The patch titled
Subject: Revert "mm: take i_mmap_lock in unmap_mapping_range() for DAX"
has been added to the -mm tree. Its filename is
revert-mm-take-i_mmap_lock-in-unmap_mapping_range-for-dax.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/revert-mm-take-i_mmap_lock-in-unmap_mapping_range-for-dax.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/revert-mm-take-i_mmap_lock-in-unmap_mapping_range-for-dax.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: Revert "mm: take i_mmap_lock in unmap_mapping_range() for DAX"
This reverts commits 46c043ede4711e8d ("mm: take i_mmap_lock in
unmap_mapping_range() for DAX") and 8346c416d17bf5b4 ("dax: fix race
between simultaneous faults").
These introduced a number of deadlocks and other issues, and need to be
reverted for the v4.3 kernel. The list of issues in DAX after these
commits (some newly introduced by the commits, some preexisting) can be
found here:
https://lkml.org/lkml/2015/9/25/602 (Subject: "Re: [PATCH] dax: fix
deadlock in __dax_fault").
This revert keeps the PMEM API changes to the zeroing code in
__dax_pmd_fault(), which were added by this commit:
commit d77e92e270ed ("dax: update PMD fault handler with PMEM API")
It also keeps the code dropping mapping->i_mmap_rwsem before calling
unmap_mapping_range(), but converts it to a read lock since that's what is
now used by the rest of __dax_pmd_fault(). This is needed to avoid
recursively acquiring mapping->i_mmap_rwsem, once with a read lock in
__dax_pmd_fault() and once with a write lock in unmap_mapping_range().
Signed-off-by: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Matthew Wilcox <matthew.r.wilcox@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/dax.c | 37 +++++++++++++------------------------
mm/memory.c | 11 +++++++++--
2 files changed, 22 insertions(+), 26 deletions(-)
diff -puN fs/dax.c~revert-mm-take-i_mmap_lock-in-unmap_mapping_range-for-dax fs/dax.c
--- a/fs/dax.c~revert-mm-take-i_mmap_lock-in-unmap_mapping_range-for-dax
+++ a/fs/dax.c
@@ -569,36 +569,14 @@ int __dax_pmd_fault(struct vm_area_struc
if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
goto fallback;
- sector = bh.b_blocknr << (blkbits - 9);
-
- if (buffer_unwritten(&bh) || buffer_new(&bh)) {
- int i;
-
- length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
- bh.b_size);
- if (length < 0) {
- result = VM_FAULT_SIGBUS;
- goto out;
- }
- if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
- goto fallback;
-
- for (i = 0; i < PTRS_PER_PMD; i++)
- clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
- wmb_pmem();
- count_vm_event(PGMAJFAULT);
- mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
- result |= VM_FAULT_MAJOR;
- }
-
/*
* If we allocated new storage, make sure no process has any
* zero pages covering this hole
*/
if (buffer_new(&bh)) {
- i_mmap_unlock_write(mapping);
+ i_mmap_unlock_read(mapping);
unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
- i_mmap_lock_write(mapping);
+ i_mmap_lock_read(mapping);
}
/*
@@ -635,6 +613,7 @@ int __dax_pmd_fault(struct vm_area_struc
result = VM_FAULT_NOPAGE;
spin_unlock(ptl);
} else {
+ sector = bh.b_blocknr << (blkbits - 9);
length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
bh.b_size);
if (length < 0) {
@@ -644,6 +623,16 @@ int __dax_pmd_fault(struct vm_area_struc
if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
goto fallback;
+ if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+ int i;
+ for (i = 0; i < PTRS_PER_PMD; i++)
+ clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
+ wmb_pmem();
+ count_vm_event(PGMAJFAULT);
+ mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+ result |= VM_FAULT_MAJOR;
+ }
+
result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
}
diff -puN mm/memory.c~revert-mm-take-i_mmap_lock-in-unmap_mapping_range-for-dax mm/memory.c
--- a/mm/memory.c~revert-mm-take-i_mmap_lock-in-unmap_mapping_range-for-dax
+++ a/mm/memory.c
@@ -2426,10 +2426,17 @@ void unmap_mapping_range(struct address_
if (details.last_index < details.first_index)
details.last_index = ULONG_MAX;
- i_mmap_lock_write(mapping);
+
+ /*
+ * DAX already holds i_mmap_lock to serialise file truncate vs
+ * page fault and page fault vs page fault.
+ */
+ if (!IS_DAX(mapping->host))
+ i_mmap_lock_write(mapping);
if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
unmap_mapping_range_tree(&mapping->i_mmap, &details);
- i_mmap_unlock_write(mapping);
+ if (!IS_DAX(mapping->host))
+ i_mmap_unlock_write(mapping);
}
EXPORT_SYMBOL(unmap_mapping_range);
_
Patches currently in -mm which might be from ross.zwisler@xxxxxxxxxxxxxxx are
revert-mm-take-i_mmap_lock-in-unmap_mapping_range-for-dax.patch
revert-dax-fix-race-between-simultaneous-faults.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
