Merge branch 'android-4.4@6fc0573' into branch 'msm-4.4'

* refs/heads/tmp-6fc0573:
  Linux 4.4.71
  xfs: only return -errno or success from attr ->put_listent
  xfs: in _attrlist_by_handle, copy the cursor back to userspace
  xfs: fix unaligned access in xfs_btree_visit_blocks
  xfs: bad assertion for delalloc an extent that start at i_size
  xfs: fix indlen accounting error on partial delalloc conversion
  xfs: wait on new inodes during quotaoff dquot release
  xfs: update ag iterator to support wait on new inodes
  xfs: support ability to wait on new inodes
  xfs: fix up quotacheck buffer list error handling
  xfs: prevent multi-fsb dir readahead from reading random blocks
  xfs: handle array index overrun in xfs_dir2_leaf_readbuf()
  xfs: fix over-copying of getbmap parameters from userspace
  xfs: fix off-by-one on max nr_pages in xfs_find_get_desired_pgoff()
  xfs: Fix missed holes in SEEK_HOLE implementation
  mlock: fix mlock count can not decrease in race condition
  mm/migrate: fix refcount handling when !hugepage_migration_supported()
  drm/gma500/psb: Actually use VBT mode when it is found
  slub/memcg: cure the brainless abuse of sysfs attributes
  ALSA: hda - apply STAC_9200_DELL_M22 quirk for Dell Latitude D430
  pcmcia: remove left-over %Z format
  drm/radeon: Unbreak HPD handling for r600+
  drm/radeon/ci: disable mclk switching for high refresh rates (v2)
  scsi: mpt3sas: Force request partial completion alignment
  HID: wacom: Have wacom_tpc_irq guard against possible NULL dereference
  mmc: sdhci-iproc: suppress spurious interrupt with Multiblock read
  i2c: i2c-tiny-usb: fix buffer not being DMA capable
  vlan: Fix tcp checksum offloads in Q-in-Q vlans
  net: phy: marvell: Limit errata to 88m1101
  netem: fix skb_orphan_partial()
  ipv4: add reference counting to metrics
  sctp: fix ICMP processing if skb is non-linear
  tcp: avoid fastopen API to be used on AF_UNSPEC
  virtio-net: enable TSO/checksum offloads for Q-in-Q vlans
  be2net: Fix offload features for Q-in-Q packets
  ipv6: fix out of bound writes in __ip6_append_data()
  bridge: start hello_timer when enabling KERNEL_STP in br_stp_start
  qmi_wwan: add another Lenovo EM74xx device ID
  bridge: netlink: check vlan_default_pvid range
  ipv6: Check ip6_find_1stfragopt() return value properly.
  ipv6: Prevent overrun when parsing v6 header options
  net: Improve handling of failures on link and route dumps
  tcp: eliminate negative reordering in tcp_clean_rtx_queue
  sctp: do not inherit ipv6_{mc|ac|fl}_list from parent
  sctp: fix src address selection if using secondary addresses for ipv6
  tcp: avoid fragmenting peculiar skbs in SACK
  s390/qeth: avoid null pointer dereference on OSN
  s390/qeth: unbreak OSM and OSN support
  s390/qeth: handle sysfs error during initialization
  ipv6/dccp: do not inherit ipv6_mc_list from parent
  dccp/tcp: do not inherit mc_list from parent
  sparc: Fix -Wstringop-overflow warning
  android: base-cfg: disable CONFIG_NFS_FS and CONFIG_NFSD
  schedstats/eas: guard properly to avoid breaking non-smp schedstats users
  BACKPORT: f2fs: sanity check size of nat and sit cache
  FROMLIST: f2fs: sanity check checkpoint segno and blkoff
  sched/tune: don't use schedtune before it is ready
  sched/fair: use SCHED_CAPACITY_SCALE for energy normalization
  sched/{fair,tune}: use reciprocal_value to compute boost margin
  sched/tune: Initialize raw_spin_lock in boosted_groups
  sched/tune: report when SchedTune has not been initialized
  sched/tune: fix sched_energy_diff tracepoint
  sched/tune: increase group count to 5
  cpufreq/schedutil: use boosted_cpu_util for PELT to match WALT
  sched/fair: Fix sched_group_energy() to support per-cpu capacity states
  sched/fair: discount task contribution to find CPU with lowest utilization
  sched/fair: ensure utilization signals are synchronized before use
  sched/fair: remove task util from own cpu when placing waking task
  trace:sched: Make util_avg in load_avg trace reflect PELT/WALT as used
  sched/fair: Add eas (& cas) specific rq, sd and task stats
  sched/core: Fix PELT jump to max OPP upon util increase
  sched: EAS & 'single cpu per cluster'/cpu hotplug interoperability
  UPSTREAM: sched/core: Fix group_entity's share update
  UPSTREAM: sched/fair: Fix calc_cfs_shares() fixed point arithmetics width confusion
  UPSTREAM: sched/fair: Fix incorrect task group ->load_avg
  UPSTREAM: sched/fair: Fix effective_load() to consistently use smoothed load
  UPSTREAM: sched/fair: Propagate asynchrous detach
  UPSTREAM: sched/fair: Propagate load during synchronous attach/detach
  UPSTREAM: sched/fair: Fix hierarchical order in rq->leaf_cfs_rq_list
  BACKPORT: sched/fair: Factorize PELT update
  UPSTREAM: sched/fair: Factorize attach/detach entity
  UPSTREAM: sched/fair: Improve PELT stuff some more
  UPSTREAM: sched/fair: Apply more PELT fixes
  UPSTREAM: sched/fair: Fix post_init_entity_util_avg() serialization
  BACKPORT: sched/fair: Initiate a new task's util avg to a bounded value
  sched/fair: Simplify idle_idx handling in select_idle_sibling()
  sched/fair: refactor find_best_target() for simplicity
  sched/fair: Change cpu iteration order in find_best_target()
  sched/core: Add first cpu w/ max/min orig capacity to root domain
  sched/core: Remove remnants of commit fd5c98da1a42
  sched: Remove sysctl_sched_is_big_little
  sched/fair: Code !is_big_little path into select_energy_cpu_brute()
  EAS: sched/fair: Re-integrate 'honor sync wakeups' into wakeup path
  Fixup!: sched/fair.c: Set SchedTune specific struct energy_env.task
  sched/fair: Energy-aware wake-up task placement
  sched/fair: Add energy_diff dead-zone margin
  sched/fair: Decommission energy_aware_wake_cpu()
  sched/fair: Do not force want_affine eq. true if EAS is enabled
  arm64: Set SD_ASYM_CPUCAPACITY sched_domain flag on DIE level
  UPSTREAM: sched/fair: Fix incorrect comment for capacity_margin
  UPSTREAM: sched/fair: Avoid pulling tasks from non-overloaded higher capacity groups
  UPSTREAM: sched/fair: Add per-CPU min capacity to sched_group_capacity
  UPSTREAM: sched/fair: Consider spare capacity in find_idlest_group()
  UPSTREAM: sched/fair: Compute task/cpu utilization at wake-up correctly
  UPSTREAM: sched/fair: Let asymmetric CPU configurations balance at wake-up
  UPSTREAM: sched/core: Enable SD_BALANCE_WAKE for asymmetric capacity systems
  UPSTREAM: sched/core: Pass child domain into sd_init()
  UPSTREAM: sched/core: Introduce SD_ASYM_CPUCAPACITY sched_domain topology flag
  UPSTREAM: sched/core: Remove unnecessary NULL-pointer check
  UPSTREAM: sched/fair: Optimize find_idlest_cpu() when there is no choice
  BACKPORT: sched/fair: Make the use of prev_cpu consistent in the wakeup path
  UPSTREAM: sched/core: Fix power to capacity renaming in comment
  Partial Revert: "WIP: sched: Add cpu capacity awareness to wakeup balancing"
  Revert "WIP: sched: Consider spare cpu capacity at task wake-up"
  FROM-LIST: cpufreq: schedutil: Redefine the rate_limit_us tunable
  cpufreq: schedutil: add up/down frequency transition rate limits
  trace/sched: add rq utilization signal for WALT
  sched/cpufreq: make schedutil use WALT signal
  sched: cpufreq: use rt_avg as estimate of required RT CPU capacity
  cpufreq: schedutil: move slow path from workqueue to SCHED_FIFO task
  BACKPORT: kthread: allow to cancel kthread work
  sched/cpufreq: fix tunables for schedfreq governor
  BACKPORT: cpufreq: schedutil: New governor based on scheduler utilization data
  sched: backport cpufreq hooks from 4.9-rc4
  ANDROID: Kconfig: add depends for UID_SYS_STATS
  ANDROID: hid: uhid: implement refcount for open and close
  Revert "ext4: require encryption feature for EXT4_IOC_SET_ENCRYPTION_POLICY"
  ANDROID: mnt: Fix next_descendent

Conflicts:
	include/trace/events/sched.h
	kernel/sched/Makefile
	kernel/sched/core.c
	kernel/sched/fair.c
	kernel/sched/sched.h

Change-Id: I55318828f2c858e192ac7015bcf2bf0ec5c5b2c5
Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>

3 files changed, 44 insertions, 27 deletions

diff --git a/net/core/dst.c b/net/core/dst.c
index a1656e3b8d72..d7ad628bf64e 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -151,13 +151,13 @@ int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dst_discard_out);
 
-const u32 dst_default_metrics[RTAX_MAX + 1] = {
+const struct dst_metrics dst_default_metrics = {
 	/* This initializer is needed to force linker to place this variable
 	 * into const section. Otherwise it might end into bss section.
 	 * We really want to avoid false sharing on this variable, and catch
 	 * any writes on it.
 	 */
-	[RTAX_MAX] = 0xdeadbeef,
+	.refcnt = ATOMIC_INIT(1),
 };
 
 void dst_init(struct dst_entry *dst, struct dst_ops *ops,
@@ -169,7 +169,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
 	if (dev)
 		dev_hold(dev);
 	dst->ops = ops;
-	dst_init_metrics(dst, dst_default_metrics, true);
+	dst_init_metrics(dst, dst_default_metrics.metrics, true);
 	dst->expires = 0UL;
 	dst->path = dst;
 	dst->from = NULL;
@@ -315,25 +315,30 @@ EXPORT_SYMBOL(dst_release);
 
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
-	u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+	struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC);
 
 	if (p) {
-		u32 *old_p = __DST_METRICS_PTR(old);
+		struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old);
 		unsigned long prev, new;
 
-		memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+		atomic_set(&p->refcnt, 1);
+		memcpy(p->metrics, old_p->metrics, sizeof(p->metrics));
 
 		new = (unsigned long) p;
 		prev = cmpxchg(&dst->_metrics, old, new);
 
 		if (prev != old) {
 			kfree(p);
-			p = __DST_METRICS_PTR(prev);
+			p = (struct dst_metrics *)__DST_METRICS_PTR(prev);
 			if (prev & DST_METRICS_READ_ONLY)
 				p = NULL;
+		} else if (prev & DST_METRICS_REFCOUNTED) {
+			if (atomic_dec_and_test(&old_p->refcnt))
+				kfree(old_p);
 		}
 	}
-	return p;
+	BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0);
+	return (u32 *)p;
 }
 EXPORT_SYMBOL(dst_cow_metrics_generic);
 
@@ -342,7 +347,7 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
 	unsigned long prev, new;
 
-	new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY;
+	new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY;
 	prev = cmpxchg(&dst->_metrics, old, new);
 	if (prev == old)
 		kfree(__DST_METRICS_PTR(old));
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fe38ef58997c..d43544ce7550 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1458,13 +1458,13 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 					       cb->nlh->nlmsg_seq, 0,
 					       NLM_F_MULTI,
 					       ext_filter_mask);
-			/* If we ran out of room on the first message,
-			 * we're in trouble
-			 */
-			WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
 
-			if (err < 0)
-				goto out;
+			if (err < 0) {
+				if (likely(skb->len))
+					goto out;
+
+				goto out_err;
+			}
 
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
@@ -1472,10 +1472,12 @@ cont:
 		}
 	}
 out:
+	err = skb->len;
+out_err:
 	cb->args[1] = idx;
 	cb->args[0] = h;
 
-	return skb->len;
+	return err;
 }
 
 int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len)
@@ -3127,8 +3129,12 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 				err = br_dev->netdev_ops->ndo_bridge_getlink(
 						skb, portid, seq, dev,
 						filter_mask, NLM_F_MULTI);
-				if (err < 0 && err != -EOPNOTSUPP)
-					break;
+				if (err < 0 && err != -EOPNOTSUPP) {
+					if (likely(skb->len))
+						break;
+
+					goto out_err;
+				}
 			}
 			idx++;
 		}
@@ -3139,16 +3145,22 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 							      seq, dev,
 							      filter_mask,
 							      NLM_F_MULTI);
-				if (err < 0 && err != -EOPNOTSUPP)
-					break;
+				if (err < 0 && err != -EOPNOTSUPP) {
+					if (likely(skb->len))
+						break;
+
+					goto out_err;
+				}
 			}
 			idx++;
 		}
 	}
+	err = skb->len;
+out_err:
 	rcu_read_unlock();
 	cb->args[0] = idx;
 
-	return skb->len;
+	return err;
 }
 
 static inline size_t bridge_nlmsg_size(void)
diff --git a/net/core/sock.c b/net/core/sock.c
index 4efaa3b6633d..39e9ab7c598e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1702,17 +1702,17 @@ EXPORT_SYMBOL(skb_set_owner_w);
 
 void skb_orphan_partial(struct sk_buff *skb)
 {
-	/* TCP stack sets skb->ooo_okay based on sk_wmem_alloc,
-	 * so we do not completely orphan skb, but transfert all
-	 * accounted bytes but one, to avoid unexpected reorders.
-	 */
 	if (skb->destructor == sock_wfree
 #ifdef CONFIG_INET
 	    || skb->destructor == tcp_wfree
 #endif
 		) {
-		atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc);
-		skb->truesize = 1;
+		struct sock *sk = skb->sk;
+
+		if (atomic_inc_not_zero(&sk->sk_refcnt)) {
+			atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
+			skb->destructor = sock_efree;
+		}
 	} else {
 		skb_orphan(skb);
 	}