mm-rmap-move-the-cache-flushing-to-the-correct-place-for-hugetlb-pmd-sharing.patch removed from -mm tree
The quilt patch titled
Subject: mm: rmap: move the cache flushing to the correct place for hugetlb PMD sharing
has been removed from the -mm tree. Its filename was
mm-rmap-move-the-cache-flushing-to-the-correct-place-for-hugetlb-pmd-sharing.patch
This patch was dropped because it was merged into mm-stable
------------------------------------------------------
From: Baolin Wang <[email protected]>
Subject: mm: rmap: move the cache flushing to the correct place for hugetlb PMD sharing
The cache level flush will always be first when changing an existing virtual–>physical mapping to a new value, since this allows us to properly handle systems whose caches are strict and require a virtual–>physical translation to exist for a virtual address. So we should move the cache flushing before huge_pmd_unshare().
As Muchun pointed out[1], now the architectures whose supporting hugetlb PMD sharing have no cache flush issues in practice. But I think we should still follow the cache/TLB flushing rules when changing a valid virtual address mapping in case of potential issues in future.
[1] https://lore.kernel.org/all/YmT%2F%[email protected]/
---
mm/rmap.c | 40 ++++++++++++++++++++++------------------ 1 file changed, 22 insertions(+), 18 deletions(-)
mm/rmap.c renamed from mm/rmap.c~mm-rmap-move-the-cache-flushing-to-the-correct-place-for-hugetlb-pmd-sharing +22 -18
@@ -1532,15 +1532,16 @@ static bool try_to_unmap_one(struct foli* do this outside rmap routines. */ VM_BUG_ON (!(flags &TTU_RMAP_LOCKED )); +/* +* huge_pmd_unshare may unmap an entire PMD page. +* There is no way of knowing exactly which PMDs may +* be cached for this mm, so we must flush them all. +* start/end were already adjusted above to cover this +* range. +*/ +flush_cache_range (vma, range.start, range.end); +if (huge_pmd_unshare (mm, vma, &address, pvmw.pte)) { -/* -* huge_pmd_unshare unmapped an entire PMD -* page. There is no way of knowing exactly -* which PMDs may be cached for this mm, so -* we must flush them all. start/end were -* already adjusted above to cover this range. -*/ -flush_cache_range (vma, range.start, range.end);flush_tlb_range (vma, range.start, range.end);mmu_notifier_invalidate_range (mm, range.start, range.end);
@@ -1557,13 +1558,14 @@ static bool try_to_unmap_one(struct folipage_vma_mapped_walk_done (&pvmw);break ; } + }else { +flush_cache_page (vma, address,pte_pfn (*pvmw.pte)); }/* * Nuke the page table entry. When having to clear * PageAnonExclusive(), we always have to flush. */ -flush_cache_page (vma, address,pte_pfn (*pvmw.pte));if (should_defer_flush (mm, flags) && !anon_exclusive) {/* * We clear the PTE but do not flush so potentially
@@ -1884,15 +1886,16 @@ static bool try_to_migrate_one(struct fo* do this outside rmap routines. */ VM_BUG_ON (!(flags &TTU_RMAP_LOCKED )); +/* +* huge_pmd_unshare may unmap an entire PMD page. +* There is no way of knowing exactly which PMDs may +* be cached for this mm, so we must flush them all. +* start/end were already adjusted above to cover this +* range. +*/ +flush_cache_range (vma, range.start, range.end); +if (huge_pmd_unshare (mm, vma, &address, pvmw.pte)) { -/* -* huge_pmd_unshare unmapped an entire PMD -* page. There is no way of knowing exactly -* which PMDs may be cached for this mm, so -* we must flush them all. start/end were -* already adjusted above to cover this range. -*/ -flush_cache_range (vma, range.start, range.end);flush_tlb_range (vma, range.start, range.end);mmu_notifier_invalidate_range (mm, range.start, range.end);
@@ -1909,10 +1912,11 @@ static bool try_to_migrate_one(struct fopage_vma_mapped_walk_done (&pvmw);break ; } + }else { +flush_cache_page (vma, address,pte_pfn (*pvmw.pte)); }/* Nuke the page table entry. */ -flush_cache_page (vma, address,pte_pfn (*pvmw.pte)); pteval =ptep_clear_flush (vma, address, pvmw.pte);/* Set the dirty flag on the folio now the pte is gone. */
_
Patches currently in -mm which might be from [email protected] are