mm: thp: fix wrong cache flush in remove_migration_pmd()
authorMuchun Song <songmuchun@bytedance.com>
Tue, 22 Mar 2022 21:41:53 +0000 (14:41 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Tue, 22 Mar 2022 22:57:04 +0000 (15:57 -0700)
Patch series "Fix some cache flush bugs", v5.

This series focuses on fixing cache maintenance.

This patch (of 7):

The flush_cache_range() is supposed to be justified only if the page is
already placed in process page table, and that is done right after
flush_cache_range().  So using this interface is wrong.  And there is no
need to invalite cache since it was non-present before in
remove_migration_pmd().  So just to remove it.

Link: https://lkml.kernel.org/r/20220210123058.79206-1-songmuchun@bytedance.com
Link: https://lkml.kernel.org/r/20220210123058.79206-2-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Lars Persson <lars.persson@axis.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Cc: Fam Zheng <fam.zheng@bytedance.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm/huge_memory.c

index 406a3c2..88fe13a 100644 (file)
@@ -3197,7 +3197,6 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
        if (pmd_swp_uffd_wp(*pvmw->pmd))
                pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde));
 
-       flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);
        if (PageAnon(new))
                page_add_anon_rmap(new, vma, mmun_start, true);
        else
@@ -3205,6 +3204,8 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
        set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
        if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new))
                mlock_vma_page(new);
+
+       /* No need to invalidate - it was non-present before */
        update_mmu_cache_pmd(vma, address, pvmw->pmd);
 }
 #endif