Add a per-transport maximum limit in the socket case, and add
helpers to allow the NFSv4 code to discover that limit.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
NFSoRDMA client updates for 5.3
New features:
- Add a way to place MRs back on the free list
- Reduce context switching
- Add new trace events
Bugfixes and cleanups:
- Fix a BUG when tracing is enabled with NFSv4.1
- Fix a use-after-free in rpcrdma_post_recvs
- Replace use of xdr_stream_pos in rpcrdma_marshal_req
- Fix occasional transport deadlock
- Fix show_nfs_errors macros, other tracing improvements
- Remove RPCRDMA_REQ_F_PENDING and fr_state
- Various simplifications and refactors
Pull SCSI scatter-gather list updates from James Bottomley:
"This topic branch covers a fundamental change in how our sg lists are
allocated to make mq more efficient by reducing the size of the
preallocated sg list.
This necessitates a large number of driver changes because the
previous guarantee that if a driver specified SG_ALL as the size of
its scatter list, it would get a non-chained list and didn't need to
bother with scatterlist iterators is now broken and every driver
*must* use scatterlist iterators.
This was broken out as a separate topic because we need to convert all
the drivers before pulling the trigger and unconverted drivers kept
being found, necessitating a rebase"
* tag 'scsi-sg' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (21 commits)
scsi: core: don't preallocate small SGL in case of NO_SG_CHAIN
scsi: lib/sg_pool.c: clear 'first_chunk' in case of no preallocation
scsi: core: avoid preallocating big SGL for data
scsi: core: avoid preallocating big SGL for protection information
scsi: lib/sg_pool.c: improve APIs for allocating sg pool
scsi: esp: use sg helper to iterate over scatterlist
scsi: NCR5380: use sg helper to iterate over scatterlist
scsi: wd33c93: use sg helper to iterate over scatterlist
scsi: ppa: use sg helper to iterate over scatterlist
scsi: pcmcia: nsp_cs: use sg helper to iterate over scatterlist
scsi: imm: use sg helper to iterate over scatterlist
scsi: aha152x: use sg helper to iterate over scatterlist
scsi: s390: zfcp_fc: use sg helper to iterate over scatterlist
scsi: staging: unisys: visorhba: use sg helper to iterate over scatterlist
scsi: usb: image: microtek: use sg helper to iterate over scatterlist
scsi: pmcraid: use sg helper to iterate over scatterlist
scsi: ipr: use sg helper to iterate over scatterlist
scsi: mvumi: use sg helper to iterate over scatterlist
scsi: lpfc: use sg helper to iterate over scatterlist
scsi: advansys: use sg helper to iterate over scatterlist
...
Adapt and apply changes that were made to the TCP socket connect
code. See the following commits for details on the purpose of
these changes:
Commit 7196dbb02e ("SUNRPC: Allow changing of the TCP timeout parameters on the fly")
Commit 3851f1cdb2 ("SUNRPC: Limit the reconnect backoff timer to the max RPC message timeout")
Commit 02910177ae ("SUNRPC: Fix reconnection timeouts")
Some common transport code is moved to xprt.c to satisfy the code
duplication police.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up.
There is only one remaining function, rpcrdma_buffer_put(), that
uses this field. Its caller can supply a pointer to the correct
rpcrdma_buffer, enabling the removal of an 8-byte pointer field
from a frequently-allocated shared data structure.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up.
Move the "not present" case into the individual chunk encoders. This
improves code organization and readability.
The reason for the original organization was to optimize for the
case where there there are no chunks. The optimization turned out to
be inconsequential, so let's err on the side of code readability.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
rb_lock is contended between rpcrdma_buffer_create,
rpcrdma_buffer_put, and rpcrdma_post_recvs.
Commit e340c2d6ef ("xprtrdma: Reduce the doorbell rate (Receive)")
causes rpcrdma_post_recvs to take the rb_lock repeatedly when it
determines more Receives are needed. Streamline this code path so
it takes the lock just once in most cases to build the Receive
chain that is about to be posted.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up.
Commit 7c8d9e7c88 ("xprtrdma: Move Receive posting to Receive
handler") reduced the number of rpcrdma_rep_create call sites to
one. After that commit, the backchannel code no longer invokes it.
Therefore the free list logic added by commit d698c4a02e
("xprtrdma: Fix backchannel allocation of extra rpcrdma_reps") is
no longer necessary, and in fact adds some extra overhead that we
can do without.
Simply post any newly created reps. They will get added back to
the rb_recv_bufs list when they subsequently complete.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Eliminate a context switch in the path that handles RPC wake-ups
when a Receive completion 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>
Since commit ba69cd122e ("xprtrdma: Remove support for FMR memory
registration"), FRWR is the only supported memory registration mode.
We can take advantage of the asynchronous nature of FRWR's LOCAL_INV
Work Requests to get rid of the completion wait by having the
LOCAL_INV completion handler take care of DMA unmapping MRs and
waking the upper layer RPC waiter.
This eliminates two context switches when local invalidation is
necessary. As a side benefit, we will no longer need the per-xprt
deferred completion work queue.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
When a marshal operation fails, any MRs that were already set up for
that request are recycled. Recycling releases MRs and creates new
ones, which is expensive.
Since commit f287762308 ("xprtrdma: Chain Send to FastReg WRs")
was merged, recycling FRWRs is unnecessary. This is because before
that commit, frwr_map had already posted FAST_REG Work Requests,
so ownership of the MRs had already been passed to the NIC and thus
dealing with them had to be delayed until they completed.
Since that commit, however, FAST_REG WRs are posted at the same time
as the Send WR. This means that if marshaling fails, we are certain
the MRs are safe to simply unmap and place back on the free list
because neither the Send nor the FAST_REG WRs have been posted yet.
The kernel still has ownership of the MRs at this point.
This reduces the total number of MRs that the xprt has to create
under heavy workloads and makes the marshaling logic less brittle.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Now that both the Send and Receive completions are handled in
process context, it is safe to DMA unmap and return MRs to the
free or recycle lists directly in the completion handlers.
Doing this means rpcrdma_frwr no longer needs to track the state of
each MR, meaning that a VALID or FLUSHED MR can no longer appear on
an xprt's MR free list. Thus there is no longer a need to track the
MR's registration state in rpcrdma_frwr.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Commit 9590d083c1 ("xprtrdma: Use xprt_pin_rqst in
rpcrdma_reply_handler") pins incoming RPC/RDMA replies so they
can be left in the pending requests queue while they are being
processed without introducing a race between ->buf_free and the
transport's reply handler. Therefore RPCRDMA_REQ_F_PENDING is no
longer necessary.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Under high I/O workloads, I've noticed that an RPC/RDMA transport
occasionally deadlocks (IOPS goes to zero, and doesn't recover).
Diagnosis shows that the sendctx queue is empty, but when sendctxs
are returned to the queue, the xprt_write_space wake-up never
occurs. The wake-up logic in rpcrdma_sendctx_put_locked is racy.
I noticed that both EMPTY_SCQ and XPRT_WRITE_SPACE are implemented
via an atomic bit. Just one of those is sufficient. Removing
EMPTY_SCQ in favor of the generic bit mechanism makes the deadlock
un-reproducible.
Without EMPTY_SCQ, rpcrdma_buffer::rb_flags is no longer used and
is therefore removed.
Unfortunately this patch does not apply cleanly to stable. If
needed, someone will have to port it and test it.
Fixes: 2fad659209 ("xprtrdma: Wait on empty sendctx queue")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
This is a latent bug. xdr_stream_pos works by subtracting
xdr_stream::nwords from xdr_buf::len. But xdr_stream::nwords is not
initialized by xdr_init_encode().
It works today only because all fields in rpcrdma_req::rl_stream
are initialized to zero by rpcrdma_req_create, making the
subtraction in xdr_stream_pos always a no-op.
I found this issue via code inspection. It was introduced by commit
39f4cd9e99 ("xprtrdma: Harden chunk list encoding against send
buffer overflow"), but the code has changed enough since then that
this fix can't be automatically applied to stable.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Pull nfsd fixes from Bruce Fields:
"Two more quick bugfixes for nfsd: fixing a regression causing mount
failures on high-memory machines and fixing the DRC over RDMA"
* tag 'nfsd-5.2-2' of git://linux-nfs.org/~bfields/linux:
nfsd: Fix overflow causing non-working mounts on 1 TB machines
svcrdma: Ignore source port when computing DRC hash
Dereference wr->next /before/ the memory backing wr has been
released. This issue was found by code inspection. It is not
expected to be a significant problem because it is in an error
path that is almost never executed.
Fixes: 7c8d9e7c88 ("xprtrdma: Move Receive posting to ... ")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
sg_alloc_table_chained() currently allows the caller to provide one
preallocated SGL and returns if the requested number isn't bigger than
size of that SGL. This is used to inline an SGL for an IO request.
However, scattergather code only allows that size of the 1st preallocated
SGL to be SG_CHUNK_SIZE(128). This means a substantial amount of memory
(4KB) is claimed for the SGL for each IO request. If the I/O is small, it
would be prudent to allocate a smaller SGL.
Introduce an extra parameter to sg_alloc_table_chained() and
sg_free_table_chained() for specifying size of the preallocated SGL.
Both __sg_free_table() and __sg_alloc_table() assume that each SGL has the
same size except for the last one. Change the code to allow both functions
to accept a variable size for the 1st preallocated SGL.
[mkp: attempted to clarify commit desc]
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Ewan D. Milne <emilne@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: netdev@vger.kernel.org
Cc: linux-nvme@lists.infradead.org
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
The DRC appears to be effectively empty after an RPC/RDMA transport
reconnect. The problem is that each connection uses a different
source port, which defeats the DRC hash.
Clients always have to disconnect before they send retransmissions
to reset the connection's credit accounting, thus every retransmit
on NFS/RDMA will miss the DRC.
An NFS/RDMA client's IP source port is meaningless for RDMA
transports. The transport layer typically sets the source port value
on the connection to a random ephemeral port. The server already
ignores it for the "secure port" check. See commit 16e4d93f6d
("NFSD: Ignore client's source port on RDMA transports").
The Linux NFS server's DRC resolves XID collisions from the same
source IP address by using the checksum of the first 200 bytes of
the RPC call header.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Cc: stable@vger.kernel.org # v4.14+
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
One of the more common cases of allocation size calculations is finding
the size of a structure that has a zero-sized array at the end, along
with memory for some number of elements for that array. For example:
struct foo {
int stuff;
struct boo entry[];
};
instance = kzalloc(sizeof(struct foo) + count * sizeof(struct boo), GFP_KERNEL);
Instead of leaving these open-coded and prone to type mistakes, we can
now use the new struct_size() helper:
instance = kzalloc(struct_size(instance, entry, count), GFP_KERNEL);
This code was detected with the help of Coccinelle.
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Commit e1ede312f1 ("xprtrdma: Fix helper that drains the
transport") replaced the ib_drain_qp() call, so update documenting
comments to reflect current operation.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up.
Move the remaining field in rpcrdma_create_data_internal so the
structure can be removed.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up.
The inline settings are actually a characteristic of the endpoint,
and not related to the device. They are also modified after the
transport instance is created, so they do not belong in the cdata
structure either.
Lastly, let's use names that are more natural to RDMA than to NFS:
inline_write -> inline_send and inline_read -> inline_recv. The
/proc files retain their names to avoid breaking user space.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up.
xprt_rdma_max_inline_{read,write} cannot be set to large values
by virtue of proc_dointvec_minmax. The current maximum is
RPCRDMA_MAX_INLINE, which is much smaller than RPCRDMA_MAX_SEGS *
PAGE_SIZE.
The .rsize and .wsize fields are otherwise unused in the current
code base, and thus can be removed.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up.
Since commit 54cbd6b0c6 ("xprtrdma: Delay DMA mapping Send and
Receive buffers"), a pointer to the device is now saved in each
regbuf when it is DMA mapped.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Instead of using a fixed number, allow the amount of Send completion
batching to vary based on the client's maximum credit limit.
- A larger default gives a small boost to IOPS throughput
- Reducing it based on max_requests gives a safe result when the
max credit limit is cranked down (eg. when the device has a small
max_qp_wr).
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Minor clean-ups I've stumbled on since sendctx was merged last year.
In particular, making Send completion processing more efficient
appears to have a measurable impact on IOPS throughput.
Note: test_and_clear_bit() returns a value, thus an explicit memory
barrier is not necessary.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Record an event when rpcrdma_marshal_req returns a non-zero return
value to help track down why an xprt close might have occurred.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
The Receive handler runs in process context, thus can use on-demand
GFP_KERNEL allocations instead of pre-allocation.
This makes the xprtrdma backchannel independent of the number of
backchannel session slots provisioned by the Upper Layer protocol.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
For code legibility, clean up the function names to be consistent
with the pattern: "rpcrdma" _ object-type _ action
Also rpcrdma_regbuf_alloc and rpcrdma_regbuf_free no longer have any
callers outside of verbs.c, and can thus be made static.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Clean up by providing an API to do this common task.
At this point, the difference between rpcrdma_get_sendbuf and
rpcrdma_get_recvbuf has become tiny. These can be collapsed into a
single helper.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Allocating an rpcrdma_req's regbufs at xprt create time enables
a pair of micro-optimizations:
First, if these regbufs are always there, we can eliminate two
conditional branches from the hot xprt_rdma_allocate path.
Second, by allocating a 1KB buffer, it places a lower bound on the
size of these buffers, without adding yet another conditional
branch. The lower bound reduces the number of hardway re-
allocations. In fact, for some workloads it completely eliminates
hardway allocations.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Allocate the struct rpcrdma_regbuf separately from the I/O buffer
to better guarantee the alignment of the I/O buffer and eliminate
the wasted space between the rpcrdma_regbuf metadata and the buffer
itself.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
For code legibility, clean up the function names to be consistent
with the pattern: "rpcrdma" _ object-type _ action
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Eventually, I'd like to invoke rpcrdma_create_req() during the
call_reserve step. Memory allocation there probably needs to use
GFP_NOIO. Therefore a set of GFP flags needs to be passed in.
As an additional clean up, just return a pointer or NULL, because
the only error return code here is -ENOMEM.
Lastly, clean up the function names to be consistent with the
pattern: "rpcrdma" _ object-type _ action
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
After a DMA map failure in frwr_map, mark the MR so that recycling
won't attempt to DMA unmap it.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Fixes: e2f34e2671 ("xprtrdma: Yet another double DMA-unmap")
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Page allocation requests made when the SPARSE_PAGES flag is set are
allowed to fail, and are not critical. No need to spend a rare
resource.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Convert the transport callback to actually put the request to sleep
instead of just setting a timeout. This is in preparation for
rpc_sleep_on_timeout().
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
We want to drain only the RQ first. Otherwise the transport can
deadlock on ->close if there are outstanding Send completions.
Fixes: 6d2d0ee27c ("xprtrdma: Replace rpcrdma_receive_wq ... ")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Cc: stable@vger.kernel.org # v5.0+
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Pull NFS server updates from Bruce Fields:
"Miscellaneous NFS server fixes.
Probably the most visible bug is one that could artificially limit
NFSv4.1 performance by limiting the number of oustanding rpcs from a
single client.
Neil Brown also gets a special mention for fixing a 14.5-year-old
memory-corruption bug in the encoding of NFSv3 readdir responses"
* tag 'nfsd-5.1' of git://linux-nfs.org/~bfields/linux:
nfsd: allow nfsv3 readdir request to be larger.
nfsd: fix wrong check in write_v4_end_grace()
nfsd: fix memory corruption caused by readdir
nfsd: fix performance-limiting session calculation
svcrpc: fix UDP on servers with lots of threads
svcrdma: Remove syslog warnings in work completion handlers
svcrdma: Squelch compiler warning when SUNRPC_DEBUG is disabled
svcrdma: Use struct_size() in kmalloc()
svcrpc: fix unlikely races preventing queueing of sockets
svcrpc: svc_xprt_has_something_to_do seems a little long
SUNRPC: Don't allow compiler optimisation of svc_xprt_release_slot()
nfsd: fix an IS_ERR() vs NULL check
Pull more NFS client fixes from Anna Schumaker:
"Three fixes this time.
Nicolas's is for xprtrdma completion vector allocation on single-core
systems. Greg's adds an error check when allocating a debugfs dentry.
And Ben's is an additional fix for nfs_page_async_flush() to prevent
pages from accidentally getting truncated.
Summary:
- Make sure Send CQ is allocated on an existing compvec
- Properly check debugfs dentry before using it
- Don't use page_file_mapping() after removing a page"
* tag 'nfs-for-5.0-4' of git://git.linux-nfs.org/projects/anna/linux-nfs:
NFS: Don't use page_file_mapping after removing the page
rpc: properly check debugfs dentry before using it
xprtrdma: Make sure Send CQ is allocated on an existing compvec
tsh_size was added to accommodate transports that send a pre-amble
before each RPC message. However, this assumes the pre-amble is
fixed in size, which isn't true for some transports. That makes
tsh_size not very generic.
Also I'd like to make the estimation of RPC send and receive
buffer sizes more precise. tsh_size doesn't currently appear to be
accounted for at all by call_allocate.
Therefore let's just remove the tsh_size concept, and make the only
transports that have a non-zero tsh_size employ a direct approach.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Having access to the controlling rpc_rqst means a trace point in the
XDR code can report:
- the XID
- the task ID and client ID
- the p_name of RPC being processed
Subsequent patches will introduce such trace points.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Post RECV WRs in batches to reduce the hardware doorbell rate per
transport. This helps the RPC-over-RDMA client scale better in
number of transports.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
