From: Hugh Dickins 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 --- include/asm-arm/tlb.h | 5 +++-- include/asm-arm26/tlb.h | 7 ++++--- include/asm-generic/tlb.h | 10 +++++----- include/asm-ia64/tlb.h | 6 ++++-- include/asm-sparc64/tlb.h | 4 +++- 5 files changed, 19 insertions(+), 13 deletions(-) diff -puN include/asm-arm26/tlb.h~mm-tlb_gather_mmu-get_cpu_var include/asm-arm26/tlb.h --- devel/include/asm-arm26/tlb.h~mm-tlb_gather_mmu-get_cpu_var 2005-09-25 15:31:15.000000000 -0700 +++ devel-akpm/include/asm-arm26/tlb.h 2005-09-25 15:31:15.000000000 -0700 @@ -17,13 +17,12 @@ struct mmu_gather { unsigned int avoided_flushes; }; -extern struct mmu_gather mmu_gathers[NR_CPUS]; +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) { - int cpu = smp_processor_id(); - struct mmu_gather *tlb = &mmu_gathers[cpu]; + struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); tlb->mm = mm; tlb->freed = 0; @@ -52,6 +51,8 @@ tlb_finish_mmu(struct mmu_gather *tlb, u /* keep the page table cache within bounds */ check_pgt_cache(); + + put_cpu_var(mmu_gathers); } diff -puN include/asm-arm/tlb.h~mm-tlb_gather_mmu-get_cpu_var include/asm-arm/tlb.h --- devel/include/asm-arm/tlb.h~mm-tlb_gather_mmu-get_cpu_var 2005-09-25 15:31:15.000000000 -0700 +++ devel-akpm/include/asm-arm/tlb.h 2005-09-25 15:31:15.000000000 -0700 @@ -39,8 +39,7 @@ DECLARE_PER_CPU(struct mmu_gather, mmu_g static inline struct mmu_gather * tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) { - int cpu = smp_processor_id(); - struct mmu_gather *tlb = &per_cpu(mmu_gathers, cpu); + struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); tlb->mm = mm; tlb->freed = 0; @@ -65,6 +64,8 @@ tlb_finish_mmu(struct mmu_gather *tlb, u /* keep the page table cache within bounds */ check_pgt_cache(); + + put_cpu_var(mmu_gathers); } static inline unsigned int tlb_is_full_mm(struct mmu_gather *tlb) diff -puN include/asm-generic/tlb.h~mm-tlb_gather_mmu-get_cpu_var include/asm-generic/tlb.h --- devel/include/asm-generic/tlb.h~mm-tlb_gather_mmu-get_cpu_var 2005-09-25 15:31:15.000000000 -0700 +++ devel-akpm/include/asm-generic/tlb.h 2005-09-25 15:31:15.000000000 -0700 @@ -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_g 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, un /* 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, u /* keep the page table cache within bounds */ check_pgt_cache(); + + put_cpu_var(mmu_gathers); } static inline unsigned int diff -puN include/asm-ia64/tlb.h~mm-tlb_gather_mmu-get_cpu_var include/asm-ia64/tlb.h --- devel/include/asm-ia64/tlb.h~mm-tlb_gather_mmu-get_cpu_var 2005-09-25 15:31:15.000000000 -0700 +++ devel-akpm/include/asm-ia64/tlb.h 2005-09-25 15:31:15.000000000 -0700 @@ -129,7 +129,7 @@ ia64_tlb_flush_mmu (struct mmu_gather *t static inline struct mmu_gather * tlb_gather_mmu (struct mm_struct *mm, unsigned int full_mm_flush) { - struct mmu_gather *tlb = &__get_cpu_var(mmu_gathers); + struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); tlb->mm = mm; /* @@ -154,7 +154,7 @@ tlb_gather_mmu (struct mm_struct *mm, un /* * Called at the end of the shootdown operation to free up any resources that were - * collected. The page table lock is still held at this point. + * collected. */ static inline void tlb_finish_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end) @@ -174,6 +174,8 @@ tlb_finish_mmu (struct mmu_gather *tlb, /* keep the page table cache within bounds */ check_pgt_cache(); + + put_cpu_var(mmu_gathers); } static inline unsigned int diff -puN include/asm-sparc64/tlb.h~mm-tlb_gather_mmu-get_cpu_var include/asm-sparc64/tlb.h --- devel/include/asm-sparc64/tlb.h~mm-tlb_gather_mmu-get_cpu_var 2005-09-25 15:31:15.000000000 -0700 +++ devel-akpm/include/asm-sparc64/tlb.h 2005-09-25 15:31:15.000000000 -0700 @@ -44,7 +44,7 @@ extern void flush_tlb_pending(void); static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) { - struct mmu_gather *mp = &__get_cpu_var(mmu_gathers); + struct mmu_gather *mp = &get_cpu_var(mmu_gathers); BUG_ON(mp->tlb_nr); @@ -97,6 +97,8 @@ static inline void tlb_finish_mmu(struct /* keep the page table cache within bounds */ check_pgt_cache(); + + put_cpu_var(mmu_gathers); } static inline unsigned int tlb_is_full_mm(struct mmu_gather *mp) _