summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorHuang Ying <ying.huang@intel.com>2023-04-24 09:54:08 +0300
committerAndrew Morton <akpm@linux-foundation.org>2023-04-27 23:42:16 +0300
commit4d4b6d66db63ceed399f1fb1a4b24081d2590eb1 (patch)
treea92cbb17d4be5951c437e3bbc6b7544d63cdee5b /mm
parent01106e140835ff94fdef79d66f166b87b0c89824 (diff)
downloadlinux-4d4b6d66db63ceed399f1fb1a4b24081d2590eb1.tar.xz
mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
0Day/LKP reported a performance regression for commit 7e12beb8ca2a ("migrate_pages: batch flushing TLB"). In the commit, the TLB flushing during page migration is batched. So, in try_to_migrate_one(), ptep_clear_flush() is replaced with set_tlb_ubc_flush_pending(). In further investigation, it is found that the TLB flushing can be avoided in ptep_clear_flush() if the PTE is inaccessible. In fact, we can optimize in similar way for the batched TLB flushing too to improve the performance. So in this patch, we check pte_accessible() before set_tlb_ubc_flush_pending() in try_to_unmap/migrate_one(). Tests show that the benchmark score of the anon-cow-rand-mt test case of vm-scalability test suite can improve up to 2.1% with the patch on a Intel server machine. The TLB flushing IPI can reduce up to 44.3%. Link: https://lore.kernel.org/oe-lkp/202303192325.ecbaf968-yujie.liu@intel.com Link: https://lore.kernel.org/oe-lkp/ab92aaddf1b52ede15e2c608696c36765a2602c1.camel@intel.com/ Link: https://lkml.kernel.org/r/20230424065408.188498-1-ying.huang@intel.com Fixes: 7e12beb8ca2a ("migrate_pages: batch flushing TLB") Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reported-by: kernel test robot <yujie.liu@intel.com> Reviewed-by: Nadav Amit <namit@vmware.com> Reviewed-by: Xin Hao <xhao@linux.alibaba.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: David Hildenbrand <david@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/rmap.c12
1 files changed, 8 insertions, 4 deletions
diff --git a/mm/rmap.c b/mm/rmap.c
index ba901c416785..19392e090bec 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -642,10 +642,14 @@ void try_to_unmap_flush_dirty(void)
#define TLB_FLUSH_BATCH_PENDING_LARGE \
(TLB_FLUSH_BATCH_PENDING_MASK / 2)
-static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
+static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval)
{
struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
int batch;
+ bool writable = pte_dirty(pteval);
+
+ if (!pte_accessible(mm, pteval))
+ return;
arch_tlbbatch_add_mm(&tlb_ubc->arch, mm);
tlb_ubc->flush_required = true;
@@ -729,7 +733,7 @@ void flush_tlb_batched_pending(struct mm_struct *mm)
}
}
#else
-static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
+static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval)
{
}
@@ -1580,7 +1584,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
*/
pteval = ptep_get_and_clear(mm, address, pvmw.pte);
- set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
+ set_tlb_ubc_flush_pending(mm, pteval);
} else {
pteval = ptep_clear_flush(vma, address, pvmw.pte);
}
@@ -1961,7 +1965,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
*/
pteval = ptep_get_and_clear(mm, address, pvmw.pte);
- set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
+ set_tlb_ubc_flush_pending(mm, pteval);
} else {
pteval = ptep_clear_flush(vma, address, pvmw.pte);
}