Skip to contentSkip to conversation

Linux 4.13.3

DISCUSSION Greg KH 1 participant 2 messages Sep 20, 2017 Stable branch

lore
Share & tools
lore

Greg KH

author maintainer
#0 lore raw

I'm announcing the release of the 4.13.3 kernel.

All users of the 4.13 kernel series must upgrade.

The updated 4.13.y git tree can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git linux-4.13.y
and can be browsed at the normal kernel.org git web browser:
http://git.kernel.org/?p=linux/kernel/git/stable/linux-stable.git;a=summary

thanks,

greg k-h

------------

 Documentation/ABI/testing/sysfs-bus-thunderbolt |    2 
 Makefile                                        |    2 
 arch/x86/include/asm/elf.h                      |    5 
 arch/x86/include/asm/page_64.h                  |    4 
 arch/x86/kernel/cpu/mcheck/mce.c                |   43 ++++
 arch/x86/kernel/process_64.c                    |  236 +++++++++++++-----------
 drivers/md/raid1.c                              |   19 +
 drivers/md/raid10.c                             |   35 +++
 drivers/md/raid5.c                              |    4 
 drivers/net/ethernet/freescale/gianfar.c        |    2 
 drivers/nvdimm/btt.c                            |    2 
 drivers/nvdimm/bus.c                            |   17 -
 drivers/thunderbolt/switch.c                    |   20 +-
 drivers/vhost/net.c                             |    7 
 fs/f2fs/recovery.c                              |    4 
 fs/fuse/dev.c                                   |   13 -
 fs/fuse/file.c                                  |    3 
 fs/inode.c                                      |    1 
 fs/internal.h                                   |    1 
 fs/overlayfs/inode.c                            |   11 -
 fs/xfs/libxfs/xfs_bmap.c                        |    2 
 fs/xfs/libxfs/xfs_bmap_btree.c                  |    1 
 fs/xfs/libxfs/xfs_btree.c                       |   27 +-
 fs/xfs/libxfs/xfs_btree.h                       |    3 
 fs/xfs/libxfs/xfs_ialloc.c                      |   57 ++---
 fs/xfs/libxfs/xfs_inode_fork.c                  |    9 
 fs/xfs/xfs_aops.c                               |   71 ++++---
 fs/xfs/xfs_bmap_util.c                          |   93 +++++++--
 fs/xfs/xfs_buf_item.c                           |  137 +++++++++----
 fs/xfs/xfs_buf_item.h                           |    5 
 fs/xfs/xfs_icache.c                             |   10 -
 fs/xfs/xfs_inode.c                              |   23 +-
 fs/xfs/xfs_inode_item.c                         |   47 ++++
 fs/xfs/xfs_ioctl.c                              |   41 ++--
 fs/xfs/xfs_iops.c                               |    2 
 fs/xfs/xfs_log.c                                |   33 ++-
 fs/xfs/xfs_log_recover.c                        |  159 ++++++++++------
 fs/xfs/xfs_super.c                              |    2 
 fs/xfs/xfs_trace.h                              |    1 
 fs/xfs/xfs_trans.h                              |   14 +
 fs/xfs/xfs_trans_ail.c                          |    3 
 fs/xfs/xfs_trans_buf.c                          |   79 ++++----
 fs/xfs/xfs_trans_priv.h                         |   31 +++
 include/linux/fs.h                              |    1 
 include/linux/mm_inline.h                       |    6 
 include/linux/skbuff.h                          |    2 
 include/net/inet_frag.h                         |   35 ---
 lib/idr.c                                       |    2 
 mm/memory-failure.c                             |    2 
 net/core/skbuff.c                               |    9 
 net/ieee802154/6lowpan/reassembly.c             |   11 -
 net/ipv4/inet_fragment.c                        |    4 
 net/ipv4/ip_fragment.c                          |   12 -
 net/ipv4/ip_tunnel.c                            |    4 
 net/ipv4/tcp_ipv4.c                             |    6 
 net/ipv4/udp.c                                  |    5 
 net/ipv6/ip6_fib.c                              |   25 +-
 net/ipv6/ip6_gre.c                              |    4 
 net/ipv6/netfilter/nf_conntrack_reasm.c         |   12 -
 net/ipv6/reassembly.c                           |   12 -
 net/ipv6/tcp_ipv6.c                             |    6 
 net/sctp/ulpqueue.c                             |    3 
 62 files changed, 928 insertions(+), 514 deletions(-)

Amir Goldstein (2):
ovl: fix false positive ESTALE on lookup
xfs: fix incorrect log_flushed on fsync

Andy Lutomirski (3):
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

Bernat, Yehezkel (3):
thunderbolt: Remove superfluous check
thunderbolt: Make key root-only accessible
thunderbolt: Allow clearing the key

Brian Foster (13):
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: 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

Carlos Maiolino (3):
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: stop searching for free slots in an inode chunk when there are none

Christoph Hellwig (3):
xfs: disable per-inode DAX flag
xfs: don't set v3 xflags for v2 inodes
xfs: open code end_buffer_async_write in xfs_finish_page_writeback

Christophe Jaillet (1):
libnvdimm, btt: check memory allocation failure

Claudiu Manoil (1):
gianfar: Fix Tx flow control deactivation

Dan Williams (1):
libnvdimm: fix integer overflow static analysis warning

Darrick J. Wong (2):
xfs: evict all inodes involved with log redo item
xfs: fix compiler warnings

Eric Biggers (1):
idr: remove WARN_ON_ONCE() when trying to replace negative ID

Eric Dumazet (2):
ipv6: fix typo in fib6_net_exit()
tcp: fix a request socket leak

Eric Sandeen (2):
xfs: write unmount record for ro mounts
xfs: toggle readonly state around xfs_log_mount_finish

Greg Kroah-Hartman (1):

      Linux 4.13.3

Haishuang Yan (1):
ip_tunnel: fix setting ttl and tos value in collect_md mode

Jaegeuk Kim (2):
f2fs: let fill_super handle roll-forward errors
f2fs: check hot_data for roll-forward recovery

Jason Wang (1):
vhost_net: correctly check tx avail during rx busy polling

Jesper Dangaard Brouer (2):
Revert "net: use lib/percpu_counter API for fragmentation mem accounting" Revert "net: fix percpu memory leaks"

Marcelo Ricardo Leitner (1):
sctp: fix missing wake ups in some situations

Miklos Szeredi (1):
fuse: allow server to run in different pid_ns

Omar Sandoval (1):
xfs: check for race with xfs_reclaim_inode() in xfs_ifree_cluster()

Pan Bian (1):
xfs: use kmem_free to free return value of kmem_zalloc

Paolo Abeni (1):
udp: drop head states only when all skb references are gone

Sabrina Dubroca (1):
ipv6: fix memory leak with multiple tables during netns destruction

Shaohua Li (1):
md/raid1/10: reset bio allocated from mempool

Song Liu (1):
md/raid5: release/flush io in raid5_do_work()

Tony Luck (1):
x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages

Xin Long (1):
ip6_gre: update mtu properly in ip6gre_err

author maintainer
#1 lore raw
Documentation/ABI/testing/sysfs-bus-thunderbolt +2 -0
index 2a98149943ea..392bef5bd399 100644
@@ -45,6 +45,8 @@ Contact:	[email protected]
 Description:	When a devices supports Thunderbolt secure connect it will
 		have this attribute. Writing 32 byte hex string changes
 		authorization to use the secure connection method instead.
+		Writing an empty string clears the key and regular connection
+		method can be used again.
 
 What:		/sys/bus/thunderbolt/devices/.../device
 Date:		Sep 2017
Makefile +1 -1
index 8aad6bc50d52..0f31ef4aea7b 100644
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 13
-SUBLEVEL = 2
+SUBLEVEL = 3
 EXTRAVERSION =
 NAME = Fearless Coyote
 
arch/x86/include/asm/elf.h +3 -2
index 9aeb91935ce0..e2c4dd051ef8 100644
@@ -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/include/asm/page_64.h +4 -0
index b4a0d43248cf..b50df06ad251 100644
@@ -51,6 +51,10 @@ static inline void clear_page(void *page)
 
 void copy_page(void *to, void *from);
 
+#ifdef CONFIG_X86_MCE
+#define arch_unmap_kpfn arch_unmap_kpfn
+#endif
+
 #endif	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
arch/x86/kernel/cpu/mcheck/mce.c +43 -0

55 lines not on this page · raw message

arch/x86/kernel/process_64.c +131 -105

270 lines not on this page · raw message

drivers/md/raid1.c +18 -1
index f50958ded9f0..79474f47eeef 100644
@@ -2564,6 +2564,23 @@ static int init_resync(struct r1conf *conf)
 	return 0;
 }
 
+static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
+{
+	struct r1bio *r1bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
+	struct resync_pages *rps;
+	struct bio *bio;
+	int i;
+
+	for (i = conf->poolinfo->raid_disks; i--; ) {
+		bio = r1bio->bios[i];
+		rps = bio->bi_private;
+		bio_reset(bio);
+		bio->bi_private = rps;
+	}
+	r1bio->master_bio = NULL;
+	return r1bio;
+}
+
 /*
  * perform a "sync" on one "block"
  *
@@ -2649,7 +2666,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 	bitmap_cond_end_sync(mddev->bitmap, sector_nr,
 		mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
-	r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
+	r1_bio = raid1_alloc_init_r1buf(conf);
 
 	raise_barrier(conf, sector_nr);
 
drivers/md/raid10.c +32 -3
index f55d4cc085f6..d51ac02e98ef 100644
@@ -2798,6 +2798,35 @@ static int init_resync(struct r10conf *conf)
 	return 0;
 }
 
+static struct r10bio *raid10_alloc_init_r10buf(struct r10conf *conf)
+{
+	struct r10bio *r10bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+	struct rsync_pages *rp;
+	struct bio *bio;
+	int nalloc;
+	int i;
+
+	if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery) ||
+	    test_bit(MD_RECOVERY_RESHAPE, &conf->mddev->recovery))
+		nalloc = conf->copies; /* resync */
+	else
+		nalloc = 2; /* recovery */
+
+	for (i = 0; i < nalloc; i++) {
+		bio = r10bio->devs[i].bio;
+		rp = bio->bi_private;
+		bio_reset(bio);
+		bio->bi_private = rp;
+		bio = r10bio->devs[i].repl_bio;
+		if (bio) {
+			rp = bio->bi_private;
+			bio_reset(bio);
+			bio->bi_private = rp;
+		}
+	}
+	return r10bio;
+}
+
 /*
  * perform a "sync" on one "block"
  *
@@ -3027,7 +3056,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				atomic_inc(&mreplace->nr_pending);
 			rcu_read_unlock();
 
-			r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+			r10_bio = raid10_alloc_init_r10buf(conf);
 			r10_bio->state = 0;
 			raise_barrier(conf, rb2 != NULL);
 			atomic_set(&r10_bio->remaining, 0);
@@ -3236,7 +3265,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		}
 		if (sync_blocks < max_sync)
 			max_sync = sync_blocks;
-		r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+		r10_bio = raid10_alloc_init_r10buf(conf);
 		r10_bio->state = 0;
 
 		r10_bio->mddev = mddev;
@@ -4360,7 +4389,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 
 read_more:
 	/* Now schedule reads for blocks from sector_nr to last */
-	r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+	r10_bio = raid10_alloc_init_r10buf(conf);
 	r10_bio->state = 0;
 	raise_barrier(conf, sectors_done != 0);
 	atomic_set(&r10_bio->remaining, 0);
drivers/md/raid5.c +4 -0
index 0fc2748aaf95..e13a8ce7f589 100644
@@ -6235,6 +6235,10 @@ static void raid5_do_work(struct work_struct *work)
 
 	spin_unlock_irq(&conf->device_lock);
 
+	flush_deferred_bios(conf);
+
+	r5l_flush_stripe_to_raid(conf->log);
+
 	async_tx_issue_pending_all();
 	blk_finish_plug(&plug);
 
drivers/net/ethernet/freescale/gianfar.c +1 -1
index c4b4b0a1bbf0..5be52d89b182 100644
@@ -3687,7 +3687,7 @@ 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/nvdimm/btt.c +2 -0
index 14323faf8bd9..7ec6393b6ba1 100644
@@ -1429,6 +1429,8 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns)
 	}
 
 	btt_sb = devm_kzalloc(&nd_btt->dev, sizeof(*btt_sb), GFP_KERNEL);
+	if (!btt_sb)
+		return -ENOMEM;
 
 	/*
 	 * If this returns < 0, that is ok as it just means there wasn't
drivers/nvdimm/bus.c +9 -8
index 937fafa1886a..54eb14c7ef90 100644
@@ -905,19 +905,20 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 		int read_only, unsigned int ioctl_cmd, unsigned long arg)
 {
 	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
-	size_t buf_len = 0, in_len = 0, out_len = 0;
 	static char out_env[ND_CMD_MAX_ENVELOPE];
 	static char in_env[ND_CMD_MAX_ENVELOPE];
 	const struct nd_cmd_desc *desc = NULL;
 	unsigned int cmd = _IOC_NR(ioctl_cmd);
-	unsigned int func = cmd;
-	void __user *p = (void __user *) arg;
 	struct device *dev = &nvdimm_bus->dev;
-	struct nd_cmd_pkg pkg;
+	void __user *p = (void __user *) arg;
 	const char *cmd_name, *dimm_name;
+	u32 in_len = 0, out_len = 0;
+	unsigned int func = cmd;
 	unsigned long cmd_mask;
-	void *buf;
+	struct nd_cmd_pkg pkg;
 	int rc, i, cmd_rc;
+	u64 buf_len = 0;
+	void *buf;
 
 	if (nvdimm) {
 		desc = nd_cmd_dimm_desc(cmd);
@@ -977,7 +978,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 
 	if (cmd == ND_CMD_CALL) {
 		func = pkg.nd_command;
-		dev_dbg(dev, "%s:%s, idx: %llu, in: %zu, out: %zu, len %zu\n",
+		dev_dbg(dev, "%s:%s, idx: %llu, in: %u, out: %u, len %llu\n",
 				__func__, dimm_name, pkg.nd_command,
 				in_len, out_len, buf_len);
 
@@ -1007,9 +1008,9 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 		out_len += out_size;
 	}
 
-	buf_len = out_len + in_len;
+	buf_len = (u64) out_len + (u64) in_len;
 	if (buf_len > ND_IOCTL_MAX_BUFLEN) {
-		dev_dbg(dev, "%s:%s cmd: %s buf_len: %zu > %d\n", __func__,
+		dev_dbg(dev, "%s:%s cmd: %s buf_len: %llu > %d\n", __func__,
 				dimm_name, cmd_name, buf_len,
 				ND_IOCTL_MAX_BUFLEN);
 		return -EINVAL;
drivers/thunderbolt/switch.c +12 -8
index e9391bbd4036..53f40c57df59 100644
@@ -807,11 +807,11 @@ static ssize_t key_store(struct device *dev, struct device_attribute *attr,
 	struct tb_switch *sw = tb_to_switch(dev);
 	u8 key[TB_SWITCH_KEY_SIZE];
 	ssize_t ret = count;
+	bool clear = false;
 
-	if (count < 64)
-		return -EINVAL;
-
-	if (hex2bin(key, buf, sizeof(key)))
+	if (!strcmp(buf, "\n"))
+		clear = true;
+	else if (hex2bin(key, buf, sizeof(key)))
 		return -EINVAL;
 
 	if (mutex_lock_interruptible(&switch_lock))
@@ -821,15 +821,19 @@ static ssize_t key_store(struct device *dev, struct device_attribute *attr,
 		ret = -EBUSY;
 	} else {
 		kfree(sw->key);
-		sw->key = kmemdup(key, sizeof(key), GFP_KERNEL);
-		if (!sw->key)
-			ret = -ENOMEM;
+		if (clear) {
+			sw->key = NULL;
+		} else {
+			sw->key = kmemdup(key, sizeof(key), GFP_KERNEL);
+			if (!sw->key)
+				ret = -ENOMEM;
+		}
 	}
 
 	mutex_unlock(&switch_lock);
 	return ret;
 }
-static DEVICE_ATTR_RW(key);
+static DEVICE_ATTR(key, 0600, key_show, key_store);
 
 static ssize_t nvm_authenticate_show(struct device *dev,
 	struct device_attribute *attr, char *buf)
drivers/vhost/net.c +6 -1
index 06d044862e58..1c75572f5a3f 100644
@@ -634,8 +634,13 @@ 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(rvq, sk);
fs/f2fs/recovery.c +1 -3
index 907d6b7dde6a..86d813a3f5d1 100644
@@ -291,7 +291,7 @@ 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];
@@ -599,8 +599,6 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	}
 
 	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/fuse/dev.c +7 -6
index c16d00e53264..13c65dd2d37d 100644
@@ -1222,9 +1222,6 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
 	struct fuse_in *in;
 	unsigned reqsize;
 
-	if (task_active_pid_ns(current) != fc->pid_ns)
-		return -EIO;
-
  restart:
 	spin_lock(&fiq->waitq.lock);
 	err = -EAGAIN;
@@ -1262,6 +1259,13 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
 
 	in = &req->in;
 	reqsize = in->h.len;
+
+	if (task_active_pid_ns(current) != fc->pid_ns) {
+		rcu_read_lock();
+		in->h.pid = pid_vnr(find_pid_ns(in->h.pid, fc->pid_ns));
+		rcu_read_unlock();
+	}
+
 	/* If request is too large, reply with an error and restart the read */
 	if (nbytes < reqsize) {
 		req->out.h.error = -EIO;
@@ -1823,9 +1827,6 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 	struct fuse_req *req;
 	struct fuse_out_header oh;
 
-	if (task_active_pid_ns(current) != fc->pid_ns)
-		return -EIO;
-
 	if (nbytes < sizeof(struct fuse_out_header))
 		return -EINVAL;
 
fs/fuse/file.c +0 -3
index ab60051be6e5..6d8e65cec01a 100644
@@ -2181,9 +2181,6 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
 	if ((fl->fl_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX)
 		return 0;
 
-	if (pid && pid_nr == 0)
-		return -EOVERFLOW;
-
 	fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg);
 	err = fuse_simple_request(fc, &args);
 
fs/inode.c +1 -0
index 50370599e371..6a1626e0edaf 100644
@@ -637,6 +637,7 @@ void evict_inodes(struct super_block *sb)
 
 	dispose_list(&dispose);
 }
+EXPORT_SYMBOL_GPL(evict_inodes);
 
 /**
  * invalidate_inodes	- attempt to free all inodes on a superblock
fs/internal.h +0 -1
index 9676fe11c093..fedfe94d84ba 100644
@@ -132,7 +132,6 @@ static inline bool atime_needs_update_rcu(const struct path *path,
 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/overlayfs/inode.c +7 -4
index 5bc71642b226..ef55c926463c 100644
@@ -576,10 +576,13 @@ static int ovl_inode_set(struct inode *inode, void *data)
 static bool ovl_verify_inode(struct inode *inode, struct dentry *lowerdentry,
 			     struct dentry *upperdentry)
 {
-	struct inode *lowerinode = lowerdentry ? d_inode(lowerdentry) : NULL;
-
-	/* Lower (origin) inode must match, even if NULL */
-	if (ovl_inode_lower(inode) != lowerinode)
+	/*
+	 * Allow non-NULL lower inode in ovl_inode even if lowerdentry is NULL.
+	 * This happens when finding a copied up overlay inode for a renamed
+	 * or hardlinked overlay dentry and lower dentry cannot be followed
+	 * by origin because lower fs does not support file handles.
+	 */
+	if (lowerdentry && ovl_inode_lower(inode) != d_inode(lowerdentry))
 		return false;
 
 	/*
fs/xfs/libxfs/xfs_bmap.c +1 -1
index c09c16b1ad3b..6f2a5baded76 100644
@@ -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 */
 
 /*
fs/xfs/libxfs/xfs_bmap_btree.c +1 -0
index 85de22513014..a6331ffa51e3 100644
@@ -858,6 +858,7 @@ 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 +18 -9
index e0bcc4a59efd..5bfb88261c7e 100644
@@ -1791,6 +1791,7 @@ 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)
@@ -4451,10 +4452,15 @@ 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
@@ -4463,16 +4469,19 @@ 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);
+	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);
-		} else {
-			xfs_buf_delwri_queue(bp, bbcoi->buffer_list);
+			return -EAGAIN;
 		}
 	} else {
-		ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
-		ASSERT(level == cur->bc_nlevels - 1);
+		xfs_buf_delwri_queue(bp, bbcoi->buffer_list);
 	}
 
 	return 0;
fs/xfs/libxfs/xfs_btree.h +2 -1
index 9c95e965cfe5..f2a88c3b1159 100644
@@ -233,7 +233,8 @@ 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_ialloc.c +27 -30

95 lines not on this page · raw message

fs/xfs/libxfs/xfs_inode_fork.c +3 -6
index 0e80f34fe97c..5eb165555934 100644
@@ -1499,14 +1499,11 @@ 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/xfs_aops.c +47 -24

108 lines not on this page · raw message

fs/xfs/xfs_bmap_util.c +69 -24

128 lines not on this page · raw message

fs/xfs/xfs_buf_item.c +90 -47

212 lines not on this page · raw message

fs/xfs/xfs_buf_item.h +4 -1
index f7eba99d19dd..9690ce62c9a7 100644
@@ -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_icache.c +5 -5
index 0a9e6985a0d0..34227115a5d6 100644
@@ -1124,11 +1124,11 @@ xfs_reclaim_inode(
 	 * 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 +18 -5
index ff48f0096810..97045e8dfed5 100644
@@ -2359,11 +2359,24 @@ xfs_ifree_cluster(
 			 * already marked stale. If we can't lock it, back off
 			 * and retry.
 			 */
-			if (ip != free_ip &&
-			    !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
-				rcu_read_unlock();
-				delay(1);
-				goto retry;
+			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();
 
fs/xfs/xfs_inode_item.c +43 -4

95 lines not on this page · raw message

fs/xfs/xfs_ioctl.c +27 -14

86 lines not on this page · raw message

fs/xfs/xfs_iops.c +1 -1
index 469c9fa4c178..17081c77ef86 100644
@@ -817,7 +817,7 @@ 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 +24 -9
index 4ebd0bafc914..c5107c7bc4bf 100644
@@ -743,10 +743,14 @@ 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;
 	}
 
 	/*
@@ -757,12 +761,27 @@ xfs_log_mount_finish(
 	 * 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;
 }
@@ -812,11 +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)));
@@ -3353,8 +3375,6 @@ _xfs_log_force(
 		 */
 		if (iclog->ic_state & XLOG_STATE_IOERROR)
 			return -EIO;
-		if (log_flushed)
-			*log_flushed = 1;
 	} else {
 
 no_sleep:
@@ -3458,8 +3478,6 @@ _xfs_log_force_lsn(
 
 				xlog_wait(&iclog->ic_prev->ic_write_wait,
 							&log->l_icloglock);
-				if (log_flushed)
-					*log_flushed = 1;
 				already_slept = 1;
 				goto try_again;
 			}
@@ -3493,9 +3511,6 @@ _xfs_log_force_lsn(
 			 */
 			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 +99 -60

240 lines not on this page · raw message

fs/xfs/xfs_super.c +1 -1
index 38aaacdbb8b3..c1c4c2ea1014 100644
@@ -1220,7 +1220,7 @@ 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 +0 -1
index bcc3cdf8e1c5..bb0099708827 100644
@@ -517,7 +517,6 @@ 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);
fs/xfs/xfs_trans.h +10 -4
index 6bdad6f58934..4709823e04b9 100644
@@ -49,6 +49,7 @@ 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 *);
@@ -64,11 +65,13 @@ typedef struct xfs_log_item {
 } xfs_log_item_t;
 
 #define	XFS_LI_IN_AIL	0x1
-#define XFS_LI_ABORTED	0x2
+#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 *);
@@ -79,6 +82,7 @@ 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,
@@ -208,12 +212,14 @@ 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);
fs/xfs/xfs_trans_ail.c +2 -1
index 9056c0f34a3c..70f5ab017323 100644
@@ -687,12 +687,13 @@ xfs_trans_ail_update_bulk(
 bool
 xfs_ail_delete_one(
 	struct xfs_ail		*ailp,
-	struct xfs_log_item 	*lip)
+	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;
 
fs/xfs/xfs_trans_buf.c +49 -30

128 lines not on this page · raw message

fs/xfs/xfs_trans_priv.h +31 -0
index d91706c56c63..b317a3644c00 100644
@@ -164,4 +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 +1 -0
index cbfe127bccf8..d0c0ca8ea8c1 100644
@@ -2831,6 +2831,7 @@ 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/mm_inline.h +6 -0
index e030a68ead7e..25438b2b6f22 100644
@@ -126,4 +126,10 @@ static __always_inline enum lru_list page_lru(struct page *page)
 
 #define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
 
+#ifdef arch_unmap_kpfn
+extern void arch_unmap_kpfn(unsigned long pfn);
+#else
+static __always_inline void arch_unmap_kpfn(unsigned long pfn) { }
+#endif
+
 #endif
include/linux/skbuff.h +1 -1
index d67a8182e5eb..63df75ae70ee 100644
@@ -885,7 +885,7 @@ void kfree_skb(struct sk_buff *skb);
 void kfree_skb_list(struct sk_buff *segs);
 void skb_tx_error(struct sk_buff *skb);
 void consume_skb(struct sk_buff *skb);
-void consume_stateless_skb(struct sk_buff *skb);
+void __consume_stateless_skb(struct sk_buff *skb);
 void  __kfree_skb(struct sk_buff *skb);
 extern struct kmem_cache *skbuff_head_cache;
 
include/net/inet_frag.h +9 -26
index 6fdcd2427776..fc59e0775e00 100644
@@ -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)
-{
-	return percpu_counter_init(&nf->mem, 0, GFP_KERNEL);
-}
-static inline void inet_frags_uninit_net(struct netns_frags *nf)
+static inline void inet_frags_init_net(struct netns_frags *nf)
 {
-	percpu_counter_destroy(&nf->mem);
+	atomic_set(&nf->mem, 0);
 }
-
 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);
@@ -140,31 +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_batch(&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_batch(&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)
 {
-	return percpu_counter_sum_positive(&nf->mem);
+	return atomic_read(&nf->mem);
 }
 
 /* RFC 3168 support :
lib/idr.c +1 -1
index b13682bb0a1c..20c2779e8d12 100644
@@ -154,7 +154,7 @@ void *idr_replace(struct idr *idr, void *ptr, int id)
 	void __rcu **slot = NULL;
 	void *entry;
 
-	if (WARN_ON_ONCE(id < 0))
+	if (id < 0)
 		return ERR_PTR(-EINVAL);
 	if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
 		return ERR_PTR(-EINVAL);
mm/memory-failure.c +2 -0
index 1cd3b3569af8..88366626c0b7 100644
@@ -1146,6 +1146,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 		return 0;
 	}
 
+	arch_unmap_kpfn(pfn);
+
 	orig_head = hpage = compound_head(p);
 	num_poisoned_pages_inc();
 
net/core/skbuff.c +3 -6
index e07556606284..72eb23d2426f 100644
@@ -753,14 +753,11 @@ EXPORT_SYMBOL(consume_skb);
  *	consume_stateless_skb - free an skbuff, assuming it is stateless
  *	@skb: buffer to free
  *
- *	Works like consume_skb(), but this variant assumes that all the head
- *	states have been already dropped.
+ *	Alike consume_skb(), but this variant assumes that this is the last
+ *	skb reference and all the head states have been already dropped
  */
-void consume_stateless_skb(struct sk_buff *skb)
+void __consume_stateless_skb(struct sk_buff *skb)
 {
-	if (!skb_unref(skb))
-		return;
-
 	trace_consume_skb(skb);
 	if (likely(skb->head))
 		skb_release_data(skb);
net/ieee802154/6lowpan/reassembly.c +3 -8
index 30d875dff6b5..f85b08baff16 100644
@@ -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 +1 -3
index 96e95e83cc61..af74d0433453 100644
@@ -234,10 +234,8 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
 	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 +3 -9
index 9a8cfac503dc..46408c220d9d 100644
@@ -844,8 +844,6 @@ 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
@@ -871,13 +869,9 @@ 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 +2 -2
index 129d1a3616f8..e1856bfa753d 100644
@@ -618,8 +618,8 @@ 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_ipv4.c +3 -3
index e9252c7df809..21022db7a2a6 100644
@@ -1722,9 +1722,9 @@ int tcp_v4_rcv(struct sk_buff *skb)
 		 */
 		sock_hold(sk);
 		refcounted = true;
-		if (tcp_filter(sk, skb))
-			goto discard_and_relse;
-		nsk = tcp_check_req(sk, skb, req, false);
+		nsk = NULL;
+		if (!tcp_filter(sk, skb))
+			nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
 			goto discard_and_relse;
net/ipv4/udp.c +4 -1
index 62344804baae..979e4d8526ba 100644
@@ -1386,12 +1386,15 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 		unlock_sock_fast(sk, slow);
 	}
 
+	if (!skb_unref(skb))
+		return;
+
 	/* In the more common cases we cleared the head states previously,
 	 * see __udp_queue_rcv_skb().
 	 */
 	if (unlikely(udp_skb_has_head_state(skb)))
 		skb_release_head_state(skb);
-	consume_stateless_skb(skb);
+	__consume_stateless_skb(skb);
 }
 EXPORT_SYMBOL_GPL(skb_consume_udp);
 
net/ipv6/ip6_fib.c +19 -6
index e1c85bb4eac0..1792bbfd80e1 100644
@@ -198,6 +198,12 @@ 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;
@@ -1915,15 +1921,22 @@ static int __net_init fib6_net_init(struct net *net)
 
 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 +3 -1
index 67ff2aaf5dcb..b7a72d409334 100644
@@ -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 +3 -9
index 986d4ca38832..b263bf3a19f7 100644
@@ -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/reassembly.c +3 -9
index e1da5b888cc4..846012eae526 100644
@@ -714,19 +714,13 @@ 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/tcp_ipv6.c +3 -3
index 206210125fd7..660b9b2a8a25 100644
@@ -1456,9 +1456,9 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 		}
 		sock_hold(sk);
 		refcounted = true;
-		if (tcp_filter(sk, skb))
-			goto discard_and_relse;
-		nsk = tcp_check_req(sk, skb, req, false);
+		nsk = NULL;
+		if (!tcp_filter(sk, skb))
+			nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
 			goto discard_and_relse;
net/sctp/ulpqueue.c +2 -1
index 0225d62a869f..a71be33f3afe 100644
@@ -265,7 +265,8 @@ 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) {
-		sp->data_ready_signalled = 1;
+		if (!sock_owned_by_user(sk))
+			sp->data_ready_signalled = 1;
 		sk->sk_data_ready(sk);
 	}
 	return 1;