From a4dad1ae24f850410c4e60f22823cba1289b8d52 Mon Sep 17 00:00:00 2001 From: David Turner Date: Tue, 24 Nov 2015 14:34:37 -0500 Subject: ext4: Fix handling of extended tv_sec In ext4, the bottom two bits of {a,c,m}time_extra are used to extend the {a,c,m}time fields, deferring the year 2038 problem to the year 2446. When decoding these extended fields, for times whose bottom 32 bits would represent a negative number, sign extension causes the 64-bit extended timestamp to be negative as well, which is not what's intended. This patch corrects that issue, so that the only negative {a,c,m}times are those between 1901 and 1970 (as per 32-bit signed timestamps). Some older kernels might have written pre-1970 dates with 1,1 in the extra bits. This patch treats those incorrectly-encoded dates as pre-1970, instead of post-2311, until kernel 4.20 is released. Hopefully by then e2fsck will have fixed up the bad data. Also add a comment explaining the encoding of ext4's extra {a,c,m}time bits. Signed-off-by: David Turner Signed-off-by: Theodore Ts'o Reported-by: Mark Harris Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=23732 Cc: stable@vger.kernel.org --- fs/ext4/ext4.h | 51 ++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 44 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 750063f7a50c..cc7ca4e87144 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -727,19 +728,55 @@ struct move_extent { <= (EXT4_GOOD_OLD_INODE_SIZE + \ (einode)->i_extra_isize)) \ +/* + * We use an encoding that preserves the times for extra epoch "00": + * + * extra msb of adjust for signed + * epoch 32-bit 32-bit tv_sec to + * bits time decoded 64-bit tv_sec 64-bit tv_sec valid time range + * 0 0 1 -0x80000000..-0x00000001 0x000000000 1901-12-13..1969-12-31 + * 0 0 0 0x000000000..0x07fffffff 0x000000000 1970-01-01..2038-01-19 + * 0 1 1 0x080000000..0x0ffffffff 0x100000000 2038-01-19..2106-02-07 + * 0 1 0 0x100000000..0x17fffffff 0x100000000 2106-02-07..2174-02-25 + * 1 0 1 0x180000000..0x1ffffffff 0x200000000 2174-02-25..2242-03-16 + * 1 0 0 0x200000000..0x27fffffff 0x200000000 2242-03-16..2310-04-04 + * 1 1 1 0x280000000..0x2ffffffff 0x300000000 2310-04-04..2378-04-22 + * 1 1 0 0x300000000..0x37fffffff 0x300000000 2378-04-22..2446-05-10 + * + * Note that previous versions of the kernel on 64-bit systems would + * incorrectly use extra epoch bits 1,1 for dates between 1901 and + * 1970. e2fsck will correct this, assuming that it is run on the + * affected filesystem before 2242. + */ + static inline __le32 ext4_encode_extra_time(struct timespec *time) { - return cpu_to_le32((sizeof(time->tv_sec) > 4 ? - (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) | - ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK)); + u32 extra = sizeof(time->tv_sec) > 4 ? + ((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0; + return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS)); } static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra) { - if (sizeof(time->tv_sec) > 4) - time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) - << 32; - time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; + if (unlikely(sizeof(time->tv_sec) > 4 && + (extra & cpu_to_le32(EXT4_EPOCH_MASK)))) { +#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0) + /* Handle legacy encoding of pre-1970 dates with epoch + * bits 1,1. We assume that by kernel version 4.20, + * everyone will have run fsck over the affected + * filesystems to correct the problem. (This + * backwards compatibility may be removed before this + * time, at the discretion of the ext4 developers.) + */ + u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK; + if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0) + extra_bits = 0; + time->tv_sec += extra_bits << 32; +#else + time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32; +#endif + } + time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; } #define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ -- cgit v1.2.1 From bc23f0c8d7ccd8d924c4e70ce311288cb3e61ea8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 24 Nov 2015 15:34:35 -0500 Subject: jbd2: Fix unreclaimed pages after truncate in data=journal mode Ted and Namjae have reported that truncated pages don't get timely reclaimed after being truncated in data=journal mode. The following test triggers the issue easily: for (i = 0; i < 1000; i++) { pwrite(fd, buf, 1024*1024, 0); fsync(fd); fsync(fd); ftruncate(fd, 0); } The reason is that journal_unmap_buffer() finds that truncated buffers are not journalled (jh->b_transaction == NULL), they are part of checkpoint list of a transaction (jh->b_cp_transaction != NULL) and have been already written out (!buffer_dirty(bh)). We clean such buffers but we leave them in the checkpoint list. Since checkpoint transaction holds a reference to the journal head, these buffers cannot be released until the checkpoint transaction is cleaned up. And at that point we don't call release_buffer_page() anymore so pages detached from mapping are lingering in the system waiting for reclaim to find them and free them. Fix the problem by removing buffers from transaction checkpoint lists when journal_unmap_buffer() finds out they don't have to be there anymore. Reported-and-tested-by: Namjae Jeon Fixes: de1b794130b130e77ffa975bb58cb843744f9ae5 Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Cc: stable@vger.kernel.org --- fs/jbd2/transaction.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6b8338ec2464..b99621277c66 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2152,6 +2152,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, if (!buffer_dirty(bh)) { /* bdflush has written it. We can drop it now */ + __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } @@ -2181,6 +2182,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, /* The orphan record's transaction has * committed. We can cleanse this buffer */ clear_buffer_jbddirty(bh); + __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } } -- cgit v1.2.1 From e2c9e0b28e146c9a3bce21408f3c02e24ac7ac31 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 26 Nov 2015 15:20:19 -0500 Subject: ext4: fix an endianness bug in ext4_encrypted_zeroout() ex->ee_block is not host-endian (note that accesses of other fields of *ex right next to that line go through the helpers that do proper conversion from little-endian to host-endian; it might make sense to add similar for ->ee_block to avoid reintroducing that kind of bugs...) Cc: stable@vger.kernel.org # v4.1+ Signed-off-by: Al Viro Signed-off-by: Theodore Ts'o --- fs/ext4/crypto.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index af06830bfc00..1a0835073663 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -389,7 +389,7 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) struct ext4_crypto_ctx *ctx; struct page *ciphertext_page = NULL; struct bio *bio; - ext4_lblk_t lblk = ex->ee_block; + ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); ext4_fsblk_t pblk = ext4_ext_pblock(ex); unsigned int len = ext4_ext_get_actual_len(ex); int ret, err = 0; -- cgit v1.2.1 From 5a1c7f47da9b32d0671e776b0f388095b7f91e2e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 26 Nov 2015 15:20:50 -0500 Subject: ext4: fix an endianness bug in ext4_encrypted_follow_link() applying le32_to_cpu() to 16bit value is a bad idea... Cc: stable@vger.kernel.org # v4.1+ Signed-off-by: Al Viro Signed-off-by: Theodore Ts'o --- fs/ext4/symlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index abe2401ce405..e8e7af62ac95 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -52,7 +52,7 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook /* Symlink is encrypted */ sd = (struct ext4_encrypted_symlink_data *)caddr; cstr.name = sd->encrypted_path; - cstr.len = le32_to_cpu(sd->len); + cstr.len = le16_to_cpu(sd->len); if ((cstr.len + sizeof(struct ext4_encrypted_symlink_data) - 1) > max_size) { -- cgit v1.2.1 From 681c46b164d79aaa5d18f7519b39e29f9b441e40 Mon Sep 17 00:00:00 2001 From: Xu Cang Date: Thu, 26 Nov 2015 15:52:24 -0500 Subject: ext4: add "static" to ext4_seq_##name##_fops struct to fix sparse warning, add static to ext4_seq_##name##_fops struct. Signed-off-by: Theodore Ts'o --- fs/ext4/sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 1b57c72f4a00..1420a3c614af 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -358,7 +358,7 @@ static int name##_open(struct inode *inode, struct file *file) \ return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \ } \ \ -const struct file_operations ext4_seq_##name##_fops = { \ +static const struct file_operations ext4_seq_##name##_fops = { \ .owner = THIS_MODULE, \ .open = name##_open, \ .read = seq_read, \ -- cgit v1.2.1 From 087ffd4eae9929afd06f6a709861df3c3508492a Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Fri, 4 Dec 2015 12:29:28 -0500 Subject: jbd2: fix null committed data return in undo_access introduced jbd2_write_access_granted() to improve write|undo_access speed, but missed to check the status of b_committed_data which caused a kernel panic on ocfs2. [ 6538.405938] ------------[ cut here ]------------ [ 6538.406686] kernel BUG at fs/ocfs2/suballoc.c:2400! [ 6538.406686] invalid opcode: 0000 [#1] SMP [ 6538.406686] 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 xen_fbfront parport_pc parport pcspkr i2c_piix4 acpi_cpufreq ext4 jbd2 mbcache xen_blkfront floppy pata_acpi ata_generic ata_piix cirrus ttm drm_kms_helper drm fb_sys_fops sysimgblt sysfillrect i2c_core syscopyarea dm_mirror dm_region_hash dm_log dm_mod [ 6538.406686] CPU: 1 PID: 16265 Comm: mmap_truncate Not tainted 4.3.0 #1 [ 6538.406686] Hardware name: Xen HVM domU, BIOS 4.3.1OVM 05/14/2014 [ 6538.406686] task: ffff88007c2bab00 ti: ffff880075b78000 task.ti: ffff880075b78000 [ 6538.406686] RIP: 0010:[] [] ocfs2_block_group_clear_bits+0x23b/0x250 [ocfs2] [ 6538.406686] RSP: 0018:ffff880075b7b7f8 EFLAGS: 00010246 [ 6538.406686] RAX: ffff8800760c5b40 RBX: ffff88006c06a000 RCX: ffffffffa06e6df0 [ 6538.406686] RDX: 0000000000000000 RSI: ffff88007a6f6ea0 RDI: ffff88007a760430 [ 6538.406686] RBP: ffff880075b7b878 R08: 0000000000000002 R09: 0000000000000001 [ 6538.406686] R10: ffffffffa06769be R11: 0000000000000000 R12: 0000000000000001 [ 6538.406686] R13: ffffffffa06a1750 R14: 0000000000000001 R15: ffff88007a6f6ea0 [ 6538.406686] FS: 00007f17fde30720(0000) GS:ffff88007f040000(0000) knlGS:0000000000000000 [ 6538.406686] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6538.406686] CR2: 0000000000601730 CR3: 000000007aea0000 CR4: 00000000000406e0 [ 6538.406686] Stack: [ 6538.406686] ffff88007c2bb5b0 ffff880075b7b8e0 ffff88007a7604b0 ffff88006c640800 [ 6538.406686] ffff88007a7604b0 ffff880075d77390 0000000075b7b878 ffffffffa06a309d [ 6538.406686] ffff880075d752d8 ffff880075b7b990 ffff880075b7b898 0000000000000000 [ 6538.406686] Call Trace: [ 6538.406686] [] ? ocfs2_read_group_descriptor+0x6d/0xa0 [ocfs2] [ 6538.406686] [] _ocfs2_free_suballoc_bits+0xe4/0x320 [ocfs2] [ 6538.406686] [] ? ocfs2_put_slot+0xf0/0xf0 [ocfs2] [ 6538.406686] [] _ocfs2_free_clusters+0xee/0x210 [ocfs2] [ 6538.406686] [] ? ocfs2_put_slot+0xf0/0xf0 [ocfs2] [ 6538.406686] [] ? ocfs2_put_slot+0xf0/0xf0 [ocfs2] [ 6538.406686] [] ? ocfs2_extend_trans+0x50/0x1a0 [ocfs2] [ 6538.406686] [] ocfs2_free_clusters+0x15/0x20 [ocfs2] [ 6538.406686] [] ocfs2_replay_truncate_records+0xfc/0x290 [ocfs2] [ 6538.406686] [] ? ocfs2_start_trans+0xec/0x1d0 [ocfs2] [ 6538.406686] [] __ocfs2_flush_truncate_log+0x140/0x2d0 [ocfs2] [ 6538.406686] [] ? ocfs2_reserve_blocks_for_rec_trunc.clone.0+0x44/0x170 [ocfs2] [ 6538.406686] [] ocfs2_remove_btree_range+0x374/0x630 [ocfs2] [ 6538.406686] [] ? jbd2_journal_stop+0x25b/0x470 [jbd2] [ 6538.406686] [] ocfs2_commit_truncate+0x305/0x670 [ocfs2] [ 6538.406686] [] ? ocfs2_journal_access_eb+0x20/0x20 [ocfs2] [ 6538.406686] [] ocfs2_truncate_file+0x297/0x380 [ocfs2] [ 6538.406686] [] ? jbd2_journal_begin_ordered_truncate+0x64/0xc0 [jbd2] [ 6538.406686] [] ocfs2_setattr+0x572/0x860 [ocfs2] [ 6538.406686] [] ? current_fs_time+0x3f/0x50 [ 6538.406686] [] notify_change+0x1d7/0x340 [ 6538.406686] [] ? generic_getxattr+0x79/0x80 [ 6538.406686] [] do_truncate+0x66/0x90 [ 6538.406686] [] ? __audit_syscall_entry+0xb0/0x110 [ 6538.406686] [] do_sys_ftruncate.clone.0+0xf3/0x120 [ 6538.406686] [] SyS_ftruncate+0xe/0x10 [ 6538.406686] [] entry_SYSCALL_64_fastpath+0x12/0x71 [ 6538.406686] Code: 28 48 81 ee b0 04 00 00 48 8b 92 50 fb ff ff 48 8b 80 b0 03 00 00 48 39 90 88 00 00 00 0f 84 30 fe ff ff 0f 0b eb fe 0f 0b eb fe <0f> 0b 0f 1f 00 eb fb 66 66 66 66 66 2e 0f 1f 84 00 00 00 00 00 [ 6538.406686] RIP [] ocfs2_block_group_clear_bits+0x23b/0x250 [ocfs2] [ 6538.406686] RSP [ 6538.691128] ---[ end trace 31cd7011d6770d7e ]--- [ 6538.694492] Kernel panic - not syncing: Fatal exception [ 6538.695484] Kernel Offset: disabled Fixes: de92c8caf16c("jbd2: speedup jbd2_journal_get_[write|undo]_access()") Cc: Signed-off-by: Junxiao Bi Signed-off-by: Theodore Ts'o --- fs/jbd2/transaction.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index b99621277c66..1498ad9f731a 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1009,7 +1009,8 @@ out: } /* Fast check whether buffer is already attached to the required transaction */ -static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh) +static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, + bool undo) { struct journal_head *jh; bool ret = false; @@ -1036,6 +1037,9 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh) jh = READ_ONCE(bh->b_private); if (!jh) goto out; + /* For undo access buffer must have data copied */ + if (undo && !jh->b_committed_data) + goto out; if (jh->b_transaction != handle->h_transaction && jh->b_next_transaction != handle->h_transaction) goto out; @@ -1073,7 +1077,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; int rc; - if (jbd2_write_access_granted(handle, bh)) + if (jbd2_write_access_granted(handle, bh, false)) return 0; jh = jbd2_journal_add_journal_head(bh); @@ -1210,7 +1214,7 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) char *committed_data = NULL; JBUFFER_TRACE(jh, "entry"); - if (jbd2_write_access_granted(handle, bh)) + if (jbd2_write_access_granted(handle, bh, true)) return 0; jh = jbd2_journal_add_journal_head(bh); -- cgit v1.2.1