diff options
Diffstat (limited to 'fs/ceph')
-rw-r--r-- | fs/ceph/addr.c | 9 | ||||
-rw-r--r-- | fs/ceph/caps.c | 38 | ||||
-rw-r--r-- | fs/ceph/file.c | 2 | ||||
-rw-r--r-- | fs/ceph/locks.c | 3 | ||||
-rw-r--r-- | fs/ceph/mds_client.c | 32 | ||||
-rw-r--r-- | fs/ceph/mdsmap.c | 8 | ||||
-rw-r--r-- | fs/ceph/snap.c | 37 | ||||
-rw-r--r-- | fs/ceph/super.h | 5 |
8 files changed, 85 insertions, 49 deletions
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index a1e2813731d1..7e7a897ae0d3 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1395,9 +1395,11 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf) ret = VM_FAULT_SIGBUS; } else { struct address_space *mapping = inode->i_mapping; - struct page *page = find_or_create_page(mapping, 0, - mapping_gfp_constraint(mapping, - ~__GFP_FS)); + struct page *page; + + filemap_invalidate_lock_shared(mapping); + page = find_or_create_page(mapping, 0, + mapping_gfp_constraint(mapping, ~__GFP_FS)); if (!page) { ret = VM_FAULT_OOM; goto out_inline; @@ -1418,6 +1420,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf) vmf->page = page; ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED; out_inline: + filemap_invalidate_unlock_shared(mapping); dout("filemap_fault %p %llu read inline data ret %x\n", inode, off, ret); } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 7bdefd0c789a..39db97f149b9 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1743,7 +1743,11 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask, struct ceph_cap_flush *ceph_alloc_cap_flush(void) { - return kmem_cache_alloc(ceph_cap_flush_cachep, GFP_KERNEL); + struct ceph_cap_flush *cf; + + cf = kmem_cache_alloc(ceph_cap_flush_cachep, GFP_KERNEL); + cf->is_capsnap = false; + return cf; } void ceph_free_cap_flush(struct ceph_cap_flush *cf) @@ -1778,7 +1782,7 @@ static bool __detach_cap_flush_from_mdsc(struct ceph_mds_client *mdsc, prev->wake = true; wake = false; } - list_del(&cf->g_list); + list_del_init(&cf->g_list); return wake; } @@ -1793,7 +1797,7 @@ static bool __detach_cap_flush_from_ci(struct ceph_inode_info *ci, prev->wake = true; wake = false; } - list_del(&cf->i_list); + list_del_init(&cf->i_list); return wake; } @@ -2352,7 +2356,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH; list_for_each_entry_reverse(cf, &ci->i_cap_flush_list, i_list) { - if (!cf->caps) { + if (cf->is_capsnap) { last_snap_flush = cf->tid; break; } @@ -2371,7 +2375,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, first_tid = cf->tid + 1; - if (cf->caps) { + if (!cf->is_capsnap) { struct cap_msg_args arg; dout("kick_flushing_caps %p cap %p tid %llu %s\n", @@ -3516,7 +3520,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid, cleaned = cf->caps; /* Is this a capsnap? */ - if (cf->caps == 0) + if (cf->is_capsnap) continue; if (cf->tid <= flush_tid) { @@ -3589,8 +3593,9 @@ out: while (!list_empty(&to_remove)) { cf = list_first_entry(&to_remove, struct ceph_cap_flush, i_list); - list_del(&cf->i_list); - ceph_free_cap_flush(cf); + list_del_init(&cf->i_list); + if (!cf->is_capsnap) + ceph_free_cap_flush(cf); } if (wake_ci) @@ -4150,11 +4155,19 @@ bad: /* * Delayed work handler to process end of delayed cap release LRU list. + * + * If new caps are added to the list while processing it, these won't get + * processed in this run. In this case, the ci->i_hold_caps_max will be + * returned so that the work can be scheduled accordingly. */ -void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) +unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc) { struct inode *inode; struct ceph_inode_info *ci; + struct ceph_mount_options *opt = mdsc->fsc->mount_options; + unsigned long delay_max = opt->caps_wanted_delay_max * HZ; + unsigned long loop_start = jiffies; + unsigned long delay = 0; dout("check_delayed_caps\n"); spin_lock(&mdsc->cap_delay_lock); @@ -4162,6 +4175,11 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) ci = list_first_entry(&mdsc->cap_delay_list, struct ceph_inode_info, i_cap_delay_list); + if (time_before(loop_start, ci->i_hold_caps_max - delay_max)) { + dout("%s caps added recently. Exiting loop", __func__); + delay = ci->i_hold_caps_max; + break; + } if ((ci->i_ceph_flags & CEPH_I_FLUSH) == 0 && time_before(jiffies, ci->i_hold_caps_max)) break; @@ -4177,6 +4195,8 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) } } spin_unlock(&mdsc->cap_delay_lock); + + return delay; } /* diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d1755ac1d964..e1d605a02d4a 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2088,6 +2088,7 @@ static long ceph_fallocate(struct file *file, int mode, if (ret < 0) goto unlock; + filemap_invalidate_lock(inode->i_mapping); ceph_zero_pagecache_range(inode, offset, length); ret = ceph_zero_objects(inode, offset, length); @@ -2100,6 +2101,7 @@ static long ceph_fallocate(struct file *file, int mode, if (dirty) __mark_inode_dirty(inode, dirty); } + filemap_invalidate_unlock(inode->i_mapping); ceph_put_cap_refs(ci, got); unlock: diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index fa8a847743d0..bdeb271f47d9 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -240,9 +240,6 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_POSIX)) return -ENOLCK; - /* No mandatory locks */ - if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK) - return -ENOLCK; dout("ceph_lock, fl_owner: %p\n", fl->fl_owner); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 9db1b39df773..0b69aec23e5c 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1616,7 +1616,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, spin_lock(&mdsc->cap_dirty_lock); list_for_each_entry(cf, &to_remove, i_list) - list_del(&cf->g_list); + list_del_init(&cf->g_list); if (!list_empty(&ci->i_dirty_item)) { pr_warn_ratelimited( @@ -1668,8 +1668,9 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, struct ceph_cap_flush *cf; cf = list_first_entry(&to_remove, struct ceph_cap_flush, i_list); - list_del(&cf->i_list); - ceph_free_cap_flush(cf); + list_del_init(&cf->i_list); + if (!cf->is_capsnap) + ceph_free_cap_flush(cf); } wake_up_all(&ci->i_cap_wq); @@ -4490,22 +4491,29 @@ void inc_session_sequence(struct ceph_mds_session *s) } /* - * delayed work -- periodically trim expired leases, renew caps with mds + * delayed work -- periodically trim expired leases, renew caps with mds. If + * the @delay parameter is set to 0 or if it's more than 5 secs, the default + * workqueue delay value of 5 secs will be used. */ -static void schedule_delayed(struct ceph_mds_client *mdsc) +static void schedule_delayed(struct ceph_mds_client *mdsc, unsigned long delay) { - int delay = 5; - unsigned hz = round_jiffies_relative(HZ * delay); - schedule_delayed_work(&mdsc->delayed_work, hz); + unsigned long max_delay = HZ * 5; + + /* 5 secs default delay */ + if (!delay || (delay > max_delay)) + delay = max_delay; + schedule_delayed_work(&mdsc->delayed_work, + round_jiffies_relative(delay)); } static void delayed_work(struct work_struct *work) { - int i; struct ceph_mds_client *mdsc = container_of(work, struct ceph_mds_client, delayed_work.work); + unsigned long delay; int renew_interval; int renew_caps; + int i; dout("mdsc delayed_work\n"); @@ -4545,7 +4553,7 @@ static void delayed_work(struct work_struct *work) } mutex_unlock(&mdsc->mutex); - ceph_check_delayed_caps(mdsc); + delay = ceph_check_delayed_caps(mdsc); ceph_queue_cap_reclaim_work(mdsc); @@ -4553,7 +4561,7 @@ static void delayed_work(struct work_struct *work) maybe_recover_session(mdsc); - schedule_delayed(mdsc); + schedule_delayed(mdsc, delay); } int ceph_mdsc_init(struct ceph_fs_client *fsc) @@ -5030,7 +5038,7 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) mdsc->mdsmap->m_epoch); mutex_unlock(&mdsc->mutex); - schedule_delayed(mdsc); + schedule_delayed(mdsc, 0); return; bad_unlock: diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index abd9af7727ad..3c444b9cb17b 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -394,9 +394,11 @@ void ceph_mdsmap_destroy(struct ceph_mdsmap *m) { int i; - for (i = 0; i < m->possible_max_rank; i++) - kfree(m->m_info[i].export_targets); - kfree(m->m_info); + if (m->m_info) { + for (i = 0; i < m->possible_max_rank; i++) + kfree(m->m_info[i].export_targets); + kfree(m->m_info); + } kfree(m->m_data_pg_pools); kfree(m); } diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 4ac0606dcbd4..15105f9da3fd 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -67,19 +67,19 @@ void ceph_get_snap_realm(struct ceph_mds_client *mdsc, { lockdep_assert_held(&mdsc->snap_rwsem); - dout("get_realm %p %d -> %d\n", realm, - atomic_read(&realm->nref), atomic_read(&realm->nref)+1); /* - * since we _only_ increment realm refs or empty the empty - * list with snap_rwsem held, adjusting the empty list here is - * safe. we do need to protect against concurrent empty list - * additions, however. + * The 0->1 and 1->0 transitions must take the snap_empty_lock + * atomically with the refcount change. Go ahead and bump the + * nref here, unless it's 0, in which case we take the spinlock + * and then do the increment and remove it from the list. */ - if (atomic_inc_return(&realm->nref) == 1) { - spin_lock(&mdsc->snap_empty_lock); + if (atomic_inc_not_zero(&realm->nref)) + return; + + spin_lock(&mdsc->snap_empty_lock); + if (atomic_inc_return(&realm->nref) == 1) list_del_init(&realm->empty_item); - spin_unlock(&mdsc->snap_empty_lock); - } + spin_unlock(&mdsc->snap_empty_lock); } static void __insert_snap_realm(struct rb_root *root, @@ -208,28 +208,28 @@ static void __put_snap_realm(struct ceph_mds_client *mdsc, { lockdep_assert_held_write(&mdsc->snap_rwsem); - dout("__put_snap_realm %llx %p %d -> %d\n", realm->ino, realm, - atomic_read(&realm->nref), atomic_read(&realm->nref)-1); + /* + * We do not require the snap_empty_lock here, as any caller that + * increments the value must hold the snap_rwsem. + */ if (atomic_dec_and_test(&realm->nref)) __destroy_snap_realm(mdsc, realm); } /* - * caller needn't hold any locks + * See comments in ceph_get_snap_realm. Caller needn't hold any locks. */ void ceph_put_snap_realm(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm) { - dout("put_snap_realm %llx %p %d -> %d\n", realm->ino, realm, - atomic_read(&realm->nref), atomic_read(&realm->nref)-1); - if (!atomic_dec_and_test(&realm->nref)) + if (!atomic_dec_and_lock(&realm->nref, &mdsc->snap_empty_lock)) return; if (down_write_trylock(&mdsc->snap_rwsem)) { + spin_unlock(&mdsc->snap_empty_lock); __destroy_snap_realm(mdsc, realm); up_write(&mdsc->snap_rwsem); } else { - spin_lock(&mdsc->snap_empty_lock); list_add(&realm->empty_item, &mdsc->snap_empty); spin_unlock(&mdsc->snap_empty_lock); } @@ -487,6 +487,9 @@ static void ceph_queue_cap_snap(struct ceph_inode_info *ci) pr_err("ENOMEM allocating ceph_cap_snap on %p\n", inode); return; } + capsnap->cap_flush.is_capsnap = true; + INIT_LIST_HEAD(&capsnap->cap_flush.i_list); + INIT_LIST_HEAD(&capsnap->cap_flush.g_list); spin_lock(&ci->i_ceph_lock); used = __ceph_caps_used(ci); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 6b6332a5c113..b1a363641beb 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -182,8 +182,9 @@ struct ceph_cap { struct ceph_cap_flush { u64 tid; - int caps; /* 0 means capsnap */ + int caps; bool wake; /* wake up flush waiters when finish ? */ + bool is_capsnap; /* true means capsnap */ struct list_head g_list; // global struct list_head i_list; // per inode }; @@ -1167,7 +1168,7 @@ extern void ceph_flush_snaps(struct ceph_inode_info *ci, extern bool __ceph_should_report_size(struct ceph_inode_info *ci); extern void ceph_check_caps(struct ceph_inode_info *ci, int flags, struct ceph_mds_session *session); -extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc); +extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc); extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc); extern int ceph_drop_caps_for_unlink(struct inode *inode); extern int ceph_encode_inode_release(void **p, struct inode *inode, |