Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 8ad1458..1b151af 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -42,7 +42,10 @@
#include "dev-replace.h"
#include "free-space-cache.h"
#include "backref.h"
+#include "space-info.h"
+#include "sysfs.h"
#include "tests/btrfs-tests.h"
+#include "block-group.h"
#include "qgroup.h"
#define CREATE_TRACE_POINTS
@@ -93,7 +96,7 @@
/*
* __btrfs_handle_fs_error decodes expected errors from the caller and
- * invokes the approciate error response.
+ * invokes the appropriate error response.
*/
__cold
void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
@@ -151,7 +154,7 @@
* although there is no way to update the progress. It would add the
* risk of a deadlock, therefore the canceling is omitted. The only
* penalty is that some I/O remains active until the procedure
- * completes. The next time when the filesystem is mounted writeable
+ * completes. The next time when the filesystem is mounted writable
* again, the device replace operation continues.
*/
}
@@ -529,7 +532,9 @@
if (token != Opt_compress &&
token != Opt_compress_force)
info->compress_level =
- btrfs_compress_str2level(args[0].from);
+ btrfs_compress_str2level(
+ BTRFS_COMPRESS_ZLIB,
+ args[0].from + 4);
btrfs_set_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
@@ -542,9 +547,13 @@
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) {
+ } else if (strncmp(args[0].from, "zstd", 4) == 0) {
compress_type = "zstd";
info->compress_type = BTRFS_COMPRESS_ZSTD;
+ info->compress_level =
+ btrfs_compress_str2level(
+ BTRFS_COMPRESS_ZSTD,
+ args[0].from + 4);
btrfs_set_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
@@ -1394,7 +1403,7 @@
}
static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid,
- const char *device_name, struct vfsmount *mnt)
+ struct vfsmount *mnt)
{
struct dentry *root;
int ret;
@@ -1458,56 +1467,6 @@
return root;
}
-static int parse_security_options(char *orig_opts,
- struct security_mnt_opts *sec_opts)
-{
- char *secdata = NULL;
- int ret = 0;
-
- secdata = alloc_secdata();
- if (!secdata)
- return -ENOMEM;
- ret = security_sb_copy_data(orig_opts, secdata);
- if (ret) {
- free_secdata(secdata);
- return ret;
- }
- ret = security_sb_parse_opts_str(secdata, sec_opts);
- free_secdata(secdata);
- return ret;
-}
-
-static int setup_security_options(struct btrfs_fs_info *fs_info,
- struct super_block *sb,
- struct security_mnt_opts *sec_opts)
-{
- int ret = 0;
-
- /*
- * Call security_sb_set_mnt_opts() to check whether new sec_opts
- * is valid.
- */
- ret = security_sb_set_mnt_opts(sb, sec_opts, 0, NULL);
- if (ret)
- return ret;
-
-#ifdef CONFIG_SECURITY
- if (!fs_info->security_opts.num_mnt_opts) {
- /* first time security setup, copy sec_opts to fs_info */
- memcpy(&fs_info->security_opts, sec_opts, sizeof(*sec_opts));
- } else {
- /*
- * Since SELinux (the only one supporting security_mnt_opts)
- * does NOT support changing context during remount/mount of
- * the same sb, this must be the same or part of the same
- * security options, just free it.
- */
- security_free_mnt_opts(sec_opts);
- }
-#endif
- return ret;
-}
-
/*
* Find a superblock for the given device / mount point.
*
@@ -1522,16 +1481,15 @@
struct btrfs_device *device = NULL;
struct btrfs_fs_devices *fs_devices = NULL;
struct btrfs_fs_info *fs_info = NULL;
- struct security_mnt_opts new_sec_opts;
+ void *new_sec_opts = NULL;
fmode_t mode = FMODE_READ;
int error = 0;
if (!(flags & SB_RDONLY))
mode |= FMODE_WRITE;
- security_init_mnt_opts(&new_sec_opts);
if (data) {
- error = parse_security_options(data, &new_sec_opts);
+ error = security_sb_eat_lsm_opts(data, &new_sec_opts);
if (error)
return ERR_PTR(error);
}
@@ -1550,7 +1508,6 @@
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;
goto error_fs_info;
@@ -1599,18 +1556,16 @@
} else {
snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
btrfs_sb(s)->bdev_holder = fs_type;
+ if (!strstr(crc32c_impl(), "generic"))
+ set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags);
error = btrfs_fill_super(s, fs_devices, data);
}
+ if (!error)
+ error = security_sb_set_mnt_opts(s, new_sec_opts, 0, NULL);
+ security_free_mnt_opts(&new_sec_opts);
if (error) {
deactivate_locked_super(s);
- goto error_sec_opts;
- }
-
- fs_info = btrfs_sb(s);
- error = setup_security_options(fs_info, s, &new_sec_opts);
- if (error) {
- deactivate_locked_super(s);
- goto error_sec_opts;
+ return ERR_PTR(error);
}
return dget(s->s_root);
@@ -1651,14 +1606,10 @@
{
struct vfsmount *mnt_root;
struct dentry *root;
- fmode_t mode = FMODE_READ;
char *subvol_name = NULL;
u64 subvol_objectid = 0;
int error = 0;
- if (!(flags & SB_RDONLY))
- mode |= FMODE_WRITE;
-
error = btrfs_parse_subvol_options(data, &subvol_name,
&subvol_objectid);
if (error) {
@@ -1677,6 +1628,7 @@
flags | SB_RDONLY, device_name, data);
if (IS_ERR(mnt_root)) {
root = ERR_CAST(mnt_root);
+ kfree(subvol_name);
goto out;
}
@@ -1686,17 +1638,19 @@
if (error < 0) {
root = ERR_PTR(error);
mntput(mnt_root);
+ kfree(subvol_name);
goto out;
}
}
}
if (IS_ERR(mnt_root)) {
root = ERR_CAST(mnt_root);
+ kfree(subvol_name);
goto out;
}
/* mount_subvol() will free subvol_name and mnt_root */
- root = mount_subvol(subvol_name, subvol_objectid, device_name, mnt_root);
+ root = mount_subvol(subvol_name, subvol_objectid, mnt_root);
out:
return root;
@@ -1779,18 +1733,14 @@
btrfs_remount_prepare(fs_info);
if (data) {
- struct security_mnt_opts new_sec_opts;
+ void *new_sec_opts = NULL;
- security_init_mnt_opts(&new_sec_opts);
- ret = parse_security_options(data, &new_sec_opts);
+ ret = security_sb_eat_lsm_opts(data, &new_sec_opts);
+ if (!ret)
+ ret = security_sb_remount(sb, new_sec_opts);
+ security_free_mnt_opts(&new_sec_opts);
if (ret)
goto restore;
- ret = setup_security_options(fs_info, sb,
- &new_sec_opts);
- if (ret) {
- security_free_mnt_opts(&new_sec_opts);
- goto restore;
- }
}
ret = btrfs_parse_options(fs_info, data, *flags);
@@ -1848,7 +1798,7 @@
if (!btrfs_check_rw_degradable(fs_info, NULL)) {
btrfs_warn(fs_info,
- "too many missing devices, writeable remount is not allowed");
+ "too many missing devices, writable remount is not allowed");
ret = -EACCES;
goto restore;
}
@@ -1916,7 +1866,7 @@
}
/* Used to sort the devices by max_avail(descending sort) */
-static int btrfs_cmp_device_free_bytes(const void *dev_info1,
+static inline int btrfs_cmp_device_free_bytes(const void *dev_info1,
const void *dev_info2)
{
if (((struct btrfs_device_info *)dev_info1)->max_avail >
@@ -1945,18 +1895,18 @@
* The helper to calc the free space on the devices that can be used to store
* file data.
*/
-static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
- u64 *free_bytes)
+static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
+ u64 *free_bytes)
{
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 min_stripe_size;
- int min_stripes = 1, num_stripes = 1;
+ int num_stripes = 1;
int i = 0, nr_devices;
+ const struct btrfs_raid_attr *rattr;
/*
* We aren't under the device list lock, so this is racy-ish, but good
@@ -1980,21 +1930,17 @@
/* calc min stripe number for data space allocation */
type = btrfs_data_alloc_profile(fs_info);
- if (type & BTRFS_BLOCK_GROUP_RAID0) {
- min_stripes = 2;
- num_stripes = nr_devices;
- } else if (type & BTRFS_BLOCK_GROUP_RAID1) {
- min_stripes = 2;
- num_stripes = 2;
- } else if (type & BTRFS_BLOCK_GROUP_RAID10) {
- min_stripes = 4;
- num_stripes = 4;
- }
+ rattr = &btrfs_raid_array[btrfs_bg_flags_to_raid_index(type)];
- if (type & BTRFS_BLOCK_GROUP_DUP)
- min_stripe_size = 2 * BTRFS_STRIPE_LEN;
- else
- min_stripe_size = BTRFS_STRIPE_LEN;
+ if (type & BTRFS_BLOCK_GROUP_RAID0)
+ num_stripes = nr_devices;
+ else if (type & BTRFS_BLOCK_GROUP_RAID1)
+ num_stripes = 2;
+ else if (type & BTRFS_BLOCK_GROUP_RAID10)
+ num_stripes = 4;
+
+ /* Adjust for more than 1 stripe per device */
+ min_stripe_size = rattr->dev_stripes * BTRFS_STRIPE_LEN;
rcu_read_lock();
list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
@@ -2010,28 +1956,21 @@
avail_space = device->total_bytes - device->bytes_used;
/* align with stripe_len */
- avail_space = div_u64(avail_space, BTRFS_STRIPE_LEN);
- avail_space *= BTRFS_STRIPE_LEN;
+ avail_space = rounddown(avail_space, BTRFS_STRIPE_LEN);
/*
* In order to avoid overwriting the superblock on the drive,
* btrfs starts at an offset of at least 1MB when doing chunk
* allocation.
+ *
+ * This ensures we have at least min_stripe_size free space
+ * after excluding 1MB.
*/
- skip_space = SZ_1M;
-
- /*
- * we can use the free space in [0, skip_space - 1], subtract
- * it from the total.
- */
- if (avail_space && avail_space >= skip_space)
- avail_space -= skip_space;
- else
- avail_space = 0;
-
- if (avail_space < min_stripe_size)
+ if (avail_space <= SZ_1M + min_stripe_size)
continue;
+ avail_space -= SZ_1M;
+
devices_info[i].dev = device;
devices_info[i].max_avail = avail_space;
@@ -2045,9 +1984,8 @@
i = nr_devices - 1;
avail_space = 0;
- while (nr_devices >= min_stripes) {
- if (num_stripes > nr_devices)
- num_stripes = nr_devices;
+ while (nr_devices >= rattr->devs_min) {
+ num_stripes = min(num_stripes, nr_devices);
if (devices_info[i].max_avail >= min_stripe_size) {
int j;
@@ -2090,7 +2028,7 @@
u64 total_free_data = 0;
u64 total_free_meta = 0;
int bits = dentry->d_sb->s_blocksize_bits;
- __be32 *fsid = (__be32 *)fs_info->fsid;
+ __be32 *fsid = (__be32 *)fs_info->fs_devices->fsid;
unsigned factor = 1;
struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
int ret;
@@ -2177,8 +2115,10 @@
buf->f_fsid.val[0] = be32_to_cpu(fsid[0]) ^ be32_to_cpu(fsid[2]);
buf->f_fsid.val[1] = be32_to_cpu(fsid[1]) ^ be32_to_cpu(fsid[3]);
/* Mask in the root object ID too, to disambiguate subvols */
- buf->f_fsid.val[0] ^= BTRFS_I(d_inode(dentry))->root->objectid >> 32;
- buf->f_fsid.val[1] ^= BTRFS_I(d_inode(dentry))->root->objectid;
+ buf->f_fsid.val[0] ^=
+ BTRFS_I(d_inode(dentry))->root->root_key.objectid >> 32;
+ buf->f_fsid.val[1] ^=
+ BTRFS_I(d_inode(dentry))->root->root_key.objectid;
return 0;
}
@@ -2245,6 +2185,9 @@
ret = PTR_ERR_OR_ZERO(device);
mutex_unlock(&uuid_mutex);
break;
+ case BTRFS_IOC_FORGET_DEV:
+ ret = btrfs_forget_devices(vol->name);
+ break;
case BTRFS_IOC_DEVICES_READY:
mutex_lock(&uuid_mutex);
device = btrfs_scan_one_device(vol->name, FMODE_READ,
@@ -2310,7 +2253,7 @@
* device_list_mutex here as we only read the device data and the list
* is protected by RCU. Even if a device is deleted during the list
* traversals, we'll get valid data, the freeing callback will wait at
- * least until until the rcu_read_unlock.
+ * least until the rcu_read_unlock.
*/
rcu_read_lock();
cur_devices = fs_info->fs_devices;
@@ -2344,6 +2287,7 @@
.show_devname = btrfs_show_devname,
.alloc_inode = btrfs_alloc_inode,
.destroy_inode = btrfs_destroy_inode,
+ .free_inode = btrfs_free_inode,
.statfs = btrfs_statfs,
.remount_fs = btrfs_remount,
.freeze_fs = btrfs_freeze,
@@ -2511,3 +2455,4 @@
module_exit(exit_btrfs_fs)
MODULE_LICENSE("GPL");
+MODULE_SOFTDEP("pre: crc32c");