summaryrefslogtreecommitdiffstats
path: root/fs/dax.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-05-13 18:49:35 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2017-05-13 18:49:35 +0200
commit1251704a631b62591ad1d1b6ead252e9e597d5f5 (patch)
treebc394a069d3b8aef8c6dc147438c05cc9ba057aa /fs/dax.c
parentMerge branch 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/g... (diff)
parentmm, docs: update memory.stat description with workingset* entries (diff)
downloadlinux-1251704a631b62591ad1d1b6ead252e9e597d5f5.tar.xz
linux-1251704a631b62591ad1d1b6ead252e9e597d5f5.zip
Merge branch 'akpm' (patches from Andrew)
Merge misc fixes from Andrew Morton: "15 fixes" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: mm, docs: update memory.stat description with workingset* entries mm: vmscan: scan until it finds eligible pages mm, thp: copying user pages must schedule on collapse dax: fix PMD data corruption when fault races with write dax: fix data corruption when fault races with write ext4: return to starting transaction in ext4_dax_huge_fault() mm: fix data corruption due to stale mmap reads dax: prevent invalidation of mapped DAX entries Tigran has moved mm, vmalloc: fix vmalloc users tracking properly mm/khugepaged: add missed tracepoint for collapse_huge_page_swapin gcov: support GCC 7.1 mm, vmstat: Remove spurious WARN() during zoneinfo print time: delete current_fs_time() hwpoison, memcg: forcibly uncharge LRU pages
Diffstat (limited to 'fs/dax.c')
-rw-r--r--fs/dax.c91
1 files changed, 31 insertions, 60 deletions
diff --git a/fs/dax.c b/fs/dax.c
index 18fe9bb22d55..c22eaf162f95 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -461,35 +461,6 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
}
/*
- * Invalidate exceptional DAX entry if easily possible. This handles DAX
- * entries for invalidate_inode_pages() so we evict the entry only if we can
- * do so without blocking.
- */
-int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index)
-{
- int ret = 0;
- void *entry, **slot;
- struct radix_tree_root *page_tree = &mapping->page_tree;
-
- spin_lock_irq(&mapping->tree_lock);
- entry = __radix_tree_lookup(page_tree, index, NULL, &slot);
- if (!entry || !radix_tree_exceptional_entry(entry) ||
- slot_locked(mapping, slot))
- goto out;
- if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
- radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
- goto out;
- radix_tree_delete(page_tree, index);
- mapping->nrexceptional--;
- ret = 1;
-out:
- spin_unlock_irq(&mapping->tree_lock);
- if (ret)
- dax_wake_mapping_entry_waiter(mapping, index, entry, true);
- return ret;
-}
-
-/*
* Invalidate exceptional DAX entry if it is clean.
*/
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
@@ -1044,7 +1015,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
* into page tables. We have to tear down these mappings so that data
* written by write(2) is visible in mmap.
*/
- if ((iomap->flags & IOMAP_F_NEW) && inode->i_mapping->nrpages) {
+ if (iomap->flags & IOMAP_F_NEW) {
invalidate_inode_pages2_range(inode->i_mapping,
pos >> PAGE_SHIFT,
(end - 1) >> PAGE_SHIFT);
@@ -1177,6 +1148,12 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
flags |= IOMAP_WRITE;
+ entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
+ if (IS_ERR(entry)) {
+ vmf_ret = dax_fault_return(PTR_ERR(entry));
+ goto out;
+ }
+
/*
* Note that we don't bother to use iomap_apply here: DAX required
* the file system block size to be equal the page size, which means
@@ -1185,17 +1162,11 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
if (error) {
vmf_ret = dax_fault_return(error);
- goto out;
+ goto unlock_entry;
}
if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
- vmf_ret = dax_fault_return(-EIO); /* fs corruption? */
- goto finish_iomap;
- }
-
- entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
- if (IS_ERR(entry)) {
- vmf_ret = dax_fault_return(PTR_ERR(entry));
- goto finish_iomap;
+ error = -EIO; /* fs corruption? */
+ goto error_finish_iomap;
}
sector = dax_iomap_sector(&iomap, pos);
@@ -1217,13 +1188,13 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
}
if (error)
- goto error_unlock_entry;
+ goto error_finish_iomap;
__SetPageUptodate(vmf->cow_page);
vmf_ret = finish_fault(vmf);
if (!vmf_ret)
vmf_ret = VM_FAULT_DONE_COW;
- goto unlock_entry;
+ goto finish_iomap;
}
switch (iomap.type) {
@@ -1243,7 +1214,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
case IOMAP_HOLE:
if (!(vmf->flags & FAULT_FLAG_WRITE)) {
vmf_ret = dax_load_hole(mapping, &entry, vmf);
- goto unlock_entry;
+ goto finish_iomap;
}
/*FALLTHRU*/
default:
@@ -1252,10 +1223,8 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
break;
}
- error_unlock_entry:
+ error_finish_iomap:
vmf_ret = dax_fault_return(error) | major;
- unlock_entry:
- put_locked_mapping_entry(mapping, vmf->pgoff, entry);
finish_iomap:
if (ops->iomap_end) {
int copied = PAGE_SIZE;
@@ -1270,7 +1239,9 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
*/
ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
}
-out:
+ unlock_entry:
+ put_locked_mapping_entry(mapping, vmf->pgoff, entry);
+ out:
trace_dax_pte_fault_done(inode, vmf, vmf_ret);
return vmf_ret;
}
@@ -1417,6 +1388,16 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
goto fallback;
/*
+ * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+ * PMD or a HZP entry. If it can't (because a 4k page is already in
+ * the tree, for instance), it will return -EEXIST and we just fall
+ * back to 4k entries.
+ */
+ entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+ if (IS_ERR(entry))
+ goto fallback;
+
+ /*
* Note that we don't use iomap_apply here. We aren't doing I/O, only
* setting up a mapping, so really we're using iomap_begin() as a way
* to look up our filesystem block.
@@ -1424,21 +1405,11 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
pos = (loff_t)pgoff << PAGE_SHIFT;
error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
if (error)
- goto fallback;
+ goto unlock_entry;
if (iomap.offset + iomap.length < pos + PMD_SIZE)
goto finish_iomap;
- /*
- * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
- * PMD or a HZP entry. If it can't (because a 4k page is already in
- * the tree, for instance), it will return -EEXIST and we just fall
- * back to 4k entries.
- */
- entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
- if (IS_ERR(entry))
- goto finish_iomap;
-
switch (iomap.type) {
case IOMAP_MAPPED:
result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry);
@@ -1446,7 +1417,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
case IOMAP_UNWRITTEN:
case IOMAP_HOLE:
if (WARN_ON_ONCE(write))
- goto unlock_entry;
+ break;
result = dax_pmd_load_hole(vmf, &iomap, &entry);
break;
default:
@@ -1454,8 +1425,6 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
break;
}
- unlock_entry:
- put_locked_mapping_entry(mapping, pgoff, entry);
finish_iomap:
if (ops->iomap_end) {
int copied = PMD_SIZE;
@@ -1471,6 +1440,8 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
&iomap);
}
+ unlock_entry:
+ put_locked_mapping_entry(mapping, pgoff, entry);
fallback:
if (result == VM_FAULT_FALLBACK) {
split_huge_pmd(vma, vmf->pmd, vmf->address);