From 2b26f0aa004995f49f7b6f4100dd0e4c39a9ed5f Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 8 Apr 2021 12:35:58 +0200 Subject: perf: Support only inheriting events if cloned with CLONE_THREAD Adds bit perf_event_attr::inherit_thread, to restricting inheriting events only if the child was cloned with CLONE_THREAD. This option supports the case where an event is supposed to be process-wide only (including subthreads), but should not propagate beyond the current process's shared environment. Suggested-by: Peter Zijlstra Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/lkml/YBvj6eJR%2FDY2TsEB@hirez.programming.kicks-ass.net/ --- include/uapi/linux/perf_event.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index ad15e40d7f5d..813efb65fea8 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -389,7 +389,8 @@ struct perf_event_attr { cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ build_id : 1, /* use build id in mmap2 events */ - __reserved_1 : 29; + inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ + __reserved_1 : 28; union { __u32 wakeup_events; /* wakeup every n events */ -- cgit v1.3-15-g9ac1 From 2e498d0a74e5b88a6689ae1b811f247f91ff188e Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 8 Apr 2021 12:35:59 +0200 Subject: perf: Add support for event removal on exec Adds bit perf_event_attr::remove_on_exec, to support removing an event from a task on exec. This option supports the case where an event is supposed to be process-wide only, and should not propagate beyond exec, to limit monitoring to the original process image only. Suggested-by: Peter Zijlstra Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210408103605.1676875-5-elver@google.com --- include/uapi/linux/perf_event.h | 3 +- kernel/events/core.c | 70 ++++++++++++++++++++++++++++++++++++----- 2 files changed, 64 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 813efb65fea8..8c5b9f5ad63f 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -390,7 +390,8 @@ struct perf_event_attr { text_poke : 1, /* include text poke events */ build_id : 1, /* use build id in mmap2 events */ inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ - __reserved_1 : 28; + remove_on_exec : 1, /* event is removed from task on exec */ + __reserved_1 : 27; union { __u32 wakeup_events; /* wakeup every n events */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 3e3c00fd0b2e..e4a584bceb7a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4248,6 +4248,57 @@ out: put_ctx(clone_ctx); } +static void perf_remove_from_owner(struct perf_event *event); +static void perf_event_exit_event(struct perf_event *event, + struct perf_event_context *ctx); + +/* + * Removes all events from the current task that have been marked + * remove-on-exec, and feeds their values back to parent events. + */ +static void perf_event_remove_on_exec(int ctxn) +{ + struct perf_event_context *ctx, *clone_ctx = NULL; + struct perf_event *event, *next; + LIST_HEAD(free_list); + unsigned long flags; + bool modified = false; + + ctx = perf_pin_task_context(current, ctxn); + if (!ctx) + return; + + mutex_lock(&ctx->mutex); + + if (WARN_ON_ONCE(ctx->task != current)) + goto unlock; + + list_for_each_entry_safe(event, next, &ctx->event_list, event_entry) { + if (!event->attr.remove_on_exec) + continue; + + if (!is_kernel_event(event)) + perf_remove_from_owner(event); + + modified = true; + + perf_event_exit_event(event, ctx); + } + + raw_spin_lock_irqsave(&ctx->lock, flags); + if (modified) + clone_ctx = unclone_ctx(ctx); + --ctx->pin_count; + raw_spin_unlock_irqrestore(&ctx->lock, flags); + +unlock: + mutex_unlock(&ctx->mutex); + + put_ctx(ctx); + if (clone_ctx) + put_ctx(clone_ctx); +} + struct perf_read_data { struct perf_event *event; bool group; @@ -7560,18 +7611,18 @@ void perf_event_exec(void) struct perf_event_context *ctx; int ctxn; - rcu_read_lock(); for_each_task_context_nr(ctxn) { - ctx = current->perf_event_ctxp[ctxn]; - if (!ctx) - continue; - perf_event_enable_on_exec(ctxn); + perf_event_remove_on_exec(ctxn); - perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, - true); + rcu_read_lock(); + ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); + if (ctx) { + perf_iterate_ctx(ctx, perf_event_addr_filters_exec, + NULL, true); + } + rcu_read_unlock(); } - rcu_read_unlock(); } struct remote_output { @@ -11656,6 +11707,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, if (!attr->inherit && attr->inherit_thread) return -EINVAL; + if (attr->remove_on_exec && attr->enable_on_exec) + return -EINVAL; + out: return ret; -- cgit v1.3-15-g9ac1 From fb6cc127e0b6e629252cdd0f77d5a1f49db95b92 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 8 Apr 2021 12:36:00 +0200 Subject: signal: Introduce TRAP_PERF si_code and si_perf to siginfo Introduces the TRAP_PERF si_code, and associated siginfo_t field si_perf. These will be used by the perf event subsystem to send signals (if requested) to the task where an event occurred. Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Acked-by: Geert Uytterhoeven # m68k Acked-by: Arnd Bergmann # asm-generic Link: https://lkml.kernel.org/r/20210408103605.1676875-6-elver@google.com --- arch/m68k/kernel/signal.c | 3 +++ arch/x86/kernel/signal_compat.c | 5 ++++- fs/signalfd.c | 4 ++++ include/linux/compat.h | 2 ++ include/linux/signal.h | 1 + include/uapi/asm-generic/siginfo.h | 6 +++++- include/uapi/linux/signalfd.h | 4 +++- kernel/signal.c | 11 +++++++++++ 8 files changed, 33 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 349570f16a78..a4b7ee1df211 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -622,6 +622,9 @@ static inline void siginfo_build_tests(void) /* _sigfault._addr_pkey */ BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x12); + /* _sigfault._perf */ + BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x10); + /* _sigpoll */ BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x0c); BUILD_BUG_ON(offsetof(siginfo_t, si_fd) != 0x10); diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index a5330ff498f0..0e5d0a7e203b 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -29,7 +29,7 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(NSIGFPE != 15); BUILD_BUG_ON(NSIGSEGV != 9); BUILD_BUG_ON(NSIGBUS != 5); - BUILD_BUG_ON(NSIGTRAP != 5); + BUILD_BUG_ON(NSIGTRAP != 6); BUILD_BUG_ON(NSIGCHLD != 6); BUILD_BUG_ON(NSIGSYS != 2); @@ -138,6 +138,9 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20); BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf) != 0x10); + CHECK_CSI_OFFSET(_sigpoll); CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int)); CHECK_SI_SIZE (_sigpoll, 4*sizeof(int)); diff --git a/fs/signalfd.c b/fs/signalfd.c index 456046e15873..040a1142915f 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -134,6 +134,10 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, #endif new.ssi_addr_lsb = (short) kinfo->si_addr_lsb; break; + case SIL_PERF_EVENT: + new.ssi_addr = (long) kinfo->si_addr; + new.ssi_perf = kinfo->si_perf; + break; case SIL_CHLD: new.ssi_pid = kinfo->si_pid; new.ssi_uid = kinfo->si_uid; diff --git a/include/linux/compat.h b/include/linux/compat.h index 6e65be753603..c8821d966812 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -236,6 +236,8 @@ typedef struct compat_siginfo { char _dummy_pkey[__COMPAT_ADDR_BND_PKEY_PAD]; u32 _pkey; } _addr_pkey; + /* used when si_code=TRAP_PERF */ + compat_u64 _perf; }; } _sigfault; diff --git a/include/linux/signal.h b/include/linux/signal.h index 205526c4003a..1e98548d7cf6 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -43,6 +43,7 @@ enum siginfo_layout { SIL_FAULT_MCEERR, SIL_FAULT_BNDERR, SIL_FAULT_PKUERR, + SIL_PERF_EVENT, SIL_CHLD, SIL_RT, SIL_SYS, diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index d2597000407a..d0bb9125c853 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -91,6 +91,8 @@ union __sifields { char _dummy_pkey[__ADDR_BND_PKEY_PAD]; __u32 _pkey; } _addr_pkey; + /* used when si_code=TRAP_PERF */ + __u64 _perf; }; } _sigfault; @@ -155,6 +157,7 @@ typedef struct siginfo { #define si_lower _sifields._sigfault._addr_bnd._lower #define si_upper _sifields._sigfault._addr_bnd._upper #define si_pkey _sifields._sigfault._addr_pkey._pkey +#define si_perf _sifields._sigfault._perf #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd #define si_call_addr _sifields._sigsys._call_addr @@ -253,7 +256,8 @@ typedef struct siginfo { #define TRAP_BRANCH 3 /* process taken branch trap */ #define TRAP_HWBKPT 4 /* hardware breakpoint/watchpoint */ #define TRAP_UNK 5 /* undiagnosed trap */ -#define NSIGTRAP 5 +#define TRAP_PERF 6 /* perf event with sigtrap=1 */ +#define NSIGTRAP 6 /* * There is an additional set of SIGTRAP si_codes used by ptrace diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h index 83429a05b698..7e333042c7e3 100644 --- a/include/uapi/linux/signalfd.h +++ b/include/uapi/linux/signalfd.h @@ -39,6 +39,8 @@ struct signalfd_siginfo { __s32 ssi_syscall; __u64 ssi_call_addr; __u32 ssi_arch; + __u32 __pad3; + __u64 ssi_perf; /* * Pad strcture to 128 bytes. Remember to update the @@ -49,7 +51,7 @@ struct signalfd_siginfo { * comes out of a read(2) and we really don't want to have * a compat on read(2). */ - __u8 __pad[28]; + __u8 __pad[16]; }; diff --git a/kernel/signal.c b/kernel/signal.c index ba4d1ef39a9e..f68351825e5e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1199,6 +1199,7 @@ static inline bool has_si_pid_and_uid(struct kernel_siginfo *info) case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: + case SIL_PERF_EVENT: case SIL_SYS: ret = false; break; @@ -2531,6 +2532,7 @@ static void hide_si_addr_tag_bits(struct ksignal *ksig) case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: + case SIL_PERF_EVENT: ksig->info.si_addr = arch_untagged_si_addr( ksig->info.si_addr, ksig->sig, ksig->info.si_code); break; @@ -3333,6 +3335,10 @@ void copy_siginfo_to_external32(struct compat_siginfo *to, #endif to->si_pkey = from->si_pkey; break; + case SIL_PERF_EVENT: + to->si_addr = ptr_to_compat(from->si_addr); + to->si_perf = from->si_perf; + break; case SIL_CHLD: to->si_pid = from->si_pid; to->si_uid = from->si_uid; @@ -3413,6 +3419,10 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, #endif to->si_pkey = from->si_pkey; break; + case SIL_PERF_EVENT: + to->si_addr = compat_ptr(from->si_addr); + to->si_perf = from->si_perf; + break; case SIL_CHLD: to->si_pid = from->si_pid; to->si_uid = from->si_uid; @@ -4593,6 +4603,7 @@ static inline void siginfo_buildtime_checks(void) CHECK_OFFSET(si_lower); CHECK_OFFSET(si_upper); CHECK_OFFSET(si_pkey); + CHECK_OFFSET(si_perf); /* sigpoll */ CHECK_OFFSET(si_band); -- cgit v1.3-15-g9ac1 From 97ba62b278674293762c3d91f724f1bb922f04e0 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 8 Apr 2021 12:36:01 +0200 Subject: perf: Add support for SIGTRAP on perf events Adds bit perf_event_attr::sigtrap, which can be set to cause events to send SIGTRAP (with si_code TRAP_PERF) to the task where the event occurred. The primary motivation is to support synchronous signals on perf events in the task where an event (such as breakpoints) triggered. To distinguish perf events based on the event type, the type is set in si_errno. For events that are associated with an address, si_addr is copied from perf_sample_data. The new field perf_event_attr::sig_data is copied to si_perf, which allows user space to disambiguate which event (of the same type) triggered the signal. For example, user space could encode the relevant information it cares about in sig_data. We note that the choice of an opaque u64 provides the simplest and most flexible option. Alternatives where a reference to some user space data is passed back suffer from the problem that modification of referenced data (be it the event fd, or the perf_event_attr) can race with the signal being delivered (of course, the same caveat applies if user space decides to store a pointer in sig_data, but the ABI explicitly avoids prescribing such a design). Suggested-by: Peter Zijlstra Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Acked-by: Dmitry Vyukov Link: https://lore.kernel.org/lkml/YBv3rAT566k+6zjg@hirez.programming.kicks-ass.net/ --- include/linux/perf_event.h | 1 + include/uapi/linux/perf_event.h | 10 ++++++++- kernel/events/core.c | 49 ++++++++++++++++++++++++++++++++++++++++- 3 files changed, 58 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1660039199b2..7d7280aa4e22 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -735,6 +735,7 @@ struct perf_event { int pending_wakeup; int pending_kill; int pending_disable; + unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending; atomic_t event_limit; diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 8c5b9f5ad63f..31b00e3b69c9 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -311,6 +311,7 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */ #define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ #define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ +#define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -391,7 +392,8 @@ struct perf_event_attr { build_id : 1, /* use build id in mmap2 events */ inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ remove_on_exec : 1, /* event is removed from task on exec */ - __reserved_1 : 27; + sigtrap : 1, /* send synchronous SIGTRAP on event */ + __reserved_1 : 26; union { __u32 wakeup_events; /* wakeup every n events */ @@ -443,6 +445,12 @@ struct perf_event_attr { __u16 __reserved_2; __u32 aux_sample_size; __u32 __reserved_3; + + /* + * User provided data if sigtrap=1, passed back to user via + * siginfo_t::si_perf, e.g. to permit user to identify the event. + */ + __u64 sig_data; }; /* diff --git a/kernel/events/core.c b/kernel/events/core.c index e4a584bceb7a..6f0723c711a9 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6392,6 +6392,33 @@ void perf_event_wakeup(struct perf_event *event) } } +static void perf_sigtrap(struct perf_event *event) +{ + struct kernel_siginfo info; + + /* + * We'd expect this to only occur if the irq_work is delayed and either + * ctx->task or current has changed in the meantime. This can be the + * case on architectures that do not implement arch_irq_work_raise(). + */ + if (WARN_ON_ONCE(event->ctx->task != current)) + return; + + /* + * perf_pending_event() can race with the task exiting. + */ + if (current->flags & PF_EXITING) + return; + + clear_siginfo(&info); + info.si_signo = SIGTRAP; + info.si_code = TRAP_PERF; + info.si_errno = event->attr.type; + info.si_perf = event->attr.sig_data; + info.si_addr = (void __user *)event->pending_addr; + force_sig_info(&info); +} + static void perf_pending_event_disable(struct perf_event *event) { int cpu = READ_ONCE(event->pending_disable); @@ -6401,6 +6428,13 @@ static void perf_pending_event_disable(struct perf_event *event) if (cpu == smp_processor_id()) { WRITE_ONCE(event->pending_disable, -1); + + if (event->attr.sigtrap) { + perf_sigtrap(event); + atomic_set_release(&event->event_limit, 1); /* rearm event */ + return; + } + perf_event_disable_local(event); return; } @@ -9103,6 +9137,7 @@ static int __perf_event_overflow(struct perf_event *event, if (events && atomic_dec_and_test(&event->event_limit)) { ret = 1; event->pending_kill = POLL_HUP; + event->pending_addr = data->addr; perf_event_disable_inatomic(event); } @@ -11384,6 +11419,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, if (!task || cpu != -1) return ERR_PTR(-EINVAL); } + if (attr->sigtrap && !task) { + /* Requires a task: avoid signalling random tasks. */ + return ERR_PTR(-EINVAL); + } node = (cpu >= 0) ? cpu_to_node(cpu) : -1; event = kmem_cache_alloc_node(perf_event_cache, GFP_KERNEL | __GFP_ZERO, @@ -11432,6 +11471,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->state = PERF_EVENT_STATE_INACTIVE; + if (event->attr.sigtrap) + atomic_set(&event->event_limit, 1); + if (task) { event->attach_state = PERF_ATTACH_TASK; /* @@ -11710,6 +11752,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, if (attr->remove_on_exec && attr->enable_on_exec) return -EINVAL; + if (attr->sigtrap && !attr->remove_on_exec) + return -EINVAL; + out: return ret; @@ -12936,7 +12981,9 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent, struct perf_event_context *child_ctx; if (!event->attr.inherit || - (event->attr.inherit_thread && !(clone_flags & CLONE_THREAD))) { + (event->attr.inherit_thread && !(clone_flags & CLONE_THREAD)) || + /* Do not inherit if sigtrap and signal handlers were cleared. */ + (event->attr.sigtrap && (clone_flags & CLONE_CLEAR_SIGHAND))) { *inherited_all = 0; return 0; } -- cgit v1.3-15-g9ac1 From d0d1dd628527c77db2391ce0293c1ed344b2365f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 10 Feb 2021 17:33:26 +0900 Subject: perf core: Add PERF_COUNT_SW_CGROUP_SWITCHES event This patch adds a new software event to count context switches involving cgroup switches. So it's counted only if cgroups of previous and next tasks are different. Note that it only checks the cgroups in the perf_event subsystem. For cgroup v2, it shouldn't matter anyway. One can argue that we can do this by using existing sched_switch event with eBPF. But some systems might not have eBPF for some reason so I'd like to add this as a simple way. Signed-off-by: Namhyung Kim Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210210083327.22726-2-namhyung@kernel.org --- include/linux/perf_event.h | 7 +++++++ include/uapi/linux/perf_event.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 92d51a7beaea..8989b2b7268d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1218,6 +1218,13 @@ static inline void perf_event_task_sched_out(struct task_struct *prev, if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES)) __perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); +#ifdef CONFIG_CGROUP_PERF + if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) && + perf_cgroup_from_task(prev, NULL) != + perf_cgroup_from_task(next, NULL)) + __perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0); +#endif + if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 31b00e3b69c9..0b58970bab6b 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -112,6 +112,7 @@ enum perf_sw_ids { PERF_COUNT_SW_EMULATION_FAULTS = 8, PERF_COUNT_SW_DUMMY = 9, PERF_COUNT_SW_BPF_OUTPUT = 10, + PERF_COUNT_SW_CGROUP_SWITCHES = 11, PERF_COUNT_SW_MAX, /* non-ABI */ }; -- cgit v1.3-15-g9ac1 From 55bcf6ef314ae8ba81bcd74aa760247b635ed47b Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 12 Apr 2021 07:31:01 -0700 Subject: perf: Extend PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE Current Hardware events and Hardware cache events have special perf types, PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE. The two types don't pass the PMU type in the user interface. For a hybrid system, the perf subsystem doesn't know which PMU the events belong to. The first capable PMU will always be assigned to the events. The events never get a chance to run on the other capable PMUs. Extend the two types to become PMU aware types. The PMU type ID is stored at attr.config[63:32]. Add a new PMU capability, PERF_PMU_CAP_EXTENDED_HW_TYPE, to indicate a PMU which supports the extended PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE. The PMU type is only required when searching a specific PMU. The PMU specific codes will only be interested in the 'real' config value, which is stored in the low 32 bit of the event->attr.config. Update the event->attr.config in the generic code, so the PMU specific codes don't need to calculate it separately. If a user specifies a PMU type, but the PMU doesn't support the extended type, error out. If an event cannot be initialized in a PMU specified by a user, error out immediately. Perf should not try to open it on other PMUs. The new PMU capability is only set for the X86 hybrid PMUs for now. Other architectures, e.g., ARM, may need it as well. The support on ARM may be implemented later separately. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1618237865-33448-22-git-send-email-kan.liang@linux.intel.com --- arch/x86/events/core.c | 1 + include/linux/perf_event.h | 19 ++++++++++--------- include/uapi/linux/perf_event.h | 15 +++++++++++++++ kernel/events/core.c | 19 ++++++++++++++++--- 4 files changed, 42 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 4f6595ee6359..3fe66b7aa721 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2173,6 +2173,7 @@ static int __init init_hw_perf_events(void) hybrid_pmu->pmu.type = -1; hybrid_pmu->pmu.attr_update = x86_pmu.attr_update; hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_HETEROGENEOUS_CPUS; + hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_EXTENDED_HW_TYPE; err = perf_pmu_register(&hybrid_pmu->pmu, hybrid_pmu->name, (hybrid_pmu->cpu_type == hybrid_big) ? PERF_TYPE_RAW : -1); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 61b385154c4a..a763928a0e41 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -260,15 +260,16 @@ struct perf_event; /** * pmu::capabilities flags */ -#define PERF_PMU_CAP_NO_INTERRUPT 0x01 -#define PERF_PMU_CAP_NO_NMI 0x02 -#define PERF_PMU_CAP_AUX_NO_SG 0x04 -#define PERF_PMU_CAP_EXTENDED_REGS 0x08 -#define PERF_PMU_CAP_EXCLUSIVE 0x10 -#define PERF_PMU_CAP_ITRACE 0x20 -#define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 -#define PERF_PMU_CAP_NO_EXCLUDE 0x80 -#define PERF_PMU_CAP_AUX_OUTPUT 0x100 +#define PERF_PMU_CAP_NO_INTERRUPT 0x0001 +#define PERF_PMU_CAP_NO_NMI 0x0002 +#define PERF_PMU_CAP_AUX_NO_SG 0x0004 +#define PERF_PMU_CAP_EXTENDED_REGS 0x0008 +#define PERF_PMU_CAP_EXCLUSIVE 0x0010 +#define PERF_PMU_CAP_ITRACE 0x0020 +#define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x0040 +#define PERF_PMU_CAP_NO_EXCLUDE 0x0080 +#define PERF_PMU_CAP_AUX_OUTPUT 0x0100 +#define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0200 struct perf_output_handle; diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 0b58970bab6b..e54e639248c8 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -37,6 +37,21 @@ enum perf_type_id { PERF_TYPE_MAX, /* non-ABI */ }; +/* + * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE + * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA + * AA: hardware event ID + * EEEEEEEE: PMU type ID + * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB + * BB: hardware cache ID + * CC: hardware cache op ID + * DD: hardware cache op result ID + * EEEEEEEE: PMU type ID + * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied. + */ +#define PERF_PMU_TYPE_SHIFT 32 +#define PERF_HW_EVENT_MASK 0xffffffff + /* * Generalized performance event event_id types, used by the * attr.event_id parameter of the sys_perf_event_open() diff --git a/kernel/events/core.c b/kernel/events/core.c index 6f0723c711a9..928b166d888e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11220,6 +11220,7 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) static struct pmu *perf_init_event(struct perf_event *event) { + bool extended_type = false; int idx, type, ret; struct pmu *pmu; @@ -11238,16 +11239,27 @@ static struct pmu *perf_init_event(struct perf_event *event) * are often aliases for PERF_TYPE_RAW. */ type = event->attr.type; - if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE) - type = PERF_TYPE_RAW; + if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE) { + type = event->attr.config >> PERF_PMU_TYPE_SHIFT; + if (!type) { + type = PERF_TYPE_RAW; + } else { + extended_type = true; + event->attr.config &= PERF_HW_EVENT_MASK; + } + } again: rcu_read_lock(); pmu = idr_find(&pmu_idr, type); rcu_read_unlock(); if (pmu) { + if (event->attr.type != type && type != PERF_TYPE_RAW && + !(pmu->capabilities & PERF_PMU_CAP_EXTENDED_HW_TYPE)) + goto fail; + ret = perf_try_init_event(pmu, event); - if (ret == -ENOENT && event->attr.type != type) { + if (ret == -ENOENT && event->attr.type != type && !extended_type) { type = event->attr.type; goto again; } @@ -11268,6 +11280,7 @@ again: goto unlock; } } +fail: pmu = ERR_PTR(-ENOENT); unlock: srcu_read_unlock(&pmus_srcu, idx); -- cgit v1.3-15-g9ac1