summaryrefslogtreecommitdiff
path: root/fs/nfs
AgeCommit message (Collapse)AuthorFilesLines
2016-07-24pNFS: Cleanup - do layout segment initialisation in one placeTrond Myklebust1-4/+6
...instead of splitting the initialisation over init_lseg() and pnfs_layout_process(). Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: Remove redundant stateid invalidationTrond Myklebust1-1/+0
The layout stateid will be invalidated once it holds no more layout segments anyway. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: Remove redundant pnfs_mark_layout_returned_if_empty()Trond Myklebust4-16/+0
That's already being taken care of in pnfs_layout_remove_lseg(). Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: Clear the layout metadata if the server changed the layout stateidTrond Myklebust1-1/+1
If the server changed the layout stateid's "other" field, then we should treat the old layout as being completely gone. In that case, we want to clear the metadata such as scheduled layoutreturns. Do this by calling pnfs_mark_layout_stateid_invalid(). Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: Cleanup - don't open code pnfs_mark_layout_stateid_invalid()Trond Myklebust4-5/+5
Ensure nfs42_layoutstat_done() layoutget don't open code layout stateid invalidation. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24NFS: pnfs_mark_matching_lsegs_return() should match the layout sequence idTrond Myklebust1-14/+23
When determining which layout segments to return, we do want pnfs_mark_matching_lsegs_return to check that they match the layout sequence id. This ensures that we don't waste time if the server is replaying a layout recall that has already been satisfied. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: Do not set plh_return_seq for non-callback related layoutreturnsTrond Myklebust1-7/+6
In cases where we need to send a layoutreturn in order to propagate an error, we should not tie that to a specific layout stateid. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: Ensure layoutreturn acts as a completion for layout callbacksTrond Myklebust1-15/+25
When we return NFS_OK to the CB_LAYOUTRECALL, we are required to send a layoutreturn that "completes" that layout recall request, using the correct stateid. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: Fix CB_LAYOUTRECALL stateid verificationTrond Myklebust1-19/+44
We want to evaluate in this order: If the client holds no layout for this inode, then return NFS4ERR_NOMATCHING_LAYOUT; it probably forgot the layout. If the client finds the inode among the list of layouts, but the corresponding stateid has not yet been initialised, then return NFS4ERR_DELAY to ask the server to retry once the outstanding LAYOUTGET is complete. If the current layout stateid's "other" field does not match the recalled stateid, return NFS4ERR_BAD_STATEID. If already processing a layout recall with a newer stateid, return NFS4ERR_OLD_STATEID. This can only happens for servers that are non-compliant with the NFSv4.1 protocol. If already processing a layout recall with an older stateid, return NFS4ERR_DELAY to ask the server to retry once the outstanding LAYOUTRETURN is complete. Again, this is technically incompliant with the NFSv4.1 protocol. If the current layout sequence id is newer than the recalled stateid's sequence id, return NFS4ERR_OLD_STATEID. This too implies protocol non-compliance. If the current layout sequence id is older than the recalled stateid's sequence id+1, return NFS4ERR_DELAY. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: Always update the layout barrier seqid on LAYOUTGETTrond Myklebust1-13/+14
Currently, pnfs_set_layout_stateid() will update the layout sequence id barrier only if the stateid itself is newer than the current layout stateid. However in a situation where multiple LAYOUTGET calls and a LAYOUTRETURN raced, it is entirely possible for one of the LAYOUTGET to set the current stateid to something newer than the LAYOUTRETURN that needs to set the barrier. The fix is to allow the "update_barrier" flag to force a check as to whether or not the barrier needs to be updated. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: Always update the layout stateid if NFS_LAYOUT_INVALID_STID is setTrond Myklebust1-1/+1
If the layout stateid is invalid, then pnfs_set_layout_stateid() must always initialise it. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: Clear the layout return tracking on layout reinitialisationTrond Myklebust1-5/+14
Ensure that we don't carry over layoutreturn info from a previous incarnation of this layout. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24pNFS: LAYOUTRETURN should only update the stateid if the layout is validTrond Myklebust2-1/+6
If the layout was completely returned, then ignore the returned layout stateid. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-24Merge commit 'e7bdea7750eb'Trond Myklebust8-23/+45
Needed in order to work on top of pNFS changes in Linus' upstream kernel.
2016-07-22nfs: don't create zero-length requestsBenjamin Coddington1-1/+4
NFS doesn't expect requests with wb_bytes set to zero and may make unexpected decisions about how to handle that request at the page IO layer. Skip request creation if we won't have any wb_bytes in the request. Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Reviewed-by: Weston Andros Adamson <dros@primarydata.com> Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-22Fix NULL pointer dereference in bl_free_device().Artem Savkov1-9/+13
When bl_parse_deviceid() fails in bl_alloc_deviceid_node() on blkdev_get_by_*() step we get an pnfs_block_dev struct that is uninitialized except for bdev field which is set to whatever error blkdev_get_by_*() returns. bl_free_device() then tries to call blkdev_put() if bdev is not 0 resulting in a wrong pointer dereference. Fixing this by setting bdev in struct pnfs_block_dev only if we didn't get an error from blkdev_get_by_*(). Signed-off-by: Artem Savkov <asavkov@redhat.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-21pNFS/files: filelayout_write_done_cb must call nfs_writeback_update_inode()Trond Myklebust1-0/+6
All write callbacks are required to call nfs_writeback_update_inode() upon success to ensure that file size changes are recorded, and the attribute cache is invalidated. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-21qstr: constify instances in nfsAl Viro6-21/+22
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-07-19nfs4: flexfiles: respect noresvport when establishing connections to DSesTigran Mkrtchyan3-4/+8
Signed-off-by: Tigran Mkrtchyan <tigran.mkrtchyan@desy.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-19nfs4: clnt: respect noresvport when establishing connections to DSesTigran Mkrtchyan3-3/+7
result: $ mount -o vers=4.1 dcache-lab007:/ /pnfs $ cp /etc/profile /pnfs tcp 0 0 131.169.185.68:1005 131.169.191.141:32049 ESTABLISHED tcp 0 0 131.169.185.68:751 131.169.191.144:2049 ESTABLISHED $ $ mount -o vers=4.1,noresvport dcache-lab007:/ /pnfs $ cp /etc/profile /pnfs tcp 0 0 131.169.185.68:34894 131.169.191.141:32049 ESTABLISHED tcp 0 0 131.169.185.68:35722 131.169.191.144:2049 ESTABLISHED $ Signed-off-by: Tigran Mkrtchyan <tigran.mkrtchyan@desy.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-19pnfs/blocklayout: put deviceid node after releasing bl_ext_lockBenjamin Coddington1-6/+21
The last put of deviceid nodes for SCSI layouts may sleep, so we shouldn't hold any spinlocks. Make sure we put them outside the bl_ext_lock. Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-19sunrpc: move NO_CRKEY_TIMEOUT to the auth->au_flagsScott Mayhew3-5/+7
A generic_cred can be used to look up a unx_cred or a gss_cred, so it's not really safe to use the the generic_cred->acred->ac_flags to store the NO_CRKEY_TIMEOUT flag. A lookup for a unx_cred triggered while the KEY_EXPIRE_SOON flag is already set will cause both NO_CRKEY_TIMEOUT and KEY_EXPIRE_SOON to be set in the ac_flags, leaving the user associated with the auth_cred to be in a state where they're perpetually doing 4K NFS_FILE_SYNC writes. This can be reproduced as follows: 1. Mount two NFS filesystems, one with sec=krb5 and one with sec=sys. They do not need to be the same export, nor do they even need to be from the same NFS server. Also, v3 is fine. $ sudo mount -o v3,sec=krb5 server1:/export /mnt/krb5 $ sudo mount -o v3,sec=sys server2:/export /mnt/sys 2. As the normal user, before accessing the kerberized mount, kinit with a short lifetime (but not so short that renewing the ticket would leave you within the 4-minute window again by the time the original ticket expires), e.g. $ kinit -l 10m -r 60m 3. Do some I/O to the kerberized mount and verify that the writes are wsize, UNSTABLE: $ dd if=/dev/zero of=/mnt/krb5/file bs=1M count=1 4. Wait until you're within 4 minutes of key expiry, then do some more I/O to the kerberized mount to ensure that RPC_CRED_KEY_EXPIRE_SOON gets set. Verify that the writes are 4K, FILE_SYNC: $ dd if=/dev/zero of=/mnt/krb5/file bs=1M count=1 5. Now do some I/O to the sec=sys mount. This will cause RPC_CRED_NO_CRKEY_TIMEOUT to be set: $ dd if=/dev/zero of=/mnt/sys/file bs=1M count=1 6. Writes for that user will now be permanently 4K, FILE_SYNC for that user, regardless of which mount is being written to, until you reboot the client. Renewing the kerberos ticket (assuming it hasn't already expired) will have no effect. Grabbing a new kerberos ticket at this point will have no effect either. Move the flag to the auth->au_flags field (which is currently unused) and rename it slightly to reflect that it's no longer associated with the auth_cred->ac_flags. Add the rpc_auth to the arg list of rpcauth_cred_key_to_expire and check the au_flags there too. Finally, add the inode to the arg list of nfs_ctx_key_to_expire so we can determine the rpc_auth to pass to rpcauth_cred_key_to_expire. Signed-off-by: Scott Mayhew <smayhew@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-19mount: use sec= that was specified on the command lineSteve Dickson1-3/+11
When older servers return RPC_AUTH_NULL, it means the rpc creds will be ignored. In that case use the sec= that was specified instead of setting sec=null Fixes Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1112983 Signed-off-by: Steve Dickson <steved@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-19pNFS: Fix LAYOUTGET handling of NFS4ERR_BAD_STATEID and NFS4ERR_EXPIREDTrond Myklebust1-19/+15
We want to recover the open stateid if there is no layout stateid and/or the stateid argument matches an open stateid. Otherwise throw out the existing layout and recover from scratch, as the layout stateid is bad. Fixes: 183d9e7b112aa ("pnfs: rework LAYOUTGET retry handling") Cc: stable@vger.kernel.org # 4.7 Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> Reviewed-by: Jeff Layton <jlayton@redhat.com>
2016-07-19pNFS: Handle NFS4ERR_RECALLCONFLICT correctly in LAYOUTGETTrond Myklebust1-2/+11
Instead of giving up altogether and falling back to doing I/O through the MDS, which may make the situation worse, wait for 2 lease periods for the callback to resolve itself, and then try destroying the existing layout. Only if this was an attempt at getting a first layout, do we give up altogether, as the server is clearly crazy. Fixes: 183d9e7b112aa ("pnfs: rework LAYOUTGET retry handling") Cc: stable@vger.kernel.org # 4.7 Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> Reviewed-by: Jeff Layton <jlayton@redhat.com>
2016-07-19pNFS: Separate handling of NFS4ERR_LAYOUTTRYLATER and RECALLCONFLICTTrond Myklebust2-9/+15
They are not the same error, and need to be handled differently. Fixes: 183d9e7b112aa ("pnfs: rework LAYOUTGET retry handling") Cc: stable@vger.kernel.org # 4.7 Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> Reviewed-by: Jeff Layton <jlayton@redhat.com>
2016-07-19pNFS: Fix post-layoutget error handling in pnfs_update_layout()Trond Myklebust1-10/+11
The non-retry error path is currently broken and ends up releasing the reference to the layout twice. It also can end up clearing the NFS_LAYOUT_FIRST_LAYOUTGET flag twice, causing a race. In addition, the retry path will fail to decrement the plh_outstanding counter. Fixes: 183d9e7b112aa ("pnfs: rework LAYOUTGET retry handling") Cc: stable@vger.kernel.org # 4.7 Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> Reviewed-by: Jeff Layton <jlayton@redhat.com>
2016-07-18pNFS: Don't mark the inode as revalidated if a LAYOUTCOMMIT is outstandingTrond Myklebust2-1/+11
We know that the attributes will need updating if there is still a LAYOUTCOMMIT outstanding. Reported-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-15tracing: Use __get_str() when manipulating stringsDaniel Bristot de Oliveira2-4/+4
Use __get_str(str) rather than __get_dynamic_array(str) when deadling with strings. It is just a code cleanup, no changes on tracepoint ABI. Link: http://lkml.kernel.org/r/ea260df91817411cca2a1f3db2abd88860094788.1467407618.git.bristot@redhat.com Cc: Trond Myklebust <trond.myklebust@primarydata.com> Cc: Anna Schumaker <anna.schumaker@netapp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: linux-nfs@vger.kernel.org Suggested-by: Steven Rostedt <rostedt@goodmis.org> Reviewed-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2016-07-15nfs/blocklayout: Check max uuids and devices before decodingKinglong Mee1-2/+12
Avoid nfs return uuids/devices larger than maximum. Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-15nfs/blocklayout: Make sure calculate signature length alignedKinglong Mee1-1/+2
Avoid a bad nfs server return an unaligned length of signature. Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-15nfs/blocklayout: support RH/Fedora dm-mpath device nodesChristoph Hellwig1-1/+25
Instead of reusing the wwn-* names for multipath devices nodes RHEL and Fedora introduce new dm-mpath-uuid-* nodes with a slightly different naming scheme. Try these names first to ensure we always get a multipath-capable device if it exists. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-15nfs/blocklayout: refactor open-by-wwnChristoph Hellwig1-26/+27
The current code works with the standard udev/systemd names, but we'll have to add another method in the next patch. Refactor it into a separate helper to make room for the new variant. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-15nfs/blocklayout: use proper fmode for opening block devicesChristoph Hellwig1-2/+2
This was fixed for the original block layout code a while ago, but also needs to be fixed for the SCSI layout path. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-14NFSv4: Revert "Truncating file opens should also sync O_DIRECT writes"Trond Myklebust1-1/+1
We're not holding any locks, so both nfs_wb_all() and inode_dio_wait() are unenforcible and have livelock potential. Just limit ourselves to flushing out the data. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-11NFS: Don't drop CB requests with invalid principalsChuck Lever1-1/+5
Before commit 778be232a207 ("NFS do not find client in NFSv4 pg_authenticate"), the Linux callback server replied with RPC_AUTH_ERROR / RPC_AUTH_BADCRED, instead of dropping the CB request. Let's restore that behavior so the server has a chance to do something useful about it, and provide a warning that helps admins correct the problem. Fixes: 778be232a207 ("NFS do not find client in NFSv4 ...") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2016-07-06NFS nfs_vm_page_mkwrite: Don't freeze me, Bro...Trond Myklebust1-0/+3
Prevent filesystem freezes while handling the write page fault. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFSv4.2: llseek(SEEK_HOLE) and llseek(SEEK_DATA) don't require data syncTrond Myklebust1-1/+5
We want to ensure that we write the cached data to the server, but don't require it be synced to disk. If the server reboots, we will get a stateid error, which will cause us to retry anyway. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFSv4.2: Fix writeback races in nfs4_copy_file_rangeTrond Myklebust4-13/+31
We need to ensure that any writes to the destination file are serialised with the copy, meaning that the writeback has to occur under the inode lock. Also relax the writeback requirement on the source, and rely on the stateid checking to tell us if the source rebooted. Add the helper nfs_filemap_write_and_wait_range() to call pnfs_sync_inode() as is appropriate for pNFS servers that may need a layoutcommit. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFSv4.2: Fix a race in nfs42_proc_deallocate()Trond Myklebust1-2/+4
When punching holes in a file, we want to ensure the operation is serialised w.r.t. other writes, meaning that we want to call nfs_sync_inode() while holding the inode lock. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFS: Getattr doesn't require data sync semanticsTrond Myklebust1-3/+1
When retrieving stat() information, NFS unfortunately does require us to sync writes to disk in order to ensure that mtime and ctime are up to date. However we shouldn't have to ensure that those writes are persisted. Relaxing that requirement does mean that we may see an mtime/ctime change if the server reboots and forces us to replay all writes. The exception to this rule are pNFS clients that are required to send layoutcommit, however that is dealt with by the call to pnfs_sync_inode() in _nfs_revalidate_inode(). Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFS: Do not aggressively cache file attributes in the case of O_DIRECTTrond Myklebust2-2/+12
A file that is open for O_DIRECT is by definition not obeying close-to-open cache consistency semantics, so let's not cache the attributes too aggressively either. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFS: Remove unused function nfs_revalidate_mapping_protected()Trond Myklebust1-34/+4
Clean up... Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFS: Remove redundant waits for O_DIRECT in fsync() and write_begin()Trond Myklebust1-6/+0
We're now waiting immediately after taking the locks, so waiting in fsync() and write_begin() is either redundant or potentially subject to livelock (if not holding the lock). Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFS: Cleanup nfs_direct_complete()Trond Myklebust1-7/+5
There is only one caller that sets the "write" argument to true, so just move the call to nfs_zap_mapping() and get rid of the now redundant argument. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFS: Do not serialise O_DIRECT reads and writesTrond Myklebust5-37/+173
Allow dio requests to be scheduled in parallel, but ensuring that they do not conflict with buffered I/O. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFS: Move buffered I/O locking into nfs_file_write()Trond Myklebust1-12/+15
Preparation for the patch that de-serialises O_DIRECT reads and writes. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFS Cleanup: move call to generic_write_checks() into fs/nfs/direct.cTrond Myklebust2-9/+9
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFS: Remove racy size manipulations in O_DIRECTTrond Myklebust1-16/+0
On success, the RPC callbacks will ensure that we make the appropriate calls to nfs_writeback_update_inode() Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2016-07-06NFS: Ensure we reset the write verifier 'committed' value on resend.Trond Myklebust2-0/+19
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
generated by cgit v1.2.3 (git 2.39.0) at 2025-09-18 09:47:32 +0300