From: Peter Zijlstra Date: Wed, 25 May 2011 00:11:48 +0000 (-0700) Subject: powerpc: mmu_gather rework X-Git-Url: http://git.cdn.openwrt.org/?a=commitdiff_plain;h=d6bf29b44ddf3ca915f77b9383bee8b7a209f3fd;p=openwrt%2Fstaging%2Fblogic.git powerpc: mmu_gather rework Fix up powerpc to the new mmu_gather stuff. PPC has an extra batching queue to RCU free the actual pagetable allocations, use the ARCH extentions for that for now. For the ppc64_tlb_batch, which tracks the vaddrs to unhash from the hardware hash-table, keep using per-cpu arrays but flush on context switch and use a TLF bit to track the lazy_mmu state. Signed-off-by: Peter Zijlstra Acked-by: Benjamin Herrenschmidt Cc: David Miller Cc: Martin Schwidefsky Cc: Russell King Cc: Paul Mundt Cc: Jeff Dike Cc: Richard Weinberger Cc: Tony Luck Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Mel Gorman Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Namhyung Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h index abe8532bd14e..df1b4cbb2e70 100644 --- a/arch/powerpc/include/asm/pgalloc.h +++ b/arch/powerpc/include/asm/pgalloc.h @@ -32,13 +32,13 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) #ifdef CONFIG_SMP extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift); -extern void pte_free_finish(void); +extern void pte_free_finish(struct mmu_gather *tlb); #else /* CONFIG_SMP */ static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift) { pgtable_free(table, shift); } -static inline void pte_free_finish(void) { } +static inline void pte_free_finish(struct mmu_gather *tlb) { } #endif /* !CONFIG_SMP */ static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage, diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index d8529ef13b23..37c353e8af7c 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -139,10 +139,12 @@ static inline struct thread_info *current_thread_info(void) #define TLF_NAPPING 0 /* idle thread enabled NAP mode */ #define TLF_SLEEPING 1 /* suspend code enabled SLEEP mode */ #define TLF_RESTORE_SIGMASK 2 /* Restore signal mask in do_signal */ +#define TLF_LAZY_MMU 3 /* tlb_batch is active */ #define _TLF_NAPPING (1 << TLF_NAPPING) #define _TLF_SLEEPING (1 << TLF_SLEEPING) #define _TLF_RESTORE_SIGMASK (1 << TLF_RESTORE_SIGMASK) +#define _TLF_LAZY_MMU (1 << TLF_LAZY_MMU) #ifndef __ASSEMBLY__ #define HAVE_SET_RESTORE_SIGMASK 1 diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index e2b428b0f7ba..8f0ed7adcd12 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -28,6 +28,16 @@ #define tlb_start_vma(tlb, vma) do { } while (0) #define tlb_end_vma(tlb, vma) do { } while (0) +#define HAVE_ARCH_MMU_GATHER 1 + +struct pte_freelist_batch; + +struct arch_mmu_gather { + struct pte_freelist_batch *batch; +}; + +#define ARCH_MMU_GATHER_INIT (struct arch_mmu_gather){ .batch = NULL, } + extern void tlb_flush(struct mmu_gather *tlb); /* Get the generic bits... */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 095043d79946..91e52df3d81d 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -395,6 +395,9 @@ struct task_struct *__switch_to(struct task_struct *prev, struct thread_struct *new_thread, *old_thread; unsigned long flags; struct task_struct *last; +#ifdef CONFIG_PPC_BOOK3S_64 + struct ppc64_tlb_batch *batch; +#endif #ifdef CONFIG_SMP /* avoid complexity of lazy save/restore of fpu @@ -513,7 +516,17 @@ struct task_struct *__switch_to(struct task_struct *prev, old_thread->accum_tb += (current_tb - start_tb); new_thread->start_tb = current_tb; } -#endif +#endif /* CONFIG_PPC64 */ + +#ifdef CONFIG_PPC_BOOK3S_64 + batch = &__get_cpu_var(ppc64_tlb_batch); + if (batch->active) { + current_thread_info()->local_flags |= _TLF_LAZY_MMU; + if (batch->index) + __flush_tlb_pending(batch); + batch->active = 0; + } +#endif /* CONFIG_PPC_BOOK3S_64 */ local_irq_save(flags); @@ -528,6 +541,14 @@ struct task_struct *__switch_to(struct task_struct *prev, hard_irq_disable(); last = _switch(old_thread, new_thread); +#ifdef CONFIG_PPC_BOOK3S_64 + if (current_thread_info()->local_flags & _TLF_LAZY_MMU) { + current_thread_info()->local_flags &= ~_TLF_LAZY_MMU; + batch = &__get_cpu_var(ppc64_tlb_batch); + batch->active = 1; + } +#endif /* CONFIG_PPC_BOOK3S_64 */ + local_irq_restore(flags); return last; diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 6a3997f98dfb..6e72788598f8 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -33,8 +33,6 @@ #include "mmu_decl.h" -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); - #ifdef CONFIG_SMP /* @@ -43,7 +41,6 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); * freeing a page table page that is being walked without locks */ -static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur); static unsigned long pte_freelist_forced_free; struct pte_freelist_batch @@ -97,12 +94,10 @@ static void pte_free_submit(struct pte_freelist_batch *batch) void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift) { - /* This is safe since tlb_gather_mmu has disabled preemption */ - struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur); + struct pte_freelist_batch **batchp = &tlb->arch.batch; unsigned long pgf; - if (atomic_read(&tlb->mm->mm_users) < 2 || - cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))){ + if (atomic_read(&tlb->mm->mm_users) < 2) { pgtable_free(table, shift); return; } @@ -124,10 +119,9 @@ void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift) } } -void pte_free_finish(void) +void pte_free_finish(struct mmu_gather *tlb) { - /* This is safe since tlb_gather_mmu has disabled preemption */ - struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur); + struct pte_freelist_batch **batchp = &tlb->arch.batch; if (*batchp == NULL) return; diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c index 690566b66e8e..d555cdb06bc8 100644 --- a/arch/powerpc/mm/tlb_hash32.c +++ b/arch/powerpc/mm/tlb_hash32.c @@ -73,7 +73,7 @@ void tlb_flush(struct mmu_gather *tlb) } /* Push out batch of freed page tables */ - pte_free_finish(); + pte_free_finish(tlb); } /* diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index c14d09f614f3..5c94ca34cd79 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -155,7 +155,7 @@ void __flush_tlb_pending(struct ppc64_tlb_batch *batch) void tlb_flush(struct mmu_gather *tlb) { - struct ppc64_tlb_batch *tlbbatch = &__get_cpu_var(ppc64_tlb_batch); + struct ppc64_tlb_batch *tlbbatch = &get_cpu_var(ppc64_tlb_batch); /* If there's a TLB batch pending, then we must flush it because the * pages are going to be freed and we really don't want to have a CPU @@ -164,8 +164,10 @@ void tlb_flush(struct mmu_gather *tlb) if (tlbbatch->index) __flush_tlb_pending(tlbbatch); + put_cpu_var(ppc64_tlb_batch); + /* Push out batch of freed page tables */ - pte_free_finish(); + pte_free_finish(tlb); } /** diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index 2a030d89bbc6..8eaf67d32043 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -301,7 +301,7 @@ void tlb_flush(struct mmu_gather *tlb) flush_tlb_mm(tlb->mm); /* Push out batch of freed page tables */ - pte_free_finish(); + pte_free_finish(tlb); } /*