Btrfs: fix unprotected device's variants on 32bits machine
->total_bytes,->disk_total_bytes,->bytes_used is protected by chunk
lock when we change them, but sometimes we read them without any lock,
and we might get unexpected value. We fix this problem like inode's
i_size.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 1be03d8..da7ac14 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -418,7 +418,7 @@
/* the disk copy procedure reuses the scrub code */
ret = btrfs_scrub_dev(fs_info, src_device->devid, 0,
- src_device->total_bytes,
+ btrfs_device_get_total_bytes(src_device),
&dev_replace->scrub_progress, 0, 1);
ret = btrfs_dev_replace_finishing(root->fs_info, ret);
@@ -555,11 +555,12 @@
memcpy(uuid_tmp, tgt_device->uuid, sizeof(uuid_tmp));
memcpy(tgt_device->uuid, src_device->uuid, sizeof(tgt_device->uuid));
memcpy(src_device->uuid, uuid_tmp, sizeof(src_device->uuid));
- tgt_device->total_bytes = src_device->total_bytes;
- tgt_device->disk_total_bytes = src_device->disk_total_bytes;
+ btrfs_device_set_total_bytes(tgt_device, src_device->total_bytes);
+ btrfs_device_set_disk_total_bytes(tgt_device,
+ src_device->disk_total_bytes);
+ btrfs_device_set_bytes_used(tgt_device, src_device->bytes_used);
ASSERT(list_empty(&src_device->resized_list));
tgt_device->commit_total_bytes = src_device->commit_total_bytes;
- tgt_device->bytes_used = src_device->bytes_used;
tgt_device->commit_bytes_used = src_device->bytes_used;
if (fs_info->sb->s_bdev == src_device->bdev)
fs_info->sb->s_bdev = tgt_device->bdev;
@@ -650,6 +651,7 @@
struct btrfs_ioctl_dev_replace_args *args)
{
struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
+ struct btrfs_device *srcdev;
btrfs_dev_replace_lock(dev_replace);
/* even if !dev_replace_is_valid, the values are good enough for
@@ -672,8 +674,9 @@
break;
case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
+ srcdev = dev_replace->srcdev;
args->status.progress_1000 = div64_u64(dev_replace->cursor_left,
- div64_u64(dev_replace->srcdev->total_bytes, 1000));
+ div64_u64(btrfs_device_get_total_bytes(srcdev), 1000));
break;
}
btrfs_dev_replace_unlock(dev_replace);
@@ -832,7 +835,7 @@
ret = btrfs_scrub_dev(fs_info, dev_replace->srcdev->devid,
dev_replace->committed_cursor_left,
- dev_replace->srcdev->total_bytes,
+ btrfs_device_get_total_bytes(dev_replace->srcdev),
&dev_replace->scrub_progress, 0, 1);
ret = btrfs_dev_replace_finishing(fs_info, ret);
WARN_ON(ret);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index f60d1ca..0ff2127 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1553,7 +1553,7 @@
goto out_free;
}
- old_size = device->total_bytes;
+ old_size = btrfs_device_get_total_bytes(device);
if (mod < 0) {
if (new_size > old_size) {
@@ -2740,8 +2740,8 @@
}
di_args->devid = dev->devid;
- di_args->bytes_used = dev->bytes_used;
- di_args->total_bytes = dev->total_bytes;
+ di_args->bytes_used = btrfs_device_get_bytes_used(dev);
+ di_args->total_bytes = btrfs_device_get_total_bytes(dev);
memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid));
if (dev->name) {
struct rcu_string *name;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d8e4a3d..41da102 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1308,7 +1308,7 @@
if (device->bytes_used > 0) {
u64 len = btrfs_dev_extent_length(leaf, extent);
- device->bytes_used -= len;
+ btrfs_device_set_bytes_used(device, device->bytes_used - len);
spin_lock(&root->fs_info->free_chunk_lock);
root->fs_info->free_chunk_space += len;
spin_unlock(&root->fs_info->free_chunk_lock);
@@ -1462,8 +1462,10 @@
btrfs_set_device_io_align(leaf, dev_item, device->io_align);
btrfs_set_device_io_width(leaf, dev_item, device->io_width);
btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
- btrfs_set_device_total_bytes(leaf, dev_item, device->disk_total_bytes);
- btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);
+ btrfs_set_device_total_bytes(leaf, dev_item,
+ btrfs_device_get_disk_total_bytes(device));
+ btrfs_set_device_bytes_used(leaf, dev_item,
+ btrfs_device_get_bytes_used(device));
btrfs_set_device_group(leaf, dev_item, 0);
btrfs_set_device_seek_speed(leaf, dev_item, 0);
btrfs_set_device_bandwidth(leaf, dev_item, 0);
@@ -2330,7 +2332,8 @@
}
- if (i_size_read(bdev->bd_inode) < srcdev->total_bytes) {
+ if (i_size_read(bdev->bd_inode) <
+ btrfs_device_get_total_bytes(srcdev)) {
btrfs_err(fs_info, "target device is smaller than source device!");
ret = -EINVAL;
goto error;
@@ -2360,11 +2363,11 @@
device->io_width = root->sectorsize;
device->io_align = root->sectorsize;
device->sector_size = root->sectorsize;
- device->total_bytes = srcdev->total_bytes;
- device->disk_total_bytes = srcdev->disk_total_bytes;
+ device->total_bytes = btrfs_device_get_total_bytes(srcdev);
+ device->disk_total_bytes = btrfs_device_get_disk_total_bytes(srcdev);
+ device->bytes_used = btrfs_device_get_bytes_used(srcdev);
ASSERT(list_empty(&srcdev->resized_list));
device->commit_total_bytes = srcdev->commit_total_bytes;
- device->bytes_used = srcdev->bytes_used;
device->commit_bytes_used = device->bytes_used;
device->dev_root = fs_info->dev_root;
device->bdev = bdev;
@@ -2435,8 +2438,10 @@
btrfs_set_device_io_align(leaf, dev_item, device->io_align);
btrfs_set_device_io_width(leaf, dev_item, device->io_width);
btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
- btrfs_set_device_total_bytes(leaf, dev_item, device->disk_total_bytes);
- btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);
+ btrfs_set_device_total_bytes(leaf, dev_item,
+ btrfs_device_get_disk_total_bytes(device));
+ btrfs_set_device_bytes_used(leaf, dev_item,
+ btrfs_device_get_bytes_used(device));
btrfs_mark_buffer_dirty(leaf);
out:
@@ -2464,8 +2469,8 @@
btrfs_set_super_total_bytes(super_copy, old_total + diff);
device->fs_devices->total_rw_bytes += diff;
- device->total_bytes = new_size;
- device->disk_total_bytes = new_size;
+ btrfs_device_set_total_bytes(device, new_size);
+ btrfs_device_set_disk_total_bytes(device, new_size);
btrfs_clear_space_info_full(device->dev_root->fs_info);
if (list_empty(&device->resized_list))
list_add_tail(&device->resized_list,
@@ -3110,11 +3115,12 @@
/* step one make some room on all the devices */
devices = &fs_info->fs_devices->devices;
list_for_each_entry(device, devices, dev_list) {
- old_size = device->total_bytes;
+ old_size = btrfs_device_get_total_bytes(device);
size_to_free = div_factor(old_size, 1);
size_to_free = min(size_to_free, (u64)1 * 1024 * 1024);
if (!device->writeable ||
- device->total_bytes - device->bytes_used > size_to_free ||
+ btrfs_device_get_total_bytes(device) -
+ btrfs_device_get_bytes_used(device) > size_to_free ||
device->is_tgtdev_for_dev_replace)
continue;
@@ -3920,8 +3926,8 @@
struct btrfs_key key;
struct btrfs_super_block *super_copy = root->fs_info->super_copy;
u64 old_total = btrfs_super_total_bytes(super_copy);
- u64 old_size = device->total_bytes;
- u64 diff = device->total_bytes - new_size;
+ u64 old_size = btrfs_device_get_total_bytes(device);
+ u64 diff = old_size - new_size;
if (device->is_tgtdev_for_dev_replace)
return -EINVAL;
@@ -3934,7 +3940,7 @@
lock_chunks(root);
- device->total_bytes = new_size;
+ btrfs_device_set_total_bytes(device, new_size);
if (device->writeable) {
device->fs_devices->total_rw_bytes -= diff;
spin_lock(&root->fs_info->free_chunk_lock);
@@ -4000,7 +4006,7 @@
ret = -ENOSPC;
lock_chunks(root);
- device->total_bytes = old_size;
+ btrfs_device_set_total_bytes(device, old_size);
if (device->writeable)
device->fs_devices->total_rw_bytes += diff;
spin_lock(&root->fs_info->free_chunk_lock);
@@ -4018,7 +4024,7 @@
}
lock_chunks(root);
- device->disk_total_bytes = new_size;
+ btrfs_device_set_disk_total_bytes(device, new_size);
if (list_empty(&device->resized_list))
list_add_tail(&device->resized_list,
&root->fs_info->fs_devices->resized_devices);
@@ -4429,8 +4435,10 @@
if (ret)
goto error_del_extent;
- for (i = 0; i < map->num_stripes; i++)
- map->stripes[i].dev->bytes_used += stripe_size;
+ for (i = 0; i < map->num_stripes; i++) {
+ num_bytes = map->stripes[i].dev->bytes_used + stripe_size;
+ btrfs_device_set_bytes_used(map->stripes[i].dev, num_bytes);
+ }
spin_lock(&extent_root->fs_info->free_chunk_lock);
extent_root->fs_info->free_chunk_space -= (stripe_size *
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index f79d532..76600a3 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -32,6 +32,19 @@
struct bio *tail;
};
+/*
+ * Use sequence counter to get consistent device stat data on
+ * 32-bit processors.
+ */
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+#include <linux/seqlock.h>
+#define __BTRFS_NEED_DEVICE_DATA_ORDERED
+#define btrfs_device_data_ordered_init(device) \
+ seqcount_init(&device->data_seqcount)
+#else
+#define btrfs_device_data_ordered_init(device) do { } while (0)
+#endif
+
struct btrfs_device {
struct list_head dev_list;
struct list_head dev_alloc_list;
@@ -61,6 +74,10 @@
int can_discard;
int is_tgtdev_for_dev_replace;
+#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
+ seqcount_t data_seqcount;
+#endif
+
/* the internal btrfs device id */
u64 devid;
@@ -133,6 +150,73 @@
atomic_t dev_stat_values[BTRFS_DEV_STAT_VALUES_MAX];
};
+/*
+ * If we read those variants at the context of their own lock, we needn't
+ * use the following helpers, reading them directly is safe.
+ */
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+#define BTRFS_DEVICE_GETSET_FUNCS(name) \
+static inline u64 \
+btrfs_device_get_##name(const struct btrfs_device *dev) \
+{ \
+ u64 size; \
+ unsigned int seq; \
+ \
+ do { \
+ seq = read_seqcount_begin(&dev->data_seqcount); \
+ size = dev->name; \
+ } while (read_seqcount_retry(&dev->data_seqcount, seq)); \
+ return size; \
+} \
+ \
+static inline void \
+btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \
+{ \
+ preempt_disable(); \
+ write_seqcount_begin(&dev->data_seqcount); \
+ dev->name = size; \
+ write_seqcount_end(&dev->data_seqcount); \
+ preempt_enable(); \
+}
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#define BTRFS_DEVICE_GETSET_FUNCS(name) \
+static inline u64 \
+btrfs_device_get_##name(const struct btrfs_device *dev) \
+{ \
+ u64 size; \
+ \
+ preempt_disable(); \
+ size = dev->name; \
+ preempt_enable(); \
+ return size; \
+} \
+ \
+static inline void \
+btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \
+{ \
+ preempt_disable(); \
+ dev->name = size; \
+ preempt_enable(); \
+}
+#else
+#define BTRFS_DEVICE_GETSET_FUNCS(name) \
+static inline u64 \
+btrfs_device_get_##name(const struct btrfs_device *dev) \
+{ \
+ return dev->name; \
+} \
+ \
+static inline void \
+btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \
+{ \
+ dev->name = size; \
+}
+#endif
+
+BTRFS_DEVICE_GETSET_FUNCS(total_bytes);
+BTRFS_DEVICE_GETSET_FUNCS(disk_total_bytes);
+BTRFS_DEVICE_GETSET_FUNCS(bytes_used);
+
struct btrfs_fs_devices {
u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */