Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main kernel side changes in this cycle were:

   - Various Intel-PT updates and optimizations (Alexander Shishkin)

   - Prohibit kprobes on Xen/KVM emulate prefixes (Masami Hiramatsu)

   - Add support for LSM and SELinux checks to control access to the
     perf syscall (Joel Fernandes)

   - Misc other changes, optimizations, fixes and cleanups - see the
     shortlog for details.

  There were numerous tooling changes as well - 254 non-merge commits.
  Here are the main changes - too many to list in detail:

   - Enhancements to core tooling infrastructure, perf.data, libperf,
     libtraceevent, event parsing, vendor events, Intel PT, callchains,
     BPF support and instruction decoding.

   - There were updates to the following tools:

        perf annotate
        perf diff
        perf inject
        perf kvm
        perf list
        perf maps
        perf parse
        perf probe
        perf record
        perf report
        perf script
        perf stat
        perf test
        perf trace

   - And a lot of other changes: please see the shortlog and Git log for
     more details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (279 commits)
  perf parse: Fix potential memory leak when handling tracepoint errors
  perf probe: Fix spelling mistake "addrees" -> "address"
  libtraceevent: Fix memory leakage in copy_filter_type
  libtraceevent: Fix header installation
  perf intel-bts: Does not support AUX area sampling
  perf intel-pt: Add support for decoding AUX area samples
  perf intel-pt: Add support for recording AUX area samples
  perf pmu: When using default config, record which bits of config were changed by the user
  perf auxtrace: Add support for queuing AUX area samples
  perf session: Add facility to peek at all events
  perf auxtrace: Add support for dumping AUX area samples
  perf inject: Cut AUX area samples
  perf record: Add aux-sample-size config term
  perf record: Add support for AUX area sampling
  perf auxtrace: Add support for AUX area sample recording
  perf auxtrace: Move perf_evsel__find_pmu()
  perf record: Add a function to test for kernel support for AUX area sampling
  perf tools: Add kernel AUX area sampling definitions
  perf/core: Make the mlock accounting simple again
  perf report: Jump to symbol source view from total cycles view
  ...

4 files changed, 120 insertions, 8 deletions

diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index a3763247547c..20d8cf194fb7 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1818,6 +1818,14 @@ union security_list_options {
 	void (*bpf_prog_free_security)(struct bpf_prog_aux *aux);
 #endif /* CONFIG_BPF_SYSCALL */
 	int (*locked_down)(enum lockdown_reason what);
+#ifdef CONFIG_PERF_EVENTS
+	int (*perf_event_open)(struct perf_event_attr *attr, int type);
+	int (*perf_event_alloc)(struct perf_event *event);
+	void (*perf_event_free)(struct perf_event *event);
+	int (*perf_event_read)(struct perf_event *event);
+	int (*perf_event_write)(struct perf_event *event);
+
+#endif
 };
 
 struct security_hook_heads {
@@ -2060,6 +2068,13 @@ struct security_hook_heads {
 	struct hlist_head bpf_prog_free_security;
 #endif /* CONFIG_BPF_SYSCALL */
 	struct hlist_head locked_down;
+#ifdef CONFIG_PERF_EVENTS
+	struct hlist_head perf_event_open;
+	struct hlist_head perf_event_alloc;
+	struct hlist_head perf_event_free;
+	struct hlist_head perf_event_read;
+	struct hlist_head perf_event_write;
+#endif
 } __randomize_layout;
 
 /*
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a07bfdb7d8ea..6d4c22aee384 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -56,6 +56,7 @@ struct perf_guest_info_callbacks {
 #include <linux/perf_regs.h>
 #include <linux/cgroup.h>
 #include <linux/refcount.h>
+#include <linux/security.h>
 #include <asm/local.h>
 
 struct perf_callchain_entry {
@@ -248,6 +249,8 @@ struct perf_event;
 #define PERF_PMU_CAP_NO_EXCLUDE			0x80
 #define PERF_PMU_CAP_AUX_OUTPUT			0x100
 
+struct perf_output_handle;
+
 /**
  * struct pmu - generic performance monitoring unit
  */
@@ -409,6 +412,15 @@ struct pmu {
 	 */
 	size_t				task_ctx_size;
 
+	/*
+	 * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data)
+	 * can be synchronized using this function. See Intel LBR callstack support
+	 * implementation and Perf core context switch handling callbacks for usage
+	 * examples.
+	 */
+	void (*swap_task_ctx)		(struct perf_event_context *prev,
+					 struct perf_event_context *next);
+					/* optional */
 
 	/*
 	 * Set up pmu-private data structures for an AUX area
@@ -423,6 +435,19 @@ struct pmu {
 	void (*free_aux)		(void *aux); /* optional */
 
 	/*
+	 * Take a snapshot of the AUX buffer without touching the event
+	 * state, so that preempting ->start()/->stop() callbacks does
+	 * not interfere with their logic. Called in PMI context.
+	 *
+	 * Returns the size of AUX data copied to the output handle.
+	 *
+	 * Optional.
+	 */
+	long (*snapshot_aux)		(struct perf_event *event,
+					 struct perf_output_handle *handle,
+					 unsigned long size);
+
+	/*
 	 * Validate address range filters: make sure the HW supports the
 	 * requested configuration and number of filters; return 0 if the
 	 * supplied filters are valid, -errno otherwise.
@@ -721,6 +746,9 @@ struct perf_event {
 	struct perf_cgroup		*cgrp; /* cgroup event is attach to */
 #endif
 
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
 	struct list_head		sb_list;
 #endif /* CONFIG_PERF_EVENTS */
 };
@@ -960,6 +988,7 @@ struct perf_sample_data {
 		u32	reserved;
 	}				cpu_entry;
 	struct perf_callchain_entry	*callchain;
+	u64				aux_size;
 
 	/*
 	 * regs_user may point to task_pt_regs or to regs_user_copy, depending
@@ -1241,19 +1270,41 @@ extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
 int perf_event_max_stack_handler(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp, loff_t *ppos);
 
-static inline bool perf_paranoid_tracepoint_raw(void)
+/* Access to perf_event_open(2) syscall. */
+#define PERF_SECURITY_OPEN		0
+
+/* Finer grained perf_event_open(2) access control. */
+#define PERF_SECURITY_CPU		1
+#define PERF_SECURITY_KERNEL		2
+#define PERF_SECURITY_TRACEPOINT	3
+
+static inline int perf_is_paranoid(void)
 {
 	return sysctl_perf_event_paranoid > -1;
 }
 
-static inline bool perf_paranoid_cpu(void)
+static inline int perf_allow_kernel(struct perf_event_attr *attr)
 {
-	return sysctl_perf_event_paranoid > 0;
+	if (sysctl_perf_event_paranoid > 1 && !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	return security_perf_event_open(attr, PERF_SECURITY_KERNEL);
 }
 
-static inline bool perf_paranoid_kernel(void)
+static inline int perf_allow_cpu(struct perf_event_attr *attr)
 {
-	return sysctl_perf_event_paranoid > 1;
+	if (sysctl_perf_event_paranoid > 0 && !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	return security_perf_event_open(attr, PERF_SECURITY_CPU);
+}
+
+static inline int perf_allow_tracepoint(struct perf_event_attr *attr)
+{
+	if (sysctl_perf_event_paranoid > -1 && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT);
 }
 
 extern void perf_event_init(void);
@@ -1327,6 +1378,9 @@ extern unsigned int perf_output_copy(struct perf_output_handle *handle,
 			     const void *buf, unsigned int len);
 extern unsigned int perf_output_skip(struct perf_output_handle *handle,
 				     unsigned int len);
+extern long perf_output_copy_aux(struct perf_output_handle *aux_handle,
+				 struct perf_output_handle *handle,
+				 unsigned long from, unsigned long to);
 extern int perf_swevent_get_recursion_context(void);
 extern void perf_swevent_put_recursion_context(int rctx);
 extern u64 perf_swevent_set_period(struct perf_event *event);
diff --git a/include/linux/security.h b/include/linux/security.h
index 9df7547afc0c..06ff66834501 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1895,5 +1895,42 @@ static inline void security_bpf_prog_free(struct bpf_prog_aux *aux)
 #endif /* CONFIG_SECURITY */
 #endif /* CONFIG_BPF_SYSCALL */
 
-#endif /* ! __LINUX_SECURITY_H */
+#ifdef CONFIG_PERF_EVENTS
+struct perf_event_attr;
+struct perf_event;
+
+#ifdef CONFIG_SECURITY
+extern int security_perf_event_open(struct perf_event_attr *attr, int type);
+extern int security_perf_event_alloc(struct perf_event *event);
+extern void security_perf_event_free(struct perf_event *event);
+extern int security_perf_event_read(struct perf_event *event);
+extern int security_perf_event_write(struct perf_event *event);
+#else
+static inline int security_perf_event_open(struct perf_event_attr *attr,
+					   int type)
+{
+	return 0;
+}
+
+static inline int security_perf_event_alloc(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline void security_perf_event_free(struct perf_event *event)
+{
+}
+
+static inline int security_perf_event_read(struct perf_event *event)
+{
+	return 0;
+}
 
+static inline int security_perf_event_write(struct perf_event *event)
+{
+	return 0;
+}
+#endif /* CONFIG_SECURITY */
+#endif /* CONFIG_PERF_EVENTS */
+
+#endif /* ! __LINUX_SECURITY_H */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index bb7b271397a6..377d794d3105 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -141,8 +141,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_TRANSACTION			= 1U << 17,
 	PERF_SAMPLE_REGS_INTR			= 1U << 18,
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
+	PERF_SAMPLE_AUX				= 1U << 20,
 
-	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 21,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -300,6 +301,7 @@ enum perf_event_read_format {
 					/* add: sample_stack_user */
 #define PERF_ATTR_SIZE_VER4	104	/* add: sample_regs_intr */
 #define PERF_ATTR_SIZE_VER5	112	/* add: aux_watermark */
+#define PERF_ATTR_SIZE_VER6	120	/* add: aux_sample_size */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -424,7 +426,9 @@ struct perf_event_attr {
 	 */
 	__u32	aux_watermark;
 	__u16	sample_max_stack;
-	__u16	__reserved_2;	/* align to __u64 */
+	__u16	__reserved_2;
+	__u32	aux_sample_size;
+	__u32	__reserved_3;
 };
 
 /*
@@ -864,6 +868,8 @@ enum perf_event_type {
 	 *	{ u64			abi; # enum perf_sample_regs_abi
 	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
 	 *	{ u64			phys_addr;} && PERF_SAMPLE_PHYS_ADDR
+	 *	{ u64			size;
+	 *	  char			data[size]; } && PERF_SAMPLE_AUX
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,