From 01573e231f18eb2d99162747186f59511f56b64d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 08 Dec 2023 10:40:48 +0000
Subject: [PATCH] 移去rt
---
kernel/fs/btrfs/volumes.c | 3618 +++++++++++++++++++++++++++++++---------------------------
1 files changed, 1,942 insertions(+), 1,676 deletions(-)
diff --git a/kernel/fs/btrfs/volumes.c b/kernel/fs/btrfs/volumes.c
index 8f05e6a..9191bbb 100644
--- a/kernel/fs/btrfs/volumes.c
+++ b/kernel/fs/btrfs/volumes.c
@@ -7,7 +7,6 @@
#include <linux/sched/mm.h>
#include <linux/bio.h>
#include <linux/slab.h>
-#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
@@ -15,6 +14,8 @@
#include <linux/semaphore.h>
#include <linux/uuid.h>
#include <linux/list_sort.h>
+#include <linux/namei.h>
+#include "misc.h"
#include "ctree.h"
#include "extent_map.h"
#include "disk-io.h"
@@ -25,10 +26,12 @@
#include "async-thread.h"
#include "check-integrity.h"
#include "rcu-string.h"
-#include "math.h"
#include "dev-replace.h"
#include "sysfs.h"
#include "tree-checker.h"
+#include "space-info.h"
+#include "block-group.h"
+#include "discard.h"
const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
[BTRFS_RAID_RAID10] = {
@@ -39,6 +42,7 @@
.tolerated_failures = 1,
.devs_increment = 2,
.ncopies = 2,
+ .nparity = 0,
.raid_name = "raid10",
.bg_flag = BTRFS_BLOCK_GROUP_RAID10,
.mindev_error = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET,
@@ -51,9 +55,36 @@
.tolerated_failures = 1,
.devs_increment = 2,
.ncopies = 2,
+ .nparity = 0,
.raid_name = "raid1",
.bg_flag = BTRFS_BLOCK_GROUP_RAID1,
.mindev_error = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
+ },
+ [BTRFS_RAID_RAID1C3] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 3,
+ .devs_min = 3,
+ .tolerated_failures = 2,
+ .devs_increment = 3,
+ .ncopies = 3,
+ .nparity = 0,
+ .raid_name = "raid1c3",
+ .bg_flag = BTRFS_BLOCK_GROUP_RAID1C3,
+ .mindev_error = BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET,
+ },
+ [BTRFS_RAID_RAID1C4] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 4,
+ .devs_min = 4,
+ .tolerated_failures = 3,
+ .devs_increment = 4,
+ .ncopies = 4,
+ .nparity = 0,
+ .raid_name = "raid1c4",
+ .bg_flag = BTRFS_BLOCK_GROUP_RAID1C4,
+ .mindev_error = BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET,
},
[BTRFS_RAID_DUP] = {
.sub_stripes = 1,
@@ -63,6 +94,7 @@
.tolerated_failures = 0,
.devs_increment = 1,
.ncopies = 2,
+ .nparity = 0,
.raid_name = "dup",
.bg_flag = BTRFS_BLOCK_GROUP_DUP,
.mindev_error = 0,
@@ -75,6 +107,7 @@
.tolerated_failures = 0,
.devs_increment = 1,
.ncopies = 1,
+ .nparity = 0,
.raid_name = "raid0",
.bg_flag = BTRFS_BLOCK_GROUP_RAID0,
.mindev_error = 0,
@@ -87,6 +120,7 @@
.tolerated_failures = 0,
.devs_increment = 1,
.ncopies = 1,
+ .nparity = 0,
.raid_name = "single",
.bg_flag = 0,
.mindev_error = 0,
@@ -99,6 +133,7 @@
.tolerated_failures = 1,
.devs_increment = 1,
.ncopies = 1,
+ .nparity = 1,
.raid_name = "raid5",
.bg_flag = BTRFS_BLOCK_GROUP_RAID5,
.mindev_error = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET,
@@ -111,24 +146,79 @@
.tolerated_failures = 2,
.devs_increment = 1,
.ncopies = 1,
+ .nparity = 2,
.raid_name = "raid6",
.bg_flag = BTRFS_BLOCK_GROUP_RAID6,
.mindev_error = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET,
},
};
-const char *get_raid_name(enum btrfs_raid_types type)
+const char *btrfs_bg_type_to_raid_name(u64 flags)
{
- if (type >= BTRFS_NR_RAID_TYPES)
+ const int index = btrfs_bg_flags_to_raid_index(flags);
+
+ if (index >= BTRFS_NR_RAID_TYPES)
return NULL;
- return btrfs_raid_array[type].raid_name;
+ return btrfs_raid_array[index].raid_name;
}
-static int init_first_rw_device(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info);
+/*
+ * Fill @buf with textual description of @bg_flags, no more than @size_buf
+ * bytes including terminating null byte.
+ */
+void btrfs_describe_block_groups(u64 bg_flags, char *buf, u32 size_buf)
+{
+ int i;
+ int ret;
+ char *bp = buf;
+ u64 flags = bg_flags;
+ u32 size_bp = size_buf;
+
+ if (!flags) {
+ strcpy(bp, "NONE");
+ return;
+ }
+
+#define DESCRIBE_FLAG(flag, desc) \
+ do { \
+ if (flags & (flag)) { \
+ ret = snprintf(bp, size_bp, "%s|", (desc)); \
+ if (ret < 0 || ret >= size_bp) \
+ goto out_overflow; \
+ size_bp -= ret; \
+ bp += ret; \
+ flags &= ~(flag); \
+ } \
+ } while (0)
+
+ DESCRIBE_FLAG(BTRFS_BLOCK_GROUP_DATA, "data");
+ DESCRIBE_FLAG(BTRFS_BLOCK_GROUP_SYSTEM, "system");
+ DESCRIBE_FLAG(BTRFS_BLOCK_GROUP_METADATA, "metadata");
+
+ DESCRIBE_FLAG(BTRFS_AVAIL_ALLOC_BIT_SINGLE, "single");
+ for (i = 0; i < BTRFS_NR_RAID_TYPES; i++)
+ DESCRIBE_FLAG(btrfs_raid_array[i].bg_flag,
+ btrfs_raid_array[i].raid_name);
+#undef DESCRIBE_FLAG
+
+ if (flags) {
+ ret = snprintf(bp, size_bp, "0x%llx|", flags);
+ size_bp -= ret;
+ }
+
+ if (size_bp < size_buf)
+ buf[size_buf - size_bp - 1] = '\0'; /* remove last | */
+
+ /*
+ * The text is trimmed, it's up to the caller to provide sufficiently
+ * large buffer
+ */
+out_overflow:;
+}
+
+static int init_first_rw_device(struct btrfs_trans_handle *trans);
static int btrfs_relocate_sys_chunks(struct btrfs_fs_info *fs_info);
-static void __btrfs_reset_dev_stats(struct btrfs_device *dev);
static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev);
static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
@@ -153,7 +243,7 @@
* the mutex can be very coarse and can cover long-running operations
*
* protects: updates to fs_devices counters like missing devices, rw devices,
- * seeding, structure cloning, openning/closing devices at mount/umount time
+ * seeding, structure cloning, opening/closing devices at mount/umount time
*
* global::fs_devs - add, remove, updates to the global list
*
@@ -183,7 +273,9 @@
* chunk_mutex
* -----------
* protects chunks, adding or removing during allocation, trim or when a new
- * device is added/removed
+ * device is added/removed. Additionally it also protects post_commit_list of
+ * individual devices, since they can be added to the transaction's
+ * post_commit_list only with chunk_mutex held.
*
* cleaner_mutex
* -------------
@@ -195,14 +287,13 @@
* ============
*
* uuid_mutex
- * volume_mutex
- * device_list_mutex
- * chunk_mutex
- * balance_mutex
+ * device_list_mutex
+ * chunk_mutex
+ * balance_mutex
*
*
- * Exclusive operations, BTRFS_FS_EXCL_OP
- * ======================================
+ * Exclusive operations
+ * ====================
*
* Maintains the exclusivity of the following operations that apply to the
* whole filesystem and cannot run in parallel.
@@ -228,30 +319,32 @@
* - system power-cycle and filesystem mounted as read-only
* - filesystem or device errors leading to forced read-only
*
- * BTRFS_FS_EXCL_OP flag is set and cleared using atomic operations.
- * During the course of Paused state, the BTRFS_FS_EXCL_OP remains set.
+ * The status of exclusive operation is set and cleared atomically.
+ * During the course of Paused state, fs_info::exclusive_operation remains set.
* A device operation in Paused or Running state can be canceled or resumed
* either by ioctl (Balance only) or when remounted as read-write.
- * BTRFS_FS_EXCL_OP flag is cleared when the device operation is canceled or
+ * The exclusive status is cleared when the device operation is canceled or
* completed.
*/
DEFINE_MUTEX(uuid_mutex);
static LIST_HEAD(fs_uuids);
-struct list_head *btrfs_get_fs_uuids(void)
+struct list_head * __attribute_const__ btrfs_get_fs_uuids(void)
{
return &fs_uuids;
}
/*
* alloc_fs_devices - allocate struct btrfs_fs_devices
- * @fsid: if not NULL, copy the uuid to fs_devices::fsid
+ * @fsid: if not NULL, copy the UUID to fs_devices::fsid
+ * @metadata_fsid: if not NULL, copy the UUID to fs_devices::metadata_fsid
*
* Return a pointer to a new struct btrfs_fs_devices on success, or ERR_PTR().
* The returned struct is not linked onto any lists and can be destroyed with
* kfree() right away.
*/
-static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid)
+static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid,
+ const u8 *metadata_fsid)
{
struct btrfs_fs_devices *fs_devs;
@@ -262,18 +355,25 @@
mutex_init(&fs_devs->device_list_mutex);
INIT_LIST_HEAD(&fs_devs->devices);
- INIT_LIST_HEAD(&fs_devs->resized_devices);
INIT_LIST_HEAD(&fs_devs->alloc_list);
INIT_LIST_HEAD(&fs_devs->fs_list);
+ INIT_LIST_HEAD(&fs_devs->seed_list);
if (fsid)
memcpy(fs_devs->fsid, fsid, BTRFS_FSID_SIZE);
+
+ if (metadata_fsid)
+ memcpy(fs_devs->metadata_uuid, metadata_fsid, BTRFS_FSID_SIZE);
+ else if (fsid)
+ memcpy(fs_devs->metadata_uuid, fsid, BTRFS_FSID_SIZE);
return fs_devs;
}
void btrfs_free_device(struct btrfs_device *device)
{
+ WARN_ON(!list_empty(&device->post_commit_list));
rcu_string_free(device->name);
+ extent_io_tree_release(&device->alloc_state);
bio_put(device->flush_bio);
kfree(device);
}
@@ -289,19 +389,6 @@
btrfs_free_device(device);
}
kfree(fs_devices);
-}
-
-static void btrfs_kobject_uevent(struct block_device *bdev,
- enum kobject_action action)
-{
- int ret;
-
- ret = kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, action);
- if (ret)
- pr_warn("BTRFS: Sending event '%d' to kobject: '%s' (%p): failed\n",
- action,
- kobject_name(&disk_to_dev(bdev->bd_disk)->kobj),
- &disk_to_dev(bdev->bd_disk)->kobj);
}
void __exit btrfs_cleanup_fs_uuids(void)
@@ -321,7 +408,7 @@
* Returned struct is not linked onto any lists and must be destroyed using
* btrfs_free_device.
*/
-static struct btrfs_device *__alloc_device(void)
+static struct btrfs_device *__alloc_device(struct btrfs_fs_info *fs_info)
{
struct btrfs_device *dev;
@@ -341,34 +428,86 @@
INIT_LIST_HEAD(&dev->dev_list);
INIT_LIST_HEAD(&dev->dev_alloc_list);
- INIT_LIST_HEAD(&dev->resized_list);
-
- spin_lock_init(&dev->io_lock);
+ INIT_LIST_HEAD(&dev->post_commit_list);
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
btrfs_device_data_ordered_init(dev);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
+ extent_io_tree_init(fs_info, &dev->alloc_state,
+ IO_TREE_DEVICE_ALLOC_STATE, NULL);
return dev;
}
-static noinline struct btrfs_fs_devices *find_fsid(u8 *fsid)
+static noinline struct btrfs_fs_devices *find_fsid(
+ const u8 *fsid, const u8 *metadata_fsid)
{
struct btrfs_fs_devices *fs_devices;
+ ASSERT(fsid);
+
+ /* Handle non-split brain cases */
list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
- if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0)
- return fs_devices;
+ if (metadata_fsid) {
+ if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0
+ && memcmp(metadata_fsid, fs_devices->metadata_uuid,
+ BTRFS_FSID_SIZE) == 0)
+ return fs_devices;
+ } else {
+ if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0)
+ return fs_devices;
+ }
}
return NULL;
}
+static struct btrfs_fs_devices *find_fsid_with_metadata_uuid(
+ struct btrfs_super_block *disk_super)
+{
+
+ struct btrfs_fs_devices *fs_devices;
+
+ /*
+ * Handle scanned device having completed its fsid change but
+ * belonging to a fs_devices that was created by first scanning
+ * a device which didn't have its fsid/metadata_uuid changed
+ * at all and the CHANGING_FSID_V2 flag set.
+ */
+ list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+ if (fs_devices->fsid_change &&
+ memcmp(disk_super->metadata_uuid, fs_devices->fsid,
+ BTRFS_FSID_SIZE) == 0 &&
+ memcmp(fs_devices->fsid, fs_devices->metadata_uuid,
+ BTRFS_FSID_SIZE) == 0) {
+ return fs_devices;
+ }
+ }
+ /*
+ * Handle scanned device having completed its fsid change but
+ * belonging to a fs_devices that was created by a device that
+ * has an outdated pair of fsid/metadata_uuid and
+ * CHANGING_FSID_V2 flag set.
+ */
+ list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+ if (fs_devices->fsid_change &&
+ memcmp(fs_devices->metadata_uuid,
+ fs_devices->fsid, BTRFS_FSID_SIZE) != 0 &&
+ memcmp(disk_super->metadata_uuid, fs_devices->metadata_uuid,
+ BTRFS_FSID_SIZE) == 0) {
+ return fs_devices;
+ }
+ }
+
+ return find_fsid(disk_super->fsid, disk_super->metadata_uuid);
+}
+
+
static int
btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder,
int flush, struct block_device **bdev,
- struct buffer_head **bh)
+ struct btrfs_super_block **disk_super)
{
int ret;
@@ -387,9 +526,9 @@
goto error;
}
invalidate_bdev(*bdev);
- *bh = btrfs_read_dev_super(*bdev);
- if (IS_ERR(*bh)) {
- ret = PTR_ERR(*bh);
+ *disk_super = btrfs_read_dev_super(*bdev);
+ if (IS_ERR(*disk_super)) {
+ ret = PTR_ERR(*disk_super);
blkdev_put(*bdev, flags);
goto error;
}
@@ -398,214 +537,50 @@
error:
*bdev = NULL;
- *bh = NULL;
return ret;
}
-static void requeue_list(struct btrfs_pending_bios *pending_bios,
- struct bio *head, struct bio *tail)
-{
-
- struct bio *old_head;
-
- old_head = pending_bios->head;
- pending_bios->head = head;
- if (pending_bios->tail)
- tail->bi_next = old_head;
- else
- pending_bios->tail = tail;
-}
-
/*
- * we try to collect pending bios for a device so we don't get a large
- * number of procs sending bios down to the same device. This greatly
- * improves the schedulers ability to collect and merge the bios.
+ * Check if the device in the path matches the device in the given struct device.
*
- * But, it also turns into a long list of bios to process and that is sure
- * to eventually make the worker thread block. The solution here is to
- * make some progress and then put this work struct back at the end of
- * the list if the block device is congested. This way, multiple devices
- * can make progress from a single worker thread.
+ * Returns:
+ * true If it is the same device.
+ * false If it is not the same device or on error.
*/
-static noinline void run_scheduled_bios(struct btrfs_device *device)
+static bool device_matched(const struct btrfs_device *device, const char *path)
{
- struct btrfs_fs_info *fs_info = device->fs_info;
- struct bio *pending;
- struct backing_dev_info *bdi;
- struct btrfs_pending_bios *pending_bios;
- struct bio *tail;
- struct bio *cur;
- int again = 0;
- unsigned long num_run;
- unsigned long batch_run = 0;
- unsigned long last_waited = 0;
- int force_reg = 0;
- int sync_pending = 0;
- struct blk_plug plug;
+ char *device_name;
+ struct block_device *bdev_old;
+ struct block_device *bdev_new;
/*
- * this function runs all the bios we've collected for
- * a particular device. We don't want to wander off to
- * another device without first sending all of these down.
- * So, setup a plug here and finish it off before we return
+ * If we are looking for a device with the matching dev_t, then skip
+ * device without a name (a missing device).
*/
- blk_start_plug(&plug);
+ if (!device->name)
+ return false;
- bdi = device->bdev->bd_bdi;
+ device_name = kzalloc(BTRFS_PATH_NAME_MAX, GFP_KERNEL);
+ if (!device_name)
+ return false;
-loop:
- spin_lock(&device->io_lock);
+ rcu_read_lock();
+ scnprintf(device_name, BTRFS_PATH_NAME_MAX, "%s", rcu_str_deref(device->name));
+ rcu_read_unlock();
-loop_lock:
- num_run = 0;
+ bdev_old = lookup_bdev(device_name);
+ kfree(device_name);
+ if (IS_ERR(bdev_old))
+ return false;
- /* take all the bios off the list at once and process them
- * later on (without the lock held). But, remember the
- * tail and other pointers so the bios can be properly reinserted
- * into the list if we hit congestion
- */
- if (!force_reg && device->pending_sync_bios.head) {
- pending_bios = &device->pending_sync_bios;
- force_reg = 1;
- } else {
- pending_bios = &device->pending_bios;
- force_reg = 0;
- }
+ bdev_new = lookup_bdev(path);
+ if (IS_ERR(bdev_new))
+ return false;
- pending = pending_bios->head;
- tail = pending_bios->tail;
- WARN_ON(pending && !tail);
+ if (bdev_old == bdev_new)
+ return true;
- /*
- * if pending was null this time around, no bios need processing
- * at all and we can stop. Otherwise it'll loop back up again
- * and do an additional check so no bios are missed.
- *
- * device->running_pending is used to synchronize with the
- * schedule_bio code.
- */
- if (device->pending_sync_bios.head == NULL &&
- device->pending_bios.head == NULL) {
- again = 0;
- device->running_pending = 0;
- } else {
- again = 1;
- device->running_pending = 1;
- }
-
- pending_bios->head = NULL;
- pending_bios->tail = NULL;
-
- spin_unlock(&device->io_lock);
-
- while (pending) {
-
- rmb();
- /* we want to work on both lists, but do more bios on the
- * sync list than the regular list
- */
- if ((num_run > 32 &&
- pending_bios != &device->pending_sync_bios &&
- device->pending_sync_bios.head) ||
- (num_run > 64 && pending_bios == &device->pending_sync_bios &&
- device->pending_bios.head)) {
- spin_lock(&device->io_lock);
- requeue_list(pending_bios, pending, tail);
- goto loop_lock;
- }
-
- cur = pending;
- pending = pending->bi_next;
- cur->bi_next = NULL;
-
- BUG_ON(atomic_read(&cur->__bi_cnt) == 0);
-
- /*
- * if we're doing the sync list, record that our
- * plug has some sync requests on it
- *
- * If we're doing the regular list and there are
- * sync requests sitting around, unplug before
- * we add more
- */
- if (pending_bios == &device->pending_sync_bios) {
- sync_pending = 1;
- } else if (sync_pending) {
- blk_finish_plug(&plug);
- blk_start_plug(&plug);
- sync_pending = 0;
- }
-
- btrfsic_submit_bio(cur);
- num_run++;
- batch_run++;
-
- cond_resched();
-
- /*
- * we made progress, there is more work to do and the bdi
- * is now congested. Back off and let other work structs
- * run instead
- */
- if (pending && bdi_write_congested(bdi) && batch_run > 8 &&
- fs_info->fs_devices->open_devices > 1) {
- struct io_context *ioc;
-
- ioc = current->io_context;
-
- /*
- * the main goal here is that we don't want to
- * block if we're going to be able to submit
- * more requests without blocking.
- *
- * This code does two great things, it pokes into
- * the elevator code from a filesystem _and_
- * it makes assumptions about how batching works.
- */
- if (ioc && ioc->nr_batch_requests > 0 &&
- time_before(jiffies, ioc->last_waited + HZ/50UL) &&
- (last_waited == 0 ||
- ioc->last_waited == last_waited)) {
- /*
- * we want to go through our batch of
- * requests and stop. So, we copy out
- * the ioc->last_waited time and test
- * against it before looping
- */
- last_waited = ioc->last_waited;
- cond_resched();
- continue;
- }
- spin_lock(&device->io_lock);
- requeue_list(pending_bios, pending, tail);
- device->running_pending = 1;
-
- spin_unlock(&device->io_lock);
- btrfs_queue_work(fs_info->submit_workers,
- &device->work);
- goto done;
- }
- }
-
- cond_resched();
- if (again)
- goto loop;
-
- spin_lock(&device->io_lock);
- if (device->pending_bios.head || device->pending_sync_bios.head)
- goto loop_lock;
- spin_unlock(&device->io_lock);
-
-done:
- blk_finish_plug(&plug);
-}
-
-static void pending_bios_fn(struct btrfs_work *work)
-{
- struct btrfs_device *device;
-
- device = container_of(work, struct btrfs_device, work);
- run_scheduled_bios(device);
+ return false;
}
/*
@@ -615,52 +590,55 @@
* matching this path only.
* skip_dev: Optional. Will skip this device when searching for the stale
* devices.
+ * Return: 0 for success or if @path is NULL.
+ * -EBUSY if @path is a mounted device.
+ * -ENOENT if @path does not match any device in the list.
*/
-static void btrfs_free_stale_devices(const char *path,
+static int btrfs_free_stale_devices(const char *path,
struct btrfs_device *skip_device)
{
struct btrfs_fs_devices *fs_devices, *tmp_fs_devices;
struct btrfs_device *device, *tmp_device;
+ int ret = 0;
+
+ lockdep_assert_held(&uuid_mutex);
+
+ if (path)
+ ret = -ENOENT;
list_for_each_entry_safe(fs_devices, tmp_fs_devices, &fs_uuids, fs_list) {
- mutex_lock(&fs_devices->device_list_mutex);
- if (fs_devices->opened) {
- mutex_unlock(&fs_devices->device_list_mutex);
- continue;
- }
+ mutex_lock(&fs_devices->device_list_mutex);
list_for_each_entry_safe(device, tmp_device,
&fs_devices->devices, dev_list) {
- int not_found = 0;
-
if (skip_device && skip_device == device)
continue;
- if (path && !device->name)
+ if (path && !device_matched(device, path))
continue;
-
- rcu_read_lock();
- if (path)
- not_found = strcmp(rcu_str_deref(device->name),
- path);
- rcu_read_unlock();
- if (not_found)
- continue;
+ if (fs_devices->opened) {
+ /* for an already deleted device return 0 */
+ if (path && ret != 0)
+ ret = -EBUSY;
+ break;
+ }
/* delete the stale device */
fs_devices->num_devices--;
list_del(&device->dev_list);
btrfs_free_device(device);
- if (fs_devices->num_devices == 0)
- break;
+ ret = 0;
}
mutex_unlock(&fs_devices->device_list_mutex);
+
if (fs_devices->num_devices == 0) {
btrfs_sysfs_remove_fsid(fs_devices);
list_del(&fs_devices->fs_list);
free_fs_devices(fs_devices);
}
}
+
+ return ret;
}
/*
@@ -674,7 +652,6 @@
{
struct request_queue *q;
struct block_device *bdev;
- struct buffer_head *bh;
struct btrfs_super_block *disk_super;
u64 devid;
int ret;
@@ -685,23 +662,29 @@
return -EINVAL;
ret = btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1,
- &bdev, &bh);
+ &bdev, &disk_super);
if (ret)
return ret;
- disk_super = (struct btrfs_super_block *)bh->b_data;
devid = btrfs_stack_device_id(&disk_super->dev_item);
if (devid != device->devid)
- goto error_brelse;
+ goto error_free_page;
if (memcmp(device->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE))
- goto error_brelse;
+ goto error_free_page;
device->generation = btrfs_super_generation(disk_super);
if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING) {
+ if (btrfs_super_incompat_flags(disk_super) &
+ BTRFS_FEATURE_INCOMPAT_METADATA_UUID) {
+ pr_err(
+ "BTRFS: Invalid seeding and uuid-changed device detected\n");
+ goto error_free_page;
+ }
+
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
- fs_devices->seeding = 1;
+ fs_devices->seeding = true;
} else {
if (bdev_read_only(bdev))
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
@@ -711,7 +694,7 @@
q = bdev_get_queue(bdev);
if (!blk_queue_nonrot(q))
- fs_devices->rotating = 1;
+ fs_devices->rotating = true;
device->bdev = bdev;
clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
@@ -723,17 +706,101 @@
fs_devices->rw_devices++;
list_add_tail(&device->dev_alloc_list, &fs_devices->alloc_list);
}
- brelse(bh);
+ btrfs_release_disk_super(disk_super);
return 0;
-error_brelse:
- brelse(bh);
+error_free_page:
+ btrfs_release_disk_super(disk_super);
blkdev_put(bdev, flags);
return -EINVAL;
}
+/*
+ * Handle scanned device having its CHANGING_FSID_V2 flag set and the fs_devices
+ * being created with a disk that has already completed its fsid change. Such
+ * disk can belong to an fs which has its FSID changed or to one which doesn't.
+ * Handle both cases here.
+ */
+static struct btrfs_fs_devices *find_fsid_inprogress(
+ struct btrfs_super_block *disk_super)
+{
+ struct btrfs_fs_devices *fs_devices;
+
+ list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+ if (memcmp(fs_devices->metadata_uuid, fs_devices->fsid,
+ BTRFS_FSID_SIZE) != 0 &&
+ memcmp(fs_devices->metadata_uuid, disk_super->fsid,
+ BTRFS_FSID_SIZE) == 0 && !fs_devices->fsid_change) {
+ return fs_devices;
+ }
+ }
+
+ return find_fsid(disk_super->fsid, NULL);
+}
+
+
+static struct btrfs_fs_devices *find_fsid_changed(
+ struct btrfs_super_block *disk_super)
+{
+ struct btrfs_fs_devices *fs_devices;
+
+ /*
+ * Handles the case where scanned device is part of an fs that had
+ * multiple successful changes of FSID but curently device didn't
+ * observe it. Meaning our fsid will be different than theirs. We need
+ * to handle two subcases :
+ * 1 - The fs still continues to have different METADATA/FSID uuids.
+ * 2 - The fs is switched back to its original FSID (METADATA/FSID
+ * are equal).
+ */
+ list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+ /* Changed UUIDs */
+ if (memcmp(fs_devices->metadata_uuid, fs_devices->fsid,
+ BTRFS_FSID_SIZE) != 0 &&
+ memcmp(fs_devices->metadata_uuid, disk_super->metadata_uuid,
+ BTRFS_FSID_SIZE) == 0 &&
+ memcmp(fs_devices->fsid, disk_super->fsid,
+ BTRFS_FSID_SIZE) != 0)
+ return fs_devices;
+
+ /* Unchanged UUIDs */
+ if (memcmp(fs_devices->metadata_uuid, fs_devices->fsid,
+ BTRFS_FSID_SIZE) == 0 &&
+ memcmp(fs_devices->fsid, disk_super->metadata_uuid,
+ BTRFS_FSID_SIZE) == 0)
+ return fs_devices;
+ }
+
+ return NULL;
+}
+
+static struct btrfs_fs_devices *find_fsid_reverted_metadata(
+ struct btrfs_super_block *disk_super)
+{
+ struct btrfs_fs_devices *fs_devices;
+
+ /*
+ * Handle the case where the scanned device is part of an fs whose last
+ * metadata UUID change reverted it to the original FSID. At the same
+ * time * fs_devices was first created by another constitutent device
+ * which didn't fully observe the operation. This results in an
+ * btrfs_fs_devices created with metadata/fsid different AND
+ * btrfs_fs_devices::fsid_change set AND the metadata_uuid of the
+ * fs_devices equal to the FSID of the disk.
+ */
+ list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+ if (memcmp(fs_devices->fsid, fs_devices->metadata_uuid,
+ BTRFS_FSID_SIZE) != 0 &&
+ memcmp(fs_devices->metadata_uuid, disk_super->fsid,
+ BTRFS_FSID_SIZE) == 0 &&
+ fs_devices->fsid_change)
+ return fs_devices;
+ }
+
+ return NULL;
+}
/*
* Add new device to list of registered devices
*
@@ -746,16 +813,40 @@
bool *new_device_added)
{
struct btrfs_device *device;
- struct btrfs_fs_devices *fs_devices;
+ struct btrfs_fs_devices *fs_devices = NULL;
struct rcu_string *name;
u64 found_transid = btrfs_super_generation(disk_super);
u64 devid = btrfs_stack_device_id(&disk_super->dev_item);
+ bool has_metadata_uuid = (btrfs_super_incompat_flags(disk_super) &
+ BTRFS_FEATURE_INCOMPAT_METADATA_UUID);
+ bool fsid_change_in_progress = (btrfs_super_flags(disk_super) &
+ BTRFS_SUPER_FLAG_CHANGING_FSID_V2);
- fs_devices = find_fsid(disk_super->fsid);
+ if (fsid_change_in_progress) {
+ if (!has_metadata_uuid)
+ fs_devices = find_fsid_inprogress(disk_super);
+ else
+ fs_devices = find_fsid_changed(disk_super);
+ } else if (has_metadata_uuid) {
+ fs_devices = find_fsid_with_metadata_uuid(disk_super);
+ } else {
+ fs_devices = find_fsid_reverted_metadata(disk_super);
+ if (!fs_devices)
+ fs_devices = find_fsid(disk_super->fsid, NULL);
+ }
+
+
if (!fs_devices) {
- fs_devices = alloc_fs_devices(disk_super->fsid);
+ if (has_metadata_uuid)
+ fs_devices = alloc_fs_devices(disk_super->fsid,
+ disk_super->metadata_uuid);
+ else
+ fs_devices = alloc_fs_devices(disk_super->fsid, NULL);
+
if (IS_ERR(fs_devices))
return ERR_CAST(fs_devices);
+
+ fs_devices->fsid_change = fsid_change_in_progress;
mutex_lock(&fs_devices->device_list_mutex);
list_add(&fs_devices->fs_list, &fs_uuids);
@@ -765,6 +856,27 @@
mutex_lock(&fs_devices->device_list_mutex);
device = btrfs_find_device(fs_devices, devid,
disk_super->dev_item.uuid, NULL, false);
+
+ /*
+ * If this disk has been pulled into an fs devices created by
+ * a device which had the CHANGING_FSID_V2 flag then replace the
+ * metadata_uuid/fsid values of the fs_devices.
+ */
+ if (fs_devices->fsid_change &&
+ found_transid > fs_devices->latest_generation) {
+ memcpy(fs_devices->fsid, disk_super->fsid,
+ BTRFS_FSID_SIZE);
+
+ if (has_metadata_uuid)
+ memcpy(fs_devices->metadata_uuid,
+ disk_super->metadata_uuid,
+ BTRFS_FSID_SIZE);
+ else
+ memcpy(fs_devices->metadata_uuid,
+ disk_super->fsid, BTRFS_FSID_SIZE);
+
+ fs_devices->fsid_change = false;
+ }
}
if (!device) {
@@ -796,11 +908,15 @@
*new_device_added = true;
if (disk_super->label[0])
- pr_info("BTRFS: device label %s devid %llu transid %llu %s\n",
- disk_super->label, devid, found_transid, path);
+ pr_info(
+ "BTRFS: device label %s devid %llu transid %llu %s scanned by %s (%d)\n",
+ disk_super->label, devid, found_transid, path,
+ current->comm, task_pid_nr(current));
else
- pr_info("BTRFS: device fsid %pU devid %llu transid %llu %s\n",
- disk_super->fsid, devid, found_transid, path);
+ pr_info(
+ "BTRFS: device fsid %pU devid %llu transid %llu %s scanned by %s (%d)\n",
+ disk_super->fsid, devid, found_transid, path,
+ current->comm, task_pid_nr(current));
} else if (!device->name || strcmp(device->name->str, path)) {
/*
@@ -897,8 +1013,11 @@
* it back. We need it to pick the disk with largest generation
* (as above).
*/
- if (!fs_devices->opened)
+ if (!fs_devices->opened) {
device->generation = found_transid;
+ fs_devices->latest_generation = max_t(u64, found_transid,
+ fs_devices->latest_generation);
+ }
fs_devices->total_devices = btrfs_super_num_devices(disk_super);
@@ -911,22 +1030,25 @@
struct btrfs_fs_devices *fs_devices;
struct btrfs_device *device;
struct btrfs_device *orig_dev;
+ int ret = 0;
- fs_devices = alloc_fs_devices(orig->fsid);
+ lockdep_assert_held(&uuid_mutex);
+
+ fs_devices = alloc_fs_devices(orig->fsid, NULL);
if (IS_ERR(fs_devices))
return fs_devices;
- mutex_lock(&orig->device_list_mutex);
fs_devices->total_devices = orig->total_devices;
- /* We have held the volume lock, it is safe to get the devices. */
list_for_each_entry(orig_dev, &orig->devices, dev_list) {
struct rcu_string *name;
device = btrfs_alloc_device(NULL, &orig_dev->devid,
orig_dev->uuid);
- if (IS_ERR(device))
+ if (IS_ERR(device)) {
+ ret = PTR_ERR(device);
goto error;
+ }
/*
* This is ok to do without rcu read locked because we hold the
@@ -937,6 +1059,7 @@
GFP_KERNEL);
if (!name) {
btrfs_free_device(device);
+ ret = -ENOMEM;
goto error;
}
rcu_assign_pointer(device->name, name);
@@ -946,36 +1069,27 @@
device->fs_devices = fs_devices;
fs_devices->num_devices++;
}
- mutex_unlock(&orig->device_list_mutex);
return fs_devices;
error:
- mutex_unlock(&orig->device_list_mutex);
free_fs_devices(fs_devices);
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(ret);
}
-/*
- * After we have read the system tree and know devids belonging to
- * this filesystem, remove the device which does not belong there.
- */
-void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step)
+static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
+ int step, struct btrfs_device **latest_dev)
{
struct btrfs_device *device, *next;
- struct btrfs_device *latest_dev = NULL;
- mutex_lock(&uuid_mutex);
-again:
/* This is the initialized path, it is safe to release the devices. */
list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
- if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA,
- &device->dev_state)) {
+ if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state)) {
if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT,
- &device->dev_state) &&
+ &device->dev_state) &&
!test_bit(BTRFS_DEV_STATE_MISSING,
&device->dev_state) &&
- (!latest_dev ||
- device->generation > latest_dev->generation)) {
- latest_dev = device;
+ (!*latest_dev ||
+ device->generation > (*latest_dev)->generation)) {
+ *latest_dev = device;
}
continue;
}
@@ -1002,22 +1116,26 @@
btrfs_free_device(device);
}
- if (fs_devices->seed) {
- fs_devices = fs_devices->seed;
- goto again;
- }
+}
+
+/*
+ * After we have read the system tree and know devids belonging to this
+ * filesystem, remove the device which does not belong there.
+ */
+void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step)
+{
+ struct btrfs_device *latest_dev = NULL;
+ struct btrfs_fs_devices *seed_dev;
+
+ mutex_lock(&uuid_mutex);
+ __btrfs_free_extra_devids(fs_devices, step, &latest_dev);
+
+ list_for_each_entry(seed_dev, &fs_devices->seed_list, seed_list)
+ __btrfs_free_extra_devids(seed_dev, step, &latest_dev);
fs_devices->latest_bdev = latest_dev->bdev;
mutex_unlock(&uuid_mutex);
-}
-
-static void free_device_rcu(struct rcu_head *head)
-{
- struct btrfs_device *device;
-
- device = container_of(head, struct btrfs_device, rcu);
- btrfs_free_device(device);
}
static void btrfs_close_bdev(struct btrfs_device *device)
@@ -1036,11 +1154,6 @@
static void btrfs_close_one_device(struct btrfs_device *device)
{
struct btrfs_fs_devices *fs_devices = device->fs_devices;
- struct btrfs_device *new_device;
- struct rcu_string *name;
-
- if (device->bdev)
- fs_devices->open_devices--;
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
device->devid != BTRFS_DEV_REPLACE_DEVID) {
@@ -1057,65 +1170,72 @@
}
btrfs_close_bdev(device);
-
- new_device = btrfs_alloc_device(NULL, &device->devid,
- device->uuid);
- BUG_ON(IS_ERR(new_device)); /* -ENOMEM */
-
- /* Safe because we are under uuid_mutex */
- if (device->name) {
- name = rcu_string_strdup(device->name->str, GFP_NOFS);
- BUG_ON(!name); /* -ENOMEM */
- rcu_assign_pointer(new_device->name, name);
+ if (device->bdev) {
+ fs_devices->open_devices--;
+ device->bdev = NULL;
}
+ clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
- list_replace_rcu(&device->dev_list, &new_device->dev_list);
- new_device->fs_devices = device->fs_devices;
+ device->fs_info = NULL;
+ atomic_set(&device->dev_stats_ccnt, 0);
+ extent_io_tree_release(&device->alloc_state);
- call_rcu(&device->rcu, free_device_rcu);
+ /*
+ * Reset the flush error record. We might have a transient flush error
+ * in this mount, and if so we aborted the current transaction and set
+ * the fs to an error state, guaranteeing no super blocks can be further
+ * committed. However that error might be transient and if we unmount the
+ * filesystem and mount it again, we should allow the mount to succeed
+ * (btrfs_check_rw_degradable() should not fail) - if after mounting the
+ * filesystem again we still get flush errors, then we will again abort
+ * any transaction and set the error state, guaranteeing no commits of
+ * unsafe super blocks.
+ */
+ device->last_flush_error = 0;
+
+ /* Verify the device is back in a pristine state */
+ ASSERT(!test_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state));
+ ASSERT(!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state));
+ ASSERT(list_empty(&device->dev_alloc_list));
+ ASSERT(list_empty(&device->post_commit_list));
+ ASSERT(atomic_read(&device->reada_in_flight) == 0);
}
-static int close_fs_devices(struct btrfs_fs_devices *fs_devices)
+static void close_fs_devices(struct btrfs_fs_devices *fs_devices)
{
struct btrfs_device *device, *tmp;
- if (--fs_devices->opened > 0)
- return 0;
+ lockdep_assert_held(&uuid_mutex);
- mutex_lock(&fs_devices->device_list_mutex);
- list_for_each_entry_safe(device, tmp, &fs_devices->devices, dev_list) {
+ if (--fs_devices->opened > 0)
+ return;
+
+ list_for_each_entry_safe(device, tmp, &fs_devices->devices, dev_list)
btrfs_close_one_device(device);
- }
- mutex_unlock(&fs_devices->device_list_mutex);
WARN_ON(fs_devices->open_devices);
WARN_ON(fs_devices->rw_devices);
fs_devices->opened = 0;
- fs_devices->seeding = 0;
-
- return 0;
+ fs_devices->seeding = false;
+ fs_devices->fs_info = NULL;
}
-int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
+void btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
{
- struct btrfs_fs_devices *seed_devices = NULL;
- int ret;
+ LIST_HEAD(list);
+ struct btrfs_fs_devices *tmp;
mutex_lock(&uuid_mutex);
- ret = close_fs_devices(fs_devices);
- if (!fs_devices->opened) {
- seed_devices = fs_devices->seed;
- fs_devices->seed = NULL;
- }
- mutex_unlock(&uuid_mutex);
+ close_fs_devices(fs_devices);
+ if (!fs_devices->opened)
+ list_splice_init(&fs_devices->seed_list, &list);
- while (seed_devices) {
- fs_devices = seed_devices;
- seed_devices = fs_devices->seed;
+ list_for_each_entry_safe(fs_devices, tmp, &list, seed_list) {
close_fs_devices(fs_devices);
+ list_del(&fs_devices->seed_list);
free_fs_devices(fs_devices);
}
- return ret;
+ mutex_unlock(&uuid_mutex);
}
static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
@@ -1123,28 +1243,33 @@
{
struct btrfs_device *device;
struct btrfs_device *latest_dev = NULL;
- int ret = 0;
+ struct btrfs_device *tmp_device;
flags |= FMODE_EXCL;
- list_for_each_entry(device, &fs_devices->devices, dev_list) {
- /* Just open everything we can; ignore failures here */
- if (btrfs_open_one_device(fs_devices, device, flags, holder))
- continue;
+ list_for_each_entry_safe(device, tmp_device, &fs_devices->devices,
+ dev_list) {
+ int ret;
- if (!latest_dev ||
- device->generation > latest_dev->generation)
+ ret = btrfs_open_one_device(fs_devices, device, flags, holder);
+ if (ret == 0 &&
+ (!latest_dev || device->generation > latest_dev->generation)) {
latest_dev = device;
+ } else if (ret == -ENODATA) {
+ fs_devices->num_devices--;
+ list_del(&device->dev_list);
+ btrfs_free_device(device);
+ }
}
- if (fs_devices->open_devices == 0) {
- ret = -EINVAL;
- goto out;
- }
+ if (fs_devices->open_devices == 0)
+ return -EINVAL;
+
fs_devices->opened = 1;
fs_devices->latest_bdev = latest_dev->bdev;
fs_devices->total_rw_bytes = 0;
-out:
- return ret;
+ fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_REGULAR;
+
+ return 0;
}
static int devid_cmp(void *priv, struct list_head *a, struct list_head *b)
@@ -1186,55 +1311,66 @@
return ret;
}
-static void btrfs_release_disk_super(struct page *page)
+void btrfs_release_disk_super(struct btrfs_super_block *super)
{
- kunmap(page);
+ struct page *page = virt_to_page(super);
+
put_page(page);
}
-static int btrfs_read_disk_super(struct block_device *bdev, u64 bytenr,
- struct page **page,
- struct btrfs_super_block **disk_super)
+static struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev,
+ u64 bytenr)
{
+ struct btrfs_super_block *disk_super;
+ struct page *page;
void *p;
pgoff_t index;
/* make sure our super fits in the device */
if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode))
- return 1;
+ return ERR_PTR(-EINVAL);
/* make sure our super fits in the page */
- if (sizeof(**disk_super) > PAGE_SIZE)
- return 1;
+ if (sizeof(*disk_super) > PAGE_SIZE)
+ return ERR_PTR(-EINVAL);
/* make sure our super doesn't straddle pages on disk */
index = bytenr >> PAGE_SHIFT;
- if ((bytenr + sizeof(**disk_super) - 1) >> PAGE_SHIFT != index)
- return 1;
+ if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_SHIFT != index)
+ return ERR_PTR(-EINVAL);
/* pull in the page with our super */
- *page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
- index, GFP_KERNEL);
+ page = read_cache_page_gfp(bdev->bd_inode->i_mapping, index, GFP_KERNEL);
- if (IS_ERR_OR_NULL(*page))
- return 1;
+ if (IS_ERR(page))
+ return ERR_CAST(page);
- p = kmap(*page);
+ p = page_address(page);
/* align our pointer to the offset of the super block */
- *disk_super = p + (bytenr & ~PAGE_MASK);
+ disk_super = p + offset_in_page(bytenr);
- if (btrfs_super_bytenr(*disk_super) != bytenr ||
- btrfs_super_magic(*disk_super) != BTRFS_MAGIC) {
- btrfs_release_disk_super(*page);
- return 1;
+ if (btrfs_super_bytenr(disk_super) != bytenr ||
+ btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
+ btrfs_release_disk_super(p);
+ return ERR_PTR(-EINVAL);
}
- if ((*disk_super)->label[0] &&
- (*disk_super)->label[BTRFS_LABEL_SIZE - 1])
- (*disk_super)->label[BTRFS_LABEL_SIZE - 1] = '\0';
+ if (disk_super->label[0] && disk_super->label[BTRFS_LABEL_SIZE - 1])
+ disk_super->label[BTRFS_LABEL_SIZE - 1] = 0;
- return 0;
+ return disk_super;
+}
+
+int btrfs_forget_devices(const char *path)
+{
+ int ret;
+
+ mutex_lock(&uuid_mutex);
+ ret = btrfs_free_stale_devices(strlen(path) ? path : NULL, NULL);
+ mutex_unlock(&uuid_mutex);
+
+ return ret;
}
/*
@@ -1249,7 +1385,6 @@
bool new_device_added = false;
struct btrfs_device *device = NULL;
struct block_device *bdev;
- struct page *page;
u64 bytenr;
lockdep_assert_held(&uuid_mutex);
@@ -1267,8 +1402,9 @@
if (IS_ERR(bdev))
return ERR_CAST(bdev);
- if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super)) {
- device = ERR_PTR(-EINVAL);
+ disk_super = btrfs_read_disk_super(bdev, bytenr);
+ if (IS_ERR(disk_super)) {
+ device = ERR_CAST(disk_super);
goto error_bdev_put;
}
@@ -1278,7 +1414,7 @@
btrfs_free_stale_devices(path, device);
}
- btrfs_release_disk_super(page);
+ btrfs_release_disk_super(disk_super);
error_bdev_put:
blkdev_put(bdev, flags);
@@ -1286,60 +1422,84 @@
return device;
}
-static int contains_pending_extent(struct btrfs_transaction *transaction,
- struct btrfs_device *device,
- u64 *start, u64 len)
+/*
+ * Try to find a chunk that intersects [start, start + len] range and when one
+ * such is found, record the end of it in *start
+ */
+static bool contains_pending_extent(struct btrfs_device *device, u64 *start,
+ u64 len)
{
- struct btrfs_fs_info *fs_info = device->fs_info;
- struct extent_map *em;
- struct list_head *search_list = &fs_info->pinned_chunks;
- int ret = 0;
- u64 physical_start = *start;
+ u64 physical_start, physical_end;
- if (transaction)
- search_list = &transaction->pending_chunks;
-again:
- list_for_each_entry(em, search_list, list) {
- struct map_lookup *map;
- int i;
+ lockdep_assert_held(&device->fs_info->chunk_mutex);
- map = em->map_lookup;
- for (i = 0; i < map->num_stripes; i++) {
- u64 end;
+ if (!find_first_extent_bit(&device->alloc_state, *start,
+ &physical_start, &physical_end,
+ CHUNK_ALLOCATED, NULL)) {
- if (map->stripes[i].dev != device)
- continue;
- if (map->stripes[i].physical >= physical_start + len ||
- map->stripes[i].physical + em->orig_block_len <=
- physical_start)
- continue;
- /*
- * Make sure that while processing the pinned list we do
- * not override our *start with a lower value, because
- * we can have pinned chunks that fall within this
- * device hole and that have lower physical addresses
- * than the pending chunks we processed before. If we
- * do not take this special care we can end up getting
- * 2 pending chunks that start at the same physical
- * device offsets because the end offset of a pinned
- * chunk can be equal to the start offset of some
- * pending chunk.
- */
- end = map->stripes[i].physical + em->orig_block_len;
- if (end > *start) {
- *start = end;
- ret = 1;
- }
+ if (in_range(physical_start, *start, len) ||
+ in_range(*start, physical_start,
+ physical_end - physical_start)) {
+ *start = physical_end + 1;
+ return true;
}
}
- if (search_list != &fs_info->pinned_chunks) {
- search_list = &fs_info->pinned_chunks;
- goto again;
- }
-
- return ret;
+ return false;
}
+static u64 dev_extent_search_start(struct btrfs_device *device, u64 start)
+{
+ switch (device->fs_devices->chunk_alloc_policy) {
+ case BTRFS_CHUNK_ALLOC_REGULAR:
+ /*
+ * We don't want to overwrite the superblock on the drive nor
+ * any area used by the boot loader (grub for example), so we
+ * make sure to start at an offset of at least 1MB.
+ */
+ return max_t(u64, start, SZ_1M);
+ default:
+ BUG();
+ }
+}
+
+/**
+ * dev_extent_hole_check - check if specified hole is suitable for allocation
+ * @device: the device which we have the hole
+ * @hole_start: starting position of the hole
+ * @hole_size: the size of the hole
+ * @num_bytes: the size of the free space that we need
+ *
+ * This function may modify @hole_start and @hole_end to reflect the suitable
+ * position for allocation. Returns 1 if hole position is updated, 0 otherwise.
+ */
+static bool dev_extent_hole_check(struct btrfs_device *device, u64 *hole_start,
+ u64 *hole_size, u64 num_bytes)
+{
+ bool changed = false;
+ u64 hole_end = *hole_start + *hole_size;
+
+ /*
+ * Check before we set max_hole_start, otherwise we could end up
+ * sending back this offset anyway.
+ */
+ if (contains_pending_extent(device, hole_start, *hole_size)) {
+ if (hole_end >= *hole_start)
+ *hole_size = hole_end - *hole_start;
+ else
+ *hole_size = 0;
+ changed = true;
+ }
+
+ switch (device->fs_devices->chunk_alloc_policy) {
+ case BTRFS_CHUNK_ALLOC_REGULAR:
+ /* No extra check */
+ break;
+ default:
+ BUG();
+ }
+
+ return changed;
+}
/*
* find_free_dev_extent_start - find free space in the specified device
@@ -1361,10 +1521,16 @@
* @len is used to store the size of the free space that we find.
* But if we don't find suitable free space, it is used to store the size of
* the max free space.
+ *
+ * NOTE: This function will search *commit* root of device tree, and does extra
+ * check to ensure dev extents are not double allocated.
+ * This makes the function safe to allocate dev extents but may not report
+ * correct usable device space, as device extent freed in current transaction
+ * is not reported as avaiable.
*/
-int find_free_dev_extent_start(struct btrfs_transaction *transaction,
- struct btrfs_device *device, u64 num_bytes,
- u64 search_start, u64 *start, u64 *len)
+static int find_free_dev_extent_start(struct btrfs_device *device,
+ u64 num_bytes, u64 search_start, u64 *start,
+ u64 *len)
{
struct btrfs_fs_info *fs_info = device->fs_info;
struct btrfs_root *root = fs_info->dev_root;
@@ -1380,12 +1546,7 @@
int slot;
struct extent_buffer *l;
- /*
- * We don't want to overwrite the superblock on the drive nor any area
- * used by the boot loader (grub for example), so we make sure to start
- * at an offset of at least 1MB.
- */
- search_start = max_t(u64, search_start, SZ_1M);
+ search_start = dev_extent_search_start(device, search_start);
path = btrfs_alloc_path();
if (!path)
@@ -1443,21 +1604,8 @@
if (key.offset > search_start) {
hole_size = key.offset - search_start;
-
- /*
- * Have to check before we set max_hole_start, otherwise
- * we could end up sending back this offset anyway.
- */
- if (contains_pending_extent(transaction, device,
- &search_start,
- hole_size)) {
- if (key.offset >= search_start) {
- hole_size = key.offset - search_start;
- } else {
- WARN_ON_ONCE(1);
- hole_size = 0;
- }
- }
+ dev_extent_hole_check(device, &search_start, &hole_size,
+ num_bytes);
if (hole_size > max_hole_size) {
max_hole_start = search_start;
@@ -1496,9 +1644,8 @@
*/
if (search_end > search_start) {
hole_size = search_end - search_start;
-
- if (contains_pending_extent(transaction, device, &search_start,
- hole_size)) {
+ if (dev_extent_hole_check(device, &search_start, &hole_size,
+ num_bytes)) {
btrfs_release_path(path);
goto again;
}
@@ -1523,13 +1670,11 @@
return ret;
}
-int find_free_dev_extent(struct btrfs_trans_handle *trans,
- struct btrfs_device *device, u64 num_bytes,
+int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes,
u64 *start, u64 *len)
{
/* FIXME use last free of some kind */
- return find_free_dev_extent_start(trans->transaction, device,
- num_bytes, 0, start, len);
+ return find_free_dev_extent_start(device, num_bytes, 0, start, len);
}
static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
@@ -1640,9 +1785,9 @@
struct rb_node *n;
u64 ret = 0;
- em_tree = &fs_info->mapping_tree.map_tree;
+ em_tree = &fs_info->mapping_tree;
read_lock(&em_tree->lock);
- n = rb_last(&em_tree->map);
+ n = rb_last(&em_tree->map.rb_root);
if (n) {
em = rb_entry(n, struct extent_map, rb_node);
ret = em->start + em->len;
@@ -1672,7 +1817,12 @@
if (ret < 0)
goto error;
- BUG_ON(ret == 0); /* Corruption */
+ if (ret == 0) {
+ /* Corruption */
+ btrfs_err(fs_info, "corrupted chunk tree devid -1 matched");
+ ret = -EUCLEAN;
+ goto error;
+ }
ret = btrfs_previous_item(fs_info->chunk_root, path,
BTRFS_DEV_ITEMS_OBJECTID,
@@ -1738,7 +1888,8 @@
ptr = btrfs_device_uuid(dev_item);
write_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
ptr = btrfs_device_fsid(dev_item);
- write_extent_buffer(leaf, trans->fs_info->fsid, ptr, BTRFS_FSID_SIZE);
+ write_extent_buffer(leaf, trans->fs_info->fs_devices->metadata_uuid,
+ ptr, BTRFS_FSID_SIZE);
btrfs_mark_buffer_dirty(leaf);
ret = 0;
@@ -1750,22 +1901,27 @@
/*
* Function to update ctime/mtime for a given device path.
* Mainly used for ctime/mtime based probe like libblkid.
+ *
+ * We don't care about errors here, this is just to be kind to userspace.
*/
-static void update_dev_time(const char *path_name)
+static void update_dev_time(const char *device_path)
{
- struct file *filp;
+ struct path path;
+ struct timespec64 now;
+ int ret;
- filp = filp_open(path_name, O_RDWR, 0);
- if (IS_ERR(filp))
+ ret = kern_path(device_path, LOOKUP_FOLLOW, &path);
+ if (ret)
return;
- file_update_time(filp);
- filp_close(filp, NULL);
+
+ now = current_time(d_inode(path.dentry));
+ inode_update_time(d_inode(path.dentry), &now, S_MTIME | S_CTIME);
+ path_put(&path);
}
-static int btrfs_rm_dev_item(struct btrfs_fs_info *fs_info,
- struct btrfs_device *device)
+static int btrfs_rm_dev_item(struct btrfs_device *device)
{
- struct btrfs_root *root = fs_info->chunk_root;
+ struct btrfs_root *root = device->fs_info->chunk_root;
int ret;
struct btrfs_path *path;
struct btrfs_key key;
@@ -1862,17 +2018,14 @@
* where this function called, there should be always be another device (or
* this_dev) which is active.
*/
-void btrfs_assign_next_active_device(struct btrfs_device *device,
- struct btrfs_device *this_dev)
+void __cold btrfs_assign_next_active_device(struct btrfs_device *device,
+ struct btrfs_device *next_device)
{
struct btrfs_fs_info *fs_info = device->fs_info;
- struct btrfs_device *next_device;
- if (this_dev)
- next_device = this_dev;
- else
+ if (!next_device)
next_device = btrfs_find_next_active_device(fs_info->fs_devices,
- device);
+ device);
ASSERT(next_device);
if (fs_info->sb->s_bdev &&
@@ -1883,8 +2036,66 @@
fs_info->fs_devices->latest_bdev = next_device->bdev;
}
+/*
+ * Return btrfs_fs_devices::num_devices excluding the device that's being
+ * currently replaced.
+ */
+static u64 btrfs_num_devices(struct btrfs_fs_info *fs_info)
+{
+ u64 num_devices = fs_info->fs_devices->num_devices;
+
+ down_read(&fs_info->dev_replace.rwsem);
+ if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) {
+ ASSERT(num_devices > 1);
+ num_devices--;
+ }
+ up_read(&fs_info->dev_replace.rwsem);
+
+ return num_devices;
+}
+
+void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
+ struct block_device *bdev,
+ const char *device_path)
+{
+ struct btrfs_super_block *disk_super;
+ int copy_num;
+
+ if (!bdev)
+ return;
+
+ for (copy_num = 0; copy_num < BTRFS_SUPER_MIRROR_MAX; copy_num++) {
+ struct page *page;
+ int ret;
+
+ disk_super = btrfs_read_dev_one_super(bdev, copy_num);
+ if (IS_ERR(disk_super))
+ continue;
+
+ memset(&disk_super->magic, 0, sizeof(disk_super->magic));
+
+ page = virt_to_page(disk_super);
+ set_page_dirty(page);
+ lock_page(page);
+ /* write_on_page() unlocks the page */
+ ret = write_one_page(page);
+ if (ret)
+ btrfs_warn(fs_info,
+ "error clearing superblock number %d (%d)",
+ copy_num, ret);
+ btrfs_release_disk_super(disk_super);
+
+ }
+
+ /* Notify udev that device has changed */
+ btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
+
+ /* Update ctime/mtime for device path for libblkid */
+ update_dev_time(device_path);
+}
+
int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
- u64 devid)
+ u64 devid)
{
struct btrfs_device *device;
struct btrfs_fs_devices *cur_devices;
@@ -1892,24 +2103,35 @@
u64 num_devices;
int ret = 0;
- mutex_lock(&uuid_mutex);
-
- num_devices = fs_devices->num_devices;
- btrfs_dev_replace_read_lock(&fs_info->dev_replace);
- if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) {
- WARN_ON(num_devices < 1);
- num_devices--;
- }
- btrfs_dev_replace_read_unlock(&fs_info->dev_replace);
+ /*
+ * The device list in fs_devices is accessed without locks (neither
+ * uuid_mutex nor device_list_mutex) as it won't change on a mounted
+ * filesystem and another device rm cannot run.
+ */
+ num_devices = btrfs_num_devices(fs_info);
ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1);
if (ret)
goto out;
- ret = btrfs_find_device_by_devspec(fs_info, devid, device_path,
- &device);
- if (ret)
+ device = btrfs_find_device_by_devspec(fs_info, devid, device_path);
+
+ if (IS_ERR(device)) {
+ if (PTR_ERR(device) == -ENOENT &&
+ device_path && strcmp(device_path, "missing") == 0)
+ ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND;
+ else
+ ret = PTR_ERR(device);
goto out;
+ }
+
+ if (btrfs_pinned_by_swapfile(fs_info, device)) {
+ btrfs_warn_in_rcu(fs_info,
+ "cannot remove device %s (devid %llu) due to active swapfile",
+ rcu_str_deref(device->name), device->devid);
+ ret = -ETXTBSY;
+ goto out;
+ }
if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) {
ret = BTRFS_ERROR_DEV_TGT_REPLACE;
@@ -1929,9 +2151,9 @@
mutex_unlock(&fs_info->chunk_mutex);
}
- mutex_unlock(&uuid_mutex);
ret = btrfs_shrink_device(device, 0);
- mutex_lock(&uuid_mutex);
+ if (!ret)
+ btrfs_reada_remove_dev(device);
if (ret)
goto error_undo;
@@ -1940,12 +2162,12 @@
* counter although write_all_supers() is not locked out. This
* could give a filesystem state which requires a degraded mount.
*/
- ret = btrfs_rm_dev_item(fs_info, device);
+ ret = btrfs_rm_dev_item(device);
if (ret)
goto error_undo;
clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
- btrfs_scrub_cancel_dev(fs_info, device);
+ btrfs_scrub_cancel_dev(device);
/*
* the device list mutex makes sure that we don't change
@@ -1980,7 +2202,7 @@
if (device->bdev) {
cur_devices->open_devices--;
/* remove sysfs entry */
- btrfs_sysfs_rm_device_link(fs_devices, device);
+ btrfs_sysfs_remove_device(device);
}
num_devices = btrfs_super_num_devices(fs_info->super_copy) - 1;
@@ -1993,29 +2215,24 @@
* supers and free the device.
*/
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state))
- btrfs_scratch_superblocks(device->bdev, device->name->str);
+ btrfs_scratch_superblocks(fs_info, device->bdev,
+ device->name->str);
btrfs_close_bdev(device);
- call_rcu(&device->rcu, free_device_rcu);
+ synchronize_rcu();
+ btrfs_free_device(device);
if (cur_devices->open_devices == 0) {
- while (fs_devices) {
- if (fs_devices->seed == cur_devices) {
- fs_devices->seed = cur_devices->seed;
- break;
- }
- fs_devices = fs_devices->seed;
- }
- cur_devices->seed = NULL;
+ list_del_init(&cur_devices->seed_list);
close_fs_devices(cur_devices);
free_fs_devices(cur_devices);
}
out:
- mutex_unlock(&uuid_mutex);
return ret;
error_undo:
+ btrfs_reada_undo_remove_dev(device);
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
mutex_lock(&fs_info->chunk_mutex);
list_add(&device->dev_alloc_list,
@@ -2053,23 +2270,18 @@
fs_devices->open_devices--;
}
-void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
- struct btrfs_device *srcdev)
+void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev)
{
struct btrfs_fs_devices *fs_devices = srcdev->fs_devices;
- if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &srcdev->dev_state)) {
- /* zero out the old super if it is writable */
- btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
- }
+ mutex_lock(&uuid_mutex);
btrfs_close_bdev(srcdev);
- call_rcu(&srcdev->rcu, free_device_rcu);
+ synchronize_rcu();
+ btrfs_free_device(srcdev);
/* if this is no devs we rather delete the fs_devices */
if (!fs_devices->num_devices) {
- struct btrfs_fs_devices *tmp_fs_devices;
-
/*
* On a mounted FS, num_devices can't be zero unless it's a
* seed. In case of a seed device being replaced, the replace
@@ -2078,28 +2290,20 @@
*/
ASSERT(fs_devices->seeding);
- tmp_fs_devices = fs_info->fs_devices;
- while (tmp_fs_devices) {
- if (tmp_fs_devices->seed == fs_devices) {
- tmp_fs_devices->seed = fs_devices->seed;
- break;
- }
- tmp_fs_devices = tmp_fs_devices->seed;
- }
- fs_devices->seed = NULL;
+ list_del_init(&fs_devices->seed_list);
close_fs_devices(fs_devices);
free_fs_devices(fs_devices);
}
+ mutex_unlock(&uuid_mutex);
}
void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
{
struct btrfs_fs_devices *fs_devices = tgtdev->fs_info->fs_devices;
- WARN_ON(!tgtdev);
mutex_lock(&fs_devices->device_list_mutex);
- btrfs_sysfs_rm_device_link(fs_devices, tgtdev);
+ btrfs_sysfs_remove_device(tgtdev);
if (tgtdev->bdev)
fs_devices->open_devices--;
@@ -2119,90 +2323,77 @@
* is already out of device list, so we don't have to hold
* the device_list_mutex lock.
*/
- btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
+ btrfs_scratch_superblocks(tgtdev->fs_info, tgtdev->bdev,
+ tgtdev->name->str);
btrfs_close_bdev(tgtdev);
- call_rcu(&tgtdev->rcu, free_device_rcu);
+ synchronize_rcu();
+ btrfs_free_device(tgtdev);
}
-static int btrfs_find_device_by_path(struct btrfs_fs_info *fs_info,
- const char *device_path,
- struct btrfs_device **device)
+static struct btrfs_device *btrfs_find_device_by_path(
+ struct btrfs_fs_info *fs_info, const char *device_path)
{
int ret = 0;
struct btrfs_super_block *disk_super;
u64 devid;
u8 *dev_uuid;
struct block_device *bdev;
- struct buffer_head *bh;
+ struct btrfs_device *device;
- *device = NULL;
ret = btrfs_get_bdev_and_sb(device_path, FMODE_READ,
- fs_info->bdev_holder, 0, &bdev, &bh);
+ fs_info->bdev_holder, 0, &bdev, &disk_super);
if (ret)
- return ret;
- disk_super = (struct btrfs_super_block *)bh->b_data;
+ return ERR_PTR(ret);
+
devid = btrfs_stack_device_id(&disk_super->dev_item);
dev_uuid = disk_super->dev_item.uuid;
- *device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
- disk_super->fsid, true);
- brelse(bh);
- if (!*device)
- ret = -ENOENT;
+ if (btrfs_fs_incompat(fs_info, METADATA_UUID))
+ device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
+ disk_super->metadata_uuid, true);
+ else
+ device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
+ disk_super->fsid, true);
+
+ btrfs_release_disk_super(disk_super);
+ if (!device)
+ device = ERR_PTR(-ENOENT);
blkdev_put(bdev, FMODE_READ);
- return ret;
-}
-
-int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
- const char *device_path,
- struct btrfs_device **device)
-{
- *device = NULL;
- if (strcmp(device_path, "missing") == 0) {
- struct list_head *devices;
- struct btrfs_device *tmp;
-
- devices = &fs_info->fs_devices->devices;
- list_for_each_entry(tmp, devices, dev_list) {
- if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA,
- &tmp->dev_state) && !tmp->bdev) {
- *device = tmp;
- break;
- }
- }
-
- if (!*device)
- return BTRFS_ERROR_DEV_MISSING_NOT_FOUND;
-
- return 0;
- } else {
- return btrfs_find_device_by_path(fs_info, device_path, device);
- }
+ return device;
}
/*
* Lookup a device given by device id, or the path if the id is 0.
*/
-int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid,
- const char *devpath,
- struct btrfs_device **device)
+struct btrfs_device *btrfs_find_device_by_devspec(
+ struct btrfs_fs_info *fs_info, u64 devid,
+ const char *device_path)
{
- int ret;
+ struct btrfs_device *device;
if (devid) {
- ret = 0;
- *device = btrfs_find_device(fs_info->fs_devices, devid,
- NULL, NULL, true);
- if (!*device)
- ret = -ENOENT;
- } else {
- if (!devpath || !devpath[0])
- return -EINVAL;
-
- ret = btrfs_find_device_missing_or_by_path(fs_info, devpath,
- device);
+ device = btrfs_find_device(fs_info->fs_devices, devid, NULL,
+ NULL, true);
+ if (!device)
+ return ERR_PTR(-ENOENT);
+ return device;
}
- return ret;
+
+ if (!device_path || !device_path[0])
+ return ERR_PTR(-EINVAL);
+
+ if (strcmp(device_path, "missing") == 0) {
+ /* Find first missing device */
+ list_for_each_entry(device, &fs_info->fs_devices->devices,
+ dev_list) {
+ if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA,
+ &device->dev_state) && !device->bdev)
+ return device;
+ }
+ return ERR_PTR(-ENOENT);
+ }
+
+ return btrfs_find_device_by_path(fs_info, device_path);
}
/*
@@ -2221,10 +2412,20 @@
if (!fs_devices->seeding)
return -EINVAL;
- seed_devices = alloc_fs_devices(NULL);
+ /*
+ * Private copy of the seed devices, anchored at
+ * fs_info->fs_devices->seed_list
+ */
+ seed_devices = alloc_fs_devices(NULL, NULL);
if (IS_ERR(seed_devices))
return PTR_ERR(seed_devices);
+ /*
+ * It's necessary to retain a copy of the original seed fs_devices in
+ * fs_uuids so that filesystems which have been seeded can successfully
+ * reference the seed device from open_seed_devices. This also supports
+ * multiple fs seed.
+ */
old_devices = clone_fs_devices(fs_devices);
if (IS_ERR(old_devices)) {
kfree(seed_devices);
@@ -2245,19 +2446,15 @@
list_for_each_entry(device, &seed_devices->devices, dev_list)
device->fs_devices = seed_devices;
- mutex_lock(&fs_info->chunk_mutex);
- list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list);
- mutex_unlock(&fs_info->chunk_mutex);
-
- fs_devices->seeding = 0;
+ fs_devices->seeding = false;
fs_devices->num_devices = 0;
fs_devices->open_devices = 0;
fs_devices->missing_devices = 0;
- fs_devices->rotating = 0;
- fs_devices->seed = seed_devices;
+ fs_devices->rotating = false;
+ list_add(&seed_devices->seed_list, &fs_devices->seed_list);
generate_random_uuid(fs_devices->fsid);
- memcpy(fs_info->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
+ memcpy(fs_devices->metadata_uuid, fs_devices->fsid, BTRFS_FSID_SIZE);
memcpy(disk_super->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
mutex_unlock(&fs_devices->device_list_mutex);
@@ -2271,9 +2468,9 @@
/*
* Store the expected generation for seed devices in device items.
*/
-static int btrfs_finish_sprout(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info)
+static int btrfs_finish_sprout(struct btrfs_trans_handle *trans)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *root = fs_info->chunk_root;
struct btrfs_path *path;
struct extent_buffer *leaf;
@@ -2357,7 +2554,7 @@
u64 orig_super_num_devices;
int seeding_dev = 0;
int ret = 0;
- bool unlocked = false;
+ bool locked = false;
if (sb_rdonly(sb) && !fs_devices->seeding)
return -EROFS;
@@ -2371,20 +2568,20 @@
seeding_dev = 1;
down_write(&sb->s_umount);
mutex_lock(&uuid_mutex);
+ locked = true;
}
- filemap_write_and_wait(bdev->bd_inode->i_mapping);
+ sync_blockdev(bdev);
- mutex_lock(&fs_devices->device_list_mutex);
- list_for_each_entry(device, &fs_devices->devices, dev_list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
if (device->bdev == bdev) {
ret = -EEXIST;
- mutex_unlock(
- &fs_devices->device_list_mutex);
+ rcu_read_unlock();
goto error;
}
}
- mutex_unlock(&fs_devices->device_list_mutex);
+ rcu_read_unlock();
device = btrfs_alloc_device(fs_info, NULL, NULL);
if (IS_ERR(device)) {
@@ -2448,7 +2645,7 @@
atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
if (!blk_queue_nonrot(q))
- fs_devices->rotating = 1;
+ fs_devices->rotating = true;
orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
btrfs_set_super_total_bytes(fs_info->super_copy,
@@ -2468,13 +2665,13 @@
mutex_unlock(&fs_info->chunk_mutex);
/* Add sysfs device entry */
- btrfs_sysfs_add_device_link(fs_devices, device);
+ btrfs_sysfs_add_device(device);
mutex_unlock(&fs_devices->device_list_mutex);
if (seeding_dev) {
mutex_lock(&fs_info->chunk_mutex);
- ret = init_first_rw_device(trans, fs_info);
+ ret = init_first_rw_device(trans);
mutex_unlock(&fs_info->chunk_mutex);
if (ret) {
btrfs_abort_transaction(trans, ret);
@@ -2489,22 +2686,17 @@
}
if (seeding_dev) {
- char fsid_buf[BTRFS_UUID_UNPARSED_SIZE];
-
- ret = btrfs_finish_sprout(trans, fs_info);
+ ret = btrfs_finish_sprout(trans);
if (ret) {
btrfs_abort_transaction(trans, ret);
goto error_sysfs;
}
- /* Sprouting would change fsid of the mounted root,
- * so rename the fsid on the sysfs
+ /*
+ * fs_devices now represents the newly sprouted filesystem and
+ * its fsid has been changed by btrfs_prepare_sprout
*/
- snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU",
- fs_info->fsid);
- if (kobject_rename(&fs_devices->fsid_kobj, fsid_buf))
- btrfs_warn(fs_info,
- "sysfs: failed to create fsid for sprout");
+ btrfs_sysfs_update_sprout_fsid(fs_devices);
}
ret = btrfs_commit_transaction(trans);
@@ -2512,7 +2704,7 @@
if (seeding_dev) {
mutex_unlock(&uuid_mutex);
up_write(&sb->s_umount);
- unlocked = true;
+ locked = false;
if (ret) /* transaction commit */
return ret;
@@ -2532,12 +2724,22 @@
ret = btrfs_commit_transaction(trans);
}
- /* Update ctime/mtime for libblkid */
+ /*
+ * Now that we have written a new super block to this device, check all
+ * other fs_devices list if device_path alienates any other scanned
+ * device.
+ * We can ignore the return value as it typically returns -EINVAL and
+ * only succeeds if the device was an alien.
+ */
+ btrfs_forget_devices(device_path);
+
+ /* Update ctime/mtime for blkid or udev */
update_dev_time(device_path);
+
return ret;
error_sysfs:
- btrfs_sysfs_rm_device_link(fs_devices, device);
+ btrfs_sysfs_remove_device(device);
mutex_lock(&fs_info->fs_devices->device_list_mutex);
mutex_lock(&fs_info->chunk_mutex);
list_del_rcu(&device->dev_list);
@@ -2563,7 +2765,7 @@
btrfs_free_device(device);
error:
blkdev_put(bdev, FMODE_EXCL);
- if (seeding_dev && !unlocked) {
+ if (locked) {
mutex_unlock(&uuid_mutex);
up_write(&sb->s_umount);
}
@@ -2621,7 +2823,6 @@
{
struct btrfs_fs_info *fs_info = device->fs_info;
struct btrfs_super_block *super_copy = fs_info->super_copy;
- struct btrfs_fs_devices *fs_devices;
u64 old_total;
u64 diff;
@@ -2640,8 +2841,6 @@
return -EINVAL;
}
- fs_devices = fs_info->fs_devices;
-
btrfs_set_super_total_bytes(super_copy,
round_down(old_total + diff, fs_info->sectorsize));
device->fs_devices->total_rw_bytes += diff;
@@ -2649,9 +2848,9 @@
btrfs_device_set_total_bytes(device, new_size);
btrfs_device_set_disk_total_bytes(device, new_size);
btrfs_clear_space_info_full(device->fs_info);
- if (list_empty(&device->resized_list))
- list_add_tail(&device->resized_list,
- &fs_devices->resized_devices);
+ if (list_empty(&device->post_commit_list))
+ list_add_tail(&device->post_commit_list,
+ &trans->transaction->dev_update_list);
mutex_unlock(&fs_info->chunk_mutex);
return btrfs_update_device(trans, device);
@@ -2739,13 +2938,20 @@
return ret;
}
-static struct extent_map *get_chunk_map(struct btrfs_fs_info *fs_info,
- u64 logical, u64 length)
+/*
+ * btrfs_get_chunk_map() - Find the mapping containing the given logical extent.
+ * @logical: Logical block offset in bytes.
+ * @length: Length of extent in bytes.
+ *
+ * Return: Chunk mapping or ERR_PTR.
+ */
+struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
+ u64 logical, u64 length)
{
struct extent_map_tree *em_tree;
struct extent_map *em;
- em_tree = &fs_info->mapping_tree.map_tree;
+ em_tree = &fs_info->mapping_tree;
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, logical, length);
read_unlock(&em_tree->lock);
@@ -2777,7 +2983,7 @@
int i, ret = 0;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
- em = get_chunk_map(fs_info, chunk_offset, 1);
+ em = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
if (IS_ERR(em)) {
/*
* This is a logic error, but we don't want to just rely on the
@@ -2818,13 +3024,11 @@
mutex_unlock(&fs_info->chunk_mutex);
}
- if (map->stripes[i].dev) {
- ret = btrfs_update_device(trans, map->stripes[i].dev);
- if (ret) {
- mutex_unlock(&fs_devices->device_list_mutex);
- btrfs_abort_transaction(trans, ret);
- goto out;
- }
+ ret = btrfs_update_device(trans, device);
+ if (ret) {
+ mutex_unlock(&fs_devices->device_list_mutex);
+ btrfs_abort_transaction(trans, ret);
+ goto out;
}
}
mutex_unlock(&fs_devices->device_list_mutex);
@@ -2861,6 +3065,7 @@
{
struct btrfs_root *root = fs_info->chunk_root;
struct btrfs_trans_handle *trans;
+ struct btrfs_block_group *block_group;
int ret;
/*
@@ -2877,10 +3082,6 @@
*/
lockdep_assert_held(&fs_info->delete_unused_bgs_mutex);
- ret = btrfs_can_relocate(fs_info, chunk_offset);
- if (ret)
- return -ENOSPC;
-
/* step one, relocate all the extents inside this chunk */
btrfs_scrub_pause(fs_info);
ret = btrfs_relocate_block_group(fs_info, chunk_offset);
@@ -2888,15 +3089,11 @@
if (ret)
return ret;
- /*
- * We add the kobjects here (and after forcing data chunk creation)
- * since relocation is the only place we'll create chunks of a new
- * type at runtime. The only place where we'll remove the last
- * chunk of a type is the call immediately below this one. Even
- * so, we're protected against races with the cleaner thread since
- * we're covered by the delete_unused_bgs_mutex.
- */
- btrfs_add_raid_kobjects(fs_info);
+ block_group = btrfs_lookup_block_group(fs_info, chunk_offset);
+ if (!block_group)
+ return -ENOENT;
+ btrfs_discard_cancel_work(&fs_info->discard_ctl, block_group);
+ btrfs_put_block_group(block_group);
trans = btrfs_start_trans_remove_block_group(root->fs_info,
chunk_offset);
@@ -2997,7 +3194,7 @@
static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
u64 chunk_offset)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
u64 bytes_used;
u64 chunk_type;
@@ -3006,30 +3203,28 @@
chunk_type = cache->flags;
btrfs_put_block_group(cache);
- if (chunk_type & BTRFS_BLOCK_GROUP_DATA) {
- spin_lock(&fs_info->data_sinfo->lock);
- bytes_used = fs_info->data_sinfo->bytes_used;
- spin_unlock(&fs_info->data_sinfo->lock);
+ if (!(chunk_type & BTRFS_BLOCK_GROUP_DATA))
+ return 0;
- if (!bytes_used) {
- struct btrfs_trans_handle *trans;
- int ret;
+ spin_lock(&fs_info->data_sinfo->lock);
+ bytes_used = fs_info->data_sinfo->bytes_used;
+ spin_unlock(&fs_info->data_sinfo->lock);
- trans = btrfs_join_transaction(fs_info->tree_root);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
+ if (!bytes_used) {
+ struct btrfs_trans_handle *trans;
+ int ret;
- ret = btrfs_force_chunk_alloc(trans,
- BTRFS_BLOCK_GROUP_DATA);
- btrfs_end_transaction(trans);
- if (ret < 0)
- return ret;
+ trans = btrfs_join_transaction(fs_info->tree_root);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
- btrfs_add_raid_kobjects(fs_info);
-
- return 1;
- }
+ ret = btrfs_force_chunk_alloc(trans, BTRFS_BLOCK_GROUP_DATA);
+ btrfs_end_transaction(trans);
+ if (ret < 0)
+ return ret;
+ return 1;
}
+
return 0;
}
@@ -3099,7 +3294,7 @@
if (!path)
return -ENOMEM;
- trans = btrfs_start_transaction(root, 0);
+ trans = btrfs_start_transaction_fallback_global_rsv(root, 0);
if (IS_ERR(trans)) {
btrfs_free_path(path);
return PTR_ERR(trans);
@@ -3208,28 +3403,28 @@
static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
struct btrfs_balance_args *bargs)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
u64 chunk_used;
u64 user_thresh_min;
u64 user_thresh_max;
int ret = 1;
cache = btrfs_lookup_block_group(fs_info, chunk_offset);
- chunk_used = btrfs_block_group_used(&cache->item);
+ chunk_used = cache->used;
if (bargs->usage_min == 0)
user_thresh_min = 0;
else
- user_thresh_min = div_factor_fine(cache->key.offset,
- bargs->usage_min);
+ user_thresh_min = div_factor_fine(cache->length,
+ bargs->usage_min);
if (bargs->usage_max == 0)
user_thresh_max = 1;
else if (bargs->usage_max > 100)
- user_thresh_max = cache->key.offset;
+ user_thresh_max = cache->length;
else
- user_thresh_max = div_factor_fine(cache->key.offset,
- bargs->usage_max);
+ user_thresh_max = div_factor_fine(cache->length,
+ bargs->usage_max);
if (user_thresh_min <= chunk_used && chunk_used < user_thresh_max)
ret = 0;
@@ -3241,20 +3436,19 @@
static int chunk_usage_filter(struct btrfs_fs_info *fs_info,
u64 chunk_offset, struct btrfs_balance_args *bargs)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
u64 chunk_used, user_thresh;
int ret = 1;
cache = btrfs_lookup_block_group(fs_info, chunk_offset);
- chunk_used = btrfs_block_group_used(&cache->item);
+ chunk_used = cache->used;
if (bargs->usage_min == 0)
user_thresh = 1;
else if (bargs->usage > 100)
- user_thresh = cache->key.offset;
+ user_thresh = cache->length;
else
- user_thresh = div_factor_fine(cache->key.offset,
- bargs->usage);
+ user_thresh = div_factor_fine(cache->length, bargs->usage);
if (chunk_used < user_thresh)
ret = 0;
@@ -3280,6 +3474,18 @@
return 1;
}
+static u64 calc_data_stripes(u64 type, int num_stripes)
+{
+ const int index = btrfs_bg_flags_to_raid_index(type);
+ const int ncopies = btrfs_raid_array[index].ncopies;
+ const int nparity = btrfs_raid_array[index].nparity;
+
+ if (nparity)
+ return num_stripes - nparity;
+ else
+ return num_stripes / ncopies;
+}
+
/* [pstart, pend) */
static int chunk_drange_filter(struct extent_buffer *leaf,
struct btrfs_chunk *chunk,
@@ -3289,22 +3495,15 @@
int num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
u64 stripe_offset;
u64 stripe_length;
+ u64 type;
int factor;
int i;
if (!(bargs->flags & BTRFS_BALANCE_ARGS_DEVID))
return 0;
- if (btrfs_chunk_type(leaf, chunk) & (BTRFS_BLOCK_GROUP_DUP |
- BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10)) {
- factor = num_stripes / 2;
- } else if (btrfs_chunk_type(leaf, chunk) & BTRFS_BLOCK_GROUP_RAID5) {
- factor = num_stripes - 1;
- } else if (btrfs_chunk_type(leaf, chunk) & BTRFS_BLOCK_GROUP_RAID6) {
- factor = num_stripes - 2;
- } else {
- factor = num_stripes;
- }
+ type = btrfs_chunk_type(leaf, chunk);
+ factor = calc_data_stripes(type, num_stripes);
for (i = 0; i < num_stripes; i++) {
stripe = btrfs_stripe_nr(chunk, i);
@@ -3365,10 +3564,10 @@
return 0;
}
-static int should_balance_chunk(struct btrfs_fs_info *fs_info,
- struct extent_buffer *leaf,
+static int should_balance_chunk(struct extent_buffer *leaf,
struct btrfs_chunk *chunk, u64 chunk_offset)
{
+ struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_balance_control *bctl = fs_info->balance_ctl;
struct btrfs_balance_args *bargs = NULL;
u64 chunk_type = btrfs_chunk_type(leaf, chunk);
@@ -3458,17 +3657,11 @@
{
struct btrfs_balance_control *bctl = fs_info->balance_ctl;
struct btrfs_root *chunk_root = fs_info->chunk_root;
- struct btrfs_root *dev_root = fs_info->dev_root;
- struct list_head *devices;
- struct btrfs_device *device;
- u64 old_size;
- u64 size_to_free;
u64 chunk_type;
struct btrfs_chunk *chunk;
struct btrfs_path *path = NULL;
struct btrfs_key key;
struct btrfs_key found_key;
- struct btrfs_trans_handle *trans;
struct extent_buffer *leaf;
int slot;
int ret;
@@ -3483,53 +3676,6 @@
u32 count_sys = 0;
int chunk_reserved = 0;
- /* 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 = btrfs_device_get_total_bytes(device);
- size_to_free = div_factor(old_size, 1);
- size_to_free = min_t(u64, size_to_free, SZ_1M);
- if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) ||
- btrfs_device_get_total_bytes(device) -
- btrfs_device_get_bytes_used(device) > size_to_free ||
- test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state))
- continue;
-
- ret = btrfs_shrink_device(device, old_size - size_to_free);
- if (ret == -ENOSPC)
- break;
- if (ret) {
- /* btrfs_shrink_device never returns ret > 0 */
- WARN_ON(ret > 0);
- goto error;
- }
-
- trans = btrfs_start_transaction(dev_root, 0);
- if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- btrfs_info_in_rcu(fs_info,
- "resize: unable to start transaction after shrinking device %s (error %d), old size %llu, new size %llu",
- rcu_str_deref(device->name), ret,
- old_size, old_size - size_to_free);
- goto error;
- }
-
- ret = btrfs_grow_device(trans, device, old_size);
- if (ret) {
- btrfs_end_transaction(trans);
- /* btrfs_grow_device never returns ret > 0 */
- WARN_ON(ret > 0);
- btrfs_info_in_rcu(fs_info,
- "resize: unable to grow device after shrinking device %s (error %d), old size %llu, new size %llu",
- rcu_str_deref(device->name), ret,
- old_size, old_size - size_to_free);
- goto error;
- }
-
- btrfs_end_transaction(trans);
- }
-
- /* step two, relocate all the chunks */
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
@@ -3601,8 +3747,7 @@
spin_unlock(&fs_info->balance_lock);
}
- ret = should_balance_chunk(fs_info, leaf, chunk,
- found_key.offset);
+ ret = should_balance_chunk(leaf, chunk, found_key.offset);
btrfs_release_path(path);
if (!ret) {
@@ -3659,10 +3804,15 @@
ret = btrfs_relocate_chunk(fs_info, found_key.offset);
mutex_unlock(&fs_info->delete_unused_bgs_mutex);
- if (ret && ret != -ENOSPC)
- goto error;
if (ret == -ENOSPC) {
enospc_errors++;
+ } else if (ret == -ETXTBSY) {
+ btrfs_info(fs_info,
+ "skipping relocation of block group %llu due to active swapfile",
+ found_key.offset);
+ ret = 0;
+ } else if (ret) {
+ goto error;
} else {
spin_lock(&fs_info->balance_lock);
bctl->stat.completed++;
@@ -3711,8 +3861,7 @@
if (flags == 0)
return !extended; /* "0" is valid for usual profiles */
- /* true if exactly one bit set */
- return (flags & (flags - 1)) == 0;
+ return has_single_bit_set(flags);
}
static inline int balance_need_close(struct btrfs_fs_info *fs_info)
@@ -3723,13 +3872,179 @@
atomic_read(&fs_info->balance_cancel_req) == 0);
}
-/* Non-zero return value signifies invalidity */
-static inline int validate_convert_profile(struct btrfs_balance_args *bctl_arg,
- u64 allowed)
+/*
+ * Validate target profile against allowed profiles and return true if it's OK.
+ * Otherwise print the error message and return false.
+ */
+static inline int validate_convert_profile(struct btrfs_fs_info *fs_info,
+ const struct btrfs_balance_args *bargs,
+ u64 allowed, const char *type)
{
- return ((bctl_arg->flags & BTRFS_BALANCE_ARGS_CONVERT) &&
- (!alloc_profile_is_valid(bctl_arg->target, 1) ||
- (bctl_arg->target & ~allowed)));
+ if (!(bargs->flags & BTRFS_BALANCE_ARGS_CONVERT))
+ return true;
+
+ /* Profile is valid and does not have bits outside of the allowed set */
+ if (alloc_profile_is_valid(bargs->target, 1) &&
+ (bargs->target & ~allowed) == 0)
+ return true;
+
+ btrfs_err(fs_info, "balance: invalid convert %s profile %s",
+ type, btrfs_bg_type_to_raid_name(bargs->target));
+ return false;
+}
+
+/*
+ * Fill @buf with textual description of balance filter flags @bargs, up to
+ * @size_buf including the terminating null. The output may be trimmed if it
+ * does not fit into the provided buffer.
+ */
+static void describe_balance_args(struct btrfs_balance_args *bargs, char *buf,
+ u32 size_buf)
+{
+ int ret;
+ u32 size_bp = size_buf;
+ char *bp = buf;
+ u64 flags = bargs->flags;
+ char tmp_buf[128] = {'\0'};
+
+ if (!flags)
+ return;
+
+#define CHECK_APPEND_NOARG(a) \
+ do { \
+ ret = snprintf(bp, size_bp, (a)); \
+ if (ret < 0 || ret >= size_bp) \
+ goto out_overflow; \
+ size_bp -= ret; \
+ bp += ret; \
+ } while (0)
+
+#define CHECK_APPEND_1ARG(a, v1) \
+ do { \
+ ret = snprintf(bp, size_bp, (a), (v1)); \
+ if (ret < 0 || ret >= size_bp) \
+ goto out_overflow; \
+ size_bp -= ret; \
+ bp += ret; \
+ } while (0)
+
+#define CHECK_APPEND_2ARG(a, v1, v2) \
+ do { \
+ ret = snprintf(bp, size_bp, (a), (v1), (v2)); \
+ if (ret < 0 || ret >= size_bp) \
+ goto out_overflow; \
+ size_bp -= ret; \
+ bp += ret; \
+ } while (0)
+
+ if (flags & BTRFS_BALANCE_ARGS_CONVERT)
+ CHECK_APPEND_1ARG("convert=%s,",
+ btrfs_bg_type_to_raid_name(bargs->target));
+
+ if (flags & BTRFS_BALANCE_ARGS_SOFT)
+ CHECK_APPEND_NOARG("soft,");
+
+ if (flags & BTRFS_BALANCE_ARGS_PROFILES) {
+ btrfs_describe_block_groups(bargs->profiles, tmp_buf,
+ sizeof(tmp_buf));
+ CHECK_APPEND_1ARG("profiles=%s,", tmp_buf);
+ }
+
+ if (flags & BTRFS_BALANCE_ARGS_USAGE)
+ CHECK_APPEND_1ARG("usage=%llu,", bargs->usage);
+
+ if (flags & BTRFS_BALANCE_ARGS_USAGE_RANGE)
+ CHECK_APPEND_2ARG("usage=%u..%u,",
+ bargs->usage_min, bargs->usage_max);
+
+ if (flags & BTRFS_BALANCE_ARGS_DEVID)
+ CHECK_APPEND_1ARG("devid=%llu,", bargs->devid);
+
+ if (flags & BTRFS_BALANCE_ARGS_DRANGE)
+ CHECK_APPEND_2ARG("drange=%llu..%llu,",
+ bargs->pstart, bargs->pend);
+
+ if (flags & BTRFS_BALANCE_ARGS_VRANGE)
+ CHECK_APPEND_2ARG("vrange=%llu..%llu,",
+ bargs->vstart, bargs->vend);
+
+ if (flags & BTRFS_BALANCE_ARGS_LIMIT)
+ CHECK_APPEND_1ARG("limit=%llu,", bargs->limit);
+
+ if (flags & BTRFS_BALANCE_ARGS_LIMIT_RANGE)
+ CHECK_APPEND_2ARG("limit=%u..%u,",
+ bargs->limit_min, bargs->limit_max);
+
+ if (flags & BTRFS_BALANCE_ARGS_STRIPES_RANGE)
+ CHECK_APPEND_2ARG("stripes=%u..%u,",
+ bargs->stripes_min, bargs->stripes_max);
+
+#undef CHECK_APPEND_2ARG
+#undef CHECK_APPEND_1ARG
+#undef CHECK_APPEND_NOARG
+
+out_overflow:
+
+ if (size_bp < size_buf)
+ buf[size_buf - size_bp - 1] = '\0'; /* remove last , */
+ else
+ buf[0] = '\0';
+}
+
+static void describe_balance_start_or_resume(struct btrfs_fs_info *fs_info)
+{
+ u32 size_buf = 1024;
+ char tmp_buf[192] = {'\0'};
+ char *buf;
+ char *bp;
+ u32 size_bp = size_buf;
+ int ret;
+ struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+
+ buf = kzalloc(size_buf, GFP_KERNEL);
+ if (!buf)
+ return;
+
+ bp = buf;
+
+#define CHECK_APPEND_1ARG(a, v1) \
+ do { \
+ ret = snprintf(bp, size_bp, (a), (v1)); \
+ if (ret < 0 || ret >= size_bp) \
+ goto out_overflow; \
+ size_bp -= ret; \
+ bp += ret; \
+ } while (0)
+
+ if (bctl->flags & BTRFS_BALANCE_FORCE)
+ CHECK_APPEND_1ARG("%s", "-f ");
+
+ if (bctl->flags & BTRFS_BALANCE_DATA) {
+ describe_balance_args(&bctl->data, tmp_buf, sizeof(tmp_buf));
+ CHECK_APPEND_1ARG("-d%s ", tmp_buf);
+ }
+
+ if (bctl->flags & BTRFS_BALANCE_METADATA) {
+ describe_balance_args(&bctl->meta, tmp_buf, sizeof(tmp_buf));
+ CHECK_APPEND_1ARG("-m%s ", tmp_buf);
+ }
+
+ if (bctl->flags & BTRFS_BALANCE_SYSTEM) {
+ describe_balance_args(&bctl->sys, tmp_buf, sizeof(tmp_buf));
+ CHECK_APPEND_1ARG("-s%s ", tmp_buf);
+ }
+
+#undef CHECK_APPEND_1ARG
+
+out_overflow:
+
+ if (size_bp < size_buf)
+ buf[size_buf - size_bp - 1] = '\0'; /* remove last " " */
+ btrfs_info(fs_info, "balance: %s %s",
+ (bctl->flags & BTRFS_BALANCE_RESUME) ?
+ "resume" : "start", buf);
+
+ kfree(buf);
}
/*
@@ -3745,11 +4060,12 @@
int ret;
u64 num_devices;
unsigned seq;
- bool reducing_integrity;
+ bool reducing_redundancy;
+ int i;
if (btrfs_fs_closing(fs_info) ||
atomic_read(&fs_info->balance_pause_req) ||
- atomic_read(&fs_info->balance_cancel_req)) {
+ btrfs_should_cancel_balance(fs_info)) {
ret = -EINVAL;
goto out;
}
@@ -3774,54 +4090,39 @@
}
}
- num_devices = fs_info->fs_devices->num_devices;
- btrfs_dev_replace_read_lock(&fs_info->dev_replace);
- if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) {
- BUG_ON(num_devices < 1);
- num_devices--;
- }
- btrfs_dev_replace_read_unlock(&fs_info->dev_replace);
- allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE | BTRFS_BLOCK_GROUP_DUP;
- if (num_devices > 1)
- allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1);
- if (num_devices > 2)
- allowed |= BTRFS_BLOCK_GROUP_RAID5;
- if (num_devices > 3)
- allowed |= (BTRFS_BLOCK_GROUP_RAID10 |
- BTRFS_BLOCK_GROUP_RAID6);
- if (validate_convert_profile(&bctl->data, allowed)) {
- int index = btrfs_bg_flags_to_raid_index(bctl->data.target);
+ /*
+ * rw_devices will not change at the moment, device add/delete/replace
+ * are exclusive
+ */
+ num_devices = fs_info->fs_devices->rw_devices;
- btrfs_err(fs_info,
- "balance: invalid convert data profile %s",
- get_raid_name(index));
- ret = -EINVAL;
- goto out;
- }
- if (validate_convert_profile(&bctl->meta, allowed)) {
- int index = btrfs_bg_flags_to_raid_index(bctl->meta.target);
+ /*
+ * SINGLE profile on-disk has no profile bit, but in-memory we have a
+ * special bit for it, to make it easier to distinguish. Thus we need
+ * to set it manually, or balance would refuse the profile.
+ */
+ allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+ for (i = 0; i < ARRAY_SIZE(btrfs_raid_array); i++)
+ if (num_devices >= btrfs_raid_array[i].devs_min)
+ allowed |= btrfs_raid_array[i].bg_flag;
- btrfs_err(fs_info,
- "balance: invalid convert metadata profile %s",
- get_raid_name(index));
- ret = -EINVAL;
- goto out;
- }
- if (validate_convert_profile(&bctl->sys, allowed)) {
- int index = btrfs_bg_flags_to_raid_index(bctl->sys.target);
-
- btrfs_err(fs_info,
- "balance: invalid convert system profile %s",
- get_raid_name(index));
+ if (!validate_convert_profile(fs_info, &bctl->data, allowed, "data") ||
+ !validate_convert_profile(fs_info, &bctl->meta, allowed, "metadata") ||
+ !validate_convert_profile(fs_info, &bctl->sys, allowed, "system")) {
ret = -EINVAL;
goto out;
}
- /* allow to reduce meta or sys integrity only if force set */
- allowed = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10 |
- BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6;
+ /*
+ * Allow to reduce metadata or system integrity only if force set for
+ * profiles with redundancy (copies, parity)
+ */
+ allowed = 0;
+ for (i = 0; i < ARRAY_SIZE(btrfs_raid_array); i++) {
+ if (btrfs_raid_array[i].ncopies >= 2 ||
+ btrfs_raid_array[i].tolerated_failures >= 1)
+ allowed |= btrfs_raid_array[i].bg_flag;
+ }
do {
seq = read_seqbegin(&fs_info->profiles_lock);
@@ -3831,9 +4132,9 @@
((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(fs_info->avail_metadata_alloc_bits & allowed) &&
!(bctl->meta.target & allowed)))
- reducing_integrity = true;
+ reducing_redundancy = true;
else
- reducing_integrity = false;
+ reducing_redundancy = false;
/* if we're not converting, the target field is uninitialized */
meta_target = (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) ?
@@ -3842,13 +4143,13 @@
bctl->data.target : fs_info->avail_data_alloc_bits;
} while (read_seqretry(&fs_info->profiles_lock, seq));
- if (reducing_integrity) {
+ if (reducing_redundancy) {
if (bctl->flags & BTRFS_BALANCE_FORCE) {
btrfs_info(fs_info,
- "balance: force reducing metadata integrity");
+ "balance: force reducing metadata redundancy");
} else {
btrfs_err(fs_info,
- "balance: reduces metadata integrity, use --force if you want this");
+ "balance: reduces metadata redundancy, use --force if you want this");
ret = -EINVAL;
goto out;
}
@@ -3856,12 +4157,18 @@
if (btrfs_get_num_tolerated_disk_barrier_failures(meta_target) <
btrfs_get_num_tolerated_disk_barrier_failures(data_target)) {
- int meta_index = btrfs_bg_flags_to_raid_index(meta_target);
- int data_index = btrfs_bg_flags_to_raid_index(data_target);
-
btrfs_warn(fs_info,
"balance: metadata profile %s has lower redundancy than data profile %s",
- get_raid_name(meta_index), get_raid_name(data_index));
+ btrfs_bg_type_to_raid_name(meta_target),
+ btrfs_bg_type_to_raid_name(data_target));
+ }
+
+ if (fs_info->send_in_progress) {
+ btrfs_warn_rl(fs_info,
+"cannot run balance while send operations are in progress (%d in progress)",
+ fs_info->send_in_progress);
+ ret = -EAGAIN;
+ goto out;
}
ret = insert_balance_item(fs_info, bctl);
@@ -3883,11 +4190,34 @@
ASSERT(!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
set_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags);
+ describe_balance_start_or_resume(fs_info);
mutex_unlock(&fs_info->balance_mutex);
ret = __btrfs_balance(fs_info);
mutex_lock(&fs_info->balance_mutex);
+ if (ret == -ECANCELED && atomic_read(&fs_info->balance_pause_req))
+ btrfs_info(fs_info, "balance: paused");
+ /*
+ * Balance can be canceled by:
+ *
+ * - Regular cancel request
+ * Then ret == -ECANCELED and balance_cancel_req > 0
+ *
+ * - Fatal signal to "btrfs" process
+ * Either the signal caught by wait_reserve_ticket() and callers
+ * got -EINTR, or caught by btrfs_should_cancel_balance() and
+ * got -ECANCELED.
+ * Either way, in this case balance_cancel_req = 0, and
+ * ret == -EINTR or ret == -ECANCELED.
+ *
+ * So here we only check the return value to catch canceled balance.
+ */
+ else if (ret == -ECANCELED || ret == -EINTR)
+ btrfs_info(fs_info, "balance: canceled");
+ else
+ btrfs_info(fs_info, "balance: ended with status: %d", ret);
+
clear_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags);
if (bargs) {
@@ -3898,7 +4228,7 @@
if ((ret && ret != -ECANCELED && ret != -ENOSPC) ||
balance_need_close(fs_info)) {
reset_balance_state(fs_info);
- clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
+ btrfs_exclop_finish(fs_info);
}
wake_up(&fs_info->balance_wait_q);
@@ -3909,7 +4239,7 @@
reset_balance_state(fs_info);
else
kfree(bctl);
- clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
+ btrfs_exclop_finish(fs_info);
return ret;
}
@@ -3919,12 +4249,12 @@
struct btrfs_fs_info *fs_info = data;
int ret = 0;
+ sb_start_write(fs_info->sb);
mutex_lock(&fs_info->balance_mutex);
- if (fs_info->balance_ctl) {
- btrfs_info(fs_info, "balance: resuming");
+ if (fs_info->balance_ctl)
ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL);
- }
mutex_unlock(&fs_info->balance_mutex);
+ sb_end_write(fs_info->sb);
return ret;
}
@@ -4013,7 +4343,7 @@
* is in a paused state and must have fs_info::balance_ctl properly
* set up.
*/
- if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags))
+ if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE))
btrfs_warn(fs_info,
"balance: cannot set exclusive op status, resume manually");
@@ -4097,7 +4427,7 @@
if (fs_info->balance_ctl) {
reset_balance_state(fs_info);
- clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
+ btrfs_exclop_finish(fs_info);
btrfs_info(fs_info, "balance: canceled");
}
}
@@ -4109,7 +4439,7 @@
return 0;
}
-static int btrfs_uuid_scan_kthread(void *data)
+int btrfs_uuid_scan_kthread(void *data)
{
struct btrfs_fs_info *fs_info = data;
struct btrfs_root *root = fs_info->tree_root;
@@ -4121,6 +4451,7 @@
struct btrfs_root_item root_item;
u32 item_size;
struct btrfs_trans_handle *trans = NULL;
+ bool closing = false;
path = btrfs_alloc_path();
if (!path) {
@@ -4133,6 +4464,10 @@
key.offset = 0;
while (1) {
+ if (btrfs_fs_closing(fs_info)) {
+ closing = true;
+ break;
+ }
ret = btrfs_search_forward(root, &key, path,
BTRFS_OLDEST_GENERATION);
if (ret) {
@@ -4233,74 +4568,10 @@
btrfs_end_transaction(trans);
if (ret)
btrfs_warn(fs_info, "btrfs_uuid_scan_kthread failed %d", ret);
- else
+ else if (!closing)
set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags);
up(&fs_info->uuid_tree_rescan_sem);
return 0;
-}
-
-/*
- * Callback for btrfs_uuid_tree_iterate().
- * returns:
- * 0 check succeeded, the entry is not outdated.
- * < 0 if an error occurred.
- * > 0 if the check failed, which means the caller shall remove the entry.
- */
-static int btrfs_check_uuid_tree_entry(struct btrfs_fs_info *fs_info,
- u8 *uuid, u8 type, u64 subid)
-{
- struct btrfs_key key;
- int ret = 0;
- struct btrfs_root *subvol_root;
-
- if (type != BTRFS_UUID_KEY_SUBVOL &&
- type != BTRFS_UUID_KEY_RECEIVED_SUBVOL)
- goto out;
-
- key.objectid = subid;
- key.type = BTRFS_ROOT_ITEM_KEY;
- key.offset = (u64)-1;
- subvol_root = btrfs_read_fs_root_no_name(fs_info, &key);
- if (IS_ERR(subvol_root)) {
- ret = PTR_ERR(subvol_root);
- if (ret == -ENOENT)
- ret = 1;
- goto out;
- }
-
- switch (type) {
- case BTRFS_UUID_KEY_SUBVOL:
- if (memcmp(uuid, subvol_root->root_item.uuid, BTRFS_UUID_SIZE))
- ret = 1;
- break;
- case BTRFS_UUID_KEY_RECEIVED_SUBVOL:
- if (memcmp(uuid, subvol_root->root_item.received_uuid,
- BTRFS_UUID_SIZE))
- ret = 1;
- break;
- }
-
-out:
- return ret;
-}
-
-static int btrfs_uuid_rescan_kthread(void *data)
-{
- struct btrfs_fs_info *fs_info = (struct btrfs_fs_info *)data;
- int ret;
-
- /*
- * 1st step is to iterate through the existing UUID tree and
- * to delete all entries that contain outdated data.
- * 2nd step is to add all missing entries to the UUID tree.
- */
- ret = btrfs_uuid_tree_iterate(fs_info, btrfs_check_uuid_tree_entry);
- if (ret < 0) {
- btrfs_warn(fs_info, "iterating uuid_tree failed %d", ret);
- up(&fs_info->uuid_tree_rescan_sem);
- return ret;
- }
- return btrfs_uuid_scan_kthread(data);
}
int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info)
@@ -4319,8 +4590,7 @@
if (IS_ERR(trans))
return PTR_ERR(trans);
- uuid_root = btrfs_create_tree(trans, fs_info,
- BTRFS_UUID_TREE_OBJECTID);
+ uuid_root = btrfs_create_tree(trans, BTRFS_UUID_TREE_OBJECTID);
if (IS_ERR(uuid_root)) {
ret = PTR_ERR(uuid_root);
btrfs_abort_transaction(trans, ret);
@@ -4346,22 +4616,6 @@
return 0;
}
-int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info)
-{
- struct task_struct *task;
-
- down(&fs_info->uuid_tree_rescan_sem);
- task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid");
- if (IS_ERR(task)) {
- /* fs_info->update_uuid_tree_gen remains 0 in all error case */
- btrfs_warn(fs_info, "failed to start uuid_rescan task");
- up(&fs_info->uuid_tree_rescan_sem);
- return PTR_ERR(task);
- }
-
- return 0;
-}
-
/*
* shrinking a device means finding all of the device extents past
* the new size, and then following the back refs to the chunks.
@@ -4380,15 +4634,16 @@
int slot;
int failed = 0;
bool retried = false;
- bool checked_pending_chunks = false;
struct extent_buffer *l;
struct btrfs_key key;
struct btrfs_super_block *super_copy = fs_info->super_copy;
u64 old_total = btrfs_super_total_bytes(super_copy);
u64 old_size = btrfs_device_get_total_bytes(device);
u64 diff;
+ u64 start;
new_size = round_down(new_size, fs_info->sectorsize);
+ start = new_size;
diff = round_down(old_size - new_size, fs_info->sectorsize);
if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state))
@@ -4400,6 +4655,12 @@
path->reada = READA_BACK;
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ btrfs_free_path(path);
+ return PTR_ERR(trans);
+ }
+
mutex_lock(&fs_info->chunk_mutex);
btrfs_device_set_total_bytes(device, new_size);
@@ -4407,7 +4668,21 @@
device->fs_devices->total_rw_bytes -= diff;
atomic64_sub(diff, &fs_info->free_chunk_space);
}
- mutex_unlock(&fs_info->chunk_mutex);
+
+ /*
+ * Once the device's size has been set to the new size, ensure all
+ * in-memory chunks are synced to disk so that the loop below sees them
+ * and relocates them accordingly.
+ */
+ if (contains_pending_extent(device, &start, diff)) {
+ mutex_unlock(&fs_info->chunk_mutex);
+ ret = btrfs_commit_transaction(trans);
+ if (ret)
+ goto done;
+ } else {
+ mutex_unlock(&fs_info->chunk_mutex);
+ btrfs_end_transaction(trans);
+ }
again:
key.objectid = device->devid;
@@ -4469,10 +4744,16 @@
ret = btrfs_relocate_chunk(fs_info, chunk_offset);
mutex_unlock(&fs_info->delete_unused_bgs_mutex);
- if (ret && ret != -ENOSPC)
- goto done;
- if (ret == -ENOSPC)
+ if (ret == -ENOSPC) {
failed++;
+ } else if (ret) {
+ if (ret == -ETXTBSY) {
+ btrfs_warn(fs_info,
+ "could not shrink block group %llu due to active swapfile",
+ chunk_offset);
+ }
+ goto done;
+ }
} while (key.offset-- > 0);
if (failed && !retried) {
@@ -4492,40 +4773,14 @@
}
mutex_lock(&fs_info->chunk_mutex);
-
- /*
- * We checked in the above loop all device extents that were already in
- * the device tree. However before we have updated the device's
- * total_bytes to the new size, we might have had chunk allocations that
- * have not complete yet (new block groups attached to transaction
- * handles), and therefore their device extents were not yet in the
- * device tree and we missed them in the loop above. So if we have any
- * pending chunk using a device extent that overlaps the device range
- * that we can not use anymore, commit the current transaction and
- * repeat the search on the device tree - this way we guarantee we will
- * not have chunks using device extents that end beyond 'new_size'.
- */
- if (!checked_pending_chunks) {
- u64 start = new_size;
- u64 len = old_size - new_size;
-
- if (contains_pending_extent(trans->transaction, device,
- &start, len)) {
- mutex_unlock(&fs_info->chunk_mutex);
- checked_pending_chunks = true;
- failed = 0;
- retried = false;
- ret = btrfs_commit_transaction(trans);
- if (ret)
- goto done;
- goto again;
- }
- }
+ /* Clear all state bits beyond the shrunk device size */
+ clear_extent_bits(&device->alloc_state, new_size, (u64)-1,
+ CHUNK_STATE_MASK);
btrfs_device_set_disk_total_bytes(device, new_size);
- if (list_empty(&device->resized_list))
- list_add_tail(&device->resized_list,
- &fs_info->fs_devices->resized_devices);
+ if (list_empty(&device->post_commit_list))
+ list_add_tail(&device->post_commit_list,
+ &trans->transaction->dev_update_list);
WARN_ON(diff > old_total);
btrfs_set_super_total_bytes(super_copy,
@@ -4609,96 +4864,119 @@
btrfs_set_fs_incompat(info, RAID56);
}
-static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
- u64 start, u64 type)
+static void check_raid1c34_incompat_flag(struct btrfs_fs_info *info, u64 type)
{
- struct btrfs_fs_info *info = trans->fs_info;
- struct btrfs_fs_devices *fs_devices = info->fs_devices;
- struct btrfs_device *device;
- struct map_lookup *map = NULL;
- struct extent_map_tree *em_tree;
- struct extent_map *em;
- struct btrfs_device_info *devices_info = NULL;
- u64 total_avail;
- int num_stripes; /* total number of stripes to allocate */
- int data_stripes; /* number of stripes that count for
- block group size */
- int sub_stripes; /* sub_stripes info for map */
- int dev_stripes; /* stripes per dev */
- int devs_max; /* max devs to use */
- int devs_min; /* min devs needed */
- int devs_increment; /* ndevs has to be a multiple of this */
- int ncopies; /* how many copies to data has */
- int ret;
+ if (!(type & (BTRFS_BLOCK_GROUP_RAID1C3 | BTRFS_BLOCK_GROUP_RAID1C4)))
+ return;
+
+ btrfs_set_fs_incompat(info, RAID1C34);
+}
+
+/*
+ * Structure used internally for __btrfs_alloc_chunk() function.
+ * Wraps needed parameters.
+ */
+struct alloc_chunk_ctl {
+ u64 start;
+ u64 type;
+ /* Total number of stripes to allocate */
+ int num_stripes;
+ /* sub_stripes info for map */
+ int sub_stripes;
+ /* Stripes per device */
+ int dev_stripes;
+ /* Maximum number of devices to use */
+ int devs_max;
+ /* Minimum number of devices to use */
+ int devs_min;
+ /* ndevs has to be a multiple of this */
+ int devs_increment;
+ /* Number of copies */
+ int ncopies;
+ /* Number of stripes worth of bytes to store parity information */
+ int nparity;
u64 max_stripe_size;
u64 max_chunk_size;
+ u64 dev_extent_min;
u64 stripe_size;
- u64 num_bytes;
+ u64 chunk_size;
int ndevs;
- int i;
- int j;
- int index;
+};
- BUG_ON(!alloc_profile_is_valid(type, 0));
-
- if (list_empty(&fs_devices->alloc_list)) {
- if (btrfs_test_opt(info, ENOSPC_DEBUG))
- btrfs_debug(info, "%s: no writable device", __func__);
- return -ENOSPC;
- }
-
- index = btrfs_bg_flags_to_raid_index(type);
-
- sub_stripes = btrfs_raid_array[index].sub_stripes;
- dev_stripes = btrfs_raid_array[index].dev_stripes;
- devs_max = btrfs_raid_array[index].devs_max;
- devs_min = btrfs_raid_array[index].devs_min;
- devs_increment = btrfs_raid_array[index].devs_increment;
- ncopies = btrfs_raid_array[index].ncopies;
+static void init_alloc_chunk_ctl_policy_regular(
+ struct btrfs_fs_devices *fs_devices,
+ struct alloc_chunk_ctl *ctl)
+{
+ u64 type = ctl->type;
if (type & BTRFS_BLOCK_GROUP_DATA) {
- max_stripe_size = SZ_1G;
- max_chunk_size = BTRFS_MAX_DATA_CHUNK_SIZE;
- if (!devs_max)
- devs_max = BTRFS_MAX_DEVS(info);
+ ctl->max_stripe_size = SZ_1G;
+ ctl->max_chunk_size = BTRFS_MAX_DATA_CHUNK_SIZE;
} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
- /* for larger filesystems, use larger metadata chunks */
+ /* For larger filesystems, use larger metadata chunks */
if (fs_devices->total_rw_bytes > 50ULL * SZ_1G)
- max_stripe_size = SZ_1G;
+ ctl->max_stripe_size = SZ_1G;
else
- max_stripe_size = SZ_256M;
- max_chunk_size = max_stripe_size;
- if (!devs_max)
- devs_max = BTRFS_MAX_DEVS(info);
+ ctl->max_stripe_size = SZ_256M;
+ ctl->max_chunk_size = ctl->max_stripe_size;
} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
- max_stripe_size = SZ_32M;
- max_chunk_size = 2 * max_stripe_size;
- if (!devs_max)
- devs_max = BTRFS_MAX_DEVS_SYS_CHUNK;
+ ctl->max_stripe_size = SZ_32M;
+ ctl->max_chunk_size = 2 * ctl->max_stripe_size;
+ ctl->devs_max = min_t(int, ctl->devs_max,
+ BTRFS_MAX_DEVS_SYS_CHUNK);
} else {
- btrfs_err(info, "invalid chunk type 0x%llx requested",
- type);
- BUG_ON(1);
+ BUG();
}
- /* we don't want a chunk larger than 10% of writeable space */
- max_chunk_size = min(div_factor(fs_devices->total_rw_bytes, 1),
- max_chunk_size);
+ /* We don't want a chunk larger than 10% of writable space */
+ ctl->max_chunk_size = min(div_factor(fs_devices->total_rw_bytes, 1),
+ ctl->max_chunk_size);
+ ctl->dev_extent_min = BTRFS_STRIPE_LEN * ctl->dev_stripes;
+}
- devices_info = kcalloc(fs_devices->rw_devices, sizeof(*devices_info),
- GFP_NOFS);
- if (!devices_info)
- return -ENOMEM;
+static void init_alloc_chunk_ctl(struct btrfs_fs_devices *fs_devices,
+ struct alloc_chunk_ctl *ctl)
+{
+ int index = btrfs_bg_flags_to_raid_index(ctl->type);
+
+ ctl->sub_stripes = btrfs_raid_array[index].sub_stripes;
+ ctl->dev_stripes = btrfs_raid_array[index].dev_stripes;
+ ctl->devs_max = btrfs_raid_array[index].devs_max;
+ if (!ctl->devs_max)
+ ctl->devs_max = BTRFS_MAX_DEVS(fs_devices->fs_info);
+ ctl->devs_min = btrfs_raid_array[index].devs_min;
+ ctl->devs_increment = btrfs_raid_array[index].devs_increment;
+ ctl->ncopies = btrfs_raid_array[index].ncopies;
+ ctl->nparity = btrfs_raid_array[index].nparity;
+ ctl->ndevs = 0;
+
+ switch (fs_devices->chunk_alloc_policy) {
+ case BTRFS_CHUNK_ALLOC_REGULAR:
+ init_alloc_chunk_ctl_policy_regular(fs_devices, ctl);
+ break;
+ default:
+ BUG();
+ }
+}
+
+static int gather_device_info(struct btrfs_fs_devices *fs_devices,
+ struct alloc_chunk_ctl *ctl,
+ struct btrfs_device_info *devices_info)
+{
+ struct btrfs_fs_info *info = fs_devices->fs_info;
+ struct btrfs_device *device;
+ u64 total_avail;
+ u64 dev_extent_want = ctl->max_stripe_size * ctl->dev_stripes;
+ int ret;
+ int ndevs = 0;
+ u64 max_avail;
+ u64 dev_offset;
/*
* in the first pass through the devices list, we gather information
* about the available holes on each device.
*/
- ndevs = 0;
list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
- u64 max_avail;
- u64 dev_offset;
-
if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
WARN(1, KERN_ERR
"BTRFS: read-only device in alloc_list\n");
@@ -4716,24 +4994,23 @@
total_avail = 0;
/* If there is no space on this device, skip it. */
- if (total_avail == 0)
+ if (total_avail < ctl->dev_extent_min)
continue;
- ret = find_free_dev_extent(trans, device,
- max_stripe_size * dev_stripes,
- &dev_offset, &max_avail);
+ ret = find_free_dev_extent(device, dev_extent_want, &dev_offset,
+ &max_avail);
if (ret && ret != -ENOSPC)
- goto error;
+ return ret;
if (ret == 0)
- max_avail = max_stripe_size * dev_stripes;
+ max_avail = dev_extent_want;
- if (max_avail < BTRFS_STRIPE_LEN * dev_stripes) {
+ if (max_avail < ctl->dev_extent_min) {
if (btrfs_test_opt(info, ENOSPC_DEBUG))
btrfs_debug(info,
- "%s: devid %llu has no free space, have=%llu want=%u",
+ "%s: devid %llu has no free space, have=%llu want=%llu",
__func__, device->devid, max_avail,
- BTRFS_STRIPE_LEN * dev_stripes);
+ ctl->dev_extent_min);
continue;
}
@@ -4748,6 +5025,7 @@
devices_info[ndevs].dev = device;
++ndevs;
}
+ ctl->ndevs = ndevs;
/*
* now sort the devices by hole size / available space
@@ -4755,20 +5033,14 @@
sort(devices_info, ndevs, sizeof(struct btrfs_device_info),
btrfs_cmp_device_info, NULL);
- /* round down to number of usable stripes */
- ndevs = round_down(ndevs, devs_increment);
+ return 0;
+}
- if (ndevs < devs_min) {
- ret = -ENOSPC;
- if (btrfs_test_opt(info, ENOSPC_DEBUG)) {
- btrfs_debug(info,
- "%s: not enough devices with free space: have=%d minimum required=%d",
- __func__, ndevs, devs_min);
- }
- goto error;
- }
-
- ndevs = min(ndevs, devs_max);
+static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl,
+ struct btrfs_device_info *devices_info)
+{
+ /* Number of stripes that count for block group size */
+ int data_stripes;
/*
* The primary goal is to maximize the number of stripes, so use as
@@ -4777,109 +5049,148 @@
* The DUP profile stores more than one stripe per device, the
* max_avail is the total size so we have to adjust.
*/
- stripe_size = div_u64(devices_info[ndevs - 1].max_avail, dev_stripes);
- num_stripes = ndevs * dev_stripes;
+ ctl->stripe_size = div_u64(devices_info[ctl->ndevs - 1].max_avail,
+ ctl->dev_stripes);
+ ctl->num_stripes = ctl->ndevs * ctl->dev_stripes;
+
+ /* This will have to be fixed for RAID1 and RAID10 over more drives */
+ data_stripes = (ctl->num_stripes - ctl->nparity) / ctl->ncopies;
/*
- * this will have to be fixed for RAID1 and RAID10 over
- * more drives
+ * Use the number of data stripes to figure out how big this chunk is
+ * really going to be in terms of logical address space, and compare
+ * that answer with the max chunk size. If it's higher, we try to
+ * reduce stripe_size.
*/
- data_stripes = num_stripes / ncopies;
-
- if (type & BTRFS_BLOCK_GROUP_RAID5)
- data_stripes = num_stripes - 1;
-
- if (type & BTRFS_BLOCK_GROUP_RAID6)
- data_stripes = num_stripes - 2;
-
- /*
- * Use the number of data stripes to figure out how big this chunk
- * is really going to be in terms of logical address space,
- * and compare that answer with the max chunk size. If it's higher,
- * we try to reduce stripe_size.
- */
- if (stripe_size * data_stripes > max_chunk_size) {
+ if (ctl->stripe_size * data_stripes > ctl->max_chunk_size) {
/*
* Reduce stripe_size, round it up to a 16MB boundary again and
* then use it, unless it ends up being even bigger than the
* previous value we had already.
*/
- stripe_size = min(round_up(div_u64(max_chunk_size,
- data_stripes), SZ_16M),
- stripe_size);
+ ctl->stripe_size = min(round_up(div_u64(ctl->max_chunk_size,
+ data_stripes), SZ_16M),
+ ctl->stripe_size);
}
- /* align to BTRFS_STRIPE_LEN */
- stripe_size = round_down(stripe_size, BTRFS_STRIPE_LEN);
+ /* Align to BTRFS_STRIPE_LEN */
+ ctl->stripe_size = round_down(ctl->stripe_size, BTRFS_STRIPE_LEN);
+ ctl->chunk_size = ctl->stripe_size * data_stripes;
- map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
- if (!map) {
- ret = -ENOMEM;
- goto error;
+ return 0;
+}
+
+static int decide_stripe_size(struct btrfs_fs_devices *fs_devices,
+ struct alloc_chunk_ctl *ctl,
+ struct btrfs_device_info *devices_info)
+{
+ struct btrfs_fs_info *info = fs_devices->fs_info;
+
+ /*
+ * Round down to number of usable stripes, devs_increment can be any
+ * number so we can't use round_down() that requires power of 2, while
+ * rounddown is safe.
+ */
+ ctl->ndevs = rounddown(ctl->ndevs, ctl->devs_increment);
+
+ if (ctl->ndevs < ctl->devs_min) {
+ if (btrfs_test_opt(info, ENOSPC_DEBUG)) {
+ btrfs_debug(info,
+ "%s: not enough devices with free space: have=%d minimum required=%d",
+ __func__, ctl->ndevs, ctl->devs_min);
+ }
+ return -ENOSPC;
}
- map->num_stripes = num_stripes;
- for (i = 0; i < ndevs; ++i) {
- for (j = 0; j < dev_stripes; ++j) {
- int s = i * dev_stripes + j;
+ ctl->ndevs = min(ctl->ndevs, ctl->devs_max);
+
+ switch (fs_devices->chunk_alloc_policy) {
+ case BTRFS_CHUNK_ALLOC_REGULAR:
+ return decide_stripe_size_regular(ctl, devices_info);
+ default:
+ BUG();
+ }
+}
+
+static int create_chunk(struct btrfs_trans_handle *trans,
+ struct alloc_chunk_ctl *ctl,
+ struct btrfs_device_info *devices_info)
+{
+ struct btrfs_fs_info *info = trans->fs_info;
+ struct map_lookup *map = NULL;
+ struct extent_map_tree *em_tree;
+ struct extent_map *em;
+ u64 start = ctl->start;
+ u64 type = ctl->type;
+ int ret;
+ int i;
+ int j;
+
+ map = kmalloc(map_lookup_size(ctl->num_stripes), GFP_NOFS);
+ if (!map)
+ return -ENOMEM;
+ map->num_stripes = ctl->num_stripes;
+
+ for (i = 0; i < ctl->ndevs; ++i) {
+ for (j = 0; j < ctl->dev_stripes; ++j) {
+ int s = i * ctl->dev_stripes + j;
map->stripes[s].dev = devices_info[i].dev;
map->stripes[s].physical = devices_info[i].dev_offset +
- j * stripe_size;
+ j * ctl->stripe_size;
}
}
map->stripe_len = BTRFS_STRIPE_LEN;
map->io_align = BTRFS_STRIPE_LEN;
map->io_width = BTRFS_STRIPE_LEN;
map->type = type;
- map->sub_stripes = sub_stripes;
+ map->sub_stripes = ctl->sub_stripes;
- num_bytes = stripe_size * data_stripes;
-
- trace_btrfs_chunk_alloc(info, map, start, num_bytes);
+ trace_btrfs_chunk_alloc(info, map, start, ctl->chunk_size);
em = alloc_extent_map();
if (!em) {
kfree(map);
- ret = -ENOMEM;
- goto error;
+ return -ENOMEM;
}
set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
em->map_lookup = map;
em->start = start;
- em->len = num_bytes;
+ em->len = ctl->chunk_size;
em->block_start = 0;
em->block_len = em->len;
- em->orig_block_len = stripe_size;
+ em->orig_block_len = ctl->stripe_size;
- em_tree = &info->mapping_tree.map_tree;
+ em_tree = &info->mapping_tree;
write_lock(&em_tree->lock);
ret = add_extent_mapping(em_tree, em, 0);
if (ret) {
write_unlock(&em_tree->lock);
free_extent_map(em);
- goto error;
+ return ret;
}
-
- list_add_tail(&em->list, &trans->transaction->pending_chunks);
- refcount_inc(&em->refs);
write_unlock(&em_tree->lock);
- ret = btrfs_make_block_group(trans, 0, type, start, num_bytes);
+ ret = btrfs_make_block_group(trans, 0, type, start, ctl->chunk_size);
if (ret)
goto error_del_extent;
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);
- map->stripes[i].dev->has_pending_chunks = true;
+ struct btrfs_device *dev = map->stripes[i].dev;
+
+ btrfs_device_set_bytes_used(dev,
+ dev->bytes_used + ctl->stripe_size);
+ if (list_empty(&dev->post_commit_list))
+ list_add_tail(&dev->post_commit_list,
+ &trans->transaction->dev_update_list);
}
- atomic64_sub(stripe_size * map->num_stripes, &info->free_chunk_space);
+ atomic64_sub(ctl->stripe_size * map->num_stripes,
+ &info->free_chunk_space);
free_extent_map(em);
check_raid56_incompat_flag(info, type);
+ check_raid1c34_incompat_flag(info, type);
- kfree(devices_info);
return 0;
error_del_extent:
@@ -4891,13 +5202,68 @@
free_extent_map(em);
/* One for the tree reference */
free_extent_map(em);
- /* One for the pending_chunks list reference */
- free_extent_map(em);
-error:
+
+ return ret;
+}
+
+int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type)
+{
+ struct btrfs_fs_info *info = trans->fs_info;
+ struct btrfs_fs_devices *fs_devices = info->fs_devices;
+ struct btrfs_device_info *devices_info = NULL;
+ struct alloc_chunk_ctl ctl;
+ int ret;
+
+ lockdep_assert_held(&info->chunk_mutex);
+
+ if (!alloc_profile_is_valid(type, 0)) {
+ ASSERT(0);
+ return -EINVAL;
+ }
+
+ if (list_empty(&fs_devices->alloc_list)) {
+ if (btrfs_test_opt(info, ENOSPC_DEBUG))
+ btrfs_debug(info, "%s: no writable device", __func__);
+ return -ENOSPC;
+ }
+
+ if (!(type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+ btrfs_err(info, "invalid chunk type 0x%llx requested", type);
+ ASSERT(0);
+ return -EINVAL;
+ }
+
+ ctl.start = find_next_chunk(info);
+ ctl.type = type;
+ init_alloc_chunk_ctl(fs_devices, &ctl);
+
+ devices_info = kcalloc(fs_devices->rw_devices, sizeof(*devices_info),
+ GFP_NOFS);
+ if (!devices_info)
+ return -ENOMEM;
+
+ ret = gather_device_info(fs_devices, &ctl, devices_info);
+ if (ret < 0)
+ goto out;
+
+ ret = decide_stripe_size(fs_devices, &ctl, devices_info);
+ if (ret < 0)
+ goto out;
+
+ ret = create_chunk(trans, &ctl, devices_info);
+
+out:
kfree(devices_info);
return ret;
}
+/*
+ * Chunk allocation falls into two parts. The first part does work
+ * that makes the new allocated chunk usable, but does not do any operation
+ * that modifies the chunk tree. The second part does the work that
+ * requires modifying the chunk tree. This division is important for the
+ * bootstrap process of adding storage to a seed btrfs.
+ */
int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
u64 chunk_offset, u64 chunk_size)
{
@@ -4916,7 +5282,7 @@
int i = 0;
int ret = 0;
- em = get_chunk_map(fs_info, chunk_offset, chunk_size);
+ em = btrfs_get_chunk_map(fs_info, chunk_offset, chunk_size);
if (IS_ERR(em))
return PTR_ERR(em);
@@ -4996,57 +5362,27 @@
return ret;
}
-/*
- * Chunk allocation falls into two parts. The first part does works
- * that make the new allocated chunk useable, but not do any operation
- * that modifies the chunk tree. The second part does the works that
- * require modifying the chunk tree. This division is important for the
- * bootstrap process of adding storage to a seed btrfs.
- */
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type)
+static noinline int init_first_rw_device(struct btrfs_trans_handle *trans)
{
- u64 chunk_offset;
-
- lockdep_assert_held(&trans->fs_info->chunk_mutex);
- chunk_offset = find_next_chunk(trans->fs_info);
- return __btrfs_alloc_chunk(trans, chunk_offset, type);
-}
-
-static noinline int init_first_rw_device(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info)
-{
- u64 chunk_offset;
- u64 sys_chunk_offset;
+ struct btrfs_fs_info *fs_info = trans->fs_info;
u64 alloc_profile;
int ret;
- chunk_offset = find_next_chunk(fs_info);
alloc_profile = btrfs_metadata_alloc_profile(fs_info);
- ret = __btrfs_alloc_chunk(trans, chunk_offset, alloc_profile);
+ ret = btrfs_alloc_chunk(trans, alloc_profile);
if (ret)
return ret;
- sys_chunk_offset = find_next_chunk(fs_info);
alloc_profile = btrfs_system_alloc_profile(fs_info);
- ret = __btrfs_alloc_chunk(trans, sys_chunk_offset, alloc_profile);
+ ret = btrfs_alloc_chunk(trans, alloc_profile);
return ret;
}
static inline int btrfs_chunk_max_errors(struct map_lookup *map)
{
- int max_errors;
+ const int index = btrfs_bg_flags_to_raid_index(map->type);
- if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10 |
- BTRFS_BLOCK_GROUP_RAID5)) {
- max_errors = 1;
- } else if (map->type & BTRFS_BLOCK_GROUP_RAID6) {
- max_errors = 2;
- } else {
- max_errors = 0;
- }
-
- return max_errors;
+ return btrfs_raid_array[index].tolerated_failures;
}
int btrfs_chunk_readonly(struct btrfs_fs_info *fs_info, u64 chunk_offset)
@@ -5057,7 +5393,7 @@
int miss_ndevs = 0;
int i;
- em = get_chunk_map(fs_info, chunk_offset, 1);
+ em = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
if (IS_ERR(em))
return 1;
@@ -5087,21 +5423,16 @@
return readonly;
}
-void btrfs_mapping_init(struct btrfs_mapping_tree *tree)
-{
- extent_map_tree_init(&tree->map_tree);
-}
-
-void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree)
+void btrfs_mapping_tree_free(struct extent_map_tree *tree)
{
struct extent_map *em;
while (1) {
- write_lock(&tree->map_tree.lock);
- em = lookup_extent_mapping(&tree->map_tree, 0, (u64)-1);
+ write_lock(&tree->lock);
+ em = lookup_extent_mapping(tree, 0, (u64)-1);
if (em)
- remove_extent_mapping(&tree->map_tree, em);
- write_unlock(&tree->map_tree.lock);
+ remove_extent_mapping(tree, em);
+ write_unlock(&tree->lock);
if (!em)
break;
/* once for us */
@@ -5117,7 +5448,7 @@
struct map_lookup *map;
int ret;
- em = get_chunk_map(fs_info, logical, len);
+ em = btrfs_get_chunk_map(fs_info, logical, len);
if (IS_ERR(em))
/*
* We could return errors for these cases, but that could get
@@ -5128,7 +5459,7 @@
return 1;
map = em->map_lookup;
- if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1))
+ if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1_MASK))
ret = map->num_stripes;
else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
ret = map->sub_stripes;
@@ -5147,11 +5478,11 @@
ret = 1;
free_extent_map(em);
- btrfs_dev_replace_read_lock(&fs_info->dev_replace);
+ down_read(&fs_info->dev_replace.rwsem);
if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace) &&
fs_info->dev_replace.tgtdev)
ret++;
- btrfs_dev_replace_read_unlock(&fs_info->dev_replace);
+ up_read(&fs_info->dev_replace.rwsem);
return ret;
}
@@ -5163,7 +5494,7 @@
struct map_lookup *map;
unsigned long len = fs_info->sectorsize;
- em = get_chunk_map(fs_info, logical, len);
+ em = btrfs_get_chunk_map(fs_info, logical, len);
if (!WARN_ON(IS_ERR(em))) {
map = em->map_lookup;
@@ -5180,7 +5511,7 @@
struct map_lookup *map;
int ret = 0;
- em = get_chunk_map(fs_info, logical, len);
+ em = btrfs_get_chunk_map(fs_info, logical, len);
if(!WARN_ON(IS_ERR(em))) {
map = em->map_lookup;
@@ -5202,7 +5533,7 @@
struct btrfs_device *srcdev;
ASSERT((map->type &
- (BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10)));
+ (BTRFS_BLOCK_GROUP_RAID1_MASK | BTRFS_BLOCK_GROUP_RAID10)));
if (map->type & BTRFS_BLOCK_GROUP_RAID10)
num_stripes = map->sub_stripes;
@@ -5240,31 +5571,19 @@
return preferred_mirror;
}
-static inline int parity_smaller(u64 a, u64 b)
-{
- return a > b;
-}
-
/* Bubble-sort the stripe set to put the parity/syndrome stripes last */
static void sort_parity_stripes(struct btrfs_bio *bbio, int num_stripes)
{
- struct btrfs_bio_stripe s;
int i;
- u64 l;
int again = 1;
while (again) {
again = 0;
for (i = 0; i < num_stripes - 1; i++) {
- if (parity_smaller(bbio->raid_map[i],
- bbio->raid_map[i+1])) {
- s = bbio->stripes[i];
- l = bbio->raid_map[i];
- bbio->stripes[i] = bbio->stripes[i+1];
- bbio->raid_map[i] = bbio->raid_map[i+1];
- bbio->stripes[i+1] = s;
- bbio->raid_map[i+1] = l;
-
+ /* Swap if parity is on a smaller index */
+ if (bbio->raid_map[i] > bbio->raid_map[i + 1]) {
+ swap(bbio->stripes[i], bbio->stripes[i + 1]);
+ swap(bbio->raid_map[i], bbio->raid_map[i + 1]);
again = 1;
}
}
@@ -5290,6 +5609,9 @@
atomic_set(&bbio->error, 0);
refcount_set(&bbio->refs, 1);
+ bbio->tgtdev_map = (int *)(bbio->stripes + total_stripes);
+ bbio->raid_map = (u64 *)(bbio->tgtdev_map + real_stripes);
+
return bbio;
}
@@ -5313,12 +5635,13 @@
* replace.
*/
static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
- u64 logical, u64 length,
+ u64 logical, u64 *length_ret,
struct btrfs_bio **bbio_ret)
{
struct extent_map *em;
struct map_lookup *map;
struct btrfs_bio *bbio;
+ u64 length = *length_ret;
u64 offset;
u64 stripe_nr;
u64 stripe_nr_end;
@@ -5339,7 +5662,7 @@
/* discard always return a bbio */
ASSERT(bbio_ret);
- em = get_chunk_map(fs_info, logical, length);
+ em = btrfs_get_chunk_map(fs_info, logical, length);
if (IS_ERR(em))
return PTR_ERR(em);
@@ -5351,7 +5674,8 @@
}
offset = logical - em->start;
- length = min_t(u64, em->len - offset, length);
+ length = min_t(u64, em->start + em->len - logical, length);
+ *length_ret = length;
stripe_len = map->stripe_len;
/*
@@ -5391,7 +5715,7 @@
&remaining_stripes);
div_u64_rem(stripe_nr_end - 1, factor, &last_stripe);
last_stripe *= sub_stripes;
- } else if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
+ } else if (map->type & (BTRFS_BLOCK_GROUP_RAID1_MASK |
BTRFS_BLOCK_GROUP_DUP)) {
num_stripes = map->num_stripes;
} else {
@@ -5635,6 +5959,106 @@
return (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS);
}
+/*
+ * btrfs_get_io_geometry - calculates the geomery of a particular (address, len)
+ * tuple. This information is used to calculate how big a
+ * particular bio can get before it straddles a stripe.
+ *
+ * @fs_info - the filesystem
+ * @logical - address that we want to figure out the geometry of
+ * @len - the length of IO we are going to perform, starting at @logical
+ * @op - type of operation - write or read
+ * @io_geom - pointer used to return values
+ *
+ * Returns < 0 in case a chunk for the given logical address cannot be found,
+ * usually shouldn't happen unless @logical is corrupted, 0 otherwise.
+ */
+int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
+ u64 logical, u64 len, struct btrfs_io_geometry *io_geom)
+{
+ struct extent_map *em;
+ struct map_lookup *map;
+ u64 offset;
+ u64 stripe_offset;
+ u64 stripe_nr;
+ u64 stripe_len;
+ u64 raid56_full_stripe_start = (u64)-1;
+ int data_stripes;
+ int ret = 0;
+
+ ASSERT(op != BTRFS_MAP_DISCARD);
+
+ em = btrfs_get_chunk_map(fs_info, logical, len);
+ if (IS_ERR(em))
+ return PTR_ERR(em);
+
+ map = em->map_lookup;
+ /* Offset of this logical address in the chunk */
+ offset = logical - em->start;
+ /* Len of a stripe in a chunk */
+ stripe_len = map->stripe_len;
+ /* Stripe wher this block falls in */
+ stripe_nr = div64_u64(offset, stripe_len);
+ /* Offset of stripe in the chunk */
+ stripe_offset = stripe_nr * stripe_len;
+ if (offset < stripe_offset) {
+ btrfs_crit(fs_info,
+"stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu",
+ stripe_offset, offset, em->start, logical, stripe_len);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* stripe_offset is the offset of this block in its stripe */
+ stripe_offset = offset - stripe_offset;
+ data_stripes = nr_data_stripes(map);
+
+ if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+ u64 max_len = stripe_len - stripe_offset;
+
+ /*
+ * In case of raid56, we need to know the stripe aligned start
+ */
+ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+ unsigned long full_stripe_len = stripe_len * data_stripes;
+ raid56_full_stripe_start = offset;
+
+ /*
+ * Allow a write of a full stripe, but make sure we
+ * don't allow straddling of stripes
+ */
+ raid56_full_stripe_start = div64_u64(raid56_full_stripe_start,
+ full_stripe_len);
+ raid56_full_stripe_start *= full_stripe_len;
+
+ /*
+ * For writes to RAID[56], allow a full stripeset across
+ * all disks. For other RAID types and for RAID[56]
+ * reads, just allow a single stripe (on a single disk).
+ */
+ if (op == BTRFS_MAP_WRITE) {
+ max_len = stripe_len * data_stripes -
+ (offset - raid56_full_stripe_start);
+ }
+ }
+ len = min_t(u64, em->len - offset, max_len);
+ } else {
+ len = em->len - offset;
+ }
+
+ io_geom->len = len;
+ io_geom->offset = offset;
+ io_geom->stripe_len = stripe_len;
+ io_geom->stripe_nr = stripe_nr;
+ io_geom->stripe_offset = stripe_offset;
+ io_geom->raid56_stripe_offset = raid56_full_stripe_start;
+
+out:
+ /* once for us */
+ free_extent_map(em);
+ return ret;
+}
+
static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
enum btrfs_map_op op,
u64 logical, u64 *length,
@@ -5643,11 +6067,11 @@
{
struct extent_map *em;
struct map_lookup *map;
- u64 offset;
u64 stripe_offset;
u64 stripe_nr;
u64 stripe_len;
u32 stripe_index;
+ int data_stripes;
int i;
int ret = 0;
int num_stripes;
@@ -5660,81 +6084,34 @@
int patch_the_first_stripe_for_dev_replace = 0;
u64 physical_to_patch_in_first_stripe = 0;
u64 raid56_full_stripe_start = (u64)-1;
+ struct btrfs_io_geometry geom;
- if (op == BTRFS_MAP_DISCARD)
- return __btrfs_map_block_for_discard(fs_info, logical,
- *length, bbio_ret);
+ ASSERT(bbio_ret);
+ ASSERT(op != BTRFS_MAP_DISCARD);
- em = get_chunk_map(fs_info, logical, *length);
- if (IS_ERR(em))
- return PTR_ERR(em);
+ ret = btrfs_get_io_geometry(fs_info, op, logical, *length, &geom);
+ if (ret < 0)
+ return ret;
+ em = btrfs_get_chunk_map(fs_info, logical, *length);
+ ASSERT(!IS_ERR(em));
map = em->map_lookup;
- offset = logical - em->start;
- stripe_len = map->stripe_len;
- stripe_nr = offset;
- /*
- * stripe_nr counts the total number of stripes we have to stride
- * to get to this block
- */
- stripe_nr = div64_u64(stripe_nr, stripe_len);
+ *length = geom.len;
+ stripe_len = geom.stripe_len;
+ stripe_nr = geom.stripe_nr;
+ stripe_offset = geom.stripe_offset;
+ raid56_full_stripe_start = geom.raid56_stripe_offset;
+ data_stripes = nr_data_stripes(map);
- stripe_offset = stripe_nr * stripe_len;
- if (offset < stripe_offset) {
- btrfs_crit(fs_info,
- "stripe math has gone wrong, stripe_offset=%llu, offset=%llu, start=%llu, logical=%llu, stripe_len=%llu",
- stripe_offset, offset, em->start, logical,
- stripe_len);
- free_extent_map(em);
- return -EINVAL;
- }
-
- /* stripe_offset is the offset of this block in its stripe*/
- stripe_offset = offset - stripe_offset;
-
- /* if we're here for raid56, we need to know the stripe aligned start */
- if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
- unsigned long full_stripe_len = stripe_len * nr_data_stripes(map);
- raid56_full_stripe_start = offset;
-
- /* allow a write of a full stripe, but make sure we don't
- * allow straddling of stripes
- */
- raid56_full_stripe_start = div64_u64(raid56_full_stripe_start,
- full_stripe_len);
- raid56_full_stripe_start *= full_stripe_len;
- }
-
- if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
- u64 max_len;
- /* For writes to RAID[56], allow a full stripeset across all disks.
- For other RAID types and for RAID[56] reads, just allow a single
- stripe (on a single disk). */
- if ((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
- (op == BTRFS_MAP_WRITE)) {
- max_len = stripe_len * nr_data_stripes(map) -
- (offset - raid56_full_stripe_start);
- } else {
- /* we limit the length of each bio to what fits in a stripe */
- max_len = stripe_len - stripe_offset;
- }
- *length = min_t(u64, em->len - offset, max_len);
- } else {
- *length = em->len - offset;
- }
-
- /* This is for when we're called from btrfs_merge_bio_hook() and all
- it cares about is the length */
- if (!bbio_ret)
- goto out;
-
- btrfs_dev_replace_read_lock(dev_replace);
+ down_read(&dev_replace->rwsem);
dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
+ /*
+ * Hold the semaphore for read during the whole operation, write is
+ * requested at commit time but must wait.
+ */
if (!dev_replace_is_ongoing)
- btrfs_dev_replace_read_unlock(dev_replace);
- else
- btrfs_dev_replace_set_lock_blocking(dev_replace);
+ up_read(&dev_replace->rwsem);
if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 &&
!need_full_stripe(op) && dev_replace->tgtdev != NULL) {
@@ -5757,7 +6134,7 @@
&stripe_index);
if (!need_full_stripe(op))
mirror_num = 1;
- } else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
+ } else if (map->type & BTRFS_BLOCK_GROUP_RAID1_MASK) {
if (need_full_stripe(op))
num_stripes = map->num_stripes;
else if (mirror_num)
@@ -5799,7 +6176,7 @@
if (need_raid_map && (need_full_stripe(op) || mirror_num > 1)) {
/* push stripe_nr back to the start of the full stripe */
stripe_nr = div64_u64(raid56_full_stripe_start,
- stripe_len * nr_data_stripes(map));
+ stripe_len * data_stripes);
/* RAID[56] write or recovery. Return all stripes */
num_stripes = map->num_stripes;
@@ -5815,10 +6192,9 @@
* Mirror #3 is RAID6 Q block.
*/
stripe_nr = div_u64_rem(stripe_nr,
- nr_data_stripes(map), &stripe_index);
+ data_stripes, &stripe_index);
if (mirror_num > 1)
- stripe_index = nr_data_stripes(map) +
- mirror_num - 2;
+ stripe_index = data_stripes + mirror_num - 2;
/* We distribute the parity blocks across stripes */
div_u64_rem(stripe_nr + stripe_index, map->num_stripes,
@@ -5858,8 +6234,13 @@
ret = -ENOMEM;
goto out;
}
- if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL)
- bbio->tgtdev_map = (int *)(bbio->stripes + num_alloc_stripes);
+
+ for (i = 0; i < num_stripes; i++) {
+ bbio->stripes[i].physical = map->stripes[stripe_index].physical +
+ stripe_offset + stripe_nr * map->stripe_len;
+ bbio->stripes[i].dev = map->stripes[stripe_index].dev;
+ stripe_index++;
+ }
/* build raid_map */
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK && need_raid_map &&
@@ -5867,17 +6248,12 @@
u64 tmp;
unsigned rot;
- bbio->raid_map = (u64 *)((void *)bbio->stripes +
- sizeof(struct btrfs_bio_stripe) *
- num_alloc_stripes +
- sizeof(int) * tgtdev_indexes);
-
/* Work out the disk rotation on this stripe-set */
div_u64_rem(stripe_nr, num_stripes, &rot);
/* Fill in the logical address of each stripe */
- tmp = stripe_nr * nr_data_stripes(map);
- for (i = 0; i < nr_data_stripes(map); i++)
+ tmp = stripe_nr * data_stripes;
+ for (i = 0; i < data_stripes; i++)
bbio->raid_map[(i+rot) % num_stripes] =
em->start + (tmp + i) * map->stripe_len;
@@ -5885,24 +6261,12 @@
if (map->type & BTRFS_BLOCK_GROUP_RAID6)
bbio->raid_map[(i+rot+1) % num_stripes] =
RAID6_Q_STRIPE;
- }
-
- for (i = 0; i < num_stripes; i++) {
- bbio->stripes[i].physical =
- map->stripes[stripe_index].physical +
- stripe_offset +
- stripe_nr * map->stripe_len;
- bbio->stripes[i].dev =
- map->stripes[stripe_index].dev;
- stripe_index++;
+ sort_parity_stripes(bbio, num_stripes);
}
if (need_full_stripe(op))
max_errors = btrfs_chunk_max_errors(map);
-
- if (bbio->raid_map)
- sort_parity_stripes(bbio, num_stripes);
if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL &&
need_full_stripe(op)) {
@@ -5929,8 +6293,9 @@
}
out:
if (dev_replace_is_ongoing) {
- btrfs_dev_replace_clear_lock_blocking(dev_replace);
- btrfs_dev_replace_read_unlock(dev_replace);
+ lockdep_assert_held(&dev_replace->rwsem);
+ /* Unlock and let waiting writers proceed */
+ up_read(&dev_replace->rwsem);
}
free_extent_map(em);
return ret;
@@ -5940,6 +6305,10 @@
u64 logical, u64 *length,
struct btrfs_bio **bbio_ret, int mirror_num)
{
+ if (op == BTRFS_MAP_DISCARD)
+ return __btrfs_map_block_for_discard(fs_info, logical,
+ length, bbio_ret);
+
return __btrfs_map_block(fs_info, op, logical, length, bbio_ret,
mirror_num, 0);
}
@@ -5950,75 +6319,6 @@
struct btrfs_bio **bbio_ret)
{
return __btrfs_map_block(fs_info, op, logical, length, bbio_ret, 0, 1);
-}
-
-int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
- u64 physical, u64 **logical, int *naddrs, int *stripe_len)
-{
- struct extent_map *em;
- struct map_lookup *map;
- u64 *buf;
- u64 bytenr;
- u64 length;
- u64 stripe_nr;
- u64 rmap_len;
- int i, j, nr = 0;
-
- em = get_chunk_map(fs_info, chunk_start, 1);
- if (IS_ERR(em))
- return -EIO;
-
- map = em->map_lookup;
- length = em->len;
- rmap_len = map->stripe_len;
-
- if (map->type & BTRFS_BLOCK_GROUP_RAID10)
- length = div_u64(length, map->num_stripes / map->sub_stripes);
- else if (map->type & BTRFS_BLOCK_GROUP_RAID0)
- length = div_u64(length, map->num_stripes);
- else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
- length = div_u64(length, nr_data_stripes(map));
- rmap_len = map->stripe_len * nr_data_stripes(map);
- }
-
- buf = kcalloc(map->num_stripes, sizeof(u64), GFP_NOFS);
- BUG_ON(!buf); /* -ENOMEM */
-
- for (i = 0; i < map->num_stripes; i++) {
- if (map->stripes[i].physical > physical ||
- map->stripes[i].physical + length <= physical)
- continue;
-
- stripe_nr = physical - map->stripes[i].physical;
- stripe_nr = div64_u64(stripe_nr, map->stripe_len);
-
- if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
- stripe_nr = stripe_nr * map->num_stripes + i;
- stripe_nr = div_u64(stripe_nr, map->sub_stripes);
- } else if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
- stripe_nr = stripe_nr * map->num_stripes + i;
- } /* else if RAID[56], multiply by nr_data_stripes().
- * Alternatively, just use rmap_len below instead of
- * map->stripe_len */
-
- bytenr = chunk_start + stripe_nr * rmap_len;
- WARN_ON(nr >= map->num_stripes);
- for (j = 0; j < nr; j++) {
- if (buf[j] == bytenr)
- break;
- }
- if (j == nr) {
- WARN_ON(nr >= map->num_stripes);
- buf[nr++] = bytenr;
- }
- }
-
- *logical = buf;
- *naddrs = nr;
- *stripe_len = rmap_len;
-
- free_extent_map(em);
- return 0;
}
static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio)
@@ -6039,23 +6339,18 @@
atomic_inc(&bbio->error);
if (bio->bi_status == BLK_STS_IOERR ||
bio->bi_status == BLK_STS_TARGET) {
- unsigned int stripe_index =
- btrfs_io_bio(bio)->stripe_index;
- struct btrfs_device *dev;
+ struct btrfs_device *dev = btrfs_io_bio(bio)->device;
- BUG_ON(stripe_index >= bbio->num_stripes);
- dev = bbio->stripes[stripe_index].dev;
- if (dev->bdev) {
- if (bio_op(bio) == REQ_OP_WRITE)
- btrfs_dev_stat_inc_and_print(dev,
+ ASSERT(dev->bdev);
+ if (bio_op(bio) == REQ_OP_WRITE)
+ btrfs_dev_stat_inc_and_print(dev,
BTRFS_DEV_STAT_WRITE_ERRS);
- else if (!(bio->bi_opf & REQ_RAHEAD))
- btrfs_dev_stat_inc_and_print(dev,
+ else if (!(bio->bi_opf & REQ_RAHEAD))
+ btrfs_dev_stat_inc_and_print(dev,
BTRFS_DEV_STAT_READ_ERRS);
- if (bio->bi_opf & REQ_PREFLUSH)
- btrfs_dev_stat_inc_and_print(dev,
+ if (bio->bi_opf & REQ_PREFLUSH)
+ btrfs_dev_stat_inc_and_print(dev,
BTRFS_DEV_STAT_FLUSH_ERRS);
- }
}
}
@@ -6090,73 +6385,25 @@
}
}
-/*
- * see run_scheduled_bios for a description of why bios are collected for
- * async submit.
- *
- * This will add one bio to the pending list for a device and make sure
- * the work struct is scheduled.
- */
-static noinline void btrfs_schedule_bio(struct btrfs_device *device,
- struct bio *bio)
-{
- struct btrfs_fs_info *fs_info = device->fs_info;
- int should_queue = 1;
- struct btrfs_pending_bios *pending_bios;
-
- /* don't bother with additional async steps for reads, right now */
- if (bio_op(bio) == REQ_OP_READ) {
- btrfsic_submit_bio(bio);
- return;
- }
-
- WARN_ON(bio->bi_next);
- bio->bi_next = NULL;
-
- spin_lock(&device->io_lock);
- if (op_is_sync(bio->bi_opf))
- pending_bios = &device->pending_sync_bios;
- else
- pending_bios = &device->pending_bios;
-
- if (pending_bios->tail)
- pending_bios->tail->bi_next = bio;
-
- pending_bios->tail = bio;
- if (!pending_bios->head)
- pending_bios->head = bio;
- if (device->running_pending)
- should_queue = 0;
-
- spin_unlock(&device->io_lock);
-
- if (should_queue)
- btrfs_queue_work(fs_info->submit_workers, &device->work);
-}
-
static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
- u64 physical, int dev_nr, int async)
+ u64 physical, struct btrfs_device *dev)
{
- struct btrfs_device *dev = bbio->stripes[dev_nr].dev;
struct btrfs_fs_info *fs_info = bbio->fs_info;
bio->bi_private = bbio;
- btrfs_io_bio(bio)->stripe_index = dev_nr;
+ btrfs_io_bio(bio)->device = dev;
bio->bi_end_io = btrfs_end_bio;
bio->bi_iter.bi_sector = physical >> 9;
btrfs_debug_in_rcu(fs_info,
"btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
bio_op(bio), bio->bi_opf, (u64)bio->bi_iter.bi_sector,
- (u_long)dev->bdev->bd_dev, rcu_str_deref(dev->name), dev->devid,
- bio->bi_iter.bi_size);
+ (unsigned long)dev->bdev->bd_dev, rcu_str_deref(dev->name),
+ dev->devid, bio->bi_iter.bi_size);
bio_set_dev(bio, dev->bdev);
btrfs_bio_counter_inc_noblocked(fs_info);
- if (async)
- btrfs_schedule_bio(dev, bio);
- else
- btrfsic_submit_bio(bio);
+ btrfsic_submit_bio(bio);
}
static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
@@ -6177,7 +6424,7 @@
}
blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
- int mirror_num, int async_submit)
+ int mirror_num)
{
struct btrfs_device *dev;
struct bio *first_bio = bio;
@@ -6245,8 +6492,7 @@
else
bio = first_bio;
- submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical,
- dev_nr, async_submit);
+ submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical, dev);
}
btrfs_bio_counter_dec(fs_info);
return BLK_STS_OK;
@@ -6262,15 +6508,25 @@
* If @seed is true, traverse through the seed devices.
*/
struct btrfs_device *btrfs_find_device(struct btrfs_fs_devices *fs_devices,
- u64 devid, u8 *uuid, u8 *fsid,
- bool seed)
+ u64 devid, u8 *uuid, u8 *fsid,
+ bool seed)
{
struct btrfs_device *device;
+ struct btrfs_fs_devices *seed_devs;
- while (fs_devices) {
+ if (!fsid || !memcmp(fs_devices->metadata_uuid, fsid, BTRFS_FSID_SIZE)) {
+ list_for_each_entry(device, &fs_devices->devices, dev_list) {
+ if (device->devid == devid &&
+ (!uuid || memcmp(device->uuid, uuid,
+ BTRFS_UUID_SIZE) == 0))
+ return device;
+ }
+ }
+
+ list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) {
if (!fsid ||
- !memcmp(fs_devices->fsid, fsid, BTRFS_FSID_SIZE)) {
- list_for_each_entry(device, &fs_devices->devices,
+ !memcmp(seed_devs->metadata_uuid, fsid, BTRFS_FSID_SIZE)) {
+ list_for_each_entry(device, &seed_devs->devices,
dev_list) {
if (device->devid == devid &&
(!uuid || memcmp(device->uuid, uuid,
@@ -6278,11 +6534,8 @@
return device;
}
}
- if (seed)
- fs_devices = fs_devices->seed;
- else
- return NULL;
}
+
return NULL;
}
@@ -6337,7 +6590,7 @@
if (WARN_ON(!devid && !fs_info))
return ERR_PTR(-EINVAL);
- dev = __alloc_device();
+ dev = __alloc_device(fs_info);
if (IS_ERR(dev))
return dev;
@@ -6359,9 +6612,6 @@
else
generate_random_uuid(dev->uuid);
- btrfs_init_work(&dev->work, btrfs_submit_helper,
- pending_bios_fn, NULL, NULL);
-
return dev;
}
@@ -6376,11 +6626,26 @@
devid, uuid);
}
-static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
- struct extent_buffer *leaf,
+static u64 calc_stripe_length(u64 type, u64 chunk_len, int num_stripes)
+{
+ int index = btrfs_bg_flags_to_raid_index(type);
+ int ncopies = btrfs_raid_array[index].ncopies;
+ const int nparity = btrfs_raid_array[index].nparity;
+ int data_stripes;
+
+ if (nparity)
+ data_stripes = num_stripes - nparity;
+ else
+ data_stripes = num_stripes / ncopies;
+
+ return div_u64(chunk_len, data_stripes);
+}
+
+static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
struct btrfs_chunk *chunk)
{
- struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
+ struct btrfs_fs_info *fs_info = leaf->fs_info;
+ struct extent_map_tree *map_tree = &fs_info->mapping_tree;
struct map_lookup *map;
struct extent_map *em;
u64 logical;
@@ -6400,14 +6665,14 @@
* as chunk item in tree block is already verified by tree-checker.
*/
if (leaf->start == BTRFS_SUPER_INFO_OFFSET) {
- ret = btrfs_check_chunk_valid(fs_info, leaf, chunk, logical);
+ ret = btrfs_check_chunk_valid(leaf, chunk, logical);
if (ret)
return ret;
}
- read_lock(&map_tree->map_tree.lock);
- em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);
- read_unlock(&map_tree->map_tree.lock);
+ read_lock(&map_tree->lock);
+ em = lookup_extent_mapping(map_tree, logical, 1);
+ read_unlock(&map_tree->lock);
/* already mapped? */
if (em && em->start <= logical && em->start + em->len > logical) {
@@ -6441,6 +6706,8 @@
map->type = btrfs_chunk_type(leaf, chunk);
map->sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
map->verified_stripes = 0;
+ em->orig_block_len = calc_stripe_length(map->type, em->len,
+ map->num_stripes);
for (i = 0; i < num_stripes; i++) {
map->stripes[i].physical =
btrfs_stripe_offset_nr(leaf, chunk, i);
@@ -6449,7 +6716,7 @@
btrfs_stripe_dev_uuid_nr(chunk, i),
BTRFS_UUID_SIZE);
map->stripes[i].dev = btrfs_find_device(fs_info->fs_devices,
- devid, uuid, NULL, true);
+ devid, uuid, NULL, true);
if (!map->stripes[i].dev &&
!btrfs_test_opt(fs_info, DEGRADED)) {
free_extent_map(em);
@@ -6474,9 +6741,9 @@
}
- write_lock(&map_tree->map_tree.lock);
- ret = add_extent_mapping(&map_tree->map_tree, em, 0);
- write_unlock(&map_tree->map_tree.lock);
+ write_lock(&map_tree->lock);
+ ret = add_extent_mapping(map_tree, em, 0);
+ write_unlock(&map_tree->lock);
if (ret < 0) {
btrfs_err(fs_info,
"failed to add chunk map, start=%llu len=%llu: %d",
@@ -6519,28 +6786,30 @@
lockdep_assert_held(&uuid_mutex);
ASSERT(fsid);
- fs_devices = fs_info->fs_devices->seed;
- while (fs_devices) {
+ /* This will match only for multi-device seed fs */
+ list_for_each_entry(fs_devices, &fs_info->fs_devices->seed_list, seed_list)
if (!memcmp(fs_devices->fsid, fsid, BTRFS_FSID_SIZE))
return fs_devices;
- fs_devices = fs_devices->seed;
- }
- fs_devices = find_fsid(fsid);
+ fs_devices = find_fsid(fsid, NULL);
if (!fs_devices) {
if (!btrfs_test_opt(fs_info, DEGRADED))
return ERR_PTR(-ENOENT);
- fs_devices = alloc_fs_devices(fsid);
+ fs_devices = alloc_fs_devices(fsid, NULL);
if (IS_ERR(fs_devices))
return fs_devices;
- fs_devices->seeding = 1;
+ fs_devices->seeding = true;
fs_devices->opened = 1;
return fs_devices;
}
+ /*
+ * Upon first call for a seed fs fsid, just create a private copy of the
+ * respective fs_devices and anchor it at fs_info->fs_devices->seed_list
+ */
fs_devices = clone_fs_devices(fs_devices);
if (IS_ERR(fs_devices))
return fs_devices;
@@ -6548,27 +6817,24 @@
ret = open_fs_devices(fs_devices, FMODE_READ, fs_info->bdev_holder);
if (ret) {
free_fs_devices(fs_devices);
- fs_devices = ERR_PTR(ret);
- goto out;
+ return ERR_PTR(ret);
}
if (!fs_devices->seeding) {
close_fs_devices(fs_devices);
free_fs_devices(fs_devices);
- fs_devices = ERR_PTR(-EINVAL);
- goto out;
+ return ERR_PTR(-EINVAL);
}
- fs_devices->seed = fs_info->fs_devices->seed;
- fs_info->fs_devices->seed = fs_devices;
-out:
+ list_add(&fs_devices->seed_list, &fs_info->fs_devices->seed_list);
+
return fs_devices;
}
-static int read_one_dev(struct btrfs_fs_info *fs_info,
- struct extent_buffer *leaf,
+static int read_one_dev(struct extent_buffer *leaf,
struct btrfs_dev_item *dev_item)
{
+ struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
struct btrfs_device *device;
u64 devid;
@@ -6582,7 +6848,7 @@
read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item),
BTRFS_FSID_SIZE);
- if (memcmp(fs_uuid, fs_info->fsid, BTRFS_FSID_SIZE)) {
+ if (memcmp(fs_uuid, fs_devices->metadata_uuid, BTRFS_FSID_SIZE)) {
fs_devices = open_seed_devices(fs_info, fs_uuid);
if (IS_ERR(fs_devices))
return PTR_ERR(fs_devices);
@@ -6725,48 +6991,49 @@
sb_array_offset += len;
cur_offset += len;
- if (key.type == BTRFS_CHUNK_ITEM_KEY) {
- chunk = (struct btrfs_chunk *)sb_array_offset;
- /*
- * At least one btrfs_chunk with one stripe must be
- * present, exact stripe count check comes afterwards
- */
- len = btrfs_chunk_item_size(1);
- if (cur_offset + len > array_size)
- goto out_short_read;
-
- num_stripes = btrfs_chunk_num_stripes(sb, chunk);
- if (!num_stripes) {
- btrfs_err(fs_info,
- "invalid number of stripes %u in sys_array at offset %u",
- num_stripes, cur_offset);
- ret = -EIO;
- break;
- }
-
- type = btrfs_chunk_type(sb, chunk);
- if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
- btrfs_err(fs_info,
- "invalid chunk type %llu in sys_array at offset %u",
- type, cur_offset);
- ret = -EIO;
- break;
- }
-
- len = btrfs_chunk_item_size(num_stripes);
- if (cur_offset + len > array_size)
- goto out_short_read;
-
- ret = read_one_chunk(fs_info, &key, sb, chunk);
- if (ret)
- break;
- } else {
+ if (key.type != BTRFS_CHUNK_ITEM_KEY) {
btrfs_err(fs_info,
"unexpected item type %u in sys_array at offset %u",
(u32)key.type, cur_offset);
ret = -EIO;
break;
}
+
+ chunk = (struct btrfs_chunk *)sb_array_offset;
+ /*
+ * At least one btrfs_chunk with one stripe must be present,
+ * exact stripe count check comes afterwards
+ */
+ len = btrfs_chunk_item_size(1);
+ if (cur_offset + len > array_size)
+ goto out_short_read;
+
+ num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+ if (!num_stripes) {
+ btrfs_err(fs_info,
+ "invalid number of stripes %u in sys_array at offset %u",
+ num_stripes, cur_offset);
+ ret = -EIO;
+ break;
+ }
+
+ type = btrfs_chunk_type(sb, chunk);
+ if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
+ btrfs_err(fs_info,
+ "invalid chunk type %llu in sys_array at offset %u",
+ type, cur_offset);
+ ret = -EIO;
+ break;
+ }
+
+ len = btrfs_chunk_item_size(num_stripes);
+ if (cur_offset + len > array_size)
+ goto out_short_read;
+
+ ret = read_one_chunk(&key, sb, chunk);
+ if (ret)
+ break;
+
array_ptr += len;
sb_array_offset += len;
cur_offset += len;
@@ -6794,14 +7061,14 @@
bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
struct btrfs_device *failing_dev)
{
- struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
+ struct extent_map_tree *map_tree = &fs_info->mapping_tree;
struct extent_map *em;
u64 next_start = 0;
bool ret = true;
- read_lock(&map_tree->map_tree.lock);
- em = lookup_extent_mapping(&map_tree->map_tree, 0, (u64)-1);
- read_unlock(&map_tree->map_tree.lock);
+ read_lock(&map_tree->lock);
+ em = lookup_extent_mapping(map_tree, 0, (u64)-1);
+ read_unlock(&map_tree->lock);
/* No chunk at all? Return false anyway */
if (!em) {
ret = false;
@@ -6830,7 +7097,7 @@
if (missing > max_tolerated) {
if (!failing_dev)
btrfs_warn(fs_info,
- "chunk %llu missing %d devices, max tolerance is %d for writeable mount",
+ "chunk %llu missing %d devices, max tolerance is %d for writable mount",
em->start, missing, max_tolerated);
free_extent_map(em);
ret = false;
@@ -6839,13 +7106,26 @@
next_start = extent_map_end(em);
free_extent_map(em);
- read_lock(&map_tree->map_tree.lock);
- em = lookup_extent_mapping(&map_tree->map_tree, next_start,
+ read_lock(&map_tree->lock);
+ em = lookup_extent_mapping(map_tree, next_start,
(u64)(-1) - next_start);
- read_unlock(&map_tree->map_tree.lock);
+ read_unlock(&map_tree->lock);
}
out:
return ret;
+}
+
+static void readahead_tree_node_children(struct extent_buffer *node)
+{
+ int i;
+ const int nr_items = btrfs_header_nritems(node);
+
+ for (i = 0; i < nr_items; i++) {
+ u64 start;
+
+ start = btrfs_node_blockptr(node, i);
+ readahead_tree_block(node->fs_info, start);
+ }
}
int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
@@ -6858,6 +7138,7 @@
int ret;
int slot;
u64 total_dev = 0;
+ u64 last_ra_node = 0;
path = btrfs_alloc_path();
if (!path)
@@ -6868,7 +7149,6 @@
* otherwise we don't need it.
*/
mutex_lock(&uuid_mutex);
- mutex_lock(&fs_info->chunk_mutex);
/*
* It is possible for mount and umount to race in such a way that
@@ -6891,6 +7171,8 @@
if (ret < 0)
goto error;
while (1) {
+ struct extent_buffer *node;
+
leaf = path->nodes[0];
slot = path->slots[0];
if (slot >= btrfs_header_nritems(leaf)) {
@@ -6901,19 +7183,32 @@
goto error;
break;
}
+ /*
+ * The nodes on level 1 are not locked but we don't need to do
+ * that during mount time as nothing else can access the tree
+ */
+ node = path->nodes[1];
+ if (node) {
+ if (last_ra_node != node->start) {
+ readahead_tree_node_children(node);
+ last_ra_node = node->start;
+ }
+ }
btrfs_item_key_to_cpu(leaf, &found_key, slot);
if (found_key.type == BTRFS_DEV_ITEM_KEY) {
struct btrfs_dev_item *dev_item;
dev_item = btrfs_item_ptr(leaf, slot,
struct btrfs_dev_item);
- ret = read_one_dev(fs_info, leaf, dev_item);
+ ret = read_one_dev(leaf, dev_item);
if (ret)
goto error;
total_dev++;
} else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) {
struct btrfs_chunk *chunk;
chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
- ret = read_one_chunk(fs_info, &found_key, leaf, chunk);
+ mutex_lock(&fs_info->chunk_mutex);
+ ret = read_one_chunk(&found_key, leaf, chunk);
+ mutex_unlock(&fs_info->chunk_mutex);
if (ret)
goto error;
}
@@ -6925,12 +7220,12 @@
* do another round of validation checks.
*/
if (total_dev != fs_info->fs_devices->total_devices) {
- btrfs_err(fs_info,
- "super_num_devices %llu mismatch with num_devices %llu found here",
+ btrfs_warn(fs_info,
+"super block num_devices %llu mismatch with DEV_ITEM count %llu, will be repaired on next transaction commit",
btrfs_super_num_devices(fs_info->super_copy),
total_dev);
- ret = -EINVAL;
- goto error;
+ fs_info->fs_devices->total_devices = total_dev;
+ btrfs_set_super_num_devices(fs_info->super_copy, total_dev);
}
if (btrfs_super_total_bytes(fs_info->super_copy) <
fs_info->fs_devices->total_rw_bytes) {
@@ -6943,7 +7238,6 @@
}
ret = 0;
error:
- mutex_unlock(&fs_info->chunk_mutex);
mutex_unlock(&uuid_mutex);
btrfs_free_path(path);
@@ -6952,86 +7246,117 @@
void btrfs_init_devices_late(struct btrfs_fs_info *fs_info)
{
- struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+ struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs;
struct btrfs_device *device;
- while (fs_devices) {
- mutex_lock(&fs_devices->device_list_mutex);
- list_for_each_entry(device, &fs_devices->devices, dev_list)
- device->fs_info = fs_info;
- mutex_unlock(&fs_devices->device_list_mutex);
+ fs_devices->fs_info = fs_info;
- fs_devices = fs_devices->seed;
+ mutex_lock(&fs_devices->device_list_mutex);
+ list_for_each_entry(device, &fs_devices->devices, dev_list)
+ device->fs_info = fs_info;
+
+ list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) {
+ list_for_each_entry(device, &seed_devs->devices, dev_list)
+ device->fs_info = fs_info;
+
+ seed_devs->fs_info = fs_info;
}
+ mutex_unlock(&fs_devices->device_list_mutex);
}
-static void __btrfs_reset_dev_stats(struct btrfs_device *dev)
+static u64 btrfs_dev_stats_value(const struct extent_buffer *eb,
+ const struct btrfs_dev_stats_item *ptr,
+ int index)
{
- int i;
+ u64 val;
- for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++)
- btrfs_dev_stat_reset(dev, i);
+ read_extent_buffer(eb, &val,
+ offsetof(struct btrfs_dev_stats_item, values) +
+ ((unsigned long)ptr) + (index * sizeof(u64)),
+ sizeof(val));
+ return val;
+}
+
+static void btrfs_set_dev_stats_value(struct extent_buffer *eb,
+ struct btrfs_dev_stats_item *ptr,
+ int index, u64 val)
+{
+ write_extent_buffer(eb, &val,
+ offsetof(struct btrfs_dev_stats_item, values) +
+ ((unsigned long)ptr) + (index * sizeof(u64)),
+ sizeof(val));
+}
+
+static int btrfs_device_init_dev_stats(struct btrfs_device *device,
+ struct btrfs_path *path)
+{
+ struct btrfs_dev_stats_item *ptr;
+ struct extent_buffer *eb;
+ struct btrfs_key key;
+ int item_size;
+ int i, ret, slot;
+
+ key.objectid = BTRFS_DEV_STATS_OBJECTID;
+ key.type = BTRFS_PERSISTENT_ITEM_KEY;
+ key.offset = device->devid;
+ ret = btrfs_search_slot(NULL, device->fs_info->dev_root, &key, path, 0, 0);
+ if (ret) {
+ for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++)
+ btrfs_dev_stat_set(device, i, 0);
+ device->dev_stats_valid = 1;
+ btrfs_release_path(path);
+ return ret < 0 ? ret : 0;
+ }
+ slot = path->slots[0];
+ eb = path->nodes[0];
+ item_size = btrfs_item_size_nr(eb, slot);
+
+ ptr = btrfs_item_ptr(eb, slot, struct btrfs_dev_stats_item);
+
+ for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) {
+ if (item_size >= (1 + i) * sizeof(__le64))
+ btrfs_dev_stat_set(device, i,
+ btrfs_dev_stats_value(eb, ptr, i));
+ else
+ btrfs_dev_stat_set(device, i, 0);
+ }
+
+ device->dev_stats_valid = 1;
+ btrfs_dev_stat_print_on_load(device);
+ btrfs_release_path(path);
+
+ return 0;
}
int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info)
{
- struct btrfs_key key;
- struct btrfs_key found_key;
- struct btrfs_root *dev_root = fs_info->dev_root;
- struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
- struct extent_buffer *eb;
- int slot;
- int ret = 0;
+ struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs;
struct btrfs_device *device;
struct btrfs_path *path = NULL;
- int i;
+ int ret = 0;
path = btrfs_alloc_path();
- if (!path) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!path)
+ return -ENOMEM;
mutex_lock(&fs_devices->device_list_mutex);
list_for_each_entry(device, &fs_devices->devices, dev_list) {
- int item_size;
- struct btrfs_dev_stats_item *ptr;
-
- key.objectid = BTRFS_DEV_STATS_OBJECTID;
- key.type = BTRFS_PERSISTENT_ITEM_KEY;
- key.offset = device->devid;
- ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
- if (ret) {
- __btrfs_reset_dev_stats(device);
- device->dev_stats_valid = 1;
- btrfs_release_path(path);
- continue;
- }
- slot = path->slots[0];
- eb = path->nodes[0];
- btrfs_item_key_to_cpu(eb, &found_key, slot);
- item_size = btrfs_item_size_nr(eb, slot);
-
- ptr = btrfs_item_ptr(eb, slot,
- struct btrfs_dev_stats_item);
-
- for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) {
- if (item_size >= (1 + i) * sizeof(__le64))
- btrfs_dev_stat_set(device, i,
- btrfs_dev_stats_value(eb, ptr, i));
- else
- btrfs_dev_stat_reset(device, i);
- }
-
- device->dev_stats_valid = 1;
- btrfs_dev_stat_print_on_load(device);
- btrfs_release_path(path);
+ ret = btrfs_device_init_dev_stats(device, path);
+ if (ret)
+ goto out;
}
+ list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) {
+ list_for_each_entry(device, &seed_devs->devices, dev_list) {
+ ret = btrfs_device_init_dev_stats(device, path);
+ if (ret)
+ goto out;
+ }
+ }
+out:
mutex_unlock(&fs_devices->device_list_mutex);
-out:
btrfs_free_path(path);
- return ret < 0 ? ret : 0;
+ return ret;
}
static int update_dev_stat_item(struct btrfs_trans_handle *trans,
@@ -7102,9 +7427,9 @@
/*
* called from commit_transaction. Writes all changed device stats to disk.
*/
-int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info)
+int btrfs_run_dev_stats(struct btrfs_trans_handle *trans)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
struct btrfs_device *device;
int stats_cnt;
@@ -7187,8 +7512,8 @@
int i;
mutex_lock(&fs_devices->device_list_mutex);
- dev = btrfs_find_device(fs_info->fs_devices, stats->devid,
- NULL, NULL, true);
+ dev = btrfs_find_device(fs_info->fs_devices, stats->devid, NULL, NULL,
+ true);
mutex_unlock(&fs_devices->device_list_mutex);
if (!dev) {
@@ -7203,7 +7528,7 @@
stats->values[i] =
btrfs_dev_stat_read_and_reset(dev, i);
else
- btrfs_dev_stat_reset(dev, i);
+ btrfs_dev_stat_set(dev, i, 0);
}
btrfs_info(fs_info, "device stats zeroed by %s (%d)",
current->comm, task_pid_nr(current));
@@ -7217,101 +7542,35 @@
return 0;
}
-void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path)
-{
- struct buffer_head *bh;
- struct btrfs_super_block *disk_super;
- int copy_num;
-
- if (!bdev)
- return;
-
- for (copy_num = 0; copy_num < BTRFS_SUPER_MIRROR_MAX;
- copy_num++) {
-
- if (btrfs_read_dev_one_super(bdev, copy_num, &bh))
- continue;
-
- disk_super = (struct btrfs_super_block *)bh->b_data;
-
- memset(&disk_super->magic, 0, sizeof(disk_super->magic));
- set_buffer_dirty(bh);
- sync_dirty_buffer(bh);
- brelse(bh);
- }
-
- /* Notify udev that device has changed */
- btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
-
- /* Update ctime/mtime for device path for libblkid */
- update_dev_time(device_path);
-}
-
/*
- * Update the size of all devices, which is used for writing out the
- * super blocks.
+ * Update the size and bytes used for each device where it changed. This is
+ * delayed since we would otherwise get errors while writing out the
+ * superblocks.
+ *
+ * Must be invoked during transaction commit.
*/
-void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info)
+void btrfs_commit_device_sizes(struct btrfs_transaction *trans)
{
- struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
struct btrfs_device *curr, *next;
- if (list_empty(&fs_devices->resized_devices))
+ ASSERT(trans->state == TRANS_STATE_COMMIT_DOING);
+
+ if (list_empty(&trans->dev_update_list))
return;
- mutex_lock(&fs_devices->device_list_mutex);
- mutex_lock(&fs_info->chunk_mutex);
- list_for_each_entry_safe(curr, next, &fs_devices->resized_devices,
- resized_list) {
- list_del_init(&curr->resized_list);
+ /*
+ * We don't need the device_list_mutex here. This list is owned by the
+ * transaction and the transaction must complete before the device is
+ * released.
+ */
+ mutex_lock(&trans->fs_info->chunk_mutex);
+ list_for_each_entry_safe(curr, next, &trans->dev_update_list,
+ post_commit_list) {
+ list_del_init(&curr->post_commit_list);
curr->commit_total_bytes = curr->disk_total_bytes;
+ curr->commit_bytes_used = curr->bytes_used;
}
- mutex_unlock(&fs_info->chunk_mutex);
- mutex_unlock(&fs_devices->device_list_mutex);
-}
-
-/* Must be invoked during the transaction commit */
-void btrfs_update_commit_device_bytes_used(struct btrfs_transaction *trans)
-{
- struct btrfs_fs_info *fs_info = trans->fs_info;
- struct extent_map *em;
- struct map_lookup *map;
- struct btrfs_device *dev;
- int i;
-
- if (list_empty(&trans->pending_chunks))
- return;
-
- /* In order to kick the device replace finish process */
- mutex_lock(&fs_info->chunk_mutex);
- list_for_each_entry(em, &trans->pending_chunks, list) {
- map = em->map_lookup;
-
- for (i = 0; i < map->num_stripes; i++) {
- dev = map->stripes[i].dev;
- dev->commit_bytes_used = dev->bytes_used;
- dev->has_pending_chunks = false;
- }
- }
- mutex_unlock(&fs_info->chunk_mutex);
-}
-
-void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info)
-{
- struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
- while (fs_devices) {
- fs_devices->fs_info = fs_info;
- fs_devices = fs_devices->seed;
- }
-}
-
-void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info)
-{
- struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
- while (fs_devices) {
- fs_devices->fs_info = NULL;
- fs_devices = fs_devices->seed;
- }
+ mutex_unlock(&trans->fs_info->chunk_mutex);
}
/*
@@ -7319,38 +7578,18 @@
*/
int btrfs_bg_type_to_factor(u64 flags)
{
- if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10))
- return 2;
- return 1;
+ const int index = btrfs_bg_flags_to_raid_index(flags);
+
+ return btrfs_raid_array[index].ncopies;
}
-static u64 calc_stripe_length(u64 type, u64 chunk_len, int num_stripes)
-{
- int index = btrfs_bg_flags_to_raid_index(type);
- int ncopies = btrfs_raid_array[index].ncopies;
- int data_stripes;
-
- switch (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
- case BTRFS_BLOCK_GROUP_RAID5:
- data_stripes = num_stripes - 1;
- break;
- case BTRFS_BLOCK_GROUP_RAID6:
- data_stripes = num_stripes - 2;
- break;
- default:
- data_stripes = num_stripes / ncopies;
- break;
- }
- return div_u64(chunk_len, data_stripes);
-}
static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
u64 chunk_offset, u64 devid,
u64 physical_offset, u64 physical_len)
{
- struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+ struct extent_map_tree *em_tree = &fs_info->mapping_tree;
struct extent_map *em;
struct map_lookup *map;
struct btrfs_device *dev;
@@ -7414,8 +7653,11 @@
/* It's possible this device is a dummy for seed device */
if (dev->disk_total_bytes == 0) {
- dev = btrfs_find_device(fs_info->fs_devices->seed, devid,
- NULL, NULL, false);
+ struct btrfs_fs_devices *devs;
+
+ devs = list_first_entry(&fs_info->fs_devices->seed_list,
+ struct btrfs_fs_devices, seed_list);
+ dev = btrfs_find_device(devs, devid, NULL, NULL, false);
if (!dev) {
btrfs_err(fs_info, "failed to find seed devid %llu",
devid);
@@ -7439,13 +7681,13 @@
static int verify_chunk_dev_extent_mapping(struct btrfs_fs_info *fs_info)
{
- struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+ struct extent_map_tree *em_tree = &fs_info->mapping_tree;
struct extent_map *em;
struct rb_node *node;
int ret = 0;
read_lock(&em_tree->lock);
- for (node = rb_first(&em_tree->map); node; node = rb_next(node)) {
+ for (node = rb_first_cached(&em_tree->map); node; node = rb_next(node)) {
em = rb_entry(node, struct extent_map, rb_node);
if (em->map_lookup->num_stripes !=
em->map_lookup->verified_stripes) {
@@ -7551,3 +7793,27 @@
btrfs_free_path(path);
return ret;
}
+
+/*
+ * Check whether the given block group or device is pinned by any inode being
+ * used as a swapfile.
+ */
+bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr)
+{
+ struct btrfs_swapfile_pin *sp;
+ struct rb_node *node;
+
+ spin_lock(&fs_info->swapfile_pins_lock);
+ node = fs_info->swapfile_pins.rb_node;
+ while (node) {
+ sp = rb_entry(node, struct btrfs_swapfile_pin, node);
+ if (ptr < sp->ptr)
+ node = node->rb_left;
+ else if (ptr > sp->ptr)
+ node = node->rb_right;
+ else
+ break;
+ }
+ spin_unlock(&fs_info->swapfile_pins_lock);
+ return node != NULL;
+}
--
Gitblit v1.6.2