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

Pull more perf updates from Thomas Gleixner:
 "A rather large set of perf updates:

  Kernel:

   - Fix various initialization issues

   - Prevent creating [ku]probes for not CAP_SYS_ADMIN users

  Tooling:

   - Show only failing syscalls with 'perf trace --failure' (Arnaldo
     Carvalho de Melo)

            e.g: See what 'openat' syscalls are failing:

        # perf trace --failure -e openat
         762.323 ( 0.007 ms): VideoCapture/4566 openat(dfd: CWD, filename: /dev/video2) = -1 ENOENT No such file or directory
         <SNIP N /dev/videoN open attempts... sigh, where is that improvised camera lid?!? >
         790.228 ( 0.008 ms): VideoCapture/4566 openat(dfd: CWD, filename: /dev/video63) = -1 ENOENT No such file or directory
        ^C#

   - Show information about the event (freq, nr_samples, total
     period/nr_events) in the annotate --tui and --stdio2 'perf
     annotate' output, similar to the first line in the 'perf report
     --tui', but just for the samples for a the annotated symbol
     (Arnaldo Carvalho de Melo)

   - Introduce 'perf version --build-options' to show what features were
     linked, aliased as well as a shorter 'perf -vv' (Jin Yao)

   - Add a "dso_size" sort order (Kim Phillips)

   - Remove redundant ')' in the tracepoint output in 'perf trace'
     (Changbin Du)

   - Synchronize x86's cpufeatures.h, no effect on toolss (Arnaldo
     Carvalho de Melo)

   - Show group details on the title line in the annotate browser and
     'perf annotate --stdio2' output, so that the per-event columns can
     have headers (Arnaldo Carvalho de Melo)

   - Fixup vertical line separating metrics from instructions and
     cleaning unused lines at the bottom, both in the annotate TUI
     browser (Arnaldo Carvalho de Melo)

   - Remove duplicated 'samples' in lost samples warning in
     'perf report' (Arnaldo Carvalho de Melo)

   - Synchronize i915_drm.h, silencing the perf build process,
     automagically adding support for the new DRM_I915_QUERY ioctl
     (Arnaldo Carvalho de Melo)

   - Make auxtrace_queues__add_buffer() allocate struct buffer, from a
     patchkit already applied (Adrian Hunter)

   - Fix the --stdio2/TUI annotate output to include group details, be
     it for a recorded '{a,b,f}' explicit event group or when forcing
     group display using 'perf report --group' for a set of events not
     recorded as a group (Arnaldo Carvalho de Melo)

   - Fix display artifacts in the ui browser (base class for the
     annotate and main report/top TUI browser) related to the extra
     title lines work (Arnaldo Carvalho de Melo)

   - perf auxtrace refactorings, leftovers from a previously partially
     processed patchset (Adrian Hunter)

   - Fix the builtin clang build (Sandipan Das, Arnaldo Carvalho de
     Melo)

   - Synchronize i915_drm.h, silencing a perf build warning and in the
     process automagically adding support for a new ioctl command
     (Arnaldo Carvalho de Melo)

   - Fix a strncpy issue in uprobe tracing"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  perf/core: Need CAP_SYS_ADMIN to create k/uprobe with perf_event_open()
  tracing/uprobe_event: Fix strncpy corner case
  perf/core: Fix perf_uprobe_init()
  perf/core: Fix perf_kprobe_init()
  perf/core: Fix use-after-free in uprobe_perf_close()
  perf tests clang: Fix function name for clang IR test
  perf clang: Add support for recent clang versions
  perf tools: Fix perf builds with clang support
  perf tools: No need to include namespaces.h in util.h
  perf hists browser: Remove leftover from row returned from refresh
  perf hists browser: Show extra_title_lines in the 'D' debug hotkey
  perf auxtrace: Make auxtrace_queues__add_buffer() do CPU filtering
  tools headers uapi: Synchronize i915_drm.h
  perf report: Remove duplicated 'samples' in lost samples warning
  perf ui browser: Fixup cleaning unused lines at the bottom
  perf annotate browser: Fixup vertical line separating metrics from instructions
  perf annotate: Show group details on the title line
  perf auxtrace: Make auxtrace_queues__add_buffer() allocate struct buffer
  perf/x86/intel: Move regs->flags EXACT bit init
  perf trace: Remove redundant ')'
  ...

33 files changed, 629 insertions, 187 deletions

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index da6780122786..8a10a045b57b 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1153,7 +1153,6 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	if (pebs == NULL)
 		return;
 
-	regs->flags &= ~PERF_EFLAGS_EXACT;
 	sample_type = event->attr.sample_type;
 	dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
 
@@ -1197,7 +1196,13 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	 * and PMI.
 	 */
 	*regs = *iregs;
-	regs->flags = pebs->flags;
+
+	/*
+	 * Initialize regs_>flags from PEBS,
+	 * Clear exact bit (which uses x86 EFLAGS Reserved bit 3),
+	 * i.e., do not rely on it being zero:
+	 */
+	regs->flags = pebs->flags & ~PERF_EFLAGS_EXACT;
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
 		regs->ax = pebs->ax;
@@ -1217,10 +1222,6 @@ static void setup_pebs_sample_data(struct perf_event *event,
 			regs->sp = pebs->sp;
 		}
 
-		/*
-		 * Preserve PERF_EFLAGS_VM from set_linear_ip().
-		 */
-		regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM);
 #ifndef CONFIG_X86_32
 		regs->r8 = pebs->r8;
 		regs->r9 = pebs->r9;
@@ -1234,20 +1235,33 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	}
 
 	if (event->attr.precise_ip > 1) {
-		/* Haswell and later have the eventing IP, so use it: */
+		/*
+		 * Haswell and later processors have an 'eventing IP'
+		 * (real IP) which fixes the off-by-1 skid in hardware.
+		 * Use it when precise_ip >= 2 :
+		 */
 		if (x86_pmu.intel_cap.pebs_format >= 2) {
 			set_linear_ip(regs, pebs->real_ip);
 			regs->flags |= PERF_EFLAGS_EXACT;
 		} else {
-			/* Otherwise use PEBS off-by-1 IP: */
+			/* Otherwise, use PEBS off-by-1 IP: */
 			set_linear_ip(regs, pebs->ip);
 
-			/* ... and try to fix it up using the LBR entries: */
+			/*
+			 * With precise_ip >= 2, try to fix up the off-by-1 IP
+			 * using the LBR. If successful, the fixup function
+			 * corrects regs->ip and calls set_linear_ip() on regs:
+			 */
 			if (intel_pmu_pebs_fixup_ip(regs))
 				regs->flags |= PERF_EFLAGS_EXACT;
 		}
-	} else
+	} else {
+		/*
+		 * When precise_ip == 1, return the PEBS off-by-1 IP,
+		 * no fixup attempted:
+		 */
 		set_linear_ip(regs, pebs->ip);
+	}
 
 
 	if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) &&
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fc1c330c6bd6..2d5fe26551f8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4447,6 +4447,9 @@ static void _free_event(struct perf_event *event)
 	if (event->ctx)
 		put_ctx(event->ctx);
 
+	if (event->hw.target)
+		put_task_struct(event->hw.target);
+
 	exclusive_event_destroy(event);
 	module_put(event->pmu->module);
 
@@ -8397,6 +8400,10 @@ static int perf_kprobe_event_init(struct perf_event *event)
 
 	if (event->attr.type != perf_kprobe.type)
 		return -ENOENT;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
 	/*
 	 * no branch sampling for probe events
 	 */
@@ -8434,6 +8441,10 @@ static int perf_uprobe_event_init(struct perf_event *event)
 
 	if (event->attr.type != perf_uprobe.type)
 		return -ENOENT;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
 	/*
 	 * no branch sampling for probe events
 	 */
@@ -9955,6 +9966,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		 * and we cannot use the ctx information because we need the
 		 * pmu before we get a ctx.
 		 */
+		get_task_struct(task);
 		event->hw.target = task;
 	}
 
@@ -10070,6 +10082,8 @@ err_ns:
 		perf_detach_cgroup(event);
 	if (event->ns)
 		put_pid_ns(event->ns);
+	if (event->hw.target)
+		put_task_struct(event->hw.target);
 	kfree(event);
 
 	return ERR_PTR(err);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 2c416509b834..c79193e598f5 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -252,6 +252,8 @@ int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe)
 		ret = strncpy_from_user(
 			func, u64_to_user_ptr(p_event->attr.kprobe_func),
 			KSYM_NAME_LEN);
+		if (ret == KSYM_NAME_LEN)
+			ret = -E2BIG;
 		if (ret < 0)
 			goto out;
 
@@ -300,6 +302,8 @@ int perf_uprobe_init(struct perf_event *p_event, bool is_retprobe)
 		return -ENOMEM;
 	ret = strncpy_from_user(
 		path, u64_to_user_ptr(p_event->attr.uprobe_path), PATH_MAX);
+	if (ret == PATH_MAX)
+		return -E2BIG;
 	if (ret < 0)
 		goto out;
 	if (path[0] == '\0') {
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 469ba7ecd14b..34fd0e0ec51d 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -151,6 +151,8 @@ static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
 		return;
 
 	ret = strncpy_from_user(dst, src, maxlen);
+	if (ret == maxlen)
+		dst[--ret] = '\0';
 
 	if (ret < 0) {	/* Failed to fetch string */
 		((u8 *)get_rloc_data(dest))[0] = '\0';
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index f41079da38c5..d554c11e01ff 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -316,6 +316,7 @@
 #define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
 #define X86_FEATURE_AVX512_VNNI		(16*32+11) /* Vector Neural Network Instructions */
 #define X86_FEATURE_AVX512_BITALG	(16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_TME			(16*32+13) /* Intel Total Memory Encryption */
 #define X86_FEATURE_AVX512_VPOPCNTDQ	(16*32+14) /* POPCNT for vectors of DW/QW */
 #define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
@@ -328,6 +329,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
diff --git a/tools/include/tools/config.h b/tools/include/tools/config.h
new file mode 100644
index 000000000000..08ade7df8132
--- /dev/null
+++ b/tools/include/tools/config.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_CONFIG_H
+#define _TOOLS_CONFIG_H
+
+/* Subset of include/linux/kconfig.h */
+
+#define __ARG_PLACEHOLDER_1 0,
+#define __take_second_arg(__ignored, val, ...) val
+
+/*
+ * Helper macros to use CONFIG_ options in C/CPP expressions. Note that
+ * these only work with boolean and tristate options.
+ */
+
+/*
+ * Getting something that works in C and CPP for an arg that may or may
+ * not be defined is tricky.  Here, if we have "#define CONFIG_BOOGER 1"
+ * we match on the placeholder define, insert the "0," for arg1 and generate
+ * the triplet (0, 1, 0).  Then the last step cherry picks the 2nd arg (a one).
+ * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
+ * the last step cherry picks the 2nd arg, we get a zero.
+ */
+#define __is_defined(x)			___is_defined(x)
+#define ___is_defined(val)		____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk)	__take_second_arg(arg1_or_junk 1, 0)
+
+/*
+ * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
+ * otherwise. For boolean options, this is equivalent to
+ * IS_ENABLED(CONFIG_FOO).
+ */
+#define IS_BUILTIN(option) __is_defined(option)
+
+#endif /* _TOOLS_CONFIG_H */
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 536ee4febd74..7f5634ce8e88 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -318,6 +318,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_PERF_OPEN		0x36
 #define DRM_I915_PERF_ADD_CONFIG	0x37
 #define DRM_I915_PERF_REMOVE_CONFIG	0x38
+#define DRM_I915_QUERY			0x39
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -375,6 +376,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
 #define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
 #define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
+#define DRM_IOCTL_I915_QUERY			DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -1358,7 +1360,9 @@ struct drm_intel_overlay_attrs {
  * active on a given plane.
  */
 
-#define I915_SET_COLORKEY_NONE		(1<<0) /* disable color key matching */
+#define I915_SET_COLORKEY_NONE		(1<<0) /* Deprecated. Instead set
+						* flags==0 to disable colorkeying.
+						*/
 #define I915_SET_COLORKEY_DESTINATION	(1<<1)
 #define I915_SET_COLORKEY_SOURCE	(1<<2)
 struct drm_intel_sprite_colorkey {
@@ -1604,15 +1608,115 @@ struct drm_i915_perf_oa_config {
 	__u32 n_flex_regs;
 
 	/*
-	 * These fields are pointers to tuples of u32 values (register
-	 * address, value). For example the expected length of the buffer
-	 * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+	 * These fields are pointers to tuples of u32 values (register address,
+	 * value). For example the expected length of the buffer pointed by
+	 * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
 	 */
 	__u64 mux_regs_ptr;
 	__u64 boolean_regs_ptr;
 	__u64 flex_regs_ptr;
 };
 
+struct drm_i915_query_item {
+	__u64 query_id;
+#define DRM_I915_QUERY_TOPOLOGY_INFO    1
+
+	/*
+	 * When set to zero by userspace, this is filled with the size of the
+	 * data to be written at the data_ptr pointer. The kernel sets this
+	 * value to a negative value to signal an error on a particular query
+	 * item.
+	 */
+	__s32 length;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * Data will be written at the location pointed by data_ptr when the
+	 * value of length matches the length of the data to be written by the
+	 * kernel.
+	 */
+	__u64 data_ptr;
+};
+
+struct drm_i915_query {
+	__u32 num_items;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * This points to an array of num_items drm_i915_query_item structures.
+	 */
+	__u64 items_ptr;
+};
+
+/*
+ * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO :
+ *
+ * data: contains the 3 pieces of information :
+ *
+ * - the slice mask with one bit per slice telling whether a slice is
+ *   available. The availability of slice X can be queried with the following
+ *   formula :
+ *
+ *           (data[X / 8] >> (X % 8)) & 1
+ *
+ * - the subslice mask for each slice with one bit per subslice telling
+ *   whether a subslice is available. The availability of subslice Y in slice
+ *   X can be queried with the following formula :
+ *
+ *           (data[subslice_offset +
+ *                 X * subslice_stride +
+ *                 Y / 8] >> (Y % 8)) & 1
+ *
+ * - the EU mask for each subslice in each slice with one bit per EU telling
+ *   whether an EU is available. The availability of EU Z in subslice Y in
+ *   slice X can be queried with the following formula :
+ *
+ *           (data[eu_offset +
+ *                 (X * max_subslices + Y) * eu_stride +
+ *                 Z / 8] >> (Z % 8)) & 1
+ */
+struct drm_i915_query_topology_info {
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u16 flags;
+
+	__u16 max_slices;
+	__u16 max_subslices;
+	__u16 max_eus_per_subslice;
+
+	/*
+	 * Offset in data[] at which the subslice masks are stored.
+	 */
+	__u16 subslice_offset;
+
+	/*
+	 * Stride at which each of the subslice masks for each slice are
+	 * stored.
+	 */
+	__u16 subslice_stride;
+
+	/*
+	 * Offset in data[] at which the EU masks are stored.
+	 */
+	__u16 eu_offset;
+
+	/*
+	 * Stride at which each of the EU masks for each subslice are stored.
+	 */
+	__u16 eu_stride;
+
+	__u8 data[];
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index e1a660e60849..917e36fde6d8 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -80,6 +80,7 @@ OPTIONS
 	- comm: command (name) of the task which can be read via /proc/<pid>/comm
 	- pid: command and tid of the task
 	- dso: name of library or module executed at the time of sample
+	- dso_size: size of library or module executed at the time of sample
 	- symbol: name of function executed at the time of sample
 	- symbol_size: size of function executed at the time of sample
 	- parent: name of function matched to the parent regex filter. Unmatched
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 5a7035c5c523..115db9e06ecd 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -117,6 +117,9 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --sched::
 	Accrue thread runtime and provide a summary at the end of the session.
 
+--failure::
+	Show only syscalls that failed, i.e. that returned < 0.
+
 -i::
 --input::
 	Process events from a given perf data file.
diff --git a/tools/perf/Documentation/perf-version.txt b/tools/perf/Documentation/perf-version.txt
new file mode 100644
index 000000000000..e207b7cfca26
--- /dev/null
+++ b/tools/perf/Documentation/perf-version.txt
@@ -0,0 +1,24 @@
+perf-version(1)
+===============
+
+NAME
+----
+perf-version - display the version of perf binary
+
+SYNOPSIS
+--------
+'perf version' [--build-options]
+
+DESCRIPTION
+-----------
+With no options given, the 'perf version' prints the perf version
+on the standard output.
+
+If the option '--build-options' is given, then the status of
+compiled-in libraries are printed on the standard output.
+
+OPTIONS
+-------
+--build-options::
+        Prints the status of compiled-in libraries on the
+        standard output.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 98ff73648b51..c7abd83a8e19 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -346,12 +346,16 @@ else
       ifneq ($(feature-dwarf_getlocations), 1)
         msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);
       else
-        CFLAGS += -DHAVE_DWARF_GETLOCATIONS
+        CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT
       endif # dwarf_getlocations
     endif # Dwarf support
   endif # libelf support
 endif # NO_LIBELF
 
+ifeq ($(feature-glibc), 1)
+  CFLAGS += -DHAVE_GLIBC_SUPPORT
+endif
+
 ifdef NO_DWARF
   NO_LIBDW_DWARF_UNWIND := 1
 endif
@@ -635,6 +639,7 @@ else
   else
     LDFLAGS += $(PERL_EMBED_LDFLAGS)
     EXTLIBS += $(PERL_EMBED_LIBADD)
+    CFLAGS += -DHAVE_LIBPERL_SUPPORT
     $(call detected,CONFIG_LIBPERL)
   endif
 endif
@@ -671,6 +676,7 @@ else
          LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
          EXTLIBS += $(PYTHON_EMBED_LIBADD)
          LANG_BINDINGS += $(obj-perf)python/perf.so
+         CFLAGS += -DHAVE_LIBPYTHON_SUPPORT
          $(call detected,CONFIG_LIBPYTHON)
       endif
     endif
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index f7517e1b73f8..83e453de36f8 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -364,7 +364,8 @@ LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive
 
 ifeq ($(USE_CLANG), 1)
   CLANGLIBS_LIST = AST Basic CodeGen Driver Frontend Lex Tooling Edit Sema Analysis Parse Serialization
-  LIBCLANG = $(foreach l,$(CLANGLIBS_LIST),$(wildcard $(shell $(LLVM_CONFIG) --libdir)/libclang$(l).a))
+  CLANGLIBS_NOEXT_LIST = $(foreach l,$(CLANGLIBS_LIST),$(shell $(LLVM_CONFIG) --libdir)/libclang$(l))
+  LIBCLANG = $(foreach l,$(CLANGLIBS_NOEXT_LIST),$(wildcard $(l).a $(l).so))
   LIBS += -Wl,--start-group $(LIBCLANG) -Wl,--end-group
 endif
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 87b95c9410b4..3ad17ee89403 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -112,6 +112,7 @@ struct trace {
 	bool			multiple_threads;
 	bool			summary;
 	bool			summary_only;
+	bool			failure_only;
 	bool			show_comm;
 	bool			print_sample;
 	bool			show_tool_stats;
@@ -1565,7 +1566,7 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 	struct thread_trace *ttrace;
 	size_t printed;
 
-	if (trace->current == NULL)
+	if (trace->failure_only || trace->current == NULL)
 		return 0;
 
 	ttrace = thread__priv(trace->current);
@@ -1638,7 +1639,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 					   args, trace, thread);
 
 	if (sc->is_exit) {
-		if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
+		if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
 			trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output);
 			fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
 		}
@@ -1742,7 +1743,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 		}
 	}
 
-	if (trace->summary_only)
+	if (trace->summary_only || (ret >= 0 && trace->failure_only))
 		goto out;
 
 	trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output);
@@ -1961,7 +1962,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				      trace->output);
 	}
 
-	fprintf(trace->output, ")\n");
+	fprintf(trace->output, "\n");
 
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
@@ -3087,6 +3088,8 @@ int cmd_trace(int argc, const char **argv)
 	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
 	OPT_BOOLEAN('T', "time", &trace.full_time,
 		    "Show full timestamp, not time relative to first start"),
+	OPT_BOOLEAN(0, "failure", &trace.failure_only,
+		    "Show only syscalls that failed"),
 	OPT_BOOLEAN('s', "summary", &trace.summary_only,
 		    "Show only syscall summary with statistics"),
 	OPT_BOOLEAN('S', "with-summary", &trace.summary,
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index 37019c5d675f..2abe3910d6b6 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -1,11 +1,91 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 #include "perf.h"
+#include "color.h"
 #include <linux/compiler.h>
+#include <tools/config.h>
 #include <stdio.h>
+#include <string.h>
+#include <subcmd/parse-options.h>
 
-int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused)
+int version_verbose;
+
+struct version {
+	bool	build_options;
+};
+
+static struct version version;
+
+static struct option version_options[] = {
+	OPT_BOOLEAN(0, "build-options", &version.build_options,
+		    "display the build options"),
+};
+
+static const char * const version_usage[] = {
+	"perf version [<options>]",
+	NULL
+};
+
+static void on_off_print(const char *status)
+{
+	printf("[ ");
+
+	if (!strcmp(status, "OFF"))
+		color_fprintf(stdout, PERF_COLOR_RED, "%-3s", status);
+	else
+		color_fprintf(stdout, PERF_COLOR_GREEN, "%-3s", status);
+
+	printf(" ]");
+}
+
+static void status_print(const char *name, const char *macro,
+			 const char *status)
 {
+	printf("%22s: ", name);
+	on_off_print(status);
+	printf("  # %s\n", macro);
+}
+
+#define STATUS(__d, __m)				\
+do {							\
+	if (IS_BUILTIN(__d))				\
+		status_print(#__m, #__d, "on");		\
+	else						\
+		status_print(#__m, #__d, "OFF");	\
+} while (0)
+
+static void library_status(void)
+{
+	STATUS(HAVE_DWARF_SUPPORT, dwarf);
+	STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations);
+	STATUS(HAVE_GLIBC_SUPPORT, glibc);
+	STATUS(HAVE_GTK2_SUPPORT, gtk2);
+	STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit);
+	STATUS(HAVE_LIBBFD_SUPPORT, libbfd);
+	STATUS(HAVE_LIBELF_SUPPORT, libelf);
+	STATUS(HAVE_LIBNUMA_SUPPORT, libnuma);
+	STATUS(HAVE_LIBNUMA_SUPPORT, numa_num_possible_cpus);
+	STATUS(HAVE_LIBPERL_SUPPORT, libperl);
+	STATUS(HAVE_LIBPYTHON_SUPPORT, libpython);
+	STATUS(HAVE_SLANG_SUPPORT, libslang);
+	STATUS(HAVE_LIBCRYPTO_SUPPORT, libcrypto);
+	STATUS(HAVE_LIBUNWIND_SUPPORT, libunwind);
+	STATUS(HAVE_DWARF_SUPPORT, libdw-dwarf-unwind);
+	STATUS(HAVE_ZLIB_SUPPORT, zlib);
+	STATUS(HAVE_LZMA_SUPPORT, lzma);
+	STATUS(HAVE_AUXTRACE_SUPPORT, get_cpuid);
+	STATUS(HAVE_LIBBPF_SUPPORT, bpf);
+}
+
+int cmd_version(int argc, const char **argv)
+{
+	argc = parse_options(argc, argv, version_options, version_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
 	printf("perf version %s\n", perf_version_string);
+
+	if (version.build_options || version_verbose == 1)
+		library_status();
+
 	return 0;
 }
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 1b3fc8ec0fa2..1659029d03fc 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -190,6 +190,12 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 			break;
 		}
 
+		if (!strcmp(cmd, "-vv")) {
+			(*argv)[0] = "version";
+			version_verbose = 1;
+			break;
+		}
+
 		/*
 		 * Check remaining flags.
 		 */
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 8fec1abd0f1f..a1a97956136f 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -84,6 +84,7 @@ struct record_opts {
 struct option;
 extern const char * const *record_usage;
 extern struct option *record_options;
+extern int version_verbose;
 
 int record__parse_freq(const struct option *opt, const char *str, int unset);
 #endif
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 9f6ce29b83b4..4f75561424ed 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -45,11 +45,16 @@ void ui_browser__set_percent_color(struct ui_browser *browser,
 	 ui_browser__set_color(browser, color);
 }
 
-void ui_browser__gotorc(struct ui_browser *browser, int y, int x)
+void ui_browser__gotorc_title(struct ui_brow