1 files changed, 68 insertions, 49 deletions

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index d019c98eb839..eae7427062cf 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -23,6 +23,7 @@
 #include "xfs_reflink.h"
 #include "xfs_ialloc.h"
 #include "xfs_ag.h"
+#include "xfs_log_priv.h"
 
 #include <linux/iversion.h>
 
@@ -77,7 +78,7 @@ xfs_inode_alloc(
 	 * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL
 	 * and return NULL here on ENOMEM.
 	 */
-	ip = kmem_cache_alloc(xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL);
+	ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL);
 
 	if (inode_init_always(mp->m_super, VFS_I(ip))) {
 		kmem_cache_free(xfs_inode_cache, ip);
@@ -87,6 +88,7 @@ xfs_inode_alloc(
 	/* VFS doesn't initialise i_mode or i_state! */
 	VFS_I(ip)->i_mode = 0;
 	VFS_I(ip)->i_state = 0;
+	mapping_set_large_folios(VFS_I(ip)->i_mapping);
 
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
@@ -96,8 +98,9 @@ xfs_inode_alloc(
 	ip->i_ino = ino;
 	ip->i_mount = mp;
 	memset(&ip->i_imap, 0, sizeof(struct xfs_imap));
-	ip->i_afp = NULL;
 	ip->i_cowfp = NULL;
+	memset(&ip->i_af, 0, sizeof(ip->i_af));
+	ip->i_af.if_format = XFS_DINODE_FMT_EXTENTS;
 	memset(&ip->i_df, 0, sizeof(ip->i_df));
 	ip->i_flags = 0;
 	ip->i_delayed_blks = 0;
@@ -109,6 +112,8 @@ xfs_inode_alloc(
 	INIT_WORK(&ip->i_ioend_work, xfs_end_io);
 	INIT_LIST_HEAD(&ip->i_ioend_list);
 	spin_lock_init(&ip->i_ioend_lock);
+	ip->i_next_unlinked = NULLAGINO;
+	ip->i_prev_unlinked = NULLAGINO;
 
 	return ip;
 }
@@ -128,10 +133,8 @@ xfs_inode_free_callback(
 		break;
 	}
 
-	if (ip->i_afp) {
-		xfs_idestroy_fork(ip->i_afp);
-		kmem_cache_free(xfs_ifork_cache, ip->i_afp);
-	}
+	xfs_ifork_zap_attr(ip);
+
 	if (ip->i_cowfp) {
 		xfs_idestroy_fork(ip->i_cowfp);
 		kmem_cache_free(xfs_ifork_cache, ip->i_cowfp);
@@ -320,6 +323,7 @@ xfs_reinit_inode(
 	inode->i_rdev = dev;
 	inode->i_uid = uid;
 	inode->i_gid = gid;
+	mapping_set_large_folios(inode->i_mapping);
 	return error;
 }
 
@@ -437,7 +441,7 @@ xfs_inodegc_queue_all(
 	for_each_online_cpu(cpu) {
 		gc = per_cpu_ptr(mp->m_inodegc, cpu);
 		if (!llist_empty(&gc->list))
-			queue_work_on(cpu, mp->m_inodegc_wq, &gc->work);
+			mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0);
 	}
 }
 
@@ -592,7 +596,7 @@ xfs_iget_cache_miss(
 	 */
 	if (xfs_has_v3inodes(mp) &&
 	    (flags & XFS_IGET_CREATE) && !xfs_has_ikeep(mp)) {
-		VFS_I(ip)->i_generation = prandom_u32();
+		VFS_I(ip)->i_generation = get_random_u32();
 	} else {
 		struct xfs_buf		*bp;
 
@@ -871,9 +875,16 @@ xfs_reclaim_inode(
 	if (xfs_iflags_test_and_set(ip, XFS_IFLUSHING))
 		goto out_iunlock;
 
-	if (xfs_is_shutdown(ip->i_mount)) {
+	/*
+	 * Check for log shutdown because aborting the inode can move the log
+	 * tail and corrupt in memory state. This is fine if the log is shut
+	 * down, but if the log is still active and only the mount is shut down
+	 * then the in-memory log tail movement caused by the abort can be
+	 * incorrectly propagated to disk.
+	 */
+	if (xlog_is_shutdown(ip->i_mount->m_log)) {
 		xfs_iunpin_wait(ip);
-		xfs_iflush_abort(ip);
+		xfs_iflush_shutdown_abort(ip);
 		goto reclaim;
 	}
 	if (xfs_ipincount(ip))
@@ -902,6 +913,7 @@ reclaim:
 	ip->i_checked = 0;
 	spin_unlock(&ip->i_flags_lock);
 
+	ASSERT(!ip->i_itemp || ip->i_itemp->ili_item.li_buf == NULL);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
 	XFS_STATS_INC(ip->i_mount, xs_ig_reclaims);
@@ -1764,7 +1776,7 @@ xfs_check_delalloc(
 	struct xfs_inode	*ip,
 	int			whichfork)
 {
-	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
 	struct xfs_bmbt_irec	got;
 	struct xfs_iext_cursor	icur;
 
@@ -1831,8 +1843,8 @@ void
 xfs_inodegc_worker(
 	struct work_struct	*work)
 {
-	struct xfs_inodegc	*gc = container_of(work, struct xfs_inodegc,
-							work);
+	struct xfs_inodegc	*gc = container_of(to_delayed_work(work),
+						struct xfs_inodegc, work);
 	struct llist_node	*node = llist_del_all(&gc->list);
 	struct xfs_inode	*ip, *n;
 
@@ -1852,28 +1864,30 @@ xfs_inodegc_worker(
 }
 
 /*
- * Force all currently queued inode inactivation work to run immediately, and
- * wait for the work to finish. Two pass - queue all the work first pass, wait
- * for it in a second pass.
+ * Expedite all pending inodegc work to run immediately. This does not wait for
+ * completion of the work.
  */
 void
-xfs_inodegc_flush(
+xfs_inodegc_push(
 	struct xfs_mount	*mp)
 {
-	struct xfs_inodegc	*gc;
-	int			cpu;
-
 	if (!xfs_is_inodegc_enabled(mp))
 		return;
-
-	trace_xfs_inodegc_flush(mp, __return_address);
-
+	trace_xfs_inodegc_push(mp, __return_address);
 	xfs_inodegc_queue_all(mp);
+}
 
-	for_each_online_cpu(cpu) {
-		gc = per_cpu_ptr(mp->m_inodegc, cpu);
-		flush_work(&gc->work);
-	}
+/*
+ * Force all currently queued inode inactivation work to run immediately and
+ * wait for the work to finish.
+ */
+void
+xfs_inodegc_flush(
+	struct xfs_mount	*mp)
+{
+	xfs_inodegc_push(mp);
+	trace_xfs_inodegc_flush(mp, __return_address);
+	flush_workqueue(mp->m_inodegc_wq);
 }
 
 /*
@@ -1884,18 +1898,12 @@ void
 xfs_inodegc_stop(
 	struct xfs_mount	*mp)
 {
-	struct xfs_inodegc	*gc;
-	int			cpu;
-
 	if (!xfs_clear_inodegc_enabled(mp))
 		return;
 
 	xfs_inodegc_queue_all(mp);
+	drain_workqueue(mp->m_inodegc_wq);
 
-	for_each_online_cpu(cpu) {
-		gc = per_cpu_ptr(mp->m_inodegc, cpu);
-		cancel_work_sync(&gc->work);
-	}
 	trace_xfs_inodegc_stop(mp, __return_address);
 }
 
@@ -1920,13 +1928,16 @@ xfs_inodegc_want_queue_rt_file(
 	struct xfs_inode	*ip)
 {
 	struct xfs_mount	*mp = ip->i_mount;
-	uint64_t		freertx;
 
 	if (!XFS_IS_REALTIME_INODE(ip))
 		return false;
 
-	freertx = READ_ONCE(mp->m_sb.sb_frextents);
-	return freertx < mp->m_low_rtexts[XFS_LOWSP_5_PCNT];
+	if (__percpu_counter_compare(&mp->m_frextents,
+				mp->m_low_rtexts[XFS_LOWSP_5_PCNT],
+				XFS_FDBLOCKS_BATCH) < 0)
+		return true;
+
+	return false;
 }
 #else
 # define xfs_inodegc_want_queue_rt_file(ip)	(false)
@@ -2015,6 +2026,7 @@ xfs_inodegc_queue(
 	struct xfs_inodegc	*gc;
 	int			items;
 	unsigned int		shrinker_hits;
+	unsigned long		queue_delay = 1;
 
 	trace_xfs_inode_set_need_inactive(ip);
 	spin_lock(&ip->i_flags_lock);
@@ -2026,19 +2038,26 @@ xfs_inodegc_queue(
 	items = READ_ONCE(gc->items);
 	WRITE_ONCE(gc->items, items + 1);
 	shrinker_hits = READ_ONCE(gc->shrinker_hits);
-	put_cpu_ptr(gc);
 
-	if (!xfs_is_inodegc_enabled(mp))
+	/*
+	 * We queue the work while holding the current CPU so that the work
+	 * is scheduled to run on this CPU.
+	 */
+	if (!xfs_is_inodegc_enabled(mp)) {
+		put_cpu_ptr(gc);
 		return;
-
-	if (xfs_inodegc_want_queue_work(ip, items)) {
-		trace_xfs_inodegc_queue(mp, __return_address);
-		queue_work(mp->m_inodegc_wq, &gc->work);
 	}
 
+	if (xfs_inodegc_want_queue_work(ip, items))
+		queue_delay = 0;
+
+	trace_xfs_inodegc_queue(mp, __return_address);
+	mod_delayed_work(mp->m_inodegc_wq, &gc->work, queue_delay);
+	put_cpu_ptr(gc);
+
 	if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) {
 		trace_xfs_inodegc_throttle(mp, __return_address);
-		flush_work(&gc->work);
+		flush_delayed_work(&gc->work);
 	}
 }
 
@@ -2055,7 +2074,7 @@ xfs_inodegc_cpu_dead(
 	unsigned int		count = 0;
 
 	dead_gc = per_cpu_ptr(mp->m_inodegc, dead_cpu);
-	cancel_work_sync(&dead_gc->work);
+	cancel_delayed_work_sync(&dead_gc->work);
 
 	if (llist_empty(&dead_gc->list))
 		return;
@@ -2074,12 +2093,12 @@ xfs_inodegc_cpu_dead(
 	llist_add_batch(first, last, &gc->list);
 	count += READ_ONCE(gc->items);
 	WRITE_ONCE(gc->items, count);
-	put_cpu_ptr(gc);
 
 	if (xfs_is_inodegc_enabled(mp)) {
 		trace_xfs_inodegc_queue(mp, __return_address);
-		queue_work(mp->m_inodegc_wq, &gc->work);
+		mod_delayed_work(mp->m_inodegc_wq, &gc->work, 0);
 	}
+	put_cpu_ptr(gc);
 }
 
 /*
@@ -2174,7 +2193,7 @@ xfs_inodegc_shrinker_scan(
 			unsigned int	h = READ_ONCE(gc->shrinker_hits);
 
 			WRITE_ONCE(gc->shrinker_hits, h + 1);
-			queue_work_on(cpu, mp->m_inodegc_wq, &gc->work);
+			mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0);
 			no_items = false;
 		}
 	}
@@ -2202,5 +2221,5 @@ xfs_inodegc_register_shrinker(
 	shrink->flags = SHRINKER_NONSLAB;
 	shrink->batch = XFS_INODEGC_SHRINKER_BATCH;
 
-	return register_shrinker(shrink);
+	return register_shrinker(shrink, "xfs-inodegc:%s", mp->m_super->s_id);
 }