Merge android-4.4.137 (a2e2217) into msm-4.4

* refs/heads/tmp-a2e2217
  Linux 4.4.137
  net: metrics: add proper netlink validation
  net: phy: broadcom: Fix bcm_write_exp()
  rtnetlink: validate attributes in do_setlink()
  team: use netdev_features_t instead of u32
  net/mlx4: Fix irq-unsafe spinlock usage
  qed: Fix mask for physical address in ILT entry
  packet: fix reserve calculation
  net: usb: cdc_mbim: add flag FLAG_SEND_ZLP
  net/packet: refine check for priv area size
  netdev-FAQ: clarify DaveM's position for stable backports
  isdn: eicon: fix a missing-check bug
  ipv4: remove warning in ip_recv_error
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  enic: set DMA mask to 47 bit
  dccp: don't free ccid2_hc_tx_sock struct in dccp_disconnect()
  bnx2x: use the right constant
  brcmfmac: Fix check for ISO3166 code
  drm: set FMODE_UNSIGNED_OFFSET for drm files
  xfs: fix incorrect log_flushed on fsync
  kconfig: Avoid format overflow warning from GCC 8.1
  mmap: relax file size limit for regular files
  mmap: introduce sane default mmap limits
  tpm: self test failure should not cause suspend to fail
  tpm: do not suspend/resume if power stays on
  ANDROID: Update arm64 ranchu64_defconfig
  Linux 4.4.136
  sparc64: Fix build warnings with gcc 7.
  mm: fix the NULL mapping case in __isolate_lru_page()
  fix io_destroy()/aio_complete() race
  Kbuild: change CC_OPTIMIZE_FOR_SIZE definition
  drm/i915: Disable LVDS on Radiant P845
  hwtracing: stm: fix build error on some arches
  stm class: Use vmalloc for the master map
  scsi: scsi_transport_srp: Fix shost to rport translation
  MIPS: prctl: Disallow FRE without FR with PR_SET_FP_MODE requests
  MIPS: ptrace: Fix PTRACE_PEEKUSR requests for 64-bit FGRs
  iio:kfifo_buf: check for uint overflow
  dmaengine: usb-dmac: fix endless loop in usb_dmac_chan_terminate_all()
  i2c: rcar: revoke START request early
  i2c: rcar: check master irqs before slave irqs
  i2c: rcar: don't issue stop when HW does it automatically
  i2c: rcar: init new messages in irq
  i2c: rcar: refactor setup of a msg
  i2c: rcar: remove spinlock
  i2c: rcar: remove unused IOERROR state
  i2c: rcar: rework hw init
  i2c: rcar: make sure clocks are on when doing clock calculation
  tcp: avoid integer overflows in tcp_rcv_space_adjust()
  irda: fix overly long udelay()
  ASoC: Intel: sst: remove redundant variable dma_dev_name
  rtlwifi: rtl8192cu: Remove variable self-assignment in rf.c
  cfg80211: further limit wiphy names to 64 bytes
  selinux: KASAN: slab-out-of-bounds in xattr_getsecurity
  tracing: Fix crash when freeing instances with event triggers
  Input: elan_i2c_smbus - fix corrupted stack
  Revert "ima: limit file hash setting by user to fix and log modes"
  xfs: detect agfl count corruption and reset agfl
  sh: New gcc support
  USB: serial: cp210x: use tcflag_t to fix incompatible pointer type
  powerpc/64s: Clear PCR on boot
  arm64: lse: Add early clobbers to some input/output asm operands
  FROMLIST: f2fs: run fstrim asynchronously if runtime discard is on
  goldfish: pipe: ANDROID: address must be written as __pa(x), not x
  goldfish: pipe: ANDROID: add missing check for memory allocated
  goldfish: pipe: ANDROID: remove redundant blank lines
  Update arch/x86/configs/x86_64_ranchu_defconfig
  ANDROID: x86_64_cuttlefish_defconfig: Enable F2FS
  ANDROID: Update x86_64_cuttlefish_defconfig
  FROMLIST: f2fs: early updates queued for v4.18-rc1

Change-Id: I314254168cd5ad06a7c6bca2fa68c8a6ae6c257d
Signed-off-by: Srinivasarao P <spathi@codeaurora.org>

10 files changed, 252 insertions, 141 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 98d327a8955d..c4b508605bab 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -629,9 +629,8 @@ static void free_ioctx_users(struct percpu_ref *ref)
 	while (!list_empty(&ctx->active_reqs)) {
 		req = list_first_entry(&ctx->active_reqs,
 				       struct aio_kiocb, ki_list);
-
-		list_del_init(&req->ki_list);
 		kiocb_cancel(req);
+		list_del_init(&req->ki_list);
 	}
 
 	spin_unlock_irq(&ctx->ctx_lock);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d0bfcfed35e2..97c17b3d984c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -238,15 +238,12 @@ enum {
 #define	CP_DISCARD	0x00000010
 #define CP_TRIMMED	0x00000020
 
-#define DEF_BATCHED_TRIM_SECTIONS	2048
-#define BATCHED_TRIM_SEGMENTS(sbi)	\
-		(GET_SEG_FROM_SEC(sbi, SM_I(sbi)->trim_sections))
-#define BATCHED_TRIM_BLOCKS(sbi)	\
-		(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
 #define MAX_DISCARD_BLOCKS(sbi)		BLKS_PER_SEC(sbi)
 #define DEF_MAX_DISCARD_REQUEST		8	/* issue 8 discards per round */
+#define DEF_MAX_DISCARD_LEN		512	/* Max. 2MB per discard */
 #define DEF_MIN_DISCARD_ISSUE_TIME	50	/* 50 ms, if exists */
 #define DEF_MAX_DISCARD_ISSUE_TIME	60000	/* 60 s, if no candidates */
+#define DEF_DISCARD_URGENT_UTIL		80	/* do more discard over 80% */
 #define DEF_CP_INTERVAL			60	/* 60 secs */
 #define DEF_IDLE_INTERVAL		5	/* 5 secs */
 
@@ -753,7 +750,8 @@ static inline void set_extent_info(struct extent_info *ei, unsigned int fofs,
 static inline bool __is_discard_mergeable(struct discard_info *back,
 						struct discard_info *front)
 {
-	return back->lstart + back->len == front->lstart;
+	return (back->lstart + back->len == front->lstart) &&
+		(back->len + front->len < DEF_MAX_DISCARD_LEN);
 }
 
 static inline bool __is_discard_back_mergeable(struct discard_info *cur,
@@ -1139,6 +1137,7 @@ enum {
 enum fsync_mode {
 	FSYNC_MODE_POSIX,	/* fsync follows posix semantics */
 	FSYNC_MODE_STRICT,	/* fsync behaves in line with ext4 */
+	FSYNC_MODE_NOBARRIER,	/* fsync behaves nobarrier based on posix */
 };
 
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
@@ -2853,8 +2852,6 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
 void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
 void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
 bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
-void init_discard_policy(struct discard_policy *dpolicy, int discard_type,
-						unsigned int granularity);
 void drop_discard_cmd(struct f2fs_sb_info *sbi);
 void stop_discard_thread(struct f2fs_sb_info *sbi);
 bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 7587758a285f..40d03d58b390 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -309,7 +309,7 @@ sync_nodes:
 	remove_ino_entry(sbi, ino, APPEND_INO);
 	clear_inode_flag(inode, FI_APPEND_WRITE);
 flush_out:
-	if (!atomic)
+	if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER)
 		ret = f2fs_issue_flush(sbi, inode->i_ino);
 	if (!ret) {
 		remove_ino_entry(sbi, ino, UPDATE_INO);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 01bc94df9f00..a02d5c1a7ed2 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -996,6 +996,39 @@ static void __check_sit_bitmap(struct f2fs_sb_info *sbi,
 #endif
 }
 
+static void __init_discard_policy(struct f2fs_sb_info *sbi,
+				struct discard_policy *dpolicy,
+				int discard_type, unsigned int granularity)
+{
+	/* common policy */
+	dpolicy->type = discard_type;
+	dpolicy->sync = true;
+	dpolicy->granularity = granularity;
+
+	dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+	dpolicy->io_aware_gran = MAX_PLIST_NUM;
+
+	if (discard_type == DPOLICY_BG) {
+		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+		dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
+		dpolicy->io_aware = true;
+		dpolicy->sync = false;
+		if (utilization(sbi) > DEF_DISCARD_URGENT_UTIL) {
+			dpolicy->granularity = 1;
+			dpolicy->max_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+		}
+	} else if (discard_type == DPOLICY_FORCE) {
+		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
+		dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
+		dpolicy->io_aware = false;
+	} else if (discard_type == DPOLICY_FSTRIM) {
+		dpolicy->io_aware = false;
+	} else if (discard_type == DPOLICY_UMOUNT) {
+		dpolicy->io_aware = false;
+	}
+}
+
+
 /* this function is copied from blkdev_issue_discard from block/blk-lib.c */
 static void __submit_discard_cmd(struct f2fs_sb_info *sbi,
 						struct discard_policy *dpolicy,
@@ -1210,68 +1243,6 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi,
 	return 0;
 }
 
-static void __issue_discard_cmd_range(struct f2fs_sb_info *sbi,
-					struct discard_policy *dpolicy,
-					unsigned int start, unsigned int end)
-{
-	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
-	struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
-	struct rb_node **insert_p = NULL, *insert_parent = NULL;
-	struct discard_cmd *dc;
-	struct blk_plug plug;
-	int issued;
-
-next:
-	issued = 0;
-
-	mutex_lock(&dcc->cmd_lock);
-	f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
-
-	dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root,
-					NULL, start,
-					(struct rb_entry **)&prev_dc,
-					(struct rb_entry **)&next_dc,
-					&insert_p, &insert_parent, true);
-	if (!dc)
-		dc = next_dc;
-
-	blk_start_plug(&plug);
-
-	while (dc && dc->lstart <= end) {
-		struct rb_node *node;
-
-		if (dc->len < dpolicy->granularity)
-			goto skip;
-
-		if (dc->state != D_PREP) {
-			list_move_tail(&dc->list, &dcc->fstrim_list);
-			goto skip;
-		}
-
-		__submit_discard_cmd(sbi, dpolicy, dc);
-
-		if (++issued >= dpolicy->max_requests) {
-			start = dc->lstart + dc->len;
-
-			blk_finish_plug(&plug);
-			mutex_unlock(&dcc->cmd_lock);
-
-			schedule();
-
-			goto next;
-		}
-skip:
-		node = rb_next(&dc->rb_node);
-		dc = rb_entry_safe(node, struct discard_cmd, rb_node);
-
-		if (fatal_signal_pending(current))
-			break;
-	}
-
-	blk_finish_plug(&plug);
-	mutex_unlock(&dcc->cmd_lock);
-}
-
 static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
 					struct discard_policy *dpolicy)
 {
@@ -1412,7 +1383,18 @@ next:
 static void __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
 						struct discard_policy *dpolicy)
 {
-	__wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
+	struct discard_policy dp;
+
+	if (dpolicy) {
+		__wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
+		return;
+	}
+
+	/* wait all */
+	__init_discard_policy(sbi, &dp, DPOLICY_FSTRIM, 1);
+	__wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
+	__init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, 1);
+	__wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
 }
 
 /* This should be covered by global mutex, &sit_i->sentry_lock */
@@ -1457,11 +1439,13 @@ bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi)
 	struct discard_policy dpolicy;
 	bool dropped;
 
-	init_discard_policy(&dpolicy, DPOLICY_UMOUNT, dcc->discard_granularity);
+	__init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT,
+					dcc->discard_granularity);
 	__issue_discard_cmd(sbi, &dpolicy);
 	dropped = __drop_discard_cmd(sbi);
-	__wait_all_discard_cmd(sbi, &dpolicy);
 
+	/* just to make sure there is no pending discard commands */
+	__wait_all_discard_cmd(sbi, NULL);
 	return dropped;
 }
 
@@ -1477,7 +1461,7 @@ static int issue_discard_thread(void *data)
 	set_freezable();
 
 	do {
-		init_discard_policy(&dpolicy, DPOLICY_BG,
+		__init_discard_policy(sbi, &dpolicy, DPOLICY_BG,
 					dcc->discard_granularity);
 
 		wait_event_interruptible_timeout(*q,
@@ -1495,7 +1479,7 @@ static int issue_discard_thread(void *data)
 			dcc->discard_wake = 0;
 
 		if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
-			init_discard_policy(&dpolicy, DPOLICY_FORCE, 1);
+			__init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1);
 
 		sb_start_intwrite(sbi->sb);
 
@@ -1788,32 +1772,6 @@ skip:
 	wake_up_discard_thread(sbi, false);
 }
 
-void init_discard_policy(struct discard_policy *dpolicy,
-				int discard_type, unsigned int granularity)
-{
-	/* common policy */
-	dpolicy->type = discard_type;
-	dpolicy->sync = true;
-	dpolicy->granularity = granularity;
-
-	dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
-	dpolicy->io_aware_gran = MAX_PLIST_NUM;
-
-	if (discard_type == DPOLICY_BG) {
-		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
-		dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
-		dpolicy->io_aware = true;
-	} else if (discard_type == DPOLICY_FORCE) {
-		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
-		dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
-		dpolicy->io_aware = false;
-	} else if (discard_type == DPOLICY_FSTRIM) {
-		dpolicy->io_aware = false;
-	} else if (discard_type == DPOLICY_UMOUNT) {
-		dpolicy->io_aware = false;
-	}
-}
-
 static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
 {
 	dev_t dev = sbi->sb->s_bdev->bd_dev;
@@ -2453,11 +2411,72 @@ bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	return has_candidate;
 }
 
+static void __issue_discard_cmd_range(struct f2fs_sb_info *sbi,
+					struct discard_policy *dpolicy,
+					unsigned int start, unsigned int end)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
+	struct rb_node **insert_p = NULL, *insert_parent = NULL;
+	struct discard_cmd *dc;
+	struct blk_plug plug;
+	int issued;
+
+next:
+	issued = 0;
+
+	mutex_lock(&dcc->cmd_lock);
+	f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
+
+	dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root,
+					NULL, start,
+					(struct rb_entry **)&prev_dc,
+					(struct rb_entry **)&next_dc,
+					&insert_p, &insert_parent, true);
+	if (!dc)
+		dc = next_dc;
+
+	blk_start_plug(&plug);
+
+	while (dc && dc->lstart <= end) {
+		struct rb_node *node;
+
+		if (dc->len < dpolicy->granularity)
+			goto skip;
+
+		if (dc->state != D_PREP) {
+			list_move_tail(&dc->list, &dcc->fstrim_list);
+			goto skip;
+		}
+
+		__submit_discard_cmd(sbi, dpolicy, dc);
+
+		if (++issued >= dpolicy->max_requests) {
+			start = dc->lstart + dc->len;
+
+			blk_finish_plug(&plug);
+			mutex_unlock(&dcc->cmd_lock);
+			__wait_all_discard_cmd(sbi, NULL);
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			goto next;
+		}
+skip:
+		node = rb_next(&dc->rb_node);
+		dc = rb_entry_safe(node, struct discard_cmd, rb_node);
+
+		if (fatal_signal_pending(current))
+			break;
+	}
+
+	blk_finish_plug(&plug);
+	mutex_unlock(&dcc->cmd_lock);
+}
+
 int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 {
 	__u64 start = F2FS_BYTES_TO_BLK(range->start);
 	__u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
-	unsigned int start_segno, end_segno, cur_segno;
+	unsigned int start_segno, end_segno;
 	block_t start_block, end_block;
 	struct cp_control cpc;
 	struct discard_policy dpolicy;
@@ -2483,40 +2502,36 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 
 	cpc.reason = CP_DISCARD;
 	cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen));
+	cpc.trim_start = start_segno;
+	cpc.trim_end = end_segno;
 
-	/* do checkpoint to issue discard commands safely */
-	for (cur_segno = start_segno; cur_segno <= end_segno;
-					cur_segno = cpc.trim_end + 1) {
-		cpc.trim_start = cur_segno;
-
-		if (sbi->discard_blks == 0)
-			break;
-		else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi))
-			cpc.trim_end = end_segno;
-		else
-			cpc.trim_end = min_t(unsigned int,
-				rounddown(cur_segno +
-				BATCHED_TRIM_SEGMENTS(sbi),
-				sbi->segs_per_sec) - 1, end_segno);
-
-		mutex_lock(&sbi->gc_mutex);
-		err = write_checkpoint(sbi, &cpc);
-		mutex_unlock(&sbi->gc_mutex);
-		if (err)
-			break;
+	if (sbi->discard_blks == 0)
+		goto out;
 
-		schedule();
-	}
+	mutex_lock(&sbi->gc_mutex);
+	err = write_checkpoint(sbi, &cpc);
+	mutex_unlock(&sbi->gc_mutex);
+	if (err)
+		goto out;
 
 	start_block = START_BLOCK(sbi, start_segno);
-	end_block = START_BLOCK(sbi, min(cur_segno, end_segno) + 1);
+	end_block = START_BLOCK(sbi, end_segno + 1);
 
-	init_discard_policy(&dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen);
+	__init_discard_policy(sbi, &dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen);
 	__issue_discard_cmd_range(sbi, &dpolicy, start_block, end_block);
-	trimmed = __wait_discard_cmd_range(sbi, &dpolicy,
+
+	/*
+	 * We filed discard candidates, but actually we don't need to wait for
+	 * all of them, since they'll be issued in idle time along with runtime
+	 * discard option. User configuration looks like using runtime discard
+	 * or periodic fstrim instead of it.
+	 */
+	if (!test_opt(sbi, DISCARD)) {
+		trimmed = __wait_discard_cmd_range(sbi, &dpolicy,
 					start_block, end_block);
+		range->len = F2FS_BLK_TO_BYTES(trimmed);
+	}
 out:
-	range->len = F2FS_BLK_TO_BYTES(trimmed);
 	return err;
 }
 
@@ -3904,8 +3919,6 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
 	sm_info->min_ssr_sections = reserved_sections(sbi);
 
-	sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
-
 	INIT_LIST_HEAD(&sm_info->sit_entry_set);
 
 	init_rwsem(&sm_info->curseg_lock);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 55b2bad55671..cb57ad3ca32d 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -740,6 +740,10 @@ static int parse_options(struct super_block *sb, char *options)
 			} else if (strlen(name) == 6 &&
 					!strncmp(name, "strict", 6)) {
 				F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_STRICT;
+			} else if (strlen(name) == 9 &&
+					!strncmp(name, "nobarrier", 9)) {
+				F2FS_OPTION(sbi).fsync_mode =
+							FSYNC_MODE_NOBARRIER;
 			} else {
 				kfree(name);
 				return -EINVAL;
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index f33a56d6e6dd..2c53de9251be 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -245,6 +245,9 @@ out:
 		return count;
 	}
 
+	if (!strcmp(a->attr.name, "trim_sections"))
+		return -EINVAL;
+
 	*ui = t;
 
 	if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0)
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index e1e7fe3b5424..b663b756f552 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -1924,6 +1924,93 @@ xfs_alloc_space_available(
 }
 
 /*
+ * Check the agfl fields of the agf for inconsistency or corruption. The purpose
+ * is to detect an agfl header padding mismatch between current and early v5
+ * kernels. This problem manifests as a 1-slot size difference between the
+ * on-disk flcount and the active [first, last] range of a wrapped agfl. This
+ * may also catch variants of agfl count corruption unrelated to padding. Either
+ * way, we'll reset the agfl and warn the user.
+ *
+ * Return true if a reset is required before the agfl can be used, false
+ * otherwise.
+ */
+static bool
+xfs_agfl_needs_reset(
+	struct xfs_mount	*mp,
+	struct xfs_agf		*agf)
+{
+	uint32_t		f = be32_to_cpu(agf->agf_flfirst);
+	uint32_t		l = be32_to_cpu(agf->agf_fllast);
+	uint32_t		c = be32_to_cpu(agf->agf_flcount);
+	int			agfl_size = XFS_AGFL_SIZE(mp);
+	int			active;
+
+	/* no agfl header on v4 supers */
+	if (!xfs_sb_version_hascrc(&mp->m_sb))
+		return false;
+
+	/*
+	 * The agf read verifier catches severe corruption of these fields.
+	 * Repeat some sanity checks to cover a packed -> unpacked mismatch if
+	 * the verifier allows it.
+	 */
+	if (f >= agfl_size || l >= agfl_size)
+		return true;
+	if (c > agfl_size)
+		return true;
+
+	/*
+	 * Check consistency between the on-disk count and the active range. An
+	 * agfl padding mismatch manifests as an inconsistent flcount.
+	 */
+	if (c && l >= f)
+		active = l - f + 1;
+	else if (c)
+		active = agfl_size - f + l + 1;
+	else
+		active = 0;
+
+	return active != c;
+}
+
+/*
+ * Reset the agfl to an empty state. Ignore/drop any existing blocks since the
+ * agfl content cannot be trusted. Warn the user that a repair is required to
+ * recover leaked blocks.
+ *
+ * The purpose of this mechanism is to handle filesystems affected by the agfl
+ * header padding mismatch problem. A reset keeps the filesystem online with a
+ * relatively minor free space accounting inconsistency rather than suffer the
+ * inevitable crash from use of an invalid agfl block.
+ */
+static void
+xfs_agfl_reset(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp,
+	struct xfs_perag	*pag)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
+
+	ASSERT(pag->pagf_agflreset);
+	trace_xfs_agfl_reset(mp, agf, 0, _RET_IP_);
+
+	xfs_warn(mp,
+	       "WARNING: Reset corrupted AGFL on AG %u. %d blocks leaked. "
+	       "Please unmount and run xfs_repair.",
+	         pag->pag_agno, pag->pagf_flcount);
+
+	agf->agf_flfirst = 0;
+	agf->agf_fllast = cpu_to_be32(XFS_AGFL_SIZE(mp) - 1);
+	agf->agf_flcount = 0;
+	xfs_alloc_log_agf(tp, agbp, XFS_AGF_FLFIRST | XFS_AGF_FLLAST |
+				    XFS_AGF_FLCOUNT);
+
+	pag->pagf_flcount = 0;
+	pag->pagf_agflreset = false;
+}
+
+/*
  * Decide whether to use this allocation group for this allocation.
  * If so, fix up the btree freelist's size.
  */
@@ -1983,6 +2070,10 @@ xfs_alloc_fix_freelist(
 		}
 	}
 
+	/* reset a padding mismatched agfl before final free space check */
+	if (pag->pagf_agflreset)
+		xfs_agfl_reset(tp, agbp, pag);
+
 	/* If there isn't enough total space or single-extent, reject it. */
 	need = xfs_alloc_min_freelist(mp, pag);
 	if (!xfs_alloc_space_available(args, need, flags))
@@ -2121,6 +2212,7 @@ xfs_alloc_get_freelist(
 		agf->agf_flfirst = 0;
 
 	pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno));
+	ASSERT(!pag->pagf_agflreset);
 	be32_add_cpu(&agf->agf_flcount, -1);
 	xfs_trans_agflist_delta(tp, -1);
 	pag->pagf_flcount--;
@@ -2226,6 +2318,7 @@ xfs_alloc_put_freelist(
 		agf->agf_fllast = 0;
 
 	pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno));
+	ASSERT(!pag->pagf_agflreset);
 	be32_add_cpu(&agf->agf_flcount, 1);
 	xfs_trans_agflist_delta(tp, 1);
 	pag->pagf_flcount++;
@@ -2417,6 +2510,7 @@ xfs_alloc_read_agf(
 		pag->pagb_count = 0;
 		pag->pagb_tree = RB_ROOT;
 		pag->pagf_init = 1;
+		pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf);
 	}
 #ifdef DEBUG
 	else if (!XFS_FORCED_SHUTDOWN(mp)) {
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index f52c72a1a06f..73b725f965eb 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -3323,8 +3323,6 @@ maybe_sleep:
 		 */
 		if (iclog->ic_state & XLOG_STATE_IOERROR)
 			return -EIO;
-		if (log_flushed)
-			*log_flushed = 1;
 	} else {
 
 no_sleep:
@@ -3432,8 +3430,6 @@ try_again:
 
 				xlog_wait(&iclog->ic_prev->ic_write_wait,
 							&log->l_icloglock);
-				if (log_flushed)
-					*log_flushed = 1;
 				already_slept = 1;
 				goto try_again;
 			}
@@ -3467,9 +3463,6 @@ try_again:
 			 */
 			if (iclog->ic_state & XLOG_STATE_IOERROR)
 				return -EIO;
-
-			if (log_flushed)
-				*log_flushed = 1;
 		} else {		/* just return */
 			spin_unlock(&log->l_icloglock);
 		}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index b57098481c10..ae3e52749f20 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -278,6 +278,7 @@ typedef struct xfs_perag {
 	char		pagi_inodeok;	/* The agi is ok for inodes */
 	__uint8_t	pagf_levels[XFS_BTNUM_AGF];
 					/* # of levels in bno & cnt btree */
+	bool		pagf_agflreset; /* agfl requires reset before use */
 	__uint32_t	pagf_flcount;	/* count of blocks in freelist */
 	xfs_extlen_t	pagf_freeblks;	/* total free blocks */
 	xfs_extlen_t	pagf_longest;	/* longest free space */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 877079eb0f8f..cc6fa64821d2 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1485,7 +1485,7 @@ TRACE_EVENT(xfs_trans_commit_lsn,
 		  __entry->lsn)
 );
 
-TRACE_EVENT(xfs_agf,
+DECLARE_EVENT_CLASS(xfs_agf_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags,
 		 unsigned long caller_ip),
 	TP_ARGS(mp, agf, flags, caller_ip),
@@ -1541,6 +1541,13 @@ TRACE_EVENT(xfs_agf,
 		  __entry->longest,
 		  (void *)__entry->caller_ip)
 );
+#define DEFINE_AGF_EVENT(name) \
+DEFINE_EVENT(xfs_agf_class, name, \
+	TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags, \
+		 unsigned long caller_ip), \
+	TP_ARGS(mp, agf, flags, caller_ip))
+DEFINE_AGF_EVENT(xfs_agf);
+DEFINE_AGF_EVENT(xfs_agfl_reset);
 
 TRACE_EVENT(xfs_free_extent,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,