summaryrefslogtreecommitdiff
path: root/fs/btrfs/super.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/super.c')
-rw-r--r--fs/btrfs/super.c141
1 files changed, 52 insertions, 89 deletions
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 4f1cdd5058f1..161694b66038 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -61,6 +61,7 @@
#include "tests/btrfs-tests.h"
#include "qgroup.h"
+#include "backref.h"
#define CREATE_TRACE_POINTS
#include <trace/events/btrfs.h>
@@ -102,7 +103,7 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
{
struct super_block *sb = fs_info->sb;
- if (sb->s_flags & MS_RDONLY)
+ if (sb_rdonly(sb))
return;
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
@@ -138,7 +139,7 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function
* Special case: if the error is EROFS, and we're already
* under MS_RDONLY, then it is safe here.
*/
- if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
+ if (errno == -EROFS && sb_rdonly(sb))
return;
#ifdef CONFIG_PRINTK
@@ -425,7 +426,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
* strsep changes the string, duplicate it because parse_options
* gets called twice
*/
- options = kstrdup(options, GFP_NOFS);
+ options = kstrdup(options, GFP_KERNEL);
if (!options)
return -ENOMEM;
@@ -498,14 +499,14 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
btrfs_test_opt(info, FORCE_COMPRESS);
if (token == Opt_compress ||
token == Opt_compress_force ||
- strcmp(args[0].from, "zlib") == 0) {
+ strncmp(args[0].from, "zlib", 4) == 0) {
compress_type = "zlib";
info->compress_type = BTRFS_COMPRESS_ZLIB;
btrfs_set_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
no_compress = 0;
- } else if (strcmp(args[0].from, "lzo") == 0) {
+ } else if (strncmp(args[0].from, "lzo", 3) == 0) {
compress_type = "lzo";
info->compress_type = BTRFS_COMPRESS_LZO;
btrfs_set_opt(info->mount_opt, COMPRESS);
@@ -513,6 +514,14 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
btrfs_clear_opt(info->mount_opt, NODATASUM);
btrfs_set_fs_incompat(info, COMPRESS_LZO);
no_compress = 0;
+ } else if (strcmp(args[0].from, "zstd") == 0) {
+ compress_type = "zstd";
+ info->compress_type = BTRFS_COMPRESS_ZSTD;
+ btrfs_set_opt(info->mount_opt, COMPRESS);
+ btrfs_clear_opt(info->mount_opt, NODATACOW);
+ btrfs_clear_opt(info->mount_opt, NODATASUM);
+ btrfs_set_fs_incompat(info, COMPRESS_ZSTD);
+ no_compress = 0;
} else if (strncmp(args[0].from, "no", 2) == 0) {
compress_type = "no";
btrfs_clear_opt(info->mount_opt, COMPRESS);
@@ -548,20 +557,22 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
break;
case Opt_ssd:
btrfs_set_and_info(info, SSD,
- "use ssd allocation scheme");
+ "enabling ssd optimizations");
btrfs_clear_opt(info->mount_opt, NOSSD);
break;
case Opt_ssd_spread:
+ btrfs_set_and_info(info, SSD,
+ "enabling ssd optimizations");
btrfs_set_and_info(info, SSD_SPREAD,
- "use spread ssd allocation scheme");
- btrfs_set_opt(info->mount_opt, SSD);
+ "using spread ssd allocation scheme");
btrfs_clear_opt(info->mount_opt, NOSSD);
break;
case Opt_nossd:
- btrfs_set_and_info(info, NOSSD,
- "not using ssd allocation scheme");
- btrfs_clear_opt(info->mount_opt, SSD);
- btrfs_clear_opt(info->mount_opt, SSD_SPREAD);
+ btrfs_set_opt(info->mount_opt, NOSSD);
+ btrfs_clear_and_info(info, SSD,
+ "not using ssd optimizations");
+ btrfs_clear_and_info(info, SSD_SPREAD,
+ "not using spread ssd allocation scheme");
break;
case Opt_barrier:
btrfs_clear_and_info(info, NOBARRIER,
@@ -601,18 +612,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
}
break;
case Opt_alloc_start:
- num = match_strdup(&args[0]);
- if (num) {
- mutex_lock(&info->chunk_mutex);
- info->alloc_start = memparse(num, NULL);
- mutex_unlock(&info->chunk_mutex);
- kfree(num);
- btrfs_info(info, "allocations start at %llu",
- info->alloc_start);
- } else {
- ret = -ENOMEM;
- goto out;
- }
+ btrfs_info(info,
+ "option alloc_start is obsolete, ignored");
break;
case Opt_acl:
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
@@ -959,7 +960,7 @@ static char *get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
}
path->leave_spinning = 1;
- name = kmalloc(PATH_MAX, GFP_NOFS);
+ name = kmalloc(PATH_MAX, GFP_KERNEL);
if (!name) {
ret = -ENOMEM;
goto err;
@@ -1134,7 +1135,7 @@ static int btrfs_fill_super(struct super_block *sb,
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
sb->s_flags |= MS_POSIXACL;
#endif
- sb->s_flags |= MS_I_VERSION;
+ sb->s_flags |= SB_I_VERSION;
sb->s_iflags |= SB_I_CGROUPWB;
err = super_setup_bdi(sb);
@@ -1164,7 +1165,6 @@ static int btrfs_fill_super(struct super_block *sb,
goto fail_close;
}
- save_mount_options(sb, data);
cleancache_init_fs(sb);
sb->s_flags |= MS_ACTIVE;
return 0;
@@ -1187,7 +1187,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
return 0;
}
- btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
+ btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
@@ -1232,16 +1232,16 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
seq_puts(seq, ",nobarrier");
if (info->max_inline != BTRFS_DEFAULT_MAX_INLINE)
seq_printf(seq, ",max_inline=%llu", info->max_inline);
- if (info->alloc_start != 0)
- seq_printf(seq, ",alloc_start=%llu", info->alloc_start);
if (info->thread_pool_size != min_t(unsigned long,
num_online_cpus() + 2, 8))
seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
if (btrfs_test_opt(info, COMPRESS)) {
if (info->compress_type == BTRFS_COMPRESS_ZLIB)
compress_type = "zlib";
- else
+ else if (info->compress_type == BTRFS_COMPRESS_LZO)
compress_type = "lzo";
+ else
+ compress_type = "zstd";
if (btrfs_test_opt(info, FORCE_COMPRESS))
seq_printf(seq, ",compress-force=%s", compress_type);
else
@@ -1348,10 +1348,11 @@ static char *setup_root_args(char *args)
char *buf, *dst, *sep;
if (!args)
- return kstrdup("subvolid=0", GFP_NOFS);
+ return kstrdup("subvolid=0", GFP_KERNEL);
/* The worst case is that we add ",subvolid=0" to the end. */
- buf = dst = kmalloc(strlen(args) + strlen(",subvolid=0") + 1, GFP_NOFS);
+ buf = dst = kmalloc(strlen(args) + strlen(",subvolid=0") + 1,
+ GFP_KERNEL);
if (!buf)
return NULL;
@@ -1580,7 +1581,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
* it for searching for existing supers, so this lets us do that and
* then open_ctree will properly initialize everything later.
*/
- fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_NOFS);
+ fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL);
if (!fs_info) {
error = -ENOMEM;
goto error_sec_opts;
@@ -1588,8 +1589,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
fs_info->fs_devices = fs_devices;
- fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
- fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
+ fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
+ fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
security_init_mnt_opts(&fs_info->security_opts);
if (!fs_info->super_copy || !fs_info->super_for_commit) {
error = -ENOMEM;
@@ -1700,8 +1701,7 @@ static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
* close or the filesystem is read only.
*/
if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
- (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
- (fs_info->sb->s_flags & MS_RDONLY))) {
+ (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) || sb_rdonly(fs_info->sb))) {
btrfs_cleanup_defrag_inodes(fs_info);
}
@@ -1716,7 +1716,6 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
unsigned long old_opts = fs_info->mount_opt;
unsigned long old_compress_type = fs_info->compress_type;
u64 old_max_inline = fs_info->max_inline;
- u64 old_alloc_start = fs_info->alloc_start;
int old_thread_pool_size = fs_info->thread_pool_size;
unsigned int old_metadata_ratio = fs_info->metadata_ratio;
int ret;
@@ -1749,7 +1748,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
btrfs_resize_thread_pool(fs_info,
fs_info->thread_pool_size, old_thread_pool_size);
- if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
+ if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb))
goto out;
if (*flags & MS_RDONLY) {
@@ -1794,8 +1793,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
goto restore;
}
- if (fs_info->fs_devices->missing_devices >
- fs_info->num_tolerated_disk_barrier_failures) {
+ if (!btrfs_check_rw_degradable(fs_info)) {
btrfs_warn(fs_info,
"too many missing devices, writeable remount is not allowed");
ret = -EACCES;
@@ -1828,6 +1826,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
goto restore;
}
+ btrfs_qgroup_rescan_resume(fs_info);
+
if (!fs_info->uuid_root) {
btrfs_info(fs_info, "creating UUID tree");
ret = btrfs_create_uuid_tree(fs_info);
@@ -1849,15 +1849,12 @@ out:
restore:
/* We've hit an error - don't reset MS_RDONLY */
- if (sb->s_flags & MS_RDONLY)
+ if (sb_rdonly(sb))
old_flags |= MS_RDONLY;
sb->s_flags = old_flags;
fs_info->mount_opt = old_opts;
fs_info->compress_type = old_compress_type;
fs_info->max_inline = old_max_inline;
- mutex_lock(&fs_info->chunk_mutex);
- fs_info->alloc_start = old_alloc_start;
- mutex_unlock(&fs_info->chunk_mutex);
btrfs_resize_thread_pool(fs_info,
old_thread_pool_size, fs_info->thread_pool_size);
fs_info->metadata_ratio = old_metadata_ratio;
@@ -1898,18 +1895,15 @@ static inline void btrfs_descending_sort_devices(
static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
u64 *free_bytes)
{
- struct btrfs_root *root = fs_info->tree_root;
struct btrfs_device_info *devices_info;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
struct btrfs_device *device;
u64 skip_space;
u64 type;
u64 avail_space;
- u64 used_space;
u64 min_stripe_size;
int min_stripes = 1, num_stripes = 1;
int i = 0, nr_devices;
- int ret;
/*
* We aren't under the device list lock, so this is racy-ish, but good
@@ -1927,12 +1921,12 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
}
devices_info = kmalloc_array(nr_devices, sizeof(*devices_info),
- GFP_NOFS);
+ GFP_KERNEL);
if (!devices_info)
return -ENOMEM;
/* calc min stripe number for data space allocation */
- type = btrfs_get_alloc_profile(root, 1);
+ type = btrfs_data_alloc_profile(fs_info);
if (type & BTRFS_BLOCK_GROUP_RAID0) {
min_stripes = 2;
num_stripes = nr_devices;
@@ -1949,8 +1943,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
else
min_stripe_size = BTRFS_STRIPE_LEN;
- if (fs_info->alloc_start)
- mutex_lock(&fs_devices->device_list_mutex);
rcu_read_lock();
list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
if (!device->in_fs_metadata || !device->bdev ||
@@ -1973,34 +1965,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
*/
skip_space = SZ_1M;
- /* user can set the offset in fs_info->alloc_start. */
- if (fs_info->alloc_start &&
- fs_info->alloc_start + BTRFS_STRIPE_LEN <=
- device->total_bytes) {
- rcu_read_unlock();
- skip_space = max(fs_info->alloc_start, skip_space);
-
- /*
- * btrfs can not use the free space in
- * [0, skip_space - 1], we must subtract it from the
- * total. In order to implement it, we account the used
- * space in this range first.
- */
- ret = btrfs_account_dev_extents_size(device, 0,
- skip_space - 1,
- &used_space);
- if (ret) {
- kfree(devices_info);
- mutex_unlock(&fs_devices->device_list_mutex);
- return ret;
- }
-
- rcu_read_lock();
-
- /* calc the free space in [0, skip_space - 1] */
- skip_space -= used_space;
- }
-
/*
* we can use the free space in [0, skip_space - 1], subtract
* it from the total.
@@ -2019,8 +1983,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
i++;
}
rcu_read_unlock();
- if (fs_info->alloc_start)
- mutex_unlock(&fs_devices->device_list_mutex);
nr_devices = i;
@@ -2057,10 +2019,9 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
* multiplier to scale the sizes.
*
* Unused device space usage is based on simulating the chunk allocator
- * algorithm that respects the device sizes, order of allocations and the
- * 'alloc_start' value, this is a close approximation of the actual use but
- * there are other factors that may change the result (like a new metadata
- * chunk).
+ * algorithm that respects the device sizes and order of allocations. This is
+ * a close approximation of the actual use but there are other factors that may
+ * change the result (like a new metadata chunk).
*
* If metadata is exhausted, f_bavail will be 0.
*/
@@ -2243,7 +2204,7 @@ static int btrfs_freeze(struct super_block *sb)
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
struct btrfs_root *root = fs_info->tree_root;
- fs_info->fs_frozen = 1;
+ set_bit(BTRFS_FS_FROZEN, &fs_info->flags);
/*
* We don't need a barrier here, we'll wait for any transaction that
* could be in progress on other threads (and do delayed iputs that
@@ -2262,7 +2223,9 @@ static int btrfs_freeze(struct super_block *sb)
static int btrfs_unfreeze(struct super_block *sb)
{
- btrfs_sb(sb)->fs_frozen = 0;
+ struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
+ clear_bit(BTRFS_FS_FROZEN, &fs_info->flags);
return 0;
}
generated by cgit v1.2.3 (git 2.46.0) at 2025-09-06 07:13:35 +0000