Merge tag 'v5.2-rc6' into perf/core, to refresh branch

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

5 files changed, 113 insertions, 30 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index f92d6ad5e080..1c9a4745e596 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -410,8 +410,6 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
-static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd);
-
 static __always_inline u64
 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 			u64 flags, struct perf_sample_data *sd)
@@ -442,24 +440,50 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 	return perf_event_output(event, sd, regs);
 }
 
+/*
+ * Support executing tracepoints in normal, irq, and nmi context that each call
+ * bpf_perf_event_output
+ */
+struct bpf_trace_sample_data {
+	struct perf_sample_data sds[3];
+};
+
+static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_trace_sds);
+static DEFINE_PER_CPU(int, bpf_trace_nest_level);
 BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags, void *, data, u64, size)
 {
-	struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd);
+	struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds);
+	int nest_level = this_cpu_inc_return(bpf_trace_nest_level);
 	struct perf_raw_record raw = {
 		.frag = {
 			.size = size,
 			.data = data,
 		},
 	};
+	struct perf_sample_data *sd;
+	int err;
 
-	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
-		return -EINVAL;
+	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	sd = &sds->sds[nest_level - 1];
+
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK))) {
+		err = -EINVAL;
+		goto out;
+	}
 
 	perf_sample_data_init(sd, 0, 0);
 	sd->raw = &raw;
 
-	return __bpf_perf_event_output(regs, map, flags, sd);
+	err = __bpf_perf_event_output(regs, map, flags, sd);
+
+out:
+	this_cpu_dec(bpf_trace_nest_level);
+	return err;
 }
 
 static const struct bpf_func_proto bpf_perf_event_output_proto = {
@@ -822,16 +846,48 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 /*
  * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp
  * to avoid potential recursive reuse issue when/if tracepoints are added
- * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack
+ * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack.
+ *
+ * Since raw tracepoints run despite bpf_prog_active, support concurrent usage
+ * in normal, irq, and nmi context.
  */
-static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs);
+struct bpf_raw_tp_regs {
+	struct pt_regs regs[3];
+};
+static DEFINE_PER_CPU(struct bpf_raw_tp_regs, bpf_raw_tp_regs);
+static DEFINE_PER_CPU(int, bpf_raw_tp_nest_level);
+static struct pt_regs *get_bpf_raw_tp_regs(void)
+{
+	struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level);
+
+	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) {
+		this_cpu_dec(bpf_raw_tp_nest_level);
+		return ERR_PTR(-EBUSY);
+	}
+
+	return &tp_regs->regs[nest_level - 1];
+}
+
+static void put_bpf_raw_tp_regs(void)
+{
+	this_cpu_dec(bpf_raw_tp_nest_level);
+}
+
 BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags, void *, data, u64, size)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
-	return ____bpf_perf_event_output(regs, map, flags, data, size);
+	ret = ____bpf_perf_event_output(regs, map, flags, data, size);
+
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
@@ -848,12 +904,18 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
 	/* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */
-	return bpf_get_stackid((unsigned long) regs, (unsigned long) map,
-			       flags, 0, 0);
+	ret = bpf_get_stackid((unsigned long) regs, (unsigned long) map,
+			      flags, 0, 0);
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
@@ -868,11 +930,17 @@ static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
 BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   void *, buf, u32, size, u64, flags)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
-	return bpf_get_stack((unsigned long) regs, (unsigned long) buf,
-			     (unsigned long) size, flags, 0);
+	ret = bpf_get_stack((unsigned long) regs, (unsigned long) buf,
+			    (unsigned long) size, flags, 0);
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a12aff849c04..38277af44f5c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -34,6 +34,7 @@
 #include <linux/hash.h>
 #include <linux/rcupdate.h>
 #include <linux/kprobes.h>
+#include <linux/memory.h>
 
 #include <trace/events/sched.h>
 
@@ -2610,10 +2611,12 @@ static void ftrace_run_update_code(int command)
 {
 	int ret;
 
+	mutex_lock(&text_mutex);
+
 	ret = ftrace_arch_code_modify_prepare();
 	FTRACE_WARN_ON(ret);
 	if (ret)
-		return;
+		goto out_unlock;
 
 	/*
 	 * By default we use stop_machine() to modify the code.
@@ -2625,6 +2628,9 @@ static void ftrace_run_update_code(int command)
 
 	ret = ftrace_arch_code_modify_post_process();
 	FTRACE_WARN_ON(ret);
+
+out_unlock:
+	mutex_unlock(&text_mutex);
 }
 
 static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
@@ -2935,14 +2941,13 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 			p = &pg->records[i];
 			p->flags = rec_flags;
 
-#ifndef CC_USING_NOP_MCOUNT
 			/*
 			 * Do the initial record conversion from mcount jump
 			 * to the NOP instructions.
 			 */
-			if (!ftrace_code_disable(mod, p))
+			if (!__is_defined(CC_USING_NOP_MCOUNT) &&
+			    !ftrace_code_disable(mod, p))
 				break;
-#endif
 
 			update_cnt++;
 		}
@@ -4221,10 +4226,13 @@ void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper,
 	struct ftrace_func_entry *entry;
 	struct ftrace_func_map *map;
 	struct hlist_head *hhd;
-	int size = 1 << mapper->hash.size_bits;
-	int i;
+	int size, i;
+
+	if (!mapper)
+		return;
 
 	if (free_func && mapper->hash.count) {
+		size = 1 << mapper->hash.size_bits;
 		for (i = 0; i < size; i++) {
 			hhd = &mapper->hash.buckets[i];
 			hlist_for_each_entry(entry, hhd, hlist) {
@@ -5776,6 +5784,7 @@ void ftrace_module_enable(struct module *mod)
 	struct ftrace_page *pg;
 
 	mutex_lock(&ftrace_lock);
+	mutex_lock(&text_mutex);
 
 	if (ftrace_disabled)
 		goto out_unlock;
@@ -5837,6 +5846,7 @@ void ftrace_module_enable(struct module *mod)
 		ftrace_arch_code_modify_post_process();
 
  out_unlock:
+	mutex_unlock(&text_mutex);
 	mutex_unlock(&ftrace_lock);
 
 	process_cached_mods(mod->name);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1c80521fd436..83e08b78dbee 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6923,7 +6923,7 @@ struct tracing_log_err {
 
 static DEFINE_MUTEX(tracing_err_log_lock);
 
-struct tracing_log_err *get_tracing_log_err(struct trace_array *tr)
+static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr)
 {
 	struct tracing_log_err *err;
 
@@ -8192,7 +8192,7 @@ static const struct file_operations buffer_percent_fops = {
 	.llseek		= default_llseek,
 };
 
-struct dentry *trace_instance_dir;
+static struct dentry *trace_instance_dir;
 
 static void
 init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 54373d93e251..ba751f993c3b 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1057,7 +1057,7 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 
 	trace_seq_puts(s, "<stack trace>\n");
 
-	for (p = field->caller; p && *p != ULONG_MAX && p < end; p++) {
+	for (p = field->caller; p && p < end && *p != ULONG_MAX; p++) {
 
 		if (trace_seq_has_overflowed(s))
 			break;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 0d60d6856de5..7860e3f59fad 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -426,8 +426,6 @@ end:
 /*
  * Argument syntax:
  *  - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS]
- *
- *  - Remove uprobe: -:[GRP/]EVENT
  */
 static int trace_uprobe_create(int argc, const char **argv)
 {
@@ -443,10 +441,17 @@ static int trace_uprobe_create(int argc, const char **argv)
 	ret = 0;
 	ref_ctr_offset = 0;
 
-	/* argc must be >= 1 */
-	if (argv[0][0] == 'r')
+	switch (argv[0][0]) {
+	case 'r':
 		is_return = true;
-	else if (argv[0][0] != 'p' || argc < 2)
+		break;
+	case 'p':
+		break;
+	default:
+		return -ECANCELED;
+	}
+
+	if (argc < 2)
 		return -ECANCELED;
 
 	if (argv[0][1] == ':')