Merge 4.9.51 into android-4.9

Changes in 4.9.51
	ipv6: accept 64k - 1 packet length in ip6_find_1stfragopt()
	ipv6: add rcu grace period before freeing fib6_node
	ipv6: fix sparse warning on rt6i_node
	macsec: add genl family module alias
	udp: on peeking bad csum, drop packets even if not at head
	fsl/man: Inherit parent device and of_node
	sctp: Avoid out-of-bounds reads from address storage
	qlge: avoid memcpy buffer overflow
	netvsc: fix deadlock betwen link status and removal
	cxgb4: Fix stack out-of-bounds read due to wrong size to t4_record_mbox()
	packet: Don't write vnet header beyond end of buffer
	kcm: do not attach PF_KCM sockets to avoid deadlock
	Revert "net: phy: Correctly process PHY_HALTED in phy_stop_machine()"
	tcp: initialize rcv_mss to TCP_MIN_MSS instead of 0
	mlxsw: spectrum: Forbid linking to devices that have uppers
	bridge: switchdev: Clear forward mark when transmitting packet
	Revert "net: use lib/percpu_counter API for fragmentation mem accounting"
	Revert "net: fix percpu memory leaks"
	gianfar: Fix Tx flow control deactivation
	vhost_net: correctly check tx avail during rx busy polling
	ip6_gre: update mtu properly in ip6gre_err
	ipv6: fix memory leak with multiple tables during netns destruction
	ipv6: fix typo in fib6_net_exit()
	sctp: fix missing wake ups in some situations
	ip_tunnel: fix setting ttl and tos value in collect_md mode
	f2fs: let fill_super handle roll-forward errors
	f2fs: check hot_data for roll-forward recovery
	x86/fsgsbase/64: Fully initialize FS and GS state in start_thread_common
	x86/fsgsbase/64: Report FSBASE and GSBASE correctly in core dumps
	x86/switch_to/64: Rewrite FS/GS switching yet again to fix AMD CPUs
	xfs: Move handling of missing page into one place in xfs_find_get_desired_pgoff()
	xfs: fix spurious spin_is_locked() assert failures on non-smp kernels
	xfs: push buffer of flush locked dquot to avoid quotacheck deadlock
	xfs: try to avoid blowing out the transaction reservation when bunmaping a shared extent
	xfs: release bli from transaction properly on fs shutdown
	xfs: remove bli from AIL before release on transaction abort
	xfs: don't allow bmap on rt files
	xfs: free uncommitted transactions during log recovery
	xfs: free cowblocks and retry on buffered write ENOSPC
	xfs: don't crash on unexpected holes in dir/attr btrees
	xfs: check _btree_check_block value
	xfs: set firstfsb to NULLFSBLOCK before feeding it to _bmapi_write
	xfs: check _alloc_read_agf buffer pointer before using
	xfs: fix quotacheck dquot id overflow infinite loop
	xfs: fix multi-AG deadlock in xfs_bunmapi
	xfs: Fix per-inode DAX flag inheritance
	xfs: fix inobt inode allocation search optimization
	xfs: clear MS_ACTIVE after finishing log recovery
	xfs: don't leak quotacheck dquots when cow recovery
	iomap: fix integer truncation issues in the zeroing and dirtying helpers
	xfs: write unmount record for ro mounts
	xfs: toggle readonly state around xfs_log_mount_finish
	xfs: remove xfs_trans_ail_delete_bulk
	xfs: Add infrastructure needed for error propagation during buffer IO failure
	xfs: Properly retry failed inode items in case of error during buffer writeback
	xfs: fix recovery failure when log record header wraps log end
	xfs: always verify the log tail during recovery
	xfs: fix log recovery corruption error due to tail overwrite
	xfs: handle -EFSCORRUPTED during head/tail verification
	xfs: add log recovery tracepoint for head/tail
	xfs: stop searching for free slots in an inode chunk when there are none
	xfs: evict all inodes involved with log redo item
	xfs: check for race with xfs_reclaim_inode() in xfs_ifree_cluster()
	xfs: open-code xfs_buf_item_dirty()
	xfs: remove unnecessary dirty bli format check for ordered bufs
	xfs: ordered buffer log items are never formatted
	xfs: refactor buffer logging into buffer dirtying helper
	xfs: don't log dirty ranges for ordered buffers
	xfs: skip bmbt block ino validation during owner change
	xfs: move bmbt owner change to last step of extent swap
	xfs: disallow marking previously dirty buffers as ordered
	xfs: relog dirty buffers during swapext bmbt owner change
	xfs: disable per-inode DAX flag
	xfs: fix incorrect log_flushed on fsync
	xfs: don't set v3 xflags for v2 inodes
	xfs: open code end_buffer_async_write in xfs_finish_page_writeback
	xfs: use kmem_free to free return value of kmem_zalloc
	md/raid5: release/flush io in raid5_do_work()
	xfs: fix compiler warnings
	ipv6: Fix may be used uninitialized warning in rt6_check
	Linux 4.9.51

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 50
+SUBLEVEL = 51
 EXTRAVERSION =
 NAME = Roaring Lionus
 

arch/x86/include/asm/elf.h

@@ -204,6 +204,7 @@ void set_personality_ia32(bool);
 
 #define ELF_CORE_COPY_REGS(pr_reg, regs)			\
 do {								\
+	unsigned long base;					\
 	unsigned v;						\
 	(pr_reg)[0] = (regs)->r15;				\
 	(pr_reg)[1] = (regs)->r14;				\
@@ -226,8 +227,8 @@ do {								\
 	(pr_reg)[18] = (regs)->flags;				\
 	(pr_reg)[19] = (regs)->sp;				\
 	(pr_reg)[20] = (regs)->ss;				\
-	(pr_reg)[21] = current->thread.fsbase;			\
-	(pr_reg)[22] = current->thread.gsbase;			\
+	rdmsrl(MSR_FS_BASE, base); (pr_reg)[21] = base;		\
+	rdmsrl(MSR_KERNEL_GS_BASE, base); (pr_reg)[22] = base;	\
 	asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v;	\
 	asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v;	\
 	asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v;	\

arch/x86/kernel/process_64.c

@@ -136,6 +136,123 @@ void release_thread(struct task_struct *dead_task)
 	}
 }
 
+enum which_selector {
+	FS,
+	GS
+};
+
+/*
+ * Saves the FS or GS base for an outgoing thread if FSGSBASE extensions are
+ * not available.  The goal is to be reasonably fast on non-FSGSBASE systems.
+ * It's forcibly inlined because it'll generate better code and this function
+ * is hot.
+ */
+static __always_inline void save_base_legacy(struct task_struct *prev_p,
+					     unsigned short selector,
+					     enum which_selector which)
+{
+	if (likely(selector == 0)) {
+		/*
+		 * On Intel (without X86_BUG_NULL_SEG), the segment base could
+		 * be the pre-existing saved base or it could be zero.  On AMD
+		 * (with X86_BUG_NULL_SEG), the segment base could be almost
+		 * anything.
+		 *
+		 * This branch is very hot (it's hit twice on almost every
+		 * context switch between 64-bit programs), and avoiding
+		 * the RDMSR helps a lot, so we just assume that whatever
+		 * value is already saved is correct.  This matches historical
+		 * Linux behavior, so it won't break existing applications.
+		 *
+		 * To avoid leaking state, on non-X86_BUG_NULL_SEG CPUs, if we
+		 * report that the base is zero, it needs to actually be zero:
+		 * see the corresponding logic in load_seg_legacy.
+		 */
+	} else {
+		/*
+		 * If the selector is 1, 2, or 3, then the base is zero on
+		 * !X86_BUG_NULL_SEG CPUs and could be anything on
+		 * X86_BUG_NULL_SEG CPUs.  In the latter case, Linux
+		 * has never attempted to preserve the base across context
+		 * switches.
+		 *
+		 * If selector > 3, then it refers to a real segment, and
+		 * saving the base isn't necessary.
+		 */
+		if (which == FS)
+			prev_p->thread.fsbase = 0;
+		else
+			prev_p->thread.gsbase = 0;
+	}
+}
+
+static __always_inline void save_fsgs(struct task_struct *task)
+{
+	savesegment(fs, task->thread.fsindex);
+	savesegment(gs, task->thread.gsindex);
+	save_base_legacy(task, task->thread.fsindex, FS);
+	save_base_legacy(task, task->thread.gsindex, GS);
+}
+
+static __always_inline void loadseg(enum which_selector which,
+				    unsigned short sel)
+{
+	if (which == FS)
+		loadsegment(fs, sel);
+	else
+		load_gs_index(sel);
+}
+
+static __always_inline void load_seg_legacy(unsigned short prev_index,
+					    unsigned long prev_base,
+					    unsigned short next_index,
+					    unsigned long next_base,
+					    enum which_selector which)
+{
+	if (likely(next_index <= 3)) {
+		/*
+		 * The next task is using 64-bit TLS, is not using this
+		 * segment at all, or is having fun with arcane CPU features.
+		 */
+		if (next_base == 0) {
+			/*
+			 * Nasty case: on AMD CPUs, we need to forcibly zero
+			 * the base.
+			 */
+			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
+				loadseg(which, __USER_DS);
+				loadseg(which, next_index);
+			} else {
+				/*
+				 * We could try to exhaustively detect cases
+				 * under which we can skip the segment load,
+				 * but there's really only one case that matters
+				 * for performance: if both the previous and
+				 * next states are fully zeroed, we can skip
+				 * the load.
+				 *
+				 * (This assumes that prev_base == 0 has no
+				 * false positives.  This is the case on
+				 * Intel-style CPUs.)
+				 */
+				if (likely(prev_index | next_index | prev_base))
+					loadseg(which, next_index);
+			}
+		} else {
+			if (prev_index != next_index)
+				loadseg(which, next_index);
+			wrmsrl(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE,
+			       next_base);
+		}
+	} else {
+		/*
+		 * The next task is using a real segment.  Loading the selector
+		 * is sufficient.
+		 */
+		loadseg(which, next_index);
+	}
+}
+
 int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 		unsigned long arg, struct task_struct *p, unsigned long tls)
 {
@@ -216,10 +333,19 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 		    unsigned long new_sp,
 		    unsigned int _cs, unsigned int _ss, unsigned int _ds)
 {
+	WARN_ON_ONCE(regs != current_pt_regs());
+
+	if (static_cpu_has(X86_BUG_NULL_SEG)) {
+		/* Loading zero below won't clear the base. */
+		loadsegment(fs, __USER_DS);
+		load_gs_index(__USER_DS);
+	}
+
 	loadsegment(fs, 0);
 	loadsegment(es, _ds);
 	loadsegment(ds, _ds);
 	load_gs_index(0);
+
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
 	regs->cs		= _cs;
@@ -264,7 +390,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
-	unsigned prev_fsindex, prev_gsindex;
 	fpu_switch_t fpu_switch;
 
 	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
@@ -274,8 +399,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 *
 	 * (e.g. xen_load_tls())
 	 */
-	savesegment(fs, prev_fsindex);
-	savesegment(gs, prev_gsindex);
+	save_fsgs(prev_p);
 
 	/*
 	 * Load TLS before restoring any segments so that segment loads
@@ -314,108 +438,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (unlikely(next->ds | prev->ds))
 		loadsegment(ds, next->ds);
 
-	/*
-	 * Switch FS and GS.
-	 *
-	 * These are even more complicated than DS and ES: they have
-	 * 64-bit bases are that controlled by arch_prctl.  The bases
-	 * don't necessarily match the selectors, as user code can do
-	 * any number of things to cause them to be inconsistent.
-	 *
-	 * We don't promise to preserve the bases if the selectors are
-	 * nonzero.  We also don't promise to preserve the base if the
-	 * selector is zero and the base doesn't match whatever was
-	 * most recently passed to ARCH_SET_FS/GS.  (If/when the
-	 * FSGSBASE instructions are enabled, we'll need to offer
-	 * stronger guarantees.)
-	 *
-	 * As an invariant,
-	 * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is
-	 * impossible.
-	 */
-	if (next->fsindex) {
-		/* Loading a nonzero value into FS sets the index and base. */
-		loadsegment(fs, next->fsindex);
-	} else {
-		if (next->fsbase) {
-			/* Next index is zero but next base is nonzero. */
-			if (prev_fsindex)
-				loadsegment(fs, 0);
-			wrmsrl(MSR_FS_BASE, next->fsbase);
-		} else {
-			/* Next base and index are both zero. */
-			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
-				/*
-				 * We don't know the previous base and can't
-				 * find out without RDMSR.  Forcibly clear it.
-				 */
-				loadsegment(fs, __USER_DS);
-				loadsegment(fs, 0);
-			} else {
-				/*
-				 * If the previous index is zero and ARCH_SET_FS
-				 * didn't change the base, then the base is
-				 * also zero and we don't need to do anything.
-				 */
-				if (prev->fsbase || prev_fsindex)
-					loadsegment(fs, 0);
-			}
-		}
-	}
-	/*
-	 * Save the old state and preserve the invariant.
-	 * NB: if prev_fsindex == 0, then we can't reliably learn the base
-	 * without RDMSR because Intel user code can zero it without telling
-	 * us and AMD user code can program any 32-bit value without telling
-	 * us.
-	 */
-	if (prev_fsindex)
-		prev->fsbase = 0;
-	prev->fsindex = prev_fsindex;
-
-	if (next->gsindex) {
-		/* Loading a nonzero value into GS sets the index and base. */
-		load_gs_index(next->gsindex);
-	} else {
-		if (next->gsbase) {
-			/* Next index is zero but next base is nonzero. */
-			if (prev_gsindex)
-				load_gs_index(0);
-			wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase);
-		} else {
-			/* Next base and index are both zero. */
-			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
-				/*
-				 * We don't know the previous base and can't
-				 * find out without RDMSR.  Forcibly clear it.
-				 *
-				 * This contains a pointless SWAPGS pair.
-				 * Fixing it would involve an explicit check
-				 * for Xen or a new pvop.
-				 */
-				load_gs_index(__USER_DS);
-				load_gs_index(0);
-			} else {
-				/*
-				 * If the previous index is zero and ARCH_SET_GS
-				 * didn't change the base, then the base is
-				 * also zero and we don't need to do anything.
-				 */
-				if (prev->gsbase || prev_gsindex)
-					load_gs_index(0);
-			}
-		}
-	}
-	/*
-	 * Save the old state and preserve the invariant.
-	 * NB: if prev_gsindex == 0, then we can't reliably learn the base
-	 * without RDMSR because Intel user code can zero it without telling
-	 * us and AMD user code can program any 32-bit value without telling
-	 * us.
-	 */
-	if (prev_gsindex)
-		prev->gsbase = 0;
-	prev->gsindex = prev_gsindex;
+	load_seg_legacy(prev->fsindex, prev->fsbase,
+			next->fsindex, next->fsbase, FS);
+	load_seg_legacy(prev->gsindex, prev->gsbase,
+			next->gsindex, next->gsbase, GS);
 
 	switch_fpu_finish(next_fpu, fpu_switch);
 

drivers/md/raid5.c

@@ -5844,6 +5844,8 @@ static void raid5_do_work(struct work_struct *work)
 
 	spin_unlock_irq(&conf->device_lock);
 
+	r5l_flush_stripe_to_raid(conf->log);
+
 	async_tx_issue_pending_all();
 	blk_finish_plug(&plug);
 

drivers/net/ethernet/chelsio/cxgb4/t4_hw.c

@@ -317,12 +317,12 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd,
 
 	if (v != MBOX_OWNER_DRV) {
 		ret = (v == MBOX_OWNER_FW) ? -EBUSY : -ETIMEDOUT;
-		t4_record_mbox(adap, cmd, MBOX_LEN, access, ret);
+		t4_record_mbox(adap, cmd, size, access, ret);
 		return ret;
 	}
 
 	/* Copy in the new mailbox command and send it on its way ... */
-	t4_record_mbox(adap, cmd, MBOX_LEN, access, 0);
+	t4_record_mbox(adap, cmd, size, access, 0);
 	for (i = 0; i < size; i += 8)
 		t4_write_reg64(adap, data_reg + i, be64_to_cpu(*p++));
 
@@ -371,7 +371,7 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd,
 	}
 
 	ret = (pcie_fw & PCIE_FW_ERR_F) ? -ENXIO : -ETIMEDOUT;
-	t4_record_mbox(adap, cmd, MBOX_LEN, access, ret);
+	t4_record_mbox(adap, cmd, size, access, ret);
 	dev_err(adap->pdev_dev, "command %#x in mailbox %d timed out\n",
 		*(const u8 *)cmd, mbox);
 	t4_report_fw_error(adap);

drivers/net/ethernet/freescale/fman/mac.c

@@ -622,6 +622,9 @@ static struct platform_device *dpaa_eth_add_device(int fman_id,
 		goto no_mem;
 	}
 
+	pdev->dev.of_node = node;
+	pdev->dev.parent = priv->dev;
+
 	ret = platform_device_add_data(pdev, &data, sizeof(data));
 	if (ret)
 		goto err;

drivers/net/ethernet/freescale/gianfar.c

@@ -3690,7 +3690,7 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 		u32 tempval1 = gfar_read(&regs->maccfg1);
 		u32 tempval = gfar_read(&regs->maccfg2);
 		u32 ecntrl = gfar_read(&regs->ecntrl);
-		u32 tx_flow_oldval = (tempval & MACCFG1_TX_FLOW);
+		u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW);
 
 		if (phydev->duplex != priv->oldduplex) {
 			if (!(phydev->duplex))

drivers/net/ethernet/mellanox/mlxsw/spectrum.c

@@ -4172,6 +4172,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 			return -EINVAL;
 		if (!info->linking)
 			break;
+		if (netdev_has_any_upper_dev(upper_dev))
+			return -EINVAL;
 		/* HW limitation forbids to put ports to multiple bridges. */
 		if (netif_is_bridge_master(upper_dev) &&
 		    !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))
@@ -4185,6 +4187,10 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 		if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) &&
 		    !netif_is_lag_master(vlan_dev_real_dev(upper_dev)))
 			return -EINVAL;
+		if (!info->linking)
+			break;
+		if (netdev_has_any_upper_dev(upper_dev))
+			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;

drivers/net/ethernet/qlogic/qlge/qlge_dbg.c

@@ -724,7 +724,7 @@ static void ql_build_coredump_seg_header(
 	seg_hdr->cookie = MPI_COREDUMP_COOKIE;
 	seg_hdr->segNum = seg_number;
 	seg_hdr->segSize = seg_size;
-	memcpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);
+	strncpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);
 }
 
 /*

drivers/net/hyperv/netvsc_drv.c

@@ -1084,7 +1084,12 @@ static void netvsc_link_change(struct work_struct *w)
 	bool notify = false, reschedule = false;
 	unsigned long flags, next_reconfig, delay;
 
-	rtnl_lock();
+	/* if changes are happening, comeback later */
+	if (!rtnl_trylock()) {
+		schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT);
+		return;
+	}
+
 	if (ndev_ctx->start_remove)
 		goto out_unlock;
 

drivers/net/macsec.c

@@ -3510,6 +3510,7 @@ module_init(macsec_init);
 module_exit(macsec_exit);
 
 MODULE_ALIAS_RTNL_LINK("macsec");
+MODULE_ALIAS_GENL_FAMILY("macsec");
 
 MODULE_DESCRIPTION("MACsec IEEE 802.1AE");
 MODULE_LICENSE("GPL v2");

drivers/net/phy/phy.c

@@ -674,9 +674,6 @@ void phy_stop_machine(struct phy_device *phydev)
 	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
-
-	/* Now we can run the state machine synchronously */
-	phy_state_machine(&phydev->state_queue.work);
 }
 
 /**

drivers/vhost/net.c

@@ -537,8 +537,13 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 
 		preempt_enable();
 
-		if (vhost_enable_notify(&net->dev, vq))
+		if (!vhost_vq_avail_empty(&net->dev, vq))
 			vhost_poll_queue(&vq->poll);
+		else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+			vhost_disable_notify(&net->dev, vq);
+			vhost_poll_queue(&vq->poll);
+		}
+
 		mutex_unlock(&vq->mutex);
 
 		len = peek_head_len(sk);

fs/f2fs/recovery.c

@@ -316,7 +316,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 		return 0;
 
 	/* Get the previous summary */
-	for (i = CURSEG_WARM_DATA; i <= CURSEG_COLD_DATA; i++) {
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
 		struct curseg_info *curseg = CURSEG_I(sbi, i);
 		if (curseg->segno == segno) {
 			sum = curseg->sum_blk->entries[blkoff];
@@ -626,8 +626,6 @@ out:
 	}
 
 	clear_sbi_flag(sbi, SBI_POR_DOING);
-	if (err)
-		set_ckpt_flags(sbi, CP_ERROR_FLAG);
 	mutex_unlock(&sbi->cp_mutex);
 
 	/* let's drop all the directory inodes for clean checkpoint */

fs/inode.c

@@ -637,6 +637,7 @@ again:
 
 	dispose_list(&dispose);
 }
+EXPORT_SYMBOL_GPL(evict_inodes);
 
 /**
  * invalidate_inodes	- attempt to free all inodes on a superblock

fs/internal.h

@@ -138,7 +138,6 @@ extern bool atime_needs_update_rcu(const struct path *, struct inode *);
 extern void inode_io_list_del(struct inode *inode);
 
 extern long get_nr_dirty_inodes(void);
-extern void evict_inodes(struct super_block *);
 extern int invalidate_inodes(struct super_block *, bool);
 
 /*

fs/iomap.c

@@ -281,7 +281,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		unsigned long bytes;	/* Bytes to write to page */
 
 		offset = (pos & (PAGE_SIZE - 1));
-		bytes = min_t(unsigned long, PAGE_SIZE - offset, length);
+		bytes = min_t(loff_t, PAGE_SIZE - offset, length);
 
 		rpage = __iomap_read_page(inode, pos);
 		if (IS_ERR(rpage))
@@ -376,7 +376,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 		unsigned offset, bytes;
 
 		offset = pos & (PAGE_SIZE - 1); /* Within page */
-		bytes = min_t(unsigned, PAGE_SIZE - offset, count);
+		bytes = min_t(loff_t, PAGE_SIZE - offset, count);
 
 		if (IS_DAX(inode))
 			status = iomap_dax_zero(pos, offset, bytes, iomap);

fs/xfs/libxfs/xfs_attr_leaf.c

@@ -351,7 +351,7 @@ xfs_attr3_leaf_read(
 
 	err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp,
 				XFS_ATTR_FORK, &xfs_attr3_leaf_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF);
 	return err;
 }

fs/xfs/libxfs/xfs_bmap.c

@@ -579,7 +579,7 @@ xfs_bmap_validate_ret(
 
 #else
 #define xfs_bmap_check_leaf_extents(cur, ip, whichfork)		do { } while (0)
-#define	xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap)
+#define	xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap)	do { } while (0)
 #endif /* DEBUG */
 
 /*
@@ -5555,6 +5555,8 @@ __xfs_bunmapi(
 	int			whichfork;	/* data or attribute fork */
 	xfs_fsblock_t		sum;
 	xfs_filblks_t		len = *rlen;	/* length to unmap in file */
+	xfs_fileoff_t		max_len;
+	xfs_agnumber_t		prev_agno = NULLAGNUMBER, agno;
 
 	trace_xfs_bunmap(ip, bno, len, flags, _RET_IP_);
 
@@ -5576,6 +5578,16 @@ __xfs_bunmapi(
 	ASSERT(len > 0);
 	ASSERT(nexts >= 0);
 
+	/*
+	 * Guesstimate how many blocks we can unmap without running the risk of
+	 * blowing out the transaction with a mix of EFIs and reflink
+	 * adjustments.
+	 */
+	if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK)
+		max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res));
+	else
+		max_len = len;
+
 	if (!(ifp->if_flags & XFS_IFEXTENTS) &&
 	    (error = xfs_iread_extents(tp, ip, whichfork)))
 		return error;
@@ -5621,7 +5633,7 @@ __xfs_bunmapi(
 
 	extno = 0;
 	while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 &&
-	       (nexts == 0 || extno < nexts)) {
+	       (nexts == 0 || extno < nexts) && max_len > 0) {
 		/*
 		 * Is the found extent after a hole in which bno lives?
 		 * Just back up to the previous extent, if so.
@@ -5647,6 +5659,17 @@ __xfs_bunmapi(
 		ASSERT(ep != NULL);
 		del = got;
 		wasdel = isnullstartblock(del.br_startblock);
+
+		/*
+		 * Make sure we don't touch multiple AGF headers out of order
+		 * in a single transaction, as that could cause AB-BA deadlocks.
+		 */
+		if (!wasdel) {
+			agno = XFS_FSB_TO_AGNO(mp, del.br_startblock);
+			if (prev_agno != NULLAGNUMBER && prev_agno > agno)
+				break;
+			prev_agno = agno;
+		}
 		if (got.br_startoff < start) {
 			del.br_startoff = start;
 			del.br_blockcount -= start - got.br_startoff;
@@ -5655,6 +5678,15 @@ __xfs_bunmapi(
 		}
 		if (del.br_startoff + del.br_blockcount > bno + 1)
 			del.br_blockcount = bno + 1 - del.br_startoff;
+
+		/* How much can we safely unmap? */
+		if (max_len < del.br_blockcount) {
+			del.br_startoff += del.br_blockcount - max_len;
+			if (!wasdel)
+				del.br_startblock += del.br_blockcount - max_len;
+			del.br_blockcount = max_len;
+		}
+
 		sum = del.br_startblock + del.br_blockcount;
 		if (isrt &&
 		    (mod = do_mod(sum, mp->m_sb.sb_rextsize))) {
@@ -5835,6 +5867,7 @@ __xfs_bunmapi(
 		if (!isrt && wasdel)
 			xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false);
 
+		max_len -= del.br_blockcount;
 		bno = del.br_startoff - 1;
 nodelete:
 		/*
@@ -6604,25 +6637,33 @@ xfs_bmap_finish_one(
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,
-	xfs_filblks_t			blockcount,
+	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
 	struct xfs_bmbt_irec		bmap;
 	int				nimaps = 1;
 	xfs_fsblock_t			firstfsb;
 	int				flags = XFS_BMAPI_REMAP;
-	int				done;
 	int				error = 0;
 
 	bmap.br_startblock = startblock;
 	bmap.br_startoff = startoff;
-	bmap.br_blockcount = blockcount;
+	bmap.br_blockcount = *blockcount;
 	bmap.br_state = state;
 
+	/*
+	 * firstfsb is tied to the transaction lifetime and is used to
+	 * ensure correct AG locking order and schedule work item
+	 * continuations.  XFS_BUI_MAX_FAST_EXTENTS (== 1) restricts us
+	 * to only making one bmap call per transaction, so it should
+	 * be safe to have it as a local variable here.
+	 */
+	firstfsb = NULLFSBLOCK;
+
 	trace_xfs_bmap_deferred(tp->t_mountp,
 			XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type,
 			XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
-			ip->i_ino, whichfork, startoff, blockcount, state);
+			ip->i_ino, whichfork, startoff, *blockcount, state);
 
 	if (whichfork != XFS_DATA_FORK && whichfork != XFS_ATTR_FORK)
 		return -EFSCORRUPTED;
@@ -6641,12 +6682,11 @@ xfs_bmap_finish_one(
 					bmap.br_blockcount, flags, &firstfsb,
 					bmap.br_blockcount, &bmap, &nimaps,
 					dfops);
+		*blockcount = 0;
 		break;
 	case XFS_BMAP_UNMAP:
-		error = xfs_bunmapi(tp, ip, bmap.br_startoff,
-				bmap.br_blockcount, flags, 1, &firstfsb,
-				dfops, &done);
-		ASSERT(done);
+		error = __xfs_bunmapi(tp, ip, startoff, blockcount,
+				XFS_BMAPI_REMAP, 1, &firstfsb, dfops);
 		break;
 	default:
 		ASSERT(0);

fs/xfs/libxfs/xfs_bmap.h

@@ -265,7 +265,7 @@ struct xfs_bmap_intent {
 int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops,
 		struct xfs_inode *ip, enum xfs_bmap_intent_type type,
 		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t blockcount, xfs_exntst_t state);
+		xfs_filblks_t *blockcount, xfs_exntst_t state);
 int	xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
 int	xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,

fs/xfs/libxfs/xfs_bmap_btree.c

@@ -888,6 +888,7 @@ xfs_bmbt_change_owner(
 	cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork);
 	if (!cur)
 		return -ENOMEM;
+	cur->bc_private.b.flags |= XFS_BTCUR_BPRV_INVALID_OWNER;
 
 	error = xfs_btree_change_owner(cur, new_owner, buffer_list);
 	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);

fs/xfs/libxfs/xfs_btree.c

@@ -714,7 +714,8 @@ xfs_btree_firstrec(
 	 * Get the block pointer for this level.
 	 */
 	block = xfs_btree_get_block(cur, level, &bp);
-	xfs_btree_check_block(cur, block, level, bp);
+	if (xfs_btree_check_block(cur, block, level, bp))
+		return 0;
 	/*
 	 * It's empty, there is no such record.
 	 */
@@ -743,7 +744,8 @@ xfs_btree_lastrec(
 	 * Get the block pointer for this level.
 	 */
 	block = xfs_btree_get_block(cur, level, &bp);
-	xfs_btree_check_block(cur, block, level, bp);
+	if (xfs_btree_check_block(cur, block, level, bp))
+		return 0;
 	/*
 	 * It's empty, there is no such record.
 	 */
@@ -1772,6 +1774,7 @@ xfs_btree_lookup_get_block(
 
 	/* Check the inode owner since the verifiers don't. */
 	if (xfs_sb_version_hascrc(&cur->bc_mp->m_sb) &&
+	    !(cur->bc_private.b.flags & XFS_BTCUR_BPRV_INVALID_OWNER) &&
 	    (cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
 	    be64_to_cpu((*blkp)->bb_u.l.bb_owner) !=
 			cur->bc_private.b.ip->i_ino)
@@ -4432,10 +4435,15 @@ xfs_btree_block_change_owner(
 
 	/* modify the owner */
 	block = xfs_btree_get_block(cur, level, &bp);
-	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		if (block->bb_u.l.bb_owner == cpu_to_be64(bbcoi->new_owner))
+			return 0;
 		block->bb_u.l.bb_owner = cpu_to_be64(bbcoi->new_owner);
-	else
+	} else {
+		if (block->bb_u.s.bb_owner == cpu_to_be32(bbcoi->new_owner))
+			return 0;
 		block->bb_u.s.bb_owner = cpu_to_be32(bbcoi->new_owner);
+	}
 
 	/*
 	 * If the block is a root block hosted in an inode, we might not have a
@@ -4444,16 +4452,19 @@ xfs_btree_block_change_owner(
 	 * block is formatted into the on-disk inode fork. We still change it,
 	 * though, so everything is consistent in memory.
 	 */
-	if (bp) {
-		if (cur->bc_tp) {
-			xfs_trans_ordered_buf(cur->bc_tp, bp);
-			xfs_btree_log_block(cur, bp, XFS_BB_OWNER);
-		} else {
-			xfs_buf_delwri_queue(bp, bbcoi->buffer_list);
-		}
-	} else {
+	if (!bp) {
 		ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
 		ASSERT(level == cur->bc_nlevels - 1);
+		return 0;
+	}
+
+	if (cur->bc_tp) {
+		if (!xfs_trans_ordered_buf(cur->bc_tp, bp)) {
+			xfs_btree_log_block(cur, bp, XFS_BB_OWNER);
+			return -EAGAIN;
+		}
+	} else {
+		xfs_buf_delwri_queue(bp, bbcoi->buffer_list);
 	}
 
 	return 0;

fs/xfs/libxfs/xfs_btree.h

@@ -268,7 +268,8 @@ typedef struct xfs_btree_cur
 			short		forksize;	/* fork's inode space */
 			char		whichfork;	/* data or attr fork */
 			char		flags;		/* flags */
-#define	XFS_BTCUR_BPRV_WASDEL	1			/* was delayed */
+#define	XFS_BTCUR_BPRV_WASDEL		(1<<0)		/* was delayed */
+#define	XFS_BTCUR_BPRV_INVALID_OWNER	(1<<1)		/* for ext swap */
 		} b;
 	}		bc_private;	/* per-btree type data */
 } xfs_btree_cur_t;

fs/xfs/libxfs/xfs_da_btree.c

@@ -263,7 +263,7 @@ xfs_da3_node_read(
 
 	err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp,
 					which_fork, &xfs_da3_node_buf_ops);
-	if (!err && tp) {
+	if (!err && tp && *bpp) {
 		struct xfs_da_blkinfo	*info = (*bpp)->b_addr;
 		int			type;
 

fs/xfs/libxfs/xfs_dir2_block.c

@@ -139,7 +139,7 @@ xfs_dir3_block_read(
 
 	err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, -1, bpp,
 				XFS_DATA_FORK, &xfs_dir3_block_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF);
 	return err;
 }

fs/xfs/libxfs/xfs_dir2_leaf.c

@@ -268,7 +268,7 @@ xfs_dir3_leaf_read(
 
 	err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
 				XFS_DATA_FORK, &xfs_dir3_leaf1_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF);
 	return err;
 }
@@ -285,7 +285,7 @@ xfs_dir3_leafn_read(
 
 	err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
 				XFS_DATA_FORK, &xfs_dir3_leafn_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF);
 	return err;
 }

fs/xfs/libxfs/xfs_ialloc.c

@@ -368,8 +368,6 @@ xfs_ialloc_inode_init(
 				 * transaction and pin the log appropriately.
 				 */
 				xfs_trans_ordered_buf(tp, fbuf);
-				xfs_trans_log_buf(tp, fbuf, 0,
-						  BBTOB(fbuf->b_length) - 1);
 			}
 		} else {
 			fbuf->b_flags |= XBF_DONE;
@@ -1123,6 +1121,7 @@ xfs_dialloc_ag_inobt(
 	int			error;
 	int			offset;
 	int			i, j;
+	int			searchdistance = 10;
 
 	pag = xfs_perag_get(mp, agno);
 
@@ -1149,7 +1148,6 @@ xfs_dialloc_ag_inobt(
 	if (pagno == agno) {
 		int		doneleft;	/* done, to the left */
 		int		doneright;	/* done, to the right */
-		int		searchdistance = 10;
 
 		error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i);
 		if (error)
@@ -1210,21 +1208,9 @@ xfs_dialloc_ag_inobt(
 		/*
 		 * Loop until we find an inode chunk with a free inode.
 		 */
-		while (!doneleft || !doneright) {
+		while (--searchdistance > 0 && (!doneleft || !doneright)) {
 			int	useleft;  /* using left inode chunk this time */
 
-			if (!--searchdistance) {
-				/*
-				 * Not in range - save last search
-				 * location and allocate a new inode
-				 */
-				xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
-				pag->pagl_leftrec = trec.ir_startino;
-				pag->pagl_rightrec = rec.ir_startino;
-				pag->pagl_pagino = pagino;
-				goto newino;
-			}
-
 			/* figure out the closer block if both are valid. */
 			if (!doneleft && !doneright) {
 				useleft = pagino -
@@ -1236,13 +1222,13 @@ xfs_dialloc_ag_inobt(
 
 			/* free inodes to the left? */
 			if (useleft && trec.ir_freecount) {
-				rec = trec;
 				xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 				cur = tcur;
 
 				pag->pagl_leftrec = trec.ir_startino;
 				pag->pagl_rightrec = rec.ir_startino;
 				pag->pagl_pagino = pagino;
+				rec = trec;
 				goto alloc_inode;
 			}
 
@@ -1268,6 +1254,17 @@ xfs_dialloc_ag_inobt(
 				goto error1;
 		}
 
+		if (searchdistance <= 0) {
+			/*
+			 * Not in range - save last search
+			 * location and allocate a new inode
+			 */
+			xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
+			pag->pagl_leftrec = trec.ir_startino;
+			pag->pagl_rightrec = rec.ir_startino;
+			pag->pagl_pagino = pagino;
+
+		} else {
 			/*
 			 * We've reached the end of the btree. because
 			 * we are only searching a small chunk of the
@@ -1282,12 +1279,12 @@ xfs_dialloc_ag_inobt(
 			xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 			goto restart_pagno;
 		}
+	}
 
 	/*
 	 * In a different AG from the parent.
 	 * See if the most recently allocated block has any free.
 	 */
-newino:
 	if (agi->agi_newino != cpu_to_be32(NULLAGINO)) {
 		error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino),
 					 XFS_LOOKUP_EQ, &i);

fs/xfs/libxfs/xfs_inode_fork.c

@@ -1539,14 +1539,11 @@ xfs_iext_realloc_indirect(
 	xfs_ifork_t	*ifp,		/* inode fork pointer */
 	int		new_size)	/* new indirection array size */
 {
-	int		nlists;		/* number of irec's (ex lists) */
-	int		size;		/* current indirection array size */
-
 	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
-	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
-	size = nlists * sizeof(xfs_ext_irec_t);
 	ASSERT(ifp->if_real_bytes);
-	ASSERT((new_size >= 0) && (new_size != size));
+	ASSERT((new_size >= 0) &&
+	       (new_size != ((ifp->if_real_bytes / XFS_IEXT_BUFSZ) *
+			     sizeof(xfs_ext_irec_t))));
 	if (new_size == 0) {
 		xfs_iext_destroy(ifp);
 	} else {

fs/xfs/libxfs/xfs_refcount.c

@@ -784,14 +784,6 @@ xfs_refcount_merge_extents(
 }
 
 /*
- * While we're adjusting the refcounts records of an extent, we have
- * to keep an eye on the number of extents we're dirtying -- run too
- * many in a single transaction and we'll exceed the transaction's
- * reservation and crash the fs.  Each record adds 12 bytes to the
- * log (plus any key updates) so we'll conservatively assume 24 bytes
- * per record.  We must also leave space for btree splits on both ends
- * of the range and space for the CUD and a new CUI.
- *
  * XXX: This is a pretty hand-wavy estimate.  The penalty for guessing
  * true incorrectly is a shutdown FS; the penalty for guessing false
  * incorrectly is more transaction rolls than might be necessary.
@@ -822,7 +814,7 @@ xfs_refcount_still_have_space(
 	else if (overhead > cur->bc_tp->t_log_res)
 		return false;
 	return  cur->bc_tp->t_log_res - overhead >
-		cur->bc_private.a.priv.refc.nr_ops * 32;
+		cur->bc_private.a.priv.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD;
 }
 
 /*
@@ -1648,6 +1640,10 @@ xfs_refcount_recover_cow_leftovers(
 	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		goto out_trans;
+	if (!agbp) {
+		error = -ENOMEM;
+		goto out_trans;
+	}
 	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
 
 	/* Find all the leftover CoW staging extents. */

fs/xfs/libxfs/xfs_refcount.h

@@ -67,4 +67,20 @@ extern int xfs_refcount_free_cow_extent(struct xfs_mount *mp,
 extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
 		xfs_agnumber_t agno);
 
+/*
+ * While we're adjusting the refcounts records of an extent, we have
+ * to keep an eye on the number of extents we're dirtying -- run too
+ * many in a single transaction and we'll exceed the transaction's
+ * reservation and crash the fs.  Each record adds 12 bytes to the
+ * log (plus any key updates) so we'll conservatively assume 32 bytes
+ * per record.  We must also leave space for btree splits on both ends
+ * of the range and space for the CUD and a new CUI.
+ */
+#define XFS_REFCOUNT_ITEM_OVERHEAD	32
+
+static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res)
+{
+	return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD;
+}
+
 #endif	/* __XFS_REFCOUNT_H__ */

fs/xfs/xfs_aops.c

@@ -90,11 +90,11 @@ xfs_find_bdev_for_inode(
  * associated buffer_heads, paying attention to the start and end offsets that
  * we need to process on the page.
  *
- * Landmine Warning: bh->b_end_io() will call end_page_writeback() on the last
- * buffer in the IO. Once it does this, it is unsafe to access the bufferhead or
- * the page at all, as we may be racing with memory reclaim and it can free both
- * the bufferhead chain and the page as it will see the page as clean and
- * unused.
+ * Note that we open code the action in end_buffer_async_write here so that we
+ * only have to iterate over the buffers attached to the page once.  This is not
+ * only more efficient, but also ensures that we only calls end_page_writeback
+ * at the end of the iteration, and thus avoids the pitfall of having the page
+ * and buffers potentially freed after every call to end_buffer_async_write.
  */
 static void
 xfs_finish_page_writeback(
@@ -102,29 +102,45 @@ xfs_finish_page_writeback(
 	struct bio_vec		*bvec,
 	int			error)
 {
-	unsigned int		end = bvec->bv_offset + bvec->bv_len - 1;
-	struct buffer_head	*head, *bh, *next;
+	struct buffer_head	*head = page_buffers(bvec->bv_page), *bh = head;
+	bool			busy = false;
 	unsigned int		off = 0;
-	unsigned int		bsize;
+	unsigned long		flags;
 
 	ASSERT(bvec->bv_offset < PAGE_SIZE);
 	ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0);
-	ASSERT(end < PAGE_SIZE);
+	ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE);
 	ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0);
 
-	bh = head = page_buffers(bvec->bv_page);
-
-	bsize = bh->b_size;
+	local_irq_save(flags);
+	bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
 	do {
-		if (off > end)
-			break;
-		next = bh->b_this_page;
-		if (off < bvec->bv_offset)
-			goto next_bh;
-		bh->b_end_io(bh, !error);
-next_bh:
-		off += bsize;
-	} while ((bh = next) != head);
+		if (off >= bvec->bv_offset &&
+		    off < bvec->bv_offset + bvec->bv_len) {
+			ASSERT(buffer_async_write(bh));
+			ASSERT(bh->b_end_io == NULL);
+
+			if (error) {
+				mapping_set_error(bvec->bv_page->mapping, -EIO);
+				set_buffer_write_io_error(bh);
+				clear_buffer_uptodate(bh);
+				SetPageError(bvec->bv_page);
+			} else {
+				set_buffer_uptodate(bh);
+			}
+			clear_buffer_async_write(bh);
+			unlock_buffer(bh);
+		} else if (buffer_async_write(bh)) {
+			ASSERT(buffer_locked(bh));
+			busy = true;
+		}
+		off += bh->b_size;
+	} while ((bh = bh->b_this_page) != head);
+	bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
+	local_irq_restore(flags);
+
+	if (!busy)
+		end_page_writeback(bvec->bv_page);
 }
 
 /*
@@ -138,8 +154,10 @@ xfs_destroy_ioend(
 	int			error)
 {
 	struct inode		*inode = ioend->io_inode;
-	struct bio		*last = ioend->io_bio;
-	struct bio		*bio, *next;
+	struct bio		*bio = &ioend->io_inline_bio;
+	struct bio		*last = ioend->io_bio, *next;
+	u64			start = bio->bi_iter.bi_sector;
+	bool			quiet = bio_flagged(bio, BIO_QUIET);
 
 	for (bio = &ioend->io_inline_bio; bio; bio = next) {
 		struct bio_vec	*bvec;
@@ -160,6 +178,11 @@ xfs_destroy_ioend(
 
 		bio_put(bio);
 	}
+
+	if (unlikely(error && !quiet)) {
+		xfs_err_ratelimited(XFS_I(inode)->i_mount,
+			"writeback error on sector %llu", start);
+	}
 }
 
 /*
@@ -427,7 +450,8 @@ xfs_start_buffer_writeback(
 	ASSERT(!buffer_delay(bh));
 	ASSERT(!buffer_unwritten(bh));
 
-	mark_buffer_async_write(bh);
+	bh->b_end_io = NULL;
+	set_buffer_async_write(bh);
 	set_buffer_uptodate(bh);
 	clear_buffer_dirty(bh);
 }
@@ -1566,9 +1590,12 @@ xfs_vm_bmap(
 	 * The swap code (ab-)uses ->bmap to get a block mapping and then
 	 * bypasseѕ the file system for actual I/O.  We really can't allow
 	 * that on reflinks inodes, so we have to skip out here.  And yes,
-	 * 0 is the magic code for a bmap error..
+	 * 0 is the magic code for a bmap error.
+	 *
+	 * Since we don't pass back blockdev info, we can't return bmap
+	 * information for rt files either.
 	 */
-	if (xfs_is_reflink_inode(ip)) {
+	if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip)) {
 		xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 		return 0;
 	}

fs/xfs/xfs_bmap_item.c

@@ -395,6 +395,7 @@ xfs_bui_recover(
 	struct xfs_map_extent		*bmap;
 	xfs_fsblock_t			startblock_fsb;
 	xfs_fsblock_t			inode_fsb;
+	xfs_filblks_t			count;
 	bool				op_ok;
 	struct xfs_bud_log_item		*budp;
 	enum xfs_bmap_intent_type	type;
@@ -403,6 +404,7 @@ xfs_bui_recover(
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip = NULL;
 	struct xfs_defer_ops		dfops;
+	struct xfs_bmbt_irec		irec;
 	xfs_fsblock_t			firstfsb;
 
 	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
@@ -480,13 +482,24 @@ xfs_bui_recover(
 	}
 	xfs_trans_ijoin(tp, ip, 0);
 
+	count = bmap->me_len;
 	error = xfs_trans_log_finish_bmap_update(tp, budp, &dfops, type,
 			ip, whichfork, bmap->me_startoff,
-			bmap->me_startblock, bmap->me_len,
-			state);
+			bmap->me_startblock, &count, state);
 	if (error)
 		goto err_dfops;
 
+	if (count > 0) {
+		ASSERT(type == XFS_BMAP_UNMAP);
+		irec.br_startblock = bmap->me_startblock;
+		irec.br_blockcount = count;
+		irec.br_startoff = bmap->me_startoff;
+		irec.br_state = state;
+		error = xfs_bmap_unmap_extent(tp->t_mountp, &dfops, ip, &irec);
+		if (error)
+			goto err_dfops;
+	}
+
 	/* Finish transaction, free inodes. */
 	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)

fs/xfs/xfs_bmap_util.c

@@ -1825,29 +1825,18 @@ xfs_swap_extent_forks(
 	}
 
 	/*
-	 * Before we've swapped the forks, lets set the owners of the forks
-	 * appropriately. We have to do this as we are demand paging the btree
-	 * buffers, and so the validation done on read will expect the owner
-	 * field to be correctly set. Once we change the owners, we can swap the
-	 * inode forks.
+	 * Btree format (v3) inodes have the inode number stamped in the bmbt
+	 * block headers. We can't start changing the bmbt blocks until the
+	 * inode owner change is logged so recovery does the right thing in the
+	 * event of a crash. Set the owner change log flags now and leave the
+	 * bmbt scan as the last step.
 	 */
 	if (ip->i_d.di_version == 3 &&
-	    ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+	    ip->i_d.di_format == XFS_DINODE_FMT_BTREE)
 		(*target_log_flags) |= XFS_ILOG_DOWNER;
-		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
-					      tip->i_ino, NULL);
-		if (error)
-			return error;
-	}
-
 	if (tip->i_d.di_version == 3 &&
-	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
 		(*src_log_flags) |= XFS_ILOG_DOWNER;
-		error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
-					      ip->i_ino, NULL);
-		if (error)
-			return error;
-	}
 
 	/*
 	 * Swap the data forks of the inodes
@@ -1925,6 +1914,48 @@ xfs_swap_extent_forks(
 	return 0;
 }
 
+/*
+ * Fix up the owners of the bmbt blocks to refer to the current inode. The
+ * change owner scan attempts to order all modified buffers in the current
+ * transaction. In the event of ordered buffer failure, the offending buffer is
+ * physically logged as a fallback and the scan returns -EAGAIN. We must roll
+ * the transaction in this case to replenish the fallback log reservation and
+ * restart the scan. This process repeats until the scan completes.
+ */
+static int
+xfs_swap_change_owner(
+	struct xfs_trans	**tpp,
+	struct xfs_inode	*ip,
+	struct xfs_inode	*tmpip)
+{
+	int			error;
+	struct xfs_trans	*tp = *tpp;
+
+	do {
+		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino,
+					      NULL);
+		/* success or fatal error */
+		if (error != -EAGAIN)
+			break;
+
+		error = xfs_trans_roll(tpp, NULL);
+		if (error)
+			break;
+		tp = *tpp;
+
+		/*
+		 * Redirty both inodes so they can relog and keep the log tail
+		 * moving forward.
+		 */
+		xfs_trans_ijoin(tp, ip, 0);
+		xfs_trans_ijoin(tp, tmpip, 0);
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+		xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE);
+	} while (true);
+
+	return error;
+}
+
 int
 xfs_swap_extents(
 	struct xfs_inode	*ip,	/* target inode */
@@ -1938,8 +1969,8 @@ xfs_swap_extents(
 	int			error = 0;
 	int			lock_flags;
 	struct xfs_ifork	*cowfp;
-	__uint64_t		f;
-	int			resblks;
+	uint64_t		f;
+	int			resblks = 0;
 
 	/*
 	 * Lock the inodes against other IO, page faults and truncate to
@@ -1987,11 +2018,8 @@ xfs_swap_extents(
 			  XFS_SWAP_RMAP_SPACE_RES(mp,
 				XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK),
 				XFS_DATA_FORK);
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks,
-				0, 0, &tp);
-	} else
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0,
-				0, 0, &tp);
+	}
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
 	if (error)
 		goto out_unlock;
 
@@ -2076,6 +2104,23 @@ xfs_swap_extents(
 	xfs_trans_log_inode(tp, ip,  src_log_flags);
 	xfs_trans_log_inode(tp, tip, target_log_flags);
 
+	/*
+	 * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems
+	 * have inode number owner values in the bmbt blocks that still refer to
+	 * the old inode. Scan each bmbt to fix up the owner values with the
+	 * inode number of the current inode.
+	 */
+	if (src_log_flags & XFS_ILOG_DOWNER) {
+		error = xfs_swap_change_owner(&tp, ip, tip);
+		if (error)
+			goto out_trans_cancel;
+	}
+	if (target_log_flags & XFS_ILOG_DOWNER) {
+		error = xfs_swap_change_owner(&tp, tip, ip);
+		if (error)
+			goto out_trans_cancel;
+	}
+
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * transaction goes to disk before returning to the user.

fs/xfs/xfs_buf.c

@@ -116,7 +116,7 @@ static inline void
 __xfs_buf_ioacct_dec(
 	struct xfs_buf	*bp)
 {
-	ASSERT(spin_is_locked(&bp->b_lock));
+	lockdep_assert_held(&bp->b_lock);
 
 	if (bp->b_state & XFS_BSTATE_IN_FLIGHT) {
 		bp->b_state &= ~XFS_BSTATE_IN_FLIGHT;
@@ -2022,6 +2022,66 @@ xfs_buf_delwri_submit(
 	return error;
 }
 
+/*
+ * Push a single buffer on a delwri queue.
+ *
+ * The purpose of this function is to submit a single buffer of a delwri queue
+ * and return with the buffer still on the original queue. The waiting delwri
+ * buffer submission infrastructure guarantees transfer of the delwri queue
+ * buffer reference to a temporary wait list. We reuse this infrastructure to
+ * transfer the buffer back to the original queue.
+ *
+ * Note the buffer transitions from the queued state, to the submitted and wait
+ * listed state and back to the queued state during this call. The buffer
+ * locking and queue management logic between _delwri_pushbuf() and
+ * _delwri_queue() guarantee that the buffer cannot be queued to another list
+ * before returning.
+ */
+int
+xfs_buf_delwri_pushbuf(
+	struct xfs_buf		*bp,
+	struct list_head	*buffer_list)
+{
+	LIST_HEAD		(submit_list);
+	int			error;
+
+	ASSERT(bp->b_flags & _XBF_DELWRI_Q);
+
+	trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_);
+
+	/*
+	 * Isolate the buffer to a new local list so we can submit it for I/O
+	 * independently from the rest of the original list.
+	 */
+	xfs_buf_lock(bp);
+	list_move(&bp->b_list, &submit_list);
+	xfs_buf_unlock(bp);
+
+	/*
+	 * Delwri submission clears the DELWRI_Q buffer flag and returns with
+	 * the buffer on the wait list with an associated reference. Rather than
+	 * bounce the buffer from a local wait list back to the original list
+	 * after I/O completion, reuse the original list as the wait list.
+	 */
+	xfs_buf_delwri_submit_buffers(&submit_list, buffer_list);
+
+	/*
+	 * The buffer is now under I/O and wait listed as during typical delwri
+	 * submission. Lock the buffer to wait for I/O completion. Rather than
+	 * remove the buffer from the wait list and release the reference, we
+	 * want to return with the buffer queued to the original list. The
+	 * buffer already sits on the original list with a wait list reference,
+	 * however. If we let the queue inherit that wait list reference, all we
+	 * need to do is reset the DELWRI_Q flag.
+	 */
+	xfs_buf_lock(bp);
+	error = bp->b_error;
+	bp->b_flags |= _XBF_DELWRI_Q;
+	xfs_buf_unlock(bp);
+
+	return error;
+}
+
 int __init
 xfs_buf_init(void)
 {

fs/xfs/xfs_buf.h

@@ -333,6 +333,7 @@ extern void xfs_buf_delwri_cancel(struct list_head *);
 extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
 extern int xfs_buf_delwri_submit(struct list_head *);
 extern int xfs_buf_delwri_submit_nowait(struct list_head *);
+extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *);
 
 /* Buffer Daemon Setup Routines */
 extern int xfs_buf_init(void);

fs/xfs/xfs_buf_item.c

@@ -29,6 +29,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_log.h"
+#include "xfs_inode.h"
 
 
 kmem_zone_t	*xfs_buf_item_zone;
@@ -322,6 +323,8 @@ xfs_buf_item_format(
 	ASSERT((bip->bli_flags & XFS_BLI_STALE) ||
 	       (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF
 	        && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF));
+	ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED) ||
+	       (bip->bli_flags & XFS_BLI_STALE));
 
 
 	/*
@@ -346,16 +349,6 @@ xfs_buf_item_format(
 		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
 	}
 
-	if ((bip->bli_flags & (XFS_BLI_ORDERED|XFS_BLI_STALE)) ==
-							XFS_BLI_ORDERED) {
-		/*
-		 * The buffer has been logged just to order it.  It is not being
-		 * included in the transaction commit, so don't format it.
-		 */
-		trace_xfs_buf_item_format_ordered(bip);
-		return;
-	}
-
 	for (i = 0; i < bip->bli_format_count; i++) {
 		xfs_buf_item_format_segment(bip, lv, &vecp, offset,
 					    &bip->bli_formats[i]);
@@ -574,26 +567,20 @@ xfs_buf_item_unlock(
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
-	bool			clean;
-	bool			aborted;
-	int			flags;
+	bool			aborted = !!(lip->li_flags & XFS_LI_ABORTED);
+	bool			hold = !!(bip->bli_flags & XFS_BLI_HOLD);
+	bool			dirty = !!(bip->bli_flags & XFS_BLI_DIRTY);
+#if defined(DEBUG) || defined(XFS_WARN)
+	bool			ordered = !!(bip->bli_flags & XFS_BLI_ORDERED);
+#endif
 
 	/* Clear the buffer's association with this transaction. */
 	bp->b_transp = NULL;
 
 	/*
-	 * If this is a transaction abort, don't return early.  Instead, allow
-	 * the brelse to happen.  Normally it would be done for stale
-	 * (cancelled) buffers at unpin time, but we'll never go through the
-	 * pin/unpin cycle if we abort inside commit.
+	 * The per-transaction state has been copied above so clear it from the
+	 * bli.
 	 */
-	aborted = (lip->li_flags & XFS_LI_ABORTED) ? true : false;
-	/*
-	 * Before possibly freeing the buf item, copy the per-transaction state
-	 * so we can reference it safely later after clearing it from the
-	 * buffer log item.
-	 */
-	flags = bip->bli_flags;
 	bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
 
 	/*
@@ -601,7 +588,7 @@ xfs_buf_item_unlock(
 	 * unlock the buffer and free the buf item when the buffer is unpinned
 	 * for the last time.
 	 */
-	if (flags & XFS_BLI_STALE) {
+	if (bip->bli_flags & XFS_BLI_STALE) {
 		trace_xfs_buf_item_unlock_stale(bip);
 		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 		if (!aborted) {
@@ -619,40 +606,34 @@ xfs_buf_item_unlock(
 	 * regardless of whether it is dirty or not. A dirty abort implies a
 	 * shutdown, anyway.
 	 *
-	 * Ordered buffers are dirty but may have no recorded changes, so ensure
-	 * we only release clean items here.
+	 * The bli dirty state should match whether the blf has logged segments
+	 * except for ordered buffers, where only the bli should be dirty.
 	 */
-	clean = (flags & XFS_BLI_DIRTY) ? false : true;
-	if (clean) {
-		int i;
-		for (i = 0; i < bip->bli_format_count; i++) {
-			if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map,
-				     bip->bli_formats[i].blf_map_size)) {
-				clean = false;
-				break;
-			}
-		}
-	}
+	ASSERT((!ordered && dirty == xfs_buf_item_dirty_format(bip)) ||
+	       (ordered && dirty && !xfs_buf_item_dirty_format(bip)));
 
 	/*
 	 * Clean buffers, by definition, cannot be in the AIL. However, aborted
-	 * buffers may be dirty and hence in the AIL. Therefore if we are
-	 * aborting a buffer and we've just taken the last refernce away, we
-	 * have to check if it is in the AIL before freeing it. We need to free
-	 * it in this case, because an aborted transaction has already shut the
-	 * filesystem down and this is the last chance we will have to do so.
+	 * buffers may be in the AIL regardless of dirty state. An aborted
+	 * transaction that invalidates a buffer already in the AIL may have
+	 * marked it stale and cleared the dirty state, for example.
+	 *
+	 * Therefore if we are aborting a buffer and we've just taken the last
+	 * reference away, we have to check if it is in the AIL before freeing
+	 * it. We need to free it in this case, because an aborted transaction
+	 * has already shut the filesystem down and this is the last chance we
+	 * will have to do so.
 	 */
 	if (atomic_dec_and_test(&bip->bli_refcount)) {
-		if (clean)
-			xfs_buf_item_relse(bp);
-		else if (aborted) {
+		if (aborted) {
 			ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
 			xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR);
 			xfs_buf_item_relse(bp);
-		}
+		} else if (!dirty)
+			xfs_buf_item_relse(bp);
 	}
 
-	if (!(flags & XFS_BLI_HOLD))
+	if (!hold)
 		xfs_buf_relse(bp);
 }
 
@@ -942,14 +923,22 @@ xfs_buf_item_log(
 
 
 /*
- * Return 1 if the buffer has been logged or ordered in a transaction (at any
- * point, not just the current transaction) and 0 if not.
+ * Return true if the buffer has any ranges logged/dirtied by a transaction,
+ * false otherwise.
  */
-uint
-xfs_buf_item_dirty(
-	xfs_buf_log_item_t	*bip)
+bool
+xfs_buf_item_dirty_format(
+	struct xfs_buf_log_item	*bip)
 {
-	return (bip->bli_flags & XFS_BLI_DIRTY);
+	int			i;
+
+	for (i = 0; i < bip->bli_format_count; i++) {
+		if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map,
+			     bip->bli_formats[i].blf_map_size))
+			return true;
+	}
+
+	return false;
 }
 
 STATIC void
@@ -1051,6 +1040,31 @@ xfs_buf_do_callbacks(
 	}
 }
 
+/*
+ * Invoke the error state callback for each log item affected by the failed I/O.
+ *
+ * If a metadata buffer write fails with a non-permanent error, the buffer is
+ * eventually resubmitted and so the completion callbacks are not run. The error
+ * state may need to be propagated to the log items attached to the buffer,
+ * however, so the next AIL push of the item knows hot to handle it correctly.
+ */
+STATIC void
+xfs_buf_do_callbacks_fail(
+	struct xfs_buf		*bp)
+{
+	struct xfs_log_item	*next;
+	struct xfs_log_item	*lip = bp->b_fspriv;
+	struct xfs_ail		*ailp = lip->li_ailp;
+
+	spin_lock(&ailp->xa_lock);
+	for (; lip; lip = next) {
+		next = lip->li_bio_list;
+		if (lip->li_ops->iop_error)
+			lip->li_ops->iop_error(lip, bp);
+	}
+	spin_unlock(&ailp->xa_lock);
+}
+
 static bool
 xfs_buf_iodone_callback_error(
 	struct xfs_buf		*bp)
@@ -1120,7 +1134,11 @@ xfs_buf_iodone_callback_error(
 	if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount)
 		goto permanent_error;
 
-	/* still a transient error, higher layers will retry */
+	/*
+	 * Still a transient error, run IO completion failure callbacks and let
+	 * the higher layers retry the buffer.
+	 */
+	xfs_buf_do_callbacks_fail(bp);
 	xfs_buf_ioerror(bp, 0);
 	xfs_buf_relse(bp);
 	return true;
@@ -1201,3 +1219,31 @@ xfs_buf_iodone(
 	xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
 	xfs_buf_item_free(BUF_ITEM(lip));
 }
+
+/*
+ * Requeue a failed buffer for writeback
+ *
+ * Return true if the buffer has been re-queued properly, false otherwise
+ */
+bool
+xfs_buf_resubmit_failed_buffers(
+	struct xfs_buf		*bp,
+	struct xfs_log_item	*lip,
+	struct list_head	*buffer_list)
+{
+	struct xfs_log_item	*next;
+
+	/*
+	 * Clear XFS_LI_FAILED flag from all items before resubmit
+	 *
+	 * XFS_LI_FAILED set/clear is protected by xa_lock, caller  this
+	 * function already have it acquired
+	 */
+	for (; lip; lip = next) {
+		next = lip->li_bio_list;
+		xfs_clear_li_failed(lip);
+	}
+
+	/* Add this buffer back to the delayed write list */
+	return xfs_buf_delwri_queue(bp, buffer_list);
+}

fs/xfs/xfs_buf_item.h

@@ -64,12 +64,15 @@ typedef struct xfs_buf_log_item {
 int	xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
 void	xfs_buf_item_relse(struct xfs_buf *);
 void	xfs_buf_item_log(xfs_buf_log_item_t *, uint, uint);
-uint	xfs_buf_item_dirty(xfs_buf_log_item_t *);
+bool	xfs_buf_item_dirty_format(struct xfs_buf_log_item *);
 void	xfs_buf_attach_iodone(struct xfs_buf *,
 			      void(*)(struct xfs_buf *, xfs_log_item_t *),
 			      xfs_log_item_t *);
 void	xfs_buf_iodone_callbacks(struct xfs_buf *);
 void	xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *);
+bool	xfs_buf_resubmit_failed_buffers(struct xfs_buf *,
+					struct xfs_log_item *,
+					struct list_head *);
 
 extern kmem_zone_t	*xfs_buf_item_zone;
 

fs/xfs/xfs_file.c

@@ -729,6 +729,7 @@ write_retry:
 		xfs_rw_iunlock(ip, iolock);
 		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
 		xfs_icache_free_eofblocks(ip->i_mount, &eofb);
+		xfs_icache_free_cowblocks(ip->i_mount, &eofb);
 		goto write_retry;
 	}
 
@@ -1139,30 +1140,9 @@ xfs_find_get_desired_pgoff(
 		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  want);
-		/*
-		 * No page mapped into given range.  If we are searching holes
-		 * and if this is the first time we got into the loop, it means
-		 * that the given offset is landed in a hole, return it.
-		 *
-		 * If we have already stepped through some block buffers to find
-		 * holes but they all contains data.  In this case, the last
-		 * offset is already updated and pointed to the end of the last
-		 * mapped page, if it does not reach the endpoint to search,
-		 * that means there should be a hole between them.
-		 */
-		if (nr_pages == 0) {
-			/* Data search found nothing */
-			if (type == DATA_OFF)
+		if (nr_pages == 0)
 			break;
 
-			ASSERT(type == HOLE_OFF);
-			if (lastoff == startoff || lastoff < endoff) {
-				found = true;
-				*offset = lastoff;
-			}
-			break;
-		}
-
 		for (i = 0; i < nr_pages; i++) {
 			struct page	*page = pvec.pages[i];
 			loff_t		b_offset;
@@ -1227,21 +1207,20 @@ xfs_find_get_desired_pgoff(
 
 		/*
 		 * The number of returned pages less than our desired, search
-		 * done.  In this case, nothing was found for searching data,
-		 * but we found a hole behind the last offset.
+		 * done.
 		 */
-		if (nr_pages < want) {
-			if (type == HOLE_OFF) {
-				*offset = lastoff;
-				found = true;
-			}
+		if (nr_pages < want)
 			break;
-		}
 
 		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	/* No page at lastoff and we are not done - we found a hole. */
+	if (type == HOLE_OFF && lastoff < endoff) {
+		*offset = lastoff;
+		found = true;
+	}
 out:
 	pagevec_release(&pvec);
 	return found;

fs/xfs/xfs_icache.c

@@ -66,7 +66,6 @@ xfs_inode_alloc(
 
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
-	ASSERT(!spin_is_locked(&ip->i_flags_lock));
 	ASSERT(!xfs_isiflocked(ip));
 	ASSERT(ip->i_ino == 0);
 
@@ -192,7 +191,7 @@ xfs_perag_set_reclaim_tag(
 {
 	struct xfs_mount	*mp = pag->pag_mount;
 
-	ASSERT(spin_is_locked(&pag->pag_ici_lock));
+	lockdep_assert_held(&pag->pag_ici_lock);
 	if (pag->pag_ici_reclaimable++)
 		return;
 
@@ -214,7 +213,7 @@ xfs_perag_clear_reclaim_tag(
 {
 	struct xfs_mount	*mp = pag->pag_mount;
 
-	ASSERT(spin_is_locked(&pag->pag_ici_lock));
+	lockdep_assert_held(&pag->pag_ici_lock);
 	if (--pag->pag_ici_reclaimable)
 		return;
 
@@ -1079,11 +1078,11 @@ reclaim:
 	 * Because we use RCU freeing we need to ensure the inode always appears
 	 * to be reclaimed with an invalid inode number when in the free state.
 	 * We do this as early as possible under the ILOCK so that
-	 * xfs_iflush_cluster() can be guaranteed to detect races with us here.
-	 * By doing this, we guarantee that once xfs_iflush_cluster has locked
-	 * XFS_ILOCK that it will see either a valid, flushable inode that will
-	 * serialise correctly, or it will see a clean (and invalid) inode that
-	 * it can skip.
+	 * xfs_iflush_cluster() and xfs_ifree_cluster() can be guaranteed to
+	 * detect races with us here. By doing this, we guarantee that once
+	 * xfs_iflush_cluster() or xfs_ifree_cluster() has locked XFS_ILOCK that
+	 * it will see either a valid inode that will serialise correctly, or it
+	 * will see an invalid inode that it can skip.
 	 */
 	spin_lock(&ip->i_flags_lock);
 	ip->i_flags = XFS_IRECLAIM;

fs/xfs/xfs_inode.c

@@ -881,7 +881,6 @@ xfs_ialloc(
 	case S_IFREG:
 	case S_IFDIR:
 		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
-			uint64_t	di_flags2 = 0;
 			uint		di_flags = 0;
 
 			if (S_ISDIR(mode)) {
@@ -918,20 +917,23 @@ xfs_ialloc(
 				di_flags |= XFS_DIFLAG_NODEFRAG;
 			if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
 				di_flags |= XFS_DIFLAG_FILESTREAM;
-			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
-				di_flags2 |= XFS_DIFLAG2_DAX;
 
 			ip->i_d.di_flags |= di_flags;
-			ip->i_d.di_flags2 |= di_flags2;
 		}
 		if (pip &&
 		    (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) &&
 		    pip->i_d.di_version == 3 &&
 		    ip->i_d.di_version == 3) {
+			uint64_t	di_flags2 = 0;
+
 			if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
-				ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+				di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
 				ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
 			}
+			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+				di_flags2 |= XFS_DIFLAG2_DAX;
+
+			ip->i_d.di_flags2 |= di_flags2;
 		}
 		/* FALLTHROUGH */
 	case S_IFLNK:
@@ -2366,12 +2368,25 @@ retry:
 			 * already marked stale. If we can't lock it, back off
 			 * and retry.
 			 */
-			if (ip != free_ip &&
-			    !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+			if (ip != free_ip) {
+				if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
 					rcu_read_unlock();
 					delay(1);
 					goto retry;
 				}
+
+				/*
+				 * Check the inode number again in case we're
+				 * racing with freeing in xfs_reclaim_inode().
+				 * See the comments in that function for more
+				 * information as to why the initial check is
+				 * not sufficient.
+				 */
+				if (ip->i_ino != inum + i) {
+					xfs_iunlock(ip, XFS_ILOCK_EXCL);
+					continue;
+				}
+			}
 			rcu_read_unlock();
 
 			xfs_iflock(ip);

fs/xfs/xfs_inode_item.c

@@ -27,6 +27,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_trans_priv.h"
+#include "xfs_buf_item.h"
 #include "xfs_log.h"
 
 
@@ -475,6 +476,23 @@ xfs_inode_item_unpin(
 		wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
 }
 
+/*
+ * Callback used to mark a buffer with XFS_LI_FAILED when items in the buffer
+ * have been failed during writeback
+ *
+ * This informs the AIL that the inode is already flush locked on the next push,
+ * and acquires a hold on the buffer to ensure that it isn't reclaimed before
+ * dirty data makes it to disk.
+ */
+STATIC void
+xfs_inode_item_error(
+	struct xfs_log_item	*lip,
+	struct xfs_buf		*bp)
+{
+	ASSERT(xfs_isiflocked(INODE_ITEM(lip)->ili_inode));
+	xfs_set_li_failed(lip, bp);
+}
+
 STATIC uint
 xfs_inode_item_push(
 	struct xfs_log_item	*lip,
@@ -484,13 +502,28 @@ xfs_inode_item_push(
 {
 	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
 	struct xfs_inode	*ip = iip->ili_inode;
-	struct xfs_buf		*bp = NULL;
+	struct xfs_buf		*bp = lip->li_buf;
 	uint			rval = XFS_ITEM_SUCCESS;
 	int			error;
 
 	if (xfs_ipincount(ip) > 0)
 		return XFS_ITEM_PINNED;
 
+	/*
+	 * The buffer containing this item failed to be written back
+	 * previously. Resubmit the buffer for IO.
+	 */
+	if (lip->li_flags & XFS_LI_FAILED) {
+		if (!xfs_buf_trylock(bp))
+			return XFS_ITEM_LOCKED;
+
+		if (!xfs_buf_resubmit_failed_buffers(bp, lip, buffer_list))
+			rval = XFS_ITEM_FLUSHING;
+
+		xfs_buf_unlock(bp);
+		return rval;
+	}
+
 	if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
 		return XFS_ITEM_LOCKED;
 
@@ -622,7 +655,8 @@ static const struct xfs_item_ops xfs_inode_item_ops = {
 	.iop_unlock	= xfs_inode_item_unlock,
 	.iop_committed	= xfs_inode_item_committed,
 	.iop_push	= xfs_inode_item_push,
-	.iop_committing = xfs_inode_item_committing
+	.iop_committing = xfs_inode_item_committing,
+	.iop_error	= xfs_inode_item_error
 };
 
 
@@ -710,7 +744,8 @@ xfs_iflush_done(
 		 * the AIL lock.
 		 */
 		iip = INODE_ITEM(blip);
-		if (iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn)
+		if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) ||
+		    lip->li_flags & XFS_LI_FAILED)
 			need_ail++;
 
 		blip = next;
@@ -718,7 +753,8 @@ xfs_iflush_done(
 
 	/* make sure we capture the state of the initial inode. */
 	iip = INODE_ITEM(lip);
-	if (iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn)
+	if ((iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) ||
+	    lip->li_flags & XFS_LI_FAILED)
 		need_ail++;
 
 	/*
@@ -731,22 +767,30 @@ xfs_iflush_done(
 	 * holding the lock before removing the inode from the AIL.
 	 */
 	if (need_ail) {
-		struct xfs_log_item *log_items[need_ail];
-		int i = 0;
+		bool			mlip_changed = false;
+
+		/* this is an opencoded batch version of xfs_trans_ail_delete */
 		spin_lock(&ailp->xa_lock);
 		for (blip = lip; blip; blip = blip->li_bio_list) {
-			iip = INODE_ITEM(blip);
-			if (iip->ili_logged &&
-			    blip->li_lsn == iip->ili_flush_lsn) {
-				log_items[i++] = blip;
+			if (INODE_ITEM(blip)->ili_logged &&
+			    blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn)
+				mlip_changed |= xfs_ail_delete_one(ailp, blip);
+			else {
+				xfs_clear_li_failed(blip);
 			}
-			ASSERT(i <= need_ail);
-		}
-		/* xfs_trans_ail_delete_bulk() drops the AIL lock. */
-		xfs_trans_ail_delete_bulk(ailp, log_items, i,
-					  SHUTDOWN_CORRUPT_INCORE);
 		}
 
+		if (mlip_changed) {
+			if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount))
+				xlog_assign_tail_lsn_locked(ailp->xa_mount);
+			if (list_empty(&ailp->xa_ail))
+				wake_up_all(&ailp->xa_empty);
+		}
+		spin_unlock(&ailp->xa_lock);
+
+		if (mlip_changed)
+			xfs_log_space_wake(ailp->xa_mount);
+	}
 
 	/*
 	 * clean up and unlock the flush lock now we are done. We can clear the

fs/xfs/xfs_ioctl.c

@@ -928,16 +928,15 @@ xfs_ioc_fsgetxattr(
 	return 0;
 }
 
-STATIC void
-xfs_set_diflags(
+STATIC uint16_t
+xfs_flags2diflags(
 	struct xfs_inode	*ip,
 	unsigned int		xflags)
 {
-	unsigned int		di_flags;
-	uint64_t		di_flags2;
-
 	/* can't set PREALLOC this way, just preserve it */
-	di_flags = (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC);
+	uint16_t		di_flags =
+		(ip->i_d.di_flags & XFS_DIFLAG_PREALLOC);
+
 	if (xflags & FS_XFLAG_IMMUTABLE)
 		di_flags |= XFS_DIFLAG_IMMUTABLE;
 	if (xflags & FS_XFLAG_APPEND)
@@ -967,19 +966,24 @@ xfs_set_diflags(
 		if (xflags & FS_XFLAG_EXTSIZE)
 			di_flags |= XFS_DIFLAG_EXTSIZE;
 	}
-	ip->i_d.di_flags = di_flags;
 
-	/* diflags2 only valid for v3 inodes. */
-	if (ip->i_d.di_version < 3)
-		return;
+	return di_flags;
+}
+
+STATIC uint64_t
+xfs_flags2diflags2(
+	struct xfs_inode	*ip,
+	unsigned int		xflags)
+{
+	uint64_t		di_flags2 =
+		(ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK);
 
-	di_flags2 = (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK);
 	if (xflags & FS_XFLAG_DAX)
 		di_flags2 |= XFS_DIFLAG2_DAX;
 	if (xflags & FS_XFLAG_COWEXTSIZE)
 		di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
 
-	ip->i_d.di_flags2 = di_flags2;
+	return di_flags2;
 }
 
 STATIC void
@@ -1005,11 +1009,12 @@ xfs_diflags_to_linux(
 		inode->i_flags |= S_NOATIME;
 	else
 		inode->i_flags &= ~S_NOATIME;
+#if 0	/* disabled until the flag switching races are sorted out */
 	if (xflags & FS_XFLAG_DAX)
 		inode->i_flags |= S_DAX;
 	else
 		inode->i_flags &= ~S_DAX;
-
+#endif
 }
 
 static int
@@ -1019,6 +1024,7 @@ xfs_ioctl_setattr_xflags(
 	struct fsxattr		*fa)
 {
 	struct xfs_mount	*mp = ip->i_mount;
+	uint64_t		di_flags2;
 
 	/* Can't change realtime flag if any extents are allocated. */
 	if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
@@ -1049,7 +1055,14 @@ xfs_ioctl_setattr_xflags(
 	    !capable(CAP_LINUX_IMMUTABLE))
 		return -EPERM;
 
-	xfs_set_diflags(ip, fa->fsx_xflags);
+	/* diflags2 only valid for v3 inodes. */
+	di_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
+	if (di_flags2 && ip->i_d.di_version < 3)
+		return -EINVAL;
+
+	ip->i_d.di_flags = xfs_flags2diflags(ip, fa->fsx_xflags);
+	ip->i_d.di_flags2 = di_flags2;
+
 	xfs_diflags_to_linux(ip);
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

fs/xfs/xfs_iops.c

@@ -802,7 +802,7 @@ xfs_vn_setattr_nonsize(
  * Caution: The caller of this function is responsible for calling
  * setattr_prepare() or otherwise verifying the change is fine.
  */
-int
+STATIC int
 xfs_setattr_size(
 	struct xfs_inode	*ip,
 	struct iattr		*iattr)

fs/xfs/xfs_log.c

@@ -743,15 +743,45 @@ xfs_log_mount_finish(
 	struct xfs_mount	*mp)
 {
 	int	error = 0;
+	bool	readonly = (mp->m_flags & XFS_MOUNT_RDONLY);
 
 	if (mp->m_flags & XFS_MOUNT_NORECOVERY) {
 		ASSERT(mp->m_flags & XFS_MOUNT_RDONLY);
 		return 0;
+	} else if (readonly) {
+		/* Allow unlinked processing to proceed */
+		mp->m_flags &= ~XFS_MOUNT_RDONLY;
 	}
 
+	/*
+	 * During the second phase of log recovery, we need iget and
+	 * iput to behave like they do for an active filesystem.
+	 * xfs_fs_drop_inode needs to be able to prevent the deletion
+	 * of inodes before we're done replaying log items on those
+	 * inodes.  Turn it off immediately after recovery finishes
+	 * so that we don't leak the quota inodes if subsequent mount
+	 * activities fail.
+	 *
+	 * We let all inodes involved in redo item processing end up on
+	 * the LRU instead of being evicted immediately so that if we do
+	 * something to an unlinked inode, the irele won't cause
+	 * premature truncation and freeing of the inode, which results
+	 * in log recovery failure.  We have to evict the unreferenced
+	 * lru inodes after clearing MS_ACTIVE because we don't
+	 * otherwise clean up the lru if there's a subsequent failure in
+	 * xfs_mountfs, which leads to us leaking the inodes if nothing
+	 * else (e.g. quotacheck) references the inodes before the
+	 * mount failure occurs.
+	 */
+	mp->m_super->s_flags |= MS_ACTIVE;
 	error = xlog_recover_finish(mp->m_log);
 	if (!error)
 		xfs_log_work_queue(mp);
+	mp->m_super->s_flags &= ~MS_ACTIVE;
+	evict_inodes(mp->m_super);
+
+	if (readonly)
+		mp->m_flags |= XFS_MOUNT_RDONLY;
 
 	return error;
 }
@@ -801,11 +831,14 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 	int		 error;
 
 	/*
-	 * Don't write out unmount record on read-only mounts.
+	 * Don't write out unmount record on norecovery mounts or ro devices.
 	 * Or, if we are doing a forced umount (typically because of IO errors).
 	 */
-	if (mp->m_flags & XFS_MOUNT_RDONLY)
+	if (mp->m_flags & XFS_MOUNT_NORECOVERY ||
+	    xfs_readonly_buftarg(log->l_mp->m_logdev_targp)) {
+		ASSERT(mp->m_flags & XFS_MOUNT_RDONLY);
 		return 0;
+	}
 
 	error = _xfs_log_force(mp, XFS_LOG_SYNC, NULL);
 	ASSERT(error || !(XLOG_FORCED_SHUTDOWN(log)));
@@ -3304,8 +3337,6 @@ maybe_sleep:
 		 */
 		if (iclog->ic_state & XLOG_STATE_IOERROR)
 			return -EIO;
-		if (log_flushed)
-			*log_flushed = 1;
 	} else {
 
 no_sleep:
@@ -3409,8 +3440,6 @@ 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;
 			}
@@ -3444,9 +3473,6 @@ 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);
 		}

fs/xfs/xfs_log_recover.c

@@ -1029,61 +1029,106 @@ out_error:
 }
 
 /*
- * Check the log tail for torn writes. This is required when torn writes are
- * detected at the head and the head had to be walked back to a previous record.
- * The tail of the previous record must now be verified to ensure the torn
- * writes didn't corrupt the previous tail.
+ * Calculate distance from head to tail (i.e., unused space in the log).
+ */
+static inline int
+xlog_tail_distance(
+	struct xlog	*log,
+	xfs_daddr_t	head_blk,
+	xfs_daddr_t	tail_blk)
+{
+	if (head_blk < tail_blk)
+		return tail_blk - head_blk;
+
+	return tail_blk + (log->l_logBBsize - head_blk);
+}
+
+/*
+ * Verify the log tail. This is particularly important when torn or incomplete
+ * writes have been detected near the front of the log and the head has been
+ * walked back accordingly.
  *
- * Return an error if CRC verification fails as recovery cannot proceed.
+ * We also have to handle the case where the tail was pinned and the head
+ * blocked behind the tail right before a crash. If the tail had been pushed
+ * immediately prior to the crash and the subsequent checkpoint was only
+ * partially written, it's possible it overwrote the last referenced tail in the
+ * log with garbage. This is not a coherency problem because the tail must have
+ * been pushed before it can be overwritten, but appears as log corruption to
+ * recovery because we have no way to know the tail was updated if the
+ * subsequent checkpoint didn't write successfully.
+ *
+ * Therefore, CRC check the log from tail to head. If a failure occurs and the
+ * offending record is within max iclog bufs from the head, walk the tail
+ * forward and retry until a valid tail is found or corruption is detected out
+ * of the range of a possible overwrite.
  */
 STATIC int
 xlog_verify_tail(
 	struct xlog		*log,
 	xfs_daddr_t		head_blk,
-	xfs_daddr_t		tail_blk)
+	xfs_daddr_t		*tail_blk,
+	int			hsize)
 {
 	struct xlog_rec_header	*thead;
 	struct xfs_buf		*bp;
 	xfs_daddr_t		first_bad;
-	int			count;
 	int			error = 0;
 	bool			wrapped;
-	xfs_daddr_t		tmp_head;
+	xfs_daddr_t		tmp_tail;
+	xfs_daddr_t		orig_tail = *tail_blk;
 
 	bp = xlog_get_bp(log, 1);
 	if (!bp)
 		return -ENOMEM;
 
 	/*
-	 * Seek XLOG_MAX_ICLOGS + 1 records past the current tail record to get
-	 * a temporary head block that points after the last possible
-	 * concurrently written record of the tail.
+	 * Make sure the tail points to a record (returns positive count on
+	 * success).
 	 */
-	count = xlog_seek_logrec_hdr(log, head_blk, tail_blk,
-				     XLOG_MAX_ICLOGS + 1, bp, &tmp_head, &thead,
-				     &wrapped);
-	if (count < 0) {
-		error = count;
+	error = xlog_seek_logrec_hdr(log, head_blk, *tail_blk, 1, bp,
+			&tmp_tail, &thead, &wrapped);
+	if (error < 0)
 		goto out;
+	if (*tail_blk != tmp_tail)
+		*tail_blk = tmp_tail;
+
+	/*
+	 * Run a CRC check from the tail to the head. We can't just check
+	 * MAX_ICLOGS records past the tail because the tail may point to stale
+	 * blocks cleared during the search for the head/tail. These blocks are
+	 * overwritten with zero-length records and thus record count is not a
+	 * reliable indicator of the iclog state before a crash.
+	 */
+	first_bad = 0;
+	error = xlog_do_recovery_pass(log, head_blk, *tail_blk,
+				      XLOG_RECOVER_CRCPASS, &first_bad);
+	while ((error == -EFSBADCRC || error == -EFSCORRUPTED) && first_bad) {
+		int	tail_distance;
+
+		/*
+		 * Is corruption within range of the head? If so, retry from
+		 * the next record. Otherwise return an error.
+		 */
+		tail_distance = xlog_tail_distance(log, head_blk, first_bad);
+		if (tail_distance > BTOBB(XLOG_MAX_ICLOGS * hsize))
+			break;
+
+		/* skip to the next record; returns positive count on success */
+		error = xlog_seek_logrec_hdr(log, head_blk, first_bad, 2, bp,
+				&tmp_tail, &thead, &wrapped);
+		if (error < 0)
+			goto out;
+
+		*tail_blk = tmp_tail;
+		first_bad = 0;
+		error = xlog_do_recovery_pass(log, head_blk, *tail_blk,
+					      XLOG_RECOVER_CRCPASS, &first_bad);
 	}
 
-	/*
-	 * If the call above didn't find XLOG_MAX_ICLOGS + 1 records, we ran
-	 * into the actual log head. tmp_head points to the start of the record
-	 * so update it to the actual head block.
-	 */
-	if (count < XLOG_MAX_ICLOGS + 1)
-		tmp_head = head_blk;
-
-	/*
-	 * We now have a tail and temporary head block that covers at least
-	 * XLOG_MAX_ICLOGS records from the tail. We need to verify that these
-	 * records were completely written. Run a CRC verification pass from
-	 * tail to head and return the result.
-	 */
-	error = xlog_do_recovery_pass(log, tmp_head, tail_blk,
-				      XLOG_RECOVER_CRCPASS, &first_bad);
-
+	if (!error && *tail_blk != orig_tail)
+		xfs_warn(log->l_mp,
+		"Tail block (0x%llx) overwrite detected. Updated to 0x%llx",
+			 orig_tail, *tail_blk);
 out:
 	xlog_put_bp(bp);
 	return error;
@@ -1143,7 +1188,7 @@ xlog_verify_head(
 	 */
 	error = xlog_do_recovery_pass(log, *head_blk, tmp_rhead_blk,
 				      XLOG_RECOVER_CRCPASS, &first_bad);
-	if (error == -EFSBADCRC) {
+	if ((error == -EFSBADCRC || error == -EFSCORRUPTED) && first_bad) {
 		/*
 		 * We've hit a potential torn write. Reset the error and warn
 		 * about it.
@@ -1183,31 +1228,12 @@ xlog_verify_head(
 			ASSERT(0);
 			return 0;
 		}
-
-		/*
-		 * Now verify the tail based on the updated head. This is
-		 * required because the torn writes trimmed from the head could
-		 * have been written over the tail of a previous record. Return
-		 * any errors since recovery cannot proceed if the tail is
-		 * corrupt.
-		 *
-		 * XXX: This leaves a gap in truly robust protection from torn
-		 * writes in the log. If the head is behind the tail, the tail
-		 * pushes forward to create some space and then a crash occurs
-		 * causing the writes into the previous record's tail region to
-		 * tear, log recovery isn't able to recover.
-		 *
-		 * How likely is this to occur? If possible, can we do something
-		 * more intelligent here? Is it safe to push the tail forward if
-		 * we can determine that the tail is within the range of the
-		 * torn write (e.g., the kernel can only overwrite the tail if
-		 * it has actually been pushed forward)? Alternatively, could we
-		 * somehow prevent this condition at runtime?
-		 */
-		error = xlog_verify_tail(log, *head_blk, *tail_blk);
 	}
-
+	if (error)
 		return error;
+
+	return xlog_verify_tail(log, *head_blk, tail_blk,
+				be32_to_cpu((*rhead)->h_size));
 }
 
 /*
@@ -4152,7 +4178,7 @@ xlog_recover_commit_trans(
 
 	#define XLOG_RECOVER_COMMIT_QUEUE_MAX 100
 
-	hlist_del(&trans->r_list);
+	hlist_del_init(&trans->r_list);
 
 	error = xlog_recover_reorder_trans(log, trans, pass);
 	if (error)
@@ -4354,6 +4380,8 @@ xlog_recover_free_trans(
 	xlog_recover_item_t	*item, *n;
 	int			i;
 
+	hlist_del_init(&trans->r_list);
+
 	list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) {
 		/* Free the regions in the item. */
 		list_del(&item->ri_list);
@@ -4799,12 +4827,16 @@ xlog_recover_process_intents(
 	int			error = 0;
 	struct xfs_ail_cursor	cur;
 	struct xfs_ail		*ailp;
+#if defined(DEBUG) || defined(XFS_WARN)
 	xfs_lsn_t		last_lsn;
+#endif
 
 	ailp = log->l_ailp;
 	spin_lock(&ailp->xa_lock);
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
+#if defined(DEBUG) || defined(XFS_WARN)
 	last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block);
+#endif
 	while (lip != NULL) {
 		/*
 		 * We're done when we see something other than an intent.
@@ -5214,7 +5246,7 @@ xlog_do_recovery_pass(
 	xfs_daddr_t		*first_bad)	/* out: first bad log rec */
 {
 	xlog_rec_header_t	*rhead;
-	xfs_daddr_t		blk_no;
+	xfs_daddr_t		blk_no, rblk_no;
 	xfs_daddr_t		rhead_blk;
 	char			*offset;
 	xfs_buf_t		*hbp, *dbp;
@@ -5222,11 +5254,15 @@ xlog_do_recovery_pass(
 	int			error2 = 0;
 	int			bblks, split_bblks;
 	int			hblks, split_hblks, wrapped_hblks;
+	int			i;
 	struct hlist_head	rhash[XLOG_RHASH_SIZE];
 	LIST_HEAD		(buffer_list);
 
 	ASSERT(head_blk != tail_blk);
-	rhead_blk = 0;
+	blk_no = rhead_blk = tail_blk;
+
+	for (i = 0; i < XLOG_RHASH_SIZE; i++)
+		INIT_HLIST_HEAD(&rhash[i]);
 
 	/*
 	 * Read the header of the tail block and get the iclog buffer size from
@@ -5301,7 +5337,6 @@ xlog_do_recovery_pass(
 	}
 
 	memset(rhash, 0, sizeof(rhash));
-	blk_no = rhead_blk = tail_blk;
 	if (tail_blk > head_blk) {
 		/*
 		 * Perform recovery around the end of the physical log.
@@ -5363,9 +5398,19 @@ xlog_do_recovery_pass(
 			bblks = (int)BTOBB(be32_to_cpu(rhead->h_len));
 			blk_no += hblks;
 
-			/* Read in data for log record */
-			if (blk_no + bblks <= log->l_logBBsize) {
-				error = xlog_bread(log, blk_no, bblks, dbp,
+			/*
+			 * Read the log record data in multiple reads if it
+			 * wraps around the end of the log. Note that if the
+			 * header already wrapped, blk_no could point past the
+			 * end of the log. The record data is contiguous in
+			 * that case.
+			 */
+			if (blk_no + bblks <= log->l_logBBsize ||
+			    blk_no >= log->l_logBBsize) {
+				/* mod blk_no in case the header wrapped and
+				 * pushed it beyond the end of the log */
+				rblk_no = do_mod(blk_no, log->l_logBBsize);
+				error = xlog_bread(log, rblk_no, bblks, dbp,
 						   &offset);
 				if (error)
 					goto bread_err2;
@@ -5464,6 +5509,19 @@ xlog_do_recovery_pass(
 	if (error && first_bad)
 		*first_bad = rhead_blk;
 
+	/*
+	 * Transactions are freed at commit time but transactions without commit
+	 * records on disk are never committed. Free any that may be left in the
+	 * hash table.
+	 */
+	for (i = 0; i < XLOG_RHASH_SIZE; i++) {
+		struct hlist_node	*tmp;
+		struct xlog_recover	*trans;
+
+		hlist_for_each_entry_safe(trans, tmp, &rhash[i], r_list)
+			xlog_recover_free_trans(trans);
+	}
+
 	return error ? error : error2;
 }
 
@@ -5542,6 +5600,8 @@ xlog_do_recover(
 	xfs_buf_t	*bp;
 	xfs_sb_t	*sbp;
 
+	trace_xfs_log_recover(log, head_blk, tail_blk);
+
 	/*
 	 * First replay the images in the log.
 	 */

fs/xfs/xfs_mount.c

@@ -924,15 +924,6 @@ xfs_mountfs(
 		}
 	}
 
-	/*
-	 * During the second phase of log recovery, we need iget and
-	 * iput to behave like they do for an active filesystem.
-	 * xfs_fs_drop_inode needs to be able to prevent the deletion
-	 * of inodes before we're done replaying log items on those
-	 * inodes.
-	 */
-	mp->m_super->s_flags |= MS_ACTIVE;
-
 	/*
 	 * Finish recovering the file system.  This part needed to be delayed
 	 * until after the root and real-time bitmap inodes were consistently
@@ -1008,12 +999,13 @@ xfs_mountfs(
  out_quota:
 	xfs_qm_unmount_quotas(mp);
  out_rtunmount:
-	mp->m_super->s_flags &= ~MS_ACTIVE;
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
 	IRELE(rip);
 	cancel_delayed_work_sync(&mp->m_reclaim_work);
 	xfs_reclaim_inodes(mp, SYNC_WAIT);
+	/* Clean out dquots that might be in memory after quotacheck. */
+	xfs_qm_unmount(mp);
  out_log_dealloc:
 	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
 	xfs_log_mount_cancel(mp);

fs/xfs/xfs_qm.c

@@ -111,6 +111,9 @@ restart:
 			skipped = 0;
 			break;
 		}
+		/* we're done if id overflows back to zero */
+		if (!next_index)
+			break;
 	}
 
 	if (skipped) {
@@ -1247,6 +1250,7 @@ xfs_qm_flush_one(
 	struct xfs_dquot	*dqp,
 	void			*data)
 {
+	struct xfs_mount	*mp = dqp->q_mount;
 	struct list_head	*buffer_list = data;
 	struct xfs_buf		*bp = NULL;
 	int			error = 0;
@@ -1257,7 +1261,32 @@ xfs_qm_flush_one(
 	if (!XFS_DQ_IS_DIRTY(dqp))
 		goto out_unlock;
 
-	xfs_dqflock(dqp);
+	/*
+	 * The only way the dquot is already flush locked by the time quotacheck
+	 * gets here is if reclaim flushed it before the dqadjust walk dirtied
+	 * it for the final time. Quotacheck collects all dquot bufs in the
+	 * local delwri queue before dquots are dirtied, so reclaim can't have
+	 * possibly queued it for I/O. The only way out is to push the buffer to
+	 * cycle the flush lock.
+	 */
+	if (!xfs_dqflock_nowait(dqp)) {
+		/* buf is pinned in-core by delwri list */
+		DEFINE_SINGLE_BUF_MAP(map, dqp->q_blkno,
+				      mp->m_quotainfo->qi_dqchunklen);
+		bp = _xfs_buf_find(mp->m_ddev_targp, &map, 1, 0, NULL);
+		if (!bp) {
+			error = -EINVAL;
+			goto out_unlock;
+		}
+		xfs_buf_unlock(bp);
+
+		xfs_buf_delwri_pushbuf(bp, buffer_list);
+		xfs_buf_rele(bp);
+
+		error = -EAGAIN;
+		goto out_unlock;
+	}
+
 	error = xfs_qm_dqflush(dqp, &bp);
 	if (error)
 		goto out_unlock;

fs/xfs/xfs_reflink.c

@@ -169,6 +169,8 @@ xfs_reflink_find_shared(
 	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
 	if (error)
 		return error;
+	if (!agbp)
+		return -ENOMEM;
 
 	cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL);
 
@@ -333,7 +335,7 @@ xfs_reflink_convert_cow_extent(
 	struct xfs_defer_ops		*dfops)
 {
 	struct xfs_bmbt_irec		irec = *imap;
-	xfs_fsblock_t			first_block;
+	xfs_fsblock_t			first_block = NULLFSBLOCK;
 	int				nimaps = 1;
 
 	if (imap->br_state == XFS_EXT_NORM)

fs/xfs/xfs_super.c

@@ -1214,7 +1214,7 @@ xfs_test_remount_options(
 	tmp_mp->m_super = sb;
 	error = xfs_parseargs(tmp_mp, options);
 	xfs_free_fsname(tmp_mp);
-	kfree(tmp_mp);
+	kmem_free(tmp_mp);
 
 	return error;
 }

fs/xfs/xfs_trace.h

@@ -366,6 +366,7 @@ DEFINE_BUF_EVENT(xfs_buf_iowait_done);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queue);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queued);
 DEFINE_BUF_EVENT(xfs_buf_delwri_split);
+DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf);
 DEFINE_BUF_EVENT(xfs_buf_get_uncached);
 DEFINE_BUF_EVENT(xfs_bdstrat_shut);
 DEFINE_BUF_EVENT(xfs_buf_item_relse);
@@ -519,7 +520,6 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_ordered);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_stale);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format);
-DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_ordered);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_stale);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_ordered);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin);
@@ -1990,6 +1990,24 @@ DEFINE_EVENT(xfs_swap_extent_class, name, \
 DEFINE_SWAPEXT_EVENT(xfs_swap_extent_before);
 DEFINE_SWAPEXT_EVENT(xfs_swap_extent_after);
 
+TRACE_EVENT(xfs_log_recover,
+	TP_PROTO(struct xlog *log, xfs_daddr_t headblk, xfs_daddr_t tailblk),
+	TP_ARGS(log, headblk, tailblk),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_daddr_t, headblk)
+		__field(xfs_daddr_t, tailblk)
+	),
+	TP_fast_assign(
+		__entry->dev = log->l_mp->m_super->s_dev;
+		__entry->headblk = headblk;
+		__entry->tailblk = tailblk;
+	),
+	TP_printk("dev %d:%d headblk 0x%llx tailblk 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->headblk,
+		  __entry->tailblk)
+)
+
 TRACE_EVENT(xfs_log_recover_record,
 	TP_PROTO(struct xlog *log, struct xlog_rec_header *rhead, int pass),
 	TP_ARGS(log, rhead, pass),

fs/xfs/xfs_trans.h

@@ -50,6 +50,7 @@ typedef struct xfs_log_item {
 	struct xfs_ail			*li_ailp;	/* ptr to AIL */
 	uint				li_type;	/* item type */
 	uint				li_flags;	/* misc flags */
+	struct xfs_buf			*li_buf;	/* real buffer pointer */
 	struct xfs_log_item		*li_bio_list;	/* buffer item list */
 	void				(*li_cb)(struct xfs_buf *,
 						 struct xfs_log_item *);
@@ -66,10 +67,12 @@ typedef struct xfs_log_item {
 
 #define	XFS_LI_IN_AIL	0x1
 #define	XFS_LI_ABORTED	0x2
+#define	XFS_LI_FAILED	0x4
 
 #define XFS_LI_FLAGS \
 	{ XFS_LI_IN_AIL,	"IN_AIL" }, \
-	{ XFS_LI_ABORTED,	"ABORTED" }
+	{ XFS_LI_ABORTED,	"ABORTED" }, \
+	{ XFS_LI_FAILED,	"FAILED" }
 
 struct xfs_item_ops {
 	void (*iop_size)(xfs_log_item_t *, int *, int *);
@@ -80,6 +83,7 @@ struct xfs_item_ops {
 	void (*iop_unlock)(xfs_log_item_t *);
 	xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t);
 	void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t);
+	void (*iop_error)(xfs_log_item_t *, xfs_buf_t *);
 };
 
 void	xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
@@ -213,12 +217,14 @@ void		xfs_trans_bhold_release(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_binval(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_inode_buf(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_stale_inode_buf(xfs_trans_t *, struct xfs_buf *);
-void		xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *);
+bool		xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_dquot_buf(xfs_trans_t *, struct xfs_buf *, uint);
 void		xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int);
 void		xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *, uint);
-void		xfs_trans_log_buf(xfs_trans_t *, struct xfs_buf *, uint, uint);
+void		xfs_trans_log_buf(struct xfs_trans *, struct xfs_buf *, uint,
+				  uint);
+void		xfs_trans_dirty_buf(struct xfs_trans *, struct xfs_buf *);
 void		xfs_trans_log_inode(xfs_trans_t *, struct xfs_inode *, uint);
 
 void		xfs_extent_free_init_defer_op(void);
@@ -277,6 +283,6 @@ int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp,
 		struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops,
 		enum xfs_bmap_intent_type type, struct xfs_inode *ip,
 		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t blockcount, xfs_exntst_t state);
+		xfs_filblks_t *blockcount, xfs_exntst_t state);
 
 #endif	/* __XFS_TRANS_H__ */

fs/xfs/xfs_trans_ail.c

@@ -684,8 +684,24 @@ xfs_trans_ail_update_bulk(
 	}
 }
 
-/*
- * xfs_trans_ail_delete_bulk - remove multiple log items from the AIL
+bool
+xfs_ail_delete_one(
+	struct xfs_ail		*ailp,
+	struct xfs_log_item	*lip)
+{
+	struct xfs_log_item	*mlip = xfs_ail_min(ailp);
+
+	trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn);
+	xfs_ail_delete(ailp, lip);
+	xfs_clear_li_failed(lip);
+	lip->li_flags &= ~XFS_LI_IN_AIL;
+	lip->li_lsn = 0;
+
+	return mlip == lip;
+}
+
+/**
+ * Remove a log items from the AIL
  *
  * @xfs_trans_ail_delete_bulk takes an array of log items that all need to
  * removed from the AIL. The caller is already holding the AIL lock, and done
@@ -706,23 +722,15 @@ xfs_trans_ail_update_bulk(
  * before returning.
  */
 void
-xfs_trans_ail_delete_bulk(
+xfs_trans_ail_delete(
 	struct xfs_ail		*ailp,
-	struct xfs_log_item	**log_items,
-	int			nr_items,
+	struct xfs_log_item	*lip,
 	int			shutdown_type) __releases(ailp->xa_lock)
 {
-	xfs_log_item_t		*mlip;
-	int			mlip_changed = 0;
-	int			i;
-
-	mlip = xfs_ail_min(ailp);
-
-	for (i = 0; i < nr_items; i++) {
-		struct xfs_log_item *lip = log_items[i];
-		if (!(lip->li_flags & XFS_LI_IN_AIL)) {
 	struct xfs_mount	*mp = ailp->xa_mount;
+	bool			mlip_changed;
 
+	if (!(lip->li_flags & XFS_LI_IN_AIL)) {
 		spin_unlock(&ailp->xa_lock);
 		if (!XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_alert_tag(mp, XFS_PTAG_AILDELETE,
@@ -733,25 +741,17 @@ xfs_trans_ail_delete_bulk(
 		return;
 	}
 
-		trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn);
-		xfs_ail_delete(ailp, lip);
-		lip->li_flags &= ~XFS_LI_IN_AIL;
-		lip->li_lsn = 0;
-		if (mlip == lip)
-			mlip_changed = 1;
-	}
-
+	mlip_changed = xfs_ail_delete_one(ailp, lip);
 	if (mlip_changed) {
-		if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount))
-			xlog_assign_tail_lsn_locked(ailp->xa_mount);
+		if (!XFS_FORCED_SHUTDOWN(mp))
+			xlog_assign_tail_lsn_locked(mp);
 		if (list_empty(&ailp->xa_ail))
 			wake_up_all(&ailp->xa_empty);
-		spin_unlock(&ailp->xa_lock);
-
-		xfs_log_space_wake(ailp->xa_mount);
-	} else {
-		spin_unlock(&ailp->xa_lock);
 	}
+
+	spin_unlock(&ailp->xa_lock);
+	if (mlip_changed)
+		xfs_log_space_wake(ailp->xa_mount);
 }
 
 int

fs/xfs/xfs_trans_bmap.c

@@ -63,7 +63,7 @@ xfs_trans_log_finish_bmap_update(
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,
-	xfs_filblks_t			blockcount,
+	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
 	int				error;
@@ -196,16 +196,23 @@ xfs_bmap_update_finish_item(
 	void				**state)
 {
 	struct xfs_bmap_intent		*bmap;
+	xfs_filblks_t			count;
 	int				error;
 
 	bmap = container_of(item, struct xfs_bmap_intent, bi_list);
+	count = bmap->bi_bmap.br_blockcount;
 	error = xfs_trans_log_finish_bmap_update(tp, done_item, dop,
 			bmap->bi_type,
 			bmap->bi_owner, bmap->bi_whichfork,
 			bmap->bi_bmap.br_startoff,
 			bmap->bi_bmap.br_startblock,
-			bmap->bi_bmap.br_blockcount,
+			&count,
 			bmap->bi_bmap.br_state);
+	if (!error && count > 0) {
+		ASSERT(bmap->bi_type == XFS_BMAP_UNMAP);
+		bmap->bi_bmap.br_blockcount = count;
+		return -EAGAIN;
+	}
 	kmem_free(bmap);
 	return error;
 }

fs/xfs/xfs_trans_buf.c

@@ -356,6 +356,7 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 		 xfs_buf_t	*bp)
 {
 	xfs_buf_log_item_t	*bip;
+	int			freed;
 
 	/*
 	 * Default to a normal brelse() call if the tp is NULL.
@@ -419,16 +420,22 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 	/*
 	 * Drop our reference to the buf log item.
 	 */
-	atomic_dec(&bip->bli_refcount);
+	freed = atomic_dec_and_test(&bip->bli_refcount);
 
 	/*
-	 * If the buf item is not tracking data in the log, then
-	 * we must free it before releasing the buffer back to the
-	 * free pool.  Before releasing the buffer to the free pool,
-	 * clear the transaction pointer in b_fsprivate2 to dissolve
-	 * its relation to this transaction.
+	 * If the buf item is not tracking data in the log, then we must free it
+	 * before releasing the buffer back to the free pool.
+	 *
+	 * If the fs has shutdown and we dropped the last reference, it may fall
+	 * on us to release a (possibly dirty) bli if it never made it to the
+	 * AIL (e.g., the aborted unpin already happened and didn't release it
+	 * due to our reference). Since we're already shutdown and need xa_lock,
+	 * just force remove from the AIL and release the bli here.
 	 */
-	if (!xfs_buf_item_dirty(bip)) {
+	if (XFS_FORCED_SHUTDOWN(tp->t_mountp) && freed) {
+		xfs_trans_ail_remove(&bip->bli_item, SHUTDOWN_LOG_IO_ERROR);
+		xfs_buf_item_relse(bp);
+	} else if (!(bip->bli_flags & XFS_BLI_DIRTY)) {
 /***
 		ASSERT(bp->b_pincount == 0);
 ***/
@@ -486,25 +493,17 @@ xfs_trans_bhold_release(xfs_trans_t	*tp,
 }
 
 /*
- * This is called to mark bytes first through last inclusive of the given
- * buffer as needing to be logged when the transaction is committed.
- * The buffer must already be associated with the given transaction.
- *
- * First and last are numbers relative to the beginning of this buffer,
- * so the first byte in the buffer is numbered 0 regardless of the
- * value of b_blkno.
+ * Mark a buffer dirty in the transaction.
  */
 void
-xfs_trans_log_buf(xfs_trans_t	*tp,
-		  xfs_buf_t	*bp,
-		  uint		first,
-		  uint		last)
+xfs_trans_dirty_buf(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
-	xfs_buf_log_item_t	*bip = bp->b_fspriv;
+	struct xfs_buf_log_item	*bip = bp->b_fspriv;
 
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
-	ASSERT(first <= last && last < BBTOB(bp->b_length));
 	ASSERT(bp->b_iodone == NULL ||
 	       bp->b_iodone == xfs_buf_iodone_callbacks);
 
@@ -524,8 +523,6 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 	bp->b_iodone = xfs_buf_iodone_callbacks;
 	bip->bli_item.li_cb = xfs_buf_iodone;
 
-	trace_xfs_trans_log_buf(bip);
-
 	/*
 	 * If we invalidated the buffer within this transaction, then
 	 * cancel the invalidation now that we're dirtying the buffer
@@ -538,16 +535,36 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 		bp->b_flags &= ~XBF_STALE;
 		bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL;
 	}
+	bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED;
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
 	bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+}
 
-	/*
-	 * If we have an ordered buffer we are not logging any dirty range but
-	 * it still needs to be marked dirty and that it has been logged.
+/*
+ * This is called to mark bytes first through last inclusive of the given
+ * buffer as needing to be logged when the transaction is committed.
+ * The buffer must already be associated with the given transaction.
+ *
+ * First and last are numbers relative to the beginning of this buffer,
+ * so the first byte in the buffer is numbered 0 regardless of the
+ * value of b_blkno.
  */
-	bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED;
-	if (!(bip->bli_flags & XFS_BLI_ORDERED))
+void
+xfs_trans_log_buf(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
+	uint			first,
+	uint			last)
+{
+	struct xfs_buf_log_item	*bip = bp->b_fspriv;
+
+	ASSERT(first <= last && last < BBTOB(bp->b_length));
+	ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED));
+
+	xfs_trans_dirty_buf(tp, bp);
+
+	trace_xfs_trans_log_buf(bip);
 	xfs_buf_item_log(bip, first, last);
 }
 
@@ -701,14 +718,13 @@ xfs_trans_inode_alloc_buf(
 }
 
 /*
- * Mark the buffer as ordered for this transaction. This means
- * that the contents of the buffer are not recorded in the transaction
- * but it is tracked in the AIL as though it was. This allows us
- * to record logical changes in transactions rather than the physical
- * changes we make to the buffer without changing writeback ordering
- * constraints of metadata buffers.
+ * Mark the buffer as ordered for this transaction. This means that the contents
+ * of the buffer are not recorded in the transaction but it is tracked in the
+ * AIL as though it was. This allows us to record logical changes in
+ * transactions rather than the physical changes we make to the buffer without
+ * changing writeback ordering constraints of metadata buffers.
  */
-void
+bool
 xfs_trans_ordered_buf(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*bp)
@@ -719,8 +735,18 @@ xfs_trans_ordered_buf(
 	ASSERT(bip != NULL);
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 
+	if (xfs_buf_item_dirty_format(bip))
+		return false;
+
 	bip->bli_flags |= XFS_BLI_ORDERED;
 	trace_xfs_buf_item_ordered(bip);
+
+	/*
+	 * We don't log a dirty range of an ordered buffer but it still needs
+	 * to be marked dirty and that it has been logged.
+	 */
+	xfs_trans_dirty_buf(tp, bp);
+	return true;
 }
 
 /*

fs/xfs/xfs_trans_priv.h

@@ -106,18 +106,9 @@ xfs_trans_ail_update(
 	xfs_trans_ail_update_bulk(ailp, NULL, &lip, 1, lsn);
 }
 
-void	xfs_trans_ail_delete_bulk(struct xfs_ail *ailp,
-				struct xfs_log_item **log_items, int nr_items,
-				int shutdown_type)
-				__releases(ailp->xa_lock);
-static inline void
-xfs_trans_ail_delete(
-	struct xfs_ail	*ailp,
-	xfs_log_item_t	*lip,
-	int		shutdown_type) __releases(ailp->xa_lock)
-{
-	xfs_trans_ail_delete_bulk(ailp, &lip, 1, shutdown_type);
-}
+bool xfs_ail_delete_one(struct xfs_ail *ailp, struct xfs_log_item *lip);
+void xfs_trans_ail_delete(struct xfs_ail *ailp, struct xfs_log_item *lip,
+		int shutdown_type) __releases(ailp->xa_lock);
 
 static inline void
 xfs_trans_ail_remove(
@@ -173,4 +164,35 @@ xfs_trans_ail_copy_lsn(
 	*dst = *src;
 }
 #endif
+
+static inline void
+xfs_clear_li_failed(
+	struct xfs_log_item	*lip)
+{
+	struct xfs_buf	*bp = lip->li_buf;
+
+	ASSERT(lip->li_flags & XFS_LI_IN_AIL);
+	lockdep_assert_held(&lip->li_ailp->xa_lock);
+
+	if (lip->li_flags & XFS_LI_FAILED) {
+		lip->li_flags &= ~XFS_LI_FAILED;
+		lip->li_buf = NULL;
+		xfs_buf_rele(bp);
+	}
+}
+
+static inline void
+xfs_set_li_failed(
+	struct xfs_log_item	*lip,
+	struct xfs_buf		*bp)
+{
+	lockdep_assert_held(&lip->li_ailp->xa_lock);
+
+	if (!(lip->li_flags & XFS_LI_FAILED)) {
+		xfs_buf_hold(bp);
+		lip->li_flags |= XFS_LI_FAILED;
+		lip->li_buf = bp;
+	}
+}
+
 #endif	/* __XFS_TRANS_PRIV_H__ */

include/linux/fs.h

@@ -2782,6 +2782,7 @@ static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
 #endif
 extern void unlock_new_inode(struct inode *);
 extern unsigned int get_next_ino(void);
+extern void evict_inodes(struct super_block *sb);
 
 extern void __iget(struct inode * inode);
 extern void iget_failed(struct inode *);

include/linux/netdevice.h

@@ -3901,6 +3901,8 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 	     updev; \
 	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
 
+bool netdev_has_any_upper_dev(struct net_device *dev);
+
 void *netdev_lower_get_next_private(struct net_device *dev,
 				    struct list_head **iter);
 void *netdev_lower_get_next_private_rcu(struct net_device *dev,

include/net/inet_frag.h

@@ -1,14 +1,9 @@
 #ifndef __NET_FRAG_H__
 #define __NET_FRAG_H__
 
-#include <linux/percpu_counter.h>
-
 struct netns_frags {
-	/* The percpu_counter "mem" need to be cacheline aligned.
-	 *  mem.count must not share cacheline with other writers
-	 */
-	struct percpu_counter   mem ____cacheline_aligned_in_smp;
-
+	/* Keep atomic mem on separate cachelines in structs that include it */
+	atomic_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
 	int			timeout;
 	int			high_thresh;
@@ -108,15 +103,10 @@ struct inet_frags {
 int inet_frags_init(struct inet_frags *);
 void inet_frags_fini(struct inet_frags *);
 
-static inline int inet_frags_init_net(struct netns_frags *nf)
+static inline void inet_frags_init_net(struct netns_frags *nf)
 {
-	return percpu_counter_init(&nf->mem, 0, GFP_KERNEL);
+	atomic_set(&nf->mem, 0);
 }
-static inline void inet_frags_uninit_net(struct netns_frags *nf)
-{
-	percpu_counter_destroy(&nf->mem);
-}
-
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
 
 void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
@@ -140,37 +130,24 @@ static inline bool inet_frag_evicting(struct inet_frag_queue *q)
 
 /* Memory Tracking Functions. */
 
-/* The default percpu_counter batch size is not big enough to scale to
- * fragmentation mem acct sizes.
- * The mem size of a 64K fragment is approx:
- *  (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes
- */
-static unsigned int frag_percpu_counter_batch = 130000;
-
 static inline int frag_mem_limit(struct netns_frags *nf)
 {
-	return percpu_counter_read(&nf->mem);
+	return atomic_read(&nf->mem);
 }
 
 static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch);
+	atomic_sub(i, &nf->mem);
 }
 
 static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch);
+	atomic_add(i, &nf->mem);
 }
 
-static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
+static inline int sum_frag_mem_limit(struct netns_frags *nf)
 {
-	unsigned int res;
-
-	local_bh_disable();
-	res = percpu_counter_sum_positive(&nf->mem);
-	local_bh_enable();
-
-	return res;
+	return atomic_read(&nf->mem);
 }
 
 /* RFC 3168 support :

include/net/ip6_fib.h

@@ -68,6 +68,7 @@ struct fib6_node {
 	__u16			fn_flags;
 	int			fn_sernum;
 	struct rt6_info		*rr_ptr;
+	struct rcu_head		rcu;
 };
 
 #ifndef CONFIG_IPV6_SUBTREES
@@ -102,7 +103,7 @@ struct rt6_info {
 	 * the same cache line.
 	 */
 	struct fib6_table		*rt6i_table;
-	struct fib6_node		*rt6i_node;
+	struct fib6_node __rcu		*rt6i_node;
 
 	struct in6_addr			rt6i_gateway;
 
@@ -165,13 +166,40 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
 	rt0->rt6i_flags |= RTF_EXPIRES;
 }
 
+/* Function to safely get fn->sernum for passed in rt
+ * and store result in passed in cookie.
+ * Return true if we can get cookie safely
+ * Return false if not
+ */
+static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
+				       u32 *cookie)
+{
+	struct fib6_node *fn;
+	bool status = false;
+
+	rcu_read_lock();
+	fn = rcu_dereference(rt->rt6i_node);
+
+	if (fn) {
+		*cookie = fn->fn_sernum;
+		status = true;
+	}
+
+	rcu_read_unlock();
+	return status;
+}
+
 static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 {
+	u32 cookie = 0;
+
 	if (rt->rt6i_flags & RTF_PCPU ||
 	    (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from))
 		rt = (struct rt6_info *)(rt->dst.from);
 
-	return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+	rt6_get_cookie_safe(rt, &cookie);
+
+	return cookie;
 }
 
 static inline void ip6_rt_put(struct rt6_info *rt)

net/bridge/br_device.c

@@ -48,6 +48,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+#endif
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);

net/core/datagram.c

@@ -351,7 +351,7 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 	if (flags & MSG_PEEK) {
 		err = -ENOENT;
 		spin_lock_bh(&sk->sk_receive_queue.lock);
-		if (skb == skb_peek(&sk->sk_receive_queue)) {
+		if (skb->next) {
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			atomic_dec(&skb->users);
 			err = 0;

net/core/dev.c

@@ -5337,12 +5337,13 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
  * Find out if a device is linked to an upper device and return true in case
  * it is. The caller must hold the RTNL lock.
  */
-static bool netdev_has_any_upper_dev(struct net_device *dev)
+bool netdev_has_any_upper_dev(struct net_device *dev)
 {
 	ASSERT_RTNL();
 
 	return !list_empty(&dev->all_adj_list.upper);
 }
+EXPORT_SYMBOL(netdev_has_any_upper_dev);
 
 /**
  * netdev_master_upper_dev_get - Get master upper device

net/ieee802154/6lowpan/reassembly.c

@@ -580,19 +580,14 @@ static int __net_init lowpan_frags_init_net(struct net *net)
 {
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
-	int res;
 
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&ieee802154_lowpan->frags);
-	if (res)
-		return res;
-	res = lowpan_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&ieee802154_lowpan->frags);
-	return res;
+	inet_frags_init_net(&ieee802154_lowpan->frags);
+
+	return lowpan_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit lowpan_frags_exit_net(struct net *net)

net/ipv4/inet_fragment.c

@@ -234,10 +234,8 @@ evict_again:
 	cond_resched();
 
 	if (read_seqretry(&f->rnd_seqlock, seq) ||
-	    percpu_counter_sum(&nf->mem))
+	    sum_frag_mem_limit(nf))
 		goto evict_again;
-
-	percpu_counter_destroy(&nf->mem);
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
 

net/ipv4/ip_fragment.c

@@ -835,8 +835,6 @@ static void __init ip4_frags_ctl_register(void)
 
 static int __net_init ipv4_frags_init_net(struct net *net)
 {
-	int res;
-
 	/* Fragment cache limits.
 	 *
 	 * The fragment memory accounting code, (tries to) account for
@@ -862,13 +860,9 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 
 	net->ipv4.frags.max_dist = 64;
 
-	res = inet_frags_init_net(&net->ipv4.frags);
-	if (res)
-		return res;
-	res = ip4_frags_ns_ctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv4.frags);
-	return res;
+	inet_frags_init_net(&net->ipv4.frags);
+
+	return ip4_frags_ns_ctl_register(net);
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)

net/ipv4/ip_tunnel.c

@@ -609,8 +609,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
 		ip_rt_put(rt);
 		goto tx_dropped;
 	}
-	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos,
-		      key->ttl, df, !net_eq(tunnel->net, dev_net(dev)));
+	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl,
+		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
 tx_error:
 	dev->stats.tx_errors++;

net/ipv4/tcp.c

@@ -2297,6 +2297,10 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tcp_clear_retrans(tp);
 	inet_csk_delack_init(sk);
+	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
+	 * issue in __tcp_select_window()
+	 */
+	icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);

net/ipv6/addrconf.c

@@ -5474,7 +5474,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 		 * our DAD process, so we don't need
 		 * to do it again
 		 */
-		if (!(ifp->rt->rt6i_node))
+		if (!rcu_access_pointer(ifp->rt->rt6i_node))
 			ip6_ins_rt(ifp->rt);
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);

net/ipv6/ip6_fib.c

@@ -148,11 +148,23 @@ static struct fib6_node *node_alloc(void)
 	return fn;
 }
 
-static void node_free(struct fib6_node *fn)
+static void node_free_immediate(struct fib6_node *fn)
 {
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
+static void node_free_rcu(struct rcu_head *head)
+{
+	struct fib6_node *fn = container_of(head, struct fib6_node, rcu);
+
+	kmem_cache_free(fib6_node_kmem, fn);
+}
+
+static void node_free(struct fib6_node *fn)
+{
+	call_rcu(&fn->rcu, node_free_rcu);
+}
+
 static void rt6_rcu_free(struct rt6_info *rt)
 {
 	call_rcu(&rt->dst.rcu_head, dst_rcu_free);
@@ -189,6 +201,12 @@ static void rt6_release(struct rt6_info *rt)
 	}
 }
 
+static void fib6_free_table(struct fib6_table *table)
+{
+	inetpeer_invalidate_tree(&table->tb6_peers);
+	kfree(table);
+}
+
 static void fib6_link_table(struct net *net, struct fib6_table *tb)
 {
 	unsigned int h;
@@ -589,9 +607,9 @@ insert_above:
 
 		if (!in || !ln) {
 			if (in)
-				node_free(in);
+				node_free_immediate(in);
 			if (ln)
-				node_free(ln);
+				node_free_immediate(ln);
 			return ERR_PTR(-ENOMEM);
 		}
 
@@ -862,7 +880,7 @@ add:
 
 		rt->dst.rt6_next = iter;
 		*ins = rt;
-		rt->rt6i_node = fn;
+		rcu_assign_pointer(rt->rt6i_node, fn);
 		atomic_inc(&rt->rt6i_ref);
 		inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
 		info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
@@ -887,7 +905,7 @@ add:
 			return err;
 
 		*ins = rt;
-		rt->rt6i_node = fn;
+		rcu_assign_pointer(rt->rt6i_node, fn);
 		rt->dst.rt6_next = iter->dst.rt6_next;
 		atomic_inc(&rt->rt6i_ref);
 		inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
@@ -1020,7 +1038,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 				   root, and then (in failure) stale node
 				   in main tree.
 				 */
-				node_free(sfn);
+				node_free_immediate(sfn);
 				err = PTR_ERR(sn);
 				goto failure;
 			}
@@ -1447,8 +1465,9 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 
 int fib6_del(struct rt6_info *rt, struct nl_info *info)
 {
+	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 	struct net *net = info->nl_net;
-	struct fib6_node *fn = rt->rt6i_node;
 	struct rt6_info **rtp;
 
 #if RT6_DEBUG >= 2
@@ -1637,7 +1656,9 @@ static int fib6_clean_node(struct fib6_walker *w)
 			if (res) {
 #if RT6_DEBUG >= 2
 				pr_debug("%s: del failed: rt=%p@%p err=%d\n",
-					 __func__, rt, rt->rt6i_node, res);
+					 __func__, rt,
+					 rcu_access_pointer(rt->rt6i_node),
+					 res);
 #endif
 				continue;
 			}
@@ -1878,15 +1899,22 @@ out_timer:
 
 static void fib6_net_exit(struct net *net)
 {
+	unsigned int i;
+
 	rt6_ifdown(net, NULL);
 	del_timer_sync(&net->ipv6.ip6_fib_timer);
 
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers);
-	kfree(net->ipv6.fib6_local_tbl);
-#endif
-	inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers);
-	kfree(net->ipv6.fib6_main_tbl);
+	for (i = 0; i < FIB6_TABLE_HASHSZ; i++) {
+		struct hlist_head *head = &net->ipv6.fib_table_hash[i];
+		struct hlist_node *tmp;
+		struct fib6_table *tb;
+
+		hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) {
+			hlist_del(&tb->tb6_hlist);
+			fib6_free_table(tb);
+		}
+	}
+
 	kfree(net->ipv6.fib_table_hash);
 	kfree(net->ipv6.rt6_stats);
 }

net/ipv6/ip6_gre.c

@@ -432,7 +432,9 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
-		mtu = be32_to_cpu(info) - offset;
+		mtu = be32_to_cpu(info) - offset - t->tun_hlen;
+		if (t->dev->type == ARPHRD_ETHER)
+			mtu -= ETH_HLEN;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;

net/ipv6/netfilter/nf_conntrack_reasm.c

@@ -622,18 +622,12 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
 
 static int nf_ct_net_init(struct net *net)
 {
-	int res;
-
 	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
-	res = inet_frags_init_net(&net->nf_frag.frags);
-	if (res)
-		return res;
-	res = nf_ct_frag6_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->nf_frag.frags);
-	return res;
+	inet_frags_init_net(&net->nf_frag.frags);
+
+	return nf_ct_frag6_sysctl_register(net);
 }
 
 static void nf_ct_net_exit(struct net *net)

net/ipv6/output_core.c

@@ -86,7 +86,6 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 	while (offset <= packet_len) {
 		struct ipv6_opt_hdr *exthdr;
-		unsigned int len;
 
 		switch (**nexthdr) {
 
@@ -112,10 +111,9 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
-		len = ipv6_optlen(exthdr);
-		if (len + offset >= IPV6_MAXPLEN)
+		offset += ipv6_optlen(exthdr);
+		if (offset > IPV6_MAXPLEN)
 			return -EINVAL;
-		offset += len;
 		*nexthdr = &exthdr->nexthdr;
 	}
 

net/ipv6/reassembly.c

@@ -709,19 +709,13 @@ static void ip6_frags_sysctl_unregister(void)
 
 static int __net_init ipv6_frags_init_net(struct net *net)
 {
-	int res;
-
 	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&net->ipv6.frags);
-	if (res)
-		return res;
-	res = ip6_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv6.frags);
-	return res;
+	inet_frags_init_net(&net->ipv6.frags);
+
+	return ip6_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit ipv6_frags_exit_net(struct net *net)

net/ipv6/route.c

@@ -1267,7 +1267,9 @@ static void rt6_dst_from_metrics_check(struct rt6_info *rt)
 
 static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
 {
-	if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
+	u32 rt_cookie = 0;
+
+	if (!rt6_get_cookie_safe(rt, &rt_cookie) || rt_cookie != cookie)
 		return NULL;
 
 	if (rt6_check_expired(rt))
@@ -1335,8 +1337,14 @@ static void ip6_link_failure(struct sk_buff *skb)
 		if (rt->rt6i_flags & RTF_CACHE) {
 			dst_hold(&rt->dst);
 			ip6_del_rt(rt);
-		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) {
-			rt->rt6i_node->fn_sernum = -1;
+		} else {
+			struct fib6_node *fn;
+
+			rcu_read_lock();
+			fn = rcu_dereference(rt->rt6i_node);
+			if (fn && (rt->rt6i_flags & RTF_DEFAULT))
+				fn->fn_sernum = -1;
+			rcu_read_unlock();
 		}
 	}
 }
@@ -1353,7 +1361,8 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
 static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
 {
 	return !(rt->rt6i_flags & RTF_CACHE) &&
-		(rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
+		(rt->rt6i_flags & RTF_PCPU ||
+		 rcu_access_pointer(rt->rt6i_node));
 }
 
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,

net/kcm/kcmsock.c

@@ -1381,6 +1381,10 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	if (!csk)
 		return -EINVAL;
 
+	/* We must prevent loops or risk deadlock ! */
+	if (csk->sk_family == PF_KCM)
+		return -EOPNOTSUPP;
+
 	psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL);
 	if (!psock)
 		return -ENOMEM;

net/packet/af_packet.c

@@ -2151,6 +2151,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct timespec ts;
 	__u32 ts_status;
 	bool is_drop_n_account = false;
+	bool do_vnet = false;
 
 	/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
 	 * We may add members to them until current aligned size without forcing
@@ -2201,8 +2202,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		netoff = TPACKET_ALIGN(po->tp_hdrlen +
 				       (maclen < 16 ? 16 : maclen)) +
 				       po->tp_reserve;
-		if (po->has_vnet_hdr)
+		if (po->has_vnet_hdr) {
 			netoff += sizeof(struct virtio_net_hdr);
+			do_vnet = true;
+		}
 		macoff = netoff - maclen;
 	}
 	if (po->tp_version <= TPACKET_V2) {
@@ -2219,8 +2222,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 					skb_set_owner_r(copy_skb, sk);
 			}
 			snaplen = po->rx_ring.frame_size - macoff;
-			if ((int)snaplen < 0)
+			if ((int)snaplen < 0) {
 				snaplen = 0;
+				do_vnet = false;
+			}
 		}
 	} else if (unlikely(macoff + snaplen >
 			    GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) {
@@ -2233,6 +2238,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely((int)snaplen < 0)) {
 			snaplen = 0;
 			macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len;
+			do_vnet = false;
 		}
 	}
 	spin_lock(&sk->sk_receive_queue.lock);
@@ -2258,7 +2264,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	}
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	if (po->has_vnet_hdr) {
+	if (do_vnet) {
 		if (__packet_rcv_vnet(skb, h.raw + macoff -
 					   sizeof(struct virtio_net_hdr))) {
 			spin_lock(&sk->sk_receive_queue.lock);

net/sctp/sctp_diag.c

@@ -70,7 +70,8 @@ static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb,
 
 	info = nla_data(attr);
 	list_for_each_entry_rcu(laddr, address_list, list) {
-		memcpy(info, &laddr->a, addrlen);
+		memcpy(info, &laddr->a, sizeof(laddr->a));
+		memset(info + sizeof(laddr->a), 0, addrlen - sizeof(laddr->a));
 		info += addrlen;
 	}
 
@@ -93,7 +94,9 @@ static int inet_diag_msg_sctpaddrs_fill(struct sk_buff *skb,
 	info = nla_data(attr);
 	list_for_each_entry(from, &asoc->peer.transport_addr_list,
 			    transports) {
-		memcpy(info, &from->ipaddr, addrlen);
+		memcpy(info, &from->ipaddr, sizeof(from->ipaddr));
+		memset(info + sizeof(from->ipaddr), 0,
+		       addrlen - sizeof(from->ipaddr));
 		info += addrlen;
 	}
 

net/sctp/socket.c

@@ -4373,8 +4373,7 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
 	info->sctpi_ictrlchunks = asoc->stats.ictrlchunks;
 
 	prim = asoc->peer.primary_path;
-	memcpy(&info->sctpi_p_address, &prim->ipaddr,
-	       sizeof(struct sockaddr_storage));
+	memcpy(&info->sctpi_p_address, &prim->ipaddr, sizeof(prim->ipaddr));
 	info->sctpi_p_state = prim->state;
 	info->sctpi_p_cwnd = prim->cwnd;
 	info->sctpi_p_srtt = prim->srtt;

net/sctp/ulpqueue.c

@@ -265,6 +265,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		sctp_ulpq_clear_pd(ulpq);
 
 	if (queue == &sk->sk_receive_queue && !sp->data_ready_signalled) {
+		if (!sock_owned_by_user(sk))
 			sp->data_ready_signalled = 1;
 		sk->sk_data_ready(sk);
 	}