[125/212] mm,do_huge_pmd_numa_page: remove unnecessary TLB flushing code

Commit Message

Andrew Morton Sept. 2, 2021, 9:56 p.m. UTC

From: Huang Ying <[e-mail]>
Subject: mm,do_huge_pmd_numa_page: remove unnecessary TLB flushing code

Before commit c5b5a3dd2c1f ("mm: thp: refactor NUMA fault handling"), the
TLB flushing is done in do_huge_pmd_numa_page() itself via
flush_tlb_range().

But after commit c5b5a3dd2c1f ("mm: thp: refactor NUMA fault handling"),
the TLB flushing is done in migrate_pages() as in the following code path
anyway.

do_huge_pmd_numa_page
  migrate_misplaced_page
    migrate_pages

So now, the TLB flushing code in do_huge_pmd_numa_page() becomes
unnecessary.  So the code is deleted in this patch to simplify the code. 
This is only code cleanup, there's no visible performance difference.

The mmu_notifier_invalidate_range() in do_huge_pmd_numa_page() is
deleted too.  Because migrate_pages() takes care of that too when CPU
TLB is flushed.

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: "Huang, Ying" <[e-mail]>
Reviewed-by: Zi Yan <[e-mail]>
Reviewed-by: Yang Shi <[e-mail]>
Cc: Dan Carpenter <[e-mail]>
Cc: Mel Gorman <[e-mail]>
Cc: Christian Borntraeger <[e-mail]>
Cc: Gerald Schaefer <[e-mail]>
Cc: Heiko Carstens <[e-mail]>
Cc: Hugh Dickins <[e-mail]>
Cc: Andrea Arcangeli <[e-mail]>
Cc: Kirill A. Shutemov <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: Vasily Gorbik <[e-mail]>
Cc: Paolo Bonzini <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
---

 mm/huge_memory.c |   26 --------------------------
 1 file changed, 26 deletions(-)

Patch

--- a/mm/huge_memory.c~mmdo_huge_pmd_numa_page-remove-unnecessary-tlb-flushing-code
+++ a/mm/huge_memory.c
@@ -1440,32 +1440,6 @@  vm_fault_t do_huge_pmd_numa_page(struct
 		goto out;
 	}
 
-	/*
-	 * Since we took the NUMA fault, we must have observed the !accessible
-	 * bit. Make sure all other CPUs agree with that, to avoid them
-	 * modifying the page we're about to migrate.
-	 *
-	 * Must be done under PTL such that we'll observe the relevant
-	 * inc_tlb_flush_pending().
-	 *
-	 * We are not sure a pending tlb flush here is for a huge page
-	 * mapping or not. Hence use the tlb range variant
-	 */
-	if (mm_tlb_flush_pending(vma->vm_mm)) {
-		flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
-		/*
-		 * change_huge_pmd() released the pmd lock before
-		 * invalidating the secondary MMUs sharing the primary
-		 * MMU pagetables (with ->invalidate_range()). The
-		 * mmu_notifier_invalidate_range_end() (which
-		 * internally calls ->invalidate_range()) in
-		 * change_pmd_range() will run after us, so we can't
-		 * rely on it here and we need an explicit invalidate.
-		 */
-		mmu_notifier_invalidate_range(vma->vm_mm, haddr,
-					      haddr + HPAGE_PMD_SIZE);
-	}
-
 	pmd = pmd_modify(oldpmd, vma->vm_page_prot);
 	page = vm_normal_page_pmd(vma, haddr, pmd);
 	if (!page)