts_extended(void) struct of_phandle_args args; int i, rc; + if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) + return; + np = of_find_node_by_path("/testcase-data/interrupts/interrupts-extended0"); if (!np) { pr_err("missing testcase data\n"); @@ -1001,15 +1007,19 @@ static void __init of_unittest_platform_populate(void) pdev = of_find_device_by_node(np); unittest(pdev, "device 1 creation failed\n"); - irq = platform_get_irq(pdev, 0); - unittest(irq == -EPROBE_DEFER, "device deferred probe failed - %d\n", irq); + if (!(of_irq_workarounds & OF_IMAP_OLDWORLD_MAC)) { + irq = platform_get_irq(pdev, 0); + unittest(irq == -EPROBE_DEFER, + "device deferred probe failed - %d\n", irq); - /* Test that a parsing failure does not return -EPROBE_DEFER */ - np = of_find_node_by_path("/testcase-data/testcase-device2"); - pdev = of_find_device_by_node(np); - unittest(pdev, "device 2 creation failed\n"); - irq = platform_get_irq(pdev, 0); - unittest(irq < 0 && irq != -EPROBE_DEFER, "device parsing error failed - %d\n", irq); + /* Test that a parsing failure does not return -EPROBE_DEFER */ + np = of_find_node_by_path("/testcase-data/testcase-device2"); + pdev = of_find_device_by_node(np); + unittest(pdev, "device 2 creation failed\n"); + irq = platform_get_irq(pdev, 0); + unittest(irq < 0 && irq != -EPROBE_DEFER, + "device parsing error failed - %d\n", irq); + } np = of_find_node_by_path("/testcase-data/platform-tests"); unittest(np, "No testcase data in device tree\n"); diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 31ff03dbeb83..2c2df4e4fc14 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -48,9 +48,14 @@ static struct opp_device *_find_opp_dev(const struct device *dev, static struct opp_table *_find_opp_table_unlocked(struct device *dev) { struct opp_table *opp_table; + bool found; list_for_each_entry(opp_table, &opp_tables, node) { - if (_find_opp_dev(dev, opp_table)) { + mutex_lock(&opp_table->lock); + found = !!_find_opp_dev(dev, opp_table); + mutex_unlock(&opp_table->lock); + + if (found) { _get_opp_table_kref(opp_table); return opp_table; @@ -313,7 +318,7 @@ int dev_pm_opp_get_opp_count(struct device *dev) count = PTR_ERR(opp_table); dev_dbg(dev, "%s: OPP table not found (%d)\n", __func__, count); - return 0; + return count; } count = _get_opp_count(opp_table); @@ -754,8 +759,8 @@ static void _remove_opp_dev(struct opp_device *opp_dev, kfree(opp_dev); } -struct opp_device *_add_opp_dev(const struct device *dev, - struct opp_table *opp_table) +static struct opp_device *_add_opp_dev_unlocked(const struct device *dev, + struct opp_table *opp_table) { struct opp_device *opp_dev; int ret; @@ -766,6 +771,7 @@ struct opp_device *_add_opp_dev(const struct device *dev, /* Initialize opp-dev */ opp_dev->dev = dev; + list_add(&opp_dev->node, &opp_table->dev_list); /* Create debugfs entries for the opp_table */ @@ -777,7 +783,19 @@ struct opp_device *_add_opp_dev(const struct device *dev, return opp_dev; } -static struct opp_table *_allocate_opp_table(struct device *dev) +struct opp_device *_add_opp_dev(const struct device *dev, + struct opp_table *opp_table) +{ + struct opp_device *opp_dev; + + mutex_lock(&opp_table->lock); + opp_dev = _add_opp_dev_unlocked(dev, opp_table); + mutex_unlock(&opp_table->lock); + + return opp_dev; +} + +static struct opp_table *_allocate_opp_table(struct device *dev, int index) { struct opp_table *opp_table; struct opp_device *opp_dev; @@ -791,6 +809,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev) if (!opp_table) return NULL; + mutex_init(&opp_table->lock); INIT_LIST_HEAD(&opp_table->dev_list); opp_dev = _add_opp_dev(dev, opp_table); @@ -799,7 +818,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev) return NULL; } - _of_init_opp_table(opp_table, dev); + _of_init_opp_table(opp_table, dev, index); /* Find clk for the device */ opp_table->clk = clk_get(dev, NULL); @@ -812,7 +831,6 @@ static struct opp_table *_allocate_opp_table(struct device *dev) BLOCKING_INIT_NOTIFIER_HEAD(&opp_table->head); INIT_LIST_HEAD(&opp_table->opp_list); - mutex_init(&opp_table->lock); kref_init(&opp_table->kref); /* Secure the device table modification */ @@ -825,7 +843,7 @@ void _get_opp_table_kref(struct opp_table *opp_table) kref_get(&opp_table->kref); } -struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) +static struct opp_table *_opp_get_opp_table(struct device *dev, int index) { struct opp_table *opp_table; @@ -836,31 +854,56 @@ struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) if (!IS_ERR(opp_table)) goto unlock; - opp_table = _allocate_opp_table(dev); + opp_table = _managed_opp(dev, index); + if (opp_table) { + if (!_add_opp_dev_unlocked(dev, opp_table)) { + dev_pm_opp_put_opp_table(opp_table); + opp_table = NULL; + } + goto unlock; + } + + opp_table = _allocate_opp_table(dev, index); unlock: mutex_unlock(&opp_table_lock); return opp_table; } + +struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) +{ + return _opp_get_opp_table(dev, 0); +} EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_table); +struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev, + int index) +{ + return _opp_get_opp_table(dev, index); +} + static void _opp_table_kref_release(struct kref *kref) { struct opp_table *opp_table = container_of(kref, struct opp_table, kref); - struct opp_device *opp_dev; + struct opp_device *opp_dev, *temp; /* Release clk */ if (!IS_ERR(opp_table->clk)) clk_put(opp_table->clk); - opp_dev = list_first_entry(&opp_table->dev_list, struct opp_device, - node); + WARN_ON(!list_empty(&opp_table->opp_list)); - _remove_opp_dev(opp_dev, opp_table); + list_for_each_entry_safe(opp_dev, temp, &opp_table->dev_list, node) { + /* + * The OPP table is getting removed, drop the performance state + * constraints. + */ + if (opp_table->genpd_performance_state) + dev_pm_genpd_set_performance_state((struct device *)(opp_dev->dev), 0); - /* dev_list must be empty now */ - WARN_ON(!list_empty(&opp_table->dev_list)); + _remove_opp_dev(opp_dev, opp_table); + } mutex_destroy(&opp_table->lock); list_del(&opp_table->node); @@ -869,6 +912,33 @@ static void _opp_table_kref_release(struct kref *kref) mutex_unlock(&opp_table_lock); } +void _opp_remove_all_static(struct opp_table *opp_table) +{ + struct dev_pm_opp *opp, *tmp; + + list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) { + if (!opp->dynamic) + dev_pm_opp_put(opp); + } + + opp_table->parsed_static_opps = false; +} + +static void _opp_table_list_kref_release(struct kref *kref) +{ + struct opp_table *opp_table = container_of(kref, struct opp_table, + list_kref); + + _opp_remove_all_static(opp_table); + mutex_unlock(&opp_table_lock); +} + +void _put_opp_list_kref(struct opp_table *opp_table) +{ + kref_put_mutex(&opp_table->list_kref, _opp_table_list_kref_release, + &opp_table_lock); +} + void dev_pm_opp_put_opp_table(struct opp_table *opp_table) { kref_put_mutex(&opp_table->kref, _opp_table_kref_release, @@ -896,7 +966,6 @@ static void _opp_kref_release(struct kref *kref) kfree(opp); mutex_unlock(&opp_table->lock); - dev_pm_opp_put_opp_table(opp_table); } void dev_pm_opp_get(struct dev_pm_opp *opp) @@ -940,11 +1009,15 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq) if (found) { dev_pm_opp_put(opp); + + /* Drop the reference taken by dev_pm_opp_add() */ + dev_pm_opp_put_opp_table(opp_table); } else { dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n", __func__, freq); } + /* Drop the reference taken by _find_opp_table() */ dev_pm_opp_put_opp_table(opp_table); } EXPORT_SYMBOL_GPL(dev_pm_opp_remove); @@ -1062,9 +1135,6 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, new_opp->opp_table = opp_table; kref_init(&new_opp->kref); - /* Get a reference to the OPP table */ - _get_opp_table_kref(opp_table); - ret = opp_debug_create_one(new_opp, opp_table); if (ret) dev_err(dev, "%s: Failed to register opp to debugfs (%d)\n", @@ -1543,8 +1613,9 @@ int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt) return -ENOMEM; ret = _opp_add_v1(opp_table, dev, freq, u_volt, true); + if (ret) + dev_pm_opp_put_opp_table(opp_table); - dev_pm_opp_put_opp_table(opp_table); return ret; } EXPORT_SYMBOL_GPL(dev_pm_opp_add); @@ -1707,35 +1778,7 @@ int dev_pm_opp_unregister_notifier(struct device *dev, } EXPORT_SYMBOL(dev_pm_opp_unregister_notifier); -/* - * Free OPPs either created using static entries present in DT or even the - * dynamically added entries based on remove_all param. - */ -void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev, - bool remove_all) -{ - struct dev_pm_opp *opp, *tmp; - - /* Find if opp_table manages a single device */ - if (list_is_singular(&opp_table->dev_list)) { - /* Free static OPPs */ - list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) { - if (remove_all || !opp->dynamic) - dev_pm_opp_put(opp); - } - - /* - * The OPP table is getting removed, drop the performance state - * constraints. - */ - if (opp_table->genpd_performance_state) - dev_pm_genpd_set_performance_state(dev, 0); - } else { - _remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table); - } -} - -void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all) +void _dev_pm_opp_find_and_remove_table(struct device *dev) { struct opp_table *opp_table; @@ -1752,8 +1795,12 @@ void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all) return; } - _dev_pm_opp_remove_table(opp_table, dev, remove_all); + _put_opp_list_kref(opp_table); + + /* Drop reference taken by _find_opp_table() */ + dev_pm_opp_put_opp_table(opp_table); + /* Drop reference taken while the OPP table was added */ dev_pm_opp_put_opp_table(opp_table); } @@ -1766,6 +1813,6 @@ void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all) */ void dev_pm_opp_remove_table(struct device *dev) { - _dev_pm_opp_find_and_remove_table(dev, true); + _dev_pm_opp_find_and_remove_table(dev); } EXPORT_SYMBOL_GPL(dev_pm_opp_remove_table); diff --git a/drivers/opp/cpu.c b/drivers/opp/cpu.c index 0c0910709435..ab6d07e78945 100644 --- a/drivers/opp/cpu.c +++ b/drivers/opp/cpu.c @@ -108,7 +108,8 @@ void dev_pm_opp_free_cpufreq_table(struct device *dev, EXPORT_SYMBOL_GPL(dev_pm_opp_free_cpufreq_table); #endif /* CONFIG_CPU_FREQ */ -void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of) +void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, + int last_cpu) { struct device *cpu_dev; int cpu; @@ -116,6 +117,9 @@ void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of) WARN_ON(cpumask_empty(cpumask)); for_each_cpu(cpu, cpumask) { + if (cpu == last_cpu) + break; + cpu_dev = get_cpu_device(cpu); if (!cpu_dev) { pr_err("%s: failed to get cpu%d device\n", __func__, @@ -123,10 +127,7 @@ void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of) continue; } - if (of) - dev_pm_opp_of_remove_table(cpu_dev); - else - dev_pm_opp_remove_table(cpu_dev); + _dev_pm_opp_find_and_remove_table(cpu_dev); } } @@ -140,7 +141,7 @@ void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of) */ void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask) { - _dev_pm_opp_cpumask_remove_table(cpumask, false); + _dev_pm_opp_cpumask_remove_table(cpumask, -1); } EXPORT_SYMBOL_GPL(dev_pm_opp_cpumask_remove_table); @@ -222,8 +223,10 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) cpumask_clear(cpumask); if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) { + mutex_lock(&opp_table->lock); list_for_each_entry(opp_dev, &opp_table->dev_list, node) cpumask_set_cpu(opp_dev->dev->id, cpumask); + mutex_unlock(&opp_table->lock); } else { cpumask_set_cpu(cpu_dev->id, cpumask); } diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 7af0ddec936b..5a4b47958073 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -23,11 +23,32 @@ #include "opp.h" -static struct opp_table *_managed_opp(const struct device_node *np) +/* + * Returns opp descriptor node for a device node, caller must + * do of_node_put(). + */ +static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np, + int index) +{ + /* "operating-points-v2" can be an array for power domain providers */ + return of_parse_phandle(np, "operating-points-v2", index); +} + +/* Returns opp descriptor node for a device, caller must do of_node_put() */ +struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev) +{ + return _opp_of_get_opp_desc_node(dev->of_node, 0); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node); + +struct opp_table *_managed_opp(struct device *dev, int index) { struct opp_table *opp_table, *managed_table = NULL; + struct device_node *np; - mutex_lock(&opp_table_lock); + np = _opp_of_get_opp_desc_node(dev->of_node, index); + if (!np) + return NULL; list_for_each_entry(opp_table, &opp_tables, node) { if (opp_table->np == np) { @@ -47,29 +68,45 @@ static struct opp_table *_managed_opp(const struct device_node *np) } } - mutex_unlock(&opp_table_lock); + of_node_put(np); return managed_table; } -void _of_init_opp_table(struct opp_table *opp_table, struct device *dev) +void _of_init_opp_table(struct opp_table *opp_table, struct device *dev, + int index) { - struct device_node *np; + struct device_node *np, *opp_np; + u32 val; /* * Only required for backward compatibility with v1 bindings, but isn't * harmful for other cases. And so we do it unconditionally. */ np = of_node_get(dev->of_node); - if (np) { - u32 val; - - if (!of_property_read_u32(np, "clock-latency", &val)) - opp_table->clock_latency_ns_max = val; - of_property_read_u32(np, "voltage-tolerance", - &opp_table->voltage_tolerance_v1); - of_node_put(np); - } + if (!np) + return; + + if (!of_property_read_u32(np, "clock-latency", &val)) + opp_table->clock_latency_ns_max = val; + of_property_read_u32(np, "voltage-tolerance", + &opp_table->voltage_tolerance_v1); + + /* Get OPP table node */ + opp_np = _opp_of_get_opp_desc_node(np, index); + of_node_put(np); + + if (!opp_np) + return; + + if (of_property_read_bool(opp_np, "opp-shared")) + opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED; + else + opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE; + + opp_table->np = opp_np; + + of_node_put(opp_np); } static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table, @@ -245,26 +282,10 @@ free_microvolt: */ void dev_pm_opp_of_remove_table(struct device *dev) { - _dev_pm_opp_find_and_remove_table(dev, false); + _dev_pm_opp_find_and_remove_table(dev); } EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table); -/* Returns opp descriptor node for a device node, caller must - * do of_node_put() */ -static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np, - int index) -{ - /* "operating-points-v2" can be an array for power domain providers */ - return of_parse_phandle(np, "operating-points-v2", index); -} - -/* Returns opp descriptor node for a device, caller must do of_node_put() */ -struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev) -{ - return _opp_of_get_opp_desc_node(dev->of_node, 0); -} -EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node); - /** * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings) * @opp_table: OPP table @@ -276,15 +297,21 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node); * removed by dev_pm_opp_remove. * * Return: - * 0 On success OR + * Valid OPP pointer: + * On success + * NULL: * Duplicate OPPs (both freq and volt are same) and opp->available - * -EEXIST Freq are same and volt are different OR + * OR if the OPP is not supported by hardware. + * ERR_PTR(-EEXIST): + * Freq are same and volt are different OR * Duplicate OPPs (both freq and volt are same) and !opp->available - * -ENOMEM Memory allocation failure - * -EINVAL Failed parsing the OPP node + * ERR_PTR(-ENOMEM): + * Memory allocation failure + * ERR_PTR(-EINVAL): + * Failed parsing the OPP node */ -static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev, - struct device_node *np) +static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table, + struct device *dev, struct device_node *np) { struct dev_pm_opp *new_opp; u64 rate = 0; @@ -294,7 +321,7 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev, new_opp = _opp_allocate(opp_table); if (!new_opp) - return -ENOMEM; + return ERR_PTR(-ENOMEM); ret = of_property_read_u64(np, "opp-hz", &rate); if (ret < 0) { @@ -369,52 +396,47 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev, * frequency/voltage list. */ blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADD, new_opp); - return 0; + return new_opp; free_opp: _opp_free(new_opp); - return ret; + return ERR_PTR(ret); } /* Initializes OPP tables based on new bindings */ -static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np) +static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table) { struct device_node *np; - struct opp_table *opp_table; - int ret = 0, count = 0, pstate_count = 0; + int ret, count = 0, pstate_count = 0; struct dev_pm_opp *opp; - opp_table = _managed_opp(opp_np); - if (opp_table) { - /* OPPs are already managed */ - if (!_add_opp_dev(dev, opp_table)) - ret = -ENOMEM; - goto put_opp_table; + /* OPP table is already initialized for the device */ + if (opp_table->parsed_static_opps) { + kref_get(&opp_table->list_kref); + return 0; } - opp_table = dev_pm_opp_get_opp_table(dev); - if (!opp_table) - return -ENOMEM; + kref_init(&opp_table->list_kref); /* We have opp-table node now, iterate over it and add OPPs */ - for_each_available_child_of_node(opp_np, np) { - count++; - - ret = _opp_add_static_v2(opp_table, dev, np); - if (ret) { + for_each_available_child_of_node(opp_table->np, np) { + opp = _opp_add_static_v2(opp_table, dev, np); + if (IS_ERR(opp)) { + ret = PTR_ERR(opp); dev_err(dev, "%s: Failed to add OPP, %d\n", __func__, ret); - _dev_pm_opp_remove_table(opp_table, dev, false); of_node_put(np); - goto put_opp_table; + goto put_list_kref; + } else if (opp) { + count++; } } /* There should be one of more OPP defined */ if (WARN_ON(!count)) { ret = -ENOENT; - goto put_opp_table; + goto put_list_kref; } list_for_each_entry(opp, &opp_table->opp_list, node) @@ -425,28 +447,25 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np) dev_err(dev, "Not all nodes have performance state set (%d: %d)\n", count, pstate_count); ret = -ENOENT; - goto put_opp_table; + goto put_list_kref; } if (pstate_count) opp_table->genpd_performance_state = true; - opp_table->np = opp_np; - if (of_property_read_bool(opp_np, "opp-shared")) - opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED; - else - opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE; + opp_table->parsed_static_opps = true; -put_opp_table: - dev_pm_opp_put_opp_table(opp_table); + return 0; + +put_list_kref: + _put_opp_list_kref(opp_table); return ret; } /* Initializes OPP tables based on old-deprecated bindings */ -static int _of_add_opp_table_v1(struct device *dev) +static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table) { - struct opp_table *opp_table; const struct property *prop; const __be32 *val; int nr, ret = 0; @@ -467,9 +486,7 @@ static int _of_add_opp_table_v1(struct device *dev) return -EINVAL; } - opp_table = dev_pm_opp_get_opp_table(dev); - if (!opp_table) - return -ENOMEM; + kref_init(&opp_table->list_kref); val = prop->value; while (nr) { @@ -480,13 +497,12 @@ static int _of_add_opp_table_v1(struct device *dev) if (ret) { dev_err(dev, "%s: Failed to add OPP %ld (%d)\n", __func__, freq, ret); - _dev_pm_opp_remove_table(opp_table, dev, false); - break; + _put_opp_list_kref(opp_table); + return ret; } nr -= 2; } - dev_pm_opp_put_opp_table(opp_table); return ret; } @@ -509,24 +525,24 @@ static int _of_add_opp_table_v1(struct device *dev) */ int dev_pm_opp_of_add_table(struct device *dev) { - struct device_node *opp_np; + struct opp_table *opp_table; int ret; + opp_table = dev_pm_opp_get_opp_table_indexed(dev, 0); + if (!opp_table) + return -ENOMEM; + /* - * OPPs have two version of bindings now. The older one is deprecated, - * try for the new binding first. + * OPPs have two version of bindings now. Also try the old (v1) + * bindings for backward compatibility with older dtbs. */ - opp_np = dev_pm_opp_of_get_opp_desc_node(dev); - if (!opp_np) { - /* - * Try old-deprecated bindings for backward compatibility with - * older dtbs. - */ - return _of_add_opp_table_v1(dev); - } + if (opp_table->np) + ret = _of_add_opp_table_v2(dev, opp_table); + else + ret = _of_add_opp_table_v1(dev, opp_table); - ret = _of_add_opp_table_v2(dev, opp_np); - of_node_put(opp_np); + if (ret) + dev_pm_opp_put_opp_table(opp_table); return ret; } @@ -553,28 +569,29 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table); */ int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) { - struct device_node *opp_np; + struct opp_table *opp_table; int ret, count; -again: - opp_np = _opp_of_get_opp_desc_node(dev->of_node, index); - if (!opp_np) { + if (index) { /* * If only one phandle is present, then the same OPP table * applies for all index requests. */ count = of_count_phandle_with_args(dev->of_node, "operating-points-v2", NULL); - if (count == 1 && index) { - index = 0; - goto again; - } + if (count != 1) + return -ENODEV; - return -ENODEV; + index = 0; } - ret = _of_add_opp_table_v2(dev, opp_np); - of_node_put(opp_np); + opp_table = dev_pm_opp_get_opp_table_indexed(dev, index); + if (!opp_table) + return -ENOMEM; + + ret = _of_add_opp_table_v2(dev, opp_table); + if (ret) + dev_pm_opp_put_opp_table(opp_table); return ret; } @@ -591,7 +608,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_indexed); */ void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask) { - _dev_pm_opp_cpumask_remove_table(cpumask, true); + _dev_pm_opp_cpumask_remove_table(cpumask, -1); } EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table); @@ -604,16 +621,18 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table); int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask) { struct device *cpu_dev; - int cpu, ret = 0; + int cpu, ret; - WARN_ON(cpumask_empty(cpumask)); + if (WARN_ON(cpumask_empty(cpumask))) + return -ENODEV; for_each_cpu(cpu, cpumask) { cpu_dev = get_cpu_device(cpu); if (!cpu_dev) { pr_err("%s: failed to get cpu%d device\n", __func__, cpu); - continue; + ret = -ENODEV; + goto remove_table; } ret = dev_pm_opp_of_add_table(cpu_dev); @@ -625,12 +644,16 @@ int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask) pr_debug("%s: couldn't find opp table for cpu:%d, %d\n", __func__, cpu, ret); - /* Free all other OPPs */ - dev_pm_opp_of_cpumask_remove_table(cpumask); - break; + goto remove_table; } } + return 0; + +remove_table: + /* Free all other OPPs */ + _dev_pm_opp_cpumask_remove_table(cpumask, cpu); + return ret; } EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_add_table); diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h index 7c540fd063b2..9c6544b4f4f9 100644 --- a/drivers/opp/opp.h +++ b/drivers/opp/opp.h @@ -126,9 +126,11 @@ enum opp_table_access { * @dev_list: list of devices that share these OPPs * @opp_list: table of opps * @kref: for reference count of the table. - * @lock: mutex protecting the opp_list. + * @list_kref: for reference count of the OPP list. + * @lock: mutex protecting the opp_list and dev_list. * @np: struct device_node pointer for opp's DT node. * @clock_latency_ns_max: Max clock latency in nanoseconds. + * @parsed_static_opps: True if OPPs are initialized from DT. * @shared_opp: OPP is shared between multiple devices. * @suspend_opp: Pointer to OPP to be used during device suspend. * @supported_hw: Array of version number to support. @@ -156,6 +158,7 @@ struct opp_table { struct list_head dev_list; struct list_head opp_list; struct kref kref; + struct kref list_kref; struct mutex lock; struct device_node *np; @@ -164,6 +167,7 @@ struct opp_table { /* For backward compatibility with v1 bindings */ unsigned int voltage_tolerance_v1; + bool parsed_static_opps; enum opp_table_access shared_opp; struct dev_pm_opp *suspend_opp; @@ -186,23 +190,26 @@ struct opp_table { /* Routines internal to opp core */ void dev_pm_opp_get(struct dev_pm_opp *opp); +void _opp_remove_all_static(struct opp_table *opp_table); void _get_opp_table_kref(struct opp_table *opp_table); int _get_opp_count(struct opp_table *opp_table); struct opp_table *_find_opp_table(struct device *dev); struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table); -void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev, bool remove_all); -void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all); +void _dev_pm_opp_find_and_remove_table(struct device *dev); struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table); void _opp_free(struct dev_pm_opp *opp); int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table, bool rate_not_available); int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic); -void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of); +void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, int last_cpu); struct opp_table *_add_opp_table(struct device *dev); +void _put_opp_list_kref(struct opp_table *opp_table); #ifdef CONFIG_OF -void _of_init_opp_table(struct opp_table *opp_table, struct device *dev); +void _of_init_opp_table(struct opp_table *opp_table, struct device *dev, int index); +struct opp_table *_managed_opp(struct device *dev, int index); #else -static inline void _of_init_opp_table(struct opp_table *opp_table, struct device *dev) {} +static inline void _of_init_opp_table(struct opp_table *opp_table, struct device *dev, int index) {} +static inline struct opp_table *_managed_opp(struct device *dev, int index) { return NULL; } #endif #ifdef CONFIG_DEBUG_FS diff --git a/drivers/pci/controller/pcie-cadence.c b/drivers/pci/controller/pcie-cadence.c index 86f1b002c846..975bcdd6b5c0 100644 --- a/drivers/pci/controller/pcie-cadence.c +++ b/drivers/pci/controller/pcie-cadence.c @@ -180,11 +180,11 @@ int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie) return 0; } - phy = devm_kzalloc(dev, sizeof(*phy) * phy_count, GFP_KERNEL); + phy = devm_kcalloc(dev, phy_count, sizeof(*phy), GFP_KERNEL); if (!phy) return -ENOMEM; - link = devm_kzalloc(dev, sizeof(*link) * phy_count, GFP_KERNEL); + link = devm_kcalloc(dev, phy_count, sizeof(*link), GFP_KERNEL); if (!link) return -ENOMEM; diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 7f01f6f60b87..d0b7dd8fb184 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -485,7 +485,13 @@ static int armpmu_filter_match(struct perf_event *event) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); unsigned int cpu = smp_processor_id(); - return cpumask_test_cpu(cpu, &armpmu->supported_cpus); + int ret; + + ret = cpumask_test_cpu(cpu, &armpmu->supported_cpus); + if (ret && armpmu->filter_match) + return armpmu->filter_match(event); + + return ret; } static ssize_t armpmu_cpumask_show(struct device *dev, diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index 4a8a8efadefa..cf73a403d22d 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -636,6 +636,14 @@ static int mcp23s08_irq_setup(struct mcp23s08 *mcp) return err; } + return 0; +} + +static int mcp23s08_irqchip_setup(struct mcp23s08 *mcp) +{ + struct gpio_chip *chip = &mcp->chip; + int err; + err = gpiochip_irqchip_add_nested(chip, &mcp23s08_irq_chip, 0, @@ -912,7 +920,7 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, } if (mcp->irq && mcp->irq_controller) { - ret = mcp23s08_irq_setup(mcp); + ret = mcp23s08_irqchip_setup(mcp); if (ret) goto fail; } @@ -944,6 +952,9 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, goto fail; } + if (mcp->irq) + ret = mcp23s08_irq_setup(mcp); + fail: if (ret < 0) dev_dbg(dev, "can't setup chip %d, --> %d\n", addr, ret); diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 398393ab5df8..b6fd4838f60f 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -520,7 +520,7 @@ static int get_next_event_xfer(struct cros_ec_device *ec_dev, ret = cros_ec_cmd_xfer(ec_dev, msg); if (ret > 0) { ec_dev->event_size = ret - 1; - memcpy(&ec_dev->event_data, msg->data, ec_dev->event_size); + memcpy(&ec_dev->event_data, msg->data, ret); } return ret; diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index 295d8dcba48c..bb92874b1175 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -1133,47 +1133,40 @@ static const struct rapl_defaults rapl_defaults_cht = { .compute_time_window = rapl_compute_time_window_atom, }; -#define RAPL_CPU(_model, _ops) { \ - .vendor = X86_VENDOR_INTEL, \ - .family = 6, \ - .model = _model, \ - .driver_data = (kernel_ulong_t)&_ops, \ - } - static const struct x86_cpu_id rapl_ids[] __initconst = { - RAPL_CPU(INTEL_FAM6_SANDYBRIDGE, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_SANDYBRIDGE_X, rapl_defaults_core), - - RAPL_CPU(INTEL_FAM6_IVYBRIDGE, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_IVYBRIDGE_X, rapl_defaults_core), - - RAPL_CPU(INTEL_FAM6_HASWELL_CORE, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_HASWELL_ULT, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_HASWELL_GT3E, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_HASWELL_X, rapl_defaults_hsw_server), - - RAPL_CPU(INTEL_FAM6_BROADWELL_CORE, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_BROADWELL_GT3E, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_BROADWELL_XEON_D, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_BROADWELL_X, rapl_defaults_hsw_server), - - RAPL_CPU(INTEL_FAM6_SKYLAKE_DESKTOP, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_SKYLAKE_MOBILE, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_SKYLAKE_X, rapl_defaults_hsw_server), - RAPL_CPU(INTEL_FAM6_KABYLAKE_MOBILE, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_KABYLAKE_DESKTOP, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_CANNONLAKE_MOBILE, rapl_defaults_core), - - RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT1, rapl_defaults_byt), - RAPL_CPU(INTEL_FAM6_ATOM_AIRMONT, rapl_defaults_cht), - RAPL_CPU(INTEL_FAM6_ATOM_MERRIFIELD, rapl_defaults_tng), - RAPL_CPU(INTEL_FAM6_ATOM_MOOREFIELD, rapl_defaults_ann), - RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_ATOM_GEMINI_LAKE, rapl_defaults_core), - RAPL_CPU(INTEL_FAM6_ATOM_DENVERTON, rapl_defaults_core), - - RAPL_CPU(INTEL_FAM6_XEON_PHI_KNL, rapl_defaults_hsw_server), - RAPL_CPU(INTEL_FAM6_XEON_PHI_KNM, rapl_defaults_hsw_server), + INTEL_CPU_FAM6(SANDYBRIDGE, rapl_defaults_core), + INTEL_CPU_FAM6(SANDYBRIDGE_X, rapl_defaults_core), + + INTEL_CPU_FAM6(IVYBRIDGE, rapl_defaults_core), + INTEL_CPU_FAM6(IVYBRIDGE_X, rapl_defaults_core), + + INTEL_CPU_FAM6(HASWELL_CORE, rapl_defaults_core), + INTEL_CPU_FAM6(HASWELL_ULT, rapl_defaults_core), + INTEL_CPU_FAM6(HASWELL_GT3E, rapl_defaults_core), + INTEL_CPU_FAM6(HASWELL_X, rapl_defaults_hsw_server), + + INTEL_CPU_FAM6(BROADWELL_CORE, rapl_defaults_core), + INTEL_CPU_FAM6(BROADWELL_GT3E, rapl_defaults_core), + INTEL_CPU_FAM6(BROADWELL_XEON_D, rapl_defaults_core), + INTEL_CPU_FAM6(BROADWELL_X, rapl_defaults_hsw_server), + + INTEL_CPU_FAM6(SKYLAKE_DESKTOP, rapl_defaults_core), + INTEL_CPU_FAM6(SKYLAKE_MOBILE, rapl_defaults_core), + INTEL_CPU_FAM6(SKYLAKE_X, rapl_defaults_hsw_server), + INTEL_CPU_FAM6(KABYLAKE_MOBILE, rapl_defaults_core), + INTEL_CPU_FAM6(KABYLAKE_DESKTOP, rapl_defaults_core), + INTEL_CPU_FAM6(CANNONLAKE_MOBILE, rapl_defaults_core), + + INTEL_CPU_FAM6(ATOM_SILVERMONT1, rapl_defaults_byt), + INTEL_CPU_FAM6(ATOM_AIRMONT, rapl_defaults_cht), + INTEL_CPU_FAM6(ATOM_MERRIFIELD, rapl_defaults_tng), + INTEL_CPU_FAM6(ATOM_MOOREFIELD, rapl_defaults_ann), + INTEL_CPU_FAM6(ATOM_GOLDMONT, rapl_defaults_core), + INTEL_CPU_FAM6(ATOM_GEMINI_LAKE, rapl_defaults_core), + INTEL_CPU_FAM6(ATOM_DENVERTON, rapl_defaults_core), + + INTEL_CPU_FAM6(XEON_PHI_KNL, rapl_defaults_hsw_server), + INTEL_CPU_FAM6(XEON_PHI_KNM, rapl_defaults_hsw_server), {} }; MODULE_DEVICE_TABLE(x86cpu, rapl_ids); diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c index eceba3858cef..2f61f5579aa5 100644 --- a/drivers/s390/char/sclp_early_core.c +++ b/drivers/s390/char/sclp_early_core.c @@ -210,11 +210,11 @@ static int sclp_early_setup(int disable, int *have_linemode, int *have_vt220) * Output one or more lines of text on the SCLP console (VT220 and / * or line-mode). */ -void __sclp_early_printk(const char *str, unsigned int len) +void __sclp_early_printk(const char *str, unsigned int len, unsigned int force) { int have_linemode, have_vt220; - if (sclp_init_state != sclp_init_state_uninitialized) + if (!force && sclp_init_state != sclp_init_state_uninitialized) return; if (sclp_early_setup(0, &have_linemode, &have_vt220) != 0) return; @@ -227,5 +227,10 @@ void __sclp_early_printk(const char *str, unsigned int len) void sclp_early_printk(const char *str) { - __sclp_early_printk(str, strlen(str)); + __sclp_early_printk(str, strlen(str), 0); +} + +void sclp_early_printk_force(const char *str) +{ + __sclp_early_printk(str, strlen(str), 1); } diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index dbe7c7ac9ac8..fd77e46eb3b2 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -163,7 +163,7 @@ static bool pfn_array_table_iova_pinned(struct pfn_array_table *pat, for (i = 0; i < pat->pat_nr; i++, pa++) for (j = 0; j < pa->pa_nr; j++) - if (pa->pa_iova_pfn[i] == iova_pfn) + if (pa->pa_iova_pfn[j] == iova_pfn) return true; return false; diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 770fa9cfc310..f47d16b5810b 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -22,6 +22,7 @@ #include "vfio_ccw_private.h" struct workqueue_struct *vfio_ccw_work_q; +struct kmem_cache *vfio_ccw_io_region; /* * Helpers @@ -79,7 +80,7 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) cp_update_scsw(&private->cp, &irb->scsw); cp_free(&private->cp); } - memcpy(private->io_region.irb_area, irb, sizeof(*irb)); + memcpy(private->io_region->irb_area, irb, sizeof(*irb)); if (private->io_trigger) eventfd_signal(private->io_trigger, 1); @@ -114,6 +115,14 @@ static int vfio_ccw_sch_probe(struct subchannel *sch) private = kzalloc(sizeof(*private), GFP_KERNEL | GFP_DMA); if (!private) return -ENOMEM; + + private->io_region = kmem_cache_zalloc(vfio_ccw_io_region, + GFP_KERNEL | GFP_DMA); + if (!private->io_region) { + kfree(private); + return -ENOMEM; + } + private->sch = sch; dev_set_drvdata(&sch->dev, private); @@ -139,6 +148,7 @@ out_disable: cio_disable_subchannel(sch); out_free: dev_set_drvdata(&sch->dev, NULL); + kmem_cache_free(vfio_ccw_io_region, private->io_region); kfree(private); return ret; } @@ -153,6 +163,7 @@ static int vfio_ccw_sch_remove(struct subchannel *sch) dev_set_drvdata(&sch->dev, NULL); + kmem_cache_free(vfio_ccw_io_region, private->io_region); kfree(private); return 0; @@ -232,10 +243,20 @@ static int __init vfio_ccw_sch_init(void) if (!vfio_ccw_work_q) return -ENOMEM; + vfio_ccw_io_region = kmem_cache_create_usercopy("vfio_ccw_io_region", + sizeof(struct ccw_io_region), 0, + SLAB_ACCOUNT, 0, + sizeof(struct ccw_io_region), NULL); + if (!vfio_ccw_io_region) { + destroy_workqueue(vfio_ccw_work_q); + return -ENOMEM; + } + isc_register(VFIO_CCW_ISC); ret = css_driver_register(&vfio_ccw_sch_driver); if (ret) { isc_unregister(VFIO_CCW_ISC); + kmem_cache_destroy(vfio_ccw_io_region); destroy_workqueue(vfio_ccw_work_q); } @@ -246,6 +267,7 @@ static void __exit vfio_ccw_sch_exit(void) { css_driver_unregister(&vfio_ccw_sch_driver); isc_unregister(VFIO_CCW_ISC); + kmem_cache_destroy(vfio_ccw_io_region); destroy_workqueue(vfio_ccw_work_q); } module_init(vfio_ccw_sch_init); diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c index 797a82731159..f94aa01f9c36 100644 --- a/drivers/s390/cio/vfio_ccw_fsm.c +++ b/drivers/s390/cio/vfio_ccw_fsm.c @@ -93,13 +93,13 @@ static void fsm_io_error(struct vfio_ccw_private *private, enum vfio_ccw_event event) { pr_err("vfio-ccw: FSM: I/O request from state:%d\n", private->state); - private->io_region.ret_code = -EIO; + private->io_region->ret_code = -EIO; } static void fsm_io_busy(struct vfio_ccw_private *private, enum vfio_ccw_event event) { - private->io_region.ret_code = -EBUSY; + private->io_region->ret_code = -EBUSY; } static void fsm_disabled_irq(struct vfio_ccw_private *private, @@ -126,7 +126,7 @@ static void fsm_io_request(struct vfio_ccw_private *private, { union orb *orb; union scsw *scsw = &private->scsw; - struct ccw_io_region *io_region = &private->io_region; + struct ccw_io_region *io_region = private->io_region; struct mdev_device *mdev = private->mdev; char *errstr = "request"; diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c index 41eeb57d68a3..f673e106c041 100644 --- a/drivers/s390/cio/vfio_ccw_ops.c +++ b/drivers/s390/cio/vfio_ccw_ops.c @@ -174,7 +174,7 @@ static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev, return -EINVAL; private = dev_get_drvdata(mdev_parent_dev(mdev)); - region = &private->io_region; + region = private->io_region; if (copy_to_user(buf, (void *)region + *ppos, count)) return -EFAULT; @@ -196,7 +196,7 @@ static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev, if (private->state != VFIO_CCW_STATE_IDLE) return -EACCES; - region = &private->io_region; + region = private->io_region; if (copy_from_user((void *)region + *ppos, buf, count)) return -EFAULT; diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h index 78a66d96756b..078e46f9623d 100644 --- a/drivers/s390/cio/vfio_ccw_private.h +++ b/drivers/s390/cio/vfio_ccw_private.h @@ -41,7 +41,7 @@ struct vfio_ccw_private { atomic_t avail; struct mdev_device *mdev; struct notifier_block nb; - struct ccw_io_region io_region; + struct ccw_io_region *io_region; struct channel_program cp; struct irb irb; diff --git a/drivers/sbus/char/openprom.c b/drivers/sbus/char/openprom.c index 7b31f19ade83..050879a2ddef 100644 --- a/drivers/sbus/char/openprom.c +++ b/drivers/sbus/char/openprom.c @@ -715,22 +715,13 @@ static struct miscdevice openprom_dev = { static int __init openprom_init(void) { - struct device_node *dp; int err; err = misc_register(&openprom_dev); if (err) return err; - dp = of_find_node_by_path("/"); - dp = dp->child; - while (dp) { - if (!strcmp(dp->name, "options")) - break; - dp = dp->sibling; - } - options_node = dp; - + options_node = of_get_child_by_name(of_find_node_by_path("/"), "options"); if (!options_node) { misc_deregister(&openprom_dev); return -EIO; diff --git a/drivers/sbus/char/oradax.c b/drivers/sbus/char/oradax.c index 524f9ea62e52..6516bc3cb58b 100644 --- a/drivers/sbus/char/oradax.c +++ b/drivers/sbus/char/oradax.c @@ -689,8 +689,7 @@ static int dax_open(struct inode *inode, struct file *f) alloc_error: kfree(ctx->ccb_buf); done: - if (ctx != NULL) - kfree(ctx); + kfree(ctx); return -ENOMEM; } diff --git a/drivers/soc/fsl/qbman/bman_ccsr.c b/drivers/soc/fsl/qbman/bman_ccsr.c index 05c42235dd41..7c3cc968053c 100644 --- a/drivers/soc/fsl/qbman/bman_ccsr.c +++ b/drivers/soc/fsl/qbman/bman_ccsr.c @@ -120,6 +120,7 @@ static void bm_set_memory(u64 ba, u32 size) */ static dma_addr_t fbpr_a; static size_t fbpr_sz; +static int __bman_probed; static int bman_fbpr(struct reserved_mem *rmem) { @@ -166,6 +167,12 @@ static irqreturn_t bman_isr(int irq, void *ptr) return IRQ_HANDLED; } +int bman_is_probed(void) +{ + return __bman_probed; +} +EXPORT_SYMBOL_GPL(bman_is_probed); + static int fsl_bman_probe(struct platform_device *pdev) { int ret, err_irq; @@ -175,6 +182,8 @@ static int fsl_bman_probe(struct platform_device *pdev) u16 id, bm_pool_cnt; u8 major, minor; + __bman_probed = -1; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { dev_err(dev, "Can't get %pOF property 'IORESOURCE_MEM'\n", @@ -255,6 +264,8 @@ static int fsl_bman_probe(struct platform_device *pdev) return ret; } + __bman_probed = 1; + return 0; }; diff --git a/drivers/soc/fsl/qbman/qman_ccsr.c b/drivers/soc/fsl/qbman/qman_ccsr.c index 79cba58387a5..6fd5fef5f39b 100644 --- a/drivers/soc/fsl/qbman/qman_ccsr.c +++ b/drivers/soc/fsl/qbman/qman_ccsr.c @@ -273,6 +273,7 @@ static const struct qman_error_info_mdata error_mdata[] = { static u32 __iomem *qm_ccsr_start; /* A SDQCR mask comprising all the available/visible pool channels */ static u32 qm_pools_sdqcr; +static int __qman_probed; static inline u32 qm_ccsr_in(u32 offset) { @@ -686,6 +687,12 @@ static int qman_resource_init(struct device *dev) return 0; } +int qman_is_probed(void) +{ + return __qman_probed; +} +EXPORT_SYMBOL_GPL(qman_is_probed); + static int fsl_qman_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -695,6 +702,8 @@ static int fsl_qman_probe(struct platform_device *pdev) u16 id; u8 major, minor; + __qman_probed = -1; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { dev_err(dev, "Can't get %pOF property 'IORESOURCE_MEM'\n", @@ -828,6 +837,8 @@ static int fsl_qman_probe(struct platform_device *pdev) if (ret) return ret; + __qman_probed = 1; + return 0; } diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c index a120002b630e..3e9391d117c5 100644 --- a/drivers/soc/fsl/qbman/qman_portal.c +++ b/drivers/soc/fsl/qbman/qman_portal.c @@ -227,6 +227,14 @@ static int qman_portal_probe(struct platform_device *pdev) int irq, cpu, err; u32 val; + err = qman_is_probed(); + if (!err) + return -EPROBE_DEFER; + if (err < 0) { + dev_err(&pdev->dev, "failing probe due to qman probe error\n"); + return -ENODEV; + } + pcfg = devm_kmalloc(dev, sizeof(*pcfg), GFP_KERNEL); if (!pcfg) return -ENOMEM; diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 29ec34387246..1515074e18fb 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -868,8 +868,8 @@ static int qcom_geni_serial_port_setup(struct uart_port *uport) geni_se_init(&port->se, port->rx_wm, port->rx_rfr); geni_se_select_mode(&port->se, port->xfer_mode); if (!uart_console(uport)) { - port->rx_fifo = devm_kzalloc(uport->dev, - port->rx_fifo_depth * sizeof(u32), GFP_KERNEL); + port->rx_fifo = devm_kcalloc(uport->dev, + port->rx_fifo_depth, sizeof(u32), GFP_KERNEL); if (!port->rx_fifo) return -ENOMEM; } diff --git a/drivers/video/fbdev/aty/atyfb.h b/drivers/video/fbdev/aty/atyfb.h index 8235b285dbb2..d09bab3bf224 100644 --- a/drivers/video/fbdev/aty/atyfb.h +++ b/drivers/video/fbdev/aty/atyfb.h @@ -333,6 +333,8 @@ extern const struct aty_pll_ops aty_pll_ct; /* Integrated */ extern void aty_set_pll_ct(const struct fb_info *info, const union aty_pll *pll); extern u8 aty_ld_pll_ct(int offset, const struct atyfb_par *par); +extern const u8 aty_postdividers[8]; + /* * Hardware cursor support @@ -359,7 +361,6 @@ static inline void wait_for_idle(struct atyfb_par *par) extern void aty_reset_engine(const struct atyfb_par *par); extern void aty_init_engine(struct atyfb_par *par, struct fb_info *info); -extern u8 aty_ld_pll_ct(int offset, const struct atyfb_par *par); void atyfb_copyarea(struct fb_info *info, const struct fb_copyarea *area); void atyfb_fillrect(struct fb_info *info, const struct fb_fillrect *rect); diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index a9a8272f7a6e..05111e90f168 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -3087,17 +3087,18 @@ static int atyfb_setup_sparc(struct pci_dev *pdev, struct fb_info *info, /* * PLL Reference Divider M: */ - M = pll_regs[2]; + M = pll_regs[PLL_REF_DIV]; /* * PLL Feedback Divider N (Dependent on CLOCK_CNTL): */ - N = pll_regs[7 + (clock_cntl & 3)]; + N = pll_regs[VCLK0_FB_DIV + (clock_cntl & 3)]; /* * PLL Post Divider P (Dependent on CLOCK_CNTL): */ - P = 1 << (pll_regs[6] >> ((clock_cntl & 3) << 1)); + P = aty_postdividers[((pll_regs[VCLK_POST_DIV] >> ((clock_cntl & 3) << 1)) & 3) | + ((pll_regs[PLL_EXT_CNTL] >> (2 + (clock_cntl & 3))) & 4)]; /* * PLL Divider Q: diff --git a/drivers/video/fbdev/aty/mach64_ct.c b/drivers/video/fbdev/aty/mach64_ct.c index 74a62aa193c0..f87cc81f4fa2 100644 --- a/drivers/video/fbdev/aty/mach64_ct.c +++ b/drivers/video/fbdev/aty/mach64_ct.c @@ -115,7 +115,7 @@ static void aty_st_pll_ct(int offset, u8 val, const struct atyfb_par *par) */ #define Maximum_DSP_PRECISION 7 -static u8 postdividers[] = {1,2,4,8,3}; +const u8 aty_postdividers[8] = {1,2,4,8,3,5,6,12}; static int aty_dsp_gt(const struct fb_info *info, u32 bpp, struct pll_ct *pll) { @@ -222,7 +222,7 @@ static int aty_valid_pll_ct(const struct fb_info *info, u32 vclk_per, struct pll pll->vclk_post_div += (q < 64*8); pll->vclk_post_div += (q < 32*8); } - pll->vclk_post_div_real = postdividers[pll->vclk_post_div]; + pll->vclk_post_div_real = aty_postdividers[pll->vclk_post_div]; // pll->vclk_post_div <<= 6; pll->vclk_fb_div = q * pll->vclk_post_div_real / 8; pllvclk = (1000000 * 2 * pll->vclk_fb_div) / @@ -513,7 +513,7 @@ static int aty_init_pll_ct(const struct fb_info *info, union aty_pll *pll) u8 mclk_fb_div, pll_ext_cntl; pll->ct.pll_ref_div = aty_ld_pll_ct(PLL_REF_DIV, par); pll_ext_cntl = aty_ld_pll_ct(PLL_EXT_CNTL, par); - pll->ct.xclk_post_div_real = postdividers[pll_ext_cntl & 0x07]; + pll->ct.xclk_post_div_real = aty_postdividers[pll_ext_cntl & 0x07]; mclk_fb_div = aty_ld_pll_ct(MCLK_FB_DIV, par); if (pll_ext_cntl & PLL_MFB_TIMES_4_2B) mclk_fb_div <<= 1; @@ -535,7 +535,7 @@ static int aty_init_pll_ct(const struct fb_info *info, union aty_pll *pll) xpost_div += (q < 64*8); xpost_div += (q < 32*8); } - pll->ct.xclk_post_div_real = postdividers[xpost_div]; + pll->ct.xclk_post_div_real = aty_postdividers[xpost_div]; pll->ct.mclk_fb_div = q * pll->ct.xclk_post_div_real / 8; #ifdef CONFIG_PPC @@ -584,7 +584,7 @@ static int aty_init_pll_ct(const struct fb_info *info, union aty_pll *pll) mpost_div += (q < 64*8); mpost_div += (q < 32*8); } - sclk_post_div_real = postdividers[mpost_div]; + sclk_post_div_real = aty_postdividers[mpost_div]; pll->ct.sclk_fb_div = q * sclk_post_div_real / 8; pll->ct.spll_cntl2 = mpost_div << 4; #ifdef DEBUG diff --git a/fs/afs/cell.c b/fs/afs/cell.c index f3d0bef16d78..6127f0fcd62c 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -514,6 +514,8 @@ static int afs_alloc_anon_key(struct afs_cell *cell) */ static int afs_activate_cell(struct afs_net *net, struct afs_cell *cell) { + struct hlist_node **p; + struct afs_cell *pcell; int ret; if (!cell->anonymous_key) { @@ -534,7 +536,18 @@ static int afs_activate_cell(struct afs_net *net, struct afs_cell *cell) return ret; mutex_lock(&net->proc_cells_lock); - list_add_tail(&cell->proc_link, &net->proc_cells); + for (p = &net->proc_cells.first; *p; p = &(*p)->next) { + pcell = hlist_entry(*p, struct afs_cell, proc_link); + if (strcmp(cell->name, pcell->name) < 0) + break; + } + + cell->proc_link.pprev = p; + cell->proc_link.next = *p; + rcu_assign_pointer(*p, &cell->proc_link.next); + if (cell->proc_link.next) + cell->proc_link.next->pprev = &cell->proc_link.next; + afs_dynroot_mkdir(net, cell); mutex_unlock(&net->proc_cells_lock); return 0; @@ -550,7 +563,7 @@ static void afs_deactivate_cell(struct afs_net *net, struct afs_cell *cell) afs_proc_cell_remove(cell); mutex_lock(&net->proc_cells_lock); - list_del_init(&cell->proc_link); + hlist_del_rcu(&cell->proc_link); afs_dynroot_rmdir(net, cell); mutex_unlock(&net->proc_cells_lock); diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 1cde710a8013..f29c6dade7f6 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -265,7 +265,7 @@ int afs_dynroot_populate(struct super_block *sb) return -ERESTARTSYS; net->dynroot_sb = sb; - list_for_each_entry(cell, &net->proc_cells, proc_link) { + hlist_for_each_entry(cell, &net->proc_cells, proc_link) { ret = afs_dynroot_mkdir(net, cell); if (ret < 0) goto error; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 871a228d7f37..34c02fdcc25f 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -242,7 +242,7 @@ struct afs_net { seqlock_t cells_lock; struct mutex proc_cells_lock; - struct list_head proc_cells; + struct hlist_head proc_cells; /* Known servers. Theoretically each fileserver can only be in one * cell, but in practice, people create aliases and subsets and there's @@ -320,7 +320,7 @@ struct afs_cell { struct afs_net *net; struct key *anonymous_key; /* anonymous user key for this cell */ struct work_struct manager; /* Manager for init/deinit/dns */ - struct list_head proc_link; /* /proc cell list link */ + struct hlist_node proc_link; /* /proc cell list link */ #ifdef CONFIG_AFS_FSCACHE struct fscache_cookie *cache; /* caching cookie */ #endif diff --git a/fs/afs/main.c b/fs/afs/main.c index e84fe822a960..107427688edd 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -87,7 +87,7 @@ static int __net_init afs_net_init(struct net *net_ns) timer_setup(&net->cells_timer, afs_cells_timer, 0); mutex_init(&net->proc_cells_lock); - INIT_LIST_HEAD(&net->proc_cells); + INIT_HLIST_HEAD(&net->proc_cells); seqlock_init(&net->fs_lock); net->fs_servers = RB_ROOT; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 476dcbb79713..9101f62707af 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -33,9 +33,8 @@ static inline struct afs_net *afs_seq2net_single(struct seq_file *m) static int afs_proc_cells_show(struct seq_file *m, void *v) { struct afs_cell *cell = list_entry(v, struct afs_cell, proc_link); - struct afs_net *net = afs_seq2net(m); - if (v == &net->proc_cells) { + if (v == SEQ_START_TOKEN) { /* display header on line 1 */ seq_puts(m, "USE NAME\n"); return 0; @@ -50,12 +49,12 @@ static void *afs_proc_cells_start(struct seq_file *m, loff_t *_pos) __acquires(rcu) { rcu_read_lock(); - return seq_list_start_head(&afs_seq2net(m)->proc_cells, *_pos); + return seq_hlist_start_head_rcu(&afs_seq2net(m)->proc_cells, *_pos); } static void *afs_proc_cells_next(struct seq_file *m, void *v, loff_t *pos) { - return seq_list_next(v, &afs_seq2net(m)->proc_cells, pos); + return seq_hlist_next_rcu(v, &afs_seq2net(m)->proc_cells, pos); } static void afs_proc_cells_stop(struct seq_file *m, void *v) diff --git a/fs/afs/server.c b/fs/afs/server.c index 1d329e6981d5..2f306c0cc4ee 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -199,9 +199,11 @@ static struct afs_server *afs_install_server(struct afs_net *net, write_sequnlock(&net->fs_addr_lock); ret = 0; + goto out; exists: afs_get_server(server); +out: write_sequnlock(&net->fs_lock); return server; } @@ -666,6 +666,8 @@ struct page *dax_layout_busy_page(struct address_space *mapping) while (index < end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { + pgoff_t nr_pages = 1; + for (i = 0; i < pagevec_count(&pvec); i++) { struct page *pvec_ent = pvec.pages[i]; void *entry; @@ -680,8 +682,15 @@ struct page *dax_layout_busy_page(struct address_space *mapping) xa_lock_irq(&mapping->i_pages); entry = get_unlocked_mapping_entry(mapping, index, NULL); - if (entry) + if (entry) { page = dax_busy_page(entry); + /* + * Account for multi-order entries at + * the end of the pagevec. + */ + if (i + 1 >= pagevec_count(&pvec)) + nr_pages = 1UL << dax_radix_order(entry); + } put_unlocked_mapping_entry(mapping, index, entry); xa_unlock_irq(&mapping->i_pages); if (page) @@ -696,7 +705,7 @@ struct page *dax_layout_busy_page(struct address_space *mapping) */ pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); - index++; + index += nr_pages; if (page) break; diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index defc2168de91..f58c0cacc531 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -682,6 +682,7 @@ int fat_count_free_clusters(struct super_block *sb) if (ops->ent_get(&fatent) == FAT_ENT_FREE) free++; } while (fat_ent_next(sbi, &fatent)); + cond_resched(); } sbi->free_clusters = free; sbi->free_clus_valid = 1; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 03128ed1f34e..84544a4f012d 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1057,7 +1057,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, } } release_metapath(&mp); - if (gfs2_is_jdata(ip)) + if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip)) iomap->page_done = gfs2_iomap_journaled_page_done; return 0; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 8e712b614e6e..933aac5da193 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -96,7 +96,9 @@ struct ocfs2_unblock_ctl { }; /* Lockdep class keys */ +#ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key lockdep_keys[OCFS2_NUM_LOCK_TYPES]; +#endif static int ocfs2_check_meta_downconvert(struct ocfs2_lock_res *lockres, int new_level); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index bf000c8aeffb..fec62e9dfbe6 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2337,8 +2337,8 @@ late_initcall(ubifs_init); static void __exit ubifs_exit(void) { - WARN_ON(list_empty(&ubifs_infos)); - WARN_ON(atomic_long_read(&ubifs_clean_zn_cnt) == 0); + WARN_ON(!list_empty(&ubifs_infos)); + WARN_ON(atomic_long_read(&ubifs_clean_zn_cnt) != 0); dbg_debugfs_exit(); ubifs_compressors_exit(); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 5289e22cb081..42ea7bab9144 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1220,35 +1220,92 @@ retry: return 0; } +/* Unlock both inodes after they've been prepped for a range clone. */ +STATIC void +xfs_reflink_remap_unlock( + struct file *file_in, + struct file *file_out) +{ + struct inode *inode_in = file_inode(file_in); + struct xfs_inode *src = XFS_I(inode_in); + struct inode *inode_out = file_inode(file_out); + struct xfs_inode *dest = XFS_I(inode_out); + bool same_inode = (inode_in == inode_out); + + xfs_iunlock(dest, XFS_MMAPLOCK_EXCL); + if (!same_inode) + xfs_iunlock(src, XFS_MMAPLOCK_SHARED); + inode_unlock(inode_out); + if (!same_inode) + inode_unlock_shared(inode_in); +} + /* - * Link a range of blocks from one file to another. + * If we're reflinking to a point past the destination file's EOF, we must + * zero any speculative post-EOF preallocations that sit between the old EOF + * and the destination file offset. */ -int -xfs_reflink_remap_range( +static int +xfs_reflink_zero_posteof( + struct xfs_inode *ip, + loff_t pos) +{ + loff_t isize = i_size_read(VFS_I(ip)); + + if (pos <= isize) + return 0; + + trace_xfs_zero_eof(ip, isize, pos - isize); + return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL, + &xfs_iomap_ops); +} + +/* + * Prepare two files for range cloning. Upon a successful return both inodes + * will have the iolock and mmaplock held, the page cache of the out file will + * be truncated, and any leases on the out file will have been broken. This + * function borrows heavily from xfs_file_aio_write_checks. + * + * The VFS allows partial EOF blocks to "match" for dedupe even though it hasn't + * checked that the bytes beyond EOF physically match. Hence we cannot use the + * EOF block in the source dedupe range because it's not a complete block match, + * hence can introduce a corruption into the file that has it's block replaced. + * + * In similar fashion, the VFS file cloning also allows partial EOF blocks to be + * "block aligned" for the purposes of cloning entire files. However, if the + * source file range includes the EOF block and it lands within the existing EOF + * of the destination file, then we can expose stale data from beyond the source + * file EOF in the destination file. + * + * XFS doesn't support partial block sharing, so in both cases we have check + * these cases ourselves. For dedupe, we can simply round the length to dedupe + * down to the previous whole block and ignore the partial EOF block. While this + * means we can't dedupe the last block of a file, this is an acceptible + * tradeoff for simplicity on implementation. + * + * For cloning, we want to share the partial EOF block if it is also the new EOF + * block of the destination file. If the partial EOF block lies inside the + * existing destination EOF, then we have to abort the clone to avoid exposing + * stale data in the destination file. Hence we reject these clone attempts with + * -EINVAL in this case. + */ +STATIC int +xfs_reflink_remap_prep( struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, + u64 *len, bool is_dedupe) { struct inode *inode_in = file_inode(file_in); struct xfs_inode *src = XFS_I(inode_in); struct inode *inode_out = file_inode(file_out); struct xfs_inode *dest = XFS_I(inode_out); - struct xfs_mount *mp = src->i_mount; bool same_inode = (inode_in == inode_out); - xfs_fileoff_t sfsbno, dfsbno; - xfs_filblks_t fsblen; - xfs_extlen_t cowextsize; + u64 blkmask = i_blocksize(inode_in) - 1; ssize_t ret; - if (!xfs_sb_version_hasreflink(&mp->m_sb)) - return -EOPNOTSUPP; - - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - /* Lock both files against IO */ ret = xfs_iolock_two_inodes_and_break_layout(inode_in, inode_out); if (ret) @@ -1270,33 +1327,115 @@ xfs_reflink_remap_range( goto out_unlock; ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, - &len, is_dedupe); + len, is_dedupe); if (ret <= 0) goto out_unlock; + /* + * If the dedupe data matches, chop off the partial EOF block + * from the source file so we don't try to dedupe the partial + * EOF block. + */ + if (is_dedupe) { + *len &= ~blkmask; + } else if (*len & blkmask) { + /* + * The user is attempting to share a partial EOF block, + * if it's inside the destination EOF then reject it. + */ + if (pos_out + *len < i_size_read(inode_out)) { + ret = -EINVAL; + goto out_unlock; + } + } + /* Attach dquots to dest inode before changing block map */ ret = xfs_qm_dqattach(dest); if (ret) goto out_unlock; - trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); - /* - * Clear out post-eof preallocations because we don't have page cache - * backing the delayed allocations and they'll never get freed on - * their own. + * Zero existing post-eof speculative preallocations in the destination + * file. */ - if (xfs_can_free_eofblocks(dest, true)) { - ret = xfs_free_eofblocks(dest); - if (ret) - goto out_unlock; - } + ret = xfs_reflink_zero_posteof(dest, pos_out); + if (ret) + goto out_unlock; /* Set flags and remap blocks. */ ret = xfs_reflink_set_inode_flag(src, dest); if (ret) goto out_unlock; + /* Zap any page cache for the destination file's range. */ + truncate_inode_pages_range(&inode_out->i_data, pos_out, + PAGE_ALIGN(pos_out + *len) - 1); + + /* If we're altering the file contents... */ + if (!is_dedupe) { + /* + * ...update the timestamps (which will grab the ilock again + * from xfs_fs_dirty_inode, so we have to call it before we + * take the ilock). + */ + if (!(file_out->f_mode & FMODE_NOCMTIME)) { + ret = file_update_time(file_out); + if (ret) + goto out_unlock; + } + + /* + * ...clear the security bits if the process is not being run + * by root. This keeps people from modifying setuid and setgid + * binaries. + */ + ret = file_remove_privs(file_out); + if (ret) + goto out_unlock; + } + + return 1; +out_unlock: + xfs_reflink_remap_unlock(file_in, file_out); + return ret; +} + +/* + * Link a range of blocks from one file to another. + */ +int +xfs_reflink_remap_range( + struct file *file_in, + loff_t pos_in, + struct file *file_out, + loff_t pos_out, + u64 len, + bool is_dedupe) +{ + struct inode *inode_in = file_inode(file_in); + struct xfs_inode *src = XFS_I(inode_in); + struct inode *inode_out = file_inode(file_out); + struct xfs_inode *dest = XFS_I(inode_out); + struct xfs_mount *mp = src->i_mount; + xfs_fileoff_t sfsbno, dfsbno; + xfs_filblks_t fsblen; + xfs_extlen_t cowextsize; + ssize_t ret; + + if (!xfs_sb_version_hasreflink(&mp->m_sb)) + return -EOPNOTSUPP; + + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + + /* Prepare and then clone file data. */ + ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out, + &len, is_dedupe); + if (ret <= 0) + return ret; + + trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); + dfsbno = XFS_B_TO_FSBT(mp, pos_out); sfsbno = XFS_B_TO_FSBT(mp, pos_in); fsblen = XFS_B_TO_FSB(mp, len); @@ -1305,10 +1444,6 @@ xfs_reflink_remap_range( if (ret) goto out_unlock; - /* Zap any page cache for the destination file's range. */ - truncate_inode_pages_range(&inode_out->i_data, pos_out, - PAGE_ALIGN(pos_out + len) - 1); - /* * Carry the cowextsize hint from src to dest if we're sharing the * entire source file to the entire destination file, the source file @@ -1325,12 +1460,7 @@ xfs_reflink_remap_range( is_dedupe); out_unlock: - xfs_iunlock(dest, XFS_MMAPLOCK_EXCL); - if (!same_inode) - xfs_iunlock(src, XFS_MMAPLOCK_SHARED); - inode_unlock(inode_out); - if (!same_inode) - inode_unlock_shared(inode_in); + xfs_reflink_remap_unlock(file_in, file_out); if (ret) trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); return ret; diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index 8e0b8250a139..cf59e6210d27 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -104,6 +104,7 @@ enum cppc_regs { * today. */ struct cppc_perf_caps { + u32 guaranteed_perf; u32 highest_perf; u32 nominal_perf; u32 lowest_perf; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 7b75ff6e2fce..d7701d466b60 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -68,7 +68,7 @@ */ #ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION #define TEXT_MAIN .text .text.[0-9a-zA-Z_]* -#define DATA_MAIN .data .data.[0-9a-zA-Z_]* +#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..LPBX* #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]* #define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* #define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* @@ -613,8 +613,8 @@ #define EXIT_DATA \ *(.exit.data .exit.data.*) \ - *(.fini_array) \ - *(.dtors) \ + *(.fini_array .fini_array.*) \ + *(.dtors .dtors.*) \ MEM_DISCARD(exit.data*) \ MEM_DISCARD(exit.rodata*) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ff20b677fb9f..22254c1fe1c5 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -412,6 +412,7 @@ struct cgroup { * specific task are charged to the dom_cgrp. */ struct cgroup *dom_cgrp; + struct cgroup *old_dom_cgrp; /* used while enabling threaded */ /* per-cpu recursive resource statistics */ struct cgroup_rstat_cpu __percpu *rstat_cpu; diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 4325d6fdde9b..faed7a8977e8 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -81,6 +81,7 @@ struct cpuidle_device { unsigned int registered:1; unsigned int enabled:1; unsigned int use_deepest_state:1; + unsigned int poll_time_limit:1; unsigned int cpu; int last_residency; @@ -99,16 +100,6 @@ struct cpuidle_device { DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices); DECLARE_PER_CPU(struct cpuidle_device, cpuidle_dev); -/** - * cpuidle_get_last_residency - retrieves the last state's residency time - * @dev: the target CPU - */ -static inline int cpuidle_get_last_residency(struct cpuidle_device *dev) -{ - return dev->last_residency; -} - - /**************************** * CPUIDLE DRIVER INTERFACE * ****************************/ diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 3aae5b3af87c..e4963b0f45da 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -198,6 +198,14 @@ extern void devm_devfreq_remove_device(struct device *dev, extern int devfreq_suspend_device(struct devfreq *devfreq); extern int devfreq_resume_device(struct devfreq *devfreq); +/** + * update_devfreq() - Reevaluate the device and configure frequency + * @devfreq: the devfreq device + * + * Note: devfreq->lock must be held + */ +extern int update_devfreq(struct devfreq *devfreq); + /* Helper functions for devfreq user device driver with OPP. */ extern struct dev_pm_opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq, u32 flags); diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 0ea328e71ec9..a4d5eb37744a 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -95,6 +95,13 @@ struct gpio_irq_chip { unsigned int num_parents; /** + * @parent_irq: + * + * For use by gpiochip_set_cascaded_irqchip() + */ + unsigned int parent_irq; + + /** * @parents: * * A list of interrupt parents of a GPIO chip. This is owned by the diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3f4c0b167333..d4b0c79d2924 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -668,10 +668,6 @@ typedef struct pglist_data { wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; #endif -#ifdef CONFIG_NUMA_BALANCING - /* Lock serializing the migrate rate limiting window */ - spinlock_t numabalancing_migrate_lock; -#endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c7861e4b402c..d837dad24b4c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2458,6 +2458,13 @@ struct netdev_notifier_info { struct netlink_ext_ack *extack; }; +struct netdev_notifier_info_ext { + struct netdev_notifier_info info; /* must be first */ + union { + u32 mtu; + } ext; +}; + struct netdev_notifier_change_info { struct netdev_notifier_info info; /* must be first */ unsigned int flags_changed; diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 10f92e1d8e7b..bf309ff6f244 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -99,6 +99,7 @@ struct arm_pmu { void (*stop)(struct arm_pmu *); void (*reset)(void *); int (*map_event)(struct perf_event *event); + int (*filter_match)(struct perf_event *event); int num_events; bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 776c546d581a..3b5d7280e52e 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -17,11 +17,36 @@ #include <linux/notifier.h> #include <linux/spinlock.h> -/* Defines used for the flags field in the struct generic_pm_domain */ -#define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ -#define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ -#define GENPD_FLAG_ALWAYS_ON (1U << 2) /* PM domain is always powered on */ -#define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3) /* Keep devices active if wakeup */ +/* + * Flags to control the behaviour of a genpd. + * + * These flags may be set in the struct generic_pm_domain's flags field by a + * genpd backend driver. The flags must be set before it calls pm_genpd_init(), + * which initializes a genpd. + * + * GENPD_FLAG_PM_CLK: Instructs genpd to use the PM clk framework, + * while powering on/off attached devices. + * + * GENPD_FLAG_IRQ_SAFE: This informs genpd that its backend callbacks, + * ->power_on|off(), doesn't sleep. Hence, these + * can be invoked from within atomic context, which + * enables genpd to power on/off the PM domain, + * even when pm_runtime_is_irq_safe() returns true, + * for any of its attached devices. Note that, a + * genpd having this flag set, requires its + * masterdomains to also have it set. + * + * GENPD_FLAG_ALWAYS_ON: Instructs genpd to always keep the PM domain + * powered on. + * + * GENPD_FLAG_ACTIVE_WAKEUP: Instructs genpd to keep the PM domain powered + * on, in case any of its attached devices is used + * in the wakeup path to serve system wakeups. + */ +#define GENPD_FLAG_PM_CLK (1U << 0) +#define GENPD_FLAG_IRQ_SAFE (1U << 1) +#define GENPD_FLAG_ALWAYS_ON (1U << 2) +#define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3) enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 099b31960dec..5d399eeef172 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -79,6 +79,7 @@ struct dev_pm_set_opp_data { #if defined(CONFIG_PM_OPP) struct opp_table *dev_pm_opp_get_opp_table(struct device *dev); +struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev, int index); void dev_pm_opp_put_opp_table(struct opp_table *opp_table); unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); @@ -136,6 +137,11 @@ static inline struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) return ERR_PTR(-ENOTSUPP); } +static inline struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev, int index) +{ + return ERR_PTR(-ENOTSUPP); +} + static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {} static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 5a28ac9284f0..3f529ad9a9d2 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -251,6 +251,7 @@ static inline bool idle_should_enter_s2idle(void) return unlikely(s2idle_state == S2IDLE_STATE_ENTER); } +extern bool pm_suspend_via_s2idle(void); extern void __init pm_states_init(void); extern void s2idle_set_ops(const struct platform_s2idle_ops *ops); extern void s2idle_wake(void); @@ -282,6 +283,7 @@ static inline void pm_set_suspend_via_firmware(void) {} static inline void pm_set_resume_via_firmware(void) {} static inline bool pm_suspend_via_firmware(void) { return false; } static inline bool pm_resume_via_firmware(void) { return false; } +static inline bool pm_suspend_via_s2idle(void) { return false; } static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } diff --git a/include/net/devlink.h b/include/net/devlink.h index b9b89d6604d4..99efc156a309 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -298,7 +298,7 @@ struct devlink_resource { #define DEVLINK_RESOURCE_ID_PARENT_TOP 0 -#define DEVLINK_PARAM_MAX_STRING_VALUE 32 +#define __DEVLINK_PARAM_MAX_STRING_VALUE 32 enum devlink_param_type { DEVLINK_PARAM_TYPE_U8, DEVLINK_PARAM_TYPE_U16, @@ -311,7 +311,7 @@ union devlink_param_value { u8 vu8; u16 vu16; u32 vu32; - const char *vstr; + char vstr[__DEVLINK_PARAM_MAX_STRING_VALUE]; bool vbool; }; @@ -553,6 +553,8 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); +void devlink_param_value_str_fill(union devlink_param_value *dst_val, + const char *src); struct devlink_region *devlink_region_create(struct devlink *devlink, const char *region_name, u32 region_max_snapshots, @@ -789,6 +791,12 @@ devlink_param_value_changed(struct devlink *devlink, u32 param_id) { } +static inline void +devlink_param_value_str_fill(union devlink_param_value *dst_val, + const char *src) +{ +} + static inline struct devlink_region * devlink_region_create(struct devlink *devlink, const char *region_name, diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 69c91d1934c1..c9b7b136939d 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -394,6 +394,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned int nh_flags); +void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, diff --git a/include/soc/fsl/bman.h b/include/soc/fsl/bman.h index eaaf56df4086..5b99cb2ea5ef 100644 --- a/include/soc/fsl/bman.h +++ b/include/soc/fsl/bman.h @@ -126,4 +126,12 @@ int bman_release(struct bman_pool *pool, const struct bm_buffer *bufs, u8 num); */ int bman_acquire(struct bman_pool *pool, struct bm_buffer *bufs, u8 num); +/** + * bman_is_probed - Check if bman is probed + * + * Returns 1 if the bman driver successfully probed, -1 if the bman driver + * failed to probe or 0 if the bman driver did not probed yet. + */ +int bman_is_probed(void); + #endif /* __FSL_BMAN_H */ diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h index d4dfefdee6c1..597783b8a3a0 100644 --- a/include/soc/fsl/qman.h +++ b/include/soc/fsl/qman.h @@ -1186,4 +1186,12 @@ int qman_alloc_cgrid_range(u32 *result, u32 count); */ int qman_release_cgrid(u32 id); +/** + * qman_is_probed - Check if qman is probed + * + * Returns 1 if the qman driver successfully probed, -1 if the qman driver + * failed to probe or 0 if the qman driver did not probed yet. + */ +int qman_is_probed(void); + #endif /* __FSL_QMAN_H */ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 837393fa897b..573d5b901fb1 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -931,6 +931,7 @@ TRACE_EVENT(rxrpc_tx_packet, TP_fast_assign( __entry->call = call_id; memcpy(&__entry->whdr, whdr, sizeof(__entry->whdr)); + __entry->where = where; ), TP_printk("c=%08x %08x:%08x:%08x:%04x %08x %08x %02x %02x %s %s", diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index ac9e8c96d9bd..8cb3a6fef553 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -18,14 +18,17 @@ struct smc_diag_req { * on the internal clcsock, and more SMC-related socket data */ struct smc_diag_msg { - __u8 diag_family; - __u8 diag_state; - __u8 diag_mode; - __u8 diag_shutdown; + __u8 diag_family; + __u8 diag_state; + union { + __u8 diag_mode; + __u8 diag_fallback; /* the old name of the field */ + }; + __u8 diag_shutdown; struct inet_diag_sockid id; - __u32 diag_uid; - __u64 diag_inode; + __u32 diag_uid; + __aligned_u64 diag_inode; }; /* Mode of a connection */ @@ -99,11 +102,11 @@ struct smc_diag_fallback { }; struct smcd_diag_dmbinfo { /* SMC-D Socket internals */ - __u32 linkid; /* Link identifier */ - __u64 peer_gid; /* Peer GID */ - __u64 my_gid; /* My GID */ - __u64 token; /* Token of DMB */ - __u64 peer_token; /* Token of remote DMBE */ + __u32 linkid; /* Link identifier */ + __aligned_u64 peer_gid; /* Peer GID */ + __aligned_u64 my_gid; /* My GID */ + __aligned_u64 token; /* Token of DMB */ + __aligned_u64 peer_token; /* Token of remote DMBE */ }; #endif /* _UAPI_SMC_DIAG_H_ */ diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h index 09d00f8c442b..09502de447f5 100644 --- a/include/uapi/linux/udp.h +++ b/include/uapi/linux/udp.h @@ -40,5 +40,6 @@ struct udphdr { #define UDP_ENCAP_L2TPINUDP 3 /* rfc2661 */ #define UDP_ENCAP_GTP0 4 /* GSM TS 09.60 */ #define UDP_ENCAP_GTP1U 5 /* 3GPP TS 29.060 */ +#define UDP_ENCAP_RXRPC 6 #endif /* _UAPI_LINUX_UDP_H */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index aae10baf1902..4a3dae2a8283 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2836,11 +2836,12 @@ restart: } /** - * cgroup_save_control - save control masks of a subtree + * cgroup_save_control - save control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * - * Save ->subtree_control and ->subtree_ss_mask to the respective old_ - * prefixed fields for @cgrp's subtree including @cgrp itself. + * Save ->subtree_control, ->subtree_ss_mask and ->dom_cgrp to the + * respective old_ prefixed fields for @cgrp's subtree including @cgrp + * itself. */ static void cgroup_save_control(struct cgroup *cgrp) { @@ -2850,6 +2851,7 @@ static void cgroup_save_control(struct cgroup *cgrp) cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->old_subtree_control = dsct->subtree_control; dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; + dsct->old_dom_cgrp = dsct->dom_cgrp; } } @@ -2875,11 +2877,12 @@ static void cgroup_propagate_control(struct cgroup *cgrp) } /** - * cgroup_restore_control - restore control masks of a subtree + * cgroup_restore_control - restore control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * - * Restore ->subtree_control and ->subtree_ss_mask from the respective old_ - * prefixed fields for @cgrp's subtree including @cgrp itself. + * Restore ->subtree_control, ->subtree_ss_mask and ->dom_cgrp from the + * respective old_ prefixed fields for @cgrp's subtree including @cgrp + * itself. */ static void cgroup_restore_control(struct cgroup *cgrp) { @@ -2889,6 +2892,7 @@ static void cgroup_restore_control(struct cgroup *cgrp) cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { dsct->subtree_control = dsct->old_subtree_control; dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; + dsct->dom_cgrp = dsct->old_dom_cgrp; } } @@ -3196,6 +3200,8 @@ static int cgroup_enable_threaded(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup *dom_cgrp = parent->dom_cgrp; + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; int ret; lockdep_assert_held(&cgroup_mutex); @@ -3225,12 +3231,13 @@ static int cgroup_enable_threaded(struct cgroup *cgrp) */ cgroup_save_control(cgrp); - cgrp->dom_cgrp = dom_cgrp; + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) + if (dsct == cgrp || cgroup_is_threaded(dsct)) + dsct->dom_cgrp = dom_cgrp; + ret = cgroup_apply_control(cgrp); if (!ret) parent->nr_threaded_children++; - else - cgrp->dom_cgrp = cgrp; cgroup_finalize_control(cgrp, ret); return ret; diff --git a/kernel/power/process.c b/kernel/power/process.c index 7381d49a44db..4b6a54da7e65 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -96,7 +96,7 @@ static int try_to_freeze_tasks(bool user_only) if (wq_busy) show_workqueue_state(); - if (!wakeup) { + if (!wakeup || pm_debug_messages_on) { read_lock(&tasklist_lock); for_each_process_thread(g, p) { if (p != current && !freezer_should_skip(p) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 5342f6fc022e..0bd595a0b610 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -63,6 +63,12 @@ static DECLARE_SWAIT_QUEUE_HEAD(s2idle_wait_head); enum s2idle_states __read_mostly s2idle_state; static DEFINE_RAW_SPINLOCK(s2idle_lock); +bool pm_suspend_via_s2idle(void) +{ + return mem_sleep_current == PM_SUSPEND_TO_IDLE; +} +EXPORT_SYMBOL_GPL(pm_suspend_via_s2idle); + void s2idle_set_ops(const struct platform_s2idle_ops *ops) { lock_system_sleep(); diff --git a/lib/Makefile b/lib/Makefile index ca3f7ebb900d..423876446810 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -119,7 +119,6 @@ obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/ obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/ obj-$(CONFIG_REED_SOLOMON) += reed_solomon/ obj-$(CONFIG_BCH) += bch.o -CFLAGS_bch.o := $(call cc-option,-Wframe-larger-than=4500) obj-$(CONFIG_LZO_COMPRESS) += lzo/ obj-$(CONFIG_LZO_DECOMPRESS) += lzo/ obj-$(CONFIG_LZ4_COMPRESS) += lz4/ diff --git a/lib/bch.c b/lib/bch.c index 7b0f2006698b..5db6d3a4c8a6 100644 --- a/lib/bch.c +++ b/lib/bch.c @@ -79,20 +79,19 @@ #define GF_T(_p) (CONFIG_BCH_CONST_T) #define GF_N(_p) ((1 << (CONFIG_BCH_CONST_M))-1) #define BCH_MAX_M (CONFIG_BCH_CONST_M) +#define BCH_MAX_T (CONFIG_BCH_CONST_T) #else #define GF_M(_p) ((_p)->m) #define GF_T(_p) ((_p)->t) #define GF_N(_p) ((_p)->n) -#define BCH_MAX_M 15 +#define BCH_MAX_M 15 /* 2KB */ +#define BCH_MAX_T 64 /* 64 bit correction */ #endif -#define BCH_MAX_T (((1 << BCH_MAX_M) - 1) / BCH_MAX_M) - #define BCH_ECC_WORDS(_p) DIV_ROUND_UP(GF_M(_p)*GF_T(_p), 32) #define BCH_ECC_BYTES(_p) DIV_ROUND_UP(GF_M(_p)*GF_T(_p), 8) #define BCH_ECC_MAX_WORDS DIV_ROUND_UP(BCH_MAX_M * BCH_MAX_T, 32) -#define BCH_ECC_MAX_BYTES DIV_ROUND_UP(BCH_MAX_M * BCH_MAX_T, 8) #ifndef dbg #define dbg(_fmt, args...) do {} while (0) @@ -202,6 +201,9 @@ void encode_bch(struct bch_control *bch, const uint8_t *data, const uint32_t * const tab3 = tab2 + 256*(l+1); const uint32_t *pdata, *p0, *p1, *p2, *p3; + if (WARN_ON(r_bytes > sizeof(r))) + return; + if (ecc) { /* load ecc parity bytes into internal 32-bit buffer */ load_ecc8(bch, bch->ecc_buf, ecc); @@ -1285,6 +1287,13 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly) */ goto fail; + if (t > BCH_MAX_T) + /* + * we can support larger than 64 bits if necessary, at the + * cost of higher stack usage. + */ + goto fail; + /* sanity checks */ if ((t < 1) || (m*t >= ((1 << m)-1))) /* invalid t value */ diff --git a/lib/vsprintf.c b/lib/vsprintf.c index d5b3a3f95c01..812e59e13fe6 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2794,7 +2794,7 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) copy = end - str; memcpy(str, args, copy); str += len; - args += len; + args += len + 1; } } if (process) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 00704060b7f7..58269f8ba7c4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2885,9 +2885,6 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, if (!(pvmw->pmd && !pvmw->pte)) return; - mmu_notifier_invalidate_range_start(mm, address, - address + HPAGE_PMD_SIZE); - flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); pmdval = *pvmw->pmd; pmdp_invalidate(vma, address, pvmw->pmd); @@ -2900,9 +2897,6 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, set_pmd_at(mm, address, pvmw->pmd, pmdswp); page_remove_rmap(page, true); put_page(page); - - mmu_notifier_invalidate_range_end(mm, address, - address + HPAGE_PMD_SIZE); } void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) diff --git a/mm/mmap.c b/mm/mmap.c index 5f2b2b184c60..f7cd9cb966c0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1410,7 +1410,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (flags & MAP_FIXED_NOREPLACE) { struct vm_area_struct *vma = find_vma(mm, addr); - if (vma && vma->vm_start <= addr) + if (vma && vma->vm_start < addr + len) return -EEXIST; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 706a738c0aee..e2ef1c17942f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6193,15 +6193,6 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages, return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT; } -#ifdef CONFIG_NUMA_BALANCING -static void pgdat_init_numabalancing(struct pglist_data *pgdat) -{ - spin_lock_init(&pgdat->numabalancing_migrate_lock); -} -#else -static void pgdat_init_numabalancing(struct pglist_data *pgdat) {} -#endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void pgdat_init_split_queue(struct pglist_data *pgdat) { @@ -6226,7 +6217,6 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat) { pgdat_resize_init(pgdat); - pgdat_init_numabalancing(pgdat); pgdat_init_split_queue(pgdat); pgdat_init_kcompactd(pgdat); diff --git a/mm/percpu.c b/mm/percpu.c index a749d4d96e3e..4b90682623e9 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1212,6 +1212,7 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; + pcpu_mem_free(chunk->md_blocks); pcpu_mem_free(chunk->bound_map); pcpu_mem_free(chunk->alloc_map); pcpu_mem_free(chunk); diff --git a/net/core/dev.c b/net/core/dev.c index 82114e1111e6..93243479085f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1752,6 +1752,28 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) } EXPORT_SYMBOL(call_netdevice_notifiers); +/** + * call_netdevice_notifiers_mtu - call all network notifier blocks + * @val: value passed unmodified to notifier function + * @dev: net_device pointer passed unmodified to notifier function + * @arg: additional u32 argument passed to the notifier function + * + * Call all network notifier blocks. Parameters and return value + * are as for raw_notifier_call_chain(). + */ +static int call_netdevice_notifiers_mtu(unsigned long val, + struct net_device *dev, u32 arg) +{ + struct netdev_notifier_info_ext info = { + .info.dev = dev, + .ext.mtu = arg, + }; + + BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0); + + return call_netdevice_notifiers_info(val, &info.info); +} + #ifdef CONFIG_NET_INGRESS static DEFINE_STATIC_KEY_FALSE(ingress_needed_key); @@ -7574,14 +7596,16 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, err = __dev_set_mtu(dev, new_mtu); if (!err) { - err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, + orig_mtu); err = notifier_to_errno(err); if (err) { /* setting mtu back and notifying everyone again, * so that they have a chance to revert changes. */ __dev_set_mtu(dev, orig_mtu); - call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, + new_mtu); } } return err; diff --git a/net/core/devlink.c b/net/core/devlink.c index 8c0ed225e280..6bc42933be4a 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2995,6 +2995,8 @@ devlink_param_value_get_from_info(const struct devlink_param *param, struct genl_info *info, union devlink_param_value *value) { + int len; + if (param->type != DEVLINK_PARAM_TYPE_BOOL && !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) return -EINVAL; @@ -3010,10 +3012,13 @@ devlink_param_value_get_from_info(const struct devlink_param *param, value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); break; case DEVLINK_PARAM_TYPE_STRING: - if (nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) > - DEVLINK_PARAM_MAX_STRING_VALUE) + len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]), + nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); + if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) || + len >= __DEVLINK_PARAM_MAX_STRING_VALUE) return -EINVAL; - value->vstr = nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + strcpy(value->vstr, + nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); break; case DEVLINK_PARAM_TYPE_BOOL: value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ? @@ -3100,7 +3105,10 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, return -EOPNOTSUPP; if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) { - param_item->driverinit_value = value; + if (param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, value.vstr); + else + param_item->driverinit_value = value; param_item->driverinit_value_valid = true; } else { if (!param->set) @@ -4540,7 +4548,10 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, DEVLINK_PARAM_CMODE_DRIVERINIT)) return -EOPNOTSUPP; - *init_val = param_item->driverinit_value; + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(init_val->vstr, param_item->driverinit_value.vstr); + else + *init_val = param_item->driverinit_value; return 0; } @@ -4571,7 +4582,10 @@ int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, DEVLINK_PARAM_CMODE_DRIVERINIT)) return -EOPNOTSUPP; - param_item->driverinit_value = init_val; + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, init_val.vstr); + else + param_item->driverinit_value = init_val; param_item->driverinit_value_valid = true; devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); @@ -4604,6 +4618,23 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) EXPORT_SYMBOL_GPL(devlink_param_value_changed); /** + * devlink_param_value_str_fill - Safely fill-up the string preventing + * from overflow of the preallocated buffer + * + * @dst_val: destination devlink_param_value + * @src: source buffer + */ +void devlink_param_value_str_fill(union devlink_param_value *dst_val, + const char *src) +{ + size_t len; + + len = strlcpy(dst_val->vstr, src, __DEVLINK_PARAM_MAX_STRING_VALUE); + WARN_ON(len >= __DEVLINK_PARAM_MAX_STRING_VALUE); +} +EXPORT_SYMBOL_GPL(devlink_param_value_str_fill); + +/** * devlink_region_create - create a new address region * * @devlink: devlink diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b2c807f67aba..428094b577fc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4452,14 +4452,16 @@ EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { - if (unlikely(start > skb_headlen(skb)) || - unlikely((int)start + off > skb_headlen(skb) - 2)) { - net_warn_ratelimited("bad partial csum: csum=%u/%u len=%u\n", - start, off, skb_headlen(skb)); + u32 csum_end = (u32)start + (u32)off + sizeof(__sum16); + u32 csum_start = skb_headroom(skb) + (u32)start; + + if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) { + net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n", + start, off, skb_headroom(skb), skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum_start = skb_headroom(skb) + start; + skb->csum_start = csum_start; skb->csum_offset = off; skb_set_transport_header(skb, start); return true; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 2998b0e47d4b..0113993e9b2c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1243,7 +1243,8 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct netdev_notifier_changeupper_info *info; + struct netdev_notifier_changeupper_info *upper_info = ptr; + struct netdev_notifier_info_ext *info_ext = ptr; struct in_device *in_dev; struct net *net = dev_net(dev); unsigned int flags; @@ -1278,16 +1279,19 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_sync_up(dev, RTNH_F_LINKDOWN); else fib_sync_down_dev(dev, event, false); - /* fall through */ + rt_cache_flush(net); + break; case NETDEV_CHANGEMTU: + fib_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(net); break; case NETDEV_CHANGEUPPER: - info = ptr; + upper_info = ptr; /* flush all routes if dev is linked to or unlinked from * an L3 master device (e.g., VRF) */ - if (info->upper_dev && netif_is_l3_master(info->upper_dev)) + if (upper_info->upper_dev && + netif_is_l3_master(upper_info->upper_dev)) fib_disable_ip(dev, NETDEV_DOWN, true); break; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f3c89ccf14c5..446204ca7406 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1470,6 +1470,56 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh, return NOTIFY_DONE; } +/* Update the PMTU of exceptions when: + * - the new MTU of the first hop becomes smaller than the PMTU + * - the old MTU was the same as the PMTU, and it limited discovery of + * larger MTUs on the path. With that limit raised, we can now + * discover larger MTUs + * A special case is locked exceptions, for which the PMTU is smaller + * than the minimal accepted PMTU: + * - if the new MTU is greater than the PMTU, don't make any change + * - otherwise, unlock and set PMTU + */ +static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig) +{ + struct fnhe_hash_bucket *bucket; + int i; + + bucket = rcu_dereference_protected(nh->nh_exceptions, 1); + if (!bucket) + return; + + for (i = 0; i < FNHE_HASH_SIZE; i++) { + struct fib_nh_exception *fnhe; + + for (fnhe = rcu_dereference_protected(bucket[i].chain, 1); + fnhe; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) { + if (fnhe->fnhe_mtu_locked) { + if (new <= fnhe->fnhe_pmtu) { + fnhe->fnhe_pmtu = new; + fnhe->fnhe_mtu_locked = false; + } + } else if (new < fnhe->fnhe_pmtu || + orig == fnhe->fnhe_pmtu) { + fnhe->fnhe_pmtu = new; + } + } + } +} + +void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) +{ + unsigned int hash = fib_devindex_hashfn(dev->ifindex); + struct hlist_head *head = &fib_info_devhash[hash]; + struct fib_nh *nh; + + hlist_for_each_entry(nh, head, nh_hash) { + if (nh->nh_dev == dev) + nh_update_mtu(nh, dev->mtu, orig_mtu); + } +} + /* Event force Flags Description * NETDEV_CHANGE 0 LINKDOWN Carrier OFF, not for scope host * NETDEV_DOWN 0 LINKDOWN|DEAD Link down, not for scope host diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b678466da451..8501554e96a4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1001,21 +1001,22 @@ out: kfree_skb(skb); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; + u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; if (ip_mtu_locked(dst)) return; - if (ipv4_mtu(dst) < mtu) + if (old_mtu < mtu) return; if (mtu < ip_rt_min_pmtu) { lock = true; - mtu = ip_rt_min_pmtu; + mtu = min(old_mtu, ip_rt_min_pmtu); } - if (rt->rt_pmtu == mtu && + if (rt->rt_pmtu == mtu && !lock && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) return; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7d69dd6fa7e8..c32a4c16b7ff 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1627,7 +1627,7 @@ busy_check: *err = error; return NULL; } -EXPORT_SYMBOL_GPL(__skb_recv_udp); +EXPORT_SYMBOL(__skb_recv_udp); /* * This should be easy, if there is something there we diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5516f55e214b..cbe46175bb59 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -196,6 +196,8 @@ void fib6_info_destroy_rcu(struct rcu_head *head) *ppcpu_rt = NULL; } } + + free_percpu(f6i->rt6i_pcpu); } lwtstate_put(f6i->fib6_nh.nh_lwtstate); diff --git a/net/rds/send.c b/net/rds/send.c index 57b3d5a8b2db..fe785ee819dd 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1007,7 +1007,8 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, return ret; } -static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn) +static int rds_send_mprds_hash(struct rds_sock *rs, + struct rds_connection *conn, int nonblock) { int hash; @@ -1023,10 +1024,16 @@ static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn) * used. But if we are interrupted, we have to use the zero * c_path in case the connection ends up being non-MP capable. */ - if (conn->c_npaths == 0) + if (conn->c_npaths == 0) { + /* Cannot wait for the connection be made, so just use + * the base c_path. + */ + if (nonblock) + return 0; if (wait_event_interruptible(conn->c_hs_waitq, conn->c_npaths != 0)) hash = 0; + } if (conn->c_npaths == 1) hash = 0; } @@ -1256,7 +1263,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) } if (conn->c_trans->t_mp_capable) - cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)]; + cpath = &conn->c_path[rds_send_mprds_hash(rs, conn, nonblock)]; else cpath = &conn->c_path[0]; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ef9554131434..a6e6cae82c30 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -302,6 +302,7 @@ struct rxrpc_peer { /* calculated RTT cache */ #define RXRPC_RTT_CACHE_SIZE 32 + spinlock_t rtt_input_lock; /* RTT lock for input routine */ ktime_t rtt_last_req; /* Time of last RTT request */ u64 rtt; /* Current RTT estimate (in nS) */ u64 rtt_sum; /* Sum of cache contents */ @@ -442,17 +443,17 @@ struct rxrpc_connection { spinlock_t state_lock; /* state-change lock */ enum rxrpc_conn_cache_state cache_state; enum rxrpc_conn_proto_state state; /* current state of connection */ - u32 local_abort; /* local abort code */ - u32 remote_abort; /* remote abort code */ + u32 abort_code; /* Abort code of connection abort */ int debug_id; /* debug ID for printks */ atomic_t serial; /* packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ u32 security_nonce; /* response re-use preventer */ - u16 service_id; /* Service ID, possibly upgraded */ + u32 service_id; /* Service ID, possibly upgraded */ u8 size_align; /* data size alignment (for security) */ u8 security_size; /* security header size */ u8 security_ix; /* security type */ u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */ + short error; /* Local error code */ }; static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp) @@ -635,6 +636,8 @@ struct rxrpc_call { bool tx_phase; /* T if transmission phase, F if receive phase */ u8 nr_jumbo_bad; /* Number of jumbo dups/exceeds-windows */ + spinlock_t input_lock; /* Lock for packet input to this call */ + /* receive-phase ACK management */ u8 ackr_reason; /* reason to ACK */ u16 ackr_skew; /* skew on packet being ACK'd */ @@ -720,8 +723,6 @@ int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); void rxrpc_discard_prealloc(struct rxrpc_sock *); struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_sock *, - struct rxrpc_peer *, - struct rxrpc_connection *, struct sk_buff *); void rxrpc_accept_incoming_calls(struct rxrpc_local *); struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long, @@ -891,8 +892,9 @@ extern unsigned long rxrpc_conn_idle_client_fast_expiry; extern struct idr rxrpc_client_conn_ids; void rxrpc_destroy_client_conn_ids(void); -int rxrpc_connect_call(struct rxrpc_call *, struct rxrpc_conn_parameters *, - struct sockaddr_rxrpc *, gfp_t); +int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, + struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, + gfp_t); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_call *); void rxrpc_put_client_conn(struct rxrpc_connection *); @@ -965,7 +967,7 @@ void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* * input.c */ -void rxrpc_data_ready(struct sock *); +int rxrpc_input_packet(struct sock *, struct sk_buff *); /* * insecure.c @@ -1045,10 +1047,11 @@ void rxrpc_peer_keepalive_worker(struct work_struct *); */ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); -struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *, +struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *, struct sockaddr_rxrpc *, gfp_t); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t); -void rxrpc_new_incoming_peer(struct rxrpc_local *, struct rxrpc_peer *); +void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *, + struct rxrpc_peer *); void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 9c7f26d06a52..652e314de38e 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -287,7 +287,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, (peer_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); - rxrpc_new_incoming_peer(local, peer); + rxrpc_new_incoming_peer(rx, local, peer); } /* Now allocate and set up the connection */ @@ -333,11 +333,11 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, */ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, struct rxrpc_sock *rx, - struct rxrpc_peer *peer, - struct rxrpc_connection *conn, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_connection *conn; + struct rxrpc_peer *peer; struct rxrpc_call *call; _enter(""); @@ -354,6 +354,13 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, goto out; } + /* The peer, connection and call may all have sprung into existence due + * to a duplicate packet being handled on another CPU in parallel, so + * we have to recheck the routing. However, we're now holding + * rx->incoming_lock, so the values should remain stable. + */ + conn = rxrpc_find_connection_rcu(local, skb, &peer); + call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb); if (!call) { skb->mark = RXRPC_SKB_MARK_REJECT_BUSY; @@ -396,20 +403,22 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, case RXRPC_CONN_SERVICE: write_lock(&call->state_lock); - if (rx->discard_new_call) - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; - else - call->state = RXRPC_CALL_SERVER_ACCEPTING; + if (call->state < RXRPC_CALL_COMPLETE) { + if (rx->discard_new_call) + call->state = RXRPC_CALL_SERVER_RECV_REQUEST; + else + call->state = RXRPC_CALL_SERVER_ACCEPTING; + } write_unlock(&call->state_lock); break; case RXRPC_CONN_REMOTELY_ABORTED: rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, - conn->remote_abort, -ECONNABORTED); + conn->abort_code, conn->error); break; case RXRPC_CONN_LOCALLY_ABORTED: rxrpc_abort_call("CON", call, sp->hdr.seq, - conn->local_abort, -ECONNABORTED); + conn->abort_code, conn->error); break; default: BUG(); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 799f75b6900d..8f1a8f85b1f9 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -138,6 +138,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, init_waitqueue_head(&call->waitq); spin_lock_init(&call->lock); spin_lock_init(&call->notify_lock); + spin_lock_init(&call->input_lock); rwlock_init(&call->state_lock); atomic_set(&call->usage, 1); call->debug_id = debug_id; @@ -287,7 +288,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, /* Set up or get a connection record and set the protocol parameters, * including channel number and call ID. */ - ret = rxrpc_connect_call(call, cp, srx, gfp); + ret = rxrpc_connect_call(rx, call, cp, srx, gfp); if (ret < 0) goto error; @@ -339,7 +340,7 @@ int rxrpc_retry_client_call(struct rxrpc_sock *rx, /* Set up or get a connection record and set the protocol parameters, * including channel number and call ID. */ - ret = rxrpc_connect_call(call, cp, srx, gfp); + ret = rxrpc_connect_call(rx, call, cp, srx, gfp); if (ret < 0) goto error; diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 8acf74fe24c0..521189f4b666 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -276,7 +276,8 @@ dont_reuse: * If we return with a connection, the call will be on its waiting list. It's * left to the caller to assign a channel and wake up the call. */ -static int rxrpc_get_client_conn(struct rxrpc_call *call, +static int rxrpc_get_client_conn(struct rxrpc_sock *rx, + struct rxrpc_call *call, struct rxrpc_conn_parameters *cp, struct sockaddr_rxrpc *srx, gfp_t gfp) @@ -289,7 +290,7 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp); + cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp); if (!cp->peer) goto error; @@ -683,7 +684,8 @@ out: * find a connection for a call * - called in process context with IRQs enabled */ -int rxrpc_connect_call(struct rxrpc_call *call, +int rxrpc_connect_call(struct rxrpc_sock *rx, + struct rxrpc_call *call, struct rxrpc_conn_parameters *cp, struct sockaddr_rxrpc *srx, gfp_t gfp) @@ -696,7 +698,7 @@ int rxrpc_connect_call(struct rxrpc_call *call, rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper); rxrpc_cull_active_client_conns(rxnet); - ret = rxrpc_get_client_conn(call, cp, srx, gfp); + ret = rxrpc_get_client_conn(rx, call, cp, srx, gfp); if (ret < 0) goto out; diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 6df56ce68861..b6fca8ebb117 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -126,7 +126,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, switch (chan->last_type) { case RXRPC_PACKET_TYPE_ABORT: - _proto("Tx ABORT %%%u { %d } [re]", serial, conn->local_abort); + _proto("Tx ABORT %%%u { %d } [re]", serial, conn->abort_code); break; case RXRPC_PACKET_TYPE_ACK: trace_rxrpc_tx_ack(chan->call_debug_id, serial, @@ -153,13 +153,12 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, * pass a connection-level abort onto all calls on that connection */ static void rxrpc_abort_calls(struct rxrpc_connection *conn, - enum rxrpc_call_completion compl, - u32 abort_code, int error) + enum rxrpc_call_completion compl) { struct rxrpc_call *call; int i; - _enter("{%d},%x", conn->debug_id, abort_code); + _enter("{%d},%x", conn->debug_id, conn->abort_code); spin_lock(&conn->channel_lock); @@ -172,9 +171,11 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, trace_rxrpc_abort(call->debug_id, "CON", call->cid, call->call_id, 0, - abort_code, error); + conn->abort_code, + conn->error); if (rxrpc_set_call_completion(call, compl, - abort_code, error)) + conn->abort_code, + conn->error)) rxrpc_notify_socket(call); } } @@ -207,10 +208,12 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, return 0; } + conn->error = error; + conn->abort_code = abort_code; conn->state = RXRPC_CONN_LOCALLY_ABORTED; spin_unlock_bh(&conn->state_lock); - rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code, error); + rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED); msg.msg_name = &conn->params.peer->srx.transport; msg.msg_namelen = conn->params.peer->srx.transport_len; @@ -229,7 +232,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, whdr._rsvd = 0; whdr.serviceId = htons(conn->service_id); - word = htonl(conn->local_abort); + word = htonl(conn->abort_code); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); @@ -240,7 +243,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, serial = atomic_inc_return(&conn->serial); whdr.serial = htonl(serial); - _proto("Tx CONN ABORT %%%u { %d }", serial, conn->local_abort); + _proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { @@ -315,9 +318,10 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, abort_code = ntohl(wtmp); _proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code); + conn->error = -ECONNABORTED; + conn->abort_code = abort_code; conn->state = RXRPC_CONN_REMOTELY_ABORTED; - rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, - abort_code, -ECONNABORTED); + rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED); return -ECONNABORTED; case RXRPC_PACKET_TYPE_CHALLENGE: diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 800f5b8a1baa..570b49d2da42 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -216,10 +216,11 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb, /* * Apply a hard ACK by advancing the Tx window. */ -static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, +static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, struct rxrpc_ack_summary *summary) { struct sk_buff *skb, *list = NULL; + bool rot_last = false; int ix; u8 annotation; @@ -243,15 +244,17 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, skb->next = list; list = skb; - if (annotation & RXRPC_TX_ANNO_LAST) + if (annotation & RXRPC_TX_ANNO_LAST) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); + rot_last = true; + } if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK) summary->nr_rot_new_acks++; } spin_unlock(&call->lock); - trace_rxrpc_transmit(call, (test_bit(RXRPC_CALL_TX_LAST, &call->flags) ? + trace_rxrpc_transmit(call, (rot_last ? rxrpc_transmit_rotate_last : rxrpc_transmit_rotate)); wake_up(&call->waitq); @@ -262,6 +265,8 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, skb->next = NULL; rxrpc_free_skb(skb, rxrpc_skb_tx_freed); } + + return rot_last; } /* @@ -273,23 +278,26 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, const char *abort_why) { + unsigned int state; ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); write_lock(&call->state_lock); - switch (call->state) { + state = call->state; + switch (state) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: if (reply_begun) - call->state = RXRPC_CALL_CLIENT_RECV_REPLY; + call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY; else - call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY; break; case RXRPC_CALL_SERVER_AWAIT_ACK: __rxrpc_call_completed(call); rxrpc_notify_socket(call); + state = call->state; break; default: @@ -297,11 +305,10 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, } write_unlock(&call->state_lock); - if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) { + if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY) trace_rxrpc_transmit(call, rxrpc_transmit_await_reply); - } else { + else trace_rxrpc_transmit(call, rxrpc_transmit_end); - } _leave(" = ok"); return true; @@ -332,11 +339,11 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); } - if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) - rxrpc_rotate_tx_window(call, top, &summary); if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { - rxrpc_proto_abort("TXL", call, top); - return false; + if (!rxrpc_rotate_tx_window(call, top, &summary)) { + rxrpc_proto_abort("TXL", call, top); + return false; + } } if (!rxrpc_end_tx_phase(call, true, "ETD")) return false; @@ -452,13 +459,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, } } + spin_lock(&call->input_lock); + /* Received data implicitly ACKs all of the request packets we sent * when we're acting as a client. */ if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && !rxrpc_receiving_reply(call)) - return; + goto unlock; call->ackr_prev_seq = seq; @@ -488,12 +497,16 @@ next_subpacket: if (flags & RXRPC_LAST_PACKET) { if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) - return rxrpc_proto_abort("LSN", call, seq); + seq != call->rx_top) { + rxrpc_proto_abort("LSN", call, seq); + goto unlock; + } } else { if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) - return rxrpc_proto_abort("LSA", call, seq); + after_eq(seq, call->rx_top)) { + rxrpc_proto_abort("LSA", call, seq); + goto unlock; + } } trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); @@ -560,8 +573,10 @@ next_subpacket: skip: offset += len; if (flags & RXRPC_JUMBO_PACKET) { - if (skb_copy_bits(skb, offset, &flags, 1) < 0) - return rxrpc_proto_abort("XJF", call, seq); + if (skb_copy_bits(skb, offset, &flags, 1) < 0) { + rxrpc_proto_abort("XJF", call, seq); + goto unlock; + } offset += sizeof(struct rxrpc_jumbo_header); seq++; serial++; @@ -601,6 +616,9 @@ ack: trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); } + +unlock: + spin_unlock(&call->input_lock); _leave(" [queued]"); } @@ -687,15 +705,14 @@ static void rxrpc_input_ping_response(struct rxrpc_call *call, ping_time = call->ping_time; smp_rmb(); - ping_serial = call->ping_serial; + ping_serial = READ_ONCE(call->ping_serial); if (orig_serial == call->acks_lost_ping) rxrpc_input_check_for_lost_ack(call); - if (!test_bit(RXRPC_CALL_PINGING, &call->flags) || - before(orig_serial, ping_serial)) + if (before(orig_serial, ping_serial) || + !test_and_clear_bit(RXRPC_CALL_PINGING, &call->flags)) return; - clear_bit(RXRPC_CALL_PINGING, &call->flags); if (after(orig_serial, ping_serial)) return; @@ -861,15 +878,32 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, rxrpc_propose_ack_respond_to_ack); } + /* Discard any out-of-order or duplicate ACKs. */ + if (before_eq(sp->hdr.serial, call->acks_latest)) + return; + + buf.info.rxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(buf.info)) { - if (skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0) - return rxrpc_proto_abort("XAI", call, 0); + if (skb->len >= ioffset + sizeof(buf.info) && + skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0) + return rxrpc_proto_abort("XAI", call, 0); + + spin_lock(&call->input_lock); + + /* Discard any out-of-order or duplicate ACKs. */ + if (before_eq(sp->hdr.serial, call->acks_latest)) + goto out; + call->acks_latest_ts = skb->tstamp; + call->acks_latest = sp->hdr.serial; + + /* Parse rwind and mtu sizes if provided. */ + if (buf.info.rxMTU) rxrpc_input_ackinfo(call, skb, &buf.info); - } - if (first_soft_ack == 0) - return rxrpc_proto_abort("AK0", call, 0); + if (first_soft_ack == 0) { + rxrpc_proto_abort("AK0", call, 0); + goto out; + } /* Ignore ACKs unless we are or have just been transmitting. */ switch (READ_ONCE(call->state)) { @@ -879,39 +913,35 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, case RXRPC_CALL_SERVER_AWAIT_ACK: break; default: - return; - } - - /* Discard any out-of-order or duplicate ACKs. */ - if (before_eq(sp->hdr.serial, call->acks_latest)) { - _debug("discard ACK %d <= %d", - sp->hdr.serial, call->acks_latest); - return; + goto out; } - call->acks_latest_ts = skb->tstamp; - call->acks_latest = sp->hdr.serial; if (before(hard_ack, call->tx_hard_ack) || - after(hard_ack, call->tx_top)) - return rxrpc_proto_abort("AKW", call, 0); - if (nr_acks > call->tx_top - hard_ack) - return rxrpc_proto_abort("AKN", call, 0); + after(hard_ack, call->tx_top)) { + rxrpc_proto_abort("AKW", call, 0); + goto out; + } + if (nr_acks > call->tx_top - hard_ack) { + rxrpc_proto_abort("AKN", call, 0); + goto out; + } - if (after(hard_ack, call->tx_hard_ack)) - rxrpc_rotate_tx_window(call, hard_ack, &summary); + if (after(hard_ack, call->tx_hard_ack)) { + if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { + rxrpc_end_tx_phase(call, false, "ETA"); + goto out; + } + } if (nr_acks > 0) { - if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) - return rxrpc_proto_abort("XSA", call, 0); + if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) { + rxrpc_proto_abort("XSA", call, 0); + goto out; + } rxrpc_input_soft_acks(call, buf.acks, first_soft_ack, nr_acks, &summary); } - if (test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { - rxrpc_end_tx_phase(call, false, "ETA"); - return; - } - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && @@ -920,7 +950,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, false, true, rxrpc_propose_ack_ping_for_lost_reply); - return rxrpc_congestion_management(call, skb, &summary, acked_serial); + rxrpc_congestion_management(call, skb, &summary, acked_serial); +out: + spin_unlock(&call->input_lock); } /* @@ -933,9 +965,12 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb) _proto("Rx ACKALL %%%u", sp->hdr.serial); - rxrpc_rotate_tx_window(call, call->tx_top, &summary); - if (test_bit(RXRPC_CALL_TX_LAST, &call->flags)) + spin_lock(&call->input_lock); + + if (rxrpc_rotate_tx_window(call, call->tx_top, &summary)) rxrpc_end_tx_phase(call, false, "ETL"); + + spin_unlock(&call->input_lock); } /* @@ -1018,18 +1053,19 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, } /* - * Handle a new call on a channel implicitly completing the preceding call on - * that channel. + * Handle a new service call on a channel implicitly completing the preceding + * call on that channel. This does not apply to client conns. * * TODO: If callNumber > call_id + 1, renegotiate security. */ -static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, +static void rxrpc_input_implicit_end_call(struct rxrpc_sock *rx, + struct rxrpc_connection *conn, struct rxrpc_call *call) { switch (READ_ONCE(call->state)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); - break; + /* Fall through */ case RXRPC_CALL_COMPLETE: break; default: @@ -1037,11 +1073,13 @@ static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, set_bit(RXRPC_CALL_EV_ABORT, &call->events); rxrpc_queue_call(call); } + trace_rxrpc_improper_term(call); break; } - trace_rxrpc_improper_term(call); + spin_lock(&rx->incoming_lock); __rxrpc_disconnect_call(conn, call); + spin_unlock(&rx->incoming_lock); rxrpc_notify_socket(call); } @@ -1120,8 +1158,10 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) * The socket is locked by the caller and this prevents the socket from being * shut down and the local endpoint from going away, thus sk_user_data will not * be cleared until this function returns. + * + * Called with the RCU read lock held from the IP layer via UDP. */ -void rxrpc_data_ready(struct sock *udp_sk) +int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) { struct rxrpc_connection *conn; struct rxrpc_channel *chan; @@ -1130,38 +1170,17 @@ void rxrpc_data_ready(struct sock *udp_sk) struct rxrpc_local *local = udp_sk->sk_user_data; struct rxrpc_peer *peer = NULL; struct rxrpc_sock *rx = NULL; - struct sk_buff *skb; unsigned int channel; - int ret, skew = 0; + int skew = 0; _enter("%p", udp_sk); - ASSERT(!irqs_disabled()); - - skb = skb_recv_udp(udp_sk, 0, 1, &ret); - if (!skb) { - if (ret == -EAGAIN) - return; - _debug("UDP socket error %d", ret); - return; - } - if (skb->tstamp == 0) skb->tstamp = ktime_get_real(); rxrpc_new_skb(skb, rxrpc_skb_rx_received); - _net("recv skb %p", skb); - - /* we'll probably need to checksum it (didn't call sock_recvmsg) */ - if (skb_checksum_complete(skb)) { - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); - __UDP_INC_STATS(&init_net, UDP_MIB_INERRORS, 0); - _leave(" [CSUM failed]"); - return; - } - - __UDP_INC_STATS(&init_net, UDP_MIB_INDATAGRAMS, 0); + skb_pull(skb, sizeof(struct udphdr)); /* The UDP protocol already released all skb resources; * we are free to add our own data there. @@ -1176,11 +1195,13 @@ void rxrpc_data_ready(struct sock *udp_sk) static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - rxrpc_lose_skb(skb, rxrpc_skb_rx_lost); - return; + rxrpc_free_skb(skb, rxrpc_skb_rx_lost); + return 0; } } + if (skb->tstamp == 0) + skb->tstamp = ktime_get_real(); trace_rxrpc_rx_packet(sp); switch (sp->hdr.type) { @@ -1234,8 +1255,6 @@ void rxrpc_data_ready(struct sock *udp_sk) if (sp->hdr.serviceId == 0) goto bad_message; - rcu_read_lock(); - if (rxrpc_to_server(sp)) { /* Weed out packets to services we're not offering. Packets * that would begin a call are explicitly rejected and the rest @@ -1247,7 +1266,7 @@ void rxrpc_data_ready(struct sock *udp_sk) if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && sp->hdr.seq == 1) goto unsupported_service; - goto discard_unlock; + goto discard; } } @@ -1257,17 +1276,23 @@ void rxrpc_data_ready(struct sock *udp_sk) goto wrong_security; if (sp->hdr.serviceId != conn->service_id) { - if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) || - conn->service_id != conn->params.service_id) + int old_id; + + if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) + goto reupgrade; + old_id = cmpxchg(&conn->service_id, conn->params.service_id, + sp->hdr.serviceId); + + if (old_id != conn->params.service_id && + old_id != sp->hdr.serviceId) goto reupgrade; - conn->service_id = sp->hdr.serviceId; } if (sp->hdr.callNumber == 0) { /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); rxrpc_post_packet_to_conn(conn, skb); - goto out_unlock; + goto out; } /* Note the serial number skew here */ @@ -1286,19 +1311,19 @@ void rxrpc_data_ready(struct sock *udp_sk) /* Ignore really old calls */ if (sp->hdr.callNumber < chan->last_call) - goto discard_unlock; + goto discard; if (sp->hdr.callNumber == chan->last_call) { if (chan->call || sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) - goto discard_unlock; + goto discard; /* For the previous service call, if completed * successfully, we discard all further packets. */ if (rxrpc_conn_is_service(conn) && chan->last_type == RXRPC_PACKET_TYPE_ACK) - goto discard_unlock; + goto discard; /* But otherwise we need to retransmit the final packet * from data cached in the connection record. @@ -1309,18 +1334,16 @@ void rxrpc_data_ready(struct sock *udp_sk) sp->hdr.serial, sp->hdr.flags, 0); rxrpc_post_packet_to_conn(conn, skb); - goto out_unlock; + goto out; } call = rcu_dereference(chan->call); if (sp->hdr.callNumber > chan->call_id) { - if (rxrpc_to_client(sp)) { - rcu_read_unlock(); + if (rxrpc_to_client(sp)) goto reject_packet; - } if (call) - rxrpc_input_implicit_end_call(conn, call); + rxrpc_input_implicit_end_call(rx, conn, call); call = NULL; } @@ -1337,55 +1360,42 @@ void rxrpc_data_ready(struct sock *udp_sk) if (!call || atomic_read(&call->usage) == 0) { if (rxrpc_to_client(sp) || sp->hdr.type != RXRPC_PACKET_TYPE_DATA) - goto bad_message_unlock; + goto bad_message; if (sp->hdr.seq != 1) - goto discard_unlock; - call = rxrpc_new_incoming_call(local, rx, peer, conn, skb); - if (!call) { - rcu_read_unlock(); + goto discard; + call = rxrpc_new_incoming_call(local, rx, skb); + if (!call) goto reject_packet; - } rxrpc_send_ping(call, skb, skew); mutex_unlock(&call->user_mutex); } rxrpc_input_call_packet(call, skb, skew); - goto discard_unlock; + goto discard; -discard_unlock: - rcu_read_unlock(); discard: rxrpc_free_skb(skb, rxrpc_skb_rx_freed); out: trace_rxrpc_rx_done(0, 0); - return; - -out_unlock: - rcu_read_unlock(); - goto out; + return 0; wrong_security: - rcu_read_unlock(); trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RXKADINCONSISTENCY, EBADMSG); skb->priority = RXKADINCONSISTENCY; goto post_abort; unsupported_service: - rcu_read_unlock(); trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RX_INVALID_OPERATION, EOPNOTSUPP); skb->priority = RX_INVALID_OPERATION; goto post_abort; reupgrade: - rcu_read_unlock(); trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RX_PROTOCOL_ERROR, EBADMSG); goto protocol_error; -bad_message_unlock: - rcu_read_unlock(); bad_message: trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RX_PROTOCOL_ERROR, EBADMSG); @@ -1397,4 +1407,5 @@ reject_packet: trace_rxrpc_rx_done(skb->mark, skb->priority); rxrpc_reject_packet(local, skb); _leave(" [badmsg]"); + return 0; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 94d234e9c685..cad0691c2bb4 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -19,6 +19,7 @@ #include <linux/ip.h> #include <linux/hashtable.h> #include <net/sock.h> +#include <net/udp.h> #include <net/af_rxrpc.h> #include "ar-internal.h" @@ -108,7 +109,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, */ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) { - struct sock *sock; + struct sock *usk; int ret, opt; _enter("%p{%d,%d}", @@ -122,6 +123,28 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) return ret; } + /* set the socket up */ + usk = local->socket->sk; + inet_sk(usk)->mc_loop = 0; + + /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */ + inet_inc_convert_csum(usk); + + rcu_assign_sk_user_data(usk, local); + + udp_sk(usk)->encap_type = UDP_ENCAP_RXRPC; + udp_sk(usk)->encap_rcv = rxrpc_input_packet; + udp_sk(usk)->encap_destroy = NULL; + udp_sk(usk)->gro_receive = NULL; + udp_sk(usk)->gro_complete = NULL; + + udp_encap_enable(); +#if IS_ENABLED(CONFIG_IPV6) + if (local->srx.transport.family == AF_INET6) + udpv6_encap_enable(); +#endif + usk->sk_error_report = rxrpc_error_report; + /* if a local address was supplied then bind it */ if (local->srx.transport_len > sizeof(sa_family_t)) { _debug("bind"); @@ -191,11 +214,6 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) BUG(); } - /* set the socket up */ - sock = local->socket->sk; - sock->sk_user_data = local; - sock->sk_data_ready = rxrpc_data_ready; - sock->sk_error_report = rxrpc_error_report; _leave(" = 0"); return 0; diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index f3e6fc670da2..05b51bdbdd41 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -301,6 +301,8 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, if (rtt < 0) return; + spin_lock(&peer->rtt_input_lock); + /* Replace the oldest datum in the RTT buffer */ sum -= peer->rtt_cache[cursor]; sum += rtt; @@ -312,6 +314,8 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, peer->rtt_usage = usage; } + spin_unlock(&peer->rtt_input_lock); + /* Now recalculate the average */ if (usage == RXRPC_RTT_CACHE_SIZE) { avg = sum / RXRPC_RTT_CACHE_SIZE; @@ -320,6 +324,7 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, do_div(avg, usage); } + /* Don't need to update this under lock */ peer->rtt = avg; trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt, usage, avg); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 01a9febfa367..5691b7d266ca 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -153,8 +153,10 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, * assess the MTU size for the network interface through which this peer is * reached */ -static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) +static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx, + struct rxrpc_peer *peer) { + struct net *net = sock_net(&rx->sk); struct dst_entry *dst; struct rtable *rt; struct flowi fl; @@ -169,7 +171,7 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) switch (peer->srx.transport.family) { case AF_INET: rt = ip_route_output_ports( - &init_net, fl4, NULL, + net, fl4, NULL, peer->srx.transport.sin.sin_addr.s_addr, 0, htons(7000), htons(7001), IPPROTO_UDP, 0, 0); if (IS_ERR(rt)) { @@ -188,7 +190,7 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) sizeof(struct in6_addr)); fl6->fl6_dport = htons(7001); fl6->fl6_sport = htons(7000); - dst = ip6_route_output(&init_net, NULL, fl6); + dst = ip6_route_output(net, NULL, fl6); if (dst->error) { _leave(" [route err %d]", dst->error); return; @@ -223,6 +225,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); spin_lock_init(&peer->lock); + spin_lock_init(&peer->rtt_input_lock); peer->debug_id = atomic_inc_return(&rxrpc_debug_id); if (RXRPC_TX_SMSS > 2190) @@ -240,10 +243,11 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) /* * Initialise peer record. */ -static void rxrpc_init_peer(struct rxrpc_peer *peer, unsigned long hash_key) +static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer, + unsigned long hash_key) { peer->hash_key = hash_key; - rxrpc_assess_MTU_size(peer); + rxrpc_assess_MTU_size(rx, peer); peer->mtu = peer->if_mtu; peer->rtt_last_req = ktime_get_real(); @@ -275,7 +279,8 @@ static void rxrpc_init_peer(struct rxrpc_peer *peer, unsigned long hash_key) /* * Set up a new peer. */ -static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, +static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, + struct rxrpc_local *local, struct sockaddr_rxrpc *srx, unsigned long hash_key, gfp_t gfp) @@ -287,7 +292,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, peer = rxrpc_alloc_peer(local, gfp); if (peer) { memcpy(&peer->srx, srx, sizeof(*srx)); - rxrpc_init_peer(peer, hash_key); + rxrpc_init_peer(rx, peer, hash_key); } _leave(" = %p", peer); @@ -299,14 +304,15 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, * since we've already done a search in the list from the non-reentrant context * (the data_ready handler) that is the only place we can add new peers. */ -void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) +void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, + struct rxrpc_peer *peer) { struct rxrpc_net *rxnet = local->rxnet; unsigned long hash_key; hash_key = rxrpc_peer_hash_key(local, &peer->srx); peer->local = local; - rxrpc_init_peer(peer, hash_key); + rxrpc_init_peer(rx, peer, hash_key); spin_lock(&rxnet->peer_hash_lock); hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); @@ -317,7 +323,8 @@ void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) /* * obtain a remote transport endpoint for the specified address */ -struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, +struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, + struct rxrpc_local *local, struct sockaddr_rxrpc *srx, gfp_t gfp) { struct rxrpc_peer *peer, *candidate; @@ -337,7 +344,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, /* The peer is not yet present in hash - create a candidate * for a new record and then redo the search. */ - candidate = rxrpc_create_peer(local, srx, hash_key, gfp); + candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp); if (!candidate) { _leave(" = NULL [nomem]"); return NULL; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index f218ccf1e2d9..b2c3406a2cf2 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -398,6 +398,7 @@ static int u32_init(struct tcf_proto *tp) rcu_assign_pointer(tp_c->hlist, root_ht); root_ht->tp_c = tp_c; + root_ht->refcnt++; rcu_assign_pointer(tp->root, root_ht); tp->data = tp_c; return 0; @@ -610,7 +611,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, struct tc_u_hnode __rcu **hn; struct tc_u_hnode *phn; - WARN_ON(ht->refcnt); + WARN_ON(--ht->refcnt); u32_clear_hnode(tp, ht, extack); @@ -649,7 +650,7 @@ static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) WARN_ON(root_ht == NULL); - if (root_ht && --root_ht->refcnt == 0) + if (root_ht && --root_ht->refcnt == 1) u32_destroy_hnode(tp, root_ht, extack); if (--tp_c->refcnt == 0) { @@ -698,7 +699,6 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, } if (ht->refcnt == 1) { - ht->refcnt--; u32_destroy_hnode(tp, ht, extack); } else { NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter"); @@ -708,11 +708,11 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, out: *last = true; if (root_ht) { - if (root_ht->refcnt > 1) { + if (root_ht->refcnt > 2) { *last = false; goto ret; } - if (root_ht->refcnt == 1) { + if (root_ht->refcnt == 2) { if (!ht_empty(root_ht)) { *last = false; goto ret; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index c07c30b916d5..793016d722ec 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2644,7 +2644,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, for (i = 1; i <= CAKE_QUEUES; i++) quantum_div[i] = 65535 / i; - q->tins = kvzalloc(CAKE_MAX_TINS * sizeof(struct cake_tin_data), + q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), GFP_KERNEL); if (!q->tins) goto nomem; diff --git a/net/tipc/link.c b/net/tipc/link.c index fb886b525d95..f6552e4f4b43 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -477,6 +477,8 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, l->in_session = false; l->bearer_id = bearer_id; l->tolerance = tolerance; + if (bc_rcvlink) + bc_rcvlink->tolerance = tolerance; l->net_plane = net_plane; l->advertised_mtu = mtu; l->mtu = mtu; @@ -843,14 +845,21 @@ static void link_prepare_wakeup(struct tipc_link *l) void tipc_link_reset(struct tipc_link *l) { + struct sk_buff_head list; + + __skb_queue_head_init(&list); + l->in_session = false; l->session++; l->mtu = l->advertised_mtu; + spin_lock_bh(&l->wakeupq.lock); + skb_queue_splice_init(&l->wakeupq, &list); + spin_unlock_bh(&l->wakeupq.lock); + spin_lock_bh(&l->inputq->lock); - skb_queue_splice_init(&l->wakeupq, l->inputq); + skb_queue_splice_init(&list, l->inputq); spin_unlock_bh(&l->inputq->lock); - spin_unlock_bh(&l->wakeupq.lock); __skb_queue_purge(&l->transmq); __skb_queue_purge(&l->deferdq); @@ -1031,7 +1040,7 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r, /* Detect repeated retransmit failures on same packet */ if (r->last_retransm != buf_seqno(skb)) { r->last_retransm = buf_seqno(skb); - r->stale_limit = jiffies + msecs_to_jiffies(l->tolerance); + r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance); } else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) { link_retransmit_failure(l, skb); if (link_is_bc_sndlink(l)) @@ -1576,9 +1585,10 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, strncpy(if_name, data, TIPC_MAX_IF_NAME); /* Update own tolerance if peer indicates a non-zero value */ - if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) + if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { l->tolerance = peers_tol; - + l->bc_rcvlink->tolerance = peers_tol; + } /* Update own priority if peer's priority is higher */ if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; @@ -1604,9 +1614,10 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, l->rcv_nxt_state = msg_seqno(hdr) + 1; /* Update own tolerance if peer indicates a non-zero value */ - if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) + if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { l->tolerance = peers_tol; - + l->bc_rcvlink->tolerance = peers_tol; + } /* Update own prio if peer indicates a different value */ if ((peers_prio != l->priority) && in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) { @@ -2223,6 +2234,8 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, struct sk_buff_head *xmitq) { l->tolerance = tol; + if (l->bc_rcvlink) + l->bc_rcvlink->tolerance = tol; if (link_is_up(l)) tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b6f99b021d09..49810fdff4c5 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1196,6 +1196,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, * @skb: pointer to message buffer. */ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct tipc_msg *hdr = buf_msg(skb); @@ -1213,7 +1214,16 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk), tsk_peer_port(tsk)); sk->sk_state_change(sk); - goto exit; + + /* State change is ignored if socket already awake, + * - convert msg to abort msg and add to inqueue + */ + msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE); + msg_set_type(hdr, TIPC_CONN_MSG); + msg_set_size(hdr, BASIC_H_SIZE); + msg_set_hdr_sz(hdr, BASIC_H_SIZE); + __skb_queue_tail(inputq, skb); + return; } tsk->probe_unacked = false; @@ -1936,7 +1946,7 @@ static void tipc_sk_proto_rcv(struct sock *sk, switch (msg_user(hdr)) { case CONN_MANAGER: - tipc_sk_conn_proto_rcv(tsk, skb, xmitq); + tipc_sk_conn_proto_rcv(tsk, skb, inputq, xmitq); return; case SOCK_WAKEUP: tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0); diff --git a/samples/Kconfig b/samples/Kconfig index bd133efc1a56..ad1ec7016d4c 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -1,5 +1,6 @@ menuconfig SAMPLES bool "Sample kernel code" + depends on !UML help You can build and test sample kernel code here. diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 5a2d1c9578a0..54da4b070db3 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -219,7 +219,7 @@ else sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \ "$(if $(CONFIG_CPU_BIG_ENDIAN),big,little)" \ "$(if $(CONFIG_64BIT),64,32)" \ - "$(OBJDUMP)" "$(OBJCOPY)" "$(CC) $(KBUILD_CFLAGS)" \ + "$(OBJDUMP)" "$(OBJCOPY)" "$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS)" \ "$(LD) $(KBUILD_LDFLAGS)" "$(NM)" "$(RM)" "$(MV)" \ "$(if $(part-of-module),1,0)" "$(@)"; recordmcount_source := $(srctree)/scripts/recordmcount.pl diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index efcaf6cac2eb..e46f51b17513 100644 --- a/tools/perf/scripts/python/export-to-postgresql.py +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -204,14 +204,23 @@ from ctypes import * libpq = CDLL("libpq.so.5") PQconnectdb = libpq.PQconnectdb PQconnectdb.restype = c_void_p +PQconnectdb.argtypes = [ c_char_p ] PQfinish = libpq.PQfinish +PQfinish.argtypes = [ c_void_p ] PQstatus = libpq.PQstatus +PQstatus.restype = c_int +PQstatus.argtypes = [ c_void_p ] PQexec = libpq.PQexec PQexec.restype = c_void_p +PQexec.argtypes = [ c_void_p, c_char_p ] PQresultStatus = libpq.PQresultStatus +PQresultStatus.restype = c_int +PQresultStatus.argtypes = [ c_void_p ] PQputCopyData = libpq.PQputCopyData +PQputCopyData.restype = c_int PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ] PQputCopyEnd = libpq.PQputCopyEnd +PQputCopyEnd.restype = c_int PQputCopyEnd.argtypes = [ c_void_p, c_void_p ] sys.path.append(os.environ['PERF_EXEC_PATH'] + \ diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py index f827bf77e9d2..e4bb82c8aba9 100644 --- a/tools/perf/scripts/python/export-to-sqlite.py +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -440,7 +440,11 @@ def branch_type_table(*x): def sample_table(*x): if branches: - bind_exec(sample_query, 18, x) + for xx in x[0:15]: + sample_query.addBindValue(str(xx)) + for xx in x[19:22]: + sample_query.addBindValue(str(xx)) + do_query_(sample_query) else: bind_exec(sample_query, 22, x) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index c4acd2001db0..111ae858cbcb 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2286,7 +2286,8 @@ static int append_inlines(struct callchain_cursor *cursor, if (!symbol_conf.inline_name || !map || !sym) return ret; - addr = map__rip_2objdump(map, ip); + addr = map__map_ip(map, ip); + addr = map__rip_2objdump(map, addr); inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr); if (!inline_node) { @@ -2312,7 +2313,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) { struct callchain_cursor *cursor = arg; const char *srcline = NULL; - u64 addr; + u64 addr = entry->ip; if (symbol_conf.hide_unresolved && entry->sym == NULL) return 0; @@ -2324,7 +2325,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) * Convert entry->ip from a virtual address to an offset in * its corresponding binary. */ - addr = map__map_ip(entry->map, entry->ip); + if (entry->map) + addr = map__map_ip(entry->map, entry->ip); srcline = callchain_srcline(entry->map, entry->sym, addr); return callchain_cursor_append(cursor, entry->ip, diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 97efbcad076e..1942f6dd24f6 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -35,7 +35,7 @@ class install_lib(_install_lib): cflags = getenv('CFLAGS', '').split() # switch off several checks (need to be at the end of cflags list) -cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ] +cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ] if cc != "clang": cflags += ['-Wno-cast-function-type' ] diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 08c341b49760..e101af52d1d6 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # # This test is for checking rtnetlink callpaths, and get as much coverage as possible. # diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index 850767befa47..99e537ab5ad9 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # # Run a series of udpgso benchmarks |