svcrdma needs 259 pages allocated to receive 1MB NFSv4.0 WRITE requests:
- 1 page for the transport header and head iovec
- 256 pages for the data payload
- 1 page for the trailing GETATTR request (since NFSD XDR decoding
does not look for a tail iovec, the GETATTR is stuck at the end
of the rqstp->rq_arg.pages list)
- 1 page for building the reply xdr_buf
But RPCSVC_MAXPAGES is already 259 (on x86_64). The problem is that
svc_alloc_arg never allocates that many pages. To address this:
1. The final element of rq_pages always points to NULL. To
accommodate up to 259 pages in rq_pages, add an extra element
to rq_pages for the array termination sentinel.
2. Adjust the calculation of "pages" to match how RPCSVC_MAXPAGES
is calculated, so it can go up to 259. Bruce noted that the
calculation assumes sv_max_mesg is a multiple of PAGE_SIZE,
which might not always be true. I didn't change this assumption.
3. Change the loop boundaries to allow 259 pages to be allocated.
Additional clean-up: WARN_ON_ONCE adds an extra conditional branch,
which is basically never taken. And there's no need to dump the
stack here because svc_alloc_arg has only one caller.
Keeping that NULL "array termination sentinel"; there doesn't appear to
be any code that depends on it, only code in nfsd_splice_actor() which
needs the 259th element to be initialized to *something*. So it's
possible we could just keep the array at 259 elements and drop that
final NULL, but we're being conservative for now.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Pull locking updates from Ingo Molnar:
"The main changes in this cycle were:
- Implement wraparound-safe refcount_t and kref_t types based on
generic atomic primitives (Peter Zijlstra)
- Improve and fix the ww_mutex code (Nicolai Hähnle)
- Add self-tests to the ww_mutex code (Chris Wilson)
- Optimize percpu-rwsems with the 'rcuwait' mechanism (Davidlohr
Bueso)
- Micro-optimize the current-task logic all around the core kernel
(Davidlohr Bueso)
- Tidy up after recent optimizations: remove stale code and APIs,
clean up the code (Waiman Long)
- ... plus misc fixes, updates and cleanups"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
fork: Fix task_struct alignment
locking/spinlock/debug: Remove spinlock lockup detection code
lockdep: Fix incorrect condition to print bug msgs for MAX_LOCKDEP_CHAIN_HLOCKS
lkdtm: Convert to refcount_t testing
kref: Implement 'struct kref' using refcount_t
refcount_t: Introduce a special purpose refcount type
sched/wake_q: Clarify queue reinit comment
sched/wait, rcuwait: Fix typo in comment
locking/mutex: Fix lockdep_assert_held() fail
locking/rtmutex: Flip unlikely() branch to likely() in __rt_mutex_slowlock()
locking/rwsem: Reinit wake_q after use
locking/rwsem: Remove unnecessary atomic_long_t casts
jump_labels: Move header guard #endif down where it belongs
locking/atomic, kref: Implement kref_put_lock()
locking/ww_mutex: Turn off __must_check for now
locking/atomic, kref: Avoid more abuse
locking/atomic, kref: Use kref_get_unless_zero() more
locking/atomic, kref: Kill kref_sub()
locking/atomic, kref: Add kref_read()
locking/atomic, kref: Add KREF_INIT()
...
Since we need to change the implementation, stop exposing internals.
Provide kref_read() to read the current reference count; typically
used for debug messages.
Kills two anti-patterns:
atomic_read(&kref->refcount)
kref->refcount.counter
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The inet6addr_chain is an atomic notifier chain, so we can't call
anything that might sleep (like lock_sock)... instead of closing the
socket from svc_age_temp_xprts_now (which is called by the notifier
function), just have the rpc service threads do it instead.
Cc: stable@vger.kernel.org
Fixes: c3d4879e01 "sunrpc: Add a function to close..."
Signed-off-by: Scott Mayhew <smayhew@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Allow the user to limit the number of requests serviced through a single
connection, to help prevent faster clients from starving slower clients.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Dropping and/or deferring requests has an impact on performance. Let's
make sure we can trace those events.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Add a tracepoint to track when the processing of incoming RPC data gets
deferred due to out-of-space issues on the outgoing transport.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
The spec allows backchannels for multiple clients to share the same tcp
connection. When that happens, we need to use the same xprt for all of
them. Similarly, we need the same xps.
This fixes list corruption introduced by the multipath code.
Cc: stable@vger.kernel.org
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Acked-by: Trond Myklebust <trondmy@primarydata.com>
This should fix failures like:
# rpc.nfsd --rdma
rpc.nfsd: Unable to request RDMA services: Protocol not supported
Reported-by: Steve Dickson <steved@redhat.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Add a function svc_age_temp_xprts_now() to close temporary transports
whose xpt_local matches the address passed in server_addr immediately
instead of waiting for them to be closed by the timer function.
The function is intended to be used by notifier_blocks that will be
added to nfsd and lockd that will run when an ip address is deleted.
This will eliminate the ACK storms and client hangs that occur in
HA-NFS configurations where nfsd & lockd is left running on the cluster
nodes all the time and the NFS 'service' is migrated back and forth
within a short timeframe.
Signed-off-by: Scott Mayhew <smayhew@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
For now, all services use svc_xprt_do_enqueue, but once we add
workqueue-based service support, we'll need to do something different.
Signed-off-by: Shirley Ma <shirley.ma@oracle.com>
Acked-by: Jeff Layton <jlayton@primarydata.com>
Tested-by: Shirley Ma <shirley.ma@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
The BKL is completely out of the picture in the lockd and sunrpc code
these days. Update the antiquated comments that refer to it.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
...move the WARN_ON_ONCE inside the following if block since they use
the same condition.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
These were useful when I was tracking down a race condition between
svc_xprt_do_enqueue and svc_get_next_xprt.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Testing has shown that the pool->sp_lock can be a bottleneck on a busy
server. Every time data is received on a socket, the server must take
that lock in order to dequeue a thread from the sp_threads list.
Address this problem by eliminating the sp_threads list (which contains
threads that are currently idle) and replacing it with a RQ_BUSY flag in
svc_rqst. This allows us to walk the sp_all_threads list under the
rcu_read_lock and find a suitable thread for the xprt by doing a
test_and_set_bit.
Note that we do still have a potential atomicity problem however with
this approach. We don't want svc_xprt_do_enqueue to set the
rqst->rq_xprt pointer unless a test_and_set_bit of RQ_BUSY returned
zero (which indicates that the thread was idle). But, by the time we
check that, the bit could be flipped by a waking thread.
To address this, we acquire a new per-rqst spinlock (rq_lock) and take
that before doing the test_and_set_bit. If that returns false, then we
can set rq_xprt and drop the spinlock. Then, when the thread wakes up,
it must set the bit under the same spinlock and can trust that if it was
already set then the rq_xprt is also properly set.
With this scheme, the case where we have an idle thread no longer needs
to take the highly contended pool->sp_lock at all, and that removes the
bottleneck.
That still leaves one issue: What of the case where we walk the whole
sp_all_threads list and don't find an idle thread? Because the search is
lockess, it's possible for the queueing to race with a thread that is
going to sleep. To address that, we queue the xprt and then search again.
If we find an idle thread at that point, we can't attach the xprt to it
directly since that might race with a different thread waking up and
finding it. All we can do is wake the idle thread back up and let it
attempt to find the now-queued xprt.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Tested-by: Chris Worley <chris.worley@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
In a later patch, we'll be removing some spinlocking around the socket
and thread queueing code in order to fix some contention problems. At
that point, the stats counters will no longer be protected by the
sp_lock.
Change the counters to atomic_long_t fields, except for the
"sockets_queued" counter which will still be manipulated under a
spinlock.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Tested-by: Chris Worley <chris.worley@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
The way that svc_wake_up works is a bit inefficient. It walks all of the
available pools for a service and either wakes up a task in each one or
sets the SP_TASK_PENDING flag in each one.
When svc_wake_up is called, there is no need to wake up more than one
thread to do this work. In practice, only lockd currently uses this
function and it's single threaded anyway. Thus, this just boils down to
doing a wake up of a thread in pool 0 or setting a single flag.
Eliminate the for loop in this function and change it to just operate on
pool 0. Also update the comments that sit above it and get rid of some
code that has been commented out for years now.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
In a later patch, we'll want to be able to handle this flag without
holding the sp_lock. Change this field to an unsigned long flags
field, and declare a new flag in it that can be managed with atomic
bitops.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
In a later patch, we're going to need some atomic bit flags. Since that
field will need to be an unsigned long, we mitigate that space
consumption by migrating some other bitflags to the new field. Start
with the rq_secure flag.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Highlights include:
Features:
- NFSv4.2 client support for hole punching and preallocation.
- Further RPC/RDMA client improvements.
- Add more RPC transport debugging tracepoints.
- Add RPC debugging tools in debugfs.
Bugfixes:
- Stable fix for layoutget error handling
- Fix a change in COMMIT behaviour resulting from the recent io code updates
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=wOP3
-----END PGP SIGNATURE-----
Merge tag 'nfs-for-3.19-1' into nfsd for-3.19 branch
Mainly what I need is 860a0d9e51 "sunrpc: add some tracepoints in
svc_rqst handling functions", which subsequent server rpc patches from
jlayton depend on. I'm merging this later tag on the assumption that's
more likely to be a tested and stable point.
All it does is indicate whether a xprt has already been deleted from
a list or not, which is unnecessary since we use list_del_init and it's
always set and checked under the sv_lock anyway.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
...just around svc_send, svc_recv and svc_process for now.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
current_task appears to be x86-only, oops.
Let's just delete this check entirely:
Any developer that adds a new user without setting rq_task will get a
crash the first time they test it. I also don't think there are
normally any important locks held here, and I can't see any other reason
why killing a server thread would bring the whole box down.
So the effort to fail gracefully here looks like overkill.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 983c684466 "SUNRPC: get rid of the request wait queue"
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Just move the transport locking out of the spin lock protected area
altogether.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
We should definitely not be exiting svc_get_next_xprt() with the
thread enqueued. Fix this by ensuring that we fall through to
the dequeue.
Also move the test itself outside the spin lock protected section.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
We're always _only_ waking up tasks from within the sp_threads list, so
we know that they are enqueued and alive. The rq_wait waitqueue is just
a distraction with extra atomic semantics.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
We already determined that there was enough wspace when we
called svc_xprt_enqueue.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Ensure that all calls to svc_xprt_enqueue() except svc_xprt_received()
check the value of XPT_BUSY, before attempting to grab spinlocks etc.
This is to avoid situations such as the following "perf" trace,
which shows heavy contention on the pool spinlock:
54.15% nfsd [kernel.kallsyms] [k] _raw_spin_lock_bh
|
--- _raw_spin_lock_bh
|
|--71.43%-- svc_xprt_enqueue
| |
| |--50.31%-- svc_reserve
| |
| |--31.35%-- svc_xprt_received
| |
| |--18.34%-- svc_tcp_data_ready
...
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
After this we can handle for example getattr of very large ACLs.
Read, readdir, readlink are still special cases with their own limits.
Also we can't handle a new operation starting close to the end of a
page.
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
If the accept() call fails, we need to put the module reference.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Cc: stable@vger.kernel.org
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
An NFS/RDMA client's source port is meaningless for RDMA transports.
The transport layer typically sets the source port value on the
connection to a random ephemeral port.
Currently, NFS server administrators must specify the "insecure"
export option to enable clients to access exports via RDMA.
But this means NFS clients can access such an export via IP using an
ephemeral port, which may not be desirable.
This patch eliminates the need to specify the "insecure" export
option to allow NFS/RDMA clients access to an export.
BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=250
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Mark functions as static in net/sunrpc/svc_xprt.c because they are not
used outside this file.
This eliminates the following warning in net/sunrpc/svc_xprt.c:
net/sunrpc/svc_xprt.c:574:5: warning: no previous prototype for ‘svc_alloc_arg’ [-Wmissing-prototypes]
net/sunrpc/svc_xprt.c:615:18: warning: no previous prototype for ‘svc_get_next_xprt’ [-Wmissing-prototypes]
net/sunrpc/svc_xprt.c:694:6: warning: no previous prototype for ‘svc_add_new_temp_xprt’ [-Wmissing-prototypes]
Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rewrite server shutdown to remove the assumption that there are no
longer any threads running (no longer true, for example, when shutting
down the service in one network namespace while it's still running in
others).
Do that by doing what we'd do in normal circumstances: just CLOSE each
socket, then enqueue it.
Since there may not be threads to handle the resulting queued xprts,
also run a simplified version of the svc_recv() loop run by a server to
clean up any closed xprts afterwards.
Cc: stable@kernel.org
Tested-by: Jason Tibbitts <tibbs@math.uh.edu>
Tested-by: Paweł Sikora <pawel.sikora@agmk.net>
Acked-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
svc_age_temp_xprts expires xprts in a two-step process: first it takes
the sv_lock and moves the xprts to expire off their server-wide list
(sv_tempsocks or sv_permsocks) to a local list. Then it drops the
sv_lock and enqueues and puts each one.
I see no reason for this: svc_xprt_enqueue() will take sp_lock, but the
sv_lock and sp_lock are not otherwise nested anywhere (and documentation
at the top of this file claims it's correct to nest these with sp_lock
inside.)
Cc: stable@kernel.org
Tested-by: Jason Tibbitts <tibbs@math.uh.edu>
Tested-by: Paweł Sikora <pawel.sikora@agmk.net>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
There is a race in enqueueing thread to a pool and
waking up a thread.
lockd doesn't wake up on reception of lock granted callback
if svc_wake_up() is called before lockd's thread is added
to a pool.
Signed-off-by: Andriy Skulysh <Andriy_Skulysh@xyratex.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Replace two bounds checking BUG_ON() calls with WARN_ON_ONCE() and resetting
the requested size to RPCSVC_MAXPAGES.
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Replace BUG_ON() with a WARN_ON_ONCE() and early return.
Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Matter of taste, I suppose, but svc_recv breaks up naturally into:
allocate pages and setup arg
dequeue (wait for, if necessary) next socket
do something with that socket
And I find it easier to read when it doesn't go on for pages and pages.
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Note this isn't used outside svc_xprt.c.
May as well move it so we don't need a declaration while we're here.
Also remove an outdated comment.
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
The only errors returned from xpo_recvfrom have been -EAGAIN and
-EAFNOSUPPORT. The latter was removed by a previous patch. That leaves
only -EAGAIN, which is treated just like 0 by the caller (svc_recv).
So, just ditch -EAGAIN and return 0 instead.
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Whenever we clear XPT_BUSY we should call svc_xprt_enqueue(). Without
that we may fail to notice any events (such as new connections) that
arrived while XPT_BUSY was set.
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Chuck Lever