1 files changed, 187 insertions, 185 deletions

diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index ab7b9ec4c240..98dc092a905e 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include "misc.h"
 #include "ctree.h"
 #include "space-info.h"
 #include "sysfs.h"
@@ -7,7 +8,7 @@
 #include "free-space-cache.h"
 #include "ordered-data.h"
 #include "transaction.h"
-#include "math.h"
+#include "block-group.h"
 
 u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
 			  bool may_use_included)
@@ -33,23 +34,6 @@ void btrfs_clear_space_info_full(struct btrfs_fs_info *info)
 	rcu_read_unlock();
 }
 
-static const char *alloc_name(u64 flags)
-{
-	switch (flags) {
-	case BTRFS_BLOCK_GROUP_METADATA|BTRFS_BLOCK_GROUP_DATA:
-		return "mixed";
-	case BTRFS_BLOCK_GROUP_METADATA:
-		return "metadata";
-	case BTRFS_BLOCK_GROUP_DATA:
-		return "data";
-	case BTRFS_BLOCK_GROUP_SYSTEM:
-		return "system";
-	default:
-		WARN_ON(1);
-		return "invalid-combination";
-	};
-}
-
 static int create_space_info(struct btrfs_fs_info *info, u64 flags)
 {
 
@@ -79,13 +63,9 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags)
 	INIT_LIST_HEAD(&space_info->tickets);
 	INIT_LIST_HEAD(&space_info->priority_tickets);
 
-	ret = kobject_init_and_add(&space_info->kobj, &space_info_ktype,
-				    info->space_info_kobj, "%s",
-				    alloc_name(space_info->flags));
-	if (ret) {
-		kobject_put(&space_info->kobj);
+	ret = btrfs_sysfs_add_space_info_type(info, space_info);
+	if (ret)
 		return ret;
-	}
 
 	list_add_rcu(&space_info->list, &info->space_info);
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
@@ -151,9 +131,7 @@ void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags,
 	found->bytes_readonly += bytes_readonly;
 	if (total_bytes > 0)
 		found->full = 0;
-	btrfs_space_info_add_new_bytes(info, found,
-				       total_bytes - bytes_used -
-				       bytes_readonly);
+	btrfs_try_granting_tickets(info, found);
 	spin_unlock(&found->lock);
 	*space_info = found;
 }
@@ -187,9 +165,7 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
 			  enum btrfs_reserve_flush_enum flush,
 			  bool system_chunk)
 {
-	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
 	u64 profile;
-	u64 space_size;
 	u64 avail;
 	u64 used;
 	int factor;
@@ -203,22 +179,7 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
 	else
 		profile = btrfs_metadata_alloc_profile(fs_info);
 
-	used = btrfs_space_info_used(space_info, false);
-
-	/*
-	 * We only want to allow over committing if we have lots of actual space
-	 * free, but if we don't have enough space to handle the global reserve
-	 * space then we could end up having a real enospc problem when trying
-	 * to allocate a chunk or some other such important allocation.
-	 */
-	spin_lock(&global_rsv->lock);
-	space_size = calc_global_rsv_need_space(global_rsv);
-	spin_unlock(&global_rsv->lock);
-	if (used + space_size >= space_info->total_bytes)
-		return 0;
-
-	used += space_info->bytes_may_use;
-
+	used = btrfs_space_info_used(space_info, true);
 	avail = atomic64_read(&fs_info->free_chunk_space);
 
 	/*
@@ -249,103 +210,41 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
  * This is for space we already have accounted in space_info->bytes_may_use, so
  * basically when we're returning space from block_rsv's.
  */
-void btrfs_space_info_add_old_bytes(struct btrfs_fs_info *fs_info,
-				    struct btrfs_space_info *space_info,
-				    u64 num_bytes)
+void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info,
+				struct btrfs_space_info *space_info)
 {
-	struct reserve_ticket *ticket;
 	struct list_head *head;
-	u64 used;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_NO_FLUSH;
-	bool check_overcommit = false;
 
-	spin_lock(&space_info->lock);
-	head = &space_info->priority_tickets;
+	lockdep_assert_held(&space_info->lock);
 
-	/*
-	 * If we are over our limit then we need to check and see if we can
-	 * overcommit, and if we can't then we just need to free up our space
-	 * and not satisfy any requests.
-	 */
-	used = btrfs_space_info_used(space_info, true);
-	if (used - num_bytes >= space_info->total_bytes)
-		check_overcommit = true;
+	head = &space_info->priority_tickets;
 again:
-	while (!list_empty(head) && num_bytes) {
-		ticket = list_first_entry(head, struct reserve_ticket,
-					  list);
-		/*
-		 * We use 0 bytes because this space is already reserved, so
-		 * adding the ticket space would be a double count.
-		 */
-		if (check_overcommit &&
-		    !can_overcommit(fs_info, space_info, 0, flush, false))
-			break;
-		if (num_bytes >= ticket->bytes) {
-			list_del_init(&ticket->list);
-			num_bytes -= ticket->bytes;
-			ticket->bytes = 0;
-			space_info->tickets_id++;
-			wake_up(&ticket->wait);
-		} else {
-			ticket->bytes -= num_bytes;
-			num_bytes = 0;
-		}
-	}
-
-	if (num_bytes && head == &space_info->priority_tickets) {
-		head = &space_info->tickets;
-		flush = BTRFS_RESERVE_FLUSH_ALL;
-		goto again;
-	}
-	btrfs_space_info_update_bytes_may_use(fs_info, space_info, -num_bytes);
-	trace_btrfs_space_reservation(fs_info, "space_info",
-				      space_info->flags, num_bytes, 0);
-	spin_unlock(&space_info->lock);
-}
+	while (!list_empty(head)) {
+		struct reserve_ticket *ticket;
+		u64 used = btrfs_space_info_used(space_info, true);
 
-/*
- * This is for newly allocated space that isn't accounted in
- * space_info->bytes_may_use yet.  So if we allocate a chunk or unpin an extent
- * we use this helper.
- */
-void btrfs_space_info_add_new_bytes(struct btrfs_fs_info *fs_info,
-				    struct btrfs_space_info *space_info,
-				    u64 num_bytes)
-{
-	struct reserve_ticket *ticket;
-	struct list_head *head = &space_info->priority_tickets;
+		ticket = list_first_entry(head, struct reserve_ticket, list);
 
-again:
-	while (!list_empty(head) && num_bytes) {
-		ticket = list_first_entry(head, struct reserve_ticket,
-					  list);
-		if (num_bytes >= ticket->bytes) {
-			trace_btrfs_space_reservation(fs_info, "space_info",
-						      space_info->flags,
-						      ticket->bytes, 1);
-			list_del_init(&ticket->list);
-			num_bytes -= ticket->bytes;
+		/* Check and see if our ticket can be satisified now. */
+		if ((used + ticket->bytes <= space_info->total_bytes) ||
+		    can_overcommit(fs_info, space_info, ticket->bytes, flush,
+				   false)) {
 			btrfs_space_info_update_bytes_may_use(fs_info,
 							      space_info,
 							      ticket->bytes);
+			list_del_init(&ticket->list);
 			ticket->bytes = 0;
 			space_info->tickets_id++;
 			wake_up(&ticket->wait);
 		} else {
-			trace_btrfs_space_reservation(fs_info, "space_info",
-						      space_info->flags,
-						      num_bytes, 1);
-			btrfs_space_info_update_bytes_may_use(fs_info,
-							      space_info,
-							      num_bytes);
-			ticket->bytes -= num_bytes;
-			num_bytes = 0;
+			break;
 		}
 	}
 
-	if (num_bytes && head == &space_info->priority_tickets) {
+	if (head == &space_info->priority_tickets) {
 		head = &space_info->tickets;
+		flush = BTRFS_RESERVE_FLUSH_ALL;
 		goto again;
 	}
 }
@@ -359,14 +258,11 @@ do {									\
 	spin_unlock(&__rsv->lock);					\
 } while (0)
 
-void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
-			   struct btrfs_space_info *info, u64 bytes,
-			   int dump_block_groups)
+static void __btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
+				    struct btrfs_space_info *info)
 {
-	struct btrfs_block_group_cache *cache;
-	int index = 0;
+	lockdep_assert_held(&info->lock);
 
-	spin_lock(&info->lock);
 	btrfs_info(fs_info, "space_info %llu has %llu free, is %sfull",
 		   info->flags,
 		   info->total_bytes - btrfs_space_info_used(info, true),
@@ -376,7 +272,6 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
 		info->total_bytes, info->bytes_used, info->bytes_pinned,
 		info->bytes_reserved, info->bytes_may_use,
 		info->bytes_readonly);
-	spin_unlock(&info->lock);
 
 	DUMP_BLOCK_RSV(fs_info, global_block_rsv);
 	DUMP_BLOCK_RSV(fs_info, trans_block_rsv);
@@ -384,6 +279,19 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
 	DUMP_BLOCK_RSV(fs_info, delayed_block_rsv);
 	DUMP_BLOCK_RSV(fs_info, delayed_refs_rsv);
 
+}
+
+void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
+			   struct btrfs_space_info *info, u64 bytes,
+			   int dump_block_groups)
+{
+	struct btrfs_block_group_cache *cache;
+	int index = 0;
+
+	spin_lock(&info->lock);
+	__btrfs_dump_space_info(fs_info, info);
+	spin_unlock(&info->lock);
+
 	if (!dump_block_groups)
 		return;
 
@@ -432,7 +340,7 @@ static inline u64 calc_reclaim_items_nr(struct btrfs_fs_info *fs_info,
 	u64 bytes;
 	u64 nr;
 
-	bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
+	bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
 	nr = div64_u64(to_reclaim, bytes);
 	if (!nr)
 		nr = 1;
@@ -557,12 +465,19 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 	struct btrfs_trans_handle *trans;
 	u64 bytes_needed;
 	u64 reclaim_bytes = 0;
+	u64 cur_free_bytes = 0;
 
 	trans = (struct btrfs_trans_handle *)current->journal_info;
 	if (trans)
 		return -EAGAIN;
 
 	spin_lock(&space_info->lock);
+	cur_free_bytes = btrfs_space_info_used(space_info, true);
+	if (cur_free_bytes < space_info->total_bytes)
+		cur_free_bytes = space_info->total_bytes - cur_free_bytes;
+	else
+		cur_free_bytes = 0;
+
 	if (!list_empty(&space_info->priority_tickets))
 		ticket = list_first_entry(&space_info->priority_tickets,
 					  struct reserve_ticket, list);
@@ -570,6 +485,11 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 		ticket = list_first_entry(&space_info->tickets,
 					  struct reserve_ticket, list);
 	bytes_needed = (ticket) ? ticket->bytes : 0;
+
+	if (bytes_needed > cur_free_bytes)
+		bytes_needed -= cur_free_bytes;
+	else
+		bytes_needed = 0;
 	spin_unlock(&space_info->lock);
 
 	if (!bytes_needed)
@@ -684,7 +604,7 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 		if (ret > 0 || ret == -ENOSPC)
 			ret = 0;
 		break;
-	case COMMIT_TRANS:
+	case RUN_DELAYED_IPUTS:
 		/*
 		 * If we have pending delayed iputs then we could free up a
 		 * bunch of pinned space, so make sure we run the iputs before
@@ -692,7 +612,8 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 		 */
 		btrfs_run_delayed_iputs(fs_info);
 		btrfs_wait_on_delayed_iputs(fs_info);
-
+		break;
+	case COMMIT_TRANS:
 		ret = may_commit_transaction(fs_info, space_info);
 		break;
 	default:
@@ -762,19 +683,70 @@ static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
 		!test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state));
 }
 
-static bool wake_all_tickets(struct list_head *head)
+/*
+ * maybe_fail_all_tickets - we've exhausted our flushing, start failing tickets
+ * @fs_info - fs_info for this fs
+ * @space_info - the space info we were flushing
+ *
+ * We call this when we've exhausted our flushing ability and haven't made
+ * progress in satisfying tickets.  The reservation code handles tickets in
+ * order, so if there is a large ticket first and then smaller ones we could
+ * very well satisfy the smaller tickets.  This will attempt to wake up any
+ * tickets in the list to catch this case.
+ *
+ * This function returns true if it was able to make progress by clearing out
+ * other tickets, or if it stumbles across a ticket that was smaller than the
+ * first ticket.
+ */
+static bool maybe_fail_all_tickets(struct btrfs_fs_info *fs_info,
+				   struct btrfs_space_info *space_info)
 {
 	struct reserve_ticket *ticket;
+	u64 tickets_id = space_info->tickets_id;
+	u64 first_ticket_bytes = 0;
+
+	if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
+		btrfs_info(fs_info, "cannot satisfy tickets, dumping space info");
+		__btrfs_dump_space_info(fs_info, space_info);
+	}
+
+	while (!list_empty(&space_info->tickets) &&
+	       tickets_id == space_info->tickets_id) {
+		ticket = list_first_entry(&space_info->tickets,
+					  struct reserve_ticket, list);
+
+		/*
+		 * may_commit_transaction will avoid committing the transaction
+		 * if it doesn't feel like the space reclaimed by the commit
+		 * would result in the ticket succeeding.  However if we have a
+		 * smaller ticket in the queue it may be small enough to be
+		 * satisified by committing the transaction, so if any
+		 * subsequent ticket is smaller than the first ticket go ahead
+		 * and send us back for another loop through the enospc flushing
+		 * code.
+		 */
+		if (first_ticket_bytes == 0)
+			first_ticket_bytes = ticket->bytes;
+		else if (first_ticket_bytes > ticket->bytes)
+			return true;
+
+		if (btrfs_test_opt(fs_info, ENOSPC_DEBUG))
+			btrfs_info(fs_info, "failing ticket with %llu bytes",
+				   ticket->bytes);
 
-	while (!list_empty(head)) {
-		ticket = list_first_entry(head, struct reserve_ticket, list);
 		list_del_init(&ticket->list);
 		ticket->error = -ENOSPC;
 		wake_up(&ticket->wait);
-		if (ticket->bytes != ticket->orig_bytes)
-			return true;
+
+		/*
+		 * We're just throwing tickets away, so more flushing may not
+		 * trip over btrfs_try_granting_tickets, so we need to call it
+		 * here to see if we can make progress with the next ticket in
+		 * the list.
+		 */
+		btrfs_try_granting_tickets(fs_info, space_info);
 	}
-	return false;
+	return (tickets_id != space_info->tickets_id);
 }
 
 /*
@@ -842,7 +814,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 		if (flush_state > COMMIT_TRANS) {
 			commit_cycles++;
 			if (commit_cycles > 2) {
-				if (wake_all_tickets(&space_info->tickets)) {
+				if (maybe_fail_all_tickets(fs_info, space_info)) {
 					flush_state = FLUSH_DELAYED_ITEMS_NR;
 					commit_cycles--;
 				} else {
@@ -867,9 +839,22 @@ static const enum btrfs_flush_state priority_flush_states[] = {
 	ALLOC_CHUNK,
 };
 
+static const enum btrfs_flush_state evict_flush_states[] = {
+	FLUSH_DELAYED_ITEMS_NR,
+	FLUSH_DELAYED_ITEMS,
+	FLUSH_DELAYED_REFS_NR,
+	FLUSH_DELAYED_REFS,
+	FLUSH_DELALLOC,
+	FLUSH_DELALLOC_WAIT,
+	ALLOC_CHUNK,
+	COMMIT_TRANS,
+};
+
 static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
-					    struct btrfs_space_info *space_info,
-					    struct reserve_ticket *ticket)
+				struct btrfs_space_info *space_info,
+				struct reserve_ticket *ticket,
+				const enum btrfs_flush_state *states,
+				int states_nr)
 {
 	u64 to_reclaim;
 	int flush_state;
@@ -885,8 +870,7 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 
 	flush_state = 0;
 	do {
-		flush_space(fs_info, space_info, to_reclaim,
-			    priority_flush_states[flush_state]);
+		flush_space(fs_info, space_info, to_reclaim, states[flush_state]);
 		flush_state++;
 		spin_lock(&space_info->lock);
 		if (ticket->bytes == 0) {
@@ -894,23 +878,22 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 			return;
 		}
 		spin_unlock(&space_info->lock);
-	} while (flush_state < ARRAY_SIZE(priority_flush_states));
+	} while (flush_state < states_nr);
 }
 
-static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
-			       struct btrfs_space_info *space_info,
-			       struct reserve_ticket *ticket)
+static void wait_reserve_ticket(struct btrfs_fs_info *fs_info,
+				struct btrfs_space_info *space_info,
+				struct reserve_ticket *ticket)
 
 {
 	DEFINE_WAIT(wait);
-	u64 reclaim_bytes = 0;
 	int ret = 0;
 
 	spin_lock(&space_info->lock);
 	while (ticket->bytes > 0 && ticket->error == 0) {
 		ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE);
 		if (ret) {
-			ret = -EINTR;
+			ticket->error = -EINTR;
 			break;
 		}
 		spin_unlock(&space_info->lock);
@@ -920,17 +903,54 @@ static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
 		finish_wait(&ticket->wait, &wait);
 		spin_lock(&space_info->lock);
 	}
-	if (!ret)
-		ret = ticket->error;
-	if (!list_empty(&ticket->list))
-		list_del_init(&ticket->list);
-	if (ticket->bytes && ticket->bytes < ticket->orig_bytes)
-		reclaim_bytes = ticket->orig_bytes - ticket->bytes;
 	spin_unlock(&space_info->lock);
+}
+
+/**
+ * handle_reserve_ticket - do the appropriate flushing and waiting for a ticket
+ * @fs_info - the fs
+ * @space_info - the space_info for the reservation
+ * @ticket - the ticket for the reservation
+ * @flush - how much we can flush
+ *
+ * This does the work of figuring out how to flush for the ticket, waiting for
+ * the reservation, and returning the appropriate error if there is one.
+ */
+static int handle_reserve_ticket(struct btrfs_fs_info *fs_info,
+				 struct btrfs_space_info *space_info,
+				 struct reserve_ticket *ticket,
+				 enum btrfs_reserve_flush_enum flush)
+{
+	int ret;
+
+	switch (flush) {
+	case BTRFS_RESERVE_FLUSH_ALL:
+		wait_reserve_ticket(fs_info, space_info, ticket);
+		break;
+	case BTRFS_RESERVE_FLUSH_LIMIT:
+		priority_reclaim_metadata_space(fs_info, space_info, ticket,
+						priority_flush_states,
+						ARRAY_SIZE(priority_flush_states));
+		break;
+	case BTRFS_RESERVE_FLUSH_EVICT:
+		priority_reclaim_metadata_space(fs_info, space_info, ticket,
+						evict_flush_states,
+						ARRAY_SIZE(evict_flush_states));
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
 
-	if (reclaim_bytes)
-		btrfs_space_info_add_old_bytes(fs_info, space_info,
-					       reclaim_bytes);
+	spin_lock(&space_info->lock);
+	ret = ticket->error;
+	if (ticket->bytes || ticket->error) {
+		list_del_init(&ticket->list);
+		if (!ret)
+			ret = -ENOSPC;
+	}
+	spin_unlock(&space_info->lock);
+	ASSERT(list_empty(&ticket->list));
 	return ret;
 }
 
@@ -956,8 +976,8 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 {
 	struct reserve_ticket ticket;
 	u64 used;
-	u64 reclaim_bytes = 0;
 	int ret = 0;
+	bool pending_tickets;
 
 	ASSERT(orig_bytes);
 	ASSERT(!current->journal_info || flush != BTRFS_RESERVE_FLUSH_ALL);
@@ -965,18 +985,19 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 	spin_lock(&space_info->lock);
 	ret = -ENOSPC;
 	used = btrfs_space_info_used(space_info, true);
+	pending_tickets = !list_empty(&space_info->tickets) ||
+		!list_empty(&space_info->priority_tickets);
 
 	/*
 	 * Carry on if we have enough space (short-circuit) OR call
 	 * can_overcommit() to ensure we can overcommit to continue.
 	 */
-	if ((used + orig_bytes <= space_info->total_bytes) ||
-	    can_overcommit(fs_info, space_info, orig_bytes, flush,
-			   system_chunk)) {
+	if (!pending_tickets &&
+	    ((used + orig_bytes <= space_info->total_bytes) ||
+	     can_overcommit(fs_info, space_info, orig_bytes, flush,
+			   system_chunk))) {
 		btrfs_space_info_update_bytes_may_use(fs_info, space_info,
 						      orig_bytes);
-		trace_btrfs_space_reservation(fs_info, "space_info",
-					      space_info->flags, orig_bytes, 1);
 		ret = 0;
 	}
 
@@ -988,7 +1009,6 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 	 * the list and we will do our own flushing further down.
 	 */
 	if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
-		ticket.orig_bytes = orig_bytes;
 		ticket.bytes = orig_bytes;
 		ticket.error = 0;
 		init_waitqueue_head(&ticket.wait);
@@ -1028,25 +1048,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 	if (!ret || flush == BTRFS_RESERVE_NO_FLUSH)
 		return ret;
 
-	if (flush == BTRFS_RESERVE_FLUSH_ALL)
-		return wait_reserve_ticket(fs_info, space_info, &ticket);
-
-	ret = 0;
-	priority_reclaim_metadata_space(fs_info, space_info, &ticket);
-	spin_lock(&space_info->lock);
-	if (ticket.bytes) {
-		if (ticket.bytes < orig_bytes)
-			reclaim_bytes = orig_bytes - ticket.bytes;
-		list_del_init(&ticket.list);
-		ret = -ENOSPC;
-	}
-	spin_unlock(&space_info->lock);
-
-	if (reclaim_bytes)
-		btrfs_space_info_add_old_bytes(fs_info, space_info,
-					       reclaim_bytes);
-	ASSERT(list_empty(&ticket.list));
-	return ret;
+	return handle_reserve_ticket(fs_info, space_info, &ticket, flush);
 }
 
 /**