From d6838ec44b4513280a3f43fcc402e246d543fb53 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 24 Jun 2022 16:13:08 -0700 Subject: [PATCH 1/8] perf offcpu: Fix build failure on old kernels Old kernels have a 'struct task_struct' which contains a "state" field and newer kernels have "__state" instead. While the get_task_state() in the BPF code handles that in some way, it assumed the current kernel has the new definition and it caused a build error on old kernels. We should not assume anything and access them carefully. Do not use 'task struct' directly access it instead using new and old definitions in a row. Fixes: edc41a1099c2d08c ("perf record: Enable off-cpu analysis with BPF") Reported-by: Ian Rogers Signed-off-by: Namhyung Kim Cc: Blake Jones Cc: Hao Luo Cc: Jiri Olsa Cc: Milian Wolff Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Link: http://lore.kernel.org/lkml/20220624231313.367909-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/off_cpu.bpf.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c index 792ae2847080..cc6d7fd55118 100644 --- a/tools/perf/util/bpf_skel/off_cpu.bpf.c +++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c @@ -71,6 +71,11 @@ struct { __uint(max_entries, 1); } cgroup_filter SEC(".maps"); +/* new kernel task_struct definition */ +struct task_struct___new { + long __state; +} __attribute__((preserve_access_index)); + /* old kernel task_struct definition */ struct task_struct___old { long state; @@ -93,14 +98,17 @@ const volatile bool uses_cgroup_v1 = false; */ static inline int get_task_state(struct task_struct *t) { - if (bpf_core_field_exists(t->__state)) - return BPF_CORE_READ(t, __state); + /* recast pointer to capture new type for compiler */ + struct task_struct___new *t_new = (void *)t; - /* recast pointer to capture task_struct___old type for compiler */ - struct task_struct___old *t_old = (void *)t; + if (bpf_core_field_exists(t_new->__state)) { + return BPF_CORE_READ(t_new, __state); + } else { + /* recast pointer to capture old type for compiler */ + struct task_struct___old *t_old = (void *)t; - /* now use old "state" name of the field */ - return BPF_CORE_READ(t_old, state); + return BPF_CORE_READ(t_old, state); + } } static inline __u64 get_cgroup_id(struct task_struct *t) From 49c692b7dfc9b6c06a1dc11359a8780575b16d4a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 24 Jun 2022 16:13:09 -0700 Subject: [PATCH 2/8] perf offcpu: Accept allowed sample types only As offcpu-time event is synthesized at the end, it could not get the all the sample info. Define OFFCPU_SAMPLE_TYPES for allowed ones and mask out others in evsel__config() to prevent parse errors. Because perf sample parsing assumes a specific ordering with the sample types, setting unsupported one would make it fail to read data like perf record -d/--data. Fixes: edc41a1099c2d08c ("perf record: Enable off-cpu analysis with BPF") Signed-off-by: Namhyung Kim Cc: Blake Jones Cc: Hao Luo Cc: Ian Rogers Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Link: http://lore.kernel.org/lkml/20220624231313.367909-3-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_off_cpu.c | 7 ++++++- tools/perf/util/evsel.c | 9 +++++++++ tools/perf/util/off_cpu.h | 9 +++++++++ 3 files changed, 24 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c index b73e84a02264..f289b7713598 100644 --- a/tools/perf/util/bpf_off_cpu.c +++ b/tools/perf/util/bpf_off_cpu.c @@ -265,6 +265,12 @@ int off_cpu_write(struct perf_session *session) sample_type = evsel->core.attr.sample_type; + if (sample_type & ~OFFCPU_SAMPLE_TYPES) { + pr_err("not supported sample type: %llx\n", + (unsigned long long)sample_type); + return -1; + } + if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) { if (evsel->core.id) sid = evsel->core.id[0]; @@ -319,7 +325,6 @@ int off_cpu_write(struct perf_session *session) } if (sample_type & PERF_SAMPLE_CGROUP) data.array[n++] = key.cgroup_id; - /* TODO: handle more sample types */ size = n * sizeof(u64); data.hdr.size = size; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ce499c5da8d7..094b0a9c0bc0 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -48,6 +48,7 @@ #include "util.h" #include "hashmap.h" #include "pmu-hybrid.h" +#include "off_cpu.h" #include "../perf-sys.h" #include "util/parse-branch-options.h" #include @@ -1102,6 +1103,11 @@ static void evsel__set_default_freq_period(struct record_opts *opts, } } +static bool evsel__is_offcpu_event(struct evsel *evsel) +{ + return evsel__is_bpf_output(evsel) && !strcmp(evsel->name, OFFCPU_EVENT); +} + /* * The enable_on_exec/disabled value strategy: * @@ -1366,6 +1372,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, */ if (evsel__is_dummy_event(evsel)) evsel__reset_sample_bit(evsel, BRANCH_STACK); + + if (evsel__is_offcpu_event(evsel)) + evsel->core.attr.sample_type &= OFFCPU_SAMPLE_TYPES; } int evsel__set_filter(struct evsel *evsel, const char *filter) diff --git a/tools/perf/util/off_cpu.h b/tools/perf/util/off_cpu.h index 548008f74d42..2dd67c60f211 100644 --- a/tools/perf/util/off_cpu.h +++ b/tools/perf/util/off_cpu.h @@ -1,6 +1,8 @@ #ifndef PERF_UTIL_OFF_CPU_H #define PERF_UTIL_OFF_CPU_H +#include + struct evlist; struct target; struct perf_session; @@ -8,6 +10,13 @@ struct record_opts; #define OFFCPU_EVENT "offcpu-time" +#define OFFCPU_SAMPLE_TYPES (PERF_SAMPLE_IDENTIFIER | PERF_SAMPLE_IP | \ + PERF_SAMPLE_TID | PERF_SAMPLE_TIME | \ + PERF_SAMPLE_ID | PERF_SAMPLE_CPU | \ + PERF_SAMPLE_PERIOD | PERF_SAMPLE_CALLCHAIN | \ + PERF_SAMPLE_CGROUP) + + #ifdef HAVE_BPF_SKEL int off_cpu_prepare(struct evlist *evlist, struct target *target, struct record_opts *opts); From 117c49505b5918388157321c68c6e5a58b67f649 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 21 Dec 2020 12:53:44 -0300 Subject: [PATCH 3/8] tools kvm headers arm64: Update KVM headers from the kernel sources To pick the changes from: 2cde51f1e10f2600 ("KVM: arm64: Hide KVM_REG_ARM_*_BMAP_BIT_COUNT from userspace") b22216e1a617ca55 ("KVM: arm64: Add vendor hypervisor firmware register") 428fd6788d4d0e0d ("KVM: arm64: Add standard hypervisor firmware register") 05714cab7d63b189 ("KVM: arm64: Setup a framework for hypercall bitmap firmware registers") 18f3976fdb5da2ba ("KVM: arm64: uapi: Add kvm_debug_exit_arch.hsr_high") a5905d6af492ee6a ("KVM: arm64: Allow SMCCC_ARCH_WORKAROUND_3 to be discovered and migrated") That don't causes any changes in tooling (when built on x86), only addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Cc: Adrian Hunter Cc: Alexandru Elisei Cc: Catalin Marinas Cc: Ian Rogers Cc: James Morse Cc: Jiri Olsa Cc: Marc Zyngier Cc: Namhyung Kim Cc: Raghavendra Rao Ananta Link: https://lore.kernel.org/lkml/YrsWcDQyJC+xsfmm@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/kvm.h | 36 +++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index c1b6ddc02d2f..3bb134355874 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -139,8 +139,10 @@ struct kvm_guest_debug_arch { __u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS]; }; +#define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 << 0) struct kvm_debug_exit_arch { __u32 hsr; + __u32 hsr_high; /* ESR_EL2[61:32] */ __u64 far; /* used for watchpoints */ }; @@ -332,6 +334,40 @@ struct kvm_arm_copy_mte_tags { #define KVM_ARM64_SVE_VLS_WORDS \ ((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1) +/* Bitmap feature firmware registers */ +#define KVM_REG_ARM_FW_FEAT_BMAP (0x0016 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_FEAT_BMAP_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW_FEAT_BMAP | \ + ((r) & 0xffff)) + +#define KVM_REG_ARM_STD_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(0) + +enum { + KVM_REG_ARM_STD_BIT_TRNG_V1_0 = 0, +#ifdef __KERNEL__ + KVM_REG_ARM_STD_BMAP_BIT_COUNT, +#endif +}; + +#define KVM_REG_ARM_STD_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(1) + +enum { + KVM_REG_ARM_STD_HYP_BIT_PV_TIME = 0, +#ifdef __KERNEL__ + KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT, +#endif +}; + +#define KVM_REG_ARM_VENDOR_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(2) + +enum { + KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT = 0, + KVM_REG_ARM_VENDOR_HYP_BIT_PTP = 1, +#ifdef __KERNEL__ + KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT, +#endif +}; + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 From 579d6c6d77a7b55d74db8a506d5fc0c77fb1a5e1 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 13 Jun 2022 18:47:14 -0700 Subject: [PATCH 4/8] perf bpf: 8 byte align bpil data bpil data is accessed assuming 64-bit alignment resulting in undefined behavior as the data is just byte aligned. With an -fsanitize=undefined build the following errors are observed: $ sudo perf record -a sleep 1 util/bpf-event.c:310:22: runtime error: load of misaligned address 0x55f61084520f for type '__u64', which requires 8 byte alignment 0x55f61084520f: note: pointer points here a8 fe ff ff 3c 51 d3 c0 ff ff ff ff 04 84 d3 c0 ff ff ff ff d8 aa d3 c0 ff ff ff ff a4 c0 d3 c0 ^ util/bpf-event.c:311:20: runtime error: load of misaligned address 0x55f61084522f for type '__u32', which requires 4 byte alignment 0x55f61084522f: note: pointer points here ff ff ff ff c7 17 00 00 f1 02 00 00 1f 04 00 00 58 04 00 00 00 00 00 00 0f 00 00 00 63 02 00 00 ^ util/bpf-event.c:198:33: runtime error: member access within misaligned address 0x55f61084523f for type 'const struct bpf_func_info', which requires 4 byte alignment 0x55f61084523f: note: pointer points here 58 04 00 00 00 00 00 00 0f 00 00 00 63 02 00 00 3b 00 00 00 ab 02 00 00 44 00 00 00 14 03 00 00 Correct this by rouding up the data sizes and aligning the pointers. Signed-off-by: Ian Rogers Acked-by: Andrii Nakryiko Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Dave Marchevsky Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Fastabend Cc: KP Singh Cc: Mark Rutland Cc: Martin KaFai Lau Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Song Liu Cc: Stephane Eranian Cc: Yonghong Song Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: https://lore.kernel.org/r/20220614014714.1407239-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-utils.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c index e271e05e51bc..80b1d2b3729b 100644 --- a/tools/perf/util/bpf-utils.c +++ b/tools/perf/util/bpf-utils.c @@ -149,11 +149,10 @@ get_bpf_prog_info_linear(int fd, __u64 arrays) count = bpf_prog_info_read_offset_u32(&info, desc->count_offset); size = bpf_prog_info_read_offset_u32(&info, desc->size_offset); - data_len += count * size; + data_len += roundup(count * size, sizeof(__u64)); } /* step 3: allocate continuous memory */ - data_len = roundup(data_len, sizeof(__u64)); info_linear = malloc(sizeof(struct perf_bpil) + data_len); if (!info_linear) return ERR_PTR(-ENOMEM); @@ -180,7 +179,7 @@ get_bpf_prog_info_linear(int fd, __u64 arrays) bpf_prog_info_set_offset_u64(&info_linear->info, desc->array_offset, ptr_to_u64(ptr)); - ptr += count * size; + ptr += roundup(count * size, sizeof(__u64)); } /* step 5: call syscall again to get required arrays */ From 7fe718fb8f3f543da1f04ca08bf652dd2afb55f8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 09:39:02 -0300 Subject: [PATCH 5/8] tools headers UAPI: Sync linux/kvm.h with the kernel sources To pick the changes in: bfbab44568779e16 ("KVM: arm64: Implement PSCI SYSTEM_SUSPEND") 7b33a09d036ffd9a ("KVM: arm64: Add support for userspace to suspend a vCPU") ffbb61d09fc56c85 ("KVM: x86: Accept KVM_[GS]ET_TSC_KHZ as a VM ioctl.") 661a20fab7d156cf ("KVM: x86/xen: Advertise and document KVM_XEN_HVM_CONFIG_EVTCHN_SEND") fde0451be8fb3208 ("KVM: x86/xen: Support per-vCPU event channel upcall via local APIC") 28d1629f751c4a5f ("KVM: x86/xen: Kernel acceleration for XENVER_version") 536395260582be74 ("KVM: x86/xen: handle PV timers oneshot mode") 942c2490c23f2800 ("KVM: x86/xen: Add KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID") 2fd6df2f2b47d430 ("KVM: x86/xen: intercept EVTCHNOP_send from guests") 35025735a79eaa89 ("KVM: x86/xen: Support direct injection of event channel events") That automatically adds support for this new ioctl: $ tools/perf/trace/beauty/kvm_ioctl.sh > before $ cp include/uapi/linux/kvm.h tools/include/uapi/linux/kvm.h $ tools/perf/trace/beauty/kvm_ioctl.sh > after $ diff -u before after --- before 2022-06-28 12:13:07.281150509 -0300 +++ after 2022-06-28 12:13:16.423392896 -0300 @@ -98,6 +98,7 @@ [0xcc] = "GET_SREGS2", [0xcd] = "SET_SREGS2", [0xce] = "GET_STATS_FD", + [0xd0] = "XEN_HVM_EVTCHN_SEND", [0xe0] = "CREATE_DEVICE", [0xe1] = "SET_DEVICE_ATTR", [0xe2] = "GET_DEVICE_ATTR", $ This silences these perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h' diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h Cc: Adrian Hunter Cc: David Woodhouse Cc: Ian Rogers Cc: Jiri Olsa Cc: Joao Martins Cc: Marc Zyngier Cc: Namhyung Kim Cc: Oliver Upton Cc: Paolo Bonzini Link: http://lore.kernel.org/lkml/Yrs4RE+qfgTaWdAt@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/kvm.h | 54 ++++++++++++++++++++++++++++++++-- 1 file changed, 52 insertions(+), 2 deletions(-) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 6a184d260c7f..5088bd9f1922 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -444,6 +444,9 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_SHUTDOWN 1 #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 +#define KVM_SYSTEM_EVENT_WAKEUP 4 +#define KVM_SYSTEM_EVENT_SUSPEND 5 +#define KVM_SYSTEM_EVENT_SEV_TERM 6 __u32 type; __u32 ndata; union { @@ -646,6 +649,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 #define KVM_MP_STATE_AP_RESET_HOLD 9 +#define KVM_MP_STATE_SUSPENDED 10 struct kvm_mp_state { __u32 mp_state; @@ -1150,8 +1154,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 #define KVM_CAP_DISABLE_QUIRKS2 213 -/* #define KVM_CAP_VM_TSC_CONTROL 214 */ +#define KVM_CAP_VM_TSC_CONTROL 214 #define KVM_CAP_SYSTEM_EVENT_DATA 215 +#define KVM_CAP_ARM_SYSTEM_SUSPEND 216 #ifdef KVM_CAP_IRQ_ROUTING @@ -1240,6 +1245,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) +#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) struct kvm_xen_hvm_config { __u32 flags; @@ -1478,7 +1484,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) /* Available with KVM_CAP_PPC_GET_PVINFO */ #define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo) -/* Available with KVM_CAP_TSC_CONTROL */ +/* Available with KVM_CAP_TSC_CONTROL for a vCPU, or with +* KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */ #define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2) #define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3) /* Available with KVM_CAP_PCI_2_3 */ @@ -1694,6 +1701,32 @@ struct kvm_xen_hvm_attr { struct { __u64 gfn; } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u32 xen_version; __u64 pad[8]; } u; }; @@ -1702,11 +1735,17 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 #define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_HVM_EVTCHN_SEND _IOW(KVMIO, 0xd0, struct kvm_irq_routing_xen_evtchn) + #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) @@ -1724,6 +1763,13 @@ struct kvm_xen_vcpu_attr { __u64 time_blocked; __u64 time_offline; } runstate; + __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; + __u8 vector; } u; }; @@ -1734,6 +1780,10 @@ struct kvm_xen_vcpu_attr { #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { From 5eb502b2e1ae1ab052cdf6bdd7615217e8517360 Mon Sep 17 00:00:00 2001 From: Ivan Babrou Date: Fri, 1 Jul 2022 11:20:46 -0700 Subject: [PATCH 6/8] perf unwind: Fix unitialized 'offset' variable on aarch64 Commit dc2cf4ca866f5715 ("perf unwind: Fix segbase for ld.lld linked objects") uncovered the following issue on aarch64: util/unwind-libunwind-local.c: In function 'find_proc_info': util/unwind-libunwind-local.c:386:28: error: 'offset' may be used uninitialized in this function [-Werror=maybe-uninitialized] 386 | if (ofs > 0) { | ^ util/unwind-libunwind-local.c:199:22: note: 'offset' was declared here 199 | u64 address, offset; | ^~~~~~ util/unwind-libunwind-local.c:371:20: error: 'offset' may be used uninitialized in this function [-Werror=maybe-uninitialized] 371 | if (ofs <= 0) { | ^ util/unwind-libunwind-local.c:199:22: note: 'offset' was declared here 199 | u64 address, offset; | ^~~~~~ util/unwind-libunwind-local.c:363:20: error: 'offset' may be used uninitialized in this function [-Werror=maybe-uninitialized] 363 | if (ofs <= 0) { | ^ util/unwind-libunwind-local.c:199:22: note: 'offset' was declared here 199 | u64 address, offset; | ^~~~~~ In file included from util/libunwind/arm64.c:37: Fixes: dc2cf4ca866f5715 ("perf unwind: Fix segbase for ld.lld linked objects") Signed-off-by: Ivan Babrou Cc: Alexander Shishkin Cc: Fangrui Song Cc: Ian Rogers Cc: James Clark Cc: Jiri Olsa Cc: kernel-team@cloudflare.com Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20220701182046.12589-1-ivan@cloudflare.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/unwind-libunwind-local.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 6e5b8cce47bf..81b6bd6e1536 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -197,7 +197,7 @@ static int elf_section_address_and_offset(int fd, const char *name, u64 *address #ifndef NO_LIBUNWIND_DEBUG_FRAME static u64 elf_section_offset(int fd, const char *name) { - u64 address, offset; + u64 address, offset = 0; if (elf_section_address_and_offset(fd, name, &address, &offset)) return 0; From 363afa3aef24f5e08df6a539f5dc3aae4cddcc1a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 1 Jul 2022 13:54:57 -0700 Subject: [PATCH 7/8] perf synthetic-events: Don't sort the task scan result from /proc It should not sort the result as procfs already returns a proper ordering of tasks. Actually sorting the order caused problems that it doesn't guararantee to process the main thread first. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20220701205458.985106-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/synthetic-events.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 27acdc5e5723..a068f42833c3 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -754,7 +754,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, snprintf(filename, sizeof(filename), "%s/proc/%d/task", machine->root_dir, pid); - n = scandir(filename, &dirent, filter_task, alphasort); + n = scandir(filename, &dirent, filter_task, NULL); if (n < 0) return n; @@ -987,7 +987,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, return 0; snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); - n = scandir(proc_path, &dirent, filter_task, alphasort); + n = scandir(proc_path, &dirent, filter_task, NULL); if (n < 0) return err; From ff898552fb32d255517fb0676f9fa500664c484d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 1 Jul 2022 13:54:58 -0700 Subject: [PATCH 8/8] perf synthetic-events: Ignore dead threads during event synthesis When it synthesize various task events, it scans the list of task first and then accesses later. There's a window threads can die between the two and proc entries may not be available. Instead of bailing out, we can ignore that thread and move on. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20220701205458.985106-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/synthetic-events.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index a068f42833c3..84d17bd4efae 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -767,11 +767,12 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (*end) continue; - rc = -1; + /* some threads may exit just after scan, ignore it */ if (perf_event__prepare_comm(comm_event, pid, _pid, machine, &tgid, &ppid, &kernel_thread) != 0) - break; + continue; + rc = -1; if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, ppid, process, machine) < 0) break;