From 4cd9973f9ff69e37dd0ba2bd6e6423f8179c329a Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Thu, 25 Jun 2020 20:29:30 -0700 Subject: ocfs2: avoid inode removal while nfsd is accessing it Patch series "ocfs2: fix nfsd over ocfs2 issues", v2. This is a series of patches to fix issues on nfsd over ocfs2. patch 1 is to avoid inode removed while nfsd access it patch 2 & 3 is to fix a panic issue. This patch (of 4): When nfsd is getting file dentry using handle or parent dentry of some dentry, one cluster lock is used to avoid inode removed from other node, but it still could be removed from local node, so use a rw lock to avoid this. Link: http://lkml.kernel.org/r/20200616183829.87211-1-junxiao.bi@oracle.com Link: http://lkml.kernel.org/r/20200616183829.87211-2-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi Reviewed-by: Joseph Qi Cc: Changwei Ge Cc: Gang He Cc: Joel Becker Cc: Jun Piao Cc: Mark Fasheh Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlmglue.c | 17 ++++++++++++++++- fs/ocfs2/ocfs2.h | 1 + 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 152a0fc4e905..751bc4dc7466 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -689,6 +689,12 @@ static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res, &ocfs2_nfs_sync_lops, osb); } +static void ocfs2_nfs_sync_lock_init(struct ocfs2_super *osb) +{ + ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb); + init_rwsem(&osb->nfs_sync_rwlock); +} + void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb) { struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres; @@ -2855,6 +2861,11 @@ int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex) if (ocfs2_is_hard_readonly(osb)) return -EROFS; + if (ex) + down_write(&osb->nfs_sync_rwlock); + else + down_read(&osb->nfs_sync_rwlock); + if (ocfs2_mount_local(osb)) return 0; @@ -2873,6 +2884,10 @@ void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex) if (!ocfs2_mount_local(osb)) ocfs2_cluster_unlock(osb, lockres, ex ? LKM_EXMODE : LKM_PRMODE); + if (ex) + up_write(&osb->nfs_sync_rwlock); + else + up_read(&osb->nfs_sync_rwlock); } int ocfs2_trim_fs_lock(struct ocfs2_super *osb, @@ -3340,7 +3355,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb) local: ocfs2_super_lock_res_init(&osb->osb_super_lockres, osb); ocfs2_rename_lock_res_init(&osb->osb_rename_lockres, osb); - ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb); + ocfs2_nfs_sync_lock_init(osb); ocfs2_orphan_scan_lock_res_init(&osb->osb_orphan_scan.os_lockres, osb); osb->cconn = conn; diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index ee5d98516212..2dd71d626196 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -395,6 +395,7 @@ struct ocfs2_super struct ocfs2_lock_res osb_super_lockres; struct ocfs2_lock_res osb_rename_lockres; struct ocfs2_lock_res osb_nfs_sync_lockres; + struct rw_semaphore nfs_sync_rwlock; struct ocfs2_lock_res osb_trim_fs_lockres; struct mutex obs_trim_fs_mutex; struct ocfs2_dlm_debug *osb_dlm_debug; -- cgit v1.2.3-70-g09d2 From 7569d3c754e452769a5747eeeba488179e38a5da Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Thu, 25 Jun 2020 20:29:33 -0700 Subject: ocfs2: load global_inode_alloc Set global_inode_alloc as OCFS2_FIRST_ONLINE_SYSTEM_INODE, that will make it load during mount. It can be used to test whether some global/system inodes are valid. One use case is that nfsd will test whether root inode is valid. Link: http://lkml.kernel.org/r/20200616183829.87211-3-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi Reviewed-by: Joseph Qi Cc: Changwei Ge Cc: Gang He Cc: Joel Becker Cc: Jun Piao Cc: Mark Fasheh Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 0dd8c41bafd4..3fc99659ed09 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -326,8 +326,8 @@ struct ocfs2_system_inode_info { enum { BAD_BLOCK_SYSTEM_INODE = 0, GLOBAL_INODE_ALLOC_SYSTEM_INODE, +#define OCFS2_FIRST_ONLINE_SYSTEM_INODE GLOBAL_INODE_ALLOC_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE, -#define OCFS2_FIRST_ONLINE_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE HEARTBEAT_SYSTEM_INODE, GLOBAL_BITMAP_SYSTEM_INODE, USER_QUOTA_SYSTEM_INODE, -- cgit v1.2.3-70-g09d2 From e5a15e17a78d58f933d17cafedfcf7486a29f5b4 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Thu, 25 Jun 2020 20:29:37 -0700 Subject: ocfs2: fix panic on nfs server over ocfs2 The following kernel panic was captured when running nfs server over ocfs2, at that time ocfs2_test_inode_bit() was checking whether one inode locating at "blkno" 5 was valid, that is ocfs2 root inode, its "suballoc_slot" was OCFS2_INVALID_SLOT(65535) and it was allocted from //global_inode_alloc, but here it wrongly assumed that it was got from per slot inode alloctor which would cause array overflow and trigger kernel panic. BUG: unable to handle kernel paging request at 0000000000001088 IP: [] _raw_spin_lock+0x18/0xf0 PGD 1e06ba067 PUD 1e9e7d067 PMD 0 Oops: 0002 [#1] SMP CPU: 6 PID: 24873 Comm: nfsd Not tainted 4.1.12-124.36.1.el6uek.x86_64 #2 Hardware name: Huawei CH121 V3/IT11SGCA1, BIOS 3.87 02/02/2018 RIP: _raw_spin_lock+0x18/0xf0 RSP: e02b:ffff88005ae97908 EFLAGS: 00010206 RAX: ffff88005ae98000 RBX: 0000000000001088 RCX: 0000000000000000 RDX: 0000000000020000 RSI: 0000000000000009 RDI: 0000000000001088 RBP: ffff88005ae97928 R08: 0000000000000000 R09: ffff880212878e00 R10: 0000000000007ff0 R11: 0000000000000000 R12: 0000000000001088 R13: ffff8800063c0aa8 R14: ffff8800650c27d0 R15: 000000000000ffff FS: 0000000000000000(0000) GS:ffff880218180000(0000) knlGS:ffff880218180000 CS: e033 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000001088 CR3: 00000002033d0000 CR4: 0000000000042660 Call Trace: igrab+0x1e/0x60 ocfs2_get_system_file_inode+0x63/0x3a0 [ocfs2] ocfs2_test_inode_bit+0x328/0xa00 [ocfs2] ocfs2_get_parent+0xba/0x3e0 [ocfs2] reconnect_path+0xb5/0x300 exportfs_decode_fh+0xf6/0x2b0 fh_verify+0x350/0x660 [nfsd] nfsd4_putfh+0x4d/0x60 [nfsd] nfsd4_proc_compound+0x3d3/0x6f0 [nfsd] nfsd_dispatch+0xe0/0x290 [nfsd] svc_process_common+0x412/0x6a0 [sunrpc] svc_process+0x123/0x210 [sunrpc] nfsd+0xff/0x170 [nfsd] kthread+0xcb/0xf0 ret_from_fork+0x61/0x90 Code: 83 c2 02 0f b7 f2 e8 18 dc 91 ff 66 90 eb bf 0f 1f 40 00 55 48 89 e5 41 56 41 55 41 54 53 0f 1f 44 00 00 48 89 fb ba 00 00 02 00 0f c1 17 89 d0 45 31 e4 45 31 ed c1 e8 10 66 39 d0 41 89 c6 RIP _raw_spin_lock+0x18/0xf0 CR2: 0000000000001088 ---[ end trace 7264463cd1aac8f9 ]--- Kernel panic - not syncing: Fatal exception Link: http://lkml.kernel.org/r/20200616183829.87211-4-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi Reviewed-by: Joseph Qi Cc: Changwei Ge Cc: Gang He Cc: Joel Becker Cc: Jun Piao Cc: Mark Fasheh Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/suballoc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 4836becb7578..45745cc3408a 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -2825,9 +2825,12 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res) goto bail; } - inode_alloc_inode = - ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE, - suballoc_slot); + if (suballoc_slot == (u16)OCFS2_INVALID_SLOT) + inode_alloc_inode = ocfs2_get_system_file_inode(osb, + GLOBAL_INODE_ALLOC_SYSTEM_INODE, suballoc_slot); + else + inode_alloc_inode = ocfs2_get_system_file_inode(osb, + INODE_ALLOC_SYSTEM_INODE, suballoc_slot); if (!inode_alloc_inode) { /* the error code could be inaccurate, but we are not able to * get the correct one. */ -- cgit v1.2.3-70-g09d2 From 9277f8334ffc719fe922d776444d6e4e884dbf30 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Thu, 25 Jun 2020 20:29:40 -0700 Subject: ocfs2: fix value of OCFS2_INVALID_SLOT In the ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implementation, slot number is 32 bits. Usually this will not cause any issue, because slot number is converted from u16 to u32, but OCFS2_INVALID_SLOT was defined as -1, when an invalid slot number from disk was obtained, its value was (u16)-1, and it was converted to u32. Then the following checking in get_local_system_inode will be always skipped: static struct inode **get_local_system_inode(struct ocfs2_super *osb, int type, u32 slot) { BUG_ON(slot == OCFS2_INVALID_SLOT); ... } Link: http://lkml.kernel.org/r/20200616183829.87211-5-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 3fc99659ed09..19137c6d087b 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -290,7 +290,7 @@ #define OCFS2_MAX_SLOTS 255 /* Slot map indicator for an empty slot */ -#define OCFS2_INVALID_SLOT -1 +#define OCFS2_INVALID_SLOT ((u16)-1) #define OCFS2_VOL_UUID_LEN 16 #define OCFS2_MAX_VOL_LABEL_LEN 64 -- cgit v1.2.3-70-g09d2