diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-25 15:34:28 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-25 15:34:28 -0700 |
commit | f01bfc977e26d010bbd6eccdd687340548f191b3 (patch) | |
tree | 75da7da52e34239ebaad37e618b13748425f59c7 /fs/nfs/write.c | |
parent | dd5957b78f9f17c3d4018dcff21dbae9a4486128 (diff) | |
parent | 92a56555bd576c61b27a5cab9f38a33a1e9a1df5 (diff) |
Merge tag 'nfs-for-3.17-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs
Pull NFS client fixes from Trond Myklebust:
"Highlights:
- more fixes for read/write codepath regressions
* sleeping while holding the inode lock
* stricter enforcement of page contiguity when coalescing requests
* fix up error handling in the page coalescing code
- don't busy wait on SIGKILL in the file locking code"
* tag 'nfs-for-3.17-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
nfs: Don't busy-wait on SIGKILL in __nfs_iocounter_wait
nfs: can_coalesce_requests must enforce contiguity
nfs: disallow duplicate pages in pgio page vectors
nfs: don't sleep with inode lock in lock_and_join_requests
nfs: fix error handling in lock_and_join_requests
nfs: use blocking page_group_lock in add_request
nfs: fix nonblocking calls to nfs_page_group_lock
nfs: change nfs_page_group_lock argument
Diffstat (limited to 'fs/nfs/write.c')
-rw-r--r-- | fs/nfs/write.c | 21 |
1 files changed, 17 insertions, 4 deletions
diff --git a/fs/nfs/write.c b/fs/nfs/write.c index e3b5cf28bdc5..175d5d073ccf 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -241,7 +241,7 @@ static bool nfs_page_group_covers_page(struct nfs_page *req) unsigned int pos = 0; unsigned int len = nfs_page_length(req->wb_page); - nfs_page_group_lock(req, true); + nfs_page_group_lock(req, false); do { tmp = nfs_page_group_search_locked(req->wb_head, pos); @@ -478,10 +478,23 @@ try_again: return NULL; } - /* lock each request in the page group */ - ret = nfs_page_group_lock(head, false); - if (ret < 0) + /* holding inode lock, so always make a non-blocking call to try the + * page group lock */ + ret = nfs_page_group_lock(head, true); + if (ret < 0) { + spin_unlock(&inode->i_lock); + + if (!nonblock && ret == -EAGAIN) { + nfs_page_group_lock_wait(head); + nfs_release_request(head); + goto try_again; + } + + nfs_release_request(head); return ERR_PTR(ret); + } + + /* lock each request in the page group */ subreq = head; do { /* |