From 15a23ffa2fc91cebdac44d4aee994f59d5c28dc0 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 29 Oct 2005 18:16:01 -0700 Subject: [PATCH] mm: tlb_gather_mmu get_cpu_var tlb_gather_mmu dates from before kernel preemption was allowed, and uses smp_processor_id or __get_cpu_var to find its per-cpu mmu_gather. That works because it's currently only called after getting page_table_lock, which is not dropped until after the matching tlb_finish_mmu. But don't rely on that, it will soon change: now disable preemption internally by proper get_cpu_var in tlb_gather_mmu, put_cpu_var in tlb_finish_mmu. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/tlb.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/asm-generic/tlb.h') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 7d02983..c823262 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -35,9 +35,7 @@ #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. This structure - * can be per-CPU or per-MM as the page table lock is held for the duration of - * TLB shootdown. + * any data needed by arch specific code for tlb_remove_page. */ struct mmu_gather { struct mm_struct *mm; @@ -57,7 +55,7 @@ DECLARE_PER_CPU(struct mmu_gather, mmu_gathers); static inline struct mmu_gather * tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) { - struct mmu_gather *tlb = &per_cpu(mmu_gathers, smp_processor_id()); + struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); tlb->mm = mm; @@ -85,7 +83,7 @@ tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) /* tlb_finish_mmu * Called at the end of the shootdown operation to free up any resources - * that were required. The page table lock is still held at this point. + * that were required. */ static inline void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) @@ -101,6 +99,8 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) /* keep the page table cache within bounds */ check_pgt_cache(); + + put_cpu_var(mmu_gathers); } static inline unsigned int -- cgit v1.1 From 4d6ddfa9242bc3d27fb0f7248f6fdee0299c731f Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 29 Oct 2005 18:16:02 -0700 Subject: [PATCH] mm: tlb_is_full_mm was obscure tlb_is_full_mm? What does that mean? The TLB is full? No, it means that the mm's last user has gone and the whole mm is being torn down. And it's an inline function because sparc64 uses a different (slightly better) "tlb_frozen" name for the flag others call "fullmm". And now the ptep_get_and_clear_full macro used in zap_pte_range refers directly to tlb->fullmm, which would be wrong for sparc64. Rather than correct that, I'd prefer to scrap tlb_is_full_mm altogether, and change sparc64 to just use the same poor name as everyone else - is that okay? Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/tlb.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/asm-generic/tlb.h') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index c823262..5d352a7 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -103,12 +103,6 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) put_cpu_var(mmu_gathers); } -static inline unsigned int -tlb_is_full_mm(struct mmu_gather *tlb) -{ - return tlb->fullmm; -} - /* 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 -- cgit v1.1 From fc2acab31be8e869b2d5f6de12f557f6f054f19c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 29 Oct 2005 18:16:03 -0700 Subject: [PATCH] mm: tlb_finish_mmu forget rss zap_pte_range has been counting the pages it frees in tlb->freed, then tlb_finish_mmu has used that to update the mm's rss. That got stranger when I added anon_rss, yet updated it by a different route; and stranger when rss and anon_rss became mm_counters with special access macros. And it would no longer be viable if we're relying on page_table_lock to stabilize the mm_counter, but calling tlb_finish_mmu outside that lock. Remove the mmu_gather's freed field, let tlb_finish_mmu stick to its own business, just decrement the rss mm_counter in zap_pte_range (yes, there was some point to batching the update, and a subsequent patch restores that). And forget the anal paranoia of first reading the counter to avoid going negative - if rss does go negative, just fix that bug. Remove the mmu_gather's flushes and avoided_flushes from arm and arm26: no use was being made of them. But arm26 alone was actually using the freed, in the way some others use need_flush: give it a need_flush. arm26 seems to prefer spaces to tabs here: respect that. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/tlb.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/asm-generic/tlb.h') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 5d352a7..cdd4145 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -42,7 +42,6 @@ struct mmu_gather { unsigned int nr; /* set to ~0U means fast mode */ unsigned int need_flush;/* Really unmapped some ptes? */ unsigned int fullmm; /* non-zero means full mm flush */ - unsigned long freed; struct page * pages[FREE_PTE_NR]; }; @@ -63,7 +62,6 @@ tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) tlb->nr = num_online_cpus() > 1 ? 0U : ~0U; tlb->fullmm = full_mm_flush; - tlb->freed = 0; return tlb; } @@ -88,13 +86,6 @@ tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) static inline void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) { - int freed = tlb->freed; - struct mm_struct *mm = tlb->mm; - int rss = get_mm_counter(mm, rss); - - if (rss < freed) - freed = rss; - add_mm_counter(mm, rss, -freed); tlb_flush_mmu(tlb, start, end); /* keep the page table cache within bounds */ -- cgit v1.1