Merge tag 'perf-tools-fixes-for-v6.10-2-2024-06-09' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

torvalds · torvalds · commit b8481381d4e2 · 2024-06-09T09:04:51.000-07:00
Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Update copies of kernel headers, which resulted in support for the
   new 'mseal' syscall, SUBVOL statx return mask bit, RISC-V and PPC
   prctls, fcntl's DUPFD_QUERY, POSTED_MSI_NOTIFICATION IRQ vector,
   'map_shadow_stack' syscall for x86-32.

 - Revert perf.data record memory allocation optimization that ended up
   causing a regression, work is being done to re-introduce it in the
   next merge window.

 - Fix handling of minimal vmlinux.h file used with BPF's CO-RE when
   interrupting the build.

* tag 'perf-tools-fixes-for-v6.10-2-2024-06-09' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools:
  perf bpf: Fix handling of minimal vmlinux.h file when interrupting the build
  Revert "perf record: Reduce memory for recording PERF_RECORD_LOST_SAMPLES event"
  tools headers arm64: Sync arm64's cputype.h with the kernel sources
  tools headers uapi: Sync linux/stat.h with the kernel sources to pick STATX_SUBVOL
  tools headers UAPI: Update i915_drm.h with the kernel sources
  tools headers UAPI: Sync kvm headers with the kernel sources
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools headers: Update the syscall tables and unistd.h, mostly to support the new 'mseal' syscall
  perf trace beauty: Update the arch/x86/include/asm/irq_vectors.h copy with the kernel sources to pick POSTED_MSI_NOTIFICATION
  perf beauty: Update copy of linux/socket.h with the kernel sources
  tools headers UAPI: Sync fcntl.h with the kernel sources to pick F_DUPFD_QUERY
  tools headers UAPI: Sync linux/prctl.h with the kernel sources
  tools include UAPI: Sync linux/stat.h with the kernel sources
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
@@ -86,6 +86,9 @@
 #define ARM_CPU_PART_CORTEX_X2		0xD48
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
 #define ARM_CPU_PART_CORTEX_A78C	0xD4B
+#define ARM_CPU_PART_NEOVERSE_V2	0xD4F
+#define ARM_CPU_PART_CORTEX_X4		0xD82
+#define ARM_CPU_PART_NEOVERSE_V3	0xD84
 
 #define APM_CPU_PART_XGENE		0x000
 #define APM_CPU_VAR_POTENZA		0x00
@@ -159,6 +162,9 @@
 #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
 #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
 #define MIDR_CORTEX_A78C	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
+#define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2)
+#define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4)
+#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
@@ -170,6 +170,10 @@
 						 * CPU is not affected by Branch
 						 * History Injection.
 						 */
+#define ARCH_CAP_XAPIC_DISABLE		BIT(21)	/*
+						 * IA32_XAPIC_DISABLE_STATUS MSR
+						 * supported
+						 */
 #define ARCH_CAP_PBRSB_NO		BIT(24)	/*
 						 * Not susceptible to Post-Barrier
 						 * Return Stack Buffer Predictions.
@@ -192,11 +196,6 @@
 						 * File.
 						 */
 
-#define ARCH_CAP_XAPIC_DISABLE		BIT(21)	/*
-						 * IA32_XAPIC_DISABLE_STATUS MSR
-						 * supported
-						 */
-
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
 						 * Writeback and invalidate the
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -457,8 +457,13 @@ struct kvm_sync_regs {
 
 #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE	0x00000001
 
-/* attributes for system fd (group 0) */
-#define KVM_X86_XCOMP_GUEST_SUPP	0
+/* vendor-independent attributes for system fd (group 0) */
+#define KVM_X86_GRP_SYSTEM		0
+#  define KVM_X86_XCOMP_GUEST_SUPP	0
+
+/* vendor-specific groups and attributes for system fd */
+#define KVM_X86_GRP_SEV			1
+#  define KVM_X86_SEV_VMSA_FEATURES	0
 
 struct kvm_vmx_nested_state_data {
 	__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
@@ -689,6 +694,9 @@ enum sev_cmd_id {
 	/* Guest Migration Extension */
 	KVM_SEV_SEND_CANCEL,
 
+	/* Second time is the charm; improved versions of the above ioctls.  */
+	KVM_SEV_INIT2,
+
 	KVM_SEV_NR_MAX,
 };
 
@@ -700,6 +708,14 @@ struct kvm_sev_cmd {
 	__u32 sev_fd;
 };
 
+struct kvm_sev_init {
+	__u64 vmsa_features;
+	__u32 flags;
+	__u16 ghcb_version;
+	__u16 pad1;
+	__u32 pad2[8];
+};
+
 struct kvm_sev_launch_start {
 	__u32 handle;
 	__u32 policy;
@@ -856,5 +872,7 @@ struct kvm_hyperv_eventfd {
 
 #define KVM_X86_DEFAULT_VM	0
 #define KVM_X86_SW_PROTECTED_VM	1
+#define KVM_X86_SEV_VM		2
+#define KVM_X86_SEV_ES_VM	3
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
@@ -842,8 +842,11 @@ __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
 #define __NR_lsm_list_modules 461
 __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
 
+#define __NR_mseal 462
+__SYSCALL(__NR_mseal, sys_mseal)
+
 #undef __NR_syscalls
-#define __NR_syscalls 462
+#define __NR_syscalls 463
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
@@ -806,6 +806,12 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_PXP_STATUS		 58
 
+/*
+ * Query if kernel allows marking a context to send a Freq hint to SLPC. This
+ * will enable use of the strategies allowed by the SLPC algorithm.
+ */
+#define I915_PARAM_HAS_CONTEXT_FREQ_HINT	59
+
 /* Must be kept compact -- no holes and well documented */
 
 /**
@@ -2148,6 +2154,15 @@ struct drm_i915_gem_context_param {
  * -EIO: The firmware did not succeed in creating the protected context.
  */
 #define I915_CONTEXT_PARAM_PROTECTED_CONTENT    0xd
+
+/*
+ * I915_CONTEXT_PARAM_LOW_LATENCY:
+ *
+ * Mark this context as a low latency workload which requires aggressive GT
+ * frequency scaling. Use I915_PARAM_HAS_CONTEXT_FREQ_HINT to check if the kernel
+ * supports this per context flag.
+ */
+#define I915_CONTEXT_PARAM_LOW_LATENCY		0xe
 /* Must be kept compact -- no holes and well documented */
 
 	/** @value: Context parameter value to be set or queried */
@@ -2623,19 +2638,29 @@ struct drm_i915_reg_read {
  *
  */
 
+/*
+ * struct drm_i915_reset_stats - Return global reset and other context stats
+ *
+ * Driver keeps few stats for each contexts and also global reset count.
+ * This struct can be used to query those stats.
+ */
 struct drm_i915_reset_stats {
+	/** @ctx_id: ID of the requested context */
 	__u32 ctx_id;
+
+	/** @flags: MBZ */
 	__u32 flags;
 
-	/* All resets since boot/module reload, for all contexts */
+	/** @reset_count: All resets since boot/module reload, for all contexts */
 	__u32 reset_count;
 
-	/* Number of batches lost when active in GPU, for this context */
+	/** @batch_active: Number of batches lost when active in GPU, for this context */
 	__u32 batch_active;
 
-	/* Number of batches lost pending for execution, for this context */
+	/** @batch_pending: Number of batches lost pending for execution, for this context */
 	__u32 batch_pending;
 
+	/** @pad: MBZ */
 	__u32 pad;
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
@@ -1221,9 +1221,9 @@ struct kvm_vfio_spapr_tce {
 /* Available with KVM_CAP_SPAPR_RESIZE_HPT */
 #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt)
 #define KVM_PPC_RESIZE_HPT_COMMIT  _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt)
-/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_MMU_HASH_V3 */
+/* Available with KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 */
 #define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
-/* Available with KVM_CAP_PPC_RADIX_MMU */
+/* Available with KVM_CAP_PPC_MMU_RADIX */
 #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
 /* Available with KVM_CAP_PPC_GET_CPU_CHAR */
 #define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
@@ -126,8 +126,9 @@ struct statx {
 	__u64	stx_mnt_id;
 	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
 	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
+	__u64	stx_subvol;	/* Subvolume identifier */
 	/* 0xa0 */
-	__u64	__spare3[12];	/* Spare space for future expansion */
+	__u64	__spare3[11];	/* Spare space for future expansion */
 	/* 0x100 */
 };
 
@@ -155,6 +156,7 @@ struct statx {
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
 #define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
+#define STATX_SUBVOL		0x00008000U	/* Want/got stx_subvol */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
@@ -214,6 +214,7 @@ NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help
 
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
+  VMLINUX_H=$(src-perf)/util/bpf_skel/vmlinux/vmlinux.h
   config := 0
 endif
 endif
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -376,3 +376,4 @@
 459	n64	lsm_get_self_attr		sys_lsm_get_self_attr
 460	n64	lsm_set_self_attr		sys_lsm_set_self_attr
 461	n64	lsm_list_modules		sys_lsm_list_modules
+462	n64	mseal				sys_mseal
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -548,3 +548,4 @@
 459	common	lsm_get_self_attr		sys_lsm_get_self_attr
 460	common	lsm_set_self_attr		sys_lsm_set_self_attr
 461	common	lsm_list_modules		sys_lsm_list_modules
+462	common	mseal				sys_mseal
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -464,3 +464,4 @@
 459  common	lsm_get_self_attr	sys_lsm_get_self_attr		sys_lsm_get_self_attr
 460  common	lsm_set_self_attr	sys_lsm_set_self_attr		sys_lsm_set_self_attr
 461  common	lsm_list_modules	sys_lsm_list_modules		sys_lsm_list_modules
+462  common	mseal			sys_mseal			sys_mseal
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -374,7 +374,7 @@
 450	common	set_mempolicy_home_node	sys_set_mempolicy_home_node
 451	common	cachestat		sys_cachestat
 452	common	fchmodat2		sys_fchmodat2
-453	64	map_shadow_stack	sys_map_shadow_stack
+453	common	map_shadow_stack	sys_map_shadow_stack
 454	common	futex_wake		sys_futex_wake
 455	common	futex_wait		sys_futex_wait
 456	common	futex_requeue		sys_futex_requeue
@@ -383,6 +383,7 @@
 459	common	lsm_get_self_attr	sys_lsm_get_self_attr
 460	common	lsm_set_self_attr	sys_lsm_set_self_attr
 461	common	lsm_list_modules	sys_lsm_list_modules
+462 	common  mseal			sys_mseal
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
@@ -1956,8 +1956,7 @@ static void record__read_lost_samples(struct record *rec)
 
 				if (count.lost) {
 					if (!lost) {
-						lost = zalloc(sizeof(*lost) +
-							      session->machines.host.id_hdr_size);
+						lost = zalloc(PERF_SAMPLE_MAX_SIZE);
 						if (!lost) {
 							pr_debug("Memory allocation failed\n");
 							return;
@@ -1973,8 +1972,7 @@ static void record__read_lost_samples(struct record *rec)
 		lost_count = perf_bpf_filter__lost_count(evsel);
 		if (lost_count) {
 			if (!lost) {
-				lost = zalloc(sizeof(*lost) +
-					      session->machines.host.id_hdr_size);
+				lost = zalloc(PERF_SAMPLE_MAX_SIZE);
 				if (!lost) {
 					pr_debug("Memory allocation failed\n");
 					return;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
@@ -765,7 +765,7 @@ static const char *fcntl_cmds[] = {
 static DEFINE_STRARRAY(fcntl_cmds, "F_");
 
 static const char *fcntl_linux_specific_cmds[] = {
-	"SETLEASE", "GETLEASE", "NOTIFY", [5] =	"CANCELLK", "DUPFD_CLOEXEC",
+	"SETLEASE", "GETLEASE", "NOTIFY", "DUPFD_QUERY", [5] = "CANCELLK", "DUPFD_CLOEXEC",
 	"SETPIPE_SZ", "GETPIPE_SZ", "ADD_SEALS", "GET_SEALS",
 	"GET_RW_HINT", "SET_RW_HINT", "GET_FILE_RW_HINT", "SET_FILE_RW_HINT",
 };
diff --git a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
@@ -97,10 +97,16 @@
 
 #define LOCAL_TIMER_VECTOR		0xec
 
+/*
+ * Posted interrupt notification vector for all device MSIs delivered to
+ * the host kernel.
+ */
+#define POSTED_MSI_NOTIFICATION_VECTOR	0xeb
+
 #define NR_VECTORS			 256
 
 #ifdef CONFIG_X86_LOCAL_APIC
-#define FIRST_SYSTEM_VECTOR		LOCAL_TIMER_VECTOR
+#define FIRST_SYSTEM_VECTOR		POSTED_MSI_NOTIFICATION_VECTOR
 #else
 #define FIRST_SYSTEM_VECTOR		NR_VECTORS
 #endif
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
@@ -16,6 +16,7 @@ struct cred;
 struct socket;
 struct sock;
 struct sk_buff;
+struct proto_accept_arg;
 
 #define __sockaddr_check_size(size)	\
 	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
@@ -433,7 +434,7 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
 extern int __sys_sendto(int fd, void __user *buff, size_t len,
 			unsigned int flags, struct sockaddr __user *addr,
 			int addr_len);
-extern struct file *do_accept(struct file *file, unsigned file_flags,
+extern struct file *do_accept(struct file *file, struct proto_accept_arg *arg,
 			      struct sockaddr __user *upeer_sockaddr,
 			      int __user *upeer_addrlen, int flags);
 extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
@@ -8,6 +8,14 @@
 #define F_SETLEASE	(F_LINUX_SPECIFIC_BASE + 0)
 #define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
 
+/*
+ * Request nofications on a directory.
+ * See below for events that may be notified.
+ */
+#define F_NOTIFY	(F_LINUX_SPECIFIC_BASE + 2)
+
+#define F_DUPFD_QUERY	(F_LINUX_SPECIFIC_BASE + 3)
+
 /*
  * Cancel a blocking posix lock; internal use only until we expose an
  * asynchronous lock api to userspace:
@@ -17,12 +25,6 @@
 /* Create a file descriptor with FD_CLOEXEC set. */
 #define F_DUPFD_CLOEXEC	(F_LINUX_SPECIFIC_BASE + 6)
 
-/*
- * Request nofications on a directory.
- * See below for events that may be notified.
- */
-#define F_NOTIFY	(F_LINUX_SPECIFIC_BASE+2)
-
 /*
  * Set and get of pipe page size array
  */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -306,4 +306,26 @@ struct prctl_mm_map {
 # define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK	0xc
 # define PR_RISCV_V_VSTATE_CTRL_MASK		0x1f
 
+#define PR_RISCV_SET_ICACHE_FLUSH_CTX	71
+# define PR_RISCV_CTX_SW_FENCEI_ON	0
+# define PR_RISCV_CTX_SW_FENCEI_OFF	1
+# define PR_RISCV_SCOPE_PER_PROCESS	0
+# define PR_RISCV_SCOPE_PER_THREAD	1
+
+/* PowerPC Dynamic Execution Control Register (DEXCR) controls */
+#define PR_PPC_GET_DEXCR		72
+#define PR_PPC_SET_DEXCR		73
+/* DEXCR aspect to act on */
+# define PR_PPC_DEXCR_SBHE		0 /* Speculative branch hint enable */
+# define PR_PPC_DEXCR_IBRTPD		1 /* Indirect branch recurrent target prediction disable */
+# define PR_PPC_DEXCR_SRAPD		2 /* Subroutine return address prediction disable */
+# define PR_PPC_DEXCR_NPHIE		3 /* Non-privileged hash instruction enable */
+/* Action to apply / return */
+# define PR_PPC_DEXCR_CTRL_EDITABLE	 0x1 /* Aspect can be modified with PR_PPC_SET_DEXCR */
+# define PR_PPC_DEXCR_CTRL_SET		 0x2 /* Set the aspect for this process */
+# define PR_PPC_DEXCR_CTRL_CLEAR	 0x4 /* Clear the aspect for this process */
+# define PR_PPC_DEXCR_CTRL_SET_ONEXEC	 0x8 /* Set the aspect on exec */
+# define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC	0x10 /* Clear the aspect on exec */
+# define PR_PPC_DEXCR_CTRL_MASK		0x1f
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h
@@ -126,8 +126,9 @@ struct statx {
 	__u64	stx_mnt_id;
 	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
 	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
+	__u64	stx_subvol;	/* Subvolume identifier */
 	/* 0xa0 */
-	__u64	__spare3[12];	/* Spare space for future expansion */
+	__u64	__spare3[11];	/* Spare space for future expansion */
 	/* 0x100 */
 };
 
@@ -155,6 +156,7 @@ struct statx {
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
 #define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
+#define STATX_SUBVOL		0x00008000U	/* Want/got stx_subvol */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
