summaryrefslogtreecommitdiffstats
path: root/net
Commit message (Collapse)AuthorAgeFilesLines
...
| * | | ipv6: fix a typo in fib6_rule_lookup()Eric Dumazet2019-09-201-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Yi Ren reported an issue discovered by syzkaller, and bisected to the cited commit. Many thanks to Yi, this trivial patch does not reflect the patient work that has been done. Fixes: d64a1f574a29 ("ipv6: honor RT6_LOOKUP_F_DST_NOREF in rule lookup logic") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Wei Wang <weiwan@google.com> Bisected-and-reported-by: Yi Ren <c4tren@gmail.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
| * | | sch_netem: fix a divide by zero in tabledist()Eric Dumazet2019-09-201-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | syzbot managed to crash the kernel in tabledist() loading an empty distribution table. t = dist->table[rnd % dist->size]; Simply return an error when such load is attempted. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
| * | | ipv4: Revert removal of rt_uses_gatewayDavid Ahern2019-09-205-19/+26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Julian noted that rt_uses_gateway has a more subtle use than 'is gateway set': https://lore.kernel.org/netdev/alpine.LFD.2.21.1909151104060.2546@ja.home.ssi.bg/ Revert that part of the commit referenced in the Fixes tag. Currently, there are no u8 holes in 'struct rtable'. There is a 4-byte hole in the second cacheline which contains the gateway declaration. So move rt_gw_family down to the gateway declarations since they are always used together, and then re-use that u8 for rt_uses_gateway. End result is that rtable size is unchanged. Fixes: 1550c171935d ("ipv4: Prepare rtable for IPv6 gateway") Reported-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: David Ahern <dsahern@gmail.com> Reviewed-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
| * | | net/sched: act_sample: don't push mac header on ip6gre ingressDavide Caratti2019-09-201-0/+1
| | |/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | current 'sample' action doesn't push the mac header of ingress packets if they are received by a layer 3 tunnel (like gre or sit); but it forgot to check for gre over ipv6, so the following script: # tc q a dev $d clsact # tc f a dev $d ingress protocol ip flower ip_proto icmp action sample \ > group 100 rate 1 # psample -v -g 100 dumps everything, including outer header and mac, when $d is a gre tunnel over ipv6. Fix this adding a missing label for ARPHRD_IP6GRE devices. Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Yotam Gigi <yotam.gi@gmail.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
| * | net/ncsi: Disable global multicast filterVijay Khemka2019-09-192-93/+12
| |/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Disabling multicast filtering from NCSI if it is supported. As it should not filter any multicast packets. In current code, multicast filter is enabled and with an exception of optional field supported by device are disabled filtering. Mainly I see if goal is to disable filtering for IPV6 packets then let it disabled for every other types as well. As we are seeing issues with LLDP not working with this enabled filtering. And there are other issues with IPV6. By Disabling this multicast completely, it is working for both IPV6 as well as LLDP. Signed-off-by: Vijay Khemka <vijaykhemka@fb.com> Acked-by: Samuel Mendoza-Jonas <sam@mendozajonas.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
* | Merge tag 'nfsd-5.4' of git://linux-nfs.org/~bfields/linuxLinus Torvalds2019-09-275-30/+26
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull nfsd updates from Bruce Fields: "Highlights: - Add a new knfsd file cache, so that we don't have to open and close on each (NFSv2/v3) READ or WRITE. This can speed up read and write in some cases. It also replaces our readahead cache. - Prevent silent data loss on write errors, by treating write errors like server reboots for the purposes of write caching, thus forcing clients to resend their writes. - Tweak the code that allocates sessions to be more forgiving, so that NFSv4.1 mounts are less likely to hang when a server already has a lot of clients. - Eliminate an arbitrary limit on NFSv4 ACL sizes; they should now be limited only by the backend filesystem and the maximum RPC size. - Allow the server to enforce use of the correct kerberos credentials when a client reclaims state after a reboot. And some miscellaneous smaller bugfixes and cleanup" * tag 'nfsd-5.4' of git://linux-nfs.org/~bfields/linux: (34 commits) sunrpc: clean up indentation issue nfsd: fix nfs read eof detection nfsd: Make nfsd_reset_boot_verifier_locked static nfsd: degraded slot-count more gracefully as allocation nears exhaustion. nfsd: handle drc over-allocation gracefully. nfsd: add support for upcall version 2 nfsd: add a "GetVersion" upcall for nfsdcld nfsd: Reset the boot verifier on all write I/O errors nfsd: Don't garbage collect files that might contain write errors nfsd: Support the server resetting the boot verifier nfsd: nfsd_file cache entries should be per net namespace nfsd: eliminate an unnecessary acl size limit Deprecate nfsd fault injection nfsd: remove duplicated include from filecache.c nfsd: Fix the documentation for svcxdr_tmpalloc() nfsd: Fix up some unused variable warnings nfsd: close cached files prior to a REMOVE or RENAME that would replace target nfsd: rip out the raparms cache nfsd: have nfsd_test_lock use the nfsd_file cache nfsd: hook up nfs4_preprocess_stateid_op to the nfsd_file cache ...
| * | sunrpc: clean up indentation issueColin Ian King2019-09-251-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | There are statements that are indented incorrectly, remove the extraneous spacing. Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * | sunrpc: add a new cache_detail operation for when a cache is flushedJeff Layton2019-08-191-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When the exports table is changed, exportfs will usually write a new time to the "flush" file in the nfsd.export cache procfile. This tells the kernel to flush any entries that are older than that value. This gives us a mechanism to tell whether an unexport might have occurred. Add a new ->flush cache_detail operation that is called after flushing the cache whenever someone writes to a "flush" file. Signed-off-by: Jeff Layton <jeff.layton@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * | svcrdma: Use llist for managing cache of recv_ctxtsChuck Lever2019-08-192-16/+11
| | | | | | | | | | | | | | | | | | | | | | | | Use a wait-free mechanism for managing the svc_rdma_recv_ctxts free list. Subsequently, sc_recv_lock can be eliminated. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * | svcrdma: Remove svc_rdma_wqChuck Lever2019-08-192-8/+2
| | | | | | | | | | | | | | | | | | | | | Clean up: the system workqueue will work just as well. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * | SUNRPC: Track writers of the 'channel' file to improve cache_listeners_existDave Wysochanski2019-07-301-4/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The sunrpc cache interface is susceptible to being fooled by a rogue process just reading a 'channel' file. If this happens the kernel may think a valid daemon exists to service the cache when it does not. For example, the following may fool the kernel: cat /proc/net/rpc/auth.unix.gid/channel Change the tracking of readers to writers when considering whether a listener exists as all valid daemon processes either open a channel file O_RDWR or O_WRONLY. While this does not prevent a rogue process from "stealing" a message from the kernel, it does at least improve the kernels perception of whether a valid process servicing the cache exists. Signed-off-by: Dave Wysochanski <dwysocha@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* | | Merge tag '9p-for-5.4' of git://github.com/martinetd/linuxLinus Torvalds2019-09-271-0/+1
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull 9p updates from Dominique Martinet: "Some of the usual small fixes and cleanup. Small fixes all around: - avoid overlayfs copy-up for PRIVATE mmaps - KUMSAN uninitialized warning for transport error - one syzbot memory leak fix in 9p cache - internal API cleanup for v9fs_fill_super" * tag '9p-for-5.4' of git://github.com/martinetd/linux: 9p/vfs_super.c: Remove unused parameter data in v9fs_fill_super 9p/cache.c: Fix memory leak in v9fs_cache_session_get_cookie 9p: Transport error uninitialized 9p: avoid attaching writeback_fid on mmap with type PRIVATE
| * | | 9p: Transport error uninitializedLu Shuaibing2019-09-031-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The p9_tag_alloc() does not initialize the transport error t_err field. The struct p9_req_t *req is allocated and stored in a struct p9_client variable. The field t_err is never initialized before p9_conn_cancel() checks its value. KUMSAN(KernelUninitializedMemorySantizer, a new error detection tool) reports this bug. ================================================================== BUG: KUMSAN: use of uninitialized memory in p9_conn_cancel+0x2d9/0x3b0 Read of size 4 at addr ffff88805f9b600c by task kworker/1:2/1216 CPU: 1 PID: 1216 Comm: kworker/1:2 Not tainted 5.2.0-rc4+ #28 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 Workqueue: events p9_write_work Call Trace: dump_stack+0x75/0xae __kumsan_report+0x17c/0x3e6 kumsan_report+0xe/0x20 p9_conn_cancel+0x2d9/0x3b0 p9_write_work+0x183/0x4a0 process_one_work+0x4d1/0x8c0 worker_thread+0x6e/0x780 kthread+0x1ca/0x1f0 ret_from_fork+0x35/0x40 Allocated by task 1979: save_stack+0x19/0x80 __kumsan_kmalloc.constprop.3+0xbc/0x120 kmem_cache_alloc+0xa7/0x170 p9_client_prepare_req.part.9+0x3b/0x380 p9_client_rpc+0x15e/0x880 p9_client_create+0x3d0/0xac0 v9fs_session_init+0x192/0xc80 v9fs_mount+0x67/0x470 legacy_get_tree+0x70/0xd0 vfs_get_tree+0x4a/0x1c0 do_mount+0xba9/0xf90 ksys_mount+0xa8/0x120 __x64_sys_mount+0x62/0x70 do_syscall_64+0x6d/0x1e0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 0: (stack is not available) The buggy address belongs to the object at ffff88805f9b6008 which belongs to the cache p9_req_t of size 144 The buggy address is located 4 bytes inside of 144-byte region [ffff88805f9b6008, ffff88805f9b6098) The buggy address belongs to the page: page:ffffea00017e6d80 refcount:1 mapcount:0 mapping:ffff888068b63740 index:0xffff88805f9b7d90 compound_mapcount: 0 flags: 0x100000000010200(slab|head) raw: 0100000000010200 ffff888068b66450 ffff888068b66450 ffff888068b63740 raw: ffff88805f9b7d90 0000000000100001 00000001ffffffff 0000000000000000 page dumped because: kumsan: bad access detected ================================================================== Link: http://lkml.kernel.org/r/20190613070854.10434-1-shuaibinglu@126.com Signed-off-by: Lu Shuaibing <shuaibinglu@126.com> [dominique.martinet@cea.fr: grouped the added init with the others] Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
* | | | Merge tag 'nfs-for-5.4-1' of git://git.linux-nfs.org/projects/anna/linux-nfsLinus Torvalds2019-09-2612-384/+388
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull NFS client updates from Anna Schumaker: "Stable bugfixes: - Dequeue the request from the receive queue while we're re-encoding # v4.20+ - Fix buffer handling of GSS MIC without slack # 5.1 Features: - Increase xprtrdma maximum transport header and slot table sizes - Add support for nfs4_call_sync() calls using a custom rpc_task_struct - Optimize the default readahead size - Enable pNFS filelayout LAYOUTGET on OPEN Other bugfixes and cleanups: - Fix possible null-pointer dereferences and memory leaks - Various NFS over RDMA cleanups - Various NFS over RDMA comment updates - Don't receive TCP data into a reset request buffer - Don't try to parse incomplete RPC messages - Fix congestion window race with disconnect - Clean up pNFS return-on-close error handling - Fixes for NFS4ERR_OLD_STATEID handling" * tag 'nfs-for-5.4-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (53 commits) pNFS/filelayout: enable LAYOUTGET on OPEN NFS: Optimise the default readahead size NFSv4: Handle NFS4ERR_OLD_STATEID in LOCKU NFSv4: Handle NFS4ERR_OLD_STATEID in CLOSE/OPEN_DOWNGRADE NFSv4: Fix OPEN_DOWNGRADE error handling pNFS: Handle NFS4ERR_OLD_STATEID on layoutreturn by bumping the state seqid NFSv4: Add a helper to increment stateid seqids NFSv4: Handle RPC level errors in LAYOUTRETURN NFSv4: Handle NFS4ERR_DELAY correctly in return-on-close NFSv4: Clean up pNFS return-on-close error handling pNFS: Ensure we do clear the return-on-close layout stateid on fatal errors NFS: remove unused check for negative dentry NFSv3: use nfs_add_or_obtain() to create and reference inodes NFS: Refactor nfs_instantiate() for dentry referencing callers SUNRPC: Fix congestion window race with disconnect SUNRPC: Don't try to parse incomplete RPC messages SUNRPC: Rename xdr_buf_read_netobj to xdr_buf_read_mic SUNRPC: Fix buffer handling of GSS MIC without slack SUNRPC: RPC level errors should always set task->tk_rpc_status SUNRPC: Don't receive TCP data into a request buffer that has been reset ...
| * | | | SUNRPC: Fix congestion window race with disconnectChuck Lever2019-09-201-0/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the congestion window closes just as the transport disconnects, a reconnect is never driven because: 1. The XPRT_CONG_WAIT flag prevents tasks from taking the write lock 2. There's no wake-up of the first task on the xprt->sending queue To address this, clear the congestion wait flag as part of completing a disconnect. 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>
| * | | | SUNRPC: Don't try to parse incomplete RPC messagesTrond Myklebust2019-09-201-1/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the copy of the RPC reply into our buffers did not complete, and we could end up with a truncated message. In that case, just resend the call. Fixes: a0584ee9aed80 ("SUNRPC: Use struct xdr_stream when decoding...") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | SUNRPC: Rename xdr_buf_read_netobj to xdr_buf_read_micBenjamin Coddington2019-09-202-23/+31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Let the name reflect the single use. The function now assumes the GSS MIC is the last object in the buffer. Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | SUNRPC: Fix buffer handling of GSS MIC without slackBenjamin Coddington2019-09-201-9/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The GSS Message Integrity Check data for krb5i may lie partially in the XDR reply buffer's pages and tail. If so, we try to copy the entire MIC into free space in the tail. But as the estimations of the slack space required for authentication and verification have improved there may be less free space in the tail to complete this copy -- see commit 2c94b8eca1a2 ("SUNRPC: Use au_rslack when computing reply buffer size"). In fact, there may only be room in the tail for a single copy of the MIC, and not part of the MIC and then another complete copy. The real world failure reported is that `ls` of a directory on NFS may sometimes return -EIO, which can be traced back to xdr_buf_read_netobj() failing to find available free space in the tail to copy the MIC. Fix this by checking for the case of the MIC crossing the boundaries of head, pages, and tail. If so, shift the buffer until the MIC is contained completely within the pages or tail. This allows the remainder of the function to create a sub buffer that directly address the complete MIC. Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Cc: stable@vger.kernel.org # v5.1 Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | SUNRPC: RPC level errors should always set task->tk_rpc_statusTrond Myklebust2019-09-172-4/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Ensure that we set task->tk_rpc_status for all RPC level errors so that the caller can distinguish between those and server reply status errors. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | SUNRPC: Don't receive TCP data into a request buffer that has been resetTrond Myklebust2019-09-171-1/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we've removed the request from the receive list, and have added it back after resetting the request receive buffer, then we should only receive message data if it is a new reply (i.e. if transport->recv.copied is zero). Fixes: 277e4ab7d530b ("SUNRPC: Simplify TCP receive code by switching...") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | SUNRPC: Dequeue the request from the receive queue while we're re-encodingTrond Myklebust2019-09-172-26/+34
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Ensure that we dequeue the request from the transport receive queue while we're re-encoding to prevent issues like use-after-free when we release the bvec. Fixes: 7536908982047 ("SUNRPC: Ensure the bvecs are reset when we re-encode...") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Send Queue size grows after a reconnectChuck Lever2019-08-261-12/+14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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>
| * | | | xprtrdma: Clear xprt->reestablish_timeout on closeChuck Lever2019-08-263-4/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Ensure that the re-establishment delay does not grow exponentially on each good reconnect. This probably should have been part of commit 675dd90ad093 ("xprtrdma: Modernize ops->connect"). Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Recycle MRs after disconnectChuck Lever2019-08-263-9/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The optimization done in "xprtrdma: Simplify rpcrdma_mr_pop" was a bit too optimistic. MRs left over after a reconnect still need to be recycled, not added back to the free list, since they could be in flight or actually fully registered. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Optimize rpcrdma_post_recvs()Chuck Lever2019-08-211-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Micro-optimization: In rpcrdma_post_recvs, since commit e340c2d6ef2a ("xprtrdma: Reduce the doorbell rate (Receive)"), the common case is to return without doing anything. Found with perf. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Inline XDR chunk encoder functionsChuck Lever2019-08-211-9/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Micro-optimization: Save the cost of three function calls during transport header encoding. These were "noinline" before to generate more meaningful call stacks during debugging, but this code is now pretty stable. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Fix bc_max_slots return valueChuck Lever2019-08-211-3/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | For the moment the returned value just happens to be correct because the current backchannel server implementation does not vary the number of credits it offers. The spec does permit this value to change during the lifetime of a connection, however. The actual maximum is fixed for all RPC/RDMA transports, because each transport instance has to pre-allocate the resources for processing BC requests. That's the value that should be returned. Fixes: 7402a4fedc2b ("SUNRPC: Fix up backchannel slot table ... ") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Clean up xprt_rdma_set_connect_timeout()Chuck Lever2019-08-211-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Clean up: The function name should match the documenting comment. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Use an llist to manage free rpcrdma_repsChuck Lever2019-08-212-59/+53
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | rpcrdma_rep objects are removed from their free list by only a single thread: the Receive completion handler. Thus that free list can be converted to an llist, where a single-threaded consumer and a multi-threaded producer (rpcrdma_buffer_put) can both access the llist without the need for any serialization. This eliminates spin lock contention between the Receive completion handler and rpcrdma_buffer_get, and makes the rep consumer wait- free. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Remove rpcrdma_buffer::rb_mrlockChuck Lever2019-08-213-18/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Clean up: Now that the free list is used sparingly, get rid of the separate spin lock protecting it. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Cache free MRs in each rpcrdma_reqChuck Lever2019-08-214-12/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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>
| * | | | xprtrdma: Ensure creating an MR does not trigger FS writebackChuck Lever2019-08-202-4/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Probably would be good to also pass GFP flags to ib_alloc_mr. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Move rpcrdma_mr_get out of frwr_mapChuck Lever2019-08-204-43/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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>
| * | | | xprtrdma: Combine rpcrdma_mr_put and rpcrdma_mr_unmap_and_putChuck Lever2019-08-203-28/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Clean up. There is only one remaining rpcrdma_mr_put call site, and it can be directly replaced with unmap_and_put because mr->mr_dir is set to DMA_NONE just before the call. Now all the call sites do a DMA unmap, and we can just rename mr_unmap_and_put to mr_put, which nicely matches mr_get. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Simplify rpcrdma_mr_popChuck Lever2019-08-204-21/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Clean up: rpcrdma_mr_pop call sites check if the list is empty first. Let's replace the list_empty with less costly logic. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Toggle XPRT_CONGESTED in xprtrdma's slot methodsChuck Lever2019-08-201-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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>
| * | | | xprtrdma: Rename rpcrdma_buffer::rb_allChuck Lever2019-08-202-19/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Clean up: There are other "all" list heads. For code clarity distinguish this one as for use only for MRs by renaming it. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Rename CQE field in Receive trace pointsChuck Lever2019-08-201-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Make the field name the same for all trace points that handle pointers to struct rpcrdma_rep. That makes it easy to grep for matching rep points in trace output. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Boost maximum transport header sizeChuck Lever2019-08-202-14/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Although I haven't seen any performance results that justify it, I've received several complaints that NFS/RDMA no longer supports a maximum rsize and wsize of 1MB. These days it is somewhat smaller. To simplify the logic that determines whether a chunk list is necessary, the implementation uses a fixed maximum size of the transport header. Currently that maximum size is 256 bytes, one quarter of the default inline threshold size for RPC/RDMA v1. Since commit a78868497c2e ("xprtrdma: Reduce max_frwr_depth"), the size of chunks is also smaller to take advantage of inline page lists in device internal MR data structures. The combination of these two design choices has reduced the maximum NFS rsize and wsize that can be used for most RNIC/HCAs. Increasing the maximum transport header size and the maximum number of RDMA segments it can contain increases the negotiated maximum rsize/wsize on common RNIC/HCAs. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Fix calculation of ri_max_segs againChuck Lever2019-08-201-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit 302d3deb206 ("xprtrdma: Prevent inline overflow") added this calculation back in 2016, but got it wrong. I tested only the lower bound, which is why there is a max_t there. The upper bound should be rounded up too. Now, when using DIV_ROUND_UP, that takes care of the lower bound as well. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Update obsolete commentChuck Lever2019-08-201-3/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Comment was made obsolete by commit 8cec3dba76a4 ("xprtrdma: rpcrdma_regbuf alignment"). Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | xprtrdma: Refresh the documenting comment in frwr_ops.cChuck Lever2019-08-201-48/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Things have changed since this comment was written. In particular, the reworking of connection closing, on-demand creation of MRs, and the removal of fr_state all mean that deferring MR recovery to frwr_map is no longer needed. The description is obsolete. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | SUNRPC: Inline xdr_commit_encodeChuck Lever2019-08-201-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Micro-optimization: For xdr_commit_encode call sites in net/sunrpc/xdr.c, eliminate the extra calling sequence. On my client, this change saves about a microsecond for every 30 calls to xdr_reserve_space(). Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
| * | | | SUNRPC: Remove rpc_wake_up_queued_task_on_wq()Chuck Lever2019-08-201-23/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Clean up: commit c544577daddb ("SUNRPC: Clean up transport write space handling") appears to have removed the last caller of rpc_wake_up_queued_task_on_wq(). Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
* | | | | Merge tag 'ceph-for-5.4-rc1' of git://github.com/ceph/ceph-clientLinus Torvalds2019-09-255-44/+140
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull ceph updates from Ilya Dryomov: "The highlights are: - automatic recovery of a blacklisted filesystem session (Zheng Yan). This is disabled by default and can be enabled by mounting with the new "recover_session=clean" option. - serialize buffered reads and O_DIRECT writes (Jeff Layton). Care is taken to avoid serializing O_DIRECT reads and writes with each other, this is based on the exclusion scheme from NFS. - handle large osdmaps better in the face of fragmented memory (myself) - don't limit what security.* xattrs can be get or set (Jeff Layton). We were overly restrictive here, unnecessarily preventing things like file capability sets stored in security.capability from working. - allow copy_file_range() within the same inode and across different filesystems within the same cluster (Luis Henriques)" * tag 'ceph-for-5.4-rc1' of git://github.com/ceph/ceph-client: (41 commits) ceph: call ceph_mdsc_destroy from destroy_fs_client libceph: use ceph_kvmalloc() for osdmap arrays libceph: avoid a __vmalloc() deadlock in ceph_kvmalloc() ceph: allow object copies across different filesystems in the same cluster ceph: include ceph_debug.h in cache.c ceph: move static keyword to the front of declarations rbd: pull rbd_img_request_create() dout out into the callers ceph: reconnect connection if session hang in opening state libceph: drop unused con parameter of calc_target() ceph: use release_pages() directly rbd: fix response length parameter for encoded strings ceph: allow arbitrary security.* xattrs ceph: only set CEPH_I_SEC_INITED if we got a MAC label ceph: turn ceph_security_invalidate_secctx into static inline ceph: add buffered/direct exclusionary locking for reads and writes libceph: handle OSD op ceph_pagelist_append() errors ceph: don't return a value from void function ceph: don't freeze during write page faults ceph: update the mtime when truncating up ceph: fix indentation in __get_snap_name() ...
| * | | | | libceph: use ceph_kvmalloc() for osdmap arraysIlya Dryomov2019-09-161-26/+43
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | osdmap has a bunch of arrays that grow linearly with the number of OSDs. osd_state, osd_weight and osd_primary_affinity take 4 bytes per OSD. osd_addr takes 136 bytes per OSD because of sockaddr_storage. The CRUSH workspace area also grows linearly with the number of OSDs. Normally these arrays are allocated at client startup. The osdmap is usually updated in small incrementals, but once in a while a full map may need to be processed. For a cluster with 10000 OSDs, this means a bunch of 40K allocations followed by a 1.3M allocation, all of which are currently required to be physically contiguous. This results in sporadic ENOMEM errors, hanging the client. Go back to manually (re)allocating arrays and use ceph_kvmalloc() to fall back to non-contiguous allocation when necessary. Link: https://tracker.ceph.com/issues/40481 Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Reviewed-by: Jeff Layton <jlayton@kernel.org>
| * | | | | libceph: avoid a __vmalloc() deadlock in ceph_kvmalloc()Ilya Dryomov2019-09-161-6/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The vmalloc allocator doesn't fully respect the specified gfp mask: while the actual pages are allocated as requested, the page table pages are always allocated with GFP_KERNEL. ceph_kvmalloc() may be called with GFP_NOFS and GFP_NOIO (for ceph and rbd respectively), so this may result in a deadlock. There is no real reason for the current PAGE_ALLOC_COSTLY_ORDER logic, it's just something that seemed sensible at the time (ceph_kvmalloc() predates kvmalloc()). kvmalloc() is smarter: in an attempt to reduce long term fragmentation, it first tries to kmalloc non-disruptively. Switch to kvmalloc() and set the respective PF_MEMALLOC_* flag using the scope API to avoid the deadlock. Note that kvmalloc() needs to be passed GFP_KERNEL to enable the fallback. Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Reviewed-by: Jeff Layton <jlayton@kernel.org>
| * | | | | libceph: drop unused con parameter of calc_target()Ilya Dryomov2019-09-161-7/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This bit was omitted from a561372405cf ("libceph: fix PG split vs OSD (re)connect race") to avoid backport conflicts. Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
| * | | | | libceph: handle OSD op ceph_pagelist_append() errorsDavid Disseldorp2019-09-161-5/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | osd_req_op_cls_init() and osd_req_op_xattr_init() currently propagate ceph_pagelist_alloc() ENOMEM errors but ignore ceph_pagelist_append() memory allocation failures. Add these checks and cleanup on error. Signed-off-by: David Disseldorp <ddiss@suse.de> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
| * | | | | libceph: add function that clears osd client's abort_errYan, Zheng2019-09-161-0/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: "Yan, Zheng" <zyan@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-12 11:47:48 +0000