svcrdma: Clean up the tracing for rw_ctx_init errors

- De-duplicate code
- Rename the tracepoint with "_err" to allow enabling via glob
- Report the sg_cnt for the failing rw_ctx
- Fix a dumb signag

svcrdma: Clean up the tracing for rw_ctx_init errors

- De-duplicate code
- Rename the tracepoint with "_err" to allow enabling via glob
- Report the sg_cnt for the failing rw_ctx
- Fix a dumb signage issue

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

show more ...

xprtrdma: Fix trace point use-after-free race

It's not safe to use resources pointed to by the @send_wr of
ib_post_send() _after_ that function returns. Those resources are
typically freed by the Se

xprtrdma: Fix trace point use-after-free race

It's not safe to use resources pointed to by the @send_wr of
ib_post_send() _after_ that function returns. Those resources are
typically freed by the Send completion handler, which can run before
ib_post_send() returns.

Thus the trace points currently around ib_post_send() in the
client's RPC/RDMA transport are a hazard, even when they are
disabled. Rearrange them so that they touch the Work Request only
_before_ ib_post_send() is invoked.

Fixes: ab03eff58eb5 ("xprtrdma: Add trace points in RPC Call transmit paths")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

show more ...

svcrdma: Fix trace point use-after-free race

I hit this while testing nfsd-5.7 with kernel memory debugging
enabled on my server:

Mar 30 13:21:45 klimt kernel: BUG: unable to handle page fault for

svcrdma: Fix trace point use-after-free race

I hit this while testing nfsd-5.7 with kernel memory debugging
enabled on my server:

Mar 30 13:21:45 klimt kernel: BUG: unable to handle page fault for address: ffff8887e6c279a8
Mar 30 13:21:45 klimt kernel: #PF: supervisor read access in kernel mode
Mar 30 13:21:45 klimt kernel: #PF: error_code(0x0000) - not-present page
Mar 30 13:21:45 klimt kernel: PGD 3601067 P4D 3601067 PUD 87c519067 PMD 87c3e2067 PTE 800ffff8193d8060
Mar 30 13:21:45 klimt kernel: Oops: 0000 [#1] SMP DEBUG_PAGEALLOC PTI
Mar 30 13:21:45 klimt kernel: CPU: 2 PID: 1933 Comm: nfsd Not tainted 5.6.0-rc6-00040-g881e87a3c6f9 #1591
Mar 30 13:21:45 klimt kernel: Hardware name: Supermicro Super Server/X10SRL-F, BIOS 1.0c 09/09/2015
Mar 30 13:21:45 klimt kernel: RIP: 0010:svc_rdma_post_chunk_ctxt+0xab/0x284 [rpcrdma]
Mar 30 13:21:45 klimt kernel: Code: c1 83 34 02 00 00 29 d0 85 c0 7e 72 48 8b bb a0 02 00 00 48 8d 54 24 08 4c 89 e6 48 8b 07 48 8b 40 20 e8 5a 5c 2b e1 41 89 c6 <8b> 45 20 89 44 24 04 8b 05 02 e9 01 00 85 c0 7e 33 e9 5e 01 00 00
Mar 30 13:21:45 klimt kernel: RSP: 0018:ffffc90000dfbdd8 EFLAGS: 00010286
Mar 30 13:21:45 klimt kernel: RAX: 0000000000000000 RBX: ffff8887db8db400 RCX: 0000000000000030
Mar 30 13:21:45 klimt kernel: RDX: 0000000000000040 RSI: 0000000000000000 RDI: 0000000000000246
Mar 30 13:21:45 klimt kernel: RBP: ffff8887e6c27988 R08: 0000000000000000 R09: 0000000000000004
Mar 30 13:21:45 klimt kernel: R10: ffffc90000dfbdd8 R11: 00c068ef00000000 R12: ffff8887eb4e4a80
Mar 30 13:21:45 klimt kernel: R13: ffff8887db8db634 R14: 0000000000000000 R15: ffff8887fc931000
Mar 30 13:21:45 klimt kernel: FS: 0000000000000000(0000) GS:ffff88885bd00000(0000) knlGS:0000000000000000
Mar 30 13:21:45 klimt kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Mar 30 13:21:45 klimt kernel: CR2: ffff8887e6c279a8 CR3: 000000081b72e002 CR4: 00000000001606e0
Mar 30 13:21:45 klimt kernel: Call Trace:
Mar 30 13:21:45 klimt kernel: ? svc_rdma_vec_to_sg+0x7f/0x7f [rpcrdma]
Mar 30 13:21:45 klimt kernel: svc_rdma_send_write_chunk+0x59/0xce [rpcrdma]
Mar 30 13:21:45 klimt kernel: svc_rdma_sendto+0xf9/0x3ae [rpcrdma]
Mar 30 13:21:45 klimt kernel: ? nfsd_destroy+0x51/0x51 [nfsd]
Mar 30 13:21:45 klimt kernel: svc_send+0x105/0x1e3 [sunrpc]
Mar 30 13:21:45 klimt kernel: nfsd+0xf2/0x149 [nfsd]
Mar 30 13:21:45 klimt kernel: kthread+0xf6/0xfb
Mar 30 13:21:45 klimt kernel: ? kthread_queue_delayed_work+0x74/0x74
Mar 30 13:21:45 klimt kernel: ret_from_fork+0x3a/0x50
Mar 30 13:21:45 klimt kernel: Modules linked in: ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue ib_umad ib_ipoib mlx4_ib sb_edac x86_pkg_temp_thermal iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel glue_helper crypto_simd cryptd pcspkr rpcrdma i2c_i801 rdma_ucm lpc_ich mfd_core ib_iser rdma_cm iw_cm ib_cm mei_me raid0 libiscsi mei sg scsi_transport_iscsi ioatdma wmi ipmi_si ipmi_devintf ipmi_msghandler acpi_power_meter nfsd nfs_acl lockd auth_rpcgss grace sunrpc ip_tables xfs libcrc32c mlx4_en sd_mod sr_mod cdrom mlx4_core crc32c_intel igb nvme i2c_algo_bit ahci i2c_core libahci nvme_core dca libata t10_pi qedr dm_mirror dm_region_hash dm_log dm_mod dax qede qed crc8 ib_uverbs ib_core
Mar 30 13:21:45 klimt kernel: CR2: ffff8887e6c279a8
Mar 30 13:21:45 klimt kernel: ---[ end trace 87971d2ad3429424 ]---

It's absolutely not safe to use resources pointed to by the @send_wr
argument of ib_post_send() _after_ that function returns. Those
resources are typically freed by the Send completion handler, which
can run before ib_post_send() returns.

Thus the trace points currently around ib_post_send() in the
server's RPC/RDMA transport are a hazard, even when they are
disabled. Rearrange them so that they touch the Work Request only
_before_ ib_post_send() is invoked.

Fixes: bd2abef33394 ("svcrdma: Trace key RDMA API events")
Fixes: 4201c7464753 ("svcrdma: Introduce svc_rdma_send_ctxt")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

show more ...

xprtrdma: kmalloc rpcrdma_ep separate from rpcrdma_xprt

Change the rpcrdma_xprt_disconnect() function so that it no longer
waits for the DISCONNECTED event. This prevents blocking if the
remote is

xprtrdma: kmalloc rpcrdma_ep separate from rpcrdma_xprt

Change the rpcrdma_xprt_disconnect() function so that it no longer
waits for the DISCONNECTED event. This prevents blocking if the
remote is unresponsive.

In rpcrdma_xprt_disconnect(), the transport's rpcrdma_ep is
detached. Upon return from rpcrdma_xprt_disconnect(), the transport
(r_xprt) is ready immediately for a new connection.

The RDMA_CM_DEVICE_REMOVAL and RDMA_CM_DISCONNECTED events are now
handled almost identically.

However, because the lifetimes of rpcrdma_xprt structures and
rpcrdma_ep structures are now independent, creating an rpcrdma_ep
needs to take a module ref count. The ep now owns most of the
hardware resources for a transport.

Also, a kref is needed to ensure that rpcrdma_ep sticks around
long enough for the cm_event_handler to finish.

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

show more ...

xprtrdma: Extract sockaddr from struct rdma_cm_id

rpcrdma_cm_event_handler() is always passed an @id pointer that is
valid. However, in a subsequent patch, we won't be able to extract
an r_xprt in e

xprtrdma: Extract sockaddr from struct rdma_cm_id

rpcrdma_cm_event_handler() is always passed an @id pointer that is
valid. However, in a subsequent patch, we won't be able to extract
an r_xprt in every case. So instead of using the r_xprt's
presentation address strings, extract them from struct rdma_cm_id.

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

show more ...

xprtrdma: Merge struct rpcrdma_ia into struct rpcrdma_ep

I eventually want to allocate rpcrdma_ep separately from struct
rpcrdma_xprt so that on occasion there can be more than one ep per
xprt.

The

xprtrdma: Merge struct rpcrdma_ia into struct rpcrdma_ep

I eventually want to allocate rpcrdma_ep separately from struct
rpcrdma_xprt so that on occasion there can be more than one ep per
xprt.

The new struct rpcrdma_ep will contain all the fields currently in
rpcrdma_ia and in rpcrdma_ep. This is all the device and CM settings
for the connection, in addition to per-connection settings
negotiated with the remote.

Take this opportunity to rename the existing ep fields from rep_* to
re_* to disambiguate these from struct rpcrdma_rep.

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

show more ...

xprtrdma: Disconnect on flushed completion

Completion errors after a disconnect often occur much sooner than a
CM_DISCONNECT event. Use this to try to detect connection loss more
quickly.

Note that

xprtrdma: Disconnect on flushed completion

Completion errors after a disconnect often occur much sooner than a
CM_DISCONNECT event. Use this to try to detect connection loss more
quickly.

Note that other kernel ULPs do take care to disconnect explicitly
when a WR is flushed.

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

show more ...

xprtrdma: Invoke rpcrdma_ia_open in the connect worker

Move rdma_cm_id creation into rpcrdma_ep_create() so that it is now
responsible for allocating all per-connection hardware resources.

With thi

xprtrdma: Invoke rpcrdma_ia_open in the connect worker

Move rdma_cm_id creation into rpcrdma_ep_create() so that it is now
responsible for allocating all per-connection hardware resources.

With this clean-up, all three arms of the switch statement in
rpcrdma_ep_connect are exactly the same now, thus the switch can be
removed.

Because device removal behaves a little differently than
disconnection, there is a little more work to be done before
rpcrdma_ep_destroy() can release the connection's rdma_cm_id. So
it is not quite symmetrical with rpcrdma_ep_create() yet.

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

show more ...

xprtrdma: Enhance MR-related trace points

Two changes:
- Show the number of SG entries that were mapped. This helps debug
DMA-related problems.
- Record the MR's resource ID instead of its memory

xprtrdma: Enhance MR-related trace points

Two changes:
- Show the number of SG entries that were mapped. This helps debug
DMA-related problems.
- Record the MR's resource ID instead of its memory address. This
groups each MR with its associated rdma-tool output, and reduces
needless exposure of memory addresses.

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

show more ...

svcrdma: Avoid DMA mapping small RPC Replies

On some platforms, DMA mapping part of a page is more costly than
copying bytes. Indeed, not involving the I/O MMU can help the
RPC/RDMA transport scale

svcrdma: Avoid DMA mapping small RPC Replies

On some platforms, DMA mapping part of a page is more costly than
copying bytes. Indeed, not involving the I/O MMU can help the
RPC/RDMA transport scale better for tiny I/Os across more RDMA
devices. This is because interaction with the I/O MMU is eliminated
for each of these small I/Os. Without the explicit unmapping, the
NIC no longer needs to do a costly internal TLB shoot down for
buffers that are just a handful of bytes.

Since pull-up is now a more a frequent operation, I've introduced a
trace point in the pull-up path. It can be used for debugging or
user-space tools that count pull-up frequency.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

show more ...

svcrdma: Rename svcrdma_encode trace points in send routines

These trace points are misnamed:

trace_svcrdma_encode_wseg
trace_svcrdma_encode_write
trace_svcrdma_encode_reply
trace_svcrdma_encod

svcrdma: Rename svcrdma_encode trace points in send routines

These trace points are misnamed:

trace_svcrdma_encode_wseg
trace_svcrdma_encode_write
trace_svcrdma_encode_reply
trace_svcrdma_encode_rseg
trace_svcrdma_encode_read
trace_svcrdma_encode_pzr

Because they actually trace posting on the Send Queue. Let's rename
them so that I can add trace points in the chunk list encoders that
actually do trace chunk list encoding events.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

show more ...

svcrdma: Use struct xdr_stream to decode ingress transport headers

The logic that checks incoming network headers has to be scrupulous.

De-duplicate: replace open-coded buffer overflow checks with

svcrdma: Use struct xdr_stream to decode ingress transport headers

The logic that checks incoming network headers has to be scrupulous.

De-duplicate: replace open-coded buffer overflow checks with the use
of xdr_stream helpers that are used most everywhere else XDR
decoding is done.

One minor change to the sanity checks: instead of checking the
length of individual segments, cap the length of the whole chunk
to be sure it can fit in the set of pages available in rq_pages.
This should be a better test of whether the server can handle the
chunks in each request.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

show more ...

svcrdma: Remove svcrdma_cm_event() trace point

Clean up. This trace point is no longer needed because the RDMA/core
CMA code has an equivalent trace point that was added by commit
ed999f820a6c ("RDM

svcrdma: Remove svcrdma_cm_event() trace point

Clean up. This trace point is no longer needed because the RDMA/core
CMA code has an equivalent trace point that was added by commit
ed999f820a6c ("RDMA/cma: Add trace points in RDMA Connection
Manager").

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

show more ...

xprtrdma: Make sendctx queue lifetime the same as connection lifetime

The size of the sendctx queue depends on the value stored in
ia->ri_max_send_sges. This value is determined by querying the
unde

xprtrdma: Make sendctx queue lifetime the same as connection lifetime

The size of the sendctx queue depends on the value stored in
ia->ri_max_send_sges. This value is determined by querying the
underlying device.

Eventually, rpcrdma_ia_open() and rpcrdma_ep_create() will be called
in the connect worker rather than at transport set-up time. The
underlying device will not have been chosen device set-up time.

The sendctx queue will thus have to be created after the underlying
device has been chosen via address and route resolution; in other
words, in the connect worker.

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

show more ...

ftrace: Rework event_create_dir()

Rework event_create_dir() to use an array of static data instead of
function pointers where possible.

The problem is that it would call the function pointer on mod

ftrace: Rework event_create_dir()

Rework event_create_dir() to use an array of static data instead of
function pointers where possible.

The problem is that it would call the function pointer on module load
before parse_args(), possibly even before jump_labels were initialized.
Luckily the generated functions don't use jump_labels but it still seems
fragile. It also gets in the way of changing when we make the module map
executable.

The generated function are basically calling trace_define_field() with a
bunch of static arguments. So instead of a function, capture these
arguments in a static array, avoiding the function call.

Now there are a number of cases where the fields are dynamic (syscall
arguments, kprobes and uprobes), in which case a static array does not
work, for these we preserve the function call. Luckily all these cases
are not related to modules and so we can retain the function call for
them.

Also fix up all broken tracepoint definitions that now generate a
compile error.

Tested-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191111132458.342979914@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

show more ...

xprtrdma: Replace dprintk in xprt_rdma_set_port

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

xprtrdma: Replace dprintk() in rpcrdma_update_connect_private()

Clean up: Use a single trace point to record each connection's
negotiated inline thresholds and the computed maximum byte size
of tran

xprtrdma: Replace dprintk() in rpcrdma_update_connect_private()

Clean up: Use a single trace point to record each connection's
negotiated inline thresholds and the computed maximum byte size
of transport headers.

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

show more ...

xprtrdma: Refine trace_xprtrdma_fixup

Slightly reduce overhead and display more useful information.

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

xprtrdma: Refine trace_xprtrdma_fixup

Slightly reduce overhead and display more useful information.

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

show more ...

xprtrdma: Report the computed connect delay

For debugging, the op_connect trace point should report the computed
connect delay. We can then ensure that the delay is computed at the
proper times, for

xprtrdma: Report the computed connect delay

For debugging, the op_connect trace point should report the computed
connect delay. We can then ensure that the delay is computed at the
proper times, for example.

As a further clean-up, remove a few low-value "heartbeat" trace
points in the connect path.

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

show more ...

xprtrdma: Pull up sometimes

On some platforms, DMA mapping part of a page is more costly than
copying bytes. Restore the pull-up code and use that when we
think it's going to be faster. The heuristi

xprtrdma: Pull up sometimes

On some platforms, DMA mapping part of a page is more costly than
copying bytes. Restore the pull-up code and use that when we
think it's going to be faster. The heuristic for now is to pull-up
when the size of the RPC message body fits in the buffer underlying
the head iovec.

Indeed, not involving the I/O MMU can help the RPC/RDMA transport
scale better for tiny I/Os across more RDMA devices. This is because
interaction with the I/O MMU is eliminated, as is handling a Send
completion, for each of these small I/Os. Without the explicit
unmapping, the NIC no longer needs to do a costly internal TLB shoot
down for buffers that are just a handful of bytes.

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

show more ...

xprtrdma: Move the rpcrdma_sendctx::sc_wr field

Clean up: This field is not needed in the Send completion handler,
so it can be moved to struct rpcrdma_req to reduce the size of
struct rpcrdma_sendc

xprtrdma: Move the rpcrdma_sendctx::sc_wr field

Clean up: This field is not needed in the Send completion handler,
so it can be moved to struct rpcrdma_req to reduce the size of
struct rpcrdma_sendctx, and to reduce the amount of memory that
is sloshed between the sending process and the Send completion
process.

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

show more ...

xprtrdma: Add unique trace points for posting Local Invalidate WRs

When adding frwr_unmap_async way back when, I re-used the existing
trace_xprtrdma_post_send() trace point to record the return code

xprtrdma: Add unique trace points for posting Local Invalidate WRs

When adding frwr_unmap_async way back when, I re-used the existing
trace_xprtrdma_post_send() trace point to record the return code
of ib_post_send.

Unfortunately there are some cases where re-using that trace point
causes a crash. Instead, construct a trace point specific to posting
Local Invalidate WRs that will always be safe to use in that context,
and will act as a trace log eye-catcher for Local Invalidation.

Fixes: 847568942f93 ("xprtrdma: Remove fr_state")
Fixes: d8099feda483 ("xprtrdma: Reduce context switching due ... ")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Bill Baker <bill.baker@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

show more ...

svcrdma: Improve DMA mapping trace points

Capture the total size of Sends, the size of DMA map and the
matching DMA unmap to ensure operation is correct.

Signed-off-by: Chuck Lever <chuck.lever@ora

svcrdma: Improve DMA mapping trace points

Capture the total size of Sends, the size of DMA map and the
matching DMA unmap to ensure operation is correct.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

show more ...

xprtrdma: Cache free MRs in each rpcrdma_req

Instead of a globally-contended MR free list, cache MRs in each
rpcrdma_req as they are released. This means acquiring and releasing
an MR will be lock-f

xprtrdma: Cache free MRs in each rpcrdma_req

Instead of a globally-contended MR free list, cache MRs in each
rpcrdma_req as they are released. This means acquiring and releasing
an MR will be lock-free in the common case, even outside the
transport send lock.

The original idea of per-rpcrdma_req MR free lists was suggested by
Shirley Ma <shirley.ma@oracle.com> several years ago. I just now
figured out how to make that idea work with on-demand MR allocation.

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

show more ...

xprtrdma: Move rpcrdma_mr_get out of frwr_map

Refactor: Retrieve an MR and handle error recovery entirely in
rpc_rdma.c, as this is not a device-specific function.

Note that since commit 89f90fe1ad

xprtrdma: Move rpcrdma_mr_get out of frwr_map

Refactor: Retrieve an MR and handle error recovery entirely in
rpc_rdma.c, as this is not a device-specific function.

Note that since commit 89f90fe1ad8b ("SUNRPC: Allow calls to
xprt_transmit() to drain the entire transmit queue"), the
xprt_transmit function handles the cond_resched. The transport no
longer has to do this itself.

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

show more ...