Merge tag 'v3.10.57' into update

This is the 3.10.57 stable release

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 10
-SUBLEVEL = 56
+SUBLEVEL = 57
 EXTRAVERSION =
 NAME = TOSSUG Baby Fish
 

drivers/block/drbd/drbd_nl.c

@@ -514,6 +514,12 @@ void conn_try_outdate_peer_async(struct drbd_tconn *tconn)
 	struct task_struct *opa;
 
 	kref_get(&tconn->kref);
+	/* We may just have force_sig()'ed this thread
+	 * to get it out of some blocking network function.
+	 * Clear signals; otherwise kthread_run(), which internally uses
+	 * wait_on_completion_killable(), will mistake our pending signal
+	 * for a new fatal signal and fail. */
+	flush_signals(current);
 	opa = kthread_run(_try_outdate_peer_async, tconn, "drbd_async_h");
 	if (IS_ERR(opa)) {
 		conn_err(tconn, "out of mem, failed to invoke fence-peer helper\n");

drivers/cpufreq/cpufreq_governor.c

@@ -65,7 +65,7 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 
 	policy = cdbs->cur_policy;
 
-	/* Get Absolute Load (in terms of freq for ondemand gov) */
+	/* Get Absolute Load */
 	for_each_cpu(j, policy->cpus) {
 		struct cpu_dbs_common_info *j_cdbs;
 		u64 cur_wall_time, cur_idle_time;

drivers/cpufreq/cpufreq_governor.h

@@ -183,7 +183,6 @@ struct od_dbs_tuners {
 	unsigned int sampling_rate;
 	unsigned int sampling_down_factor;
 	unsigned int up_threshold;
-	unsigned int adj_up_threshold;
 	unsigned int powersave_bias;
 	unsigned int io_is_busy;
 };

drivers/cpufreq/cpufreq_ondemand.c

@@ -29,11 +29,9 @@
 #include "cpufreq_governor.h"
 
 /* On-demand governor macros */
-#define DEF_FREQUENCY_DOWN_DIFFERENTIAL		(10)
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(100000)
-#define MICRO_FREQUENCY_DOWN_DIFFERENTIAL	(3)
 #define MICRO_FREQUENCY_UP_THRESHOLD		(95)
 #define MICRO_FREQUENCY_MIN_SAMPLE_RATE		(10000)
 #define MIN_FREQUENCY_UP_THRESHOLD		(11)
@@ -161,14 +159,10 @@ static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
 
 /*
  * Every sampling_rate, we check, if current idle time is less than 20%
- * (default), then we try to increase frequency. Every sampling_rate, we look
+ * (default), then we try to increase frequency. Else, we adjust the frequency
- * for the lowest frequency which can sustain the load while keeping idle time
+ * proportional to load.
- * over 30%. If such a frequency exist, we try to decrease to this frequency.
- *
- * Any frequency increase takes it to the maximum frequency. Frequency reduction
- * happens at minimum steps of 5% (default) of current frequency
  */
-static void od_check_cpu(int cpu, unsigned int load_freq)
+static void od_check_cpu(int cpu, unsigned int load)
 {
 	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
@@ -178,29 +172,17 @@ static void od_check_cpu(int cpu, unsigned int load_freq)
 	dbs_info->freq_lo = 0;
 
 	/* Check for frequency increase */
-	if (load_freq > od_tuners->up_threshold * policy->cur) {
+	if (load > od_tuners->up_threshold) {
 		/* If switching to max speed, apply sampling_down_factor */
 		if (policy->cur < policy->max)
 			dbs_info->rate_mult =
 				od_tuners->sampling_down_factor;
 		dbs_freq_increase(policy, policy->max);
 		return;
-	}
+	} else {
-
+		/* Calculate the next frequency proportional to load */
-	/* Check for frequency decrease */
-	/* if we cannot reduce the frequency anymore, break out early */
-	if (policy->cur == policy->min)
-		return;
-
-	/*
-	 * The optimal frequency is the frequency that is the lowest that can
-	 * support the current CPU usage without triggering the up policy. To be
-	 * safe, we focus 10 points under the threshold.
-	 */
-	if (load_freq < od_tuners->adj_up_threshold
-			* policy->cur) {
 		unsigned int freq_next;
-		freq_next = load_freq / od_tuners->adj_up_threshold;
+		freq_next = load * policy->cpuinfo.max_freq / 100;
 
 		/* No longer fully busy, reset rate_mult */
 		dbs_info->rate_mult = 1;
@@ -374,9 +356,6 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 			input < MIN_FREQUENCY_UP_THRESHOLD) {
 		return -EINVAL;
 	}
-	/* Calculate the new adj_up_threshold */
-	od_tuners->adj_up_threshold += input;
-	od_tuners->adj_up_threshold -= od_tuners->up_threshold;
 
 	od_tuners->up_threshold = input;
 	return count;
@@ -525,8 +504,6 @@ static int od_init(struct dbs_data *dbs_data)
 	if (idle_time != -1ULL) {
 		/* Idle micro accounting is supported. Use finer thresholds */
 		tuners->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
-		tuners->adj_up_threshold = MICRO_FREQUENCY_UP_THRESHOLD -
-			MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
 		/*
 		 * In nohz/micro accounting case we set the minimum frequency
 		 * not depending on HZ, but fixed (very low). The deferred
@@ -535,8 +512,6 @@ static int od_init(struct dbs_data *dbs_data)
 		dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
 	} else {
 		tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
-		tuners->adj_up_threshold = DEF_FREQUENCY_UP_THRESHOLD -
-			DEF_FREQUENCY_DOWN_DIFFERENTIAL;
 
 		/* For correct statistics, we need 10 ticks for each measure */
 		dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *

drivers/cpufreq/cpufreq_stats.c

@@ -107,7 +107,7 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 	for (i = 0; i < stat->state_num; i++) {
 		len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i],
 			(unsigned long long)
-			cputime64_to_clock_t(stat->time_in_state[i]));
+			jiffies_64_to_clock_t(stat->time_in_state[i]));
 	}
 	return len;
 }

drivers/md/raid5.c

@@ -60,6 +60,10 @@
 #include "raid0.h"
 #include "bitmap.h"
 
+static bool devices_handle_discard_safely = false;
+module_param(devices_handle_discard_safely, bool, 0644);
+MODULE_PARM_DESC(devices_handle_discard_safely,
+		 "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
 /*
  * Stripe cache
  */
@@ -5611,7 +5615,7 @@ static int run(struct mddev *mddev)
 		mddev->queue->limits.discard_granularity = stripe;
 		/*
 		 * unaligned part of discard request will be ignored, so can't
-		 * guarantee discard_zerors_data
+		 * guarantee discard_zeroes_data
 		 */
 		mddev->queue->limits.discard_zeroes_data = 0;
 
@@ -5636,6 +5640,18 @@ static int run(struct mddev *mddev)
 			    !bdev_get_queue(rdev->bdev)->
 						limits.discard_zeroes_data)
 				discard_supported = false;
+			/* Unfortunately, discard_zeroes_data is not currently
+			 * a guarantee - just a hint.  So we only allow DISCARD
+			 * if the sysadmin has confirmed that only safe devices
+			 * are in use by setting a module parameter.
+			 */
+			if (!devices_handle_discard_safely) {
+				if (discard_supported) {
+					pr_info("md/raid456: discard support disabled due to uncertainty.\n");
+					pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n");
+				}
+				discard_supported = false;
+			}
 		}
 
 		if (discard_supported &&

drivers/media/v4l2-core/videobuf2-core.c

@@ -666,6 +666,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 	 * to the userspace.
 	 */
 	req->count = allocated_buffers;
+	q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 
 	return 0;
 }
@@ -714,6 +715,7 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create
 		memset(q->plane_sizes, 0, sizeof(q->plane_sizes));
 		memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx));
 		q->memory = create->memory;
+		q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 	}
 
 	num_buffers = min(create->count, VIDEO_MAX_FRAME - q->num_buffers);
@@ -1355,6 +1357,7 @@ int vb2_qbuf(struct vb2_queue *q, struct v4l2_buffer *b)
 	 * dequeued in dqbuf.
 	 */
 	list_add_tail(&vb->queued_entry, &q->queued_list);
+	q->waiting_for_buffers = false;
 	vb->state = VB2_BUF_STATE_QUEUED;
 
 	/*
@@ -1724,6 +1727,7 @@ int vb2_streamoff(struct vb2_queue *q, enum v4l2_buf_type type)
 	 * and videobuf, effectively returning control over them to userspace.
 	 */
 	__vb2_queue_cancel(q);
+	q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 
 	dprintk(3, "Streamoff successful\n");
 	return 0;
@@ -2009,9 +2013,16 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait)
 	}
 
 	/*
-	 * There is nothing to wait for if no buffers have already been queued.
+	 * There is nothing to wait for if the queue isn't streaming.
 	 */
-	if (list_empty(&q->queued_list))
+	if (!vb2_is_streaming(q))
+		return res | POLLERR;
+	/*
+	 * For compatibility with vb1: if QBUF hasn't been called yet, then
+	 * return POLLERR as well. This only affects capture queues, output
+	 * queues will always initialize waiting_for_buffers to false.
+	 */
+	if (q->waiting_for_buffers)
 		return res | POLLERR;
 
 	if (list_empty(&q->done_list))

fs/udf/inode.c

@@ -1270,13 +1270,22 @@ update_time:
 	return 0;
 }
 
+/*
+ * Maximum length of linked list formed by ICB hierarchy. The chosen number is
+ * arbitrary - just that we hopefully don't limit any real use of rewritten
+ * inode on write-once media but avoid looping for too long on corrupted media.
+ */
+#define UDF_MAX_ICB_NESTING 1024
+
 static void __udf_read_inode(struct inode *inode)
 {
 	struct buffer_head *bh = NULL;
 	struct fileEntry *fe;
 	uint16_t ident;
 	struct udf_inode_info *iinfo = UDF_I(inode);
+	unsigned int indirections = 0;
 
+reread:
 	/*
 	 * Set defaults, but the inode is still incomplete!
 	 * Note: get_new_inode() sets the following on a new inode:
@@ -1313,28 +1322,26 @@ static void __udf_read_inode(struct inode *inode)
 		ibh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 1,
 					&ident);
 		if (ident == TAG_IDENT_IE && ibh) {
-			struct buffer_head *nbh = NULL;
 			struct kernel_lb_addr loc;
 			struct indirectEntry *ie;
 
 			ie = (struct indirectEntry *)ibh->b_data;
 			loc = lelb_to_cpu(ie->indirectICB.extLocation);
 
-			if (ie->indirectICB.extLength &&
+			if (ie->indirectICB.extLength) {
-				(nbh = udf_read_ptagged(inode->i_sb, &loc, 0,
+				brelse(bh);
-							&ident))) {
+				brelse(ibh);
-				if (ident == TAG_IDENT_FE ||
+				memcpy(&iinfo->i_location, &loc,
-					ident == TAG_IDENT_EFE) {
+				       sizeof(struct kernel_lb_addr));
-					memcpy(&iinfo->i_location,
+				if (++indirections > UDF_MAX_ICB_NESTING) {
-						&loc,
+					udf_err(inode->i_sb,
-						sizeof(struct kernel_lb_addr));
+						"too many ICBs in ICB hierarchy"
-					brelse(bh);
+						" (max %d supported)\n",
-					brelse(ibh);
+						UDF_MAX_ICB_NESTING);
-					brelse(nbh);
+					make_bad_inode(inode);
-					__udf_read_inode(inode);
 					return;
 				}
-				brelse(nbh);
+				goto reread;
 			}
 		}
 		brelse(ibh);

include/linux/jiffies.h

@@ -254,23 +254,11 @@ extern unsigned long preset_lpj;
 #define SEC_JIFFIE_SC (32 - SHIFT_HZ)
 #endif
 #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29)
-#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19)
 #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\
                                 TICK_NSEC -1) / (u64)TICK_NSEC))
 
 #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\
                                         TICK_NSEC -1) / (u64)TICK_NSEC))
-#define USEC_CONVERSION  \
-                    ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\
-                                        TICK_NSEC -1) / (u64)TICK_NSEC))
-/*
- * USEC_ROUND is used in the timeval to jiffie conversion.  See there
- * for more details.  It is the scaled resolution rounding value.  Note
- * that it is a 64-bit value.  Since, when it is applied, we are already
- * in jiffies (albit scaled), it is nothing but the bits we will shift
- * off.
- */
-#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1)
 /*
  * The maximum jiffie value is (MAX_INT >> 1).  Here we translate that
  * into seconds.  The 64-bit case will overflow if we are not careful,

include/media/videobuf2-core.h

@@ -318,6 +318,9 @@ struct v4l2_fh;
  * @done_wq:	waitqueue for processes waiting for buffers ready to be dequeued
  * @alloc_ctx:	memory type/allocator-specific contexts for each plane
  * @streaming:	current streaming state
+ * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for
+ *		buffers. Only set for capture queues if qbuf has not yet been
+ *		called since poll() needs to return POLLERR in that situation.
  * @fileio:	file io emulator internal data, used only if emulator is active
  */
 struct vb2_queue {
@@ -350,6 +353,7 @@ struct vb2_queue {
 	unsigned int			plane_sizes[VIDEO_MAX_PLANES];
 
 	unsigned int			streaming:1;
+	unsigned int			waiting_for_buffers:1;
 
 	struct vb2_fileio_data		*fileio;
 };

init/Kconfig

@@ -1376,6 +1376,7 @@ config FUTEX
 
 config HAVE_FUTEX_CMPXCHG
 	bool
+	depends on FUTEX
 	help
 	  Architectures should select this if futex_atomic_cmpxchg_inatomic()
 	  is implemented and always working. This removes a couple of runtime

kernel/events/core.c

@@ -7479,8 +7479,10 @@ int perf_event_init_task(struct task_struct *child)
 
 	for_each_task_context_nr(ctxn) {
 		ret = perf_event_init_context(child, ctxn);
-		if (ret)
+		if (ret) {
+			perf_event_free_task(child);
 			return ret;
+		}
 	}
 
 	return 0;

kernel/fork.c

@@ -1428,7 +1428,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_policy;
 	retval = audit_alloc(p);
 	if (retval)
-		goto bad_fork_cleanup_policy;
+		goto bad_fork_cleanup_perf;
 	/* copy all the process information */
 	retval = copy_semundo(clone_flags, p);
 	if (retval)
@@ -1635,8 +1635,9 @@ bad_fork_cleanup_semundo:
 	exit_sem(p);
 bad_fork_cleanup_audit:
 	audit_free(p);
-bad_fork_cleanup_policy:
+bad_fork_cleanup_perf:
 	perf_event_free_task(p);
+bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:

kernel/time.c

@@ -496,17 +496,20 @@ EXPORT_SYMBOL(usecs_to_jiffies);
  * that a remainder subtract here would not do the right thing as the
  * resolution values don't fall on second boundries.  I.e. the line:
  * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ * Note that due to the small error in the multiplier here, this
+ * rounding is incorrect for sufficiently large values of tv_nsec, but
+ * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
+ * OK.
  *
  * Rather, we just shift the bits off the right.
  *
  * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
  * value to a scaled second value.
  */
-unsigned long
+static unsigned long
-timespec_to_jiffies(const struct timespec *value)
+__timespec_to_jiffies(unsigned long sec, long nsec)
 {
-	unsigned long sec = value->tv_sec;
+	nsec = nsec + TICK_NSEC - 1;
-	long nsec = value->tv_nsec + TICK_NSEC - 1;
 
 	if (sec >= MAX_SEC_IN_JIFFIES){
 		sec = MAX_SEC_IN_JIFFIES;
@@ -517,6 +520,13 @@ timespec_to_jiffies(const struct timespec *value)
 		 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
 
 }
+
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+	return __timespec_to_jiffies(value->tv_sec, value->tv_nsec);
+}
+
 EXPORT_SYMBOL(timespec_to_jiffies);
 
 void
@@ -533,31 +543,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
 }
 EXPORT_SYMBOL(jiffies_to_timespec);
 
-/* Same for "timeval"
+/*
+ * We could use a similar algorithm to timespec_to_jiffies (with a
+ * different multiplier for usec instead of nsec). But this has a
+ * problem with rounding: we can't exactly add TICK_NSEC - 1 to the
+ * usec value, since it's not necessarily integral.
  *
- * Well, almost.  The problem here is that the real system resolution is
+ * We could instead round in the intermediate scaled representation
- * in nanoseconds and the value being converted is in micro seconds.
+ * (i.e. in units of 1/2^(large scale) jiffies) but that's also
- * Also for some machines (those that use HZ = 1024, in-particular),
+ * perilous: the scaling introduces a small positive error, which
- * there is a LARGE error in the tick size in microseconds.
+ * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1
-
+ * units to the intermediate before shifting) leads to accidental
- * The solution we use is to do the rounding AFTER we convert the
+ * overflow and overestimates.
- * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
+ *
- * Instruction wise, this should cost only an additional add with carry
+ * At the cost of one additional multiplication by a constant, just
- * instruction above the way it was done above.
+ * use the timespec implementation.
  */
 unsigned long
 timeval_to_jiffies(const struct timeval *value)
 {
-	unsigned long sec = value->tv_sec;
+	return __timespec_to_jiffies(value->tv_sec,
-	long usec = value->tv_usec;
+				     value->tv_usec * NSEC_PER_USEC);
-
-	if (sec >= MAX_SEC_IN_JIFFIES){
-		sec = MAX_SEC_IN_JIFFIES;
-		usec = 0;
-	}
-	return (((u64)sec * SEC_CONVERSION) +
-		(((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
-		 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
 }
 EXPORT_SYMBOL(timeval_to_jiffies);
 

kernel/trace/ring_buffer.c

@@ -3399,7 +3399,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 	iter->head = cpu_buffer->reader_page->read;
 
 	iter->cache_reader_page = iter->head_page;
-	iter->cache_read = iter->head;
+	iter->cache_read = cpu_buffer->read;
 
 	if (iter->head)
 		iter->read_stamp = cpu_buffer->read_stamp;

mm/huge_memory.c

@@ -1733,21 +1733,24 @@ static int __split_huge_page_map(struct page *page,
 	if (pmd) {
 		pgtable = pgtable_trans_huge_withdraw(mm);
 		pmd_populate(mm, &_pmd, pgtable);
+		if (pmd_write(*pmd))
+			BUG_ON(page_mapcount(page) != 1);
 
 		haddr = address;
 		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
 			pte_t *pte, entry;
 			BUG_ON(PageCompound(page+i));
+			/*
+			 * Note that pmd_numa is not transferred deliberately
+			 * to avoid any possibility that pte_numa leaks to
+			 * a PROT_NONE VMA by accident.
+			 */
 			entry = mk_pte(page + i, vma->vm_page_prot);
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 			if (!pmd_write(*pmd))
 				entry = pte_wrprotect(entry);
-			else
-				BUG_ON(page_mapcount(page) != 1);
 			if (!pmd_young(*pmd))
 				entry = pte_mkold(entry);
-			if (pmd_numa(*pmd))
-				entry = pte_mknuma(entry);
 			pte = pte_offset_map(&_pmd, haddr);
 			BUG_ON(!pte_none(*pte));
 			set_pte_at(mm, haddr, pte, entry);

net/wireless/nl80211.c

@@ -6642,6 +6642,9 @@ void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp)
 	void *hdr = ((void **)skb->cb)[1];
 	struct nlattr *data = ((void **)skb->cb)[2];
 
+	/* clear CB data for netlink core to own from now on */
+	memset(skb->cb, 0, sizeof(skb->cb));
+
 	nla_nest_end(skb, data);
 	genlmsg_end(skb, hdr);