From: Greg Kroah-Hartman Date: Wed, 4 Jun 2014 05:42:53 +0000 (-0700) Subject: 3.10-stable patches X-Git-Tag: v3.14.6~52 X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=7d60808f484f1daea022bc317f146fc9415fd343;p=thirdparty%2Fkernel%2Fstable-queue.git 3.10-stable patches added patches: bus-mvebu-mbus-allow-several-windows-with-the-same-target-attribute.patch nfsd-call-rpc_destroy_wait_queue-from-free_client.patch nfsd-call-set_acl-with-a-null-acl-structure-if-no-entries.patch nfsd-move-default-initialisers-from-create_client-to.patch nfsd4-remove-lockowner-when-removing-lock-stateid.patch nfsd4-warn-on-finding-lockowner-without-stateid-s.patch percpu-make-pcpu_alloc_chunk-use-pcpu_mem_free-instead-of-kfree.patch workqueue-fix-a-possible-race-condition-between-rescuer-and-pwq-release.patch workqueue-fix-bugs-in-wq_update_unbound_numa-failure-path.patch workqueue-make-rescuer_thread-empty-wq-maydays-list-before-exiting.patch --- diff --git a/queue-3.10/bus-mvebu-mbus-allow-several-windows-with-the-same-target-attribute.patch b/queue-3.10/bus-mvebu-mbus-allow-several-windows-with-the-same-target-attribute.patch new file mode 100644 index 00000000000..edb1e7eefb5 --- /dev/null +++ b/queue-3.10/bus-mvebu-mbus-allow-several-windows-with-the-same-target-attribute.patch @@ -0,0 +1,40 @@ +From b566e782be32145664d96ada3e389f17d32742e5 Mon Sep 17 00:00:00 2001 +From: Thomas Petazzoni +Date: Fri, 18 Apr 2014 14:19:52 +0200 +Subject: bus: mvebu-mbus: allow several windows with the same target/attribute + +From: Thomas Petazzoni + +commit b566e782be32145664d96ada3e389f17d32742e5 upstream. + +Having multiple windows with the same target and attribute is actually +legal, and can be useful for PCIe windows, when PCIe BARs have a size +that isn't a power of two, and we therefore need to create several +MBus windows to cover the PCIe BAR for a given PCIe interface. + +Fixes: fddddb52a6c4 ('bus: introduce an Marvell EBU MBus driver') +Signed-off-by: Thomas Petazzoni +Link: https://lkml.kernel.org/r/1397823593-1932-7-git-send-email-thomas.petazzoni@free-electrons.com +Tested-by: Neil Greatorex +Signed-off-by: Jason Cooper +Signed-off-by: Greg Kroah-Hartman + +--- + drivers/bus/mvebu-mbus.c | 6 ------ + 1 file changed, 6 deletions(-) + +--- a/drivers/bus/mvebu-mbus.c ++++ b/drivers/bus/mvebu-mbus.c +@@ -250,12 +250,6 @@ static int mvebu_mbus_window_conflicts(s + */ + if ((u64)base < wend && end > wbase) + return 0; +- +- /* +- * Check if target/attribute conflicts +- */ +- if (target == wtarget && attr == wattr) +- return 0; + } + + return 1; diff --git a/queue-3.10/nfsd-call-rpc_destroy_wait_queue-from-free_client.patch b/queue-3.10/nfsd-call-rpc_destroy_wait_queue-from-free_client.patch new file mode 100644 index 00000000000..bcdd61a05a9 --- /dev/null +++ b/queue-3.10/nfsd-call-rpc_destroy_wait_queue-from-free_client.patch @@ -0,0 +1,29 @@ +From 4cb57e3032d4e4bf5e97780e9907da7282b02b0c Mon Sep 17 00:00:00 2001 +From: Trond Myklebust +Date: Fri, 18 Apr 2014 14:43:57 -0400 +Subject: NFSd: call rpc_destroy_wait_queue() from free_client() + +From: Trond Myklebust + +commit 4cb57e3032d4e4bf5e97780e9907da7282b02b0c upstream. + +Mainly to ensure that we don't leave any hanging timers. + +Signed-off-by: Trond Myklebust +Signed-off-by: J. Bruce Fields +Signed-off-by: Greg Kroah-Hartman + +--- + fs/nfsd/nfs4state.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/fs/nfsd/nfs4state.c ++++ b/fs/nfsd/nfs4state.c +@@ -1110,6 +1110,7 @@ free_client(struct nfs4_client *clp) + WARN_ON_ONCE(atomic_read(&ses->se_ref)); + free_session(ses); + } ++ rpc_destroy_wait_queue(&clp->cl_cb_waitq); + free_svc_cred(&clp->cl_cred); + kfree(clp->cl_name.data); + idr_destroy(&clp->cl_stateids); diff --git a/queue-3.10/nfsd-call-set_acl-with-a-null-acl-structure-if-no-entries.patch b/queue-3.10/nfsd-call-set_acl-with-a-null-acl-structure-if-no-entries.patch new file mode 100644 index 00000000000..30b73e1e09a --- /dev/null +++ b/queue-3.10/nfsd-call-set_acl-with-a-null-acl-structure-if-no-entries.patch @@ -0,0 +1,140 @@ +From aa07c713ecfc0522916f3cd57ac628ea6127c0ec Mon Sep 17 00:00:00 2001 +From: Kinglong Mee +Date: Fri, 18 Apr 2014 20:49:04 +0800 +Subject: NFSD: Call ->set_acl with a NULL ACL structure if no entries + +From: Kinglong Mee + +commit aa07c713ecfc0522916f3cd57ac628ea6127c0ec upstream. + +After setting ACL for directory, I got two problems that caused +by the cached zero-length default posix acl. + +This patch make sure nfsd4_set_nfs4_acl calls ->set_acl +with a NULL ACL structure if there are no entries. + +Thanks for Christoph Hellwig's advice. + +First problem: +............ hang ........... + +Second problem: +[ 1610.167668] ------------[ cut here ]------------ +[ 1610.168320] kernel BUG at /root/nfs/linux/fs/nfsd/nfs4acl.c:239! +[ 1610.168320] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC +[ 1610.168320] Modules linked in: nfsv4(OE) nfs(OE) nfsd(OE) +rpcsec_gss_krb5 fscache ip6t_rpfilter ip6t_REJECT cfg80211 xt_conntrack +rfkill ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables +ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 +ip6table_mangle ip6table_security ip6table_raw ip6table_filter +ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 +nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw +auth_rpcgss nfs_acl snd_intel8x0 ppdev lockd snd_ac97_codec ac97_bus +snd_pcm snd_timer e1000 pcspkr parport_pc snd parport serio_raw joydev +i2c_piix4 sunrpc(OE) microcode soundcore i2c_core ata_generic pata_acpi +[last unloaded: nfsd] +[ 1610.168320] CPU: 0 PID: 27397 Comm: nfsd Tainted: G OE +3.15.0-rc1+ #15 +[ 1610.168320] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS +VirtualBox 12/01/2006 +[ 1610.168320] task: ffff88005ab653d0 ti: ffff88005a944000 task.ti: +ffff88005a944000 +[ 1610.168320] RIP: 0010:[] [] +_posix_to_nfsv4_one+0x3cd/0x3d0 [nfsd] +[ 1610.168320] RSP: 0018:ffff88005a945b00 EFLAGS: 00010293 +[ 1610.168320] RAX: 0000000000000001 RBX: ffff88006700bac0 RCX: +0000000000000000 +[ 1610.168320] RDX: 0000000000000000 RSI: ffff880067c83f00 RDI: +ffff880068233300 +[ 1610.168320] RBP: ffff88005a945b48 R08: ffffffff81c64830 R09: +0000000000000000 +[ 1610.168320] R10: ffff88004ea85be0 R11: 000000000000f475 R12: +ffff880068233300 +[ 1610.168320] R13: 0000000000000003 R14: 0000000000000002 R15: +ffff880068233300 +[ 1610.168320] FS: 0000000000000000(0000) GS:ffff880077800000(0000) +knlGS:0000000000000000 +[ 1610.168320] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b +[ 1610.168320] CR2: 00007f5bcbd3b0b9 CR3: 0000000001c0f000 CR4: +00000000000006f0 +[ 1610.168320] DR0: 0000000000000000 DR1: 0000000000000000 DR2: +0000000000000000 +[ 1610.168320] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: +0000000000000400 +[ 1610.168320] Stack: +[ 1610.168320] ffffffff00000000 0000000b67c83500 000000076700bac0 +0000000000000000 +[ 1610.168320] ffff88006700bac0 ffff880068233300 ffff88005a945c08 +0000000000000002 +[ 1610.168320] 0000000000000000 ffff88005a945b88 ffffffffa034e2d5 +000000065a945b68 +[ 1610.168320] Call Trace: +[ 1610.168320] [] nfsd4_get_nfs4_acl+0x95/0x150 [nfsd] +[ 1610.168320] [] nfsd4_encode_fattr+0x646/0x1e70 [nfsd] +[ 1610.168320] [] ? kmemleak_alloc+0x4e/0xb0 +[ 1610.168320] [] ? +nfsd_setuser_and_check_port+0x52/0x80 [nfsd] +[ 1610.168320] [] ? selinux_cred_prepare+0x1b/0x30 +[ 1610.168320] [] nfsd4_encode_getattr+0x5a/0x60 [nfsd] +[ 1610.168320] [] nfsd4_encode_operation+0x67/0x110 +[nfsd] +[ 1610.168320] [] nfsd4_proc_compound+0x21d/0x810 [nfsd] +[ 1610.168320] [] nfsd_dispatch+0xbb/0x200 [nfsd] +[ 1610.168320] [] svc_process_common+0x46d/0x6d0 [sunrpc] +[ 1610.168320] [] svc_process+0x103/0x170 [sunrpc] +[ 1610.168320] [] nfsd+0xbf/0x130 [nfsd] +[ 1610.168320] [] ? nfsd_destroy+0x80/0x80 [nfsd] +[ 1610.168320] [] kthread+0xd2/0xf0 +[ 1610.168320] [] ? insert_kthread_work+0x40/0x40 +[ 1610.168320] [] ret_from_fork+0x7c/0xb0 +[ 1610.168320] [] ? insert_kthread_work+0x40/0x40 +[ 1610.168320] Code: 78 02 e9 e7 fc ff ff 31 c0 31 d2 31 c9 66 89 45 ce +41 8b 04 24 66 89 55 d0 66 89 4d d2 48 8d 04 80 49 8d 5c 84 04 e9 37 fd +ff ff <0f> 0b 90 0f 1f 44 00 00 55 8b 56 08 c7 07 00 00 00 00 8b 46 0c +[ 1610.168320] RIP [] _posix_to_nfsv4_one+0x3cd/0x3d0 +[nfsd] +[ 1610.168320] RSP +[ 1610.257313] ---[ end trace 838254e3e352285b ]--- + +Signed-off-by: Kinglong Mee +Signed-off-by: J. Bruce Fields +Signed-off-by: Greg Kroah-Hartman + +--- + fs/nfsd/nfs4acl.c | 17 +++++++++-------- + 1 file changed, 9 insertions(+), 8 deletions(-) + +--- a/fs/nfsd/nfs4acl.c ++++ b/fs/nfsd/nfs4acl.c +@@ -385,8 +385,10 @@ sort_pacl(struct posix_acl *pacl) + * by uid/gid. */ + int i, j; + +- if (pacl->a_count <= 4) +- return; /* no users or groups */ ++ /* no users or groups */ ++ if (!pacl || pacl->a_count <= 4) ++ return; ++ + i = 1; + while (pacl->a_entries[i].e_tag == ACL_USER) + i++; +@@ -513,13 +515,12 @@ posix_state_to_acl(struct posix_acl_stat + + /* + * ACLs with no ACEs are treated differently in the inheritable +- * and effective cases: when there are no inheritable ACEs, we +- * set a zero-length default posix acl: ++ * and effective cases: when there are no inheritable ACEs, ++ * calls ->set_acl with a NULL ACL structure. + */ +- if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) { +- pacl = posix_acl_alloc(0, GFP_KERNEL); +- return pacl ? pacl : ERR_PTR(-ENOMEM); +- } ++ if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) ++ return NULL; ++ + /* + * When there are no effective ACEs, the following will end + * up setting a 3-element effective posix ACL with all diff --git a/queue-3.10/nfsd-move-default-initialisers-from-create_client-to.patch b/queue-3.10/nfsd-move-default-initialisers-from-create_client-to.patch new file mode 100644 index 00000000000..fb015eeffd3 --- /dev/null +++ b/queue-3.10/nfsd-move-default-initialisers-from-create_client-to.patch @@ -0,0 +1,72 @@ +From 5694c93e6c4954fa9424c215f75eeb919bddad64 Mon Sep 17 00:00:00 2001 +From: Trond Myklebust +Date: Fri, 18 Apr 2014 14:43:56 -0400 +Subject: NFSd: Move default initialisers from create_client() to + alloc_client() + +From: Trond Myklebust + +commit 5694c93e6c4954fa9424c215f75eeb919bddad64 upstream. + +Aside from making it clearer what is non-trivial in create_client(), it +also fixes a bug whereby we can call free_client() before idr_init() +has been called. + +Signed-off-by: Trond Myklebust +Signed-off-by: J. Bruce Fields +Signed-off-by: Greg Kroah-Hartman + +--- + fs/nfsd/nfs4state.c | 24 ++++++++++++------------ + 1 file changed, 12 insertions(+), 12 deletions(-) + +--- a/fs/nfsd/nfs4state.c ++++ b/fs/nfsd/nfs4state.c +@@ -1081,6 +1081,18 @@ static struct nfs4_client *alloc_client( + return NULL; + } + clp->cl_name.len = name.len; ++ INIT_LIST_HEAD(&clp->cl_sessions); ++ idr_init(&clp->cl_stateids); ++ atomic_set(&clp->cl_refcount, 0); ++ clp->cl_cb_state = NFSD4_CB_UNKNOWN; ++ INIT_LIST_HEAD(&clp->cl_idhash); ++ INIT_LIST_HEAD(&clp->cl_openowners); ++ INIT_LIST_HEAD(&clp->cl_delegations); ++ INIT_LIST_HEAD(&clp->cl_lru); ++ INIT_LIST_HEAD(&clp->cl_callbacks); ++ INIT_LIST_HEAD(&clp->cl_revoked); ++ spin_lock_init(&clp->cl_lock); ++ rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); + return clp; + } + +@@ -1315,7 +1327,6 @@ static struct nfs4_client *create_client + if (clp == NULL) + return NULL; + +- INIT_LIST_HEAD(&clp->cl_sessions); + ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred); + if (ret) { + spin_lock(&nn->client_lock); +@@ -1323,20 +1334,9 @@ static struct nfs4_client *create_client + spin_unlock(&nn->client_lock); + return NULL; + } +- idr_init(&clp->cl_stateids); +- atomic_set(&clp->cl_refcount, 0); +- clp->cl_cb_state = NFSD4_CB_UNKNOWN; +- INIT_LIST_HEAD(&clp->cl_idhash); +- INIT_LIST_HEAD(&clp->cl_openowners); +- INIT_LIST_HEAD(&clp->cl_delegations); +- INIT_LIST_HEAD(&clp->cl_lru); +- INIT_LIST_HEAD(&clp->cl_callbacks); +- INIT_LIST_HEAD(&clp->cl_revoked); +- spin_lock_init(&clp->cl_lock); + nfsd4_init_callback(&clp->cl_cb_null); + clp->cl_time = get_seconds(); + clear_bit(0, &clp->cl_cb_slot_busy); +- rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); + copy_verf(clp, verf); + rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa); + gen_confirm(clp); diff --git a/queue-3.10/nfsd4-remove-lockowner-when-removing-lock-stateid.patch b/queue-3.10/nfsd4-remove-lockowner-when-removing-lock-stateid.patch new file mode 100644 index 00000000000..df4825c10e4 --- /dev/null +++ b/queue-3.10/nfsd4-remove-lockowner-when-removing-lock-stateid.patch @@ -0,0 +1,48 @@ +From a1b8ff4c97b4375d21b6d6c45d75877303f61b3b Mon Sep 17 00:00:00 2001 +From: "J. Bruce Fields" +Date: Tue, 20 May 2014 15:55:21 -0400 +Subject: nfsd4: remove lockowner when removing lock stateid + +From: "J. Bruce Fields" + +commit a1b8ff4c97b4375d21b6d6c45d75877303f61b3b upstream. + +The nfsv4 state code has always assumed a one-to-one correspondance +between lock stateid's and lockowners even if it appears not to in some +places. + +We may actually change that, but for now when FREE_STATEID releases a +lock stateid it also needs to release the parent lockowner. + +Symptoms were a subsequent LOCK crashing in find_lockowner_str when it +calls same_lockowner_ino on a lockowner that unexpectedly has an empty +so_stateids list. + +Signed-off-by: J. Bruce Fields +Signed-off-by: Greg Kroah-Hartman + +--- + fs/nfsd/nfs4state.c | 11 +++++++++-- + 1 file changed, 9 insertions(+), 2 deletions(-) + +--- a/fs/nfsd/nfs4state.c ++++ b/fs/nfsd/nfs4state.c +@@ -3599,9 +3599,16 @@ out: + static __be32 + nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp) + { +- if (check_for_locks(stp->st_file, lockowner(stp->st_stateowner))) ++ struct nfs4_lockowner *lo = lockowner(stp->st_stateowner); ++ ++ if (check_for_locks(stp->st_file, lo)) + return nfserr_locks_held; +- release_lock_stateid(stp); ++ /* ++ * Currently there's a 1-1 lock stateid<->lockowner ++ * correspondance, and we have to delete the lockowner when we ++ * delete the lock stateid: ++ */ ++ unhash_lockowner(lo); + return nfs_ok; + } + diff --git a/queue-3.10/nfsd4-warn-on-finding-lockowner-without-stateid-s.patch b/queue-3.10/nfsd4-warn-on-finding-lockowner-without-stateid-s.patch new file mode 100644 index 00000000000..7114c24118d --- /dev/null +++ b/queue-3.10/nfsd4-warn-on-finding-lockowner-without-stateid-s.patch @@ -0,0 +1,32 @@ +From 27b11428b7de097c42f205beabb1764f4365443b Mon Sep 17 00:00:00 2001 +From: "J. Bruce Fields" +Date: Thu, 8 May 2014 11:19:41 -0400 +Subject: nfsd4: warn on finding lockowner without stateid's + +From: "J. Bruce Fields" + +commit 27b11428b7de097c42f205beabb1764f4365443b upstream. + +The current code assumes a one-to-one lockowner<->lock stateid +correspondance. + +Signed-off-by: J. Bruce Fields +Signed-off-by: Greg Kroah-Hartman + +--- + fs/nfsd/nfs4state.c | 4 ++++ + 1 file changed, 4 insertions(+) + +--- a/fs/nfsd/nfs4state.c ++++ b/fs/nfsd/nfs4state.c +@@ -4045,6 +4045,10 @@ static bool same_lockowner_ino(struct nf + + if (!same_owner_str(&lo->lo_owner, owner, clid)) + return false; ++ if (list_empty(&lo->lo_owner.so_stateids)) { ++ WARN_ON_ONCE(1); ++ return false; ++ } + lst = list_first_entry(&lo->lo_owner.so_stateids, + struct nfs4_ol_stateid, st_perstateowner); + return lst->st_file->fi_inode == inode; diff --git a/queue-3.10/percpu-make-pcpu_alloc_chunk-use-pcpu_mem_free-instead-of-kfree.patch b/queue-3.10/percpu-make-pcpu_alloc_chunk-use-pcpu_mem_free-instead-of-kfree.patch new file mode 100644 index 00000000000..1a37854fe4c --- /dev/null +++ b/queue-3.10/percpu-make-pcpu_alloc_chunk-use-pcpu_mem_free-instead-of-kfree.patch @@ -0,0 +1,42 @@ +From 5a838c3b60e3a36ade764cf7751b8f17d7c9c2da Mon Sep 17 00:00:00 2001 +From: Jianyu Zhan +Date: Mon, 14 Apr 2014 13:47:40 +0800 +Subject: percpu: make pcpu_alloc_chunk() use pcpu_mem_free() instead of kfree() + +From: Jianyu Zhan + +commit 5a838c3b60e3a36ade764cf7751b8f17d7c9c2da upstream. + +pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + + BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long) + +It hardly could be ever bigger than PAGE_SIZE even for large-scale machine, +but for consistency with its couterpart pcpu_mem_zalloc(), +use pcpu_mem_free() instead. + +Commit b4916cb17c26 ("percpu: make pcpu_free_chunk() use +pcpu_mem_free() instead of kfree()") addressed this problem, but +missed this one. + +tj: commit message updated + +Signed-off-by: Jianyu Zhan +Signed-off-by: Tejun Heo +Fixes: 099a19d91ca4 ("percpu: allow limited allocation before slab is online) +Signed-off-by: Greg Kroah-Hartman + +--- + mm/percpu.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/mm/percpu.c ++++ b/mm/percpu.c +@@ -612,7 +612,7 @@ static struct pcpu_chunk *pcpu_alloc_chu + chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC * + sizeof(chunk->map[0])); + if (!chunk->map) { +- kfree(chunk); ++ pcpu_mem_free(chunk, pcpu_chunk_struct_size); + return NULL; + } + diff --git a/queue-3.10/series b/queue-3.10/series index 72d55179afd..32746d1fb50 100644 --- a/queue-3.10/series +++ b/queue-3.10/series @@ -66,3 +66,13 @@ input-elantech-fix-touchpad-initialization-on-gigabyte-u2442.patch input-synaptics-add-min-max-quirk-for-the-thinkpad-w540.patch input-synaptics-t540p-unify-with-other-len0034-models.patch alsa-hda-fix-onboard-audio-on-intel-h97-z97-chipsets.patch +nfsd-move-default-initialisers-from-create_client-to.patch +nfsd-call-rpc_destroy_wait_queue-from-free_client.patch +nfsd-call-set_acl-with-a-null-acl-structure-if-no-entries.patch +nfsd4-warn-on-finding-lockowner-without-stateid-s.patch +nfsd4-remove-lockowner-when-removing-lock-stateid.patch +workqueue-fix-bugs-in-wq_update_unbound_numa-failure-path.patch +workqueue-fix-a-possible-race-condition-between-rescuer-and-pwq-release.patch +workqueue-make-rescuer_thread-empty-wq-maydays-list-before-exiting.patch +bus-mvebu-mbus-allow-several-windows-with-the-same-target-attribute.patch +percpu-make-pcpu_alloc_chunk-use-pcpu_mem_free-instead-of-kfree.patch diff --git a/queue-3.10/workqueue-fix-a-possible-race-condition-between-rescuer-and-pwq-release.patch b/queue-3.10/workqueue-fix-a-possible-race-condition-between-rescuer-and-pwq-release.patch new file mode 100644 index 00000000000..7624675ee61 --- /dev/null +++ b/queue-3.10/workqueue-fix-a-possible-race-condition-between-rescuer-and-pwq-release.patch @@ -0,0 +1,60 @@ +From 77668c8b559e4fe2acf2a0749c7c83cde49a5025 Mon Sep 17 00:00:00 2001 +From: Lai Jiangshan +Date: Fri, 18 Apr 2014 11:04:16 -0400 +Subject: workqueue: fix a possible race condition between rescuer and pwq-release + +From: Lai Jiangshan + +commit 77668c8b559e4fe2acf2a0749c7c83cde49a5025 upstream. + +There is a race condition between rescuer_thread() and +pwq_unbound_release_workfn(). + +Even after a pwq is scheduled for rescue, the associated work items +may be consumed by any worker. If all of them are consumed before the +rescuer gets to them and the pwq's base ref was put due to attribute +change, the pwq may be released while still being linked on +@wq->maydays list making the rescuer dereference already freed pwq +later. + +Make send_mayday() pin the target pwq until the rescuer is done with +it. + +tj: Updated comment and patch description. + +Signed-off-by: Lai Jiangshan +Signed-off-by: Tejun Heo +Signed-off-by: Greg Kroah-Hartman + +--- + kernel/workqueue.c | 12 ++++++++++++ + 1 file changed, 12 insertions(+) + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -1881,6 +1881,12 @@ static void send_mayday(struct work_stru + + /* mayday mayday mayday */ + if (list_empty(&pwq->mayday_node)) { ++ /* ++ * If @pwq is for an unbound wq, its base ref may be put at ++ * any time due to an attribute change. Pin @pwq until the ++ * rescuer is done with it. ++ */ ++ get_pwq(pwq); + list_add_tail(&pwq->mayday_node, &wq->maydays); + wake_up_process(wq->rescuer->task); + } +@@ -2403,6 +2409,12 @@ repeat: + process_scheduled_works(rescuer); + + /* ++ * Put the reference grabbed by send_mayday(). @pool won't ++ * go away while we're holding its lock. ++ */ ++ put_pwq(pwq); ++ ++ /* + * Leave this pool. If keep_working() is %true, notify a + * regular worker; otherwise, we end up with 0 concurrency + * and stalling the execution. diff --git a/queue-3.10/workqueue-fix-bugs-in-wq_update_unbound_numa-failure-path.patch b/queue-3.10/workqueue-fix-bugs-in-wq_update_unbound_numa-failure-path.patch new file mode 100644 index 00000000000..5a3251a168a --- /dev/null +++ b/queue-3.10/workqueue-fix-bugs-in-wq_update_unbound_numa-failure-path.patch @@ -0,0 +1,43 @@ +From 77f300b198f93328c26191b52655ce1b62e202cf Mon Sep 17 00:00:00 2001 +From: Daeseok Youn +Date: Wed, 16 Apr 2014 14:32:29 +0900 +Subject: workqueue: fix bugs in wq_update_unbound_numa() failure path + +From: Daeseok Youn + +commit 77f300b198f93328c26191b52655ce1b62e202cf upstream. + +wq_update_unbound_numa() failure path has the following two bugs. + +- alloc_unbound_pwq() is called without holding wq->mutex; however, if + the allocation fails, it jumps to out_unlock which tries to unlock + wq->mutex. + +- The function should switch to dfl_pwq on failure but didn't do so + after alloc_unbound_pwq() failure. + +Fix it by regrabbing wq->mutex and jumping to use_dfl_pwq on +alloc_unbound_pwq() failure. + +Signed-off-by: Daeseok Youn +Acked-by: Lai Jiangshan +Signed-off-by: Tejun Heo +Fixes: 4c16bd327c74 ("workqueue: implement NUMA affinity for unbound workqueues") +Signed-off-by: Greg Kroah-Hartman + +--- + kernel/workqueue.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -4043,7 +4043,8 @@ static void wq_update_unbound_numa(struc + if (!pwq) { + pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n", + wq->name); +- goto out_unlock; ++ mutex_lock(&wq->mutex); ++ goto use_dfl_pwq; + } + + /* diff --git a/queue-3.10/workqueue-make-rescuer_thread-empty-wq-maydays-list-before-exiting.patch b/queue-3.10/workqueue-make-rescuer_thread-empty-wq-maydays-list-before-exiting.patch new file mode 100644 index 00000000000..e8570ff8483 --- /dev/null +++ b/queue-3.10/workqueue-make-rescuer_thread-empty-wq-maydays-list-before-exiting.patch @@ -0,0 +1,78 @@ +From 4d595b866d2c653dc90a492b9973a834eabfa354 Mon Sep 17 00:00:00 2001 +From: Lai Jiangshan +Date: Fri, 18 Apr 2014 11:04:16 -0400 +Subject: workqueue: make rescuer_thread() empty wq->maydays list before exiting + +From: Lai Jiangshan + +commit 4d595b866d2c653dc90a492b9973a834eabfa354 upstream. + +After a @pwq is scheduled for emergency execution, other workers may +consume the affectd work items before the rescuer gets to them. This +means that a workqueue many have pwqs queued on @wq->maydays list +while not having any work item pending or in-flight. If +destroy_workqueue() executes in such condition, the rescuer may exit +without emptying @wq->maydays. + +This currently doesn't cause any actual harm. destroy_workqueue() can +safely destroy all the involved data structures whether @wq->maydays +is populated or not as nobody access the list once the rescuer exits. + +However, this is nasty and makes future development difficult. Let's +update rescuer_thread() so that it empties @wq->maydays after seeing +should_stop to guarantee that the list is empty on rescuer exit. + +tj: Updated comment and patch description. + +Signed-off-by: Lai Jiangshan +Signed-off-by: Tejun Heo +Signed-off-by: Greg Kroah-Hartman + +--- + kernel/workqueue.c | 21 ++++++++++++++++----- + 1 file changed, 16 insertions(+), 5 deletions(-) + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -2362,6 +2362,7 @@ static int rescuer_thread(void *__rescue + struct worker *rescuer = __rescuer; + struct workqueue_struct *wq = rescuer->rescue_wq; + struct list_head *scheduled = &rescuer->scheduled; ++ bool should_stop; + + set_user_nice(current, RESCUER_NICE_LEVEL); + +@@ -2373,11 +2374,15 @@ static int rescuer_thread(void *__rescue + repeat: + set_current_state(TASK_INTERRUPTIBLE); + +- if (kthread_should_stop()) { +- __set_current_state(TASK_RUNNING); +- rescuer->task->flags &= ~PF_WQ_WORKER; +- return 0; +- } ++ /* ++ * By the time the rescuer is requested to stop, the workqueue ++ * shouldn't have any work pending, but @wq->maydays may still have ++ * pwq(s) queued. This can happen by non-rescuer workers consuming ++ * all the work items before the rescuer got to them. Go through ++ * @wq->maydays processing before acting on should_stop so that the ++ * list is always empty on exit. ++ */ ++ should_stop = kthread_should_stop(); + + /* see whether any pwq is asking for help */ + spin_lock_irq(&wq_mayday_lock); +@@ -2429,6 +2434,12 @@ repeat: + + spin_unlock_irq(&wq_mayday_lock); + ++ if (should_stop) { ++ __set_current_state(TASK_RUNNING); ++ rescuer->task->flags &= ~PF_WQ_WORKER; ++ return 0; ++ } ++ + /* rescuers should never participate in concurrency management */ + WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); + schedule();