Merge branch 'WIP.x86/asm' into x86/urgent, because the topic is ready

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

81 files changed, 4023 insertions, 2503 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e24aa3241387..43f95d190eea 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1845,7 +1845,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	union bpf_attr attr = {};
 	int err;
 
-	if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled)
+	if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
 	err = check_uarg_tail_zero(uattr, sizeof(attr), size);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 8cda3bc3ae22..4bfb2908ec15 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3183,6 +3183,16 @@ static int cgroup_enable_threaded(struct cgroup *cgrp)
 	if (cgroup_is_threaded(cgrp))
 		return 0;
 
+	/*
+	 * If @cgroup is populated or has domain controllers enabled, it
+	 * can't be switched.  While the below cgroup_can_be_thread_root()
+	 * test can catch the same conditions, that's only when @parent is
+	 * not mixable, so let's check it explicitly.
+	 */
+	if (cgroup_is_populated(cgrp) ||
+	    cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask)
+		return -EOPNOTSUPP;
+
 	/* we're joining the parent's domain, ensure its validity */
 	if (!cgroup_is_valid_domain(dom_cgrp) ||
 	    !cgroup_can_be_thread_root(dom_cgrp))
diff --git a/kernel/compat.c b/kernel/compat.c
index 3247fe761f60..6d21894806b4 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -488,80 +488,6 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat)
 }
 EXPORT_SYMBOL_GPL(get_compat_sigset);
 
-int
-put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set,
-		  unsigned int size)
-{
-	/* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */
-#ifdef __BIG_ENDIAN
-	compat_sigset_t v;
-	switch (_NSIG_WORDS) {
-	case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3];
-	case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2];
-	case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1];
-	case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0];
-	}
-	return copy_to_user(compat, &v, size) ? -EFAULT : 0;
-#else
-	return copy_to_user(compat, set, size) ? -EFAULT : 0;
-#endif
-}
-
-#ifdef CONFIG_NUMA
-COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
-		       compat_uptr_t __user *, pages32,
-		       const int __user *, nodes,
-		       int __user *, status,
-		       int, flags)
-{
-	const void __user * __user *pages;
-	int i;
-
-	pages = compat_alloc_user_space(nr_pages * sizeof(void *));
-	for (i = 0; i < nr_pages; i++) {
-		compat_uptr_t p;
-
-		if (get_user(p, pages32 + i) ||
-			put_user(compat_ptr(p), pages + i))
-			return -EFAULT;
-	}
-	return sys_move_pages(pid, nr_pages, pages, nodes, status, flags);
-}
-
-COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid,
-		       compat_ulong_t, maxnode,
-		       const compat_ulong_t __user *, old_nodes,
-		       const compat_ulong_t __user *, new_nodes)
-{
-	unsigned long __user *old = NULL;
-	unsigned long __user *new = NULL;
-	nodemask_t tmp_mask;
-	unsigned long nr_bits;
-	unsigned long size;
-
-	nr_bits = min_t(unsigned long, maxnode - 1, MAX_NUMNODES);
-	size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
-	if (old_nodes) {
-		if (compat_get_bitmap(nodes_addr(tmp_mask), old_nodes, nr_bits))
-			return -EFAULT;
-		old = compat_alloc_user_space(new_nodes ? size * 2 : size);
-		if (new_nodes)
-			new = old + size / sizeof(unsigned long);
-		if (copy_to_user(old, nodes_addr(tmp_mask), size))
-			return -EFAULT;
-	}
-	if (new_nodes) {
-		if (compat_get_bitmap(nodes_addr(tmp_mask), new_nodes, nr_bits))
-			return -EFAULT;
-		if (new == NULL)
-			new = compat_alloc_user_space(size);
-		if (copy_to_user(new, nodes_addr(tmp_mask), size))
-			return -EFAULT;
-	}
-	return sys_migrate_pages(pid, nr_bits + 1, old, new);
-}
-#endif
-
 /*
  * Allocate user-space memory for the duration of a single system call,
  * in order to marshall parameters inside a compat thunk.
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 53f7dc65f9a3..0db8938fbb23 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -124,24 +124,11 @@ struct cpuhp_step {
 };
 
 static DEFINE_MUTEX(cpuhp_state_mutex);
-static struct cpuhp_step cpuhp_bp_states[];
-static struct cpuhp_step cpuhp_ap_states[];
-
-static bool cpuhp_is_ap_state(enum cpuhp_state state)
-{
-	/*
-	 * The extra check for CPUHP_TEARDOWN_CPU is only for documentation
-	 * purposes as that state is handled explicitly in cpu_down.
-	 */
-	return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
-}
+static struct cpuhp_step cpuhp_hp_states[];
 
 static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
 {
-	struct cpuhp_step *sp;
-
-	sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states;
-	return sp + state;
+	return cpuhp_hp_states + state;
 }
 
 /**
@@ -239,6 +226,15 @@ err:
 }
 
 #ifdef CONFIG_SMP
+static bool cpuhp_is_ap_state(enum cpuhp_state state)
+{
+	/*
+	 * The extra check for CPUHP_TEARDOWN_CPU is only for documentation
+	 * purposes as that state is handled explicitly in cpu_down.
+	 */
+	return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
+}
+
 static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
 {
 	struct completion *done = bringup ? &st->done_up : &st->done_down;
@@ -1224,7 +1220,7 @@ int __boot_cpu_id;
 #endif /* CONFIG_SMP */
 
 /* Boot processor state steps */
-static struct cpuhp_step cpuhp_bp_states[] = {
+static struct cpuhp_step cpuhp_hp_states[] = {
 	[CPUHP_OFFLINE] = {
 		.name			= "offline",
 		.startup.single		= NULL,
@@ -1289,24 +1285,6 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 		.teardown.single	= NULL,
 		.cant_stop		= true,
 	},
-	/*
-	 * Handled on controll processor until the plugged processor manages
-	 * this itself.
-	 */
-	[CPUHP_TEARDOWN_CPU] = {
-		.name			= "cpu:teardown",
-		.startup.single		= NULL,
-		.teardown.single	= takedown_cpu,
-		.cant_stop		= true,
-	},
-#else
-	[CPUHP_BRINGUP_CPU] = { },
-#endif
-};
-
-/* Application processor state steps */
-static struct cpuhp_step cpuhp_ap_states[] = {
-#ifdef CONFIG_SMP
 	/* Final state before CPU kills itself */
 	[CPUHP_AP_IDLE_DEAD] = {
 		.name			= "idle:dead",
@@ -1340,6 +1318,16 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 	[CPUHP_AP_ONLINE] = {
 		.name			= "ap:online",
 	},
+	/*
+	 * Handled on controll processor until the plugged processor manages
+	 * this itself.
+	 */
+	[CPUHP_TEARDOWN_CPU] = {
+		.name			= "cpu:teardown",
+		.startup.single		= NULL,
+		.teardown.single	= takedown_cpu,
+		.cant_stop		= true,
+	},
 	/* Handle smpboot threads park/unpark */
 	[CPUHP_AP_SMPBOOT_THREADS] = {
 		.name			= "smpboot/threads:online",
@@ -1408,11 +1396,11 @@ static int cpuhp_reserve_state(enum cpuhp_state state)
 
 	switch (state) {
 	case CPUHP_AP_ONLINE_DYN:
-		step = cpuhp_ap_states + CPUHP_AP_ONLINE_DYN;
+		step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN;
 		end = CPUHP_AP_ONLINE_DYN_END;
 		break;
 	case CPUHP_BP_PREPARE_DYN:
-		step = cpuhp_bp_states + CPUHP_BP_PREPARE_DYN;
+		step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN;
 		end = CPUHP_BP_PREPARE_DYN_END;
 		break;
 	default:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 96db9ae5d5af..fc1c330c6bd6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -430,7 +430,7 @@ static void update_perf_cpu_limits(void)
 	WRITE_ONCE(perf_sample_allowed_ns, tmp);
 }
 
-static int perf_rotate_context(struct perf_cpu_context *cpuctx);
+static bool perf_rotate_context(struct perf_cpu_context *cpuctx);
 
 int perf_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
@@ -643,7 +643,7 @@ static void perf_event_update_sibling_time(struct perf_event *leader)
 {
 	struct perf_event *sibling;
 
-	list_for_each_entry(sibling, &leader->sibling_list, group_entry)
+	for_each_sibling_event(sibling, leader)
 		perf_event_update_time(sibling);
 }
 
@@ -724,9 +724,15 @@ static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
 
 static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
 {
-	struct perf_cgroup *cgrp_out = cpuctx->cgrp;
-	if (cgrp_out)
-		__update_cgrp_time(cgrp_out);
+	struct perf_cgroup *cgrp = cpuctx->cgrp;
+	struct cgroup_subsys_state *css;
+
+	if (cgrp) {
+		for (css = &cgrp->css; css; css = css->parent) {
+			cgrp = container_of(css, struct perf_cgroup, css);
+			__update_cgrp_time(cgrp);
+		}
+	}
 }
 
 static inline void update_cgrp_time_from_event(struct perf_event *event)
@@ -754,6 +760,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 {
 	struct perf_cgroup *cgrp;
 	struct perf_cgroup_info *info;
+	struct cgroup_subsys_state *css;
 
 	/*
 	 * ctx->lock held by caller
@@ -764,8 +771,12 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 		return;
 
 	cgrp = perf_cgroup_from_task(task, ctx);
-	info = this_cpu_ptr(cgrp->info);
-	info->timestamp = ctx->timestamp;
+
+	for (css = &cgrp->css; css; css = css->parent) {
+		cgrp = container_of(css, struct perf_cgroup, css);
+		info = this_cpu_ptr(cgrp->info);
+		info->timestamp = ctx->timestamp;
+	}
 }
 
 static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);
@@ -937,27 +948,39 @@ list_update_cgroup_event(struct perf_event *event,
 	if (!is_cgroup_event(event))
 		return;
 
-	if (add && ctx->nr_cgroups++)
-		return;
-	else if (!add && --ctx->nr_cgroups)
-		return;
 	/*
 	 * Because cgroup events are always per-cpu events,
 	 * this will always be called from the right CPU.
 	 */
 	cpuctx = __get_cpu_context(ctx);
-	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
-	/* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
-	if (add) {
+
+	/*
+	 * Since setting cpuctx->cgrp is conditional on the current @cgrp
+	 * matching the event's cgroup, we must do this for every new event,
+	 * because if the first would mismatch, the second would not try again
+	 * and we would leave cpuctx->cgrp unset.
+	 */
+	if (add && !cpuctx->cgrp) {
 		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
 
-		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
 		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 			cpuctx->cgrp = cgrp;
-	} else {
-		list_del(cpuctx_entry);
-		cpuctx->cgrp = NULL;
 	}
+
+	if (add && ctx->nr_cgroups++)
+		return;
+	else if (!add && --ctx->nr_cgroups)
+		return;
+
+	/* no cgroup running */
+	if (!add)
+		cpuctx->cgrp = NULL;
+
+	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
+	if (add)
+		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
+	else
+		list_del(cpuctx_entry);
 }
 
 #else /* !CONFIG_CGROUP_PERF */
@@ -1041,7 +1064,7 @@ list_update_cgroup_event(struct perf_event *event,
 static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
 {
 	struct perf_cpu_context *cpuctx;
-	int rotations = 0;
+	bool rotations;
 
 	lockdep_assert_irqs_disabled();
 
@@ -1460,8 +1483,21 @@ static enum event_type_t get_event_type(struct perf_event *event)
 	return event_type;
 }
 
-static struct list_head *
-ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
+/*
+ * Helper function to initialize event group nodes.
+ */
+static void init_event_group(struct perf_event *event)
+{
+	RB_CLEAR_NODE(&event->group_node);
+	event->group_index = 0;
+}
+
+/*
+ * Extract pinned or flexible groups from the context
+ * based on event attrs bits.
+ */
+static struct perf_event_groups *
+get_event_groups(struct perf_event *event, struct perf_event_context *ctx)
 {
 	if (event->attr.pinned)
 		return &ctx->pinned_groups;
@@ -1470,6 +1506,156 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 }
 
 /*
+ * Helper function to initializes perf_event_group trees.
+ */
+static void perf_event_groups_init(struct perf_event_groups *groups)
+{
+	groups->tree = RB_ROOT;
+	groups->index = 0;
+}
+
+/*
+ * Compare function for event groups;
+ *
+ * Implements complex key that first sorts by CPU and then by virtual index
+ * which provides ordering when rotating groups for the same CPU.
+ */
+static bool
+perf_event_groups_less(struct perf_event *left, struct perf_event *right)
+{
+	if (left->cpu < right->cpu)
+		return true;
+	if (left->cpu > right->cpu)
+		return false;
+
+	if (left->group_index < right->group_index)
+		return true;
+	if (left->group_index > right->group_index)
+		return false;
+
+	return false;
+}
+
+/*
+ * Insert @event into @groups' tree; using {@event->cpu, ++@groups->index} for
+ * key (see perf_event_groups_less). This places it last inside the CPU
+ * subtree.
+ */
+static void
+perf_event_groups_insert(struct perf_event_groups *groups,
+			 struct perf_event *event)
+{
+	struct perf_event *node_event;
+	struct rb_node *parent;
+	struct rb_node **node;
+
+	event->group_index = ++groups->index;
+
+	node = &groups->tree.rb_node;
+	parent = *node;
+
+	while (*node) {
+		parent = *node;
+		node_event = container_of(*node, struct perf_event, group_node);
+
+		if (perf_event_groups_less(event, node_event))
+			node = &parent->rb_left;
+		else
+			node = &parent->rb_right;
+	}
+
+	rb_link_node(&event->group_node, parent, node);
+	rb_insert_color(&event->group_node, &groups->tree);
+}
+
+/*
+ * Helper function to insert event into the pinned or flexible groups.
+ */
+static void
+add_event_to_groups(struct perf_event *event, struct perf_event_context *ctx)
+{
+	struct perf_event_groups *groups;
+