From ed6a79352cad00e9a49d6e438be40e45107207bf Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 31 Aug 2018 14:46:08 +0200 Subject: asm-generic/tlb, arch: Provide CONFIG_HAVE_MMU_GATHER_PAGE_SIZE Move the mmu_gather::page_size things into the generic code instead of PowerPC specific bits. No change in behavior intended. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrew Morton Cc: Andy Lutomirski Cc: Aneesh Kumar K.V Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Nick Piggin Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- mm/huge_memory.c | 4 ++-- mm/hugetlb.c | 2 +- mm/madvise.c | 2 +- mm/memory.c | 4 ++-- mm/mmu_gather.c | 5 +++++ 5 files changed, 11 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 404acdcd0455..76b75112a259 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1641,7 +1641,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, struct mm_struct *mm = tlb->mm; bool ret = false; - tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE); + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = pmd_trans_huge_lock(pmd, vma); if (!ptl) @@ -1717,7 +1717,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t orig_pmd; spinlock_t *ptl; - tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE); + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = __pmd_trans_huge_lock(pmd, vma); if (!ptl) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 97b1e0290c66..3fc37a626b52 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3353,7 +3353,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, * This is a hugetlb vma, all the pte entries should point * to huge page. */ - tlb_remove_check_page_size_change(tlb, sz); + tlb_change_page_size(tlb, sz); tlb_start_vma(tlb, vma); /* diff --git a/mm/madvise.c b/mm/madvise.c index 21a7881a2db4..bb3a4554d5d5 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -328,7 +328,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, if (pmd_trans_unstable(pmd)) return 0; - tlb_remove_check_page_size_change(tlb, PAGE_SIZE); + tlb_change_page_size(tlb, PAGE_SIZE); orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); diff --git a/mm/memory.c b/mm/memory.c index ab650c21bccd..1aa5c03566f1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -356,7 +356,7 @@ void free_pgd_range(struct mmu_gather *tlb, * We add page table cache pages with PAGE_SIZE, * (see pte_free_tlb()), flush the tlb if we need */ - tlb_remove_check_page_size_change(tlb, PAGE_SIZE); + tlb_change_page_size(tlb, PAGE_SIZE); pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); @@ -1046,7 +1046,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pte_t *pte; swp_entry_t entry; - tlb_remove_check_page_size_change(tlb, PAGE_SIZE); + tlb_change_page_size(tlb, PAGE_SIZE); again: init_rss_vec(rss); start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index f2f03c655807..14dfc97155e4 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -58,7 +58,9 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, #ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb->batch = NULL; #endif +#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE tlb->page_size = 0; +#endif __tlb_reset_range(tlb); } @@ -121,7 +123,10 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ struct mmu_gather_batch *batch; VM_BUG_ON(!tlb->end); + +#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE VM_WARN_ON(tlb->page_size != page_size); +#endif batch = tlb->active; /* -- cgit v1.2.3-71-gd317 From 96bc9567cbe112e9320250f01b9c060c882e8619 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 Sep 2018 13:24:41 +0200 Subject: asm-generic/tlb, arch: Invert CONFIG_HAVE_RCU_TABLE_INVALIDATE Make issuing a TLB invalidate for page-table pages the normal case. The reason is twofold: - too many invalidates is safer than too few, - most architectures use the linux page-tables natively and would thus require this. Make it an opt-out, instead of an opt-in. No change in behavior intended. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/Kconfig | 2 +- arch/arm64/Kconfig | 1 - arch/powerpc/Kconfig | 1 + arch/sparc/Kconfig | 1 + arch/x86/Kconfig | 1 - include/asm-generic/tlb.h | 9 +++++---- mm/mmu_gather.c | 2 +- 7 files changed, 9 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/arch/Kconfig b/arch/Kconfig index cdc7f3d5d278..04b3e8b94cfe 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -383,7 +383,7 @@ 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 diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7e34b9eba5de..78d9fafac983 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 diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a7aa4feabc09..8e1e2abf17eb 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -218,6 +218,7 @@ 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 diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 40f8f4f73fe8..db79290ed6d5 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 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5ad92419be19..b0f30d86c23f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -183,7 +183,6 @@ 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 diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 1c861989b704..81799e6a4304 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -135,11 +135,12 @@ * When used, an architecture is expected to provide __tlb_remove_table() * which does the actual freeing of these pages. * - * HAVE_RCU_TABLE_INVALIDATE + * HAVE_RCU_TABLE_NO_INVALIDATE * - * This makes HAVE_RCU_TABLE_FREE call tlb_flush_mmu_tlbonly() before freeing - * the page-table pages. Required if you use HAVE_RCU_TABLE_FREE and your - * architecture uses the Linux page-tables natively. + * This makes HAVE_RCU_TABLE_FREE avoid calling tlb_flush_mmu_tlbonly() before + * freeing the page-table pages. This can be avoided if you use + * HAVE_RCU_TABLE_FREE and your architecture does _NOT_ use the Linux + * page-tables natively. * * MMU_GATHER_NO_RANGE * diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 14dfc97155e4..2a5322d52b0a 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -157,7 +157,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ */ static inline void tlb_table_invalidate(struct mmu_gather *tlb) { -#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE +#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE /* * Invalidate page-table caches used by hardware walkers. Then we still * need to RCU-sched wait while freeing the pages because software -- cgit v1.2.3-71-gd317 From 952a31c9e6fa963eabf3692f31a769e59f4c8303 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Tue, 18 Sep 2018 14:51:50 +0200 Subject: asm-generic/tlb: Introduce CONFIG_HAVE_MMU_GATHER_NO_GATHER=y Add the Kconfig option HAVE_MMU_GATHER_NO_GATHER to the generic mmu_gather code. If the option is set the mmu_gather will not track individual pages for delayed page free anymore. A platform that enables the option needs to provide its own implementation of the __tlb_remove_page_size() function to free pages. No change in behavior intended. Signed-off-by: Martin Schwidefsky Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: aneesh.kumar@linux.vnet.ibm.com Cc: heiko.carstens@de.ibm.com Cc: linux@armlinux.org.uk Cc: npiggin@gmail.com Link: http://lkml.kernel.org/r/20180918125151.31744-2-schwidefsky@de.ibm.com Signed-off-by: Ingo Molnar --- arch/Kconfig | 3 ++ include/asm-generic/tlb.h | 9 +++- mm/mmu_gather.c | 107 ++++++++++++++++++++++++++-------------------- 3 files changed, 70 insertions(+), 49 deletions(-) (limited to 'mm') diff --git a/arch/Kconfig b/arch/Kconfig index 04b3e8b94cfe..a826843470ed 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -389,6 +389,9 @@ config HAVE_RCU_TABLE_NO_INVALIDATE config HAVE_MMU_GATHER_PAGE_SIZE bool +config HAVE_MMU_GATHER_NO_GATHER + bool + config ARCH_HAVE_NMI_SAFE_CMPXCHG bool diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 81799e6a4304..af20aa8255cd 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -191,6 +191,7 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #endif +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER /* * 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. @@ -215,6 +216,10 @@ struct mmu_gather_batch { */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) +extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, + int page_size); +#endif + /* * 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. @@ -261,6 +266,7 @@ struct mmu_gather { unsigned int batch_count; +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; @@ -268,6 +274,7 @@ struct mmu_gather { #ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE unsigned int page_size; #endif +#endif }; void arch_tlb_gather_mmu(struct mmu_gather *tlb, @@ -276,8 +283,6 @@ void tlb_flush_mmu(struct mmu_gather *tlb); void arch_tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end, bool force); void tlb_flush_mmu_free(struct mmu_gather *tlb); -extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, - int page_size); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 2a5322d52b0a..ab220edcd7ef 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -13,6 +13,8 @@ #ifdef HAVE_GENERIC_MMU_GATHER +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER + static bool tlb_next_batch(struct mmu_gather *tlb) { struct mmu_gather_batch *batch; @@ -41,6 +43,56 @@ static bool tlb_next_batch(struct mmu_gather *tlb) return true; } +static void tlb_batch_pages_flush(struct mmu_gather *tlb) +{ + struct mmu_gather_batch *batch; + + for (batch = &tlb->local; batch && batch->nr; batch = batch->next) { + free_pages_and_swap_cache(batch->pages, batch->nr); + batch->nr = 0; + } + tlb->active = &tlb->local; +} + +static void tlb_batch_list_free(struct mmu_gather *tlb) +{ + struct mmu_gather_batch *batch, *next; + + for (batch = tlb->local.next; batch; batch = next) { + next = batch->next; + free_pages((unsigned long)batch, 0); + } + tlb->local.next = NULL; +} + +bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) +{ + struct mmu_gather_batch *batch; + + VM_BUG_ON(!tlb->end); + +#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE + VM_WARN_ON(tlb->page_size != page_size); +#endif + + batch = tlb->active; + /* + * Add the page and check if we are full. If so + * force a flush. + */ + batch->pages[batch->nr++] = page; + if (batch->nr == batch->max) { + if (!tlb_next_batch(tlb)) + return true; + batch = tlb->active; + } + VM_BUG_ON_PAGE(batch->nr > batch->max, page); + + return false; +} + +#endif /* HAVE_MMU_GATHER_NO_GATHER */ + void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) { @@ -48,12 +100,15 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, /* Is it from 0 to ~0? */ tlb->fullmm = !(start | (end+1)); + +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER tlb->need_flush_all = 0; tlb->local.next = NULL; tlb->local.nr = 0; tlb->local.max = ARRAY_SIZE(tlb->__pages); tlb->active = &tlb->local; tlb->batch_count = 0; +#endif #ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb->batch = NULL; @@ -67,16 +122,12 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, void tlb_flush_mmu_free(struct mmu_gather *tlb) { - struct mmu_gather_batch *batch; - #ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb_table_flush(tlb); #endif - for (batch = &tlb->local; batch && batch->nr; batch = batch->next) { - free_pages_and_swap_cache(batch->pages, batch->nr); - batch->nr = 0; - } - tlb->active = &tlb->local; +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER + tlb_batch_pages_flush(tlb); +#endif } void tlb_flush_mmu(struct mmu_gather *tlb) @@ -92,8 +143,6 @@ void tlb_flush_mmu(struct mmu_gather *tlb) void arch_tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end, bool force) { - struct mmu_gather_batch *batch, *next; - if (force) { __tlb_reset_range(tlb); __tlb_adjust_range(tlb, start, end - start); @@ -103,45 +152,9 @@ void arch_tlb_finish_mmu(struct mmu_gather *tlb, /* keep the page table cache within bounds */ check_pgt_cache(); - - for (batch = tlb->local.next; batch; batch = next) { - next = batch->next; - free_pages((unsigned long)batch, 0); - } - tlb->local.next = NULL; -} - -/* __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. Returns the number of free page slots left. - * When out of page slots we must call tlb_flush_mmu(). - *returns true if the caller should flush. - */ -bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) -{ - struct mmu_gather_batch *batch; - - VM_BUG_ON(!tlb->end); - -#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE - VM_WARN_ON(tlb->page_size != page_size); +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER + tlb_batch_list_free(tlb); #endif - - batch = tlb->active; - /* - * Add the page and check if we are full. If so - * force a flush. - */ - batch->pages[batch->nr++] = page; - if (batch->nr == batch->max) { - if (!tlb_next_batch(tlb)) - return true; - batch = tlb->active; - } - VM_BUG_ON_PAGE(batch->nr > batch->max, page); - - return false; } #endif /* HAVE_GENERIC_MMU_GATHER */ -- cgit v1.2.3-71-gd317 From 1808d65b55e4489770dd4f76fb0dff5b81eb9b11 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 Sep 2018 10:50:11 +0200 Subject: asm-generic/tlb: Remove arch_tlb*_mmu() Now that all architectures are converted to the generic code, remove the arch hooks. No change in behavior intended. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- mm/mmu_gather.c | 93 ++++++++++++++++++++++++++------------------------------- 1 file changed, 42 insertions(+), 51 deletions(-) (limited to 'mm') diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index ab220edcd7ef..60ef38d200c0 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -93,33 +93,6 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ #endif /* HAVE_MMU_GATHER_NO_GATHER */ -void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - tlb->mm = mm; - - /* Is it from 0 to ~0? */ - tlb->fullmm = !(start | (end+1)); - -#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER - tlb->need_flush_all = 0; - tlb->local.next = NULL; - tlb->local.nr = 0; - tlb->local.max = ARRAY_SIZE(tlb->__pages); - tlb->active = &tlb->local; - tlb->batch_count = 0; -#endif - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - tlb->batch = NULL; -#endif -#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE - tlb->page_size = 0; -#endif - - __tlb_reset_range(tlb); -} - void tlb_flush_mmu_free(struct mmu_gather *tlb) { #ifdef CONFIG_HAVE_RCU_TABLE_FREE @@ -136,27 +109,6 @@ void tlb_flush_mmu(struct mmu_gather *tlb) tlb_flush_mmu_free(tlb); } -/* tlb_finish_mmu - * Called at the end of the shootdown operation to free up any resources - * that were required. - */ -void arch_tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end, bool force) -{ - if (force) { - __tlb_reset_range(tlb); - __tlb_adjust_range(tlb, start, end - start); - } - - tlb_flush_mmu(tlb); - - /* keep the page table cache within bounds */ - check_pgt_cache(); -#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER - tlb_batch_list_free(tlb); -#endif -} - #endif /* HAVE_GENERIC_MMU_GATHER */ #ifdef CONFIG_HAVE_RCU_TABLE_FREE @@ -258,10 +210,40 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) { - arch_tlb_gather_mmu(tlb, mm, start, end); + tlb->mm = mm; + + /* Is it from 0 to ~0? */ + tlb->fullmm = !(start | (end+1)); + +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER + tlb->need_flush_all = 0; + tlb->local.next = NULL; + tlb->local.nr = 0; + tlb->local.max = ARRAY_SIZE(tlb->__pages); + tlb->active = &tlb->local; + tlb->batch_count = 0; +#endif + +#ifdef CONFIG_HAVE_RCU_TABLE_FREE + tlb->batch = NULL; +#endif +#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE + tlb->page_size = 0; +#endif + + __tlb_reset_range(tlb); inc_tlb_flush_pending(tlb->mm); } +/** + * tlb_finish_mmu - finish an mmu_gather structure + * @tlb: the mmu_gather structure to finish + * @start: start of the region that will be removed from the page-table + * @end: end of the region that will be removed from the page-table + * + * Called at the end of the shootdown operation to free up any resources that + * were required. + */ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) { @@ -272,8 +254,17 @@ void tlb_finish_mmu(struct mmu_gather *tlb, * the TLB by observing pte_none|!pte_dirty, for example so flush TLB * forcefully if we detect parallel PTE batching threads. */ - bool force = mm_tlb_flush_nested(tlb->mm); + if (mm_tlb_flush_nested(tlb->mm)) { + __tlb_reset_range(tlb); + __tlb_adjust_range(tlb, start, end - start); + } - arch_tlb_finish_mmu(tlb, start, end, force); + tlb_flush_mmu(tlb); + + /* keep the page table cache within bounds */ + check_pgt_cache(); +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER + tlb_batch_list_free(tlb); +#endif dec_tlb_flush_pending(tlb->mm); } -- cgit v1.2.3-71-gd317 From b3fa8ed4e48802e6ba0aa5f3283313a27dcbf46f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 Sep 2018 10:51:01 +0200 Subject: asm-generic/tlb: Remove CONFIG_HAVE_GENERIC_MMU_GATHER Since all architectures are now using it, it is redundant. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/asm-generic/tlb.h | 1 - mm/mmu_gather.c | 4 ---- 2 files changed, 5 deletions(-) (limited to 'mm') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index af20aa8255cd..2648a02a6b1b 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -146,7 +146,6 @@ * * Use this if your architecture lacks an efficient flush_tlb_range(). */ -#define HAVE_GENERIC_MMU_GATHER #ifdef CONFIG_HAVE_RCU_TABLE_FREE /* diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 60ef38d200c0..7f5b2b8aa9dd 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -11,8 +11,6 @@ #include #include -#ifdef HAVE_GENERIC_MMU_GATHER - #ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER static bool tlb_next_batch(struct mmu_gather *tlb) @@ -109,8 +107,6 @@ void tlb_flush_mmu(struct mmu_gather *tlb) tlb_flush_mmu_free(tlb); } -#endif /* HAVE_GENERIC_MMU_GATHER */ - #ifdef CONFIG_HAVE_RCU_TABLE_FREE /* -- cgit v1.2.3-71-gd317 From fa0aafb8acb684e68231ff0a547ed249f8dc31a5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 Sep 2018 10:54:04 +0200 Subject: asm-generic/tlb: Remove tlb_flush_mmu_free() As the comment notes; it is a potentially dangerous operation. Just use tlb_flush_mmu(), that will skip the (double) TLB invalidate if it really isn't needed anyway. No change in behavior intended. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/asm-generic/tlb.h | 10 +++------- mm/memory.c | 2 +- mm/mmu_gather.c | 2 +- 3 files changed, 5 insertions(+), 9 deletions(-) (limited to 'mm') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 2648a02a6b1b..ddd3d02be93d 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -67,16 +67,13 @@ * call before __tlb_remove_page*() to set the current page-size; implies a * possible tlb_flush_mmu() call. * - * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() / tlb_flush_mmu_free() + * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() * * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets * related state, like the range) * - * tlb_flush_mmu_free() - frees the queued pages; make absolutely - * sure no additional tlb_remove_page() - * calls happen between _tlbonly() and this. - * - * tlb_flush_mmu() - the above two calls. + * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees + * whatever pages are still batched. * * - mmu_gather::fullmm * @@ -281,7 +278,6 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb, void tlb_flush_mmu(struct mmu_gather *tlb); void arch_tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end, bool force); -void tlb_flush_mmu_free(struct mmu_gather *tlb); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, diff --git a/mm/memory.c b/mm/memory.c index 1aa5c03566f1..36aac6844662 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1155,7 +1155,7 @@ again: */ if (force_flush) { force_flush = 0; - tlb_flush_mmu_free(tlb); + tlb_flush_mmu(tlb); if (addr != end) goto again; } diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 7f5b2b8aa9dd..35699a4d0a74 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -91,7 +91,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ #endif /* HAVE_MMU_GATHER_NO_GATHER */ -void tlb_flush_mmu_free(struct mmu_gather *tlb) +static void tlb_flush_mmu_free(struct mmu_gather *tlb) { #ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb_table_flush(tlb); -- cgit v1.2.3-71-gd317 From 0a8caf211bcf52cbb59e100ead4908fe88d2a510 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 Sep 2018 10:55:10 +0200 Subject: asm-generic/tlb: Remove tlb_table_flush() There are no external users of this API (nor should there be); remove it. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/asm-generic/tlb.h | 1 - mm/mmu_gather.c | 34 +++++++++++++++++----------------- 2 files changed, 17 insertions(+), 18 deletions(-) (limited to 'mm') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index ddd3d02be93d..fc661b4675ff 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -182,7 +182,6 @@ struct mmu_table_batch { #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); #endif diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 35699a4d0a74..99740e1dd273 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -91,22 +91,6 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ #endif /* HAVE_MMU_GATHER_NO_GATHER */ -static void tlb_flush_mmu_free(struct mmu_gather *tlb) -{ -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - tlb_table_flush(tlb); -#endif -#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER - tlb_batch_pages_flush(tlb); -#endif -} - -void tlb_flush_mmu(struct mmu_gather *tlb) -{ - tlb_flush_mmu_tlbonly(tlb); - tlb_flush_mmu_free(tlb); -} - #ifdef CONFIG_HAVE_RCU_TABLE_FREE /* @@ -159,7 +143,7 @@ static void tlb_remove_table_rcu(struct rcu_head *head) free_page((unsigned long)batch); } -void tlb_table_flush(struct mmu_gather *tlb) +static void tlb_table_flush(struct mmu_gather *tlb) { struct mmu_table_batch **batch = &tlb->batch; @@ -191,6 +175,22 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) #endif /* CONFIG_HAVE_RCU_TABLE_FREE */ +static void tlb_flush_mmu_free(struct mmu_gather *tlb) +{ +#ifdef CONFIG_HAVE_RCU_TABLE_FREE + tlb_table_flush(tlb); +#endif +#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER + tlb_batch_pages_flush(tlb); +#endif +} + +void tlb_flush_mmu(struct mmu_gather *tlb) +{ + tlb_flush_mmu_tlbonly(tlb); + tlb_flush_mmu_free(tlb); +} + /** * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down * @tlb: the mmu_gather structure to initialize -- cgit v1.2.3-71-gd317