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

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Add branch type profiling/tracing support. (Jin Yao)

   - Add the PERF_SAMPLE_PHYS_ADDR ABI to allow the tracing/profiling of
     physical memory addresses, where the PMU supports it. (Kan Liang)

   - Export some PMU capability details in the new
     /sys/bus/event_source/devices/cpu/caps/ sysfs directory. (Andi
     Kleen)

   - Aux data fixes and updates (Will Deacon)

   - kprobes fixes and updates (Masami Hiramatsu)

   - AMD uncore PMU driver fixes and updates (Janakarajan Natarajan)

  On the tooling side, here's a (limited!) list of highlights - there
  were many other changes that I could not list, see the shortlog and
  git history for details:

  UI improvements:

   - Implement a visual marker for fused x86 instructions in the
     annotate TUI browser, available now in 'perf report', more work
     needed to have it available as well in 'perf top' (Jin Yao)

     Further explanation from one of Jin's patches:

             │   ┌──cmpl   $0x0,argp_program_version_hook
       81.93 │   ├──je     20
             │   │  lock   cmpxchg %esi,0x38a9a4(%rip)
             │   │↓ jne    29
             │   │↓ jmp    43
       11.47 │20:└─→cmpxch %esi,0x38a999(%rip)

     That means the cmpl+je is a fused instruction pair and they should
     be considered together.

   - Record the branch type and then show statistics and info about in
     callchain entries (Jin Yao)

     Example from one of Jin's patches:

        # perf record -g -j any,save_type
        # perf report --branch-history --stdio --no-children

        38.50%  div.c:45                [.] main                    div
                |
                ---main div.c:42 (RET CROSS_2M cycles:2)
                   compute_flag div.c:28 (cycles:2)
                   compute_flag div.c:27 (RET CROSS_2M cycles:1)
                   rand rand.c:28 (cycles:1)
                   rand rand.c:28 (RET CROSS_2M cycles:1)
                   __random random.c:298 (cycles:1)
                   __random random.c:297 (COND_BWD CROSS_2M cycles:1)
                   __random random.c:295 (cycles:1)
                   __random random.c:295 (COND_BWD CROSS_2M cycles:1)
                   __random random.c:295 (cycles:1)
                   __random random.c:295 (RET CROSS_2M cycles:9)

  namespaces support:

   - Add initial support for namespaces, using setns to access files in
     namespaces, grabbing their build-ids, etc. (Krister Johansen)

  perf trace enhancements:

   - Beautify pkey_{alloc,free,mprotect} arguments in 'perf trace'
     (Arnaldo Carvalho de Melo)

   - Add initial 'clone' syscall args beautifier in 'perf trace'
     (Arnaldo Carvalho de Melo)

   - Ignore 'fd' and 'offset' args for MAP_ANONYMOUS in 'perf trace'
     (Arnaldo Carvalho de Melo)

   - Beautifiers for the 'cmd' arg of several ioctl types, including:
     sound, DRM, KVM, vhost virtio and perf_events. (Arnaldo Carvalho de
     Melo)

   - Add PERF_SAMPLE_CALLCHAIN and PERF_RECORD_MMAP[2] to 'perf data'
     CTF conversion, allowing CTF trace visualization tools to show
     callchains and to resolve symbols (Geneviève Bastien)

   - Beautify the fcntl syscall, which is an interesting one in the
     sense that infrastructure had to be put in place to change the
     formatters of some arguments according to the value in a previous
     one, i.e. cmd dictates how arg and the syscall return will be
     formatted. (Arnaldo Carvalho de Melo

  perf stat enhancements:

   - Use group read for event groups in 'perf stat', reducing overhead
     when groups are defined in the event specification, i.e. when using
     {} to enclose a list of events, asking them to be read at the same
     time, e.g.: "perf stat -e '{cycles,instructions}'" (Jiri Olsa)

  pipe mode improvements:

   - Process tracing data in 'perf annotate' pipe mode (David
     Carrillo-Cisneros)

   - Add header record types to pipe-mode, now this command:

        $ perf record -o - -e cycles sleep 1 | perf report --stdio --header

     Will show the same as in non-pipe mode, i.e. involving a perf.data
     file (David Carrillo-Cisneros)

  Vendor specific hardware event support updates/enhancements:

   - Update POWER9 vendor events tables (Sukadev Bhattiprolu)

   - Add POWER9 PMU events Sukadev (Bhattiprolu)

   - Support additional POWER8+ PVR in PMU mapfile (Shriya)

   - Add Skylake server uncore JSON vendor events (Andi Kleen)

   - Support exporting Intel PT data to sqlite3 with python perf
     scripts, this is in addition to the postgresql support that was
     already there (Adrian Hunter)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (253 commits)
  perf symbols: Fix plt entry calculation for ARM and AARCH64
  perf probe: Fix kprobe blacklist checking condition
  perf/x86: Fix caps/ for !Intel
  perf/core, x86: Add PERF_SAMPLE_PHYS_ADDR
  perf/core, pt, bts: Get rid of itrace_started
  perf trace beauty: Beautify pkey_{alloc,free,mprotect} arguments
  tools headers: Sync cpu features kernel ABI headers with tooling headers
  perf tools: Pass full path of FEATURES_DUMP
  perf tools: Robustify detection of clang binary
  tools lib: Allow external definition of CC, AR and LD
  perf tools: Allow external definition of flex and bison binary names
  tools build tests: Don't hardcode gcc name
  perf report: Group stat values on global event id
  perf values: Zero value buffers
  perf values: Fix allocation check
  perf values: Fix thread index bug
  perf report: Add dump_read function
  perf record: Set read_format for inherit_stat
  perf c2c: Fix remote HITM detection for Skylake
  perf tools: Fix static build with newer toolchains
  ...

5 files changed, 66 insertions, 28 deletions

diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 532372c6cf15..e5da44eddd2f 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -27,6 +27,8 @@
  *	__kprobes_text_start, __kprobes_text_end
  *	__entry_text_start, __entry_text_end
  *	__ctors_start, __ctors_end
+ *	__irqentry_text_start, __irqentry_text_end
+ *	__softirqentry_text_start, __softirqentry_text_end
  */
 extern char _text[], _stext[], _etext[];
 extern char _data[], _sdata[], _edata[];
@@ -39,6 +41,8 @@ extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
 extern char __entry_text_start[], __entry_text_end[];
 extern char __start_rodata[], __end_rodata[];
+extern char __irqentry_text_start[], __irqentry_text_end[];
+extern char __softirqentry_text_start[], __softirqentry_text_end[];
 
 /* Start and end of .ctors section - used for constructor calls. */
 extern char __ctors_start[], __ctors_end[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 9623d78f8494..e7e955d4ab9e 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -497,25 +497,17 @@
 		*(.entry.text)						\
 		VMLINUX_SYMBOL(__entry_text_end) = .;
 
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
 #define IRQENTRY_TEXT							\
 		ALIGN_FUNCTION();					\
 		VMLINUX_SYMBOL(__irqentry_text_start) = .;		\
 		*(.irqentry.text)					\
 		VMLINUX_SYMBOL(__irqentry_text_end) = .;
-#else
-#define IRQENTRY_TEXT
-#endif
 
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
 #define SOFTIRQENTRY_TEXT						\
 		ALIGN_FUNCTION();					\
 		VMLINUX_SYMBOL(__softirqentry_text_start) = .;		\
 		*(.softirqentry.text)					\
 		VMLINUX_SYMBOL(__softirqentry_text_end) = .;
-#else
-#define SOFTIRQENTRY_TEXT
-#endif
 
 /* Section used for early init (in .S files) */
 #define HEAD_TEXT  *(.head.text)
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a2fddddb0d60..59ba11661b6e 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -18,6 +18,7 @@
 #include <linux/atomic.h>
 #include <asm/ptrace.h>
 #include <asm/irq.h>
+#include <asm/sections.h>
 
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
@@ -726,7 +727,6 @@ extern int early_irq_init(void);
 extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
 
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
 /*
  * We want to know which function is an entrypoint of a hardirq or a softirq.
  */
@@ -734,16 +734,4 @@ extern int arch_early_irq_init(void);
 #define __softirq_entry  \
 	__attribute__((__section__(".softirqentry.text")))
 
-/* Limits of hardirq entrypoints */
-extern char __irqentry_text_start[];
-extern char __irqentry_text_end[];
-/* Limits of softirq entrypoints */
-extern char __softirqentry_text_start[];
-extern char __softirqentry_text_end[];
-
-#else
-#define __irq_entry
-#define __softirq_entry
-#endif
-
 #endif
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c00cd4b02f32..718ba163c1b9 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -147,9 +147,6 @@ struct hw_perf_event {
 			struct list_head	cqm_groups_entry;
 			struct list_head	cqm_group_entry;
 		};
-		struct { /* itrace */
-			int			itrace_started;
-		};
 		struct { /* amd_power */
 			u64	pwr_acc;
 			u64	ptsc;
@@ -541,6 +538,7 @@ struct swevent_hlist {
 #define PERF_ATTACH_GROUP	0x02
 #define PERF_ATTACH_TASK	0x04
 #define PERF_ATTACH_TASK_DATA	0x08
+#define PERF_ATTACH_ITRACE	0x10
 
 struct perf_cgroup;
 struct ring_buffer;
@@ -864,6 +862,7 @@ extern int perf_aux_output_skip(struct perf_output_handle *handle,
 				unsigned long size);
 extern void *perf_get_aux(struct perf_output_handle *handle);
 extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags);
+extern void perf_event_itrace_started(struct perf_event *event);
 
 extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
 extern void perf_pmu_unregister(struct pmu *pmu);
@@ -944,6 +943,8 @@ struct perf_sample_data {
 
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
+
+	u64				phys_addr;
 } ____cacheline_aligned;
 
 /* default value for data source */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b1c0b187acfe..140ae638cfd6 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -139,8 +139,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 	PERF_SAMPLE_TRANSACTION			= 1U << 17,
 	PERF_SAMPLE_REGS_INTR			= 1U << 18,
+	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 
-	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
 };
 
 /*
@@ -174,6 +175,8 @@ enum perf_branch_sample_type_shift {
 	PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT	= 14, /* no flags */
 	PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT	= 15, /* no cycles */
 
+	PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT	= 16, /* save branch type */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -198,9 +201,30 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_NO_FLAGS	= 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
 	PERF_SAMPLE_BRANCH_NO_CYCLES	= 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
 
+	PERF_SAMPLE_BRANCH_TYPE_SAVE	=
+		1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
+/*
+ * Common flow change classification
+ */
+enum {
+	PERF_BR_UNKNOWN		= 0,	/* unknown */
+	PERF_BR_COND		= 1,	/* conditional */
+	PERF_BR_UNCOND		= 2,	/* unconditional  */
+	PERF_BR_IND		= 3,	/* indirect */
+	PERF_BR_CALL		= 4,	/* function call */
+	PERF_BR_IND_CALL	= 5,	/* indirect function call */
+	PERF_BR_RET		= 6,	/* function return */
+	PERF_BR_SYSCALL		= 7,	/* syscall */
+	PERF_BR_SYSRET		= 8,	/* syscall return */
+	PERF_BR_COND_CALL	= 9,	/* conditional function call */
+	PERF_BR_COND_RET	= 10,	/* conditional function return */
+	PERF_BR_MAX,
+};
+
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
 	(PERF_SAMPLE_BRANCH_USER|\
 	 PERF_SAMPLE_BRANCH_KERNEL|\
@@ -791,6 +815,7 @@ enum perf_event_type {
 	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
 	 *	{ u64			abi; # enum perf_sample_regs_abi
 	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+	 *	{ u64			phys_addr;} && PERF_SAMPLE_PHYS_ADDR
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
@@ -931,14 +956,20 @@ union perf_mem_data_src {
 			mem_snoop:5,	/* snoop mode */
 			mem_lock:2,	/* lock instr */
 			mem_dtlb:7,	/* tlb access */
-			mem_rsvd:31;
+			mem_lvl_num:4,	/* memory hierarchy level number */
+			mem_remote:1,   /* remote */
+			mem_snoopx:2,	/* snoop mode, ext */
+			mem_rsvd:24;
 	};
 };
 #elif defined(__BIG_ENDIAN_BITFIELD)
 union perf_mem_data_src {
 	__u64 val;
 	struct {
-		__u64	mem_rsvd:31,
+		__u64	mem_rsvd:24,
+			mem_snoopx:2,	/* snoop mode, ext */
+			mem_remote:1,   /* remote */
+			mem_lvl_num:4,	/* memory hierarchy level number */
 			mem_dtlb:7,	/* tlb access */
 			mem_lock:2,	/* lock instr */
 			mem_snoop:5,	/* snoop mode */
@@ -975,6 +1006,22 @@ union perf_mem_data_src {
 #define PERF_MEM_LVL_UNC	0x2000 /* Uncached memory */
 #define PERF_MEM_LVL_SHIFT	5
 
+#define PERF_MEM_REMOTE_REMOTE	0x01  /* Remote */
+#define PERF_MEM_REMOTE_SHIFT	37
+
+#define PERF_MEM_LVLNUM_L1	0x01 /* L1 */
+#define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
+#define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
+#define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
+/* 5-0xa available */
+#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
+#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB */
+#define PERF_MEM_LVLNUM_RAM	0x0d /* RAM */
+#define PERF_MEM_LVLNUM_PMEM	0x0e /* PMEM */
+#define PERF_MEM_LVLNUM_NA	0x0f /* N/A */
+
+#define PERF_MEM_LVLNUM_SHIFT	33
+
 /* snoop mode */
 #define PERF_MEM_SNOOP_NA	0x01 /* not available */
 #define PERF_MEM_SNOOP_NONE	0x02 /* no snoop */
@@ -983,6 +1030,10 @@ union perf_mem_data_src {
 #define PERF_MEM_SNOOP_HITM	0x10 /* snoop hit modified */
 #define PERF_MEM_SNOOP_SHIFT	19
 
+#define PERF_MEM_SNOOPX_FWD	0x01 /* forward */
+/* 1 free */
+#define PERF_MEM_SNOOPX_SHIFT	37
+
 /* locked instruction */
 #define PERF_MEM_LOCK_NA	0x01 /* not available */
 #define PERF_MEM_LOCK_LOCKED	0x02 /* locked transaction */
@@ -1015,6 +1066,7 @@ union perf_mem_data_src {
  *     in_tx: running in a hardware transaction
  *     abort: aborting a hardware transaction
  *    cycles: cycles from last branch (or 0 if not supported)
+ *      type: branch type
  */
 struct perf_branch_entry {
 	__u64	from;
@@ -1024,7 +1076,8 @@ struct perf_branch_entry {
 		in_tx:1,    /* in transaction */
 		abort:1,    /* transaction abort */
 		cycles:16,  /* cycle count to last branch */
-		reserved:44;
+		type:4,     /* branch type */
+		reserved:40;
 };
 
 #endif /* _UAPI_LINUX_PERF_EVENT_H */