From dea2434c23c102b3e7d320849ec1cfeb432edb60 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 4 Sep 2018 10:43:14 +0200 Subject: asm-generic/tlb: Provide a comment Write a comment explaining some of this.. 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 --- include/asm-generic/tlb.h | 119 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 116 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 6be86c1c5c58..f1594ba8b2de 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -22,6 +22,118 @@ #ifdef CONFIG_MMU +/* + * Generic MMU-gather implementation. + * + * The mmu_gather data structure is used by the mm code to implement the + * correct and efficient ordering of freeing pages and TLB invalidations. + * + * This correct ordering is: + * + * 1) unhook page + * 2) TLB invalidate page + * 3) free page + * + * That is, we must never free a page before we have ensured there are no live + * translations left to it. Otherwise it might be possible to observe (or + * worse, change) the page content after it has been reused. + * + * The mmu_gather API consists of: + * + * - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather + * + * Finish in particular will issue a (final) TLB invalidate and free + * all (remaining) queued pages. + * + * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA + * + * Defaults to flushing at tlb_end_vma() to reset the range; helps when + * there's large holes between the VMAs. + * + * - tlb_remove_page() / __tlb_remove_page() + * - tlb_remove_page_size() / __tlb_remove_page_size() + * + * __tlb_remove_page_size() is the basic primitive that queues a page for + * freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a + * boolean indicating if the queue is (now) full and a call to + * tlb_flush_mmu() is required. + * + * tlb_remove_page() and tlb_remove_page_size() imply the call to + * tlb_flush_mmu() when required and has no return value. + * + * - tlb_remove_check_page_size_change() + * + * 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_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. + * + * - mmu_gather::fullmm + * + * A flag set by tlb_gather_mmu() to indicate we're going to free + * the entire mm; this allows a number of optimizations. + * + * - We can ignore tlb_{start,end}_vma(); because we don't + * care about ranges. Everything will be shot down. + * + * - (RISC) architectures that use ASIDs can cycle to a new ASID + * and delay the invalidation until ASID space runs out. + * + * - mmu_gather::need_flush_all + * + * A flag that can be set by the arch code if it wants to force + * flush the entire TLB irrespective of the range. For instance + * x86-PAE needs this when changing top-level entries. + * + * And requires the architecture to provide and implement tlb_flush(). + * + * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make + * use of: + * + * - mmu_gather::start / mmu_gather::end + * + * which provides the range that needs to be flushed to cover the pages to + * be freed. + * + * - mmu_gather::freed_tables + * + * set when we freed page table pages + * + * - tlb_get_unmap_shift() / tlb_get_unmap_size() + * + * returns the smallest TLB entry size unmapped in this range + * + * Additionally there are a few opt-in features: + * + * HAVE_RCU_TABLE_FREE + * + * This provides tlb_remove_table(), to be used instead of tlb_remove_page() + * for page directores (__p*_free_tlb()). This provides separate freeing of + * the page-table pages themselves in a semi-RCU fashion (see comment below). + * Useful if your architecture doesn't use IPIs for remote TLB invalidates + * and therefore doesn't naturally serialize with software page-table walkers. + * + * When used, an architecture is expected to provide __tlb_remove_table() + * which does the actual freeing of these pages. + * + * HAVE_RCU_TABLE_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. + * + */ +#define HAVE_GENERIC_MMU_GATHER + #ifdef CONFIG_HAVE_RCU_TABLE_FREE /* * Semi RCU freeing of the page directories. @@ -89,14 +201,17 @@ struct mmu_gather_batch { */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) -/* struct mmu_gather is an opaque type used by the mm code for passing around +/* + * 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; + #ifdef CONFIG_HAVE_RCU_TABLE_FREE struct mmu_table_batch *batch; #endif + unsigned long start; unsigned long end; /* @@ -131,8 +246,6 @@ struct mmu_gather { int page_size; }; -#define HAVE_GENERIC_MMU_GATHER - void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end); void tlb_flush_mmu(struct mmu_gather *tlb); -- cgit v1.2.3 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 --- arch/Kconfig | 3 +++ arch/arm/include/asm/tlb.h | 3 +-- arch/ia64/include/asm/tlb.h | 3 +-- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/tlb.h | 17 ----------------- arch/s390/include/asm/tlb.h | 4 +--- arch/sh/include/asm/tlb.h | 4 +--- arch/um/include/asm/tlb.h | 4 +--- include/asm-generic/tlb.h | 32 +++++++++++++++++++------------- mm/huge_memory.c | 4 ++-- mm/hugetlb.c | 2 +- mm/madvise.c | 2 +- mm/memory.c | 4 ++-- mm/mmu_gather.c | 5 +++++ 14 files changed, 39 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/arch/Kconfig b/arch/Kconfig index 33687dddd86a..cdc7f3d5d278 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -386,6 +386,9 @@ config HAVE_RCU_TABLE_FREE config HAVE_RCU_TABLE_INVALIDATE bool +config HAVE_MMU_GATHER_PAGE_SIZE + bool + config ARCH_HAVE_NMI_SAFE_CMPXCHG bool diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index f854148c8d7c..d644c3c7c6f3 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -286,8 +286,7 @@ tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr #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, +static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { } diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index 516355a774bf..bf8985f5f876 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -282,8 +282,7 @@ do { \ #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, +static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { } diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2d0be82c3061..a7aa4feabc09 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_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/tlb.h b/arch/powerpc/include/asm/tlb.h index e24c67d5ba75..b018e9f9b491 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -27,7 +27,6 @@ #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 extern void tlb_flush(struct mmu_gather *tlb); @@ -46,22 +45,6 @@ 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/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index b31c779cf581..9941a1442a88 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -180,9 +180,7 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, #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) +static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { } diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h index 77abe192fb43..af7c9d891cf8 100644 --- a/arch/sh/include/asm/tlb.h +++ b/arch/sh/include/asm/tlb.h @@ -127,9 +127,7 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, 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) +static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { } diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h index dce6db147f24..6463f3ab1767 100644 --- a/arch/um/include/asm/tlb.h +++ b/arch/um/include/asm/tlb.h @@ -146,9 +146,7 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, #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) +static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { } diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index f1594ba8b2de..e75620e41ba4 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -61,7 +61,7 @@ * tlb_remove_page() and tlb_remove_page_size() imply the call to * tlb_flush_mmu() when required and has no return value. * - * - tlb_remove_check_page_size_change() + * - tlb_change_page_size() * * call before __tlb_remove_page*() to set the current page-size; implies a * possible tlb_flush_mmu() call. @@ -114,6 +114,11 @@ * * Additionally there are a few opt-in features: * + * HAVE_MMU_GATHER_PAGE_SIZE + * + * This ensures we call tlb_flush() every time tlb_change_page_size() actually + * changes the size and provides mmu_gather::page_size to tlb_flush(). + * * HAVE_RCU_TABLE_FREE * * This provides tlb_remove_table(), to be used instead of tlb_remove_page() @@ -239,11 +244,15 @@ struct mmu_gather { unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; + unsigned int batch_count; + struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; - unsigned int batch_count; - int page_size; + +#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE + unsigned int page_size; +#endif }; void arch_tlb_gather_mmu(struct mmu_gather *tlb, @@ -309,21 +318,18 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) return tlb_remove_page_size(tlb, page, PAGE_SIZE); } -#ifndef tlb_remove_check_page_size_change -#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, +static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { - /* - * We don't care about page size change, just update - * mmu_gather page size here so that debug checks - * doesn't throw false warning. - */ -#ifdef CONFIG_DEBUG_VM +#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE + if (tlb->page_size && tlb->page_size != page_size) { + if (!tlb->fullmm) + tlb_flush_mmu(tlb); + } + tlb->page_size = page_size; #endif } -#endif static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb) { 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 From e7fd28a706bfaf9cd65dccf18140187f7ad04839 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 27 Aug 2018 13:00:17 +0200 Subject: asm-generic/tlb, arch: Provide generic VIPT cache flush The one obvious thing SH and ARM want is a sensible default for tlb_start_vma(). (also: https://lkml.org/lkml/2004/1/15/6 ) Avoid all VIPT architectures providing their own tlb_start_vma() implementation and rely on architectures to provide a no-op flush_cache_range() when it is not relevant. This patch makes tlb_start_vma() default to flush_cache_range(), which should be right and sufficient. The only exceptions that I found where (oddly): - m68k-mmu - sparc64 - unicore Those architectures appear to have flush_cache_range(), but their current tlb_start_vma() does not call it. 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: David Miller Cc: Guan Xuetao 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 --- arch/arc/include/asm/tlb.h | 9 --------- arch/mips/include/asm/tlb.h | 9 --------- arch/nds32/include/asm/tlb.h | 6 ------ arch/nios2/include/asm/tlb.h | 10 ---------- arch/parisc/include/asm/tlb.h | 5 ----- arch/sparc/include/asm/tlb_32.h | 5 ----- arch/xtensa/include/asm/tlb.h | 9 --------- include/asm-generic/tlb.h | 19 +++++++++++-------- 8 files changed, 11 insertions(+), 61 deletions(-) (limited to 'include') diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h index a9db5f62aaf3..7af2b373ebe7 100644 --- a/arch/arc/include/asm/tlb.h +++ b/arch/arc/include/asm/tlb.h @@ -23,15 +23,6 @@ do { \ * * 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 { \ diff --git a/arch/mips/include/asm/tlb.h b/arch/mips/include/asm/tlb.h index b6823b9e94da..32b8a8187733 100644 --- a/arch/mips/include/asm/tlb.h +++ b/arch/mips/include/asm/tlb.h @@ -5,15 +5,6 @@ #include #include -/* - * 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) diff --git a/arch/nds32/include/asm/tlb.h b/arch/nds32/include/asm/tlb.h index b35ae5eae3ab..0bf7c9482381 100644 --- a/arch/nds32/include/asm/tlb.h +++ b/arch/nds32/include/asm/tlb.h @@ -4,12 +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) \ diff --git a/arch/nios2/include/asm/tlb.h b/arch/nios2/include/asm/tlb.h index d3bc648e08b5..9b518c6d0f62 100644 --- a/arch/nios2/include/asm/tlb.h +++ b/arch/nios2/include/asm/tlb.h @@ -15,16 +15,6 @@ 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. - */ -#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) diff --git a/arch/parisc/include/asm/tlb.h b/arch/parisc/include/asm/tlb.h index 0c881e74d8a6..b1984f9cd3af 100644 --- a/arch/parisc/include/asm/tlb.h +++ b/arch/parisc/include/asm/tlb.h @@ -7,11 +7,6 @@ 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); \ diff --git a/arch/sparc/include/asm/tlb_32.h b/arch/sparc/include/asm/tlb_32.h index 343cea19e573..68d817273de8 100644 --- a/arch/sparc/include/asm/tlb_32.h +++ b/arch/sparc/include/asm/tlb_32.h @@ -2,11 +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); \ diff --git a/arch/xtensa/include/asm/tlb.h b/arch/xtensa/include/asm/tlb.h index 0d766f9c1083..1a93e350382e 100644 --- a/arch/xtensa/include/asm/tlb.h +++ b/arch/xtensa/include/asm/tlb.h @@ -16,19 +16,10 @@ #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) \ diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index e75620e41ba4..f0aa53db5e60 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -19,6 +19,7 @@ #include #include #include +#include #ifdef CONFIG_MMU @@ -356,17 +357,19 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) * the vmas are adjusted to only cover the region to be torn down. */ #ifndef tlb_start_vma -#define tlb_start_vma(tlb, vma) do { } while (0) +#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) \ - tlb_flush_mmu_tlbonly(tlb); \ - } while (0) - #ifndef tlb_end_vma -#define tlb_end_vma __tlb_end_vma +#define tlb_end_vma(tlb, vma) \ +do { \ + if (!tlb->fullmm) \ + tlb_flush_mmu_tlbonly(tlb); \ +} while (0) #endif #ifndef __tlb_remove_tlb_entry -- cgit v1.2.3 From 5f307be18b32aeff7bbad540c0d3897ecedbeb56 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 4 Sep 2018 13:18:15 +0200 Subject: asm-generic/tlb, arch: Provide generic tlb_flush() based on flush_tlb_range() Provide a generic tlb_flush() implementation that relies on flush_tlb_range(). This is a little awkward because flush_tlb_range() assumes a VMA for range invalidation, but we no longer have one. Audit of all flush_tlb_range() implementations shows only vma->vm_mm and vma->vm_flags are used, and of the latter only VM_EXEC (I-TLB invalidates) and VM_HUGETLB (large TLB invalidate) are used. Therefore, track VM_EXEC and VM_HUGETLB in two more bits, and create a 'fake' VMA. This allows architectures that have a reasonably efficient flush_tlb_range() to not require any additional effort. 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 --- arch/arm64/include/asm/tlb.h | 1 + arch/powerpc/include/asm/tlb.h | 1 + arch/riscv/include/asm/tlb.h | 1 + arch/x86/include/asm/tlb.h | 1 + include/asm-generic/tlb.h | 95 ++++++++++++++++++++++++++++++++++++------ 5 files changed, 87 insertions(+), 12 deletions(-) (limited to 'include') 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 diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index b018e9f9b491..34fba1ce27f7 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -28,6 +28,7 @@ #define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry __tlb_remove_tlb_entry +#define tlb_flush tlb_flush extern void tlb_flush(struct mmu_gather *tlb); /* Get the generic bits... */ 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 static inline void tlb_flush(struct mmu_gather *tlb) 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 diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index f0aa53db5e60..e6a4c407be6c 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -95,7 +95,7 @@ * flush the entire TLB irrespective of the range. For instance * x86-PAE needs this when changing top-level entries. * - * And requires the architecture to provide and implement tlb_flush(). + * And allows the architecture to provide and implement tlb_flush(): * * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make * use of: @@ -111,7 +111,10 @@ * * - tlb_get_unmap_shift() / tlb_get_unmap_size() * - * returns the smallest TLB entry size unmapped in this range + * returns the smallest TLB entry size unmapped in this range. + * + * If an architecture does not provide tlb_flush() a default implementation + * based on flush_tlb_range() will be used. * * Additionally there are a few opt-in features: * @@ -245,6 +248,12 @@ struct mmu_gather { unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; + /* + * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma + */ + unsigned int vma_exec : 1; + unsigned int vma_huge : 1; + unsigned int batch_count; struct mmu_gather_batch *active; @@ -286,8 +295,59 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; + /* + * Do not reset mmu_gather::vma_* fields here, we do not + * call into tlb_start_vma() again to set them if there is an + * intermediate flush. + */ +} + +#ifndef tlb_flush + +#if defined(tlb_start_vma) || defined(tlb_end_vma) +#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma() +#endif + +static inline void tlb_flush(struct mmu_gather *tlb) +{ + if (tlb->fullmm || tlb->need_flush_all) { + flush_tlb_mm(tlb->mm); + } else if (tlb->end) { + struct vm_area_struct vma = { + .vm_mm = tlb->mm, + .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) | + (tlb->vma_huge ? VM_HUGETLB : 0), + }; + + flush_tlb_range(&vma, tlb->start, tlb->end); + } +} + +static inline void +tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + /* + * flush_tlb_range() implementations that look at VM_HUGETLB (tile, + * mips-4k) flush only large pages. + * + * flush_tlb_range() implementations that flush I-TLB also flush D-TLB + * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing + * range. + * + * We rely on tlb_end_vma() to issue a flush, such that when we reset + * these values the batch is empty. + */ + tlb->vma_huge = !!(vma->vm_flags & VM_HUGETLB); + tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); } +#else + +static inline void +tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } + +#endif + static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { if (!tlb->end) @@ -357,19 +417,30 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) * the vmas are adjusted to only cover the region to be torn down. */ #ifndef tlb_start_vma -#define tlb_start_vma(tlb, vma) \ -do { \ - if (!tlb->fullmm) \ - flush_cache_range(vma, vma->vm_start, vma->vm_end); \ -} while (0) +static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + if (tlb->fullmm) + return; + + tlb_update_vma_flags(tlb, vma); + flush_cache_range(vma, vma->vm_start, vma->vm_end); +} #endif #ifndef tlb_end_vma -#define tlb_end_vma(tlb, vma) \ -do { \ - if (!tlb->fullmm) \ - tlb_flush_mmu_tlbonly(tlb); \ -} while (0) +static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + if (tlb->fullmm) + return; + + /* + * Do a TLB flush and reset the range at VMA boundaries; this avoids + * the ranges growing with the unused space between consecutive VMAs, + * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on + * this. + */ + tlb_flush_mmu_tlbonly(tlb); +} #endif #ifndef __tlb_remove_tlb_entry -- cgit v1.2.3 From a30e32bd79e924f460b8b83408d88af34a402f6d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 11 Oct 2018 16:51:51 +0200 Subject: asm-generic/tlb: Provide generic tlb_flush() based on flush_tlb_mm() When an architecture does not have (an efficient) flush_tlb_range(), but instead always uses full TLB invalidates, the current generic tlb_flush() is sub-optimal, for it will generate extra flushes in order to keep the range small. But if we cannot do range flushes, that is a moot concern. Optionally provide this simplified default. 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 | 41 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index e6a4c407be6c..6850d8bab6d3 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -114,7 +114,8 @@ * returns the smallest TLB entry size unmapped in this range. * * If an architecture does not provide tlb_flush() a default implementation - * based on flush_tlb_range() will be used. + * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is + * specified, in which case we'll default to flush_tlb_mm(). * * Additionally there are a few opt-in features: * @@ -140,6 +141,9 @@ * the page-table pages. Required if you use HAVE_RCU_TABLE_FREE and your * architecture uses the Linux page-tables natively. * + * MMU_GATHER_NO_RANGE + * + * Use this if your architecture lacks an efficient flush_tlb_range(). */ #define HAVE_GENERIC_MMU_GATHER @@ -302,12 +306,45 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) */ } +#ifdef CONFIG_MMU_GATHER_NO_RANGE + +#if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma) +#error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma() +#endif + +/* + * When an architecture does not have efficient means of range flushing TLBs + * there is no point in doing intermediate flushes on tlb_end_vma() to keep the + * range small. We equally don't have to worry about page granularity or other + * things. + * + * All we need to do is issue a full flush for any !0 range. + */ +static inline void tlb_flush(struct mmu_gather *tlb) +{ + if (tlb->end) + flush_tlb_mm(tlb->mm); +} + +static inline void +tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } + +#define tlb_end_vma tlb_end_vma +static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { } + +#else /* CONFIG_MMU_GATHER_NO_RANGE */ + #ifndef tlb_flush #if defined(tlb_start_vma) || defined(tlb_end_vma) #error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma() #endif +/* + * When an architecture does not provide its own tlb_flush() implementation + * but does have a reasonably efficient flush_vma_range() implementation + * use that. + */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->fullmm || tlb->need_flush_all) { @@ -348,6 +385,8 @@ tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #endif +#endif /* CONFIG_MMU_GATHER_NO_RANGE */ + static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { if (!tlb->end) -- cgit v1.2.3 From 8b6dd0c47894e2c190560914318aa4181bc8c2f2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 4 Sep 2018 16:00:53 +0200 Subject: asm-generic/tlb, ia64: Conditionally provide tlb_migrate_finish() Needed for ia64 -- alternatively we drop the entire hook. 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 --- include/asm-generic/tlb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 6850d8bab6d3..1c861989b704 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -604,6 +604,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm #endif /* CONFIG_MMU */ +#ifndef tlb_migrate_finish #define tlb_migrate_finish(mm) do {} while (0) +#endif #endif /* _ASM_GENERIC__TLB_H */ -- cgit v1.2.3 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 'include') 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 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 'include') 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 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 'include') 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 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 'include') 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 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 'include') 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 From 6455959819bf2469190ae9f6b4ccebaa9827e884 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 19 Feb 2019 14:38:37 +0100 Subject: ia64/tlb: Eradicate tlb_migrate_finish() callback Only ia64-sn2 uses this as an optimization, and there it is of questionable correctness due to the mm_users==1 test. Remove it entirely. No change in behavior intended. Signed-off-by: Peter Zijlstra (Intel) 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 --- Documentation/core-api/cachetlb.rst | 10 ---------- arch/ia64/include/asm/machvec.h | 13 ------------- arch/ia64/include/asm/machvec_sn2.h | 2 -- arch/ia64/include/asm/tlb.h | 2 -- arch/ia64/sn/kernel/sn2/sn2_smp.c | 7 ------- arch/nds32/include/asm/tlbflush.h | 1 - include/asm-generic/tlb.h | 4 ---- kernel/sched/core.c | 1 - 8 files changed, 40 deletions(-) (limited to 'include') diff --git a/Documentation/core-api/cachetlb.rst b/Documentation/core-api/cachetlb.rst index 6eb9d3f090cd..93cb65d52720 100644 --- a/Documentation/core-api/cachetlb.rst +++ b/Documentation/core-api/cachetlb.rst @@ -101,16 +101,6 @@ changes occur: translations for software managed TLB configurations. The sparc64 port currently does this. -6) ``void tlb_migrate_finish(struct mm_struct *mm)`` - - This interface is called at the end of an explicit - process migration. This interface provides a hook - to allow a platform to update TLB or context-specific - information for the address space. - - The ia64 sn2 platform is one example of a platform - that uses this interface. - Next, we have the cache flushing interfaces. In general, when Linux is changing an existing virtual-->physical mapping to a new value, the sequence will be in one of the following forms:: 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 *); @@ -79,11 +78,6 @@ 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 @@ -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/tlb.h b/arch/ia64/include/asm/tlb.h index 849fab9ccb33..86ec034ba499 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -47,8 +47,6 @@ #include #include -#define tlb_migrate_finish(mm) platform_tlb_migrate_finish(mm) - #include #endif /* _ASM_IA64_TLB_H */ 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/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/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index fc661b4675ff..b9edc7608d90 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -604,8 +604,4 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm #endif /* CONFIG_MMU */ -#ifndef tlb_migrate_finish -#define tlb_migrate_finish(mm) do {} while (0) -#endif - #endif /* _ASM_GENERIC__TLB_H */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4778c48a7fda..ade3f2287d1f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1151,7 +1151,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, /* Need help from migration thread: drop lock and wait. */ task_rq_unlock(rq, p, &rf); stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); - tlb_migrate_finish(p->mm); return 0; } else if (task_on_rq_queued(p)) { /* -- cgit v1.2.3