Merge tag 'perf-tools-fixes-for-v6.4-1-2023-05-20' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fail graciously if BUILD_BPF_SKEL=1 is specified and clang isn't
   available

 - Add empty 'struct rq' to 'perf lock contention' to satisfy libbpf
   'runqueue' type verification. This feature is built only with
   BUILD_BPF_SKEL=1

 - Make vmlinux.h use bpf.h and perf_event.h in source directory, not
   system ones that may be old and not have things like 'union
   perf_sample_weight'

 - Add system include paths to BPF builds to pick things missing in the
   headers included by clang -target bpf

 - Update various header copies with the kernel sources

 - Change divide by zero and not supported events behavior to show
   'nan'/'not counted' in 'perf stat' output.

   This happens when using things like 'perf stat -M TopdownL2 true',
   involving JSON metrics

 - Update no event/metric expectations affected by using JSON metrics in
   'perf stat -ddd' perf test

 - Avoid segv with 'perf stat --topdown' for metrics without a group

 - Do not assume which events may have a PMU name, allowing the logic to
   keep an AUX event group together. Makes this usecase work again:

     $ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1
     [ perf record: Woken up 1 times to write data ]
     [ perf record: Captured and wrote 0.078 MB perf.data ]
     $ perf script -F-dso,+addr | grep -C5 tlb_flush.stlb_any | head -11
     sleep 20444 [003]  7939.510243:  1  branches:uH:  7f5350cc82a2 dl_main+0x9a2 => 7f5350cb38f0 _dl_add_to_namespace_list+0x0
     sleep 20444 [003]  7939.510243:  1  branches:uH:  7f5350cb3908 _dl_add_to_namespace_list+0x18 => 7f5350cbb080 rtld_mutex_dummy+0x0
     sleep 20444 [003]  7939.510243:  1  branches:uH:  7f5350cc8350 dl_main+0xa50 => 0 [unknown]
     sleep 20444 [003]  7939.510244:  1  branches:uH:  7f5350cc83ca dl_main+0xaca => 7f5350caeb60 _dl_process_pt_gnu_property+0x0
     sleep 20444 [003]  7939.510245:  1  branches:uH:  7f5350caeb60 _dl_process_pt_gnu_property+0x0 => 0 [unknown]
     sleep 20444  7939.510245:       10 tlb_flush.stlb_any/aux-sample-size=8192/pp: 0 7f5350caeb60 _dl_process_pt_gnu_property+0x0
     sleep 20444 [003]  7939.510254:  1  branches:uH:  7f5350cc87fe dl_main+0xefe => 7f5350ccd240 strcmp+0x0
     sleep 20444 [003]  7939.510254:  1  branches:uH:  7f5350cc8862 dl_main+0xf62 => 0 [unknown]

 - Add a check for the above use case in 'perf test test_intel_pt'

 - Fix build with refcount checking on arm64, it was still accessing
   fields that need to be wrapped so that the refcounted struct gets
   checked

 - Fix contextid validation in ARM's CS-ETM, so that older kernels
   without that field can still be supported

 - Skip unsupported aggregation for stat events found in perf.data files
   in 'perf script'

 - Add stat test for record and script to check the previous problem

 - Remove needless debuginfod queries from 'perf test java symbol', this
   was just making the test take a long time to complete

 - Address python SafeConfigParser() deprecation warning in 'perf test
   attr'

 - Fix __NR_execve undeclared on i386 'perf bench syscall' build error

* tag 'perf-tools-fixes-for-v6.4-1-2023-05-20' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (33 commits)
  perf bench syscall: Fix __NR_execve undeclared build error
  perf test attr: Fix python SafeConfigParser() deprecation warning
  perf test attr: Update no event/metric expectations
  tools headers disabled-features: Sync with the kernel sources
  tools headers UAPI: Sync arch prctl headers with the kernel sources
  tools headers: Update the copy of x86's mem{cpy,set}_64.S used in 'perf bench'
  tools headers x86 cpufeatures: Sync with the kernel sources
  tools headers UAPI: Sync s390 syscall table file that wires up the memfd_secret syscall
  tools headers UAPI: Sync linux/prctl.h with the kernel sources
  perf metrics: Avoid segv with --topdown for metrics without a group
  perf lock contention: Add empty 'struct rq' to satisfy libbpf 'runqueue' type verification
  perf cs-etm: Fix contextid validation
  perf arm64: Fix build with refcount checking
  perf test: Add stat test for record and script
  perf script: Skip aggregation for stat events
  perf build: Add system include paths to BPF builds
  perf bpf skels: Make vmlinux.h use bpf.h and perf_event.h in source directory
  perf parse-events: Do not break up AUX event group
  perf test test_intel_pt.sh: Test sample mode with event with PMU name
  perf evsel: Modify group pmu name for software events
  ...

7 files changed, 103 insertions, 10 deletions

diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 642808520d92..a87bbbbca2d4 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -972,6 +972,19 @@ extern "C" {
 #define DRM_IOCTL_GET_STATS             DRM_IOR( 0x06, struct drm_stats)
 #define DRM_IOCTL_SET_VERSION		DRM_IOWR(0x07, struct drm_set_version)
 #define DRM_IOCTL_MODESET_CTL           DRM_IOW(0x08, struct drm_modeset_ctl)
+/**
+ * DRM_IOCTL_GEM_CLOSE - Close a GEM handle.
+ *
+ * GEM handles are not reference-counted by the kernel. User-space is
+ * responsible for managing their lifetime. For example, if user-space imports
+ * the same memory object twice on the same DRM file description, the same GEM
+ * handle is returned by both imports, and user-space needs to ensure
+ * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen
+ * when a memory object is allocated, then exported and imported again on the
+ * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception
+ * and always returns fresh new GEM handles even if an existing GEM handle
+ * already refers to the same memory object before the IOCTL is performed.
+ */
 #define DRM_IOCTL_GEM_CLOSE		DRM_IOW (0x09, struct drm_gem_close)
 #define DRM_IOCTL_GEM_FLINK		DRM_IOWR(0x0a, struct drm_gem_flink)
 #define DRM_IOCTL_GEM_OPEN		DRM_IOWR(0x0b, struct drm_gem_open)
@@ -1012,7 +1025,37 @@ extern "C" {
 #define DRM_IOCTL_UNLOCK		DRM_IOW( 0x2b, struct drm_lock)
 #define DRM_IOCTL_FINISH		DRM_IOW( 0x2c, struct drm_lock)
 
+/**
+ * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD.
+ *
+ * User-space sets &drm_prime_handle.handle with the GEM handle to export and
+ * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in
+ * &drm_prime_handle.fd.
+ *
+ * The export can fail for any driver-specific reason, e.g. because export is
+ * not supported for this specific GEM handle (but might be for others).
+ *
+ * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT.
+ */
 #define DRM_IOCTL_PRIME_HANDLE_TO_FD    DRM_IOWR(0x2d, struct drm_prime_handle)
+/**
+ * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle.
+ *
+ * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to
+ * import, and gets back a GEM handle in &drm_prime_handle.handle.
+ * &drm_prime_handle.flags is unused.
+ *
+ * If an existing GEM handle refers to the memory object backing the DMA-BUF,
+ * that GEM handle is returned. Therefore user-space which needs to handle
+ * arbitrary DMA-BUFs must have a user-space lookup data structure to manually
+ * reference-count duplicated GEM handles. For more information see
+ * &DRM_IOCTL_GEM_CLOSE.
+ *
+ * The import can fail for any driver-specific reason, e.g. because import is
+ * only supported for DMA-BUFs allocated on this DRM device.
+ *
+ * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT.
+ */
 #define DRM_IOCTL_PRIME_FD_TO_HANDLE    DRM_IOWR(0x2e, struct drm_prime_handle)
 
 #define DRM_IOCTL_AGP_ACQUIRE		DRM_IO(  0x30)
@@ -1104,8 +1147,13 @@ extern "C" {
  * struct as the output.
  *
  * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles
- * will be filled with GEM buffer handles. Planes are valid until one has a
- * zero handle -- this can be used to compute the number of planes.
+ * will be filled with GEM buffer handles. Fresh new GEM handles are always
+ * returned, even if another GEM handle referring to the same memory object
+ * already exists on the DRM file description. The caller is responsible for
+ * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same
+ * new handle will be returned for multiple planes in case they use the same
+ * memory object. Planes are valid until one has a zero handle -- this can be
+ * used to compute the number of planes.
  *
  * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid
  * until one has a zero &drm_mode_fb_cmd2.pitches.
@@ -1113,6 +1161,11 @@ extern "C" {
  * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set
  * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the
  * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier.
+ *
+ * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space
+ * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately
+ * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not
+ * double-close handles which are specified multiple times in the array.
  */
 #define DRM_IOCTL_MODE_GETFB2		DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
 
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 8df261c5ab9b..dba7c5a5b25e 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -2491,7 +2491,7 @@ struct i915_context_param_engines {
 #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];
+	struct i915_engine_class_instance engines[];
 } __attribute__((packed));
 
 #define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \
@@ -2676,6 +2676,10 @@ enum drm_i915_oa_format {
 	I915_OAR_FORMAT_A32u40_A4u32_B8_C8,
 	I915_OA_FORMAT_A24u40_A14u32_B8_C8,
 
+	/* MTL OAM */
+	I915_OAM_FORMAT_MPEC8u64_B8_C8,
+	I915_OAM_FORMAT_MPEC8u32_B8_C8,
+
 	I915_OA_FORMAT_MAX	    /* non-ABI */
 };
 
@@ -2758,6 +2762,25 @@ enum drm_i915_perf_property_id {
 	 */
 	DRM_I915_PERF_PROP_POLL_OA_PERIOD,
 
+	/**
+	 * Multiple engines may be mapped to the same OA unit. The OA unit is
+	 * identified by class:instance of any engine mapped to it.
+	 *
+	 * This parameter specifies the engine class and must be passed along
+	 * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE.
+	 *
+	 * This property is available in perf revision 6.
+	 */
+	DRM_I915_PERF_PROP_OA_ENGINE_CLASS,
+
+	/**
+	 * This parameter specifies the engine instance and must be passed along
+	 * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS.
+	 *
+	 * This property is available in perf revision 6.
+	 */
+	DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE,
+
 	DRM_I915_PERF_PROP_MAX /* non-ABI */
 };
 
diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h
index af2a44c08683..a429381e7ca5 100644
--- a/tools/include/uapi/linux/const.h
+++ b/tools/include/uapi/linux/const.h
@@ -28,7 +28,7 @@
 #define _BITUL(x)	(_UL(1) << (x))
 #define _BITULL(x)	(_ULL(1) << (x))
 
-#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1)
 #define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
 
 #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 07a4cb149305..4b7f2df66b99 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -162,6 +162,7 @@ struct in_addr {
 #define MCAST_MSFILTER			48
 #define IP_MULTICAST_ALL		49
 #define IP_UNICAST_IF			50
+#define IP_LOCAL_PORT_RANGE		51
 
 #define MCAST_EXCLUDE	0
 #define MCAST_INCLUDE	1
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 4003a166328c..737318b1c1d9 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -341,8 +341,13 @@ struct kvm_run {
 			__u64 nr;
 			__u64 args[6];
 			__u64 ret;
-			__u32 longmode;
-			__u32 pad;
+
+			union {
+#ifndef __KERNEL__
+				__u32 longmode;
+#endif
+				__u64 flags;
+			};
 		} hypercall;
 		/* KVM_EXIT_TPR_ACCESS */
 		struct {
@@ -1184,6 +1189,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224
 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226
+#define KVM_CAP_COUNTER_OFFSET 227
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1543,6 +1549,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct kvm_pmu_event_filter)
 #define KVM_PPC_SVM_OFF		  _IO(KVMIO,  0xb3)
 #define KVM_ARM_MTE_COPY_TAGS	  _IOR(KVMIO,  0xb4, struct kvm_arm_copy_mte_tags)
+/* Available with KVM_CAP_COUNTER_OFFSET */
+#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO,  0xb5, struct kvm_arm_counter_offset)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 759b3f53e53f..f23d9a16507f 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -290,6 +290,8 @@ struct prctl_mm_map {
 #define PR_SET_VMA		0x53564d41
 # define PR_SET_VMA_ANON_NAME		0
 
+#define PR_GET_AUXV			0x41555856
+
 #define PR_SET_MEMORY_MERGE		67
 #define PR_GET_MEMORY_MERGE		68
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index de6810e94abe..0aa955aa8246 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -429,9 +429,14 @@ struct snd_pcm_sw_params {
 	snd_pcm_uframes_t avail_min;		/* min avail frames for wakeup */
 	snd_pcm_uframes_t xfer_align;		/* obsolete: xfer size need to be a multiple */
 	snd_pcm_uframes_t start_threshold;	/* min hw_avail frames for automatic start */
-	snd_pcm_uframes_t stop_threshold;	/* min avail frames for automatic stop */
-	snd_pcm_uframes_t silence_threshold;	/* min distance from noise for silence filling */
-	snd_pcm_uframes_t silence_size;		/* silence block size */
+	/*
+	 * The following two thresholds alleviate playback buffer underruns; when
+	 * hw_avail drops below the threshold, the respective action is triggered:
+	 */
+	snd_pcm_uframes_t stop_threshold;	/* - stop playback */
+	snd_pcm_uframes_t silence_threshold;	/* - pre-fill buffer with silence */
+	snd_pcm_uframes_t silence_size;		/* max size of silence pre-fill; when >= boundary,
+						 * fill played area with silence immediately */
 	snd_pcm_uframes_t boundary;		/* pointers wrap point */
 	unsigned int proto;			/* protocol version */
 	unsigned int tstamp_type;		/* timestamp type (req. proto >= 2.0.12) */
@@ -570,7 +575,8 @@ struct __snd_pcm_mmap_status64 {
 struct __snd_pcm_mmap_control64 {
 	__pad_before_uframe __pad1;
 	snd_pcm_uframes_t appl_ptr;	 /* RW: appl ptr (0...boundary-1) */
-	__pad_before_uframe __pad2;
+	__pad_before_uframe __pad2;	 // This should be __pad_after_uframe, but binary
+					 // backwards compatibility constraints prevent a fix.
 
 	__pad_before_uframe __pad3;
 	snd_pcm_uframes_t  avail_min;	 /* RW: min available frames for wakeup */