Merge tag 'perf-tools-fixes-for-v6.5-1-2023-07-18' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Don't group events when computing metrics that require more than the
   maximum number of simultaneously enabled events on AMD systems.

 - Fix multi CU handling in 'perf probe', add a 'perf test' entry to
   regress test it.

 - Make the 'perf test task_exit' stop generating samples by using the
   'dummy' event, all it is testing is if a PERF_RECORD_EXIT is
   generated at the end of a perf session. This makes this perf test to
   stop sometimes failing on some systems due to a full ring buffer.

 - Avoid SEGV if PMU lookup fails for legacy cache terms.

 - Fix libsubcmd SEGV/use-after-free when commands aren't excluded.

 - Fix OpenCSD (ARM64's CoreSight hardware tracing) library path
   resolution when specifying CSLIBS= in the make command line.

 - Fix broken feature check for libtracefs due to external lib changes,
   use the provided pkgconfig file instead future proof it.

 - Sync drm, fcntl, kvm, mount, prctl, socket, vhost, asound, arm64's
   cputype headers with the kernel sources, in some cases this made the
   tools become aware of new kernel APIs such as ioctls and the
   cachestat sysctl.

* tag 'perf-tools-fixes-for-v6.5-1-2023-07-18' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools:
  perf test task_exit: No need for a cycles event to check if we get an PERF_RECORD_EXIT
  tools headers arm64: Sync arm64's cputype.h with the kernel sources
  tools include UAPI: Sync the sound/asound.h copy with the kernel sources
  tools include UAPI: Sync linux/vhost.h with the kernel sources
  perf beauty: Update copy of linux/socket.h with the kernel sources
  perf parse-events: Avoid SEGV if PMU lookup fails for legacy cache terms
  libsubcmd: Avoid SEGV/use-after-free when commands aren't excluded
  tools headers UAPI: Sync linux/prctl.h with the kernel sources
  perf build: Fix broken feature check for libtracefs due to external lib changes
  tools include UAPI: Sync linux/mount.h copy with the kernel sources
  tools headers UAPI: Sync linux/kvm.h with the kernel sources
  tools headers uapi: Sync linux/fcntl.h with the kernel sources
  perf vendor events amd: Fix large metrics
  perf build: Fix library not found error when using CSLIBS
  tools headers UAPI: Sync files changed by new cachestat syscall with the kernel sources
  tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
  perf probe: Read DWARF files from the correct CU
  perf probe: Add test for regression introduced by switch to die_get_decl_file()

Author: torvalds

tools/arch/arm64/include/asm/cputype.h

@@ -126,6 +126,10 @@
 #define APPLE_CPU_PART_M1_FIRESTORM_MAX	0x029
 #define APPLE_CPU_PART_M2_BLIZZARD	0x032
 #define APPLE_CPU_PART_M2_AVALANCHE	0x033
+#define APPLE_CPU_PART_M2_BLIZZARD_PRO	0x034
+#define APPLE_CPU_PART_M2_AVALANCHE_PRO	0x035
+#define APPLE_CPU_PART_M2_BLIZZARD_MAX	0x038
+#define APPLE_CPU_PART_M2_AVALANCHE_MAX	0x039
 
 #define AMPERE_CPU_PART_AMPERE1		0xAC3
 
@@ -181,6 +185,10 @@
 #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
 #define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD)
 #define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE)
+#define MIDR_APPLE_M2_BLIZZARD_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_PRO)
+#define MIDR_APPLE_M2_AVALANCHE_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_PRO)
+#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
+#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
 
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */

tools/build/feature/Makefile

@@ -208,7 +208,7 @@ $(OUTPUT)test-libtraceevent.bin:
 	$(BUILD) -ltraceevent
 
 $(OUTPUT)test-libtracefs.bin:
-	$(BUILD) -ltracefs
+	 $(BUILD) $(shell $(PKG_CONFIG) --cflags libtraceevent 2>/dev/null) -ltracefs
 
 $(OUTPUT)test-libcrypto.bin:
 	$(BUILD) -lcrypto

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

@@ -817,8 +817,11 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 #define __NR_set_mempolicy_home_node 450
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 
+#define __NR_cachestat 451
+__SYSCALL(__NR_cachestat, sys_cachestat)
+
 #undef __NR_syscalls
-#define __NR_syscalls 451
+#define __NR_syscalls 452
 
 /*
  * 32 bit systems traditionally used different

tools/include/uapi/drm/i915_drm.h

@@ -280,7 +280,16 @@ enum drm_i915_pmu_engine_sample {
 #define I915_PMU_ENGINE_SEMA(class, instance) \
 	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)
 
-#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))
+/*
+ * Top 4 bits of every non-engine counter are GT id.
+ */
+#define __I915_PMU_GT_SHIFT (60)
+
+#define ___I915_PMU_OTHER(gt, x) \
+	(((__u64)__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) | \
+	((__u64)(gt) << __I915_PMU_GT_SHIFT))
+
+#define __I915_PMU_OTHER(x) ___I915_PMU_OTHER(0, x)
 
 #define I915_PMU_ACTUAL_FREQUENCY	__I915_PMU_OTHER(0)
 #define I915_PMU_REQUESTED_FREQUENCY	__I915_PMU_OTHER(1)
@@ -290,6 +299,12 @@ enum drm_i915_pmu_engine_sample {
 
 #define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY
 
+#define __I915_PMU_ACTUAL_FREQUENCY(gt)		___I915_PMU_OTHER(gt, 0)
+#define __I915_PMU_REQUESTED_FREQUENCY(gt)	___I915_PMU_OTHER(gt, 1)
+#define __I915_PMU_INTERRUPTS(gt)		___I915_PMU_OTHER(gt, 2)
+#define __I915_PMU_RC6_RESIDENCY(gt)		___I915_PMU_OTHER(gt, 3)
+#define __I915_PMU_SOFTWARE_GT_AWAKE_TIME(gt)	___I915_PMU_OTHER(gt, 4)
+
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */
 #define I915_NR_TEX_REGIONS 255	/* table size 2k - maximum due to use
@@ -659,7 +674,8 @@ typedef struct drm_i915_irq_wait {
  * If the IOCTL is successful, the returned parameter will be set to one of the
  * following values:
  *  * 0 if HuC firmware load is not complete,
- *  * 1 if HuC firmware is authenticated and running.
+ *  * 1 if HuC firmware is loaded and fully authenticated,
+ *  * 2 if HuC firmware is loaded and authenticated for clear media only
  */
 #define I915_PARAM_HUC_STATUS		 42
 
@@ -771,6 +787,25 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_OA_TIMESTAMP_FREQUENCY 57
 
+/*
+ * Query the status of PXP support in i915.
+ *
+ * The query can fail in the following scenarios with the listed error codes:
+ *     -ENODEV = PXP support is not available on the GPU device or in the
+ *               kernel due to missing component drivers or kernel configs.
+ *
+ * If the IOCTL is successful, the returned parameter will be set to one of
+ * the following values:
+ *     1 = PXP feature is supported and is ready for use.
+ *     2 = PXP feature is supported but should be ready soon (pending
+ *         initialization of non-i915 system dependencies).
+ *
+ * NOTE: When param is supported (positive return values), user space should
+ *       still refer to the GEM PXP context-creation UAPI header specs to be
+ *       aware of possible failure due to system state machine at the time.
+ */
+#define I915_PARAM_PXP_STATUS		 58
+
 /* Must be kept compact -- no holes and well documented */
 
 /**
@@ -2096,6 +2131,21 @@ struct drm_i915_gem_context_param {
  *
  * -ENODEV: feature not available
  * -EPERM: trying to mark a recoverable or not bannable context as protected
+ * -ENXIO: A dependency such as a component driver or firmware is not yet
+ *         loaded so user space may need to attempt again. Depending on the
+ *         device, this error may be reported if protected context creation is
+ *         attempted very early after kernel start because the internal timeout
+ *         waiting for such dependencies is not guaranteed to be larger than
+ *         required (numbers differ depending on system and kernel config):
+ *            - ADL/RPL: dependencies may take up to 3 seconds from kernel start
+ *                       while context creation internal timeout is 250 milisecs
+ *            - MTL: dependencies may take up to 8 seconds from kernel start
+ *                   while context creation internal timeout is 250 milisecs
+ *         NOTE: such dependencies happen once, so a subsequent call to create a
+ *         protected context after a prior successful call will not experience
+ *         such timeouts and will not return -ENXIO (unless the driver is reloaded,
+ *         or, depending on the device, resumes from a suspended state).
+ * -EIO: The firmware did not succeed in creating the protected context.
  */
 #define I915_CONTEXT_PARAM_PROTECTED_CONTENT    0xd
 /* Must be kept compact -- no holes and well documented */
@@ -3630,9 +3680,13 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
 	 * struct drm_i915_gem_create_ext_protected_content.
+	 *
+	 * For I915_GEM_CREATE_EXT_SET_PAT usage see
+	 * struct drm_i915_gem_create_ext_set_pat.
 	 */
 #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
 #define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
+#define I915_GEM_CREATE_EXT_SET_PAT 2
 	__u64 extensions;
 };
 
@@ -3747,6 +3801,43 @@ struct drm_i915_gem_create_ext_protected_content {
 	__u32 flags;
 };
 
+/**
+ * struct drm_i915_gem_create_ext_set_pat - The
+ * I915_GEM_CREATE_EXT_SET_PAT extension.
+ *
+ * If this extension is provided, the specified caching policy (PAT index) is
+ * applied to the buffer object.
+ *
+ * Below is an example on how to create an object with specific caching policy:
+ *
+ * .. code-block:: C
+ *
+ *      struct drm_i915_gem_create_ext_set_pat set_pat_ext = {
+ *              .base = { .name = I915_GEM_CREATE_EXT_SET_PAT },
+ *              .pat_index = 0,
+ *      };
+ *      struct drm_i915_gem_create_ext create_ext = {
+ *              .size = PAGE_SIZE,
+ *              .extensions = (uintptr_t)&set_pat_ext,
+ *      };
+ *
+ *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ *      if (err) ...
+ */
+struct drm_i915_gem_create_ext_set_pat {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+	/**
+	 * @pat_index: PAT index to be set
+	 * PAT index is a bit field in Page Table Entry to control caching
+	 * behaviors for GPU accesses. The definition of PAT index is
+	 * platform dependent and can be found in hardware specifications,
+	 */
+	__u32 pat_index;
+	/** @rsvd: reserved for future use */
+	__u32 rsvd;
+};
+
 /* ID of the protected content session managed by i915 when PXP is active */
 #define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
 

tools/include/uapi/linux/fcntl.h

@@ -112,4 +112,9 @@
 
 #define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
 
+/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */
+#define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
+					compare object identity and may not
+					be usable to open_by_handle_at(2) */
+
 #endif /* _UAPI_LINUX_FCNTL_H */

tools/include/uapi/linux/kvm.h

@@ -1190,6 +1190,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226
 #define KVM_CAP_COUNTER_OFFSET 227
+#define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
+#define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1442,6 +1444,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_XIVE		KVM_DEV_TYPE_XIVE
 	KVM_DEV_TYPE_ARM_PV_TIME,
 #define KVM_DEV_TYPE_ARM_PV_TIME	KVM_DEV_TYPE_ARM_PV_TIME
+	KVM_DEV_TYPE_RISCV_AIA,
+#define KVM_DEV_TYPE_RISCV_AIA		KVM_DEV_TYPE_RISCV_AIA
 	KVM_DEV_TYPE_MAX,
 };
 
@@ -1613,7 +1617,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_GET_DEBUGREGS         _IOR(KVMIO,  0xa1, struct kvm_debugregs)
 #define KVM_SET_DEBUGREGS         _IOW(KVMIO,  0xa2, struct kvm_debugregs)
 /*
- * vcpu version available with KVM_ENABLE_CAP
+ * vcpu version available with KVM_CAP_ENABLE_CAP
  * vm version available with KVM_CAP_ENABLE_CAP_VM
  */
 #define KVM_ENABLE_CAP            _IOW(KVMIO,  0xa3, struct kvm_enable_cap)

tools/include/uapi/linux/mman.h

@@ -4,6 +4,7 @@
 
 #include <asm/mman.h>
 #include <asm-generic/hugetlb_encode.h>
+#include <linux/types.h>
 
 #define MREMAP_MAYMOVE		1
 #define MREMAP_FIXED		2
@@ -41,4 +42,17 @@
 #define MAP_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
 #define MAP_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
 
+struct cachestat_range {
+	__u64 off;
+	__u64 len;
+};
+
+struct cachestat {
+	__u64 nr_cache;
+	__u64 nr_dirty;
+	__u64 nr_writeback;
+	__u64 nr_evicted;
+	__u64 nr_recently_evicted;
+};
+
 #endif /* _UAPI_LINUX_MMAN_H */

tools/include/uapi/linux/mount.h

@@ -74,7 +74,8 @@
 #define MOVE_MOUNT_T_AUTOMOUNTS		0x00000020 /* Follow automounts on to path */
 #define MOVE_MOUNT_T_EMPTY_PATH		0x00000040 /* Empty to path permitted */
 #define MOVE_MOUNT_SET_GROUP		0x00000100 /* Set sharing group instead */
-#define MOVE_MOUNT__MASK		0x00000177
+#define MOVE_MOUNT_BENEATH		0x00000200 /* Mount beneath top mount */
+#define MOVE_MOUNT__MASK		0x00000377
 
 /*
  * fsopen() flags.

tools/include/uapi/linux/prctl.h

@@ -294,4 +294,15 @@ struct prctl_mm_map {
 
 #define PR_SET_MEMORY_MERGE		67
 #define PR_GET_MEMORY_MERGE		68
+
+#define PR_RISCV_V_SET_CONTROL		69
+#define PR_RISCV_V_GET_CONTROL		70
+# define PR_RISCV_V_VSTATE_CTRL_DEFAULT		0
+# define PR_RISCV_V_VSTATE_CTRL_OFF		1
+# define PR_RISCV_V_VSTATE_CTRL_ON		2
+# define PR_RISCV_V_VSTATE_CTRL_INHERIT		(1 << 4)
+# define PR_RISCV_V_VSTATE_CTRL_CUR_MASK	0x3
+# define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK	0xc
+# define PR_RISCV_V_VSTATE_CTRL_MASK		0x1f
+
 #endif /* _LINUX_PRCTL_H */

tools/include/uapi/linux/vhost.h

@@ -45,6 +45,25 @@
 #define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
 /* Specify an eventfd file descriptor to signal on log write. */
 #define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+/* By default, a device gets one vhost_worker that its virtqueues share. This
+ * command allows the owner of the device to create an additional vhost_worker
+ * for the device. It can later be bound to 1 or more of its virtqueues using
+ * the VHOST_ATTACH_VRING_WORKER command.
+ *
+ * This must be called after VHOST_SET_OWNER and the caller must be the owner
+ * of the device. The new thread will inherit caller's cgroups and namespaces,
+ * and will share the caller's memory space. The new thread will also be
+ * counted against the caller's RLIMIT_NPROC value.
+ *
+ * The worker's ID used in other commands will be returned in
+ * vhost_worker_state.
+ */
+#define VHOST_NEW_WORKER _IOR(VHOST_VIRTIO, 0x8, struct vhost_worker_state)
+/* Free a worker created with VHOST_NEW_WORKER if it's not attached to any
+ * virtqueue. If userspace is not able to call this for workers its created,
+ * the kernel will free all the device's workers when the device is closed.
+ */
+#define VHOST_FREE_WORKER _IOW(VHOST_VIRTIO, 0x9, struct vhost_worker_state)
 
 /* Ring setup. */
 /* Set number of descriptors in ring. This parameter can not
@@ -70,6 +89,18 @@
 #define VHOST_VRING_BIG_ENDIAN 1
 #define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
 #define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
+/* Attach a vhost_worker created with VHOST_NEW_WORKER to one of the device's
+ * virtqueues.
+ *
+ * This will replace the virtqueue's existing worker. If the replaced worker
+ * is no longer attached to any virtqueues, it can be freed with
+ * VHOST_FREE_WORKER.
+ */
+#define VHOST_ATTACH_VRING_WORKER _IOW(VHOST_VIRTIO, 0x15,		\
+				       struct vhost_vring_worker)
+/* Return the vring worker's ID */
+#define VHOST_GET_VRING_WORKER _IOWR(VHOST_VIRTIO, 0x16,		\
+				     struct vhost_vring_worker)
 
 /* The following ioctls use eventfd file descriptors to signal and poll
  * for events. */