Fix up powerpc to the new mmu_gather stuffs. 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 TIF bit to track the laxy_mmu state. Signed-off-by: Peter Zijlstra Cc: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pgalloc.h | 4 +-- arch/powerpc/include/asm/thread_info.h | 2 + arch/powerpc/include/asm/tlb.h | 10 +++++++++ arch/powerpc/include/asm/tlbflush.h | 16 ++++++++++----- arch/powerpc/kernel/process.c | 18 +++++++++++++++++ arch/powerpc/mm/pgtable.c | 34 +++++++++++++++++++++++---------- arch/powerpc/mm/tlb_hash32.c | 2 - arch/powerpc/mm/tlb_hash64.c | 12 ++++++----- arch/powerpc/mm/tlb_nohash.c | 2 - 9 files changed, 76 insertions(+), 24 deletions(-) Index: linux-2.6/arch/powerpc/include/asm/tlb.h =================================================================== --- linux-2.6.orig/arch/powerpc/include/asm/tlb.h +++ linux-2.6/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... */ Index: linux-2.6/arch/powerpc/include/asm/tlbflush.h =================================================================== --- linux-2.6.orig/arch/powerpc/include/asm/tlbflush.h +++ linux-2.6/arch/powerpc/include/asm/tlbflush.h @@ -108,18 +108,24 @@ extern void hpte_need_flush(struct mm_st static inline void arch_enter_lazy_mmu_mode(void) { - struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); + struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch); batch->active = 1; + + put_cpu_var(ppc64_tlb_batch); } static inline void arch_leave_lazy_mmu_mode(void) { - struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); + struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch); + + if (batch->active) { + if (batch->index) + __flush_tlb_pending(batch); + batch->active = 0; + } - if (batch->index) - __flush_tlb_pending(batch); - batch->active = 0; + put_cpu_var(ppc64_tlb_batch); } #define arch_flush_lazy_mmu_mode() do {} while (0) Index: linux-2.6/arch/powerpc/kernel/process.c =================================================================== --- linux-2.6.orig/arch/powerpc/kernel/process.c +++ linux-2.6/arch/powerpc/kernel/process.c @@ -389,6 +389,9 @@ struct task_struct *__switch_to(struct t struct thread_struct *new_thread, *old_thread; unsigned long flags; struct task_struct *last; +#ifdef CONFIG_PPC64 + struct ppc64_tlb_batch *batch; +#endif #ifdef CONFIG_SMP /* avoid complexity of lazy save/restore of fpu @@ -479,6 +482,14 @@ struct task_struct *__switch_to(struct t old_thread->accum_tb += (current_tb - start_tb); new_thread->start_tb = current_tb; } + + batch = &__get_cpu_var(ppc64_tlb_batch); + if (batch->active) { + set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU); + if (batch->index) + __flush_tlb_pending(batch); + batch->active = 0; + } #endif local_irq_save(flags); @@ -495,6 +506,13 @@ struct task_struct *__switch_to(struct t hard_irq_disable(); last = _switch(old_thread, new_thread); +#ifdef CONFIG_PPC64 + if (test_and_clear_ti_thread_flag(task_thread_info(new), TIF_LAZY_MMU)) { + batch = &__get_cpu_var(ppc64_tlb_batch); + batch->active = 1; + } +#endif + local_irq_restore(flags); return last; Index: linux-2.6/arch/powerpc/mm/pgtable.c =================================================================== --- linux-2.6.orig/arch/powerpc/mm/pgtable.c +++ linux-2.6/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_ga * 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 @@ -98,12 +95,30 @@ static void pte_free_submit(struct pte_f 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()))){ + /* + * A comment here about on why we have RCU freed page tables might be + * interesting, also explaining why we don't need any sort of grace + * period for mm_users == 1, and have some home brewn smp_call_func() + * for single frees. + * + * The only lockless page table walker I know of is gup_fast() which + * relies on irq_disable(). So my guess is that mm_users == 1 means + * that there cannot be another thread and so precludes gup_fast() + * concurrency. + * + * If there are, but we fail to batch, we need to IPI (all?) CPUs so as + * to serialize against the IRQ disable. In case we do batch, the RCU + * grace period is at least long enough to cover IRQ disabled sections + * (XXX assumption, not strictly true). + * + * All this results in us doing our own free batching and not using + * the generic mmu_gather batches (XXX fix that somehow?). + */ + + if (atomic_read(&tlb->mm->mm_users) < 2) { pgtable_free(table, shift); return; } @@ -125,10 +140,9 @@ void pgtable_free_tlb(struct mmu_gather } } -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; Index: linux-2.6/arch/powerpc/mm/tlb_hash64.c =================================================================== --- linux-2.6.orig/arch/powerpc/mm/tlb_hash64.c +++ linux-2.6/arch/powerpc/mm/tlb_hash64.c @@ -38,13 +38,11 @@ DEFINE_PER_CPU(struct ppc64_tlb_batch, p * neesd to be flushed. This function will either perform the flush * immediately or will batch it up if the current CPU has an active * batch on it. - * - * Must be called from within some kind of spinlock/non-preempt region... */ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pte, int huge) { - struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); + struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch); unsigned long vsid, vaddr; unsigned int psize; int ssize; @@ -99,6 +97,7 @@ void hpte_need_flush(struct mm_struct *m */ if (!batch->active) { flush_hash_page(vaddr, rpte, psize, ssize, 0); + put_cpu_var(ppc64_tlb_batch); return; } @@ -127,6 +126,7 @@ void hpte_need_flush(struct mm_struct *m batch->index = ++i; if (i >= PPC64_TLB_BATCH_NR) __flush_tlb_pending(batch); + put_cpu_var(ppc64_tlb_batch); } /* @@ -155,7 +155,7 @@ void __flush_tlb_pending(struct ppc64_tl 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); } /** Index: linux-2.6/arch/powerpc/include/asm/thread_info.h =================================================================== --- linux-2.6.orig/arch/powerpc/include/asm/thread_info.h +++ linux-2.6/arch/powerpc/include/asm/thread_info.h @@ -111,6 +111,7 @@ static inline struct thread_info *curren #define TIF_NOTIFY_RESUME 13 /* callback before returning to user */ #define TIF_FREEZE 14 /* Freezing for suspend */ #define TIF_RUNLATCH 15 /* Is the runlatch enabled? */ +#define TIF_LAZY_MMU 16 /* tlb_batch is active */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<mm); /* Push out batch of freed page tables */ - pte_free_finish(); + pte_free_finish(tlb); } /* -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/