From 6f1f622019f95d79d6e2f8bb3781144ad0aff75f Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Mon, 6 Mar 2017 17:49:42 +0800 Subject: [PATCH 1/9] nfs4: fix a typo of NFS_ATTR_FATTR_GROUP_NAME This typo cause a memory leak, and a bad client's group id. unreferenced object 0xffff96d8073998d0 (size 8): comm "kworker/0:3", pid 34224, jiffies 4295361338 (age 761.752s) hex dump (first 8 bytes): 30 00 39 07 d8 96 ff ff 0.9..... backtrace: [] kmemleak_alloc+0x4a/0xa0 [] __kmalloc+0x140/0x220 [] xdr_stream_decode_string_dup+0x7c/0x110 [sunrpc] [] decode_getfattr_attrs+0x940/0x1630 [nfsv4] [] decode_getfattr_generic.constprop.108+0x9b/0x100 [nfsv4] [] nfs4_xdr_dec_open+0xcf/0x100 [nfsv4] [] rpcauth_unwrap_resp+0xa7/0xe0 [sunrpc] [] call_decode+0x1e0/0x810 [sunrpc] [] __rpc_execute+0x8d/0x420 [sunrpc] [] rpc_async_schedule+0x12/0x20 [sunrpc] [] process_one_work+0x197/0x430 [] worker_thread+0x4e/0x4a0 [] kthread+0x101/0x140 [] ret_from_fork+0x2c/0x40 [] 0xffffffffffffffff Fixes: 686a816ab6 ("NFSv4: Clean up owner/group attribute decode") Signed-off-by: Kinglong Mee Signed-off-by: Anna Schumaker --- fs/nfs/nfs4xdr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index f0369e362753..80ce289eea05 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3942,7 +3942,7 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, if (len <= 0) goto out; dprintk("%s: name=%s\n", __func__, group_name->data); - return NFS_ATTR_FATTR_OWNER_NAME; + return NFS_ATTR_FATTR_GROUP_NAME; } else { len = xdr_stream_decode_opaque_inline(xdr, (void **)&p, XDR_MAX_NETOBJ); From 366a1569bff3fe14abfdf9285e31e05e091745f5 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Mon, 6 Mar 2017 22:29:14 +0800 Subject: [PATCH 2/9] NFSv4: fix a reference leak caused WARNING messages Because nfs4_opendata_access() has close the state when access is denied, so the state isn't leak. Rather than revert the commit a974deee47, I'd like clean the strange state close. [ 1615.094218] ------------[ cut here ]------------ [ 1615.094607] WARNING: CPU: 0 PID: 23702 at lib/list_debug.c:31 __list_add_valid+0x8e/0xa0 [ 1615.094913] list_add double add: new=ffff9d7901d9f608, prev=ffff9d7901d9f608, next=ffff9d7901ee8dd0. [ 1615.095458] Modules linked in: nfsv4(E) nfs(E) nfsd(E) tun bridge stp llc fuse ip_set nfnetlink vmw_vsock_vmci_transport vsock f2fs snd_seq_midi snd_seq_midi_event fscrypto coretemp ppdev crct10dif_pclmul crc32_pclmul ghash_clmulni_intel intel_rapl_perf vmw_balloon snd_ens1371 joydev gameport snd_ac97_codec ac97_bus snd_seq snd_pcm snd_rawmidi snd_timer snd_seq_device snd soundcore nfit parport_pc parport acpi_cpufreq tpm_tis tpm_tis_core tpm i2c_piix4 vmw_vmci shpchp auth_rpcgss nfs_acl lockd(E) grace sunrpc(E) xfs libcrc32c vmwgfx drm_kms_helper ttm drm crc32c_intel mptspi e1000 serio_raw scsi_transport_spi mptscsih mptbase ata_generic pata_acpi fjes [last unloaded: nfs] [ 1615.097663] CPU: 0 PID: 23702 Comm: fstest Tainted: G W E 4.11.0-rc1+ #517 [ 1615.098015] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015 [ 1615.098807] Call Trace: [ 1615.099183] dump_stack+0x63/0x86 [ 1615.099578] __warn+0xcb/0xf0 [ 1615.099967] warn_slowpath_fmt+0x5f/0x80 [ 1615.100370] __list_add_valid+0x8e/0xa0 [ 1615.100760] nfs4_put_state_owner+0x75/0xc0 [nfsv4] [ 1615.101136] __nfs4_close+0x109/0x140 [nfsv4] [ 1615.101524] nfs4_close_state+0x15/0x20 [nfsv4] [ 1615.101949] nfs4_close_context+0x21/0x30 [nfsv4] [ 1615.102691] __put_nfs_open_context+0xb8/0x110 [nfs] [ 1615.103155] put_nfs_open_context+0x10/0x20 [nfs] [ 1615.103586] nfs4_file_open+0x13b/0x260 [nfsv4] [ 1615.103978] do_dentry_open+0x20a/0x2f0 [ 1615.104369] ? nfs4_copy_file_range+0x30/0x30 [nfsv4] [ 1615.104739] vfs_open+0x4c/0x70 [ 1615.105106] ? may_open+0x5a/0x100 [ 1615.105469] path_openat+0x623/0x1420 [ 1615.105823] do_filp_open+0x91/0x100 [ 1615.106174] ? __alloc_fd+0x3f/0x170 [ 1615.106568] do_sys_open+0x130/0x220 [ 1615.106920] ? __put_cred+0x3d/0x50 [ 1615.107256] SyS_open+0x1e/0x20 [ 1615.107588] entry_SYSCALL_64_fastpath+0x1a/0xa9 [ 1615.107922] RIP: 0033:0x7fab599069b0 [ 1615.108247] RSP: 002b:00007ffcf0600d78 EFLAGS: 00000246 ORIG_RAX: 0000000000000002 [ 1615.108575] RAX: ffffffffffffffda RBX: 00007fab59bcfae0 RCX: 00007fab599069b0 [ 1615.108896] RDX: 0000000000000200 RSI: 0000000000000200 RDI: 00007ffcf060255e [ 1615.109211] RBP: 0000000000040010 R08: 0000000000000000 R09: 0000000000000016 [ 1615.109515] R10: 00000000000006a1 R11: 0000000000000246 R12: 0000000000041000 [ 1615.109806] R13: 0000000000040010 R14: 0000000000001000 R15: 0000000000002710 [ 1615.110152] ---[ end trace 96ed63b1306bf2f3 ]--- Fixes: a974deee47 ("NFSv4: Fix memory and state leak in...") Signed-off-by: Kinglong Mee Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 1b183686c6d4..c1f5369cd339 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2258,8 +2258,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred, if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0) return 0; - /* even though OPEN succeeded, access is denied. Close the file */ - nfs4_close_state(state, fmode); return -EACCES; } From 38a33101dd5fb8f07244e7e6dd04747a6cd2e3fb Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Thu, 9 Mar 2017 11:36:36 +0800 Subject: [PATCH 3/9] NFS: fix the fault nrequests decreasing for nfs_inode COPY The nfs_commit_file for NFSv4.2's COPY operation goes through the commit path for normal WRITE, but without increase nrequests, so, the nrequests decreased in nfs_commit_release_pages is fault. After that, the nrequests will be wrong. [ 5670.299881] ------------[ cut here ]------------ [ 5670.300295] WARNING: CPU: 0 PID: 27656 at fs/nfs/inode.c:127 nfs_clear_inode+0x66/0x90 [nfs] [ 5670.300558] Modules linked in: nfsv4(E) nfs(E) fscache(E) tun bridge stp llc fuse ip_set nfnetlink vmw_vsock_vmci_transport vsock snd_seq_midi snd_seq_midi_event ppdev f2fs coretemp crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_ens1371 intel_rapl_perf gameport snd_ac97_codec vmw_balloon ac97_bus snd_seq snd_pcm joydev snd_rawmidi snd_timer snd_seq_device snd soundcore nfit parport_pc parport acpi_cpufreq tpm_tis tpm_tis_core tpm i2c_piix4 vmw_vmci shpchp nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c vmwgfx drm_kms_helper ttm drm e1000 crc32c_intel mptspi scsi_transport_spi serio_raw mptscsih mptbase ata_generic pata_acpi fjes [last unloaded: fscache] [ 5670.302925] CPU: 0 PID: 27656 Comm: umount.nfs4 Tainted: G W E 4.11.0-rc1+ #519 [ 5670.303292] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015 [ 5670.304094] Call Trace: [ 5670.304510] dump_stack+0x63/0x86 [ 5670.304917] __warn+0xcb/0xf0 [ 5670.305276] warn_slowpath_null+0x1d/0x20 [ 5670.305661] nfs_clear_inode+0x66/0x90 [nfs] [ 5670.306093] nfs4_evict_inode+0x61/0x70 [nfsv4] [ 5670.306480] evict+0xbb/0x1c0 [ 5670.306888] dispose_list+0x4d/0x70 [ 5670.307233] evict_inodes+0x178/0x1a0 [ 5670.307579] generic_shutdown_super+0x44/0xf0 [ 5670.307985] nfs_kill_super+0x21/0x40 [nfs] [ 5670.308325] deactivate_locked_super+0x43/0x70 [ 5670.308698] deactivate_super+0x5a/0x60 [ 5670.309036] cleanup_mnt+0x3f/0x90 [ 5670.309407] __cleanup_mnt+0x12/0x20 [ 5670.309837] task_work_run+0x80/0xa0 [ 5670.310162] exit_to_usermode_loop+0x89/0x90 [ 5670.310497] syscall_return_slowpath+0xaa/0xb0 [ 5670.310875] entry_SYSCALL_64_fastpath+0xa7/0xa9 [ 5670.311197] RIP: 0033:0x7f1bb3617fe7 [ 5670.311545] RSP: 002b:00007ffecbabb828 EFLAGS: 00000206 ORIG_RAX: 00000000000000a6 [ 5670.311906] RAX: 0000000000000000 RBX: 0000000001dca1f0 RCX: 00007f1bb3617fe7 [ 5670.312239] RDX: 000000000000000c RSI: 0000000000000001 RDI: 0000000001dc83c0 [ 5670.312653] RBP: 0000000001dc83c0 R08: 0000000000000001 R09: 0000000000000000 [ 5670.312998] R10: 0000000000000755 R11: 0000000000000206 R12: 00007ffecbabc66a [ 5670.313335] R13: 0000000001dc83a0 R14: 0000000000000000 R15: 0000000000000000 [ 5670.313758] ---[ end trace bf4bfe7764e4eb40 ]--- Cc: linux-kernel@vger.kernel.org Fixes: 67911c8f18 ("NFS: Add nfs_commit_file()") Signed-off-by: Kinglong Mee Cc: stable@vger.kernel.org # 4.7+ Signed-off-by: Anna Schumaker --- fs/nfs/write.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index e75b056f46f4..abb2c8a3be42 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1784,7 +1784,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) (long long)req_offset(req)); if (status < 0) { nfs_context_set_write_error(req->wb_context, status); - nfs_inode_remove_request(req); + if (req->wb_page) + nfs_inode_remove_request(req); dprintk_cont(", error = %d\n", status); goto next; } @@ -1793,7 +1794,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) * returned by the server against all stored verfs. */ if (!nfs_write_verifier_cmp(&req->wb_verf, &data->verf.verifier)) { /* We have a match */ - nfs_inode_remove_request(req); + if (req->wb_page) + nfs_inode_remove_request(req); dprintk_cont(" OK\n"); goto next; } From eed50879d64ab1b9f76445dbab822e43a098b309 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 11 Mar 2017 15:52:47 -0500 Subject: [PATCH 4/9] xprtrdma: Squelch kbuild sparse complaint New complaint from kbuild for 4.9.y: net/sunrpc/xprtrdma/verbs.c:489:19: sparse: incompatible types in comparison expression (different type sizes) verbs.c: 489 max_sge = min(ia->ri_device->attrs.max_sge, RPCRDMA_MAX_SEND_SGES); I can't reproduce this running sparse here. Likewise, "make W=1 net/sunrpc/xprtrdma/verbs.o" never indicated any issue. A little poking suggests that because the range of its values is small, gcc can make the actual width of RPCRDMA_MAX_SEND_SGES smaller than the width of an unsigned integer. Fixes: 16f906d66cd7 ("xprtrdma: Reduce required number of send SGEs") Signed-off-by: Chuck Lever Cc: stable@kernel.org Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/verbs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 81cd31acf690..3b332b395045 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -503,7 +503,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, struct ib_cq *sendcq, *recvcq; int rc; - max_sge = min(ia->ri_device->attrs.max_sge, RPCRDMA_MAX_SEND_SGES); + max_sge = min_t(unsigned int, ia->ri_device->attrs.max_sge, + RPCRDMA_MAX_SEND_SGES); if (max_sge < RPCRDMA_MIN_SEND_SGES) { pr_warn("rpcrdma: HCA provides only %d send SGEs\n", max_sge); return -ENOMEM; From 05fae7bbc237bc7de0ee9c3dcf85b2572a80e3b5 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Fri, 10 Mar 2017 10:48:13 +0800 Subject: [PATCH 5/9] nfs: make nfs4_cb_sv_ops static Fixes the following sparse warning: fs/nfs/callback.c:235:21: warning: symbol 'nfs4_cb_sv_ops' was not declared. Should it be static? Signed-off-by: Jason Yan Signed-off-by: Anna Schumaker --- fs/nfs/callback.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 484bebc20bca..5c8a096d763e 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -231,12 +231,12 @@ static struct svc_serv_ops nfs41_cb_sv_ops = { .svo_module = THIS_MODULE, }; -struct svc_serv_ops *nfs4_cb_sv_ops[] = { +static struct svc_serv_ops *nfs4_cb_sv_ops[] = { [0] = &nfs40_cb_sv_ops, [1] = &nfs41_cb_sv_ops, }; #else -struct svc_serv_ops *nfs4_cb_sv_ops[] = { +static struct svc_serv_ops *nfs4_cb_sv_ops[] = { [0] = &nfs40_cb_sv_ops, [1] = NULL, }; From 63513232f8cd219dcaa5eafae028740ed3067d83 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 13 Mar 2017 10:36:19 -0400 Subject: [PATCH 6/9] NFS prevent double free in async nfs4_exchange_id Since rpc_task is async, the release function should be called which will free the impl_id, scope, and owner. Trond pointed at 2 more problems: -- use of client pointer after free in the nfs4_exchangeid_release() function -- cl_count mismatch if rpc_run_task() isn't run Fixes: 8d89bd70bc9 ("NFS setup async exchange_id") Signed-off-by: Olga Kornievskaia Cc: stable@vger.kernel.org # 4.9 Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c1f5369cd339..c780d98035cc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7425,11 +7425,11 @@ static void nfs4_exchange_id_release(void *data) struct nfs41_exchange_id_data *cdata = (struct nfs41_exchange_id_data *)data; - nfs_put_client(cdata->args.client); if (cdata->xprt) { xprt_put(cdata->xprt); rpc_clnt_xprt_switch_put(cdata->args.client->cl_rpcclient); } + nfs_put_client(cdata->args.client); kfree(cdata->res.impl_id); kfree(cdata->res.server_scope); kfree(cdata->res.server_owner); @@ -7536,10 +7536,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, task_setup_data.callback_data = calldata; task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) { - status = PTR_ERR(task); - goto out_impl_id; - } + if (IS_ERR(task)) + return PTR_ERR(task); if (!xprt) { status = rpc_wait_for_completion_task(task); @@ -7567,6 +7565,7 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, kfree(calldata->res.server_owner); out_calldata: kfree(calldata); + nfs_put_client(clp); goto out; } From 033853325fe3bdc70819a8b97915bd3bca41d3af Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 8 Mar 2017 14:39:15 -0500 Subject: [PATCH 7/9] NFSv4.1 respect server's max size in CREATE_SESSION Currently client doesn't respect max sizes server returns in CREATE_SESSION. nfs4_session_set_rwsize() gets called and server->rsize, server->wsize are 0 so they never get set to the sizes returned by the server. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- fs/nfs/nfs4client.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 5ae9d64ea08b..8346ccbf2d52 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1023,9 +1023,9 @@ static void nfs4_session_set_rwsize(struct nfs_server *server) server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead; server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead; - if (server->rsize > server_resp_sz) + if (!server->rsize || server->rsize > server_resp_sz) server->rsize = server_resp_sz; - if (server->wsize > server_rqst_sz) + if (!server->wsize || server->wsize > server_rqst_sz) server->wsize = server_rqst_sz; #endif /* CONFIG_NFS_V4_1 */ } From a33e4b036d4612f62220f37a9fa29d273b6fd0ca Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 9 Mar 2017 12:56:48 -0500 Subject: [PATCH 8/9] pNFS: return status from nfs4_pnfs_ds_connect The nfs4_pnfs_ds_connect path can call rpc_create which can fail or it can wait on another context to reach the same failure. This checks that the rpc_create succeeded and returns the error to the caller. When an error is returned, both the files and flexfiles layouts will return NULL from _prepare_ds(). The flexfiles layout will also return the layout with the error NFS4ERR_NXIO. Signed-off-by: Weston Andros Adamson Signed-off-by: Anna Schumaker --- fs/nfs/client.c | 25 ++++++++++++++++++++++- fs/nfs/filelayout/filelayoutdev.c | 7 ++++++- fs/nfs/flexfilelayout/flexfilelayoutdev.c | 3 ++- fs/nfs/internal.h | 2 ++ fs/nfs/pnfs.h | 2 +- fs/nfs/pnfs_nfs.c | 15 ++++++++++++-- 6 files changed, 48 insertions(+), 6 deletions(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 91a8d610ba0f..390ada8741bc 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -325,10 +325,33 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat return NULL; } -static bool nfs_client_init_is_complete(const struct nfs_client *clp) +/* + * Return true if @clp is done initializing, false if still working on it. + * + * Use nfs_client_init_status to check if it was successful. + */ +bool nfs_client_init_is_complete(const struct nfs_client *clp) { return clp->cl_cons_state <= NFS_CS_READY; } +EXPORT_SYMBOL_GPL(nfs_client_init_is_complete); + +/* + * Return 0 if @clp was successfully initialized, -errno otherwise. + * + * This must be called *after* nfs_client_init_is_complete() returns true, + * otherwise it will pop WARN_ON_ONCE and return -EINVAL + */ +int nfs_client_init_status(const struct nfs_client *clp) +{ + /* called without checking nfs_client_init_is_complete */ + if (clp->cl_cons_state > NFS_CS_READY) { + WARN_ON_ONCE(1); + return -EINVAL; + } + return clp->cl_cons_state; +} +EXPORT_SYMBOL_GPL(nfs_client_init_status); int nfs_wait_client_init_complete(const struct nfs_client *clp) { diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index f956ca20a8a3..188120626179 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -266,6 +266,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); struct nfs4_pnfs_ds *ret = ds; struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode); + int status; if (ds == NULL) { printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", @@ -277,9 +278,13 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) if (ds->ds_clp) goto out_test_devid; - nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, + status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, dataserver_retrans, 4, s->nfs_client->cl_minorversion); + if (status) { + ret = NULL; + goto out; + } out_test_devid: if (ret->ds_clp == NULL || diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index e5a6f248697b..544e7725e679 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -384,6 +384,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, struct inode *ino = lseg->pls_layout->plh_inode; struct nfs_server *s = NFS_SERVER(ino); unsigned int max_payload; + int status; if (!ff_layout_mirror_valid(lseg, mirror, true)) { pr_err_ratelimited("NFS: %s: No data server for offset index %d\n", @@ -404,7 +405,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, /* FIXME: For now we assume the server sent only one version of NFS * to use for the DS. */ - nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, + status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, dataserver_retrans, mirror->mirror_ds->ds_versions[0].version, mirror->mirror_ds->ds_versions[0].minor_version); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 09ca5095c04e..7b38fedb7e03 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -186,6 +186,8 @@ extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); +extern bool nfs_client_init_is_complete(const struct nfs_client *clp); +extern int nfs_client_init_status(const struct nfs_client *clp); extern int nfs_wait_client_init_complete(const struct nfs_client *clp); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 63f77b49a586..590e1e35781f 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -367,7 +367,7 @@ void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds); struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags); void nfs4_pnfs_v3_ds_connect_unload(void); -void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, +int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_deviceid_node *devid, unsigned int timeo, unsigned int retrans, u32 version, u32 minor_version); struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net, diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 9414b492439f..a7691b927af6 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -745,9 +745,9 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, /* * Create an rpc connection to the nfs4_pnfs_ds data server. * Currently only supports IPv4 and IPv6 addresses. - * If connection fails, make devid unavailable. + * If connection fails, make devid unavailable and return a -errno. */ -void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, +int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_deviceid_node *devid, unsigned int timeo, unsigned int retrans, u32 version, u32 minor_version) { @@ -772,6 +772,17 @@ void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, } else { nfs4_wait_ds_connect(ds); } + + /* + * At this point the ds->ds_clp should be ready, but it might have + * hit an error. + */ + if (!ds->ds_clp || !nfs_client_init_is_complete(ds->ds_clp)) { + WARN_ON_ONCE(1); + return -EINVAL; + } + + return nfs_client_init_status(ds->ds_clp); } EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect); From da066f3f039eba3e72e97b2ccad0dd8b45ba84bd Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 9 Mar 2017 12:56:49 -0500 Subject: [PATCH 9/9] pNFS/flexfiles: never nfs4_mark_deviceid_unavailable The flexfiles layout should never mark a device unavailable. Move nfs4_mark_deviceid_unavailable out of nfs4_pnfs_ds_connect and call directly from files layout where it's still needed. The flexfiles driver still handles marked devices in error paths, but will now print a rate limited warning. Signed-off-by: Weston Andros Adamson Signed-off-by: Anna Schumaker --- fs/nfs/filelayout/filelayoutdev.c | 1 + fs/nfs/flexfilelayout/flexfilelayout.h | 14 ++++++++++++- fs/nfs/flexfilelayout/flexfilelayoutdev.c | 2 +- fs/nfs/pnfs_nfs.c | 24 +++++++++++++++-------- 4 files changed, 31 insertions(+), 10 deletions(-) diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 188120626179..d913e818858f 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -282,6 +282,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) dataserver_retrans, 4, s->nfs_client->cl_minorversion); if (status) { + nfs4_mark_deviceid_unavailable(devid); ret = NULL; goto out; } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h index f4f39b0ab09b..98b34c9b0564 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.h +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -175,7 +175,19 @@ ff_layout_no_read_on_rw(struct pnfs_layout_segment *lseg) static inline bool ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node) { - return nfs4_test_deviceid_unavailable(node); + /* + * Flexfiles should never mark a DS unavailable, but if it does + * print a (ratelimited) warning as this can affect performance. + */ + if (nfs4_test_deviceid_unavailable(node)) { + u32 *p = (u32 *)node->deviceid.data; + + pr_warn_ratelimited("NFS: flexfiles layout referencing an " + "unavailable device [%x%x%x%x]\n", + p[0], p[1], p[2], p[3]); + return true; + } + return false; } static inline int diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 544e7725e679..85fde93dff77 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -421,11 +421,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, mirror->mirror_ds->ds_versions[0].wsize = max_payload; goto out; } +out_fail: ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), mirror, lseg->pls_range.offset, lseg->pls_range.length, NFS4ERR_NXIO, OP_ILLEGAL, GFP_NOIO); -out_fail: if (fail_return || !ff_layout_has_available_ds(lseg)) pnfs_error_mark_layout_for_return(ino, lseg); ds = NULL; diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index a7691b927af6..7250b95549ec 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -751,9 +751,11 @@ int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_deviceid_node *devid, unsigned int timeo, unsigned int retrans, u32 version, u32 minor_version) { - if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { - int err = 0; + int err; +again: + err = 0; + if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { if (version == 3) { err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo, retrans); @@ -766,23 +768,29 @@ int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, err = -EPROTONOSUPPORT; } - if (err) - nfs4_mark_deviceid_unavailable(devid); nfs4_clear_ds_conn_bit(ds); } else { nfs4_wait_ds_connect(ds); + + /* what was waited on didn't connect AND didn't mark unavail */ + if (!ds->ds_clp && !nfs4_test_deviceid_unavailable(devid)) + goto again; } /* * At this point the ds->ds_clp should be ready, but it might have * hit an error. */ - if (!ds->ds_clp || !nfs_client_init_is_complete(ds->ds_clp)) { - WARN_ON_ONCE(1); - return -EINVAL; + if (!err) { + if (!ds->ds_clp || !nfs_client_init_is_complete(ds->ds_clp)) { + WARN_ON_ONCE(ds->ds_clp || + !nfs4_test_deviceid_unavailable(devid)); + return -EINVAL; + } + err = nfs_client_init_status(ds->ds_clp); } - return nfs_client_init_status(ds->ds_clp); + return err; } EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect);