diff options
| -rw-r--r-- | arch/s390/include/asm/tlb.h | 3 | ||||
| -rw-r--r-- | include/asm-generic/tlb.h | 31 | ||||
| -rw-r--r-- | mm/memory.c | 23 | ||||
| -rw-r--r-- | mm/mmu_gather.c | 33 |
4 files changed, 82 insertions, 8 deletions
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 05142226d65d..b91f4a9b044c 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -41,6 +41,9 @@ static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, * Release the page cache reference for a pte removed by * tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page * has already been freed, so just do free_page_and_swap_cache. + * + * s390 doesn't delay rmap removal, so there is nothing encoded in + * the page pointer. */ static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, struct encoded_page *page, diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 54d03d1e712e..b46617207c93 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -263,6 +263,28 @@ struct mmu_gather_batch { extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct encoded_page *page, int page_size); + +#ifdef CONFIG_SMP +/* + * This both sets 'delayed_rmap', and returns true. It would be an inline + * function, except we define it before the 'struct mmu_gather'. + */ +#define tlb_delay_rmap(tlb) (((tlb)->delayed_rmap = 1), true) +extern void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma); +#endif + +#endif + +/* + * We have a no-op version of the rmap removal that doesn't + * delay anything. That is used on S390, which flushes remote + * TLBs synchronously, and on UP, which doesn't have any + * remote TLBs to flush and is not preemptible due to this + * all happening under the page table lock. + */ +#ifndef tlb_delay_rmap +#define tlb_delay_rmap(tlb) (false) +static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #endif /* @@ -296,6 +318,11 @@ struct mmu_gather { unsigned int freed_tables : 1; /* + * Do we have pending delayed rmap removals? + */ + unsigned int delayed_rmap : 1; + + /* * at which levels have we cleared entries? */ unsigned int cleared_ptes : 1; @@ -440,9 +467,9 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, tlb_flush_mmu(tlb); } -static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) +static __always_inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page, unsigned int flags) { - return __tlb_remove_page_size(tlb, encode_page(page, 0), PAGE_SIZE); + return __tlb_remove_page_size(tlb, encode_page(page, flags), PAGE_SIZE); } /* tlb_remove_page diff --git a/mm/memory.c b/mm/memory.c index 1749c638734f..6c85cba02113 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1374,6 +1374,8 @@ again: break; if (pte_present(ptent)) { + unsigned int delay_rmap; + page = vm_normal_page(vma, addr, ptent); if (unlikely(!should_zap_page(details, page))) continue; @@ -1385,20 +1387,26 @@ again: if (unlikely(!page)) continue; + delay_rmap = 0; if (!PageAnon(page)) { if (pte_dirty(ptent)) { - force_flush = 1; set_page_dirty(page); + if (tlb_delay_rmap(tlb)) { + delay_rmap = 1; + force_flush = 1; + } } if (pte_young(ptent) && likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); } rss[mm_counter(page)]--; - page_remove_rmap(page, vma, false); - if (unlikely(page_mapcount(page) < 0)) - print_bad_pte(vma, addr, ptent, page); - if (unlikely(__tlb_remove_page(tlb, page))) { + if (!delay_rmap) { + page_remove_rmap(page, vma, false); + if (unlikely(page_mapcount(page) < 0)) + print_bad_pte(vma, addr, ptent, page); + } + if (unlikely(__tlb_remove_page(tlb, page, delay_rmap))) { force_flush = 1; addr += PAGE_SIZE; break; @@ -1455,8 +1463,11 @@ again: arch_leave_lazy_mmu_mode(); /* Do the actual TLB flush before dropping ptl */ - if (force_flush) + if (force_flush) { tlb_flush_mmu_tlbonly(tlb); + if (tlb->delayed_rmap) + tlb_flush_rmaps(tlb, vma); + } pte_unmap_unlock(start_pte, ptl); /* diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 382581c4a9f6..1de1cf9ba581 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -9,6 +9,7 @@ #include <linux/rcupdate.h> #include <linux/smp.h> #include <linux/swap.h> +#include <linux/rmap.h> #include <asm/pgalloc.h> #include <asm/tlb.h> @@ -19,6 +20,10 @@ static bool tlb_next_batch(struct mmu_gather *tlb) { struct mmu_gather_batch *batch; + /* No more batching if we have delayed rmaps pending */ + if (tlb->delayed_rmap) + return false; + batch = tlb->active; if (batch->next) { tlb->active = batch->next; @@ -43,6 +48,33 @@ static bool tlb_next_batch(struct mmu_gather *tlb) return true; } +#ifdef CONFIG_SMP +/** + * tlb_flush_rmaps - do pending rmap removals after we have flushed the TLB + * @tlb: the current mmu_gather + * + * Note that because of how tlb_next_batch() above works, we will + * never start new batches with pending delayed rmaps, so we only + * need to walk through the current active batch. + */ +void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + struct mmu_gather_batch *batch; + + batch = tlb->active; + for (int i = 0; i < batch->nr; i++) { + struct encoded_page *enc = batch->encoded_pages[i]; + + if (encoded_page_flags(enc)) { + struct page *page = encoded_page_ptr(enc); + page_remove_rmap(page, vma, false); + } + } + + tlb->delayed_rmap = 0; +} +#endif + static void tlb_batch_pages_flush(struct mmu_gather *tlb) { struct mmu_gather_batch *batch; @@ -284,6 +316,7 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, tlb->active = &tlb->local; tlb->batch_count = 0; #endif + tlb->delayed_rmap = 0; tlb_table_init(tlb); #ifdef CONFIG_MMU_GATHER_PAGE_SIZE |