Clean up: Move #include <trace/events/rpcrdma.h> into source files,
similar to how it is done with trace/events/sunrpc.h.

Server-side trace points will be part of the rpcrdma subsystem,
just like the client-side trace points.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NJ. Bruce Fields <bfields@redhat.com>

Currently, when the MR free list is exhausted during marshaling, the
RPC/RDMA transport places the RPC task on the delayq, which forces a
wait for HZ >> 2 before the marshal and send is retried.

With this change, the transport now places such an RPC task on the
pending queue, and wakes it just as soon as more MRs have been
created. Creating more MRs typically takes less than a millisecond,
and this waking mechanism is less deadlock-prone.

Moreover, the waiting RPC task is holding the transport's write
lock, which blocks the transport from sending RPCs. Therefore faster
recovery from MR exhaustion is desirable.

This is the same mechanism that the TCP transport utilizes when
handling write buffer space exhaustion.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

With v4.15, on one of my NFS/RDMA clients I measured a nearly
doubling in the latency of small read and write system calls. There
was no change in server round trip time. The extra latency appears
in the whole RPC execution path.

"git bisect" settled on commit ccede759 ("xprtrdma: Spread reply
processing over more CPUs") .

After some experimentation, I found that leaving the WQ bound and
allowing the scheduler to pick the dispatch CPU seems to eliminate
the long latencies, and it does not introduce any new regressions.

The fix is implemented by reverting only the part of
commit ccede759 ("xprtrdma: Spread reply processing over more
CPUs") that dispatches RPC replies specifically on the CPU where the
matching RPC call was made.

Interestingly, saving the CPU number and later queuing reply
processing there was effective _only_ for a NFS READ and WRITE
request. On my NUMA client, in-kernel RPC reply processing for
asynchronous RPCs was dispatched on the same CPU where the RPC call
was made, as expected. However synchronous RPCs seem to get their
reply dispatched on some other CPU than where the call was placed,
every time.

Fixes: ccede759 ("xprtrdma: Spread reply processing over ... ")
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Cc: stable@vger.kernel.org # v4.15+
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Commit 16f906d6 ("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 ae72950a ("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: NMichal Kalderon <Michal.Kalderon@cavium.com>
Fixes: 16f906d6 ("xprtrdma: Reduce required number of send SGEs")
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Tested-by: NMichal Kalderon <Michal.Kalderon@cavium.com>
Cc: stable@vger.kernel.org # v4.10+
Signed-off-by: NAnna 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: 9d6b0409 ("xprtrdma: Place registered MWs on a ... ")
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

This includes decoding Write and Reply chunks, and fixing up inline
payloads.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna 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: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna 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: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna 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: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna 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: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Commit d8f532d2 ("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: d8f532d2 ("xprtrdma: Invoke rpcrdma_reply_handler ...")
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Credit work contributed by Oracle engineers since 2014.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna 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: NChuck Lever <chuck.lever@oracle.com>
Reviewed-by: NDevesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: NAnna 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: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna 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: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna 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: NSagi Grimberg <sagi@grimberg.me>
Suggested-by: NJason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Commit 655fec69 ("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: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Clean up: Make rpcrdma_prepare_send_sges() return a negative errno
instead of a bool. Soon callers will want distinct treatments of
different types of failures.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

When this function fails, it needs to undo the DMA mappings it's
done so far. Otherwise these are leaked.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Clean up. rpcrdma_prepare_hdr_sge() sets num_sge to one, then
rpcrdma_prepare_msg_sges() sets num_sge again to the count of SGEs
it added, plus one for the header SGE just mapped in
rpcrdma_prepare_hdr_sge(). This is confusing, and nails in an
assumption about when these functions are called.

Instead, maintain a running count that both functions can update
with just the number of SGEs they have added to the SGE array.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

We need to decode and save the incoming rdma_credits field _after_
we know that the direction of the message is "forward direction
Reply". Otherwise, the credits value in reverse direction Calls is
also used to update the forward direction credits.

It is safe to decode the rdma_credits field in rpcrdma_reply_handler
now that rpcrdma_reply_handler is single-threaded. Receives complete
in the same order as they were sent on the NFS server.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

I noticed that the soft IRQ thread looked pretty busy under heavy
I/O workloads. perf suggested one area that was expensive was the
queue_work() call in rpcrdma_wc_receive. That gave me some ideas.

Instead of scheduling a separate worker to process RPC Replies,
promote the Receive completion handler to IB_POLL_WORKQUEUE, and
invoke rpcrdma_reply_handler directly.

Note that the poll workqueue is single-threaded. In order to keep
memory invalidation from serializing all RPC Replies, handle any
necessary invalidation tasks in a separate multi-threaded workqueue.

This provides a two-tier scheme, similar to OS I/O interrupt
handlers: A fast interrupt handler that schedules the slow handler
and re-enables the interrupt, and a slower handler that is invoked
for any needed heavy lifting.

Benefits include:
- One less context switch for RPCs that don't register memory
- Receive completion handling is moved out of soft IRQ context to
  make room for other users of soft IRQ
- The same CPU core now DMA syncs and XDR decodes the Receive buffer
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Clean up: I'd like to be able to invoke the tail of
rpcrdma_reply_handler in two different places. Split the tail out
into its own helper function.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Clean up: Make it easier to pass the decoded XID, vers, credits, and
proc fields around by moving these variables into struct rpcrdma_rep.

Note: the credits field will be handled in a subsequent patch.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

A reply with an unrecognized value in the version field means the
transport header is potentially garbled and therefore all the fields
are untrustworthy.

Fixes: 59aa1f9a ("xprtrdma: Properly handle RDMA_ERROR ... ")
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Adopt the use of xprt_pin_rqst to eliminate contention between
Call-side users of rb_lock and the use of rb_lock in
rpcrdma_reply_handler.

This replaces the mechanism introduced in 431af645 ("xprtrdma:
Fix client lock-up after application signal fires").

Use recv_lock to quickly find the completing rqst, pin it, then
drop the lock. At that point invalidation and pull-up of the Reply
XDR can be done. Both are often expensive operations.

Finally, take recv_lock again to signal completion to the RPC
layer. It also protects adjustment of "cwnd".

This greatly reduces the amount of time a lock is held by the
reply handler. Comparing lock_stat results shows a marked decrease
in contention on rb_lock and recv_lock.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
[trond.myklebust@primarydata.com: Remove call to rpcrdma_buffer_put() from
   the "out_norqst:" path in rpcrdma_reply_handler.]
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

This further reduces contention with the transport_lock, and allows us
to convert to using a non-bh-safe spinlock, since the list is now never
accessed from a bh context.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Re-arrange the pointer arithmetic in the chunk list encoders to
eliminate several more integer multiplication instructions during
Transport Header encoding.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Re-arrange the pointer arithmetic in rpcrdma_convert_iovs() to
eliminate several integer multiplication instructions during
Transport Header encoding.

Also, array overflow does not occur outside development
environments, so replace overflow checking with one spot check
at the end. This reduces the number of conditional branches in
the common case.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

While marshaling chunk lists which are variable-length XDR objects,
check for XDR buffer overflow at every step. Measurements show no
significant changes in CPU utilization.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Initialize an xdr_stream at the top of rpcrdma_marshal_req(), and
use it to encode the fixed transport header fields. This xdr_stream
will be used to encode the chunk lists in a subsequent patch.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Clean up: Remove a variable whose result is no longer used.
Commit 655fec69 ("xprtrdma: Use gathered Send for large inline
messages") should have removed it.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Clean up: The caller already has rpcrdma_xprt, so pass that directly
instead. And provide a documenting comment for this critical
function.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

This field is no longer used outside the Receive completion handler.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Clean up chunk list decoding by using the xdr_stream set up in
rpcrdma_reply_handler. This hardens decoding by checking for buffer
overflow at every step while unmarshaling variable-length XDR
objects.
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Refactor the reply handler's transport header decoding logic to make
it easier to understand and update.

Convert some of the handler to use xdr_streams, which will enable
stricter validation of input data and enable the eventual addition
of support for new combinations of chunks, such as "Write + Reply"
or "PZRC + normal Read".
Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Signed-off-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>