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/transaction.c | 661 ++++++++++++++++++++++++++++++++----------------------
1 files changed, 392 insertions(+), 269 deletions(-)
diff --git a/kernel/fs/btrfs/transaction.c b/kernel/fs/btrfs/transaction.c
index 0495351..8daa9e4 100644
--- a/kernel/fs/btrfs/transaction.c
+++ b/kernel/fs/btrfs/transaction.c
@@ -10,6 +10,7 @@
#include <linux/pagemap.h>
#include <linux/blkdev.h>
#include <linux/uuid.h>
+#include "misc.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
@@ -19,12 +20,84 @@
#include "volumes.h"
#include "dev-replace.h"
#include "qgroup.h"
+#include "block-group.h"
+#include "space-info.h"
#define BTRFS_ROOT_TRANS_TAG 0
+/*
+ * Transaction states and transitions
+ *
+ * No running transaction (fs tree blocks are not modified)
+ * |
+ * | To next stage:
+ * | Call start_transaction() variants. Except btrfs_join_transaction_nostart().
+ * V
+ * Transaction N [[TRANS_STATE_RUNNING]]
+ * |
+ * | New trans handles can be attached to transaction N by calling all
+ * | start_transaction() variants.
+ * |
+ * | To next stage:
+ * | Call btrfs_commit_transaction() on any trans handle attached to
+ * | transaction N
+ * V
+ * Transaction N [[TRANS_STATE_COMMIT_START]]
+ * |
+ * | Will wait for previous running transaction to completely finish if there
+ * | is one
+ * |
+ * | Then one of the following happes:
+ * | - Wait for all other trans handle holders to release.
+ * | The btrfs_commit_transaction() caller will do the commit work.
+ * | - Wait for current transaction to be committed by others.
+ * | Other btrfs_commit_transaction() caller will do the commit work.
+ * |
+ * | At this stage, only btrfs_join_transaction*() variants can attach
+ * | to this running transaction.
+ * | All other variants will wait for current one to finish and attach to
+ * | transaction N+1.
+ * |
+ * | To next stage:
+ * | Caller is chosen to commit transaction N, and all other trans handle
+ * | haven been released.
+ * V
+ * Transaction N [[TRANS_STATE_COMMIT_DOING]]
+ * |
+ * | The heavy lifting transaction work is started.
+ * | From running delayed refs (modifying extent tree) to creating pending
+ * | snapshots, running qgroups.
+ * | In short, modify supporting trees to reflect modifications of subvolume
+ * | trees.
+ * |
+ * | At this stage, all start_transaction() calls will wait for this
+ * | transaction to finish and attach to transaction N+1.
+ * |
+ * | To next stage:
+ * | Until all supporting trees are updated.
+ * V
+ * Transaction N [[TRANS_STATE_UNBLOCKED]]
+ * | Transaction N+1
+ * | All needed trees are modified, thus we only [[TRANS_STATE_RUNNING]]
+ * | need to write them back to disk and update |
+ * | super blocks. |
+ * | |
+ * | At this stage, new transaction is allowed to |
+ * | start. |
+ * | All new start_transaction() calls will be |
+ * | attached to transid N+1. |
+ * | |
+ * | To next stage: |
+ * | Until all tree blocks are super blocks are |
+ * | written to block devices |
+ * V |
+ * Transaction N [[TRANS_STATE_COMPLETED]] V
+ * All tree blocks and super blocks are written. Transaction N+1
+ * This transaction is finished and all its [[TRANS_STATE_COMMIT_START]]
+ * data structures will be cleaned up. | Life goes on
+ */
static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = {
[TRANS_STATE_RUNNING] = 0U,
- [TRANS_STATE_BLOCKED] = __TRANS_START,
[TRANS_STATE_COMMIT_START] = (__TRANS_START | __TRANS_ATTACH),
[TRANS_STATE_COMMIT_DOING] = (__TRANS_START |
__TRANS_ATTACH |
@@ -47,19 +120,14 @@
WARN_ON(refcount_read(&transaction->use_count) == 0);
if (refcount_dec_and_test(&transaction->use_count)) {
BUG_ON(!list_empty(&transaction->list));
- WARN_ON(!RB_EMPTY_ROOT(&transaction->delayed_refs.href_root));
+ WARN_ON(!RB_EMPTY_ROOT(
+ &transaction->delayed_refs.href_root.rb_root));
+ WARN_ON(!RB_EMPTY_ROOT(
+ &transaction->delayed_refs.dirty_extent_root));
if (transaction->delayed_refs.pending_csums)
btrfs_err(transaction->fs_info,
"pending csums is %llu",
transaction->delayed_refs.pending_csums);
- while (!list_empty(&transaction->pending_chunks)) {
- struct extent_map *em;
-
- em = list_first_entry(&transaction->pending_chunks,
- struct extent_map, list);
- list_del_init(&em->list);
- free_extent_map(em);
- }
/*
* If any block groups are found in ->deleted_bgs then it's
* because the transaction was aborted and a commit did not
@@ -68,75 +136,90 @@
* discard the physical locations of the block groups.
*/
while (!list_empty(&transaction->deleted_bgs)) {
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
cache = list_first_entry(&transaction->deleted_bgs,
- struct btrfs_block_group_cache,
+ struct btrfs_block_group,
bg_list);
list_del_init(&cache->bg_list);
- btrfs_put_block_group_trimming(cache);
+ btrfs_unfreeze_block_group(cache);
btrfs_put_block_group(cache);
}
+ WARN_ON(!list_empty(&transaction->dev_update_list));
kfree(transaction);
}
}
-static void clear_btree_io_tree(struct extent_io_tree *tree)
+static noinline void switch_commit_roots(struct btrfs_trans_handle *trans)
{
- spin_lock(&tree->lock);
- /*
- * Do a single barrier for the waitqueue_active check here, the state
- * of the waitqueue should not change once clear_btree_io_tree is
- * called.
- */
- smp_mb();
- while (!RB_EMPTY_ROOT(&tree->state)) {
- struct rb_node *node;
- struct extent_state *state;
-
- node = rb_first(&tree->state);
- state = rb_entry(node, struct extent_state, rb_node);
- rb_erase(&state->rb_node, &tree->state);
- RB_CLEAR_NODE(&state->rb_node);
- /*
- * btree io trees aren't supposed to have tasks waiting for
- * changes in the flags of extent states ever.
- */
- ASSERT(!waitqueue_active(&state->wq));
- free_extent_state(state);
-
- cond_resched_lock(&tree->lock);
- }
- spin_unlock(&tree->lock);
-}
-
-static noinline void switch_commit_roots(struct btrfs_transaction *trans)
-{
+ struct btrfs_transaction *cur_trans = trans->transaction;
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *root, *tmp;
+ struct btrfs_caching_control *caching_ctl, *next;
down_write(&fs_info->commit_root_sem);
- list_for_each_entry_safe(root, tmp, &trans->switch_commits,
+ list_for_each_entry_safe(root, tmp, &cur_trans->switch_commits,
dirty_list) {
list_del_init(&root->dirty_list);
free_extent_buffer(root->commit_root);
root->commit_root = btrfs_root_node(root);
- if (is_fstree(root->objectid))
+ if (is_fstree(root->root_key.objectid))
btrfs_unpin_free_ino(root);
- clear_btree_io_tree(&root->dirty_log_pages);
+ extent_io_tree_release(&root->dirty_log_pages);
+ btrfs_qgroup_clean_swapped_blocks(root);
}
/* We can free old roots now. */
- spin_lock(&trans->dropped_roots_lock);
- while (!list_empty(&trans->dropped_roots)) {
- root = list_first_entry(&trans->dropped_roots,
+ spin_lock(&cur_trans->dropped_roots_lock);
+ while (!list_empty(&cur_trans->dropped_roots)) {
+ root = list_first_entry(&cur_trans->dropped_roots,
struct btrfs_root, root_list);
list_del_init(&root->root_list);
- spin_unlock(&trans->dropped_roots_lock);
+ spin_unlock(&cur_trans->dropped_roots_lock);
+ btrfs_free_log(trans, root);
btrfs_drop_and_free_fs_root(fs_info, root);
- spin_lock(&trans->dropped_roots_lock);
+ spin_lock(&cur_trans->dropped_roots_lock);
}
- spin_unlock(&trans->dropped_roots_lock);
+ spin_unlock(&cur_trans->dropped_roots_lock);
+
+ /*
+ * We have to update the last_byte_to_unpin under the commit_root_sem,
+ * at the same time we swap out the commit roots.
+ *
+ * This is because we must have a real view of the last spot the caching
+ * kthreads were while caching. Consider the following views of the
+ * extent tree for a block group
+ *
+ * commit root
+ * +----+----+----+----+----+----+----+
+ * |\\\\| |\\\\|\\\\| |\\\\|\\\\|
+ * +----+----+----+----+----+----+----+
+ * 0 1 2 3 4 5 6 7
+ *
+ * new commit root
+ * +----+----+----+----+----+----+----+
+ * | | | |\\\\| | |\\\\|
+ * +----+----+----+----+----+----+----+
+ * 0 1 2 3 4 5 6 7
+ *
+ * If the cache_ctl->progress was at 3, then we are only allowed to
+ * unpin [0,1) and [2,3], because the caching thread has already
+ * processed those extents. We are not allowed to unpin [5,6), because
+ * the caching thread will re-start it's search from 3, and thus find
+ * the hole from [4,6) to add to the free space cache.
+ */
+ list_for_each_entry_safe(caching_ctl, next,
+ &fs_info->caching_block_groups, list) {
+ struct btrfs_block_group *cache = caching_ctl->block_group;
+
+ if (btrfs_block_group_done(cache)) {
+ cache->last_byte_to_unpin = (u64)-1;
+ list_del_init(&caching_ctl->list);
+ btrfs_put_caching_control(caching_ctl);
+ } else {
+ cache->last_byte_to_unpin = caching_ctl->progress;
+ }
+ }
up_write(&fs_info->commit_root_sem);
}
@@ -166,6 +249,24 @@
}
/*
+ * To be called after all the new block groups attached to the transaction
+ * handle have been created (btrfs_create_pending_block_groups()).
+ */
+void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
+{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+
+ if (!trans->chunk_bytes_reserved)
+ return;
+
+ WARN_ON_ONCE(!list_empty(&trans->new_bgs));
+
+ btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv,
+ trans->chunk_bytes_reserved, NULL);
+ trans->chunk_bytes_reserved = 0;
+}
+
+/*
* either allocate a new transaction or hop into the existing one
*/
static noinline int join_transaction(struct btrfs_fs_info *fs_info,
@@ -183,7 +284,7 @@
cur_trans = fs_info->running_transaction;
if (cur_trans) {
- if (cur_trans->aborted) {
+ if (TRANS_ABORTED(cur_trans)) {
spin_unlock(&fs_info->trans_lock);
return cur_trans->aborted;
}
@@ -231,24 +332,24 @@
}
cur_trans->fs_info = fs_info;
+ atomic_set(&cur_trans->pending_ordered, 0);
+ init_waitqueue_head(&cur_trans->pending_wait);
atomic_set(&cur_trans->num_writers, 1);
extwriter_counter_init(cur_trans, type);
init_waitqueue_head(&cur_trans->writer_wait);
init_waitqueue_head(&cur_trans->commit_wait);
- init_waitqueue_head(&cur_trans->pending_wait);
cur_trans->state = TRANS_STATE_RUNNING;
/*
* One for this trans handle, one so it will live on until we
* commit the transaction.
*/
refcount_set(&cur_trans->use_count, 2);
- atomic_set(&cur_trans->pending_ordered, 0);
cur_trans->flags = 0;
cur_trans->start_time = ktime_get_seconds();
memset(&cur_trans->delayed_refs, 0, sizeof(cur_trans->delayed_refs));
- cur_trans->delayed_refs.href_root = RB_ROOT;
+ cur_trans->delayed_refs.href_root = RB_ROOT_CACHED;
cur_trans->delayed_refs.dirty_extent_root = RB_ROOT;
atomic_set(&cur_trans->delayed_refs.num_entries, 0);
@@ -266,19 +367,20 @@
spin_lock_init(&cur_trans->delayed_refs.lock);
INIT_LIST_HEAD(&cur_trans->pending_snapshots);
- INIT_LIST_HEAD(&cur_trans->pending_chunks);
+ INIT_LIST_HEAD(&cur_trans->dev_update_list);
INIT_LIST_HEAD(&cur_trans->switch_commits);
INIT_LIST_HEAD(&cur_trans->dirty_bgs);
INIT_LIST_HEAD(&cur_trans->io_bgs);
INIT_LIST_HEAD(&cur_trans->dropped_roots);
mutex_init(&cur_trans->cache_write_mutex);
- cur_trans->num_dirty_bgs = 0;
spin_lock_init(&cur_trans->dirty_bgs_lock);
INIT_LIST_HEAD(&cur_trans->deleted_bgs);
spin_lock_init(&cur_trans->dropped_roots_lock);
list_add_tail(&cur_trans->list, &fs_info->trans_list);
- extent_io_tree_init(&cur_trans->dirty_pages,
- fs_info->btree_inode);
+ extent_io_tree_init(fs_info, &cur_trans->dirty_pages,
+ IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode);
+ extent_io_tree_init(fs_info, &cur_trans->pinned_extents,
+ IO_TREE_FS_PINNED_EXTENTS, NULL);
fs_info->generation++;
cur_trans->transid = fs_info->generation;
fs_info->running_transaction = cur_trans;
@@ -289,10 +391,10 @@
}
/*
- * this does all the record keeping required to make sure that a reference
- * counted root is properly recorded in a given transaction. This is required
- * to make sure the old root from before we joined the transaction is deleted
- * when the transaction commits
+ * This does all the record keeping required to make sure that a shareable root
+ * is properly recorded in a given transaction. This is required to make sure
+ * the old root from before we joined the transaction is deleted when the
+ * transaction commits.
*/
static int record_root_in_trans(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
@@ -300,7 +402,7 @@
{
struct btrfs_fs_info *fs_info = root->fs_info;
- if ((test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+ if ((test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
root->last_trans < trans->transid) || force) {
WARN_ON(root == fs_info->extent_root);
WARN_ON(!force && root->commit_root != root->node);
@@ -379,7 +481,7 @@
{
struct btrfs_fs_info *fs_info = root->fs_info;
- if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
+ if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
return 0;
/*
@@ -400,9 +502,9 @@
static inline int is_transaction_blocked(struct btrfs_transaction *trans)
{
- return (trans->state >= TRANS_STATE_BLOCKED &&
+ return (trans->state >= TRANS_STATE_COMMIT_START &&
trans->state < TRANS_STATE_UNBLOCKED &&
- !trans->aborted);
+ !TRANS_ABORTED(trans));
}
/* wait for commit against the current transaction to become unblocked
@@ -421,7 +523,7 @@
wait_event(fs_info->transaction_wait,
cur_trans->state >= TRANS_STATE_UNBLOCKED ||
- cur_trans->aborted);
+ TRANS_ABORTED(cur_trans));
btrfs_put_transaction(cur_trans);
} else {
spin_unlock(&fs_info->trans_lock);
@@ -444,7 +546,7 @@
struct btrfs_fs_info *fs_info = root->fs_info;
if (!fs_info->reloc_ctl ||
- !test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+ !test_bit(BTRFS_ROOT_SHAREABLE, &root->state) ||
root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
root->reloc_root)
return false;
@@ -458,12 +560,13 @@
bool enforce_qgroups)
{
struct btrfs_fs_info *fs_info = root->fs_info;
-
+ struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
struct btrfs_trans_handle *h;
struct btrfs_transaction *cur_trans;
u64 num_bytes = 0;
u64 qgroup_reserved = 0;
bool reloc_reserved = false;
+ bool do_chunk_alloc = false;
int ret;
/* Send isn't supposed to start transactions. */
@@ -487,13 +590,29 @@
* the appropriate flushing if need be.
*/
if (num_items && root != fs_info->chunk_root) {
+ struct btrfs_block_rsv *rsv = &fs_info->trans_block_rsv;
+ u64 delayed_refs_bytes = 0;
+
qgroup_reserved = num_items * fs_info->nodesize;
ret = btrfs_qgroup_reserve_meta_pertrans(root, qgroup_reserved,
enforce_qgroups);
if (ret)
return ERR_PTR(ret);
- num_bytes = btrfs_calc_trans_metadata_size(fs_info, num_items);
+ /*
+ * We want to reserve all the bytes we may need all at once, so
+ * we only do 1 enospc flushing cycle per transaction start. We
+ * accomplish this by simply assuming we'll do 2 x num_items
+ * worth of delayed refs updates in this trans handle, and
+ * refill that amount for whatever is missing in the reserve.
+ */
+ num_bytes = btrfs_calc_insert_metadata_size(fs_info, num_items);
+ if (flush == BTRFS_RESERVE_FLUSH_ALL &&
+ delayed_refs_rsv->full == 0) {
+ delayed_refs_bytes = num_bytes;
+ num_bytes <<= 1;
+ }
+
/*
* Do the reservation for the relocation root creation
*/
@@ -502,8 +621,27 @@
reloc_reserved = true;
}
- ret = btrfs_block_rsv_add(root, &fs_info->trans_block_rsv,
- num_bytes, flush);
+ ret = btrfs_block_rsv_add(root, rsv, num_bytes, flush);
+ if (ret)
+ goto reserve_fail;
+ if (delayed_refs_bytes) {
+ btrfs_migrate_to_delayed_refs_rsv(fs_info, rsv,
+ delayed_refs_bytes);
+ num_bytes -= delayed_refs_bytes;
+ }
+
+ if (rsv->space_info->force_alloc)
+ do_chunk_alloc = true;
+ } else if (num_items == 0 && flush == BTRFS_RESERVE_FLUSH_ALL &&
+ !delayed_refs_rsv->full) {
+ /*
+ * Some people call with btrfs_start_transaction(root, 0)
+ * because they can be throttled, but have some other mechanism
+ * for reserving space. We still want these guys to refill the
+ * delayed block_rsv so just add 1 items worth of reservation
+ * here.
+ */
+ ret = btrfs_delayed_refs_rsv_refill(fs_info, flush);
if (ret)
goto reserve_fail;
}
@@ -556,7 +694,7 @@
INIT_LIST_HEAD(&h->new_bgs);
smp_mb();
- if (cur_trans->state >= TRANS_STATE_BLOCKED &&
+ if (cur_trans->state >= TRANS_STATE_COMMIT_START &&
may_wait_transaction(fs_info, type)) {
current->journal_info = h;
btrfs_commit_transaction(h);
@@ -574,6 +712,19 @@
got_it:
if (!current->journal_info)
current->journal_info = h;
+
+ /*
+ * If the space_info is marked ALLOC_FORCE then we'll get upgraded to
+ * ALLOC_FORCE the first run through, and then we won't allocate for
+ * anybody else who races in later. We don't care about the return
+ * value here.
+ */
+ if (do_chunk_alloc && num_bytes) {
+ u64 flags = h->block_rsv->space_info->flags;
+
+ btrfs_chunk_alloc(h, btrfs_get_alloc_profile(fs_info, flags),
+ CHUNK_ALLOC_NO_FORCE);
+ }
/*
* btrfs_record_root_in_trans() needs to alloc new extents, and may
@@ -594,7 +745,7 @@
alloc_fail:
if (num_bytes)
btrfs_block_rsv_release(fs_info, &fs_info->trans_block_rsv,
- num_bytes);
+ num_bytes, NULL);
reserve_fail:
btrfs_qgroup_free_meta_pertrans(root, qgroup_reserved);
return ERR_PTR(ret);
@@ -609,43 +760,10 @@
struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
struct btrfs_root *root,
- unsigned int num_items,
- int min_factor)
+ unsigned int num_items)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
- struct btrfs_trans_handle *trans;
- u64 num_bytes;
- int ret;
-
- /*
- * We have two callers: unlink and block group removal. The
- * former should succeed even if we will temporarily exceed
- * quota and the latter operates on the extent root so
- * qgroup enforcement is ignored anyway.
- */
- trans = start_transaction(root, num_items, TRANS_START,
- BTRFS_RESERVE_FLUSH_ALL, false);
- if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
- return trans;
-
- trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans))
- return trans;
-
- num_bytes = btrfs_calc_trans_metadata_size(fs_info, num_items);
- ret = btrfs_cond_migrate_bytes(fs_info, &fs_info->trans_block_rsv,
- num_bytes, min_factor);
- if (ret) {
- btrfs_end_transaction(trans);
- return ERR_PTR(ret);
- }
-
- trans->block_rsv = &fs_info->trans_block_rsv;
- trans->bytes_reserved = num_bytes;
- trace_btrfs_space_reservation(fs_info, "transaction",
- trans->transid, num_bytes, 1);
-
- return trans;
+ return start_transaction(root, num_items, TRANS_START,
+ BTRFS_RESERVE_FLUSH_ALL_STEAL, false);
}
struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
@@ -654,7 +772,7 @@
true);
}
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
+struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root)
{
return start_transaction(root, 0, TRANS_JOIN_NOLOCK,
BTRFS_RESERVE_NO_FLUSH, true);
@@ -692,7 +810,7 @@
/*
* btrfs_attach_transaction_barrier() - catch the running transaction
*
- * It is similar to the above function, the differentia is this one
+ * It is similar to the above function, the difference is this one
* will wait for all the inactive transactions until they fully
* complete.
*/
@@ -782,7 +900,7 @@
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- if (btrfs_check_space_for_delayed_refs(trans, fs_info))
+ if (btrfs_check_space_for_delayed_refs(fs_info))
return 1;
return !!btrfs_block_rsv_check(&fs_info->global_block_rsv, 5);
@@ -791,21 +909,11 @@
int btrfs_should_end_transaction(struct btrfs_trans_handle *trans)
{
struct btrfs_transaction *cur_trans = trans->transaction;
- int updates;
- int err;
smp_mb();
- if (cur_trans->state >= TRANS_STATE_BLOCKED ||
+ if (cur_trans->state >= TRANS_STATE_COMMIT_START ||
cur_trans->delayed_refs.flushing)
return 1;
-
- updates = trans->delayed_ref_updates;
- trans->delayed_ref_updates = 0;
- if (updates) {
- err = btrfs_run_delayed_refs(trans, updates * 2);
- if (err) /* Error code will also eval true */
- return err;
- }
return should_end_transaction(trans);
}
@@ -827,7 +935,7 @@
trace_btrfs_space_reservation(fs_info, "transaction",
trans->transid, trans->bytes_reserved, 0);
btrfs_block_rsv_release(fs_info, trans->block_rsv,
- trans->bytes_reserved);
+ trans->bytes_reserved, NULL);
trans->bytes_reserved = 0;
}
@@ -836,11 +944,7 @@
{
struct btrfs_fs_info *info = trans->fs_info;
struct btrfs_transaction *cur_trans = trans->transaction;
- u64 transid = trans->transid;
- unsigned long cur = trans->delayed_ref_updates;
- int lock = (trans->type != TRANS_JOIN_NOLOCK);
int err = 0;
- int must_run_delayed_refs = 0;
if (refcount_read(&trans->use_count) > 1) {
refcount_dec(&trans->use_count);
@@ -851,46 +955,9 @@
btrfs_trans_release_metadata(trans);
trans->block_rsv = NULL;
- if (!list_empty(&trans->new_bgs))
- btrfs_create_pending_block_groups(trans);
-
- trans->delayed_ref_updates = 0;
- if (!trans->sync) {
- must_run_delayed_refs =
- btrfs_should_throttle_delayed_refs(trans, info);
- cur = max_t(unsigned long, cur, 32);
-
- /*
- * don't make the caller wait if they are from a NOLOCK
- * or ATTACH transaction, it will deadlock with commit
- */
- if (must_run_delayed_refs == 1 &&
- (trans->type & (__TRANS_JOIN_NOLOCK | __TRANS_ATTACH)))
- must_run_delayed_refs = 2;
- }
-
- btrfs_trans_release_metadata(trans);
- trans->block_rsv = NULL;
-
- if (!list_empty(&trans->new_bgs))
- btrfs_create_pending_block_groups(trans);
+ btrfs_create_pending_block_groups(trans);
btrfs_trans_release_chunk_metadata(trans);
-
- if (lock && should_end_transaction(trans) &&
- READ_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) {
- spin_lock(&info->trans_lock);
- if (cur_trans->state == TRANS_STATE_RUNNING)
- cur_trans->state = TRANS_STATE_BLOCKED;
- spin_unlock(&info->trans_lock);
- }
-
- if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
- if (throttle)
- return btrfs_commit_transaction(trans);
- else
- wake_up_process(info->transaction_kthread);
- }
if (trans->type & __TRANS_FREEZABLE)
sb_end_intwrite(info->sb);
@@ -909,17 +976,16 @@
if (throttle)
btrfs_run_delayed_iputs(info);
- if (trans->aborted ||
+ if (TRANS_ABORTED(trans) ||
test_bit(BTRFS_FS_STATE_ERROR, &info->fs_state)) {
wake_up_process(info->transaction_kthread);
- err = -EIO;
+ if (TRANS_ABORTED(trans))
+ err = trans->aborted;
+ else
+ err = -EROFS;
}
kmem_cache_free(btrfs_trans_handle_cachep, trans);
- if (must_run_delayed_refs) {
- btrfs_async_run_delayed_refs(info, cur, transid,
- must_run_delayed_refs == 1);
- }
return err;
}
@@ -967,7 +1033,7 @@
* superblock that points to btree nodes/leafs for which
* writeback hasn't finished yet (and without errors).
* We cleanup any entries left in the io tree when committing
- * the transaction (through clear_btree_io_tree()).
+ * the transaction (through extent_io_tree_release()).
*/
if (err == -ENOMEM) {
err = 0;
@@ -1012,7 +1078,7 @@
* left in the io tree. For a log commit, we don't remove them
* after committing the log because the tree can be accessed
* concurrently - we do it only at transaction commit time when
- * it's safe to do it (through clear_btree_io_tree()).
+ * it's safe to do it (through extent_io_tree_release()).
*/
err = clear_extent_bit(dirty_pages, start, end,
EXTENT_NEED_WAIT, 0, 0, &cached_state);
@@ -1032,7 +1098,7 @@
return werr;
}
-int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
+static int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
struct extent_io_tree *dirty_pages)
{
bool errors = false;
@@ -1090,7 +1156,7 @@
blk_finish_plug(&plug);
ret2 = btrfs_wait_extents(fs_info, dirty_pages);
- clear_btree_io_tree(&trans->transaction->dirty_pages);
+ extent_io_tree_release(&trans->transaction->dirty_pages);
if (ret)
return ret;
@@ -1158,7 +1224,7 @@
eb = btrfs_lock_root_node(fs_info->tree_root);
ret = btrfs_cow_block(trans, fs_info->tree_root, eb, NULL,
- 0, &eb);
+ 0, &eb, BTRFS_NESTING_COW);
btrfs_tree_unlock(eb);
free_extent_buffer(eb);
@@ -1169,17 +1235,17 @@
if (ret)
return ret;
- ret = btrfs_run_dev_stats(trans, fs_info);
+ ret = btrfs_run_dev_stats(trans);
if (ret)
return ret;
- ret = btrfs_run_dev_replace(trans, fs_info);
+ ret = btrfs_run_dev_replace(trans);
if (ret)
return ret;
ret = btrfs_run_qgroups(trans);
if (ret)
return ret;
- ret = btrfs_setup_space_cache(trans, fs_info);
+ ret = btrfs_setup_space_cache(trans);
if (ret)
return ret;
@@ -1207,7 +1273,7 @@
}
while (!list_empty(dirty_bgs) || !list_empty(io_bgs)) {
- ret = btrfs_write_dirty_block_groups(trans, fs_info);
+ ret = btrfs_write_dirty_block_groups(trans);
if (ret)
return ret;
ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
@@ -1220,7 +1286,10 @@
list_add_tail(&fs_info->extent_root->dirty_list,
&trans->transaction->switch_commits);
- btrfs_after_dev_replace_commit(fs_info);
+
+ /* Update dev-replace pointer once everything is committed */
+ fs_info->dev_replace.committed_cursor_left =
+ fs_info->dev_replace.cursor_left_last_write_of_item;
return 0;
}
@@ -1235,8 +1304,10 @@
struct btrfs_fs_info *fs_info = root->fs_info;
spin_lock(&fs_info->trans_lock);
- if (list_empty(&root->root_list))
+ if (list_empty(&root->root_list)) {
+ btrfs_grab_root(root);
list_add_tail(&root->root_list, &fs_info->dead_roots);
+ }
spin_unlock(&fs_info->trans_lock);
}
@@ -1360,7 +1431,7 @@
return 0;
/*
- * Ensure dirty @src will be commited. Or, after comming
+ * Ensure dirty @src will be committed. Or, after coming
* commit_fs_roots() and switch_commit_roots(), any dirty but not
* recorded root will never be updated again, causing an outdated root
* item.
@@ -1401,7 +1472,7 @@
ret = commit_cowonly_roots(trans);
if (ret)
goto out;
- switch_commit_roots(trans->transaction);
+ switch_commit_roots(trans);
ret = btrfs_write_and_wait_transaction(trans);
if (ret)
btrfs_handle_fs_error(fs_info, ret,
@@ -1453,7 +1524,6 @@
u64 index = 0;
u64 objectid;
u64 root_flags;
- uuid_le new_uuid;
ASSERT(pending->path);
path = pending->path;
@@ -1546,8 +1616,7 @@
btrfs_set_root_generation_v2(new_root_item,
trans->transid);
- uuid_le_gen(&new_uuid);
- memcpy(new_root_item->uuid, new_uuid.b, BTRFS_UUID_SIZE);
+ generate_random_guid(new_root_item->uuid);
memcpy(new_root_item->parent_uuid, root->root_item.uuid,
BTRFS_UUID_SIZE);
if (!(root_flags & BTRFS_ROOT_SUBVOL_RDONLY)) {
@@ -1563,7 +1632,8 @@
btrfs_set_root_otransid(new_root_item, trans->transid);
old = btrfs_lock_root_node(root);
- ret = btrfs_cow_block(trans, root, old, NULL, 0, &old);
+ ret = btrfs_cow_block(trans, root, old, NULL, 0, &old,
+ BTRFS_NESTING_COW);
if (ret) {
btrfs_tree_unlock(old);
free_extent_buffer(old);
@@ -1571,7 +1641,7 @@
goto fail;
}
- btrfs_set_lock_blocking(old);
+ btrfs_set_lock_blocking_write(old);
ret = btrfs_copy_root(trans, root, old, &tmp, objectid);
/* clean up in any case */
@@ -1609,9 +1679,10 @@
}
key.offset = (u64)-1;
- pending->snap = btrfs_read_fs_root_no_name(fs_info, &key);
+ pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev);
if (IS_ERR(pending->snap)) {
ret = PTR_ERR(pending->snap);
+ pending->snap = NULL;
btrfs_abort_transaction(trans, ret);
goto fail;
}
@@ -1639,10 +1710,9 @@
if (ret < 0)
goto fail;
- ret = btrfs_insert_dir_item(trans, parent_root,
- dentry->d_name.name, dentry->d_name.len,
- BTRFS_I(parent_inode), &key,
- BTRFS_FT_DIR, index);
+ ret = btrfs_insert_dir_item(trans, dentry->d_name.name,
+ dentry->d_name.len, BTRFS_I(parent_inode),
+ &key, BTRFS_FT_DIR, index);
/* We have check then name at the beginning, so it is impossible. */
BUG_ON(ret == -EEXIST || ret == -EOVERFLOW);
if (ret) {
@@ -1659,7 +1729,8 @@
btrfs_abort_transaction(trans, ret);
goto fail;
}
- ret = btrfs_uuid_tree_add(trans, new_uuid.b, BTRFS_UUID_KEY_SUBVOL,
+ ret = btrfs_uuid_tree_add(trans, new_root_item->uuid,
+ BTRFS_UUID_KEY_SUBVOL,
objectid);
if (ret) {
btrfs_abort_transaction(trans, ret);
@@ -1771,7 +1842,8 @@
struct btrfs_transaction *trans)
{
wait_event(fs_info->transaction_blocked_wait,
- trans->state >= TRANS_STATE_COMMIT_START || trans->aborted);
+ trans->state >= TRANS_STATE_COMMIT_START ||
+ TRANS_ABORTED(trans));
}
/*
@@ -1783,7 +1855,8 @@
struct btrfs_transaction *trans)
{
wait_event(fs_info->transaction_wait,
- trans->state >= TRANS_STATE_UNBLOCKED || trans->aborted);
+ trans->state >= TRANS_STATE_UNBLOCKED ||
+ TRANS_ABORTED(trans));
}
/*
@@ -1865,7 +1938,6 @@
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_transaction *cur_trans = trans->transaction;
- DEFINE_WAIT(wait);
WARN_ON(refcount_read(&trans->use_count) > 1);
@@ -1880,7 +1952,6 @@
*/
BUG_ON(list_empty(&cur_trans->list));
- list_del_init(&cur_trans->list);
if (cur_trans == fs_info->running_transaction) {
cur_trans->state = TRANS_STATE_COMMIT_DOING;
spin_unlock(&fs_info->trans_lock);
@@ -1889,6 +1960,17 @@
spin_lock(&fs_info->trans_lock);
}
+
+ /*
+ * Now that we know no one else is still using the transaction we can
+ * remove the transaction from the list of transactions. This avoids
+ * the transaction kthread from cleaning up the transaction while some
+ * other task is still using it, which could result in a use-after-free
+ * on things like log trees, as it forces the transaction kthread to
+ * wait for this transaction to be cleaned up by us.
+ */
+ list_del_init(&cur_trans->list);
+
spin_unlock(&fs_info->trans_lock);
btrfs_cleanup_one_transaction(trans->transaction, fs_info);
@@ -1912,8 +1994,25 @@
kmem_cache_free(btrfs_trans_handle_cachep, trans);
}
-static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
+/*
+ * Release reserved delayed ref space of all pending block groups of the
+ * transaction and remove them from the list
+ */
+static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+ struct btrfs_block_group *block_group, *tmp;
+
+ list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
+ btrfs_delayed_refs_rsv_release(fs_info, 1);
+ list_del_init(&block_group->bg_list);
+ }
+}
+
+static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans)
+{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+
/*
* We use writeback_inodes_sb here because if we used
* btrfs_start_delalloc_roots we would deadlock with fs freeze.
@@ -1923,22 +2022,50 @@
* from already being in a transaction and our join_transaction doesn't
* have to re-take the fs freeze lock.
*/
- if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
+ if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC);
+ } else {
+ struct btrfs_pending_snapshot *pending;
+ struct list_head *head = &trans->transaction->pending_snapshots;
+
+ /*
+ * Flush dellaloc for any root that is going to be snapshotted.
+ * This is done to avoid a corrupted version of files, in the
+ * snapshots, that had both buffered and direct IO writes (even
+ * if they were done sequentially) due to an unordered update of
+ * the inode's size on disk.
+ */
+ list_for_each_entry(pending, head, list) {
+ int ret;
+
+ ret = btrfs_start_delalloc_snapshot(pending->root);
+ if (ret)
+ return ret;
+ }
+ }
return 0;
}
-static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
+static inline void btrfs_wait_delalloc_flush(struct btrfs_trans_handle *trans)
{
- if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
- btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
-}
+ struct btrfs_fs_info *fs_info = trans->fs_info;
-static inline void
-btrfs_wait_pending_ordered(struct btrfs_transaction *cur_trans)
-{
- wait_event(cur_trans->pending_wait,
- atomic_read(&cur_trans->pending_ordered) == 0);
+ if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
+ btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
+ } else {
+ struct btrfs_pending_snapshot *pending;
+ struct list_head *head = &trans->transaction->pending_snapshots;
+
+ /*
+ * Wait for any dellaloc that we started previously for the roots
+ * that are going to be snapshotted. This is to avoid a corrupted
+ * version of files in the snapshots that had both buffered and
+ * direct IO writes (even if they were done sequentially).
+ */
+ list_for_each_entry(pending, head, list)
+ btrfs_wait_ordered_extents(pending->root,
+ U64_MAX, 0, U64_MAX);
+ }
}
int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
@@ -1947,6 +2074,8 @@
struct btrfs_transaction *cur_trans = trans->transaction;
struct btrfs_transaction *prev_trans = NULL;
int ret;
+
+ ASSERT(refcount_read(&trans->use_count) == 1);
/*
* Some places just start a transaction to commit it. We need to make
@@ -1957,7 +2086,7 @@
trans->dirty = true;
/* Stop the commit early if ->aborted is set */
- if (unlikely(READ_ONCE(cur_trans->aborted))) {
+ if (TRANS_ABORTED(cur_trans)) {
ret = cur_trans->aborted;
btrfs_end_transaction(trans);
return ret;
@@ -1984,8 +2113,7 @@
cur_trans->delayed_refs.flushing = 1;
smp_wmb();
- if (!list_empty(&trans->new_bgs))
- btrfs_create_pending_block_groups(trans);
+ btrfs_create_pending_block_groups(trans);
ret = btrfs_run_delayed_refs(trans, 0);
if (ret) {
@@ -2032,7 +2160,7 @@
wait_for_commit(cur_trans);
- if (unlikely(cur_trans->aborted))
+ if (TRANS_ABORTED(cur_trans))
ret = cur_trans->aborted;
btrfs_put_transaction(cur_trans);
@@ -2051,7 +2179,7 @@
spin_unlock(&fs_info->trans_lock);
wait_for_commit(prev_trans);
- ret = prev_trans->aborted;
+ ret = READ_ONCE(prev_trans->aborted);
btrfs_put_transaction(prev_trans);
if (ret)
@@ -2075,7 +2203,7 @@
extwriter_counter_dec(cur_trans, trans->type);
- ret = btrfs_start_delalloc_flush(fs_info);
+ ret = btrfs_start_delalloc_flush(trans);
if (ret)
goto cleanup_transaction;
@@ -2091,9 +2219,15 @@
if (ret)
goto cleanup_transaction;
- btrfs_wait_delalloc_flush(fs_info);
+ btrfs_wait_delalloc_flush(trans);
- btrfs_wait_pending_ordered(cur_trans);
+ /*
+ * Wait for all ordered extents started by a fast fsync that joined this
+ * transaction. Otherwise if this transaction commits before the ordered
+ * extents complete we lose logged data after a power failure.
+ */
+ wait_event(cur_trans->pending_wait,
+ atomic_read(&cur_trans->pending_ordered) == 0);
btrfs_scrub_pause(fs_info);
/*
@@ -2107,8 +2241,7 @@
wait_event(cur_trans->writer_wait,
atomic_read(&cur_trans->num_writers) == 1);
- /* ->aborted might be set after the previous check, so check it */
- if (unlikely(READ_ONCE(cur_trans->aborted))) {
+ if (TRANS_ABORTED(cur_trans)) {
ret = cur_trans->aborted;
goto scrub_continue;
}
@@ -2125,10 +2258,8 @@
* core function of the snapshot creation.
*/
ret = create_pending_snapshots(trans);
- if (ret) {
- mutex_unlock(&fs_info->reloc_mutex);
- goto scrub_continue;
- }
+ if (ret)
+ goto unlock_reloc;
/*
* We insert the dir indexes of the snapshots and update the inode
@@ -2141,16 +2272,12 @@
* the nodes and leaves.
*/
ret = btrfs_run_delayed_items(trans);
- if (ret) {
- mutex_unlock(&fs_info->reloc_mutex);
- goto scrub_continue;
- }
+ if (ret)
+ goto unlock_reloc;
ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
- if (ret) {
- mutex_unlock(&fs_info->reloc_mutex);
- goto scrub_continue;
- }
+ if (ret)
+ goto unlock_reloc;
/*
* make sure none of the code above managed to slip in a
@@ -2176,11 +2303,8 @@
mutex_lock(&fs_info->tree_log_mutex);
ret = commit_fs_roots(trans);
- if (ret) {
- mutex_unlock(&fs_info->tree_log_mutex);
- mutex_unlock(&fs_info->reloc_mutex);
- goto scrub_continue;
- }
+ if (ret)
+ goto unlock_tree_log;
/*
* Since the transaction is done, we can apply the pending changes
@@ -2198,42 +2322,29 @@
* new delayed refs. Must handle them or qgroup can be wrong.
*/
ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
- if (ret) {
- mutex_unlock(&fs_info->tree_log_mutex);
- mutex_unlock(&fs_info->reloc_mutex);
- goto scrub_continue;
- }
+ if (ret)
+ goto unlock_tree_log;
/*
* Since fs roots are all committed, we can get a quite accurate
* new_roots. So let's do quota accounting.
*/
ret = btrfs_qgroup_account_extents(trans);
- if (ret < 0) {
- mutex_unlock(&fs_info->tree_log_mutex);
- mutex_unlock(&fs_info->reloc_mutex);
- goto scrub_continue;
- }
+ if (ret < 0)
+ goto unlock_tree_log;
ret = commit_cowonly_roots(trans);
- if (ret) {
- mutex_unlock(&fs_info->tree_log_mutex);
- mutex_unlock(&fs_info->reloc_mutex);
- goto scrub_continue;
- }
+ if (ret)
+ goto unlock_tree_log;
/*
* The tasks which save the space cache and inode cache may also
* update ->aborted, check it.
*/
- if (unlikely(READ_ONCE(cur_trans->aborted))) {
+ if (TRANS_ABORTED(cur_trans)) {
ret = cur_trans->aborted;
- mutex_unlock(&fs_info->tree_log_mutex);
- mutex_unlock(&fs_info->reloc_mutex);
- goto scrub_continue;
+ goto unlock_tree_log;
}
-
- btrfs_prepare_extent_commit(fs_info);
cur_trans = fs_info->running_transaction;
@@ -2247,7 +2358,7 @@
list_add_tail(&fs_info->chunk_root->dirty_list,
&cur_trans->switch_commits);
- switch_commit_roots(cur_trans);
+ switch_commit_roots(trans);
ASSERT(list_empty(&cur_trans->dirty_bgs));
ASSERT(list_empty(&cur_trans->io_bgs));
@@ -2258,8 +2369,7 @@
memcpy(fs_info->super_for_commit, fs_info->super_copy,
sizeof(*fs_info->super_copy));
- btrfs_update_commit_device_size(fs_info);
- btrfs_update_commit_device_bytes_used(cur_trans);
+ btrfs_commit_device_sizes(cur_trans);
clear_bit(BTRFS_FS_LOG1_ERR, &fs_info->flags);
clear_bit(BTRFS_FS_LOG2_ERR, &fs_info->flags);
@@ -2278,6 +2388,10 @@
if (ret) {
btrfs_handle_fs_error(fs_info, ret,
"Error while writing out transaction");
+ /*
+ * reloc_mutex has been unlocked, tree_log_mutex is still held
+ * but we can't jump to unlock_tree_log causing double unlock
+ */
mutex_unlock(&fs_info->tree_log_mutex);
goto scrub_continue;
}
@@ -2303,7 +2417,6 @@
*/
cur_trans->state = TRANS_STATE_COMPLETED;
wake_up(&cur_trans->commit_wait);
- clear_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
spin_lock(&fs_info->trans_lock);
list_del_init(&cur_trans->list);
@@ -2326,10 +2439,15 @@
return ret;
+unlock_tree_log:
+ mutex_unlock(&fs_info->tree_log_mutex);
+unlock_reloc:
+ mutex_unlock(&fs_info->reloc_mutex);
scrub_continue:
btrfs_scrub_continue(fs_info);
cleanup_transaction:
btrfs_trans_release_metadata(trans);
+ btrfs_cleanup_pending_block_groups(trans);
btrfs_trans_release_chunk_metadata(trans);
trans->block_rsv = NULL;
btrfs_warn(fs_info, "Skipping commit of aborted transaction.");
@@ -2365,16 +2483,21 @@
list_del_init(&root->root_list);
spin_unlock(&fs_info->trans_lock);
- btrfs_debug(fs_info, "cleaner removing %llu", root->objectid);
+ btrfs_debug(fs_info, "cleaner removing %llu", root->root_key.objectid);
btrfs_kill_all_delayed_nodes(root);
+ if (root->ino_cache_inode) {
+ iput(root->ino_cache_inode);
+ root->ino_cache_inode = NULL;
+ }
if (btrfs_header_backref_rev(root->node) <
BTRFS_MIXED_BACKREF_REV)
- ret = btrfs_drop_snapshot(root, NULL, 0, 0);
+ ret = btrfs_drop_snapshot(root, 0, 0);
else
- ret = btrfs_drop_snapshot(root, NULL, 1, 0);
+ ret = btrfs_drop_snapshot(root, 1, 0);
+ btrfs_put_root(root);
return (ret < 0) ? 0 : 1;
}
--
Gitblit v1.6.2