Merge tag 'perf-core-for-mingo-4.12-20170503' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

Fixes:

- Support setting probes in versioned user space symbols, such as
  pthread_create@@GLIBC_2.1, picking the default one, more work
  needed to make it possible to set it on the other versions, as
  the 'perf probe' syntax already uses @ for other purposes.
  (Paul Clarke)

- Do not special case address zero as an error for routines that
  return addresses (symbol lookup), instead use the return as the
  success/error indication and pass a pointer to return the address,
  fixing 'perf test vmlinux' (the one that compares address between
  vmlinux and kallsyms) on s/390, where the '_text' address is equal
  to zero (Arnaldo Carvalho de Melo)

Infrastructure changes:

- More header sanitization, moving stuff out of util.h into
  more appropriate headers and objects and sometimes creating
  new ones (Arnaldo Carvalho de Melo)

- Refactor a duplicated code for obtaining config file name (Taeung Song)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/events/core.c

@@ -48,6 +48,8 @@
 #include <linux/parser.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/mm.h>
+#include <linux/proc_ns.h>
+#include <linux/mount.h>
 
 #include "internal.h"
 
@@ -379,6 +381,7 @@ static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
+static atomic_t nr_namespaces_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
 static atomic_t nr_freq_events __read_mostly;
 static atomic_t nr_switch_events __read_mostly;
@@ -3991,6 +3994,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_mmap_events);
 	if (event->attr.comm)
 		atomic_dec(&nr_comm_events);
+	if (event->attr.namespaces)
+		atomic_dec(&nr_namespaces_events);
 	if (event->attr.task)
 		atomic_dec(&nr_task_events);
 	if (event->attr.freq)
@@ -6491,6 +6496,7 @@ static void perf_event_task(struct task_struct *task,
 void perf_event_fork(struct task_struct *task)
 {
 	perf_event_task(task, NULL, 1);
+	perf_event_namespaces(task);
 }
 
 /*
@@ -6592,6 +6598,132 @@ void perf_event_comm(struct task_struct *task, bool exec)
 	perf_event_comm_event(&comm_event);
 }
 
+/*
+ * namespaces tracking
+ */
+
+struct perf_namespaces_event {
+	struct task_struct		*task;
+
+	struct {
+		struct perf_event_header	header;
+
+		u32				pid;
+		u32				tid;
+		u64				nr_namespaces;
+		struct perf_ns_link_info	link_info[NR_NAMESPACES];
+	} event_id;
+};
+
+static int perf_event_namespaces_match(struct perf_event *event)
+{
+	return event->attr.namespaces;
+}
+
+static void perf_event_namespaces_output(struct perf_event *event,
+					 void *data)
+{
+	struct perf_namespaces_event *namespaces_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	if (!perf_event_namespaces_match(event))
+		return;
+
+	perf_event_header__init_id(&namespaces_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				namespaces_event->event_id.header.size);
+	if (ret)
+		return;
+
+	namespaces_event->event_id.pid = perf_event_pid(event,
+							namespaces_event->task);
+	namespaces_event->event_id.tid = perf_event_tid(event,
+							namespaces_event->task);
+
+	perf_output_put(&handle, namespaces_event->event_id);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,
+				   struct task_struct *task,
+				   const struct proc_ns_operations *ns_ops)
+{
+	struct path ns_path;
+	struct inode *ns_inode;
+	void *error;
+
+	error = ns_get_path(&ns_path, task, ns_ops);
+	if (!error) {
+		ns_inode = ns_path.dentry->d_inode;
+		ns_link_info->dev = new_encode_dev(ns_inode->i_sb->s_dev);
+		ns_link_info->ino = ns_inode->i_ino;
+	}
+}
+
+void perf_event_namespaces(struct task_struct *task)
+{
+	struct perf_namespaces_event namespaces_event;
+	struct perf_ns_link_info *ns_link_info;
+
+	if (!atomic_read(&nr_namespaces_events))
+		return;
+
+	namespaces_event = (struct perf_namespaces_event){
+		.task	= task,
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_NAMESPACES,
+				.misc = 0,
+				.size = sizeof(namespaces_event.event_id),
+			},
+			/* .pid */
+			/* .tid */
+			.nr_namespaces = NR_NAMESPACES,
+			/* .link_info[NR_NAMESPACES] */
+		},
+	};
+
+	ns_link_info = namespaces_event.event_id.link_info;
+
+	perf_fill_ns_link_info(&ns_link_info[MNT_NS_INDEX],
+			       task, &mntns_operations);
+
+#ifdef CONFIG_USER_NS
+	perf_fill_ns_link_info(&ns_link_info[USER_NS_INDEX],
+			       task, &userns_operations);
+#endif
+#ifdef CONFIG_NET_NS
+	perf_fill_ns_link_info(&ns_link_info[NET_NS_INDEX],
+			       task, &netns_operations);
+#endif
+#ifdef CONFIG_UTS_NS
+	perf_fill_ns_link_info(&ns_link_info[UTS_NS_INDEX],
+			       task, &utsns_operations);
+#endif
+#ifdef CONFIG_IPC_NS
+	perf_fill_ns_link_info(&ns_link_info[IPC_NS_INDEX],
+			       task, &ipcns_operations);
+#endif
+#ifdef CONFIG_PID_NS
+	perf_fill_ns_link_info(&ns_link_info[PID_NS_INDEX],
+			       task, &pidns_operations);
+#endif
+#ifdef CONFIG_CGROUPS
+	perf_fill_ns_link_info(&ns_link_info[CGROUP_NS_INDEX],
+			       task, &cgroupns_operations);
+#endif
+
+	perf_iterate_sb(perf_event_namespaces_output,
+			&namespaces_event,
+			NULL);
+}
+
 /*
  * mmap tracking
  */
@@ -9146,6 +9278,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_mmap_events);
 	if (event->attr.comm)
 		atomic_inc(&nr_comm_events);
+	if (event->attr.namespaces)
+		atomic_inc(&nr_namespaces_events);
 	if (event->attr.task)
 		atomic_inc(&nr_task_events);
 	if (event->attr.freq)
@@ -9691,6 +9825,11 @@ SYSCALL_DEFINE5(perf_event_open,
 			return -EACCES;
 	}
 
+	if (attr.namespaces) {
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+	}
+
 	if (attr.freq) {
 		if (attr.sample_freq > sysctl_perf_event_sample_rate)
 			return -EINVAL;

kernel/events/ring_buffer.c

@@ -297,6 +297,19 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 		rb->paused = 1;
 }
 
+void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags)
+{
+	/*
+	 * OVERWRITE is determined by perf_aux_output_end() and can't
+	 * be passed in directly.
+	 */
+	if (WARN_ON_ONCE(flags & PERF_AUX_FLAG_OVERWRITE))
+		return;
+
+	handle->aux_flags |= flags;
+}
+EXPORT_SYMBOL_GPL(perf_aux_output_flag);
+
 /*
  * This is called before hardware starts writing to the AUX area to
  * obtain an output handle and make sure there's room in the buffer.
@@ -360,6 +373,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	handle->event = event;
 	handle->head = aux_head;
 	handle->size = 0;
+	handle->aux_flags = 0;
 
 	/*
 	 * In overwrite mode, AUX data stores do not depend on aux_tail,
@@ -408,34 +422,32 @@ err:
  * of the AUX buffer management code is that after pmu::stop(), the AUX
  * transaction must be stopped and therefore drop the AUX reference count.
  */
-void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
-			 bool truncated)
+void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 {
+	bool wakeup = !!(handle->aux_flags & PERF_AUX_FLAG_TRUNCATED);
 	struct ring_buffer *rb = handle->rb;
-	bool wakeup = truncated;
 	unsigned long aux_head;
-	u64 flags = 0;
-
-	if (truncated)
-		flags |= PERF_AUX_FLAG_TRUNCATED;
 
 	/* in overwrite mode, driver provides aux_head via handle */
 	if (rb->aux_overwrite) {
-		flags |= PERF_AUX_FLAG_OVERWRITE;
+		handle->aux_flags |= PERF_AUX_FLAG_OVERWRITE;
 
 		aux_head = handle->head;
 		local_set(&rb->aux_head, aux_head);
 	} else {
+		handle->aux_flags &= ~PERF_AUX_FLAG_OVERWRITE;
+
 		aux_head = local_read(&rb->aux_head);
 		local_add(size, &rb->aux_head);
 	}
 
-	if (size || flags) {
+	if (size || handle->aux_flags) {
 		/*
 		 * Only send RECORD_AUX if we have something useful to communicate
 		 */
 
-		perf_event_aux_event(handle->event, aux_head, size, flags);
+		perf_event_aux_event(handle->event, aux_head, size,
+		                     handle->aux_flags);
 	}
 
 	aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
@@ -446,7 +458,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 	}
 
 	if (wakeup) {
-		if (truncated)
+		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
 			handle->event->pending_disable = 1;
 		perf_output_wakeup(handle);
 	}

kernel/fork.c

@@ -2352,6 +2352,8 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 		}
 	}
 
+	perf_event_namespaces(current);
+
 bad_unshare_cleanup_cred:
 	if (new_cred)
 		put_cred(new_cred);

kernel/kprobes.c

@@ -1391,21 +1391,19 @@ bool within_kprobe_blacklist(unsigned long addr)
  * This returns encoded errors if it fails to look up symbol or invalid
  * combination of parameters.
  */
-static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
+static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr,
+			const char *symbol_name, unsigned int offset)
 {
-	kprobe_opcode_t *addr = p->addr;
-
-	if ((p->symbol_name && p->addr) ||
-	    (!p->symbol_name && !p->addr))
+	if ((symbol_name && addr) || (!symbol_name && !addr))
 		goto invalid;
 
-	if (p->symbol_name) {
-		kprobe_lookup_name(p->symbol_name, addr);
+	if (symbol_name) {
+		kprobe_lookup_name(symbol_name, addr);
 		if (!addr)
 			return ERR_PTR(-ENOENT);
 	}
 
-	addr = (kprobe_opcode_t *)(((char *)addr) + p->offset);
+	addr = (kprobe_opcode_t *)(((char *)addr) + offset);
 	if (addr)
 		return addr;
 
@@ -1413,6 +1411,11 @@ invalid:
 	return ERR_PTR(-EINVAL);
 }
 
+static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
+{
+	return _kprobe_addr(p->addr, p->symbol_name, p->offset);
+}
+
 /* Check passed kprobe is valid and return kprobe in kprobe_table. */
 static struct kprobe *__get_valid_kprobe(struct kprobe *p)
 {
@@ -1740,11 +1743,12 @@ void unregister_kprobes(struct kprobe **kps, int num)
 }
 EXPORT_SYMBOL_GPL(unregister_kprobes);
 
-int __weak __kprobes kprobe_exceptions_notify(struct notifier_block *self,
-					      unsigned long val, void *data)
+int __weak kprobe_exceptions_notify(struct notifier_block *self,
+					unsigned long val, void *data)
 {
 	return NOTIFY_DONE;
 }
+NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
 static struct notifier_block kprobe_exceptions_nb = {
 	.notifier_call = kprobe_exceptions_notify,
@@ -1875,6 +1879,25 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(pre_handler_kretprobe);
 
+bool __weak arch_function_offset_within_entry(unsigned long offset)
+{
+	return !offset;
+}
+
+bool function_offset_within_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
+{
+	kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset);
+
+	if (IS_ERR(kp_addr))
+		return false;
+
+	if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) ||
+						!arch_function_offset_within_entry(offset))
+		return false;
+
+	return true;
+}
+
 int register_kretprobe(struct kretprobe *rp)
 {
 	int ret = 0;
@@ -1882,6 +1905,9 @@ int register_kretprobe(struct kretprobe *rp)
 	int i;
 	void *addr;
 
+	if (!function_offset_within_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset))
+		return -EINVAL;
+
 	if (kretprobe_blacklist_size) {
 		addr = kprobe_addr(&rp->kp);
 		if (IS_ERR(addr))

kernel/nsproxy.c

@@ -26,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/syscalls.h>
 #include <linux/cgroup.h>
+#include <linux/perf_event.h>
 
 static struct kmem_cache *nsproxy_cachep;
 
@@ -262,6 +263,8 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 		goto out;
 	}
 	switch_task_namespaces(tsk, new_nsproxy);
+
+	perf_event_namespaces(tsk);
 out:
 	fput(file);
 	return err;

kernel/trace/Kconfig

@@ -455,7 +455,7 @@ config UPROBE_EVENTS
 	select UPROBES
 	select PROBE_EVENTS
 	select TRACING
-	default n
+	default y
 	help
 	  This allows the user to add tracing events on top of userspace
 	  dynamic events (similar to tracepoints) on the fly via the trace

kernel/trace/trace.c

@@ -4355,6 +4355,7 @@ static const char readme_msg[] =
 	"\t           -:[<group>/]<event>\n"
 #ifdef CONFIG_KPROBE_EVENTS
 	"\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
+  "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n"
 #endif
 #ifdef CONFIG_UPROBE_EVENTS
 	"\t    place: <path>:<offset>\n"

kernel/trace/trace_kprobe.c

@@ -681,10 +681,6 @@ static int create_trace_kprobe(int argc, char **argv)
 		return -EINVAL;
 	}
 	if (isdigit(argv[1][0])) {
-		if (is_return) {
-			pr_info("Return probe point must be a symbol.\n");
-			return -EINVAL;
-		}
 		/* an address specified */
 		ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr);
 		if (ret) {
@@ -700,8 +696,9 @@ static int create_trace_kprobe(int argc, char **argv)
 			pr_info("Failed to parse symbol.\n");
 			return ret;
 		}
-		if (offset && is_return) {
-			pr_info("Return probe must be used without offset.\n");
+		if (offset && is_return &&
+		    !function_offset_within_entry(NULL, symbol, offset)) {
+			pr_info("Given offset is not valid for return probe.\n");
 			return -EINVAL;
 		}
 	}