Merge branch 'perf/urgent'

Merge urgent fixes for dependencies.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>

8 files changed, 114 insertions, 71 deletions

diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 367eaf2c78b7..0ebbbe37a60f 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -347,12 +347,17 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 /* Get path information necessary for adding watches. */
 static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 {
-	struct dentry *d = kern_path_locked(watch->path, parent);
+	struct dentry *d;
+
+	d = kern_path_locked_negative(watch->path, parent);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
-	/* update watch filter fields */
-	watch->dev = d->d_sb->s_dev;
-	watch->ino = d_backing_inode(d)->i_ino;
+
+	if (d_is_positive(d)) {
+		/* update watch filter fields */
+		watch->dev = d->d_sb->s_dev;
+		watch->ino = d_backing_inode(d)->i_ino;
+	}
 
 	inode_unlock(d_backing_inode(parent->dentry));
 	dput(d);
@@ -418,11 +423,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 	/* caller expects mutex locked */
 	mutex_lock(&audit_filter_mutex);
 
-	if (ret && ret != -ENOENT) {
+	if (ret) {
 		audit_put_watch(watch);
 		return ret;
 	}
-	ret = 0;
 
 	/* either find an old parent or attach a new one */
 	parent = audit_find_parent(d_backing_inode(parent_path.dentry));
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 3caf2cd86e65..63e5b90da1f3 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -90,7 +90,7 @@
 DEFINE_MUTEX(cgroup_mutex);
 DEFINE_SPINLOCK(css_set_lock);
 
-#ifdef CONFIG_PROVE_RCU
+#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)
 EXPORT_SYMBOL_GPL(cgroup_mutex);
 EXPORT_SYMBOL_GPL(css_set_lock);
 #endif
@@ -2353,9 +2353,37 @@ static struct file_system_type cgroup2_fs_type = {
 };
 
 #ifdef CONFIG_CPUSETS_V1
+enum cpuset_param {
+	Opt_cpuset_v2_mode,
+};
+
+static const struct fs_parameter_spec cpuset_fs_parameters[] = {
+	fsparam_flag  ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+	{}
+};
+
+static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, cpuset_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_cpuset_v2_mode:
+		ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static const struct fs_context_operations cpuset_fs_context_ops = {
 	.get_tree	= cgroup1_get_tree,
 	.free		= cgroup_fs_context_free,
+	.parse_param	= cpuset_parse_param,
 };
 
 /*
@@ -2392,6 +2420,7 @@ static int cpuset_init_fs_context(struct fs_context *fc)
 static struct file_system_type cpuset_fs_type = {
 	.name			= "cpuset",
 	.init_fs_context	= cpuset_init_fs_context,
+	.parameters		= cpuset_fs_parameters,
 	.fs_flags		= FS_USERNS_MOUNT,
 };
 #endif
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 07414cb1279b..3c69a1a3f41c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3962,7 +3962,7 @@ static int merge_sched_in(struct perf_event *event, void *data)
 			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
 
 			if (*perf_event_fasync(event))
-				event->pending_kill = POLL_HUP;
+				event->pending_kill = POLL_ERR;
 
 			perf_event_wakeup(event);
 		} else {
@@ -6075,7 +6075,7 @@ static __poll_t perf_poll(struct file *file, poll_table *wait)
 
 	if (unlikely(READ_ONCE(event->state) == PERF_EVENT_STATE_ERROR &&
 		     event->attr.pinned))
-		return events;
+		return EPOLLERR;
 
 	/*
 	 * Pin the event->rb by taking event->mmap_mutex; otherwise
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 1a19d69b91ed..816f07f9d30f 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -81,9 +81,23 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 	if (!cpufreq_this_cpu_can_update(sg_policy->policy))
 		return false;
 
-	if (unlikely(sg_policy->limits_changed)) {
-		sg_policy->limits_changed = false;
-		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+	if (unlikely(READ_ONCE(sg_policy->limits_changed))) {
+		WRITE_ONCE(sg_policy->limits_changed, false);
+		sg_policy->need_freq_update = true;
+
+		/*
+		 * The above limits_changed update must occur before the reads
+		 * of policy limits in cpufreq_driver_resolve_freq() or a policy
+		 * limits update might be missed, so use a memory barrier to
+		 * ensure it.
+		 *
+		 * This pairs with the write memory barrier in sugov_limits().
+		 */
+		smp_mb();
+
+		return true;
+	} else if (sg_policy->need_freq_update) {
+		/* ignore_dl_rate_limit() wants a new frequency to be found. */
 		return true;
 	}
 
@@ -95,10 +109,22 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 				   unsigned int next_freq)
 {
-	if (sg_policy->need_freq_update)
+	if (sg_policy->need_freq_update) {
 		sg_policy->need_freq_update = false;
-	else if (sg_policy->next_freq == next_freq)
+		/*
+		 * The policy limits have changed, but if the return value of
+		 * cpufreq_driver_resolve_freq() after applying the new limits
+		 * is still equal to the previously selected frequency, the
+		 * driver callback need not be invoked unless the driver
+		 * specifically wants that to happen on every update of the
+		 * policy limits.
+		 */
+		if (sg_policy->next_freq == next_freq &&
+		    !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
+			return false;
+	} else if (sg_policy->next_freq == next_freq) {
 		return false;
+	}
 
 	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
@@ -365,7 +391,7 @@ static inline bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { return false; }
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
 {
 	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
-		sg_cpu->sg_policy->limits_changed = true;
+		sg_cpu->sg_policy->need_freq_update = true;
 }
 
 static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
@@ -871,7 +897,16 @@ static void sugov_limits(struct cpufreq_policy *policy)
 		mutex_unlock(&sg_policy->work_lock);
 	}
 
-	sg_policy->limits_changed = true;
+	/*
+	 * The limits_changed update below must take place before the updates
+	 * of policy limits in cpufreq_set_policy() or a policy limits update
+	 * might be missed, so use a memory barrier to ensure it.
+	 *
+	 * This pairs with the memory barrier in sugov_should_update_freq().
+	 */
+	smp_wmb();
+
+	WRITE_ONCE(sg_policy->limits_changed, true);
 }
 
 struct cpufreq_governor schedutil_gov = {
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 66bcd40a28ca..fdbf249d1c68 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -163,7 +163,7 @@ enum scx_ops_flags {
 	/*
 	 * CPU cgroup support flags
 	 */
-	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* cpu.weight */
+	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* DEPRECATED, will be removed on 6.18 */
 
 	SCX_OPS_ALL_FLAGS	= SCX_OPS_KEEP_BUILTIN_IDLE |
 				  SCX_OPS_ENQ_LAST |
@@ -3899,35 +3899,6 @@ bool scx_can_stop_tick(struct rq *rq)
 
 DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
 static bool scx_cgroup_enabled;
-static bool cgroup_warned_missing_weight;
-static bool cgroup_warned_missing_idle;
-
-static void scx_cgroup_warn_missing_weight(struct task_group *tg)
-{
-	if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
-	    cgroup_warned_missing_weight)
-		return;
-
-	if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
-		return;
-
-	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
-		scx_ops.name);
-	cgroup_warned_missing_weight = true;
-}
-
-static void scx_cgroup_warn_missing_idle(struct task_group *tg)
-{
-	if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
-		return;
-
-	if (!tg->idle)
-		return;
-
-	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
-		scx_ops.name);
-	cgroup_warned_missing_idle = true;
-}
 
 int scx_tg_online(struct task_group *tg)
 {
@@ -3937,8 +3908,6 @@ int scx_tg_online(struct task_group *tg)
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	scx_cgroup_warn_missing_weight(tg);
-
 	if (scx_cgroup_enabled) {
 		if (SCX_HAS_OP(cgroup_init)) {
 			struct scx_cgroup_init_args args =
@@ -4076,9 +4045,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 
 void scx_group_set_idle(struct task_group *tg, bool idle)
 {
-	percpu_down_read(&scx_cgroup_rwsem);
-	scx_cgroup_warn_missing_idle(tg);
-	percpu_up_read(&scx_cgroup_rwsem);
+	/* TODO: Implement ops->cgroup_set_idle() */
 }
 
 static void scx_cgroup_lock(void)
@@ -4272,9 +4239,6 @@ static int scx_cgroup_init(void)
 
 	percpu_rwsem_assert_held(&scx_cgroup_rwsem);
 
-	cgroup_warned_missing_weight = false;
-	cgroup_warned_missing_idle = false;
-
 	/*
 	 * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
 	 * cgroups and init, all online cgroups are initialized.
@@ -4284,9 +4248,6 @@ static int scx_cgroup_init(void)
 		struct task_group *tg = css_tg(css);
 		struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
 
-		scx_cgroup_warn_missing_weight(tg);
-		scx_cgroup_warn_missing_idle(tg);
-
 		if ((tg->scx_flags &
 		     (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
 			continue;
@@ -4623,7 +4584,7 @@ unlock:
 
 static void free_exit_info(struct scx_exit_info *ei)
 {
-	kfree(ei->dump);
+	kvfree(ei->dump);
 	kfree(ei->msg);
 	kfree(ei->bt);
 	kfree(ei);
@@ -4639,7 +4600,7 @@ static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len)
 
 	ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL);
 	ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL);
-	ei->dump = kzalloc(exit_dump_len, GFP_KERNEL);
+	ei->dump = kvzalloc(exit_dump_len, GFP_KERNEL);
 
 	if (!ei->bt || !ei->msg || !ei->dump) {
 		free_exit_info(ei);
@@ -5252,6 +5213,9 @@ static int validate_ops(const struct sched_ext_ops *ops)
 		return -EINVAL;
 	}
 
+	if (ops->flags & SCX_OPS_HAS_CGROUP_WEIGHT)
+		pr_warn("SCX_OPS_HAS_CGROUP_WEIGHT is deprecated and a noop\n");
+
 	return 0;
 }
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a8a02868b435..61130bb34d6c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1297,6 +1297,8 @@ void ftrace_free_filter(struct ftrace_ops *ops)
 		return;
 	free_ftrace_hash(ops->func_hash->filter_hash);
 	free_ftrace_hash(ops->func_hash->notrace_hash);
+	ops->func_hash->filter_hash = EMPTY_HASH;
+	ops->func_hash->notrace_hash = EMPTY_HASH;
 }
 EXPORT_SYMBOL_GPL(ftrace_free_filter);
 
@@ -3443,6 +3445,7 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **
 				  size_bits);
 		if (ret < 0) {
 			free_ftrace_hash(*filter_hash);
+			*filter_hash = EMPTY_HASH;
 			return ret;
 		}
 	}
@@ -3472,6 +3475,7 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **
 				     subops_hash->notrace_hash);
 		if (ret < 0) {
 			free_ftrace_hash(*notrace_hash);
+			*notrace_hash = EMPTY_HASH;
 			return ret;
 		}
 	}
@@ -3490,8 +3494,8 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **
  */
 int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
 {
-	struct ftrace_hash *filter_hash;
-	struct ftrace_hash *notrace_hash;
+	struct ftrace_hash *filter_hash = EMPTY_HASH;
+	struct ftrace_hash *notrace_hash = EMPTY_HASH;
 	struct ftrace_hash *save_filter_hash;
 	struct ftrace_hash *save_notrace_hash;
 	int ret;
@@ -3605,6 +3609,9 @@ static int rebuild_hashes(struct ftrace_hash **filter_hash, struct ftrace_hash *
 			}
 		}
 
+		free_ftrace_hash(temp_hash.filter_hash);
+		free_ftrace_hash(temp_hash.notrace_hash);
+
 		temp_hash.filter_hash = *filter_hash;
 		temp_hash.notrace_hash = *notrace_hash;
 	}
@@ -3625,8 +3632,8 @@ static int rebuild_hashes(struct ftrace_hash **filter_hash, struct ftrace_hash *
  */
 int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
 {
-	struct ftrace_hash *filter_hash;
-	struct ftrace_hash *notrace_hash;
+	struct ftrace_hash *filter_hash = EMPTY_HASH;
+	struct ftrace_hash *notrace_hash = EMPTY_HASH;
 	int ret;
 
 	if (unlikely(ftrace_disabled))
@@ -3699,8 +3706,11 @@ static int ftrace_hash_move_and_update_subops(struct ftrace_ops *subops,
 	}
 
 	ret = rebuild_hashes(&filter_hash, &notrace_hash, ops);
-	if (!ret)
+	if (!ret) {
 		ret = ftrace_update_ops(ops, filter_hash, notrace_hash);
+		free_ftrace_hash(filter_hash);
+		free_ftrace_hash(notrace_hash);
+	}
 
 	if (ret) {
 		/* Put back the original hash */
@@ -5954,9 +5964,10 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 
 	/* Make a copy hash to place the new and the old entries in */
 	size = hash->count + direct_functions->count;
-	if (size > 32)
-		size = 32;
-	new_hash = alloc_ftrace_hash(fls(size));
+	size = fls(size);
+	if (size > FTRACE_HASH_MAX_BITS)
+		size = FTRACE_HASH_MAX_BITS;
+	new_hash = alloc_ftrace_hash(size);
 	if (!new_hash)
 		goto out_unlock;
 
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index ee40d4e6ad1c..4ef4df6623a8 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -80,11 +80,11 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ent,	graph_ent	)
 		__field_packed(	unsigned long,	graph_ent,	func		)
-		__field_packed(	unsigned long,	graph_ent,	depth		)
+		__field_packed(	unsigned int,	graph_ent,	depth		)
 		__dynamic_array(unsigned long,	args				)
 	),
 
-	F_printk("--> %ps (%lu)", (void *)__entry->func, __entry->depth)
+	F_printk("--> %ps (%u)", (void *)__entry->func, __entry->depth)
 );
 
 #ifdef CONFIG_FUNCTION_GRAPH_RETADDR
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0993dfc1c5c1..2048560264bb 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -808,7 +808,7 @@ static __always_inline char *test_string(char *str)
 	kstr = ubuf->buffer;
 
 	/* For safety, do not trust the string pointer */
-	if (!strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE))
+	if (strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE) < 0)
 		return NULL;
 	return kstr;
 }
@@ -827,7 +827,7 @@ static __always_inline char *test_ustring(char *str)
 
 	/* user space address? */
 	ustr = (char __user *)str;
-	if (!strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE))
+	if (strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE) < 0)
 		return NULL;
 
 	return kstr;