Merge 4.4.163 into android-4.4-p

Changes in 4.4.163
	xfrm: Validate address prefix lengths in the xfrm selector.
	xfrm6: call kfree_skb when skb is toobig
	mac80211: Always report TX status
	cfg80211: reg: Init wiphy_idx in regulatory_hint_core()
	ARM: 8799/1: mm: fix pci_ioremap_io() offset check
	xfrm: validate template mode
	mac80211_hwsim: do not omit multicast announce of first added radio
	Bluetooth: SMP: fix crash in unpairing
	pxa168fb: prepare the clock
	asix: Check for supported Wake-on-LAN modes
	ax88179_178a: Check for supported Wake-on-LAN modes
	lan78xx: Check for supported Wake-on-LAN modes
	sr9800: Check for supported Wake-on-LAN modes
	r8152: Check for supported Wake-on-LAN Modes
	smsc75xx: Check for Wake-on-LAN modes
	smsc95xx: Check for Wake-on-LAN modes
	perf/ring_buffer: Prevent concurent ring buffer access
	net: cxgb3_main: fix a missing-check bug
	KEYS: put keyring if install_session_keyring_to_cred() fails
	ipv6: suppress sparse warnings in IP6_ECN_set_ce()
	net: drop write-only stack variable
	ser_gigaset: use container_of() instead of detour
	tracing: Skip more functions when doing stack tracing of events
	ARM: dts: apq8064: add ahci ports-implemented mask
	x86/mm/pat: Prevent hang during boot when mapping pages
	radix-tree: fix radix_tree_iter_retry() for tagged iterators.
	af_iucv: Move sockaddr length checks to before accessing sa_family in bind and connect handlers
	net/mlx4_en: Resolve dividing by zero in 32-bit system
	ipv6: orphan skbs in reassembly unit
	um: Avoid longjmp/setjmp symbol clashes with libpthread.a
	sched/cgroup: Fix cgroup entity load tracking tear-down
	btrfs: don't create or leak aliased root while cleaning up orphans
	thermal: allow spear-thermal driver to be a module
	thermal: allow u8500-thermal driver to be a module
	tpm: fix: return rc when devm_add_action() fails
	x86/PCI: Mark Broadwell-EP Home Agent 1 as having non-compliant BARs
	aacraid: Start adapter after updating number of MSIX vectors
	perf/core: Don't leak event in the syscall error path
	usbvision: revert commit 588afcc1
	MIPS: Fix FCSR Cause bit handling for correct SIGFPE issue
	ASoC: ak4613: Enable cache usage to fix crashes on resume
	ASoC: wm8940: Enable cache usage to fix crashes on resume
	CIFS: handle guest access errors to Windows shares
	arm64: Fix potential race with hardware DBM in ptep_set_access_flags()
	xfrm: Clear sk_dst_cache when applying per-socket policy.
	scsi: Add STARGET_CREATED_REMOVE state to scsi_target_state
	sparc/pci: Refactor dev_archdata initialization into pci_init_dev_archdata
	sch_red: update backlog as well
	usb-storage: fix bogus hardware error messages for ATA pass-thru devices
	bpf: generally move prog destruction to RCU deferral
	drm/nouveau/fbcon: fix oops without fbdev emulation
	fuse: Dont call set_page_dirty_lock() for ITER_BVEC pages for async_dio
	ixgbevf: Fix handling of NAPI budget when multiple queues are enabled per vector
	net/mlx5e: Fix LRO modify
	net/mlx5e: Correctly handle RSS indirection table when changing number of channels
	ixgbe: fix RSS limit for X550
	ixgbe: Correct X550EM_x revision check
	ALSA: timer: Fix zero-division by continue of uninitialized instance
	vti6: flush x-netns xfrm cache when vti interface is removed
	gro: Allow tunnel stacking in the case of FOU/GUE
	brcmfmac: Fix glom_skb leak in brcmf_sdiod_recv_chain
	l2tp: hold socket before dropping lock in l2tp_ip{, 6}_recv()
	tty: serial: sprd: fix error return code in sprd_probe()
	video: fbdev: pxa3xx_gcu: fix error return code in pxa3xx_gcu_probe()
	sparc64 mm: Fix more TSB sizing issues
	gpu: host1x: fix error return code in host1x_probe()
	sparc64: Fix exception handling in UltraSPARC-III memcpy.
	gpio: msic: fix error return code in platform_msic_gpio_probe()
	usb: imx21-hcd: fix error return code in imx21_probe()
	usb: ehci-omap: fix error return code in ehci_hcd_omap_probe()
	usb: dwc3: omap: fix error return code in dwc3_omap_probe()
	spi/bcm63xx-hspi: fix error return code in bcm63xx_hsspi_probe()
	MIPS: Handle non word sized instructions when examining frame
	spi/bcm63xx: fix error return code in bcm63xx_spi_probe()
	spi: xlp: fix error return code in xlp_spi_probe()
	ASoC: spear: fix error return code in spdif_in_probe()
	PM / devfreq: tegra: fix error return code in tegra_devfreq_probe()
	bonding: avoid defaulting hard_header_len to ETH_HLEN on slave removal
	scsi: aacraid: Fix typo in blink status
	MIPS: microMIPS: Fix decoding of swsp16 instruction
	igb: Remove superfluous reset to PHY and page 0 selection
	MIPS: DEC: Fix an int-handler.S CPU_DADDI_WORKAROUNDS regression
	ARM: dts: imx53-qsb: disable 1.2GHz OPP
	fs/fat/fatent.c: add cond_resched() to fat_count_free_clusters()
	mtd: spi-nor: Add support for is25wp series chips
	perf tools: Disable parallelism for 'make clean'
	bridge: do not add port to router list when receives query with source 0.0.0.0
	net: bridge: remove ipv6 zero address check in mcast queries
	ipv6: mcast: fix a use-after-free in inet6_mc_check
	ipv6/ndisc: Preserve IPv6 control buffer if protocol error handlers are called
	net/ipv6: Fix index counter for unicast addresses in in6_dump_addrs
	net: sched: gred: pass the right attribute to gred_change_table_def()
	net: socket: fix a missing-check bug
	net: stmmac: Fix stmmac_mdio_reset() when building stmmac as modules
	r8169: fix NAPI handling under high load
	sctp: fix race on sctp_id2asoc
	net: drop skb on failure in ip_check_defrag()
	vhost: Fix Spectre V1 vulnerability
	rtnetlink: Disallow FDB configuration for non-Ethernet device
	mremap: properly flush TLB before releasing the page
	crypto: shash - Fix a sleep-in-atomic bug in shash_setkey_unaligned
	ahci: don't ignore result code of ahci_reset_controller()
	cachefiles: fix the race between cachefiles_bury_object() and rmdir(2)
	ptp: fix Spectre v1 vulnerability
	RDMA/ucma: Fix Spectre v1 vulnerability
	IB/ucm: Fix Spectre v1 vulnerability
	cdc-acm: correct counting of UART states in serial state notification
	usb: gadget: storage: Fix Spectre v1 vulnerability
	USB: fix the usbfs flag sanitization for control transfers
	Input: elan_i2c - add ACPI ID for Lenovo IdeaPad 330-15IGM
	sched/fair: Fix throttle_list starvation with low CFS quota
	x86/percpu: Fix this_cpu_read()
	cpuidle: Do not access cpuidle_devices when !CONFIG_CPU_IDLE
	l2tp: hold tunnel socket when handling control frames in l2tp_ip and l2tp_ip6
	x86/time: Correct the attribute on jiffies' definition
	Linux 4.4.163

Change-Id: Ic88925a69ebd358554c032f243219ff0b9b73e0d
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

8 files changed, 71 insertions, 39 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 0eb11b4ac4c7..daa4e0782cf7 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -270,9 +270,7 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
 
 static void prog_fd_array_put_ptr(void *ptr)
 {
-	struct bpf_prog *prog = ptr;
-
-	bpf_prog_put_rcu(prog);
+	bpf_prog_put(ptr);
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4b9bbfe764e8..04fc1022ad9f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -487,7 +487,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
 	free_uid(user);
 }
 
-static void __prog_put_common(struct rcu_head *rcu)
+static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 {
 	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
 
@@ -496,17 +496,10 @@ static void __prog_put_common(struct rcu_head *rcu)
 	bpf_prog_free(aux->prog);
 }
 
-/* version of bpf_prog_put() that is called after a grace period */
-void bpf_prog_put_rcu(struct bpf_prog *prog)
-{
-	if (atomic_dec_and_test(&prog->aux->refcnt))
-		call_rcu(&prog->aux->rcu, __prog_put_common);
-}
-
 void bpf_prog_put(struct bpf_prog *prog)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt))
-		__prog_put_common(&prog->aux->rcu);
+		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_put);
 
@@ -514,7 +507,7 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
 {
 	struct bpf_prog *prog = filp->private_data;
 
-	bpf_prog_put_rcu(prog);
+	bpf_prog_put(prog);
 	return 0;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bfed031c5beb..0f9ada220789 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7023,6 +7023,8 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
 			goto unlock;
 
 		list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+			if (event->cpu != smp_processor_id())
+				continue;
 			if (event->attr.type != PERF_TYPE_TRACEPOINT)
 				continue;
 			if (event->attr.config != entry->type)
@@ -7144,7 +7146,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 	prog = event->tp_event->prog;
 	if (prog && event->tp_event->bpf_prog_owner == event) {
 		event->tp_event->prog = NULL;
-		bpf_prog_put_rcu(prog);
+		bpf_prog_put(prog);
 	}
 }
 
@@ -8538,6 +8540,7 @@ SYSCALL_DEFINE5(perf_event_open,
 					f_flags);
 	if (IS_ERR(event_file)) {
 		err = PTR_ERR(event_file);
+		event_file = NULL;
 		goto err_context;
 	}
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0c1b195a2aaf..d6a90c8bfedc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8144,11 +8144,9 @@ void sched_destroy_group(struct task_group *tg)
 void sched_offline_group(struct task_group *tg)
 {
 	unsigned long flags;
-	int i;
 
 	/* end participation in shares distribution */
-	for_each_possible_cpu(i)
-		unregister_fair_sched_group(tg, i);
+	unregister_fair_sched_group(tg);
 
 	spin_lock_irqsave(&task_group_lock, flags);
 	list_del_rcu(&tg->list);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ccf212fcd5bf..54cf946d1a4c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4104,9 +4104,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 	/*
 	 * Add to the _head_ of the list, so that an already-started
-	 * distribute_cfs_runtime will not see us
+	 * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is
+	 * not running add to the tail so that later runqueues don't get starved.
 	 */
-	list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+	if (cfs_b->distribute_running)
+		list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+	else
+		list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
 
 	/*
 	 * If we're the first throttled task, make sure the bandwidth
@@ -4249,14 +4253,16 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	 * in us over-using our runtime if it is all used during this loop, but
 	 * only by limited amounts in that extreme case.
 	 */
-	while (throttled && cfs_b->runtime > 0) {
+	while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) {
 		runtime = cfs_b->runtime;
+		cfs_b->distribute_running = 1;
 		raw_spin_unlock(&cfs_b->lock);
 		/* we can't nest cfs_b->lock while distributing bandwidth */
 		runtime = distribute_cfs_runtime(cfs_b, runtime,
 						 runtime_expires);
 		raw_spin_lock(&cfs_b->lock);
 
+		cfs_b->distribute_running = 0;
 		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
 
 		cfs_b->runtime -= min(runtime, cfs_b->runtime);
@@ -4367,6 +4373,11 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 
 	/* confirm we're still not at a refresh boundary */
 	raw_spin_lock(&cfs_b->lock);
+	if (cfs_b->distribute_running) {
+		raw_spin_unlock(&cfs_b->lock);
+		return;
+	}
+
 	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
 		raw_spin_unlock(&cfs_b->lock);
 		return;
@@ -4376,6 +4387,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 		runtime = cfs_b->runtime;
 
 	expires = cfs_b->runtime_expires;
+	if (runtime)
+		cfs_b->distribute_running = 1;
+
 	raw_spin_unlock(&cfs_b->lock);
 
 	if (!runtime)
@@ -4386,6 +4400,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 	raw_spin_lock(&cfs_b->lock);
 	if (expires == cfs_b->runtime_expires)
 		cfs_b->runtime -= min(runtime, cfs_b->runtime);
+	cfs_b->distribute_running = 0;
 	raw_spin_unlock(&cfs_b->lock);
 }
 
@@ -4497,6 +4512,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	cfs_b->period_timer.function = sched_cfs_period_timer;
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
+	cfs_b->distribute_running = 0;
 }
 
 static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
@@ -10265,11 +10281,8 @@ void free_fair_sched_group(struct task_group *tg)
 	for_each_possible_cpu(i) {
 		if (tg->cfs_rq)
 			kfree(tg->cfs_rq[i]);
-		if (tg->se) {
-			if (tg->se[i])
-				remove_entity_load_avg(tg->se[i]);
+		if (tg->se)
 			kfree(tg->se[i]);
-		}
 	}
 
 	kfree(tg->cfs_rq);
@@ -10324,21 +10337,29 @@ err:
 	return 0;
 }
 
-void unregister_fair_sched_group(struct task_group *tg, int cpu)
+void unregister_fair_sched_group(struct task_group *tg)
 {
-	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
+	struct rq *rq;
+	int cpu;
 
-	/*
-	* Only empty task groups can be destroyed; so we can speculatively
-	* check on_list without danger of it being re-added.
-	*/
-	if (!tg->cfs_rq[cpu]->on_list)
-		return;
+	for_each_possible_cpu(cpu) {
+		if (tg->se[cpu])
+			remove_entity_load_avg(tg->se[cpu]);
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+		/*
+		 * Only empty task groups can be destroyed; so we can speculatively
+		 * check on_list without danger of it being re-added.
+		 */
+		if (!tg->cfs_rq[cpu]->on_list)
+			continue;
+
+		rq = cpu_rq(cpu);
+
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	}
 }
 
 void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
@@ -10422,7 +10443,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	return 1;
 }
 
-void unregister_fair_sched_group(struct task_group *tg, int cpu) { }
+void unregister_fair_sched_group(struct task_group *tg) { }
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 917c94abf5bb..cc0975f94a8d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -133,7 +133,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
  */
 static void cpuidle_idle_call(void)
 {
-	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_device *dev = cpuidle_get_device();
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 	int next_state, entered_state;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d9ad549591d8..7f18a3243af5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -235,6 +235,8 @@ struct cfs_bandwidth {
 	/* statistics */
 	int nr_periods, nr_throttled;
 	u64 throttled_time;
+
+	bool distribute_running;
 #endif
 };
 
@@ -310,7 +312,7 @@ extern int tg_nop(struct task_group *tg, void *data);
 
 extern void free_fair_sched_group(struct task_group *tg);
 extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
-extern void unregister_fair_sched_group(struct task_group *tg, int cpu);
+extern void unregister_fair_sched_group(struct task_group *tg);
 extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 			struct sched_entity *se, int cpu,
 			struct sched_entity *parent);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a3a3dd833fcf..eb1ac8faac16 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1778,7 +1778,17 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 {
 	__buffer_unlock_commit(buffer, event);
 
-	ftrace_trace_stack(tr, buffer, flags, 0, pc, regs);
+	/*
+	 * If regs is not set, then skip the following callers:
+	 *   trace_buffer_unlock_commit_regs
+	 *   event_trigger_unlock_commit
+	 *   trace_event_buffer_commit
+	 *   trace_event_raw_event_sched_switch
+	 * Note, we can still get here via blktrace, wakeup tracer
+	 * and mmiotrace, but that's ok if they lose a function or
+	 * two. They are that meaningful.
+	 */
+	ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs);
 	ftrace_trace_userstack(buffer, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs);
@@ -1837,6 +1847,13 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	trace.skip		= skip;
 
 	/*
+	 * Add two, for this function and the call to save_stack_trace()
+	 * If regs is set, then these functions will not be in the way.
+	 */
+	if (!regs)
+		trace.skip += 2;
+
+	/*
 	 * Since events can happen in NMIs there's no safe way to
 	 * use the per cpu ftrace_stacks. We reserve it and if an interrupt
 	 * or NMI comes in, it will just have to use the default