Merge tag 'perf-tools-for-v5.14-2021-07-10' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull more perf tool updates from Arnaldo Carvalho de Melo:
 "New features:

   - Enable use of BPF counters with 'perf stat --for-each-cgroup',
     using per-CPU 'cgroup-switch' events with an attached BPF program
     that does aggregation per-cgroup in the kernel instead of using
     per-cgroup perf events.

   - Add Topdown metrics L2 events as default events in 'perf stat' for
     systems having those events.

  Hardware tracing:

   - Add a config for max loops without consuming a packet in the Intel
     PT packet decoder, set via 'perf config intel-pt.max-loops=N'

  Hardware enablement:

   - Disable misleading NMI watchdog message in 'perf stat' on hybrid
     systems such as Intel Alder Lake.

   - Add a dummy event on hybrid systems to collect metadata records.

   - Add 24x7 nest metric events for the Power10 platform.

  Fixes:

   - Fix event parsing for PMUs starting with the same prefix.

   - Fix the 'perf trace' 'trace' alias installation dir.

   - Fix buffer size to report iregs in perf script python scripts,
     supporting the extended registers in PowerPC.

   - Fix overflow in elf_sec__is_text().

   - Fix 's' on source line when disasm is empty in the annotation TUI,
     accessible via 'perf annotate', 'perf report' and 'perf top'.

   - Plug leaks in scandir() returned dirent entries in 'perf test' when
     sorting the shell tests.

   - Fix --task and --stat with pipe input in 'perf report'.

   - Fix 'perf probe' use of debuginfo files by build id.

   - If a DSO has both dynsym and symtab ELF sections, read from both
     when loading the symbol table, fixing a problem processing Fedora
     32 glibc DSOs.

  Libraries:

   - Add grouping of events to libperf, from code in tools/perf,
     allowing libperf users to use that mode.

  Misc:

   - Filter plt stubs from the 'perf probe --functions' output.

   - Update UAPI header copies for asound, DRM, mman-common.h and the
     ones affected by the quotactl_fd syscall"

* tag 'perf-tools-for-v5.14-2021-07-10' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (29 commits)
  perf test: Add free() calls for scandir() returned dirent entries
  libperf: Add tests for perf_evlist__set_leader()
  libperf: Remove BUG_ON() from library code in get_group_fd()
  libperf: Add group support to perf_evsel__open()
  perf tools: Fix pattern matching for same substring in different PMU type
  perf record: Add a dummy event on hybrid systems to collect metadata records
  perf stat: Add Topdown metrics L2 events as default events
  libperf: Adopt evlist__set_leader() from tools/perf as perf_evlist__set_leader()
  libperf: Move 'nr_groups' from tools/perf to evlist::nr_groups
  libperf: Move 'leader' from tools/perf to perf_evsel::leader
  libperf: Move 'idx' from tools/perf to perf_evsel::idx
  libperf: Change tests to single static and shared binaries
  perf intel-pt: Add a config for max loops without consuming a packet
  perf stat: Disable the NMI watchdog message on hybrid
  perf vendor events power10: Adds 24x7 nest metric events for power10 platform
  perf script python: Fix buffer size to report iregs in perf script
  perf trace: Fix the perf trace link location
  perf top: Fix overflow in elf_sec__is_text()
  perf annotate: Fix 's' on source line when disasm is empty
  perf probe: Do not show @plt function by default
  ...

77 files changed, 1872 insertions, 331 deletions

diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index f94f65d429be..1567a3294c3d 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -72,6 +72,9 @@
 #define MADV_COLD	20		/* deactivate these pages */
 #define MADV_PAGEOUT	21		/* reclaim these pages */
 
+#define MADV_POPULATE_READ	22	/* populate (prefault) page tables readable */
+#define MADV_POPULATE_WRITE	23	/* populate (prefault) page tables writable */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index d2a942086fcb..f211961ce1da 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -863,7 +863,8 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise)
 __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
 #define __NR_mount_setattr 442
 __SYSCALL(__NR_mount_setattr, sys_mount_setattr)
-/* 443 is reserved for quotactl_path */
+#define __NR_quotactl_fd 443
+__SYSCALL(__NR_quotactl_fd, sys_quotactl_fd)
 
 #define __NR_landlock_create_ruleset 444
 __SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 67b94bc3c885..d043752a74cf 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -777,9 +777,12 @@ struct drm_get_cap {
 /**
  * DRM_CLIENT_CAP_STEREO_3D
  *
- * if set to 1, the DRM core will expose the stereo 3D capabilities of the
+ * If set to 1, the DRM core will expose the stereo 3D capabilities of the
  * monitor by advertising the supported 3D layouts in the flags of struct
- * drm_mode_modeinfo.
+ * drm_mode_modeinfo. See ``DRM_MODE_FLAG_3D_*``.
+ *
+ * This capability is always supported for all drivers starting from kernel
+ * version 3.13.
  */
 #define DRM_CLIENT_CAP_STEREO_3D	1
 
@@ -788,6 +791,9 @@ struct drm_get_cap {
  *
  * If set to 1, the DRM core will expose all planes (overlay, primary, and
  * cursor) to userspace.
+ *
+ * This capability has been introduced in kernel version 3.15. Starting from
+ * kernel version 3.17, this capability is always supported for all drivers.
  */
 #define DRM_CLIENT_CAP_UNIVERSAL_PLANES  2
 
@@ -797,6 +803,13 @@ struct drm_get_cap {
  * If set to 1, the DRM core will expose atomic properties to userspace. This
  * implicitly enables &DRM_CLIENT_CAP_UNIVERSAL_PLANES and
  * &DRM_CLIENT_CAP_ASPECT_RATIO.
+ *
+ * If the driver doesn't support atomic mode-setting, enabling this capability
+ * will fail with -EOPNOTSUPP.
+ *
+ * This capability has been introduced in kernel version 4.0. Starting from
+ * kernel version 4.2, this capability is always supported for atomic-capable
+ * drivers.
  */
 #define DRM_CLIENT_CAP_ATOMIC	3
 
@@ -804,6 +817,10 @@ struct drm_get_cap {
  * DRM_CLIENT_CAP_ASPECT_RATIO
  *
  * If set to 1, the DRM core will provide aspect ratio information in modes.
+ * See ``DRM_MODE_FLAG_PIC_AR_*``.
+ *
+ * This capability is always supported for all drivers starting from kernel
+ * version 4.18.
  */
 #define DRM_CLIENT_CAP_ASPECT_RATIO    4
 
@@ -811,8 +828,11 @@ struct drm_get_cap {
  * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS
  *
  * If set to 1, the DRM core will expose special connectors to be used for
- * writing back to memory the scene setup in the commit. Depends on client
- * also supporting DRM_CLIENT_CAP_ATOMIC
+ * writing back to memory the scene setup in the commit. The client must enable
+ * &DRM_CLIENT_CAP_ATOMIC first.
+ *
+ * This capability is always supported for atomic-capable drivers starting from
+ * kernel version 4.19.
  */
 #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
 
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index ddc47bbf48b6..c2c7759b7d2e 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -62,8 +62,8 @@ extern "C" {
 #define I915_ERROR_UEVENT		"ERROR"
 #define I915_RESET_UEVENT		"RESET"
 
-/*
- * i915_user_extension: Base class for defining a chain of extensions
+/**
+ * struct i915_user_extension - Base class for defining a chain of extensions
  *
  * Many interfaces need to grow over time. In most cases we can simply
  * extend the struct and have userspace pass in more data. Another option,
@@ -76,12 +76,58 @@ extern "C" {
  * increasing complexity, and for large parts of that interface to be
  * entirely optional. The downside is more pointer chasing; chasing across
  * the __user boundary with pointers encapsulated inside u64.
+ *
+ * Example chaining:
+ *
+ * .. code-block:: C
+ *
+ *	struct i915_user_extension ext3 {
+ *		.next_extension = 0, // end
+ *		.name = ...,
+ *	};
+ *	struct i915_user_extension ext2 {
+ *		.next_extension = (uintptr_t)&ext3,
+ *		.name = ...,
+ *	};
+ *	struct i915_user_extension ext1 {
+ *		.next_extension = (uintptr_t)&ext2,
+ *		.name = ...,
+ *	};
+ *
+ * Typically the struct i915_user_extension would be embedded in some uAPI
+ * struct, and in this case we would feed it the head of the chain(i.e ext1),
+ * which would then apply all of the above extensions.
+ *
  */
 struct i915_user_extension {
+	/**
+	 * @next_extension:
+	 *
+	 * Pointer to the next struct i915_user_extension, or zero if the end.
+	 */
 	__u64 next_extension;
+	/**
+	 * @name: Name of the extension.
+	 *
+	 * Note that the name here is just some integer.
+	 *
+	 * Also note that the name space for this is not global for the whole
+	 * driver, but rather its scope/meaning is limited to the specific piece
+	 * of uAPI which has embedded the struct i915_user_extension.
+	 */
 	__u32 name;
-	__u32 flags; /* All undefined bits must be zero. */
-	__u32 rsvd[4]; /* Reserved for future use; must be zero. */
+	/**
+	 * @flags: MBZ
+	 *
+	 * All undefined bits must be zero.
+	 */
+	__u32 flags;
+	/**
+	 * @rsvd: MBZ
+	 *
+	 * Reserved for future use; must be zero.
+	 */
+	__u32 rsvd[4];
 };
 
 /*
@@ -360,6 +406,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_QUERY			0x39
 #define DRM_I915_GEM_VM_CREATE		0x3a
 #define DRM_I915_GEM_VM_DESTROY		0x3b
+#define DRM_I915_GEM_CREATE_EXT		0x3c
 /* Must be kept compact -- no holes */
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
@@ -392,6 +439,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_ENTERVT	DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT)
 #define DRM_IOCTL_I915_GEM_LEAVEVT	DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT)
 #define DRM_IOCTL_I915_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create)
+#define DRM_IOCTL_I915_GEM_CREATE_EXT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext)
 #define DRM_IOCTL_I915_GEM_PREAD	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread)
 #define DRM_IOCTL_I915_GEM_PWRITE	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
 #define DRM_IOCTL_I915_GEM_MMAP		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
@@ -1054,12 +1102,12 @@ struct drm_i915_gem_exec_fence {
 	__u32 flags;
 };
 
-/**
+/*
  * See drm_i915_gem_execbuffer_ext_timeline_fences.
  */
 #define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
 
-/**
+/*
  * This structure describes an array of drm_syncobj and associated points for
  * timeline variants of drm_syncobj. It is invalid to append this structure to
  * the execbuf if I915_EXEC_FENCE_ARRAY is set.
@@ -1700,7 +1748,7 @@ struct drm_i915_gem_context_param {
 	__u64 value;
 };
 
-/**
+/*
  * Context SSEU programming
  *
  * It may be necessary for either functional or performance reason to configure
@@ -2067,7 +2115,7 @@ struct drm_i915_perf_open_param {
 	__u64 properties_ptr;
 };
 
-/**
+/*
  * Enable data capture for a stream that was either opened in a disabled state
  * via I915_PERF_FLAG_DISABLED or was later disabled via
  * I915_PERF_IOCTL_DISABLE.
@@ -2081,7 +2129,7 @@ struct drm_i915_perf_open_param {
  */
 #define I915_PERF_IOCTL_ENABLE	_IO('i', 0x0)
 
-/**
+/*
  * Disable data capture for a stream.
  *
  * It is an error to try and read a stream that is disabled.
@@ -2090,7 +2138,7 @@ struct drm_i915_perf_open_param {
  */
 #define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
 
-/**
+/*
  * Change metrics_set captured by a stream.
  *
  * If the stream is bound to a specific context, the configuration change
@@ -2103,7 +2151,7 @@ struct drm_i915_perf_open_param {
  */
 #define I915_PERF_IOCTL_CONFIG	_IO('i', 0x2)
 
-/**
+/*
  * Common to all i915 perf records
  */
 struct drm_i915_perf_record_header {
@@ -2151,7 +2199,7 @@ enum drm_i915_perf_record_type {
 	DRM_I915_PERF_RECORD_MAX /* non-ABI */
 };
 
-/**
+/*
  * Structure to upload perf dynamic configuration into the kernel.
  */
 struct drm_i915_perf_oa_config {
@@ -2172,53 +2220,95 @@ struct drm_i915_perf_oa_config {
 	__u64 flex_regs_ptr;
 };
 
+/**
+ * struct drm_i915_query_item - An individual query for the kernel to process.
+ *
+ * The behaviour is determined by the @query_id. Note that exactly what
+ * @data_ptr is also depends on the specific @query_id.
+ */
 struct drm_i915_query_item {
+	/** @query_id: The id for this query */
 	__u64 query_id;
 #define DRM_I915_QUERY_TOPOLOGY_INFO    1
 #define DRM_I915_QUERY_ENGINE_INFO	2
 #define DRM_I915_QUERY_PERF_CONFIG      3
+#define DRM_I915_QUERY_MEMORY_REGIONS   4
 /* Must be kept compact -- no holes and well documented */
 
-	/*
+	/**
+	 * @length:
+	 *
 	 * 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
+	 * 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;
 
-	/*
+	/**
+	 * @flags:
+	 *
 	 * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
 	 *
 	 * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the
-	 * following :
-	 *         - DRM_I915_QUERY_PERF_CONFIG_LIST
-	 *         - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
-	 *         - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
+	 * following:
+	 *
+	 *	- DRM_I915_QUERY_PERF_CONFIG_LIST
+	 *      - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
+	 *      - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
 	 */
 	__u32 flags;
 #define DRM_I915_QUERY_PERF_CONFIG_LIST          1
 #define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2
 #define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID   3
 
-	/*
-	 * 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
+	/**
+	 * @data_ptr:
+	 *
+	 * 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 - Supply an array of struct drm_i915_query_item for the
+ * kernel to fill out.
+ *
+ * Note that this is generally a two step process for each struct
+ * drm_i915_query_item in the array:
+ *
+ * 1. Call the DRM_IOCTL_I915_QUERY, giving it our array of struct
+ *    drm_i915_query_item, with &drm_i915_query_item.length set to zero. The
+ *    kernel will then fill in the size, in bytes, which tells userspace how
+ *    memory it needs to allocate for the blob(say for an array of properties).
+ *
+ * 2. Next we call DRM_IOCTL_I915_QUERY again, this time with the
+ *    &drm_i915_query_item.data_ptr equal to our newly allocated blob. Note that
+ *    the &drm_i915_query_item.length should still be the same as what the
+ *    kernel previously set. At this point the kernel can fill in the blob.
+ *
+ * Note that for some query items it can make sense for userspace to just pass
+ * in a buffer/blob equal to or larger than the required size. In this case only
+ * a single ioctl call is needed. For some smaller query items this can work
+ * quite well.
+ *
+ */
 struct drm_i915_query {
+	/** @num_items: The number of elements in the @items_ptr array */
 	__u32 num_items;
 
-	/*
-	 * Unused for now. Must be cleared to zero.
+	/**
+	 * @flags: Unused for now. Must be cleared to zero.
 	 */
 	__u32 flags;
 
-	/*
-	 * This points to an array of num_items drm_i915_query_item structures.
+	/**
+	 * @items_ptr:
+	 *
+	 * Pointer to an array of struct drm_i915_query_item. The number of
+	 * array elements is @num_items.
 	 */
 	__u64 items_ptr;
 };
@@ -2292,21 +2382,21 @@ struct drm_i915_query_topology_info {
  * Describes one engine and it's capabilities as known to the driver.
  */
 struct drm_i915_engine_info {
-	/** Engine class and instance. */
+	/** @engine: Engine class and instance. */
 	struct i915_engine_class_instance engine;
 
-	/** Reserved field. */
+	/** @rsvd0: Reserved field. */
 	__u32 rsvd0;
 
-	/** Engine flags. */
+	/** @flags: Engine flags. */
 	__u64 flags;
 
-	/** Capabilities of this engine. */
+	/** @capabilities: Capabilities of this eng