From 1e8f915868c59be4d6e49d9aff928454a5d5d569 Mon Sep 17 00:00:00 2001 From: Wang Shilong Date: Mon, 6 May 2013 11:03:27 +0000 Subject: Btrfs: introduce qgroup_ulist to avoid frequently allocating/freeing ulist When doing qgroup accounting, we call ulist_alloc()/ulist_free() every time when we want to walk qgroup tree. By introducing 'qgroup_ulist', we only need to call ulist_alloc()/ulist_free() once. This reduce some sys time to allocate memory, see the measurements below fsstress -p 4 -n 10000 -d $dir With this patch: real 0m50.153s user 0m0.081s sys 0m6.294s real 0m51.113s user 0m0.092s sys 0m6.220s real 0m52.610s user 0m0.096s sys 0m6.125s avg 6.213 ----------------------------------------------------- Without the patch: real 0m54.825s user 0m0.061s sys 0m10.665s real 1m6.401s user 0m0.089s sys 0m11.218s real 1m13.768s user 0m0.087s sys 0m10.665s avg 10.849 we can see the sys time reduce ~43%. Signed-off-by: Wang Shilong Signed-off-by: Josef Bacik --- fs/btrfs/qgroup.c | 70 ++++++++++++++++++++++++++++--------------------------- 1 file changed, 36 insertions(+), 34 deletions(-) (limited to 'fs/btrfs/qgroup.c') diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 9d49c586995..7f38cce2528 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -259,6 +259,12 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) if (!fs_info->quota_enabled) return 0; + fs_info->qgroup_ulist = ulist_alloc(GFP_NOFS); + if (!fs_info->qgroup_ulist) { + ret = -ENOMEM; + goto out; + } + path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; @@ -424,6 +430,9 @@ out: } btrfs_free_path(path); + if (ret) + ulist_free(fs_info->qgroup_ulist); + return ret < 0 ? ret : 0; } @@ -460,6 +469,7 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info) } kfree(qgroup); } + ulist_free(fs_info->qgroup_ulist); } static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, @@ -819,6 +829,12 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans, goto out; } + fs_info->qgroup_ulist = ulist_alloc(GFP_NOFS); + if (!fs_info->qgroup_ulist) { + ret = -ENOMEM; + goto out; + } + /* * initially create the quota tree */ @@ -916,6 +932,8 @@ out_free_root: kfree(quota_root); } out: + if (ret) + ulist_free(fs_info->qgroup_ulist); mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; } @@ -1355,7 +1373,6 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans, u64 ref_root; struct btrfs_qgroup *qgroup; struct ulist *roots = NULL; - struct ulist *tmp = NULL; u64 seq; int ret = 0; int sgn; @@ -1448,31 +1465,28 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans, /* * step 1: for each old ref, visit all nodes once and inc refcnt */ - tmp = ulist_alloc(GFP_ATOMIC); - if (!tmp) { - ret = -ENOMEM; - goto unlock; - } + ulist_reinit(fs_info->qgroup_ulist); seq = fs_info->qgroup_seq; fs_info->qgroup_seq += roots->nnodes + 1; /* max refcnt */ - ret = qgroup_account_ref_step1(fs_info, roots, tmp, seq); + ret = qgroup_account_ref_step1(fs_info, roots, fs_info->qgroup_ulist, + seq); if (ret) goto unlock; /* * step 2: walk from the new root */ - ret = qgroup_account_ref_step2(fs_info, roots, tmp, seq, sgn, - node->num_bytes, qgroup); + ret = qgroup_account_ref_step2(fs_info, roots, fs_info->qgroup_ulist, + seq, sgn, node->num_bytes, qgroup); if (ret) goto unlock; /* * step 3: walk again from old refs */ - ret = qgroup_account_ref_step3(fs_info, roots, tmp, seq, sgn, - node->num_bytes); + ret = qgroup_account_ref_step3(fs_info, roots, fs_info->qgroup_ulist, + seq, sgn, node->num_bytes); if (ret) goto unlock; @@ -1480,7 +1494,6 @@ unlock: spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); ulist_free(roots); - ulist_free(tmp); return ret; } @@ -1720,7 +1733,6 @@ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes) struct btrfs_fs_info *fs_info = root->fs_info; u64 ref_root = root->root_key.objectid; int ret = 0; - struct ulist *ulist = NULL; struct ulist_node *unode; struct ulist_iterator uiter; @@ -1743,17 +1755,13 @@ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes) * in a first step, we check all affected qgroups if any limits would * be exceeded */ - ulist = ulist_alloc(GFP_ATOMIC); - if (!ulist) { - ret = -ENOMEM; - goto out; - } - ret = ulist_add(ulist, qgroup->qgroupid, + ulist_reinit(fs_info->qgroup_ulist); + ret = ulist_add(fs_info->qgroup_ulist, qgroup->qgroupid, (uintptr_t)qgroup, GFP_ATOMIC); if (ret < 0) goto out; ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(ulist, &uiter))) { + while ((unode = ulist_next(fs_info->qgroup_ulist, &uiter))) { struct btrfs_qgroup *qg; struct btrfs_qgroup_list *glist; @@ -1774,7 +1782,8 @@ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes) } list_for_each_entry(glist, &qg->groups, next_group) { - ret = ulist_add(ulist, glist->group->qgroupid, + ret = ulist_add(fs_info->qgroup_ulist, + glist->group->qgroupid, (uintptr_t)glist->group, GFP_ATOMIC); if (ret < 0) goto out; @@ -1785,7 +1794,7 @@ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes) * no limits exceeded, now record the reservation into all qgroups */ ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(ulist, &uiter))) { + while ((unode = ulist_next(fs_info->qgroup_ulist, &uiter))) { struct btrfs_qgroup *qg; qg = (struct btrfs_qgroup *)(uintptr_t)unode->aux; @@ -1795,8 +1804,6 @@ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes) out: spin_unlock(&fs_info->qgroup_lock); - ulist_free(ulist); - return ret; } @@ -1805,7 +1812,6 @@ void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes) struct btrfs_root *quota_root; struct btrfs_qgroup *qgroup; struct btrfs_fs_info *fs_info = root->fs_info; - struct ulist *ulist = NULL; struct ulist_node *unode; struct ulist_iterator uiter; u64 ref_root = root->root_key.objectid; @@ -1827,17 +1833,13 @@ void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes) if (!qgroup) goto out; - ulist = ulist_alloc(GFP_ATOMIC); - if (!ulist) { - btrfs_std_error(fs_info, -ENOMEM); - goto out; - } - ret = ulist_add(ulist, qgroup->qgroupid, + ulist_reinit(fs_info->qgroup_ulist); + ret = ulist_add(fs_info->qgroup_ulist, qgroup->qgroupid, (uintptr_t)qgroup, GFP_ATOMIC); if (ret < 0) goto out; ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(ulist, &uiter))) { + while ((unode = ulist_next(fs_info->qgroup_ulist, &uiter))) { struct btrfs_qgroup *qg; struct btrfs_qgroup_list *glist; @@ -1846,7 +1848,8 @@ void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes) qg->reserved -= num_bytes; list_for_each_entry(glist, &qg->groups, next_group) { - ret = ulist_add(ulist, glist->group->qgroupid, + ret = ulist_add(fs_info->qgroup_ulist, + glist->group->qgroupid, (uintptr_t)glist->group, GFP_ATOMIC); if (ret < 0) goto out; @@ -1855,7 +1858,6 @@ void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes) out: spin_unlock(&fs_info->qgroup_lock); - ulist_free(ulist); } void assert_qgroups_uptodate(struct btrfs_trans_handle *trans) -- cgit v1.2.3-18-g5258 From 57254b6ebce4ceca02d9c8b615f6059c56c19238 Mon Sep 17 00:00:00 2001 From: Jan Schmidt Date: Mon, 6 May 2013 19:14:17 +0000 Subject: Btrfs: add ioctl to wait for qgroup rescan completion btrfs_qgroup_wait_for_completion waits until the currently running qgroup operation completes. It returns immediately when no rescan process is in progress. This is useful to automate things around the rescan process (e.g. testing). Signed-off-by: Jan Schmidt Signed-off-by: Josef Bacik --- fs/btrfs/qgroup.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'fs/btrfs/qgroup.c') diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 7f38cce2528..d059d86c313 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2070,6 +2070,8 @@ out: } else { pr_err("btrfs: qgroup scan failed with %d\n", err); } + + complete_all(&fs_info->qgroup_rescan_completion); } static void @@ -2110,6 +2112,7 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN; memset(&fs_info->qgroup_rescan_progress, 0, sizeof(fs_info->qgroup_rescan_progress)); + init_completion(&fs_info->qgroup_rescan_completion); /* clear all current qgroup tracking information */ for (n = rb_first(&fs_info->qgroup_tree); n; n = rb_next(n)) { @@ -2126,3 +2129,21 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) return 0; } + +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info) +{ + int running; + int ret = 0; + + mutex_lock(&fs_info->qgroup_rescan_lock); + spin_lock(&fs_info->qgroup_lock); + running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN; + spin_unlock(&fs_info->qgroup_lock); + mutex_unlock(&fs_info->qgroup_rescan_lock); + + if (running) + ret = wait_for_completion_interruptible( + &fs_info->qgroup_rescan_completion); + + return ret; +} -- cgit v1.2.3-18-g5258 From 4373519db4dbca05341a60b28f6e159b106e4c4b Mon Sep 17 00:00:00 2001 From: Jan Schmidt Date: Tue, 28 May 2013 15:47:22 +0000 Subject: Btrfs: fix memory patcher through fs_info->qgroup_ulist Commit 5b7c665e introduced fs_info->qgroup_ulist, that is allocated during btrfs_read_qgroup_config and meant to be used later by the qgroup accounting code. However, it is always freed before btrfs_read_qgroup_config returns, becuase the commit mentioned above adds a check for (ret), where a check for (ret < 0) would have been the right choice. This commit fixes the check. Cc: Wang Shilong Signed-off-by: Jan Schmidt Signed-off-by: Josef Bacik --- fs/btrfs/qgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/qgroup.c') diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index d059d86c313..74b432d0b70 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -430,7 +430,7 @@ out: } btrfs_free_path(path); - if (ret) + if (ret < 0) ulist_free(fs_info->qgroup_ulist); return ret < 0 ? ret : 0; -- cgit v1.2.3-18-g5258 From eb1716af887375f1e2099f69bb89dfc5bd169bfa Mon Sep 17 00:00:00 2001 From: Jan Schmidt Date: Tue, 28 May 2013 15:47:23 +0000 Subject: Btrfs: avoid double free of fs_info->qgroup_ulist When btrfs_read_qgroup_config or btrfs_quota_enable return non-zero, we've already freed the fs_info->qgroup_ulist. The final btrfs_free_qgroup_config called from quota_disable makes another ulist_free(fs_info->qgroup_ulist) call. We set fs_info->qgroup_ulist to NULL on the mentioned error paths, turning the ulist_free in btrfs_free_qgroup_config into a noop. Cc: Wang Shilong Signed-off-by: Jan Schmidt Signed-off-by: Josef Bacik --- fs/btrfs/qgroup.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/qgroup.c') diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 74b432d0b70..c6ce6427686 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -430,8 +430,10 @@ out: } btrfs_free_path(path); - if (ret < 0) + if (ret < 0) { ulist_free(fs_info->qgroup_ulist); + fs_info->qgroup_ulist = NULL; + } return ret < 0 ? ret : 0; } @@ -932,8 +934,10 @@ out_free_root: kfree(quota_root); } out: - if (ret) + if (ret) { ulist_free(fs_info->qgroup_ulist); + fs_info->qgroup_ulist = NULL; + } mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; } -- cgit v1.2.3-18-g5258 From b382a324b60f4923e9fc8e11f023e4f493c51318 Mon Sep 17 00:00:00 2001 From: Jan Schmidt Date: Tue, 28 May 2013 15:47:24 +0000 Subject: Btrfs: fix qgroup rescan resume on mount When called during mount, we cannot start the rescan worker thread until open_ctree is done. This commit restuctures the qgroup rescan internals to enable a clean deferral of the rescan resume operation. First of all, the struct qgroup_rescan is removed, saving us a malloc and some initialization synchronizations problems. Its only element (the worker struct) now lives within fs_info just as the rest of the rescan code. Then setting up a rescan worker is split into several reusable stages. Currently we have three different rescan startup scenarios: (A) rescan ioctl (B) rescan resume by mount (C) rescan by quota enable Each case needs its own combination of the four following steps: (1) set the progress [A, C: zero; B: state of umount] (2) commit the transaction [A] (3) set the counters [A, C: zero; B: state of umount] (4) start worker [A, B, C] qgroup_rescan_init does step (1). There's no extra function added to commit a transaction, we've got that already. qgroup_rescan_zero_tracking does step (3). Step (4) is nothing more than a call to the generic btrfs_queue_worker. We also get rid of a double check for the rescan progress during btrfs_qgroup_account_ref, which is no longer required due to having step 2 from the list above. As a side effect, this commit prepares to move the rescan start code from btrfs_run_qgroups (which is run during commit) to a less time critical section. Signed-off-by: Jan Schmidt Signed-off-by: Josef Bacik --- fs/btrfs/qgroup.c | 190 ++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 121 insertions(+), 69 deletions(-) (limited to 'fs/btrfs/qgroup.c') diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index c6ce6427686..1280eff8af5 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -98,13 +98,10 @@ struct btrfs_qgroup_list { struct btrfs_qgroup *member; }; -struct qgroup_rescan { - struct btrfs_work work; - struct btrfs_fs_info *fs_info; -}; - -static void qgroup_rescan_start(struct btrfs_fs_info *fs_info, - struct qgroup_rescan *qscan); +static int +qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, + int init_flags); +static void qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info); /* must be called with qgroup_ioctl_lock held */ static struct btrfs_qgroup *find_qgroup_rb(struct btrfs_fs_info *fs_info, @@ -255,6 +252,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) int slot; int ret = 0; u64 flags = 0; + u64 rescan_progress = 0; if (!fs_info->quota_enabled) return 0; @@ -312,20 +310,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) } fs_info->qgroup_flags = btrfs_qgroup_status_flags(l, ptr); - fs_info->qgroup_rescan_progress.objectid = - btrfs_qgroup_status_rescan(l, ptr); - if (fs_info->qgroup_flags & - BTRFS_QGROUP_STATUS_FLAG_RESCAN) { - struct qgroup_rescan *qscan = - kmalloc(sizeof(*qscan), GFP_NOFS); - if (!qscan) { - ret = -ENOMEM; - goto out; - } - fs_info->qgroup_rescan_progress.type = 0; - fs_info->qgroup_rescan_progress.offset = 0; - qgroup_rescan_start(fs_info, qscan); - } + rescan_progress = btrfs_qgroup_status_rescan(l, ptr); goto next1; } @@ -427,12 +412,16 @@ out: if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) { fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; + } else if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN && + ret >= 0) { + ret = qgroup_rescan_init(fs_info, rescan_progress, 0); } btrfs_free_path(path); if (ret < 0) { ulist_free(fs_info->qgroup_ulist); fs_info->qgroup_ulist = NULL; + fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; } return ret < 0 ? ret : 0; @@ -1449,14 +1438,7 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans, if (ret < 0) return ret; - mutex_lock(&fs_info->qgroup_rescan_lock); spin_lock(&fs_info->qgroup_lock); - if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) { - if (fs_info->qgroup_rescan_progress.objectid <= node->bytenr) { - ret = 0; - goto unlock; - } - } quota_root = fs_info->quota_root; if (!quota_root) @@ -1496,7 +1478,6 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans, unlock: spin_unlock(&fs_info->qgroup_lock); - mutex_unlock(&fs_info->qgroup_rescan_lock); ulist_free(roots); return ret; @@ -1544,9 +1525,12 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; if (!ret && start_rescan_worker) { - ret = btrfs_qgroup_rescan(fs_info); - if (ret) - pr_err("btrfs: start rescan quota failed: %d\n", ret); + ret = qgroup_rescan_init(fs_info, 0, 1); + if (!ret) { + qgroup_rescan_zero_tracking(fs_info); + btrfs_queue_worker(&fs_info->qgroup_rescan_workers, + &fs_info->qgroup_rescan_work); + } ret = 0; } @@ -1880,12 +1864,11 @@ void assert_qgroups_uptodate(struct btrfs_trans_handle *trans) * returns 1 when done, 2 when done and FLAG_INCONSISTENT was cleared. */ static int -qgroup_rescan_leaf(struct qgroup_rescan *qscan, struct btrfs_path *path, +qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path, struct btrfs_trans_handle *trans, struct ulist *tmp, struct extent_buffer *scratch_leaf) { struct btrfs_key found; - struct btrfs_fs_info *fs_info = qscan->fs_info; struct ulist *roots = NULL; struct ulist_node *unode; struct ulist_iterator uiter; @@ -2013,11 +1996,10 @@ out: static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) { - struct qgroup_rescan *qscan = container_of(work, struct qgroup_rescan, - work); + struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info, + qgroup_rescan_work); struct btrfs_path *path; struct btrfs_trans_handle *trans = NULL; - struct btrfs_fs_info *fs_info = qscan->fs_info; struct ulist *tmp = NULL; struct extent_buffer *scratch_leaf = NULL; int err = -ENOMEM; @@ -2042,7 +2024,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) if (!fs_info->quota_enabled) { err = -EINTR; } else { - err = qgroup_rescan_leaf(qscan, path, trans, + err = qgroup_rescan_leaf(fs_info, path, trans, tmp, scratch_leaf); } if (err > 0) @@ -2055,7 +2037,6 @@ out: kfree(scratch_leaf); ulist_free(tmp); btrfs_free_path(path); - kfree(qscan); mutex_lock(&fs_info->qgroup_rescan_lock); fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; @@ -2078,46 +2059,70 @@ out: complete_all(&fs_info->qgroup_rescan_completion); } -static void -qgroup_rescan_start(struct btrfs_fs_info *fs_info, struct qgroup_rescan *qscan) -{ - memset(&qscan->work, 0, sizeof(qscan->work)); - qscan->work.func = btrfs_qgroup_rescan_worker; - qscan->fs_info = fs_info; - - pr_info("btrfs: qgroup scan started\n"); - btrfs_queue_worker(&fs_info->qgroup_rescan_workers, &qscan->work); -} - -int -btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) +/* + * Checks that (a) no rescan is running and (b) quota is enabled. Allocates all + * memory required for the rescan context. + */ +static int +qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, + int init_flags) { int ret = 0; - struct rb_node *n; - struct btrfs_qgroup *qgroup; - struct qgroup_rescan *qscan = kmalloc(sizeof(*qscan), GFP_NOFS); - if (!qscan) - return -ENOMEM; + if (!init_flags && + (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) || + !(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))) { + ret = -EINVAL; + goto err; + } mutex_lock(&fs_info->qgroup_rescan_lock); spin_lock(&fs_info->qgroup_lock); - if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) - ret = -EINPROGRESS; - else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) - ret = -EINVAL; - if (ret) { - spin_unlock(&fs_info->qgroup_lock); - mutex_unlock(&fs_info->qgroup_rescan_lock); - kfree(qscan); - return ret; + + if (init_flags) { + if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) + ret = -EINPROGRESS; + else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) + ret = -EINVAL; + + if (ret) { + spin_unlock(&fs_info->qgroup_lock); + mutex_unlock(&fs_info->qgroup_rescan_lock); + goto err; + } + + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN; } - fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN; memset(&fs_info->qgroup_rescan_progress, 0, sizeof(fs_info->qgroup_rescan_progress)); + fs_info->qgroup_rescan_progress.objectid = progress_objectid; + + spin_unlock(&fs_info->qgroup_lock); + mutex_unlock(&fs_info->qgroup_rescan_lock); + init_completion(&fs_info->qgroup_rescan_completion); + memset(&fs_info->qgroup_rescan_work, 0, + sizeof(fs_info->qgroup_rescan_work)); + fs_info->qgroup_rescan_work.func = btrfs_qgroup_rescan_worker; + + if (ret) { +err: + pr_info("btrfs: qgroup_rescan_init failed with %d\n", ret); + return ret; + } + + return 0; +} + +static void +qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info) +{ + struct rb_node *n; + struct btrfs_qgroup *qgroup; + + spin_lock(&fs_info->qgroup_lock); /* clear all current qgroup tracking information */ for (n = rb_first(&fs_info->qgroup_tree); n; n = rb_next(n)) { qgroup = rb_entry(n, struct btrfs_qgroup, node); @@ -2127,9 +2132,44 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) qgroup->excl_cmpr = 0; } spin_unlock(&fs_info->qgroup_lock); - mutex_unlock(&fs_info->qgroup_rescan_lock); +} - qgroup_rescan_start(fs_info, qscan); +int +btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) +{ + int ret = 0; + struct btrfs_trans_handle *trans; + + ret = qgroup_rescan_init(fs_info, 0, 1); + if (ret) + return ret; + + /* + * We have set the rescan_progress to 0, which means no more + * delayed refs will be accounted by btrfs_qgroup_account_ref. + * However, btrfs_qgroup_account_ref may be right after its call + * to btrfs_find_all_roots, in which case it would still do the + * accounting. + * To solve this, we're committing the transaction, which will + * ensure we run all delayed refs and only after that, we are + * going to clear all tracking information for a clean start. + */ + + trans = btrfs_join_transaction(fs_info->fs_root); + if (IS_ERR(trans)) { + fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; + return PTR_ERR(trans); + } + ret = btrfs_commit_transaction(trans, fs_info->fs_root); + if (ret) { + fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; + return ret; + } + + qgroup_rescan_zero_tracking(fs_info); + + btrfs_queue_worker(&fs_info->qgroup_rescan_workers, + &fs_info->qgroup_rescan_work); return 0; } @@ -2151,3 +2191,15 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info) return ret; } + +/* + * this is only called from open_ctree where we're still single threaded, thus + * locking is omitted here. + */ +void +btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info) +{ + if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) + btrfs_queue_worker(&fs_info->qgroup_rescan_workers, + &fs_info->qgroup_rescan_work); +} -- cgit v1.2.3-18-g5258