From e6f0c6e6170fec175fe676495f29029aecdf486c Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Mon, 19 Sep 2016 14:43:55 -0700 Subject: ocfs2/dlm: fix race between convert and migration Commit ac7cf246dfdb ("ocfs2/dlm: fix race between convert and recovery") checks if lockres master has changed to identify whether new master has finished recovery or not. This will introduce a race that right after old master does umount ( means master will change), a new convert request comes. In this case, it will reset lockres state to DLM_RECOVERING and then retry convert, and then fail with lockres->l_action being set to OCFS2_AST_INVALID, which will cause inconsistent lock level between ocfs2 and dlm, and then finally BUG. Since dlm recovery will clear lock->convert_pending in dlm_move_lockres_to_recovery_list, we can use it to correctly identify the race case between convert and recovery. So fix it. Fixes: ac7cf246dfdb ("ocfs2/dlm: fix race between convert and recovery") Link: http://lkml.kernel.org/r/57CE1569.8010704@huawei.com Signed-off-by: Joseph Qi Signed-off-by: Jun Piao Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlm/dlmconvert.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index cdeafb4e7ed6..0bb128659d4b 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -268,7 +268,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, struct dlm_lock *lock, int flags, int type) { enum dlm_status status; - u8 old_owner = res->owner; mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type, lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS); @@ -335,7 +334,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); res->state &= ~DLM_LOCK_RES_IN_PROGRESS; - lock->convert_pending = 0; /* if it failed, move it back to granted queue. * if master returns DLM_NORMAL and then down before sending ast, * it may have already been moved to granted queue, reset to @@ -344,12 +342,14 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, if (status != DLM_NOTQUEUED) dlm_error(status); dlm_revert_pending_convert(res, lock); - } else if ((res->state & DLM_LOCK_RES_RECOVERING) || - (old_owner != res->owner)) { - mlog(0, "res %.*s is in recovering or has been recovered.\n", - res->lockname.len, res->lockname.name); + } else if (!lock->convert_pending) { + mlog(0, "%s: res %.*s, owner died and lock has been moved back " + "to granted list, retry convert.\n", + dlm->name, res->lockname.len, res->lockname.name); status = DLM_RECOVERING; } + + lock->convert_pending = 0; bail: spin_unlock(&res->spinlock); -- cgit 1.4.1 From 7cbdb4a286a60c5d519cb9223fe2134d26870d39 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Mon, 19 Sep 2016 14:44:12 -0700 Subject: autofs: use dentry flags to block walks during expire Somewhere along the way the autofs expire operation has changed to hold a spin lock over expired dentry selection. The autofs indirect mount expired dentry selection is complicated and quite lengthy so it isn't appropriate to hold a spin lock over the operation. Commit 47be61845c77 ("fs/dcache.c: avoid soft-lockup in dput()") added a might_sleep() to dput() causing a WARN_ONCE() about this usage to be issued. But the spin lock doesn't need to be held over this check, the autofs dentry info. flags are enough to block walks into dentrys during the expire. I've left the direct mount expire as it is (for now) because it is much simpler and quicker than the indirect mount expire and adding spin lock release and re-aquires would do nothing more than add overhead. Fixes: 47be61845c77 ("fs/dcache.c: avoid soft-lockup in dput()") Link: http://lkml.kernel.org/r/20160912014017.1773.73060.stgit@pluto.themaw.net Signed-off-by: Ian Kent Reported-by: Takashi Iwai Tested-by: Takashi Iwai Cc: Takashi Iwai Cc: NeilBrown Cc: Al Viro Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs4/expire.c | 55 ++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 42 insertions(+), 13 deletions(-) (limited to 'fs') diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index b493909e7492..d8e6d421c27f 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -417,6 +417,7 @@ static struct dentry *should_expire(struct dentry *dentry, } return NULL; } + /* * Find an eligible tree to time-out * A tree is eligible if :- @@ -432,6 +433,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, struct dentry *root = sb->s_root; struct dentry *dentry; struct dentry *expired; + struct dentry *found; struct autofs_info *ino; if (!root) @@ -442,31 +444,46 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, dentry = NULL; while ((dentry = get_next_positive_subdir(dentry, root))) { + int flags = how; + spin_lock(&sbi->fs_lock); ino = autofs4_dentry_ino(dentry); - if (ino->flags & AUTOFS_INF_WANT_EXPIRE) - expired = NULL; - else - expired = should_expire(dentry, mnt, timeout, how); - if (!expired) { + if (ino->flags & AUTOFS_INF_WANT_EXPIRE) { spin_unlock(&sbi->fs_lock); continue; } + spin_unlock(&sbi->fs_lock); + + expired = should_expire(dentry, mnt, timeout, flags); + if (!expired) + continue; + + spin_lock(&sbi->fs_lock); ino = autofs4_dentry_ino(expired); ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); - spin_lock(&sbi->fs_lock); - if (should_expire(expired, mnt, timeout, how)) { - if (expired != dentry) - dput(dentry); - goto found; - } + /* Make sure a reference is not taken on found if + * things have changed. + */ + flags &= ~AUTOFS_EXP_LEAVES; + found = should_expire(expired, mnt, timeout, how); + if (!found || found != expired) + /* Something has changed, continue */ + goto next; + + if (expired != dentry) + dput(dentry); + + spin_lock(&sbi->fs_lock); + goto found; +next: + spin_lock(&sbi->fs_lock); ino->flags &= ~AUTOFS_INF_WANT_EXPIRE; + spin_unlock(&sbi->fs_lock); if (expired != dentry) dput(expired); - spin_unlock(&sbi->fs_lock); } return NULL; @@ -483,6 +500,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk) struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); struct autofs_info *ino = autofs4_dentry_ino(dentry); int status; + int state; /* Block on any pending expire */ if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE)) @@ -490,8 +508,19 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk) if (rcu_walk) return -ECHILD; +retry: spin_lock(&sbi->fs_lock); - if (ino->flags & AUTOFS_INF_EXPIRING) { + state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING); + if (state == AUTOFS_INF_WANT_EXPIRE) { + spin_unlock(&sbi->fs_lock); + /* + * Possibly being selected for expire, wait until + * it's selected or not. + */ + schedule_timeout_uninterruptible(HZ/10); + goto retry; + } + if (state & AUTOFS_INF_EXPIRING) { spin_unlock(&sbi->fs_lock); pr_debug("waiting for expire %p name=%pd\n", dentry, dentry); -- cgit 1.4.1 From 31b4beb473e3bdee1bf79db849502dcb24b5c202 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Mon, 19 Sep 2016 14:44:18 -0700 Subject: ipc/shm: fix crash if CONFIG_SHMEM is not set Commit c01d5b300774 ("shmem: get_unmapped_area align huge page") makes use of shm_get_unmapped_area() in shm_file_operations() unconditional to CONFIG_MMU. As Tony Battersby pointed this can lead NULL-pointer dereference on machine with CONFIG_MMU=y and CONFIG_SHMEM=n. In this case ipc/shm is backed by ramfs which doesn't provide f_op->get_unmapped_area for configurations with MMU. The solution is to provide dummy f_op->get_unmapped_area for ramfs when CONFIG_MMU=y, which just call current->mm->get_unmapped_area(). Fixes: c01d5b300774 ("shmem: get_unmapped_area align huge page") Link: http://lkml.kernel.org/r/20160912102704.140442-1-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reported-by: Tony Battersby Tested-by: Tony Battersby Cc: Hugh Dickins Cc: [4.7.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ramfs/file-mmu.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'fs') diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 183a212694bf..12af0490322f 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -27,9 +27,17 @@ #include #include #include +#include #include "internal.h" +static unsigned long ramfs_mmu_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); +} + const struct file_operations ramfs_file_operations = { .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, @@ -38,6 +46,7 @@ const struct file_operations ramfs_file_operations = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .llseek = generic_file_llseek, + .get_unmapped_area = ramfs_mmu_get_unmapped_area, }; const struct inode_operations ramfs_file_inode_operations = { -- cgit 1.4.1 From 2b0ad0085aa47ace4756aa501274a7de0325c09c Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Mon, 19 Sep 2016 14:44:21 -0700 Subject: ocfs2: fix trans extend while flush truncate log Every time, ocfs2_extend_trans() included a credit for truncate log inode, but as that inode had been managed by jbd2 running transaction first time, it will not consume that credit until jbd2_journal_restart(). Since total credits to extend always included the un-consumed ones, there will be more and more un-consumed credit, at last jbd2_journal_restart() will fail due to credit number over the half of max transction credit. The following error was caught when unlinking a large file with many extents: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 13626 at fs/jbd2/transaction.c:269 start_this_handle+0x4c3/0x510 [jbd2]() Modules linked in: ocfs2 nfsd lockd grace nfs_acl auth_rpcgss sunrpc autofs4 ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs sd_mod sg ip6t_REJECT nf_reject_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables be2iscsi iscsi_boot_sysfs bnx2i cnic uio cxgb4i cxgb4 cxgb3i libcxgbi cxgb3 mdio ib_iser rdma_cm ib_cm iw_cm ib_sa ib_mad ib_core ib_addr ipv6 iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ppdev xen_kbdfront xen_netfront fb_sys_fops sysimgblt sysfillrect syscopyarea parport_pc parport pcspkr i2c_piix4 i2c_core acpi_cpufreq ext4 jbd2 mbcache xen_blkfront floppy pata_acpi ata_generic ata_piix dm_mirror dm_region_hash dm_log dm_mod CPU: 0 PID: 13626 Comm: unlink Tainted: G W 4.1.12-37.6.3.el6uek.x86_64 #2 Hardware name: Xen HVM domU, BIOS 4.4.4OVM 02/11/2016 Call Trace: dump_stack+0x48/0x5c warn_slowpath_common+0x95/0xe0 warn_slowpath_null+0x1a/0x20 start_this_handle+0x4c3/0x510 [jbd2] jbd2__journal_restart+0x161/0x1b0 [jbd2] jbd2_journal_restart+0x13/0x20 [jbd2] ocfs2_extend_trans+0x74/0x220 [ocfs2] ocfs2_replay_truncate_records+0x93/0x360 [ocfs2] __ocfs2_flush_truncate_log+0x13e/0x3a0 [ocfs2] ocfs2_remove_btree_range+0x458/0x7f0 [ocfs2] ocfs2_commit_truncate+0x1b3/0x6f0 [ocfs2] ocfs2_truncate_for_delete+0xbd/0x380 [ocfs2] ocfs2_wipe_inode+0x136/0x6a0 [ocfs2] ocfs2_delete_inode+0x2a2/0x3e0 [ocfs2] ocfs2_evict_inode+0x28/0x60 [ocfs2] evict+0xab/0x1a0 iput_final+0xf6/0x190 iput+0xc8/0xe0 do_unlinkat+0x1b7/0x310 SyS_unlink+0x16/0x20 system_call_fastpath+0x12/0x71 ---[ end trace 28aa7410e69369cf ]--- JBD2: unlink wants too many credits (251 > 128) Link: http://lkml.kernel.org/r/1473674623-11810-1-git-send-email-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/alloc.c | 29 ++++++++++------------------- 1 file changed, 10 insertions(+), 19 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 7dabbc31060e..51128789a661 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -5922,7 +5922,6 @@ bail: } static int ocfs2_replay_truncate_records(struct ocfs2_super *osb, - handle_t *handle, struct inode *data_alloc_inode, struct buffer_head *data_alloc_bh) { @@ -5935,11 +5934,19 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb, struct ocfs2_truncate_log *tl; struct inode *tl_inode = osb->osb_tl_inode; struct buffer_head *tl_bh = osb->osb_tl_bh; + handle_t *handle; di = (struct ocfs2_dinode *) tl_bh->b_data; tl = &di->id2.i_dealloc; i = le16_to_cpu(tl->tl_used) - 1; while (i >= 0) { + handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC); + if (IS_ERR(handle)) { + status = PTR_ERR(handle); + mlog_errno(status); + goto bail; + } + /* Caller has given us at least enough credits to * update the truncate log dinode */ status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh, @@ -5974,12 +5981,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb, } } - status = ocfs2_extend_trans(handle, - OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC); - if (status < 0) { - mlog_errno(status); - goto bail; - } + ocfs2_commit_trans(osb, handle); i--; } @@ -5994,7 +5996,6 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb) { int status; unsigned int num_to_flush; - handle_t *handle; struct inode *tl_inode = osb->osb_tl_inode; struct inode *data_alloc_inode = NULL; struct buffer_head *tl_bh = osb->osb_tl_bh; @@ -6038,21 +6039,11 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb) goto out_mutex; } - handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC); - if (IS_ERR(handle)) { - status = PTR_ERR(handle); - mlog_errno(status); - goto out_unlock; - } - - status = ocfs2_replay_truncate_records(osb, handle, data_alloc_inode, + status = ocfs2_replay_truncate_records(osb, data_alloc_inode, data_alloc_bh); if (status < 0) mlog_errno(status); - ocfs2_commit_trans(osb, handle); - -out_unlock: brelse(data_alloc_bh); ocfs2_inode_unlock(data_alloc_inode, 1); -- cgit 1.4.1 From d5bf141893880f7283fe97e1812c58ff22c8f9a5 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Mon, 19 Sep 2016 14:44:24 -0700 Subject: ocfs2: fix trans extend while free cached blocks The root cause of this issue is the same with the one fixed by the last patch, but this time credits for allocator inode and group descriptor may not be consumed before trans extend. The following error was caught: WARNING: CPU: 0 PID: 2037 at fs/jbd2/transaction.c:269 start_this_handle+0x4c3/0x510 [jbd2]() Modules linked in: ocfs2 nfsd lockd grace nfs_acl auth_rpcgss sunrpc autofs4 ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs sd_mod sg ip6t_REJECT nf_reject_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables be2iscsi iscsi_boot_sysfs bnx2i cnic uio cxgb4i cxgb4 cxgb3i libcxgbi cxgb3 mdio ib_iser rdma_cm ib_cm iw_cm ib_sa ib_mad ib_core ib_addr ipv6 iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ppdev xen_kbdfront fb_sys_fops sysimgblt sysfillrect syscopyarea xen_netfront parport_pc parport pcspkr i2c_piix4 i2c_core acpi_cpufreq ext4 jbd2 mbcache xen_blkfront floppy pata_acpi ata_generic ata_piix dm_mirror dm_region_hash dm_log dm_mod CPU: 0 PID: 2037 Comm: rm Tainted: G W 4.1.12-37.6.3.el6uek.bug24573128v2.x86_64 #2 Hardware name: Xen HVM domU, BIOS 4.4.4OVM 02/11/2016 Call Trace: dump_stack+0x48/0x5c warn_slowpath_common+0x95/0xe0 warn_slowpath_null+0x1a/0x20 start_this_handle+0x4c3/0x510 [jbd2] jbd2__journal_restart+0x161/0x1b0 [jbd2] jbd2_journal_restart+0x13/0x20 [jbd2] ocfs2_extend_trans+0x74/0x220 [ocfs2] ocfs2_free_cached_blocks+0x16b/0x4e0 [ocfs2] ocfs2_run_deallocs+0x70/0x270 [ocfs2] ocfs2_commit_truncate+0x474/0x6f0 [ocfs2] ocfs2_truncate_for_delete+0xbd/0x380 [ocfs2] ocfs2_wipe_inode+0x136/0x6a0 [ocfs2] ocfs2_delete_inode+0x2a2/0x3e0 [ocfs2] ocfs2_evict_inode+0x28/0x60 [ocfs2] evict+0xab/0x1a0 iput_final+0xf6/0x190 iput+0xc8/0xe0 do_unlinkat+0x1b7/0x310 SyS_unlinkat+0x22/0x40 system_call_fastpath+0x12/0x71 ---[ end trace a62437cb060baa71 ]--- JBD2: rm wants too many credits (149 > 128) Link: http://lkml.kernel.org/r/1473674623-11810-2-git-send-email-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/alloc.c | 27 +++++++++------------------ 1 file changed, 9 insertions(+), 18 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 51128789a661..f165f867f332 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -6404,43 +6404,34 @@ static int ocfs2_free_cached_blocks(struct ocfs2_super *osb, goto out_mutex; } - handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - mlog_errno(ret); - goto out_unlock; - } - while (head) { if (head->free_bg) bg_blkno = head->free_bg; else bg_blkno = ocfs2_which_suballoc_group(head->free_blk, head->free_bit); + handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto out_unlock; + } + trace_ocfs2_free_cached_blocks( (unsigned long long)head->free_blk, head->free_bit); ret = ocfs2_free_suballoc_bits(handle, inode, di_bh, head->free_bit, bg_blkno, 1); - if (ret) { + if (ret) mlog_errno(ret); - goto out_journal; - } - ret = ocfs2_extend_trans(handle, OCFS2_SUBALLOC_FREE); - if (ret) { - mlog_errno(ret); - goto out_journal; - } + ocfs2_commit_trans(osb, handle); tmp = head; head = head->free_next; kfree(tmp); } -out_journal: - ocfs2_commit_trans(osb, handle); - out_unlock: ocfs2_inode_unlock(inode, 1); brelse(di_bh); -- cgit 1.4.1 From 12703dbfeb15402260e7554d32a34ac40c233990 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 19 Sep 2016 14:44:27 -0700 Subject: fsnotify: add a way to stop queueing events on group shutdown Implement a function that can be called when a group is being shutdown to stop queueing new events to the group. Fanotify will use this. Fixes: 5838d4442bd5 ("fanotify: fix double free of pending permission events") Link: http://lkml.kernel.org/r/1473797711-14111-2-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reviewed-by: Miklos Szeredi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/group.c | 19 +++++++++++++++++++ fs/notify/notification.c | 8 +++++++- include/linux/fsnotify_backend.h | 3 +++ 3 files changed, 29 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/notify/group.c b/fs/notify/group.c index 3e2dd85be5dd..b47f7cfdcaa4 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -39,6 +39,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) kfree(group); } +/* + * Stop queueing new events for this group. Once this function returns + * fsnotify_add_event() will not add any new events to the group's queue. + */ +void fsnotify_group_stop_queueing(struct fsnotify_group *group) +{ + mutex_lock(&group->notification_mutex); + group->shutdown = true; + mutex_unlock(&group->notification_mutex); +} + /* * Trying to get rid of a group. Remove all marks, flush all events and release * the group reference. @@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) */ void fsnotify_destroy_group(struct fsnotify_group *group) { + /* + * Stop queueing new events. The code below is careful enough to not + * require this but fanotify needs to stop queuing events even before + * fsnotify_destroy_group() is called and this makes the other callers + * of fsnotify_destroy_group() to see the same behavior. + */ + fsnotify_group_stop_queueing(group); + /* clear all inode marks for this group, attach them to destroy_list */ fsnotify_detach_group_marks(group); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index a95d8e037aeb..3d76e65ff84f 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -82,7 +82,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group, * Add an event to the group notification queue. The group can later pull this * event off the queue to deal with. The function returns 0 if the event was * added to the queue, 1 if the event was merged with some other queued event, - * 2 if the queue of events has overflown. + * 2 if the event was not queued - either the queue of events has overflown + * or the group is shutting down. */ int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, @@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group, mutex_lock(&group->notification_mutex); + if (group->shutdown) { + mutex_unlock(&group->notification_mutex); + return 2; + } + if (group->q_len >= group->max_events) { ret = 2; /* Queue overflow event only if it isn't already queued */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 58205f33af02..40a9e99de703 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -148,6 +148,7 @@ struct fsnotify_group { #define FS_PRIO_1 1 /* fanotify content based access control */ #define FS_PRIO_2 2 /* fanotify pre-content access */ unsigned int priority; + bool shutdown; /* group is being shut down, don't queue more events */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ @@ -292,6 +293,8 @@ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *op extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); +/* group destruction begins, stop queuing new events */ +extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ -- cgit 1.4.1 From 96d41019e3ac55f6f0115b0ce97e4f24a3d636d2 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 19 Sep 2016 14:44:30 -0700 Subject: fanotify: fix list corruption in fanotify_get_response() fanotify_get_response() calls fsnotify_remove_event() when it finds that group is being released from fanotify_release() (bypass_perm is set). However the event it removes need not be only in the group's notification queue but it can have already moved to access_list (userspace read the event before closing the fanotify instance fd) which is protected by a different lock. Thus when fsnotify_remove_event() races with fanotify_release() operating on access_list, the list can get corrupted. Fix the problem by moving all the logic removing permission events from the lists to one place - fanotify_release(). Fixes: 5838d4442bd5 ("fanotify: fix double free of pending permission events") Link: http://lkml.kernel.org/r/1473797711-14111-3-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reported-by: Miklos Szeredi Tested-by: Miklos Szeredi Reviewed-by: Miklos Szeredi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/fanotify/fanotify.c | 13 +------------ fs/notify/fanotify/fanotify_user.c | 36 ++++++++++++++++++++++++------------ fs/notify/notification.c | 15 --------------- include/linux/fsnotify_backend.h | 3 --- 4 files changed, 25 insertions(+), 42 deletions(-) (limited to 'fs') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index d2f97ecca6a5..e0e5f7c3c99f 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - wait_event(group->fanotify_data.access_waitq, event->response || - atomic_read(&group->fanotify_data.bypass_perm)); - - if (!event->response) { /* bypass_perm set */ - /* - * Event was canceled because group is being destroyed. Remove - * it from group's event list because we are responsible for - * freeing the permission event. - */ - fsnotify_remove_event(group, &event->fae.fse); - return 0; - } + wait_event(group->fanotify_data.access_waitq, event->response); /* userspace responded, convert to something usable */ switch (event->response) { diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 8e8e6bcd1d43..a64313868d3a 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS struct fanotify_perm_event_info *event, *next; + struct fsnotify_event *fsn_event; /* - * There may be still new events arriving in the notification queue - * but since userspace cannot use fanotify fd anymore, no event can - * enter or leave access_list by now. + * Stop new events from arriving in the notification queue. since + * userspace cannot use fanotify fd anymore, no event can enter or + * leave access_list by now either. */ - spin_lock(&group->fanotify_data.access_lock); - - atomic_inc(&group->fanotify_data.bypass_perm); + fsnotify_group_stop_queueing(group); + /* + * Process all permission events on access_list and notification queue + * and simulate reply from userspace. + */ + spin_lock(&group->fanotify_data.access_lock); list_for_each_entry_safe(event, next, &group->fanotify_data.access_list, fae.fse.list) { pr_debug("%s: found group=%p event=%p\n", __func__, group, @@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file) spin_unlock(&group->fanotify_data.access_lock); /* - * Since bypass_perm is set, newly queued events will not wait for - * access response. Wake up the already sleeping ones now. - * synchronize_srcu() in fsnotify_destroy_group() will wait for all - * processes sleeping in fanotify_handle_event() waiting for access - * response and thus also for all permission events to be freed. + * Destroy all non-permission events. For permission events just + * dequeue them and set the response. They will be freed once the + * response is consumed and fanotify_get_response() returns. */ + mutex_lock(&group->notification_mutex); + while (!fsnotify_notify_queue_is_empty(group)) { + fsn_event = fsnotify_remove_first_event(group); + if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) + fsnotify_destroy_event(group, fsn_event); + else + FANOTIFY_PE(fsn_event)->response = FAN_ALLOW; + } + mutex_unlock(&group->notification_mutex); + + /* Response for all permission events it set, wakeup waiters */ wake_up(&group->fanotify_data.access_waitq); #endif @@ -755,7 +768,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) spin_lock_init(&group->fanotify_data.access_lock); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); - atomic_set(&group->fanotify_data.bypass_perm, 0); #endif switch (flags & FAN_ALL_CLASS_BITS) { case FAN_CLASS_NOTIF: diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 3d76e65ff84f..e455e83ceeeb 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -131,21 +131,6 @@ queue: return ret; } -/* - * Remove @event from group's notification queue. It is the responsibility of - * the caller to destroy the event. - */ -void fsnotify_remove_event(struct fsnotify_group *group, - struct fsnotify_event *event) -{ - mutex_lock(&group->notification_mutex); - if (!list_empty(&event->list)) { - list_del_init(&event->list); - group->q_len--; - } - mutex_unlock(&group->notification_mutex); -} - /* * Remove and return the first event from the notification list. It is the * responsibility of the caller to destroy the obtained event diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 40a9e99de703..7268ed076be8 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -180,7 +180,6 @@ struct fsnotify_group { spinlock_t access_lock; struct list_head access_list; wait_queue_head_t access_waitq; - atomic_t bypass_perm; #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ int f_flags; unsigned int max_marks; @@ -307,8 +306,6 @@ extern int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct list_head *, struct fsnotify_event *)); -/* Remove passed event from groups notification queue */ -extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event); /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ -- cgit 1.4.1 From 3bb8b653c86f6b1d2cc05aa1744fed4b18f99485 Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Mon, 19 Sep 2016 14:44:33 -0700 Subject: ocfs2: fix double unlock in case retry after free truncate log If ocfs2_reserve_cluster_bitmap_bits() fails with ENOSPC, it will try to free truncate log and then retry. Since ocfs2_try_to_free_truncate_log will lock/unlock global bitmap inode, we have to unlock it before calling this function. But when retry reserve and it fails with no global bitmap inode lock taken, it will unlock again in error handling branch and BUG. This issue also exists if no need retry and then ocfs2_inode_lock fails. So fix it. Fixes: 2070ad1aebff ("ocfs2: retry on ENOSPC if sufficient space in truncate log") Link: http://lkml.kernel.org/r/57D91939.6030809@huawei.com Signed-off-by: Joseph Qi Signed-off-by: Jiufei Xue Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/suballoc.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index ea47120a85ff..6ad3533940ba 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1199,14 +1199,24 @@ retry: inode_unlock((*ac)->ac_inode); ret = ocfs2_try_to_free_truncate_log(osb, bits_wanted); - if (ret == 1) + if (ret == 1) { + iput((*ac)->ac_inode); + (*ac)->ac_inode = NULL; goto retry; + } if (ret < 0) mlog_errno(ret); inode_lock((*ac)->ac_inode); - ocfs2_inode_lock((*ac)->ac_inode, NULL, 1); + ret = ocfs2_inode_lock((*ac)->ac_inode, NULL, 1); + if (ret < 0) { + mlog_errno(ret); + inode_unlock((*ac)->ac_inode); + iput((*ac)->ac_inode); + (*ac)->ac_inode = NULL; + goto bail; + } } if (status < 0) { if (status != -ENOSPC) -- cgit 1.4.1 From d21c353d5e99c56cdd5b5c1183ffbcaf23b8b960 Mon Sep 17 00:00:00 2001 From: Ashish Samant Date: Mon, 19 Sep 2016 14:44:42 -0700 Subject: ocfs2: fix start offset to ocfs2_zero_range_for_truncate() If we punch a hole on a reflink such that following conditions are met: 1. start offset is on a cluster boundary 2. end offset is not on a cluster boundary 3. (end offset is somewhere in another extent) or (hole range > MAX_CONTIG_BYTES(1MB)), we dont COW the first cluster starting at the start offset. But in this case, we were wrongly passing this cluster to ocfs2_zero_range_for_truncate() to zero out. This will modify the cluster in place and zero it in the source too. Fix this by skipping this cluster in such a scenario. To reproduce: 1. Create a random file of say 10 MB xfs_io -c 'pwrite -b 4k 0 10M' -f 10MBfile 2. Reflink it reflink -f 10MBfile reflnktest 3. Punch a hole at starting at cluster boundary with range greater that 1MB. You can also use a range that will put the end offset in another extent. fallocate -p -o 0 -l 1048615 reflnktest 4. sync 5. Check the first cluster in the source file. (It will be zeroed out). dd if=10MBfile iflag=direct bs= count=1 | hexdump -C Link: http://lkml.kernel.org/r/1470957147-14185-1-git-send-email-ashish.samant@oracle.com Signed-off-by: Ashish Samant Reported-by: Saar Maoz Reviewed-by: Srinivas Eeda Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Cc: Eric Ren Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/file.c | 34 ++++++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 4e7b0dc22450..0b055bfb8e86 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1506,7 +1506,8 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, u64 start, u64 len) { int ret = 0; - u64 tmpend, end = start + len; + u64 tmpend = 0; + u64 end = start + len; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); unsigned int csize = osb->s_clustersize; handle_t *handle; @@ -1538,18 +1539,31 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, } /* - * We want to get the byte offset of the end of the 1st cluster. + * If start is on a cluster boundary and end is somewhere in another + * cluster, we have not COWed the cluster starting at start, unless + * end is also within the same cluster. So, in this case, we skip this + * first call to ocfs2_zero_range_for_truncate() truncate and move on + * to the next one. */ - tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1)); - if (tmpend > end) - tmpend = end; + if ((start & (csize - 1)) != 0) { + /* + * We want to get the byte offset of the end of the 1st + * cluster. + */ + tmpend = (u64)osb->s_clustersize + + (start & ~(osb->s_clustersize - 1)); + if (tmpend > end) + tmpend = end; - trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start, - (unsigned long long)tmpend); + trace_ocfs2_zero_partial_clusters_range1( + (unsigned long long)start, + (unsigned long long)tmpend); - ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend); - if (ret) - mlog_errno(ret); + ret = ocfs2_zero_range_for_truncate(inode, handle, start, + tmpend); + if (ret) + mlog_errno(ret); + } if (tmpend < end) { /* -- cgit 1.4.1 From 63b52c4936a2e679639c38ef51a50aa8ca1c5c07 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Mon, 19 Sep 2016 14:44:44 -0700 Subject: Revert "ocfs2: bump up o2cb network protocol version" This reverts commit 38b52efd218b ("ocfs2: bump up o2cb network protocol version"). This commit made rolling upgrade fail. When one node is upgraded to new version with this commit, the remaining nodes will fail to establish connections to it, then the application like VMs on the remaining nodes can't be live migrated to the upgraded one. This will cause an outage. Since negotiate hb timeout behavior didn't change without this commit, so revert it. Fixes: 38b52efd218bf ("ocfs2: bump up o2cb network protocol version") Link: http://lkml.kernel.org/r/1471396924-10375-1-git-send-email-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi Cc: Mark Fasheh Cc: Joel Becker Cc: Joseph Qi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/tcp_internal.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h index 94b18369b1cc..b95e7df5b76a 100644 --- a/fs/ocfs2/cluster/tcp_internal.h +++ b/fs/ocfs2/cluster/tcp_internal.h @@ -44,9 +44,6 @@ * version here in tcp_internal.h should not need to be bumped for * filesystem locking changes. * - * New in version 12 - * - Negotiate hb timeout when storage is down. - * * New in version 11 * - Negotiation of filesystem locking in the dlm join. * @@ -78,7 +75,7 @@ * - full 64 bit i_size in the metadata lock lvbs * - introduction of "rw" lock and pushing meta/data locking down */ -#define O2NET_PROTOCOL_VERSION 12ULL +#define O2NET_PROTOCOL_VERSION 11ULL struct o2net_handshake { __be64 protocol_version; __be64 connector_id; -- cgit 1.4.1