Merge tag 'v4.19-rc5' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/bpf/btf.c

@@ -1844,7 +1844,7 @@ static int btf_check_all_metas(struct btf_verifier_env *env)
 
 	hdr = &btf->hdr;
 	cur = btf->nohdr_data + hdr->type_off;
-	end = btf->nohdr_data + hdr->type_len;
+	end = cur + hdr->type_len;
 
 	env->log_type_id = 1;
 	while (cur < end) {

kernel/bpf/verifier.c

@@ -3163,7 +3163,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 				 * an arbitrary scalar. Disallow all math except
 				 * pointer subtraction
 				 */
-				if (opcode == BPF_SUB){
+				if (opcode == BPF_SUB && env->allow_ptr_leaks) {
 					mark_reg_unknown(env, regs, insn->dst_reg);
 					return 0;
 				}

kernel/events/core.c

@@ -5943,6 +5943,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 		unsigned long sp;
 		unsigned int rem;
 		u64 dyn_size;
+		mm_segment_t fs;
 
 		/*
 		 * We dump:
@@ -5960,7 +5961,10 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 
 		/* Data. */
 		sp = perf_user_stack_pointer(regs);
+		fs = get_fs();
+		set_fs(USER_DS);
 		rem = __output_copy_user(handle, (void *) sp, dump_size);
+		set_fs(fs);
 		dyn_size = dump_size - rem;
 
 		perf_output_skip(handle, rem);

kernel/jump_label.c

@@ -678,7 +678,7 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val,
 	case MODULE_STATE_COMING:
 		ret = jump_label_add_module(mod);
 		if (ret) {
-			WARN(1, "Failed to allocatote memory: jump_label may not work properly.\n");
+			WARN(1, "Failed to allocate memory: jump_label may not work properly.\n");
 			jump_label_del_module(mod);
 		}
 		break;

kernel/locking/lockdep.c

@@ -55,7 +55,6 @@
 
 #include "lockdep_internals.h"
 
-#include <trace/events/preemptirq.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/lock.h>
 

kernel/locking/mutex.c

@@ -389,7 +389,7 @@ static bool __ww_mutex_wound(struct mutex *lock,
 		/*
 		 * wake_up_process() paired with set_current_state()
 		 * inserts sufficient barriers to make sure @owner either sees
-		 * it's wounded in __ww_mutex_lock_check_stamp() or has a
+		 * it's wounded in __ww_mutex_check_kill() or has a
 		 * wakeup pending to re-read the wounded state.
 		 */
 		if (owner != current)
@@ -946,7 +946,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	}
 
 	debug_mutex_lock_common(lock, &waiter);
-	debug_mutex_add_waiter(lock, &waiter, current);
 
 	lock_contended(&lock->dep_map, ip);
 

kernel/locking/test-ww_mutex.c

@@ -324,7 +324,7 @@ static int __test_cycle(unsigned int nthreads)
 		if (!cycle->result)
 			continue;
 
-		pr_err("cylic deadlock not resolved, ret[%d/%d] = %d\n",
+		pr_err("cyclic deadlock not resolved, ret[%d/%d] = %d\n",
 		       n, nthreads, cycle->result);
 		ret = -EINVAL;
 		break;

kernel/pid.c

@@ -195,7 +195,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 		idr_preload_end();
 
 		if (nr < 0) {
-			retval = nr;
+			retval = (nr == -ENOSPC) ? -EAGAIN : nr;
 			goto out_free;
 		}
 

kernel/printk/printk.c

@@ -351,7 +351,6 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
  */
 
 enum log_flags {
-	LOG_NOCONS	= 1,	/* suppress print, do not print to console */
 	LOG_NEWLINE	= 2,	/* text ended with a newline */
 	LOG_PREFIX	= 4,	/* text started with a prefix */
 	LOG_CONT	= 8,	/* text is a fragment of a continuation line */
@@ -1881,9 +1880,6 @@ int vprintk_store(int facility, int level,
 	if (dict)
 		lflags |= LOG_PREFIX|LOG_NEWLINE;
 
-	if (suppress_message_printing(level))
-		lflags |= LOG_NOCONS;
-
 	return log_output(facility, level, lflags,
 			  dict, dictlen, text, text_len);
 }
@@ -2032,6 +2028,7 @@ static void call_console_drivers(const char *ext_text, size_t ext_len,
 				 const char *text, size_t len) {}
 static size_t msg_print_text(const struct printk_log *msg,
 			     bool syslog, char *buf, size_t size) { return 0; }
+static bool suppress_message_printing(int level) { return false; }
 
 #endif /* CONFIG_PRINTK */
 
@@ -2368,10 +2365,11 @@ skip:
 			break;
 
 		msg = log_from_idx(console_idx);
-		if (msg->flags & LOG_NOCONS) {
+		if (suppress_message_printing(msg->level)) {
 			/*
-			 * Skip record if !ignore_loglevel, and
-			 * record has level above the console loglevel.
+			 * Skip record we have buffered and already printed
+			 * directly to the console when we received it, and
+			 * record that has level above the console loglevel.
 			 */
 			console_idx = log_next(console_idx);
 			console_seq++;

kernel/sched/debug.c

@@ -89,12 +89,12 @@ struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
 
 static void sched_feat_disable(int i)
 {
-	static_key_disable(&sched_feat_keys[i]);
+	static_key_disable_cpuslocked(&sched_feat_keys[i]);
 }
 
 static void sched_feat_enable(int i)
 {
-	static_key_enable(&sched_feat_keys[i]);
+	static_key_enable_cpuslocked(&sched_feat_keys[i]);
 }
 #else
 static void sched_feat_disable(int i) { };
@@ -146,9 +146,11 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 
 	/* Ensure the static_key remains in a consistent state */
 	inode = file_inode(filp);
+	cpus_read_lock();
 	inode_lock(inode);
 	ret = sched_feat_set(cmp);
 	inode_unlock(inode);
+	cpus_read_unlock();
 	if (ret < 0)
 		return ret;
 

kernel/sched/fair.c

@@ -3362,6 +3362,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
  * attach_entity_load_avg - attach this entity to its cfs_rq load avg
  * @cfs_rq: cfs_rq to attach to
  * @se: sched_entity to attach
+ * @flags: migration hints
  *
  * Must call update_cfs_rq_load_avg() before this, since we rely on
  * cfs_rq->avg.last_update_time being current.
@@ -7263,6 +7264,7 @@ static void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq, *pos;
+	const struct sched_class *curr_class;
 	struct rq_flags rf;
 	bool done = true;
 
@@ -7299,8 +7301,10 @@ static void update_blocked_averages(int cpu)
 		if (cfs_rq_has_blocked(cfs_rq))
 			done = false;
 	}
-	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
-	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
+	curr_class = rq->curr->sched_class;
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class);
 	update_irq_load_avg(rq, 0);
 	/* Don't need periodic decay once load/util_avg are null */
 	if (others_have_blocked(rq))
@@ -7365,13 +7369,16 @@ static inline void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq = &rq->cfs;
+	const struct sched_class *curr_class;
 	struct rq_flags rf;
 
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
-	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
-	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
+	curr_class = rq->curr->sched_class;
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class);
 	update_irq_load_avg(rq, 0);
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
@@ -7482,10 +7489,10 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 	return load_idx;
 }
 
-static unsigned long scale_rt_capacity(int cpu)
+static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+	unsigned long max = arch_scale_cpu_capacity(sd, cpu);
 	unsigned long used, free;
 	unsigned long irq;
 
@@ -7507,7 +7514,7 @@ static unsigned long scale_rt_capacity(int cpu)
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = scale_rt_capacity(cpu);
+	unsigned long capacity = scale_rt_capacity(sd, cpu);
 	struct sched_group *sdg = sd->groups;
 
 	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
@@ -8269,7 +8276,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 force_balance:
 	/* Looks like there is an imbalance. Compute it */
 	calculate_imbalance(env, &sds);
-	return sds.busiest;
+	return env->imbalance ? sds.busiest : NULL;
 
 out_balanced:
 	env->imbalance = 0;
@@ -9638,7 +9645,8 @@ static inline bool vruntime_normalized(struct task_struct *p)
 	 * - A task which has been woken up by try_to_wake_up() and
 	 *   waiting for actually being woken up by sched_ttwu_pending().
 	 */
-	if (!se->sum_exec_runtime || p->state == TASK_WAKING)
+	if (!se->sum_exec_runtime ||
+	    (p->state == TASK_WAKING && p->sched_remote_wakeup))
 		return true;
 
 	return false;

kernel/sched/topology.c

@@ -1295,7 +1295,7 @@ static void init_numa_topology_type(void)
 
 	n = sched_max_numa_distance;
 
-	if (sched_domains_numa_levels <= 1) {
+	if (sched_domains_numa_levels <= 2) {
 		sched_numa_topology_type = NUMA_DIRECT;
 		return;
 	}
@@ -1380,9 +1380,6 @@ void sched_init_numa(void)
 			break;
 	}
 
-	if (!level)
-		return;
-
 	/*
 	 * 'level' contains the number of unique distances
 	 *

kernel/sys.c

@@ -71,9 +71,6 @@
 #include <asm/io.h>
 #include <asm/unistd.h>
 
-/* Hardening for Spectre-v1 */
-#include <linux/nospec.h>
-
 #include "uid16.h"
 
 #ifndef SET_UNALIGN_CTL

kernel/trace/ring_buffer.c

@@ -1546,6 +1546,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 	tmp_iter_page = first_page;
 
 	do {
+		cond_resched();
+
 		to_remove_page = tmp_iter_page;
 		rb_inc_page(cpu_buffer, &tmp_iter_page);