diff options
99 files changed, 1518 insertions, 216 deletions
diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt index 41ef9d8efe95..5ea85059db3b 100644 --- a/Documentation/trace/kprobetrace.txt +++ b/Documentation/trace/kprobetrace.txt @@ -8,8 +8,9 @@ Overview -------- These events are similar to tracepoint based events. Instead of Tracepoint, this is based on kprobes (kprobe and kretprobe). So it can probe wherever -kprobes can probe (this means, all functions body except for __kprobes -functions). Unlike the Tracepoint based event, this can be added and removed +kprobes can probe (this means, all functions except those with +__kprobes/nokprobe_inline annotation and those marked NOKPROBE_SYMBOL). +Unlike the Tracepoint based event, this can be added and removed dynamically, on the fly. To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y. diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index c328e4f7dcad..177bdf6c6aeb 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -267,6 +267,7 @@ extern int arch_init_kprobes(void); extern void show_registers(struct pt_regs *regs); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); +extern bool arch_function_offset_within_entry(unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 000fdb211c7d..f19a82362851 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1112,6 +1112,7 @@ extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); +extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); /* Callchains */ @@ -1315,6 +1316,7 @@ static inline int perf_unregister_guest_info_callbacks static inline void perf_event_mmap(struct vm_area_struct *vma) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } +static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index c66a485a24ac..bec0aad0e15c 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -344,7 +344,8 @@ struct perf_event_attr { use_clockid : 1, /* use @clockid for time fields */ context_switch : 1, /* context switch data */ write_backward : 1, /* Write ring buffer from end to beginning */ - __reserved_1 : 36; + namespaces : 1, /* include namespaces data */ + __reserved_1 : 35; union { __u32 wakeup_events; /* wakeup every n events */ @@ -610,6 +611,23 @@ struct perf_event_header { __u16 size; }; +struct perf_ns_link_info { + __u64 dev; + __u64 ino; +}; + +enum { + NET_NS_INDEX = 0, + UTS_NS_INDEX = 1, + IPC_NS_INDEX = 2, + PID_NS_INDEX = 3, + USER_NS_INDEX = 4, + MNT_NS_INDEX = 5, + CGROUP_NS_INDEX = 6, + + NR_NAMESPACES, /* number of available namespaces */ +}; + enum perf_event_type { /* @@ -862,6 +880,18 @@ enum perf_event_type { */ PERF_RECORD_SWITCH_CPU_WIDE = 15, + /* + * struct { + * struct perf_event_header header; + * u32 pid; + * u32 tid; + * u64 nr_namespaces; + * { u64 dev, inode; } [nr_namespaces]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_NAMESPACES = 16, + PERF_RECORD_MAX, /* non-ABI */ }; diff --git a/kernel/events/core.c b/kernel/events/core.c index a17ed56c8ce1..2d7990d4e988 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -48,6 +48,8 @@ #include <linux/parser.h> #include <linux/sched/clock.h> #include <linux/sched/mm.h> +#include <linux/proc_ns.h> +#include <linux/mount.h> #include "internal.h" @@ -379,6 +381,7 @@ static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events); static atomic_t nr_mmap_events __read_mostly; static atomic_t nr_comm_events __read_mostly; +static atomic_t nr_namespaces_events __read_mostly; static atomic_t nr_task_events __read_mostly; static atomic_t nr_freq_events __read_mostly; static atomic_t nr_switch_events __read_mostly; @@ -3991,6 +3994,8 @@ static void unaccount_event(struct perf_event *event) atomic_dec(&nr_mmap_events); if (event->attr.comm) atomic_dec(&nr_comm_events); + if (event->attr.namespaces) + atomic_dec(&nr_namespaces_events); if (event->attr.task) atomic_dec(&nr_task_events); if (event->attr.freq) @@ -6491,6 +6496,7 @@ static void perf_event_task(struct task_struct *task, void perf_event_fork(struct task_struct *task) { perf_event_task(task, NULL, 1); + perf_event_namespaces(task); } /* @@ -6593,6 +6599,132 @@ void perf_event_comm(struct task_struct *task, bool exec) } /* + * namespaces tracking + */ + +struct perf_namespaces_event { + struct task_struct *task; + + struct { + struct perf_event_header header; + + u32 pid; + u32 tid; + u64 nr_namespaces; + struct perf_ns_link_info link_info[NR_NAMESPACES]; + } event_id; +}; + +static int perf_event_namespaces_match(struct perf_event *event) +{ + return event->attr.namespaces; +} + +static void perf_event_namespaces_output(struct perf_event *event, + void *data) +{ + struct perf_namespaces_event *namespaces_event = data; + struct perf_output_handle handle; + struct perf_sample_data sample; + int ret; + + if (!perf_event_namespaces_match(event)) + return; + + perf_event_header__init_id(&namespaces_event->event_id.header, + &sample, event); + ret = perf_output_begin(&handle, event, + namespaces_event->event_id.header.size); + if (ret) + return; + + namespaces_event->event_id.pid = perf_event_pid(event, + namespaces_event->task); + namespaces_event->event_id.tid = perf_event_tid(event, + namespaces_event->task); + + perf_output_put(&handle, namespaces_event->event_id); + + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + +static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info, + struct task_struct *task, + const struct proc_ns_operations *ns_ops) +{ + struct path ns_path; + struct inode *ns_inode; + void *error; + + error = ns_get_path(&ns_path, task, ns_ops); + if (!error) { + ns_inode = ns_path.dentry->d_inode; + ns_link_info->dev = new_encode_dev(ns_inode->i_sb->s_dev); + ns_link_info->ino = ns_inode->i_ino; + } +} + +void perf_event_namespaces(struct task_struct *task) +{ + struct perf_namespaces_event namespaces_event; + struct perf_ns_link_info *ns_link_info; + + if (!atomic_read(&nr_namespaces_events)) + return; + + namespaces_event = (struct perf_namespaces_event){ + .task = task, + .event_id = { + .header = { + .type = PERF_RECORD_NAMESPACES, + .misc = 0, + .size = sizeof(namespaces_event.event_id), + }, + /* .pid */ + /* .tid */ + .nr_namespaces = NR_NAMESPACES, + /* .link_info[NR_NAMESPACES] */ + }, + }; + + ns_link_info = namespaces_event.event_id.link_info; + + perf_fill_ns_link_info(&ns_link_info[MNT_NS_INDEX], + task, &mntns_operations); + +#ifdef CONFIG_USER_NS + perf_fill_ns_link_info(&ns_link_info[USER_NS_INDEX], + task, &userns_operations); +#endif +#ifdef CONFIG_NET_NS + perf_fill_ns_link_info(&ns_link_info[NET_NS_INDEX], + task, &netns_operations); +#endif +#ifdef CONFIG_UTS_NS + perf_fill_ns_link_info(&ns_link_info[UTS_NS_INDEX], + task, &utsns_operations); +#endif +#ifdef CONFIG_IPC_NS + perf_fill_ns_link_info(&ns_link_info[IPC_NS_INDEX], + task, &ipcns_operations); +#endif +#ifdef CONFIG_PID_NS + perf_fill_ns_link_info(&ns_link_info[PID_NS_INDEX], + task, &pidns_operations); +#endif +#ifdef CONFIG_CGROUPS + perf_fill_ns_link_info(&ns_link_info[CGROUP_NS_INDEX], + task, &cgroupns_operations); +#endif + + perf_iterate_sb(perf_event_namespaces_output, + &namespaces_event, + NULL); +} + +/* * mmap tracking */ @@ -9146,6 +9278,8 @@ static void account_event(struct perf_event *event) atomic_inc(&nr_mmap_events); if (event->attr.comm) atomic_inc(&nr_comm_events); + if (event->attr.namespaces) + atomic_inc(&nr_namespaces_events); if (event->attr.task) atomic_inc(&nr_task_events); if (event->attr.freq) @@ -9691,6 +9825,11 @@ SYSCALL_DEFINE5(perf_event_open, return -EACCES; } + if (attr.namespaces) { + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + } + if (attr.freq) { if (attr.sample_freq > sysctl_perf_event_sample_rate) return -EINVAL; diff --git a/kernel/fork.c b/kernel/fork.c index 6c463c80e93d..afa2947286cd 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2352,6 +2352,8 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) } } + perf_event_namespaces(current); + bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 699c5bc51a92..4780ec236035 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1740,11 +1740,12 @@ void unregister_kprobes(struct kprobe **kps, int num) } EXPORT_SYMBOL_GPL(unregister_kprobes); -int __weak __kprobes kprobe_exceptions_notify(struct notifier_block *self, - unsigned long val, void *data) +int __weak kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) { return NOTIFY_DONE; } +NOKPROBE_SYMBOL(kprobe_exceptions_notify); static struct notifier_block kprobe_exceptions_nb = { .notifier_call = kprobe_exceptions_notify, @@ -1875,12 +1876,25 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) } NOKPROBE_SYMBOL(pre_handler_kretprobe); +bool __weak arch_function_offset_within_entry(unsigned long offset) +{ + return !offset; +} + int register_kretprobe(struct kretprobe *rp) { int ret = 0; struct kretprobe_instance *inst; int i; void *addr; + unsigned long offset; + + addr = kprobe_addr(&rp->kp); + if (!kallsyms_lookup_size_offset((unsigned long)addr, NULL, &offset)) + return -EINVAL; + + if (!arch_function_offset_within_entry(offset)) + return -EINVAL; if (kretprobe_blacklist_size) { addr = kprobe_addr(&rp->kp); diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 782102e59eed..f6c5d330059a 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -26,6 +26,7 @@ #include <linux/file.h> #include <linux/syscalls.h> #include <linux/cgroup.h> +#include <linux/perf_event.h> static struct kmem_cache *nsproxy_cachep; @@ -262,6 +263,8 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype) goto out; } switch_task_namespaces(tsk, new_nsproxy); + + perf_event_namespaces(tsk); out: fput(file); return err; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f35109514a01..0ed834d6beb0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4355,6 +4355,7 @@ static const char readme_msg[] = "\t -:[<group>/]<event>\n" #ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" + "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n" #endif #ifdef CONFIG_UPROBE_EVENTS "\t place: <path>:<offset>\n" diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 5f688cc724f0..12fb540da0e5 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -681,10 +681,6 @@ static int create_trace_kprobe(int argc, char **argv) return -EINVAL; } if (isdigit(argv[1][0])) { - if (is_return) { - pr_info("Return probe point must be a symbol.\n"); - return -EINVAL; - } /* an address specified */ ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr); if (ret) { @@ -700,8 +696,9 @@ static int create_trace_kprobe(int argc, char **argv) pr_info("Failed to parse symbol.\n"); return ret; } - if (offset && is_return) { - pr_info("Return probe must be used without offset.\n"); + if (offset && is_return && + !arch_function_offset_within_entry(offset)) { + pr_info("Given offset is not valid for return probe.\n"); return -EINVAL; } } diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h index 059e33e94260..328eeceec709 100644 --- a/tools/arch/x86/include/asm/atomic.h +++ b/tools/arch/x86/include/asm/atomic.h @@ -7,6 +7,8 @@ #define LOCK_PREFIX "\n\tlock; " +#include <asm/cmpxchg.h> + /* * Atomic operations that C can't guarantee us. Useful for * resource counting etc.. @@ -62,4 +64,9 @@ static inline int atomic_dec_and_test(atomic_t *v) GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e"); } +static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) +{ + return cmpxchg(&v->counter, old, new); +} + #endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */ diff --git a/tools/arch/x86/include/asm/cmpxchg.h b/tools/arch/x86/include/asm/cmpxchg.h new file mode 100644 index 000000000000..f5253260f3cc --- /dev/null +++ b/tools/arch/x86/include/asm/cmpxchg.h @@ -0,0 +1,89 @@ +#ifndef TOOLS_ASM_X86_CMPXCHG_H +#define TOOLS_ASM_X86_CMPXCHG_H + +#include <linux/compiler.h> + +/* + * Non-existant functions to indicate usage errors at link time + * (or compile-time if the compiler implements __compiletime_error(). + */ +extern void __cmpxchg_wrong_size(void) + __compiletime_error("Bad argument size for cmpxchg"); + +/* + * Constants for operation sizes. On 32-bit, the 64-bit size it set to + * -1 because sizeof will never return -1, thereby making those switch + * case statements guaranteeed dead code which the compiler will + * eliminate, and allowing the "missing symbol in the default case" to + * indicate a usage error. + */ +#define __X86_CASE_B 1 +#define __X86_CASE_W 2 +#define __X86_CASE_L 4 +#ifdef __x86_64__ +#define __X86_CASE_Q 8 +#else +#define __X86_CASE_Q -1 /* sizeof will never return -1 */ +#endif + +/* + * Atomic compare and exchange. Compare OLD with MEM, if identical, + * store NEW in MEM. Return the initial value in MEM. Success is + * indicated by comparing RETURN with OLD. + */ +#define __raw_cmpxchg(ptr, old, new, size, lock) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (old); \ + __typeof__(*(ptr)) __new = (new); \ + switch (size) { \ + case __X86_CASE_B: \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_W: \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_L: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_Q: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ + asm volatile(lock "cmpxchgq %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + __ret; \ +}) + +#define __cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX) + +#define cmpxchg(ptr, old, new) \ + __cmpxchg(ptr, old, new, sizeof(*(ptr))) + + +#endif /* TOOLS_ASM_X86_CMPXCHG_H */ diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index e3fb5ecbdcb6..523911f316ce 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -63,6 +63,7 @@ FEATURE_TESTS_BASIC := \ lzma \ get_cpuid \ bpf \ + sched_getcpu \ sdt # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index b564a2eea039..09c9626ea666 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -48,12 +48,13 @@ FILES= \ test-get_cpuid.bin \ test-sdt.bin \ test-cxx.bin \ - test-jvmti.bin + test-jvmti.bin \ + test-sched_getcpu.bin FILES := $(addprefix $(OUTPUT),$(FILES)) -CC := $(CROSS_COMPILE)gcc -MD -CXX := $(CROSS_COMPILE)g++ -MD +CC ?= $(CROSS_COMPILE)gcc -MD +CXX ?= $(CROSS_COMPILE)g++ -MD PKG_CONFIG := $(CROSS_COMPILE)pkg-config LLVM_CONFIG ?= llvm-config @@ -91,6 +92,9 @@ $(OUTPUT)test-libelf.bin: $(OUTPUT)test-glibc.bin: $(BUILD) +$(OUTPUT)test-sched_getcpu.bin: + $(BUILD) + DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) DWARFLIBS += -lelf -lebl -lz -llzma -lbz2 diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 699e43627397..cc6c7c01f4ca 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -117,6 +117,10 @@ # include "test-pthread-attr-setaffinity-np.c" #undef main +#define main main_test_sched_getcpu +# include "test-sched_getcpu.c" +#undef main + # if 0 /* * Disable libbabeltrace check for test-all, because the requested @@ -182,6 +186,7 @@ int main(int argc, char *argv[]) main_test_get_cpuid(); main_test_bpf(); main_test_libcrypto(); + main_test_sched_getcpu(); main_test_sdt(); return 0; diff --git a/tools/build/feature/test-sched_getcpu.c b/tools/build/feature/test-sched_getcpu.c new file mode 100644 index 000000000000..c4a148dd7104 --- /dev/null +++ b/tools/build/feature/test-sched_getcpu.c @@ -0,0 +1,7 @@ +#define _GNU_SOURCE +#include <sched.h> + +int main(void) +{ + return sched_getcpu(); +} diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h index 2ba78c9f5701..5e9738f97bf3 100644 --- a/tools/include/asm-generic/atomic-gcc.h +++ b/tools/include/asm-generic/atomic-gcc.h @@ -60,4 +60,12 @@ static inline int atomic_dec_and_test(atomic_t *v) return __sync_sub_and_fetch(&v->counter, 1) == 0; } +#define cmpxchg(ptr, oldval, newval) \ + __sync_val_compare_and_swap(ptr, oldval, newval) + +static inline int atomic_cmpxchg(atomic_t *v, int oldval, int newval) +{ + return cmpxchg(&(v)->counter, oldval, newval); +} + #endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */ diff --git a/tools/include/linux/atomic.h b/tools/include/linux/atomic.h index 4e3d3d18ebab..9f21fc2b092b 100644 --- a/tools/include/linux/atomic.h +++ b/tools/include/linux/atomic.h @@ -3,4 +3,10 @@ #include <asm/atomic.h> +/* atomic_cmpxchg_relaxed */ +#ifndef atomic_cmpxchg_relaxed +#define atomic_cmpxchg_relaxed atomic_cmpxchg +#define atomic_cmpxchg_release atomic_cmpxchg +#endif /* atomic_cmpxchg_relaxed */ + #endif /* __TOOLS_LINUX_ATOMIC_H */ diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 48af2f10a42d..616935f1ff56 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -12,3 +12,7 @@ #if GCC_VERSION >= 70000 && !defined(__CHECKER__) # define __fallthrough __attribute__ ((fallthrough)) #endif + +#if GCC_VERSION >= 40300 +# define __compiletime_error(message) __attribute__((error(message))) +#endif /* GCC_VERSION >= 40300 */ diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 8de163b17c0d..c9e65e8faacd 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -5,6 +5,10 @@ #include <linux/compiler-gcc.h> #endif +#ifndef __compiletime_error +# define __compiletime_error(message) +#endif + /* Optimization barrier */ /* The "volatile" is due to gcc bugs */ #define barrier() __asm__ __volatile__("": : :"memory") diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index 28607db02bd3..adb4d0147755 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -5,6 +5,10 @@ #include <stddef.h> #include <assert.h> +#ifndef UINT_MAX +#define UINT_MAX (~0U) +#endif + #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) #define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1) diff --git a/tools/include/linux/refcount.h b/tools/include/linux/refcount.h new file mode 100644 index 000000000000..a0177c1f55b1 --- /dev/null +++ b/tools/include/linux/refcount.h @@ -0,0 +1,151 @@ +#ifndef _TOOLS_LINUX_REFCOUNT_H +#define _TOOLS_LINUX_REFCOUNT_H + +/* + * Variant of atomic_t specialized for reference counts. + * + * The interface matches the atomic_t interface (to aid in porting) but only + * provides the few functions one should use for reference counting. + * + * It differs in that the counter saturates at UINT_MAX and will not move once + * there. This avoids wrapping the counter and causing 'spurious' + * use-after-free issues. + * + * Memory ordering rules are slightly relaxed wrt regular atomic_t functions + * and provide only what is strictly required for refcounts. + * + * The increments are fully relaxed; these will not provide ordering. The + * rationale is that whatever is used to obtain the object we're increasing the + * reference count on will provide the ordering. For locked data structures, + * its the lock acquire, for RCU/lockless data structures its the dependent + * load. + * + * Do note that inc_not_zero() provides a control dependency which will order + * future stores against the inc, this ensures we'll never modify the object + * if we did not in fact acquire a reference. + * + * The decrements will provide release order, such that all the prior loads and + * stores will be issued before, it also provides a control dependency, which + * will order us against the subsequent free(). + * + * The control dependency is against the load of the cmpxchg (ll/sc) that + * succeeded. This means the stores aren't fully ordered, but this is fine + * because the 1->0 transition indicates no concurrency. + * + * Note that the allocator is responsible for ordering things between free() + * and alloc(). + * + */ + +#include <linux/atomic.h> +#include <linux/kernel.h> + +#ifdef NDEBUG +#define REFCOUNT_WARN(cond, str) (void)(cond) +#define __refcount_check +#else +#define REFCOUNT_WARN(cond, str) BUG_ON(cond) +#define __refcount_check __must_check +#endif + +typedef struct refcount_struct { + atomic_t refs; +} refcount_t; + +#define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } + +static inline void refcount_set(refcount_t *r, unsigned int n) +{ + atomic_set(&r->refs, n); +} + +static inline unsigned int refcount_read(const refcount_t *r) +{ + return atomic_read(&r->refs); +} + +/* + * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + */ +static inline __refcount_check +bool refcount_inc_not_zero(refcount_t *r) +{ + unsigned int old, new, val = atomic_read(&r->refs); + + for (;;) { + new = val + 1; + + if (!val) + return false; + + if (unlikely(!new)) + return true; + + old = atomic_cmpxchg_relaxed(&r->refs, val, new); + if (old == val) + break; + + val = old; + } + + REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); + + return true; +} + +/* + * Similar to atomic_inc(), will saturate at UINT_MAX and WARN. + * + * Provides no memory ordering, it is assumed the caller already has a + * reference on the object, will WARN when this is not so. + */ +static inline void refcount_inc(refcount_t *r) +{ + REFCOUNT_WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); +} + +/* + * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to + * decrement when saturated at UINT_MAX. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides a control dependency such that free() must come after. + * See the comment on top. + */ +static inline __refcount_check +bool refcount_sub_and_test(unsigned int i, refcount_t *r) +{ + unsigned int old, new, val = atomic_read(&r->refs); + + for (;;) { + if (unlikely(val == UINT_MAX)) + return false; + + new = val - i; + if (new > val) { + REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n"); + return false; + } + + old = atomic_cmpxchg_release(&r->refs, val, new); + if (old == val) + break; + + val = old; + } + + return !new; +} + +static inline __refcount_check +bool refcount_dec_and_test(refcount_t *r) +{ + return refcount_sub_and_test(1, r); +} + + +#endif /* _ATOMIC_LINUX_REFCOUNT_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index c66a485a24ac..bec0aad0e15c 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -344,7 +344,8 @@ struct perf_event_attr { use_clockid : 1, /* use @clockid for time fields */ context_switch : 1, /* context switch data */ write_backward : 1, /* Write ring buffer from end to beginning */ - __reserved_1 : 36; + namespaces : 1, /* include namespaces data */ + __reserved_1 : 35; union { __u32 wakeup_events; /* wakeup every n events */ @@ -610,6 +611,23 @@ struct perf_event_header { __u16 size; }; +struct perf_ns_link_info { + __u64 dev; + __u64 ino; +}; + +enum { + NET_NS_INDEX = 0, + UTS_NS_INDEX = 1, + IPC_NS_INDEX = 2, + PID_NS_INDEX = 3, + USER_NS_INDEX = 4, + MNT_NS_INDEX = 5, + CGROUP_NS_INDEX = 6, + + NR_NAMESPACES, /* number of available namespaces */ +}; + enum perf_event_type { /* @@ -862,6 +880,18 @@ enum perf_event_type { */ PERF_RECORD_SWITCH_CPU_WIDE = 15, + /* + * struct { + * struct perf_event_header header; + * u32 pid; + * u32 tid; + * u64 nr_namespaces; + * { u64 dev, inode; } [nr_namespaces]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_NAMESPACES = 16, + PERF_RECORD_MAX, /* non-ABI */ }; diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 3db3db9278be..643cc4ba6872 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -31,3 +31,5 @@ config.mak.autogen .config-detected util/intel-pt-decoder/inat-tables.c arch/*/include/generated/ +pmu-events/pmu-events.c +pmu-events/jevents diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index 2d96de6132a9..6e6a8b22c859 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -30,6 +30,24 @@ OPTIONS --verbose=:: Verbosity level. +-p:: +--pid=:: + Trace on existing process id (comma separated list). + +-a:: +--all-cpus:: + Force system-wide collection. Scripts run without a <command> + normally use -a by default, while scripts run with a <command> + normally don't - this option allows the latter to be run in + system-wide mode. + +-C:: +--cpu=:: + Only trace for the list of CPUs provided. Multiple CPUs can + be provided as a comma separated list with no space like: 0,1. + Ranges of CPUs are specified with -: 0-2. + Default is to trace on all online CPUs. + SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index b16003ec14a7..ea3789d05e5e 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -347,6 +347,9 @@ Enable weightened sampling. An additional weight is recorded per sample and can displayed with the weight and local_weight sort keys. This currently works for TSX abort events and some memory events in precise mode on modern Intel CPUs. +--namespaces:: +Record events of type PERF_RECORD_NAMESPACES. + --transaction:: Record transaction flags for transaction related events. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index c04cc0647c16..e9a61f5485eb 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -72,7 +72,8 @@ OPTIONS --sort=:: Sort histogram entries by given key(s) - multiple keys can be specified in CSV format. Following sort keys are available: - pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight. + pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, + local_weight, cgroup_id. Each key has following meaning: @@ -80,6 +81,7 @@ OPTIONS - pid: command and tid of the task - dso: name of library or module executed at the time of sample - symbol: name of function executed at the time of sample + - symbol_size: size of function executed at the time of sample - parent: name of function matched to the parent regex filter. Unmatched entries are displayed as "[other]". - cpu: cpu number the task ran at the time of sample @@ -91,6 +93,7 @@ OPTIONS - weight: Event specific weight, e.g. memory latency or transaction abort cost. This is the global weight. - local_weight: Local weight version of the weight above. + - cgroup_id: ID derived from cgroup namespace device and inode numbers. - transaction: Transaction abort flags. - overhead: Overhead percentage of sample - overhead_sys: Overhead percentage of sample running in system mode @@ -172,6 +175,9 @@ OPTIONS By default, every sort keys not specified in -F will be appended automatically. + If the keys starts with a prefix '+', then it will append the specified + field(s) to the default field order. For example: perf report -F +period,sample. + -p:: --parent=<regex>:: A regex filter to identify parent. The parent is a caller of this diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index d33deddb0146..a092a2499e8f 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -132,6 +132,10 @@ OPTIONS for 'perf sched timehist' --migrations:: Show migration events. +-n:: +--next:: + Show next task. + -I:: --idle-hist:: Show idle-related events only. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 4ed5f239ba7d..62c9b0c77a3a 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -248,6 +248,9 @@ OPTIONS --show-mmap-events Display mmap related events (e.g. MMAP, MMAP2). +--show-namespace-events + Display namespace events i.e. events of type PERF_RECORD_NAMESPACES. + --show-switch-events Display context switch events i.e. events of type PERF_RECORD_SWITCH or PERF_RECORD_SWITCH_CPU_WIDE. diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 8672f835ae4e..28648c09dcd6 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -12,6 +12,7 @@ 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 @@ -78,6 +79,7 @@ tools/include/uapi/linux/perf_event.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 diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 27c9fbca7bd9..2b656de99495 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -317,6 +317,10 @@ ifdef NO_DWARF NO_LIBDW_DWARF_UNWIND := 1 endif +ifeq ($(feature-sched_getcpu), 1) + CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT +endif + ifndef NO_LIBELF CFLAGS += -DHAVE_LIBELF_SUPPORT EXTLIBS += -lelf diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 1030a6e504bb..39dbe512b9fc 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -10,6 +10,7 @@ #include "symbol.h" #include "map.h" #include "probe-event.h" +#include "probe-file.h" #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) @@ -79,13 +80,18 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, * However, if the user specifies an offset, we fall back to using the * GEP since all userspace applications (objdump/readelf) show function * disassembly with offsets from the GEP. - * - * In addition, we shouldn't specify an offset for kretprobes. */ - if (pev->point.offset || (!pev->uprobes && pev->point.retprobe) || - !map || !sym) + if (pev->point.offset || !map || !sym) return; + /* For kretprobes, add an offset only if the kernel supports it */ + if (!pev->uprobes && pev->point.retprobe) { +#ifdef HAVE_LIBELF_SUPPORT + if (!kretprobe_offset_is_supported()) +#endif + return; + } + lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym); if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index da04b8c5568a..2499e1b0c6fb 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -9,6 +9,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <errno.h> diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 91877777ec6e..a20814d94af1 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -3,6 +3,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 2b9705a8734c..9fad1e4fcd3e 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -9,6 +9,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 2c8fa67ad537..40f5fcf1d120 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -8,6 +8,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index e246b1b8388a..789490281ae3 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -9,6 +9,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h index b2e06d1190d0..e44fd3239530 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -88,13 +88,11 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak #ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP #include <pthread.h> -static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr, - size_t cpusetsize, - cpu_set_t *cpuset) +#include <linux/compiler.h> +static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused, + size_t cpusetsize __maybe_unused, + cpu_set_t *cpuset __maybe_unused) { - attr = attr; - cpusetsize = cpusetsize; - cpuset = cpuset; return 0; } #endif diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 3083fc36282b..6bd0581de298 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -187,7 +187,8 @@ static const struct option options[] = { OPT_INCR ('d', "show_details" , &p0.show_details, "Show details"), OPT_INCR ('a', "all" , &p0.run_all, "Run all tests in the suite"), OPT_INTEGER('H', "thp" , &p0.thp, "MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"), - OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"), + OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details, " + "convergence is reached when each process (all its threads) is running on a single NUMA node."), OPT_BOOLEAN('m', "measure_convergence", &p0.measure_convergence, "measure convergence latency"), OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "quiet mode"), OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"), diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 4f52d85f5ebc..e54b1f9fe1ee 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -393,6 +393,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) .comm = perf_event__process_comm, .exit = perf_event__process_exit, .fork = perf_event__process_fork, + .namespaces = perf_event__process_namespaces, .ordered_events = true, .ordering_requires_timestamps = true, }, diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index e2b21723bbf8..5cd6d7a047b9 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2334,7 +2334,7 @@ out: static void perf_c2c_display(struct perf_session *session) { - if (c2c.use_stdio) + if (use_browser == 0) perf_c2c__hists_fprintf(stdout, session); else perf_c2c__hists_browse(&c2c.hists.hists); @@ -2536,7 +2536,7 @@ static int perf_c2c__report(int argc, const char **argv) OPT_BOOLEAN(0, "stdio", &c2c.use_stdio, "Use the stdio interface"), #endif OPT_BOOLEAN(0, "stats", &c2c.stats_only, - "Use the stdio interface"), + "Display only statistic tables (implies --stdio)"), OPT_BOOLEAN(0, "full-symbols", &c2c.symbol_full, "Display full length of symbols"), OPT_BOOLEAN(0, "no-source", &no_source, diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 1b96a3122228..5e4803158672 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -364,6 +364,7 @@ static struct perf_tool tool = { .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost, + .namespaces = perf_event__process_namespaces, .ordered_events = true, .ordering_requires_timestamps = true, }; diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index c3e643666c72..6087295f8827 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -11,11 +11,13 @@ #include <unistd.h> #include <signal.h> +#include <fcntl.h> #include "debug.h" #include <subcmd/parse-options.h> #include "evlist.h" #include "target.h" +#include "cpumap.h" #include "thread_map.h" #include "util/config.h" @@ -50,11 +52,12 @@ static void ftrace__workload_exec_failed_signal(int signo __maybe_unused, done = true; } -static int write_tracing_file(const char *name, const char *val) +static int __write_tracing_file(const char *name, const char *val, bool append) { char *file; int fd, ret = -1; ssize_t size = strlen(val); + int flags = O_WRONLY; file = get_tracing_file(name); if (!file) { @@ -62,7 +65,12 @@ static int write_tracing_file(const char *name, const char *val) return -1; } - fd = open(file, O_WRONLY); + if (append) + flags |= O_APPEND; + else + flags |= O_TRUNC; + + fd = open(file, flags); if (fd < 0) { pr_debug("cannot open tracing file: %s\n", name); goto out; @@ -79,6 +87,18 @@ out: return ret; } +static int write_tracing_file(const char *name, const char *val) +{ + return __write_tracing_file(name, val, false); +} + +static int append_tracing_file(const char *name, const char *val) +{ + return __write_tracing_file(name, val, true); +} + +static int reset_tracing_cpu(void); + static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused) { if (write_tracing_file("tracing_on", "0") < 0) @@ -90,14 +110,78 @@ static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused) if (write_tracing_file("set_ftrace_pid", " ") < 0) return -1; + if (reset_tracing_cpu() < 0) + return -1; + + return 0; +} + +static int set_tracing_pid(struct perf_ftrace *ftrace) +{ + int i; + char buf[16]; + + if (target__has_cpu(&ftrace->target)) + return 0; + + for (i = 0; i < thread_map__nr(ftrace->evlist->threads); i++) { + scnprintf(buf, sizeof(buf), "%d", + ftrace->evlist->threads->map[i]); + if (append_tracing_file("set_ftrace_pid", buf) < 0) + return -1; + } return 0; } +static int set_tracing_cpumask(struct cpu_map *cpumap) +{ + char *cpumask; + size_t mask_size; + int ret; + int last_cpu; + + last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1); + mask_size = (last_cpu + 3) / 4 + 1; + mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */ + + cpumask = malloc(mask_size); + if (cpumask == NULL) { + pr_debug("failed to allocate cpu mask\n"); + return -1; + } + + cpu_map__snprint_mask(cpumap, cpumask, mask_size); + + ret = write_tracing_file("tracing_cpumask", cpumask); + + free(cpumask); + return ret; +} + +static int set_tracing_cpu(struct perf_ftrace *ftrace) +{ + struct cpu_map *cpumap = ftrace->evlist->cpus; + + if (!target__has_cpu(&ftrace->target)) + return 0; + + return set_tracing_cpumask(cpumap); +} + +static int reset_tracing_cpu(void) +{ + struct cpu_map *cpumap = cpu_map__new(NULL); + int ret; + + ret = set_tracing_cpumask(cpumap); + cpu_map__put(cpumap); + return ret; +} + static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) { char *trace_file; int trace_fd; - char *trace_pid; char buf[4096]; struct pollfd pollfd = { .events = POLLIN, @@ -108,42 +192,43 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) return -1; } - if (argc < 1) - return -1; - signal(SIGINT, sig_handler); signal(SIGUSR1, sig_handler); signal(SIGCHLD, sig_handler); + signal(SIGPIPE, sig_handler); - reset_tracing_files(ftrace); + if (reset_tracing_files(ftrace) < 0) + goto out; /* reset ftrace buffer */ if (write_tracing_file("trace", "0") < 0) goto out; - if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target, - argv, false, ftrace__workload_exec_failed_signal) < 0) + if (argc && perf_evlist__prepare_workload(ftrace->evlist, + &ftrace->target, argv, false, + ftrace__workload_exec_failed_signal) < 0) { goto out; + } - if (write_tracing_file("current_tracer", ftrace->tracer) < 0) { - pr_err("failed to set current_tracer to %s\n", ftrace->tracer); - goto out; + if (set_tracing_pid(ftrace) < 0) { + pr_err("failed to set ftrace pid\n"); + goto out_reset; } - if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) { - pr_err("failed to allocate pid string\n"); - goto out; + if (set_tracing_cpu(ftrace) < 0) { + pr_err("failed to set tracing cpumask\n"); + goto out_reset; } - if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) { - pr_err("failed to set pid: %s\n", trace_pid); - goto out_free_pid; + if (write_tracing_file("current_tracer", ftrace->tracer) < 0) { + pr_err("failed to set current_tracer to %s\n", ftrace->tracer); + goto out_reset; } trace_file = get_tracing_file("trace_pipe"); if (!trace_file) { pr_err("failed to open trace_pipe\n"); - goto out_free_pid; + goto out_reset; } trace_fd = open(trace_file, O_RDONLY); @@ -152,7 +237,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) if (trace_fd < 0) { pr_err("failed to open trace_pipe\n"); - goto out_free_pid; + goto out_reset; } fcntl(trace_fd, F_SETFL, O_NONBLOCK); @@ -163,6 +248,8 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) goto out_close_fd; } + setup_pager(); + perf_evlist__start_workload(ftrace->evlist); while (!done) { @@ -191,11 +278,9 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) out_close_fd: close(trace_fd); -out_free_pid: - free(trace_pid); -out: +out_reset: reset_tracing_files(ftrace); - +out: return done ? 0 : -1; } @@ -227,15 +312,21 @@ int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused) .target = { .uid = UINT_MAX, }, }; const char * const ftrace_usage[] = { - "perf ftrace [<options>] <command>", + "perf ftrace [<options>] [<command>]", "perf ftrace [<options>] -- <command> [<options>]", NULL }; const struct option ftrace_options[] = { OPT_STRING('t', "tracer", &ftrace.tracer, "tracer", "tracer to use: function_graph(default) or function"), + OPT_STRING('p', "pid", &ftrace.target.pid, "pid", + "trace on existing process id"), OPT_INCR('v', "verbose", &verbose, "be more verbose"), + OPT_BOOLEAN('a', "all-cpus", &ftrace.target.system_wide, + "system-wide collection from all CPUs"), + OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu", + "list of cpus to monitor"), OPT_END() }; @@ -245,9 +336,18 @@ int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused) argc = parse_options(argc, argv, ftrace_options, ftrace_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc) + if (!argc && target__none(&ftrace.target)) usage_with_options(ftrace_usage, ftrace_options); + ret = target__validate(&ftrace.target); + if (ret) { + char errbuf[512]; + + target__strerror(&ftrace.target, ret, errbuf, 512); + pr_err("%s\n", errbuf); + return -EINVAL; + } + ftrace.evlist = perf_evlist__new(); if (ftrace.evlist == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index b9bc7e39833a..8d1d13b9bab6 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -333,6 +333,18 @@ static int perf_event__repipe_comm(struct perf_tool *tool, return err; } +static int perf_event__repipe_namespaces(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + int err = perf_event__process_namespaces(tool, event, sample, machine); + + perf_event__repipe(tool, event, sample, machine); + + return err; +} + static int perf_event__repipe_exit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -660,6 +672,7 @@ static int __cmd_inject(struct perf_inject *inject) session->itrace_synth_opts = &inject->itrace_synth_opts; inject->itrace_synth_opts.inject = true; inject->tool.comm = perf_event__repipe_comm; + inject->tool.namespaces = perf_event__repipe_namespaces; inject->tool.exit = perf_event__repipe_exit; inject->tool.id_index = perf_event__repipe_id_index; inject->tool.auxtrace_info = perf_event__process_auxtrace_info; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 6da8d083e4e5..d509e74bc6e8 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -964,6 +964,7 @@ static struct perf_tool perf_kmem = { .comm = perf_event__process_comm, .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }; diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 08fa88f62a24..18e6c38864bc 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1044,6 +1044,7 @@ static int read_events(struct perf_kvm_stat *kvm) struct perf_tool eops = { .sample = process_sample_event, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }; struct perf_data_file file = { @@ -1348,6 +1349,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, kvm->tool.exit = perf_event__process_exit; kvm->tool.fork = perf_event__process_fork; kvm->tool.lost = process_lost_event; + kvm->tool.namespaces = perf_event__process_namespaces; kvm->tool.ordered_events = true; perf_tool__fill_defaults(&kvm->tool); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index ce3bfb48b26f..d750ccaa978f 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -858,6 +858,7 @@ static int __cmd_report(bool display_info) struct perf_tool eops = { .sample = process_sample_event, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }; struct perf_data_file file = { diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 6114e07ca613..030a6cfdda59 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -342,6 +342,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) .lost = perf_event__process_lost, .fork = perf_event__process_fork, .build_id = perf_event__process_build_id, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }, .input_name = "perf.data", diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index bc84a375295d..04faef79a548 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -876,6 +876,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) signal(SIGTERM, sig_handler); signal(SIGSEGV, sigsegv_handler); + if (rec->opts.record_namespaces) + tool->namespace_events = true; + if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) { signal(SIGUSR2, snapshot_sig_handler); if (rec->opts.auxtrace_snapshot_mode) @@ -983,6 +986,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) */ if (forks) { union perf_event *event; + pid_t tgid; event = malloc(sizeof(event->comm) + machine->id_hdr_size); if (event == NULL) { @@ -996,10 +1000,30 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * cannot see a correct process name for those events. * Synthesize COMM event to prevent it. */ - perf_event__synthesize_comm(tool, event, - rec->evlist->workload.pid, - process_synthesized_event, - machine); + tgid = perf_event__synthesize_comm(tool, event, + rec->evlist->workload.pid, + process_synthesized_event, + machine); + free(event); + + if (tgid == -1) + goto out_child; + + event = malloc(sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (event == NULL) { + err = -ENOMEM; + goto out_child; + } + + /* + * Synthesize NAMESPACES event for the command specified. + */ + perf_event__synthesize_namespaces(tool, event, + rec->evlist->workload.pid, + tgid, process_synthesized_event, + machine); free(event); perf_evlist__start_workload(rec->evlist); @@ -1497,6 +1521,7 @@ static struct record record = { .fork = perf_event__process_fork, .exit = perf_event__process_exit, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, .ordered_events = true, @@ -1611,6 +1636,8 @@ static struct option __record_options[] = { "opts", "AUX area tracing Snapshot Mode", ""), OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout, "per thread proc mmap processing timeout in ms"), + OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces, + "Record namespaces events"), OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events, "Record context switch events"), OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel, diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 0a88670e56f3..5ab8117c3bfd 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -394,8 +394,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, fprintf(stdout, "\n\n"); } - if (sort_order == NULL && - parent_pattern == default_parent_pattern) + if (!quiet) fprintf(stdout, "#\n# (%s)\n#\n", help); if (rep->show_threads) { @@ -701,6 +700,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost, diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index b94cf0de715a..b92c4d97192c 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -221,6 +221,7 @@ struct perf_sched { unsigned int max_stack; bool show_cpu_visual; bool show_wakeups; + bool show_next; bool show_migrations; bool show_state; u64 skipped_samples; @@ -1897,14 +1898,18 @@ static char task_state_char(struct thread *thread, int state) } static void timehist_print_sample(struct perf_sched *sched, + struct perf_evsel *evsel, struct perf_sample *sample, struct addr_location *al, struct thread *thread, u64 t, int state) { struct thread_runtime *tr = thread__priv(thread); + const char *next_comm = perf_evsel__strval(evsel, sample, "next_comm"); + const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid"); u32 max_cpus = sched->max_cpu + 1; char tstr[64]; + char nstr[30]; u64 wait_time; timestamp__scnprintf_usec(t, tstr, sizeof(tstr)); @@ -1937,7 +1942,12 @@ static void timehist_print_sample(struct perf_sched *sched, if (sched->show_state) printf(" %5c ", task_state_char(thread, state)); - if (sched->show_wakeups) + if (sched->show_next) { + snprintf(nstr, sizeof(nstr), "next: %s[%d]", next_comm, next_pid); + printf(" %-*s", comm_width, nstr); + } + + if (sched->show_wakeups && !sched->show_next) printf(" %-*s", comm_width, ""); if (thread->tid == 0) @@ -2531,7 +2541,7 @@ static int timehist_sched_change_event(struct perf_tool *tool, } if (!sched->summary_only) - timehist_print_sample(sched, sample, &al, thread, t, state); + timehist_print_sample(sched, evsel, sample, &al, thread, t, state); out: if (sched->hist_time.start == 0 && t >= ptime->start) @@ -3272,6 +3282,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) .tool = { .sample = perf_sched__process_tracepoint_sample, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .lost = perf_event__process_lost, .fork = perf_sched__process_fork_event, .ordered_events = true, @@ -3340,6 +3351,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('S', "with-summary", &sched.summary, "Show all syscalls and summary with statistics"), OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"), + OPT_BOOLEAN('n', "next", &sched.show_next, "Show next task"), OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"), OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"), OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"), @@ -3437,10 +3449,14 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) if (argc) usage_with_options(timehist_usage, timehist_options); } - if (sched.show_wakeups && sched.summary_only) { - pr_err(" Error: -s and -w are mutually exclusive.\n"); + if ((sched.show_wakeups || sched.show_next) && + sched.summary_only) { + pr_err(" Error: -s and -[n|w] are mutually exclusive.\n"); parse_options_usage(timehist_usage, timehist_options, "s", true); - parse_options_usage(NULL, timehist_options, "w", true); + if (sched.show_wakeups) + parse_options_usage(NULL, timehist_options, "w", true); + if (sched.show_next) + parse_options_usage(NULL, timehist_options, "n", true); return -EINVAL; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index c0783b4f7b6c..66d62c98dff9 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -830,6 +830,7 @@ struct perf_script { bool show_task_events; bool show_mmap_events; bool show_switch_events; + bool show_namespace_events; bool allocated; struct cpu_map *cpus; struct thread_map *threads; @@ -1118,6 +1119,41 @@ out: return ret; } +static int process_namespaces_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct thread *thread; + struct perf_script *script = container_of(tool, struct perf_script, tool); + struct perf_session *session = script->session; + struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + int ret = -1; + + thread = machine__findnew_thread(machine, event->namespaces.pid, + event->namespaces.tid); + if (thread == NULL) { + pr_debug("problem processing NAMESPACES event, skipping it.\n"); + return -1; + } + + if (perf_event__process_namespaces(tool, event, sample, machine) < 0) + goto out; + + if (!evsel->attr.sample_id_all) { + sample->cpu = 0; + sample->time = 0; + sample->tid = event->namespaces.tid; + sample->pid = event->namespaces.pid; + } + print_sample_start(sample, thread, evsel); + perf_event__fprintf(event, stdout); + ret = 0; +out: + thread__put(thread); + return ret; +} + static int process_fork_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -1293,6 +1329,8 @@ static int __cmd_script(struct perf_script *script) } if (script->show_switch_events) script->tool.context_switch = process_switch_event; + if (script->show_namespace_events) + script->tool.namespaces = process_namespaces_event; ret = perf_session__process_events(script->session); @@ -2097,6 +2135,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .attr = process_attr, @@ -2180,6 +2219,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Show the mmap events"), OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events, "Show context switch events (if recorded)"), + OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events, + "Show namespace events (if recorded)"), OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), OPT_BOOLEAN(0, "ns", &nanosecs, "Use 9 decimal places when displaying time"), diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 13b54999ad79..f53f449d864d 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -146,6 +146,7 @@ static aggr_get_id_t aggr_get_id; static bool append_file; static const char *output_name; static int output_fd; +static int print_free_counters_hint; struct perf_stat { bool record; @@ -1109,6 +1110,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep); + if (counter->supported) + print_free_counters_hint = 1; + fprintf(stat_config.output, "%-*s%s", csv_output ? 0 : unit_width, counter->unit, csv_sep); @@ -1477,6 +1481,13 @@ static void print_footer(void) avg_stats(&walltime_nsecs_stats)); } fprintf(output, "\n\n"); + + if (print_free_counters_hint) + fprintf(output, +"Some events weren't counted. Try disabling the NMI watchdog:\n" +" echo 0 > /proc/sys/kernel/nmi_watchdog\n" +" perf stat ...\n" +" echo 1 > /proc/sys/kernel/nmi_watchdog\n"); } static void print_counters(struct timespec *ts, int argc, const char **argv) @@ -2339,6 +2350,35 @@ static int __cmd_report(int argc, const char **argv) return 0; } +static void setup_system_wide(int forks) +{ + /* + * Make system wide (-a) the default target if + * no target was specified and one of following + * conditions is met: + * + * - there's no workload specified + * - there is workload specified but all requested + * events are system wide events + */ + if (!target__none(&target)) + return; + + if (!forks) + target.system_wide = true; + else { + struct perf_evsel *counter; + + evlist__for_each_entry(evsel_list, counter) { + if (!counter->system_wide) + return; + } + + if (evsel_list->nr_entries) + target.system_wide = true; + } +} + int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) { const char * const stat_usage[] = { @@ -2445,9 +2485,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) } else if (big_num_opt == 0) /* User passed --no-big-num */ big_num = false; - /* Make system wide (-a) the default target. */ - if (!argc && target__none(&target)) - target.system_wide = true; + setup_system_wide(argc); if (run_count < 0) { pr_err("Run count must be a positive number\n"); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 256f1fac6f7e..912fedc5b42d 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2415,8 +2415,9 @@ static int trace__replay(struct trace *trace) trace->tool.exit = perf_event__process_exit; trace->tool.fork = perf_event__process_fork; trace->tool.attr = perf_event__process_attr; - trace->tool.tracing_data = perf_event__process_tracing_data; + trace->tool.tracing_data = perf_event__process_tracing_data; trace->tool.build_id = perf_event__process_build_id; + trace->tool.namespaces = perf_event__process_namespaces; trace->tool.ordered_events = true; trace->tool.ordering_requires_timestamps = true; diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index ac3efd396a72..2d0caf20ff3a 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -9,6 +9,7 @@ perf-buildid-cache mainporcelain common perf-buildid-list mainporcelain common perf-data mainporcelain common perf-diff mainporcelain common +perf-c2c mainporcelain common perf-config mainporcelain common perf-evlist mainporcelain common perf-ftrace mainporcelain common diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 1c27d947c2fe..806c216a1078 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -50,6 +50,7 @@ struct record_opts { bool running_time; bool full_auxtrace; bool auxtrace_snapshot_mode; + bool record_namespaces; bool record_switch_events; bool all_kernel; bool all_user; diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 12181bb1da2a..d1a12e584c1b 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -17,6 +17,7 @@ GenuineIntel-6-3A,v18,ivybridge,core GenuineIntel-6-3E,v19,ivytown,core GenuineIntel-6-2D,v20,jaketown,core GenuineIntel-6-57,v9,knightslanding,core +GenuineIntel-6-85,v9,knightslanding,core GenuineIntel-6-1E,v2,nehalemep,core GenuineIntel-6-1F,v2,nehalemep,core GenuineIntel-6-1A,v2,nehalemep,core diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index f168a85992d0..4478773cdb97 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -66,7 +66,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong nr", map->nr == 2); TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1); TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256); - TEST_ASSERT_VAL("wrong refcnt", atomic_read(&map->refcnt) == 1); + TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1); cpu_map__put(map); return 0; } diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index f2d2e542d0ee..a63d6945807b 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -29,7 +29,7 @@ int test__thread_map(int subtest __maybe_unused) thread_map__comm(map, 0) && !strcmp(thread_map__comm(map, 0), NAME)); TEST_ASSERT_VAL("wrong refcnt", - atomic_read(&map->refcnt) == 1); + refcount_read(&map->refcnt) == 1); thread_map__put(map); /* test dummy pid */ @@ -44,7 +44,7 @@ int test__thread_map(int subtest __maybe_unused) thread_map__comm(map, 0) && !strcmp(thread_map__comm(map, 0), "dummy")); TEST_ASSERT_VAL("wrong refcnt", - atomic_read(&map->refcnt) == 1); + refcount_read(&map->refcnt) == 1); thread_map__put(map); return 0; } @@ -71,7 +71,7 @@ static int process_event(struct perf_tool *tool __maybe_unused, thread_map__comm(threads, 0) && !strcmp(thread_map__comm(threads, 0), NAME)); TEST_ASSERT_VAL("wrong refcnt", - atomic_read(&threads->refcnt) == 1); + refcount_read(&threads->refcnt) == 1); thread_map__put(threads); return 0; } diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c index 188b63140fc8..76686dd6f5ec 100644 --- a/tools/perf/tests/thread-mg-share.c +++ b/tools/perf/tests/thread-mg-share.c @@ -43,7 +43,7 @@ int test__thread_mg_share(int subtest __maybe_unused) leader && t1 && t2 && t3 && other); mg = leader->mg; - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 4); /* test the map groups pointer is shared */ TEST_ASSERT_VAL("map groups don't match", mg == t1->mg); @@ -71,25 +71,25 @@ int test__thread_mg_share(int subtest __maybe_unused) machine__remove_thread(machine, other_leader); other_mg = other->mg; - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 2); TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg); /* release thread group */ thread__put(leader); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 3); thread__put(t1); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 2); thread__put(t2); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 1); thread__put(t3); /* release other group */ thread__put(other_leader); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 1); thread__put(other); diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index fc4fb669ceee..2dc82bec10c0 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2308,7 +2308,7 @@ static int switch_data_file(void) return ret; memset(options, 0, sizeof(options)); - memset(options, 0, sizeof(abs_path)); + memset(abs_path, 0, sizeof(abs_path)); while ((dent = readdir(pwd_dir))) { char path[PATH_MAX]; diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 5da376bc1afc..2ea5ee179a3b 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -42,6 +42,7 @@ libperf-y += pstack.o libperf-y += session.o libperf-$(CONFIG_AUDIT) += syscalltbl.o libperf-y += ordered-events.o +libperf-y += namespaces.o libperf-y += comm.o libperf-y += thread.o libperf-y += thread_map.o diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index eafbf11442b2..86399eda3684 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -127,19 +127,19 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) goto found; n++; } - if (atomic_read(&cgrp->refcnt) == 0) + if (refcount_read(&cgrp->refcnt) == 0) free(cgrp); return -1; found: - atomic_inc(&cgrp->refcnt); + refcount_inc(&cgrp->refcnt); counter->cgrp = cgrp; return 0; } void close_cgroup(struct cgroup_sel *cgrp) { - if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) { + if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) { close(cgrp->fd); zfree(&cgrp->name); free(cgrp); diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index 31f8dcdbd7ef..d91966b97cbd 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -1,14 +1,14 @@ #ifndef __CGROUP_H__ #define __CGROUP_H__ -#include <linux/atomic.h> +#include <linux/refcount.h> struct option; struct cgroup_sel { char *name; int fd; - atomic_t refcnt; + refcount_t refcnt; }; diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h index d0d465953d36..94a5a7d829d5 100644 --- a/tools/perf/util/cloexec.h +++ b/tools/perf/util/cloexec.h @@ -3,10 +3,4 @@ unsigned long perf_event_open_cloexec_flag(void); -#ifdef __GLIBC_PREREQ -#if !__GLIBC_PREREQ(2, 6) && !defined(__UCLIBC__) -int sched_getcpu(void) __THROW; -#endif -#endif - #endif /* __PERF_CLOEXEC_H */ diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 21b7ff382c3f..32837b6f7879 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -2,12 +2,12 @@ #include "util.h" #include <stdlib.h> #include <stdio.h> -#include <linux/atomic.h> +#include <linux/refcount.h> struct comm_str { char *str; struct rb_node rb_node; - atomic_t refcnt; + refcount_t refcnt; }; /* Should perhaps be moved to struct machine */ @@ -16,13 +16,13 @@ static struct rb_root comm_str_root; static struct comm_str *comm_str__get(struct comm_str *cs) { if (cs) - atomic_inc(&cs->refcnt); + refcount_inc(&cs->refcnt); return cs; } static void comm_str__put(struct comm_str *cs) { - if (cs && atomic_dec_and_test(&cs->refcnt)) { + if (cs && refcount_dec_and_test(&cs->refcnt)) { rb_erase(&cs->rb_node, &comm_str_root); zfree(&cs->str); free(cs); @@ -43,7 +43,7 @@ static struct comm_str *comm_str__alloc(const char *str) return NULL; } - atomic_set(&cs->refcnt, 0); + refcount_set(&cs->refcnt, 1); return cs; } @@ -61,7 +61,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) cmp = strcmp(str, iter->str); if (!cmp) - return iter; + return comm_str__get(iter); if (cmp < 0) p = &(*p)->rb_left; @@ -95,8 +95,6 @@ struct comm *comm__new(const char *str, u64 timestamp, bool exec) return NULL; } - comm_str__get(comm->comm_str); - return comm; } @@ -108,7 +106,6 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec) if (!new) return -ENOMEM; - comm_str__get(new); comm_str__put(old); comm->comm_str = new; comm->start = timestamp; diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 8c7504939113..061018b42393 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -29,7 +29,7 @@ static struct cpu_map *cpu_map__default_new(void) cpus->map[i] = i; cpus->nr = nr_cpus; - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -43,7 +43,7 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) if (cpus != NULL) { cpus->nr = nr_cpus; memcpy(cpus->map, tmp_cpus, payload_size); - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -252,7 +252,7 @@ struct cpu_map *cpu_map__dummy_new(void) if (cpus != NULL) { cpus->nr = 1; cpus->map[0] = -1; - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -269,7 +269,7 @@ struct cpu_map *cpu_map__empty_new(int nr) for (i = 0; i < nr; i++) cpus->map[i] = -1; - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -278,7 +278,7 @@ struct cpu_map *cpu_map__empty_new(int nr) static void cpu_map__delete(struct cpu_map *map) { if (map) { - WARN_ONCE(atomic_read(&map->refcnt) != 0, + WARN_ONCE(refcount_read(&map->refcnt) != 0, "cpu_map refcnt unbalanced\n"); free(map); } @@ -287,13 +287,13 @@ static void cpu_map__delete(struct cpu_map *map) struct cpu_map *cpu_map__get(struct cpu_map *map) { if (map) - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); return map; } void cpu_map__put(struct cpu_map *map) { - if (map && atomic_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(&map->refcnt)) cpu_map__delete(map); } @@ -357,7 +357,7 @@ int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, /* ensure we process id in increasing order */ qsort(c->map, c->nr, sizeof(int), cmp_ids); - atomic_set(&c->refcnt, 1); + refcount_set(&c->refcnt, 1); *res = c; return 0; } @@ -673,3 +673,49 @@ size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size) pr_debug("cpumask list: %s\n", buf); return ret; } + +static char hex_char(unsigned char val) +{ + if (val < 10) + return val + '0'; + if (val < 16) + return val - 10 + 'a'; + return '?'; +} + +size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) +{ + int i, cpu; + char *ptr = buf; + unsigned char *bitmap; + int last_cpu = cpu_map__cpu(map, map->nr - 1); + + bitmap = zalloc((last_cpu + 7) / 8); + if (bitmap == NULL) { + buf[0] = '\0'; + return 0; + } + + for (i = 0; i < map->nr; i++) { + cpu = cpu_map__cpu(map, i); + bitmap[cpu / 8] |= 1 << (cpu % 8); + } + + for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) { + unsigned char bits = bitmap[cpu / 8]; + + if (cpu % 8) + bits >>= 4; + else + bits &= 0xf; + + *ptr++ = hex_char(bits); + if ((cpu % 32) == 0 && cpu > 0) + *ptr++ = ','; + } + *ptr = '\0'; + free(bitmap); + + buf[size - 1] = '\0'; + return ptr - buf; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 1a0549af8f5c..6b8bff87481d 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -3,13 +3,13 @@ #include <stdio.h> #include <stdbool.h> -#include <linux/atomic.h> +#include <linux/refcount.h> #include "perf.h" #include "util/debug.h" struct cpu_map { - atomic_t refcnt; + refcount_t refcnt; int nr; int map[]; }; @@ -20,6 +20,7 @@ struct cpu_map *cpu_map__dummy_new(void); struct cpu_map *cpu_map__new_data(struct cpu_map_data *data); struct cpu_map *cpu_map__read(FILE *file); size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size); +size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size); size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); int cpu_map__get_socket_id(int cpu); int cpu_map__get_socket(struct cpu_map *map, int idx, void *data); diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 4e6cbc99f08e..89ece2445713 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -1468,6 +1468,7 @@ int bt_convert__perf2ctf(const char *input, const char *path, .lost = perf_event__process_lost, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, + .namespaces = perf_event__process_namespaces, .ordered_events = true, .ordering_requires_timestamps = true, }, diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index d38b62a700ca..42db00d78573 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1109,7 +1109,7 @@ struct dso *dso__new(const char *name) INIT_LIST_HEAD(&dso->node); INIT_LIST_HEAD(&dso->data.open_entry); pthread_mutex_init(&dso->lock, NULL); - atomic_set(&dso->refcnt, 1); + refcount_set(&dso->refcnt, 1); } return dso; @@ -1147,13 +1147,13 @@ void dso__delete(struct dso *dso) struct dso *dso__get(struct dso *dso) { if (dso) - atomic_inc(&dso->refcnt); + refcount_inc(&dso->refcnt); return dso; } void dso__put(struct dso *dso) { - if (dso && atomic_dec_and_test(&dso->refcnt)) + if (dso && refcount_dec_and_test(&dso->refcnt)) dso__delete(dso); } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index ecc4bbd3f82e..12350b171727 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -1,7 +1,7 @@ #ifndef __PERF_DSO #define __PERF_DSO -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/types.h> #include <linux/rbtree.h> #include <sys/types.h> @@ -187,7 +187,7 @@ struct dso { void *priv; u64 db_id; }; - atomic_t refcnt; + refcount_t refcnt; char name[0]; }; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 4ea7ce72ed9c..d082cb70445d 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -31,6 +31,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_LOST_SAMPLES] = "LOST_SAMPLES", [PERF_RECORD_SWITCH] = "SWITCH", [PERF_RECORD_SWITCH_CPU_WIDE] = "SWITCH_CPU_WIDE", + [PERF_RECORD_NAMESPACES] = "NAMESPACES", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", @@ -49,6 +50,16 @@ static const char *perf_event__names[] = { [PERF_RECORD_TIME_CONV] = "TIME_CONV", }; +static const char *perf_ns__names[] = { + [NET_NS_INDEX] = "net", + [UTS_NS_INDEX] = "uts", + [IPC_NS_INDEX] = "ipc", + [PID_NS_INDEX] = "pid", + [USER_NS_INDEX] = "user", + [MNT_NS_INDEX] = "mnt", + [CGROUP_NS_INDEX] = "cgroup", +}; + const char *perf_event__name(unsigned int id) { if (id >= ARRAY_SIZE(perf_event__names)) @@ -58,6 +69,13 @@ const char *perf_event__name(unsigned int id) return perf_event__names[id]; } +static const char *perf_ns__name(unsigned int id) +{ + if (id >= ARRAY_SIZE(perf_ns__names)) + return "UNKNOWN"; + return perf_ns__names[id]; +} + static int perf_tool__process_synth_event(struct perf_tool *tool, union perf_event *event, struct machine *machine, @@ -203,6 +221,58 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool, return tgid; } +static void perf_event__get_ns_link_info(pid_t pid, const char *ns, + struct perf_ns_link_info *ns_link_info) +{ + struct stat64 st; + char proc_ns[128]; + + sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns); + if (stat64(proc_ns, &st) == 0) { + ns_link_info->dev = st.st_dev; + ns_link_info->ino = st.st_ino; + } +} + +int perf_event__synthesize_namespaces(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine) +{ + u32 idx; + struct perf_ns_link_info *ns_link_info; + + if (!tool || !tool->namespace_events) + return 0; + + memset(&event->namespaces, 0, (sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size)); + + event->namespaces.pid = tgid; + event->namespaces.tid = pid; + + event->namespaces.nr_namespaces = NR_NAMESPACES; + + ns_link_info = event->namespaces.link_info; + + for (idx = 0; idx < event->namespaces.nr_namespaces; idx++) + perf_event__get_ns_link_info(pid, perf_ns__name(idx), + &ns_link_info[idx]); + + event->namespaces.header.type = PERF_RECORD_NAMESPACES; + + event->namespaces.header.size = (sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) + return -1; + + return 0; +} + static int perf_event__synthesize_fork(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, pid_t ppid, @@ -434,8 +504,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool, static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *mmap_event, union perf_event *fork_event, + union perf_event *namespaces_event, pid_t pid, int full, - perf_event__handler_t process, + perf_event__handler_t process, struct perf_tool *tool, struct machine *machine, bool mmap_data, @@ -455,6 +526,11 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (tgid == -1) return -1; + if (perf_event__synthesize_namespaces(tool, namespaces_event, pid, + tgid, process, machine) < 0) + return -1; + + return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data, proc_map_timeout); @@ -488,6 +564,11 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, ppid, process, machine) < 0) break; + + if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid, + tgid, process, machine) < 0) + break; + /* * Send the prepared comm event */ @@ -516,6 +597,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, unsigned int proc_map_timeout) { union perf_event *comm_event, *mmap_event, *fork_event; + union perf_event *namespaces_event; int err = -1, thread, j; comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); @@ -530,10 +612,16 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, if (fork_event == NULL) goto out_free_mmap; + namespaces_event = malloc(sizeof(namespaces_event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (namespaces_event == NULL) + goto out_free_fork; + err = 0; for (thread = 0; thread < threads->nr; ++thread) { if (__event__synthesize_thread(comm_event, mmap_event, - fork_event, + fork_event, namespaces_event, thread_map__pid(threads, thread), 0, process, tool, machine, mmap_data, proc_map_timeout)) { @@ -559,7 +647,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, /* if not, generate events for it */ if (need_leader && __event__synthesize_thread(comm_event, mmap_event, - fork_event, + fork_event, namespaces_event, comm_event->comm.pid, 0, process, tool, machine, mmap_data, proc_map_timeout)) { @@ -568,6 +656,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, } } } + free(namespaces_event); +out_free_fork: free(fork_event); out_free_mmap: free(mmap_event); @@ -587,6 +677,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, char proc_path[PATH_MAX]; struct dirent *dirent; union perf_event *comm_event, *mmap_event, *fork_event; + union perf_event *namespaces_event; int err = -1; if (machine__is_default_guest(machine)) @@ -604,11 +695,17 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (fork_event == NULL) goto out_free_mmap; + namespaces_event = malloc(sizeof(namespaces_event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (namespaces_event == NULL) + goto out_free_fork; + snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); proc = opendir(proc_path); if (proc == NULL) - goto out_free_fork; + goto out_free_namespaces; while ((dirent = readdir(proc)) != NULL) { char *end; @@ -620,13 +717,16 @@ int perf_event__synthesize_threads(struct perf_tool *tool, * 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, pid, - 1, process, tool, machine, mmap_data, + __event__synthesize_thread(comm_event, mmap_event, fork_event, + namespaces_event, pid, 1, process, + tool, machine, mmap_data, proc_map_timeout); } err = 0; closedir(proc); +out_free_namespaces: + free(namespaces_event); out_free_fork: free(fork_event); out_free_mmap: @@ -1008,6 +1108,33 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid); } +size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp) +{ + size_t ret = 0; + struct perf_ns_link_info *ns_link_info; + u32 nr_namespaces, idx; + + ns_link_info = event->namespaces.link_info; + nr_namespaces = event->namespaces.nr_namespaces; + + ret += fprintf(fp, " %d/%d - nr_namespaces: %u\n\t\t[", + event->namespaces.pid, + event->namespaces.tid, + nr_namespaces); + + for (idx = 0; idx < nr_namespaces; idx++) { + if (idx && (idx % 4 == 0)) + ret += fprintf(fp, "\n\t\t "); + + ret += fprintf(fp, "%u/%s: %" PRIu64 "/%#" PRIx64 "%s", idx, + perf_ns__name(idx), (u64)ns_link_info[idx].dev, + (u64)ns_link_info[idx].ino, + ((idx + 1) != nr_namespaces) ? ", " : "]\n"); + } + + return ret; +} + int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -1016,6 +1143,14 @@ int perf_event__process_comm(struct perf_tool *tool __maybe_unused, return machine__process_comm_event(machine, event, sample); } +int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_namespaces_event(machine, event, sample); +} + int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -1196,6 +1331,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) case PERF_RECORD_MMAP: ret += perf_event__fprintf_mmap(event, fp); break; + case PERF_RECORD_NAMESPACES: + ret += perf_event__fprintf_namespaces(event, fp); + break; case PERF_RECORD_MMAP2: ret += perf_event__fprintf_mmap2(event, fp); break; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index c735c53a26f8..e1d8166ebbd5 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -39,6 +39,13 @@ struct comm_event { char comm[16]; }; +struct namespaces_event { + struct perf_event_header header; + u32 pid, tid; + u64 nr_namespaces; + struct perf_ns_link_info link_info[]; +}; + struct fork_event { struct perf_event_header header; u32 pid, ppid; @@ -485,6 +492,7 @@ union perf_event { struct mmap_event mmap; struct mmap2_event mmap2; struct comm_event comm; + struct namespaces_event namespaces; struct fork_event fork; struct lost_event lost; struct lost_samples_event lost_samples; @@ -587,6 +595,10 @@ int perf_event__process_switch(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_namespaces(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -636,6 +648,12 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_namespaces(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine); + int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, @@ -653,6 +671,7 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp); size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp); size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); u64 kallsyms__get_function_start(const char *kallsyms_filename, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index b601f2814a30..50420cd35446 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -777,7 +777,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messu /* * Check if event was unmapped due to a POLLHUP/POLLERR. */ - if (!atomic_read(&md->refcnt)) + if (!refcount_read(&md->refcnt)) return NULL; head = perf_mmap__read_head(md); @@ -794,7 +794,7 @@ perf_mmap__read_backward(struct perf_mmap *md) /* * Check if event was unmapped due to a POLLHUP/POLLERR. */ - if (!atomic_read(&md->refcnt)) + if (!refcount_read(&md->refcnt)) return NULL; head = perf_mmap__read_head(md); @@ -856,7 +856,7 @@ void perf_mmap__read_catchup(struct perf_mmap *md) { u64 head; - if (!atomic_read(&md->refcnt)) + if (!refcount_read(&md->refcnt)) return; head = perf_mmap__read_head(md); @@ -875,14 +875,14 @@ static bool perf_mmap__empty(struct perf_mmap *md) static void perf_mmap__get(struct perf_mmap *map) { - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); } static void perf_mmap__put(struct perf_mmap *md) { - BUG_ON(md->base && atomic_read(&md->refcnt) == 0); + BUG_ON(md->base && refcount_read(&md->refcnt) == 0); - if (atomic_dec_and_test(&md->refcnt)) + if (refcount_dec_and_test(&md->refcnt)) perf_mmap__munmap(md); } @@ -894,7 +894,7 @@ void perf_mmap__consume(struct perf_mmap *md, bool overwrite) perf_mmap__write_tail(md, old); } - if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md)) + if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md)) perf_mmap__put(md); } @@ -937,7 +937,7 @@ static void perf_mmap__munmap(struct perf_mmap *map) munmap(map->base, perf_mmap__mmap_len(map)); map->base = NULL; map->fd = -1; - atomic_set(&map->refcnt, 0); + refcount_set(&map->refcnt, 0); } auxtrace_mmap__munmap(&map->auxtrace_mmap); } @@ -974,8 +974,19 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist) if (!map) return NULL; - for (i = 0; i < evlist->nr_mmaps; i++) + for (i = 0; i < evlist->nr_mmaps; i++) { map[i].fd = -1; + /* + * When the perf_mmap() call is made we grab one refcount, plus + * one extra to let perf_evlist__mmap_consume() get the last + * events after all real references (perf_mmap__get()) are + * dropped. + * + * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and + * thus does perf_mmap__get() on it. + */ + refcount_set(&map[i].refcnt, 0); + } return map; } @@ -1001,7 +1012,7 @@ static int perf_mmap__mmap(struct perf_mmap *map, * evlist layer can't just drop it when filtering events in * perf_evlist__filter_pollfd(). */ - atomic_set(&map->refcnt, 2); + refcount_set(&map->refcnt, 2); map->prev = 0; map->mask = mp->mask; map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 389b9ccdf8c7..39942995f537 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -1,7 +1,7 @@ #ifndef __PERF_EVLIST_H #define __PERF_EVLIST_H 1 -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/list.h> #include <api/fd/array.h> #include <stdio.h> @@ -29,7 +29,7 @@ struct perf_mmap { void *base; int mask; int fd; - atomic_t refcnt; + refcount_t refcnt; u64 prev; struct auxtrace_mmap auxtrace_mmap; char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8))); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ac59710b79e0..175dc2305aa8 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -932,6 +932,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; + if (opts->record_namespaces) + attr->namespaces = track; + if (opts->record_switch_events) attr->context_switch = track; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index eaf72a938fb4..e3b38f629504 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -3,6 +3,7 @@ #include "hist.h" #include "map.h" #include "session.h" +#include "namespaces.h" #include "sort.h" #include "evlist.h" #include "evsel.h" @@ -169,6 +170,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO); } + hists__new_col_len(hists, HISTC_CGROUP_ID, 20); hists__new_col_len(hists, HISTC_CPU, 3); hists__new_col_len(hists, HISTC_SOCKET, 6); hists__new_col_len(hists, HISTC_MEM_LOCKED, 6); @@ -574,9 +576,14 @@ __hists__add_entry(struct hists *hists, bool sample_self, struct hist_entry_ops *ops) { + struct namespaces *ns = thread__namespaces(al->thread); struct hist_entry entry = { .thread = al->thread, .comm = thread__comm(al->thread), + .cgroup_id = { + .dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0, + .ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0, + }, .ms = { .map = al->map, .sym = al->sym, diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 28c216e3d5b7..ee3670a388df 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -30,6 +30,7 @@ enum hist_column { HISTC_DSO, HISTC_THREAD, HISTC_COMM, + HISTC_CGROUP_ID, HISTC_PARENT, HISTC_CPU, HISTC_SOCKET, @@ -57,6 +58,7 @@ enum hist_column { HISTC_SRCLINE_FROM, HISTC_SRCLINE_TO, HISTC_TRACE, + HISTC_SYM_SIZE, HISTC_NR_COLS, /* Last entry */ }; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 4f3c758d875d..459352a9978f 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -39,6 +39,8 @@ static void intel_pt_insn_decoder(struct insn *insn, enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH; int ext; + intel_pt_insn->rel = 0; + if (insn_is_avx(insn)) { intel_pt_insn->op = INTEL_PT_OP_OTHER; intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 71c9720d4973..dfc600446586 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -13,6 +13,7 @@ #include <symbol/kallsyms.h> #include "unwind.h" #include "linux/hash.h" +#include "asm/bug.h" static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock); @@ -501,6 +502,37 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event return err; } +int machine__process_namespaces_event(struct machine *machine __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused) +{ + struct thread *thread = machine__findnew_thread(machine, + event->namespaces.pid, + event->namespaces.tid); + int err = 0; + + WARN_ONCE(event->namespaces.nr_namespaces > NR_NAMESPACES, + "\nWARNING: kernel seems to support more namespaces than perf" + " tool.\nTry updating the perf tool..\n\n"); + + WARN_ONCE(event->namespaces.nr_namespaces < NR_NAMESPACES, + "\nWARNING: perf tool seems to support more namespaces than" + " the kernel.\nTry updating the kernel..\n\n"); + + if (dump_trace) + perf_event__fprintf_namespaces(event, stdout); + + if (thread == NULL || + thread__set_namespaces(thread, sample->time, &event->namespaces)) { + dump_printf("problem processing PERF_RECORD_NAMESPACES, skipping event.\n"); + err = -1; + } + + thread__put(thread); + + return err; +} + int machine__process_lost_event(struct machine *machine __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused) { @@ -1439,7 +1471,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th, if (machine->last_match == th) machine->last_match = NULL; - BUG_ON(atomic_read(&th->refcnt) == 0); + BUG_ON(refcount_read(&th->refcnt) == 0); if (lock) pthread_rwlock_wrlock(&machine->threads_lock); rb_erase_init(&th->rb_node, &machine->threads); @@ -1538,6 +1570,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, ret = machine__process_comm_event(machine, event, sample); break; case PERF_RECORD_MMAP: ret = machine__process_mmap_event(machine, event, sample); break; + case PERF_RECORD_NAMESPACES: + ret = machine__process_namespaces_event(machine, event, sample); break; case PERF_RECORD_MMAP2: ret = machine__process_mmap2_event(machine, event, sample); break; case PERF_RECORD_FORK: diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index a28305029711..3cdb1340f917 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -97,6 +97,9 @@ int machine__process_itrace_start_event(struct machine *machine, union perf_event *event); int machine__process_switch_event(struct machine *machine, union perf_event *event); +int machine__process_namespaces_event(struct machine *machine, + union perf_event *event, + struct perf_sample *sample); int machine__process_mmap_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); int machine__process_mmap2_event(struct machine *machine, union perf_event *event, diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 0a943e7b1ea7..1d9ebcf9e38e 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -141,7 +141,7 @@ void map__init(struct map *map, enum map_type type, RB_CLEAR_NODE(&map->rb_node); map->groups = NULL; map->erange_warned = false; - atomic_set(&map->refcnt, 1); + refcount_set(&map->refcnt, 1); } struct map *map__new(struct machine *machine, u64 start, u64 len, @@ -255,7 +255,7 @@ void map__delete(struct map *map) void map__put(struct map *map) { - if (map && atomic_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(&map->refcnt)) map__delete(map); } @@ -354,7 +354,7 @@ struct map *map__clone(struct map *from) struct map *map = memdup(from, sizeof(*map)); if (map != NULL) { - atomic_set(&map->refcnt, 1); + refcount_set(&map->refcnt, 1); RB_CLEAR_NODE(&map->rb_node); dso__get(map->dso); map->groups = NULL; @@ -485,7 +485,7 @@ void map_groups__init(struct map_groups *mg, struct machine *machine) maps__init(&mg->maps[i]); } mg->machine = machine; - atomic_set(&mg->refcnt, 1); + refcount_set(&mg->refcnt, 1); } static void __maps__purge(struct maps *maps) @@ -547,7 +547,7 @@ void map_groups__delete(struct map_groups *mg) void map_groups__put(struct map_groups *mg) { - if (mg && atomic_dec_and_test(&mg->refcnt)) + if (mg && refcount_dec_and_test(&mg->refcnt)) map_groups__delete(mg); } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index abdacf800c98..c8a5a644c0a9 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -1,7 +1,7 @@ #ifndef __PERF_MAP_H #define __PERF_MAP_H -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/compiler.h> #include <linux/list.h> #include <linux/rbtree.h> @@ -51,7 +51,7 @@ struct map { struct dso *dso; struct map_groups *groups; - atomic_t refcnt; + refcount_t refcnt; }; struct kmap { @@ -67,7 +67,7 @@ struct maps { struct map_groups { struct maps maps[MAP__NR_TYPES]; struct machine *machine; - atomic_t refcnt; + refcount_t refcnt; }; struct map_groups *map_groups__new(struct machine *machine); @@ -77,7 +77,7 @@ bool map_groups__empty(struct map_groups *mg); static inline struct map_groups *map_groups__get(struct map_groups *mg) { if (mg) - atomic_inc(&mg->refcnt); + refcount_inc(&mg->refcnt); return mg; } @@ -150,7 +150,7 @@ struct map *map__clone(struct map *map); static inline struct map *map__get(struct map *map) { if (map) - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); return map; } diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c new file mode 100644 index 000000000000..2de8da64d90c --- /dev/null +++ b/tools/perf/util/namespaces.c @@ -0,0 +1,36 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * Copyright (C) 2017 Hari Bathini, IBM Corporation + */ + +#include "namespaces.h" +#include "util.h" +#include "event.h" +#include <stdlib.h> +#include <stdio.h> + +struct namespaces *namespaces__new(struct namespaces_event *event) +{ + struct namespaces *namespaces; + u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) * + sizeof(struct perf_ns_link_info)); + + namespaces = zalloc(sizeof(struct namespaces) + link_info_size); + if (!namespaces) + return NULL; + + namespaces->end_time = -1; + + if (event) + memcpy(namespaces->link_info, event->link_info, link_info_size); + + return namespaces; +} + +void namespaces__free(struct namespaces *namespaces) +{ + free(namespaces); +} diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h new file mode 100644 index 000000000000..468f1e9a1484 --- /dev/null +++ b/tools/perf/util/namespaces.h @@ -0,0 +1,26 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * Copyright (C) 2017 Hari Bathini, IBM Corporation + */ + +#ifndef __PERF_NAMESPACES_H +#define __PERF_NAMESPACES_H + +#include "../perf.h" +#include <linux/list.h> + +struct namespaces_event; + +struct namespaces { + struct list_head list; + u64 end_time; + struct perf_ns_link_info link_info[]; +}; + +struct namespaces *namespaces__new(struct namespaces_event *event); +void namespaces__free(struct namespaces *namespaces); + +#endif /* __PERF_NAMESPACES_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 67a8aebc67ab..54355d3caf09 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -316,8 +316,9 @@ __add_event(struct list_head *list, int *idx, return NULL; (*idx)++; - evsel->cpus = cpu_map__get(cpus); - evsel->own_cpus = cpu_map__get(cpus); + evsel->cpus = cpu_map__get(cpus); + evsel->own_cpus = cpu_map__get(cpus); + evsel->system_wide = !!cpus; if (name) evsel->name = strdup(name); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 28fb62c32678..c9bdc9ded0c3 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -757,7 +757,9 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, } for (i = 0; i < ntevs; i++) { - if (!tevs[i].point.address || tevs[i].point.retprobe) + if (!tevs[i].point.address) + continue; + if (tevs[i].point.retprobe && !kretprobe_offset_is_supported()) continue; /* If we found a wrong one, mark it by NULL symbol */ if (kprobe_warn_out_range(tevs[i].point.symbol, @@ -1528,11 +1530,6 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) return -EINVAL; } - if (pp->retprobe && !pp->function) { - semantic_error("Return probe requires an entry function.\n"); - return -EINVAL; - } - if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) { semantic_error("Offset/Line/Lazy pattern can't be used with " "return probe.\n"); @@ -2841,7 +2838,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } /* Note that the symbols in the kmodule are not relocated */ - if (!pev->uprobes && !pp->retprobe && !pev->target) { + if (!pev->uprobes && !pev->target && + (!pp->retprobe || kretprobe_offset_is_supported())) { reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 436b64731f65..1542cd0d6799 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -70,7 +70,7 @@ static void print_both_open_warning(int kerr, int uerr) } } -static int open_probe_events(const char *trace_file, bool readwrite) +int open_trace_file(const char *trace_file, bool readwrite) { char buf[PATH_MAX]; int ret; @@ -92,12 +92,12 @@ static int open_probe_events(const char *trace_file, bool readwrite) static int open_kprobe_events(bool readwrite) { - return open_probe_events("kprobe_events", readwrite); + return open_trace_file("kprobe_events", readwrite); } static int open_uprobe_events(bool readwrite) { - return open_probe_events("uprobe_events", readwrite); + return open_trace_file("uprobe_events", readwrite); } int probe_file__open(int flag) @@ -877,59 +877,72 @@ int probe_cache__show_all_caches(struct strfilter *filter) return 0; } +enum ftrace_readme { + FTRACE_README_PROBE_TYPE_X = 0, + FTRACE_README_KRETPROBE_OFFSET, + FTRACE_README_END, +}; + static struct { const char *pattern; - bool avail; - bool checked; -} probe_type_table[] = { -#define DEFINE_TYPE(idx, pat, def_avail) \ - [idx] = {.pattern = pat, .avail = (def_avail)} - DEFINE_TYPE(PROBE_TYPE_U, "* u8/16/32/64,*", true), - DEFINE_TYPE(PROBE_TYPE_S, "* s8/16/32/64,*", true), - DEFINE_TYPE(PROBE_TYPE_X, "* x8/16/32/64,*", false), - DEFINE_TYPE(PROBE_TYPE_STRING, "* string,*", true), - DEFINE_TYPE(PROBE_TYPE_BITFIELD, - "* b<bit-width>@<bit-offset>/<container-size>", true), + bool avail; +} ftrace_readme_table[] = { +#define DEFINE_TYPE(idx, pat) \ + [idx] = {.pattern = pat, .avail = false} + DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"), + DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"), }; -bool probe_type_is_available(enum probe_type type) +static bool scan_ftrace_readme(enum ftrace_readme type) { + int fd; FILE *fp; char *buf = NULL; size_t len = 0; - bool target_line = false; - bool ret = probe_type_table[type].avail; + bool ret = false; + static bool scanned = false; - if (type >= PROBE_TYPE_END) - return false; - /* We don't have to check the type which supported by default */ - if (ret || probe_type_table[type].checked) - return ret; + if (scanned) + goto result; - if (asprintf(&buf, "%s/README", tracing_path) < 0) + fd = open_trace_file("README", false); + if (fd < 0) return ret; - fp = fopen(buf, "r"); - if (!fp) - goto end; - - zfree(&buf); - while (getline(&buf, &len, fp) > 0 && !ret) { - if (!target_line) { - target_line = !!strstr(buf, " type: "); - if (!target_line) - continue; - } else if (strstr(buf, "\t ") != buf) - break; - ret = strglobmatch(buf, probe_type_table[type].pattern); + fp = fdopen(fd, "r"); + if (!fp) { + close(fd); + return ret; } - /* Cache the result */ - probe_type_table[type].checked = true; - probe_type_table[type].avail = ret; + + while (getline(&buf, &len, fp) > 0) + for (enum ftrace_readme i = 0; i < FTRACE_README_END; i++) + if (!ftrace_readme_table[i].avail) + ftrace_readme_table[i].avail = + strglobmatch(buf, ftrace_readme_table[i].pattern); + scanned = true; fclose(fp); -end: free(buf); - return ret; +result: + if (type >= FTRACE_README_END) + return false; + + return ftrace_readme_table[type].avail; +} + +bool probe_type_is_available(enum probe_type type) +{ + if (type >= PROBE_TYPE_END) + return false; + else if (type == PROBE_TYPE_X) + return scan_ftrace_readme(FTRACE_README_PROBE_TYPE_X); + + return true; +} + +bool kretprobe_offset_is_supported(void) +{ + return scan_ftrace_readme(FTRACE_README_KRETPROBE_OFFSET); } diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index eba44c3e9dca..dbf95a00864a 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -35,6 +35,7 @@ enum probe_type { /* probe-file.c depends on libelf */ #ifdef HAVE_LIBELF_SUPPORT +int open_trace_file(const char *trace_file, bool readwrite); int probe_file__open(int flag); int probe_file__open_both(int *kfd, int *ufd, int flag); struct strlist *probe_file__get_namelist(int fd); @@ -64,6 +65,7 @@ struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache, const char *group, const char *event); int probe_cache__show_all_caches(struct strfilter *filter); bool probe_type_is_available(enum probe_type type); +bool kretprobe_offset_is_supported(void); #else /* ! HAVE_LIBELF_SUPPORT */ static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 1dd617d116b5..ae42e742d461 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1239,6 +1239,8 @@ static int machines__deliver_event(struct machines *machines, return tool->mmap2(tool, event, sample, machine); case PERF_RECORD_COMM: return tool->comm(tool, event, sample, machine); + case PERF_RECORD_NAMESPACES: + return tool->namespaces(tool, event, sample, machine); case PERF_RECORD_FORK: return tool->fork(tool, event, sample, machine); case PERF_RECORD_EXIT: @@ -1494,6 +1496,11 @@ int perf_session__register_idle_thread(struct perf_session *session) err = -1; } + if (thread == NULL || thread__set_namespaces(thread, 0, NULL)) { + pr_err("problem inserting idle task.\n"); + err = -1; + } + /* machine__findnew_thread() got the thread, so put it */ thread__put(thread); return err; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 0ff622288d24..8b0d4e39f640 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -536,6 +536,46 @@ struct sort_entry sort_cpu = { .se_width_idx = HISTC_CPU, }; +/* --sort cgroup_id */ + +static int64_t _sort__cgroup_dev_cmp(u64 left_dev, u64 right_dev) +{ + return (int64_t)(right_dev - left_dev); +} + +static int64_t _sort__cgroup_inode_cmp(u64 left_ino, u64 right_ino) +{ + return (int64_t)(right_ino - left_ino); +} + +static int64_t +sort__cgroup_id_cmp(struct hist_entry *left, struct hist_entry *right) +{ + int64_t ret; + + ret = _sort__cgroup_dev_cmp(right->cgroup_id.dev, left->cgroup_id.dev); + if (ret != 0) + return ret; + + return _sort__cgroup_inode_cmp(right->cgroup_id.ino, + left->cgroup_id.ino); +} + +static int hist_entry__cgroup_id_snprintf(struct hist_entry *he, + char *bf, size_t size, + unsigned int width __maybe_unused) +{ + return repsep_snprintf(bf, size, "%lu/0x%lx", he->cgroup_id.dev, + he->cgroup_id.ino); +} + +struct sort_entry sort_cgroup_id = { + .se_header = "cgroup id (dev/inode)", + .se_cmp = sort__cgroup_id_cmp, + .se_snprintf = hist_entry__cgroup_id_snprintf, + .se_width_idx = HISTC_CGROUP_ID, +}; + /* --sort socket */ static int64_t @@ -846,6 +886,9 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf, static int64_t sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return left->branch_info->flags.cycles - right->branch_info->flags.cycles; } @@ -853,6 +896,8 @@ sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__cycles_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { + if (!he->branch_info) + return scnprintf(bf, size, "%-.*s", width, "N/A"); if (he->branch_info->flags.cycles == 0) return repsep_snprintf(bf, size, "%-*s", width, "-"); return repsep_snprintf(bf, size, "%-*hd", width, @@ -1396,6 +1441,46 @@ struct sort_entry sort_transaction = { .se_width_idx = HISTC_TRANSACTION, }; +/* --sort symbol_size */ + +static int64_t _sort__sym_size_cmp(struct symbol *sym_l, struct symbol *sym_r) +{ + int64_t size_l = sym_l != NULL ? symbol__size(sym_l) : 0; + int64_t size_r = sym_r != NULL ? symbol__size(sym_r) : 0; + + return size_l < size_r ? -1 : + size_l == size_r ? 0 : 1; +} + +static int64_t +sort__sym_size_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return _sort__sym_size_cmp(right->ms.sym, left->ms.sym); +} + +static int _hist_entry__sym_size_snprintf(struct symbol *sym, char *bf, + size_t bf_size, unsigned int width) +{ + if (sym) + return repsep_snprintf(bf, bf_size, "%*d", width, symbol__size(sym)); + + return repsep_snprintf(bf, bf_size, "%*s", width, "unknown"); +} + +static int hist_entry__sym_size_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__sym_size_snprintf(he->ms.sym, bf, size, width); +} + +struct sort_entry sort_sym_size = { + .se_header = "Symbol size", + .se_cmp = sort__sym_size_cmp, + .se_snprintf = hist_entry__sym_size_snprintf, + .se_width_idx = HISTC_SYM_SIZE, +}; + + struct sort_dimension { const char *name; struct sort_entry *entry; @@ -1418,6 +1503,8 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), DIM(SORT_TRANSACTION, "transaction", sort_transaction), DIM(SORT_TRACE, "trace", sort_trace), + DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size), + DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id), }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 796c847e2f00..baf20a399f34 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -54,6 +54,11 @@ struct he_stat { u32 nr_events; }; +struct namespace_id { + u64 dev; + u64 ino; +}; + struct hist_entry_diff { bool computed; union { @@ -91,6 +96,7 @@ struct hist_entry { struct map_symbol ms; struct thread *thread; struct comm *comm; + struct namespace_id cgroup_id; u64 ip; u64 transaction; s32 socket; @@ -211,6 +217,8 @@ enum sort_type { SORT_GLOBAL_WEIGHT, SORT_TRANSACTION, SORT_TRACE, + SORT_SYM_SIZE, + SORT_CGROUP_ID, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index f5af87f66663..dcdb87a5d0a1 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -7,6 +7,7 @@ #include "thread-stack.h" #include "util.h" #include "debug.h" +#include "namespaces.h" #include "comm.h" #include "unwind.h" @@ -40,6 +41,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread->tid = tid; thread->ppid = -1; thread->cpu = -1; + INIT_LIST_HEAD(&thread->namespaces_list); INIT_LIST_HEAD(&thread->comm_list); comm_str = malloc(32); @@ -53,7 +55,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) goto err_thread; list_add(&comm->list, &thread->comm_list); - atomic_set(&thread->refcnt, 1); + refcount_set(&thread->refcnt, 1); RB_CLEAR_NODE(&thread->rb_node); } @@ -66,7 +68,8 @@ err_thread: void thread__delete(struct thread *thread) { - struct comm *comm, *tmp; + struct namespaces *namespaces, *tmp_namespaces; + struct comm *comm, *tmp_comm; BUG_ON(!RB_EMPTY_NODE(&thread->rb_node)); @@ -76,7 +79,12 @@ void thread__delete(struct thread *thread) map_groups__put(thread->mg); thread->mg = NULL; } - list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) { + list_for_each_entry_safe(namespaces, tmp_namespaces, + &thread->namespaces_list, list) { + list_del(&namespaces->list); + namespaces__free(namespaces); + } + list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) { list_del(&comm->list); comm__free(comm); } @@ -88,13 +96,13 @@ void thread__delete(struct thread *thread) struct thread *thread__get(struct thread *thread) { if (thread) - atomic_inc(&thread->refcnt); + refcount_inc(&thread->refcnt); return thread; } void thread__put(struct thread *thread) { - if (thread && atomic_dec_and_test(&thread->refcnt)) { + if (thread && refcount_dec_and_test(&thread->refcnt)) { /* * Remove it from the dead_threads list, as last reference * is gone. @@ -104,6 +112,38 @@ void thread__put(struct thread *thread) } } +struct namespaces *thread__namespaces(const struct thread *thread) +{ + if (list_empty(&thread->namespaces_list)) + return NULL; + + return list_first_entry(&thread->namespaces_list, struct namespaces, list); +} + +int thread__set_namespaces(struct thread *thread, u64 timestamp, + struct namespaces_event *event) +{ + struct namespaces *new, *curr = thread__namespaces(thread); + + new = namespaces__new(event); + if (!new) + return -ENOMEM; + + list_add(&new->list, &thread->namespaces_list); + + if (timestamp && curr) { + /* + * setns syscall must have changed few or all the namespaces + * of this thread. Update end time for the namespaces + * previously used. + */ + curr = list_next_entry(new, list); + curr->end_time = timestamp; + } + + return 0; +} + struct comm *thread__comm(const struct thread *thread) { if (list_empty(&thread->comm_list)) diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 99263cb6e6b6..4eb849e9098f 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -1,7 +1,7 @@ #ifndef __PERF_THREAD_H #define __PERF_THREAD_H -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/rbtree.h> #include <linux/list.h> #include <unistd.h> @@ -23,11 +23,12 @@ struct thread { pid_t tid; pid_t ppid; int cpu; - atomic_t refcnt; + refcount_t refcnt; char shortname[3]; bool comm_set; int comm_len; bool dead; /* if set thread has exited */ + struct list_head namespaces_list; struct list_head comm_list; u64 db_id; @@ -40,6 +41,7 @@ struct thread { }; struct machine; +struct namespaces; struct comm; struct thread *thread__new(pid_t pid, pid_t tid); @@ -62,6 +64,10 @@ static inline void thread__exited(struct thread *thread) thread->dead = true; } +struct namespaces *thread__namespaces(const struct thread *thread); +int thread__set_namespaces(struct thread *thread, u64 timestamp, + struct namespaces_event *event); + int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp, bool exec); static inline int thread__set_comm(struct thread *thread, const char *comm, diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 7c3fcc538a70..9026408ea55b 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -66,7 +66,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid) for (i = 0; i < items; i++) thread_map__set_pid(threads, i, atoi(namelist[i]->d_name)); threads->nr = items; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } for (i=0; i<items; i++) @@ -83,7 +83,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid) if (threads != NULL) { thread_map__set_pid(threads, 0, tid); threads->nr = 1; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } return threads; @@ -105,7 +105,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) goto out_free_threads; threads->nr = 0; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); while ((dirent = readdir(proc)) != NULL) { char *end; @@ -235,7 +235,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) out: strlist__delete(slist); if (threads) - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); return threads; out_free_namelist: @@ -255,7 +255,7 @@ struct thread_map *thread_map__new_dummy(void) if (threads != NULL) { thread_map__set_pid(threads, 0, -1); threads->nr = 1; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } return threads; } @@ -300,7 +300,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str) } out: if (threads) - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); return threads; out_free_threads: @@ -326,7 +326,7 @@ static void thread_map__delete(struct thread_map *threads) if (threads) { int i; - WARN_ONCE(atomic_read(&threads->refcnt) != 0, + WARN_ONCE(refcount_read(&threads->refcnt) != 0, "thread map refcnt unbalanced\n"); for (i = 0; i < threads->nr; i++) free(thread_map__comm(threads, i)); @@ -337,13 +337,13 @@ static void thread_map__delete(struct thread_map *threads) struct thread_map *thread_map__get(struct thread_map *map) { if (map) - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); return map; } void thread_map__put(struct thread_map *map) { - if (map && atomic_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(&map->refcnt)) thread_map__delete(map); } @@ -423,7 +423,7 @@ static void thread_map__copy_event(struct thread_map *threads, threads->map[i].comm = strndup(event->entries[i].comm, 16); } - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } struct thread_map *thread_map__new_event(struct thread_map_event *event) diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index ea0ef08c6303..bd34d7a0b9fa 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -3,7 +3,7 @@ #include <sys/types.h> #include <stdio.h> -#include <linux/atomic.h> +#include <linux/refcount.h> struct thread_map_data { pid_t pid; @@ -11,7 +11,7 @@ struct thread_map_data { }; struct thread_map { - atomic_t refcnt; + refcount_t refcnt; int nr; struct thread_map_data map[]; }; diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index ac2590a3de2d..829471a1c6d7 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -40,6 +40,7 @@ struct perf_tool { event_op mmap, mmap2, comm, + namespaces, fork, exit, lost, @@ -66,6 +67,7 @@ struct perf_tool { event_op3 auxtrace; bool ordered_events; bool ordering_requires_timestamps; + bool namespace_events; }; #endif /* __PERF_TOOL_H */ diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index c74708da8571..b2cfa47990dc 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -355,8 +355,8 @@ void print_binary(unsigned char *data, size_t len, size_t bytes_per_line, print_binary_t printer, void *extra); -#if !defined(__GLIBC__) && !defined(__ANDROID__) -extern int sched_getcpu(void); +#ifndef HAVE_SCHED_GETCPU_SUPPORT +int sched_getcpu(void); #endif int is_printable_array(char *p, unsigned int len); diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 621578aa12d6..fc74db62fef4 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -43,6 +43,15 @@ ifneq ($(CC), clang) EXTRA_WARNINGS += -Wstrict-aliasing=3 endif +# Hack to avoid type-punned warnings on old systems such as RHEL5: +# We should be changing CFLAGS and checking gcc version, but this +# will do for now and keep the above -Wstrict-aliasing=3 in place +# in newer systems. +# Needed for the __raw_cmpxchg in tools/arch/x86/include/asm/cmpxchg.h +ifneq ($(filter 3.%,$(MAKE_VERSION)),) # make-3 +EXTRA_WARNINGS += -fno-strict-aliasing +endif + ifneq ($(findstring $(MAKEFLAGS), w),w) PRINT_DIR = --no-print-directory else |