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

9 files changed, 169 insertions, 59 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 1eb4f1303756..503d4211988a 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -146,10 +146,11 @@ void __bpf_prog_free(struct bpf_prog *fp)
 	vfree(fp);
 }
 
-int bpf_prog_calc_digest(struct bpf_prog *fp)
+int bpf_prog_calc_tag(struct bpf_prog *fp)
 {
 	const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64);
-	u32 raw_size = bpf_prog_digest_scratch_size(fp);
+	u32 raw_size = bpf_prog_tag_scratch_size(fp);
+	u32 digest[SHA_DIGEST_WORDS];
 	u32 ws[SHA_WORKSPACE_WORDS];
 	u32 i, bsize, psize, blocks;
 	struct bpf_insn *dst;
@@ -162,7 +163,7 @@ int bpf_prog_calc_digest(struct bpf_prog *fp)
 	if (!raw)
 		return -ENOMEM;
 
-	sha_init(fp->digest);
+	sha_init(digest);
 	memset(ws, 0, sizeof(ws));
 
 	/* We need to take out the map fd for the digest calculation
@@ -204,13 +205,14 @@ int bpf_prog_calc_digest(struct bpf_prog *fp)
 	*bits = cpu_to_be64((psize - 1) << 3);
 
 	while (blocks--) {
-		sha_transform(fp->digest, todo, ws);
+		sha_transform(digest, todo, ws);
 		todo += SHA_MESSAGE_BYTES;
 	}
 
-	result = (__force __be32 *)fp->digest;
+	result = (__force __be32 *)digest;
 	for (i = 0; i < SHA_DIGEST_WORDS; i++)
-		result[i] = cpu_to_be32(fp->digest[i]);
+		result[i] = cpu_to_be32(digest[i]);
+	memcpy(fp->tag, result, sizeof(fp->tag));
 
 	vfree(raw);
 	return 0;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e89acea22ecf..1d6b29e4e2c3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -688,17 +688,17 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
 static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
 {
 	const struct bpf_prog *prog = filp->private_data;
-	char prog_digest[sizeof(prog->digest) * 2 + 1] = { };
+	char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
 
-	bin2hex(prog_digest, prog->digest, sizeof(prog->digest));
+	bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
 	seq_printf(m,
 		   "prog_type:\t%u\n"
 		   "prog_jited:\t%u\n"
-		   "prog_digest:\t%s\n"
+		   "prog_tag:\t%s\n"
 		   "memlock:\t%llu\n",
 		   prog->type,
 		   prog->jited,
-		   prog_digest,
+		   prog_tag,
 		   prog->pages * 1ULL << PAGE_SHIFT);
 }
 #endif
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d60e12c67266..8f69df7e8167 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3016,7 +3016,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 	int insn_cnt = env->prog->len;
 	int i, j, err;
 
-	err = bpf_prog_calc_digest(env->prog);
+	err = bpf_prog_calc_tag(env->prog);
 	if (err)
 		return err;
 
diff --git a/kernel/capability.c b/kernel/capability.c
index a98e814f216f..f97fe77ceb88 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -318,6 +318,7 @@ bool has_capability(struct task_struct *t, int cap)
 {
 	return has_ns_capability(t, &init_user_ns, cap);
 }
+EXPORT_SYMBOL(has_capability);
 
 /**
  * has_ns_capability_noaudit - Does a task have a capability (unaudited)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ab15509fab8c..110b38a58493 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2249,7 +2249,7 @@ static int  __perf_install_in_context(void *info)
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	struct perf_event_context *task_ctx = cpuctx->task_ctx;
-	bool activate = true;
+	bool reprogram = true;
 	int ret = 0;
 
 	raw_spin_lock(&cpuctx->ctx.lock);
@@ -2257,27 +2257,26 @@ static int  __perf_install_in_context(void *info)
 		raw_spin_lock(&ctx->lock);
 		task_ctx = ctx;
 
-		/* If we're on the wrong CPU, try again */
-		if (task_cpu(ctx->task) != smp_processor_id()) {
-			ret = -ESRCH;
-			goto unlock;
-		}
+		reprogram = (ctx->task == current);
 
 		/*
-		 * If we're on the right CPU, see if the task we target is
-		 * current, if not we don't have to activate the ctx, a future
-		 * context switch will do that for us.
+		 * If the task is running, it must be running on this CPU,
+		 * otherwise we cannot reprogram things.
+		 *
+		 * If its not running, we don't care, ctx->lock will
+		 * serialize against it becoming runnable.
 		 */
-		if (ctx->task != current)
-			activate = false;
-		else
-			WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx);
+		if (task_curr(ctx->task) && !reprogram) {
+			ret = -ESRCH;
+			goto unlock;
+		}
 
+		WARN_ON_ONCE(reprogram && cpuctx->task_ctx && cpuctx->task_ctx != ctx);
 	} else if (task_ctx) {
 		raw_spin_lock(&task_ctx->lock);
 	}
 
-	if (activate) {
+	if (reprogram) {
 		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 		add_event_to_ctx(event, ctx);
 		ctx_resched(cpuctx, task_ctx);
@@ -2328,13 +2327,36 @@ perf_install_in_context(struct perf_event_context *ctx,
 	/*
 	 * Installing events is tricky because we cannot rely on ctx->is_active
 	 * to be set in case this is the nr_events 0 -> 1 transition.
+	 *
+	 * Instead we use task_curr(), which tells us if the task is running.
+	 * However, since we use task_curr() outside of rq::lock, we can race
+	 * against the actual state. This means the result can be wrong.
+	 *
+	 * If we get a false positive, we retry, this is harmless.
+	 *
+	 * If we get a false negative, things are complicated. If we are after
+	 * perf_event_context_sched_in() ctx::lock will serialize us, and the
+	 * value must be correct. If we're before, it doesn't matter since
+	 * perf_event_context_sched_in() will program the counter.
+	 *
+	 * However, this hinges on the remote context switch having observed
+	 * our task->perf_event_ctxp[] store, such that it will in fact take
+	 * ctx::lock in perf_event_context_sched_in().
+	 *
+	 * We do this by task_function_call(), if the IPI fails to hit the task
+	 * we know any future context switch of task must see the
+	 * perf_event_ctpx[] store.
 	 */
-again:
+
 	/*
-	 * Cannot use task_function_call() because we need to run on the task's
-	 * CPU regardless of whether its current or not.
+	 * This smp_mb() orders the task->perf_event_ctxp[] store with the
+	 * task_cpu() load, such that if the IPI then does not find the task
+	 * running, a future context switch of that task must observe the
+	 * store.
 	 */
-	if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event))
+	smp_mb();
+again:
+	if (!task_function_call(task, __perf_install_in_context, event))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -2348,12 +2370,16 @@ again:
 		raw_spin_unlock_irq(&ctx->lock);
 		return;
 	}
-	raw_spin_unlock_irq(&ctx->lock);
 	/*
-	 * Since !ctx->is_active doesn't mean anything, we must IPI
-	 * unconditionally.
+	 * If the task is not running, ctx->lock will avoid it becoming so,
+	 * thus we can safely install the event.
 	 */
-	goto again;
+	if (task_curr(task)) {
+		raw_spin_unlock_irq(&ctx->lock);
+		goto again;
+	}
+	add_event_to_ctx(event, ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 }
 
 /*
@@ -7034,25 +7060,12 @@ static void perf_log_itrace_start(struct perf_event *event)
 	perf_output_end(&handle);
 }
 
-/*
- * Generic event overflow handling, sampling.
- */
-
-static int __perf_event_overflow(struct perf_event *event,
-				   int throttle, struct perf_sample_data *data,
-				   struct pt_regs *regs)
+static int
+__perf_event_account_interrupt(struct perf_event *event, int throttle)
 {
-	int events = atomic_read(&event->event_limit);
 	struct hw_perf_event *hwc = &event->hw;
-	u64 seq;
 	int ret = 0;
-
-	/*
-	 * Non-sampling counters might still use the PMI to fold short
-	 * hardware counters, ignore those.
-	 */
-	if (unlikely(!is_sampling_event(event)))
-		return 0;
+	u64 seq;
 
 	seq = __this_cpu_read(perf_throttled_seq);
 	if (seq != hwc->interrupts_seq) {
@@ -7080,6 +7093,34 @@ static int __perf_event_overflow(struct perf_event *event,
 			perf_adjust_period(event, delta, hwc->last_period, true);
 	}
 
+	return ret;
+}
+
+int perf_event_account_interrupt(struct perf_event *event)
+{
+	return __perf_event_account_interrupt(event, 1);
+}
+
+/*
+ * Generic event overflow handling, sampling.
+ */
+
+static int __perf_event_overflow(struct perf_event *event,
+				   int throttle, struct perf_sample_data *data,
+				   struct pt_regs *regs)
+{
+	int events = atomic_read(&event->event_limit);
+	int ret = 0;
+
+	/*
+	 * Non-sampling counters might still use the PMI to fold short
+	 * hardware counters, ignore those.
+	 */
+	if (unlikely(!is_sampling_event(event)))
+		return 0;
+
+	ret = __perf_event_account_interrupt(event, throttle);
+
 	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
@@ -9503,6 +9544,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
 	return 0;
 }
 
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+			     struct perf_event_context *ctx)
+{
+	struct perf_event_context *gctx;
+
+again:
+	rcu_read_lock();
+	gctx = READ_ONCE(group_leader->ctx);
+	if (!atomic_inc_not_zero(&gctx->refcount)) {
+		rcu_read_unlock();
+		goto again;
+	}
+	rcu_read_unlock();
+
+	mutex_lock_double(&gctx->mutex, &ctx->mutex);
+
+	if (group_leader->ctx != gctx) {
+		mutex_unlock(&ctx->mutex);
+		mutex_unlock(&gctx->mutex);
+		put_ctx(gctx);
+		goto again;
+	}
+
+	return gctx;
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -9746,12 +9818,31 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (move_group) {
-		gctx = group_leader->ctx;
-		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+		gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
 		if (gctx->task == TASK_TOMBSTONE) {
 			err = -ESRCH;
 			goto err_locked;
 		}
+
+		/*
+		 * Check if we raced against another sys_perf_event_open() call
+		 * moving the software group underneath us.
+		 */
+		if (!(group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) {
+			/*
+			 * If someone moved the group out from under us, check
+			 * if this new event wound up on the same ctx, if so
+			 * its the regular !move_group case, otherwise fail.
+			 */
+			if (gctx != ctx) {
+				err = -EINVAL;
+				goto err_locked;
+			} else {
+				perf_event_ctx_unlock(group_leader, gctx);
+				move_group = 0;
+			}
+		}
 	} else {
 		mutex_lock(&ctx->mutex);
 	}
@@ -9853,7 +9944,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	perf_unpin_context(ctx);
 
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 
 	if (task) {
@@ -9879,7 +9970,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 err_locked:
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 /* err_file: */
 	fput(event_file);
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 93ad6c1fb9b6..a9b8cf500591 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -182,6 +182,13 @@ void static_key_slow_dec_deferred(struct static_key_deferred *key)
 }
 EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
 
+void static_key_deferred_flush(struct static_key_deferred *key)
+{
+	STATIC_KEY_CHECK_USE();
+	flush_delayed_work(&key->work);
+}
+EXPORT_SYMBOL_GPL(static_key_deferred_flush);
+
 void jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
 {
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index df9e8e9e0be7..eef2ce968636 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -151,8 +151,12 @@ out:
 
 static void delayed_free_pidns(struct rcu_head *p)
 {
-	kmem_cache_free(pid_ns_cachep,
-			container_of(p, struct pid_namespace, rcu));
+	struct pid_namespace *ns = container_of(p, struct pid_namespace, rcu);
+
+	dec_pid_namespaces(ns->ucounts);
+	put_user_ns(ns->user_ns);
+
+	kmem_cache_free(pid_ns_cachep, ns);
 }
 
 static void destroy_pid_namespace(struct pid_namespace *ns)
@@ -162,8 +166,6 @@ static void destroy_pid_namespace(struct pid_namespace *ns)
 	ns_free_inum(&ns->ns);
 	for (i = 0; i < PIDMAP_ENTRIES; i++)
 		kfree(ns->pidmap[i].page);
-	dec_pid_namespaces(ns->ucounts);
-	put_user_ns(ns->user_ns);
 	call_rcu(&ns->rcu, delayed_free_pidns);
 }
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 2c115fdab397..74e0388cc88d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -767,7 +767,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	tick = expires;
 
 	/* Skip reprogram of event if its not changed */
-	if (ts->tick_stopped && (expires == dev->next_event))
+	if (ts->tick_stopped && (expires == ts->next_tick))
 		goto out;
 
 	/*
@@ -787,6 +787,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		trace_tick_stop(1, TICK_DEP_MASK_NONE);
 	}
 
+	ts->next_tick = tick;
+
 	/*
 	 * If the expiration time == KTIME_MAX, then we simply stop
 	 * the tick timer.
@@ -802,7 +804,10 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	else
 		tick_program_event(tick, 1);
 out:
-	/* Update the estimated sleep length */
+	/*
+	 * Update the estimated sleep length until the next timer
+	 * (not only the tick).
+	 */
 	ts->sleep_length = ktime_sub(dev->next_event, now);
 	return tick;
 }
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index bf38226e5c17..075444e3d48e 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -27,6 +27,7 @@ enum tick_nohz_mode {
  *			timer is modified for nohz sleeps. This is necessary
  *			to resume the tick timer operation in the timeline
  *			when the CPU returns from nohz sleep.
+ * @next_tick:		Next tick to be fired when in dynticks mode.
  * @tick_stopped:	Indicator that the idle tick has been stopped
  * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
  * @idle_calls:		Total number of idle calls
@@ -44,6 +45,7 @@ struct tick_sched {
 	unsigned long			check_clocks;
 	enum tick_nohz_mode		nohz_mode;
 	ktime_t				last_tick;
+	ktime_t				next_tick;
 	int				inidle;
 	int				tick_stopped;
 	unsigned long			idle_jiffies;