From 8be04b9374e59923fa337766aaa74151b95b7099 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 19 Jun 2013 12:15:53 -0700 Subject: treewide: Add __GFP_NOWARN to k.alloc calls with v.alloc fallbacks Don't emit OOM warnings when k.alloc calls fail when there there is a v.alloc immediately afterwards. Converted a kmalloc/vmalloc with memset to kzalloc/vzalloc. Signed-off-by: Joe Perches Acked-by: "Theodore Ts'o" Signed-off-by: Jiri Kosina --- fs/ext4/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index bca26f34edf4..ffdfe385b029 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -162,7 +162,7 @@ void *ext4_kvmalloc(size_t size, gfp_t flags) { void *ret; - ret = kmalloc(size, flags); + ret = kmalloc(size, flags | __GFP_NOWARN); if (!ret) ret = __vmalloc(size, flags, PAGE_KERNEL); return ret; @@ -172,7 +172,7 @@ void *ext4_kvzalloc(size_t size, gfp_t flags) { void *ret; - ret = kzalloc(size, flags); + ret = kzalloc(size, flags | __GFP_NOWARN); if (!ret) ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL); return ret; -- cgit v1.2.3 From ad4eec613536dc7e5ea0c6e59849e6edca634d8b Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 28 Aug 2013 19:05:07 -0400 Subject: ext4: allow specifying external journal by pathname mount option It's always been a hassle that if an external journal's device number changes, the filesystem won't mount. And since boot-time enumeration can change, device number changes aren't unusual. The current mechanism to update the journal location is by passing in a mount option w/ a new devnum, but that's a hassle; it's a manual approach, fixing things after the fact. Adding a mount option, "-o journal_path=/dev/$DEVICE" would help, since then we can do i.e. # mount -o journal_path=/dev/disk/by-label/$JOURNAL_LABEL ... and it'll mount even if the devnum has changed, as shown here: # losetup /dev/loop0 journalfile # mke2fs -L mylabel-journal -O journal_dev /dev/loop0 # mkfs.ext4 -L mylabel -J device=/dev/loop0 /dev/sdb1 Change the journal device number: # losetup -d /dev/loop0 # losetup /dev/loop1 journalfile And today it will fail: # mount /dev/sdb1 /mnt/test mount: wrong fs type, bad option, bad superblock on /dev/sdb1, missing codepage or helper program, or other error In some cases useful info is found in syslog - try dmesg | tail or so # dmesg | tail -n 1 [17343.240702] EXT4-fs (sdb1): error: couldn't read superblock of external journal But with this new mount option, we can specify the new path: # mount -o journal_path=/dev/loop1 /dev/sdb1 /mnt/test # (which does update the encoded device number, incidentally): # umount /dev/sdb1 # dumpe2fs -h /dev/sdb1 | grep "Journal device" dumpe2fs 1.41.12 (17-May-2010) Journal device: 0x0701 But best of all we can just always mount by journal-path, and it'll always work: # mount -o journal_path=/dev/disk/by-label/mylabel-journal /dev/sdb1 /mnt/test # So the journal_path option can be specified in fstab, and as long as the disk is available somewhere, and findable by label (or by UUID), we can mount. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" Reviewed-by: Jan Kara Reviewed-by: Carlos Maiolino --- fs/ext4/super.c | 47 ++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 44 insertions(+), 3 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index b59373b625e9..42337141e79f 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1134,8 +1134,8 @@ enum { Opt_nouid32, Opt_debug, Opt_removed, Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, - Opt_commit, Opt_min_batch_time, Opt_max_batch_time, - Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit, + Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev, + Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, @@ -1179,6 +1179,7 @@ static const match_table_t tokens = { {Opt_min_batch_time, "min_batch_time=%u"}, {Opt_max_batch_time, "max_batch_time=%u"}, {Opt_journal_dev, "journal_dev=%u"}, + {Opt_journal_path, "journal_path=%s"}, {Opt_journal_checksum, "journal_checksum"}, {Opt_journal_async_commit, "journal_async_commit"}, {Opt_abort, "abort"}, @@ -1338,6 +1339,7 @@ static int clear_qf_name(struct super_block *sb, int qtype) #define MOPT_NO_EXT2 0x0100 #define MOPT_NO_EXT3 0x0200 #define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3) +#define MOPT_STRING 0x0400 static const struct mount_opts { int token; @@ -1387,6 +1389,7 @@ static const struct mount_opts { {Opt_resuid, 0, MOPT_GTE0}, {Opt_resgid, 0, MOPT_GTE0}, {Opt_journal_dev, 0, MOPT_GTE0}, + {Opt_journal_path, 0, MOPT_STRING}, {Opt_journal_ioprio, 0, MOPT_GTE0}, {Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ}, {Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ}, @@ -1480,7 +1483,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, return -1; } - if (args->from && match_int(args, &arg)) + if (args->from && !(m->flags & MOPT_STRING) && match_int(args, &arg)) return -1; if (args->from && (m->flags & MOPT_GTE0) && (arg < 0)) return -1; @@ -1544,6 +1547,44 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, return -1; } *journal_devnum = arg; + } else if (token == Opt_journal_path) { + char *journal_path; + struct inode *journal_inode; + struct path path; + int error; + + if (is_remount) { + ext4_msg(sb, KERN_ERR, + "Cannot specify journal on remount"); + return -1; + } + journal_path = match_strdup(&args[0]); + if (!journal_path) { + ext4_msg(sb, KERN_ERR, "error: could not dup " + "journal device string"); + return -1; + } + + error = kern_path(journal_path, LOOKUP_FOLLOW, &path); + if (error) { + ext4_msg(sb, KERN_ERR, "error: could not find " + "journal device path: error %d", error); + kfree(journal_path); + return -1; + } + + journal_inode = path.dentry->d_inode; + if (!S_ISBLK(journal_inode->i_mode)) { + ext4_msg(sb, KERN_ERR, "error: journal path %s " + "is not a block device", journal_path); + path_put(&path); + kfree(journal_path); + return -1; + } + + *journal_devnum = new_encode_dev(journal_inode->i_rdev); + path_put(&path); + kfree(journal_path); } else if (token == Opt_journal_ioprio) { if (arg > 7) { ext4_msg(sb, KERN_ERR, "Invalid journal IO priority" -- cgit v1.2.3 From 7b7a8665edd8db733980389b098530f9e4f630b2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 4 Sep 2013 15:04:39 +0200 Subject: direct-io: Implement generic deferred AIO completions Add support to the core direct-io code to defer AIO completions to user context using a workqueue. This replaces opencoded and less efficient code in XFS and ext4 (we save a memory allocation for each direct IO) and will be needed to properly support O_(D)SYNC for AIO. The communication between the filesystem and the direct I/O code requires a new buffer head flag, which is a bit ugly but not avoidable until the direct I/O code stops abusing the buffer_head structure for communicating with the filesystems. Currently this creates a per-superblock unbound workqueue for these completions, which is taken from an earlier patch by Jan Kara. I'm not really convinced about this use and would prefer a "normal" global workqueue with a high concurrency limit, but this needs further discussion. JK: Fixed ext4 part, dynamic allocation of the workqueue. Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara Signed-off-by: Al Viro --- fs/ext4/super.c | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index b59373b625e9..5db4f0df8174 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -762,9 +762,7 @@ static void ext4_put_super(struct super_block *sb) ext4_unregister_li_request(sb); dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); - flush_workqueue(sbi->unrsv_conversion_wq); flush_workqueue(sbi->rsv_conversion_wq); - destroy_workqueue(sbi->unrsv_conversion_wq); destroy_workqueue(sbi->rsv_conversion_wq); if (sbi->s_journal) { @@ -875,14 +873,12 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) #endif ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_rsv_conversion_list); - INIT_LIST_HEAD(&ei->i_unrsv_conversion_list); spin_lock_init(&ei->i_completed_io_lock); ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_ioend_count, 0); atomic_set(&ei->i_unwritten, 0); INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); - INIT_WORK(&ei->i_unrsv_conversion_work, ext4_end_io_unrsv_work); return &ei->vfs_inode; } @@ -3954,14 +3950,6 @@ no_journal: goto failed_mount4; } - EXT4_SB(sb)->unrsv_conversion_wq = - alloc_workqueue("ext4-unrsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); - if (!EXT4_SB(sb)->unrsv_conversion_wq) { - printk(KERN_ERR "EXT4-fs: failed to create workqueue\n"); - ret = -ENOMEM; - goto failed_mount4; - } - /* * The jbd2_journal_load will have done any necessary log recovery, * so we can safely mount the rest of the filesystem now. @@ -4115,8 +4103,6 @@ failed_mount4: ext4_msg(sb, KERN_ERR, "mount failed"); if (EXT4_SB(sb)->rsv_conversion_wq) destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq); - if (EXT4_SB(sb)->unrsv_conversion_wq) - destroy_workqueue(EXT4_SB(sb)->unrsv_conversion_wq); failed_mount_wq: if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); @@ -4564,7 +4550,6 @@ static int ext4_sync_fs(struct super_block *sb, int wait) trace_ext4_sync_fs(sb, wait); flush_workqueue(sbi->rsv_conversion_wq); - flush_workqueue(sbi->unrsv_conversion_wq); /* * Writeback quota in non-journalled quota case - journalled quota has * no dirty dquots @@ -4600,7 +4585,6 @@ static int ext4_sync_fs_nojournal(struct super_block *sb, int wait) trace_ext4_sync_fs(sb, wait); flush_workqueue(EXT4_SB(sb)->rsv_conversion_wq); - flush_workqueue(EXT4_SB(sb)->unrsv_conversion_wq); dquot_writeback_dquots(sb, -1); if (wait && test_opt(sb, BARRIER)) ret = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL); -- cgit v1.2.3