diff options
Diffstat (limited to 'arch')
32 files changed, 487 insertions, 196 deletions
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 114234e83caa..edda76fae83f 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -67,7 +67,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, sigset_t *set) { int err; - err = __copy_to_user(&(sf->uc.uc_mcontext.regs), regs, + err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs, sizeof(sf->uc.uc_mcontext.regs.scratch)); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t)); @@ -83,7 +83,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) if (!err) set_current_blocked(&set); - err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs), + err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch), sizeof(sf->uc.uc_mcontext.regs.scratch)); return err; @@ -131,6 +131,15 @@ SYSCALL_DEFINE0(rt_sigreturn) /* Don't restart from sigreturn */ syscall_wont_restart(regs); + /* + * Ensure that sigreturn always returns to user mode (in case the + * regs saved on user stack got fudged between save and sigreturn) + * Otherwise it is easy to panic the kernel with a custom + * signal handler and/or restorer which clobberes the status32/ret + * to return to a bogus location in kernel mode. + */ + regs->status32 |= STATUS_U_MASK; + return regs->r0; badframe: @@ -229,8 +238,11 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) /* * handler returns using sigreturn stub provided already by userpsace + * If not, nuke the process right away */ - BUG_ON(!(ksig->ka.sa.sa_flags & SA_RESTORER)); + if(!(ksig->ka.sa.sa_flags & SA_RESTORER)) + return 1; + regs->blink = (unsigned long)ksig->ka.sa.sa_restorer; /* User Stack for signal handler will be above the frame just carved */ @@ -296,12 +308,12 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { sigset_t *oldset = sigmask_to_save(); - int ret; + int failed; /* Set up the stack frame */ - ret = setup_rt_frame(ksig, oldset, regs); + failed = setup_rt_frame(ksig, oldset, regs); - signal_setup_done(ret, ksig, 0); + signal_setup_done(failed, ksig, 0); } void do_signal(struct pt_regs *regs) 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/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index f213f5b4c423..d17437238a2c 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -26,7 +26,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) if (likely(pgd != NULL)) { memset(pgd, 0, PAGE_SIZE<<PGD_ALLOC_ORDER); -#ifdef CONFIG_64BIT +#if PT_NLEVELS == 3 actual_pgd += PTRS_PER_PGD; /* Populate first pmd with allocated memory. We mark it * with PxD_FLAG_ATTACHED as a signal to the system that this @@ -45,7 +45,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { -#ifdef CONFIG_64BIT +#if PT_NLEVELS == 3 pgd -= PTRS_PER_PGD; #endif free_pages((unsigned long)pgd, PGD_ALLOC_ORDER); @@ -72,12 +72,15 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { -#ifdef CONFIG_64BIT if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED) - /* This is the permanent pmd attached to the pgd; - * cannot free it */ + /* + * This is the permanent pmd attached to the pgd; + * cannot free it. + * Increment the counter to compensate for the decrement + * done by generic mm code. + */ + mm_inc_nr_pmds(mm); return; -#endif free_pages((unsigned long)pmd, PMD_ORDER); } @@ -99,7 +102,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { -#ifdef CONFIG_64BIT +#if PT_NLEVELS == 3 /* preserve the gateway marker if this is the beginning of * the permanent pmd */ if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED) diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 5a8997d63899..8eefb12d1d33 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -55,8 +55,8 @@ #define ENTRY_COMP(_name_) .word sys_##_name_ #endif - ENTRY_SAME(restart_syscall) /* 0 */ - ENTRY_SAME(exit) +90: ENTRY_SAME(restart_syscall) /* 0 */ +91: ENTRY_SAME(exit) ENTRY_SAME(fork_wrapper) ENTRY_SAME(read) ENTRY_SAME(write) @@ -439,7 +439,10 @@ ENTRY_SAME(bpf) ENTRY_COMP(execveat) - /* Nothing yet */ + +.ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b)) +.error "size of syscall table does not fit value of __NR_Linux_syscalls" +.endif #undef ENTRY_SAME #undef ENTRY_DIFF 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/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index de4018a1bc4b..de747563d29d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -636,7 +636,7 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu) spin_lock(&vcpu->arch.vpa_update_lock); lppaca = (struct lppaca *)vcpu->arch.vpa.pinned_addr; if (lppaca) - yield_count = lppaca->yield_count; + yield_count = be32_to_cpu(lppaca->yield_count); spin_unlock(&vcpu->arch.vpa_update_lock); return yield_count; } @@ -942,20 +942,20 @@ static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu, static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, bool preserve_top32) { + struct kvm *kvm = vcpu->kvm; struct kvmppc_vcore *vc = vcpu->arch.vcore; u64 mask; + mutex_lock(&kvm->lock); spin_lock(&vc->lock); /* * If ILE (interrupt little-endian) has changed, update the * MSR_LE bit in the intr_msr for each vcpu in this vcore. */ if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) { - struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *vcpu; int i; - mutex_lock(&kvm->lock); kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.vcore != vc) continue; @@ -964,7 +964,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, else vcpu->arch.intr_msr &= ~MSR_LE; } - mutex_unlock(&kvm->lock); } /* @@ -981,6 +980,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, mask &= 0xFFFFFFFF; vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask); spin_unlock(&vc->lock); + mutex_unlock(&kvm->lock); } static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index bb94e6f20c81..6cbf1630cb70 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1005,6 +1005,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* Save HEIR (HV emulation assist reg) in emul_inst if this is an HEI (HV emulation interrupt, e40) */ li r3,KVM_INST_FETCH_FAILED + stw r3,VCPU_LAST_INST(r9) cmpwi r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST bne 11f mfspr r3,SPRN_HEIR 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/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index 4f6725ff4c33..f5b6537306f0 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2957,6 +2957,17 @@ unsigned long sun4v_t5_set_perfreg(unsigned long reg_num, unsigned long reg_val); #endif + +#define HV_FAST_M7_GET_PERFREG 0x43 +#define HV_FAST_M7_SET_PERFREG 0x44 + +#ifndef __ASSEMBLY__ +unsigned long sun4v_m7_get_perfreg(unsigned long reg_num, + unsigned long *reg_val); +unsigned long sun4v_m7_set_perfreg(unsigned long reg_num, + unsigned long reg_val); +#endif + /* Function numbers for HV_CORE_TRAP. */ #define HV_CORE_SET_VER 0x00 #define HV_CORE_PUTCHAR 0x01 @@ -2981,6 +2992,7 @@ unsigned long sun4v_t5_set_perfreg(unsigned long reg_num, #define HV_GRP_SDIO 0x0108 #define HV_GRP_SDIO_ERR 0x0109 #define HV_GRP_REBOOT_DATA 0x0110 +#define HV_GRP_M7_PERF 0x0114 #define HV_GRP_NIAG_PERF 0x0200 #define HV_GRP_FIRE_PERF 0x0201 #define HV_GRP_N2_CPU 0x0202 diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c index 5c55145bfbf0..662500fa555f 100644 --- a/arch/sparc/kernel/hvapi.c +++ b/arch/sparc/kernel/hvapi.c @@ -48,6 +48,7 @@ static struct api_info api_table[] = { { .group = HV_GRP_VT_CPU, }, { .group = HV_GRP_T5_CPU, }, { .group = HV_GRP_DIAG, .flags = FLAG_PRE_API }, + { .group = HV_GRP_M7_PERF, }, }; static DEFINE_SPINLOCK(hvapi_lock); diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index caedf8320416..afbaba52d2f1 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -837,3 +837,19 @@ ENTRY(sun4v_t5_set_perfreg) retl nop ENDPROC(sun4v_t5_set_perfreg) + +ENTRY(sun4v_m7_get_perfreg) + mov %o1, %o4 + mov HV_FAST_M7_GET_PERFREG, %o5 + ta HV_FAST_TRAP + stx %o1, [%o4] + retl + nop +ENDPROC(sun4v_m7_get_perfreg) + +ENTRY(sun4v_m7_set_perfreg) + mov HV_FAST_M7_SET_PERFREG, %o5 + ta HV_FAST_TRAP + retl + nop +ENDPROC(sun4v_m7_set_perfreg) diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index 7e967c8018c8..eb978c77c76a 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -217,6 +217,31 @@ static const struct pcr_ops n5_pcr_ops = { .pcr_nmi_disable = PCR_N4_PICNPT, }; +static u64 m7_pcr_read(unsigned long reg_num) +{ + unsigned long val; + + (void) sun4v_m7_get_perfreg(reg_num, &val); + + return val; +} + +static void m7_pcr_write(unsigned long reg_num, u64 val) +{ + (void) sun4v_m7_set_perfreg(reg_num, val); +} + +static const struct pcr_ops m7_pcr_ops = { + .read_pcr = m7_pcr_read, + .write_pcr = m7_pcr_write, + .read_pic = n4_pic_read, + .write_pic = n4_pic_write, + .nmi_picl_value = n4_picl_value, + .pcr_nmi_enable = (PCR_N4_PICNPT | PCR_N4_STRACE | + PCR_N4_UTRACE | PCR_N4_TOE | + (26 << PCR_N4_SL_SHIFT)), + .pcr_nmi_disable = PCR_N4_PICNPT, +}; static unsigned long perf_hsvc_group; static unsigned long perf_hsvc_major; @@ -248,6 +273,10 @@ static int __init register_perf_hsvc(void) perf_hsvc_group = HV_GRP_T5_CPU; break; + case SUN4V_CHIP_SPARC_M7: + perf_hsvc_group = HV_GRP_M7_PERF; + break; + default: return -ENODEV; } @@ -293,6 +322,10 @@ static int __init setup_sun4v_pcr_ops(void) pcr_ops = &n5_pcr_ops; break; + case SUN4V_CHIP_SPARC_M7: + pcr_ops = &m7_pcr_ops; + break; + default: ret = -ENODEV; break; diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 46a5e4508752..86eebfa3b158 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -792,6 +792,42 @@ static const struct sparc_pmu niagara4_pmu = { .num_pic_regs = 4, }; +static void sparc_m7_write_pmc(int idx, u64 val) +{ + u64 pcr; + + pcr = pcr_ops->read_pcr(idx); + /* ensure ov and ntc are reset */ + pcr &= ~(PCR_N4_OV | PCR_N4_NTC); + + pcr_ops->write_pic(idx, val & 0xffffffff); + + pcr_ops->write_pcr(idx, pcr); +} + +static const struct sparc_pmu sparc_m7_pmu = { + .event_map = niagara4_event_map, + .cache_map = &niagara4_cache_map, + .max_events = ARRAY_SIZE(niagara4_perfmon_event_map), + .read_pmc = sparc_vt_read_pmc, + .write_pmc = sparc_m7_write_pmc, + .upper_shift = 5, + .lower_shift = 5, + .event_mask = 0x7ff, + .user_bit = PCR_N4_UTRACE, + .priv_bit = PCR_N4_STRACE, + + /* We explicitly don't support hypervisor tracing. */ + .hv_bit = 0, + + .irq_bit = PCR_N4_TOE, + .upper_nop = 0, + .lower_nop = 0, + .flags = 0, + .max_hw_events = 4, + .num_pcrs = 4, + .num_pic_regs = 4, +}; static const struct sparc_pmu *sparc_pmu __read_mostly; static u64 event_encoding(u64 event_id, int idx) @@ -960,6 +996,8 @@ out: cpuc->pcr[0] |= cpuc->event[0]->hw.config_base; } +static void sparc_pmu_start(struct perf_event *event, int flags); + /* On this PMU each PIC has it's own PCR control register. */ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc) { @@ -972,20 +1010,13 @@ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc) struct perf_event *cp = cpuc->event[i]; struct hw_perf_event *hwc = &cp->hw; int idx = hwc->idx; - u64 enc; if (cpuc->current_idx[i] != PIC_NO_INDEX) continue; - sparc_perf_event_set_period(cp, hwc, idx); cpuc->current_idx[i] = idx; - enc = perf_event_get_enc(cpuc->events[i]); - cpuc->pcr[idx] &= ~mask_for_index(idx); - if (hwc->state & PERF_HES_STOPPED) - cpuc->pcr[idx] |= nop_for_index(idx); - else - cpuc->pcr[idx] |= event_encoding(enc, idx); + sparc_pmu_start(cp, PERF_EF_RELOAD); } out: for (i = 0; i < cpuc->n_events; i++) { @@ -1101,7 +1132,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags) int i; local_irq_save(flags); - perf_pmu_disable(event->pmu); for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event[i]) { @@ -1127,7 +1157,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags) } } - perf_pmu_enable(event->pmu); local_irq_restore(flags); } @@ -1361,7 +1390,6 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags) unsigned long flags; local_irq_save(flags); - perf_pmu_disable(event->pmu); n0 = cpuc->n_events; if (n0 >= sparc_pmu->max_hw_events) @@ -1394,7 +1422,6 @@ nocheck: ret = 0; out: - perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; } @@ -1667,6 +1694,10 @@ static bool __init supported_pmu(void) sparc_pmu = &niagara4_pmu; return true; } + if (!strcmp(sparc_pmu_type, "sparc-m7")) { + sparc_pmu = &sparc_m7_pmu; + return true; + } return false; } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 0be7bf978cb1..46a59643bb1c 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -287,6 +287,8 @@ void arch_trigger_all_cpu_backtrace(bool include_self) printk(" TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n", gp->tpc, gp->o7, gp->i7, gp->rpc); } + + touch_nmi_watchdog(); } memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); @@ -362,6 +364,8 @@ static void pmu_snapshot_all_cpus(void) (cpu == this_cpu ? '*' : ' '), cpu, pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3], pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]); + + touch_nmi_watchdog(); } memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S index b7f6334e159f..857ad4f8905f 100644 --- a/arch/sparc/lib/memmove.S +++ b/arch/sparc/lib/memmove.S @@ -8,9 +8,11 @@ .text ENTRY(memmove) /* o0=dst o1=src o2=len */ - mov %o0, %g1 + brz,pn %o2, 99f + mov %o0, %g1 + cmp %o0, %o1 - bleu,pt %xcc, memcpy + bleu,pt %xcc, 2f add %o1, %o2, %g7 cmp %g7, %o0 bleu,pt %xcc, memcpy @@ -24,7 +26,34 @@ ENTRY(memmove) /* o0=dst o1=src o2=len */ stb %g7, [%o0] bne,pt %icc, 1b sub %o0, 1, %o0 - +99: retl mov %g1, %o0 + + /* We can't just call memcpy for these memmove cases. On some + * chips the memcpy uses cache initializing stores and when dst + * and src are close enough, those can clobber the source data + * before we've loaded it in. + */ +2: or %o0, %o1, %g7 + or %o2, %g7, %g7 + andcc %g7, 0x7, %g0 + bne,pn %xcc, 4f + nop + +3: ldx [%o1], %g7 + add %o1, 8, %o1 + subcc %o2, 8, %o2 + add %o0, 8, %o0 + bne,pt %icc, 3b + stx %g7, [%o0 - 0x8] + ba,a,pt %xcc, 99b + +4: ldub [%o1], %g7 + add %o1, 1, %o1 + subcc %o2, 1, %o2 + add %o0, 1, %o0 + bne,pt %icc, 4b + stb %g7, [%o0 - 0x1] + ba,a,pt %xcc, 99b ENDPROC(memmove) 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, |