+ dax-fix-missing-writeprotect-the-pte-entry.patch added to -mm tree

* + dax-fix-missing-writeprotect-the-pte-entry.patch added to -mm tree
@ 2022-04-04 20:14 Andrew Morton
  0 siblings, 0 replies; 5+ messages in thread
From: Andrew Morton @ 2022-04-04 20:14 UTC (permalink / raw)
  To: mm-commits, zwisler, xiyuyang19, willy, viro, shy828301,
	rcampbell, kirill.shutemov, jack, hughd, hch, duanxiongchun,
	dan.j.williams, apopple, songmuchun, akpm


The patch titled
     Subject: dax: fix missing writeprotect the pte entry
has been added to the -mm tree.  Its filename is
     dax-fix-missing-writeprotect-the-pte-entry.patch

This patch should soon appear at
    https://ozlabs.org/~akpm/mmots/broken-out/dax-fix-missing-writeprotect-the-pte-entry.patch
and later at
    https://ozlabs.org/~akpm/mmotm/broken-out/dax-fix-missing-writeprotect-the-pte-entry.patch

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next and is updated
there every 3-4 working days

------------------------------------------------------
From: Muchun Song <songmuchun@bytedance.com>
Subject: dax: fix missing writeprotect the pte entry

Currently dax_mapping_entry_mkclean() fails to clean and write protect the
pte entry within a DAX PMD entry during an *sync operation.  This can
result in data loss in the following sequence:

  1) process A mmap write to DAX PMD, dirtying PMD radix tree entry and
     making the pmd entry dirty and writeable.
  2) process B mmap with the @offset (e.g. 4K) and @length (e.g. 4K)
     write to the same file, dirtying PMD radix tree entry (already
     done in 1)) and making the pte entry dirty and writeable.
  3) fsync, flushing out PMD data and cleaning the radix tree entry. We
     currently fail to mark the pte entry as clean and write protected
     since the vma of process B is not covered in dax_entry_mkclean().
  4) process B writes to the pte. These don't cause any page faults since
     the pte entry is dirty and writeable. The radix tree entry remains
     clean.
  5) fsync, which fails to flush the dirty PMD data because the radix tree
     entry was clean.
  6) crash - dirty data that should have been fsync'd as part of 5) could
     still have been in the processor cache, and is lost.

Just to use pfn_mkclean_range() to clean the pfns to fix this issue.

Link: https://lkml.kernel.org/r/20220403053957.10770-6-songmuchun@bytedance.com
Fixes: 4b4bb46d00b3 ("dax: clear dirty entry tags on cache flush")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Ross Zwisler <zwisler@kernel.org>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Cc: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 fs/dax.c |   99 ++++++-----------------------------------------------
 1 file changed, 12 insertions(+), 87 deletions(-)

--- a/fs/dax.c~dax-fix-missing-writeprotect-the-pte-entry
+++ a/fs/dax.c
@@ -24,6 +24,7 @@
 #include <linux/sizes.h>
 #include <linux/mmu_notifier.h>
 #include <linux/iomap.h>
+#include <linux/rmap.h>
 #include <asm/pgalloc.h>
 
 #define CREATE_TRACE_POINTS
@@ -789,96 +790,12 @@ static void *dax_insert_entry(struct xa_
 	return entry;
 }
 
-static inline
-unsigned long pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma)
-{
-	unsigned long address;
-
-	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
-	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
-	return address;
-}
-
-/* Walk all mappings of a given index of a file and writeprotect them */
-static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
-		unsigned long pfn)
-{
-	struct vm_area_struct *vma;
-	pte_t pte, *ptep = NULL;
-	pmd_t *pmdp = NULL;
-	spinlock_t *ptl;
-
-	i_mmap_lock_read(mapping);
-	vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
-		struct mmu_notifier_range range;
-		unsigned long address;
-
-		cond_resched();
-
-		if (!(vma->vm_flags & VM_SHARED))
-			continue;
-
-		address = pgoff_address(index, vma);
-
-		/*
-		 * follow_invalidate_pte() will use the range to call
-		 * mmu_notifier_invalidate_range_start() on our behalf before
-		 * taking any lock.
-		 */
-		if (follow_invalidate_pte(vma->vm_mm, address, &range, &ptep,
-					  &pmdp, &ptl))
-			continue;
-
-		/*
-		 * No need to call mmu_notifier_invalidate_range() as we are
-		 * downgrading page table protection not changing it to point
-		 * to a new page.
-		 *
-		 * See Documentation/vm/mmu_notifier.rst
-		 */
-		if (pmdp) {
-#ifdef CONFIG_FS_DAX_PMD
-			pmd_t pmd;
-
-			if (pfn != pmd_pfn(*pmdp))
-				goto unlock_pmd;
-			if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
-				goto unlock_pmd;
-
-			flush_cache_range(vma, address,
-					  address + HPAGE_PMD_SIZE);
-			pmd = pmdp_invalidate(vma, address, pmdp);
-			pmd = pmd_wrprotect(pmd);
-			pmd = pmd_mkclean(pmd);
-			set_pmd_at(vma->vm_mm, address, pmdp, pmd);
-unlock_pmd:
-#endif
-			spin_unlock(ptl);
-		} else {
-			if (pfn != pte_pfn(*ptep))
-				goto unlock_pte;
-			if (!pte_dirty(*ptep) && !pte_write(*ptep))
-				goto unlock_pte;
-
-			flush_cache_page(vma, address, pfn);
-			pte = ptep_clear_flush(vma, address, ptep);
-			pte = pte_wrprotect(pte);
-			pte = pte_mkclean(pte);
-			set_pte_at(vma->vm_mm, address, ptep, pte);
-unlock_pte:
-			pte_unmap_unlock(ptep, ptl);
-		}
-
-		mmu_notifier_invalidate_range_end(&range);
-	}
-	i_mmap_unlock_read(mapping);
-}
-
 static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
 		struct address_space *mapping, void *entry)
 {
-	unsigned long pfn, index, count;
+	unsigned long pfn, index, count, end;
 	long ret = 0;
+	struct vm_area_struct *vma;
 
 	/*
 	 * A page got tagged dirty in DAX mapping? Something is seriously
@@ -936,8 +853,16 @@ static int dax_writeback_one(struct xa_s
 	pfn = dax_to_pfn(entry);
 	count = 1UL << dax_entry_order(entry);
 	index = xas->xa_index & ~(count - 1);
+	end = index + count - 1;
+
+	/* Walk all mappings of a given index of a file and writeprotect them */
+	i_mmap_lock_read(mapping);
+	vma_interval_tree_foreach(vma, &mapping->i_mmap, index, end) {
+		pfn_mkclean_range(pfn, count, index, vma);
+		cond_resched();
+	}
+	i_mmap_unlock_read(mapping);
 
-	dax_entry_mkclean(mapping, index, pfn);
 	dax_flush(dax_dev, page_address(pfn_to_page(pfn)), count * PAGE_SIZE);
 	/*
 	 * After we have flushed the cache, we can clear the dirty tag. There
_

Patches currently in -mm which might be from songmuchun@bytedance.com are

mm-hugetlb_vmemmap-introduce-arch_want_hugetlb_page_free_vmemmap.patch
arm64-mm-hugetlb-enable-hugetlb_page_free_vmemmap-for-arm64.patch
mm-hugetlb_vmemmap-cleanup-hugetlb_vmemmap-related-functions.patch
mm-hugetlb_vmemmap-cleanup-hugetlb_free_vmemmap_enabled.patch
mm-hugetlb_vmemmap-cleanup-config_hugetlb_page_free_vmemmap.patch
mm-rmap-fix-cache-flush-on-thp-pages.patch
dax-fix-cache-flush-on-pmd-mapped-pages.patch
mm-rmap-introduce-pfn_mkclean_range-to-cleans-ptes.patch
mm-pvmw-add-support-for-walking-devmap-pages.patch
dax-fix-missing-writeprotect-the-pte-entry.patch
mm-simplify-follow_invalidate_pte.patch


^ permalink raw reply	[flat|nested] 5+ messages in thread