Merge tag 'perf-tools-for-v5.16-2021-11-13' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull more perf tools updates from Arnaldo Carvalho de Melo:
 "Hardware tracing:

   - ARM:
      * Print the size of the buffer size consistently in hexadecimal in
        ARM Coresight.
      * Add Coresight snapshot mode support.
      * Update --switch-events docs in 'perf record'.
      * Support hardware-based PID tracing.
      * Track task context switch for cpu-mode events.

   - Vendor events:
      * Add metric events JSON file for power10 platform

  perf test:

   - Get 'perf test' unit tests closer to kunit.

   - Topology tests improvements.

   - Remove bashisms from some tests.

  perf bench:

   - Fix memory leak of perf_cpu_map__new() in the futex benchmarks.

  libbpf:

   - Add some more weak libbpf functions o allow building with the
     libbpf versions, old ones, present in distros.

  libbeauty:

   - Translate [gs]setsockopt 'level' argument integer values to
     strings.

  tools headers UAPI:

   - Sync futex_waitv, arch prctl, sound, i195_drm and msr-index files
     with the kernel sources.

  Documentation:

   - Add documentation to 'struct symbol'.

   - Synchronize the definition of enum perf_hw_id with code in
     tools/perf/design.txt"

* tag 'perf-tools-for-v5.16-2021-11-13' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (67 commits)
  perf tests: Remove bash constructs from stat_all_pmu.sh
  perf tests: Remove bash construct from record+zstd_comp_decomp.sh
  perf test: Remove bash construct from stat_bpf_counters.sh test
  perf bench futex: Fix memory leak of perf_cpu_map__new()
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
  tools headers UAPI: Sync sound/asound.h with the kernel sources
  tools headers UAPI: Sync linux/prctl.h with the kernel sources
  tools headers UAPI: Sync arch prctl headers with the kernel sources
  perf tools: Add more weak libbpf functions
  perf bpf: Avoid memory leak from perf_env__insert_btf()
  perf symbols: Factor out annotation init/exit
  perf symbols: Bit pack to save a byte
  perf symbols: Add documentation to 'struct symbol'
  tools headers UAPI: Sync files changed by new futex_waitv syscall
  perf test bpf: Use ARRAY_CHECK() instead of ad-hoc equivalent, addressing array_size.cocci warning
  perf arm-spe: Support hardware-based PID tracing
  perf arm-spe: Save context ID in record
  perf arm-spe: Update --switch-events docs in 'perf record'
  perf arm-spe: Track task context switch for cpu-mode events
  ...

Author: torvalds

tools/arch/x86/include/asm/msr-index.h

@@ -625,6 +625,8 @@
 
 #define MSR_IA32_BNDCFGS_RSVD		0x00000ffc
 
+#define MSR_IA32_XFD			0x000001c4
+#define MSR_IA32_XFD_ERR		0x000001c5
 #define MSR_IA32_XSS			0x00000da0
 
 #define MSR_IA32_APICBASE		0x0000001b

tools/arch/x86/include/uapi/asm/prctl.h

@@ -10,6 +10,10 @@
 #define ARCH_GET_CPUID		0x1011
 #define ARCH_SET_CPUID		0x1012
 
+#define ARCH_GET_XCOMP_SUPP	0x1021
+#define ARCH_GET_XCOMP_PERM	0x1022
+#define ARCH_REQ_XCOMP_PERM	0x1023
+
 #define ARCH_MAP_VDSO_X32	0x2001
 #define ARCH_MAP_VDSO_32	0x2002
 #define ARCH_MAP_VDSO_64	0x2003

tools/include/uapi/asm-generic/unistd.h

@@ -880,8 +880,11 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret)
 #define __NR_process_mrelease 448
 __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 
+#define __NR_futex_waitv 449
+__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
+
 #undef __NR_syscalls
-#define __NR_syscalls 449
+#define __NR_syscalls 450
 
 /*
  * 32 bit systems traditionally used different

tools/include/uapi/drm/i915_drm.h

@@ -1522,6 +1522,12 @@ struct drm_i915_gem_caching {
 #define I915_TILING_NONE	0
 #define I915_TILING_X		1
 #define I915_TILING_Y		2
+/*
+ * Do not add new tiling types here.  The I915_TILING_* values are for
+ * de-tiling fence registers that no longer exist on modern platforms.  Although
+ * the hardware may support new types of tiling in general (e.g., Tile4), we
+ * do not need to add them to the uapi that is specific to now-defunct ioctls.
+ */
 #define I915_TILING_LAST	I915_TILING_Y
 
 #define I915_BIT_6_SWIZZLE_NONE		0
@@ -1824,6 +1830,7 @@ struct drm_i915_gem_context_param {
  * Extensions:
  *   i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
  *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
+ *   i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT)
  */
 #define I915_CONTEXT_PARAM_ENGINES	0xa
 
@@ -1846,6 +1853,55 @@ struct drm_i915_gem_context_param {
  * attempted to use it, never re-use this context param number.
  */
 #define I915_CONTEXT_PARAM_RINGSIZE	0xc
+
+/*
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT:
+ *
+ * Mark that the context makes use of protected content, which will result
+ * in the context being invalidated when the protected content session is.
+ * Given that the protected content session is killed on suspend, the device
+ * is kept awake for the lifetime of a protected context, so the user should
+ * make sure to dispose of them once done.
+ * This flag can only be set at context creation time and, when set to true,
+ * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE
+ * to false. This flag can't be set to true in conjunction with setting the
+ * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example:
+ *
+ * .. code-block:: C
+ *
+ *	struct drm_i915_gem_context_create_ext_setparam p_protected = {
+ *		.base = {
+ *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ *		},
+ *		.param = {
+ *			.param = I915_CONTEXT_PARAM_PROTECTED_CONTENT,
+ *			.value = 1,
+ *		}
+ *	};
+ *	struct drm_i915_gem_context_create_ext_setparam p_norecover = {
+ *		.base = {
+ *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ *			.next_extension = to_user_pointer(&p_protected),
+ *		},
+ *		.param = {
+ *			.param = I915_CONTEXT_PARAM_RECOVERABLE,
+ *			.value = 0,
+ *		}
+ *	};
+ *	struct drm_i915_gem_context_create_ext create = {
+ *		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ *		.extensions = to_user_pointer(&p_norecover);
+ *	};
+ *
+ *	ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * In addition to the normal failure cases, setting this flag during context
+ * creation can result in the following errors:
+ *
+ * -ENODEV: feature not available
+ * -EPERM: trying to mark a recoverable or not bannable context as protected
+ */
+#define I915_CONTEXT_PARAM_PROTECTED_CONTENT    0xd
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
@@ -2049,6 +2105,135 @@ struct i915_context_engines_bond {
 	struct i915_engine_class_instance engines[N__]; \
 } __attribute__((packed)) name__
 
+/**
+ * struct i915_context_engines_parallel_submit - Configure engine for
+ * parallel submission.
+ *
+ * Setup a slot in the context engine map to allow multiple BBs to be submitted
+ * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
+ * in parallel. Multiple hardware contexts are created internally in the i915 to
+ * run these BBs. Once a slot is configured for N BBs only N BBs can be
+ * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
+ * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
+ * many BBs there are based on the slot's configuration. The N BBs are the last
+ * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
+ *
+ * The default placement behavior is to create implicit bonds between each
+ * context if each context maps to more than 1 physical engine (e.g. context is
+ * a virtual engine). Also we only allow contexts of same engine class and these
+ * contexts must be in logically contiguous order. Examples of the placement
+ * behavior are described below. Lastly, the default is to not allow BBs to be
+ * preempted mid-batch. Rather insert coordinated preemption points on all
+ * hardware contexts between each set of BBs. Flags could be added in the future
+ * to change both of these default behaviors.
+ *
+ * Returns -EINVAL if hardware context placement configuration is invalid or if
+ * the placement configuration isn't supported on the platform / submission
+ * interface.
+ * Returns -ENODEV if extension isn't supported on the platform / submission
+ * interface.
+ *
+ * .. code-block:: none
+ *
+ *	Examples syntax:
+ *	CS[X] = generic engine of same class, logical instance X
+ *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
+ *
+ *	Example 1 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=1,
+ *		     engines=CS[0],CS[1])
+ *
+ *	Results in the following valid placement:
+ *	CS[0], CS[1]
+ *
+ *	Example 2 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[2],CS[1],CS[3])
+ *
+ *	Results in the following valid placements:
+ *	CS[0], CS[1]
+ *	CS[2], CS[3]
+ *
+ *	This can be thought of as two virtual engines, each containing two
+ *	engines thereby making a 2D array. However, there are bonds tying the
+ *	entries together and placing restrictions on how they can be scheduled.
+ *	Specifically, the scheduler can choose only vertical columns from the 2D
+ *	array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the
+ *	scheduler wants to submit to CS[0], it must also choose CS[1] and vice
+ *	versa. Same for CS[2] requires also using CS[3].
+ *	VE[0] = CS[0], CS[2]
+ *	VE[1] = CS[1], CS[3]
+ *
+ *	Example 3 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[1],CS[1],CS[3])
+ *
+ *	Results in the following valid and invalid placements:
+ *	CS[0], CS[1]
+ *	CS[1], CS[3] - Not logically contiguous, return -EINVAL
+ */
+struct i915_context_engines_parallel_submit {
+	/**
+	 * @base: base user extension.
+	 */
+	struct i915_user_extension base;
+
+	/**
+	 * @engine_index: slot for parallel engine
+	 */
+	__u16 engine_index;
+
+	/**
+	 * @width: number of contexts per parallel engine or in other words the
+	 * number of batches in each submission
+	 */
+	__u16 width;
+
+	/**
+	 * @num_siblings: number of siblings per context or in other words the
+	 * number of possible placements for each submission
+	 */
+	__u16 num_siblings;
+
+	/**
+	 * @mbz16: reserved for future use; must be zero
+	 */
+	__u16 mbz16;
+
+	/**
+	 * @flags: all undefined flags must be zero, currently not defined flags
+	 */
+	__u64 flags;
+
+	/**
+	 * @mbz64: reserved for future use; must be zero
+	 */
+	__u64 mbz64[3];
+
+	/**
+	 * @engines: 2-d array of engine instances to configure parallel engine
+	 *
+	 * length = width (i) * num_siblings (j)
+	 * index = j + i * num_siblings
+	 */
+	struct i915_engine_class_instance engines[0];
+
+} __packed;
+
+#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \
+	struct i915_user_extension base; \
+	__u16 engine_index; \
+	__u16 width; \
+	__u16 num_siblings; \
+	__u16 mbz16; \
+	__u64 flags; \
+	__u64 mbz64[3]; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
 /**
  * DOC: Context Engine Map uAPI
  *
@@ -2108,6 +2293,7 @@ struct i915_context_param_engines {
 	__u64 extensions; /* linked chain of extension blocks, 0 terminates */
 #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
 #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
+#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
 	struct i915_engine_class_instance engines[0];
 } __attribute__((packed));
 
@@ -2726,14 +2912,20 @@ struct drm_i915_engine_info {
 
 	/** @flags: Engine flags. */
 	__u64 flags;
+#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE		(1 << 0)
 
 	/** @capabilities: Capabilities of this engine. */
 	__u64 capabilities;
 #define I915_VIDEO_CLASS_CAPABILITY_HEVC		(1 << 0)
 #define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC	(1 << 1)
 
+	/** @logical_instance: Logical instance of engine */
+	__u16 logical_instance;
+
 	/** @rsvd1: Reserved fields. */
-	__u64 rsvd1[4];
+	__u16 rsvd1[3];
+	/** @rsvd2: Reserved fields. */
+	__u64 rsvd2[3];
 };
 
 /**
@@ -2979,8 +3171,12 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see
 	 * struct drm_i915_gem_create_ext_memory_regions.
+	 *
+	 * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
+	 * struct drm_i915_gem_create_ext_protected_content.
 	 */
 #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
+#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
 	__u64 extensions;
 };
 
@@ -3038,6 +3234,50 @@ struct drm_i915_gem_create_ext_memory_regions {
 	__u64 regions;
 };
 
+/**
+ * struct drm_i915_gem_create_ext_protected_content - The
+ * I915_OBJECT_PARAM_PROTECTED_CONTENT extension.
+ *
+ * If this extension is provided, buffer contents are expected to be protected
+ * by PXP encryption and require decryption for scan out and processing. This
+ * is only possible on platforms that have PXP enabled, on all other scenarios
+ * using this extension will cause the ioctl to fail and return -ENODEV. The
+ * flags parameter is reserved for future expansion and must currently be set
+ * to zero.
+ *
+ * The buffer contents are considered invalid after a PXP session teardown.
+ *
+ * The encryption is guaranteed to be processed correctly only if the object
+ * is submitted with a context created using the
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks
+ * at submission time on the validity of the objects involved.
+ *
+ * Below is an example on how to create a protected object:
+ *
+ * .. code-block:: C
+ *
+ *      struct drm_i915_gem_create_ext_protected_content protected_ext = {
+ *              .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT },
+ *              .flags = 0,
+ *      };
+ *      struct drm_i915_gem_create_ext create_ext = {
+ *              .size = PAGE_SIZE,
+ *              .extensions = (uintptr_t)&protected_ext,
+ *      };
+ *
+ *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ *      if (err) ...
+ */
+struct drm_i915_gem_create_ext_protected_content {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+	/** @flags: reserved for future usage, currently MBZ */
+	__u32 flags;
+};
+
+/* ID of the protected content session managed by i915 when PXP is active */
+#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
+
 #if defined(__cplusplus)
 }
 #endif

tools/include/uapi/linux/prctl.h

@@ -268,5 +268,8 @@ struct prctl_mm_map {
 # define PR_SCHED_CORE_SHARE_TO		2 /* push core_sched cookie to pid */
 # define PR_SCHED_CORE_SHARE_FROM	3 /* pull core_sched cookie to pid */
 # define PR_SCHED_CORE_MAX		4
+# define PR_SCHED_CORE_SCOPE_THREAD		0
+# define PR_SCHED_CORE_SCOPE_THREAD_GROUP	1
+# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP	2
 
 #endif /* _LINUX_PRCTL_H */

tools/include/uapi/sound/asound.h

@@ -1002,7 +1002,7 @@ typedef int __bitwise snd_ctl_elem_iface_t;
 #define SNDRV_CTL_ELEM_ACCESS_WRITE		(1<<1)
 #define SNDRV_CTL_ELEM_ACCESS_READWRITE		(SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
 #define SNDRV_CTL_ELEM_ACCESS_VOLATILE		(1<<2)	/* control value may be changed without a notification */
-// (1 << 3) is unused.
+/* (1 << 3) is unused. */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READ		(1<<4)	/* TLV read is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE		(1<<5)	/* TLV write is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE	(SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)

tools/perf/Documentation/perf-record.txt

@@ -469,7 +469,7 @@ This option sets the time out limit. The default value is 500 ms.
 
 --switch-events::
 Record context switch events i.e. events of type PERF_RECORD_SWITCH or
-PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT or CoreSight)
+PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT, CoreSight or Arm SPE)
 switch events will be enabled automatically, which can be suppressed by
 by the option --no-switch-events.