summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorJeff Layton <jlayton@redhat.com>2014-01-27 13:46:15 -0500
committerTrond Myklebust <trond.myklebust@primarydata.com>2014-01-27 15:35:56 -0500
commitd529ef83c355f97027ff85298a9709fe06216a66 (patch)
treeb13587538729686d8f366ab734782de0aeba1fa7 /fs
parent7dd7d95916fe7c8494aa8708204d5a2b8689d270 (diff)
downloadlinux-d529ef83c355f97027ff85298a9709fe06216a66.tar.bz2
NFS: fix the handling of NFS_INO_INVALID_DATA flag in nfs_revalidate_mapping
There is a possible race in how the nfs_invalidate_mapping function is handled. Currently, we go and invalidate the pages in the file and then clear NFS_INO_INVALID_DATA. The problem is that it's possible for a stale page to creep into the mapping after the page was invalidated (i.e., via readahead). If another writer comes along and sets the flag after that happens but before invalidate_inode_pages2 returns then we could clear the flag without the cache having been properly invalidated. So, we must clear the flag first and then invalidate the pages. Doing this however, opens another race: It's possible to have two concurrent read() calls that end up in nfs_revalidate_mapping at the same time. The first one clears the NFS_INO_INVALID_DATA flag and then goes to call nfs_invalidate_mapping. Just before calling that though, the other task races in, checks the flag and finds it cleared. At that point, it trusts that the mapping is good and gets the lock on the page, allowing the read() to be satisfied from the cache even though the data is no longer valid. These effects are easily manifested by running diotest3 from the LTP test suite on NFS. That program does a series of DIO writes and buffered reads. The operations are serialized and page-aligned but the existing code fails the test since it occasionally allows a read to come out of the cache incorrectly. While mixing direct and buffered I/O isn't recommended, I believe it's possible to hit this in other ways that just use buffered I/O, though that situation is much harder to reproduce. The problem is that the checking/clearing of that flag and the invalidation of the mapping really need to be atomic. Fix this by serializing concurrent invalidations with a bitlock. At the same time, we also need to allow other places that check NFS_INO_INVALID_DATA to check whether we might be in the middle of invalidating the file, so fix up a couple of places that do that to look for the new NFS_INO_INVALIDATING flag. Doing this requires us to be careful not to set the bitlock unnecessarily, so this code only does that if it believes it will be doing an invalidation. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Diffstat (limited to 'fs')
-rw-r--r--fs/nfs/dir.c3
-rw-r--r--fs/nfs/inode.c42
-rw-r--r--fs/nfs/nfstrace.h1
-rw-r--r--fs/nfs/write.c6
4 files changed, 46 insertions, 6 deletions
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b266f734bd53..b39a0468829b 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -288,7 +288,8 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
new_pos = desc->current_index + i;
if (ctx->attr_gencount != nfsi->attr_gencount
- || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) {
+ || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))
+ || test_bit(NFS_INO_INVALIDATING, &nfsi->flags)) {
ctx->duped = 0;
ctx->attr_gencount = nfsi->attr_gencount;
} else if (new_pos < desc->ctx->pos) {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c63e15224466..0a972ee9ccc1 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -977,11 +977,11 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
if (ret < 0)
return ret;
}
- spin_lock(&inode->i_lock);
- nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
- if (S_ISDIR(inode->i_mode))
+ if (S_ISDIR(inode->i_mode)) {
+ spin_lock(&inode->i_lock);
memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
- spin_unlock(&inode->i_lock);
+ spin_unlock(&inode->i_lock);
+ }
nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
nfs_fscache_wait_on_invalidate(inode);
@@ -1008,6 +1008,7 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
+ unsigned long *bitlock = &nfsi->flags;
int ret = 0;
/* swapfiles are not supposed to be shared. */
@@ -1019,12 +1020,45 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
if (ret < 0)
goto out;
}
+
+ /*
+ * We must clear NFS_INO_INVALID_DATA first to ensure that
+ * invalidations that come in while we're shooting down the mappings
+ * are respected. But, that leaves a race window where one revalidator
+ * can clear the flag, and then another checks it before the mapping
+ * gets invalidated. Fix that by serializing access to this part of
+ * the function.
+ *
+ * At the same time, we need to allow other tasks to see whether we
+ * might be in the middle of invalidating the pages, so we only set
+ * the bit lock here if it looks like we're going to be doing that.
+ */
+ for (;;) {
+ ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING,
+ nfs_wait_bit_killable, TASK_KILLABLE);
+ if (ret)
+ goto out;
+ if (!(nfsi->cache_validity & NFS_INO_INVALID_DATA))
+ goto out;
+ if (!test_and_set_bit_lock(NFS_INO_INVALIDATING, bitlock))
+ break;
+ }
+
+ spin_lock(&inode->i_lock);
if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
+ nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
+ spin_unlock(&inode->i_lock);
trace_nfs_invalidate_mapping_enter(inode);
ret = nfs_invalidate_mapping(inode, mapping);
trace_nfs_invalidate_mapping_exit(inode, ret);
+ } else {
+ /* something raced in and cleared the flag */
+ spin_unlock(&inode->i_lock);
}
+ clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
+ smp_mb__after_clear_bit();
+ wake_up_bit(bitlock, NFS_INO_INVALIDATING);
out:
return ret;
}
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 89fe741e58b1..59f838cdc009 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -36,6 +36,7 @@
__print_flags(v, "|", \
{ 1 << NFS_INO_ADVISE_RDPLUS, "ADVISE_RDPLUS" }, \
{ 1 << NFS_INO_STALE, "STALE" }, \
+ { 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \
{ 1 << NFS_INO_FLUSHING, "FLUSHING" }, \
{ 1 << NFS_INO_FSCACHE, "FSCACHE" }, \
{ 1 << NFS_INO_COMMIT, "COMMIT" }, \
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index a44a87268a6e..5511a4247190 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -909,9 +909,13 @@ bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx)
*/
static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
{
+ struct nfs_inode *nfsi = NFS_I(inode);
+
if (nfs_have_delegated_attributes(inode))
goto out;
- if (NFS_I(inode)->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+ if (nfsi->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+ return false;
+ if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags))
return false;
out:
return PageUptodate(page) != 0;