diff options
Diffstat (limited to 'arch')
139 files changed, 1733 insertions, 2580 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 33687dddd86a..3ab446bd12ef 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -383,7 +383,13 @@ config HAVE_ARCH_JUMP_LABEL_RELATIVE config HAVE_RCU_TABLE_FREE bool -config HAVE_RCU_TABLE_INVALIDATE +config HAVE_RCU_TABLE_NO_INVALIDATE + bool + +config HAVE_MMU_GATHER_PAGE_SIZE + bool + +config HAVE_MMU_GATHER_NO_GATHER bool config ARCH_HAVE_NMI_SAFE_CMPXCHG @@ -901,6 +907,15 @@ config HAVE_ARCH_PREL32_RELOCATIONS config ARCH_USE_MEMREMAP_PROT bool +config LOCK_EVENT_COUNTS + bool "Locking event counts collection" + depends on DEBUG_FS + ---help--- + Enable light-weight counting of various locking related events + in the system with minimal performance impact. This reduces + the chance of application behavior change because of timing + differences. The counts are reported via debugfs. + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 584a6e114853..f7b19b813a70 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -36,6 +36,7 @@ config ALPHA select ODD_RT_SIGACTION select OLD_SIGSUSPEND select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67 + select MMU_GATHER_NO_RANGE help The Alpha is a 64-bit general-purpose processor designed and marketed by the Digital Equipment Corporation of blessed memory, @@ -49,13 +50,6 @@ config MMU bool default y -config RWSEM_GENERIC_SPINLOCK - bool - -config RWSEM_XCHGADD_ALGORITHM - bool - default y - config ARCH_HAS_ILOG2_U32 bool default n diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h deleted file mode 100644 index cf8fc8f9a2ed..000000000000 --- a/arch/alpha/include/asm/rwsem.h +++ /dev/null @@ -1,211 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ALPHA_RWSEM_H -#define _ALPHA_RWSEM_H - -/* - * Written by Ivan Kokshaysky <ink@jurassic.park.msu.ru>, 2001. - * Based on asm-alpha/semaphore.h and asm-i386/rwsem.h - */ - -#ifndef _LINUX_RWSEM_H -#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead" -#endif - -#ifdef __KERNEL__ - -#include <linux/compiler.h> - -#define RWSEM_UNLOCKED_VALUE 0x0000000000000000L -#define RWSEM_ACTIVE_BIAS 0x0000000000000001L -#define RWSEM_ACTIVE_MASK 0x00000000ffffffffL -#define RWSEM_WAITING_BIAS (-0x0000000100000000L) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -static inline int ___down_read(struct rw_semaphore *sem) -{ - long oldcount; -#ifndef CONFIG_SMP - oldcount = sem->count.counter; - sem->count.counter += RWSEM_ACTIVE_READ_BIAS; -#else - long temp; - __asm__ __volatile__( - "1: ldq_l %0,%1\n" - " addq %0,%3,%2\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - " mb\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) - :"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory"); -#endif - return (oldcount < 0); -} - -static inline void __down_read(struct rw_semaphore *sem) -{ - if (unlikely(___down_read(sem))) - rwsem_down_read_failed(sem); -} - -static inline int __down_read_killable(struct rw_semaphore *sem) -{ - if (unlikely(___down_read(sem))) - if (IS_ERR(rwsem_down_read_failed_killable(sem))) - return -EINTR; - - return 0; -} - -/* - * trylock for reading -- returns 1 if successful, 0 if contention - */ -static inline int __down_read_trylock(struct rw_semaphore *sem) -{ - long old, new, res; - - res = atomic_long_read(&sem->count); - do { - new = res + RWSEM_ACTIVE_READ_BIAS; - if (new <= 0) - break; - old = res; - res = atomic_long_cmpxchg(&sem->count, old, new); - } while (res != old); - return res >= 0 ? 1 : 0; -} - -static inline long ___down_write(struct rw_semaphore *sem) -{ - long oldcount; -#ifndef CONFIG_SMP - oldcount = sem->count.counter; - sem->count.counter += RWSEM_ACTIVE_WRITE_BIAS; -#else - long temp; - __asm__ __volatile__( - "1: ldq_l %0,%1\n" - " addq %0,%3,%2\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - " mb\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) - :"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory"); -#endif - return oldcount; -} - -static inline void __down_write(struct rw_semaphore *sem) -{ - if (unlikely(___down_write(sem))) - rwsem_down_write_failed(sem); -} - -static inline int __down_write_killable(struct rw_semaphore *sem) -{ - if (unlikely(___down_write(sem))) { - if (IS_ERR(rwsem_down_write_failed_killable(sem))) - return -EINTR; - } - - return 0; -} - -/* - * trylock for writing -- returns 1 if successful, 0 if contention - */ -static inline int __down_write_trylock(struct rw_semaphore *sem) -{ - long ret = atomic_long_cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, - RWSEM_ACTIVE_WRITE_BIAS); - if (ret == RWSEM_UNLOCKED_VALUE) - return 1; - return 0; -} - -static inline void __up_read(struct rw_semaphore *sem) -{ - long oldcount; -#ifndef CONFIG_SMP - oldcount = sem->count.counter; - sem->count.counter -= RWSEM_ACTIVE_READ_BIAS; -#else - long temp; - __asm__ __volatile__( - " mb\n" - "1: ldq_l %0,%1\n" - " subq %0,%3,%2\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) - :"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory"); -#endif - if (unlikely(oldcount < 0)) - if ((int)oldcount - RWSEM_ACTIVE_READ_BIAS == 0) - rwsem_wake(sem); -} - -static inline void __up_write(struct rw_semaphore *sem) -{ - long count; -#ifndef CONFIG_SMP - sem->count.counter -= RWSEM_ACTIVE_WRITE_BIAS; - count = sem->count.counter; -#else - long temp; - __asm__ __volatile__( - " mb\n" - "1: ldq_l %0,%1\n" - " subq %0,%3,%2\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - " subq %0,%3,%0\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (count), "=m" (sem->count), "=&r" (temp) - :"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory"); -#endif - if (unlikely(count)) - if ((int)count == 0) - rwsem_wake(sem); -} - -/* - * downgrade write lock to read lock - */ -static inline void __downgrade_write(struct rw_semaphore *sem) -{ - long oldcount; -#ifndef CONFIG_SMP - oldcount = sem->count.counter; - sem->count.counter -= RWSEM_WAITING_BIAS; -#else - long temp; - __asm__ __volatile__( - "1: ldq_l %0,%1\n" - " addq %0,%3,%2\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - " mb\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) - :"Ir" (-RWSEM_WAITING_BIAS), "m" (sem->count) : "memory"); -#endif - if (unlikely(oldcount < 0)) - rwsem_downgrade_wake(sem); -} - -#endif /* __KERNEL__ */ -#endif /* _ALPHA_RWSEM_H */ diff --git a/arch/alpha/include/asm/tlb.h b/arch/alpha/include/asm/tlb.h index 8f5042b61875..4f79e331af5e 100644 --- a/arch/alpha/include/asm/tlb.h +++ b/arch/alpha/include/asm/tlb.h @@ -2,12 +2,6 @@ #ifndef _ALPHA_TLB_H #define _ALPHA_TLB_H -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) -#define __tlb_remove_tlb_entry(tlb, pte, addr) do { } while (0) - -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - #include <asm-generic/tlb.h> #define __pte_free_tlb(tlb, pte, address) pte_free((tlb)->mm, pte) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index c781e45d1d99..23e063df5d2c 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -63,9 +63,6 @@ config SCHED_OMIT_FRAME_POINTER config GENERIC_CSUM def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - config ARCH_DISCONTIGMEM_ENABLE def_bool n diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h index a9db5f62aaf3..90cac97643a4 100644 --- a/arch/arc/include/asm/tlb.h +++ b/arch/arc/include/asm/tlb.h @@ -9,38 +9,6 @@ #ifndef _ASM_ARC_TLB_H #define _ASM_ARC_TLB_H -#define tlb_flush(tlb) \ -do { \ - if (tlb->fullmm) \ - flush_tlb_mm((tlb)->mm); \ -} while (0) - -/* - * This pair is called at time of munmap/exit to flush cache and TLB entries - * for mappings being torn down. - * 1) cache-flush part -implemented via tlb_start_vma( ) for VIPT aliasing D$ - * 2) tlb-flush part - implemted via tlb_end_vma( ) flushes the TLB range - * - * Note, read http://lkml.org/lkml/2004/1/15/6 - */ -#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING -#define tlb_start_vma(tlb, vma) -#else -#define tlb_start_vma(tlb, vma) \ -do { \ - if (!tlb->fullmm) \ - flush_cache_range(vma, vma->vm_start, vma->vm_end); \ -} while(0) -#endif - -#define tlb_end_vma(tlb, vma) \ -do { \ - if (!tlb->fullmm) \ - flush_tlb_range(vma, vma->vm_start, vma->vm_end); \ -} while (0) - -#define __tlb_remove_tlb_entry(tlb, ptep, address) - #include <linux/pagemap.h> #include <asm-generic/tlb.h> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9aed25a6019b..dc9855c4a3b4 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -178,10 +178,6 @@ config TRACE_IRQFLAGS_SUPPORT bool default !CPU_V7M -config RWSEM_XCHGADD_ALGORITHM - bool - default y - config ARCH_HAS_ILOG2_U32 bool diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index a8a4eb7f6dae..8fb51b7bf1d5 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -12,7 +12,6 @@ generic-y += mm-arch-hooks.h generic-y += msi.h generic-y += parport.h generic-y += preempt.h -generic-y += rwsem.h generic-y += seccomp.h generic-y += segment.h generic-y += serial.h diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index f854148c8d7c..bc6d04a09899 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -33,271 +33,42 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> -#define MMU_GATHER_BUNDLE 8 - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE static inline void __tlb_remove_table(void *_table) { free_page_and_swap_cache((struct page *)_table); } -struct mmu_table_batch { - struct rcu_head rcu; - unsigned int nr; - void *tables[0]; -}; - -#define MAX_TABLE_BATCH \ - ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) - -extern void tlb_table_flush(struct mmu_gather *tlb); -extern void tlb_remove_table(struct mmu_gather *tlb, void *table); - -#define tlb_remove_entry(tlb, entry) tlb_remove_table(tlb, entry) -#else -#define tlb_remove_entry(tlb, entry) tlb_remove_page(tlb, entry) -#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ - -/* - * TLB handling. This allows us to remove pages from the page - * tables, and efficiently handle the TLB issues. - */ -struct mmu_gather { - struct mm_struct *mm; -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - struct mmu_table_batch *batch; - unsigned int need_flush; -#endif - unsigned int fullmm; - struct vm_area_struct *vma; - unsigned long start, end; - unsigned long range_start; - unsigned long range_end; - unsigned int nr; - unsigned int max; - struct page **pages; - struct page *local[MMU_GATHER_BUNDLE]; -}; - -DECLARE_PER_CPU(struct mmu_gather, mmu_gathers); - -/* - * This is unnecessarily complex. There's three ways the TLB shootdown - * code is used: - * 1. Unmapping a range of vmas. See zap_page_range(), unmap_region(). - * tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called. - * tlb->vma will be non-NULL. - * 2. Unmapping all vmas. See exit_mmap(). - * tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called. - * tlb->vma will be non-NULL. Additionally, page tables will be freed. - * 3. Unmapping argument pages. See shift_arg_pages(). - * tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called. - * tlb->vma will be NULL. - */ -static inline void tlb_flush(struct mmu_gather *tlb) -{ - if (tlb->fullmm || !tlb->vma) - flush_tlb_mm(tlb->mm); - else if (tlb->range_end > 0) { - flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end); - tlb->range_start = TASK_SIZE; - tlb->range_end = 0; - } -} - -static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr) -{ - if (!tlb->fullmm) { - if (addr < tlb->range_start) - tlb->range_start = addr; - if (addr + PAGE_SIZE > tlb->range_end) - tlb->range_end = addr + PAGE_SIZE; - } -} - -static inline void __tlb_alloc_page(struct mmu_gather *tlb) -{ - unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0); - - if (addr) { - tlb->pages = (void *)addr; - tlb->max = PAGE_SIZE / sizeof(struct page *); - } -} - -static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) -{ - tlb_flush(tlb); -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - tlb_table_flush(tlb); -#endif -} - -static inline void tlb_flush_mmu_free(struct mmu_gather *tlb) -{ - free_pages_and_swap_cache(tlb->pages, tlb->nr); - tlb->nr = 0; - if (tlb->pages == tlb->local) - __tlb_alloc_page(tlb); -} - -static inline void tlb_flush_mmu(struct mmu_gather *tlb) -{ - tlb_flush_mmu_tlbonly(tlb); - tlb_flush_mmu_free(tlb); -} - -static inline void -arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - tlb->mm = mm; - tlb->fullmm = !(start | (end+1)); - tlb->start = start; - tlb->end = end; - tlb->vma = NULL; - tlb->max = ARRAY_SIZE(tlb->local); - tlb->pages = tlb->local; - tlb->nr = 0; - __tlb_alloc_page(tlb); +#include <asm-generic/tlb.h> -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - tlb->batch = NULL; +#ifndef CONFIG_HAVE_RCU_TABLE_FREE +#define tlb_remove_table(tlb, entry) tlb_remove_page(tlb, entry) #endif -} - -static inline void -arch_tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end, bool force) -{ - if (force) { - tlb->range_start = start; - tlb->range_end = end; - } - - tlb_flush_mmu(tlb); - - /* keep the page table cache within bounds */ - check_pgt_cache(); - - if (tlb->pages != tlb->local) - free_pages((unsigned long)tlb->pages, 0); -} - -/* - * Memorize the range for the TLB flush. - */ -static inline void -tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr) -{ - tlb_add_flush(tlb, addr); -} - -#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ - tlb_remove_tlb_entry(tlb, ptep, address) -/* - * In the case of tlb vma handling, we can optimise these away in the - * case where we're doing a full MM flush. When we're doing a munmap, - * the vmas are adjusted to only cover the region to be torn down. - */ -static inline void -tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) -{ - if (!tlb->fullmm) { - flush_cache_range(vma, vma->vm_start, vma->vm_end); - tlb->vma = vma; - tlb->range_start = TASK_SIZE; - tlb->range_end = 0; - } -} static inline void -tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) -{ - if (!tlb->fullmm) - tlb_flush(tlb); -} - -static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - tlb->pages[tlb->nr++] = page; - VM_WARN_ON(tlb->nr > tlb->max); - if (tlb->nr == tlb->max) - return true; - return false; -} - -static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - if (__tlb_remove_page(tlb, page)) - tlb_flush_mmu(tlb); -} - -static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size) -{ - return __tlb_remove_page(tlb, page); -} - -static inline void tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size) -{ - return tlb_remove_page(tlb, page); -} - -static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, - unsigned long addr) +__pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { pgtable_page_dtor(pte); -#ifdef CONFIG_ARM_LPAE - tlb_add_flush(tlb, addr); -#else +#ifndef CONFIG_ARM_LPAE /* * With the classic ARM MMU, a pte page has two corresponding pmd * entries, each covering 1MB. */ - addr &= PMD_MASK; - tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE); - tlb_add_flush(tlb, addr + SZ_1M); + addr = (addr & PMD_MASK) + SZ_1M; + __tlb_adjust_range(tlb, addr - PAGE_SIZE, 2 * PAGE_SIZE); #endif - tlb_remove_entry(tlb, pte); -} - -static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, - unsigned long addr) -{ -#ifdef CONFIG_ARM_LPAE - tlb_add_flush(tlb, addr); - tlb_remove_entry(tlb, virt_to_page(pmdp)); -#endif + tlb_remove_table(tlb, pte); } static inline void -tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) -{ - tlb_add_flush(tlb, addr); -} - -#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr) -#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr) -#define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp) - -#define tlb_migrate_finish(mm) do { } while (0) - -#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change -static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, - unsigned int page_size) +__pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) { -} - -static inline void tlb_flush_remove_tables(struct mm_struct *mm) -{ -} +#ifdef CONFIG_ARM_LPAE + struct page *page = virt_to_page(pmdp); -static inline void tlb_flush_remove_tables_local(void *arg) -{ + tlb_remove_table(tlb, page); +#endif } #endif /* CONFIG_MMU */ diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 76bb8de6bf6b..be5edfdde558 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -549,8 +549,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) int ret; /* - * Increment event counter and perform fixup for the pre-signal - * frame. + * Perform fixup for the pre-signal frame. */ rseq_signal_deliver(ksig, regs); diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index a56e7c856ab5..86870f40f9a0 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -115,8 +115,6 @@ static noinline void __save_stack_trace(struct task_struct *tsk, * running on another CPU? For now, ignore it as we * can't guarantee we won't explode. */ - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; return; #else frame.fp = thread_saved_fp(tsk); @@ -134,8 +132,6 @@ static noinline void __save_stack_trace(struct task_struct *tsk, } walk_stackframe(&frame, save_trace, &data); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) @@ -153,8 +149,6 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) frame.pc = regs->ARM_pc; walk_stackframe(&frame, save_trace, &data); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7e34b9eba5de..d81adca1b04d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -149,7 +149,6 @@ config ARM64 select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RCU_TABLE_FREE - select HAVE_RCU_TABLE_INVALIDATE select HAVE_RSEQ select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS @@ -237,9 +236,6 @@ config LOCKDEP_SUPPORT config TRACE_IRQFLAGS_SUPPORT def_bool y -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config GENERIC_BUG def_bool y depends on BUG diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 1e17ea5c372b..60a933b07001 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -16,7 +16,6 @@ generic-y += mm-arch-hooks.h generic-y += msi.h generic-y += qrwlock.h generic-y += qspinlock.h -generic-y += rwsem.h generic-y += segment.h generic-y += serial.h generic-y += set_memory.h diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index 106fdc951b6e..37603b5616a5 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -27,6 +27,7 @@ static inline void __tlb_remove_table(void *_table) free_page_and_swap_cache((struct page *)_table); } +#define tlb_flush tlb_flush static void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index d908b5e9e949..b00ec7d483d1 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -140,8 +140,6 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) #endif walk_stackframe(current, &frame, save_trace, &data); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace_regs); @@ -172,8 +170,6 @@ static noinline void __save_stack_trace(struct task_struct *tsk, #endif walk_stackframe(tsk, &frame, save_trace, &data); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; put_task_stack(tsk); } diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig index e5cd3c5f8399..eeb0471268a0 100644 --- a/arch/c6x/Kconfig +++ b/arch/c6x/Kconfig @@ -20,6 +20,7 @@ config C6X select GENERIC_CLOCKEVENTS select MODULES_USE_ELF_RELA select ARCH_NO_COHERENT_DMA_MMAP + select MMU_GATHER_NO_RANGE if MMU config MMU def_bool n @@ -27,9 +28,6 @@ config MMU config FPU def_bool n -config RWSEM_GENERIC_SPINLOCK - def_bool y - config GENERIC_CALIBRATE_DELAY def_bool y diff --git a/arch/c6x/include/asm/tlb.h b/arch/c6x/include/asm/tlb.h index 34525dea1356..240ba0febb57 100644 --- a/arch/c6x/include/asm/tlb.h +++ b/arch/c6x/include/asm/tlb.h @@ -2,8 +2,6 @@ #ifndef _ASM_C6X_TLB_H #define _ASM_C6X_TLB_H -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - #include <asm-generic/tlb.h> #endif /* _ASM_C6X_TLB_H */ diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 725a115759c9..6555d1781132 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -92,9 +92,6 @@ config GENERIC_HWEIGHT config MMU def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - config STACKTRACE_SUPPORT def_bool y diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index c071da34e081..61c01db6c292 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -27,9 +27,6 @@ config H8300 config CPU_BIG_ENDIAN def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - config GENERIC_HWEIGHT def_bool y diff --git a/arch/h8300/include/asm/tlb.h b/arch/h8300/include/asm/tlb.h index 98f344279904..d8201ca31206 100644 --- a/arch/h8300/include/asm/tlb.h +++ b/arch/h8300/include/asm/tlb.h @@ -2,8 +2,6 @@ #ifndef __H8300_TLB_H__ #define __H8300_TLB_H__ -#define tlb_flush(tlb) do { } while (0) - #include <asm-generic/tlb.h> #endif diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index ac441680dcc0..3e54a53208d5 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -65,12 +65,6 @@ config GENERIC_CSUM config GENERIC_IRQ_PROBE def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool n - -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config GENERIC_HWEIGHT def_bool y diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index d046e8ccdf78..3ff5f297acda 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -27,7 +27,6 @@ generic-y += mm-arch-hooks.h generic-y += pci.h generic-y += percpu.h generic-y += preempt.h -generic-y += rwsem.h generic-y += sections.h generic-y += segment.h generic-y += serial.h diff --git a/arch/hexagon/include/asm/tlb.h b/arch/hexagon/include/asm/tlb.h index 2f00772cc08a..f71c4ba83614 100644 --- a/arch/hexagon/include/asm/tlb.h +++ b/arch/hexagon/include/asm/tlb.h @@ -22,18 +22,6 @@ #include <linux/pagemap.h> #include <asm/tlbflush.h> -/* - * We don't need any special per-pte or per-vma handling... - */ -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) -#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) - -/* - * .. because we flush the whole mm when it fills up - */ -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - #include <asm-generic/tlb.h> #endif diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 8d7396bd1790..73a26f04644e 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -83,10 +83,6 @@ config STACKTRACE_SUPPORT config GENERIC_LOCKBREAK def_bool n -config RWSEM_XCHGADD_ALGORITHM - bool - default y - config HUGETLB_PAGE_SIZE_VARIABLE bool depends on HUGETLB_PAGE diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h index 5133739966bc..beae261fbcb4 100644 --- a/arch/ia64/include/asm/machvec.h +++ b/arch/ia64/include/asm/machvec.h @@ -30,7 +30,6 @@ typedef void ia64_mv_irq_init_t (void); typedef void ia64_mv_send_ipi_t (int, int, int, int); typedef void ia64_mv_timer_interrupt_t (int, void *); typedef void ia64_mv_global_tlb_purge_t (struct mm_struct *, unsigned long, unsigned long, unsigned long); -typedef void ia64_mv_tlb_migrate_finish_t (struct mm_struct *); typedef u8 ia64_mv_irq_to_vector (int); typedef unsigned int ia64_mv_local_vector_to_irq (u8); typedef char *ia64_mv_pci_get_legacy_mem_t (struct pci_bus *); @@ -80,11 +79,6 @@ machvec_noop (void) } static inline void -machvec_noop_mm (struct mm_struct *mm) -{ -} - -static inline void machvec_noop_task (struct task_struct *task) { } @@ -96,7 +90,6 @@ machvec_noop_bus (struct pci_bus *bus) extern void machvec_setup (char **); extern void machvec_timer_interrupt (int, void *); -extern void machvec_tlb_migrate_finish (struct mm_struct *); # if defined (CONFIG_IA64_HP_SIM) # include <asm/machvec_hpsim.h> @@ -124,7 +117,6 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *); # define platform_send_ipi ia64_mv.send_ipi # define platform_timer_interrupt ia64_mv.timer_interrupt # define platform_global_tlb_purge ia64_mv.global_tlb_purge -# define platform_tlb_migrate_finish ia64_mv.tlb_migrate_finish # define platform_dma_init ia64_mv.dma_init # define platform_dma_get_ops ia64_mv.dma_get_ops # define platform_irq_to_vector ia64_mv.irq_to_vector @@ -167,7 +159,6 @@ struct ia64_machine_vector { ia64_mv_send_ipi_t *send_ipi; ia64_mv_timer_interrupt_t *timer_interrupt; ia64_mv_global_tlb_purge_t *global_tlb_purge; - ia64_mv_tlb_migrate_finish_t *tlb_migrate_finish; ia64_mv_dma_init *dma_init; ia64_mv_dma_get_ops *dma_get_ops; ia64_mv_irq_to_vector *irq_to_vector; @@ -206,7 +197,6 @@ struct ia64_machine_vector { platform_send_ipi, \ platform_timer_interrupt, \ platform_global_tlb_purge, \ - platform_tlb_migrate_finish, \ platform_dma_init, \ platform_dma_get_ops, \ platform_irq_to_vector, \ @@ -270,9 +260,6 @@ extern const struct dma_map_ops *dma_get_ops(struct device *); #ifndef platform_global_tlb_purge # define platform_global_tlb_purge ia64_global_tlb_purge /* default to architected version */ #endif -#ifndef platform_tlb_migrate_finish -# define platform_tlb_migrate_finish machvec_noop_mm -#endif #ifndef platform_kernel_launch_event # define platform_kernel_launch_event machvec_noop #endif diff --git a/arch/ia64/include/asm/machvec_sn2.h b/arch/ia64/include/asm/machvec_sn2.h index b5153d300289..a243e4fb4877 100644 --- a/arch/ia64/include/asm/machvec_sn2.h +++ b/arch/ia64/include/asm/machvec_sn2.h @@ -34,7 +34,6 @@ extern ia64_mv_irq_init_t sn_irq_init; extern ia64_mv_send_ipi_t sn2_send_IPI; extern ia64_mv_timer_interrupt_t sn_timer_interrupt; extern ia64_mv_global_tlb_purge_t sn2_global_tlb_purge; -extern ia64_mv_tlb_migrate_finish_t sn_tlb_migrate_finish; extern ia64_mv_irq_to_vector sn_irq_to_vector; extern ia64_mv_local_vector_to_irq sn_local_vector_to_irq; extern ia64_mv_pci_get_legacy_mem_t sn_pci_get_legacy_mem; @@ -77,7 +76,6 @@ extern ia64_mv_pci_fixup_bus_t sn_pci_fixup_bus; #define platform_send_ipi sn2_send_IPI #define platform_timer_interrupt sn_timer_interrupt #define platform_global_tlb_purge sn2_global_tlb_purge -#define platform_tlb_migrate_finish sn_tlb_migrate_finish #define platform_pci_fixup sn_pci_fixup #define platform_inb __sn_inb #define platform_inw __sn_inw diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h deleted file mode 100644 index 917910607e0e..000000000000 --- a/arch/ia64/include/asm/rwsem.h +++ /dev/null @@ -1,172 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * R/W semaphores for ia64 - * - * Copyright (C) 2003 Ken Chen <kenneth.w.chen@intel.com> - * Copyright (C) 2003 Asit Mallick <asit.k.mallick@intel.com> - * Copyright (C) 2005 Christoph Lameter <cl@linux.com> - * - * Based on asm-i386/rwsem.h and other architecture implementation. - * - * The MSW of the count is the negated number of active writers and - * waiting lockers, and the LSW is the total number of active locks. - * - * The lock count is initialized to 0 (no active and no waiting lockers). - * - * When a writer subtracts WRITE_BIAS, it'll get 0xffffffff00000001 for - * the case of an uncontended lock. Readers increment by 1 and see a positive - * value when uncontended, negative if there are writers (and maybe) readers - * waiting (in which case it goes to sleep). - */ - -#ifndef _ASM_IA64_RWSEM_H -#define _ASM_IA64_RWSEM_H - -#ifndef _LINUX_RWSEM_H -#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead." -#endif - -#include <asm/intrinsics.h> - -#define RWSEM_UNLOCKED_VALUE __IA64_UL_CONST(0x0000000000000000) -#define RWSEM_ACTIVE_BIAS (1L) -#define RWSEM_ACTIVE_MASK (0xffffffffL) -#define RWSEM_WAITING_BIAS (-0x100000000L) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -/* - * lock for reading - */ -static inline int -___down_read (struct rw_semaphore *sem) -{ - long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1); - - return (result < 0); -} - -static inline void -__down_read (struct rw_semaphore *sem) -{ - if (___down_read(sem)) - rwsem_down_read_failed(sem); -} - -static inline int -__down_read_killable (struct rw_semaphore *sem) -{ - if (___down_read(sem)) - if (IS_ERR(rwsem_down_read_failed_killable(sem))) - return -EINTR; - - return 0; -} - -/* - * lock for writing - */ -static inline long -___down_write (struct rw_semaphore *sem) -{ - long old, new; - - do { - old = atomic_long_read(&sem->count); - new = old + RWSEM_ACTIVE_WRITE_BIAS; - } while (atomic_long_cmpxchg_acquire(&sem->count, old, new) != old); - - return old; -} - -static inline void -__down_write (struct rw_semaphore *sem) -{ - if (___down_write(sem)) - rwsem_down_write_failed(sem); -} - -static inline int -__down_write_killable (struct rw_semaphore *sem) -{ - if (___down_write(sem)) { - if (IS_ERR(rwsem_down_write_failed_killable(sem))) - return -EINTR; - } - - return 0; -} - -/* - * unlock after reading - */ -static inline void -__up_read (struct rw_semaphore *sem) -{ - long result = ia64_fetchadd8_rel((unsigned long *)&sem->count.counter, -1); - - if (result < 0 && (--result & RWSEM_ACTIVE_MASK) == 0) - rwsem_wake(sem); -} - -/* - * unlock after writing - */ -static inline void -__up_write (struct rw_semaphore *sem) -{ - long old, new; - - do { - old = atomic_long_read(&sem->count); - new = old - RWSEM_ACTIVE_WRITE_BIAS; - } while (atomic_long_cmpxchg_release(&sem->count, old, new) != old); - - if (new < 0 && (new & RWSEM_ACTIVE_MASK) == 0) - rwsem_wake(sem); -} - -/* - * trylock for reading -- returns 1 if successful, 0 if contention - */ -static inline int -__down_read_trylock (struct rw_semaphore *sem) -{ - long tmp; - while ((tmp = atomic_long_read(&sem->count)) >= 0) { - if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, tmp+1)) { - return 1; - } - } - return 0; -} - -/* - * trylock for writing -- returns 1 if successful, 0 if contention - */ -static inline int -__down_write_trylock (struct rw_semaphore *sem) -{ - long tmp = atomic_long_cmpxchg_acquire(&sem->count, - RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS); - return tmp == RWSEM_UNLOCKED_VALUE; -} - -/* - * downgrade write lock to read lock - */ -static inline void -__downgrade_write (struct rw_semaphore *sem) -{ - long old, new; - - do { - old = atomic_long_read(&sem->count); - new = old - RWSEM_WAITING_BIAS; - } while (atomic_long_cmpxchg_release(&sem->count, old, new) != old); - - if (old < 0) - rwsem_downgrade_wake(sem); -} - -#endif /* _ASM_IA64_RWSEM_H */ diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index 516355a774bf..86ec034ba499 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -47,263 +47,6 @@ #include <asm/tlbflush.h> #include <asm/machvec.h> -/* - * If we can't allocate a page to make a big batch of page pointers - * to work on, then just handle a few from the on-stack structure. - */ -#define IA64_GATHER_BUNDLE 8 - -struct mmu_gather { - struct mm_struct *mm; - unsigned int nr; - unsigned int max; - unsigned char fullmm; /* non-zero means full mm flush */ - unsigned char need_flush; /* really unmapped some PTEs? */ - unsigned long start, end; - unsigned long start_addr; - unsigned long end_addr; - struct page **pages; - struct page *local[IA64_GATHER_BUNDLE]; -}; - -struct ia64_tr_entry { - u64 ifa; - u64 itir; - u64 pte; - u64 rr; -}; /*Record for tr entry!*/ - -extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size); -extern void ia64_ptr_entry(u64 target_mask, int slot); - -extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS]; - -/* - region register macros -*/ -#define RR_TO_VE(val) (((val) >> 0) & 0x0000000000000001) -#define RR_VE(val) (((val) & 0x0000000000000001) << 0) -#define RR_VE_MASK 0x0000000000000001L -#define RR_VE_SHIFT 0 -#define RR_TO_PS(val) (((val) >> 2) & 0x000000000000003f) -#define RR_PS(val) (((val) & 0x000000000000003f) << 2) -#define RR_PS_MASK 0x00000000000000fcL -#define RR_PS_SHIFT 2 -#define RR_RID_MASK 0x00000000ffffff00L -#define RR_TO_RID(val) ((val >> 8) & 0xffffff) - -static inline void -ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned long end) -{ - tlb->need_flush = 0; - - if (tlb->fullmm) { - /* - * Tearing down the entire address space. This happens both as a result - * of exit() and execve(). The latter case necessitates the call to - * flush_tlb_mm() here. - */ - flush_tlb_mm(tlb->mm); - } else if (unlikely (end - start >= 1024*1024*1024*1024UL - || REGION_NUMBER(start) != REGION_NUMBER(end - 1))) - { - /* - * If we flush more than a tera-byte or across regions, we're probably - * better off just flushing the entire TLB(s). This should be very rare - * and is not worth optimizing for. - */ - flush_tlb_all(); - } else { - /* - * flush_tlb_range() takes a vma instead of a mm pointer because - * some architectures want the vm_flags for ITLB/DTLB flush. - */ - struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); - - /* flush the address range from the tlb: */ - flush_tlb_range(&vma, start, end); - /* now flush the virt. page-table area mapping the address range: */ - flush_tlb_range(&vma, ia64_thash(start), ia64_thash(end)); - } - -} - -static inline void -ia64_tlb_flush_mmu_free(struct mmu_gather *tlb) -{ - unsigned long i; - unsigned int nr; - - /* lastly, release the freed pages */ - nr = tlb->nr; - - tlb->nr = 0; - tlb->start_addr = ~0UL; - for (i = 0; i < nr; ++i) - free_page_and_swap_cache(tlb->pages[i]); -} - -/* - * Flush the TLB for address range START to END and, if not in fast mode, release the - * freed pages that where gathered up to this point. - */ -static inline void -ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end) -{ - if (!tlb->need_flush) - return; - ia64_tlb_flush_mmu_tlbonly(tlb, start, end); - ia64_tlb_flush_mmu_free(tlb); -} - -static inline void __tlb_alloc_page(struct mmu_gather *tlb) -{ - unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0); - - if (addr) { - tlb->pages = (void *)addr; - tlb->max = PAGE_SIZE / sizeof(void *); - } -} - - -static inline void -arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - tlb->mm = mm; - tlb->max = ARRAY_SIZE(tlb->local); - tlb->pages = tlb->local; - tlb->nr = 0; - tlb->fullmm = !(start | (end+1)); - tlb->start = start; - tlb->end = end; - tlb->start_addr = ~0UL; -} - -/* - * Called at the end of the shootdown operation to free up any resources that were - * collected. - */ -static inline void -arch_tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end, bool force) -{ - if (force) - tlb->need_flush = 1; - /* - * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and - * tlb->end_addr. - */ - ia64_tlb_flush_mmu(tlb, start, end); - - /* keep the page table cache within bounds */ - check_pgt_cache(); - - if (tlb->pages != tlb->local) - free_pages((unsigned long)tlb->pages, 0); -} - -/* - * Logically, this routine frees PAGE. On MP machines, the actual freeing of the page - * must be delayed until after the TLB has been flushed (see comments at the beginning of - * this file). - */ -static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - tlb->need_flush = 1; - - if (!tlb->nr && tlb->pages == tlb->local) - __tlb_alloc_page(tlb); - - tlb->pages[tlb->nr++] = page; - VM_WARN_ON(tlb->nr > tlb->max); - if (tlb->nr == tlb->max) - return true; - return false; -} - -static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) -{ - ia64_tlb_flush_mmu_tlbonly(tlb, tlb->start_addr, tlb->end_addr); -} - -static inline void tlb_flush_mmu_free(struct mmu_gather *tlb) -{ - ia64_tlb_flush_mmu_free(tlb); -} - -static inline void tlb_flush_mmu(struct mmu_gather *tlb) -{ - ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr); -} - -static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - if (__tlb_remove_page(tlb, page)) - tlb_flush_mmu(tlb); -} - -static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size) -{ - return __tlb_remove_page(tlb, page); -} - -static inline void tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size) -{ - return tlb_remove_page(tlb, page); -} - -/* - * Remove TLB entry for PTE mapped at virtual address ADDRESS. This is called for any - * PTE, not just those pointing to (normal) physical memory. - */ -static inline void -__tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long address) -{ - if (tlb->start_addr == ~0UL) - tlb->start_addr = address; - tlb->end_addr = address + PAGE_SIZE; -} - -#define tlb_migrate_finish(mm) platform_tlb_migrate_finish(mm) - -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) - -#define tlb_remove_tlb_entry(tlb, ptep, addr) \ -do { \ - tlb->need_flush = 1; \ - __tlb_remove_tlb_entry(tlb, ptep, addr); \ -} while (0) - -#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ - tlb_remove_tlb_entry(tlb, ptep, address) - -#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change -static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, - unsigned int page_size) -{ -} - -#define pte_free_tlb(tlb, ptep, address) \ -do { \ - tlb->need_flush = 1; \ - __pte_free_tlb(tlb, ptep, address); \ -} while (0) - -#define pmd_free_tlb(tlb, ptep, address) \ -do { \ - tlb->need_flush = 1; \ - __pmd_free_tlb(tlb, ptep, address); \ -} while (0) - -#define pud_free_tlb(tlb, pudp, address) \ -do { \ - tlb->need_flush = 1; \ - __pud_free_tlb(tlb, pudp, address); \ -} while (0) +#include <asm-generic/tlb.h> #endif /* _ASM_IA64_TLB_H */ diff --git a/arch/ia64/include/asm/tlbflush.h b/arch/ia64/include/asm/tlbflush.h index 25e280810f6c..ceac10c4d6e2 100644 --- a/arch/ia64/include/asm/tlbflush.h +++ b/arch/ia64/include/asm/tlbflush.h @@ -14,6 +14,31 @@ #include <asm/mmu_context.h> #include <asm/page.h> +struct ia64_tr_entry { + u64 ifa; + u64 itir; + u64 pte; + u64 rr; +}; /*Record for tr entry!*/ + +extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size); +extern void ia64_ptr_entry(u64 target_mask, int slot); +extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS]; + +/* + region register macros +*/ +#define RR_TO_VE(val) (((val) >> 0) & 0x0000000000000001) +#define RR_VE(val) (((val) & 0x0000000000000001) << 0) +#define RR_VE_MASK 0x0000000000000001L +#define RR_VE_SHIFT 0 +#define RR_TO_PS(val) (((val) >> 2) & 0x000000000000003f) +#define RR_PS(val) (((val) & 0x000000000000003f) << 2) +#define RR_PS_MASK 0x00000000000000fcL +#define RR_PS_SHIFT 2 +#define RR_RID_MASK 0x00000000ffffff00L +#define RR_TO_RID(val) ((val >> 8) & 0xffffff) + /* * Now for some TLB flushing routines. This is the kind of stuff that * can be very expensive, so try to avoid them whenever possible. diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 583a3746d70b..c9cfa760cd57 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -1058,9 +1058,7 @@ check_bugs (void) static int __init run_dmi_scan(void) { - dmi_scan_machine(); - dmi_memdev_walk(); - dmi_set_dump_stack_arch_desc(); + dmi_setup(); return 0; } core_initcall(run_dmi_scan); diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c index 5fc89aabdce1..5158bd28de05 100644 --- a/arch/ia64/mm/tlb.c +++ b/arch/ia64/mm/tlb.c @@ -305,8 +305,8 @@ local_flush_tlb_all (void) ia64_srlz_i(); /* srlz.i implies srlz.d */ } -void -flush_tlb_range (struct vm_area_struct *vma, unsigned long start, +static void +__flush_tlb_range (struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; @@ -343,6 +343,25 @@ flush_tlb_range (struct vm_area_struct *vma, unsigned long start, preempt_enable(); ia64_srlz_i(); /* srlz.i implies srlz.d */ } + +void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (unlikely(end - start >= 1024*1024*1024*1024UL + || REGION_NUMBER(start) != REGION_NUMBER(end - 1))) { + /* + * If we flush more than a tera-byte or across regions, we're + * probably better off just flushing the entire TLB(s). This + * should be very rare and is not worth optimizing for. + */ + flush_tlb_all(); + } else { + /* flush the address range from the tlb */ + __flush_tlb_range(vma, start, end); + /* flush the virt. page-table area mapping the addr range */ + __flush_tlb_range(vma, ia64_thash(start), ia64_thash(end)); + } +} EXPORT_SYMBOL(flush_tlb_range); void ia64_tlb_init(void) diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c index b73b0ebf8214..b510f4f17fd4 100644 --- a/arch/ia64/sn/kernel/sn2/sn2_smp.c +++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c @@ -120,13 +120,6 @@ void sn_migrate(struct task_struct *task) cpu_relax(); } -void sn_tlb_migrate_finish(struct mm_struct *mm) -{ - /* flush_tlb_mm is inefficient if more than 1 users of mm */ - if (mm == current->mm && mm && atomic_read(&mm->mm_users) == 1) - flush_tlb_mm(mm); -} - static void sn2_ipi_flush_all_tlb(struct mm_struct *mm) { diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index b54206408f91..735b9679fe6f 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -28,17 +28,11 @@ config M68K select OLD_SIGSUSPEND3 select OLD_SIGACTION select ARCH_DISCARD_MEMBLOCK + select MMU_GATHER_NO_RANGE if MMU config CPU_BIG_ENDIAN def_bool y -config RWSEM_GENERIC_SPINLOCK - bool - default y - -config RWSEM_XCHGADD_ALGORITHM - bool - config ARCH_HAS_ILOG2_U32 bool diff --git a/arch/m68k/include/asm/tlb.h b/arch/m68k/include/asm/tlb.h index b4b9efb6f963..3c81f6adfc8b 100644 --- a/arch/m68k/include/asm/tlb.h +++ b/arch/m68k/include/asm/tlb.h @@ -2,20 +2,6 @@ #ifndef _M68K_TLB_H #define _M68K_TLB_H -/* - * m68k doesn't need any special per-pte or - * per-vma handling.. - */ -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) -#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) - -/* - * .. because we flush the whole mm when it - * fills up. - */ -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - #include <asm-generic/tlb.h> #endif /* _M68K_TLB_H */ diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index a51b965b3b82..adb179f519f9 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -41,6 +41,7 @@ config MICROBLAZE select TRACING_SUPPORT select VIRT_TO_BUS select CPU_NO_EFFICIENT_FFS + select MMU_GATHER_NO_RANGE if MMU # Endianness selection choice @@ -58,15 +59,9 @@ config CPU_LITTLE_ENDIAN endchoice -config RWSEM_GENERIC_SPINLOCK - def_bool y - config ZONE_DMA def_bool y -config RWSEM_XCHGADD_ALGORITHM - bool - config ARCH_HAS_ILOG2_U32 def_bool n diff --git a/arch/microblaze/include/asm/tlb.h b/arch/microblaze/include/asm/tlb.h index 99b6ded54849..628a78ee0a72 100644 --- a/arch/microblaze/include/asm/tlb.h +++ b/arch/microblaze/include/asm/tlb.h @@ -11,16 +11,7 @@ #ifndef _ASM_MICROBLAZE_TLB_H #define _ASM_MICROBLAZE_TLB_H -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - #include <linux/pagemap.h> - -#ifdef CONFIG_MMU -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) -#define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0) -#endif - #include <asm-generic/tlb.h> #endif /* _ASM_MICROBLAZE_TLB_H */ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 4a5f5b0ee9a9..b9c48b27162d 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1037,13 +1037,6 @@ source "arch/mips/paravirt/Kconfig" endmenu -config RWSEM_GENERIC_SPINLOCK - bool - default y - -config RWSEM_XCHGADD_ALGORITHM - bool - config GENERIC_HWEIGHT bool default y diff --git a/arch/mips/include/asm/tlb.h b/arch/mips/include/asm/tlb.h index b6823b9e94da..90f3ad76d9e0 100644 --- a/arch/mips/include/asm/tlb.h +++ b/arch/mips/include/asm/tlb.h @@ -5,23 +5,6 @@ #include <asm/cpu-features.h> #include <asm/mipsregs.h> -/* - * MIPS doesn't need any special per-pte or per-vma handling, except - * we need to flush cache for area to be unmapped. - */ -#define tlb_start_vma(tlb, vma) \ - do { \ - if (!tlb->fullmm) \ - flush_cache_range(vma, vma->vm_start, vma->vm_end); \ - } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) -#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) - -/* - * .. because we flush the whole mm when it fills up. - */ -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - #define _UNIQUE_ENTRYHI(base, idx) \ (((base) + ((idx) << (PAGE_SHIFT + 1))) | \ (cpu_has_tlbinv ? MIPS_ENTRYHI_EHINV : 0)) diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index addb7f5f5264..55559ca0efe4 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -60,9 +60,6 @@ config GENERIC_LOCKBREAK def_bool y depends on PREEMPT -config RWSEM_GENERIC_SPINLOCK - def_bool y - config TRACE_IRQFLAGS_SUPPORT def_bool y diff --git a/arch/nds32/include/asm/tlb.h b/arch/nds32/include/asm/tlb.h index b35ae5eae3ab..d5ae571c8d30 100644 --- a/arch/nds32/include/asm/tlb.h +++ b/arch/nds32/include/asm/tlb.h @@ -4,22 +4,6 @@ #ifndef __ASMNDS32_TLB_H #define __ASMNDS32_TLB_H -#define tlb_start_vma(tlb,vma) \ - do { \ - if (!tlb->fullmm) \ - flush_cache_range(vma, vma->vm_start, vma->vm_end); \ - } while (0) - -#define tlb_end_vma(tlb,vma) \ - do { \ - if(!tlb->fullmm) \ - flush_tlb_range(vma, vma->vm_start, vma->vm_end); \ - } while (0) - -#define __tlb_remove_tlb_entry(tlb, pte, addr) do { } while (0) - -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - #include <asm-generic/tlb.h> #define __pte_free_tlb(tlb, pte, addr) pte_free((tlb)->mm, pte) diff --git a/arch/nds32/include/asm/tlbflush.h b/arch/nds32/include/asm/tlbflush.h index 9b411f401903..38ee769b18d8 100644 --- a/arch/nds32/include/asm/tlbflush.h +++ b/arch/nds32/include/asm/tlbflush.h @@ -42,6 +42,5 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long addr); void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t * pte); -void tlb_migrate_finish(struct mm_struct *mm); #endif diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 4ef15a61b7bc..ea37394ff3ea 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -24,6 +24,7 @@ config NIOS2 select USB_ARCH_HAS_HCD if USB_SUPPORT select CPU_NO_EFFICIENT_FFS select ARCH_DISCARD_MEMBLOCK + select MMU_GATHER_NO_RANGE if MMU config GENERIC_CSUM def_bool y @@ -40,9 +41,6 @@ config NO_IOPORT_MAP config FPU def_bool n -config RWSEM_GENERIC_SPINLOCK - def_bool y - config TRACE_IRQFLAGS_SUPPORT def_bool n diff --git a/arch/nios2/include/asm/tlb.h b/arch/nios2/include/asm/tlb.h index d3bc648e08b5..f9f2e27e32dd 100644 --- a/arch/nios2/include/asm/tlb.h +++ b/arch/nios2/include/asm/tlb.h @@ -11,22 +11,12 @@ #ifndef _ASM_NIOS2_TLB_H #define _ASM_NIOS2_TLB_H -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - extern void set_mmu_pid(unsigned long pid); /* - * NiosII doesn't need any special per-pte or per-vma handling, except - * we need to flush cache for the area to be unmapped. + * NIOS32 does have flush_tlb_range(), but it lacks a limit and fallback to + * full mm invalidation. So use flush_tlb_mm() for everything. */ -#define tlb_start_vma(tlb, vma) \ - do { \ - if (!tlb->fullmm) \ - flush_cache_range(vma, vma->vm_start, vma->vm_end); \ - } while (0) - -#define tlb_end_vma(tlb, vma) do { } while (0) -#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) #include <linux/pagemap.h> #include <asm-generic/tlb.h> diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index a5e361fbb75a..7cfb20555b10 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -36,6 +36,7 @@ config OPENRISC select OMPIC if SMP select ARCH_WANT_FRAME_POINTERS select GENERIC_IRQ_MULTI_HANDLER + select MMU_GATHER_NO_RANGE if MMU config CPU_BIG_ENDIAN def_bool y @@ -43,12 +44,6 @@ config CPU_BIG_ENDIAN config MMU def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - -config RWSEM_XCHGADD_ALGORITHM - def_bool n - config GENERIC_HWEIGHT def_bool y diff --git a/arch/openrisc/include/asm/tlb.h b/arch/openrisc/include/asm/tlb.h index fa4376a4515d..92d8a4209884 100644 --- a/arch/openrisc/include/asm/tlb.h +++ b/arch/openrisc/include/asm/tlb.h @@ -20,14 +20,10 @@ #define __ASM_OPENRISC_TLB_H__ /* - * or32 doesn't need any special per-pte or - * per-vma handling.. + * OpenRISC doesn't have an efficient flush_tlb_range() so use flush_tlb_mm() + * for everything. */ -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) -#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) #include <linux/pagemap.h> #include <asm-generic/tlb.h> diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index c8e621296092..f1ed8ddfe486 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -75,12 +75,6 @@ config GENERIC_LOCKBREAK default y depends on SMP && PREEMPT -config RWSEM_GENERIC_SPINLOCK - def_bool y - -config RWSEM_XCHGADD_ALGORITHM - bool - config ARCH_HAS_ILOG2_U32 bool default n diff --git a/arch/parisc/include/asm/tlb.h b/arch/parisc/include/asm/tlb.h index 0c881e74d8a6..8c0446b04c9e 100644 --- a/arch/parisc/include/asm/tlb.h +++ b/arch/parisc/include/asm/tlb.h @@ -2,24 +2,6 @@ #ifndef _PARISC_TLB_H #define _PARISC_TLB_H -#define tlb_flush(tlb) \ -do { if ((tlb)->fullmm) \ - flush_tlb_mm((tlb)->mm);\ -} while (0) - -#define tlb_start_vma(tlb, vma) \ -do { if (!(tlb)->fullmm) \ - flush_cache_range(vma, vma->vm_start, vma->vm_end); \ -} while (0) - -#define tlb_end_vma(tlb, vma) \ -do { if (!(tlb)->fullmm) \ - flush_tlb_range(vma, vma->vm_start, vma->vm_end); \ -} while (0) - -#define __tlb_remove_tlb_entry(tlb, pte, address) \ - do { } while (0) - #include <asm-generic/tlb.h> #define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd) diff --git a/arch/parisc/kernel/stacktrace.c b/arch/parisc/kernel/stacktrace.c index ec5835e83a7a..6f0b9c8d8052 100644 --- a/arch/parisc/kernel/stacktrace.c +++ b/arch/parisc/kernel/stacktrace.c @@ -29,22 +29,17 @@ static void dump_trace(struct task_struct *task, struct stack_trace *trace) } } - /* * Save stack-backtrace addresses into a stack_trace buffer. */ void save_stack_trace(struct stack_trace *trace) { dump_trace(current, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace); void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { dump_trace(tsk, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index bc98b0e37a10..88a4fb3647a2 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -103,13 +103,6 @@ config LOCKDEP_SUPPORT bool default y -config RWSEM_GENERIC_SPINLOCK - bool - -config RWSEM_XCHGADD_ALGORITHM - bool - default y - config GENERIC_LOCKBREAK bool default y @@ -218,6 +211,8 @@ config PPC select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if SMP + select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE + select HAVE_MMU_GATHER_PAGE_SIZE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN select HAVE_SYSCALL_TRACEPOINTS diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index a0c132bedfae..36bda391e549 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -8,6 +8,5 @@ generic-y += irq_regs.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += preempt.h -generic-y += rwsem.h generic-y += vtime.h generic-y += msi.h diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index e24c67d5ba75..34fba1ce27f7 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -27,8 +27,8 @@ #define tlb_start_vma(tlb, vma) do { } while (0) #define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry __tlb_remove_tlb_entry -#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change +#define tlb_flush tlb_flush extern void tlb_flush(struct mmu_gather *tlb); /* Get the generic bits... */ @@ -46,22 +46,6 @@ static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, #endif } -static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, - unsigned int page_size) -{ - if (!tlb->page_size) - tlb->page_size = page_size; - else if (tlb->page_size != page_size) { - if (!tlb->fullmm) - tlb_flush_mmu(tlb); - /* - * update the page size after flush for the new - * mmu_gather. - */ - tlb->page_size = page_size; - } -} - #ifdef CONFIG_SMP static inline int mm_is_core_local(struct mm_struct *mm) { diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index b33bafb8fcea..70568ccbd9fd 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -57,7 +57,7 @@ void setup_barrier_nospec(void) enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR); - if (!no_nospec) + if (!no_nospec && !cpu_mitigations_off()) enable_barrier_nospec(enable); } @@ -116,7 +116,7 @@ static int __init handle_nospectre_v2(char *p) early_param("nospectre_v2", handle_nospectre_v2); void setup_spectre_v2(void) { - if (no_spectrev2) + if (no_spectrev2 || cpu_mitigations_off()) do_btb_flush_fixups(); else btb_flush_enabled = true; @@ -300,7 +300,7 @@ void setup_stf_barrier(void) stf_enabled_flush_types = type; - if (!no_stf_barrier) + if (!no_stf_barrier && !cpu_mitigations_off()) stf_barrier_enable(enable); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index ba404dd9ce1d..4f49e1a3594c 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -932,7 +932,7 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable) enabled_flush_types = types; - if (!no_rfi_flush) + if (!no_rfi_flush && !cpu_mitigations_off()) rfi_flush_enable(enable); } diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index f02b04973710..f100e331e69b 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -543,14 +543,14 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, if (ret != H_SUCCESS) return ret; + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvmppc_tce_validate(stt, tce); if (ret != H_SUCCESS) - return ret; + goto unlock_exit; dir = iommu_tce_direction(tce); - idx = srcu_read_lock(&vcpu->kvm->srcu); - if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) { ret = H_PARAMETER; goto unlock_exit; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 06964350b97a..b2b29d4f9842 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3423,7 +3423,9 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2); vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3); - mtspr(SPRN_PSSCR, host_psscr); + /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ + mtspr(SPRN_PSSCR, host_psscr | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); mtspr(SPRN_HFSCR, host_hfscr); mtspr(SPRN_CIABR, host_ciabr); mtspr(SPRN_DAWR, host_dawr); diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index f29d2f118b44..5d9c3ff728c9 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -98,10 +98,20 @@ static int find_free_bat(void) return -1; } +/* + * This function calculates the size of the larger block usable to map the + * beginning of an area based on the start address and size of that area: + * - max block size is 8M on 601 and 256 on other 6xx. + * - base address must be aligned to the block size. So the maximum block size + * is identified by the lowest bit set to 1 in the base address (for instance + * if base is 0x16000000, max size is 0x02000000). + * - block size has to be a power of two. This is calculated by finding the + * highest bit set to 1. + */ static unsigned int block_size(unsigned long base, unsigned long top) { unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20; - unsigned int base_shift = (fls(base) - 1) & 31; + unsigned int base_shift = (ffs(base) - 1) & 31; unsigned int block_shift = (fls(top - base) - 1) & 31; return min3(max_size, 1U << base_shift, 1U << block_shift); @@ -157,7 +167,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) { - int done; + unsigned long done; unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET; if (__map_without_bats) { @@ -169,10 +179,10 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) return __mmu_mapin_ram(base, top); done = __mmu_mapin_ram(base, border); - if (done != border - base) + if (done != border) return done; - return done + __mmu_mapin_ram(border, top); + return __mmu_mapin_ram(border, top); } void mmu_mark_initmem_nx(void) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index eb56c82d8aa1..0582260fb6c2 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -69,9 +69,6 @@ config STACKTRACE_SUPPORT config TRACE_IRQFLAGS_SUPPORT def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - config GENERIC_BUG def_bool y depends on BUG diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h index 439dc7072e05..1ad8d093c58b 100644 --- a/arch/riscv/include/asm/tlb.h +++ b/arch/riscv/include/asm/tlb.h @@ -18,6 +18,7 @@ struct mmu_gather; static void tlb_flush(struct mmu_gather *tlb); +#define tlb_flush tlb_flush #include <asm-generic/tlb.h> static inline void tlb_flush(struct mmu_gather *tlb) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index a4b1d94371a0..4d403274c2e8 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -169,8 +169,6 @@ static bool save_trace(unsigned long pc, void *arg) void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { walk_stackframe(tsk, NULL, save_trace, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index b6e3d0653002..97b555e772d7 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -14,12 +14,6 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y -config RWSEM_GENERIC_SPINLOCK - bool - -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config ARCH_HAS_ILOG2_U32 def_bool n @@ -164,11 +158,13 @@ config S390 select HAVE_PERF_USER_STACK_DUMP select HAVE_MEMBLOCK_NODE_MAP select HAVE_MEMBLOCK_PHYS_MAP + select HAVE_MMU_GATHER_NO_GATHER select HAVE_MOD_ARCH_SPECIFIC select HAVE_NOP_MCOUNT select HAVE_OPROFILE select HAVE_PCI select HAVE_PERF_EVENTS + select HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RSEQ select HAVE_SYSCALL_TRACEPOINTS diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 12d77cb11fe5..d5fadefea33c 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -20,7 +20,6 @@ generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += rwsem.h generic-y += trace_clock.h generic-y += unaligned.h generic-y += word-at-a-time.h diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index b31c779cf581..aa406c05a350 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -22,98 +22,39 @@ * Pages used for the page tables is a different story. FIXME: more */ -#include <linux/mm.h> -#include <linux/pagemap.h> -#include <linux/swap.h> -#include <asm/processor.h> -#include <asm/pgalloc.h> -#include <asm/tlbflush.h> - -struct mmu_gather { - struct mm_struct *mm; - struct mmu_table_batch *batch; - unsigned int fullmm; - unsigned long start, end; -}; - -struct mmu_table_batch { - struct rcu_head rcu; - unsigned int nr; - void *tables[0]; -}; - -#define MAX_TABLE_BATCH \ - ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) - -extern void tlb_table_flush(struct mmu_gather *tlb); -extern void tlb_remove_table(struct mmu_gather *tlb, void *table); - -static inline void -arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - tlb->mm = mm; - tlb->start = start; - tlb->end = end; - tlb->fullmm = !(start | (end+1)); - tlb->batch = NULL; -} - -static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) -{ - __tlb_flush_mm_lazy(tlb->mm); -} - -static inline void tlb_flush_mmu_free(struct mmu_gather *tlb) -{ - tlb_table_flush(tlb); -} - +void __tlb_remove_table(void *_table); +static inline void tlb_flush(struct mmu_gather *tlb); +static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size); -static inline void tlb_flush_mmu(struct mmu_gather *tlb) -{ - tlb_flush_mmu_tlbonly(tlb); - tlb_flush_mmu_free(tlb); -} +#define tlb_start_vma(tlb, vma) do { } while (0) +#define tlb_end_vma(tlb, vma) do { } while (0) -static inline void -arch_tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end, bool force) -{ - if (force) { - tlb->start = start; - tlb->end = end; - } +#define tlb_flush tlb_flush +#define pte_free_tlb pte_free_tlb +#define pmd_free_tlb pmd_free_tlb +#define p4d_free_tlb p4d_free_tlb +#define pud_free_tlb pud_free_tlb - tlb_flush_mmu(tlb); -} +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> +#include <asm-generic/tlb.h> /* * Release the page cache reference for a pte removed by * tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page * has already been freed, so just do free_page_and_swap_cache. */ -static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - free_page_and_swap_cache(page); - return false; /* avoid calling tlb_flush_mmu */ -} - -static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - free_page_and_swap_cache(page); -} - static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) { - return __tlb_remove_page(tlb, page); + free_page_and_swap_cache(page); + return false; } -static inline void tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size) +static inline void tlb_flush(struct mmu_gather *tlb) { - return tlb_remove_page(tlb, page); + __tlb_flush_mm_lazy(tlb->mm); } /* @@ -121,8 +62,17 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, * page table from the tlb. */ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, - unsigned long address) + unsigned long address) { + __tlb_adjust_range(tlb, address, PAGE_SIZE); + tlb->mm->context.flush_mm = 1; + tlb->freed_tables = 1; + tlb->cleared_ptes = 1; + /* + * page_table_free_rcu takes care of the allocation bit masks + * of the 2K table fragments in the 4K page table page, + * then calls tlb_remove_table. + */ page_table_free_rcu(tlb, (unsigned long *) pte, address); } @@ -139,6 +89,10 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, if (mm_pmd_folded(tlb->mm)) return; pgtable_pmd_page_dtor(virt_to_page(pmd)); + __tlb_adjust_range(tlb, address, PAGE_SIZE); + tlb->mm->context.flush_mm = 1; + tlb->freed_tables = 1; + tlb->cleared_puds = 1; tlb_remove_table(tlb, pmd); } @@ -154,6 +108,10 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, { if (mm_p4d_folded(tlb->mm)) return; + __tlb_adjust_range(tlb, address, PAGE_SIZE); + tlb->mm->context.flush_mm = 1; + tlb->freed_tables = 1; + tlb->cleared_p4ds = 1; tlb_remove_table(tlb, p4d); } @@ -169,21 +127,11 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, { if (mm_pud_folded(tlb->mm)) return; + tlb->mm->context.flush_mm = 1; + tlb->freed_tables = 1; + tlb->cleared_puds = 1; tlb_remove_table(tlb, pud); } -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) -#define tlb_remove_tlb_entry(tlb, ptep, addr) do { } while (0) -#define tlb_remove_pmd_tlb_entry(tlb, pmdp, addr) do { } while (0) -#define tlb_migrate_finish(mm) do { } while (0) -#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ - tlb_remove_tlb_entry(tlb, ptep, address) - -#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change -static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, - unsigned int page_size) -{ -} #endif /* _S390_TLB_H */ diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c index bdddaae96559..649135cbedd5 100644 --- a/arch/s390/kernel/nospec-branch.c +++ b/arch/s390/kernel/nospec-branch.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> #include <linux/device.h> +#include <linux/cpu.h> #include <asm/nospec-branch.h> static int __init nobp_setup_early(char *str) @@ -58,7 +59,7 @@ early_param("nospectre_v2", nospectre_v2_setup_early); void __init nospec_auto_detect(void) { - if (test_facility(156)) { + if (test_facility(156) || cpu_mitigations_off()) { /* * The machine supports etokens. * Disable expolines and disable nobp. diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 460dcfba7d4e..cc9ed9787068 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -45,8 +45,6 @@ void save_stack_trace(struct stack_trace *trace) sp = current_stack_pointer(); dump_trace(save_address, trace, NULL, sp); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace); @@ -58,8 +56,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) if (tsk == current) sp = current_stack_pointer(); dump_trace(save_address_nosched, trace, tsk, sp); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); @@ -69,7 +65,5 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) sp = kernel_stack_pointer(regs); dump_trace(save_address, trace, NULL, sp); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace_regs); diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index db6bb2f97a2c..99e06213a22b 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -290,7 +290,7 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table, tlb_remove_table(tlb, table); } -static void __tlb_remove_table(void *_table) +void __tlb_remove_table(void *_table) { unsigned int mask = (unsigned long) _table & 3; void *table = (void *)((unsigned long) _table ^ mask); @@ -316,67 +316,6 @@ static void __tlb_remove_table(void *_table) } } -static void tlb_remove_table_smp_sync(void *arg) -{ - /* Simply deliver the interrupt */ -} - -static void tlb_remove_table_one(void *table) -{ - /* - * This isn't an RCU grace period and hence the page-tables cannot be - * assumed to be actually RCU-freed. - * - * It is however sufficient for software page-table walkers that rely - * on IRQ disabling. See the comment near struct mmu_table_batch. - */ - smp_call_function(tlb_remove_table_smp_sync, NULL, 1); - __tlb_remove_table(table); -} - -static void tlb_remove_table_rcu(struct rcu_head *head) -{ - struct mmu_table_batch *batch; - int i; - - batch = container_of(head, struct mmu_table_batch, rcu); - - for (i = 0; i < batch->nr; i++) - __tlb_remove_table(batch->tables[i]); - - free_page((unsigned long)batch); -} - -void tlb_table_flush(struct mmu_gather *tlb) -{ - struct mmu_table_batch **batch = &tlb->batch; - - if (*batch) { - call_rcu(&(*batch)->rcu, tlb_remove_table_rcu); - *batch = NULL; - } -} - -void tlb_remove_table(struct mmu_gather *tlb, void *table) -{ - struct mmu_table_batch **batch = &tlb->batch; - - tlb->mm->context.flush_mm = 1; - if (*batch == NULL) { - *batch = (struct mmu_table_batch *) - __get_free_page(GFP_NOWAIT | __GFP_NOWARN); - if (*batch == NULL) { - __tlb_flush_mm_lazy(tlb->mm); - tlb_remove_table_one(table); - return; - } - (*batch)->nr = 0; - } - (*batch)->tables[(*batch)->nr++] = table; - if ((*batch)->nr == MAX_TABLE_BATCH) - tlb_flush_mmu(tlb); -} - /* * Base infrastructure required to generate basic asces, region, segment, * and page tables that do not make use of enhanced features like EDAT1. diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index b1c91ea9a958..0be08d586d40 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -90,12 +90,6 @@ config ARCH_DEFCONFIG default "arch/sh/configs/shx3_defconfig" if SUPERH32 default "arch/sh/configs/cayman_defconfig" if SUPERH64 -config RWSEM_GENERIC_SPINLOCK - def_bool y - -config RWSEM_XCHGADD_ALGORITHM - bool - config GENERIC_BUG def_bool y depends on BUG && SUPERH32 diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 7bf2cb680d32..73fff39a0122 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -17,7 +17,6 @@ generic-y += mm-arch-hooks.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h -generic-y += rwsem.h generic-y += serial.h generic-y += sizes.h generic-y += trace_clock.h diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index 8ad73cb31121..b56f908b1395 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -70,6 +70,15 @@ do { \ tlb_remove_page((tlb), (pte)); \ } while (0) +#if CONFIG_PGTABLE_LEVELS > 2 +#define __pmd_free_tlb(tlb, pmdp, addr) \ +do { \ + struct page *page = virt_to_page(pmdp); \ + pgtable_pmd_page_dtor(page); \ + tlb_remove_page((tlb), page); \ +} while (0); +#endif + static inline void check_pgt_cache(void) { quicklist_trim(QUICK_PT, NULL, 25, 16); diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h index 77abe192fb43..bc77f3dd4261 100644 --- a/arch/sh/include/asm/tlb.h +++ b/arch/sh/include/asm/tlb.h @@ -11,133 +11,8 @@ #ifdef CONFIG_MMU #include <linux/swap.h> -#include <asm/pgalloc.h> -#include <asm/tlbflush.h> -#include <asm/mmu_context.h> -/* - * TLB handling. This allows us to remove pages from the page - * tables, and efficiently handle the TLB issues. - */ -struct mmu_gather { - struct mm_struct *mm; - unsigned int fullmm; - unsigned long start, end; -}; - -static inline void init_tlb_gather(struct mmu_gather *tlb) -{ - tlb->start = TASK_SIZE; - tlb->end = 0; - - if (tlb->fullmm) { - tlb->start = 0; - tlb->end = TASK_SIZE; - } -} - -static inline void -arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - tlb->mm = mm; - tlb->start = start; - tlb->end = end; - tlb->fullmm = !(start | (end+1)); - - init_tlb_gather(tlb); -} - -static inline void -arch_tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end, bool force) -{ - if (tlb->fullmm || force) - flush_tlb_mm(tlb->mm); - - /* keep the page table cache within bounds */ - check_pgt_cache(); -} - -static inline void -tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address) -{ - if (tlb->start > address) - tlb->start = address; - if (tlb->end < address + PAGE_SIZE) - tlb->end = address + PAGE_SIZE; -} - -#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ - tlb_remove_tlb_entry(tlb, ptep, address) - -/* - * In the case of tlb vma handling, we can optimise these away in the - * case where we're doing a full MM flush. When we're doing a munmap, - * the vmas are adjusted to only cover the region to be torn down. - */ -static inline void -tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) -{ - if (!tlb->fullmm) - flush_cache_range(vma, vma->vm_start, vma->vm_end); -} - -static inline void -tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) -{ - if (!tlb->fullmm && tlb->end) { - flush_tlb_range(vma, tlb->start, tlb->end); - init_tlb_gather(tlb); - } -} - -static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) -{ -} - -static inline void tlb_flush_mmu_free(struct mmu_gather *tlb) -{ -} - -static inline void tlb_flush_mmu(struct mmu_gather *tlb) -{ -} - -static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - free_page_and_swap_cache(page); - return false; /* avoid calling tlb_flush_mmu */ -} - -static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - __tlb_remove_page(tlb, page); -} - -static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size) -{ - return __tlb_remove_page(tlb, page); -} - -static inline void tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size) -{ - return tlb_remove_page(tlb, page); -} - -#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change -static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, - unsigned int page_size) -{ -} - -#define pte_free_tlb(tlb, ptep, addr) pte_free((tlb)->mm, ptep) -#define pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, pmdp) -#define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp) - -#define tlb_migrate_finish(mm) do { } while (0) +#include <asm-generic/tlb.h> #if defined(CONFIG_CPU_SH4) || defined(CONFIG_SUPERH64) extern void tlb_wire_entry(struct vm_area_struct *, unsigned long, pte_t); @@ -157,11 +32,6 @@ static inline void tlb_unwire_entry(void) #else /* CONFIG_MMU */ -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) -#define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0) -#define tlb_flush(tlb) do { } while (0) - #include <asm-generic/tlb.h> #endif /* CONFIG_MMU */ diff --git a/arch/sh/kernel/stacktrace.c b/arch/sh/kernel/stacktrace.c index f3cb2cccb262..2950b19ad077 100644 --- a/arch/sh/kernel/stacktrace.c +++ b/arch/sh/kernel/stacktrace.c @@ -49,8 +49,6 @@ void save_stack_trace(struct stack_trace *trace) unsigned long *sp = (unsigned long *)current_stack_pointer; unwind_stack(current, NULL, sp, &save_stack_ops, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace); @@ -84,7 +82,5 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) unsigned long *sp = (unsigned long *)tsk->thread.sp; unwind_stack(current, NULL, sp, &save_stack_ops_nosched, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 40f8f4f73fe8..f6421c9ce5d3 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -63,6 +63,7 @@ config SPARC64 select HAVE_KRETPROBES select HAVE_KPROBES select HAVE_RCU_TABLE_FREE if SMP + select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE select HAVE_MEMBLOCK_NODE_MAP select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_DYNAMIC_FTRACE @@ -191,14 +192,6 @@ config NR_CPUS source "kernel/Kconfig.hz" -config RWSEM_GENERIC_SPINLOCK - bool - default y if SPARC32 - -config RWSEM_XCHGADD_ALGORITHM - bool - default y if SPARC64 - config GENERIC_HWEIGHT bool default y diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index a22cfd5c0ee8..2ca3200d3616 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -18,7 +18,6 @@ generic-y += mm-arch-hooks.h generic-y += module.h generic-y += msi.h generic-y += preempt.h -generic-y += rwsem.h generic-y += serial.h generic-y += trace_clock.h generic-y += word-at-a-time.h diff --git a/arch/sparc/include/asm/tlb_32.h b/arch/sparc/include/asm/tlb_32.h index 343cea19e573..5cd28a8793e3 100644 --- a/arch/sparc/include/asm/tlb_32.h +++ b/arch/sparc/include/asm/tlb_32.h @@ -2,24 +2,6 @@ #ifndef _SPARC_TLB_H #define _SPARC_TLB_H -#define tlb_start_vma(tlb, vma) \ -do { \ - flush_cache_range(vma, vma->vm_start, vma->vm_end); \ -} while (0) - -#define tlb_end_vma(tlb, vma) \ -do { \ - flush_tlb_range(vma, vma->vm_start, vma->vm_end); \ -} while (0) - -#define __tlb_remove_tlb_entry(tlb, pte, address) \ - do { } while (0) - -#define tlb_flush(tlb) \ -do { \ - flush_tlb_mm((tlb)->mm); \ -} while (0) - #include <asm-generic/tlb.h> #endif /* _SPARC_TLB_H */ diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h index dce6db147f24..70ee60383900 100644 --- a/arch/um/include/asm/tlb.h +++ b/arch/um/include/asm/tlb.h @@ -2,162 +2,8 @@ #ifndef __UM_TLB_H #define __UM_TLB_H -#include <linux/pagemap.h> -#include <linux/swap.h> -#include <asm/percpu.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> - -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - -/* struct mmu_gather is an opaque type used by the mm code for passing around - * any data needed by arch specific code for tlb_remove_page. - */ -struct mmu_gather { - struct mm_struct *mm; - unsigned int need_flush; /* Really unmapped some ptes? */ - unsigned long start; - unsigned long end; - unsigned int fullmm; /* non-zero means full mm flush */ -}; - -static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, - unsigned long address) -{ - if (tlb->start > address) - tlb->start = address; - if (tlb->end < address + PAGE_SIZE) - tlb->end = address + PAGE_SIZE; -} - -static inline void init_tlb_gather(struct mmu_gather *tlb) -{ - tlb->need_flush = 0; - - tlb->start = TASK_SIZE; - tlb->end = 0; - - if (tlb->fullmm) { - tlb->start = 0; - tlb->end = TASK_SIZE; - } -} - -static inline void -arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - tlb->mm = mm; - tlb->start = start; - tlb->end = end; - tlb->fullmm = !(start | (end+1)); - - init_tlb_gather(tlb); -} - -extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, - unsigned long end); - -static inline void -tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) -{ - flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end); -} - -static inline void -tlb_flush_mmu_free(struct mmu_gather *tlb) -{ - init_tlb_gather(tlb); -} - -static inline void -tlb_flush_mmu(struct mmu_gather *tlb) -{ - if (!tlb->need_flush) - return; - - tlb_flush_mmu_tlbonly(tlb); - tlb_flush_mmu_free(tlb); -} - -/* arch_tlb_finish_mmu - * Called at the end of the shootdown operation to free up any resources - * that were required. - */ -static inline void -arch_tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end, bool force) -{ - if (force) { - tlb->start = start; - tlb->end = end; - tlb->need_flush = 1; - } - tlb_flush_mmu(tlb); - - /* keep the page table cache within bounds */ - check_pgt_cache(); -} - -/* tlb_remove_page - * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), - * while handling the additional races in SMP caused by other CPUs - * caching valid mappings in their TLBs. - */ -static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - tlb->need_flush = 1; - free_page_and_swap_cache(page); - return false; /* avoid calling tlb_flush_mmu */ -} - -static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - __tlb_remove_page(tlb, page); -} - -static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size) -{ - return __tlb_remove_page(tlb, page); -} - -static inline void tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size) -{ - return tlb_remove_page(tlb, page); -} - -/** - * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. - * - * Record the fact that pte's were really umapped in ->need_flush, so we can - * later optimise away the tlb invalidate. This helps when userspace is - * unmapping already-unmapped pages, which happens quite a lot. - */ -#define tlb_remove_tlb_entry(tlb, ptep, address) \ - do { \ - tlb->need_flush = 1; \ - __tlb_remove_tlb_entry(tlb, ptep, address); \ - } while (0) - -#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ - tlb_remove_tlb_entry(tlb, ptep, address) - -#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change -static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, - unsigned int page_size) -{ -} - -#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr) - -#define pud_free_tlb(tlb, pudp, addr) __pud_free_tlb(tlb, pudp, addr) - -#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr) - -#define tlb_migrate_finish(mm) do {} while (0) +#include <asm-generic/cacheflush.h> +#include <asm-generic/tlb.h> #endif diff --git a/arch/um/kernel/stacktrace.c b/arch/um/kernel/stacktrace.c index ebe7bcf62684..bd95e020d509 100644 --- a/arch/um/kernel/stacktrace.c +++ b/arch/um/kernel/stacktrace.c @@ -63,8 +63,6 @@ static const struct stacktrace_ops dump_ops = { static void __save_stack_trace(struct task_struct *tsk, struct stack_trace *trace) { dump_trace(tsk, &dump_ops, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } void save_stack_trace(struct stack_trace *trace) diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 817d82608712..2445dfcf6444 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -20,6 +20,7 @@ config UNICORE32 select GENERIC_IOMAP select MODULES_USE_ELF_REL select NEED_DMA_MAP_STATE + select MMU_GATHER_NO_RANGE if MMU help UniCore-32 is 32-bit Instruction Set Architecture, including a series of low-power-consumption RISC chip @@ -38,12 +39,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - -config RWSEM_XCHGADD_ALGORITHM - bool - config ARCH_HAS_ILOG2_U32 bool diff --git a/arch/unicore32/include/asm/tlb.h b/arch/unicore32/include/asm/tlb.h index 9cca15cdae94..00a8477333f6 100644 --- a/arch/unicore32/include/asm/tlb.h +++ b/arch/unicore32/include/asm/tlb.h @@ -12,10 +12,9 @@ #ifndef __UNICORE_TLB_H__ #define __UNICORE_TLB_H__ -#define tlb_start_vma(tlb, vma) do { } while (0) -#define tlb_end_vma(tlb, vma) do { } while (0) -#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) +/* + * unicore32 lacks an efficient flush_tlb_range(), use flush_tlb_mm(). + */ #define __pte_free_tlb(tlb, pte, addr) \ do { \ diff --git a/arch/unicore32/kernel/stacktrace.c b/arch/unicore32/kernel/stacktrace.c index 9976e767d51c..e37da8c6837b 100644 --- a/arch/unicore32/kernel/stacktrace.c +++ b/arch/unicore32/kernel/stacktrace.c @@ -120,8 +120,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) } walk_stackframe(&frame, save_trace, &data); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } void save_stack_trace(struct stack_trace *trace) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 62fc3fda1a05..90e2640ade75 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -74,6 +74,7 @@ config X86 select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO + select ARCH_STACKWALK select ARCH_SUPPORTS_ACPI select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 @@ -183,7 +184,6 @@ config X86 select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if PARAVIRT - select HAVE_RCU_TABLE_INVALIDATE if HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_FUNCTION_ARG_ACCESS_API @@ -268,9 +268,6 @@ config ARCH_MAY_HAVE_PC_FDC def_bool y depends on ISA_DMA_API -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config GENERIC_CALIBRATE_DELAY def_bool y @@ -783,14 +780,6 @@ config PARAVIRT_SPINLOCKS If you are unsure how to answer this question, answer Y. -config QUEUED_LOCK_STAT - bool "Paravirt queued spinlock statistics" - depends on PARAVIRT_SPINLOCKS && DEBUG_FS - ---help--- - Enable the collection of statistical data on the slowpath - behavior of paravirtualized queued spinlocks and report - them on debugfs. - source "arch/x86/xen/Kconfig" config KVM_GUEST diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index d309f30cf7af..5fc76b755510 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -650,6 +650,7 @@ ENTRY(__switch_to_asm) pushl %ebx pushl %edi pushl %esi + pushfl /* switch stack */ movl %esp, TASK_threadsp(%eax) @@ -672,6 +673,7 @@ ENTRY(__switch_to_asm) #endif /* restore callee-saved registers */ + popfl popl %esi popl %edi popl %ebx diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index d45f3fbd232e..f15441b07dad 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -116,6 +116,110 @@ static __initconst const u64 amd_hw_cache_event_ids }, }; +static __initconst const u64 amd_hw_cache_event_ids_f17h + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { +[C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */ + [C(RESULT_MISS)] = 0xc860, /* L2$ access from DC Miss */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */ + [C(RESULT_MISS)] = 0, + }, +}, +[C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches */ + [C(RESULT_MISS)] = 0x0081, /* Instruction cache misses */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, +}, +[C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, +}, +[C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */ + [C(RESULT_MISS)] = 0xf045, /* L2 DTLB misses (PT walks) */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, +}, +[C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */ + [C(RESULT_MISS)] = 0xff85, /* L1 ITLB misses, L2 misses */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, +}, +[C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr. */ + [C(RESULT_MISS)] = 0x00c3, /* Retired Mispredicted BI */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, +}, +[C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, +}, +}; + /* * AMD Performance Monitor K7 and later, up to and including Family 16h: */ @@ -865,9 +969,10 @@ __init int amd_pmu_init(void) x86_pmu.amd_nb_constraints = 0; } - /* Events are common for all AMDs */ - memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, - sizeof(hw_cache_event_ids)); + if (boot_cpu_data.x86 >= 0x17) + memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids)); + else + memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids)); return 0; } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 81911e11a15d..f315425d8468 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -560,6 +560,21 @@ int x86_pmu_hw_config(struct perf_event *event) return -EINVAL; } + /* sample_regs_user never support XMM registers */ + if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS)) + return -EINVAL; + /* + * Besides the general purpose registers, XMM registers may + * be collected in PEBS on some platforms, e.g. Icelake + */ + if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) { + if (x86_pmu.pebs_no_xmm_regs) + return -EINVAL; + + if (!event->attr.precise_ip) + return -EINVAL; + } + return x86_setup_perfctr(event); } @@ -661,6 +676,10 @@ static inline int is_x86_event(struct perf_event *event) return event->pmu == &pmu; } +struct pmu *x86_get_pmu(void) +{ + return &pmu; +} /* * Event scheduler state: * @@ -849,18 +868,43 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) struct event_constraint *c; unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; struct perf_event *e; - int i, wmin, wmax, unsched = 0; + int n0, i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; bitmap_zero(used_mask, X86_PMC_IDX_MAX); + /* + * Compute the number of events already present; see x86_pmu_add(), + * validate_group() and x86_pmu_commit_txn(). For the former two + * cpuc->n_events hasn't been updated yet, while for the latter + * cpuc->n_txn contains the number of events added in the current + * transaction. + */ + n0 = cpuc->n_events; + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) + n0 -= cpuc->n_txn; + if (x86_pmu.start_scheduling) x86_pmu.start_scheduling(cpuc); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { - cpuc->event_constraint[i] = NULL; - c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); - cpuc->event_constraint[i] = c; + c = cpuc->event_constraint[i]; + + /* + * Previously scheduled events should have a cached constraint, + * while new events should not have one. + */ + WARN_ON_ONCE((c && i >= n0) || (!c && i < n0)); + + /* + * Request constraints for new events; or for those events that + * have a dynamic constraint -- for those the constraint can + * change due to external factors (sibling state, allow_tfa). + */ + if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) { + c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); + cpuc->event_constraint[i] = c; + } wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); @@ -925,25 +969,20 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (!unsched && assign) { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; - e->hw.flags |= PERF_X86_EVENT_COMMITTED; if (x86_pmu.commit_scheduling) x86_pmu.commit_scheduling(cpuc, i, assign[i]); } } else { - for (i = 0; i < n; i++) { + for (i = n0; i < n; i++) { e = cpuc->event_list[i]; - /* - * do not put_constraint() on comitted events, - * because they are good to go - */ - if ((e->hw.flags & PERF_X86_EVENT_COMMITTED)) - continue; /* * release events that failed scheduling */ if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, e); + + cpuc->event_constraint[i] = NULL; } } @@ -1373,11 +1412,6 @@ static void x86_pmu_del(struct perf_event *event, int flags) int i; /* - * event is descheduled - */ - event->hw.flags &= ~PERF_X86_EVENT_COMMITTED; - - /* * If we're called during a txn, we only need to undo x86_pmu.add. * The events never got scheduled and ->cancel_txn will truncate * the event_list. @@ -1413,6 +1447,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; } + cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; perf_event_update_userpage(event); @@ -2024,7 +2059,7 @@ static int validate_event(struct perf_event *event) if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); - c = x86_pmu.get_event_constraints(fake_cpuc, -1, event); + c = x86_pmu.get_event_constraints(fake_cpuc, 0, event); if (!c || !c->weight) ret = -EINVAL; @@ -2072,8 +2107,7 @@ static int validate_group(struct perf_event *event) if (n < 0) goto out; - fake_cpuc->n_events = n; - + fake_cpuc->n_events = 0; ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); out: @@ -2348,6 +2382,15 @@ void arch_perf_update_userpage(struct perf_event *event, cyc2ns_read_end(); } +/* + * Determine whether the regs were taken from an irq/exception handler rather + * than from perf_arch_fetch_caller_regs(). + */ +static bool perf_hw_regs(struct pt_regs *regs) +{ + return regs->flags & X86_EFLAGS_FIXED; +} + void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { @@ -2359,11 +2402,15 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re return; } - if (perf_callchain_store(entry, regs->ip)) - return; + if (perf_hw_regs(regs)) { + if (perf_callchain_store(entry, regs->ip)) + return; + unwind_start(&state, current, regs, NULL); + } else { + unwind_start(&state, current, NULL, (void *)regs->sp); + } - for (unwind_start(&state, current, regs, NULL); !unwind_done(&state); - unwind_next_frame(&state)) { + for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || perf_callchain_store(entry, addr)) return; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index f9451566cd9b..ef763f535e3a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -239,6 +239,35 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +static struct event_constraint intel_icl_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ + INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf), + INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */ + INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf), + INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */ + INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.STALLS_MEM_ANY */ + INTEL_EVENT_CONSTRAINT(0xa3, 0xf), /* CYCLE_ACTIVITY.* */ + INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg intel_icl_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + EVENT_EXTRA_END +}; + EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); @@ -1827,6 +1856,45 @@ static __initconst const u64 glp_hw_cache_extra_regs }, }; +#define TNT_LOCAL_DRAM BIT_ULL(26) +#define TNT_DEMAND_READ GLM_DEMAND_DATA_RD +#define TNT_DEMAND_WRITE GLM_DEMAND_RFO +#define TNT_LLC_ACCESS GLM_ANY_RESPONSE +#define TNT_SNP_ANY (SNB_SNP_NOT_NEEDED|SNB_SNP_MISS| \ + SNB_NO_FWD|SNB_SNP_FWD|SNB_HITM) +#define TNT_LLC_MISS (TNT_SNP_ANY|SNB_NON_DRAM|TNT_LOCAL_DRAM) + +static __initconst const u64 tnt_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = TNT_DEMAND_READ| + TNT_LLC_ACCESS, + [C(RESULT_MISS)] = TNT_DEMAND_READ| + TNT_LLC_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = TNT_DEMAND_WRITE| + TNT_LLC_ACCESS, + [C(RESULT_MISS)] = TNT_DEMAND_WRITE| + TNT_LLC_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, +}; + +static struct extra_reg intel_tnt_extra_regs[] __read_mostly = { + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1), + EVENT_EXTRA_END +}; + #define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ #define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ #define KNL_MCDRAM_LOCAL BIT_ULL(21) @@ -2015,7 +2083,7 @@ static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int /* * We're going to use PMC3, make sure TFA is set before we touch it. */ - if (cntr == 3 && !cpuc->is_fake) + if (cntr == 3) intel_set_tfa(cpuc, true); } @@ -2091,15 +2159,19 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); cpuc->intel_cp_status &= ~(1ull << hwc->idx); - if (unlikely(event->attr.precise_ip)) - intel_pmu_pebs_disable(event); - if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_disable_fixed(hwc); return; } x86_pmu_disable_event(event); + + /* + * Needs to be called after x86_pmu_disable_event, + * so we don't trigger the event without PEBS bit set. + */ + if (unlikely(event->attr.precise_ip)) + intel_pmu_pebs_disable(event); } static void intel_pmu_del_event(struct perf_event *event) @@ -2145,6 +2217,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event) bits <<= (idx * 4); mask = 0xfULL << (idx * 4); + if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) { + bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4); + mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4); + } + rdmsrl(hwc->config_base, ctrl_val); ctrl_val &= ~mask; ctrl_val |= bits; @@ -2688,7 +2765,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx, if (x86_pmu.event_constraints) { for_each_event_constraint(c, x86_pmu.event_constraints) { - if ((event->hw.config & c->cmask) == c->code) { + if (constraint_match(c, event->hw.config)) { event->hw.flags |= c->flags; return c; } @@ -2838,7 +2915,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; struct intel_excl_states *xlo; int tid = cpuc->excl_thread_id; - int is_excl, i; + int is_excl, i, w; /* * validating a group does not require @@ -2894,36 +2971,40 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * SHARED : sibling counter measuring non-exclusive event * UNUSED : sibling counter unused */ + w = c->weight; for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) { /* * exclusive event in sibling counter * our corresponding counter cannot be used * regardless of our event */ - if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) + if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) { __clear_bit(i, c->idxmsk); + w--; + continue; + } /* * if measuring an exclusive event, sibling * measuring non-exclusive, then counter cannot * be used */ - if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) + if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) { __clear_bit(i, c->idxmsk); + w--; + continue; + } } /* - * recompute actual bit weight for scheduling algorithm - */ - c->weight = hweight64(c->idxmsk64); - - /* * if we return an empty mask, then switch * back to static empty constraint to avoid * the cost of freeing later on */ - if (c->weight == 0) + if (!w) c = &emptyconstraint; + c->weight = w; + return c; } @@ -2931,11 +3012,9 @@ static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { - struct event_constraint *c1 = NULL; - struct event_constraint *c2; + struct event_constraint *c1, *c2; - if (idx >= 0) /* fake does < 0 */ - c1 = cpuc->event_constraint[idx]; + c1 = cpuc->event_constraint[idx]; /* * first time only @@ -2943,7 +3022,8 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, * - dynamic constraint: handled by intel_get_excl_constraints() */ c2 = __intel_get_event_constraints(cpuc, idx, event); - if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) { + if (c1) { + WARN_ON_ONCE(!(c1->flags & PERF_X86_EVENT_DYNAMIC)); bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX); c1->weight = c2->weight; c2 = c1; @@ -3366,6 +3446,12 @@ static struct event_constraint counter0_constraint = static struct event_constraint counter2_constraint = EVENT_CONSTRAINT(0, 0x4, 0); +static struct event_constraint fixed0_constraint = + FIXED_EVENT_CONSTRAINT(0x00c0, 0); + +static struct event_constraint fixed0_counter0_constraint = + INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000001ULL); + static struct event_constraint * hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -3385,6 +3471,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, } static struct event_constraint * +icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + /* + * Fixed counter 0 has less skid. + * Force instruction:ppp in Fixed counter 0 + */ + if ((event->attr.precise_ip == 3) && + constraint_match(&fixed0_constraint, event->hw.config)) + return &fixed0_constraint; + + return hsw_get_event_constraints(cpuc, idx, event); +} + +static struct event_constraint * glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { @@ -3399,6 +3500,29 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, return c; } +static struct event_constraint * +tnt_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c; + + /* + * :ppp means to do reduced skid PEBS, + * which is available on PMC0 and fixed counter 0. + */ + if (event->attr.precise_ip == 3) { + /* Force instruction:ppp on PMC0 and Fixed counter 0 */ + if (constraint_match(&fixed0_constraint, event->hw.config)) + return &fixed0_counter0_constraint; + + return &counter0_constraint; + } + + c = intel_get_event_constraints(cpuc, idx, event); + + return c; +} + static bool allow_tsx_force_abort = true; static struct event_constraint * @@ -3410,7 +3534,7 @@ tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx, /* * Without TFA we must not use PMC3. */ - if (!allow_tsx_force_abort && test_bit(3, c->idxmsk) && idx >= 0) { + if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) { c = dyn_constraint(cpuc, c, idx); c->idxmsk64 &= ~(1ULL << 3); c->weight--; @@ -3507,6 +3631,8 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) { + cpuc->pebs_record_size = x86_pmu.pebs_record_size; + if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) @@ -4114,6 +4240,42 @@ static struct attribute *hsw_tsx_events_attrs[] = { NULL }; +EVENT_ATTR_STR(tx-capacity-read, tx_capacity_read, "event=0x54,umask=0x80"); +EVENT_ATTR_STR(tx-capacity-write, tx_capacity_write, "event=0x54,umask=0x2"); +EVENT_ATTR_STR(el-capacity-read, el_capacity_read, "event=0x54,umask=0x80"); +EVENT_ATTR_STR(el-capacity-write, el_capacity_write, "event=0x54,umask=0x2"); + +static struct attribute *icl_events_attrs[] = { + EVENT_PTR(mem_ld_hsw), + EVENT_PTR(mem_st_hsw), + NULL, +}; + +static struct attribute *icl_tsx_events_attrs[] = { + EVENT_PTR(tx_start), + EVENT_PTR(tx_abort), + EVENT_PTR(tx_commit), + EVENT_PTR(tx_capacity_read), + EVENT_PTR(tx_capacity_write), + EVENT_PTR(tx_conflict), + EVENT_PTR(el_start), + EVENT_PTR(el_abort), + EVENT_PTR(el_commit), + EVENT_PTR(el_capacity_read), + EVENT_PTR(el_capacity_write), + EVENT_PTR(el_conflict), + EVENT_PTR(cycles_t), + EVENT_PTR(cycles_ct), + NULL, +}; + +static __init struct attribute **get_icl_events_attrs(void) +{ + return boot_cpu_has(X86_FEATURE_RTM) ? + merge_attr(icl_events_attrs, icl_tsx_events_attrs) : + icl_events_attrs; +} + static ssize_t freeze_on_smi_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -4153,6 +4315,50 @@ done: return count; } +static void update_tfa_sched(void *ignored) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + /* + * check if PMC3 is used + * and if so force schedule out for all event types all contexts + */ + if (test_bit(3, cpuc->active_mask)) + perf_pmu_resched(x86_get_pmu()); +} + +static ssize_t show_sysctl_tfa(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, 40, "%d\n", allow_tsx_force_abort); +} + +static ssize_t set_sysctl_tfa(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + bool val; + ssize_t ret; + + ret = kstrtobool(buf, &val); + if (ret) + return ret; + + /* no change */ + if (val == allow_tsx_force_abort) + return count; + + allow_tsx_force_abort = val; + + get_online_cpus(); + on_each_cpu(update_tfa_sched, NULL, 1); + put_online_cpus(); + + return count; +} + + static DEVICE_ATTR_RW(freeze_on_smi); static ssize_t branches_show(struct device *cdev, @@ -4185,7 +4391,9 @@ static struct attribute *intel_pmu_caps_attrs[] = { NULL }; -static DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort); +static DEVICE_ATTR(allow_tsx_force_abort, 0644, + show_sysctl_tfa, + set_sysctl_tfa); static struct attribute *intel_pmu_attrs[] = { &dev_attr_freeze_on_smi.attr, @@ -4446,6 +4654,32 @@ __init int intel_pmu_init(void) name = "goldmont_plus"; break; + case INTEL_FAM6_ATOM_TREMONT_X: + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.extra_regs = intel_tnt_extra_regs; + /* + * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS + * for precise cycles. + */ + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.get_event_constraints = tnt_get_event_constraints; + extra_attr = slm_format_attr; + pr_cont("Tremont events, "); + name = "Tremont"; + break; + case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: @@ -4694,13 +4928,41 @@ __init int intel_pmu_init(void) x86_pmu.get_event_constraints = tfa_get_event_constraints; x86_pmu.enable_all = intel_tfa_pmu_enable_all; x86_pmu.commit_scheduling = intel_tfa_commit_scheduling; - intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr; + intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr; } pr_cont("Skylake events, "); name = "skylake"; break; + case INTEL_FAM6_ICELAKE_MOBILE: + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_icl_event_constraints; + x86_pmu.pebs_constraints = intel_icl_pebs_event_constraints; + x86_pmu.extra_regs = intel_icl_extra_regs; + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = icl_get_event_constraints; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; + extra_attr = merge_attr(extra_attr, skl_format_attr); + x86_pmu.cpu_events = get_icl_events_attrs(); + x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02); + x86_pmu.lbr_pt_coexist = true; + intel_pmu_pebs_data_source_skl(false); + pr_cont("Icelake events, "); + name = "icelake"; + break; + default: switch (x86_pmu.version) { case 1: diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index d41de9af7a39..6072f92cb8ea 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -578,6 +578,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 10c99ce1fead..7a9f5dac5abe 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -849,6 +849,26 @@ struct event_constraint intel_skl_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_icl_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */ + + INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */ + + INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + + /* + * Everything else is handled by PMU_FL_PEBS_ALL, because we + * need the full constraints from the main table. + */ + + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -858,7 +878,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) if (x86_pmu.pebs_constraints) { for_each_event_constraint(c, x86_pmu.pebs_constraints) { - if ((event->hw.config & c->cmask) == c->code) { + if (constraint_match(c, event->hw.config)) { event->hw.flags |= c->flags; return c; } @@ -906,17 +926,87 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) if (cpuc->n_pebs == cpuc->n_large_pebs) { threshold = ds->pebs_absolute_maximum - - reserved * x86_pmu.pebs_record_size; + reserved * cpuc->pebs_record_size; } else { - threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; + threshold = ds->pebs_buffer_base + cpuc->pebs_record_size; } ds->pebs_interrupt_threshold = threshold; } +static void adaptive_pebs_record_size_update(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 pebs_data_cfg = cpuc->pebs_data_cfg; + int sz = sizeof(struct pebs_basic); + + if (pebs_data_cfg & PEBS_DATACFG_MEMINFO) + sz += sizeof(struct pebs_meminfo); + if (pebs_data_cfg & PEBS_DATACFG_GP) + sz += sizeof(struct pebs_gprs); + if (pebs_data_cfg & PEBS_DATACFG_XMMS) + sz += sizeof(struct pebs_xmm); + if (pebs_data_cfg & PEBS_DATACFG_LBRS) + sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry); + + cpuc->pebs_record_size = sz; +} + +#define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \ + PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \ + PERF_SAMPLE_TRANSACTION) + +static u64 pebs_update_adaptive_cfg(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + u64 sample_type = attr->sample_type; + u64 pebs_data_cfg = 0; + bool gprs, tsx_weight; + + if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) && + attr->precise_ip > 1) + return pebs_data_cfg; + + if (sample_type & PERF_PEBS_MEMINFO_TYPE) + pebs_data_cfg |= PEBS_DATACFG_MEMINFO; + + /* + * We need GPRs when: + * + user requested them + * + precise_ip < 2 for the non event IP + * + For RTM TSX weight we need GPRs for the abort code. + */ + gprs = (sample_type & PERF_SAMPLE_REGS_INTR) && + (attr->sample_regs_intr & PEBS_GP_REGS); + + tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) && + ((attr->config & INTEL_ARCH_EVENT_MASK) == + x86_pmu.rtm_abort_event); + + if (gprs || (attr->precise_ip < 2) || tsx_weight) + pebs_data_cfg |= PEBS_DATACFG_GP; + + if ((sample_type & PERF_SAMPLE_REGS_INTR) && + (attr->sample_regs_intr & PEBS_XMM_REGS)) + pebs_data_cfg |= PEBS_DATACFG_XMMS; + + if (sample_type & PERF_SAMPLE_BRANCH_STACK) { + /* + * For now always log all LBRs. Could configure this + * later. + */ + pebs_data_cfg |= PEBS_DATACFG_LBRS | + ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT); + } + + return pebs_data_cfg; +} + static void -pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu) +pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, + struct perf_event *event, bool add) { + struct pmu *pmu = event->ctx->pmu; /* * Make sure we get updated with the first PEBS * event. It will trigger also during removal, but @@ -933,6 +1023,29 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu) update = true; } + /* + * The PEBS record doesn't shrink on pmu::del(). Doing so would require + * iterating all remaining PEBS events to reconstruct the config. + */ + if (x86_pmu.intel_cap.pebs_baseline && add) { + u64 pebs_data_cfg; + + /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */ + if (cpuc->n_pebs == 1) { + cpuc->pebs_data_cfg = 0; + cpuc->pebs_record_size = sizeof(struct pebs_basic); + } + + pebs_data_cfg = pebs_update_adaptive_cfg(event); + + /* Update pebs_record_size if new event requires more data. */ + if (pebs_data_cfg & ~cpuc->pebs_data_cfg) { + cpuc->pebs_data_cfg |= pebs_data_cfg; + adaptive_pebs_record_size_update(); + update = true; + } + } + if (update) pebs_update_threshold(cpuc); } @@ -947,7 +1060,7 @@ void intel_pmu_pebs_add(struct perf_event *event) if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs++; - pebs_update_state(needed_cb, cpuc, event->ctx->pmu); + pebs_update_state(needed_cb, cpuc, event, true); } void intel_pmu_pebs_enable(struct perf_event *event) @@ -960,11 +1073,19 @@ void intel_pmu_pebs_enable(struct perf_event *event) cpuc->pebs_enabled |= 1ULL << hwc->idx; - if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) + if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5)) cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled |= 1ULL << 63; + if (x86_pmu.intel_cap.pebs_baseline) { + hwc->config |= ICL_EVENTSEL_ADAPTIVE; + if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) { + wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg); + cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg; + } + } + /* * Use auto-reload if possible to save a MSR write in the PMI. * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD. @@ -991,7 +1112,7 @@ void intel_pmu_pebs_del(struct perf_event *event) if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs--; - pebs_update_state(needed_cb, cpuc, event->ctx->pmu); + pebs_update_state(needed_cb, cpuc, event, false); } void intel_pmu_pebs_disable(struct perf_event *event) @@ -1004,7 +1125,8 @@ void intel_pmu_pebs_disable(struct perf_event *event) cpuc->pebs_enabled &= ~(1ULL << hwc->idx); - if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) + if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && + (x86_pmu.version < 5)) cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32)); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled &= ~(1ULL << 63); @@ -1125,34 +1247,57 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 0; } -static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs) +static inline u64 intel_get_tsx_weight(u64 tsx_tuning) { - if (pebs->tsx_tuning) { - union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning }; + if (tsx_tuning) { + union hsw_tsx_tuning tsx = { .value = tsx_tuning }; return tsx.cycles_last_block; } return 0; } -static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs) +static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax) { - u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32; + u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32; /* For RTM XABORTs also log the abort code from AX */ - if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1)) - txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT; + if ((txn & PERF_TXN_TRANSACTION) && (ax & 1)) + txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT; return txn; } -static void setup_pebs_sample_data(struct perf_event *event, - struct pt_regs *iregs, void *__pebs, - struct perf_sample_data *data, - struct pt_regs *regs) +static inline u64 get_pebs_status(void *n) { + if (x86_pmu.intel_cap.pebs_format < 4) + return ((struct pebs_record_nhm *)n)->status; + return ((struct pebs_basic *)n)->applicable_counters; +} + #define PERF_X86_EVENT_PEBS_HSW_PREC \ (PERF_X86_EVENT_PEBS_ST_HSW | \ PERF_X86_EVENT_PEBS_LD_HSW | \ PERF_X86_EVENT_PEBS_NA_HSW) + +static u64 get_data_src(struct perf_event *event, u64 aux) +{ + u64 val = PERF_MEM_NA; + int fl = event->hw.flags; + bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); + + if (fl & PERF_X86_EVENT_PEBS_LDLAT) + val = load_latency_data(aux); + else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) + val = precise_datala_hsw(event, aux); + else if (fst) + val = precise_store_data(aux); + return val; +} + +static void setup_pebs_fixed_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) +{ /* * We cast to the biggest pebs_record but are careful not to * unconditionally access the 'extra' entries. @@ -1160,17 +1305,13 @@ static void setup_pebs_sample_data(struct perf_event *event, struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_record_skl *pebs = __pebs; u64 sample_type; - int fll, fst, dsrc; - int fl = event->hw.flags; + int fll; if (pebs == NULL) return; sample_type = event->attr.sample_type; - dsrc = sample_type & PERF_SAMPLE_DATA_SRC; - - fll = fl & PERF_X86_EVENT_PEBS_LDLAT; - fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); + fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT; perf_sample_data_init(data, 0, event->hw.last_period); @@ -1185,16 +1326,8 @@ static void setup_pebs_sample_data(struct perf_event *event, /* * data.data_src encodes the data source */ - if (dsrc) { - u64 val = PERF_MEM_NA; - if (fll) - val = load_latency_data(pebs->dse); - else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) - val = precise_datala_hsw(event, pebs->dse); - else if (fst) - val = precise_store_data(pebs->dse); - data->data_src.val = val; - } + if (sample_type & PERF_SAMPLE_DATA_SRC) + data->data_src.val = get_data_src(event, pebs->dse); /* * We must however always use iregs for the unwinder to stay sane; the @@ -1281,10 +1414,11 @@ static void setup_pebs_sample_data(struct perf_event *event, if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) - data->weight = intel_hsw_weight(pebs); + data->weight = intel_get_tsx_weight(pebs->tsx_tuning); if (sample_type & PERF_SAMPLE_TRANSACTION) - data->txn = intel_hsw_transaction(pebs); + data->txn = intel_get_tsx_transaction(pebs->tsx_tuning, + pebs->ax); } /* @@ -1301,6 +1435,140 @@ static void setup_pebs_sample_data(struct perf_event *event, data->br_stack = &cpuc->lbr_stack; } +static void adaptive_pebs_save_regs(struct pt_regs *regs, + struct pebs_gprs *gprs) +{ + regs->ax = gprs->ax; + regs->bx = gprs->bx; + regs->cx = gprs->cx; + regs->dx = gprs->dx; + regs->si = gprs->si; + regs->di = gprs->di; + regs->bp = gprs->bp; + regs->sp = gprs->sp; +#ifndef CONFIG_X86_32 + regs->r8 = gprs->r8; + regs->r9 = gprs->r9; + regs->r10 = gprs->r10; + regs->r11 = gprs->r11; + regs->r12 = gprs->r12; + regs->r13 = gprs->r13; + regs->r14 = gprs->r14; + regs->r15 = gprs->r15; +#endif +} + +/* + * With adaptive PEBS the layout depends on what fields are configured. + */ + +static void setup_pebs_adaptive_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct pebs_basic *basic = __pebs; + void *next_record = basic + 1; + u64 sample_type; + u64 format_size; + struct pebs_meminfo *meminfo = NULL; + struct pebs_gprs *gprs = NULL; + struct x86_perf_regs *perf_regs; + + if (basic == NULL) + return; + + perf_regs = container_of(regs, struct x86_perf_regs, regs); + perf_regs->xmm_regs = NULL; + + sample_type = event->attr.sample_type; + format_size = basic->format_size; + perf_sample_data_init(data, 0, event->hw.last_period); + data->period = event->hw.last_period; + + if (event->attr.use_clockid == 0) + data->time = native_sched_clock_from_tsc(basic->tsc); + + /* + * We must however always use iregs for the unwinder to stay sane; the + * record BP,SP,IP can point into thin air when the record is from a + * previous PMI context or an (I)RET happened between the record and + * PMI. + */ + if (sample_type & PERF_SAMPLE_CALLCHAIN) + data->callchain = perf_callchain(event, iregs); + + *regs = *iregs; + /* The ip in basic is EventingIP */ + set_linear_ip(regs, basic->ip); + regs->flags = PERF_EFLAGS_EXACT; + + /* + * The record for MEMINFO is in front of GP + * But PERF_SAMPLE_TRANSACTION needs gprs->ax. + * Save the pointer here but process later. + */ + if (format_size & PEBS_DATACFG_MEMINFO) { + meminfo = next_record; + next_record = meminfo + 1; + } + + if (format_size & PEBS_DATACFG_GP) { + gprs = next_record; + next_record = gprs + 1; + + if (event->attr.precise_ip < 2) { + set_linear_ip(regs, gprs->ip); + regs->flags &= ~PERF_EFLAGS_EXACT; + } + + if (sample_type & PERF_SAMPLE_REGS_INTR) + adaptive_pebs_save_regs(regs, gprs); + } + + if (format_size & PEBS_DATACFG_MEMINFO) { + if (sample_type & PERF_SAMPLE_WEIGHT) + data->weight = meminfo->latency ?: + intel_get_tsx_weight(meminfo->tsx_tuning); + + if (sample_type & PERF_SAMPLE_DATA_SRC) + data->data_src.val = get_data_src(event, meminfo->aux); + + if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) + data->addr = meminfo->address; + + if (sample_type & PERF_SAMPLE_TRANSACTION) + data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning, + gprs ? gprs->ax : 0); + } + + if (format_size & PEBS_DATACFG_XMMS) { + struct pebs_xmm *xmm = next_record; + + next_record = xmm + 1; + perf_regs->xmm_regs = xmm->xmm; + } + + if (format_size & PEBS_DATACFG_LBRS) { + struct pebs_lbr *lbr = next_record; + int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT) + & 0xff) + 1; + next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry); + + if (has_branch_stack(event)) { + intel_pmu_store_pebs_lbrs(lbr); + data->br_stack = &cpuc->lbr_stack; + } + } + + WARN_ONCE(next_record != __pebs + (format_size >> 48), + "PEBS record size %llu, expected %llu, config %llx\n", + format_size >> 48, + (u64)(next_record - __pebs), + basic->format_size); +} + static inline void * get_next_pebs_record_by_bit(void *base, void *top, int bit) { @@ -1318,19 +1586,19 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) if (base == NULL) return NULL; - for (at = base; at < top; at += x86_pmu.pebs_record_size) { - struct pebs_record_nhm *p = at; + for (at = base; at < top; at += cpuc->pebs_record_size) { + unsigned long status = get_pebs_status(at); - if (test_bit(bit, (unsigned long *)&p->status)) { + if (test_bit(bit, (unsigned long *)&status)) { /* PEBS v3 has accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) return at; - if (p->status == (1 << bit)) + if (status == (1 << bit)) return at; /* clear non-PEBS bit and re-check */ - pebs_status = p->status & cpuc->pebs_enabled; + pebs_status = status & cpuc->pebs_enabled; pebs_status &= PEBS_COUNTER_MASK; if (pebs_status == (1 << bit)) return at; @@ -1410,11 +1678,18 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *base, void *top, - int bit, int count) + int bit, int count, + void (*setup_sample)(struct perf_event *, + struct pt_regs *, + void *, + struct perf_sample_data *, + struct pt_regs *)) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; struct perf_sample_data data; - struct pt_regs regs; + struct x86_perf_regs perf_regs; + struct pt_regs *regs = &perf_regs.regs; void *at = get_next_pebs_record_by_bit(base, top, bit); if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { @@ -1429,20 +1704,20 @@ static void __intel_pmu_pebs_event(struct perf_event *event, return; while (count > 1) { - setup_pebs_sample_data(event, iregs, at, &data, ®s); - perf_event_output(event, &data, ®s); - at += x86_pmu.pebs_record_size; + setup_sample(event, iregs, at, &data, regs); + perf_event_output(event, &data, regs); + at += cpuc->pebs_record_size; at = get_next_pebs_record_by_bit(at, top, bit); count--; } - setup_pebs_sample_data(event, iregs, at, &data, ®s); + setup_sample(event, iregs, at, &data, regs); /* * All but the last records are processed. * The last one is left to be able to call the overflow handler. */ - if (perf_event_overflow(event, &data, ®s)) { + if (perf_event_overflow(event, &data, regs)) { x86_pmu_stop(event, 0); return; } @@ -1483,7 +1758,27 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) return; } - __intel_pmu_pebs_event(event, iregs, at, top, 0, n); + __intel_pmu_pebs_event(event, iregs, at, top, 0, n, + setup_pebs_fixed_sample_data); +} + +static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size) +{ + struct perf_event *event; + int bit; + + /* + * The drain_pebs() could be called twice in a short period + * for auto-reload event in pmu::read(). There are no + * overflows have happened in between. + * It needs to call intel_pmu_save_and_restart_reload() to + * update the event->count for this case. + */ + for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) { + event = cpuc->events[bit]; + if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) + intel_pmu_save_and_restart_reload(event, 0); + } } static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) @@ -1513,19 +1808,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) } if (unlikely(base >= top)) { - /* - * The drain_pebs() could be called twice in a short period - * for auto-reload event in pmu::read(). There are no - * overflows have happened in between. - * It needs to call intel_pmu_save_and_restart_reload() to - * update the event->count for this case. - */ - for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, - size) { - event = cpuc->events[bit]; - if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) - intel_pmu_save_and_restart_reload(event, 0); - } + intel_pmu_pebs_event_update_no_drain(cpuc, size); return; } @@ -1538,8 +1821,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) /* PEBS v3 has more accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) { - for_each_set_bit(bit, (unsigned long *)&pebs_status, - size) + for_each_set_bit(bit, (unsigned long *)&pebs_status, size) counts[bit]++; continue; @@ -1578,8 +1860,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * If collision happened, the record will be dropped. */ if (p->status != (1ULL << bit)) { - for_each_set_bit(i, (unsigned long *)&pebs_status, - x86_pmu.max_pebs_events) + for_each_set_bit(i, (unsigned long *)&pebs_status, size) error[i]++; continue; } @@ -1587,7 +1868,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) counts[bit]++; } - for (bit = 0; bit < size; bit++) { + for_each_set_bit(bit, (unsigned long *)&mask, size) { if ((counts[bit] == 0) && (error[bit] == 0)) continue; @@ -1608,11 +1889,66 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) if (counts[bit]) { __intel_pmu_pebs_event(event, iregs, base, - top, bit, counts[bit]); + top, bit, counts[bit], + setup_pebs_fixed_sample_data); } } } +static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) +{ + short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct perf_event *event; + void *base, *at, *top; + int bit, size; + u64 mask; + + if (!x86_pmu.pebs_active) + return; + + base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_basic *)(unsigned long)ds->pebs_index; + + ds->pebs_index = ds->pebs_buffer_base; + + mask = ((1ULL << x86_pmu.max_pebs_events) - 1) | + (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED); + size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed; + + if (unlikely(base >= top)) { + intel_pmu_pebs_event_update_no_drain(cpuc, size); + return; + } + + for (at = base; at < top; at += cpuc->pebs_record_size) { + u64 pebs_status; + + pebs_status = get_pebs_status(at) & cpuc->pebs_enabled; + pebs_status &= mask; + + for_each_set_bit(bit, (unsigned long *)&pebs_status, size) + counts[bit]++; + } + + for_each_set_bit(bit, (unsigned long *)&mask, size) { + if (counts[bit] == 0) + continue; + + event = cpuc->events[bit]; + if (WARN_ON_ONCE(!event)) + continue; + + if (WARN_ON_ONCE(!event->attr.precise_ip)) + continue; + + __intel_pmu_pebs_event(event, iregs, base, + top, bit, counts[bit], + setup_pebs_adaptive_sample_data); + } +} + /* * BTS, PEBS probe and setup */ @@ -1628,12 +1964,18 @@ void __init intel_ds_init(void) x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; - if (x86_pmu.version <= 4) + if (x86_pmu.version <= 4) { x86_pmu.pebs_no_isolation = 1; + x86_pmu.pebs_no_xmm_regs = 1; + } if (x86_pmu.pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; + char *pebs_qual = ""; int format = x86_pmu.intel_cap.pebs_format; + if (format < 4) + x86_pmu.intel_cap.pebs_baseline = 0; + switch (format) { case 0: pr_cont("PEBS fmt0%c, ", pebs_type); @@ -1669,6 +2011,29 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; + case 4: + x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl; + x86_pmu.pebs_record_size = sizeof(struct pebs_basic); + if (x86_pmu.intel_cap.pebs_baseline) { + x86_pmu.large_pebs_flags |= + PERF_SAMPLE_BRANCH_STACK | + PERF_SAMPLE_TIME; + x86_pmu.flags |= PMU_FL_PEBS_ALL; + pebs_qual = "-baseline"; + } else { + /* Only basic record supported */ + x86_pmu.pebs_no_xmm_regs = 1; + x86_pmu.large_pebs_flags &= + ~(PERF_SAMPLE_ADDR | + PERF_SAMPLE_TIME | + PERF_SAMPLE_DATA_SRC | + PERF_SAMPLE_TRANSACTION | + PERF_SAMPLE_REGS_USER | + PERF_SAMPLE_REGS_INTR); + } + pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual); + break; + default: pr_cont("no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 580c1b91c454..6f814a27416b 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -488,6 +488,8 @@ void intel_pmu_lbr_add(struct perf_event *event) * be 'new'. Conversely, a new event can get installed through the * context switch path for the first time. */ + if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0) + cpuc->lbr_pebs_users++; perf_sched_cb_inc(event->ctx->pmu); if (!cpuc->lbr_users++ && !event->total_time_running) intel_pmu_lbr_reset(); @@ -507,8 +509,11 @@ void intel_pmu_lbr_del(struct perf_event *event) task_ctx->lbr_callstack_users--; } + if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0) + cpuc->lbr_pebs_users--; cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); + WARN_ON_ONCE(cpuc->lbr_pebs_users < 0); perf_sched_cb_dec(event->ctx->pmu); } @@ -658,7 +663,13 @@ void intel_pmu_lbr_read(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - if (!cpuc->lbr_users) + /* + * Don't read when all LBRs users are using adaptive PEBS. + * + * This could be smarter and actually check the event, + * but this simple approach seems to work for now. + */ + if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users) return; if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) @@ -1080,6 +1091,28 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) } } +void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int i; + + cpuc->lbr_stack.nr = x86_pmu.lbr_nr; + for (i = 0; i < x86_pmu.lbr_nr; i++) { + u64 info = lbr->lbr[i].info; + struct perf_branch_entry *e = &cpuc->lbr_entries[i]; + + e->from = lbr->lbr[i].from; + e->to = lbr->lbr[i].to; + e->mispred = !!(info & LBR_INFO_MISPRED); + e->predicted = !(info & LBR_INFO_MISPRED); + e->in_tx = !!(info & LBR_INFO_IN_TX); + e->abort = !!(info & LBR_INFO_ABORT); + e->cycles = info & LBR_INFO_CYCLES; + e->reserved = 0; + } + intel_pmu_lbr_filter(cpuc); +} + /* * Map interface branch filters onto LBR filters */ diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index fb3a2f13fc70..339d7628080c 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -1525,8 +1525,7 @@ static __init int pt_init(void) } if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) - pt_pmu.pmu.capabilities = - PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF; + pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG; pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE; pt_pmu.pmu.attr_groups = pt_attr_groups; diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 94dc564146ca..37ebf6fc5415 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -775,6 +775,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init), + + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, skl_rapl_init), {}, }; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 9fe64c01a2e5..fc40a1473058 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1367,6 +1367,11 @@ static const struct intel_uncore_init_fun skx_uncore_init __initconst = { .pci_init = skx_uncore_pci_init, }; +static const struct intel_uncore_init_fun icl_uncore_init __initconst = { + .cpu_init = icl_uncore_cpu_init, + .pci_init = skl_uncore_pci_init, +}; + static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init), @@ -1393,6 +1398,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init), {}, }; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 853a49a8ccf6..79eb2e21e4f0 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -512,6 +512,7 @@ int skl_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); void skl_uncore_cpu_init(void); +void icl_uncore_cpu_init(void); int snb_pci2phy_map_init(int devid); /* uncore_snbep.c */ diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 13493f43b247..f8431819b3e1 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -34,6 +34,8 @@ #define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33 #define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca #define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32 +#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02 +#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -93,6 +95,12 @@ #define SKL_UNC_PERF_GLOBAL_CTL 0xe01 #define SKL_UNC_GLOBAL_CTL_CORE_ALL ((1 << 5) - 1) +/* ICL Cbo register */ +#define ICL_UNC_CBO_CONFIG 0x396 +#define ICL_UNC_NUM_CBO_MASK 0xf +#define ICL_UNC_CBO_0_PER_CTR0 0x702 +#define ICL_UNC_CBO_MSR_OFFSET 0x8 + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); @@ -280,6 +288,70 @@ void skl_uncore_cpu_init(void) snb_uncore_arb.ops = &skl_uncore_msr_ops; } +static struct intel_uncore_type icl_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .perf_ctr_bits = 44, + .perf_ctr = ICL_UNC_CBO_0_PER_CTR0, + .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .msr_offset = ICL_UNC_CBO_MSR_OFFSET, + .ops = &skl_uncore_msr_ops, + .format_group = &snb_uncore_format_group, +}; + +static struct uncore_event_desc icl_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff"), + { /* end: all zeroes */ }, +}; + +static struct attribute *icl_uncore_clock_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group icl_uncore_clock_format_group = { + .name = "format", + .attrs = icl_uncore_clock_formats_attr, +}; + +static struct intel_uncore_type icl_uncore_clockbox = { + .name = "clock", + .num_counters = 1, + .num_boxes = 1, + .fixed_ctr_bits = 48, + .fixed_ctr = SNB_UNC_FIXED_CTR, + .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, + .single_fixed = 1, + .event_mask = SNB_UNC_CTL_EV_SEL_MASK, + .format_group = &icl_uncore_clock_format_group, + .ops = &skl_uncore_msr_ops, + .event_descs = icl_uncore_events, +}; + +static struct intel_uncore_type *icl_msr_uncores[] = { + &icl_uncore_cbox, + &snb_uncore_arb, + &icl_uncore_clockbox, + NULL, +}; + +static int icl_get_cbox_num(void) +{ + u64 num_boxes; + + rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes); + + return num_boxes & ICL_UNC_NUM_CBO_MASK; +} + +void icl_uncore_cpu_init(void) +{ + uncore_msr_uncores = icl_msr_uncores; + icl_uncore_cbox.num_boxes = icl_get_cbox_num(); + snb_uncore_arb.ops = &skl_uncore_msr_ops; +} + enum { SNB_PCI_UNCORE_IMC, }; @@ -668,6 +740,18 @@ static const struct pci_device_id skl_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id icl_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -693,6 +777,11 @@ static struct pci_driver skl_uncore_pci_driver = { .id_table = skl_uncore_pci_ids, }; +static struct pci_driver icl_uncore_pci_driver = { + .name = "icl_uncore", + .id_table = icl_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -732,6 +821,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */ IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */ IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */ + IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */ + IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */ { /* end marker */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index a878e6286e4a..f3f4c2263501 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -89,6 +89,7 @@ static bool test_intel(int idx) case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_KABYLAKE_MOBILE: case INTEL_FAM6_KABYLAKE_DESKTOP: + case INTEL_FAM6_ICELAKE_MOBILE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 1e98a42b560a..07fc84bb85c1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -49,28 +49,33 @@ struct event_constraint { unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; u64 idxmsk64; }; - u64 code; - u64 cmask; - int weight; - int overlap; - int flags; + u64 code; + u64 cmask; + int weight; + int overlap; + int flags; + unsigned int size; }; + +static inline bool constraint_match(struct event_constraint *c, u64 ecode) +{ + return ((ecode & c->cmask) - c->code) <= (u64)c->size; +} + /* * struct hw_perf_event.flags flags */ #define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */ #define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */ #define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */ -#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */ -#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */ -#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */ -#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */ -#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ -#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ -#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ -#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ -#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */ - +#define PERF_X86_EVENT_PEBS_LD_HSW 0x0008 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */ +#define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */ +#define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */ +#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0080 /* grant rdpmc permission */ +#define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */ +#define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ +#define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -116,6 +121,24 @@ struct amd_nb { (1ULL << PERF_REG_X86_R14) | \ (1ULL << PERF_REG_X86_R15)) +#define PEBS_XMM_REGS \ + ((1ULL << PERF_REG_X86_XMM0) | \ + (1ULL << PERF_REG_X86_XMM1) | \ + (1ULL << PERF_REG_X86_XMM2) | \ + (1ULL << PERF_REG_X86_XMM3) | \ + (1ULL << PERF_REG_X86_XMM4) | \ + (1ULL << PERF_REG_X86_XMM5) | \ + (1ULL << PERF_REG_X86_XMM6) | \ + (1ULL << PERF_REG_X86_XMM7) | \ + (1ULL << PERF_REG_X86_XMM8) | \ + (1ULL << PERF_REG_X86_XMM9) | \ + (1ULL << PERF_REG_X86_XMM10) | \ + (1ULL << PERF_REG_X86_XMM11) | \ + (1ULL << PERF_REG_X86_XMM12) | \ + (1ULL << PERF_REG_X86_XMM13) | \ + (1ULL << PERF_REG_X86_XMM14) | \ + (1ULL << PERF_REG_X86_XMM15)) + /* * Per register state. */ @@ -207,10 +230,16 @@ struct cpu_hw_events { int n_pebs; int n_large_pebs; + /* Current super set of events hardware configuration */ + u64 pebs_data_cfg; + u64 active_pebs_data_cfg; + int pebs_record_size; + /* * Intel LBR bits */ int lbr_users; + int lbr_pebs_users; struct perf_branch_stack lbr_stack; struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; struct er_account *lbr_sel; @@ -257,18 +286,29 @@ struct cpu_hw_events { void *kfree_on_online[X86_PERF_KFREE_MAX]; }; -#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\ +#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \ { .idxmsk64 = (n) }, \ .code = (c), \ + .size = (e) - (c), \ .cmask = (m), \ .weight = (w), \ .overlap = (o), \ .flags = f, \ } +#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \ + __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f) + #define EVENT_CONSTRAINT(c, n, m) \ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0) +/* + * The constraint_match() function only works for 'simple' event codes + * and not for extended (AMD64_EVENTSEL_EVENT) events codes. + */ +#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \ + __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0) + #define INTEL_EXCLEVT_CONSTRAINT(c, n) \ __EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\ 0, PERF_X86_EVENT_EXCL) @@ -304,6 +344,12 @@ struct cpu_hw_events { EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) /* + * Constraint on a range of Event codes + */ +#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \ + EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT) + +/* * Constraint on the Event code + UMask + fixed-mask * * filter mask to validate fixed counter events. @@ -350,6 +396,9 @@ struct cpu_hw_events { #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) +#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \ + EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) + /* Check only flags, but allow all event/umask */ #define INTEL_ALL_EVENT_CONSTRAINT(code, n) \ EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS) @@ -366,6 +415,11 @@ struct cpu_hw_events { ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) +#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \ + __EVENT_CONSTRAINT_RANGE(code, end, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) + #define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \ __EVENT_CONSTRAINT(code, n, \ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ @@ -473,6 +527,7 @@ union perf_capabilities { * values > 32bit. */ u64 full_width_write:1; + u64 pebs_baseline:1; }; u64 capabilities; }; @@ -613,14 +668,16 @@ struct x86_pmu { pebs_broken :1, pebs_prec_dist :1, pebs_no_tlb :1, - pebs_no_isolation :1; + pebs_no_isolation :1, + pebs_no_xmm_regs :1; int pebs_record_size; int pebs_buffer_size; + int max_pebs_events; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); - int max_pebs_events; unsigned long large_pebs_flags; + u64 rtm_abort_event; /* * Intel LBR @@ -714,6 +771,7 @@ static struct perf_pmu_events_ht_attr event_attr_##v = { \ .event_str_ht = ht, \ } +struct pmu *x86_get_pmu(void); extern struct x86_pmu x86_pmu __read_mostly; static inline bool x86_pmu_has_lbr_callstack(void) @@ -941,6 +999,8 @@ extern struct event_constraint intel_bdw_pebs_event_constraints[]; extern struct event_constraint intel_skl_pebs_event_constraints[]; +extern struct event_constraint intel_icl_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_add(struct perf_event *event); @@ -959,6 +1019,8 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); void intel_pmu_auto_reload_read(struct perf_event *event); +void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr); + void intel_ds_init(void); void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 321fe5f5d0e9..4d5fcd47ab75 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -61,9 +61,8 @@ } while (0) #define RELOAD_SEG(seg) { \ - unsigned int pre = GET_SEG(seg); \ + unsigned int pre = (seg) | 3; \ unsigned int cur = get_user_seg(seg); \ - pre |= 3; \ if (pre != cur) \ set_user_seg(seg, pre); \ } @@ -72,6 +71,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, struct sigcontext_32 __user *sc) { unsigned int tmpflags, err = 0; + u16 gs, fs, es, ds; void __user *buf; u32 tmp; @@ -79,16 +79,10 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, current->restart_block.fn = do_no_restart_syscall; get_user_try { - /* - * Reload fs and gs if they have changed in the signal - * handler. This does not handle long fs/gs base changes in - * the handler, but does not clobber them at least in the - * normal case. - */ - RELOAD_SEG(gs); - RELOAD_SEG(fs); - RELOAD_SEG(ds); - RELOAD_SEG(es); + gs = GET_SEG(gs); + fs = GET_SEG(fs); + ds = GET_SEG(ds); + es = GET_SEG(es); COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); COPY(dx); COPY(cx); COPY(ip); COPY(ax); @@ -106,6 +100,17 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, buf = compat_ptr(tmp); } get_user_catch(err); + /* + * Reload fs and gs if they have changed in the signal + * handler. This does not handle long fs/gs base changes in + * the handler, but does not clobber them at least in the + * normal case. + */ + RELOAD_SEG(gs); + RELOAD_SEG(fs); + RELOAD_SEG(ds); + RELOAD_SEG(es); + err |= fpu__restore_sig(buf, 1); force_iret(); diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index 31b627b43a8e..464034db299f 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -20,6 +20,17 @@ #endif /* + * objtool annotation to ignore the alternatives and only consider the original + * instruction(s). + */ +.macro ANNOTATE_IGNORE_ALTERNATIVE + .Lannotate_\@: + .pushsection .discard.ignore_alts + .long .Lannotate_\@ - . + .popsection +.endm + +/* * Issue one struct alt_instr descriptor entry (need to put it into * the section .altinstructions, see below). This entry contains * enough information for the alternatives patching code to patch an diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 4c74073a19cc..094fbc9c0b1c 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -45,6 +45,16 @@ #define LOCK_PREFIX "" #endif +/* + * objtool annotation to ignore the alternatives and only consider the original + * instruction(s). + */ +#define ANNOTATE_IGNORE_ALTERNATIVE \ + "999:\n\t" \ + ".pushsection .discard.ignore_alts\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" + struct alt_instr { s32 instr_offset; /* original instruction */ s32 repl_offset; /* offset to replacement instruction */ diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 6467757bb39f..3ff577c0b102 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -148,30 +148,6 @@ _ASM_PTR (entry); \ .popsection -.macro ALIGN_DESTINATION - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jz 102f /* already aligned */ - subl $8,%ecx - negl %ecx - subl %ecx,%edx -100: movb (%rsi),%al -101: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 100b -102: - .section .fixup,"ax" -103: addl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE_UA(100b, 103b) - _ASM_EXTABLE_UA(101b, 103b) - .endm - #else # define _EXPAND_EXTABLE_HANDLE(x) #x # define _ASM_EXTABLE_HANDLE(from, to, handler) \ diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h index ae26df1c2789..8380c3ddd4b2 100644 --- a/arch/x86/include/asm/intel_ds.h +++ b/arch/x86/include/asm/intel_ds.h @@ -8,7 +8,7 @@ /* The maximal number of PEBS events: */ #define MAX_PEBS_EVENTS 8 -#define MAX_FIXED_PEBS_EVENTS 3 +#define MAX_FIXED_PEBS_EVENTS 4 /* * A debug store configuration. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a9d03af34030..c79abe7ca093 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -295,6 +295,7 @@ union kvm_mmu_extended_role { unsigned int valid:1; unsigned int execonly:1; unsigned int cr0_pg:1; + unsigned int cr4_pae:1; unsigned int cr4_pse:1; unsigned int cr4_pke:1; unsigned int cr4_smap:1; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ca5bc0eacb95..1378518cf63f 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -116,6 +116,7 @@ #define LBR_INFO_CYCLES 0xffff #define MSR_IA32_PEBS_ENABLE 0x000003f1 +#define MSR_PEBS_DATA_CFG 0x000003f2 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index dad12b767ba0..daf25b60c9e3 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -11,6 +11,15 @@ #include <asm/msr-index.h> /* + * This should be used immediately before a retpoline alternative. It tells + * objtool where the retpolines are so that it can make sense of the control + * flow by just reading the original instruction(s) and ignoring the + * alternatives. + */ +#define ANNOTATE_NOSPEC_ALTERNATIVE \ + ANNOTATE_IGNORE_ALTERNATIVE + +/* * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an @@ -57,19 +66,6 @@ #ifdef __ASSEMBLY__ /* - * This should be used immediately before a retpoline alternative. It tells - * objtool where the retpolines are so that it can make sense of the control - * flow by just reading the original instruction(s) and ignoring the - * alternatives. - */ -.macro ANNOTATE_NOSPEC_ALTERNATIVE - .Lannotate_\@: - .pushsection .discard.nospec - .long .Lannotate_\@ - . - .popsection -.endm - -/* * This should be used immediately before an indirect jump/call. It tells * objtool the subsequent indirect jump/call is vouched safe for retpoline * builds. @@ -152,12 +148,6 @@ #else /* __ASSEMBLY__ */ -#define ANNOTATE_NOSPEC_ALTERNATIVE \ - "999:\n\t" \ - ".pushsection .discard.nospec\n\t" \ - ".long 999b - .\n\t" \ - ".popsection\n\t" - #define ANNOTATE_RETPOLINE_SAFE \ "999:\n\t" \ ".pushsection .discard.retpoline_safe\n\t" \ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8bdf74902293..1392d5e6e8d6 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -7,7 +7,7 @@ */ #define INTEL_PMC_MAX_GENERIC 32 -#define INTEL_PMC_MAX_FIXED 3 +#define INTEL_PMC_MAX_FIXED 4 #define INTEL_PMC_IDX_FIXED 32 #define X86_PMC_IDX_MAX 64 @@ -32,6 +32,8 @@ #define HSW_IN_TX (1ULL << 32) #define HSW_IN_TX_CHECKPOINTED (1ULL << 33) +#define ICL_EVENTSEL_ADAPTIVE (1ULL << 34) +#define ICL_FIXED_0_ADAPTIVE (1ULL << 32) #define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36) #define AMD64_EVENTSEL_GUESTONLY (1ULL << 40) @@ -87,6 +89,12 @@ #define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6 #define ARCH_PERFMON_EVENTS_COUNT 7 +#define PEBS_DATACFG_MEMINFO BIT_ULL(0) +#define PEBS_DATACFG_GP BIT_ULL(1) +#define PEBS_DATACFG_XMMS BIT_ULL(2) +#define PEBS_DATACFG_LBRS BIT_ULL(3) +#define PEBS_DATACFG_LBR_SHIFT 24 + /* * Intel "Architectural Performance Monitoring" CPUID * detection/enumeration details: @@ -177,6 +185,41 @@ struct x86_pmu_capability { #define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55) /* + * Adaptive PEBS v4 + */ + +struct pebs_basic { + u64 format_size; + u64 ip; + u64 applicable_counters; + u64 tsc; +}; + +struct pebs_meminfo { + u64 address; + u64 aux; + u64 latency; + u64 tsx_tuning; +}; + +struct pebs_gprs { + u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di; + u64 r8, r9, r10, r11, r12, r13, r14, r15; +}; + +struct pebs_xmm { + u64 xmm[16*2]; /* two entries for each register */ +}; + +struct pebs_lbr_entry { + u64 from, to, info; +}; + +struct pebs_lbr { + struct pebs_lbr_entry lbr[0]; /* Variable length */ +}; + +/* * IBS cpuid feature detection */ @@ -248,6 +291,11 @@ extern void perf_events_lapic_init(void); #define PERF_EFLAGS_VM (1UL << 5) struct pt_regs; +struct x86_perf_regs { + struct pt_regs regs; + u64 *xmm_regs; +}; + extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) @@ -260,14 +308,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); */ #define perf_arch_fetch_caller_regs(regs, __ip) { \ (regs)->ip = (__ip); \ - (regs)->bp = caller_frame_pointer(); \ + (regs)->sp = (unsigned long)__builtin_frame_address(0); \ (regs)->cs = __KERNEL_CS; \ regs->flags = 0; \ - asm volatile( \ - _ASM_MOV "%%"_ASM_SP ", %0\n" \ - : "=m" ((regs)->sp) \ - :: "memory" \ - ); \ } struct perf_guest_switch_msr { diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h deleted file mode 100644 index 4c25cf6caefa..000000000000 --- a/arch/x86/include/asm/rwsem.h +++ /dev/null @@ -1,237 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+ - * - * Written by David Howells (dhowells@redhat.com). - * - * Derived from asm-x86/semaphore.h - * - * - * The MSW of the count is the negated number of active writers and waiting - * lockers, and the LSW is the total number of active locks - * - * The lock count is initialized to 0 (no active and no waiting lockers). - * - * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an - * uncontended lock. This can be determined because XADD returns the old value. - * Readers increment by 1 and see a positive value when uncontended, negative - * if there are writers (and maybe) readers waiting (in which case it goes to - * sleep). - * - * The value of WAITING_BIAS supports up to 32766 waiting processes. This can - * be extended to 65534 by manually checking the whole MSW rather than relying - * on the S flag. - * - * The value of ACTIVE_BIAS supports up to 65535 active processes. - * - * This should be totally fair - if anything is waiting, a process that wants a - * lock will go to the back of the queue. When the currently active lock is - * released, if there's a writer at the front of the queue, then that and only - * that will be woken up; if there's a bunch of consecutive readers at the - * front, then they'll all be woken up, but no other readers will be. - */ - -#ifndef _ASM_X86_RWSEM_H -#define _ASM_X86_RWSEM_H - -#ifndef _LINUX_RWSEM_H -#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead" -#endif - -#ifdef __KERNEL__ -#include <asm/asm.h> - -/* - * The bias values and the counter type limits the number of - * potential readers/writers to 32767 for 32 bits and 2147483647 - * for 64 bits. - */ - -#ifdef CONFIG_X86_64 -# define RWSEM_ACTIVE_MASK 0xffffffffL -#else -# define RWSEM_ACTIVE_MASK 0x0000ffffL -#endif - -#define RWSEM_UNLOCKED_VALUE 0x00000000L -#define RWSEM_ACTIVE_BIAS 0x00000001L -#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -/* - * lock for reading - */ -#define ____down_read(sem, slow_path) \ -({ \ - struct rw_semaphore* ret; \ - asm volatile("# beginning down_read\n\t" \ - LOCK_PREFIX _ASM_INC "(%[sem])\n\t" \ - /* adds 0x00000001 */ \ - " jns 1f\n" \ - " call " slow_path "\n" \ - "1:\n\t" \ - "# ending down_read\n\t" \ - : "+m" (sem->count), "=a" (ret), \ - ASM_CALL_CONSTRAINT \ - : [sem] "a" (sem) \ - : "memory", "cc"); \ - ret; \ -}) - -static inline void __down_read(struct rw_semaphore *sem) -{ - ____down_read(sem, "call_rwsem_down_read_failed"); -} - -static inline int __down_read_killable(struct rw_semaphore *sem) -{ - if (IS_ERR(____down_read(sem, "call_rwsem_down_read_failed_killable"))) - return -EINTR; - return 0; -} - -/* - * trylock for reading -- returns 1 if successful, 0 if contention - */ -static inline bool __down_read_trylock(struct rw_semaphore *sem) -{ - long result, tmp; - asm volatile("# beginning __down_read_trylock\n\t" - " mov %[count],%[result]\n\t" - "1:\n\t" - " mov %[result],%[tmp]\n\t" - " add %[inc],%[tmp]\n\t" - " jle 2f\n\t" - LOCK_PREFIX " cmpxchg %[tmp],%[count]\n\t" - " jnz 1b\n\t" - "2:\n\t" - "# ending __down_read_trylock\n\t" - : [count] "+m" (sem->count), [result] "=&a" (result), - [tmp] "=&r" (tmp) - : [inc] "i" (RWSEM_ACTIVE_READ_BIAS) - : "memory", "cc"); - return result >= 0; -} - -/* - * lock for writing - */ -#define ____down_write(sem, slow_path) \ -({ \ - long tmp; \ - struct rw_semaphore* ret; \ - \ - asm volatile("# beginning down_write\n\t" \ - LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" \ - /* adds 0xffff0001, returns the old value */ \ - " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \ - /* was the active mask 0 before? */\ - " jz 1f\n" \ - " call " slow_path "\n" \ - "1:\n" \ - "# ending down_write" \ - : "+m" (sem->count), [tmp] "=d" (tmp), \ - "=a" (ret), ASM_CALL_CONSTRAINT \ - : [sem] "a" (sem), "[tmp]" (RWSEM_ACTIVE_WRITE_BIAS) \ - : "memory", "cc"); \ - ret; \ -}) - -static inline void __down_write(struct rw_semaphore *sem) -{ - ____down_write(sem, "call_rwsem_down_write_failed"); -} - -static inline int __down_write_killable(struct rw_semaphore *sem) -{ - if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable"))) - return -EINTR; - - return 0; -} - -/* - * trylock for writing -- returns 1 if successful, 0 if contention - */ -static inline bool __down_write_trylock(struct rw_semaphore *sem) -{ - bool result; - long tmp0, tmp1; - asm volatile("# beginning __down_write_trylock\n\t" - " mov %[count],%[tmp0]\n\t" - "1:\n\t" - " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" - /* was the active mask 0 before? */ - " jnz 2f\n\t" - " mov %[tmp0],%[tmp1]\n\t" - " add %[inc],%[tmp1]\n\t" - LOCK_PREFIX " cmpxchg %[tmp1],%[count]\n\t" - " jnz 1b\n\t" - "2:\n\t" - CC_SET(e) - "# ending __down_write_trylock\n\t" - : [count] "+m" (sem->count), [tmp0] "=&a" (tmp0), - [tmp1] "=&r" (tmp1), CC_OUT(e) (result) - : [inc] "er" (RWSEM_ACTIVE_WRITE_BIAS) - : "memory"); - return result; -} - -/* - * unlock after reading - */ -static inline void __up_read(struct rw_semaphore *sem) -{ - long tmp; - asm volatile("# beginning __up_read\n\t" - LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" - /* subtracts 1, returns the old value */ - " jns 1f\n\t" - " call call_rwsem_wake\n" /* expects old value in %edx */ - "1:\n" - "# ending __up_read\n" - : "+m" (sem->count), [tmp] "=d" (tmp) - : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_READ_BIAS) - : "memory", "cc"); -} - -/* - * unlock after writing - */ -static inline void __up_write(struct rw_semaphore *sem) -{ - long tmp; - asm volatile("# beginning __up_write\n\t" - LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" - /* subtracts 0xffff0001, returns the old value */ - " jns 1f\n\t" - " call call_rwsem_wake\n" /* expects old value in %edx */ - "1:\n\t" - "# ending __up_write\n" - : "+m" (sem->count), [tmp] "=d" (tmp) - : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_WRITE_BIAS) - : "memory", "cc"); -} - -/* - * downgrade write lock to read lock - */ -static inline void __downgrade_write(struct rw_semaphore *sem) -{ - asm volatile("# beginning __downgrade_write\n\t" - LOCK_PREFIX _ASM_ADD "%[inc],(%[sem])\n\t" - /* - * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386) - * 0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64) - */ - " jns 1f\n\t" - " call call_rwsem_downgrade_wake\n" - "1:\n\t" - "# ending __downgrade_write\n" - : "+m" (sem->count) - : [sem] "a" (sem), [inc] "er" (-RWSEM_WAITING_BIAS) - : "memory", "cc"); -} - -#endif /* __KERNEL__ */ -#endif /* _ASM_X86_RWSEM_H */ diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index db333300bd4b..f94a7d0ddd49 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -13,13 +13,12 @@ #ifndef _ASM_X86_SMAP_H #define _ASM_X86_SMAP_H -#include <linux/stringify.h> #include <asm/nops.h> #include <asm/cpufeatures.h> /* "Raw" instruction opcodes */ -#define __ASM_CLAC .byte 0x0f,0x01,0xca -#define __ASM_STAC .byte 0x0f,0x01,0xcb +#define __ASM_CLAC ".byte 0x0f,0x01,0xca" +#define __ASM_STAC ".byte 0x0f,0x01,0xcb" #ifdef __ASSEMBLY__ @@ -28,10 +27,10 @@ #ifdef CONFIG_X86_SMAP #define ASM_CLAC \ - ALTERNATIVE "", __stringify(__ASM_CLAC), X86_FEATURE_SMAP + ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP #define ASM_STAC \ - ALTERNATIVE "", __stringify(__ASM_STAC), X86_FEATURE_SMAP + ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP #else /* CONFIG_X86_SMAP */ @@ -49,26 +48,46 @@ static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ - alternative("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP); + alternative("", __ASM_CLAC, X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ - alternative("", __stringify(__ASM_STAC), X86_FEATURE_SMAP); + alternative("", __ASM_STAC, X86_FEATURE_SMAP); +} + +static __always_inline unsigned long smap_save(void) +{ + unsigned long flags; + + asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC, + X86_FEATURE_SMAP) + : "=rm" (flags) : : "memory", "cc"); + + return flags; +} + +static __always_inline void smap_restore(unsigned long flags) +{ + asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP) + : : "g" (flags) : "memory", "cc"); } /* These macros can be used in asm() statements */ #define ASM_CLAC \ - ALTERNATIVE("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP) + ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP) #define ASM_STAC \ - ALTERNATIVE("", __stringify(__ASM_STAC), X86_FEATURE_SMAP) + ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) #else /* CONFIG_X86_SMAP */ static inline void clac(void) { } static inline void stac(void) { } +static inline unsigned long smap_save(void) { return 0; } +static inline void smap_restore(unsigned long flags) { } + #define ASM_CLAC #define ASM_STAC diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f335aad404a4..beef7ad9e43a 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -98,19 +98,6 @@ struct stack_frame_ia32 { u32 return_address; }; -static inline unsigned long caller_frame_pointer(void) -{ - struct stack_frame *frame; - - frame = __builtin_frame_address(0); - -#ifdef CONFIG_FRAME_POINTER - frame = frame->next_frame; -#endif - - return (unsigned long)frame; -} - void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 7cf1a270d891..18a4b6890fa8 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -46,6 +46,7 @@ struct inactive_task_frame { unsigned long r13; unsigned long r12; #else + unsigned long flags; unsigned long si; unsigned long di; #endif diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 404b8b1d44f5..f23e7aaff4cd 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -6,6 +6,7 @@ #define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) +#define tlb_flush tlb_flush static inline void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 1954dd5552a2..bb21913885a3 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -427,10 +427,11 @@ do { \ ({ \ __label__ __pu_label; \ int __pu_err = -EFAULT; \ - __typeof__(*(ptr)) __pu_val; \ - __pu_val = x; \ + __typeof__(*(ptr)) __pu_val = (x); \ + __typeof__(ptr) __pu_ptr = (ptr); \ + __typeof__(size) __pu_size = (size); \ __uaccess_begin(); \ - __put_user_size(__pu_val, (ptr), (size), __pu_label); \ + __put_user_size(__pu_val, __pu_ptr, __pu_size, __pu_label); \ __pu_err = 0; \ __pu_label: \ __uaccess_end(); \ @@ -705,7 +706,7 @@ extern struct movsl_mask { * checking before using them, but you have to surround them with the * user_access_begin/end() pair. */ -static __must_check inline bool user_access_begin(const void __user *ptr, size_t len) +static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr,len))) return 0; @@ -715,6 +716,9 @@ static __must_check inline bool user_access_begin(const void __user *ptr, size_t #define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() __uaccess_end() +#define user_access_save() smap_save() +#define user_access_restore(x) smap_restore(x) + #define unsafe_put_user(x, ptr, label) \ __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index a9d637bc301d..5cd1caa8bc65 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -208,9 +208,6 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) } unsigned long -copy_user_handle_tail(char *to, char *from, unsigned len); - -unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len); #endif /* _ASM_X86_UACCESS_64_H */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 2863c2026655..d50c7b747d8b 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -217,6 +217,22 @@ xen_single_call(unsigned int call, return (long)__res; } +static __always_inline void __xen_stac(void) +{ + /* + * Suppress objtool seeing the STAC/CLAC and getting confused about it + * calling random code with AC=1. + */ + asm volatile(ANNOTATE_IGNORE_ALTERNATIVE + ASM_STAC ::: "memory", "flags"); +} + +static __always_inline void __xen_clac(void) +{ + asm volatile(ANNOTATE_IGNORE_ALTERNATIVE + ASM_CLAC ::: "memory", "flags"); +} + static inline long privcmd_call(unsigned int call, unsigned long a1, unsigned long a2, @@ -225,9 +241,9 @@ privcmd_call(unsigned int call, { long res; - stac(); + __xen_stac(); res = xen_single_call(call, a1, a2, a3, a4, a5); - clac(); + __xen_clac(); return res; } @@ -424,9 +440,9 @@ HYPERVISOR_dm_op( domid_t dom, unsigned int nr_bufs, struct xen_dm_op_buf *bufs) { int ret; - stac(); + __xen_stac(); ret = _hypercall3(int, dm_op, dom, nr_bufs, bufs); - clac(); + __xen_clac(); return ret; } diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index dabfcf7c3941..7a0e64ccd6ff 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -381,6 +381,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h index f3329cabce5c..ac67bbea10ca 100644 --- a/arch/x86/include/uapi/asm/perf_regs.h +++ b/arch/x86/include/uapi/asm/perf_regs.h @@ -27,8 +27,29 @@ enum perf_event_x86_regs { PERF_REG_X86_R13, PERF_REG_X86_R14, PERF_REG_X86_R15, - + /* These are the limits for the GPRs. */ PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1, PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1, + + /* These all need two bits set because they are 128bit */ + PERF_REG_X86_XMM0 = 32, + PERF_REG_X86_XMM1 = 34, + PERF_REG_X86_XMM2 = 36, + PERF_REG_X86_XMM3 = 38, + PERF_REG_X86_XMM4 = 40, + PERF_REG_X86_XMM5 = 42, + PERF_REG_X86_XMM6 = 44, + PERF_REG_X86_XMM7 = 46, + PERF_REG_X86_XMM8 = 48, + PERF_REG_X86_XMM9 = 50, + PERF_REG_X86_XMM10 = 52, + PERF_REG_X86_XMM11 = 54, + PERF_REG_X86_XMM12 = 56, + PERF_REG_X86_XMM13 = 58, + PERF_REG_X86_XMM14 = 60, + PERF_REG_X86_XMM15 = 62, + + /* These include both GPRs and XMMX registers */ + PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2, }; #endif /* _ASM_X86_PERF_REGS_H */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index b91b3bfa5cfb..29630393f300 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -440,7 +440,8 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) char arg[20]; int ret, i; - if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") || + cpu_mitigations_off()) return SPECTRE_V2_CMD_NONE; ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); @@ -672,7 +673,8 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) char arg[20]; int ret, i; - if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) { + if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") || + cpu_mitigations_off()) { return SPEC_STORE_BYPASS_CMD_NONE; } else { ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", @@ -1008,6 +1010,11 @@ static void __init l1tf_select_mitigation(void) if (!boot_cpu_has_bug(X86_BUG_L1TF)) return; + if (cpu_mitigations_off()) + l1tf_mitigation = L1TF_MITIGATION_OFF; + else if (cpu_mitigations_auto_nosmt()) + l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT; + override_cache_bits(&boot_cpu_data); switch (l1tf_mitigation) { diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index c06c4c16c6b6..07c30ee17425 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -59,18 +59,34 @@ static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = { u64 perf_reg_value(struct pt_regs *regs, int idx) { + struct x86_perf_regs *perf_regs; + + if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) { + perf_regs = container_of(regs, struct x86_perf_regs, regs); + if (!perf_regs->xmm_regs) + return 0; + return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0]; + } + if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset))) return 0; return regs_get_register(regs, pt_regs_offset[idx]); } -#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL)) - #ifdef CONFIG_X86_32 +#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \ + (1ULL << PERF_REG_X86_R9) | \ + (1ULL << PERF_REG_X86_R10) | \ + (1ULL << PERF_REG_X86_R11) | \ + (1ULL << PERF_REG_X86_R12) | \ + (1ULL << PERF_REG_X86_R13) | \ + (1ULL << PERF_REG_X86_R14) | \ + (1ULL << PERF_REG_X86_R15)) + int perf_reg_validate(u64 mask) { - if (!mask || mask & REG_RESERVED) + if (!mask || (mask & REG_NOSUPPORT)) return -EINVAL; return 0; @@ -96,10 +112,7 @@ void perf_get_regs_user(struct perf_regs *regs_user, int perf_reg_validate(u64 mask) { - if (!mask || mask & REG_RESERVED) - return -EINVAL; - - if (mask & REG_NOSUPPORT) + if (!mask || (mask & REG_NOSUPPORT)) return -EINVAL; return 0; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index e471d8e6f0b2..70933193878c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -127,6 +127,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, struct task_struct *tsk; int err; + /* + * For a new task use the RESET flags value since there is no before. + * All the status flags are zero; DF and all the system flags must also + * be 0, specifically IF must be 0 because we context switch to the new + * task with interrupts disabled. + */ + frame->flags = X86_EFLAGS_FIXED; frame->bp = 0; frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6a62f4af9fcf..844a28b29967 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -392,6 +392,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, childregs = task_pt_regs(p); fork_frame = container_of(childregs, struct fork_frame, regs); frame = &fork_frame->frame; + frame->bp = 0; frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3d872a527cd9..3773905cd2c1 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1005,13 +1005,11 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled(EFI_BOOT)) efi_init(); - dmi_scan_machine(); - dmi_memdev_walk(); - dmi_set_dump_stack_arch_desc(); + dmi_setup(); /* * VMware detection requires dmi to be available, so this - * needs to be done after dmi_scan_machine(), for the boot CPU. + * needs to be done after dmi_setup(), for the boot CPU. */ init_hypervisor_platform(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 08dfd4c1a4f9..dff90fb6a9af 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -132,16 +132,6 @@ static int restore_sigcontext(struct pt_regs *regs, COPY_SEG_CPL3(cs); COPY_SEG_CPL3(ss); -#ifdef CONFIG_X86_64 - /* - * Fix up SS if needed for the benefit of old DOSEMU and - * CRIU. - */ - if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && - user_64bit_mode(regs))) - force_valid_ss(regs); -#endif - get_user_ex(tmpflags, &sc->flags); regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); regs->orig_ax = -1; /* disable syscall checks */ @@ -150,6 +140,15 @@ static int restore_sigcontext(struct pt_regs *regs, buf = (void __user *)buf_val; } get_user_catch(err); +#ifdef CONFIG_X86_64 + /* + * Fix up SS if needed for the benefit of old DOSEMU and + * CRIU. + */ + if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs))) + force_valid_ss(regs); +#endif + err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32)); force_iret(); @@ -461,6 +460,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, { struct rt_sigframe __user *frame; void __user *fp = NULL; + unsigned long uc_flags; int err = 0; frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp); @@ -473,9 +473,11 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, return -EFAULT; } + uc_flags = frame_uc_flags(regs); + put_user_try { /* Create the ucontext. */ - put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags); + put_user_ex(uc_flags, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); save_altstack_ex(&frame->uc.uc_stack, regs->sp); @@ -541,6 +543,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, { #ifdef CONFIG_X86_X32_ABI struct rt_sigframe_x32 __user *frame; + unsigned long uc_flags; void __user *restorer; int err = 0; void __user *fpstate = NULL; @@ -555,9 +558,11 @@ static int x32_setup_rt_frame(struct ksignal *ksig, return -EFAULT; } + uc_flags = frame_uc_flags(regs); + put_user_try { /* Create the ucontext. */ - put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags); + put_user_ex(uc_flags, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); @@ -688,10 +693,7 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) sigset_t *set = sigmask_to_save(); compat_sigset_t *cset = (compat_sigset_t *) set; - /* - * Increment event counter and perform fixup for the pre-signal - * frame. - */ + /* Perform fixup for the pre-signal frame. */ rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 5c2d71a1dc06..2abf27d7df6b 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -12,78 +12,31 @@ #include <asm/stacktrace.h> #include <asm/unwind.h> -static int save_stack_address(struct stack_trace *trace, unsigned long addr, - bool nosched) -{ - if (nosched && in_sched_functions(addr)) - return 0; - - if (trace->skip > 0) { - trace->skip--; - return 0; - } - - if (trace->nr_entries >= trace->max_entries) - return -1; - - trace->entries[trace->nr_entries++] = addr; - return 0; -} - -static void noinline __save_stack_trace(struct stack_trace *trace, - struct task_struct *task, struct pt_regs *regs, - bool nosched) +void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs) { struct unwind_state state; unsigned long addr; - if (regs) - save_stack_address(trace, regs->ip, nosched); + if (regs && !consume_entry(cookie, regs->ip, false)) + return; for (unwind_start(&state, task, regs, NULL); !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); - if (!addr || save_stack_address(trace, addr, nosched)) + if (!addr || !consume_entry(cookie, addr, false)) break; } - - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } /* - * Save stack-backtrace addresses into a stack_trace buffer. + * This function returns an error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is reliable. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. */ -void save_stack_trace(struct stack_trace *trace) -{ - trace->skip++; - __save_stack_trace(trace, current, NULL, false); -} -EXPORT_SYMBOL_GPL(save_stack_trace); - -void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) -{ - __save_stack_trace(trace, current, regs, false); -} - -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) -{ - if (!try_get_task_stack(tsk)) - return; - - if (tsk == current) - trace->skip++; - __save_stack_trace(trace, tsk, NULL, true); - - put_task_stack(tsk); -} -EXPORT_SYMBOL_GPL(save_stack_trace_tsk); - -#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE - -static int __always_inline -__save_stack_trace_reliable(struct stack_trace *trace, - struct task_struct *task) +int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, + void *cookie, struct task_struct *task) { struct unwind_state state; struct pt_regs *regs; @@ -97,7 +50,7 @@ __save_stack_trace_reliable(struct stack_trace *trace, if (regs) { /* Success path for user tasks */ if (user_mode(regs)) - goto success; + return 0; /* * Kernel mode registers on the stack indicate an @@ -120,7 +73,7 @@ __save_stack_trace_reliable(struct stack_trace *trace, if (!addr) return -EINVAL; - if (save_stack_address(trace, addr, false)) + if (!consume_entry(cookie, addr, false)) return -EINVAL; } @@ -132,39 +85,9 @@ __save_stack_trace_reliable(struct stack_trace *trace, if (!(task->flags & (PF_KTHREAD | PF_IDLE))) return -EINVAL; -success: - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; - return 0; } -/* - * This function returns an error if it detects any unreliable features of the - * stack. Otherwise it guarantees that the stack trace is reliable. - * - * If the task is not 'current', the caller *must* ensure the task is inactive. - */ -int save_stack_trace_tsk_reliable(struct task_struct *tsk, - struct stack_trace *trace) -{ - int ret; - - /* - * If the task doesn't have a stack (e.g., a zombie), the stack is - * "reliably" empty. - */ - if (!try_get_task_stack(tsk)) - return 0; - - ret = __save_stack_trace_reliable(trace, tsk); - - put_task_stack(tsk); - - return ret; -} -#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */ - /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */ struct stack_frame_user { @@ -189,15 +112,15 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) return ret; } -static inline void __save_stack_trace_user(struct stack_trace *trace) +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, + const struct pt_regs *regs) { - const struct pt_regs *regs = task_pt_regs(current); const void __user *fp = (const void __user *)regs->bp; - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = regs->ip; + if (!consume_entry(cookie, regs->ip, false)) + return; - while (trace->nr_entries < trace->max_entries) { + while (1) { struct stack_frame_user frame; frame.next_fp = NULL; @@ -207,8 +130,8 @@ static inline void __save_stack_trace_user(struct stack_trace *trace) if ((unsigned long)fp < regs->sp) break; if (frame.ret_addr) { - trace->entries[trace->nr_entries++] = - frame.ret_addr; + if (!consume_entry(cookie, frame.ret_addr, false)) + return; } if (fp == frame.next_fp) break; @@ -216,14 +139,3 @@ static inline void __save_stack_trace_user(struct stack_trace *trace) } } -void save_stack_trace_user(struct stack_trace *trace) -{ - /* - * Trace user stack if we are not a kernel thread - */ - if (current->mm) { - __save_stack_trace_user(trace); - } - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; -} diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 421899f6ad7b..cc24b3a32c44 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1371,7 +1371,16 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa, valid_bank_mask = BIT_ULL(0); sparse_banks[0] = flush.processor_mask; - all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS; + + /* + * Work around possible WS2012 bug: it sends hypercalls + * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear, + * while also expecting us to flush something and crashing if + * we don't. Let's treat processor_mask == 0 same as + * HV_FLUSH_ALL_PROCESSORS. + */ + all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) || + flush.processor_mask == 0; } else { if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex, sizeof(flush_ex)))) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 9bf70cf84564..bd13fdddbdc4 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -70,7 +70,6 @@ #define APIC_BROADCAST 0xFF #define X2APIC_BROADCAST 0xFFFFFFFFul -static bool lapic_timer_advance_adjust_done = false; #define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 @@ -1482,14 +1481,32 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) return false; } +static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles) +{ + u64 timer_advance_ns = vcpu->arch.apic->lapic_timer.timer_advance_ns; + + /* + * If the guest TSC is running at a different ratio than the host, then + * convert the delay to nanoseconds to achieve an accurate delay. Note + * that __delay() uses delay_tsc whenever the hardware has TSC, thus + * always for VMX enabled hardware. + */ + if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) { + __delay(min(guest_cycles, + nsec_to_cycles(vcpu, timer_advance_ns))); + } else { + u64 delay_ns = guest_cycles * 1000000ULL; + do_div(delay_ns, vcpu->arch.virtual_tsc_khz); + ndelay(min_t(u32, delay_ns, timer_advance_ns)); + } +} + void wait_lapic_expire(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; + u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns; u64 guest_tsc, tsc_deadline, ns; - if (!lapic_in_kernel(vcpu)) - return; - if (apic->lapic_timer.expired_tscdeadline == 0) return; @@ -1501,33 +1518,37 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); - /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ if (guest_tsc < tsc_deadline) - __delay(min(tsc_deadline - guest_tsc, - nsec_to_cycles(vcpu, lapic_timer_advance_ns))); + __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - if (!lapic_timer_advance_adjust_done) { + if (!apic->lapic_timer.timer_advance_adjust_done) { /* too early */ if (guest_tsc < tsc_deadline) { ns = (tsc_deadline - guest_tsc) * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - lapic_timer_advance_ns -= min((unsigned int)ns, - lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns -= min((u32)ns, + timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); } else { /* too late */ ns = (guest_tsc - tsc_deadline) * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - lapic_timer_advance_ns += min((unsigned int)ns, - lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns += min((u32)ns, + timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); } if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE) - lapic_timer_advance_adjust_done = true; + apic->lapic_timer.timer_advance_adjust_done = true; + if (unlikely(timer_advance_ns > 5000)) { + timer_advance_ns = 0; + apic->lapic_timer.timer_advance_adjust_done = true; + } + apic->lapic_timer.timer_advance_ns = timer_advance_ns; } } static void start_sw_tscdeadline(struct kvm_lapic *apic) { - u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; + struct kvm_timer *ktimer = &apic->lapic_timer; + u64 guest_tsc, tscdeadline = ktimer->tscdeadline; u64 ns = 0; ktime_t expire; struct kvm_vcpu *vcpu = apic->vcpu; @@ -1542,13 +1563,15 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) now = ktime_get(); guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); - if (likely(tscdeadline > guest_tsc)) { - ns = (tscdeadline - guest_tsc) * 1000000ULL; - do_div(ns, this_tsc_khz); + + ns = (tscdeadline - guest_tsc) * 1000000ULL; + do_div(ns, this_tsc_khz); + + if (likely(tscdeadline > guest_tsc) && + likely(ns > apic->lapic_timer.timer_advance_ns)) { expire = ktime_add_ns(now, ns); - expire = ktime_sub_ns(expire, lapic_timer_advance_ns); - hrtimer_start(&apic->lapic_timer.timer, - expire, HRTIMER_MODE_ABS_PINNED); + expire = ktime_sub_ns(expire, ktimer->timer_advance_ns); + hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_PINNED); } else apic_timer_expired(apic); @@ -2255,7 +2278,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } -int kvm_create_lapic(struct kvm_vcpu *vcpu) +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) { struct kvm_lapic *apic; @@ -2279,6 +2302,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); apic->lapic_timer.timer.function = apic_timer_fn; + if (timer_advance_ns == -1) { + apic->lapic_timer.timer_advance_ns = 1000; + apic->lapic_timer.timer_advance_adjust_done = false; + } else { + apic->lapic_timer.timer_advance_ns = timer_advance_ns; + apic->lapic_timer.timer_advance_adjust_done = true; + } + /* * APIC is created enabled. This will prevent kvm_lapic_set_base from diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index ff6ef9c3d760..d6d049ba3045 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -31,8 +31,10 @@ struct kvm_timer { u32 timer_mode_mask; u64 tscdeadline; u64 expired_tscdeadline; + u32 timer_advance_ns; atomic_t pending; /* accumulated triggered timers */ bool hv_timer_in_use; + bool timer_advance_adjust_done; }; struct kvm_lapic { @@ -62,7 +64,7 @@ struct kvm_lapic { struct dest_map; -int kvm_create_lapic(struct kvm_vcpu *vcpu); +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns); void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e10962dfc203..d9c7b45d231f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4781,6 +4781,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu) union kvm_mmu_extended_role ext = {0}; ext.cr0_pg = !!is_paging(vcpu); + ext.cr4_pae = !!is_pae(vcpu); ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); ext.cr4_pse = !!is_pse(vcpu); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 6401eb7ef19c..0c601d079cd2 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5423,7 +5423,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return ret; /* Empty 'VMXON' state is permitted */ - if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12)) + if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) return 0; if (kvm_state->vmx.vmcs_pa != -1ull) { @@ -5467,7 +5467,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmcs12->vmcs_link_pointer != -1ull) { struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); - if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12)) + if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12)) return -EINVAL; if (copy_from_user(shadow_vmcs12, diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 7b272738c576..d4cb1945b2e3 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -3,6 +3,7 @@ #include <asm/asm.h> #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> +#include <asm/nospec-branch.h> #define WORD_SIZE (BITS_PER_LONG / 8) @@ -77,6 +78,17 @@ ENDPROC(vmx_vmenter) * referred to by VMCS.HOST_RIP. */ ENTRY(vmx_vmexit) +#ifdef CONFIG_RETPOLINE + ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE + /* Preserve guest's RAX, it's used to stuff the RSB. */ + push %_ASM_AX + + /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + + pop %_ASM_AX +.Lvmexit_skip_rsb: +#endif ret ENDPROC(vmx_vmexit) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index b4e7d645275a..0c955bb286ff 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6462,9 +6462,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); - /* Eliminate branch target predictions from guest mode */ - vmexit_fill_RSB(); - /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) current_evmcs->hv_clean_fields |= @@ -7032,6 +7029,7 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) { struct vcpu_vmx *vmx; u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; + struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer; if (kvm_mwait_in_guest(vcpu->kvm)) return -EOPNOTSUPP; @@ -7040,7 +7038,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) tscl = rdtsc(); guest_tscl = kvm_read_l1_tsc(vcpu, tscl); delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; - lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns); + lapic_timer_advance_cycles = nsec_to_cycles(vcpu, + ktimer->timer_advance_ns); if (delta_tsc > lapic_timer_advance_cycles) delta_tsc -= lapic_timer_advance_cycles; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a0d1fc80ac5a..b5edc8e3ce1d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -136,10 +136,14 @@ EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio); static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); -/* lapic timer advance (tscdeadline mode only) in nanoseconds */ -unsigned int __read_mostly lapic_timer_advance_ns = 1000; +/* + * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables + * adaptive tuning starting from default advancment of 1000ns. '0' disables + * advancement entirely. Any other value is used as-is and disables adaptive + * tuning, i.e. allows priveleged userspace to set an exact advancement time. + */ +static int __read_mostly lapic_timer_advance_ns = -1; module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); -EXPORT_SYMBOL_GPL(lapic_timer_advance_ns); static bool __read_mostly vector_hashing = true; module_param(vector_hashing, bool, S_IRUGO); @@ -6535,6 +6539,12 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); +static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pio.count = 0; + return 1; +} + static int complete_fast_pio_out(struct kvm_vcpu *vcpu) { vcpu->arch.pio.count = 0; @@ -6551,12 +6561,23 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, size, port, &val, 1); + if (ret) + return ret; - if (!ret) { + /* + * Workaround userspace that relies on old KVM behavior of %rip being + * incremented prior to exiting to userspace to handle "OUT 0x7e". + */ + if (port == 0x7e && + kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) { + vcpu->arch.complete_userspace_io = + complete_fast_pio_out_port_0x7e; + kvm_skip_emulated_instruction(vcpu); + } else { vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_out; } - return ret; + return 0; } static int complete_fast_pio_in(struct kvm_vcpu *vcpu) @@ -7873,7 +7894,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } trace_kvm_entry(vcpu->vcpu_id); - if (lapic_timer_advance_ns) + if (lapic_in_kernel(vcpu) && + vcpu->arch.apic->lapic_timer.timer_advance_ns) wait_lapic_expire(vcpu); guest_enter_irqoff(); @@ -9061,7 +9083,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) if (irqchip_in_kernel(vcpu->kvm)) { vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); - r = kvm_create_lapic(vcpu); + r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); if (r < 0) goto fail_mmu_destroy; } else diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index aedc5d0d4989..534d3f28bb01 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -294,8 +294,6 @@ extern u64 kvm_supported_xcr0(void); extern unsigned int min_timer_period_us; -extern unsigned int lapic_timer_advance_ns; - extern bool enable_vmware_backdoor; extern struct static_key kvm_no_apic_vcpu; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 140e61843a07..5246db42de45 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -6,6 +6,18 @@ # Produces uninteresting flaky coverage. KCOV_INSTRUMENT_delay.o := n +# Early boot use of cmdline; don't instrument it +ifdef CONFIG_AMD_MEM_ENCRYPT +KCOV_INSTRUMENT_cmdline.o := n +KASAN_SANITIZE_cmdline.o := n + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_cmdline.o = -pg +endif + +CFLAGS_cmdline.o := $(call cc-option, -fno-stack-protector) +endif + inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt quiet_cmd_inat_tables = GEN $@ @@ -23,7 +35,6 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o -lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index db4e5aa0858b..b2f1822084ae 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -16,6 +16,30 @@ #include <asm/smap.h> #include <asm/export.h> +.macro ALIGN_DESTINATION + /* check for bad alignment of destination */ + movl %edi,%ecx + andl $7,%ecx + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +100: movb (%rsi),%al +101: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 100b +102: + .section .fixup,"ax" +103: addl %ecx,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous + + _ASM_EXTABLE_UA(100b, 103b) + _ASM_EXTABLE_UA(101b, 103b) + .endm + /* * copy_user_generic_unrolled - memory copy with exception handling. * This version is for CPUs like P4 that don't have efficient micro @@ -194,6 +218,30 @@ ENDPROC(copy_user_enhanced_fast_string) EXPORT_SYMBOL(copy_user_enhanced_fast_string) /* + * Try to copy last bytes and clear the rest if needed. + * Since protection fault in copy_from/to_user is not a normal situation, + * it is not necessary to optimize tail handling. + * + * Input: + * rdi destination + * rsi source + * rdx count + * + * Output: + * eax uncopied bytes or 0 if successful. + */ +ALIGN; +copy_user_handle_tail: + movl %edx,%ecx +1: rep movsb +2: mov %ecx,%eax + ASM_CLAC + ret + + _ASM_EXTABLE_UA(1b, 2b) +ENDPROC(copy_user_handle_tail) + +/* * copy_user_nocache - Uncached memory copy with exception handling * This will force destination out of cache for more performance. * diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 3b24dc05251c..9d05572370ed 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -257,6 +257,7 @@ ENTRY(__memcpy_mcsafe) /* Copy successful. Return zero */ .L_done_memcpy_trap: xorl %eax, %eax +.L_done: ret ENDPROC(__memcpy_mcsafe) EXPORT_SYMBOL_GPL(__memcpy_mcsafe) @@ -273,7 +274,7 @@ EXPORT_SYMBOL_GPL(__memcpy_mcsafe) addl %edx, %ecx .E_trailing_bytes: mov %ecx, %eax - ret + jmp .L_done /* * For write fault handling, given the destination is unaligned, diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S deleted file mode 100644 index dc2ab6ea6768..000000000000 --- a/arch/x86/lib/rwsem.S +++ /dev/null @@ -1,156 +0,0 @@ -/* - * x86 semaphore implementation. - * - * (C) Copyright 1999 Linus Torvalds - * - * Portions Copyright 1999 Red Hat, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org> - */ - -#include <linux/linkage.h> -#include <asm/alternative-asm.h> -#include <asm/frame.h> - -#define __ASM_HALF_REG(reg) __ASM_SEL(reg, e##reg) -#define __ASM_HALF_SIZE(inst) __ASM_SEL(inst##w, inst##l) - -#ifdef CONFIG_X86_32 - -/* - * The semaphore operations have a special calling sequence that - * allow us to do a simpler in-line version of them. These routines - * need to convert that sequence back into the C sequence when - * there is contention on the semaphore. - * - * %eax contains the semaphore pointer on entry. Save the C-clobbered - * registers (%eax, %edx and %ecx) except %eax which is either a return - * value or just gets clobbered. Same is true for %edx so make sure GCC - * reloads it after the slow path, by making it hold a temporary, for - * example see ____down_write(). - */ - -#define save_common_regs \ - pushl %ecx - -#define restore_common_regs \ - popl %ecx - - /* Avoid uglifying the argument copying x86-64 needs to do. */ - .macro movq src, dst - .endm - -#else - -/* - * x86-64 rwsem wrappers - * - * This interfaces the inline asm code to the slow-path - * C routines. We need to save the call-clobbered regs - * that the asm does not mark as clobbered, and move the - * argument from %rax to %rdi. - * - * NOTE! We don't need to save %rax, because the functions - * will always return the semaphore pointer in %rax (which - * is also the input argument to these helpers) - * - * The following can clobber %rdx because the asm clobbers it: - * call_rwsem_down_write_failed - * call_rwsem_wake - * but %rdi, %rsi, %rcx, %r8-r11 always need saving. - */ - -#define save_common_regs \ - pushq %rdi; \ - pushq %rsi; \ - pushq %rcx; \ - pushq %r8; \ - pushq %r9; \ - pushq %r10; \ - pushq %r11 - -#define restore_common_regs \ - popq %r11; \ - popq %r10; \ - popq %r9; \ - popq %r8; \ - popq %rcx; \ - popq %rsi; \ - popq %rdi - -#endif - -/* Fix up special calling conventions */ -ENTRY(call_rwsem_down_read_failed) - FRAME_BEGIN - save_common_regs - __ASM_SIZE(push,) %__ASM_REG(dx) - movq %rax,%rdi - call rwsem_down_read_failed - __ASM_SIZE(pop,) %__ASM_REG(dx) - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_read_failed) - -ENTRY(call_rwsem_down_read_failed_killable) - FRAME_BEGIN - save_common_regs - __ASM_SIZE(push,) %__ASM_REG(dx) - movq %rax,%rdi - call rwsem_down_read_failed_killable - __ASM_SIZE(pop,) %__ASM_REG(dx) - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_read_failed_killable) - -ENTRY(call_rwsem_down_write_failed) - FRAME_BEGIN - save_common_regs - movq %rax,%rdi - call rwsem_down_write_failed - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_write_failed) - -ENTRY(call_rwsem_down_write_failed_killable) - FRAME_BEGIN - save_common_regs - movq %rax,%rdi - call rwsem_down_write_failed_killable - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_write_failed_killable) - -ENTRY(call_rwsem_wake) - FRAME_BEGIN - /* do nothing if still outstanding active readers */ - __ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx) - jnz 1f - save_common_regs - movq %rax,%rdi - call rwsem_wake - restore_common_regs -1: FRAME_END - ret -ENDPROC(call_rwsem_wake) - -ENTRY(call_rwsem_downgrade_wake) - FRAME_BEGIN - save_common_regs - __ASM_SIZE(push,) %__ASM_REG(dx) - movq %rax,%rdi - call rwsem_downgrade_wake - __ASM_SIZE(pop,) %__ASM_REG(dx) - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_downgrade_wake) diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index ee42bb0cbeb3..9952a01cad24 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -55,26 +55,6 @@ unsigned long clear_user(void __user *to, unsigned long n) EXPORT_SYMBOL(clear_user); /* - * Try to copy last bytes and clear the rest if needed. - * Since protection fault in copy_from/to_user is not a normal situation, - * it is not necessary to optimize tail handling. - */ -__visible unsigned long -copy_user_handle_tail(char *to, char *from, unsigned len) -{ - for (; len; --len, to++) { - char c; - - if (__get_user_nocheck(c, from++, sizeof(char))) - break; - if (__put_user_nocheck(c, to, sizeof(char))) - break; - } - clac(); - return len; -} - -/* * Similar to copy_user_handle_tail, probe for the write fault point, * but reuse __memcpy_mcsafe in case a new read error is encountered. * clac() is handled in _copy_to_iter_mcsafe(). diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 139b28a01ce4..d0255d64edce 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -35,6 +35,7 @@ #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/uaccess.h> +#include <linux/cpu.h> #include <asm/cpufeature.h> #include <asm/hypervisor.h> @@ -115,7 +116,8 @@ void __init pti_check_boottime_disable(void) } } - if (cmdline_find_option_bool(boot_command_line, "nopti")) { + if (cmdline_find_option_bool(boot_command_line, "nopti") || + cpu_mitigations_off()) { pti_mode = PTI_FORCE_OFF; pti_print_if_insecure("disabled on command line."); return; diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index a9e80e44178c..a8985e1f7432 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -32,12 +32,6 @@ config ARCH_DEFCONFIG default "arch/um/configs/i386_defconfig" if X86_32 default "arch/um/configs/x86_64_defconfig" if X86_64 -config RWSEM_XCHGADD_ALGORITHM - def_bool 64BIT - -config RWSEM_GENERIC_SPINLOCK - def_bool !RWSEM_XCHGADD_ALGORITHM - config 3_LEVEL_PGTABLES bool "Three-level pagetables" if !64BIT default 64BIT diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index 2d686ae54681..33c51c064c77 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -21,14 +21,12 @@ obj-y += checksum_32.o syscalls_32.o obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o -subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o else obj-y += syscalls_64.o vdso/ -subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \ - ../lib/rwsem.o +subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o endif diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 4b9aafe766c5..35c8d91e6106 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -46,9 +46,6 @@ config XTENSA with reasonable minimum requirements. The Xtensa Linux project has a home page at <http://www.linux-xtensa.org/>. -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config GENERIC_HWEIGHT def_bool y diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 3843198e03d4..4148090cafb0 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -25,7 +25,6 @@ generic-y += percpu.h generic-y += preempt.h generic-y += qrwlock.h generic-y += qspinlock.h -generic-y += rwsem.h generic-y += sections.h generic-y += socket.h generic-y += topology.h diff --git a/arch/xtensa/include/asm/tlb.h b/arch/xtensa/include/asm/tlb.h index 0d766f9c1083..50889935138a 100644 --- a/arch/xtensa/include/asm/tlb.h +++ b/arch/xtensa/include/asm/tlb.h @@ -14,32 +14,6 @@ #include <asm/cache.h> #include <asm/page.h> -#if (DCACHE_WAY_SIZE <= PAGE_SIZE) - -/* Note, read http://lkml.org/lkml/2004/1/15/6 */ - -# define tlb_start_vma(tlb,vma) do { } while (0) -# define tlb_end_vma(tlb,vma) do { } while (0) - -#else - -# define tlb_start_vma(tlb, vma) \ - do { \ - if (!tlb->fullmm) \ - flush_cache_range(vma, vma->vm_start, vma->vm_end); \ - } while(0) - -# define tlb_end_vma(tlb, vma) \ - do { \ - if (!tlb->fullmm) \ - flush_tlb_range(vma, vma->vm_start, vma->vm_end); \ - } while(0) - -#endif - -#define __tlb_remove_tlb_entry(tlb,pte,addr) do { } while (0) -#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) - #include <asm-generic/tlb.h> #define __pte_free_tlb(tlb, pte, address) pte_free((tlb)->mm, pte) |