diff options
| -rw-r--r-- | mm/mmu_gather.c | 24 |
1 files changed, 19 insertions, 5 deletions
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 99740e1dd273..8c943a6e1696 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -245,14 +245,28 @@ void tlb_finish_mmu(struct mmu_gather *tlb, { /* * If there are parallel threads are doing PTE changes on same range - * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB - * flush by batching, a thread has stable TLB entry can fail to flush - * the TLB by observing pte_none|!pte_dirty, for example so flush TLB - * forcefully if we detect parallel PTE batching threads. + * under non-exclusive lock (e.g., mmap_sem read-side) but defer TLB + * flush by batching, one thread may end up seeing inconsistent PTEs + * and result in having stale TLB entries. So flush TLB forcefully + * if we detect parallel PTE batching threads. + * + * However, some syscalls, e.g. munmap(), may free page tables, this + * needs force flush everything in the given range. Otherwise this + * may result in having stale TLB entries for some architectures, + * e.g. aarch64, that could specify flush what level TLB. */ if (mm_tlb_flush_nested(tlb->mm)) { + /* + * The aarch64 yields better performance with fullmm by + * avoiding multiple CPUs spamming TLBI messages at the + * same time. + * + * On x86 non-fullmm doesn't yield significant difference + * against fullmm. + */ + tlb->fullmm = 1; __tlb_reset_range(tlb); - __tlb_adjust_range(tlb, start, end - start); + tlb->freed_tables = 1; } tlb_flush_mmu(tlb); |