summaryrefslogtreecommitdiffstats
path: root/net/sunrpc/xprtrdma
AgeCommit message (Collapse)Author
2020-06-04svcrdma: Fix leak of svc_rdma_recv_ctxt objectsChuck Lever
commit 23cf1ee1f1869966b75518c59b5cbda4c6c92450 upstream. Utilize the xpo_release_rqst transport method to ensure that each rqstp's svc_rdma_recv_ctxt object is released even when the server cannot return a Reply for that rqstp. Without this fix, each RPC whose Reply cannot be sent leaks one svc_rdma_recv_ctxt. This is a 2.5KB structure, a 4KB DMA-mapped Receive buffer, and any pages that might be part of the Reply message. The leak is infrequent unless the network fabric is unreliable or Kerberos is in use, as GSS sequence window overruns, which result in connection loss, are more common on fast transports. Fixes: 3a88092ee319 ("svcrdma: Preserve Receive buffer until svc_rdma_sendto") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2020-06-04svcrdma: Fix trace point use-after-free raceChuck Lever
commit e28b4fc652c1830796a4d3e09565f30c20f9a2cf upstream. 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> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2020-06-04SUNRPC: Fix backchannel RPC soft lockupsChuck Lever
commit 6221f1d9b63fed6260273e59a2b89ab30537a811 upstream. Currently, after the forward channel connection goes away, backchannel operations are causing soft lockups on the server because call_transmit_status's SOFTCONN logic ignores ENOTCONN. Such backchannel Calls are aggressively retried until the client reconnects. Backchannel Calls should use RPC_TASK_NOCONNECT rather than RPC_TASK_SOFTCONN. If there is no forward connection, the server is not capable of establishing a connection back to the client, thus that backchannel request should fail before the server attempts to send it. Commit 58255a4e3ce5 ("NFSD: NFSv4 callback client should use RPC_TASK_SOFTCONN") was merged several years before RPC_TASK_NOCONNECT was available. Because setup_callback_client() explicitly sets NOPING, the NFSv4.0 callback connection depends on the first callback RPC to initiate a connection to the client. Thus NFSv4.0 needs to continue to use RPC_TASK_SOFTCONN. Suggested-by: Trond Myklebust <trondmy@hammerspace.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: <stable@vger.kernel.org> # v4.20+ Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2020-05-04xprtrdma: Fix DMA scatter-gather list mapping imbalanceChuck Lever
commit ca1c671302825182629d3c1a60363cee6f5455bb upstream. The @nents value that was passed to ib_dma_map_sg() has to be passed to the matching ib_dma_unmap_sg() call. If ib_dma_map_sg() choses to concatenate sg entries, it will return a different nents value than it was passed. The bug was exposed by recent changes to the AMD IOMMU driver, which enabled sg entry concatenation. Looking all the way back to commit 4143f34e01e9 ("xprtrdma: Port to new memory registration API") and reviewing other kernel ULPs, it's not clear that the frwr_map() logic was ever correct for this case. Reported-by: Andre Tomt <andre@tomt.net> Suggested-by: Robin Murphy <robin.murphy@arm.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: stable@vger.kernel.org Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2020-04-12SUNRPC: Fix backchannel latency metricsChuck Lever
commit 8729aaba74626c4ebce3abf1b9e96bb62d2958ca upstream. I noticed that for callback requests, the reported backlog latency is always zero, and the rtt value is crazy big. The problem was that rqst->rq_xtime is never set for backchannel requests. Fixes: 78215759e20d ("SUNRPC: Make RTT measurement more ... ") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2020-03-30xprtrdma: Fix completion wait during device removalChuck Lever
commit 13cb886c591f341a8759f175292ddf978ef903a1 upstream. I've found that on occasion, "rmmod <dev>" will hang while if an NFS is under load. Ensure that ri_remove_done is initialized only just before the transport is woken up to force a close. This avoids the completion possibly getting initialized again while the CM event handler is waiting for a wake-up. Fixes: bebd031866ca ("xprtrdma: Support unplugging an HCA from under an NFS mount") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2020-03-30xprtrdma: Fix create_qp crash on device unloadChuck Lever
commit b32b9ed493f938e191f790a0991d20b18b38c35b upstream. On device re-insertion, the RDMA device driver crashes trying to set up a new QP: Nov 27 16:32:06 manet kernel: BUG: kernel NULL pointer dereference, address: 00000000000001c0 Nov 27 16:32:06 manet kernel: #PF: supervisor write access in kernel mode Nov 27 16:32:06 manet kernel: #PF: error_code(0x0002) - not-present page Nov 27 16:32:06 manet kernel: PGD 0 P4D 0 Nov 27 16:32:06 manet kernel: Oops: 0002 [#1] SMP Nov 27 16:32:06 manet kernel: CPU: 1 PID: 345 Comm: kworker/u28:0 Tainted: G W 5.4.0 #852 Nov 27 16:32:06 manet kernel: Hardware name: Supermicro SYS-6028R-T/X10DRi, BIOS 1.1a 10/16/2015 Nov 27 16:32:06 manet kernel: Workqueue: xprtiod xprt_rdma_connect_worker [rpcrdma] Nov 27 16:32:06 manet kernel: RIP: 0010:atomic_try_cmpxchg+0x2/0x12 Nov 27 16:32:06 manet kernel: Code: ff ff 48 8b 04 24 5a c3 c6 07 00 0f 1f 40 00 c3 31 c0 48 81 ff 08 09 68 81 72 0c 31 c0 48 81 ff 83 0c 68 81 0f 92 c0 c3 8b 06 <f0> 0f b1 17 0f 94 c2 84 d2 75 02 89 06 88 d0 c3 53 ba 01 00 00 00 Nov 27 16:32:06 manet kernel: RSP: 0018:ffffc900035abbf0 EFLAGS: 00010046 Nov 27 16:32:06 manet kernel: RAX: 0000000000000000 RBX: 00000000000001c0 RCX: 0000000000000000 Nov 27 16:32:06 manet kernel: RDX: 0000000000000001 RSI: ffffc900035abbfc RDI: 00000000000001c0 Nov 27 16:32:06 manet kernel: RBP: ffffc900035abde0 R08: 000000000000000e R09: ffffffffffffc000 Nov 27 16:32:06 manet kernel: R10: 0000000000000000 R11: 000000000002e800 R12: ffff88886169d9f8 Nov 27 16:32:06 manet kernel: R13: ffff88886169d9f4 R14: 0000000000000246 R15: 0000000000000000 Nov 27 16:32:06 manet kernel: FS: 0000000000000000(0000) GS:ffff88846fa40000(0000) knlGS:0000000000000000 Nov 27 16:32:06 manet kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 Nov 27 16:32:06 manet kernel: CR2: 00000000000001c0 CR3: 0000000002009006 CR4: 00000000001606e0 Nov 27 16:32:06 manet kernel: Call Trace: Nov 27 16:32:06 manet kernel: do_raw_spin_lock+0x2f/0x5a Nov 27 16:32:06 manet kernel: create_qp_common.isra.47+0x856/0xadf [mlx4_ib] Nov 27 16:32:06 manet kernel: ? slab_post_alloc_hook.isra.60+0xa/0x1a Nov 27 16:32:06 manet kernel: ? __kmalloc+0x125/0x139 Nov 27 16:32:06 manet kernel: mlx4_ib_create_qp+0x57f/0x972 [mlx4_ib] The fix is to copy the qp_init_attr struct that was just created by rpcrdma_ep_create() instead of using the one from the previous connection instance. Fixes: 98ef77d1aaa7 ("xprtrdma: Send Queue size grows after a reconnect") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2020-03-30xprtrdma: Close window between waking RPC senders and posting ReceivesChuck Lever
commit 2ae50ad68cd79224198b525f7bd645c9da98b6ff upstream. A recent clean up attempted to separate Receive handling and RPC Reply processing, in the name of clean layering. Unfortunately, we can't do this because the Receive Queue has to be refilled _after_ the most recent credit update from the responder is parsed from the transport header, but _before_ we wake up the next RPC sender. That is right in the middle of rpcrdma_reply_handler(). Usually this isn't a problem because current responder implementations don't vary their credit grant. The one exception is when a connection is established: the grant goes from one to a much larger number on the first Receive. The requester MUST post enough Receives right then so that any outstanding requests can be sent without risking RNR and connection loss. Fixes: 6ceea36890a0 ("xprtrdma: Refactor Receive accounting") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2019-12-29SUNRPC: The RDMA back channel mustn't disappear while requests are outstandingTrond Myklebust
commit 9edb455e6797bb50aa38ef71e62668966065ede8 upstream. If there are RDMA back channel requests being processed by the server threads, then we should hold a reference to the transport to ensure it doesn't get freed from underneath us. Reported-by: Neil Brown <neilb@suse.de> Fixes: 63cae47005af ("xprtrdma: Handle incoming backward direction RPC calls") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2019-11-09xprtrdma: Send Queue size grows after a reconnectChuck Lever
commit 98ef77d1aaa7a2f4e1b2a721faa084222021fda7 upstream. Eli Dorfman reports that after a series of idle disconnects, an RPC/RDMA transport becomes unusable (rdma_create_qp returns -ENOMEM). Problem was tracked down to increasing Send Queue size after each reconnect. The rdma_create_qp() API does not promise to leave its @qp_init_attr parameter unaltered. In fact, some drivers do modify one or more of its fields. Thus our calls to rdma_create_qp must use a fresh copy of ib_qp_init_attr each time. This fix is appropriate for kernels dating back to late 2007, though it will have to be adapted, as the connect code has changed over the years. Reported-by: Eli Dorfman <eli@vastdata.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2019-11-09xprtrdma: Toggle XPRT_CONGESTED in xprtrdma's slot methodsChuck Lever
commit 395790566eec37706dedeb94779045adc3a7581e upstream. Commit 48be539dd44a ("xprtrdma: Introduce ->alloc_slot call-out for xprtrdma") added a separate alloc_slot and free_slot to the RPC/RDMA transport. Later, commit 75891f502f5f ("SUNRPC: Support for congestion control when queuing is enabled") modified the generic alloc/free_slot methods, but neglected the methods in xprtrdma. Found via code review. Fixes: 75891f502f5f ("SUNRPC: Support for congestion control ... ") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2019-07-05Merge tag 'nfsd-5.2-2' of git://linux-nfs.org/~bfields/linuxLinus Torvalds
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
2019-06-19svcrdma: Ignore source port when computing DRC hashChuck Lever
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 16e4d93f6de7 ("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>
2019-05-28xprtrdma: Use struct_size() in kzalloc()Gustavo A. R. Silva
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>
2019-04-25xprtrdma: Remove stale commentChuck Lever
The comment hasn't been accurate for several years. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2019-04-25xprtrdma: Update comments that reference ib_drain_qpChuck Lever
Commit e1ede312f17e ("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>
2019-04-25xprtrdma: Remove pr_err() call sites from completion handlersChuck Lever
Clean up: rely on the trace points instead. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2019-04-25xprtrdma: Eliminate struct rpcrdma_create_data_internalChuck Lever
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>
2019-04-25xprtrdma: Aggregate the inline settings in struct rpcrdma_epChuck Lever
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>
2019-04-25xprtrdma: Remove rpcrdma_create_data_internal::rsize and wsizeChuck Lever
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>
2019-04-25xprtrdma: Eliminate rpcrdma_ia::ri_deviceChuck Lever
Clean up. Since commit 54cbd6b0c6b9 ("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>
2019-04-25xprtrdma: More Send completion batchingChuck Lever
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>
2019-04-25xprtrdma: Clean up sendctx functionsChuck Lever
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>
2019-04-25xprtrdma: Trace marshaling failuresChuck Lever
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>
2019-04-25xprtrdma: Increase maximum number of backchannel requestsChuck Lever
Reflects the change introduced in commit 067c46967160 ("NFSv4.1: Bump the default callback session slot count to 16"). Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2019-04-25xprtrdma: Backchannel can use GFP_KERNEL allocationsChuck Lever
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>
2019-04-25xprtrdma: Clean up regbuf helpersChuck Lever
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>
2019-04-25xprtrdma: De-duplicate "allocate new, free old regbuf"Chuck Lever
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>
2019-04-25xprtrdma: Allocate req's regbufs at xprt create timeChuck Lever
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>
2019-04-25xprtrdma: rpcrdma_regbuf alignmentChuck Lever
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>
2019-04-25xprtrdma: Clean up rpcrdma_create_rep() and rpcrdma_destroy_rep()Chuck Lever
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>
2019-04-25xprtrdma: Clean up rpcrdma_create_req()Chuck Lever
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>
2019-04-25xprtrdma: Fix an frwr_map recovery nitChuck Lever
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: e2f34e26710b ("xprtrdma: Yet another double DMA-unmap") Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2019-04-25SUNRPC: Avoid digging into the ATOMIC poolChuck Lever
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>
2019-04-25SUNRPC: Refactor xprt_request_wait_receive()Trond Myklebust
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>
2019-04-11xprtrdma: Fix helper that drains the transportChuck Lever
We want to drain only the RQ first. Otherwise the transport can deadlock on ->close if there are outstanding Send completions. Fixes: 6d2d0ee27c7a ("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>
2019-03-12Merge tag 'nfsd-5.1' of git://linux-nfs.org/~bfields/linuxLinus Torvalds
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
2019-02-25Merge tag 'nfs-rdma-for-5.1-1' of ↵Trond Myklebust
git://git.linux-nfs.org/projects/anna/linux-nfs NFSoRDMA client updates for 5.1 New features: - Convert rpc auth layer to use xdr_streams - Config option to disable insecure enctypes - Reduce size of RPC receive buffers Bugfixes and cleanups: - Fix sparse warnings - Check inline size before providing a write chunk - Reduce the receive doorbell rate - Various tracepoint improvements [Trond: Fix up merge conflicts] Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2019-02-20SUNRPC: Ensure rq_bytes_sent is reset before request transmissionTrond Myklebust
When we resend a request, ensure that the 'rq_bytes_sent' is reset to zero. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2019-02-16Merge tag 'nfs-for-5.0-4' of git://git.linux-nfs.org/projects/anna/linux-nfsLinus Torvalds
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
2019-02-13SUNRPC: Remove rpc_xprt::tsh_sizeChuck Lever
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>
2019-02-13SUNRPC: Add xdr_stream::rqst fieldChuck Lever
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>
2019-02-13xprtrdma: Reduce the doorbell rate (Receive)Chuck Lever
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>
2019-02-13xprtrdma: Check inline size before providing a Write chunkChuck Lever
In very rare cases, an NFS READ operation might predict that the non-payload part of the RPC Call is large. For instance, an NFSv4 COMPOUND with a large GETATTR result, in combination with a large Kerberos credential, could push the non-payload part to be several kilobytes. If the non-payload part is larger than the connection's inline threshold, the client is required to provision a Reply chunk. The current Linux client does not check for this case. There are two obvious ways to handle it: a. Provision a Write chunk for the payload and a Reply chunk for the non-payload part b. Provision a Reply chunk for the whole RPC Reply Some testing at a recent NFS bake-a-thon showed that servers can mostly handle a. but there are some corner cases that do not work yet. b. already works (it has to, to handle krb5i/p), but could be somewhat less efficient. However, I expect this scenario to be very rare -- no-one has reported a problem yet. So I'm going to implement b. Sometime later I will provide some patches to help make b. a little more efficient by more carefully choosing the Reply chunk's segment sizes to ensure the payload is optimally aligned. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2019-02-13xprtrdma: Fix sparse warningsChuck Lever
linux/net/sunrpc/xprtrdma/rpc_rdma.c:375:63: warning: incorrect type in argument 5 (different base types) linux/net/sunrpc/xprtrdma/rpc_rdma.c:375:63: expected unsigned int [usertype] xid linux/net/sunrpc/xprtrdma/rpc_rdma.c:375:63: got restricted __be32 [usertype] rq_xid linux/net/sunrpc/xprtrdma/rpc_rdma.c:432:62: warning: incorrect type in argument 5 (different base types) linux/net/sunrpc/xprtrdma/rpc_rdma.c:432:62: expected unsigned int [usertype] xid linux/net/sunrpc/xprtrdma/rpc_rdma.c:432:62: got restricted __be32 [usertype] rq_xid linux/net/sunrpc/xprtrdma/rpc_rdma.c:489:62: warning: incorrect type in argument 5 (different base types) linux/net/sunrpc/xprtrdma/rpc_rdma.c:489:62: expected unsigned int [usertype] xid linux/net/sunrpc/xprtrdma/rpc_rdma.c:489:62: got restricted __be32 [usertype] rq_xid Fixes: 0a93fbcb16e6 ("xprtrdma: Plant XID in on-the-wire RDMA ... ") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2019-02-12xprtrdma: Make sure Send CQ is allocated on an existing compvecNicolas Morey-Chaisemartin
Make sure the device has at least 2 completion vectors before allocating to compvec#1 Fixes: a4699f5647f3 (xprtrdma: Put Send CQ in IB_POLL_WORKQUEUE mode) Signed-off-by: Nicolas Morey-Chaisemartin <nmoreychaisemartin@suse.com> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2019-02-06svcrdma: Remove syslog warnings in work completion handlersChuck Lever
These can result in a lot of log noise, and are able to be triggered by client misbehavior. Since there are trace points in these handlers now, there's no need to spam the log. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2019-02-06svcrdma: Squelch compiler warning when SUNRPC_DEBUG is disabledChuck Lever
CC [M] net/sunrpc/xprtrdma/svc_rdma_transport.o linux/net/sunrpc/xprtrdma/svc_rdma_transport.c: In function ‘svc_rdma_accept’: linux/net/sunrpc/xprtrdma/svc_rdma_transport.c:452:19: warning: variable ‘sap’ set but not used [-Wunused-but-set-variable] struct sockaddr *sap; ^ Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2019-02-06svcrdma: Use struct_size() in kmalloc()Gustavo A. R. Silva
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 = kmalloc(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 = kmalloc(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: J. Bruce Fields <bfields@redhat.com>
2019-02-06svcrpc: fix unlikely races preventing queueing of socketsJ. Bruce Fields
In the rpc server, When something happens that might be reason to wake up a thread to do something, what we do is - modify xpt_flags, sk_sock->flags, xpt_reserved, or xpt_nr_rqsts to indicate the new situation - call svc_xprt_enqueue() to decide whether to wake up a thread. svc_xprt_enqueue may require multiple conditions to be true before queueing up a thread to handle the xprt. In the SMP case, one of the other CPU's may have set another required condition, and in that case, although both CPUs run svc_xprt_enqueue(), it's possible that neither call sees the writes done by the other CPU in time, and neither one recognizes that all the required conditions have been set. A socket could therefore be ignored indefinitely. Add memory barries to ensure that any svc_xprt_enqueue() call will always see the conditions changed by other CPUs before deciding to ignore a socket. I've never seen this race reported. In the unlikely event it happens, another event will usually come along and the problem will fix itself. So I don't think this is worth backporting to stable. Chuck tried this patch and said "I don't see any performance regressions, but my server has only a single last-level CPU cache." Tested-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-07-01 11:09:10 +0000