Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

All three conflicts were cases of simple overlapping
changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

12 files changed, 178 insertions, 53 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1903b8f..3cfabdf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -242,18 +242,6 @@ unlock:
 	return ret;
 }
 
-static void event_function_local(struct perf_event *event, event_f func, void *data)
-{
-	struct event_function_struct efs = {
-		.event = event,
-		.func = func,
-		.data = data,
-	};
-
-	int ret = event_function(&efs);
-	WARN_ON_ONCE(ret);
-}
-
 static void event_function_call(struct perf_event *event, event_f func, void *data)
 {
 	struct perf_event_context *ctx = event->ctx;
@@ -303,6 +291,54 @@ again:
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
+/*
+ * Similar to event_function_call() + event_function(), but hard assumes IRQs
+ * are already disabled and we're on the right CPU.
+ */
+static void event_function_local(struct perf_event *event, event_f func, void *data)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	struct task_struct *task = READ_ONCE(ctx->task);
+	struct perf_event_context *task_ctx = NULL;
+
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (task) {
+		if (task == TASK_TOMBSTONE)
+			return;
+
+		task_ctx = ctx;
+	}
+
+	perf_ctx_lock(cpuctx, task_ctx);
+
+	task = ctx->task;
+	if (task == TASK_TOMBSTONE)
+		goto unlock;
+
+	if (task) {
+		/*
+		 * We must be either inactive or active and the right task,
+		 * otherwise we're screwed, since we cannot IPI to somewhere
+		 * else.
+		 */
+		if (ctx->is_active) {
+			if (WARN_ON_ONCE(task != current))
+				goto unlock;
+
+			if (WARN_ON_ONCE(cpuctx->task_ctx != ctx))
+				goto unlock;
+		}
+	} else {
+		WARN_ON_ONCE(&cpuctx->ctx != ctx);
+	}
+
+	func(event, cpuctx, ctx, data);
+unlock:
+	perf_ctx_unlock(cpuctx, task_ctx);
+}
+
 #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
 		       PERF_FLAG_FD_OUTPUT  |\
 		       PERF_FLAG_PID_CGROUP |\
@@ -3513,9 +3549,10 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.group = group,
 			.ret = 0,
 		};
-		smp_call_function_single(event->oncpu,
-					 __perf_event_read, &data, 1);
-		ret = data.ret;
+		ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+		/* The event must have been read from an online CPU: */
+		WARN_ON_ONCE(ret);
+		ret = ret ? : data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
 		unsigned long flags;
@@ -6129,7 +6166,7 @@ static int __perf_pmu_output_stop(void *info)
 {
 	struct perf_event *event = info;
 	struct pmu *pmu = event->pmu;
-	struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 	struct remote_output ro = {
 		.rb	= event->rb,
 	};
@@ -6584,15 +6621,6 @@ got_name:
 }
 
 /*
- * Whether this @filter depends on a dynamic object which is not loaded
- * yet or its load addresses are not known.
- */
-static bool perf_addr_filter_needs_mmap(struct perf_addr_filter *filter)
-{
-	return filter->filter && filter->inode;
-}
-
-/*
  * Check whether inode and address range match filter criteria.
  */
 static bool perf_addr_filter_match(struct perf_addr_filter *filter,
@@ -6653,6 +6681,13 @@ static void perf_addr_filters_adjust(struct vm_area_struct *vma)
 	struct perf_event_context *ctx;
 	int ctxn;
 
+	/*
+	 * Data tracing isn't supported yet and as such there is no need
+	 * to keep track of anything that isn't related to executable code:
+	 */
+	if (!(vma->vm_flags & VM_EXEC))
+		return;
+
 	rcu_read_lock();
 	for_each_task_context_nr(ctxn) {
 		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
@@ -7805,7 +7840,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	list_for_each_entry(filter, &ifh->list, entry) {
 		event->addr_filters_offs[count] = 0;
 
-		if (perf_addr_filter_needs_mmap(filter))
+		/*
+		 * Adjust base offset if the filter is associated to a binary
+		 * that needs to be mapped:
+		 */
+		if (filter->inode)
 			event->addr_filters_offs[count] =
 				perf_addr_filter_apply(filter, mm);
 
@@ -7936,8 +7975,10 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 					goto fail;
 			}
 
-			if (token == IF_SRC_FILE) {
-				filename = match_strdup(&args[2]);
+			if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) {
+				int fpos = filter->range ? 2 : 1;
+
+				filename = match_strdup(&args[fpos]);
 				if (!filename) {
 					ret = -ENOMEM;
 					goto fail;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index b7a525a..8c50276 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -172,8 +172,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	err = -EAGAIN;
 	ptep = page_check_address(page, mm, addr, &ptl, 0);
-	if (!ptep)
+	if (!ptep) {
+		mem_cgroup_cancel_charge(kpage, memcg, false);
 		goto unlock;
+	}
 
 	get_page(kpage);
 	page_add_new_anon_rmap(kpage, vma, addr, false);
@@ -200,7 +202,6 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	err = 0;
  unlock:
-	mem_cgroup_cancel_charge(kpage, memcg, false);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	unlock_page(page);
 	return err;
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index f689593..32f6cfc 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -39,6 +39,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
 		return NULL;
 	}
 
+	get_online_cpus();
 	if (max_vecs >= num_online_cpus()) {
 		cpumask_copy(affinity_mask, cpu_online_mask);
 		*nr_vecs = num_online_cpus();
@@ -56,6 +57,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
 		}
 		*nr_vecs = vecs;
 	}
+	put_online_cpus();
 
 	return affinity_mask;
 }
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b4c1bc7..6373890 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -820,6 +820,17 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 	desc->name = name;
 
 	if (handle != handle_bad_irq && is_chained) {
+		/*
+		 * We're about to start this interrupt immediately,
+		 * hence the need to set the trigger configuration.
+		 * But the .set_type callback may have overridden the
+		 * flow handler, ignoring that we're dealing with a
+		 * chained interrupt. Reset it immediately because we
+		 * do know better.
+		 */
+		__irq_set_trigger(desc, irqd_get_trigger_type(&desc->irq_data));
+		desc->handle_irq = handle;
+
 		irq_settings_set_noprobe(desc);
 		irq_settings_set_norequest(desc);
 		irq_settings_set_nothread(desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 73a2b78..9530fcd 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1681,8 +1681,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	action->dev_id = dev_id;
 
 	retval = irq_chip_pm_get(&desc->irq_data);
-	if (retval < 0)
+	if (retval < 0) {
+		kfree(action);
 		return retval;
+	}
 
 	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, action);
@@ -1985,8 +1987,10 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler,
 	action->percpu_dev_id = dev_id;
 
 	retval = irq_chip_pm_get(&desc->irq_data);
-	if (retval < 0)
+	if (retval < 0) {
+		kfree(action);
 		return retval;
+	}
 
 	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, action);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 9a0178c..b022284 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -835,9 +835,9 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn)
  */
 static bool rtree_next_node(struct memory_bitmap *bm)
 {
-	bm->cur.node = list_entry(bm->cur.node->list.next,
-				  struct rtree_node, list);
-	if (&bm->cur.node->list != &bm->cur.zone->leaves) {
+	if (!list_is_last(&bm->cur.node->list, &bm->cur.zone->leaves)) {
+		bm->cur.node = list_entry(bm->cur.node->list.next,
+					  struct rtree_node, list);
 		bm->cur.node_pfn += BM_BITS_PER_BLOCK;
 		bm->cur.node_bit  = 0;
 		touch_softlockup_watchdog();
@@ -845,9 +845,9 @@ static bool rtree_next_node(struct memory_bitmap *bm)
 	}
 
 	/* No more nodes, goto next zone */
-	bm->cur.zone = list_entry(bm->cur.zone->list.next,
+	if (!list_is_last(&bm->cur.zone->list, &bm->zones)) {
+		bm->cur.zone = list_entry(bm->cur.zone->list.next,
 				  struct mem_zone_bm_rtree, list);
-	if (&bm->cur.zone->list != &bm->zones) {
 		bm->cur.node = list_entry(bm->cur.zone->leaves.next,
 					  struct rtree_node, list);
 		bm->cur.node_pfn = 0;
diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c
index 276762f..d5760c4 100644
--- a/kernel/printk/braille.c
+++ b/kernel/printk/braille.c
@@ -9,10 +9,10 @@
 
 char *_braille_console_setup(char **str, char **brl_options)
 {
-	if (!memcmp(*str, "brl,", 4)) {
+	if (!strncmp(*str, "brl,", 4)) {
 		*brl_options = "";
 		*str += 4;
-	} else if (!memcmp(str, "brl=", 4)) {
+	} else if (!strncmp(*str, "brl=", 4)) {
 		*brl_options = *str + 4;
 		*str = strchr(*brl_options, ',');
 		if (!*str)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 9858266..a846cf8 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -263,6 +263,11 @@ void account_idle_time(cputime_t cputime)
 		cpustat[CPUTIME_IDLE] += (__force u64) cputime;
 }
 
+/*
+ * When a guest is interrupted for a longer amount of time, missed clock
+ * ticks are not redelivered later. Due to that, this function may on
+ * occasion account more time than the calling functions think elapsed.
+ */
 static __always_inline cputime_t steal_account_process_time(cputime_t maxtime)
 {
 #ifdef CONFIG_PARAVIRT
@@ -371,7 +376,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 	 * idle, or potentially user or system time. Due to rounding,
 	 * other time can exceed ticks occasionally.
 	 */
-	other = account_other_time(cputime);
+	other = account_other_time(ULONG_MAX);
 	if (other >= cputime)
 		return;
 	cputime -= other;
@@ -486,7 +491,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	}
 
 	cputime = cputime_one_jiffy;
-	steal = steal_account_process_time(cputime);
+	steal = steal_account_process_time(ULONG_MAX);
 
 	if (steal >= cputime)
 		return;
@@ -516,7 +521,7 @@ void account_idle_ticks(unsigned long ticks)
 	}
 
 	cputime = jiffies_to_cputime(ticks);
-	steal = steal_account_process_time(cputime);
+	steal = steal_account_process_time(ULONG_MAX);
 
 	if (steal >= cputime)
 		return;
@@ -614,19 +619,25 @@ static void cputime_adjust(struct task_cputime *curr,
 	stime = curr->stime;
 	utime = curr->utime;
 
-	if (utime == 0) {
-		stime = rtime;
+	/*
+	 * If either stime or both stime and utime are 0, assume all runtime is
+	 * userspace. Once a task gets some ticks, the monotonicy code at
+	 * 'update' will ensure things converge to the observed ratio.
+	 */
+	if (stime == 0) {
+		utime = rtime;
 		goto update;
 	}
 
-	if (stime == 0) {
-		utime = rtime;
+	if (utime == 0) {
+		stime = rtime;
 		goto update;
 	}
 
 	stime = scale_stime((__force u64)stime, (__force u64)rtime,
 			    (__force u64)(stime + utime));
 
+update:
 	/*
 	 * Make sure stime doesn't go backwards; this preserves monotonicity
 	 * for utime because rtime is monotonic.
@@ -649,7 +660,6 @@ static void cputime_adjust(struct task_cputime *curr,
 		stime = rtime - utime;
 	}
 
-update:
 	prev->stime = stime;
 	prev->utime = utime;
 out:
@@ -694,6 +704,13 @@ static cputime_t get_vtime_delta(struct task_struct *tsk)
 	unsigned long now = READ_ONCE(jiffies);
 	cputime_t delta, other;
 
+	/*
+	 * Unlike tick based timing, vtime based timing never has lost
+	 * ticks, and no need for steal time accounting to make up for
+	 * lost ticks. Vtime accounts a rounded version of actual
+	 * elapsed time. Limit account_other_time to prevent rounding
+	 * errors from causing elapsed vtime to go negative.
+	 */
 	delta = jiffies_to_cputime(now - tsk->vtime_snap);
 	other = account_other_time(delta);
 	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b43d0b2..a13bbda 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2140,6 +2140,21 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
 	return 0;
 }
 
+static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp,
+				 int *valp,
+				 int write, void *data)
+{
+	if (write) {
+		if (*negp)
+			return -EINVAL;
+		*valp = *lvalp;
+	} else {
+		unsigned int val = *valp;
+		*lvalp = (unsigned long)val;
+	}
+	return 0;
+}
+
 static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
 
 static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
@@ -2259,8 +2274,27 @@ static int do_proc_dointvec(struct ctl_table *table, int write,
 int proc_dointvec(struct ctl_table *table, int write,
 		     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,buffer,lenp,ppos,
-		    	    NULL,NULL);
+	return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
+}
+
+/**
+ * proc_douintvec - read a vector of unsigned integers
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * Returns 0 on success.
+ */
+int proc_douintvec(struct ctl_table *table, int write,
+		     void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return do_proc_dointvec(table, write, buffer, lenp, ppos,
+				do_proc_douintvec_conv, NULL);
 }
 
 /*
@@ -2858,6 +2892,12 @@ int proc_dointvec(struct ctl_table *table, int write,
 	return -ENOSYS;
 }
 
+int proc_douintvec(struct ctl_table *table, int write,
+		  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
 int proc_dointvec_minmax(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -2903,6 +2943,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
  * exception granted :-)
  */
 EXPORT_SYMBOL(proc_dointvec);
+EXPORT_SYMBOL(proc_douintvec);
 EXPORT_SYMBOL(proc_dointvec_jiffies);
 EXPORT_SYMBOL(proc_dointvec_minmax);
 EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3b65746..e07fb09 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -401,7 +401,10 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
 	do {
 		seq = raw_read_seqcount_latch(&tkf->seq);
 		tkr = tkf->base + (seq & 0x01);
-		now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+		now = ktime_to_ns(tkr->base);
+
+		now += clocksource_delta(tkr->read(tkr->clock),
+					 tkr->cycle_last, tkr->mask);
 	} while (read_seqcount_retry(&tkf->seq, seq));
 
 	return now;
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index f6bd652..107310a 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -23,7 +23,9 @@
 
 #include "timekeeping_internal.h"
 
-static unsigned int sleep_time_bin[32] = {0};
+#define NUM_BINS 32
+
+static unsigned int sleep_time_bin[NUM_BINS] = {0};
 
 static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
 {
@@ -69,6 +71,9 @@ late_initcall(tk_debug_sleep_time_init);
 
 void tk_debug_account_sleep_time(struct timespec64 *t)
 {
-	sleep_time_bin[fls(t->tv_sec)]++;
+	/* Cap bin index so we don't overflow the array */
+	int bin = min(fls(t->tv_sec), NUM_BINS-1);
+
+	sleep_time_bin[bin]++;
 }
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7598e6c..dbafc5d 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -223,7 +223,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= MASK_TC_BIT(op_flags, META);
 	what |= MASK_TC_BIT(op_flags, PREFLUSH);
 	what |= MASK_TC_BIT(op_flags, FUA);
-	if (op == REQ_OP_DISCARD)
+	if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
 		what |= BLK_TC_ACT(BLK_TC_DISCARD);
 	if (op == REQ_OP_FLUSH)
 		what |= BLK_TC_ACT(BLK_TC_FLUSH);