Lazy itable initialization for Ext4
Subsystems (2)
v3 cover Lazy itable initialization for Ext4
Hi all,
not much has changed since my last post. Some small cleanup and adjustments proposed by Andreas. There are two noticeable changes though:
* you can now mount with inititable=n option, where n is a number which be used as wait multiplier for thread scheduling purposes (see patch #3).
* introduced sysfs interface for advertising features like lazy itable initialization, to user space (see patch #6)
Thanks for review!
-Lukas
---
[PATCH 1/6] Add helper function for blkdev_issue_zeroout [PATCH 2/6] Add inititable/noinititable mount options for ext4 [PATCH 3/6] Add inode table initialization code for Ext4 [PATCH 4/6] Use sb_issue_zeroout in setup_new_group_blocks [PATCH 5/6] Use sb_issue_discard in ext4_ext_zeroout [PATCH 6/6] Add interface to advertise ext4 features in sysfs
fs/ext4/ext4.h | 44 +++++ fs/ext4/extents.c | 68 +------ fs/ext4/ialloc.c | 116 ++++++++++++ fs/ext4/resize.c | 44 +---- fs/ext4/super.c | 490 +++++++++++++++++++++++++++++++++++++++++++++++- include/linux/blkdev.h | 8 + 6 files changed, 671 insertions(+), 99 deletions(-)
PATCH v3 1/6 Add helper function for blkdev_issue_zeroout
This is done the same way as function sb_issue_discard for blkdev_issue_discard.
--- include/linux/blkdev.h | 8 ++++++++ 1 files changed, 8 insertions(+), 0 deletions(-)
include/linux/blkdev.h +8 -0
@@ -1023,6 +1023,14 @@ static inline int sb_issue_discard(struct super_block *sb,return blkdev_issue_discard (sb->s_bdev, block, nr_blocks,GFP_KERNEL ,BLKDEV_IFL_WAIT |BLKDEV_IFL_BARRIER ); } +static inline int sb_issue_zeroout (struct super_block *sb, +sector_t block,sector_t nr_blocks) +{ + block <<= (sb->s_blocksize_bits -9 ); + nr_blocks <<= (sb->s_blocksize_bits -9 ); +return blkdev_issue_zeroout (sb->s_bdev, block, nr_blocks,GFP_KERNEL , +BLKDEV_IFL_WAIT |BLKDEV_IFL_BARRIER ); +}extern int blk_verify_command (unsigned char *cmd,fmode_t has_write_perm);
Signature · 1 line
1.7.2.2
Re: [PATCH 1/6] Add helper function for blkdev_issue_zeroout
Quoted 14 lines · Lukas Czerner
This is done the same way as function
sb_issue_discardforblkdev_issue_discard.Signed-off-by Lukas Czerner <[email protected]>---
include/linux/blkdev.h | 8 ++++++++1 files changed, 8 insertions(+), 0 deletions(-)include/linux/blkdev.h +0
-0@@ -1023,6 +1023,14 @@ static inline int sb_issue_discard(struct super_block *sb, return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL,
include/linux/blkdev.h static inline int sb_issue_discard(struct super_block *sb, · line 1033
Quoted 10 lines
include/linux/blkdev.h +8
-0BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); } +static inline int sb_issue_zeroout (struct super_block *sb, + sector_t block, sector_t nr_blocks) +{ + block <<= (sb->s_blocksize_bits - 9); + nr_blocks <<= (sb->s_blocksize_bits - 9); + return blkdev_issue_zeroout(sb->s_bdev, block, nr_blocks, GFP_KERNEL, + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); +}
You'll need to rebase this patch against Jens' linux-2.6-block.git 'for-next' branch. The flags have changed such that the sb_issue_discard caller passes them in (and BLKDEV_IFL_BARRIER no longer exists). See the following commits from linux-2.6-block.git:
http://git.kernel.org/?p=linux/kernel/git/axboe/linux-2.6-block.git;a=commit;h=2cf6d26a354ab
http://git.kernel.org/?p=linux/kernel/git/axboe/linux-2.6-block.git;a=commit;h=61002f7db33c7
http://git.kernel.org/?p=linux/kernel/git/axboe/linux-2.6-block.git;a=commit;h=8c5553678237b
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
PATCH v3 2/6 Add inititable/noinititable mount options for ext4
In reply to Lukas CzernerAdd new mount flag EXT4_MOUNT_INIT_INODE_TABLE and add new pair of mount options (inititable/noinititable). When mounted with inititable file system should try to initialize uninitialized inode tables, otherwise it should prevent initializing inode tables. For now, default is noinittable.
One can also specify inititable=n where n is a number that will be used as the wait multiplier (see "Add inode table initialization code into Ext4" patch for more info). Bigger number means slower inode table initialization thus less impact on performance, but longer inititalization (default is 10).
--- fs/ext4/ext4.h | 1 + fs/ext4/super.c | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+), 0 deletions(-)
fs/ext4/ext4.h +1 -0
@@ -885,6 +885,7 @@ struct ext4_inode_info {#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000/* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000/* Block validity checking */ #define EXT4_MOUNT_DISCARD 0x40000000/* Issue DISCARD requests */ +#define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000/* Initialize uninitialized itables */ #define clear_opt (o, opt) o &= ~EXT4_MOUNT_##opt#define set_opt (o, opt) o |= EXT4_MOUNT_##opt
fs/ext4/super.c +22 -0
@@ -986,6 +986,10 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)if (test_opt (sb,DIOREAD_NOLOCK ))seq_puts (seq,",dioread_nolock" ); +if (test_opt (sb,INIT_INODE_TABLE )) +seq_printf (seq,",init_inode_table=%u" , + (unsigned ) sbi->s_li_wait_mult); +ext4_show_quota_options (seq, sb);return 0 ;
@@ -1161,6 +1165,7 @@ enum { Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, + Opt_init_inode_table, Opt_noinit_inode_table, }; static const match_table_t tokens = {
@@ -1231,6 +1236,9 @@ static const match_table_t tokens = { {Opt_dioread_lock, "dioread_lock"}, {Opt_discard, "discard"}, {Opt_nodiscard, "nodiscard"}, + {Opt_init_inode_table, "inititable=%u"}, + {Opt_init_inode_table, "inititable"}, + {Opt_noinit_inode_table, "noinititable"}, {Opt_err, NULL}, };
@@ -1699,6 +1707,20 @@ set_qf_format:case Opt_dioread_lock:clear_opt (sbi->s_mount_opt,DIOREAD_NOLOCK );break ; +case Opt_init_inode_table: +set_opt (sbi->s_mount_opt,INIT_INODE_TABLE ); +if (args[0 ].from) { +if (match_int (&args[0 ], &option)) +return 0 ; + }else + option =EXT4_DEF_LI_WAIT_MULT ; +if (option <0 ) +return 0 ; + sbi->s_li_wait_mult = option; +break ; +case Opt_noinit_inode_table: +clear_opt (sbi->s_mount_opt,INIT_INODE_TABLE ); +break ;default :ext4_msg (sb,KERN_ERR , "Unrecognized mount option \"%s\" "
Signature · 1 line
1.7.2.2
PATCH v3 3/6 Add inode table initialization code for Ext4
In reply to Lukas CzernerWhen lazy_itable_init extended option is passed to mke2fs, it considerably speed up filesystem creation because inode tables are not zeroed out, thus contains some old data. When this fs is mounted filesystem code should initialize (zero out) inode tables. So far this code was missing for ext4 and this patch adds this feature.
For purpose of zeroing inode tables it introduces new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list.
This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (inititable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem).
We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait.
--- fs/ext4/ext4.h | 38 +++++ fs/ext4/ialloc.c | 116 +++++++++++++++ fs/ext4/super.c | 418 +++++++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 569 insertions(+), 3 deletions(-)
fs/ext4/ext4.h +38 -0
@@ -1144,6 +1144,11 @@ struct ext4_sb_info {/* workqueue for dio unwritten */ struct workqueue_struct *dio_unwritten_wq; + +/* Lazy inode table initialization info */ +struct ext4_li_request *s_li_request; +/* Wait multiplier for lazy initialization thread */ +unsigned int s_li_wait_mult; };static inline struct ext4_sb_info *EXT4_SB (struct super_block *sb)
@@ -1467,6 +1472,37 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,extern struct proc_dir_entry *ext4_proc_root;/* +* Timeout and state flag for lazy initialization inode thread. +*/ +#define EXT4_DEF_LI_WAIT_MULT 10 +#define EXT4_DEF_LI_MAX_START_DELAY 5 +#define EXT4_LAZYINIT_QUIT 0x0001 +#define EXT4_LAZYINIT_RUNNING 0x0002 + +/* +* Lazy inode table initialization info +*/ +struct ext4_lazy_init { +unsigned long li_state; + +wait_queue_head_t li_wait_daemon; +wait_queue_head_t li_wait_task; +struct timer_list li_timer; +struct task_struct *li_task; + +struct list_head li_request_list; +struct mutex li_list_mtx; +}; + +struct ext4_li_request { +struct super_block *lr_super; +struct ext4_sb_info *lr_sbi; +ext4_group_t lr_next_group; +struct list_head lr_request; +unsigned long lr_next_sched; +}; + +/* * Function prototypes */
@@ -1539,6 +1575,8 @@ extern unsigned ext4_init_inode_bitmap(struct super_block *sb,ext4_group_t group, struct ext4_group_desc *desc);extern void mark_bitmap_end (int start_bit,int end_bit,char *bitmap); +extern int ext4_init_inode_table (struct super_block *sb, +ext4_group_t group);/* mballoc.c */ extern long ext4_mb_stats;
fs/ext4/ialloc.c +116 -0
157 lines not on this page · raw message
fs/ext4/super.c +415 -3
508 lines not on this page · raw message
Signature · 1 line
1.7.2.2
Re: [PATCH 3/6] Add inode table initialization code for Ext4
When lazy_itable_init extended option is passed to mke2fs, it considerably speed up filesystem creation because inode tables are not zeroed out, thus contains some old data. When this fs is mounted filesystem code should initialize (zero out) inode tables. So far this code was missing for ext4 and this patch adds this feature.
For purpose of zeroing inode tables it introduces new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list.
This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (inititable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem).
We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait.
--- fs/ext4/ext4.h | 38 +++++ fs/ext4/ialloc.c | 116 +++++++++++++++ fs/ext4/super.c | 415 +++++++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 566 insertions(+), 3 deletions(-)
fs/ext4/ext4.h +38 -0
@@ -1144,6 +1144,11 @@ struct ext4_sb_info {/* workqueue for dio unwritten */ struct workqueue_struct *dio_unwritten_wq; + +/* Lazy inode table initialization info */ +struct ext4_li_request *s_li_request; +/* Wait multiplier for lazy initialization thread */ +unsigned int s_li_wait_mult; };static inline struct ext4_sb_info *EXT4_SB (struct super_block *sb)
@@ -1467,6 +1472,37 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,extern struct proc_dir_entry *ext4_proc_root;/* +* Timeout and state flag for lazy initialization inode thread. +*/ +#define EXT4_DEF_LI_WAIT_MULT 10 +#define EXT4_DEF_LI_MAX_START_DELAY 5 +#define EXT4_LAZYINIT_QUIT 0x0001 +#define EXT4_LAZYINIT_RUNNING 0x0002 + +/* +* Lazy inode table initialization info +*/ +struct ext4_lazy_init { +unsigned long li_state; + +wait_queue_head_t li_wait_daemon; +wait_queue_head_t li_wait_task; +struct timer_list li_timer; +struct task_struct *li_task; + +struct list_head li_request_list; +struct mutex li_list_mtx; +}; + +struct ext4_li_request { +struct super_block *lr_super; +struct ext4_sb_info *lr_sbi; +ext4_group_t lr_next_group; +struct list_head lr_request; +unsigned long lr_next_sched; +}; + +/* * Function prototypes */
@@ -1539,6 +1575,8 @@ extern unsigned ext4_init_inode_bitmap(struct super_block *sb,ext4_group_t group, struct ext4_group_desc *desc);extern void mark_bitmap_end (int start_bit,int end_bit,char *bitmap); +extern int ext4_init_inode_table (struct super_block *sb, +ext4_group_t group);/* mballoc.c */ extern long ext4_mb_stats;
fs/ext4/ialloc.c +116 -0
157 lines not on this page · raw message
fs/ext4/super.c +412 -3
505 lines not on this page · raw message
Signature · 1 line
1.7.2.2
PATCH v3 4/6 Use sb_issue_zeroout in setup_new_group_blocks
In reply to Lukas CzernerUse sn_issue_discard to zero out inode table and descriptor table blocks instead of old approach which involves journaling.
--- fs/ext4/resize.c | 44 +++++++++++--------------------------------- 1 files changed, 11 insertions(+), 33 deletions(-)
fs/ext4/resize.c +5 -24
@@ -226,23 +226,12 @@ static int setup_new_group_blocks(struct super_block *sb, }/* Zero out all of the reserved backup group descriptor table blocks */ -for (i =0 , bit = gdblocks +1 , block = start + bit; - i < reserved_gdb; i++, block++, bit++) { -struct buffer_head *gdb; - -ext4_debug ("clear reserved block %#04llx (+%d)\n" , block, bit); - -if ((err =extend_or_restart_transaction (handle,1 , bh))) - goto exit_bh; +ext4_debug ("clear inode table blocks %#04llx -> %#04llx\n" , + block, sbi->s_itb_per_group); + err =sb_issue_zeroout (sb, gdblocks + start +1 , reserved_gdb); +if (err) + goto exit_journal; -if (IS_ERR (gdb =bclean (handle, sb, block))) { - err =PTR_ERR (gdb); - goto exit_bh; - } -ext4_handle_dirty_metadata (handle,NULL , gdb); -ext4_set_bit (bit, bh->b_data); -brelse (gdb); - }ext4_debug ("mark block bitmap %#04llx (+%llu)\n" , input->block_bitmap, input->block_bitmap - start);ext4_set_bit (input->block_bitmap - start, bh->b_data);
@@ -251,23 +240,12 @@ static int setup_new_group_blocks(struct super_block *sb,ext4_set_bit (input->inode_bitmap - start, bh->b_data);/* Zero out all of the inode table blocks */ -for (i =0 , block = input->inode_table, bit = block - start; - i < sbi->s_itb_per_group; i++, bit++, block++) { -struct buffer_head *it; - -ext4_debug ("clear inode block %#04llx (+%d)\n" , block, bit); - -if ((err =extend_or_restart_transaction (handle,1 , bh))) - goto exit_bh;
PATCH v3 5/6 Use sb_issue_discard in ext4_ext_zeroout
In reply to Lukas CzernerChange ext4_ext4_zeroout to use sb_issue_discard instead of its own approach to zero out extents.
--- fs/ext4/extents.c | 68 ++++------------------------------------------------ 1 files changed, 6 insertions(+), 62 deletions(-)
fs/ext4/extents.c +6 -62
@@ -2536,77 +2536,21 @@ void ext4_ext_release(struct super_block *sb)#endif } -static void bi_complete (struct bio *bio,int error) -{ -complete ((struct completion *)bio->bi_private); -} -/* FIXME!! we need to try to merge to left or right after zero-out */ static int ext4_ext_zeroout (struct inode *inode,struct ext4_extent *ex) { +ext4_fsblk_t ee_pblock; +unsigned int ee_len;int ret; -struct bio *bio; -int blkbits, blocksize; -sector_t ee_pblock; -struct completion event; -unsigned int ee_len, len, done, offset; - - blkbits = inode->i_blkbits; - blocksize = inode->i_sb->s_blocksize; ee_len =ext4_ext_get_actual_len (ex); ee_pblock =ext_pblock (ex); -/* convert ee_pblock to 512 byte sectors */ - ee_pblock = ee_pblock << (blkbits -9 ); - -while (ee_len >0 ) { - -if (ee_len >BIO_MAX_PAGES ) - len =BIO_MAX_PAGES ; -else - len = ee_len; - - bio =bio_alloc (GFP_NOIO , len); -if (!bio) -return -ENOMEM ; - - bio->bi_sector = ee_pblock; - bio->bi_bdev = inode->i_sb->s_bdev; - - done =0 ; - offset =0 ; -while (done < len) { - ret =bio_add_page (bio,ZERO_PAGE (0 ), - blocksize, offset); -if (ret != blocksize) { -/* -* We can't add any more pages because of -* hardware limitations. Start a new bio. -*/ -break ; - } - done++; - offset += blocksize; -if (offset >=PAGE_CACHE_SIZE ) - offset =0 ; - } - -init_completion (&event); - bio->bi_private = &event; - bio->bi_end_io = bi_complete; -submit_bio (WRITE , bio); -wait_for_completion (&event); + ret =sb_issue_zeroout (inode->i_sb, ee_pblock, ee_len); +if (ret >0 ) + ret =0 ; -if (!test_bit (BIO_UPTODATE , &bio->bi_flags)) { -bio_put (bio); -return -EIO ; - } -bio_put (bio); - ee_len -= done; - ee_pblock += done << (blkbits -9 ); - } -return 0 ; +return ret; }#define EXT4_EXT_ZERO_LEN 7
Signature · 1 line
1.7.2.2
Re: [PATCH 5/6] Use sb_issue_discard in ext4_ext_zeroout
Quoted 2 lines · Lukas Czerner
Change
ext4_ext4_zerooutto usesb_issue_discardinstead of its own approach to zero out extents.
s/sb_issue_discard/sb_issue_zeroout/ in both the Subject and patch header (above).
Patch 4/6 header also has a typo: s/sn_issue_discard/sb_issue_zeroout/
PATCH v3 6/6 Add interface to advertise ext4 features in sysfs
In reply to Lukas CzernerUser-space should have the opportunity to check what features doest ext4 support in each particular copy. This adds easy interface by creating new "features" directory in sys/fs/ext4/. In that directory files advertising feature names can be created.
Add lazy_itable_init to the feature list.
--- fs/ext4/ext4.h | 5 +++++ fs/ext4/super.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 54 insertions(+), 1 deletions(-)
fs/ext4/ext4.h +5 -0
@@ -1502,6 +1502,11 @@ struct ext4_li_request {unsigned long lr_next_sched; }; +struct ext4_features { +struct kobject f_kobj; +struct completion f_kobj_unregister; +}; +/* * Function prototypes */
fs/ext4/super.c +49 -1
98 lines not on this page · raw message
Signature · 1 line
1.7.2.2
Re: [PATCH 6/6] Add interface to advertise ext4 features in sysfs
Quoted 6 lines · Lukas Czerner
User-space should have the opportunity to check what features doest ext4 support in each particular copy. This adds easy interface by creating new "features" directory in sys/fs/ext4/. In that directory files advertising feature names can be created.
Add
lazy_itable_initto the feature list.
This seems to break unloading/reloading in .37; near as I can tell /sys/fs/ext4 never gets unregistered on module unload.
-Eric
Quoted 132 lines
Signed-off-by Lukas Czerner <[email protected]>--- fs/ext4/ext4.h | 5 +++++ fs/ext4/super.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 54 insertions(+), 1 deletions(-)fs/ext4/ext4.h +5
-0@@ -1502,6 +1502,11 @@ struct ext4_li_request {unsigned long lr_next_sched; }; +struct ext4_features { +struct kobject f_kobj; +struct completion f_kobj_unregister; +}; +/* * Function prototypes */ fs/ext4/super.c +49
-1@@ -57,6 +57,7 @@ struct proc_dir_entry *ext4_proc_root;static struct kset *ext4_kset;struct ext4_lazy_init *ext4_li_info;struct mutex ext4_li_mtx; +struct ext4_features *ext4_feat;static int ext4_load_journal (struct super_block *,struct ext4_super_block *,unsigned long journal_devnum);@@ -2349,6 +2350,7 @@ static struct ext4_attr ext4_attr_##_name = { \#define EXT4_ATTR (name, mode, show, store) \ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store) +#define EXT4_INFO_ATTR (name) EXT4_ATTR(name, 0444, NULL, NULL)#define EXT4_RO_ATTR (name) EXT4_ATTR(name, 0444, name##_show, NULL)#define EXT4_RW_ATTR (name) EXT4_ATTR(name, 0644, name##_show, name##_store)#define EXT4_RW_ATTR_SBI_UI (name, elname) \@@ -2385,6 +2387,14 @@ static struct attribute *ext4_attrs[] = { NULL, }; +/* Features this copy of ext4 supports */ +EXT4_INFO_ATTR (lazy_itable_init); + +static struct attribute *ext4_feat_attrs[] = { +ATTR_LIST (lazy_itable_init), +NULL , +}; +static ssize_t ext4_attr_show (struct kobject *kobj,struct attribute *attr,char *buf) {@@ -2413,7 +2423,6 @@ static void ext4_sb_release(struct kobject *kobj)complete (&sbi->s_kobj_unregister); } -static const struct sysfs_ops ext4_attr_ops = { .show = ext4_attr_show, .store = ext4_attr_store,@@ -2425,6 +2434,17 @@ static struct kobj_type ext4_ktype = { .release = ext4_sb_release, }; +static void ext4_feat_release (struct kobject *kobj) +{ +complete (&ext4_feat->f_kobj_unregister); +} + +static struct kobj_type ext4_feat_ktype = { + .default_attrs = ext4_feat_attrs, + .sysfs_ops = &ext4_attr_ops, + .release = ext4_feat_release, +}; +/* * Check whether this filesystem can be mounted based on * the features present and the RDONLY/RDWR mount requested. @@ -4581,6 +4601,30 @@ static struct file_system_type ext4_fs_type = { .fs_flags = FS_REQUIRES_DEV, }; +int __init ext4_init_feat_adverts (void ) +{ +struct ext4_features *ef; +int ret = -ENOMEM ; + + ef =kzalloc (sizeof (struct ext4_features ),GFP_KERNEL ); +if (!ef) + goto out; + + ef->f_kobj.kset = ext4_kset; +init_completion (&ef->f_kobj_unregister); + ret =kobject_init_and_add (&ef->f_kobj, &ext4_feat_ktype,NULL , +"features" ); +if (ret) { +kfree (ef); + goto out; + } + + ext4_feat = ef; + ret =0 ; +out: +return ret; +} +static int __init init_ext4_fs (void ) {int err;@@ -4593,6 +4637,9 @@ static int __init init_ext4_fs(void)if (!ext4_kset) goto out4; ext4_proc_root =proc_mkdir ("fs/ext4" ,NULL ); + + err =ext4_init_feat_adverts (); + err =init_ext4_mballoc ();if (err) goto out3;@@ -4621,6 +4668,7 @@ out1: out2:exit_ext4_mballoc (); out3: +kfree (ext4_feat);remove_proc_entry ("fs/ext4" ,NULL );kset_unregister (ext4_kset); out4:
Re: [PATCH 6/6] Add interface to advertise ext4 features in sysfs
Quoted 10 lines · Eric Sandeen
Quoted 6 lines · Lukas Czerner
User-space should have the opportunity to check what features doest ext4 support in each particular copy. This adds easy interface by creating new "features" directory in sys/fs/ext4/. In that directory files advertising feature names can be created.
Add
lazy_itable_initto the feature list.This seems to break unloading/reloading in .37; near as I can tell
/sys/fs/ext4never gets unregistered on module unload.
That's not good, I'll look at it.
Thanks!
-Lukas
Quoted 137 lines
-Eric
Quoted 132 lines
Signed-off-by Lukas Czerner <[email protected]>--- fs/ext4/ext4.h | 5 +++++ fs/ext4/super.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 54 insertions(+), 1 deletions(-)fs/ext4/ext4.h +5
-0@@ -1502,6 +1502,11 @@ struct ext4_li_request {unsigned long lr_next_sched; }; +struct ext4_features { +struct kobject f_kobj; +struct completion f_kobj_unregister; +}; +/* * Function prototypes */ fs/ext4/super.c +49
-1@@ -57,6 +57,7 @@ struct proc_dir_entry *ext4_proc_root;static struct kset *ext4_kset;struct ext4_lazy_init *ext4_li_info;struct mutex ext4_li_mtx; +struct ext4_features *ext4_feat;static int ext4_load_journal (struct super_block *,struct ext4_super_block *,unsigned long journal_devnum);@@ -2349,6 +2350,7 @@ static struct ext4_attr ext4_attr_##_name = { \#define EXT4_ATTR (name, mode, show, store) \ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store) +#define EXT4_INFO_ATTR (name) EXT4_ATTR(name, 0444, NULL, NULL)#define EXT4_RO_ATTR (name) EXT4_ATTR(name, 0444, name##_show, NULL)#define EXT4_RW_ATTR (name) EXT4_ATTR(name, 0644, name##_show, name##_store)#define EXT4_RW_ATTR_SBI_UI (name, elname) \@@ -2385,6 +2387,14 @@ static struct attribute *ext4_attrs[] = { NULL, }; +/* Features this copy of ext4 supports */ +EXT4_INFO_ATTR (lazy_itable_init); + +static struct attribute *ext4_feat_attrs[] = { +ATTR_LIST (lazy_itable_init), +NULL , +}; +static ssize_t ext4_attr_show (struct kobject *kobj,struct attribute *attr,char *buf) {@@ -2413,7 +2423,6 @@ static void ext4_sb_release(struct kobject *kobj)complete (&sbi->s_kobj_unregister); } -static const struct sysfs_ops ext4_attr_ops = { .show = ext4_attr_show, .store = ext4_attr_store,@@ -2425,6 +2434,17 @@ static struct kobj_type ext4_ktype = { .release = ext4_sb_release, }; +static void ext4_feat_release (struct kobject *kobj) +{ +complete (&ext4_feat->f_kobj_unregister); +} + +static struct kobj_type ext4_feat_ktype = { + .default_attrs = ext4_feat_attrs, + .sysfs_ops = &ext4_attr_ops, + .release = ext4_feat_release, +}; +/* * Check whether this filesystem can be mounted based on * the features present and the RDONLY/RDWR mount requested. @@ -4581,6 +4601,30 @@ static struct file_system_type ext4_fs_type = { .fs_flags = FS_REQUIRES_DEV, }; +int __init ext4_init_feat_adverts (void ) +{ +struct ext4_features *ef; +int ret = -ENOMEM ; + + ef =kzalloc (sizeof (struct ext4_features ),GFP_KERNEL ); +if (!ef) + goto out; + + ef->f_kobj.kset = ext4_kset; +init_completion (&ef->f_kobj_unregister); + ret =kobject_init_and_add (&ef->f_kobj, &ext4_feat_ktype,NULL , +"features" ); +if (ret) { +kfree (ef); + goto out; + } + + ext4_feat = ef; + ret =0 ; +out: +return ret; +} +static int __init init_ext4_fs (void ) {int err;@@ -4593,6 +4637,9 @@ static int __init init_ext4_fs(void)if (!ext4_kset) goto out4; ext4_proc_root =proc_mkdir ("fs/ext4" ,NULL ); + + err =ext4_init_feat_adverts (); + err =init_ext4_mballoc ();if (err) goto out3;@@ -4621,6 +4668,7 @@ out1: out2:exit_ext4_mballoc (); out3: +kfree (ext4_feat);remove_proc_entry ("fs/ext4" ,NULL );kset_unregister (ext4_kset); out4: