ocfs2: fix nfsd over ocfs2 issues
PATCH v2 1/1 ocfs2: fix nfsd over ocfs2 issues
This is serial 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
v2 <- v1:
- coding style fixing in patch 1
- add patch 4 to fix ignored invalid slot checking
Thanks,
Junxiao.
PATCH 1/4 ocfs2: avoid inode removed while nfsd access it
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.
--- fs/ocfs2/dlmglue.c | 17 ++++++++++++++++- fs/ocfs2/ocfs2.h | 1 + 2 files changed, 17 insertions(+), 1 deletion(-)
fs/ocfs2/dlmglue.c +16 -1
@@ -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;
fs/ocfs2/ocfs2.h +1 -0
@@ -395,6 +395,7 @@ struct ocfs2_superstruct 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;
Signature · 1 line
2.20.1 (Apple Git-117)
Joseph Qi
maintainerPATCH 1/4 ocfs2: avoid inode removed while nfsd access it
Quoted 6 lines · Junxiao Bi
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.
Signed-off-by Junxiao Bi <[email protected]>
Quoted 67 lines
--- fs/ocfs2/dlmglue.c | 17 ++++++++++++++++- fs/ocfs2/ocfs2.h | 1 + 2 files changed, 17 insertions(+), 1 deletion(-)fs/ocfs2/dlmglue.c +16
-1@@ -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;fs/ocfs2/ocfs2.h +1
-0@@ -395,6 +395,7 @@ struct ocfs2_superstruct 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;
PATCH 1/4 ocfs2: avoid inode removed while nfsd access it
Quoted 9 lines · On Wed, 17 Jun 2020 11:01:12 +0800 Joseph Qi <[email protected]>…
Quoted 6 lines · Junxiao Bi
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.
Signed-off-by Junxiao Bi <[email protected]>Reviewed-by Joseph Qi <[email protected]>
Which kernel version(s) do we think need these four patches? 5.9? 5.8? 5.8 and -stable?
PATCH 1/4 ocfs2: avoid inode removed while nfsd access it
Quoted 8 lines · Andrew Morton
Quoted 6 lines · On Wed, 17 Jun 2020 11:01:12 +0800 Joseph Qi <[email protected]>…
Quoted 5 lines · Junxiao Bi
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.
Quoted 4 lines
Quoted 2 lines
Quoted 1 line
Signed-off-by Junxiao Bi <[email protected]>Reviewed-by Joseph Qi <[email protected]>Which kernel version(s) do we think need these four patches? 5.9? 5.8? 5.8 and -stable?
sorry, forgot cc stable, all stable kernel will need these fixes.
Thanks,
Junxiao.
PATCH 2/4 ocfs2: load global_inode_alloc
In reply to Junxiao Biset 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.
--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/ocfs2/ocfs2_fs.h +1 -1
@@ -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_INODEHEARTBEAT_SYSTEM_INODE ,GLOBAL_BITMAP_SYSTEM_INODE ,USER_QUOTA_SYSTEM_INODE ,
Signature · 1 line
2.20.1 (Apple Git-117)
Joseph Qi
maintainerPATCH 2/4 ocfs2: load global_inode_alloc
Quoted 6 lines · Junxiao Bi
set
global_inode_allocasOCFS2_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.Signed-off-by Junxiao Bi <[email protected]>
Quoted 19 lines
--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)fs/ocfs2/ocfs2_fs.h +1
-1@@ -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_INODEHEARTBEAT_SYSTEM_INODE ,GLOBAL_BITMAP_SYSTEM_INODE ,USER_QUOTA_SYSTEM_INODE ,
PATCH 3/4 ocfs2: fix panic on nfs server over ocfs2
In reply to Junxiao BiThe 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.
[430033.469151] BUG: unable to handle kernel paging request at 0000000000001088 [430033.469367] IP: [<ffffffff816f6898>] _raw_spin_lock+0x18/0xf0 [430033.469567] PGD 1e06ba067 PUD 1e9e7d067 PMD 0 [430033.469769] Oops: 0002 [#1] SMP [430033.469975] Modules linked in: tun nfsd lockd grace nfs_acl auth_rpcgss
ocfs2 xen_netback xen_blkback xen_gntalloc xen_gntdev xen_evtchn xenfs xen_privcmd ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs bnx2fc fcoe libfcoe libfc sunrpc bridge 8021q mrp garp stp llc bonding dm_round_robin scsi_dh_emc dm_multipath iTCO_wdt iTCO_vendor_support pcspkr sb_edac edac_core i2c_i801 i2c_core lpc_ich mfd_core sg ext4 jbd2 mbcache2 sd_mod ahci libahci lpfc scsi_transport_fc be2net vxlan udp_tunnel ip6_udp_tunnel mpt3sas scsi_transport_sas raid_class crc32c_intel be2iscsi bnx2i cnic uio cxgb4i cxgb4 cxgb3i libcxgbi ipv6 cxgb3 mdio libiscsi_tcp qla4xxx iscsi_boot_sysfs libiscsi scsi_transport_iscsi dm_mirror dm_region_hash dm_log dm_mod
[430033.472350] CPU: 6 PID: 24873 Comm: nfsd Not tainted 4.1.12-124.36.1.el6uek.x86_64 #2 [430033.472719] Hardware name: Huawei CH121 V3/IT11SGCA1, BIOS 3.87 02/02/2018 [430033.472910] task: ffff88005ae98000 ti: ffff88005ae94000 task.ti: ffff88005ae94000 [430033.473277] RIP: e030:[<ffffffff816f6898>] [<ffffffff816f6898>] _raw_spin_lock+0x18/0xf0 [430033.473655] RSP: e02b:ffff88005ae97908 EFLAGS: 00010206 [430033.473850] RAX: ffff88005ae98000 RBX: 0000000000001088 RCX: 0000000000000000 [430033.474205] RDX: 0000000000020000 RSI: 0000000000000009 RDI: 0000000000001088 [430033.474574] RBP: ffff88005ae97928 R08: 0000000000000000 R09: ffff880212878e00 [430033.474938] R10: 0000000000007ff0 R11: 0000000000000000 R12: 0000000000001088 [430033.475324] R13: ffff8800063c0aa8 R14: ffff8800650c27d0 R15: 000000000000ffff [430033.475721] FS: 0000000000000000(0000) GS:ffff880218180000(0000) knlGS:ffff880218180000 [430033.476199] CS: e033 DS: 0000 ES: 0000 CR0: 0000000080050033 [430033.476390] CR2: 0000000000001088 CR3: 00000002033d0000 CR4: 0000000000042660 [430033.476760] Stack: [430033.476942] 0000000000001000 0000000000001088 ffff8800063c0aa8 ffff8800650c27d0 [430033.477329] ffff88005ae97948 ffffffff8122a3de 0000000000000009 ffff8800063c0000 [430033.477718] ffff88005ae979e8 ffffffffc0714e43 ffff88005ae97968 ffff88019de8f958 [430033.478104] Call Trace: [430033.478286] [<ffffffff8122a3de>] igrab+0x1e/0x60 [430033.478494] [<ffffffffc0714e43>] ocfs2_get_system_file_inode+0x63/0x3a0 [ocfs2] [430033.478870] [<ffffffffc06a87df>] ? ocfs2_read_blocks_sync+0x13f/0x3c0 [ocfs2] [430033.479267] [<ffffffffc06ff2d8>] ocfs2_test_inode_bit+0x328/0xa00 [ocfs2] [430033.479498] [<ffffffffc06bef5a>] ocfs2_get_parent+0xba/0x3e0 [ocfs2] [430033.479730] [<ffffffff8129b305>] reconnect_path+0xb5/0x300 [430033.479933] [<ffffffff8129b646>] exportfs_decode_fh+0xf6/0x2b0 [430033.480124] [<ffffffffc0814af0>] ? nfsd_proc_getattr+0xa0/0xa0 [nfsd] [430033.480294] [<ffffffffc081a682>] ? exp_find+0xe2/0x190 [nfsd] [430033.480461] [<ffffffff810e5a7e>] ? irq_get_irq_data+0xe/0x10 [430033.480627] [<ffffffff810ea1a7>] ? __call_rcu_nocb_enqueue+0xd7/0xe0 [430033.480794] [<ffffffff810eb9e8>] ? __call_rcu+0xe8/0x360 [430033.480959] [<ffffffffc0815860>] fh_verify+0x350/0x660 [nfsd] [430033.481134] [<ffffffffc0535076>] ? cache_check+0x56/0x3a0 [sunrpc] [430033.481317] [<ffffffffc0823a4d>] nfsd4_putfh+0x4d/0x60 [nfsd] [430033.481505] [<ffffffffc0826003>] nfsd4_proc_compound+0x3d3/0x6f0 [nfsd] [430033.481730] [<ffffffffc0811f60>] nfsd_dispatch+0xe0/0x290 [nfsd] [430033.481950] [<ffffffffc052b752>] ? svc_tcp_adjust_wspace+0x12/0x30 [sunrpc] [430033.482152] [<ffffffffc052a512>] svc_process_common+0x412/0x6a0 [sunrpc] [430033.482351] [<ffffffffc052a8c3>] svc_process+0x123/0x210 [sunrpc] [430033.482550] [<ffffffffc081190f>] nfsd+0xff/0x170 [nfsd] [430033.482744] [<ffffffffc0811810>] ? nfsd_destroy+0x80/0x80 [nfsd] [430033.482943] [<ffffffff810a7aeb>] kthread+0xcb/0xf0 [430033.483151] [<ffffffff816f10ea>] ? __schedule+0x24a/0x810 [430033.483354] [<ffffffff816f10ea>] ? __schedule+0x24a/0x810 [430033.483553] [<ffffffff810a7a20>] ? kthread_create_on_node+0x180/0x180 [430033.483777] [<ffffffff816f72a1>] ret_from_fork+0x61/0x90 [430033.483976] [<ffffffff810a7a20>] ? kthread_create_on_node+0x180/0x180 [430033.484191] 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 <f0> 0f c1 17 89 d0 45 31 e4 45 31 ed c1 e8 10 66 39 d0 41 89 c6 [430033.485174] RIP [<ffffffff816f6898>] _raw_spin_lock+0x18/0xf0 [430033.485370] RSP <ffff88005ae97908> [430033.485566] CR2: 0000000000001088 [430033.486223] ---[ end trace 7264463cd1aac8f9 ]--- [430033.666368] Kernel panic - not syncing: Fatal exception
--- fs/ocfs2/suballoc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
fs/ocfs2/suballoc.c +6 -3
@@ -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. */
Signature · 1 line
2.20.1 (Apple Git-117)
Joseph Qi
maintainerPATCH 3/4 ocfs2: fix panic on nfs server over ocfs2
Quoted 96 lines · Junxiao Bi
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" wasOCFS2_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.[430033.469151] BUG: unable to handle kernel paging request at 0000000000001088 [430033.469367] IP: [<ffffffff816f6898>] _raw_spin_lock+0x18/0xf0 [430033.469567] PGD 1e06ba067 PUD 1e9e7d067 PMD 0 [430033.469769] Oops: 0002 [#1] SMP [430033.469975] Modules linked in: tun nfsd lockd grace nfs_acl auth_rpcgssocfs2
xen_netbackxen_blkbackxen_gntallocxen_gntdevxen_evtchnxenfsxen_privcmdocfs2_dlmfsocfs2_stack_o2cbocfs2_dlmocfs2_nodemanagerocfs2_stackglueconfigfs bnx2fc fcoe libfcoe libfc sunrpc bridge 8021q mrp garp stp llc bondingdm_round_robinscsi_dh_emcdm_multipathiTCO_wdtiTCO_vendor_supportpcspkrsb_edacedac_corei2c_i801i2c_corelpc_ichmfd_coresg ext4 jbd2 mbcache2sd_modahci libahci lpfcscsi_transport_fcbe2net vxlanudp_tunnelip6_udp_tunnelmpt3sasscsi_transport_sasraid_classcrc32c_intelbe2iscsi bnx2i cnic uio cxgb4i cxgb4 cxgb3i libcxgbi ipv6 cxgb3 mdiolibiscsi_tcpqla4xxxiscsi_boot_sysfslibiscsiscsi_transport_iscsidm_mirrordm_region_hashdm_logdm_mod[430033.472350] CPU: 6 PID: 24873 Comm: nfsd Not tainted 4.1.12-124.36.1.el6uek.x86_64 #2 [430033.472719] Hardware name: Huawei CH121 V3/IT11SGCA1, BIOS 3.87 02/02/2018 [430033.472910] task: ffff88005ae98000 ti: ffff88005ae94000 task.ti: ffff88005ae94000 [430033.473277] RIP: e030:[<ffffffff816f6898>] [<ffffffff816f6898>] _raw_spin_lock+0x18/0xf0 [430033.473655] RSP: e02b:ffff88005ae97908 EFLAGS: 00010206 [430033.473850] RAX: ffff88005ae98000 RBX: 0000000000001088 RCX: 0000000000000000 [430033.474205] RDX: 0000000000020000 RSI: 0000000000000009 RDI: 0000000000001088 [430033.474574] RBP: ffff88005ae97928 R08: 0000000000000000 R09: ffff880212878e00 [430033.474938] R10: 0000000000007ff0 R11: 0000000000000000 R12: 0000000000001088 [430033.475324] R13: ffff8800063c0aa8 R14: ffff8800650c27d0 R15: 000000000000ffff [430033.475721] FS: 0000000000000000(0000) GS:ffff880218180000(0000) knlGS:ffff880218180000 [430033.476199] CS: e033 DS: 0000 ES: 0000 CR0: 0000000080050033 [430033.476390] CR2: 0000000000001088 CR3: 00000002033d0000 CR4: 0000000000042660 [430033.476760] Stack: [430033.476942] 0000000000001000 0000000000001088 ffff8800063c0aa8 ffff8800650c27d0 [430033.477329] ffff88005ae97948 ffffffff8122a3de 0000000000000009 ffff8800063c0000 [430033.477718] ffff88005ae979e8 ffffffffc0714e43 ffff88005ae97968 ffff88019de8f958 [430033.478104] Call Trace: [430033.478286] [<ffffffff8122a3de>] igrab+0x1e/0x60 [430033.478494] [<ffffffffc0714e43>] ocfs2_get_system_file_inode+0x63/0x3a0 [ocfs2] [430033.478870] [<ffffffffc06a87df>] ? ocfs2_read_blocks_sync+0x13f/0x3c0 [ocfs2] [430033.479267] [<ffffffffc06ff2d8>] ocfs2_test_inode_bit+0x328/0xa00 [ocfs2] [430033.479498] [<ffffffffc06bef5a>] ocfs2_get_parent+0xba/0x3e0 [ocfs2] [430033.479730] [<ffffffff8129b305>] reconnect_path+0xb5/0x300 [430033.479933] [<ffffffff8129b646>] exportfs_decode_fh+0xf6/0x2b0 [430033.480124] [<ffffffffc0814af0>] ? nfsd_proc_getattr+0xa0/0xa0 [nfsd] [430033.480294] [<ffffffffc081a682>] ? exp_find+0xe2/0x190 [nfsd] [430033.480461] [<ffffffff810e5a7e>] ? irq_get_irq_data+0xe/0x10 [430033.480627] [<ffffffff810ea1a7>] ? __call_rcu_nocb_enqueue+0xd7/0xe0 [430033.480794] [<ffffffff810eb9e8>] ? __call_rcu+0xe8/0x360 [430033.480959] [<ffffffffc0815860>] fh_verify+0x350/0x660 [nfsd] [430033.481134] [<ffffffffc0535076>] ? cache_check+0x56/0x3a0 [sunrpc] [430033.481317] [<ffffffffc0823a4d>] nfsd4_putfh+0x4d/0x60 [nfsd] [430033.481505] [<ffffffffc0826003>] nfsd4_proc_compound+0x3d3/0x6f0 [nfsd] [430033.481730] [<ffffffffc0811f60>] nfsd_dispatch+0xe0/0x290 [nfsd] [430033.481950] [<ffffffffc052b752>] ? svc_tcp_adjust_wspace+0x12/0x30 [sunrpc] [430033.482152] [<ffffffffc052a512>] svc_process_common+0x412/0x6a0 [sunrpc] [430033.482351] [<ffffffffc052a8c3>] svc_process+0x123/0x210 [sunrpc] [430033.482550] [<ffffffffc081190f>] nfsd+0xff/0x170 [nfsd] [430033.482744] [<ffffffffc0811810>] ? nfsd_destroy+0x80/0x80 [nfsd] [430033.482943] [<ffffffff810a7aeb>] kthread+0xcb/0xf0 [430033.483151] [<ffffffff816f10ea>] ? __schedule+0x24a/0x810 [430033.483354] [<ffffffff816f10ea>] ? __schedule+0x24a/0x810 [430033.483553] [<ffffffff810a7a20>] ? kthread_create_on_node+0x180/0x180 [430033.483777] [<ffffffff816f72a1>] ret_from_fork+0x61/0x90 [430033.483976] [<ffffffff810a7a20>] ? kthread_create_on_node+0x180/0x180 [430033.484191] 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 <f0> 0f c1 17 89 d0 45 31 e4 45 31 ed c1 e8 10 66 39 d0 41 89 c6 [430033.485174] RIP [<ffffffff816f6898>] _raw_spin_lock+0x18/0xf0 [430033.485370] RSP <ffff88005ae97908> [430033.485566] CR2: 0000000000001088 [430033.486223] ---[ end trace 7264463cd1aac8f9 ]--- [430033.666368] Kernel panic - not syncing: Fatal exception
Quoted 1 line
Signed-off-by Junxiao Bi <[email protected]>
Quoted 25 lines
--- fs/ocfs2/suballoc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)fs/ocfs2/suballoc.c +6
-3@@ -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. */
PATCH 4/4 ocfs2: fix value of OCFS2_INVALID_SLOT
In reply to Junxiao BiFrom ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implemtation, slot number is 32 bits, usually this will not cause any issue, because slot number is converting from u16 to u32, but OCFS2_INVALID_SLOT was defined as -1, when an invalid slot number from disk was got, it 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);
...}
--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/ocfs2/ocfs2_fs.h +1 -1
@@ -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
Signature · 1 line
2.20.1 (Apple Git-117)
Joseph Qi
maintainerPATCH 4/4 ocfs2: fix value of OCFS2_INVALID_SLOT
Quoted 8 lines · Junxiao Bi
From ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implemtation, slot number is 32 bits, usually this will not cause any issue, because slot number is converting from u16 to u32, but
OCFS2_INVALID_SLOTwas defined as -1, when an invalid slot number from disk was got, it value was (u16)-1, and it was converted to u32, then the following checking inget_local_system_inodewill be always skipped.static struct inode **get_local_system_inode(struct
ocfs2_super*osb,
Quoted 8 lines
int type, u32 slot) { BUG_ON(slot == OCFS2_INVALID_SLOT); ...}
Signed-off-by Junxiao Bi <[email protected]>
Quoted 18 lines
--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)fs/ocfs2/ocfs2_fs.h +1
-1@@ -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
PATCH 4/4 ocfs2: fix value of OCFS2_INVALID_SLOT
In reply to Junxiao BiHello Junxiao,
Thank for your patches, which looks to fix the nfsd access problem. But the patches bring a new bug, like below,
[ 251.406698] BUG: unable to handle kernel paging request at 0000565336a6bdf8 [ 251.406706] #PF error: [WRITE] [ 251.406710] PGD 0 P4D 0 [ 251.406717] Oops: 0002 [#1] SMP PTI [ 251.406724] CPU: 3 PID: 3758 Comm: mkdir Tainted: G OE 5.0.6-1-default #1 openSUSE Tumbleweed (unreleased) [ 251.406729] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20151112_172657-sheep25 04/01/2014 [ 251.406739] RIP: 0010:_raw_spin_lock+0xc/0x20 [ 251.406743] Code: 02 00 00 f0 0f c1 03 a9 ff 01 00 00 75 06 48 89 e8 5b 5d c3 48 89 df e8 a2 4f 87 ff eb f0 0f 1f 44 00 00 31 c0 ba 01 00 00 00 <f0> 0f b1 17 75 01 c3 89 c6 e8 76 3a 87 ff 66 90 c3 0f 1f 00 0f 1f [ 251.406750] RSP: 0018:ffffb65401087bf0 EFLAGS: 00010246 [ 251.406755] RAX: 0000000000000000 RBX: 0000565336a6bd70 RCX: 00000000ffffffff [ 251.406759] RDX: 0000000000000001 RSI: 0000000000000009 RDI: 0000565336a6bdf8 [ 251.406763] RBP: 0000565336a6bdf8 R08: 0000000000000000 R09: 0000000000000000 [ 251.406767] R10: 0000000000000005 R11: ffff9d7ded1bb000 R12: ffff9d7e38c559d0 [ 251.406771] R13: ffff9d7e39354be8 R14: ffff9d7e393540c8 R15: 00000000ffffffff [ 251.406777] FS: 00007f32d9e39c40(0000) GS:ffff9d7e3db80000(0000) knlGS:0000000000000000 [ 251.406782] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 251.406788] CR2: 0000565336a6bdf8 CR3: 0000000076496000 CR4: 00000000000006e0 [ 251.406801] Call Trace: [ 251.406824] igrab+0x19/0x50 [ 251.406941] ocfs2_get_system_file_inode+0x65/0x2e0 [ocfs2] [ 251.406980] ? ocfs2_find_entry+0x354/0x7f0 [ocfs2] [ 251.407025] ocfs2_reserve_suballoc_bits+0x3b/0x450 [ocfs2] [ 251.407070] ocfs2_steal_resource+0x8d/0x100 [ocfs2] [ 251.407113] ocfs2_reserve_new_inode+0x97/0x3d0 [ocfs2] [ 251.407154] ocfs2_mknod+0x3a7/0xe70 [ocfs2] [ 251.407191] ? __ocfs2_cluster_unlock.isra.47+0x24/0xd0 [ocfs2] [ 251.407231] ocfs2_mkdir+0x33/0x120 [ocfs2] [ 251.407239] ? inode_permission+0xbe/0x180 [ 251.407244] vfs_mkdir+0x102/0x1b0 [ 251.407250] do_mkdirat+0xd9/0x100 [ 251.407258] do_syscall_64+0x60/0x110 [ 251.407265] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 251.407271] RIP: 0033:0x7f32d9fbf307 [ 251.407276] Code: 1f 40 00 48 8b 05 91 eb 0c 00 64 c7 00 5f 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 b8 53 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 61 eb 0c 00 f7 d8 64 89 01 48 [ 251.407283] RSP: 002b:00007fff36999c98 EFLAGS: 00000202 ORIG_RAX: 0000000000000053 [ 251.407289] RAX: ffffffffffffffda RBX: 00007fff3699b618 RCX: 00007f32d9fbf307 [ 251.407294] RDX: 0000000000000000 RSI: 00000000000001ff RDI: 00007fff3699b618 [ 251.407298] RBP: 00007fff3699b618 R08: 00000000000001ff R09:
000055a9fe8b2c00
I feel the problem looks related to this patch.
Thanks
Gang
Quoted 34 lines · Junxiao Bi
Quoted 1 line
From ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implemtation,
slot number is 32 bits, usually this will not cause any issue, because slot number is converting from u16 to u32, but
OCFS2_INVALID_SLOTwas defined as -1, when an invalid slot number from disk was got, it value was (u16)-1, and it was converted to u32, then the following checking inget_local_system_inodewill be always skipped.static struct inode **get_local_system_inode(struct
ocfs2_super*osb,int type, u32 slot) { BUG_ON(slot == OCFS2_INVALID_SLOT); ...}
Signed-off-by Junxiao Bi <[email protected]>--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)fs/ocfs2/ocfs2_fs.h +1
-1@@ -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
Joseph Qi
maintainerPATCH 4/4 ocfs2: fix value of OCFS2_INVALID_SLOT
Hi Gang,
From the call tree it seems has relation with steal slot. Could you try the following patch in linux-next:88b4270f4999 ("ocfs2: change slot number type s16 to u16")
Thanks,
Joseph
Quoted 109 lines · Gang He
Hello Junxiao,
Thank for your patches, which looks to fix the nfsd access problem. But the patches bring a new bug, like below,
[ 251.406698] BUG: unable to handle kernel paging request at 0000565336a6bdf8 [ 251.406706] #PF error: [WRITE] [ 251.406710] PGD 0 P4D 0 [ 251.406717] Oops: 0002 [#1] SMP PTI [ 251.406724] CPU: 3 PID: 3758 Comm: mkdir Tainted: G OE 5.0.6-1-default #1 openSUSE Tumbleweed (unreleased) [ 251.406729] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20151112_172657-sheep25 04/01/2014 [ 251.406739] RIP: 0010:_raw_spin_lock+0xc/0x20 [ 251.406743] Code: 02 00 00 f0 0f c1 03 a9 ff 01 00 00 75 06 48 89 e8 5b 5d c3 48 89 df e8 a2 4f 87 ff eb f0 0f 1f 44 00 00 31 c0 ba 01 00 00 00 <f0> 0f b1 17 75 01 c3 89 c6 e8 76 3a 87 ff 66 90 c3 0f 1f 00 0f 1f [ 251.406750] RSP: 0018:ffffb65401087bf0 EFLAGS: 00010246 [ 251.406755] RAX: 0000000000000000 RBX: 0000565336a6bd70 RCX: 00000000ffffffff [ 251.406759] RDX: 0000000000000001 RSI: 0000000000000009 RDI: 0000565336a6bdf8 [ 251.406763] RBP: 0000565336a6bdf8 R08: 0000000000000000 R09: 0000000000000000 [ 251.406767] R10: 0000000000000005 R11: ffff9d7ded1bb000 R12: ffff9d7e38c559d0 [ 251.406771] R13: ffff9d7e39354be8 R14: ffff9d7e393540c8 R15: 00000000ffffffff [ 251.406777] FS: 00007f32d9e39c40(0000) GS:ffff9d7e3db80000(0000) knlGS:0000000000000000 [ 251.406782] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 251.406788] CR2: 0000565336a6bdf8 CR3: 0000000076496000 CR4: 00000000000006e0 [ 251.406801] Call Trace: [ 251.406824] igrab+0x19/0x50 [ 251.406941] ocfs2_get_system_file_inode+0x65/0x2e0 [ocfs2] [ 251.406980] ? ocfs2_find_entry+0x354/0x7f0 [ocfs2] [ 251.407025] ocfs2_reserve_suballoc_bits+0x3b/0x450 [ocfs2] [ 251.407070] ocfs2_steal_resource+0x8d/0x100 [ocfs2] [ 251.407113] ocfs2_reserve_new_inode+0x97/0x3d0 [ocfs2] [ 251.407154] ocfs2_mknod+0x3a7/0xe70 [ocfs2] [ 251.407191] ? __ocfs2_cluster_unlock.isra.47+0x24/0xd0 [ocfs2] [ 251.407231] ocfs2_mkdir+0x33/0x120 [ocfs2] [ 251.407239] ? inode_permission+0xbe/0x180 [ 251.407244] vfs_mkdir+0x102/0x1b0 [ 251.407250] do_mkdirat+0xd9/0x100 [ 251.407258] do_syscall_64+0x60/0x110 [ 251.407265] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 251.407271] RIP: 0033:0x7f32d9fbf307 [ 251.407276] Code: 1f 40 00 48 8b 05 91 eb 0c 00 64 c7 00 5f 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 b8 53 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 61 eb 0c 00 f7 d8 64 89 01 48 [ 251.407283] RSP: 002b:00007fff36999c98 EFLAGS: 00000202 ORIG_RAX: 0000000000000053 [ 251.407289] RAX: ffffffffffffffda RBX: 00007fff3699b618 RCX: 00007f32d9fbf307 [ 251.407294] RDX: 0000000000000000 RSI: 00000000000001ff RDI: 00007fff3699b618 [ 251.407298] RBP: 00007fff3699b618 R08: 00000000000001ff R09:
000055a9fe8b2c00I feel the problem looks related to this patch.
Thanks
GangQuoted 26 lines · Junxiao Bi
Quoted 1 line
From ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implemtation,
slot number is 32 bits, usually this will not cause any issue, because slot number is converting from u16 to u32, but
OCFS2_INVALID_SLOTwas defined as -1, when an invalid slot number from disk was got, it value was (u16)-1, and it was converted to u32, then the following checking inget_local_system_inodewill be always skipped.static struct inode **get_local_system_inode(struct
ocfs2_super*osb,int type, u32 slot) { BUG_ON(slot == OCFS2_INVALID_SLOT); ...}
Signed-off-by Junxiao Bi <[email protected]>--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)fs/ocfs2/ocfs2_fs.h +0
-0fs/ocfs2/ocfs2_fs.h line 296
Quoted 8 lines
fs/ocfs2/ocfs2_fs.h +1
-1@@ -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_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel
PATCH 4/4 ocfs2: fix value of OCFS2_INVALID_SLOT
Yeah, commit 88b4270f4999 may help.
Thanks,
Junxiao.
Quoted 117 lines · Joseph Qi
Hi Gang,
From the call tree it seems has relation with steal slot.
Could you try the following patch in linux-next:88b4270f4999("ocfs2: change slot number type s16 to u16")Thanks,
JosephQuoted 108 lines · Gang He
Hello Junxiao,
Thank for your patches, which looks to fix the nfsd access problem. But the patches bring a new bug, like below,
[ 251.406698] BUG: unable to handle kernel paging request at 0000565336a6bdf8 [ 251.406706] #PF error: [WRITE] [ 251.406710] PGD 0 P4D 0 [ 251.406717] Oops: 0002 [#1] SMP PTI [ 251.406724] CPU: 3 PID: 3758 Comm: mkdir Tainted: G OE 5.0.6-1-default #1 openSUSE Tumbleweed (unreleased) [ 251.406729] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20151112_172657-sheep25 04/01/2014 [ 251.406739] RIP: 0010:_raw_spin_lock+0xc/0x20 [ 251.406743] Code: 02 00 00 f0 0f c1 03 a9 ff 01 00 00 75 06 48 89 e8 5b 5d c3 48 89 df e8 a2 4f 87 ff eb f0 0f 1f 44 00 00 31 c0 ba 01 00 00 00 <f0> 0f b1 17 75 01 c3 89 c6 e8 76 3a 87 ff 66 90 c3 0f 1f 00 0f 1f [ 251.406750] RSP: 0018:ffffb65401087bf0 EFLAGS: 00010246 [ 251.406755] RAX: 0000000000000000 RBX: 0000565336a6bd70 RCX: 00000000ffffffff [ 251.406759] RDX: 0000000000000001 RSI: 0000000000000009 RDI: 0000565336a6bdf8 [ 251.406763] RBP: 0000565336a6bdf8 R08: 0000000000000000 R09: 0000000000000000 [ 251.406767] R10: 0000000000000005 R11: ffff9d7ded1bb000 R12: ffff9d7e38c559d0 [ 251.406771] R13: ffff9d7e39354be8 R14: ffff9d7e393540c8 R15: 00000000ffffffff [ 251.406777] FS: 00007f32d9e39c40(0000) GS:ffff9d7e3db80000(0000) knlGS:0000000000000000 [ 251.406782] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 251.406788] CR2: 0000565336a6bdf8 CR3: 0000000076496000 CR4: 00000000000006e0 [ 251.406801] Call Trace: [ 251.406824] igrab+0x19/0x50 [ 251.406941] ocfs2_get_system_file_inode+0x65/0x2e0 [ocfs2] [ 251.406980] ? ocfs2_find_entry+0x354/0x7f0 [ocfs2] [ 251.407025] ocfs2_reserve_suballoc_bits+0x3b/0x450 [ocfs2] [ 251.407070] ocfs2_steal_resource+0x8d/0x100 [ocfs2] [ 251.407113] ocfs2_reserve_new_inode+0x97/0x3d0 [ocfs2] [ 251.407154] ocfs2_mknod+0x3a7/0xe70 [ocfs2] [ 251.407191] ? __ocfs2_cluster_unlock.isra.47+0x24/0xd0 [ocfs2] [ 251.407231] ocfs2_mkdir+0x33/0x120 [ocfs2] [ 251.407239] ? inode_permission+0xbe/0x180 [ 251.407244] vfs_mkdir+0x102/0x1b0 [ 251.407250] do_mkdirat+0xd9/0x100 [ 251.407258] do_syscall_64+0x60/0x110 [ 251.407265] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 251.407271] RIP: 0033:0x7f32d9fbf307 [ 251.407276] Code: 1f 40 00 48 8b 05 91 eb 0c 00 64 c7 00 5f 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 b8 53 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 61 eb 0c 00 f7 d8 64 89 01 48 [ 251.407283] RSP: 002b:00007fff36999c98 EFLAGS: 00000202 ORIG_RAX: 0000000000000053 [ 251.407289] RAX: ffffffffffffffda RBX: 00007fff3699b618 RCX: 00007f32d9fbf307 [ 251.407294] RDX: 0000000000000000 RSI: 00000000000001ff RDI: 00007fff3699b618 [ 251.407298] RBP: 00007fff3699b618 R08: 00000000000001ff R09:
000055a9fe8b2c00I feel the problem looks related to this patch.
Thanks
GangQuoted 26 lines · Junxiao Bi
Quoted 1 line
From ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implemtation,
slot number is 32 bits, usually this will not cause any issue, because slot number is converting from u16 to u32, but
OCFS2_INVALID_SLOTwas defined as -1, when an invalid slot number from disk was got, it value was (u16)-1, and it was converted to u32, then the following checking inget_local_system_inodewill be always skipped.static struct inode **get_local_system_inode(struct ocfs2_super *osb, int type, u32 slot) { BUG_ON(slot == OCFS2_INVALID_SLOT); ... }Signed-off-by Junxiao Bi <[email protected]>--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)fs/ocfs2/ocfs2_fs.h +0
-0fs/ocfs2/ocfs2_fs.h line 296
Quoted 8 lines
fs/ocfs2/ocfs2_fs.h +1
-1@@ -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_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel
PATCH 4/4 ocfs2: fix value of OCFS2_INVALID_SLOT
In reply to Joseph QiHi Joseph and All,
Quoted 4 lines · Joseph Qi
Hi Gang,
From the call tree it seems has relation with steal slot.
Could you try the following patch in linux-next:88b4270f4999("ocfs2: change slot number type s16 to u16")
When I delete the commit(9277f8 ocfs2: fix value of OCFS2_INVALID_SLOT), the problem (as below) does not happen again.
I will try the patch(88b4270f4999 ocfs2: change slot number type s16 to u16), to see if which can help the commit 9277f8.
Thanks
Gang
Quoted 115 lines
Thanks,
JosephQuoted 109 lines · Gang He
Hello Junxiao,
Thank for your patches, which looks to fix the nfsd access problem. But the patches bring a new bug, like below,
[ 251.406698] BUG: unable to handle kernel paging request at 0000565336a6bdf8 [ 251.406706] #PF error: [WRITE] [ 251.406710] PGD 0 P4D 0 [ 251.406717] Oops: 0002 [#1] SMP PTI [ 251.406724] CPU: 3 PID: 3758 Comm: mkdir Tainted: G OE 5.0.6-1-default #1 openSUSE Tumbleweed (unreleased) [ 251.406729] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20151112_172657-sheep25 04/01/2014 [ 251.406739] RIP: 0010:_raw_spin_lock+0xc/0x20 [ 251.406743] Code: 02 00 00 f0 0f c1 03 a9 ff 01 00 00 75 06 48 89 e8 5b 5d c3 48 89 df e8 a2 4f 87 ff eb f0 0f 1f 44 00 00 31 c0 ba 01 00 00 00 <f0> 0f b1 17 75 01 c3 89 c6 e8 76 3a 87 ff 66 90 c3 0f 1f 00 0f 1f [ 251.406750] RSP: 0018:ffffb65401087bf0 EFLAGS: 00010246 [ 251.406755] RAX: 0000000000000000 RBX: 0000565336a6bd70 RCX: 00000000ffffffff [ 251.406759] RDX: 0000000000000001 RSI: 0000000000000009 RDI: 0000565336a6bdf8 [ 251.406763] RBP: 0000565336a6bdf8 R08: 0000000000000000 R09: 0000000000000000 [ 251.406767] R10: 0000000000000005 R11: ffff9d7ded1bb000 R12: ffff9d7e38c559d0 [ 251.406771] R13: ffff9d7e39354be8 R14: ffff9d7e393540c8 R15: 00000000ffffffff [ 251.406777] FS: 00007f32d9e39c40(0000) GS:ffff9d7e3db80000(0000) knlGS:0000000000000000 [ 251.406782] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 251.406788] CR2: 0000565336a6bdf8 CR3: 0000000076496000 CR4: 00000000000006e0 [ 251.406801] Call Trace: [ 251.406824] igrab+0x19/0x50 [ 251.406941] ocfs2_get_system_file_inode+0x65/0x2e0 [ocfs2] [ 251.406980] ? ocfs2_find_entry+0x354/0x7f0 [ocfs2] [ 251.407025] ocfs2_reserve_suballoc_bits+0x3b/0x450 [ocfs2] [ 251.407070] ocfs2_steal_resource+0x8d/0x100 [ocfs2] [ 251.407113] ocfs2_reserve_new_inode+0x97/0x3d0 [ocfs2] [ 251.407154] ocfs2_mknod+0x3a7/0xe70 [ocfs2] [ 251.407191] ? __ocfs2_cluster_unlock.isra.47+0x24/0xd0 [ocfs2] [ 251.407231] ocfs2_mkdir+0x33/0x120 [ocfs2] [ 251.407239] ? inode_permission+0xbe/0x180 [ 251.407244] vfs_mkdir+0x102/0x1b0 [ 251.407250] do_mkdirat+0xd9/0x100 [ 251.407258] do_syscall_64+0x60/0x110 [ 251.407265] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 251.407271] RIP: 0033:0x7f32d9fbf307 [ 251.407276] Code: 1f 40 00 48 8b 05 91 eb 0c 00 64 c7 00 5f 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 b8 53 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 61 eb 0c 00 f7 d8 64 89 01 48 [ 251.407283] RSP: 002b:00007fff36999c98 EFLAGS: 00000202 ORIG_RAX: 0000000000000053 [ 251.407289] RAX: ffffffffffffffda RBX: 00007fff3699b618 RCX: 00007f32d9fbf307 [ 251.407294] RDX: 0000000000000000 RSI: 00000000000001ff RDI: 00007fff3699b618 [ 251.407298] RBP: 00007fff3699b618 R08: 00000000000001ff R09:
000055a9fe8b2c00I feel the problem looks related to this patch.
Thanks
GangQuoted 26 lines · Junxiao Bi
Quoted 1 line
From ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implemtation,
slot number is 32 bits, usually this will not cause any issue, because slot number is converting from u16 to u32, but
OCFS2_INVALID_SLOTwas defined as -1, when an invalid slot number from disk was got, it value was (u16)-1, and it was converted to u32, then the following checking inget_local_system_inodewill be always skipped.static struct inode **get_local_system_inode(struct ocfs2_super *osb, int type, u32 slot) { BUG_ON(slot == OCFS2_INVALID_SLOT); ... }Signed-off-by Junxiao Bi <[email protected]>--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)fs/ocfs2/ocfs2_fs.h +0
-0fs/ocfs2/ocfs2_fs.h line 296
Quoted 8 lines
fs/ocfs2/ocfs2_fs.h +1
-1@@ -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_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel
PATCH 4/4 ocfs2: fix value of OCFS2_INVALID_SLOT
Hi Guys,
Quoted 11 lines · Gang He
Hi Joseph and All,
Quoted 4 lines · Joseph Qi
Hi Gang,
From the call tree it seems has relation with steal slot.
Could you try the following patch in linux-next:88b4270f4999("ocfs2: change slot number type s16 to u16")When I delete the
commit(9277f8 ocfs2: fix value of OCFS2_INVALID_SLOT), the problem (as below) does not happen again.
I will try the patch(88b4270f4999 ocfs2: change slot number type s16 to u16), to see if which can help the commit 9277f8.
Apply the patch (88b4270f4999 ocfs2: change slot number type s16 to u16), the problem does not happen.
That means this patch fixed the patch (9277f8334ffc ocfs2: fix value of OCFS2_INVALID_SLOT).
Thanks
Gang
Quoted 127 lines
Thanks
GangQuoted 115 lines
Thanks,
JosephQuoted 109 lines · Gang He
Hello Junxiao,
Thank for your patches, which looks to fix the nfsd access problem. But the patches bring a new bug, like below,
[ 251.406698] BUG: unable to handle kernel paging request at 0000565336a6bdf8 [ 251.406706] #PF error: [WRITE] [ 251.406710] PGD 0 P4D 0 [ 251.406717] Oops: 0002 [#1] SMP PTI [ 251.406724] CPU: 3 PID: 3758 Comm: mkdir Tainted: G OE 5.0.6-1-default #1 openSUSE Tumbleweed (unreleased) [ 251.406729] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20151112_172657-sheep25 04/01/2014 [ 251.406739] RIP: 0010:_raw_spin_lock+0xc/0x20 [ 251.406743] Code: 02 00 00 f0 0f c1 03 a9 ff 01 00 00 75 06 48 89 e8 5b 5d c3 48 89 df e8 a2 4f 87 ff eb f0 0f 1f 44 00 00 31 c0 ba 01 00 00 00 <f0> 0f b1 17 75 01 c3 89 c6 e8 76 3a 87 ff 66 90 c3 0f 1f 00 0f 1f [ 251.406750] RSP: 0018:ffffb65401087bf0 EFLAGS: 00010246 [ 251.406755] RAX: 0000000000000000 RBX: 0000565336a6bd70 RCX: 00000000ffffffff [ 251.406759] RDX: 0000000000000001 RSI: 0000000000000009 RDI: 0000565336a6bdf8 [ 251.406763] RBP: 0000565336a6bdf8 R08: 0000000000000000 R09: 0000000000000000 [ 251.406767] R10: 0000000000000005 R11: ffff9d7ded1bb000 R12: ffff9d7e38c559d0 [ 251.406771] R13: ffff9d7e39354be8 R14: ffff9d7e393540c8 R15: 00000000ffffffff [ 251.406777] FS: 00007f32d9e39c40(0000) GS:ffff9d7e3db80000(0000) knlGS:0000000000000000 [ 251.406782] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 251.406788] CR2: 0000565336a6bdf8 CR3: 0000000076496000 CR4: 00000000000006e0 [ 251.406801] Call Trace: [ 251.406824] igrab+0x19/0x50 [ 251.406941] ocfs2_get_system_file_inode+0x65/0x2e0 [ocfs2] [ 251.406980] ? ocfs2_find_entry+0x354/0x7f0 [ocfs2] [ 251.407025] ocfs2_reserve_suballoc_bits+0x3b/0x450 [ocfs2] [ 251.407070] ocfs2_steal_resource+0x8d/0x100 [ocfs2] [ 251.407113] ocfs2_reserve_new_inode+0x97/0x3d0 [ocfs2] [ 251.407154] ocfs2_mknod+0x3a7/0xe70 [ocfs2] [ 251.407191] ? __ocfs2_cluster_unlock.isra.47+0x24/0xd0 [ocfs2] [ 251.407231] ocfs2_mkdir+0x33/0x120 [ocfs2] [ 251.407239] ? inode_permission+0xbe/0x180 [ 251.407244] vfs_mkdir+0x102/0x1b0 [ 251.407250] do_mkdirat+0xd9/0x100 [ 251.407258] do_syscall_64+0x60/0x110 [ 251.407265] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 251.407271] RIP: 0033:0x7f32d9fbf307 [ 251.407276] Code: 1f 40 00 48 8b 05 91 eb 0c 00 64 c7 00 5f 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 b8 53 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 61 eb 0c 00 f7 d8 64 89 01 48 [ 251.407283] RSP: 002b:00007fff36999c98 EFLAGS: 00000202 ORIG_RAX: 0000000000000053 [ 251.407289] RAX: ffffffffffffffda RBX: 00007fff3699b618 RCX: 00007f32d9fbf307 [ 251.407294] RDX: 0000000000000000 RSI: 00000000000001ff RDI: 00007fff3699b618 [ 251.407298] RBP: 00007fff3699b618 R08: 00000000000001ff R09:
000055a9fe8b2c00I feel the problem looks related to this patch.
Thanks
GangQuoted 26 lines · Junxiao Bi
Quoted 1 line
From ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implemtation,
slot number is 32 bits, usually this will not cause any issue, because slot number is converting from u16 to u32, but
OCFS2_INVALID_SLOTwas defined as -1, when an invalid slot number from disk was got, it value was (u16)-1, and it was converted to u32, then the following checking inget_local_system_inodewill be always skipped.static struct inode **get_local_system_inode(struct ocfs2_super *osb, int type, u32 slot) { BUG_ON(slot == OCFS2_INVALID_SLOT); ... }Signed-off-by Junxiao Bi <[email protected]>--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)fs/ocfs2/ocfs2_fs.h +0
-0fs/ocfs2/ocfs2_fs.h line 296
Quoted 8 lines
fs/ocfs2/ocfs2_fs.h +1
-1@@ -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_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel
Joseph Qi
maintainerPATCH 4/4 ocfs2: fix value of OCFS2_INVALID_SLOT
Quoted 10 lines · Gang He
Hi Guys,
Quoted 7 lines · Gang He
Hi Joseph and All,
Quoted 4 lines · Joseph Qi
Hi Gang,
From the call tree it seems has relation with steal slot.
Could you try the following patch in linux-next:88b4270f4999("ocfs2: change slot number type s16 to u16")
Quoted 9 lines
Quoted 4 lines
When I delete the
commit(9277f8 ocfs2: fix value of OCFS2_INVALID_SLOT), the problem (as below) does not happen again.
I will try the patch(88b4270f4999 ocfs2: change slot number type s16 to u16), to see if which can help the commit 9277f8.Apply the patch (
88b4270f4999ocfs2: change slot number type s16 to u16), the problem does not happen.
That means this patch fixed the patch (9277f8334ffcocfs2: fix value ofOCFS2_INVALID_SLOT).
So this patch should also cc stable, right?
Thanks,
Joseph
Quoted 126 lines
Quoted 114 lines
Quoted 101 lines · Gang He
Quoted 99 lines
Hello Junxiao,
Thank for your patches, which looks to fix the nfsd access problem. But the patches bring a new bug, like below,
[ 251.406698] BUG: unable to handle kernel paging request at 0000565336a6bdf8 [ 251.406706] #PF error: [WRITE] [ 251.406710] PGD 0 P4D 0 [ 251.406717] Oops: 0002 [#1] SMP PTI [ 251.406724] CPU: 3 PID: 3758 Comm: mkdir Tainted: G OE 5.0.6-1-default #1 openSUSE Tumbleweed (unreleased) [ 251.406729] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20151112_172657-sheep25 04/01/2014 [ 251.406739] RIP: 0010:_raw_spin_lock+0xc/0x20 [ 251.406743] Code: 02 00 00 f0 0f c1 03 a9 ff 01 00 00 75 06 48 89 e8 5b 5d c3 48 89 df e8 a2 4f 87 ff eb f0 0f 1f 44 00 00 31 c0 ba 01 00 00 00 <f0> 0f b1 17 75 01 c3 89 c6 e8 76 3a 87 ff 66 90 c3 0f 1f 00 0f 1f [ 251.406750] RSP: 0018:ffffb65401087bf0 EFLAGS: 00010246 [ 251.406755] RAX: 0000000000000000 RBX: 0000565336a6bd70 RCX: 00000000ffffffff [ 251.406759] RDX: 0000000000000001 RSI: 0000000000000009 RDI: 0000565336a6bdf8 [ 251.406763] RBP: 0000565336a6bdf8 R08: 0000000000000000 R09: 0000000000000000 [ 251.406767] R10: 0000000000000005 R11: ffff9d7ded1bb000 R12: ffff9d7e38c559d0 [ 251.406771] R13: ffff9d7e39354be8 R14: ffff9d7e393540c8 R15: 00000000ffffffff [ 251.406777] FS: 00007f32d9e39c40(0000) GS:ffff9d7e3db80000(0000) knlGS:0000000000000000 [ 251.406782] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 251.406788] CR2: 0000565336a6bdf8 CR3: 0000000076496000 CR4: 00000000000006e0 [ 251.406801] Call Trace: [ 251.406824] igrab+0x19/0x50 [ 251.406941] ocfs2_get_system_file_inode+0x65/0x2e0 [ocfs2] [ 251.406980] ? ocfs2_find_entry+0x354/0x7f0 [ocfs2] [ 251.407025] ocfs2_reserve_suballoc_bits+0x3b/0x450 [ocfs2] [ 251.407070] ocfs2_steal_resource+0x8d/0x100 [ocfs2] [ 251.407113] ocfs2_reserve_new_inode+0x97/0x3d0 [ocfs2] [ 251.407154] ocfs2_mknod+0x3a7/0xe70 [ocfs2] [ 251.407191] ? __ocfs2_cluster_unlock.isra.47+0x24/0xd0 [ocfs2] [ 251.407231] ocfs2_mkdir+0x33/0x120 [ocfs2] [ 251.407239] ? inode_permission+0xbe/0x180 [ 251.407244] vfs_mkdir+0x102/0x1b0 [ 251.407250] do_mkdirat+0xd9/0x100 [ 251.407258] do_syscall_64+0x60/0x110 [ 251.407265] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 251.407271] RIP: 0033:0x7f32d9fbf307 [ 251.407276] Code: 1f 40 00 48 8b 05 91 eb 0c 00 64 c7 00 5f 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 b8 53 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 61 eb 0c 00 f7 d8 64 89 01 48 [ 251.407283] RSP: 002b:00007fff36999c98 EFLAGS: 00000202 ORIG_RAX: 0000000000000053 [ 251.407289] RAX: ffffffffffffffda RBX: 00007fff3699b618 RCX: 00007f32d9fbf307 [ 251.407294] RDX: 0000000000000000 RSI: 00000000000001ff RDI: 00007fff3699b618 [ 251.407298] RBP: 00007fff3699b618 R08: 00000000000001ff R09:
000055a9fe8b2c00I feel the problem looks related to this patch.
Thanks
GangQuoted 31 lines · Junxiao Bi
Quoted 1 line
From ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implemtation,
slot number is 32 bits, usually this will not cause any issue, because slot number is converting from u16 to u32, but
OCFS2_INVALID_SLOTwas defined as -1, when an invalid slot number from disk was got, it value was (u16)-1, and it was converted to u32, then the following checking inget_local_system_inodewill be always skipped.static struct inode **get_local_system_inode(struct ocfs2_super *osb, int type, u32 slot) { BUG_ON(slot == OCFS2_INVALID_SLOT); ... }Signed-off-by Junxiao Bi <[email protected]>--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)fs/ocfs2/ocfs2_fs.h +1
-1@@ -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)Quoted 11 lines
Quoted 10 lines
fs/ocfs2/ocfs2_fs.h line 296
Quoted 3 lines
fs/ocfs2/ocfs2_fs.h +0
-0#define OCFS2_VOL_UUID_LEN 16#define OCFS2_MAX_VOL_LABEL_LEN 64_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-develQuoted 5 lines
_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel
PATCH 4/4 ocfs2: fix value of OCFS2_INVALID_SLOT
Quoted 17 lines · Joseph Qi
Quoted 14 lines · Gang He
Hi Guys,
Quoted 11 lines · Gang He
Hi Joseph and All,
Quoted 4 lines · Joseph Qi
Hi Gang,
From the call tree it seems has relation with steal slot.
Could you try the following patch in linux-next:88b4270f4999("ocfs2: change slot number type s16 to u16")When I delete the
commit(9277f8 ocfs2: fix value of OCFS2_INVALID_SLOT), the problem (as below) does not happen again.
I will try the patch(88b4270f4999 ocfs2: change slot number type s16 to u16), to see if which can help the commit 9277f8.
Quoted 7 lines
Quoted 5 lines
Apply the patch (
88b4270f4999ocfs2: change slot number type s16 to u16), the problem does not happen.
That means this patch fixed the patch (9277f8334ffcocfs2: fix value ofOCFS2_INVALID_SLOT).So this patch should also cc stable, right?
Depend on the patch 9277f8334ffc ("ocfs2: fix value of OCFS2_INVALID_SLOT"), the patch 88b4270f4999 must go along with the patch 9277f8334ffc.
Thanks
Gang
Quoted 131 lines
Thanks,
JosephQuoted 126 lines
Quoted 114 lines
Quoted 101 lines · Gang He
Quoted 99 lines
Hello Junxiao,
Thank for your patches, which looks to fix the nfsd access problem. But the patches bring a new bug, like below,
[ 251.406698] BUG: unable to handle kernel paging request at 0000565336a6bdf8 [ 251.406706] #PF error: [WRITE] [ 251.406710] PGD 0 P4D 0 [ 251.406717] Oops: 0002 [#1] SMP PTI [ 251.406724] CPU: 3 PID: 3758 Comm: mkdir Tainted: G OE 5.0.6-1-default #1 openSUSE Tumbleweed (unreleased) [ 251.406729] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20151112_172657-sheep25 04/01/2014 [ 251.406739] RIP: 0010:_raw_spin_lock+0xc/0x20 [ 251.406743] Code: 02 00 00 f0 0f c1 03 a9 ff 01 00 00 75 06 48 89 e8 5b 5d c3 48 89 df e8 a2 4f 87 ff eb f0 0f 1f 44 00 00 31 c0 ba 01 00 00 00 <f0> 0f b1 17 75 01 c3 89 c6 e8 76 3a 87 ff 66 90 c3 0f 1f 00 0f 1f [ 251.406750] RSP: 0018:ffffb65401087bf0 EFLAGS: 00010246 [ 251.406755] RAX: 0000000000000000 RBX: 0000565336a6bd70 RCX: 00000000ffffffff [ 251.406759] RDX: 0000000000000001 RSI: 0000000000000009 RDI: 0000565336a6bdf8 [ 251.406763] RBP: 0000565336a6bdf8 R08: 0000000000000000 R09: 0000000000000000 [ 251.406767] R10: 0000000000000005 R11: ffff9d7ded1bb000 R12: ffff9d7e38c559d0 [ 251.406771] R13: ffff9d7e39354be8 R14: ffff9d7e393540c8 R15: 00000000ffffffff [ 251.406777] FS: 00007f32d9e39c40(0000) GS:ffff9d7e3db80000(0000) knlGS:0000000000000000 [ 251.406782] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 251.406788] CR2: 0000565336a6bdf8 CR3: 0000000076496000 CR4: 00000000000006e0 [ 251.406801] Call Trace: [ 251.406824] igrab+0x19/0x50 [ 251.406941] ocfs2_get_system_file_inode+0x65/0x2e0 [ocfs2] [ 251.406980] ? ocfs2_find_entry+0x354/0x7f0 [ocfs2] [ 251.407025] ocfs2_reserve_suballoc_bits+0x3b/0x450 [ocfs2] [ 251.407070] ocfs2_steal_resource+0x8d/0x100 [ocfs2] [ 251.407113] ocfs2_reserve_new_inode+0x97/0x3d0 [ocfs2] [ 251.407154] ocfs2_mknod+0x3a7/0xe70 [ocfs2] [ 251.407191] ? __ocfs2_cluster_unlock.isra.47+0x24/0xd0 [ocfs2] [ 251.407231] ocfs2_mkdir+0x33/0x120 [ocfs2] [ 251.407239] ? inode_permission+0xbe/0x180 [ 251.407244] vfs_mkdir+0x102/0x1b0 [ 251.407250] do_mkdirat+0xd9/0x100 [ 251.407258] do_syscall_64+0x60/0x110 [ 251.407265] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 251.407271] RIP: 0033:0x7f32d9fbf307 [ 251.407276] Code: 1f 40 00 48 8b 05 91 eb 0c 00 64 c7 00 5f 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 b8 53 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 61 eb 0c 00 f7 d8 64 89 01 48 [ 251.407283] RSP: 002b:00007fff36999c98 EFLAGS: 00000202 ORIG_RAX: 0000000000000053 [ 251.407289] RAX: ffffffffffffffda RBX: 00007fff3699b618 RCX: 00007f32d9fbf307 [ 251.407294] RDX: 0000000000000000 RSI: 00000000000001ff RDI: 00007fff3699b618 [ 251.407298] RBP: 00007fff3699b618 R08: 00000000000001ff R09:
000055a9fe8b2c00I feel the problem looks related to this patch.
Thanks
GangQuoted 31 lines · Junxiao Bi
Quoted 1 line
From ocfs2 disk layout, slot number is 16 bits, but in ocfs2 implemtation,
slot number is 32 bits, usually this will not cause any issue, because slot number is converting from u16 to u32, but
OCFS2_INVALID_SLOTwas defined as -1, when an invalid slot number from disk was got, it value was (u16)-1, and it was converted to u32, then the following checking inget_local_system_inodewill be always skipped.static struct inode **get_local_system_inode(struct ocfs2_super *osb, int type, u32 slot) { BUG_ON(slot == OCFS2_INVALID_SLOT); ... }Signed-off-by Junxiao Bi <[email protected]>--- fs/ocfs2/ocfs2_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)fs/ocfs2/ocfs2_fs.h +1
-1@@ -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)Quoted 11 lines
Quoted 10 lines
fs/ocfs2/ocfs2_fs.h line 296
Quoted 3 lines
fs/ocfs2/ocfs2_fs.h +0
-0#define OCFS2_VOL_UUID_LEN 16#define OCFS2_MAX_VOL_LABEL_LEN 64_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-develQuoted 5 lines
_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel