Hightlights include:
Stable fixes:
- Fix an incorrect calculation of the RDMA send scatter gather element limit
- Fix an Oops when attempting to free resources after RDMA device removal
Bugfixes:
- SUNRPC: Ensure we always release the TCP socket in a timely fashion when
the connection is shut down.
- SUNRPC: Don't call __UDPX_INC_STATS() from a preemptible context
Latency/Performance:
- SUNRPC: Queue latency sensitive socket tasks to the less contended
xprtiod queue
- SUNRPC: Make the xprtiod workqueue unbounded.
- SUNRPC: Make the rpciod workqueue unbounded
-----BEGIN PGP SIGNATURE-----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=KST7
-----END PGP SIGNATURE-----
Merge tag 'nfs-for-4.16-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs
Pull more NFS client updates from Trond Myklebust:
"A few bugfixes and some small sunrpc latency/performance improvements
before the merge window closes:
Stable fixes:
- fix an incorrect calculation of the RDMA send scatter gather
element limit
- fix an Oops when attempting to free resources after RDMA device
removal
Bugfixes:
- SUNRPC: Ensure we always release the TCP socket in a timely fashion
when the connection is shut down.
- SUNRPC: Don't call __UDPX_INC_STATS() from a preemptible context
Latency/Performance:
- SUNRPC: Queue latency sensitive socket tasks to the less contended
xprtiod queue
- SUNRPC: Make the xprtiod workqueue unbounded.
- SUNRPC: Make the rpciod workqueue unbounded"
* tag 'nfs-for-4.16-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
SUNRPC: Don't call __UDPX_INC_STATS() from a preemptible context
fix parallelism for rpc tasks
Make the xprtiod workqueue unbounded.
SUNRPC: Queue latency-sensitive socket tasks to xprtiod
SUNRPC: Ensure we always close the socket after a connection shuts down
xprtrdma: Fix BUG after a device removal
xprtrdma: Fix calculation of ri_max_send_sges
But it's also a fairly small update this time around. Some cleanup,
RDMA fixes, overlayfs fixes, and a fix for an NFSv4 state bug.
The bigger deal for nfsd this time around is Jeff Layton's
already-merged i_version patches. This series has a minor conflict with
that one, and the resolution should be obvious. (Stephen Rothwell has
been carrying it in linux-next for what it's worth.)
-----BEGIN PGP SIGNATURE-----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=icEX
-----END PGP SIGNATURE-----
Merge tag 'nfsd-4.16' of git://linux-nfs.org/~bfields/linux
Pull nfsd update from Bruce Fields:
"A fairly small update this time around. Some cleanup, RDMA fixes,
overlayfs fixes, and a fix for an NFSv4 state bug.
The bigger deal for nfsd this time around was Jeff Layton's
already-merged i_version patches"
* tag 'nfsd-4.16' of git://linux-nfs.org/~bfields/linux:
svcrdma: Fix Read chunk round-up
NFSD: hide unused svcxdr_dupstr()
nfsd: store stat times in fill_pre_wcc() instead of inode times
nfsd: encode stat->mtime for getattr instead of inode->i_mtime
nfsd: return RESOURCE not GARBAGE_ARGS on too many ops
nfsd4: don't set lock stateid's sc_type to CLOSED
nfsd: Detect unhashed stids in nfsd4_verify_open_stid()
sunrpc: remove dead code in svc_sock_setbufsize
svcrdma: Post Receives in the Receive completion handler
nfsd4: permit layoutget of executable-only files
lockd: convert nlm_rqst.a_count from atomic_t to refcount_t
lockd: convert nlm_lockowner.count from atomic_t to refcount_t
lockd: convert nsm_handle.sm_count from atomic_t to refcount_t
A single NFSv4 WRITE compound can often have three operations:
PUTFH, WRITE, then GETATTR.
When the WRITE payload is sent in a Read chunk, the client places
the GETATTR in the inline part of the RPC/RDMA message, just after
the WRITE operation (sans payload). The position value in the Read
chunk enables the receiver to insert the Read chunk at the correct
place in the received XDR stream; that is between the WRITE and
GETATTR.
According to RFC 8166, an NFS/RDMA client does not have to add XDR
round-up to the Read chunk that carries the WRITE payload. The
receiver adds XDR round-up padding if it is absent and the
receiver's XDR decoder requires it to be present.
Commit 193bcb7b37 ("svcrdma: Populate tail iovec when receiving")
attempted to add support for receiving such a compound so that just
the WRITE payload appears in rq_arg's page list, and the trailing
GETATTR is placed in rq_arg's tail iovec. (TCP just strings the
whole compound into the head iovec and page list, without regard
to the alignment of the WRITE payload).
The server transport logic also had to accommodate the optional XDR
round-up of the Read chunk, which it did simply by lengthening the
tail iovec when round-up was needed. This approach is adequate for
the NFSv2 and NFSv3 WRITE decoders.
Unfortunately it is not sufficient for nfsd4_decode_write. When the
Read chunk length is a couple of bytes less than PAGE_SIZE, the
computation at the end of nfsd4_decode_write allows argp->pagelen to
go negative, which breaks the logic in read_buf that looks for the
tail iovec.
The result is that a WRITE operation whose payload length is just
less than a multiple of a page succeeds, but the subsequent GETATTR
in the same compound fails with NFS4ERR_OP_ILLEGAL because the XDR
decoder can't find it. Clients ignore the error, but they must
update their attribute cache via a separate round trip.
As nfsd4_decode_write appears to expect the payload itself to always
have appropriate XDR round-up, have svc_rdma_build_normal_read_chunk
add the Read chunk XDR round-up to the page_len rather than
lengthening the tail iovec.
Reported-by: Olga Kornievskaia <kolga@netapp.com>
Fixes: 193bcb7b37 ("svcrdma: Populate tail iovec when receiving")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Michal Kalderon reports a BUG that occurs just after device removal:
[ 169.112490] rpcrdma: removing device qedr0 for 192.168.110.146:20049
[ 169.143909] BUG: unable to handle kernel NULL pointer dereference at 0000000000000010
[ 169.181837] IP: rpcrdma_dma_unmap_regbuf+0xa/0x60 [rpcrdma]
The RPC/RDMA client transport attempts to allocate some resources
on demand. Registered buffers are one such resource. These are
allocated (or re-allocated) by xprt_rdma_allocate to hold RPC Call
and Reply messages. A hardware resource is associated with each of
these buffers, as they can be used for a Send or Receive Work
Request.
If a device is removed from under an NFS/RDMA mount, the transport
layer is responsible for releasing all hardware resources before
the device can be finally unplugged. A BUG results when the NFS
mount hasn't yet seen much activity: the transport tries to release
resources that haven't yet been allocated.
rpcrdma_free_regbuf() already checks for this case, so just move
that check to cover the DEVICE_REMOVAL case as well.
Reported-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Fixes: bebd031866 ("xprtrdma: Support unplugging an HCA ...")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Cc: stable@vger.kernel.org # v4.12+
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Commit 16f906d66c ("xprtrdma: Reduce required number of send
SGEs") introduced the rpcrdma_ia::ri_max_send_sges field. This fixes
a problem where xprtrdma would not work if the device's max_sge
capability was small (low single digits).
At least RPCRDMA_MIN_SEND_SGES are needed for the inline parts of
each RPC. ri_max_send_sges is set to this value:
ia->ri_max_send_sges = max_sge - RPCRDMA_MIN_SEND_SGES;
Then when marshaling each RPC, rpcrdma_args_inline uses that value
to determine whether the device has enough Send SGEs to convey an
NFS WRITE payload inline, or whether instead a Read chunk is
required.
More recently, commit ae72950abf ("xprtrdma: Add data structure to
manage RDMA Send arguments") used the ri_max_send_sges value to
calculate the size of an array, but that commit erroneously assumed
ri_max_send_sges contains a value similar to the device's max_sge,
and not one that was reduced by the minimum SGE count.
This assumption results in the calculated size of the sendctx's
Send SGE array to be too small. When the array is used to marshal
an RPC, the code can write Send SGEs into the following sendctx
element in that array, corrupting it. When the device's max_sge is
large, this issue is entirely harmless; but it results in an oops
in the provider's post_send method, if dev.attrs.max_sge is small.
So let's straighten this out: ri_max_send_sges will now contain a
value with the same meaning as dev.attrs.max_sge, which makes
the code easier to understand, and enables rpcrdma_sendctx_create
to calculate the size of the SGE array correctly.
Reported-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Fixes: 16f906d66c ("xprtrdma: Reduce required number of send SGEs")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Cc: stable@vger.kernel.org # v4.10+
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Track RPC timeouts: report the XID and the server address to match
the content of network capture.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Fix kernel-doc warnings in net/sunrpc/xprtrdma/ .
net/sunrpc/xprtrdma/verbs.c:1575: warning: No description found for parameter 'count'
net/sunrpc/xprtrdma/verbs.c:1575: warning: Excess function parameter 'min_reqs' description in 'rpcrdma_ep_post_extra_recv'
net/sunrpc/xprtrdma/backchannel.c:288: warning: No description found for parameter 'r_xprt'
net/sunrpc/xprtrdma/backchannel.c:288: warning: Excess function parameter 'xprt' description in 'rpcrdma_bc_receive_call'
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
The contents of seg->mr_len changed when ->ro_map stopped returning
the full chunk length in the first segment. Count the full length of
each Write chunk, not the length of the first segment (which now can
only be as large as a page).
Fixes: 9d6b040978 ("xprtrdma: Place registered MWs on a ... ")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
This includes decoding Write and Reply chunks, and fixing up inline
payloads.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
This change improves Receive efficiency by posting Receives only
on the same CPU that handles Receive completion. Improved latency
and throughput has been noted with this change.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Clean up: Code review suggested that a common bit of code can be
placed into a helper function, and this gives us fewer places to
stick an "I DMA unmapped something" trace point.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up: struct rpcrdma_mw was named after Memory Windows, but
xprtrdma no longer supports a Memory Window registration mode.
Rename rpcrdma_mw and its fields to reduce confusion and make
the code more sensible to read.
Renaming "mw" was suggested by Tom Talpey, the author of the
original xprtrdma implementation. It's a good idea, but I haven't
done this until now because it's a huge diffstat for no benefit
other than code readability.
However, I'm about to introduce static trace points that expose
a few of xprtrdma's internal data structures. They should make sense
in the trace report, and it's reasonable to treat trace points as a
kernel API contract which might be difficult to change later.
While I'm churning things up, two additional changes:
- rename variables unhelpfully called "r" to "mr", to improve code
clarity, and
- rename the MR-related helper functions using the form
"rpcrdma_mr_<verb>", to be consistent with other areas of the
code.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up: Over time, the industry has adopted the term "frwr"
instead of "frmr". The term "frwr" is now more widely recognized.
For the past couple of years I've attempted to add new code using
"frwr" , but there still remains plenty of older code that still
uses "frmr". Replace all usage of "frmr" to avoid confusion.
While we're churning code, rename variables unhelpfully called "f"
to "frwr", to improve code clarity.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
No need for the overhead of atomically setting and clearing this bit
flag for every use of a pre-allocated backchannel rpc_rqst. These
are a distinct pool of rpc_rqsts that are used only for callback
operations, so it is safe to simply leave the bit set.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up. @rqst is set up differently for backchannel Replies. For
example, rqst->rq_task and task->tk_client are both NULL. So it is
easier to understand and maintain this code path if it is separated.
Also, we can get rid of the confusing rl_connect_cookie hack in
rpcrdma_bc_receive_call.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Since commit 5a6d1db455 ("SUNRPC: Add a transport-specific private
field in rpc_rqst"), the rpc_rqst's for RPC-over-RDMA backchannel
operations leave rq_buffer set to NULL.
xprt_release does not invoke ->op->buf_free when rq_buffer is NULL.
The RPCRDMA_REQ_F_BACKCHANNEL check in xprt_rdma_free is therefore
redundant because xprt_rdma_free is not invoked for backchannel
requests.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up. This logic is related to marshaling the request, and I'd
like to keep everything that touches req->rl_registered close
together, for CPU cache efficiency.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up a harmless oversight. xprtrdma's ->set_port method has
never properly supported IPv6.
This issue has never been a problem because NFS/RDMA mounts have
always required "port=20049", thus so far, rpcbind is not invoked
for these mounts.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Save more space in struct rpcrdma_xprt by removing the redundant
"addr" field from struct rpcrdma_create_data_internal. Wherever
we have rpcrdma_xprt, we also have the rpc_xprt, which has a
sockaddr_storage field with the same content.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
This makes the address strings available for debugging messages in
earlier stages of transport set up.
The first benefit is to get rid of the single-use rep_remote_addr
field, saving 128+ bytes in struct rpcrdma_ep.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up. Remove fields that should have been removed by
commit b3221d6a53 ("xprtrdma: Remove logic that constructs
RDMA_MSGP type calls").
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up.
Commit b5f0afbea4 ("xprtrdma: Per-connection pad optimization")
should have removed this.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Refactoring change: Remote Invalidation is particular to the memory
registration mode that is use. Use a callout instead of a generic
function to handle Remote Invalidation.
This gets rid of the 8-byte flags field in struct rpcrdma_mw, of
which only a single bit flag has been allocated.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
The rpcrdma_req is not shared yet, and its associated Send hasn't
been posted, thus RMW should be safe. There's no need for the
expense of a lock cycle here.
Fixes: 0ba6f37012 ("xprtrdma: Refactor rpcrdma_deferred_completion")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
The backchannel code uses rpcrdma_recv_buffer_put to add new reps
to the free rep list. This also decrements rb_recv_count, which
spoofs the receive overrun logic in rpcrdma_buffer_get_rep.
Commit 9b06688bc3 ("xprtrdma: Fix additional uses of
spin_lock_irqsave(rb_lock)") replaced the original open-coded
list_add with a call to rpcrdma_recv_buffer_put(), but then a year
later, commit 05c974669e ("xprtrdma: Fix receive buffer
accounting") added rep accounting to rpcrdma_recv_buffer_put.
It was an oversight to let the backchannel continue to use this
function.
The fix this, let's combine the "add to free list" logic with
rpcrdma_create_rep.
Also, do not allocate RPCRDMA_MAX_BC_REQUESTS rpcrdma_reps in
rpcrdma_buffer_create and then allocate additional rpcrdma_reps in
rpcrdma_bc_setup_reps. Allocating the extra reps during backchannel
set-up is sufficient.
Fixes: 05c974669e ("xprtrdma: Fix receive buffer accounting")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
This leak has been around forever, and is exceptionally rare.
EINVAL causes mount to fail with "an incorrect mount option was
specified" although it's not likely that one of the mount
options is incorrect. Instead, return ENODEV in this case, as this
appears to be an issue with system or device configuration rather
than a specific mount option.
Some obsolete comments are also removed.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Stable bugfixes:
- NFS: Avoid a BUG_ON() in nfs_commit_inode() by not waiting for a
commit in the case that there were no commit requests.
- SUNRPC: Fix a race in the receive code path
Other fixes:
- NFS: Fix a deadlock in nfs client initialization
- xprtrdma: Fix a performance regression for small IOs
-----BEGIN PGP SIGNATURE-----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=XhEC
-----END PGP SIGNATURE-----
Merge tag 'nfs-for-4.15-3' of git://git.linux-nfs.org/projects/anna/linux-nfs
Pull NFS client fixes from Anna Schumaker:
"This has two stable bugfixes, one to fix a BUG_ON() when
nfs_commit_inode() is called with no outstanding commit requests and
another to fix a race in the SUNRPC receive codepath.
Additionally, there are also fixes for an NFS client deadlock and an
xprtrdma performance regression.
Summary:
Stable bugfixes:
- NFS: Avoid a BUG_ON() in nfs_commit_inode() by not waiting for a
commit in the case that there were no commit requests.
- SUNRPC: Fix a race in the receive code path
Other fixes:
- NFS: Fix a deadlock in nfs client initialization
- xprtrdma: Fix a performance regression for small IOs"
* tag 'nfs-for-4.15-3' of git://git.linux-nfs.org/projects/anna/linux-nfs:
SUNRPC: Fix a race in the receive code path
nfs: don't wait on commit in nfs_commit_inode() if there were no commit requests
xprtrdma: Spread reply processing over more CPUs
nfs: fix a deadlock in nfs client initialization
Commit d8f532d20e ("xprtrdma: Invoke rpcrdma_reply_handler
directly from RECV completion") introduced a performance regression
for NFS I/O small enough to not need memory registration. In multi-
threaded benchmarks that generate primarily small I/O requests,
IOPS throughput is reduced by nearly a third. This patch restores
the previous level of throughput.
Because workqueues are typically BOUND (in particular ib_comp_wq,
nfsiod_workqueue, and rpciod_workqueue), NFS/RDMA workloads tend
to aggregate on the CPU that is handling Receive completions.
The usual approach to addressing this problem is to create a QP
and CQ for each CPU, and then schedule transactions on the QP
for the CPU where you want the transaction to complete. The
transaction then does not require an extra context switch during
completion to end up on the same CPU where the transaction was
started.
This approach doesn't work for the Linux NFS/RDMA client because
currently the Linux NFS client does not support multiple connections
per client-server pair, and the RDMA core API does not make it
straightforward for ULPs to determine which CPU is responsible for
handling Receive completions for a CQ.
So for the moment, record the CPU number in the rpcrdma_req before
the transport sends each RPC Call. Then during Receive completion,
queue the RPC completion on that same CPU.
Additionally, move all RPC completion processing to the deferred
handler so that even RPCs with simple small replies complete on
the CPU that sent the corresponding RPC Call.
Fixes: d8f532d20e ("xprtrdma: Invoke rpcrdma_reply_handler ...")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
- fix a number of races in the NFSv4+ state code.
- fix some shutdown crashes in multiple-network-namespace cases.
- relax our 4.1 session limits; if you've an artificially low limit
to the number of 4.1 clients that can mount simultaneously, try
upgrading.
-----BEGIN PGP SIGNATURE-----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=PBs+
-----END PGP SIGNATURE-----
Merge tag 'nfsd-4.15' of git://linux-nfs.org/~bfields/linux
Pull nfsd updates from Bruce Fields:
"Lots of good bugfixes, including:
- fix a number of races in the NFSv4+ state code
- fix some shutdown crashes in multiple-network-namespace cases
- relax our 4.1 session limits; if you've an artificially low limit
to the number of 4.1 clients that can mount simultaneously, try
upgrading"
* tag 'nfsd-4.15' of git://linux-nfs.org/~bfields/linux: (22 commits)
SUNRPC: Improve ordering of transport processing
nfsd: deal with revoked delegations appropriately
svcrdma: Enqueue after setting XPT_CLOSE in completion handlers
nfsd: use nfs->ns.inum as net ID
rpc: remove some BUG()s
svcrdma: Preserve CB send buffer across retransmits
nfds: avoid gettimeofday for nfssvc_boot time
fs, nfsd: convert nfs4_file.fi_ref from atomic_t to refcount_t
fs, nfsd: convert nfs4_cntl_odstate.co_odcount from atomic_t to refcount_t
fs, nfsd: convert nfs4_stid.sc_count from atomic_t to refcount_t
lockd: double unregister of inetaddr notifiers
nfsd4: catch some false session retries
nfsd4: fix cached replies to solo SEQUENCE compounds
sunrcp: make function _svc_create_xprt static
SUNRPC: Fix tracepoint storage issues with svc_recv and svc_rqst_status
nfsd: use ARRAY_SIZE
nfsd: give out fewer session slots as limit approaches
nfsd: increase DRC cache limit
nfsd: remove unnecessary nofilehandle checks
nfs_common: convert int to bool
...
Stable bugfixes:
- Revalidate "." and ".." correctly on open
- Avoid RCU usage in tracepoints
- Fix ugly referral attributes
- Fix a typo in nomigration mount option
- Revert "NFS: Move the flock open mode check into nfs_flock()"
Features:
- Implement a stronger send queue accounting system for NFS over RDMA
- Switch some atomics to the new refcount_t type
Other bugfixes and cleanups:
- Clean up access mode bits
- Remove special-case revalidations in nfs_opendir()
- Improve invalidating NFS over RDMA memory for async operations that time out
- Handle NFS over RDMA replies with a worqueue
- Handle NFS over RDMA sends with a workqueue
- Fix up replaying interrupted requests
- Remove dead NFS over RDMA definitions
- Update NFS over RDMA copyright information
- Be more consistent with bool initialization and comparisons
- Mark expected switch fall throughs
- Various sunrpc tracepoint cleanups
- Fix various OPEN races
- Fix a typo in nfs_rename()
- Use common error handling code in nfs_lock_and_join_request()
- Check that some structures are properly cleaned up during net_exit()
- Remove net pointer from dprintk()s
-----BEGIN PGP SIGNATURE-----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=2Zc1
-----END PGP SIGNATURE-----
Merge tag 'nfs-for-4.15-1' of git://git.linux-nfs.org/projects/anna/linux-nfs
Pull NFS client updates from Anna Schumaker:
"Stable bugfixes:
- Revalidate "." and ".." correctly on open
- Avoid RCU usage in tracepoints
- Fix ugly referral attributes
- Fix a typo in nomigration mount option
- Revert "NFS: Move the flock open mode check into nfs_flock()"
Features:
- Implement a stronger send queue accounting system for NFS over RDMA
- Switch some atomics to the new refcount_t type
Other bugfixes and cleanups:
- Clean up access mode bits
- Remove special-case revalidations in nfs_opendir()
- Improve invalidating NFS over RDMA memory for async operations that
time out
- Handle NFS over RDMA replies with a worqueue
- Handle NFS over RDMA sends with a workqueue
- Fix up replaying interrupted requests
- Remove dead NFS over RDMA definitions
- Update NFS over RDMA copyright information
- Be more consistent with bool initialization and comparisons
- Mark expected switch fall throughs
- Various sunrpc tracepoint cleanups
- Fix various OPEN races
- Fix a typo in nfs_rename()
- Use common error handling code in nfs_lock_and_join_request()
- Check that some structures are properly cleaned up during
net_exit()
- Remove net pointer from dprintk()s"
* tag 'nfs-for-4.15-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (62 commits)
NFS: Revert "NFS: Move the flock open mode check into nfs_flock()"
NFS: Fix typo in nomigration mount option
nfs: Fix ugly referral attributes
NFS: super: mark expected switch fall-throughs
sunrpc: remove net pointer from messages
nfs: remove net pointer from messages
sunrpc: exit_net cleanup check added
nfs client: exit_net cleanup check added
nfs/write: Use common error handling code in nfs_lock_and_join_requests()
NFSv4: Replace closed stateids with the "invalid special stateid"
NFSv4: nfs_set_open_stateid must not trigger state recovery for closed state
NFSv4: Check the open stateid when searching for expired state
NFSv4: Clean up nfs4_delegreturn_done
NFSv4: cleanup nfs4_close_done
NFSv4: Retry NFS4ERR_OLD_STATEID errors in layoutreturn
pNFS: Retry NFS4ERR_OLD_STATEID errors in layoutreturn-on-close
NFSv4: Don't try to CLOSE if the stateid 'other' field has changed
NFSv4: Retry CLOSE and DELEGRETURN on NFS4ERR_OLD_STATEID.
NFS: Fix a typo in nfs_rename()
NFSv4: Fix open create exclusive when the server reboots
...
Credit work contributed by Oracle engineers since 2014.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up. This include should have been removed by
commit 23826c7aea ("xprtrdma: Serialize credit accounting again").
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up: C-structure style XDR encoding and decoding logic has
been replaced over the past several merge windows on both the
client and server. These data structures are no longer used.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Lift the Send and LocalInv completion handlers out of soft IRQ mode
to make room for other work. Also, move the Send CQ to a different
CPU than the CPU where the Receive CQ is running, for improved
scalability.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
The sendctx circular queue now guarantees that xprtrdma cannot
overflow the Send Queue, so remove the remaining bits of the
original Send WQE counting mechanism.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
When an RPC Call includes a file data payload, that payload can come
from pages in the page cache, or a user buffer (for direct I/O).
If the payload can fit inline, xprtrdma includes it in the Send
using a scatter-gather technique. xprtrdma mustn't allow the RPC
consumer to re-use the memory where that payload resides before the
Send completes. Otherwise, the new contents of that memory would be
exposed by an HCA retransmit of the Send operation.
So, block RPC completion on Send completion, but only in the case
where a separate file data payload is part of the Send. This
prevents the reuse of that memory while it is still part of a Send
operation without an undue cost to other cases.
Waiting is avoided in the common case because typically the Send
will have completed long before the RPC Reply arrives.
These days, an RPC timeout will trigger a disconnect, which tears
down the QP. The disconnect flushes all waiting Sends. This bounds
the amount of time the reply handler has to wait for a Send
completion.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Invoke a common routine for releasing hardware resources (for
example, invalidating MRs). This needs to be done whether an
RPC Reply has arrived or the RPC was terminated early.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
We have one boolean flag in rpcrdma_req today. I'd like to add more
flags, so convert that boolean to a bit flag.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Problem statement:
Recently Sagi Grimberg <sagi@grimberg.me> observed that kernel RDMA-
enabled storage initiators don't handle delayed Send completion
correctly. If Send completion is delayed beyond the end of a ULP
transaction, the ULP may release resources that are still being used
by the HCA to complete a long-running Send operation.
This is a common design trait amongst our initiators. Most Send
operations are faster than the ULP transaction they are part of.
Waiting for a completion for these is typically unnecessary.
Infrequently, a network partition or some other problem crops up
where an ordering problem can occur. In NFS parlance, the RPC Reply
arrives and completes the RPC, but the HCA is still retrying the
Send WR that conveyed the RPC Call. In this case, the HCA can try
to use memory that has been invalidated or DMA unmapped, and the
connection is lost. If that memory has been re-used for something
else (possibly not related to NFS), and the Send retransmission
exposes that data on the wire.
Thus we cannot assume that it is safe to release Send-related
resources just because a ULP reply has arrived.
After some analysis, we have determined that the completion
housekeeping will not be difficult for xprtrdma:
- Inline Send buffers are registered via the local DMA key, and
are already left DMA mapped for the lifetime of a transport
connection, thus no additional handling is necessary for those
- Gathered Sends involving page cache pages _will_ need to
DMA unmap those pages after the Send completes. But like
inline send buffers, they are registered via the local DMA key,
and thus will not need to be invalidated
In addition, RPC completion will need to wait for Send completion
in the latter case. However, nearly always, the Send that conveys
the RPC Call will have completed long before the RPC Reply
arrives, and thus no additional latency will be accrued.
Design notes:
In this patch, the rpcrdma_sendctx object is introduced, and a
lock-free circular queue is added to manage a set of them per
transport.
The RPC client's send path already prevents sending more than one
RPC Call at the same time. This allows us to treat the consumer
side of the queue (rpcrdma_sendctx_get_locked) as if there is a
single consumer thread.
The producer side of the queue (rpcrdma_sendctx_put_locked) is
invoked only from the Send completion handler, which is a single
thread of execution (soft IRQ).
The only care that needs to be taken is with the tail index, which
is shared between the producer and consumer. Only the producer
updates the tail index. The consumer compares the head with the
tail to ensure that the a sendctx that is in use is never handed
out again (or, expressed more conventionally, the queue is empty).
When the sendctx queue empties completely, there are enough Sends
outstanding that posting more Send operations can result in a Send
Queue overflow. In this case, the ULP is told to wait and try again.
This introduces strong Send Queue accounting to xprtrdma.
As a final touch, Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
suggested a mechanism that does not require signaling every Send.
We signal once every N Sends, and perform SGE unmapping of N Send
operations during that one completion.
Reported-by: Sagi Grimberg <sagi@grimberg.me>
Suggested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Commit 655fec6987 ("xprtrdma: Use gathered Send for large inline
messages") assumed that, since the zeroeth element of the Send SGE
array always pointed to req->rl_rdmabuf, it needed to be initialized
just once. This was a valid assumption because the Send SGE array
and rl_rdmabuf both live in the same rpcrdma_req.
In a subsequent patch, the Send SGE array will be separated from the
rpcrdma_req, so the zeroeth element of the SGE array needs to be
initialized every time.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
