ext4: use ext4_get_block_write in buffer write

Allocate uninitialized extent before ext4 buffer write and
convert the extent to initialized after io completes.
The purpose is to make sure an extent can only be marked
initialized after it has been written with new data so
we can safely drop the i_mutex lock in ext4 DIO read without
exposing stale data. This helps to improve multi-thread DIO
read performance on high-speed disks.

Skip the nobh and data=journal mount cases to make things simple for now.

Signed-off-by: Jiaying Zhang <jiayingz@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

1 files changed, 33 insertions, 4 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index dc7a97e79e3b..5e8f9077b0fc 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -709,6 +709,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
         ei->i_reserved_quota = 0;
 #endif
         INIT_LIST_HEAD(&ei->i_completed_io_list);
+        spin_lock_init(&ei->i_completed_io_lock);
         ei->cur_aio_dio = NULL;
         ei->i_sync_tid = 0;
         ei->i_datasync_tid = 0;
@@ -926,6 +927,9 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
         if (test_opt(sb, NOLOAD))
                 seq_puts(seq, ",norecovery");
 
+        if (test_opt(sb, DIOREAD_NOLOCK))
+                seq_puts(seq, ",dioread_nolock");
+
         ext4_show_quota_options(seq, sb);
 
         return 0;
@@ -1109,6 +1113,7 @@ enum {
         Opt_stripe, Opt_delalloc, Opt_nodelalloc,
         Opt_block_validity, Opt_noblock_validity,
         Opt_inode_readahead_blks, Opt_journal_ioprio,
+        Opt_dioread_nolock, Opt_dioread_lock,
         Opt_discard, Opt_nodiscard,
 };
 
@@ -1176,6 +1181,8 @@ static const match_table_t tokens = {
         {Opt_auto_da_alloc, "auto_da_alloc=%u"},
         {Opt_auto_da_alloc, "auto_da_alloc"},
         {Opt_noauto_da_alloc, "noauto_da_alloc"},
+        {Opt_dioread_nolock, "dioread_nolock"},
+        {Opt_dioread_lock, "dioread_lock"},
         {Opt_discard, "discard"},
         {Opt_nodiscard, "nodiscard"},
         {Opt_err, NULL},
@@ -1640,6 +1647,12 @@ set_qf_format:
                 case Opt_nodiscard:
                         clear_opt(sbi->s_mount_opt, DISCARD);
                         break;
+                case Opt_dioread_nolock:
+                        set_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+                        break;
+                case Opt_dioread_lock:
+                        clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+                        break;
                 default:
                         ext4_msg(sb, KERN_ERR,
                                "Unrecognized mount option \"%s\" "
@@ -2795,7 +2808,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
               EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
                 ext4_msg(sb, KERN_ERR, "required journal recovery "
                        "suppressed and not mounted read-only");
-                goto failed_mount4;
+                goto failed_mount_wq;
         } else {
                 clear_opt(sbi->s_mount_opt, DATA_FLAGS);
                 set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
@@ -2808,7 +2821,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
             !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
                                        JBD2_FEATURE_INCOMPAT_64BIT)) {
                 ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
-                goto failed_mount4;
+                goto failed_mount_wq;
         }
 
         if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
@@ -2847,7 +2860,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                     (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
                         ext4_msg(sb, KERN_ERR, "Journal does not support "
                                "requested data journaling mode");
-                        goto failed_mount4;
+                        goto failed_mount_wq;
                 }
         default:
                 break;
@@ -2855,13 +2868,17 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
         set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 
 no_journal:
-
         if (test_opt(sb, NOBH)) {
                 if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
                         ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
                                 "its supported only with writeback mode");
                         clear_opt(sbi->s_mount_opt, NOBH);
                 }
+                if (test_opt(sb, DIOREAD_NOLOCK)) {
+                        ext4_msg(sb, KERN_WARNING, "dioread_nolock option is "
+                                "not supported with nobh mode");
+                        goto failed_mount_wq;
+                }
         }
         EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
         if (!EXT4_SB(sb)->dio_unwritten_wq) {
@@ -2926,6 +2943,18 @@ no_journal:
                          "requested data journaling mode");
                 clear_opt(sbi->s_mount_opt, DELALLOC);
         }
+        if (test_opt(sb, DIOREAD_NOLOCK)) {
+                if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+                        ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
+                                "option - requested data journaling mode");
+                        clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+                }
+                if (sb->s_blocksize < PAGE_SIZE) {
+                        ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
+                                "option - block size is too small");
+                        clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+                }
+        }
 
         err = ext4_setup_system_zone(sb);
         if (err) {