The patch titled
Subject: dax: wrprotect pmd_t in dax_mapping_entry_mkclean
has been added to the -mm tree. Its filename is
dax-wrprotect-pmd_t-in-dax_mapping_entry_mkclean.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/dax-wrprotect-pmd_t-in-dax_mapping_entry_mkclean.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/dax-wrprotect-pmd_t-in-dax_mapping_entry_mkclean.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/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Subject: dax: wrprotect pmd_t in dax_mapping_entry_mkclean
Currently dax_mapping_entry_mkclean() fails to clean and write protect the
pmd_t of a DAX PMD entry during an *sync operation. This can result in
data loss in the following sequence:
1) mmap write to DAX PMD, dirtying PMD radix tree entry and making the
pmd_t dirty and writeable
2) fsync, flushing out PMD data and cleaning the radix tree entry. We
currently fail to mark the pmd_t as clean and write protected.
3) more mmap writes to the PMD. These don't cause any page faults since
the pmd_t is dirty and writeable. The radix tree entry remains clean.
4) fsync, which fails to flush the dirty PMD data because the radix tree
entry was clean.
5) crash - dirty data that should have been fsync'd as part of 4) could
still have been in the processor cache, and is lost.
Fix this by marking the pmd_t clean and write protected in
dax_mapping_entry_mkclean(), which is called as part of the fsync
operation 2). This will cause the writes in step 3) above to generate
page faults where we'll re-dirty the PMD radix tree entry, resulting in
flushes in the fsync that happens in step 4).
Fixes: 4b4bb46d00b3 ("dax: clear dirty entry tags on cache flush")
Link: http://lkml.kernel.org/r/1482272586-21177-3-git-send-email-ross.zwisler@xxxxxxxxxxxxxxx
Signed-off-by: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/dax.c | 53 ++++++++++++++++++++++++++++++-------------
include/linux/mm.h | 2 -
mm/memory.c | 4 +--
3 files changed, 39 insertions(+), 20 deletions(-)
diff -puN fs/dax.c~dax-wrprotect-pmd_t-in-dax_mapping_entry_mkclean fs/dax.c
--- a/fs/dax.c~dax-wrprotect-pmd_t-in-dax_mapping_entry_mkclean
+++ a/fs/dax.c
@@ -630,8 +630,8 @@ static void dax_mapping_entry_mkclean(st
pgoff_t index, unsigned long pfn)
{
struct vm_area_struct *vma;
- pte_t *ptep;
- pte_t pte;
+ pte_t pte, *ptep = NULL;
+ pmd_t *pmdp = NULL;
spinlock_t *ptl;
bool changed;
@@ -646,21 +646,42 @@ static void dax_mapping_entry_mkclean(st
address = pgoff_address(index, vma);
changed = false;
- if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
+ if (follow_pte_pmd(vma->vm_mm, address, &ptep, &pmdp, &ptl))
continue;
- if (pfn != pte_pfn(*ptep))
- goto unlock;
- if (!pte_dirty(*ptep) && !pte_write(*ptep))
- goto unlock;
-
- 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);
- changed = true;
-unlock:
- pte_unmap_unlock(ptep, ptl);
+
+ 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_page(vma, address, pfn);
+ pmd = pmdp_huge_clear_flush(vma, address, pmdp);
+ pmd = pmd_wrprotect(pmd);
+ pmd = pmd_mkclean(pmd);
+ set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+ changed = true;
+unlock_pmd:
+ spin_unlock(ptl);
+#endif
+ } 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);
+ changed = true;
+unlock_pte:
+ pte_unmap_unlock(ptep, ptl);
+ }
if (changed)
mmu_notifier_invalidate_page(vma->vm_mm, address);
diff -puN include/linux/mm.h~dax-wrprotect-pmd_t-in-dax_mapping_entry_mkclean include/linux/mm.h
--- a/include/linux/mm.h~dax-wrprotect-pmd_t-in-dax_mapping_entry_mkclean
+++ a/include/linux/mm.h
@@ -1210,8 +1210,6 @@ int copy_page_range(struct mm_struct *ds
struct vm_area_struct *vma);
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows);
-int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp,
- spinlock_t **ptlp);
int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp);
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
diff -puN mm/memory.c~dax-wrprotect-pmd_t-in-dax_mapping_entry_mkclean mm/memory.c
--- a/mm/memory.c~dax-wrprotect-pmd_t-in-dax_mapping_entry_mkclean
+++ a/mm/memory.c
@@ -3819,8 +3819,8 @@ out:
return -EINVAL;
}
-int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp,
- spinlock_t **ptlp)
+static inline int follow_pte(struct mm_struct *mm, unsigned long address,
+ pte_t **ptepp, spinlock_t **ptlp)
{
int res;
_
Patches currently in -mm which might be from ross.zwisler@xxxxxxxxxxxxxxx are
mm-add-follow_pte_pmd.patch
dax-wrprotect-pmd_t-in-dax_mapping_entry_mkclean.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
