diff options
60 files changed, 605 insertions, 369 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 358eb0105e00..88c09ca2584f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1186,7 +1186,7 @@ M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-mvebu/ -F: drivers/rtc/armada38x-rtc +F: drivers/rtc/rtc-armada38x.c ARM/Marvell Berlin SoC support M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> @@ -1675,8 +1675,8 @@ F: drivers/misc/eeprom/at24.c F: include/linux/platform_data/at24.h ATA OVER ETHERNET (AOE) DRIVER -M: "Ed L. Cashin" <ecashin@coraid.com> -W: http://support.coraid.com/support/linux +M: "Ed L. Cashin" <ed.cashin@acm.org> +W: http://www.openaoe.org/ S: Supported F: Documentation/aoe/ F: drivers/block/aoe/ @@ -3252,6 +3252,13 @@ S: Maintained F: Documentation/hwmon/dme1737 F: drivers/hwmon/dme1737.c +DMI/SMBIOS SUPPORT +M: Jean Delvare <jdelvare@suse.de> +S: Maintained +F: drivers/firmware/dmi-id.c +F: drivers/firmware/dmi_scan.c +F: include/linux/dmi.h + DOCKING STATION DRIVER M: Shaohua Li <shaohua.li@intel.com> L: linux-acpi@vger.kernel.org diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index cb9593079f29..d8c25b7b18fb 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -246,14 +246,30 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old, __ret; \ }) -#define this_cpu_cmpxchg_1(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) -#define this_cpu_cmpxchg_2(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) -#define this_cpu_cmpxchg_4(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) -#define this_cpu_cmpxchg_8(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n) - -#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \ - cmpxchg_double_local(raw_cpu_ptr(&(ptr1)), raw_cpu_ptr(&(ptr2)), \ - o1, o2, n1, n2) +#define _protect_cmpxchg_local(pcp, o, n) \ +({ \ + typeof(*raw_cpu_ptr(&(pcp))) __ret; \ + preempt_disable(); \ + __ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n); \ + preempt_enable(); \ + __ret; \ +}) + +#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) + +#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \ +({ \ + int __ret; \ + preempt_disable(); \ + __ret = cmpxchg_double_local( raw_cpu_ptr(&(ptr1)), \ + raw_cpu_ptr(&(ptr2)), \ + o1, o2, n1, n2); \ + preempt_enable(); \ + __ret; \ +}) #define cmpxchg64(ptr,o,n) cmpxchg((ptr),(o),(n)) #define cmpxchg64_local(ptr,o,n) cmpxchg_local((ptr),(o),(n)) diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index a9eee33dfa62..101a42bde728 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -151,6 +151,15 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, { unsigned int cpu = smp_processor_id(); + /* + * init_mm.pgd does not contain any user mappings and it is always + * active for kernel addresses in TTBR1. Just set the reserved TTBR0. + */ + if (next == &init_mm) { + cpu_set_reserved_ttbr0(); + return; + } + if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) check_and_switch_context(next, tsk); } diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 09da25bc596f..4fde8c1df97f 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -204,25 +204,47 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, return ret; } +#define _percpu_read(pcp) \ +({ \ + typeof(pcp) __retval; \ + preempt_disable(); \ + __retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), \ + sizeof(pcp)); \ + preempt_enable(); \ + __retval; \ +}) + +#define _percpu_write(pcp, val) \ +do { \ + preempt_disable(); \ + __percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), \ + sizeof(pcp)); \ + preempt_enable(); \ +} while(0) \ + +#define _pcp_protect(operation, pcp, val) \ +({ \ + typeof(pcp) __retval; \ + preempt_disable(); \ + __retval = (typeof(pcp))operation(raw_cpu_ptr(&(pcp)), \ + (val), sizeof(pcp)); \ + preempt_enable(); \ + __retval; \ +}) + #define _percpu_add(pcp, val) \ - __percpu_add(raw_cpu_ptr(&(pcp)), val, sizeof(pcp)) + _pcp_protect(__percpu_add, pcp, val) -#define _percpu_add_return(pcp, val) (typeof(pcp)) (_percpu_add(pcp, val)) +#define _percpu_add_return(pcp, val) _percpu_add(pcp, val) #define _percpu_and(pcp, val) \ - __percpu_and(raw_cpu_ptr(&(pcp)), val, sizeof(pcp)) + _pcp_protect(__percpu_and, pcp, val) #define _percpu_or(pcp, val) \ - __percpu_or(raw_cpu_ptr(&(pcp)), val, sizeof(pcp)) - -#define _percpu_read(pcp) (typeof(pcp)) \ - (__percpu_read(raw_cpu_ptr(&(pcp)), sizeof(pcp))) - -#define _percpu_write(pcp, val) \ - __percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp)) + _pcp_protect(__percpu_or, pcp, val) #define _percpu_xchg(pcp, val) (typeof(pcp)) \ - (__percpu_xchg(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp))) + _pcp_protect(__percpu_xchg, pcp, (unsigned long)(val)) #define this_cpu_add_1(pcp, val) _percpu_add(pcp, val) #define this_cpu_add_2(pcp, val) _percpu_add(pcp, val) diff --git a/arch/metag/include/asm/io.h b/arch/metag/include/asm/io.h index 9359e5048442..d5779b0ec573 100644 --- a/arch/metag/include/asm/io.h +++ b/arch/metag/include/asm/io.h @@ -2,6 +2,7 @@ #define _ASM_METAG_IO_H #include <linux/types.h> +#include <asm/pgtable-bits.h> #define IO_SPACE_LIMIT 0 diff --git a/arch/metag/include/asm/pgtable-bits.h b/arch/metag/include/asm/pgtable-bits.h new file mode 100644 index 000000000000..25ba6729f496 --- /dev/null +++ b/arch/metag/include/asm/pgtable-bits.h @@ -0,0 +1,104 @@ +/* + * Meta page table definitions. + */ + +#ifndef _METAG_PGTABLE_BITS_H +#define _METAG_PGTABLE_BITS_H + +#include <asm/metag_mem.h> + +/* + * Definitions for MMU descriptors + * + * These are the hardware bits in the MMCU pte entries. + * Derived from the Meta toolkit headers. + */ +#define _PAGE_PRESENT MMCU_ENTRY_VAL_BIT +#define _PAGE_WRITE MMCU_ENTRY_WR_BIT +#define _PAGE_PRIV MMCU_ENTRY_PRIV_BIT +/* Write combine bit - this can cause writes to occur out of order */ +#define _PAGE_WR_COMBINE MMCU_ENTRY_WRC_BIT +/* Sys coherent bit - this bit is never used by Linux */ +#define _PAGE_SYS_COHERENT MMCU_ENTRY_SYS_BIT +#define _PAGE_ALWAYS_ZERO_1 0x020 +#define _PAGE_CACHE_CTRL0 0x040 +#define _PAGE_CACHE_CTRL1 0x080 +#define _PAGE_ALWAYS_ZERO_2 0x100 +#define _PAGE_ALWAYS_ZERO_3 0x200 +#define _PAGE_ALWAYS_ZERO_4 0x400 +#define _PAGE_ALWAYS_ZERO_5 0x800 + +/* These are software bits that we stuff into the gaps in the hardware + * pte entries that are not used. Note, these DO get stored in the actual + * hardware, but the hardware just does not use them. + */ +#define _PAGE_ACCESSED _PAGE_ALWAYS_ZERO_1 +#define _PAGE_DIRTY _PAGE_ALWAYS_ZERO_2 + +/* Pages owned, and protected by, the kernel. */ +#define _PAGE_KERNEL _PAGE_PRIV + +/* No cacheing of this page */ +#define _PAGE_CACHE_WIN0 (MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S) +/* burst cacheing - good for data streaming */ +#define _PAGE_CACHE_WIN1 (MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S) +/* One cache way per thread */ +#define _PAGE_CACHE_WIN2 (MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S) +/* Full on cacheing */ +#define _PAGE_CACHE_WIN3 (MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S) + +#define _PAGE_CACHEABLE (_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE) + +/* which bits are used for cache control ... */ +#define _PAGE_CACHE_MASK (_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \ + _PAGE_WR_COMBINE) + +/* This is a mask of the bits that pte_modify is allowed to change. */ +#define _PAGE_CHG_MASK (PAGE_MASK) + +#define _PAGE_SZ_SHIFT 1 +#define _PAGE_SZ_4K (0x0) +#define _PAGE_SZ_8K (0x1 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_16K (0x2 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_32K (0x3 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_64K (0x4 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_128K (0x5 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_256K (0x6 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_512K (0x7 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_1M (0x8 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_2M (0x9 << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_4M (0xa << _PAGE_SZ_SHIFT) +#define _PAGE_SZ_MASK (0xf << _PAGE_SZ_SHIFT) + +#if defined(CONFIG_PAGE_SIZE_4K) +#define _PAGE_SZ (_PAGE_SZ_4K) +#elif defined(CONFIG_PAGE_SIZE_8K) +#define _PAGE_SZ (_PAGE_SZ_8K) +#elif defined(CONFIG_PAGE_SIZE_16K) +#define _PAGE_SZ (_PAGE_SZ_16K) +#endif +#define _PAGE_TABLE (_PAGE_SZ | _PAGE_PRESENT) + +#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K) +# define _PAGE_SZHUGE (_PAGE_SZ_8K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K) +# define _PAGE_SZHUGE (_PAGE_SZ_16K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K) +# define _PAGE_SZHUGE (_PAGE_SZ_32K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K) +# define _PAGE_SZHUGE (_PAGE_SZ_64K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K) +# define _PAGE_SZHUGE (_PAGE_SZ_128K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K) +# define _PAGE_SZHUGE (_PAGE_SZ_256K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K) +# define _PAGE_SZHUGE (_PAGE_SZ_512K) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M) +# define _PAGE_SZHUGE (_PAGE_SZ_1M) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M) +# define _PAGE_SZHUGE (_PAGE_SZ_2M) +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M) +# define _PAGE_SZHUGE (_PAGE_SZ_4M) +#endif + +#endif /* _METAG_PGTABLE_BITS_H */ diff --git a/arch/metag/include/asm/pgtable.h b/arch/metag/include/asm/pgtable.h index d0604c0a8702..ffa3a3a2ecad 100644 --- a/arch/metag/include/asm/pgtable.h +++ b/arch/metag/include/asm/pgtable.h @@ -5,6 +5,7 @@ #ifndef _METAG_PGTABLE_H #define _METAG_PGTABLE_H +#include <asm/pgtable-bits.h> #include <asm-generic/pgtable-nopmd.h> /* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */ @@ -21,100 +22,6 @@ #endif /* - * Definitions for MMU descriptors - * - * These are the hardware bits in the MMCU pte entries. - * Derived from the Meta toolkit headers. - */ -#define _PAGE_PRESENT MMCU_ENTRY_VAL_BIT -#define _PAGE_WRITE MMCU_ENTRY_WR_BIT -#define _PAGE_PRIV MMCU_ENTRY_PRIV_BIT -/* Write combine bit - this can cause writes to occur out of order */ -#define _PAGE_WR_COMBINE MMCU_ENTRY_WRC_BIT -/* Sys coherent bit - this bit is never used by Linux */ -#define _PAGE_SYS_COHERENT MMCU_ENTRY_SYS_BIT -#define _PAGE_ALWAYS_ZERO_1 0x020 -#define _PAGE_CACHE_CTRL0 0x040 -#define _PAGE_CACHE_CTRL1 0x080 -#define _PAGE_ALWAYS_ZERO_2 0x100 -#define _PAGE_ALWAYS_ZERO_3 0x200 -#define _PAGE_ALWAYS_ZERO_4 0x400 -#define _PAGE_ALWAYS_ZERO_5 0x800 - -/* These are software bits that we stuff into the gaps in the hardware - * pte entries that are not used. Note, these DO get stored in the actual - * hardware, but the hardware just does not use them. - */ -#define _PAGE_ACCESSED _PAGE_ALWAYS_ZERO_1 -#define _PAGE_DIRTY _PAGE_ALWAYS_ZERO_2 - -/* Pages owned, and protected by, the kernel. */ -#define _PAGE_KERNEL _PAGE_PRIV - -/* No cacheing of this page */ -#define _PAGE_CACHE_WIN0 (MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S) -/* burst cacheing - good for data streaming */ -#define _PAGE_CACHE_WIN1 (MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S) -/* One cache way per thread */ -#define _PAGE_CACHE_WIN2 (MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S) -/* Full on cacheing */ -#define _PAGE_CACHE_WIN3 (MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S) - -#define _PAGE_CACHEABLE (_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE) - -/* which bits are used for cache control ... */ -#define _PAGE_CACHE_MASK (_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \ - _PAGE_WR_COMBINE) - -/* This is a mask of the bits that pte_modify is allowed to change. */ -#define _PAGE_CHG_MASK (PAGE_MASK) - -#define _PAGE_SZ_SHIFT 1 -#define _PAGE_SZ_4K (0x0) -#define _PAGE_SZ_8K (0x1 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_16K (0x2 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_32K (0x3 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_64K (0x4 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_128K (0x5 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_256K (0x6 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_512K (0x7 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_1M (0x8 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_2M (0x9 << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_4M (0xa << _PAGE_SZ_SHIFT) -#define _PAGE_SZ_MASK (0xf << _PAGE_SZ_SHIFT) - -#if defined(CONFIG_PAGE_SIZE_4K) -#define _PAGE_SZ (_PAGE_SZ_4K) -#elif defined(CONFIG_PAGE_SIZE_8K) -#define _PAGE_SZ (_PAGE_SZ_8K) -#elif defined(CONFIG_PAGE_SIZE_16K) -#define _PAGE_SZ (_PAGE_SZ_16K) -#endif -#define _PAGE_TABLE (_PAGE_SZ | _PAGE_PRESENT) - -#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K) -# define _PAGE_SZHUGE (_PAGE_SZ_8K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K) -# define _PAGE_SZHUGE (_PAGE_SZ_16K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K) -# define _PAGE_SZHUGE (_PAGE_SZ_32K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K) -# define _PAGE_SZHUGE (_PAGE_SZ_64K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K) -# define _PAGE_SZHUGE (_PAGE_SZ_128K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K) -# define _PAGE_SZHUGE (_PAGE_SZ_256K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K) -# define _PAGE_SZHUGE (_PAGE_SZ_512K) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M) -# define _PAGE_SZHUGE (_PAGE_SZ_1M) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M) -# define _PAGE_SZHUGE (_PAGE_SZ_2M) -#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M) -# define _PAGE_SZHUGE (_PAGE_SZ_4M) -#endif - -/* * The Linux memory management assumes a three-level page table setup. On * Meta, we use that, but "fold" the mid level into the top-level page * table. diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 03cd858a401c..4cbe23af400a 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -153,6 +153,7 @@ #define PPC_INST_MFSPR_PVR_MASK 0xfc1fffff #define PPC_INST_MFTMR 0x7c0002dc #define PPC_INST_MSGSND 0x7c00019c +#define PPC_INST_MSGCLR 0x7c0001dc #define PPC_INST_MSGSNDP 0x7c00011c #define PPC_INST_MTTMR 0x7c0003dc #define PPC_INST_NOP 0x60000000 @@ -309,6 +310,8 @@ ___PPC_RB(b) | __PPC_EH(eh)) #define PPC_MSGSND(b) stringify_in_c(.long PPC_INST_MSGSND | \ ___PPC_RB(b)) +#define PPC_MSGCLR(b) stringify_in_c(.long PPC_INST_MSGCLR | \ + ___PPC_RB(b)) #define PPC_MSGSNDP(b) stringify_in_c(.long PPC_INST_MSGSNDP | \ ___PPC_RB(b)) #define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_INST_POPCNTB | \ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 1c874fb533bb..af56b5c6c81a 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -608,13 +608,16 @@ #define SRR1_ISI_N_OR_G 0x10000000 /* ISI: Access is no-exec or G */ #define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */ #define SRR1_WAKEMASK 0x00380000 /* reason for wakeup */ +#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 */ #define SRR1_WAKESYSERR 0x00300000 /* System error */ #define SRR1_WAKEEE 0x00200000 /* External interrupt */ #define SRR1_WAKEMT 0x00280000 /* mtctrl */ #define SRR1_WAKEHMI 0x00280000 /* Hypervisor maintenance */ #define SRR1_WAKEDEC 0x00180000 /* Decrementer interrupt */ +#define SRR1_WAKEDBELL 0x00140000 /* Privileged doorbell on P8 */ #define SRR1_WAKETHERM 0x00100000 /* Thermal management interrupt */ #define SRR1_WAKERESET 0x00100000 /* System reset */ +#define SRR1_WAKEHDBELL 0x000c0000 /* Hypervisor doorbell on P8 */ #define SRR1_WAKESTATE 0x00030000 /* Powersave exit mask [46:47] */ #define SRR1_WS_DEEPEST 0x00030000 /* Some resources not maintained, * may not be recoverable */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index f337666768a7..f83046878336 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -437,6 +437,26 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, + { /* Power8NVL */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004c0000, + .cpu_name = "POWER8NVL (raw)", + .cpu_features = CPU_FTRS_POWER8, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power8", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, { /* Power8 DD1: Does not support doorbell IPIs */ .pvr_mask = 0xffffff00, .pvr_value = 0x004d0100, diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index f4217819cc31..2128f3a96c32 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -17,6 +17,7 @@ #include <asm/dbell.h> #include <asm/irq_regs.h> +#include <asm/kvm_ppc.h> #ifdef CONFIG_SMP void doorbell_setup_this_cpu(void) @@ -41,6 +42,7 @@ void doorbell_exception(struct pt_regs *regs) may_hard_irq_enable(); + kvmppc_set_host_ipi(smp_processor_id(), 0); __this_cpu_inc(irq_stat.doorbell_irqs); smp_ipi_demux(); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index c2df8150bd7a..9519e6bdc6d7 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1408,7 +1408,7 @@ machine_check_handle_early: bne 9f /* continue in V mode if we are. */ 5: -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER /* * We are coming from kernel context. Check if we are coming from * guest. if yes, then we can continue. We will fall through diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index fc34025ef822..38a45088f633 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -33,6 +33,8 @@ #include <asm/runlatch.h> #include <asm/code-patching.h> #include <asm/dbell.h> +#include <asm/kvm_ppc.h> +#include <asm/ppc-opcode.h> #include "powernv.h" @@ -149,7 +151,7 @@ static int pnv_smp_cpu_disable(void) static void pnv_smp_cpu_kill_self(void) { unsigned int cpu; - unsigned long srr1; + unsigned long srr1, wmask; u32 idle_states; /* Standard hot unplug procedure */ @@ -161,6 +163,10 @@ static void pnv_smp_cpu_kill_self(void) generic_set_cpu_dead(cpu); smp_wmb(); + wmask = SRR1_WAKEMASK; + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + wmask = SRR1_WAKEMASK_P8; + idle_states = pnv_get_supported_cpuidle_states(); /* We don't want to take decrementer interrupts while we are offline, * so clear LPCR:PECE1. We keep PECE2 enabled. @@ -191,10 +197,14 @@ static void pnv_smp_cpu_kill_self(void) * having finished executing in a KVM guest, then srr1 * contains 0. */ - if ((srr1 & SRR1_WAKEMASK) == SRR1_WAKEEE) { + if ((srr1 & wmask) == SRR1_WAKEEE) { icp_native_flush_interrupt(); local_paca->irq_happened &= PACA_IRQ_HARD_DIS; smp_mb(); + } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { + unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); + asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); + kvmppc_set_host_ipi(cpu, 0); } if (cpu_core_split_required()) diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 90cf3dcbd9f2..8f35d525cede 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -25,10 +25,10 @@ static struct kobject *mobility_kobj; struct update_props_workarea { - u32 phandle; - u32 state; - u64 reserved; - u32 nprops; + __be32 phandle; + __be32 state; + __be64 reserved; + __be32 nprops; } __packed; #define NODE_ACTION_MASK 0xff000000 @@ -54,11 +54,11 @@ static int mobility_rtas_call(int token, char *buf, s32 scope) return rc; } -static int delete_dt_node(u32 phandle) +static int delete_dt_node(__be32 phandle) { struct device_node *dn; - dn = of_find_node_by_phandle(phandle); + dn = of_find_node_by_phandle(be32_to_cpu(phandle)); if (!dn) return -ENOENT; @@ -127,7 +127,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, return 0; } -static int update_dt_node(u32 phandle, s32 scope) +static int update_dt_node(__be32 phandle, s32 scope) { struct update_props_workarea *upwa; struct device_node *dn; @@ -136,6 +136,7 @@ static int update_dt_node(u32 phandle, s32 scope) char *prop_data; char *rtas_buf; int update_properties_token; + u32 nprops; u32 vd; update_properties_token = rtas_token("ibm,update-properties"); @@ -146,7 +147,7 @@ static int update_dt_node(u32 phandle, s32 scope) if (!rtas_buf) return -ENOMEM; - dn = of_find_node_by_phandle(phandle); + dn = of_find_node_by_phandle(be32_to_cpu(phandle)); if (!dn) { kfree(rtas_buf); return -ENOENT; @@ -162,6 +163,7 @@ static int update_dt_node(u32 phandle, s32 scope) break; prop_data = rtas_buf + sizeof(*upwa); + nprops = be32_to_cpu(upwa->nprops); /* On the first call to ibm,update-properties for a node the * the first property value descriptor contains an empty @@ -170,17 +172,17 @@ static int update_dt_node(u32 phandle, s32 scope) */ if (*prop_data == 0) { prop_data++; - vd = *(u32 *)prop_data; + vd = be32_to_cpu(*(__be32 *)prop_data); prop_data += vd + sizeof(vd); - upwa->nprops--; + nprops--; } - for (i = 0; i < upwa->nprops; i++) { + for (i = 0; i < nprops; i++) { char *prop_name; prop_name = prop_data; prop_data += strlen(prop_name) + 1; - vd = *(u32 *)prop_data; + vd = be32_to_cpu(*(__be32 *)prop_data); prop_data += sizeof(vd); switch (vd) { @@ -212,13 +214,13 @@ static int update_dt_node(u32 phandle, s32 scope) return 0; } -static int add_dt_node(u32 parent_phandle, u32 drc_index) +static int add_dt_node(__be32 parent_phandle, __be32 drc_index) { struct device_node *dn; struct device_node *parent_dn; int rc; - parent_dn = of_find_node_by_phandle(parent_phandle); + parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle)); if (!parent_dn) return -ENOENT; @@ -237,7 +239,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index) int pseries_devicetree_update(s32 scope) { char *rtas_buf; - u32 *data; + __be32 *data; int update_nodes_token; int rc; @@ -254,17 +256,17 @@ int pseries_devicetree_update(s32 scope) if (rc && rc != 1) break; - data = (u32 *)rtas_buf + 4; - while (*data & NODE_ACTION_MASK) { + data = (__be32 *)rtas_buf + 4; + while (be32_to_cpu(*data) & NODE_ACTION_MASK) { int i; - u32 action = *data & NODE_ACTION_MASK; - int node_count = *data & NODE_COUNT_MASK; + u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK; + u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK; data++; for (i = 0; i < node_count; i++) { - u32 phandle = *data++; - u32 drc_index; + __be32 phandle = *data++; + __be32 drc_index; switch (action) { case DELETE_DT_NODE: diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index c9df40b5c0ac..c9c875d9ed31 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -211,7 +211,7 @@ do { \ extern unsigned long mmap_rnd_mask; -#define STACK_RND_MASK (mmap_rnd_mask) +#define STACK_RND_MASK (test_thread_flag(TIF_31BIT) ? 0x7ff : mmap_rnd_mask) #define ARCH_DLINFO \ do { \ diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 82c19899574f..6c79f1b44fe7 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -57,6 +57,44 @@ unsigned long ftrace_plt; +static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn) +{ +#ifdef CC_USING_HOTPATCH + /* brcl 0,0 */ + insn->opc = 0xc004; + insn->disp = 0; +#else + /* stg r14,8(r15) */ + insn->opc = 0xe3e0; + insn->disp = 0xf0080024; +#endif +} + +static inline int is_kprobe_on_ftrace(struct ftrace_insn *insn) +{ +#ifdef CONFIG_KPROBES + if (insn->opc == BREAKPOINT_INSTRUCTION) + return 1; +#endif + return 0; +} + +static inline void ftrace_generate_kprobe_nop_insn(struct ftrace_insn *insn) +{ +#ifdef CONFIG_KPROBES + insn->opc = BREAKPOINT_INSTRUCTION; + insn->disp = KPROBE_ON_FTRACE_NOP; +#endif +} + +static inline void ftrace_generate_kprobe_call_insn(struct ftrace_insn *insn) +{ +#ifdef CONFIG_KPROBES + insn->opc = BREAKPOINT_INSTRUCTION; + insn->disp = KPROBE_ON_FTRACE_CALL; +#endif +} + int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { @@ -72,16 +110,9 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return -EFAULT; if (addr == MCOUNT_ADDR) { /* Initial code replacement */ -#ifdef CC_USING_HOTPATCH - /* We expect to see brcl 0,0 */ - ftrace_generate_nop_insn(&orig); -#else - /* We expect to see stg r14,8(r15) */ - orig.opc = 0xe3e0; - orig.disp = 0xf0080024; -#endif + ftrace_generate_orig_insn(&orig); ftrace_generate_nop_insn(&new); - } else if (old.opc == BREAKPOINT_INSTRUCTION) { + } else if (is_kprobe_on_ftrace(&old)) { /* * If we find a breakpoint instruction, a kprobe has been * placed at the beginning of the function. We write the @@ -89,9 +120,8 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, * bytes of the original instruction so that the kprobes * handler can execute a nop, if it reaches this breakpoint. */ - new.opc = orig.opc = BREAKPOINT_INSTRUCTION; - orig.disp = KPROBE_ON_FTRACE_CALL; - new.disp = KPROBE_ON_FTRACE_NOP; + ftrace_generate_kprobe_call_insn(&orig); + ftrace_generate_kprobe_nop_insn(&new); } else { /* Replace ftrace call with a nop. */ ftrace_generate_call_insn(&orig, rec->ip); @@ -111,7 +141,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; - if (old.opc == BREAKPOINT_INSTRUCTION) { + if (is_kprobe_on_ftrace(&old)) { /* * If we find a breakpoint instruction, a kprobe has been * placed at the beginning of the function. We write the @@ -119,9 +149,8 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * bytes of the original instruction so that the kprobes * handler can execute a brasl if it reaches this breakpoint. */ - new.opc = orig.opc = BREAKPOINT_INSTRUCTION; - orig.disp = KPROBE_ON_FTRACE_NOP; - new.disp = KPROBE_ON_FTRACE_CALL; + ftrace_generate_kprobe_nop_insn(&orig); + ftrace_generate_kprobe_call_insn(&new); } else { /* Replace nop with an ftrace call. */ ftrace_generate_nop_insn(&orig); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index c3f8d157cb0d..e6a1578fc000 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1415,7 +1415,7 @@ CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG); static struct attribute *cpumsf_pmu_events_attr[] = { CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC), - CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG), + NULL, NULL, }; @@ -1606,8 +1606,11 @@ static int __init init_cpum_sampling_pmu(void) return -EINVAL; } - if (si.ad) + if (si.ad) { sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB); + cpumsf_pmu_events_attr[1] = + CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG); + } sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80); if (!sfdbg) diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index 6b09fdffbd2f..ca6294645dd3 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -177,6 +177,17 @@ restart_entry: lhi %r1,1 sigp %r1,%r0,SIGP_SET_ARCHITECTURE sam64 +#ifdef CONFIG_SMP + larl %r1,smp_cpu_mt_shift + icm %r1,15,0(%r1) + jz smt_done + llgfr %r1,%r1 +smt_loop: + sigp %r1,%r0,SIGP_SET_MULTI_THREADING + brc 8,smt_done /* accepted */ + brc 2,smt_loop /* busy, try again */ +smt_done: +#endif larl %r1,.Lnew_pgm_check_psw lpswe 0(%r1) pgm_check_entry: diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index b1947e0f3e10..46d4449772bc 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -422,6 +422,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, struct kvm_ioapic *ioapic, int vector, int trigger_mode) { int i; + struct kvm_lapic *apic = vcpu->arch.apic; for (i = 0; i < IOAPIC_NUM_PINS; i++) { union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; @@ -443,7 +444,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i); spin_lock(&ioapic->lock); - if (trigger_mode != IOAPIC_LEVEL_TRIG) + if (trigger_mode != IOAPIC_LEVEL_TRIG || + kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) continue; ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index bd4e34de24c7..4ee827d7bf36 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -833,8 +833,7 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) { - if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) && - kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { + if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { int trigger_mode; if (apic_test_vector(vector, apic->regs + APIC_TMR)) trigger_mode = IOAPIC_LEVEL_TRIG; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 10a481b7674d..ae4f6d35d19c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2479,8 +2479,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ vmx->nested.nested_vmx_secondary_ctls_high |= - SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST; + SECONDARY_EXEC_ENABLE_EPT; vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT | VMX_EPT_INVEPT_BIT; @@ -2494,6 +2493,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) } else vmx->nested.nested_vmx_ept_caps = 0; + if (enable_unrestricted_guest) + vmx->nested.nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_UNRESTRICTED_GUEST; + /* miscellaneous data */ rdmsr(MSR_IA32_VMX_MISC, vmx->nested.nested_vmx_misc_low, diff --git a/block/blk-merge.c b/block/blk-merge.c index fc1ff3b1ea1f..fd3fee81c23c 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -592,7 +592,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) { struct bio_vec *bprev; - bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1]; + bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1]; if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset)) return false; } diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index d53a764b05ea..be3290cc0644 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -278,9 +278,11 @@ static int bt_get(struct blk_mq_alloc_data *data, /* * We're out of tags on this hardware queue, kick any * pending IO submits before going to sleep waiting for - * some to complete. + * some to complete. Note that hctx can be NULL here for + * reserved tag allocation. */ - blk_mq_run_hw_queue(hctx, false); + if (hctx) + blk_mq_run_hw_queue(hctx, false); /* * Retry tag allocation after running the hardware queue, diff --git a/block/blk-mq.c b/block/blk-mq.c index 4f4bea21052e..b7b8933ec241 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1938,7 +1938,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) */ if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) - goto err_map; + goto err_mq_usage; setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q); blk_queue_rq_timeout(q, 30000); @@ -1981,7 +1981,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) blk_mq_init_cpu_queues(q, set->nr_hw_queues); if (blk_mq_init_hw_queues(q, set)) - goto err_hw; + goto err_mq_usage; mutex_lock(&all_q_mutex); list_add_tail(&q->all_q_node, &all_q_list); @@ -1993,7 +1993,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) return q; -err_hw: +err_mq_usage: blk_cleanup_queue(q); err_hctxs: kfree(map); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 4c35f0822d06..ef150ebb4c30 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4737,7 +4737,7 @@ struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag) return NULL; /* libsas case */ - if (!ap->scsi_host) { + if (ap->flags & ATA_FLAG_SAS_HOST) { tag = ata_sas_allocate_tag(ap); if (tag < 0) return NULL; @@ -4776,7 +4776,7 @@ void ata_qc_free(struct ata_queued_cmd *qc) tag = qc->tag; if (likely(ata_tag_valid(tag))) { qc->tag = ATA_TAG_POISON; - if (!ap->scsi_host) + if (ap->flags & ATA_FLAG_SAS_HOST) ata_sas_free_tag(tag, ap); } } diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index beb8b27d4621..a13587b5c2be 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -243,4 +243,12 @@ extern struct regcache_ops regcache_rbtree_ops; extern struct regcache_ops regcache_lzo_ops; extern struct regcache_ops regcache_flat_ops; +static inline const char *regmap_name(const struct regmap *map) +{ + if (map->dev) + return dev_name(map->dev); + + return map->name; +} + #endif diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index da84f544c544..87db9893b463 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -218,7 +218,7 @@ int regcache_read(struct regmap *map, ret = map->cache_ops->read(map, reg, value); if (ret == 0) - trace_regmap_reg_read_cache(map->dev, reg, *value); + trace_regmap_reg_read_cache(map, reg, *value); return ret; } @@ -311,7 +311,7 @@ int regcache_sync(struct regmap *map) dev_dbg(map->dev, "Syncing %s cache\n", map->cache_ops->name); name = map->cache_ops->name; - trace_regcache_sync(map->dev, name, "start"); + trace_regcache_sync(map, name, "start"); if (!map->cache_dirty) goto out; @@ -346,7 +346,7 @@ out: regmap_async_complete(map); - trace_regcache_sync(map->dev, name, "stop"); + trace_regcache_sync(map, name, "stop"); return ret; } @@ -381,7 +381,7 @@ int regcache_sync_region(struct regmap *map, unsigned int min, name = map->cache_ops->name; dev_dbg(map->dev, "Syncing %s cache from %d-%d\n", name, min, max); - trace_regcache_sync(map->dev, name, "start region"); + trace_regcache_sync(map, name, "start region"); if (!map->cache_dirty) goto out; @@ -401,7 +401,7 @@ out: regmap_async_complete(map); - trace_regcache_sync(map->dev, name, "stop region"); + trace_regcache_sync(map, name, "stop region"); return ret; } @@ -428,7 +428,7 @@ int regcache_drop_region(struct regmap *map, unsigned int min, map->lock(map->lock_arg); - trace_regcache_drop_region(map->dev, min, max); + trace_regcache_drop_region(map, min, max); ret = map->cache_ops->drop(map, min, max); @@ -455,7 +455,7 @@ void regcache_cache_only(struct regmap *map, bool enable) map->lock(map->lock_arg); WARN_ON(map->cache_bypass && enable); map->cache_only = enable; - trace_regmap_cache_only(map->dev, enable); + trace_regmap_cache_only(map, enable); map->unlock(map->lock_arg); } EXPORT_SYMBOL_GPL(regcache_cache_only); @@ -493,7 +493,7 @@ void regcache_cache_bypass(struct regmap *map, bool enable) map->lock(map->lock_arg); WARN_ON(map->cache_only && enable); map->cache_bypass = enable; - trace_regmap_cache_bypass(map->dev, enable); + trace_regmap_cache_bypass(map, enable); map->unlock(map->lock_arg); } EXPORT_SYMBOL_GPL(regcache_cache_bypass); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index f99b098ddabf..dbfe6a69c3da 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1281,7 +1281,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, if (map->async && map->bus->async_write) { struct regmap_async *async; - trace_regmap_async_write_start(map->dev, reg, val_len); + trace_regmap_async_write_start(map, reg, val_len); spin_lock_irqsave(&map->async_lock, flags); async = list_first_entry_or_null(&map->async_free, @@ -1339,8 +1339,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, return ret; } - trace_regmap_hw_write_start(map->dev, reg, - val_len / map->format.val_bytes); + trace_regmap_hw_write_start(map, reg, val_len / map->format.val_bytes); /* If we're doing a single register write we can probably just * send the work_buf directly, otherwise try to do a gather @@ -1372,8 +1371,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, kfree(buf); } - trace_regmap_hw_write_done(map->dev, reg, - val_len / map->format.val_bytes); + trace_regmap_hw_write_done(map, reg, val_len / map->format.val_bytes); return ret; } @@ -1407,12 +1405,12 @@ static int _regmap_bus_formatted_write(void *context, unsigned int reg, map->format.format_write(map, reg, val); - trace_regmap_hw_write_start(map->dev, reg, 1); + trace_regmap_hw_write_start(map, reg, 1); ret = map->bus->write(map->bus_context, map->work_buf, map->format.buf_size); - trace_regmap_hw_write_done(map->dev, reg, 1); + trace_regmap_hw_write_done(map, reg, 1); return ret; } @@ -1470,7 +1468,7 @@ int _regmap_write(struct regmap *map, unsigned int reg, dev_info(map->dev, "%x <= %x\n", reg, val); #endif - trace_regmap_reg_write(map->dev, reg, val); + trace_regmap_reg_write(map, reg, val); return map->reg_write(context, reg, val); } @@ -1773,7 +1771,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map, for (i = 0; i < num_regs; i++) { int reg = regs[i].reg; int val = regs[i].def; - trace_regmap_hw_write_start(map->dev, reg, 1); + trace_regmap_hw_write_start(map, reg, 1); map->format.format_reg(u8, reg, map->reg_shift); u8 += reg_bytes + pad_bytes; map->format.format_val(u8, val, 0); @@ -1788,7 +1786,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map, for (i = 0; i < num_regs; i++) { int reg = regs[i].reg; - trace_regmap_hw_write_done(map->dev, reg, 1); + trace_regmap_hw_write_done(map, reg, 1); } return ret; } @@ -2059,15 +2057,13 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, */ u8[0] |= map->read_flag_mask; - trace_regmap_hw_read_start(map->dev, reg, - val_len / map->format.val_bytes); + trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes); ret = map->bus->read(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes, val, val_len); - trace_regmap_hw_read_done(map->dev, reg, - val_len / map->format.val_bytes); + trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes); return ret; } @@ -2123,7 +2119,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg, dev_info(map->dev, "%x => %x\n", reg, *val); #endif - trace_regmap_reg_read(map->dev, reg, *val); + trace_regmap_reg_read(map, reg, *val); if (!map->cache_bypass) regcache_write(map, reg, *val); @@ -2480,7 +2476,7 @@ void regmap_async_complete_cb(struct regmap_async *async, int ret) struct regmap *map = async->map; bool wake; - trace_regmap_async_io_complete(map->dev); + trace_regmap_async_io_complete(map); spin_lock(&map->async_lock); list_move(&async->list, &map->async_free); @@ -2525,7 +2521,7 @@ int regmap_async_complete(struct regmap *map) if (!map->bus || !map->bus->async_write) return 0; - trace_regmap_async_complete_start(map->dev); + trace_regmap_async_complete_start(map); wait_event(map->async_waitq, regmap_async_is_done(map)); @@ -2534,7 +2530,7 @@ int regmap_async_complete(struct regmap *map) map->async_ret = 0; spin_unlock_irqrestore(&map->async_lock, flags); - trace_regmap_async_complete_done(map->dev); + trace_regmap_async_complete_done(map); return ret; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 4bc2a5cb9935..a98c41f72c63 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -803,10 +803,6 @@ static int __init nbd_init(void) return -EINVAL; } - nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL); - if (!nbd_dev) - return -ENOMEM; - part_shift = 0; if (max_part > 0) { part_shift = fls(max_part); @@ -828,6 +824,10 @@ static int __init nbd_init(void) if (nbds_max > 1UL << (MINORBITS - part_shift)) return -EINVAL; + nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL); + if (!nbd_dev) + return -ENOMEM; + for (i = 0; i < nbds_max; i++) { struct gendisk *disk = alloc_disk(1 << part_shift); if (!disk) diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index ceb32dd52a6c..e23be20a3417 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -3003,6 +3003,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) } get_device(dev->device); + INIT_LIST_HEAD(&dev->node); INIT_WORK(&dev->probe_work, nvme_async_probe); schedule_work(&dev->probe_work); return 0; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 9b641b38b857..8001fe9e3434 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -433,7 +433,6 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode) dm_get(md); atomic_inc(&md->open_count); - out: spin_unlock(&_minor_lock); @@ -442,16 +441,20 @@ out: static void dm_blk_close(struct gendisk *disk, fmode_t mode) { - struct mapped_device *md = disk->private_data; + struct mapped_device *md; spin_lock(&_minor_lock); + md = disk->private_data; + if (WARN_ON(!md)) + goto out; + if (atomic_dec_and_test(&md->open_count) && (test_bit(DMF_DEFERRED_REMOVE, &md->flags))) queue_work(deferred_remove_workqueue, &deferred_remove_work); dm_put(md); - +out: spin_unlock(&_minor_lock); } @@ -2241,7 +2244,6 @@ static void free_dev(struct mapped_device *md) int minor = MINOR(disk_devt(md->disk)); unlock_fs(md); - bdput(md->bdev); destroy_workqueue(md->wq); if (md->kworker_task) @@ -2252,19 +2254,22 @@ static void free_dev(struct mapped_device *md) mempool_destroy(md->rq_pool); if (md->bs) bioset_free(md->bs); - blk_integrity_unregister(md->disk); - del_gendisk(md->disk); + cleanup_srcu_struct(&md->io_barrier); free_table_devices(&md->table_devices); - free_minor(minor); + dm_stats_cleanup(&md->stats); spin_lock(&_minor_lock); md->disk->private_data = NULL; spin_unlock(&_minor_lock); - + if (blk_get_integrity(md->disk)) + blk_integrity_unregister(md->disk); + del_gendisk(md->disk); put_disk(md->disk); blk_cleanup_queue(md->queue); - dm_stats_cleanup(&md->stats); + bdput(md->bdev); + free_minor(minor); + module_put(THIS_MODULE); kfree(md); } @@ -2642,8 +2647,9 @@ static void __dm_destroy(struct mapped_device *md, bool wait) might_sleep(); - spin_lock(&_minor_lock); map = dm_get_live_table(md, &srcu_idx); + + spin_lock(&_minor_lock); idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md)))); set_bit(DMF_FREEING, &md->flags); spin_unlock(&_minor_lock); diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c index f38ec424872e..5615522f8d62 100644 --- a/drivers/mfd/kempld-core.c +++ b/drivers/mfd/kempld-core.c @@ -739,7 +739,7 @@ static int __init kempld_init(void) for (id = kempld_dmi_table; id->matches[0].slot != DMI_NONE; id++) if (strstr(id->ident, force_device_id)) - if (id->callback && id->callback(id)) + if (id->callback && !id->callback(id)) break; if (id->matches[0].slot == DMI_NONE) return -ENODEV; diff --git a/drivers/mfd/rtsx_usb.c b/drivers/mfd/rtsx_usb.c index ede50244f265..dbd907d7170e 100644 --- a/drivers/mfd/rtsx_usb.c +++ b/drivers/mfd/rtsx_usb.c @@ -196,18 +196,27 @@ EXPORT_SYMBOL_GPL(rtsx_usb_ep0_write_register); int rtsx_usb_ep0_read_register(struct rtsx_ucr *ucr, u16 addr, u8 *data) { u16 value; + u8 *buf; + int ret; if (!data) return -EINVAL; - *data = 0; + + buf = kzalloc(sizeof(u8), GFP_KERNEL); + if (!buf) + return -ENOMEM; addr |= EP0_READ_REG_CMD << EP0_OP_SHIFT; value = swab16(addr); - return usb_control_msg(ucr->pusb_dev, + ret = usb_control_msg(ucr->pusb_dev, usb_rcvctrlpipe(ucr->pusb_dev, 0), RTSX_USB_REQ_REG_OP, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - value, 0, data, 1, 100); + value, 0, buf, 1, 100); + *data = *buf; + + kfree(buf); + return ret; } EXPORT_SYMBOL_GPL(rtsx_usb_ep0_read_register); @@ -288,18 +297,27 @@ static int rtsx_usb_get_status_with_bulk(struct rtsx_ucr *ucr, u16 *status) int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status) { int ret; + u16 *buf; if (!status) return -EINVAL; - if (polling_pipe == 0) + if (polling_pipe == 0) { + buf = kzalloc(sizeof(u16), GFP_KERNEL); + if (!buf) + return -ENOMEM; + ret = usb_control_msg(ucr->pusb_dev, usb_rcvctrlpipe(ucr->pusb_dev, 0), RTSX_USB_REQ_POLL, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - 0, 0, status, 2, 100); - else + 0, 0, buf, 2, 100); + *status = *buf; + + kfree(buf); + } else { ret = rtsx_usb_get_status_with_bulk(ucr, status); + } /* usb_control_msg may return positive when success */ if (ret < 0) diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c index 9205f433573c..18198316b6cf 100644 --- a/drivers/regulator/palmas-regulator.c +++ b/drivers/regulator/palmas-regulator.c @@ -1572,6 +1572,10 @@ static int palmas_regulators_probe(struct platform_device *pdev) if (!pmic) return -ENOMEM; + if (of_device_is_compatible(node, "ti,tps659038-pmic")) + palmas_generic_regs_info[PALMAS_REG_REGEN2].ctrl_addr = + TPS659038_REGEN2_CTRL; + pmic->dev = &pdev->dev; pmic->palmas = palmas; palmas->pmic = pmic; diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c index e2436d140175..3a6fd3a8a2ec 100644 --- a/drivers/rtc/rtc-mrst.c +++ b/drivers/rtc/rtc-mrst.c @@ -413,8 +413,8 @@ static void rtc_mrst_do_remove(struct device *dev) mrst->dev = NULL; } -#ifdef CONFIG_PM -static int mrst_suspend(struct device *dev, pm_message_t mesg) +#ifdef CONFIG_PM_SLEEP +static int mrst_suspend(struct device *dev) { struct mrst_rtc *mrst = dev_get_drvdata(dev); unsigned char tmp; @@ -453,7 +453,7 @@ static int mrst_suspend(struct device *dev, pm_message_t mesg) */ static inline int mrst_poweroff(struct device *dev) { - return mrst_suspend(dev, PMSG_HIBERNATE); + return mrst_suspend(dev); } static int mrst_resume(struct device *dev) @@ -490,9 +490,11 @@ static int mrst_resume(struct device *dev) return 0; } +static SIMPLE_DEV_PM_OPS(mrst_pm_ops, mrst_suspend, mrst_resume); +#define MRST_PM_OPS (&mrst_pm_ops) + #else -#define mrst_suspend NULL -#define mrst_resume NULL +#define MRST_PM_OPS NULL static inline int mrst_poweroff(struct device *dev) { @@ -529,9 +531,8 @@ static struct platform_driver vrtc_mrst_platform_driver = { .remove = vrtc_mrst_platform_remove, .shutdown = vrtc_mrst_platform_shutdown, .driver = { - .name = (char *) driver_name, - .suspend = mrst_suspend, - .resume = mrst_resume, + .name = driver_name, + .pm = MRST_PM_OPS, } }; diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 9219953ee949..d9afc51af7d3 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -6815,7 +6815,8 @@ static struct ata_port_operations ipr_sata_ops = { }; static struct ata_port_info sata_port_info = { - .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA, + .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | + ATA_FLAG_SAS_HOST, .pio_mask = ATA_PIO4_ONLY, .mwdma_mask = ATA_MWDMA2, .udma_mask = ATA_UDMA6, diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 932d9cc98d2f..9c706d8c1441 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -547,7 +547,8 @@ static struct ata_port_operations sas_sata_ops = { }; static struct ata_port_info sata_port_info = { - .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ, + .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ | + ATA_FLAG_SAS_HOST, .pio_mask = ATA_PIO4, .mwdma_mask = ATA_MWDMA2, .udma_mask = ATA_UDMA6, diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c index 3ce39d10fafb..4f8c798e0633 100644 --- a/drivers/spi/spi-dw-mid.c +++ b/drivers/spi/spi-dw-mid.c @@ -108,7 +108,8 @@ static void dw_spi_dma_tx_done(void *arg) { struct dw_spi *dws = arg; - if (test_and_clear_bit(TX_BUSY, &dws->dma_chan_busy) & BIT(RX_BUSY)) + clear_bit(TX_BUSY, &dws->dma_chan_busy); + if (test_bit(RX_BUSY, &dws->dma_chan_busy)) return; dw_spi_xfer_done(dws); } @@ -156,7 +157,8 @@ static void dw_spi_dma_rx_done(void *arg) { struct dw_spi *dws = arg; - if (test_and_clear_bit(RX_BUSY, &dws->dma_chan_busy) & BIT(TX_BUSY)) + clear_bit(RX_BUSY, &dws->dma_chan_busy); + if (test_bit(TX_BUSY, &dws->dma_chan_busy)) return; dw_spi_xfer_done(dws); } diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c index ff9cdbdb6672..2b2c359f5a50 100644 --- a/drivers/spi/spi-qup.c +++ b/drivers/spi/spi-qup.c @@ -498,7 +498,7 @@ static int spi_qup_probe(struct platform_device *pdev) struct resource *res; struct device *dev; void __iomem *base; - u32 max_freq, iomode; + u32 max_freq, iomode, num_cs; int ret, irq, size; dev = &pdev->dev; @@ -550,10 +550,11 @@ static int spi_qup_probe(struct platform_device *pdev) } /* use num-cs unless not present or out of range */ - if (of_property_read_u16(dev->of_node, "num-cs", - &master->num_chipselect) || - (master->num_chipselect > SPI_NUM_CHIPSELECTS)) + if (of_property_read_u32(dev->of_node, "num-cs", &num_cs) || + num_cs > SPI_NUM_CHIPSELECTS) master->num_chipselect = SPI_NUM_CHIPSELECTS; + else + master->num_chipselect = num_cs; master->bus_num = pdev->id; master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index c64a3e59fce3..57a195041dc7 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1105,13 +1105,14 @@ void spi_finalize_current_message(struct spi_master *master) "failed to unprepare message: %d\n", ret); } } + + trace_spi_message_done(mesg); + master->cur_msg_prepared = false; mesg->state = NULL; if (mesg->complete) mesg->complete(mesg->context); - - trace_spi_message_done(mesg); } EXPORT_SYMBOL_GPL(spi_finalize_current_message); diff --git a/fs/affs/file.c b/fs/affs/file.c index d2468bf95669..a91795e01a7f 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -699,8 +699,10 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, boff = tmp % bsize; if (boff) { bh = affs_bread_ino(inode, bidx, 0); - if (IS_ERR(bh)) - return PTR_ERR(bh); + if (IS_ERR(bh)) { + written = PTR_ERR(bh); + goto err_first_bh; + } tmp = min(bsize - boff, to - from); BUG_ON(boff + tmp > bsize || tmp > bsize); memcpy(AFFS_DATA(bh) + boff, data + from, tmp); @@ -712,14 +714,16 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, bidx++; } else if (bidx) { bh = affs_bread_ino(inode, bidx - 1, 0); - if (IS_ERR(bh)) - return PTR_ERR(bh); + if (IS_ERR(bh)) { + written = PTR_ERR(bh); + goto err_first_bh; + } } while (from + bsize <= to) { prev_bh = bh; bh = affs_getemptyblk_ino(inode, bidx); if (IS_ERR(bh)) - goto out; + goto err_bh; memcpy(AFFS_DATA(bh), data + from, bsize); if (buffer_new(bh)) { AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA); @@ -751,7 +755,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, prev_bh = bh; bh = affs_bread_ino(inode, bidx, 1); if (IS_ERR(bh)) - goto out; + goto err_bh; tmp = min(bsize, to - from); BUG_ON(tmp > bsize); memcpy(AFFS_DATA(bh), data + from, tmp); @@ -790,12 +794,13 @@ done: if (tmp > inode->i_size) inode->i_size = AFFS_I(inode)->mmu_private = tmp; +err_first_bh: unlock_page(page); page_cache_release(page); return written; -out: +err_bh: bh = prev_bh; if (!written) written = PTR_ERR(bh); diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 6e560d56094b..754fdf8c6356 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -131,13 +131,16 @@ skip: hfs_bnode_write(node, entry, data_off + key_len, entry_len); hfs_bnode_dump(node); - if (new_node) { - /* update parent key if we inserted a key - * at the start of the first node - */ - if (!rec && new_node != node) - hfs_brec_update_parent(fd); + /* + * update parent key if we inserted a key + * at the start of the node and it is not the new node + */ + if (!rec && new_node != node) { + hfs_bnode_read_key(node, fd->search_key, data_off + size); + hfs_brec_update_parent(fd); + } + if (new_node) { hfs_bnode_put(fd->bnode); if (!new_node->parent) { hfs_btree_inc_height(tree); @@ -168,9 +171,6 @@ skip: goto again; } - if (!rec) - hfs_brec_update_parent(fd); - return 0; } @@ -370,6 +370,8 @@ again: if (IS_ERR(parent)) return PTR_ERR(parent); __hfs_brec_find(parent, fd, hfs_find_rec_by_key); + if (fd->record < 0) + return -ENOENT; hfs_bnode_dump(parent); rec = fd->record; diff --git a/include/linux/libata.h b/include/linux/libata.h index fc03efa64ffe..6b08cc106c21 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -232,6 +232,7 @@ enum { * led */ ATA_FLAG_NO_DIPM = (1 << 23), /* host not happy with DIPM */ ATA_FLAG_LOWTAG = (1 << 24), /* host wants lowest available tag */ + ATA_FLAG_SAS_HOST = (1 << 25), /* SAS host */ /* bits 24:31 of ap->flags are reserved for LLD specific flags */ diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index fb0390a1a498..ee7b1ce7a6f8 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -2999,6 +2999,9 @@ enum usb_irq_events { #define PALMAS_GPADC_TRIM15 0x0E #define PALMAS_GPADC_TRIM16 0x0F +/* TPS659038 regen2_ctrl offset iss different from palmas */ +#define TPS659038_REGEN2_CTRL 0x12 + /* TPS65917 Interrupt registers */ /* Registers for function INTERRUPT */ diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index d4ad5b5a02bb..045f709cb89b 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -316,7 +316,7 @@ struct regulator_desc { * @driver_data: private regulator data * @of_node: OpenFirmware node to parse for device tree bindings (may be * NULL). - * @regmap: regmap to use for core regmap helpers if dev_get_regulator() is + * @regmap: regmap to use for core regmap helpers if dev_get_regmap() is * insufficient. * @ena_gpio_initialized: GPIO controlling regulator enable was properly * initialized, meaning that >= 0 is a valid gpio diff --git a/include/linux/sched.h b/include/linux/sched.h index 6d77432e14ff..a419b65770d6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1625,11 +1625,11 @@ struct task_struct { /* * numa_faults_locality tracks if faults recorded during the last - * scan window were remote/local. The task scan period is adapted - * based on the locality of the faults with different weights - * depending on whether they were shared or private faults + * scan window were remote/local or failed to migrate. The task scan + * period is adapted based on the locality of the faults with different + * weights depending on whether they were shared or private faults */ - unsigned long numa_faults_locality[2]; + unsigned long numa_faults_locality[3]; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ @@ -1719,6 +1719,7 @@ struct task_struct { #define TNF_NO_GROUP 0x02 #define TNF_SHARED 0x04 #define TNF_FAULT_LOCAL 0x08 +#define TNF_MIGRATE_FAIL 0x10 #ifdef CONFIG_NUMA_BALANCING extern void task_numa_fault(int last_node, int node, int pages, int flags); diff --git a/include/trace/events/regmap.h b/include/trace/events/regmap.h index 23d561512f64..22317d2b52ab 100644 --- a/include/trace/events/regmap.h +++ b/include/trace/events/regmap.h @@ -7,27 +7,26 @@ #include <linux/ktime.h> #include <linux/tracepoint.h> -struct device; -struct regmap; +#include "../../../drivers/base/regmap/internal.h" /* * Log register events */ DECLARE_EVENT_CLASS(regmap_reg, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val), + TP_ARGS(map, reg, val), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( unsigned int, reg ) - __field( unsigned int, val ) + __string( name, regmap_name(map) ) + __field( unsigned int, reg ) + __field( unsigned int, val ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->reg = reg; __entry->val = val; ), @@ -39,45 +38,45 @@ DECLARE_EVENT_CLASS(regmap_reg, DEFINE_EVENT(regmap_reg, regmap_reg_write, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val) + TP_ARGS(map, reg, val) ); DEFINE_EVENT(regmap_reg, regmap_reg_read, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val) + TP_ARGS(map, reg, val) ); DEFINE_EVENT(regmap_reg, regmap_reg_read_cache, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val) + TP_ARGS(map, reg, val) ); DECLARE_EVENT_CLASS(regmap_block, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count), + TP_ARGS(map, reg, count), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( unsigned int, reg ) - __field( int, count ) + __string( name, regmap_name(map) ) + __field( unsigned int, reg ) + __field( int, count ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->reg = reg; __entry->count = count; ), @@ -89,48 +88,48 @@ DECLARE_EVENT_CLASS(regmap_block, DEFINE_EVENT(regmap_block, regmap_hw_read_start, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_block, regmap_hw_read_done, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_block, regmap_hw_write_start, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_block, regmap_hw_write_done, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); TRACE_EVENT(regcache_sync, - TP_PROTO(struct device *dev, const char *type, + TP_PROTO(struct regmap *map, const char *type, const char *status), - TP_ARGS(dev, type, status), + TP_ARGS(map, type, status), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __string( status, status ) - __string( type, type ) - __field( int, type ) + __string( name, regmap_name(map) ) + __string( status, status ) + __string( type, type ) + __field( int, type ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __assign_str(status, status); __assign_str(type, type); ), @@ -141,17 +140,17 @@ TRACE_EVENT(regcache_sync, DECLARE_EVENT_CLASS(regmap_bool, - TP_PROTO(struct device *dev, bool flag), + TP_PROTO(struct regmap *map, bool flag), - TP_ARGS(dev, flag), + TP_ARGS(map, flag), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( int, flag ) + __string( name, regmap_name(map) ) + __field( int, flag ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->flag = flag; ), @@ -161,32 +160,32 @@ DECLARE_EVENT_CLASS(regmap_bool, DEFINE_EVENT(regmap_bool, regmap_cache_only, - TP_PROTO(struct device *dev, bool flag), + TP_PROTO(struct regmap *map, bool flag), - TP_ARGS(dev, flag) + TP_ARGS(map, flag) ); DEFINE_EVENT(regmap_bool, regmap_cache_bypass, - TP_PROTO(struct device *dev, bool flag), + TP_PROTO(struct regmap *map, bool flag), - TP_ARGS(dev, flag) + TP_ARGS(map, flag) ); DECLARE_EVENT_CLASS(regmap_async, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev), + TP_ARGS(map), TP_STRUCT__entry( - __string( name, dev_name(dev) ) + __string( name, regmap_name(map) ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); ), TP_printk("%s", __get_str(name)) @@ -194,50 +193,50 @@ DECLARE_EVENT_CLASS(regmap_async, DEFINE_EVENT(regmap_block, regmap_async_write_start, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_async, regmap_async_io_complete, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev) + TP_ARGS(map) ); DEFINE_EVENT(regmap_async, regmap_async_complete_start, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev) + TP_ARGS(map) ); DEFINE_EVENT(regmap_async, regmap_async_complete_done, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev) + TP_ARGS(map) ); TRACE_EVENT(regcache_drop_region, - TP_PROTO(struct device *dev, unsigned int from, + TP_PROTO(struct regmap *map, unsigned int from, unsigned int to), - TP_ARGS(dev, from, to), + TP_ARGS(map, from, to), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( unsigned int, from ) - __field( unsigned int, to ) + __string( name, regmap_name(map) ) + __field( unsigned int, from ) + __field( unsigned int, to ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->from = from; __entry->to = to; ), diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7ce18f3c097a..bcfe32088b37 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1609,9 +1609,11 @@ static void update_task_scan_period(struct task_struct *p, /* * If there were no record hinting faults then either the task is * completely idle or all activity is areas that are not of interest - * to automatic numa balancing. Scan slower + * to automatic numa balancing. Related to that, if there were failed + * migration then it implies we are migrating too quickly or the local + * node is overloaded. In either case, scan slower */ - if (local + shared == 0) { + if (local + shared == 0 || p->numa_faults_locality[2]) { p->numa_scan_period = min(p->numa_scan_period_max, p->numa_scan_period << 1); @@ -2080,6 +2082,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) if (migrated) p->numa_pages_migrated += pages; + if (flags & TNF_MIGRATE_FAIL) + p->numa_faults_locality[2] += pages; p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages; p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 626e93db28ba..6817b0350c71 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1260,6 +1260,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, int target_nid, last_cpupid = -1; bool page_locked; bool migrated = false; + bool was_writable; int flags = 0; /* A PROT_NONE fault should not end up here */ @@ -1291,17 +1292,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, flags |= TNF_FAULT_LOCAL; } - /* - * Avoid grouping on DSO/COW pages in specific and RO pages - * in general, RO pages shouldn't hurt as much anyway since - * they can be in shared cache state. - * - * FIXME! This checks "pmd_dirty()" as an approximation of - * "is this a read-only page", since checking "pmd_write()" - * is even more broken. We haven't actually turned this into - * a writable page, so pmd_write() will always be false. - */ - if (!pmd_dirty(pmd)) + /* See similar comment in do_numa_page for explanation */ + if (!(vma->vm_flags & VM_WRITE)) flags |= TNF_NO_GROUP; /* @@ -1358,12 +1350,17 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, if (migrated) { flags |= TNF_MIGRATED; page_nid = target_nid; - } + } else + flags |= TNF_MIGRATE_FAIL; goto out; clear_pmdnuma: BUG_ON(!PageLocked(page)); + was_writable = pmd_write(pmd); pmd = pmd_modify(pmd, vma->vm_page_prot); + pmd = pmd_mkyoung(pmd); + if (was_writable) + pmd = pmd_mkwrite(pmd); set_pmd_at(mm, haddr, pmdp, pmd); update_mmu_cache_pmd(vma, addr, pmdp); unlock_page(page); @@ -1487,6 +1484,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pmd_t entry; + bool preserve_write = prot_numa && pmd_write(*pmd); ret = 1; /* @@ -1502,9 +1500,11 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (!prot_numa || !pmd_protnone(*pmd)) { entry = pmdp_get_and_clear_notify(mm, addr, pmd); entry = pmd_modify(entry, newprot); + if (preserve_write) + entry = pmd_mkwrite(entry); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); - BUG_ON(pmd_write(entry)); + BUG_ON(!preserve_write && pmd_write(entry)); } spin_unlock(ptl); } diff --git a/mm/memory.c b/mm/memory.c index 411144f977b1..97839f5c8c30 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3035,6 +3035,7 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, int last_cpupid; int target_nid; bool migrated = false; + bool was_writable = pte_write(pte); int flags = 0; /* A PROT_NONE fault should not end up here */ @@ -3059,6 +3060,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Make it present again */ pte = pte_modify(pte, vma->vm_page_prot); pte = pte_mkyoung(pte); + if (was_writable) + pte = pte_mkwrite(pte); set_pte_at(mm, addr, ptep, pte); update_mmu_cache(vma, addr, ptep); @@ -3069,16 +3072,14 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, } /* - * Avoid grouping on DSO/COW pages in specific and RO pages - * in general, RO pages shouldn't hurt as much anyway since - * they can be in shared cache state. - * - * FIXME! This checks "pmd_dirty()" as an approximation of - * "is this a read-only page", since checking "pmd_write()" - * is even more broken. We haven't actually turned this into - * a writable page, so pmd_write() will always be false. + * Avoid grouping on RO pages in general. RO pages shouldn't hurt as + * much anyway since they can be in shared cache state. This misses + * the case where a mapping is writable but the process never writes + * to it but pte_write gets cleared during protection updates and + * pte_dirty has unpredictable behaviour between PTE scan updates, + * background writeback, dirty balancing and application behaviour. */ - if (!pte_dirty(pte)) + if (!(vma->vm_flags & VM_WRITE)) flags |= TNF_NO_GROUP; /* @@ -3102,7 +3103,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, if (migrated) { page_nid = target_nid; flags |= TNF_MIGRATED; - } + } else + flags |= TNF_MIGRATE_FAIL; out: if (page_nid != -1) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9fab10795bea..65842d688b7c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1092,6 +1092,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) return NULL; arch_refresh_nodedata(nid, pgdat); + } else { + /* Reset the nr_zones and classzone_idx to 0 before reuse */ + pgdat->nr_zones = 0; + pgdat->classzone_idx = 0; } /* we can use NODE_DATA(nid) from here */ @@ -1977,15 +1981,6 @@ void try_offline_node(int nid) if (is_vmalloc_addr(zone->wait_table)) vfree(zone->wait_table); } - - /* - * Since there is no way to guarentee the address of pgdat/zone is not - * on stack of any kernel threads or used by other kernel objects - * without reference counting or other symchronizing method, do not - * reset node_data and free pgdat here. Just reset it to 0 and reuse - * the memory when the node is online again. - */ - memset(pgdat, 0, sizeof(*pgdat)); } EXPORT_SYMBOL(try_offline_node); diff --git a/mm/mmap.c b/mm/mmap.c index da9990acc08b..9ec50a368634 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -774,10 +774,8 @@ again: remove_next = 1 + (end > next->vm_end); importer->anon_vma = exporter->anon_vma; error = anon_vma_clone(importer, exporter); - if (error) { - importer->anon_vma = NULL; + if (error) return error; - } } } diff --git a/mm/mprotect.c b/mm/mprotect.c index 44727811bf4c..88584838e704 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -75,6 +75,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, oldpte = *pte; if (pte_present(oldpte)) { pte_t ptent; + bool preserve_write = prot_numa && pte_write(oldpte); /* * Avoid trapping faults against the zero or KSM @@ -94,6 +95,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, ptent = ptep_modify_prot_start(mm, addr, pte); ptent = pte_modify(ptent, newprot); + if (preserve_write) + ptent = pte_mkwrite(ptent); /* Avoid taking write faults for known dirty pages */ if (dirty_accountable && pte_dirty(ptent) && diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 45e187b2d971..644bcb665773 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -857,8 +857,11 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period + * + * @written may have decreased due to account_page_redirty(). + * Avoid underflowing @bw calculation. */ - bw = written - bdi->written_stamp; + bw = written - min(written, bdi->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { do_div(bw, elapsed); @@ -922,7 +925,7 @@ static void global_update_bandwidth(unsigned long thresh, unsigned long now) { static DEFINE_SPINLOCK(dirty_lock); - static unsigned long update_time; + static unsigned long update_time = INITIAL_JIFFIES; /* * check locklessly first to optimize away locking for the most time diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 72f5ac381ab3..755a42c76eb4 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -103,6 +103,7 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype) if (!is_migrate_isolate_page(buddy)) { __isolate_free_page(page, order); + kernel_map_pages(page, (1 << order), 1); set_page_refcounted(page); isolated_page = page; } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 75c1f2878519..29f2f8b853ae 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -265,8 +265,15 @@ int walk_page_range(unsigned long start, unsigned long end, vma = vma->vm_next; err = walk_page_test(start, next, walk); - if (err > 0) + if (err > 0) { + /* + * positive return values are purely for + * controlling the pagewalk, so should never + * be passed to the callers. + */ + err = 0; continue; + } if (err < 0) break; } diff --git a/mm/rmap.c b/mm/rmap.c index 5e3e09081164..c161a14b6a8f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -287,6 +287,13 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) return 0; enomem_failure: + /* + * dst->anon_vma is dropped here otherwise its degree can be incorrectly + * decremented in unlink_anon_vmas(). + * We can safely do this because callers of anon_vma_clone() don't care + * about dst->anon_vma if anon_vma_clone() failed. + */ + dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } diff --git a/mm/slub.c b/mm/slub.c index 6832c4eab104..82c473780c91 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2449,7 +2449,8 @@ redo: do { tid = this_cpu_read(s->cpu_slab->tid); c = raw_cpu_ptr(s->cpu_slab); - } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + } while (IS_ENABLED(CONFIG_PREEMPT) && + unlikely(tid != READ_ONCE(c->tid))); /* * Irqless object alloc/free algorithm used here depends on sequence @@ -2718,7 +2719,8 @@ redo: do { tid = this_cpu_read(s->cpu_slab->tid); c = raw_cpu_ptr(s->cpu_slab); - } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + } while (IS_ENABLED(CONFIG_PREEMPT) && + unlikely(tid != READ_ONCE(c->tid))); /* Same with comment on barrier() in slab_alloc_node() */ barrier(); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 4e511221a0c1..0db571340edb 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -22,6 +22,14 @@ TARGETS += vm TARGETS_HOTPLUG = cpu-hotplug TARGETS_HOTPLUG += memory-hotplug +# Clear LDFLAGS and MAKEFLAGS if called from main +# Makefile to avoid test build failures when test +# Makefile doesn't have explicit build rules. +ifeq (1,$(MAKELEVEL)) +undefine LDFLAGS +override MAKEFLAGS = +endif + all: for TARGET in $(TARGETS); do \ make -C $$TARGET; \ diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a2214d9609bd..cc6a25d95fbf 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -471,7 +471,7 @@ static struct kvm *kvm_create_vm(unsigned long type) BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); r = -ENOMEM; - kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + kvm->memslots = kvm_kvzalloc(sizeof(struct kvm_memslots)); if (!kvm->memslots) goto out_err_no_srcu; @@ -522,7 +522,7 @@ out_err_no_srcu: out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm->buses[i]); - kfree(kvm->memslots); + kvfree(kvm->memslots); kvm_arch_free_vm(kvm); return ERR_PTR(r); } @@ -578,7 +578,7 @@ static void kvm_free_physmem(struct kvm *kvm) kvm_for_each_memslot(memslot, slots) kvm_free_physmem_slot(kvm, memslot, NULL); - kfree(kvm->memslots); + kvfree(kvm->memslots); } static void kvm_destroy_devices(struct kvm *kvm) @@ -871,10 +871,10 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out_free; } - slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), - GFP_KERNEL); + slots = kvm_kvzalloc(sizeof(struct kvm_memslots)); if (!slots) goto out_free; + memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { slot = id_to_memslot(slots, mem->slot); @@ -917,7 +917,7 @@ int __kvm_set_memory_region(struct kvm *kvm, kvm_arch_commit_memory_region(kvm, mem, &old, change); kvm_free_physmem_slot(kvm, &old, &new); - kfree(old_memslots); + kvfree(old_memslots); /* * IOMMU mapping: New slots need to be mapped. Old slots need to be @@ -936,7 +936,7 @@ int __kvm_set_memory_region(struct kvm *kvm, return 0; out_slots: - kfree(slots); + kvfree(slots); out_free: kvm_free_physmem_slot(kvm, &new, &old); out: |