Merge tag 'perf-tools-2020-12-24' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/acme/linux Pull more perf tools updates from Arnaldo Carvalho de Melo: - Refactor 'perf stat' per CPU/socket/die/thread aggregation fixing use cases in ARM machines. - Fix memory leak when synthesizing SDT probes in 'perf probe'. - Update kernel header copies related to KVM, epol_pwait. msr-index and powerpc and s390 syscall tables. * tag 'perf-tools-2020-12-24' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (24 commits) perf probe: Fix memory leak when synthesizing SDT probes perf stat aggregation: Add separate thread member perf stat aggregation: Add separate core member perf stat aggregation: Add separate die member perf stat aggregation: Add separate socket member perf stat aggregation: Add separate node member perf stat aggregation: Start using cpu_aggr_id in map perf cpumap: Drop in cpu_aggr_map struct perf cpumap: Add new map type for aggregation perf stat: Replace aggregation ID with a struct perf cpumap: Add new struct for cpu aggregation perf cpumap: Use existing allocator to avoid using malloc perf tests: Improve topology test to check all aggregation types perf tools: Update s390's syscall.tbl copy from the kernel sources perf tools: Update powerpc's syscall.tbl copy from the kernel sources perf s390: Move syscall.tbl check into check-headers.sh perf powerpc: Move syscall.tbl check to check-headers.sh tools headers UAPI: Synch KVM's svm.h header with the kernel tools kvm headers: Update KVM headers from the kernel sources tools headers UAPI: Sync KVM's vmx.h header with the kernel sources ...
niw · Dec 25, 2020 · 5814bc2 · 5814bc2
2 parents 42dc45e + 5149303
commit 5814bc2
Show file tree

Hide file tree

Showing 23 changed files with 688 additions and 391 deletions.
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -156,9 +156,6 @@ struct kvm_sync_regs {
 	__u64 device_irq_level;
 };
 
-struct kvm_arch_memory_slot {
-};
-
 /*
  * PMU filter structure. Describe a range of events with a particular
  * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
@@ -237,6 +237,7 @@
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
 #define X86_FEATURE_SEV_ES		( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_VM_PAGE_FLUSH	( 8*32+21) /* "" VM Page Flush MSR is supported */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -376,6 +377,7 @@
 #define X86_FEATURE_TSXLDTRK		(18*32+16) /* TSX Suspend Load Address Tracking */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
+#define X86_FEATURE_AVX512_FP16		(18*32+23) /* AVX512 FP16 */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
@@ -472,6 +472,7 @@
 #define MSR_AMD64_ICIBSEXTDCTL		0xc001103c
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_VM_PAGE_FLUSH		0xc001011e
 #define MSR_AMD64_SEV_ES_GHCB		0xc0010130
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -12,6 +12,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
 
 #define DE_VECTOR 0
 #define DB_VECTOR 1

diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
@@ -77,10 +77,28 @@
 #define SVM_EXIT_MWAIT_COND    0x08c
 #define SVM_EXIT_XSETBV        0x08d
 #define SVM_EXIT_RDPRU         0x08e
+#define SVM_EXIT_EFER_WRITE_TRAP		0x08f
+#define SVM_EXIT_CR0_WRITE_TRAP			0x090
+#define SVM_EXIT_CR1_WRITE_TRAP			0x091
+#define SVM_EXIT_CR2_WRITE_TRAP			0x092
+#define SVM_EXIT_CR3_WRITE_TRAP			0x093
+#define SVM_EXIT_CR4_WRITE_TRAP			0x094
+#define SVM_EXIT_CR5_WRITE_TRAP			0x095
+#define SVM_EXIT_CR6_WRITE_TRAP			0x096
+#define SVM_EXIT_CR7_WRITE_TRAP			0x097
+#define SVM_EXIT_CR8_WRITE_TRAP			0x098
+#define SVM_EXIT_CR9_WRITE_TRAP			0x099
+#define SVM_EXIT_CR10_WRITE_TRAP		0x09a
+#define SVM_EXIT_CR11_WRITE_TRAP		0x09b
+#define SVM_EXIT_CR12_WRITE_TRAP		0x09c
+#define SVM_EXIT_CR13_WRITE_TRAP		0x09d
+#define SVM_EXIT_CR14_WRITE_TRAP		0x09e
+#define SVM_EXIT_CR15_WRITE_TRAP		0x09f
 #define SVM_EXIT_INVPCID       0x0a2
 #define SVM_EXIT_NPF           0x400
 #define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
+#define SVM_EXIT_VMGEXIT       0x403
 
 /* SEV-ES software-defined VMGEXIT events */
 #define SVM_VMGEXIT_MMIO_READ			0x80000001
@@ -183,10 +201,20 @@
 	{ SVM_EXIT_MONITOR,     "monitor" }, \
 	{ SVM_EXIT_MWAIT,       "mwait" }, \
 	{ SVM_EXIT_XSETBV,      "xsetbv" }, \
+	{ SVM_EXIT_EFER_WRITE_TRAP,	"write_efer_trap" }, \
+	{ SVM_EXIT_CR0_WRITE_TRAP,	"write_cr0_trap" }, \
+	{ SVM_EXIT_CR4_WRITE_TRAP,	"write_cr4_trap" }, \
+	{ SVM_EXIT_CR8_WRITE_TRAP,	"write_cr8_trap" }, \
 	{ SVM_EXIT_INVPCID,     "invpcid" }, \
 	{ SVM_EXIT_NPF,         "npf" }, \
 	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \
 	{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS,   "avic_unaccelerated_access" }, \
+	{ SVM_EXIT_VMGEXIT,		"vmgexit" }, \
+	{ SVM_VMGEXIT_MMIO_READ,	"vmgexit_mmio_read" }, \
+	{ SVM_VMGEXIT_MMIO_WRITE,	"vmgexit_mmio_write" }, \
+	{ SVM_VMGEXIT_NMI_COMPLETE,	"vmgexit_nmi_complete" }, \
+	{ SVM_VMGEXIT_AP_HLT_LOOP,	"vmgexit_ap_hlt_loop" }, \
+	{ SVM_VMGEXIT_AP_JUMP_TABLE,	"vmgexit_ap_jump_table" }, \
 	{ SVM_EXIT_ERR,         "invalid_guest_state" }
 
 

diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -32,6 +32,7 @@
 #define EXIT_REASON_EXTERNAL_INTERRUPT  1
 #define EXIT_REASON_TRIPLE_FAULT        2
 #define EXIT_REASON_INIT_SIGNAL			3
+#define EXIT_REASON_SIPI_SIGNAL         4
 
 #define EXIT_REASON_INTERRUPT_WINDOW    7
 #define EXIT_REASON_NMI_WINDOW          8
@@ -94,6 +95,7 @@
 	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
 	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
 	{ EXIT_REASON_INIT_SIGNAL,           "INIT_SIGNAL" }, \
+	{ EXIT_REASON_SIPI_SIGNAL,           "SIPI_SIGNAL" }, \
 	{ EXIT_REASON_INTERRUPT_WINDOW,      "INTERRUPT_WINDOW" }, \
 	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \

diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
@@ -859,9 +859,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
 #define __NR_process_madvise 440
 __SYSCALL(__NR_process_madvise, sys_process_madvise)
+#define __NR_epoll_pwait2 441
+__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
 
 #undef __NR_syscalls
-#define __NR_syscalls 441
+#define __NR_syscalls 442
 
 /*
  * 32 bit systems traditionally used different

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
@@ -250,6 +250,7 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_ARM_NISV         28
 #define KVM_EXIT_X86_RDMSR        29
 #define KVM_EXIT_X86_WRMSR        30
+#define KVM_EXIT_DIRTY_RING_FULL  31
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -1053,6 +1054,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_X86_USER_SPACE_MSR 188
 #define KVM_CAP_X86_MSR_FILTER 189
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
+#define KVM_CAP_SYS_HYPERV_CPUID 191
+#define KVM_CAP_DIRTY_LOG_RING 192
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1511,7 +1514,7 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */
 #define KVM_CLEAR_DIRTY_LOG          _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
 
-/* Available with KVM_CAP_HYPERV_CPUID */
+/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */
 #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
 
 /* Available with KVM_CAP_ARM_SVE */
@@ -1557,6 +1560,9 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_X86_MSR_FILTER */
 #define KVM_X86_SET_MSR_FILTER	_IOW(KVMIO,  0xc6, struct kvm_msr_filter)
 
+/* Available with KVM_CAP_DIRTY_LOG_RING */
+#define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1710,4 +1716,52 @@ struct kvm_hyperv_eventfd {
 #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
 #define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
 
+/*
+ * Arch needs to define the macro after implementing the dirty ring
+ * feature.  KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the
+ * starting page offset of the dirty ring structures.
+ */
+#ifndef KVM_DIRTY_LOG_PAGE_OFFSET
+#define KVM_DIRTY_LOG_PAGE_OFFSET 0
+#endif
+
+/*
+ * KVM dirty GFN flags, defined as:
+ *
+ * |---------------+---------------+--------------|
+ * | bit 1 (reset) | bit 0 (dirty) | Status       |
+ * |---------------+---------------+--------------|
+ * |             0 |             0 | Invalid GFN  |
+ * |             0 |             1 | Dirty GFN    |
+ * |             1 |             X | GFN to reset |
+ * |---------------+---------------+--------------|
+ *
+ * Lifecycle of a dirty GFN goes like:
+ *
+ *      dirtied         harvested        reset
+ * 00 -----------> 01 -------------> 1X -------+
+ *  ^                                          |
+ *  |                                          |
+ *  +------------------------------------------+
+ *
+ * The userspace program is only responsible for the 01->1X state
+ * conversion after harvesting an entry.  Also, it must not skip any
+ * dirty bits, so that dirty bits are always harvested in sequence.
+ */
+#define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
+#define KVM_DIRTY_GFN_F_RESET           BIT(1)
+#define KVM_DIRTY_GFN_F_MASK            0x3
+
+/*
+ * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of
+ * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn.  The
+ * size of the gfn buffer is decided by the first argument when
+ * enabling KVM_CAP_DIRTY_LOG_RING.
+ */
+struct kvm_dirty_gfn {
+	__u32 flags;
+	__u32 slot;
+	__u64 offset;
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
@@ -14,7 +14,6 @@ PERF_HAVE_JITDUMP := 1
 out    := $(OUTPUT)arch/powerpc/include/generated/asm
 header32 := $(out)/syscalls_32.c
 header64 := $(out)/syscalls_64.c
-syskrn := $(srctree)/arch/powerpc/kernel/syscalls/syscall.tbl
 sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls
 sysdef := $(sysprf)/syscall.tbl
 systbl := $(sysprf)/mksyscalltbl
@@ -23,15 +22,9 @@ systbl := $(sysprf)/mksyscalltbl
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header64): $(sysdef) $(systbl)
-	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
-	(diff -B $(sysdef) $(syskrn) >/dev/null) \
-	|| echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
 	$(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@
 
 $(header32): $(sysdef) $(systbl)
-	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
-	(diff -B $(sysdef) $(syskrn) >/dev/null) \
-	|| echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
 	$(Q)$(SHELL) '$(systbl)' '32' $(sysdef) > $@
 
 clean::

diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -9,7 +9,9 @@
 #
 0	nospu	restart_syscall			sys_restart_syscall
 1	nospu	exit				sys_exit
-2	nospu	fork				ppc_fork
+2	32	fork				ppc_fork			sys_fork
+2	64	fork				sys_fork
+2	spu	fork				sys_ni_syscall
 3	common	read				sys_read
 4	common	write				sys_write
 5	common	open				sys_open			compat_sys_open
@@ -158,7 +160,9 @@
 119	32	sigreturn			sys_sigreturn			compat_sys_sigreturn
 119	64	sigreturn			sys_ni_syscall
 119	spu	sigreturn			sys_ni_syscall
-120	nospu	clone				ppc_clone
+120	32	clone				ppc_clone			sys_clone
+120	64	clone				sys_clone
+120	spu	clone				sys_ni_syscall
 121	common	setdomainname			sys_setdomainname
 122	common	uname				sys_newuname
 123	common	modify_ldt			sys_ni_syscall
@@ -240,7 +244,9 @@
 186	spu	sendfile			sys_sendfile64
 187	common	getpmsg				sys_ni_syscall
 188	common 	putpmsg				sys_ni_syscall
-189	nospu	vfork				ppc_vfork
+189	32	vfork				ppc_vfork			sys_vfork
+189	64	vfork				sys_vfork
+189	spu	vfork				sys_ni_syscall
 190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
 191	common	readahead			sys_readahead			compat_sys_readahead
 192	32	mmap2				sys_mmap2			compat_sys_mmap2
@@ -316,8 +322,8 @@
 248	32	clock_nanosleep			sys_clock_nanosleep_time32
 248	64	clock_nanosleep			sys_clock_nanosleep
 248	spu	clock_nanosleep			sys_clock_nanosleep
-249	32	swapcontext			ppc_swapcontext			ppc32_swapcontext
-249	64	swapcontext			ppc64_swapcontext
+249	32	swapcontext			ppc_swapcontext			compat_sys_swapcontext
+249	64	swapcontext			sys_swapcontext
 249	spu	swapcontext			sys_ni_syscall
 250	common	tgkill				sys_tgkill
 251	32	utimes				sys_utimes_time32
@@ -456,7 +462,7 @@
 361	common	bpf				sys_bpf
 362	nospu	execveat			sys_execveat			compat_sys_execveat
 363	32	switch_endian			sys_ni_syscall
-363	64	switch_endian			ppc_switch_endian
+363	64	switch_endian			sys_switch_endian
 363	spu	switch_endian			sys_ni_syscall
 364	common	userfaultfd			sys_userfaultfd
 365	common	membarrier			sys_membarrier
@@ -516,6 +522,12 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
-435	nospu	clone3				ppc_clone3
+435	32	clone3				ppc_clone3			sys_clone3
+435	64	clone3				sys_clone3
+435	spu	clone3				sys_ni_syscall
+436	common	close_range			sys_close_range
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
@@ -12,7 +12,6 @@ PERF_HAVE_JITDUMP := 1
 
 out    := $(OUTPUT)arch/s390/include/generated/asm
 header := $(out)/syscalls_64.c
-syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl
 sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls
 sysdef := $(sysprf)/syscall.tbl
 systbl := $(sysprf)/mksyscalltbl
@@ -21,9 +20,6 @@ systbl := $(sysprf)/mksyscalltbl
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header): $(sysdef) $(systbl)
-	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
-        (diff -B $(sysdef) $(syskrn) >/dev/null) \
-        || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
 	$(Q)$(SHELL) '$(systbl)' $(sysdef) > $@
 
 clean::