Merge 4.4.107 into android-4.4

Changes in 4.4.107
	crypto: hmac - require that the underlying hash algorithm is unkeyed
	crypto: salsa20 - fix blkcipher_walk API usage
	autofs: fix careless error in recent commit
	tracing: Allocate mask_str buffer dynamically
	USB: uas and storage: Add US_FL_BROKEN_FUA for another JMicron JMS567 ID
	USB: core: prevent malicious bNumInterfaces overflow
	usbip: fix stub_send_ret_submit() vulnerability to null transfer_buffer
	ceph: drop negative child dentries before try pruning inode's alias
	Bluetooth: btusb: driver to enable the usb-wakeup feature
	xhci: Don't add a virt_dev to the devs array before it's fully allocated
	sched/rt: Do not pull from current CPU if only one CPU to pull
	dmaengine: dmatest: move callback wait queue to thread context
	ext4: fix fdatasync(2) after fallocate(2) operation
	ext4: fix crash when a directory's i_size is too small
	KEYS: add missing permission check for request_key() destination
	mac80211: Fix addition of mesh configuration element
	usb: phy: isp1301: Add OF device ID table
	md-cluster: free md_cluster_info if node leave cluster
	userfaultfd: shmem: __do_fault requires VM_FAULT_NOPAGE
	userfaultfd: selftest: vm: allow to build in vm/ directory
	net: initialize msg.msg_flags in recvfrom
	net: bcmgenet: correct the RBUF_OVFL_CNT and RBUF_ERR_CNT MIB values
	net: bcmgenet: correct MIB access of UniMAC RUNT counters
	net: bcmgenet: reserved phy revisions must be checked first
	net: bcmgenet: power down internal phy if open or resume fails
	net: bcmgenet: Power up the internal PHY before probing the MII
	NFSD: fix nfsd_minorversion(.., NFSD_AVAIL)
	NFSD: fix nfsd_reset_versions for NFSv4.
	Input: i8042 - add TUXEDO BU1406 (N24_25BU) to the nomux list
	drm/omap: fix dmabuf mmap for dma_alloc'ed buffers
	netfilter: bridge: honor frag_max_size when refragmenting
	writeback: fix memory leak in wb_queue_work()
	net: wimax/i2400m: fix NULL-deref at probe
	dmaengine: Fix array index out of bounds warning in __get_unmap_pool()
	net: Resend IGMP memberships upon peer notification.
	mlxsw: reg: Fix SPVM max record count
	mlxsw: reg: Fix SPVMLR max record count
	intel_th: pci: Add Gemini Lake support
	openrisc: fix issue handling 8 byte get_user calls
	scsi: hpsa: update check for logical volume status
	scsi: hpsa: limit outstanding rescans
	fjes: Fix wrong netdevice feature flags
	drm/radeon/si: add dpm quirk for Oland
	sched/deadline: Make sure the replenishment timer fires in the next period
	sched/deadline: Throttle a constrained deadline task activated after the deadline
	sched/deadline: Use deadline instead of period when calculating overflow
	mmc: mediatek: Fixed bug where clock frequency could be set wrong
	drm/radeon: reinstate oland workaround for sclk
	afs: Fix missing put_page()
	afs: Populate group ID from vnode status
	afs: Adjust mode bits processing
	afs: Flush outstanding writes when an fd is closed
	afs: Migrate vlocation fields to 64-bit
	afs: Prevent callback expiry timer overflow
	afs: Fix the maths in afs_fs_store_data()
	afs: Populate and use client modification time
	afs: Fix page leak in afs_write_begin()
	afs: Fix afs_kill_pages()
	net/mlx4_core: Avoid delays during VF driver device shutdown
	perf symbols: Fix symbols__fixup_end heuristic for corner cases
	efi/esrt: Cleanup bad memory map log messages
	NFSv4.1 respect server's max size in CREATE_SESSION
	btrfs: add missing memset while reading compressed inline extents
	target: Use system workqueue for ALUA transitions
	target: fix ALUA transition timeout handling
	target: fix race during implicit transition work flushes
	sfc: don't warn on successful change of MAC
	fbdev: controlfb: Add missing modes to fix out of bounds access
	video: udlfb: Fix read EDID timeout
	video: fbdev: au1200fb: Release some resources if a memory allocation fails
	video: fbdev: au1200fb: Return an error code if a memory allocation fails
	rtc: pcf8563: fix output clock rate
	dmaengine: ti-dma-crossbar: Correct am335x/am43xx mux value type
	PCI/PME: Handle invalid data when reading Root Status
	powerpc/powernv/cpufreq: Fix the frequency read by /proc/cpuinfo
	netfilter: ipvs: Fix inappropriate output of procfs
	powerpc/opal: Fix EBUSY bug in acquiring tokens
	powerpc/ipic: Fix status get and status clear
	target/iscsi: Fix a race condition in iscsit_add_reject_from_cmd()
	iscsi-target: fix memory leak in lio_target_tiqn_addtpg()
	target:fix condition return in core_pr_dump_initiator_port()
	target/file: Do not return error for UNMAP if length is zero
	arm-ccn: perf: Prevent module unload while PMU is in use
	crypto: tcrypt - fix buffer lengths in test_aead_speed()
	mm: Handle 0 flags in _calc_vm_trans() macro
	clk: mediatek: add the option for determining PLL source clock
	clk: imx6: refine hdmi_isfr's parent to make HDMI work on i.MX6 SoCs w/o VPU
	clk: tegra: Fix cclk_lp divisor register
	ppp: Destroy the mutex when cleanup
	thermal/drivers/step_wise: Fix temperature regulation misbehavior
	GFS2: Take inode off order_write list when setting jdata flag
	bcache: explicitly destroy mutex while exiting
	bcache: fix wrong cache_misses statistics
	l2tp: cleanup l2tp_tunnel_delete calls
	xfs: fix log block underflow during recovery cycle verification
	xfs: fix incorrect extent state in xfs_bmap_add_extent_unwritten_real
	PCI: Detach driver before procfs & sysfs teardown on device remove
	scsi: hpsa: cleanup sas_phy structures in sysfs when unloading
	scsi: hpsa: destroy sas transport properties before scsi_host
	powerpc/perf/hv-24x7: Fix incorrect comparison in memord
	tty fix oops when rmmod 8250
	usb: musb: da8xx: fix babble condition handling
	pinctrl: adi2: Fix Kconfig build problem
	raid5: Set R5_Expanded on parity devices as well as data.
	scsi: scsi_devinfo: Add REPORTLUN2 to EMC SYMMETRIX blacklist entry
	vt6655: Fix a possible sleep-in-atomic bug in vt6655_suspend
	scsi: sd: change manage_start_stop to bool in sysfs interface
	scsi: sd: change allow_restart to bool in sysfs interface
	scsi: bfa: integer overflow in debugfs
	udf: Avoid overflow when session starts at large offset
	macvlan: Only deliver one copy of the frame to the macvlan interface
	RDMA/cma: Avoid triggering undefined behavior
	IB/ipoib: Grab rtnl lock on heavy flush when calling ndo_open/stop
	ath9k: fix tx99 potential info leak
	Linux 4.4.107

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

3 files changed, 72 insertions, 27 deletions

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index cdf2a0b97611..0d0c8e954861 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -461,13 +461,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
  *
  * This function returns true if:
  *
- *   runtime / (deadline - t) > dl_runtime / dl_period ,
+ *   runtime / (deadline - t) > dl_runtime / dl_deadline ,
  *
  * IOW we can't recycle current parameters.
  *
- * Notice that the bandwidth check is done against the period. For
+ * Notice that the bandwidth check is done against the deadline. For
  * task with deadline equal to period this is the same of using
- * dl_deadline instead of dl_period in the equation above.
+ * dl_period instead of dl_deadline in the equation above.
  */
 static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 			       struct sched_dl_entity *pi_se, u64 t)
@@ -492,7 +492,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 	 * of anything below microseconds resolution is actually fiction
 	 * (but still we want to give the user that illusion >;).
 	 */
-	left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+	left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
 	right = ((dl_se->deadline - t) >> DL_SCALE) *
 		(pi_se->dl_runtime >> DL_SCALE);
 
@@ -533,10 +533,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
 	}
 }
 
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+	return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period;
+}
+
 /*
  * If the entity depleted all its runtime, and if we want it to sleep
  * while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
  * and try to activate it.
  *
  * Notice that it is important for the caller to know if the timer
@@ -558,7 +563,7 @@ static int start_dl_timer(struct task_struct *p)
 	 * that it is actually coming from rq->clock and not from
 	 * hrtimer's time base reading.
 	 */
-	act = ns_to_ktime(dl_se->deadline);
+	act = ns_to_ktime(dl_next_period(dl_se));
 	now = hrtimer_cb_get_time(timer);
 	delta = ktime_to_ns(now) - rq_clock(rq);
 	act = ktime_add_ns(act, delta);
@@ -722,6 +727,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 	timer->function = dl_task_timer;
 }
 
+/*
+ * During the activation, CBS checks if it can reuse the current task's
+ * runtime and period. If the deadline of the task is in the past, CBS
+ * cannot use the runtime, and so it replenishes the task. This rule
+ * works fine for implicit deadline tasks (deadline == period), and the
+ * CBS was designed for implicit deadline tasks. However, a task with
+ * constrained deadline (deadine < period) might be awakened after the
+ * deadline, but before the next period. In this case, replenishing the
+ * task would allow it to run for runtime / deadline. As in this case
+ * deadline < period, CBS enables a task to run for more than the
+ * runtime / period. In a very loaded system, this can cause a domino
+ * effect, making other tasks miss their deadlines.
+ *
+ * To avoid this problem, in the activation of a constrained deadline
+ * task after the deadline but before the next period, throttle the
+ * task and set the replenishing timer to the begin of the next period,
+ * unless it is boosted.
+ */
+static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+
+	if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+	    dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
+		if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+			return;
+		dl_se->dl_throttled = 1;
+	}
+}
+
 static
 int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
 {
@@ -979,6 +1015,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
 	__dequeue_dl_entity(dl_se);
 }
 
+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_deadline < dl_se->dl_period;
+}
+
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *pi_task = rt_mutex_get_top_task(p);
@@ -1005,6 +1046,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	}
 
 	/*
+	 * Check if a constrained deadline task was activated
+	 * after the deadline but before the next period.
+	 * If that is the case, the task will be throttled and
+	 * the replenishment timer will be set to the next period.
+	 */
+	if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
+		dl_check_constrained_dl(&p->dl);
+
+	/*
 	 * If p is throttled, we do nothing. In fact, if it exhausted
 	 * its budget it needs a replenishment and, since it now is on
 	 * its rq, the bandwidth timer callback (which clearly has not
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0af072f64e52..0f21b12332df 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2025,8 +2025,9 @@ static void pull_rt_task(struct rq *this_rq)
 	bool resched = false;
 	struct task_struct *p;
 	struct rq *src_rq;
+	int rt_overload_count = rt_overloaded(this_rq);
 
-	if (likely(!rt_overloaded(this_rq)))
+	if (likely(!rt_overload_count))
 		return;
 
 	/*
@@ -2035,6 +2036,11 @@ static void pull_rt_task(struct rq *this_rq)
 	 */
 	smp_rmb();
 
+	/* If we are the only overloaded CPU do nothing */
+	if (rt_overload_count == 1 &&
+	    cpumask_test_cpu(this_rq->cpu, this_rq->rd->rto_mask))
+		return;
+
 #ifdef HAVE_RT_PUSH_IPI
 	if (sched_feat(RT_PUSH_IPI)) {
 		tell_cpu_to_push(this_rq);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 23de746b2195..6d4ff15b8c0d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3430,37 +3430,30 @@ static const struct file_operations show_traces_fops = {
 	.llseek		= seq_lseek,
 };
 
-/*
- * The tracer itself will not take this lock, but still we want
- * to provide a consistent cpumask to user-space:
- */
-static DEFINE_MUTEX(tracing_cpumask_update_lock);
-
-/*
- * Temporary storage for the character representation of the
- * CPU bitmask (and one more byte for the newline):
- */
-static char mask_str[NR_CPUS + 1];
-
 static ssize_t
 tracing_cpumask_read(struct file *filp, char __user *ubuf,
 		     size_t count, loff_t *ppos)
 {
 	struct trace_array *tr = file_inode(filp)->i_private;
+	char *mask_str;
 	int len;
 
-	mutex_lock(&tracing_cpumask_update_lock);
+	len = snprintf(NULL, 0, "%*pb\n",
+		       cpumask_pr_args(tr->tracing_cpumask)) + 1;
+	mask_str = kmalloc(len, GFP_KERNEL);
+	if (!mask_str)
+		return -ENOMEM;
 
-	len = snprintf(mask_str, count, "%*pb\n",
+	len = snprintf(mask_str, len, "%*pb\n",
 		       cpumask_pr_args(tr->tracing_cpumask));
 	if (len >= count) {
 		count = -EINVAL;
 		goto out_err;
 	}
-	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
+	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
 
 out_err:
-	mutex_unlock(&tracing_cpumask_update_lock);
+	kfree(mask_str);
 
 	return count;
 }
@@ -3480,8 +3473,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	if (err)
 		goto err_unlock;
 
-	mutex_lock(&tracing_cpumask_update_lock);
-
 	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 	for_each_tracing_cpu(cpu) {
@@ -3504,8 +3495,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	local_irq_enable();
 
 	cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
-
-	mutex_unlock(&tracing_cpumask_update_lock);
 	free_cpumask_var(tracing_cpumask_new);
 
 	return count;