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

6 files changed, 90 insertions, 40 deletions

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index a515f7b..da0f536 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -52,6 +52,7 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
 		e = rcu_dereference_protected(parent->bpf.effective[type],
 					      lockdep_is_held(&cgroup_mutex));
 		rcu_assign_pointer(cgrp->bpf.effective[type], e);
+		cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type];
 	}
 }
 
@@ -82,30 +83,63 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
  *
  * Must be called with cgroup_mutex held.
  */
-void __cgroup_bpf_update(struct cgroup *cgrp,
-			 struct cgroup *parent,
-			 struct bpf_prog *prog,
-			 enum bpf_attach_type type)
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+			struct bpf_prog *prog, enum bpf_attach_type type,
+			bool new_overridable)
 {
-	struct bpf_prog *old_prog, *effective;
+	struct bpf_prog *old_prog, *effective = NULL;
 	struct cgroup_subsys_state *pos;
+	bool overridable = true;
 
-	old_prog = xchg(cgrp->bpf.prog + type, prog);
+	if (parent) {
+		overridable = !parent->bpf.disallow_override[type];
+		effective = rcu_dereference_protected(parent->bpf.effective[type],
+						      lockdep_is_held(&cgroup_mutex));
+	}
+
+	if (prog && effective && !overridable)
+		/* if parent has non-overridable prog attached, disallow
+		 * attaching new programs to descendent cgroup
+		 */
+		return -EPERM;
+
+	if (prog && effective && overridable != new_overridable)
+		/* if parent has overridable prog attached, only
+		 * allow overridable programs in descendent cgroup
+		 */
+		return -EPERM;
 
-	effective = (!prog && parent) ?
-		rcu_dereference_protected(parent->bpf.effective[type],
-					  lockdep_is_held(&cgroup_mutex)) :
-		prog;
+	old_prog = cgrp->bpf.prog[type];
+
+	if (prog) {
+		overridable = new_overridable;
+		effective = prog;
+		if (old_prog &&
+		    cgrp->bpf.disallow_override[type] == new_overridable)
+			/* disallow attaching non-overridable on top
+			 * of existing overridable in this cgroup
+			 * and vice versa
+			 */
+			return -EPERM;
+	}
+
+	if (!prog && !old_prog)
+		/* report error when trying to detach and nothing is attached */
+		return -ENOENT;
+
+	cgrp->bpf.prog[type] = prog;
 
 	css_for_each_descendant_pre(pos, &cgrp->self) {
 		struct cgroup *desc = container_of(pos, struct cgroup, self);
 
 		/* skip the subtree if the descendant has its own program */
-		if (desc->bpf.prog[type] && desc != cgrp)
+		if (desc->bpf.prog[type] && desc != cgrp) {
 			pos = css_rightmost_descendant(pos);
-		else
+		} else {
 			rcu_assign_pointer(desc->bpf.effective[type],
 					   effective);
+			desc->bpf.disallow_override[type] = !overridable;
+		}
 	}
 
 	if (prog)
@@ -115,6 +149,7 @@ void __cgroup_bpf_update(struct cgroup *cgrp,
 		bpf_prog_put(old_prog);
 		static_branch_dec(&cgroup_bpf_enabled_key);
 	}
+	return 0;
 }
 
 /**
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 08a4d28..f74ca17 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -935,13 +935,14 @@ static int bpf_obj_get(const union bpf_attr *attr)
 
 #ifdef CONFIG_CGROUP_BPF
 
-#define BPF_PROG_ATTACH_LAST_FIELD attach_type
+#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
 
 static int bpf_prog_attach(const union bpf_attr *attr)
 {
+	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
 	struct cgroup *cgrp;
-	enum bpf_prog_type ptype;
+	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -949,6 +950,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_PROG_ATTACH))
 		return -EINVAL;
 
+	if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE)
+		return -EINVAL;
+
 	switch (attr->attach_type) {
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
@@ -971,10 +975,13 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		return PTR_ERR(cgrp);
 	}
 
-	cgroup_bpf_update(cgrp, prog, attr->attach_type);
+	ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
+				attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
+	if (ret)
+		bpf_prog_put(prog);
 	cgroup_put(cgrp);
 
-	return 0;
+	return ret;
 }
 
 #define BPF_PROG_DETACH_LAST_FIELD attach_type
@@ -982,6 +989,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 static int bpf_prog_detach(const union bpf_attr *attr)
 {
 	struct cgroup *cgrp;
+	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -997,7 +1005,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		if (IS_ERR(cgrp))
 			return PTR_ERR(cgrp);
 
-		cgroup_bpf_update(cgrp, NULL, attr->attach_type);
+		ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
 		cgroup_put(cgrp);
 		break;
 
@@ -1005,7 +1013,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		return -EINVAL;
 	}
 
-	return 0;
+	return ret;
 }
 #endif /* CONFIG_CGROUP_BPF */
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 688dd02..53bbca7 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -6498,15 +6498,16 @@ static __init int cgroup_namespaces_init(void)
 subsys_initcall(cgroup_namespaces_init);
 
 #ifdef CONFIG_CGROUP_BPF
-void cgroup_bpf_update(struct cgroup *cgrp,
-		       struct bpf_prog *prog,
-		       enum bpf_attach_type type)
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, bool overridable)
 {
 	struct cgroup *parent = cgroup_parent(cgrp);
+	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	__cgroup_bpf_update(cgrp, parent, prog, type);
+	ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
 	mutex_unlock(&cgroup_mutex);
+	return ret;
 }
 #endif /* CONFIG_CGROUP_BPF */
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e5aaa80..e235bb9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3487,14 +3487,15 @@ struct perf_read_data {
 	int ret;
 };
 
-static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
 {
-	int event_cpu = event->oncpu;
 	u16 local_pkg, event_pkg;
 
 	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
-		event_pkg =  topology_physical_package_id(event_cpu);
-		local_pkg =  topology_physical_package_id(local_cpu);
+		int local_cpu = smp_processor_id();
+
+		event_pkg = topology_physical_package_id(event_cpu);
+		local_pkg = topology_physical_package_id(local_cpu);
 
 		if (event_pkg == local_pkg)
 			return local_cpu;
@@ -3624,7 +3625,7 @@ u64 perf_event_read_local(struct perf_event *event)
 
 static int perf_event_read(struct perf_event *event, bool group)
 {
-	int ret = 0, cpu_to_read, local_cpu;
+	int event_cpu, ret = 0;
 
 	/*
 	 * If event is enabled and currently active on a CPU, update the
@@ -3637,21 +3638,25 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.ret = 0,
 		};
 
-		local_cpu = get_cpu();
-		cpu_to_read = find_cpu_to_read(event, local_cpu);
-		put_cpu();
+		event_cpu = READ_ONCE(event->oncpu);
+		if ((unsigned)event_cpu >= nr_cpu_ids)
+			return 0;
+
+		preempt_disable();
+		event_cpu = __perf_event_read_cpu(event, event_cpu);
 
 		/*
 		 * Purposely ignore the smp_call_function_single() return
 		 * value.
 		 *
-		 * If event->oncpu isn't a valid CPU it means the event got
+		 * If event_cpu isn't a valid CPU it means the event got
 		 * scheduled out and that will have updated the event count.
 		 *
 		 * Therefore, either way, we'll have an up-to-date event count
 		 * after this.
 		 */
-		(void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
+		(void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1);
+		preempt_enable();
 		ret = data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index b6e4c16..9c15a91 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -18,10 +18,8 @@ void print_stack_trace(struct stack_trace *trace, int spaces)
 	if (WARN_ON(!trace->entries))
 		return;
 
-	for (i = 0; i < trace->nr_entries; i++) {
-		printk("%*c", 1 + spaces, ' ');
-		print_ip_sym(trace->entries[i]);
-	}
+	for (i = 0; i < trace->nr_entries; i++)
+		printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]);
 }
 EXPORT_SYMBOL_GPL(print_stack_trace);
 
@@ -29,7 +27,6 @@ int snprint_stack_trace(char *buf, size_t size,
 			struct stack_trace *trace, int spaces)
 {
 	int i;
-	unsigned long ip;
 	int generated;
 	int total = 0;
 
@@ -37,9 +34,8 @@ int snprint_stack_trace(char *buf, size_t size,
 		return 0;
 
 	for (i = 0; i < trace->nr_entries; i++) {
-		ip = trace->entries[i];
-		generated = snprintf(buf, size, "%*c[<%p>] %pS\n",
-				1 + spaces, ' ', (void *) ip, (void *) ip);
+		generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ',
+				     (void *)trace->entries[i]);
 
 		total += generated;
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 74e0388..fc6f740 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -725,6 +725,11 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		 */
 		if (delta == 0) {
 			tick_nohz_restart(ts, now);
+			/*
+			 * Make sure next tick stop doesn't get fooled by past
+			 * clock deadline
+			 */
+			ts->next_tick = 0;
 			goto out;
 		}
 	}