summaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2021-04-26xprtrdma: Put flushed Receives on free list instead of destroying themChuck Lever1-1/+3
Defer destruction of an rpcrdma_rep until transport tear-down to preserve the rb_all_reps list while Receives flush. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Tom Talpey <tom@talpey.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-26xprtrdma: Do not refresh Receive Queue while it is drainingChuck Lever2-0/+14
Currently the Receive completion handler refreshes the Receive Queue whenever a successful Receive completion occurs. On disconnect, xprtrdma drains the Receive Queue. The first few Receive completions after a disconnect are typically successful, until the first flushed Receive. This means the Receive completion handler continues to post more Receive WRs after the drain sentinel has been posted. The late- posted Receives flush after the drain sentinel has completed, leading to a crash later in rpcrdma_xprt_disconnect(). To prevent this crash, xprtrdma has to ensure that the Receive handler stops posting Receives before ib_drain_rq() posts its drain sentinel. Suggested-by: Tom Talpey <tom@talpey.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-26xprtrdma: Avoid Receive Queue wrappingChuck Lever1-0/+1
Commit e340c2d6ef2a ("xprtrdma: Reduce the doorbell rate (Receive)") increased the number of Receive WRs that are posted by the client, but did not increase the size of the Receive Queue allocated during transport set-up. This is usually not an issue because RPCRDMA_BACKWARD_WRS is defined as (32) when SUNRPC_BACKCHANNEL is defined. In cases where it isn't, there is a real risk of Receive Queue wrapping. Fixes: e340c2d6ef2a ("xprtrdma: Reduce the doorbell rate (Receive)") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Tom Talpey <tom@talpey.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-21NFS: The 'fattr_valid' field in struct nfs_server should be unsigned intTrond Myklebust1-2/+1
Fix up a static compiler warning: "fs/nfs/nfs4proc.c:3882 _nfs4_server_capabilities() warn: was expecting a 64 bit value instead of '(1 << 11)'" The fix is to convert the fattr_valid field to match the type of the 'valid' field in struct nfs_fattr. Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-18NFSv4.1: Simplify layout return in pnfs_layout_process()Trond Myklebust1-3/+1
If the server hands us a layout that does not match the one we currently hold, then have pnfs_mark_matching_lsegs_return() just ditch the old layout if NFS_LSEG_LAYOUTRETURN is not set. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-18NFSv4: Don't discard segments marked for return in _pnfs_return_layout()Trond Myklebust1-1/+1
If the pNFS layout segment is marked with the NFS_LSEG_LAYOUTRETURN flag, then the assumption is that it has some reporting requirement to perform through a layoutreturn (e.g. flexfiles layout stats or error information). Fixes: 6d597e175012 ("pnfs: only tear down lsegs that precede seqid in LAYOUTRETURN args") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-16NFS: Don't discard pNFS layout segments that are marked for returnTrond Myklebust1-0/+5
If the pNFS layout segment is marked with the NFS_LSEG_LAYOUTRETURN flag, then the assumption is that it has some reporting requirement to perform through a layoutreturn (e.g. flexfiles layout stats or error information). Fixes: e0b7d420f72a ("pNFS: Don't discard layout segments that are marked for return") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-16NFSv4.x: Don't return NFS4ERR_NOMATCHING_LAYOUT if we're unmountingTrond Myklebust1-8/+9
If the NFS super block is being unmounted, then we currently may end up telling the server that we've forgotten the layout while it is actually still in use by the client. In that case, just assume that the client will soon return the layout anyway, and so return NFS4ERR_DELAY in response to the layout recall. Fixes: 58ac3e59235f ("NFSv4/pnfs: Clean up nfs_layout_find_inode()") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14NFSv42: Don't force attribute revalidation of the copy offload sourceTrond Myklebust1-6/+1
When a copy offload is performed, we do not expect the source file to change other than perhaps to see the atime be updated. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14NFSv42: Copy offload should update the file size when appropriateTrond Myklebust1-9/+32
If the result of a copy offload or clone operation is to grow the destination file size, then we should update it. The reason is that when a client holds a delegation, it is authoritative for the file size. Fixes: 16abd2a0c124 ("NFSv4.2: fix client's attribute cache management for copy_file_range") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14SUNRPC: Handle major timeout in xprt_adjust_timeout()Chris Dion1-2/+2
Currently if a major timeout value is reached, but the minor value has not been reached, an ETIMEOUT will not be sent back to the caller. This can occur if the v4 server is not responding to requests and retrans is configured larger than the default of two. For example, A TCP mount with a configured timeout value of 50 and a retransmission count of 3 to a v4 server which is not responding: 1. Initial value and increment set to 5s, maxval set to 20s, retries at 3 2. Major timeout is set to 20s, minor timeout set to 5s initially 3. xport_adjust_timeout() is called after 5s, retry with 10s timeout, minor timeout is bumped to 10s 4. And again after another 10s, 15s total time with minor timeout set to 15s 5. After 20s total time xport_adjust_timeout is called as major timeout is reached, but skipped because the minor timeout is not reached - After this time the cpu spins continually calling xport_adjust_timeout() and returning 0 for 10 seconds. As seen on perf sched: 39243.913182 [0005] mount.nfs[3794] 4607.938 0.017 9746.863 6. This continues until the 15s minor timeout condition is reached (in this case for 10 seconds). After which the ETIMEOUT is processed back to the caller, the cpu spinning stops, and normal operations continue Fixes: 7de62bc09fe6 ("SUNRPC dont update timeout value on connection reset") Signed-off-by: Chris Dion <Christopher.Dion@dell.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14SUNRPC: Remove trace_xprt_transmit_queuedChuck Lever2-3/+0
This tracepoint can crash when dereferencing snd_task because when some transports connect, they put a cookie in that field instead of a pointer to an rpc_task. BUG: KASAN: use-after-free in trace_event_raw_event_xprt_writelock_event+0x141/0x18e [sunrpc] Read of size 2 at addr ffff8881a83bd3a0 by task git/331872 CPU: 11 PID: 331872 Comm: git Tainted: G S 5.12.0-rc2-00007-g3ab6e585a7f9 #1453 Hardware name: Supermicro SYS-6028R-T/X10DRi, BIOS 1.1a 10/16/2015 Call Trace: dump_stack+0x9c/0xcf print_address_description.constprop.0+0x18/0x239 kasan_report+0x174/0x1b0 trace_event_raw_event_xprt_writelock_event+0x141/0x18e [sunrpc] xprt_prepare_transmit+0x8e/0xc1 [sunrpc] call_transmit+0x4d/0xc6 [sunrpc] Fixes: 9ce07ae5eb1d ("SUNRPC: Replace dprintk() call site in xprt_prepare_transmit") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14SUNRPC: Add tracepoint that fires when an RPC is retransmittedChuck Lever2-1/+43
A separate tracepoint can be left enabled all the time to capture rare but important retransmission events. So for example: kworker/u26:3-568 [009] 156.967933: xprt_retransmit: task:44093@5 xid=0xa25dbc79 nfsv3 WRITE ntrans=2 Or, for example, enable all nfs and nfs4 tracepoints, and set up a trigger to disable tracing when xprt_retransmit fires to capture everything that leads up to it. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14SUNRPC: Move fault injection call sitesChuck Lever3-5/+8
I've hit some crashes that occur in the xprt_rdma_inject_disconnect path. It appears that, for some provides, rdma_disconnect() can take so long that the transport can disconnect and release its hardware resources while rdma_disconnect() is still running, resulting in a UAF in the provider. The transport's fault injection method may depend on the stability of transport data structures. That means it needs to be invoked only from contexts that hold the transport write lock. Fixes: 4a0682583988 ("SUNRPC: Transport fault injection") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14NFSv4.2 fix handling of sr_eof in SEEK's replyOlga Kornievskaia1-1/+4
Currently the client ignores the value of the sr_eof of the SEEK operation. According to the spec, if the server didn't find the requested extent and reached the end of the file, the server would return sr_eof=true. In case the request for DATA and no data was found (ie in the middle of the hole), then the lseek expects that ENXIO would be returned. Fixes: 1c6dcbe5ceff8 ("NFS: Implement SEEK") Signed-off-by: Olga Kornievskaia <kolga@netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14pNFS/flexfiles: fix incorrect size check in decode_nfs_fh()Nikola Livic1-1/+1
We (adam zabrocki, alexander matrosov, alexander tereshkin, maksym bazalii) observed the check: if (fh->size > sizeof(struct nfs_fh)) should not use the size of the nfs_fh struct which includes an extra two bytes from the size field. struct nfs_fh { unsigned short size; unsigned char data[NFS_MAXFHSIZE]; } but should determine the size from data[NFS_MAXFHSIZE] so the memcpy will not write 2 bytes beyond destination. The proposed fix is to compare against the NFS_MAXFHSIZE directly, as is done elsewhere in fs code base. Fixes: d67ae825a59d ("pnfs/flexfiles: Add the FlexFile Layout Driver") Signed-off-by: Nikola Livic <nlivic@gmail.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14NFSv4: Catch and trace server filehandle encoding errorsTrond Myklebust5-6/+14
If the server returns a filehandle with an invalid length, then trace that, and return an EREMOTEIO error. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14NFSv4: Convert nfs_xdr_status tracepoint to an event classTrond Myklebust2-2/+19
We would like the ability to record other XDR errors, particularly those that are due to server bugs. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14NFSv4: Add tracing for COMPOUND errorsTrond Myklebust2-3/+36
When the server returns a different operation than we expected, then trace that. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14NFS: Split attribute support out from the server capabilitiesTrond Myklebust4-56/+70
There are lots of attributes, and they are crowding out the bit space. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14NFS: Don't store NFS_INO_REVAL_FORCEDTrond Myklebust4-52/+43
NFS_INO_REVAL_FORCED is intended to tell us that the cache needs revalidation despite the fact that we hold a delegation. We shouldn't need to store it anymore, though. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14NFSv4: link must update the inode nlink.Trond Myklebust2-1/+10
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-14NFSv4: nfs4_inc/dec_nlink_locked should also invalidate ctimeTrond Myklebust1-7/+11
If the nlink changes, then so will the ctime. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Another inode revalidation improvementTrond Myklebust1-1/+29
If we're trying to update the inode because a previous update left the cache in a partially unrevalidated state, then allow the update if the change attrs match. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Use information about the change attribute to optimise updatesTrond Myklebust2-21/+110
If the NFSv4.2 server supports the 'change_attr_type' attribute, then allow the client to optimise its attribute cache update strategy. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFSv4: Add support for the NFSv4.2 "change_attr_type" attributeTrond Myklebust8-0/+52
The change_attr_type allows the server to provide a description of how the change attribute will behave. This again will allow the client to optimise its behaviour w.r.t. attribute revalidation. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFSv4: Don't modify the change attribute cached in the inodeTrond Myklebust1-3/+0
When the client is caching data and a write delegation is held, then the server may send a CB_GETATTR to query the attributes. When this happens, the client is supposed to bump the change attribute value that it returns if it holds cached data. However that process uses a value that is stored in the delegation. We do not want to bump the change attribute held in the inode. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFSv4: Fix value of decode_fsinfo_maxszTrond Myklebust1-1/+10
At least two extra fields have been added to fsinfo since this was last updated. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Simplify cache consistency in nfs_check_inode_attributes()Trond Myklebust1-13/+5
We should not be invalidating the access or acl caches in nfs_check_inode_attributes(), since the point is we're unsure about whether the contents of the struct nfs_fattr are fully up to date. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Remove a line of code that has no effect in nfs_update_inode()Trond Myklebust1-1/+0
Commit 0b467264d0db ("NFS: Fix attribute revalidation") changed the way we populate the 'invalid' attribute, and made the line that strips away the NFS_INO_INVALID_ATTR bits redundant. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Fix up handling of outstanding layoutcommit in nfs_update_inode()Trond Myklebust1-1/+5
If there is an outstanding layoutcommit, then the list of attributes whose values are expected to change is not the full set. So let's be explicit about the full list. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Separate tracking of file mode cache validity from the uid/gidTrond Myklebust6-15/+30
chown()/chgrp() and chmod() are separate operations, and in addition, there are mode operations that are performed automatically by the server. So let's track mode validity separately from the file ownership validity. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Separate tracking of file nlinks cache validity from the mode/uid/gidTrond Myklebust5-13/+23
Rename can cause us to revalidate the access cache, so lets track the nlinks separately from the mode/uid/gid. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFSv4: Fix nfs4_bitmap_copy_adjust()Trond Myklebust1-17/+16
Don't remove flags from the set retrieved from the cache_validity. We do want to retrieve all attributes that are listed as being invalid, whether or not there is a delegation set. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Don't set NFS_INO_REVAL_PAGECACHE in the inode cache validityTrond Myklebust2-5/+2
It is no longer necessary to preserve the NFS_INO_REVAL_PAGECACHE flag. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Replace use of NFS_INO_REVAL_PAGECACHE when checking cache validityTrond Myklebust4-34/+16
When checking cache validity, be more specific than just 'we want to check the page cache validity'. In almost all cases, we want to check that change attribute, and possibly also the size. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Add a cache validity flag argument to nfs_revalidate_inode()Trond Myklebust6-29/+14
Add an argument to nfs_revalidate_inode() to allow callers to specify which attributes they need to check for validity. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: nfs_setattr_update_inode() should clear the suid/sgid bitsTrond Myklebust1-2/+8
When we do a 'chown' or 'chgrp', the server will clear the suid/sgid bits. Ensure that we mirror that in nfs_setattr_update_inode(). Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Fix up statx() resultsTrond Myklebust1-3/+26
If statx has valid attributes available that weren't asked for, then return them and set the result mask appropriately. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Don't revalidate attributes that are not being asked forTrond Myklebust1-4/+9
If the user doesn't set STATX_UID/GID/MODE, then don't care if they are known to be stale. Ditto if we're not being asked for the file size. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Fix up revalidation of space usedTrond Myklebust1-3/+12
Ensure that when the change attribute or the size change, we also remember to revalidate the space used. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: NFS_INO_REVAL_PAGECACHE should mark the change attribute invalidTrond Myklebust1-1/+2
When we're looking to revalidate the page cache, we should just ensure that we mark the change attribute invalid. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Mask out unsupported attributes in nfs_getattr()Trond Myklebust1-0/+4
We don't currently support STATX_BTIME, so don't advertise it in the return values for nfs_getattr(). Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Fix up inode cache tracingTrond Myklebust1-0/+5
Add missing enum definitions and missing entries for nfs_show_cache_validity(). Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Deal correctly with attribute generation counter overflowTrond Myklebust1-4/+4
We need to use unsigned long subtraction and then convert to signed in order to deal correcly with C overflow rules. Fixes: f5062003465c ("NFS: Set an attribute barrier on all updates") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFSv4.2: Always flush out writes in nfs42_proc_fallocate()Trond Myklebust1-7/+9
Whether we're allocating or delallocating space, we should flush out the pending writes in order to avoid races with attribute updates. Fixes: 1e564d3dbd68 ("NFSv4.2: Fix a race in nfs42_proc_deallocate()") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: Fix attribute bitmask in _nfs42_proc_fallocate()Trond Myklebust1-2/+8
We can't use nfs4_fattr_bitmap as a bitmask, because it hasn't been filtered to represent the attributes supported by the server. Instead, let's revert to using server->cache_consistency_bitmask after adding in the missing SPACE_USED attribute. Fixes: 913eca1aea87 ("NFS: Fallocate should use the nfs4_fattr_bitmap") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-13NFS: nfs4_bitmask_adjust() must not change the server global bitmasksTrond Myklebust2-25/+42
As currently set, the calls to nfs4_bitmask_adjust() will end up overwriting the contents of the nfs_server cache_consistency_bitmask field. The intention here should be to modify a private copy of that mask in the close/delegreturn/write arguments. Fixes: 76bd5c016ef4 ("NFSv4: make cache consistency bitmask dynamic") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-05NFS: Fix fscache invalidation in nfs_set_cache_invalid()Trond Myklebust1-2/+2
Ensure that we invalidate the fscache before we strip the NFS_INO_INVALID_DATA flag. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2021-04-05NFS: fix nfs_fetch_iversion()Trond Myklebust1-11/+4
The change attribute is always set by all NFS client versions so get rid of the open-coded version. Fixes: 3cc55f4434b4 ("nfs: use change attribute for NFS re-exports") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-04 22:46:21 +0300