From 89975bd335f37b96ffd3cc24b9effb1fa25e7788 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 20 Sep 2017 16:41:34 -0300 Subject: [PATCH 01/15] perf tools: Get all of tools/{arch,include}/ in the MANIFEST Now that I'm switching the container builds from using a local volume pointing to the kernel repository with the perf sources, instead getting a detached tarball to be able to use a container cluster, some places broke because I forgot to put some of the required files in tools/perf/MANIFEST, namely some bitsperlong.h files. So, to fix it do the same as for tools/build/ and pack the whole tools/arch/ directory. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-wmenpjfjsobwdnfde30qqncj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/MANIFEST | 87 ++------------------------------------------- 1 file changed, 2 insertions(+), 85 deletions(-) diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 62072822dc85..627b7cada144 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,34 +1,8 @@ tools/perf -tools/arch/alpha/include/asm/barrier.h -tools/arch/arm/include/asm/barrier.h -tools/arch/arm64/include/asm/barrier.h -tools/arch/ia64/include/asm/barrier.h -tools/arch/mips/include/asm/barrier.h -tools/arch/powerpc/include/asm/barrier.h -tools/arch/s390/include/asm/barrier.h -tools/arch/sh/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier_32.h -tools/arch/sparc/include/asm/barrier_64.h -tools/arch/tile/include/asm/barrier.h -tools/arch/x86/include/asm/barrier.h -tools/arch/x86/include/asm/cmpxchg.h -tools/arch/x86/include/asm/cpufeatures.h -tools/arch/x86/include/asm/disabled-features.h -tools/arch/x86/include/asm/required-features.h -tools/arch/x86/include/uapi/asm/svm.h -tools/arch/x86/include/uapi/asm/vmx.h -tools/arch/x86/include/uapi/asm/kvm.h -tools/arch/x86/include/uapi/asm/kvm_perf.h -tools/arch/x86/lib/memcpy_64.S -tools/arch/x86/lib/memset_64.S -tools/arch/s390/include/uapi/asm/kvm_perf.h -tools/arch/s390/include/uapi/asm/sie.h -tools/arch/xtensa/include/asm/barrier.h +tools/arch tools/scripts tools/build -tools/arch/x86/include/asm/atomic.h -tools/arch/x86/include/asm/rmwcc.h +tools/include tools/lib/traceevent tools/lib/api tools/lib/bpf @@ -42,60 +16,3 @@ tools/lib/find_bit.c tools/lib/bitmap.c tools/lib/str_error_r.c tools/lib/vsprintf.c -tools/include/asm/alternative-asm.h -tools/include/asm/atomic.h -tools/include/asm/barrier.h -tools/include/asm/bug.h -tools/include/asm-generic/atomic-gcc.h -tools/include/asm-generic/barrier.h -tools/include/asm-generic/bitops/arch_hweight.h -tools/include/asm-generic/bitops/atomic.h -tools/include/asm-generic/bitops/const_hweight.h -tools/include/asm-generic/bitops/__ffs.h -tools/include/asm-generic/bitops/__ffz.h -tools/include/asm-generic/bitops/__fls.h -tools/include/asm-generic/bitops/find.h -tools/include/asm-generic/bitops/fls64.h -tools/include/asm-generic/bitops/fls.h -tools/include/asm-generic/bitops/hweight.h -tools/include/asm-generic/bitops.h -tools/include/linux/atomic.h -tools/include/linux/bitops.h -tools/include/linux/compiler.h -tools/include/linux/compiler-gcc.h -tools/include/linux/coresight-pmu.h -tools/include/linux/bug.h -tools/include/linux/filter.h -tools/include/linux/hash.h -tools/include/linux/kernel.h -tools/include/linux/list.h -tools/include/linux/log2.h -tools/include/uapi/asm-generic/fcntl.h -tools/include/uapi/asm-generic/ioctls.h -tools/include/uapi/asm-generic/mman-common.h -tools/include/uapi/asm-generic/mman.h -tools/include/uapi/drm/drm.h -tools/include/uapi/drm/i915_drm.h -tools/include/uapi/linux/bpf.h -tools/include/uapi/linux/bpf_common.h -tools/include/uapi/linux/fcntl.h -tools/include/uapi/linux/hw_breakpoint.h -tools/include/uapi/linux/kvm.h -tools/include/uapi/linux/mman.h -tools/include/uapi/linux/perf_event.h -tools/include/uapi/linux/sched.h -tools/include/uapi/linux/stat.h -tools/include/uapi/linux/vhost.h -tools/include/uapi/sound/asound.h -tools/include/linux/poison.h -tools/include/linux/rbtree.h -tools/include/linux/rbtree_augmented.h -tools/include/linux/refcount.h -tools/include/linux/string.h -tools/include/linux/stringify.h -tools/include/linux/types.h -tools/include/linux/err.h -tools/include/linux/bitmap.h -tools/include/linux/time64.h -tools/arch/*/include/uapi/asm/mman.h -tools/arch/*/include/uapi/asm/perf_regs.h From 549a3976523c69a0245c0a310210c824a0b26e35 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 13 Sep 2017 09:38:23 +0200 Subject: [PATCH 02/15] tools include: Sync kernel ABI headers with tooling headers Time for a sync with ABI/uapi headers with the upcoming v4.14 kernel. None of the ABI changes require any source code level changes to our existing in-kernel tooling code: - tools/arch/s390/include/uapi/asm/kvm.h: New KVM_S390_VM_TOD_EXT ABI, not used by in-kernel tooling. - tools/arch/x86/include/asm/cpufeatures.h: tools/arch/x86/include/asm/disabled-features.h: New PCID, SME and VGIF x86 CPU feature bits defined. - tools/include/asm-generic/hugetlb_encode.h: tools/include/uapi/asm-generic/mman-common.h: tools/include/uapi/linux/mman.h: Two new madvise() flags, plus a hugetlb system call mmap flags restructuring/extension changes. - tools/include/uapi/drm/drm.h: tools/include/uapi/drm/i915_drm.h: New drm_syncobj_create flags definitions, new drm_syncobj_wait and drm_syncobj_array ABIs. DRM_I915_PERF_* calls and a new I915_PARAM_HAS_EXEC_FENCE_ARRAY ABI for the Intel driver. - tools/include/uapi/linux/bpf.h: New bpf_sock fields (::mark and ::priority), new XDP_REDIRECT action, new kvm_ppc_smmu_info fields (::data_keys, instr_keys) Signed-off-by: Ingo Molnar Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Taeung Song Cc: Wang Nan Cc: Yao Jin Link: http://lkml.kernel.org/r/20170913073823.lxmi4c7ejqlfabjx@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/s390/include/uapi/asm/kvm.h | 6 +++ tools/arch/x86/include/asm/cpufeatures.h | 2 + .../arch/x86/include/asm/disabled-features.h | 4 +- tools/include/asm-generic/hugetlb_encode.h | 34 +++++++++++++ tools/include/uapi/asm-generic/mman-common.h | 14 ++--- tools/include/uapi/drm/drm.h | 22 ++++++++ tools/include/uapi/drm/i915_drm.h | 51 ++++++++++++++++++- tools/include/uapi/linux/bpf.h | 32 +++++++----- tools/include/uapi/linux/kvm.h | 3 +- tools/include/uapi/linux/mman.h | 24 ++++++++- 10 files changed, 164 insertions(+), 28 deletions(-) create mode 100644 tools/include/asm-generic/hugetlb_encode.h diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 69d09c39bbcd..cd7359e23d86 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -88,6 +88,12 @@ struct kvm_s390_io_adapter_req { /* kvm attributes for KVM_S390_VM_TOD */ #define KVM_S390_VM_TOD_LOW 0 #define KVM_S390_VM_TOD_HIGH 1 +#define KVM_S390_VM_TOD_EXT 2 + +struct kvm_s390_vm_tod_clock { + __u8 epoch_idx; + __u64 tod; +}; /* kvm attributes for KVM_S390_VM_CPU_MODEL */ /* processor related attributes are r/w */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 8ea315a11fe0..2519c6c801c9 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -196,6 +196,7 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ @@ -287,6 +288,7 @@ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dff775af7cd..c10c9128f54e 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -21,11 +21,13 @@ # define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) # define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31)) # define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31)) +# define DISABLE_PCID 0 #else # define DISABLE_VME 0 # define DISABLE_K6_MTRR 0 # define DISABLE_CYRIX_ARR 0 # define DISABLE_CENTAUR_MCR 0 +# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31)) #endif /* CONFIG_X86_64 */ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -49,7 +51,7 @@ #define DISABLED_MASK1 0 #define DISABLED_MASK2 0 #define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR) -#define DISABLED_MASK4 0 +#define DISABLED_MASK4 (DISABLE_PCID) #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 0 diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h new file mode 100644 index 000000000000..e4732d3c2998 --- /dev/null +++ b/tools/include/asm-generic/hugetlb_encode.h @@ -0,0 +1,34 @@ +#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_ +#define _ASM_GENERIC_HUGETLB_ENCODE_H_ + +/* + * Several system calls take a flag to request "hugetlb" huge pages. + * Without further specification, these system calls will use the + * system's default huge page size. If a system supports multiple + * huge page sizes, the desired huge page size can be specified in + * bits [26:31] of the flag arguments. The value in these 6 bits + * will encode the log2 of the huge page size. + * + * The following definitions are associated with this huge page size + * encoding in flag arguments. System call specific header files + * that use this encoding should include this file. They can then + * provide definitions based on these with their own specific prefix. + * for example: + * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT + */ + +#define HUGETLB_FLAG_ENCODE_SHIFT 26 +#define HUGETLB_FLAG_ENCODE_MASK 0x3f + +#define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT) + +#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */ diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index 8c27db0c5c08..203268f9231e 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -58,20 +58,12 @@ overrides the coredump filter bits */ #define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */ +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 101593ab10ac..97677cd6964d 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -700,6 +700,7 @@ struct drm_prime_handle { struct drm_syncobj_create { __u32 handle; +#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0) __u32 flags; }; @@ -718,6 +719,24 @@ struct drm_syncobj_handle { __u32 pad; }; +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0) +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1) +struct drm_syncobj_wait { + __u64 handles; + /* absolute timeout */ + __s64 timeout_nsec; + __u32 count_handles; + __u32 flags; + __u32 first_signaled; /* only valid when not waiting all */ + __u32 pad; +}; + +struct drm_syncobj_array { + __u64 handles; + __u32 count_handles; + __u32 pad; +}; + #if defined(__cplusplus) } #endif @@ -840,6 +859,9 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_DESTROY DRM_IOWR(0xC0, struct drm_syncobj_destroy) #define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD DRM_IOWR(0xC1, struct drm_syncobj_handle) #define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE DRM_IOWR(0xC2, struct drm_syncobj_handle) +#define DRM_IOCTL_SYNCOBJ_WAIT DRM_IOWR(0xC3, struct drm_syncobj_wait) +#define DRM_IOCTL_SYNCOBJ_RESET DRM_IOWR(0xC4, struct drm_syncobj_array) +#define DRM_IOCTL_SYNCOBJ_SIGNAL DRM_IOWR(0xC5, struct drm_syncobj_array) /** * Device specific ioctls should only be in their respective headers diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 7ccbd6a2bbe0..6598fb76d2c2 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -260,6 +260,8 @@ typedef struct _drm_i915_sarea { #define DRM_I915_GEM_CONTEXT_GETPARAM 0x34 #define DRM_I915_GEM_CONTEXT_SETPARAM 0x35 #define DRM_I915_PERF_OPEN 0x36 +#define DRM_I915_PERF_ADD_CONFIG 0x37 +#define DRM_I915_PERF_REMOVE_CONFIG 0x38 #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) #define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) @@ -315,6 +317,8 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param) +#define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) +#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -431,6 +435,11 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_HAS_EXEC_BATCH_FIRST 48 +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * drm_i915_gem_exec_fence structures. See I915_EXEC_FENCE_ARRAY. + */ +#define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49 + typedef struct drm_i915_getparam { __s32 param; /* @@ -812,6 +821,17 @@ struct drm_i915_gem_exec_object2 { __u64 rsvd2; }; +struct drm_i915_gem_exec_fence { + /** + * User's handle for a drm_syncobj to wait on or signal. + */ + __u32 handle; + +#define I915_EXEC_FENCE_WAIT (1<<0) +#define I915_EXEC_FENCE_SIGNAL (1<<1) + __u32 flags; +}; + struct drm_i915_gem_execbuffer2 { /** * List of gem_exec_object2 structs @@ -826,7 +846,11 @@ struct drm_i915_gem_execbuffer2 { __u32 DR1; __u32 DR4; __u32 num_cliprects; - /** This is a struct drm_clip_rect *cliprects */ + /** + * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY + * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a + * struct drm_i915_gem_exec_fence *fences. + */ __u64 cliprects_ptr; #define I915_EXEC_RING_MASK (7<<0) #define I915_EXEC_DEFAULT (0<<0) @@ -927,7 +951,14 @@ struct drm_i915_gem_execbuffer2 { * element). */ #define I915_EXEC_BATCH_FIRST (1<<18) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1)) + +/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr + * define an array of i915_gem_exec_fence structures which specify a set of + * dma fences to wait upon or signal. + */ +#define I915_EXEC_FENCE_ARRAY (1<<19) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ @@ -1467,6 +1498,22 @@ enum drm_i915_perf_record_type { DRM_I915_PERF_RECORD_MAX /* non-ABI */ }; +/** + * Structure to upload perf dynamic configuration into the kernel. + */ +struct drm_i915_perf_oa_config { + /** String formatted like "%08x-%04x-%04x-%04x-%012x" */ + char uuid[36]; + + __u32 n_mux_regs; + __u32 n_boolean_regs; + __u32 n_flex_regs; + + __u64 __user mux_regs_ptr; + __u64 __user boolean_regs_ptr; + __u64 __user flex_regs_ptr; +}; + #if defined(__cplusplus) } #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 461811e57140..43ab5c402f98 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -143,12 +143,6 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -enum bpf_sockmap_flags { - BPF_SOCKMAP_UNSPEC, - BPF_SOCKMAP_STRPARSER, - __MAX_BPF_SOCKMAP_FLAG -}; - /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup @@ -368,9 +362,20 @@ union bpf_attr { * int bpf_redirect(ifindex, flags) * redirect to another netdev * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: TC_ACT_REDIRECT + * @flags: + * cls_bpf: + * bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * xdp_bpf: + * all bits - reserved + * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error + * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error + * int bpf_redirect_map(map, key, flags) + * redirect to endpoint in map + * @map: pointer to dev map + * @key: index in map to lookup + * @flags: -- + * Return: XDP_REDIRECT on success or XDP_ABORT on error * * u32 bpf_get_route_realm(skb) * retrieve a dst's tclassid @@ -632,7 +637,7 @@ union bpf_attr { FN(skb_adjust_room), \ FN(redirect_map), \ FN(sk_redirect_map), \ - FN(sock_map_update), + FN(sock_map_update), \ /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -753,20 +758,23 @@ struct bpf_sock { __u32 family; __u32 type; __u32 protocol; + __u32 mark; + __u32 priority; }; #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other - * return codes are reserved for future use. Unknown return codes will result - * in packet drop. + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). */ enum xdp_action { XDP_ABORTED = 0, XDP_DROP, XDP_PASS, XDP_TX, + XDP_REDIRECT, }; /* user accessible metadata for XDP packet hook diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 6cd63c18708a..838887587411 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -711,7 +711,8 @@ struct kvm_ppc_one_seg_page_size { struct kvm_ppc_smmu_info { __u64 flags; __u32 slb_size; - __u32 pad; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; }; diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index 81d8edf11789..a937480d7cd3 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -1,7 +1,8 @@ #ifndef _UAPI_LINUX_MMAN_H #define _UAPI_LINUX_MMAN_H -#include +#include +#include #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -10,4 +11,25 @@ #define OVERCOMMIT_ALWAYS 1 #define OVERCOMMIT_NEVER 2 +/* + * Huge page size encoding when MAP_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + #endif /* _UAPI_LINUX_MMAN_H */ From f1e52f14a69386ac460a8d700df0647a631cf595 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 22 Sep 2017 15:41:44 -0300 Subject: [PATCH 03/15] perf evsel: Fix attr.exclude_kernel setting for default cycles:p Yet another fix for probing the max attr.precise_ip setting: it is not enough settting attr.exclude_kernel for !root users, as they _can_ profile the kernel if the kernel.perf_event_paranoid sysctl is set to -1, so check that as well. Testing it: As non root: $ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = 2 $ perf record sleep 1 $ perf evlist -v cycles:uppp: ..., exclude_kernel: 1, ... precise_ip: 3, ... Now as non-root, but with kernel.perf_event_paranoid set set to the most permissive value, -1: $ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = -1 $ perf record sleep 1 $ perf evlist -v cycles:ppp: ..., exclude_kernel: 0, ... precise_ip: 3, ... $ I.e. non-root, default kernel.perf_event_paranoid: :uppp modifier = not allowed to sample the kernel, non-root, most permissible kernel.perf_event_paranoid: :ppp = allowed to sample the kernel. In both cases, use the highest available precision: attr.precise_ip = 3. Reported-and-Tested-by: Ingo Molnar Cc: Adrian Hunter Cc: Andy Lutomirski Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Fixes: d37a36979077 ("perf evsel: Fix attr.exclude_kernel setting for default cycles:p") Link: http://lkml.kernel.org/n/tip-nj2qkf75xsd6pw6hhjzfqqdx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4bb89373eb52..0dccdb89572c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -271,12 +271,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } +static bool perf_event_can_profile_kernel(void) +{ + return geteuid() == 0 || perf_event_paranoid() == -1; +} + struct perf_evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = geteuid() != 0, + .exclude_kernel = !perf_event_can_profile_kernel(), }; struct perf_evsel *evsel; From 9789e7e93f2b892098d7684ac8131092aa617814 Mon Sep 17 00:00:00 2001 From: Mengting Zhang Date: Sat, 23 Sep 2017 16:18:14 +0800 Subject: [PATCH 04/15] perf report: Fix debug messages with --call-graph option With --call-graph option, perf report can display call chains using type, min percent threshold, optional print limit and order. And the default call-graph parameter is 'graph,0.5,caller,function,percent'. Before this patch, 'perf report --call-graph' shows incorrect debug messages as below: # perf report --call-graph Invalid callchain mode: 0.5 Invalid callchain order: 0.5 Invalid callchain sort key: 0.5 Invalid callchain config key: 0.5 Invalid callchain mode: caller Invalid callchain mode: function Invalid callchain order: function Invalid callchain mode: percent Invalid callchain order: percent Invalid callchain sort key: percent That is because in function __parse_callchain_report_opt(),each field of the call-graph parameter is passed to parse_callchain_{mode,order, sort_key,value} in turn until it meets the matching value. For example, the order field "caller" is passed to parse_callchain_mode() firstly and obviously it doesn't match any mode field. Therefore parse_callchain_mode() will shows the debug message "Invalid callchain mode: caller", which could confuse users. The patch fixes this issue by moving the warning out of the function parse_callchain_{mode,order,sort_key,value}. Signed-off-by: Mengting Zhang Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Krister Johansen Cc: Li Bin Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Cc: Yao Jin Link: http://lkml.kernel.org/r/1506154694-39691-1-git-send-email-zhangmengting@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/callchain.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-) diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 510b513e0f01..be09d77cade0 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -65,8 +65,6 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_FOLDED; return 0; } - - pr_err("Invalid callchain mode: %s\n", value); return -1; } @@ -82,8 +80,6 @@ static int parse_callchain_order(const char *value) callchain_param.order_set = true; return 0; } - - pr_err("Invalid callchain order: %s\n", value); return -1; } @@ -105,8 +101,6 @@ static int parse_callchain_sort_key(const char *value) callchain_param.branch_callstack = 1; return 0; } - - pr_err("Invalid callchain sort key: %s\n", value); return -1; } @@ -124,8 +118,6 @@ static int parse_callchain_value(const char *value) callchain_param.value = CCVAL_COUNT; return 0; } - - pr_err("Invalid callchain config key: %s\n", value); return -1; } @@ -319,12 +311,27 @@ int perf_callchain_config(const char *var, const char *value) return ret; } - if (!strcmp(var, "print-type")) - return parse_callchain_mode(value); - if (!strcmp(var, "order")) - return parse_callchain_order(value); - if (!strcmp(var, "sort-key")) - return parse_callchain_sort_key(value); + if (!strcmp(var, "print-type")){ + int ret; + ret = parse_callchain_mode(value); + if (ret == -1) + pr_err("Invalid callchain mode: %s\n", value); + return ret; + } + if (!strcmp(var, "order")){ + int ret; + ret = parse_callchain_order(value); + if (ret == -1) + pr_err("Invalid callchain order: %s\n", value); + return ret; + } + if (!strcmp(var, "sort-key")){ + int ret; + ret = parse_callchain_sort_key(value); + if (ret == -1) + pr_err("Invalid callchain sort key: %s\n", value); + return ret; + } if (!strcmp(var, "threshold")) { callchain_param.min_percent = strtod(value, &endptr); if (value == endptr) { From 090657c9fb7094e4c1b05c1713d6c2a12ef43dea Mon Sep 17 00:00:00 2001 From: Akemi Yagi Date: Fri, 22 Sep 2017 22:11:53 +0000 Subject: [PATCH 05/15] perf tools: Fix syscalltbl build failure The build of kernel v4.14-rc1 for i686 fails on RHEL 6 with the error in tools/perf: util/syscalltbl.c:157: error: expected ';', ',' or ')' before '__maybe_unused' mv: cannot stat `util/.syscalltbl.o.tmp': No such file or directory Fix it by placing/moving: #include outside of #ifdef HAVE_SYSCALL_TABLE block. Signed-off-by: Akemi Yagi Cc: Alan Bartlett Link: http://lkml.kernel.org/r/oq41r8$1v9$1@blaine.gmane.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/syscalltbl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 19e5db90394c..6eea7cff3d4e 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -15,9 +15,9 @@ #include "syscalltbl.h" #include +#include #ifdef HAVE_SYSCALL_TABLE -#include #include #include "string2.h" #include "util.h" From b28503a3fe6400757817e4460090f96bc1b9d6e7 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 15 Sep 2017 09:14:03 +0200 Subject: [PATCH 06/15] perf test: Fix vmlinux failure on s390x On s390x perf test 1 failed. It turned out that commit 4a084ecfc821 ("perf report: Fix module symbol adjustment for s390x") was incorrect. The previous implementation in dso__load_sym() is also suitable for s390x. Therefore this patch undoes commit 4a084ecfc821. Signed-off-by: Thomas-Mich Richter Cc: Hendrik Brueckner Cc: Zvonko Kosic Fixes: 4a084ecfc821 ("perf report: Fix module symbol adjustment for s390x") LPU-Reference: 20170915071404.58398-1-tmricht@linux.vnet.ibm.com Link: http://lkml.kernel.org/n/tip-5ani7ly57zji7s0hmzkx416l@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/sym-handling.c | 8 -------- tools/perf/util/symbol-elf.c | 8 +------- tools/perf/util/symbol.h | 3 --- 3 files changed, 1 insertion(+), 18 deletions(-) diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c index e103f6e46afe..581d4c5a896b 100644 --- a/tools/perf/arch/s390/util/sym-handling.c +++ b/tools/perf/arch/s390/util/sym-handling.c @@ -18,12 +18,4 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) return false; return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN; } - -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map) -{ - if (map->type == MAP__FUNCTION) - sym->st_value += map->start; -} #endif diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 5c39f420111e..9cf781f0d8a2 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -810,12 +810,6 @@ static u64 ref_reloc(struct kmap *kmap) void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } -void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr, - struct map *map __maybe_unused) -{ - sym->st_value -= shdr->sh_addr - shdr->sh_offset; -} - int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { @@ -996,7 +990,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, /* Adjust symbol to map to file offset */ if (adjust_kernel_syms) - arch__adjust_sym_map_offset(&sym, &shdr, map); + sym.st_value -= shdr.sh_addr - shdr.sh_offset; if (strcmp(section_name, (curr_dso->short_name + diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 2bd6a1f01a1c..aad99e7e179b 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -344,9 +344,6 @@ int setup_intlist(struct intlist **list, const char *list_str, #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr); void arch__sym_update(struct symbol *s, GElf_Sym *sym); -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map __maybe_unused); #endif #define SYMBOL_A 0 From 5357413f5c067f60933e4b8d79d483fbe62b2bb5 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 15 Sep 2017 09:14:04 +0200 Subject: [PATCH 07/15] perf test: Fix vmlinux failure on s390x part 2 On s390x perf test 1 failed. It turned out that commit cf6383f73cf2 ("perf report: Fix kernel symbol adjustment for s390x") was incorrect. The previous implementation in dso__load_sym() is also suitable for s390x. Therefore this patch undoes commit cf6383f73cf2 Signed-off-by: Thomas-Mich Richter Cc: Zvonko Kosic Cc: Hendrik Brueckner Fixes: cf6383f73cf2 ("perf report: Fix kernel symbol adjustment for s390x") LPU-Reference: 20170915071404.58398-2-tmricht@linux.vnet.ibm.com Link: http://lkml.kernel.org/n/tip-v101o8k25vuja2ogosgf15yy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/Build | 1 - tools/perf/arch/s390/util/sym-handling.c | 21 --------------------- 2 files changed, 22 deletions(-) delete mode 100644 tools/perf/arch/s390/util/sym-handling.c diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index bd518b623d7a..5bd7b9260cc0 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -1,5 +1,4 @@ libperf-y += header.o -libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c deleted file mode 100644 index 581d4c5a896b..000000000000 --- a/tools/perf/arch/s390/util/sym-handling.c +++ /dev/null @@ -1,21 +0,0 @@ -/* - * Architecture specific ELF symbol handling and relocation mapping. - * - * Copyright 2017 IBM Corp. - * Author(s): Thomas Richter - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - */ - -#include "symbol.h" - -#ifdef HAVE_LIBELF_SUPPORT -bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) -{ - if (ehdr.e_type == ET_EXEC) - return false; - return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN; -} -#endif From 10836d9f9ac63d40ccfa756f871ce4ed51ae3b52 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 3 Jul 2017 16:50:30 +0200 Subject: [PATCH 08/15] perf tests attr: Fix task term values The perf_event_attr::task is 1 by default for first (tracking) event in the session. Setting task=1 as default and adding task=0 for cases that need it. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas-Mich Richter Link: http://lkml.kernel.org/r/20170703145030.12903-16-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr/base-record | 2 +- tools/perf/tests/attr/test-record-group | 1 + tools/perf/tests/attr/test-record-group-sampling | 2 +- tools/perf/tests/attr/test-record-group1 | 1 + 4 files changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 31e0b1da830b..37940665f736 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -23,7 +23,7 @@ comm=1 freq=1 inherit_stat=0 enable_on_exec=1 -task=0 +task=1 watermark=0 precise_ip=0|1|2|3 mmap_data=0 diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group index 6e7961f6f7a5..618ba1c17474 100644 --- a/tools/perf/tests/attr/test-record-group +++ b/tools/perf/tests/attr/test-record-group @@ -17,5 +17,6 @@ sample_type=327 read_format=4 mmap=0 comm=0 +task=0 enable_on_exec=0 disabled=0 diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index ef59afd6d635..f906b793196f 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -23,7 +23,7 @@ sample_type=343 # PERF_FORMAT_ID | PERF_FORMAT_GROUP read_format=12 - +task=0 mmap=0 comm=0 enable_on_exec=0 diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1 index 87a222d014d8..48e8bd12fe46 100644 --- a/tools/perf/tests/attr/test-record-group1 +++ b/tools/perf/tests/attr/test-record-group1 @@ -18,5 +18,6 @@ sample_type=327 read_format=4 mmap=0 comm=0 +task=0 enable_on_exec=0 disabled=0 From 3440fe2790aa3d13530260af6033533b18959aee Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 13 Sep 2017 10:12:08 +0200 Subject: [PATCH 09/15] perf test attr: Fix python error on empty result Commit d78ada4a767 ("perf tests attr: Do not store failed events") does not create an event file in the /tmp directory when the perf_open_event() system call failed. This can lead to a situation where not /tmp/event-xx-yy-zz result file exists at all (for example on a s390x virtual machine environment) where no CPUMF hardware is available. The following command then fails with a python call back chain instead of printing failure: [root@s8360046 perf]# /usr/bin/python2 ./tests/attr.py -d ./tests/attr/ \ -p ./perf -v -ttest-stat-basic running './tests/attr//test-stat-basic' Traceback (most recent call last): File "./tests/attr.py", line 379, in main() File "./tests/attr.py", line 370, in main run_tests(options) File "./tests/attr.py", line 311, in run_tests Test(f, options).run() File "./tests/attr.py", line 300, in run self.compare(self.expect, self.result) File "./tests/attr.py", line 248, in compare exp_event.diff(res_event) UnboundLocalError: local variable 'res_event' referenced before assignment [root@s8360046 perf]# This patch catches this pitfall and prints an error message instead: [root@s8360047 perf]# /usr/bin/python2 ./tests/attr.py -d ./tests/attr/ \ -p ./perf -vvv -ttest-stat-basic running './tests/attr//test-stat-basic' loading expected events Event event:base-stat fd = 1 group_fd = -1 flags = 0|8 [....] sample_regs_user = 0 sample_stack_user = 0 'PERF_TEST_ATTR=/tmp/tmpJbMQMP ./perf stat -o /tmp/tmpJbMQMP/perf.data -e cycles kill >/dev/null 2>&1' ret '1', expected '1' loading result events compare matching [event:base-stat] match: [event:base-stat] matches [] res_event is empty FAILED './tests/attr//test-stat-basic' - match failure [root@s8360047 perf]# Signed-off-by: Thomas-Mich Richter Acked-by: Jiri Olsa Cc: Heiko Carstens Cc: Hendrik Brueckner Cc: Martin Schwidefsky Cc: Thomas-Mich Richter LPU-Reference: 20170913081209.39570-1-tmricht@linux.vnet.ibm.com Link: http://lkml.kernel.org/n/tip-04d63nn7svfgxdhi60gq2mlm@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index 6bb50e82a3e3..a13cd780148e 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -237,6 +237,7 @@ class Test(object): # events in result. Fail if there's not any. for exp_name, exp_event in expect.items(): exp_list = [] + res_event = {} log.debug(" matching [%s]" % exp_name) for res_name, res_event in result.items(): log.debug(" to [%s]" % res_name) @@ -253,7 +254,10 @@ class Test(object): if exp_event.optional(): log.debug(" %s does not match, but is optional" % exp_name) else: - exp_event.diff(res_event) + if not res_event: + log.debug(" res_event is empty"); + else: + exp_event.diff(res_event) raise Fail(self, 'match failure'); match[exp_name] = exp_list From 22905582f6dd4bbd0c370fe5732c607452010c04 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 13 Sep 2017 10:12:09 +0200 Subject: [PATCH 10/15] perf test attr: Fix ignored test case result Command perf test -v 16 (Setup struct perf_event_attr test) always reports success even if the test case fails. It works correctly if you also specify -F (for don't fork). root@s35lp76 perf]# ./perf test -v 16 15: Setup struct perf_event_attr : --- start --- running './tests/attr/test-record-no-delay' [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.002 MB /tmp/tmp4E1h7R/perf.data (1 samples) ] expected task=0, got 1 expected precise_ip=0, got 3 expected wakeup_events=1, got 0 FAILED './tests/attr/test-record-no-delay' - match failure test child finished with 0 ---- end ---- Setup struct perf_event_attr: Ok The reason for the wrong error reporting is the return value of the system() library call. It is called in run_dir() file tests/attr.c and returns the exit status, in above case 0xff00. This value is given as parameter to the exit() function which can only handle values 0-0xff. The child process terminates with exit value of 0 and the parent does not detect any error. This patch corrects the error reporting and prints the correct test result. Signed-off-by: Thomas-Mich Richter Acked-by: Jiri Olsa Cc: Heiko Carstens Cc: Hendrik Brueckner Cc: Martin Schwidefsky Cc: Thomas-Mich Richter LPU-Reference: 20170913081209.39570-2-tmricht@linux.vnet.ibm.com Link: http://lkml.kernel.org/n/tip-rdube6rfcjsr1nzue72c7lqn@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index c9aafed7da15..25ede4472465 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -166,7 +166,7 @@ static int run_dir(const char *d, const char *perf) snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s", d, d, perf, vcnt, v); - return system(cmd); + return system(cmd) ? TEST_FAIL : TEST_OK; } int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused) From b32ee9e522f7ba26339856a047cfe9efc0be0ff3 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 29 Sep 2017 07:47:52 -0700 Subject: [PATCH 11/15] perf tools: Lock to protect namespaces and comm list Add two locks to protect namespaces_list and comm_list. The lock is only needed for multithreaded code, so using mutex wrappers provided by perf tool. Not all the comm_list/namespaces_list accessing are protected, e.g. thread__exec_comm. Because the multithread code for perf top event synthesizing does not touch them. They don't need a lock. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Andi Kleen Cc: He Kuang Cc: Lukasz Odzioba Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1506696477-146932-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/thread.c | 53 ++++++++++++++++++++++++++++++++++++---- tools/perf/util/thread.h | 3 +++ 2 files changed, 51 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index c09bdb509d82..bf73117b4822 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -45,6 +45,8 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread->cpu = -1; INIT_LIST_HEAD(&thread->namespaces_list); INIT_LIST_HEAD(&thread->comm_list); + init_rwsem(&thread->namespaces_lock); + init_rwsem(&thread->comm_lock); comm_str = malloc(32); if (!comm_str) @@ -83,18 +85,26 @@ void thread__delete(struct thread *thread) map_groups__put(thread->mg); thread->mg = NULL; } + down_write(&thread->namespaces_lock); list_for_each_entry_safe(namespaces, tmp_namespaces, &thread->namespaces_list, list) { list_del(&namespaces->list); namespaces__free(namespaces); } + up_write(&thread->namespaces_lock); + + down_write(&thread->comm_lock); list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) { list_del(&comm->list); comm__free(comm); } + up_write(&thread->comm_lock); + unwind__finish_access(thread); nsinfo__zput(thread->nsinfo); + exit_rwsem(&thread->namespaces_lock); + exit_rwsem(&thread->comm_lock); free(thread); } @@ -125,8 +135,8 @@ struct namespaces *thread__namespaces(const struct thread *thread) return list_first_entry(&thread->namespaces_list, struct namespaces, list); } -int thread__set_namespaces(struct thread *thread, u64 timestamp, - struct namespaces_event *event) +static int __thread__set_namespaces(struct thread *thread, u64 timestamp, + struct namespaces_event *event) { struct namespaces *new, *curr = thread__namespaces(thread); @@ -149,6 +159,17 @@ int thread__set_namespaces(struct thread *thread, u64 timestamp, return 0; } +int thread__set_namespaces(struct thread *thread, u64 timestamp, + struct namespaces_event *event) +{ + int ret; + + down_write(&thread->namespaces_lock); + ret = __thread__set_namespaces(thread, timestamp, event); + up_write(&thread->namespaces_lock); + return ret; +} + struct comm *thread__comm(const struct thread *thread) { if (list_empty(&thread->comm_list)) @@ -170,8 +191,8 @@ struct comm *thread__exec_comm(const struct thread *thread) return last; } -int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, - bool exec) +static int ____thread__set_comm(struct thread *thread, const char *str, + u64 timestamp, bool exec) { struct comm *new, *curr = thread__comm(thread); @@ -195,6 +216,17 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, return 0; } +int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, + bool exec) +{ + int ret; + + down_write(&thread->comm_lock); + ret = ____thread__set_comm(thread, str, timestamp, exec); + up_write(&thread->comm_lock); + return ret; +} + int thread__set_comm_from_proc(struct thread *thread) { char path[64]; @@ -212,7 +244,7 @@ int thread__set_comm_from_proc(struct thread *thread) return err; } -const char *thread__comm_str(const struct thread *thread) +static const char *__thread__comm_str(const struct thread *thread) { const struct comm *comm = thread__comm(thread); @@ -222,6 +254,17 @@ const char *thread__comm_str(const struct thread *thread) return comm__str(comm); } +const char *thread__comm_str(const struct thread *thread) +{ + const char *str; + + down_read((struct rw_semaphore *)&thread->comm_lock); + str = __thread__comm_str(thread); + up_read((struct rw_semaphore *)&thread->comm_lock); + + return str; +} + /* CHECKME: it should probably better return the max comm len from its comm list */ int thread__comm_len(struct thread *thread) { diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index cb1a5dd5c2b9..10555d6a0b86 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -9,6 +9,7 @@ #include "symbol.h" #include #include +#include "rwsem.h" struct thread_stack; struct unwind_libunwind_ops; @@ -29,7 +30,9 @@ struct thread { int comm_len; bool dead; /* if set thread has exited */ struct list_head namespaces_list; + struct rw_semaphore namespaces_lock; struct list_head comm_list; + struct rw_semaphore comm_lock; u64 db_id; void *priv; From f988e71bc6220d8b404dbd43c0e0962e30305795 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 29 Sep 2017 07:47:53 -0700 Subject: [PATCH 12/15] perf tools: Lock to protect comm_str rb tree Add comm_str_lock to protect comm_str rb tree. The lock is only needed for multithreaded code, so using mutex wrappers provided by perf tool. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Andi Kleen Cc: He Kuang Cc: Lukasz Odzioba Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1506696477-146932-3-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/comm.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 7bc981b6bf29..756a9c14efbb 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -5,6 +5,7 @@ #include #include #include +#include "rwsem.h" struct comm_str { char *str; @@ -14,6 +15,7 @@ struct comm_str { /* Should perhaps be moved to struct machine */ static struct rb_root comm_str_root; +static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,}; static struct comm_str *comm_str__get(struct comm_str *cs) { @@ -25,7 +27,9 @@ static struct comm_str *comm_str__get(struct comm_str *cs) static void comm_str__put(struct comm_str *cs) { if (cs && refcount_dec_and_test(&cs->refcnt)) { + down_write(&comm_str_lock); rb_erase(&cs->rb_node, &comm_str_root); + up_write(&comm_str_lock); zfree(&cs->str); free(cs); } @@ -50,7 +54,8 @@ static struct comm_str *comm_str__alloc(const char *str) return cs; } -static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) +static +struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -81,6 +86,17 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) return new; } +static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) +{ + struct comm_str *cs; + + down_write(&comm_str_lock); + cs = __comm_str__findnew(str, root); + up_write(&comm_str_lock); + + return cs; +} + struct comm *comm__new(const char *str, u64 timestamp, bool exec) { struct comm *comm = zalloc(sizeof(*comm)); From 340b47f510bbe55a76b7309107276f02ea11f117 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 29 Sep 2017 07:47:54 -0700 Subject: [PATCH 13/15] perf top: Implement multithreading for perf_event__synthesize_threads The proc files which is sorted with alphabetical order are evenly assigned to several synthesize threads to be processed in parallel. For 'perf top', the threads number hard code to online CPU number. The following patch will introduce an option to set it. For other perf tools, the thread number is 1. Because the process function is not ready for multithreading, e.g. process_synthesized_event. This patch series only support event synthesize multithreading for 'perf top'. For other tools, it can be done separately later. With multithread applied, the total processing time can get up to 1.56x speedup on Knights Mill for 'perf top'. For specific single event processing, the processing time could increase because of the lock contention. So proc_map_timeout may need to be increased. Otherwise some proc maps will be truncated. Based on my test, increasing the proc_map_timeout has small impact on the total processing time. The total processing time still get 1.49x speedup on Knights Mill after increasing the proc_map_timeout. The patch itself doesn't increase the proc_map_timeout. Doesn't need to implement multithreading for per task monitoring, perf_event__synthesize_thread_map. It doesn't have performance issue. Committer testing: # getconf _NPROCESSORS_ONLN 4 # perf trace --no-inherit -e clone -o /tmp/output perf top # tail -4 /tmp/bla 0.124 ( 0.041 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eb3a8f30, parent_tidptr: 0x7fc3eb3a99d0, child_tidptr: 0x7fc3eb3a99d0, tls: 0x7fc3eb3a9700) = 9548 (perf) 0.246 ( 0.023 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3eaba7f30, parent_tidptr: 0x7fc3eaba89d0, child_tidptr: 0x7fc3eaba89d0, tls: 0x7fc3eaba8700) = 9549 (perf) 0.286 ( 0.019 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9550 (perf) 246.540 ( 0.047 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7fc3ea3a6f30, parent_tidptr: 0x7fc3ea3a79d0, child_tidptr: 0x7fc3ea3a79d0, tls: 0x7fc3ea3a7700) = 9551 (perf) # Signed-off-by: Kan Liang Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Andi Kleen Cc: He Kuang Cc: Lukasz Odzioba Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1506696477-146932-4-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 3 +- tools/perf/builtin-record.c | 2 +- tools/perf/builtin-top.c | 8 +- tools/perf/builtin-trace.c | 2 +- tools/perf/tests/mmap-thread-lookup.c | 2 +- tools/perf/util/event.c | 160 +++++++++++++++++++++----- tools/perf/util/event.h | 3 +- tools/perf/util/machine.c | 8 +- tools/perf/util/machine.h | 9 +- 9 files changed, 155 insertions(+), 42 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index c747a1af49fe..721f4f91291a 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1441,7 +1441,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, perf_session__set_id_hdr_size(kvm->session); ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true); machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target, - kvm->evlist->threads, false, kvm->opts.proc_map_timeout); + kvm->evlist->threads, false, + kvm->opts.proc_map_timeout, 1); err = kvm_live_open_events(kvm); if (err) goto out; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 9b379f3a3d99..234fdf4734f6 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -863,7 +863,7 @@ static int record__synthesize(struct record *rec, bool tail) err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads, process_synthesized_event, opts->sample_address, - opts->proc_map_timeout); + opts->proc_map_timeout, 1); out: return err; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index ee954bde7e3e..bc31b93cc1d8 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -958,8 +958,14 @@ static int __cmd_top(struct perf_top *top) if (perf_session__register_idle_thread(top->session) < 0) goto out_delete; + perf_set_multithreaded(); + machine__synthesize_threads(&top->session->machines.host, &opts->target, - top->evlist->threads, false, opts->proc_map_timeout); + top->evlist->threads, false, + opts->proc_map_timeout, + (unsigned int)sysconf(_SC_NPROCESSORS_ONLN)); + + perf_set_singlethreaded(); if (perf_hpp_list.socket) { ret = perf_env__read_cpu_topology_map(&perf_env); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 967bd351b58d..afef6fe46c45 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1131,7 +1131,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target, evlist->threads, trace__tool_process, false, - trace->opts.proc_map_timeout); + trace->opts.proc_map_timeout, 1); if (err) symbol__exit(); diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index f94a4196e7c9..2a0068afe3bf 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -131,7 +131,7 @@ static int synth_all(struct machine *machine) { return perf_event__synthesize_threads(NULL, perf_event__process, - machine, 0, 500); + machine, 0, 500, 1); } static int synth_process(struct machine *machine) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 10366b87d0b5..0e678dd6bdbe 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -678,23 +678,21 @@ out: return err; } -int perf_event__synthesize_threads(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data, - unsigned int proc_map_timeout) +static int __perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data, + unsigned int proc_map_timeout, + struct dirent **dirent, + int start, + int num) { union perf_event *comm_event, *mmap_event, *fork_event; union perf_event *namespaces_event; - char proc_path[PATH_MAX]; - struct dirent **dirent; int err = -1; char *end; pid_t pid; - int n, i; - - if (machine__is_default_guest(machine)) - return 0; + int i; comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); if (comm_event == NULL) @@ -714,34 +712,25 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (namespaces_event == NULL) goto out_free_fork; - snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); - n = scandir(proc_path, &dirent, 0, alphasort); - - if (n < 0) - goto out_free_namespaces; - - for (i = 0; i < n; i++) { + for (i = start; i < start + num; i++) { if (!isdigit(dirent[i]->d_name[0])) continue; pid = (pid_t)strtol(dirent[i]->d_name, &end, 10); /* only interested in proper numerical dirents */ - if (!*end) { - /* - * We may race with exiting thread, so don't stop just because - * one thread couldn't be synthesized. - */ - __event__synthesize_thread(comm_event, mmap_event, fork_event, - namespaces_event, pid, 1, process, - tool, machine, mmap_data, - proc_map_timeout); - } - free(dirent[i]); + if (*end) + continue; + /* + * We may race with exiting thread, so don't stop just because + * one thread couldn't be synthesized. + */ + __event__synthesize_thread(comm_event, mmap_event, fork_event, + namespaces_event, pid, 1, process, + tool, machine, mmap_data, + proc_map_timeout); } - free(dirent); err = 0; -out_free_namespaces: free(namespaces_event); out_free_fork: free(fork_event); @@ -753,6 +742,115 @@ out: return err; } +struct synthesize_threads_arg { + struct perf_tool *tool; + perf_event__handler_t process; + struct machine *machine; + bool mmap_data; + unsigned int proc_map_timeout; + struct dirent **dirent; + int num; + int start; +}; + +static void *synthesize_threads_worker(void *arg) +{ + struct synthesize_threads_arg *args = arg; + + __perf_event__synthesize_threads(args->tool, args->process, + args->machine, args->mmap_data, + args->proc_map_timeout, args->dirent, + args->start, args->num); + return NULL; +} + +int perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data, + unsigned int proc_map_timeout, + unsigned int nr_threads_synthesize) +{ + struct synthesize_threads_arg *args = NULL; + pthread_t *synthesize_threads = NULL; + char proc_path[PATH_MAX]; + struct dirent **dirent; + int num_per_thread; + int m, n, i, j; + int thread_nr; + int base = 0; + int err = -1; + + + if (machine__is_default_guest(machine)) + return 0; + + snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); + n = scandir(proc_path, &dirent, 0, alphasort); + if (n < 0) + return err; + + thread_nr = nr_threads_synthesize; + + if (thread_nr <= 1) { + err = __perf_event__synthesize_threads(tool, process, + machine, mmap_data, + proc_map_timeout, + dirent, base, n); + goto free_dirent; + } + if (thread_nr > n) + thread_nr = n; + + synthesize_threads = calloc(sizeof(pthread_t), thread_nr); + if (synthesize_threads == NULL) + goto free_dirent; + + args = calloc(sizeof(*args), thread_nr); + if (args == NULL) + goto free_threads; + + num_per_thread = n / thread_nr; + m = n % thread_nr; + for (i = 0; i < thread_nr; i++) { + args[i].tool = tool; + args[i].process = process; + args[i].machine = machine; + args[i].mmap_data = mmap_data; + args[i].proc_map_timeout = proc_map_timeout; + args[i].dirent = dirent; + } + for (i = 0; i < m; i++) { + args[i].num = num_per_thread + 1; + args[i].start = i * args[i].num; + } + if (i != 0) + base = args[i-1].start + args[i-1].num; + for (j = i; j < thread_nr; j++) { + args[j].num = num_per_thread; + args[j].start = base + (j - i) * args[i].num; + } + + for (i = 0; i < thread_nr; i++) { + if (pthread_create(&synthesize_threads[i], NULL, + synthesize_threads_worker, &args[i])) + goto out_join; + } + err = 0; +out_join: + for (i = 0; i < thread_nr; i++) + pthread_join(synthesize_threads[i], NULL); + free(args); +free_threads: + free(synthesize_threads); +free_dirent: + for (i = 0; i < n; i++) + free(dirent[i]); + free(dirent); + + return err; +} + struct process_symbol_args { const char *name; u64 start; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index ee7bcc898d35..d6cbb0a0d919 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -680,7 +680,8 @@ int perf_event__synthesize_cpu_map(struct perf_tool *tool, int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, - unsigned int proc_map_timeout); + unsigned int proc_map_timeout, + unsigned int nr_threads_synthesize); int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 585b4a3d64a4..7c3aa479201a 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2218,12 +2218,16 @@ int machines__for_each_thread(struct machines *machines, int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct thread_map *threads, perf_event__handler_t process, bool data_mmap, - unsigned int proc_map_timeout) + unsigned int proc_map_timeout, + unsigned int nr_threads_synthesize) { if (target__has_task(target)) return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout); else if (target__has_cpu(target)) - return perf_event__synthesize_threads(tool, process, machine, data_mmap, proc_map_timeout); + return perf_event__synthesize_threads(tool, process, + machine, data_mmap, + proc_map_timeout, + nr_threads_synthesize); /* command specified */ return 0; } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index b1cd516f2025..c6a299ea506c 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -257,15 +257,18 @@ int machines__for_each_thread(struct machines *machines, int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct thread_map *threads, perf_event__handler_t process, bool data_mmap, - unsigned int proc_map_timeout); + unsigned int proc_map_timeout, + unsigned int nr_threads_synthesize); static inline int machine__synthesize_threads(struct machine *machine, struct target *target, struct thread_map *threads, bool data_mmap, - unsigned int proc_map_timeout) + unsigned int proc_map_timeout, + unsigned int nr_threads_synthesize) { return __machine__synthesize_threads(machine, NULL, target, threads, perf_event__process, data_mmap, - proc_map_timeout); + proc_map_timeout, + nr_threads_synthesize); } pid_t machine__get_current_tid(struct machine *machine, int cpu); From 0c6b499495e928777c41ca2de4fbb58788269690 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 29 Sep 2017 07:47:55 -0700 Subject: [PATCH 14/15] perf top: Add option to set the number of thread for event synthesize Using UINT_MAX to indicate the default thread#, which is the max number of online CPU. Committer testing: # perf trace --no-inherit -e clone -o /tmp/output perf top --num-thread-synthesize 9 # cat /tmp/output ? ( ? ): ... [continued]: clone()) = 26651 (perf) 0.059 ( 0.010 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5bfac44f30, parent_tidptr: 0x7f5bfac459d0, child_tidptr: 0x7f5bfac459d0, tls: 0x7f5bfac45700) = 26652 (perf) 0.116 ( 0.014 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5bfa443f30, parent_tidptr: 0x7f5bfa4449d0, child_tidptr: 0x7f5bfa4449d0, tls: 0x7f5bfa444700) = 26653 (perf) 0.141 ( 0.009 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5bf9c42f30, parent_tidptr: 0x7f5bf9c439d0, child_tidptr: 0x7f5bf9c439d0, tls: 0x7f5bf9c43700) = 26654 (perf) 0.160 ( 0.012 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5bf9441f30, parent_tidptr: 0x7f5bf94429d0, child_tidptr: 0x7f5bf94429d0, tls: 0x7f5bf9442700) = 26655 (perf) 0.232 ( 0.013 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5bf8c40f30, parent_tidptr: 0x7f5bf8c419d0, child_tidptr: 0x7f5bf8c419d0, tls: 0x7f5bf8c41700) = 26656 (perf) 0.393 ( 0.011 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5be3ffef30, parent_tidptr: 0x7f5be3fff9d0, child_tidptr: 0x7f5be3fff9d0, tls: 0x7f5be3fff700) = 26657 (perf) 0.802 ( 0.012 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5be37fdf30, parent_tidptr: 0x7f5be37fe9d0, child_tidptr: 0x7f5be37fe9d0, tls: 0x7f5be37fe700) = 26658 (perf) 1.411 ( 0.022 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5be2ffcf30, parent_tidptr: 0x7f5be2ffd9d0, child_tidptr: 0x7f5be2ffd9d0, tls: 0x7f5be2ffd700) = 26659 (perf) 246.422 ( 0.042 ms): clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f5be2ffcf30, parent_tidptr: 0x7f5be2ffd9d0, child_tidptr: 0x7f5be2ffd9d0, tls: 0x7f5be2ffd700) = 26660 (perf) # Signed-off-by: Kan Liang Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Andi Kleen Cc: He Kuang Cc: Lukasz Odzioba Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1506696477-146932-5-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-top.txt | 3 +++ tools/perf/builtin-top.c | 11 ++++++++--- tools/perf/util/event.c | 5 ++++- tools/perf/util/top.h | 1 + 4 files changed, 16 insertions(+), 4 deletions(-) diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index d864ea6fd367..4353262bc462 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -240,6 +240,9 @@ Default is to monitor all CPUS. --force:: Don't do ownership validation. +--num-thread-synthesize:: + The number of threads to run when synthesizing events for existing processes. + By default, the number of threads equals to the number of online CPUs. INTERACTIVE PROMPTING KEYS -------------------------- diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index bc31b93cc1d8..477a8699f0b5 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -958,14 +958,16 @@ static int __cmd_top(struct perf_top *top) if (perf_session__register_idle_thread(top->session) < 0) goto out_delete; - perf_set_multithreaded(); + if (top->nr_threads_synthesize > 1) + perf_set_multithreaded(); machine__synthesize_threads(&top->session->machines.host, &opts->target, top->evlist->threads, false, opts->proc_map_timeout, - (unsigned int)sysconf(_SC_NPROCESSORS_ONLN)); + top->nr_threads_synthesize); - perf_set_singlethreaded(); + if (top->nr_threads_synthesize > 1) + perf_set_singlethreaded(); if (perf_hpp_list.socket) { ret = perf_env__read_cpu_topology_map(&perf_env); @@ -1118,6 +1120,7 @@ int cmd_top(int argc, const char **argv) }, .max_stack = sysctl_perf_event_max_stack, .sym_pcnt_filter = 5, + .nr_threads_synthesize = UINT_MAX, }; struct record_opts *opts = &top.record_opts; struct target *target = &opts->target; @@ -1227,6 +1230,8 @@ int cmd_top(int argc, const char **argv) OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy, "Show entries in a hierarchy"), OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"), + OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize, + "number of thread to run event synthesize"), OPT_END() }; const char * const top_usage[] = { diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 0e678dd6bdbe..47eff4767edb 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -790,7 +790,10 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (n < 0) return err; - thread_nr = nr_threads_synthesize; + if (nr_threads_synthesize == UINT_MAX) + thread_nr = sysconf(_SC_NPROCESSORS_ONLN); + else + thread_nr = nr_threads_synthesize; if (thread_nr <= 1) { err = __perf_event__synthesize_threads(tool, process, diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 9bdfb78a9a35..f4296e1e3bb8 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -37,6 +37,7 @@ struct perf_top { int sym_pcnt_filter; const char *sym_filter; float min_percent; + unsigned int nr_threads_synthesize; }; #define CONSOLE_CLEAR "" From f6a9820d572bd8384d982357cbad214b3a6c04bb Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 28 Sep 2017 18:06:33 +0200 Subject: [PATCH 15/15] perf tests attr: Fix group stat tests We started to use group read whenever it's possible: 82bf311e15d2 perf stat: Use group read for event groups That breaks some of attr tests, this change adds the new possible read_format value. Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Heiko Carstens Cc: Hendrik Brueckner Cc: Martin Schwidefsky Cc: Thomas-Mich Richter LPU-Reference: 20170928160633.GA26973@krava Link: http://lkml.kernel.org/n/tip-1ko2zc4nph93d8lfwjyk9ivz@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr/test-stat-group | 2 ++ tools/perf/tests/attr/test-stat-group1 | 2 ++ 2 files changed, 4 insertions(+) diff --git a/tools/perf/tests/attr/test-stat-group b/tools/perf/tests/attr/test-stat-group index fdc1596a8862..e15d6946e9b3 100644 --- a/tools/perf/tests/attr/test-stat-group +++ b/tools/perf/tests/attr/test-stat-group @@ -6,6 +6,7 @@ ret = 1 [event-1:base-stat] fd=1 group_fd=-1 +read_format=3|15 [event-2:base-stat] fd=2 @@ -13,3 +14,4 @@ group_fd=1 config=1 disabled=0 enable_on_exec=0 +read_format=3|15 diff --git a/tools/perf/tests/attr/test-stat-group1 b/tools/perf/tests/attr/test-stat-group1 index 2a1f86e4a904..1746751123dc 100644 --- a/tools/perf/tests/attr/test-stat-group1 +++ b/tools/perf/tests/attr/test-stat-group1 @@ -6,6 +6,7 @@ ret = 1 [event-1:base-stat] fd=1 group_fd=-1 +read_format=3|15 [event-2:base-stat] fd=2 @@ -13,3 +14,4 @@ group_fd=1 config=1 disabled=0 enable_on_exec=0 +read_format=3|15