From 7f5a08c79df35e68f1a43033450c5050f12bc155 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 18 Jan 2022 12:43:15 -0800 Subject: user_events: Add minimal support for trace_event into ftrace Minimal support for interacting with dynamic events, trace_event and ftrace. Core outline of flow between user process, ioctl and trace_event APIs. User mode processes that wish to use trace events to get data into ftrace, perf, eBPF, etc are limited to uprobes today. The user events features enables an ABI for user mode processes to create and write to trace events that are isolated from kernel level trace events. This enables a faster path for tracing from user mode data as well as opens managed code to participate in trace events, where stub locations are dynamic. User processes often want to trace only when it's useful. To enable this a set of pages are mapped into the user process space that indicate the current state of the user events that have been registered. User processes can check if their event is hooked to a trace/probe, and if it is, emit the event data out via the write() syscall. Two new files are introduced into tracefs to accomplish this: user_events_status - This file is mmap'd into participating user mode processes to indicate event status. user_events_data - This file is opened and register/delete ioctl's are issued to create/open/delete trace events that can be used for tracing. The typical scenario is on process start to mmap user_events_status. Processes then register the events they plan to use via the REG ioctl. The ioctl reads and updates the passed in user_reg struct. The status_index of the struct is used to know the byte in the status page to check for that event. The write_index of the struct is used to describe that event when writing out to the fd that was used for the ioctl call. The data must always include this index first when writing out data for an event. Data can be written either by write() or by writev(). For example, in memory: int index; char data[]; Psuedo code example of typical usage: struct user_reg reg; int page_fd = open("user_events_status", O_RDWR); char *page_data = mmap(NULL, PAGE_SIZE, PROT_READ, MAP_SHARED, page_fd, 0); close(page_fd); int data_fd = open("user_events_data", O_RDWR); reg.size = sizeof(reg); reg.name_args = (__u64)"test"; ioctl(data_fd, DIAG_IOCSREG, ®); int status_id = reg.status_index; int write_id = reg.write_index; struct iovec io[2]; io[0].iov_base = &write_id; io[0].iov_len = sizeof(write_id); io[1].iov_base = payload; io[1].iov_len = sizeof(payload); if (page_data[status_id]) writev(data_fd, io, 2); User events are also exposed via the dynamic_events tracefs file for both create and delete. Current status is exposed via the user_events_status tracefs file. Simple example to register a user event via dynamic_events: echo u:test >> dynamic_events cat dynamic_events u:test If an event is hooked to a probe, the probe hooked shows up: echo 1 > events/user_events/test/enable cat user_events_status 1:test # Used by ftrace Active: 1 Busy: 1 Max: 4096 If an event is not hooked to a probe, no probe status shows up: echo 0 > events/user_events/test/enable cat user_events_status 1:test Active: 1 Busy: 0 Max: 4096 Users can describe the trace event format via the following format: name[:FLAG1[,FLAG2...] [field1[;field2...]] Each field has the following format: type name Example for char array with a size of 20 named msg: echo 'u:detailed char[20] msg' >> dynamic_events cat dynamic_events u:detailed char[20] msg Data offsets are based on the data written out via write() and will be updated to reflect the correct offset in the trace_event fields. For dynamic data it is recommended to use the new __rel_loc data type. This type will be the same as __data_loc, but the offset is relative to this entry. This allows user_events to not worry about what common fields are being inserted before the data. The above format is valid for both the ioctl and the dynamic_events file. Link: https://lkml.kernel.org/r/20220118204326.2169-2-beaub@linux.microsoft.com Acked-by: Masami Hiramatsu Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/uapi/linux/user_events.h | 116 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 include/uapi/linux/user_events.h (limited to 'include') diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h new file mode 100644 index 000000000000..e570840571e1 --- /dev/null +++ b/include/uapi/linux/user_events.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (c) 2021, Microsoft Corporation. + * + * Authors: + * Beau Belgrave + */ +#ifndef _UAPI_LINUX_USER_EVENTS_H +#define _UAPI_LINUX_USER_EVENTS_H + +#include +#include + +#ifdef __KERNEL__ +#include +#else +#include +#endif + +#define USER_EVENTS_SYSTEM "user_events" +#define USER_EVENTS_PREFIX "u:" + +/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */ +#define EVENT_BIT_FTRACE 0 +#define EVENT_BIT_PERF 1 +#define EVENT_BIT_OTHER 7 + +#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE) +#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF) +#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER) + +/* Create dynamic location entry within a 32-bit value */ +#define DYN_LOC(offset, size) ((size) << 16 | (offset)) + +/* Use raw iterator for attached BPF program(s), no affect on ftrace/perf */ +#define FLAG_BPF_ITER (1 << 0) + +/* + * Describes an event registration and stores the results of the registration. + * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum + * must set the size and name_args before invocation. + */ +struct user_reg { + + /* Input: Size of the user_reg structure being used */ + __u32 size; + + /* Input: Pointer to string with event name, description and flags */ + __u64 name_args; + + /* Output: Byte index of the event within the status page */ + __u32 status_index; + + /* Output: Index of the event to use when writing data */ + __u32 write_index; +}; + +#define DIAG_IOC_MAGIC '*' + +/* Requests to register a user_event */ +#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) + +/* Requests to delete a user_event */ +#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) + +/* Data type that was passed to the BPF program */ +enum { + /* Data resides in kernel space */ + USER_BPF_DATA_KERNEL, + + /* Data resides in user space */ + USER_BPF_DATA_USER, + + /* Data is a pointer to a user_bpf_iter structure */ + USER_BPF_DATA_ITER, +}; + +/* + * Describes an iovec iterator that BPF programs can use to access data for + * a given user_event write() / writev() call. + */ +struct user_bpf_iter { + + /* Offset of the data within the first iovec */ + __u32 iov_offset; + + /* Number of iovec structures */ + __u32 nr_segs; + + /* Pointer to iovec structures */ + const struct iovec *iov; +}; + +/* Context that BPF programs receive when attached to a user_event */ +struct user_bpf_context { + + /* Data type being passed (see union below) */ + __u32 data_type; + + /* Length of the data */ + __u32 data_len; + + /* Pointer to data, varies by data type */ + union { + /* Kernel data (data_type == USER_BPF_DATA_KERNEL) */ + void *kdata; + + /* User data (data_type == USER_BPF_DATA_USER) */ + void *udata; + + /* Direct iovec (data_type == USER_BPF_DATA_ITER) */ + struct user_bpf_iter *iter; + }; +}; + +#endif /* _UAPI_LINUX_USER_EVENTS_H */ -- cgit v1.2.3 From af6b9668e85ffd1502aada8036ccbf4dbd481708 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 3 Mar 2022 17:05:33 -0500 Subject: tracing: Move the defines to create TRACE_EVENTS into their own files In an effort to add custom event macros that can be used to create your own custom events based on existing tracepoints, move the defines of the special macros used in TRACE_EVENT() into their own files such that they can be reused for TRACE_CUSTOM_EVENT(). Link: https://lkml.kernel.org/r/20220303220625.553406495@goodmis.org Cc: Ingo Molnar Cc: Andrew Morton Cc: Joel Fernandes Cc: Peter Zijlstra Cc: Masami Hiramatsu Cc: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- include/trace/stages/init.h | 37 +++ include/trace/stages/stage1_defines.h | 45 +++ include/trace/stages/stage2_defines.h | 48 ++++ include/trace/stages/stage3_defines.h | 129 +++++++++ include/trace/stages/stage4_defines.h | 57 ++++ include/trace/stages/stage5_defines.h | 83 ++++++ include/trace/stages/stage6_defines.h | 86 ++++++ include/trace/stages/stage7_defines.h | 34 +++ include/trace/trace_events.h | 499 +--------------------------------- 9 files changed, 527 insertions(+), 491 deletions(-) create mode 100644 include/trace/stages/init.h create mode 100644 include/trace/stages/stage1_defines.h create mode 100644 include/trace/stages/stage2_defines.h create mode 100644 include/trace/stages/stage3_defines.h create mode 100644 include/trace/stages/stage4_defines.h create mode 100644 include/trace/stages/stage5_defines.h create mode 100644 include/trace/stages/stage6_defines.h create mode 100644 include/trace/stages/stage7_defines.h (limited to 'include') diff --git a/include/trace/stages/init.h b/include/trace/stages/init.h new file mode 100644 index 000000000000..000bcfc8dd2e --- /dev/null +++ b/include/trace/stages/init.h @@ -0,0 +1,37 @@ + +#define __app__(x, y) str__##x##y +#define __app(x, y) __app__(x, y) + +#define TRACE_SYSTEM_STRING __app(TRACE_SYSTEM_VAR,__trace_system_name) + +#define TRACE_MAKE_SYSTEM_STR() \ + static const char TRACE_SYSTEM_STRING[] = \ + __stringify(TRACE_SYSTEM) + +TRACE_MAKE_SYSTEM_STR(); + +#undef TRACE_DEFINE_ENUM +#define TRACE_DEFINE_ENUM(a) \ + static struct trace_eval_map __used __initdata \ + __##TRACE_SYSTEM##_##a = \ + { \ + .system = TRACE_SYSTEM_STRING, \ + .eval_string = #a, \ + .eval_value = a \ + }; \ + static struct trace_eval_map __used \ + __section("_ftrace_eval_map") \ + *TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a + +#undef TRACE_DEFINE_SIZEOF +#define TRACE_DEFINE_SIZEOF(a) \ + static struct trace_eval_map __used __initdata \ + __##TRACE_SYSTEM##_##a = \ + { \ + .system = TRACE_SYSTEM_STRING, \ + .eval_string = "sizeof(" #a ")", \ + .eval_value = sizeof(a) \ + }; \ + static struct trace_eval_map __used \ + __section("_ftrace_eval_map") \ + *TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a diff --git a/include/trace/stages/stage1_defines.h b/include/trace/stages/stage1_defines.h new file mode 100644 index 000000000000..8ab88c766d2b --- /dev/null +++ b/include/trace/stages/stage1_defines.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 1 definitions for creating trace events */ + +#undef __field +#define __field(type, item) type item; + +#undef __field_ext +#define __field_ext(type, item, filter_type) type item; + +#undef __field_struct +#define __field_struct(type, item) type item; + +#undef __field_struct_ext +#define __field_struct_ext(type, item, filter_type) type item; + +#undef __array +#define __array(type, item, len) type item[len]; + +#undef __dynamic_array +#define __dynamic_array(type, item, len) u32 __data_loc_##item; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) u32 __rel_loc_##item; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(char, item, -1) + +#undef TP_STRUCT__entry +#define TP_STRUCT__entry(args...) args diff --git a/include/trace/stages/stage2_defines.h b/include/trace/stages/stage2_defines.h new file mode 100644 index 000000000000..9f2341df40da --- /dev/null +++ b/include/trace/stages/stage2_defines.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 2 definitions for creating trace events */ + +#undef TRACE_DEFINE_ENUM +#define TRACE_DEFINE_ENUM(a) + +#undef TRACE_DEFINE_SIZEOF +#define TRACE_DEFINE_SIZEOF(a) + +#undef __field +#define __field(type, item) + +#undef __field_ext +#define __field_ext(type, item, filter_type) + +#undef __field_struct +#define __field_struct(type, item) + +#undef __field_struct_ext +#define __field_struct_ext(type, item, filter_type) + +#undef __array +#define __array(type, item, len) + +#undef __dynamic_array +#define __dynamic_array(type, item, len) u32 item; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) u32 item; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) diff --git a/include/trace/stages/stage3_defines.h b/include/trace/stages/stage3_defines.h new file mode 100644 index 000000000000..0bc131993b7a --- /dev/null +++ b/include/trace/stages/stage3_defines.h @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 3 definitions for creating trace events */ + +#undef __entry +#define __entry field + +#undef TP_printk +#define TP_printk(fmt, args...) fmt "\n", args + +#undef __get_dynamic_array +#define __get_dynamic_array(field) \ + ((void *)__entry + (__entry->__data_loc_##field & 0xffff)) + +#undef __get_dynamic_array_len +#define __get_dynamic_array_len(field) \ + ((__entry->__data_loc_##field >> 16) & 0xffff) + +#undef __get_str +#define __get_str(field) ((char *)__get_dynamic_array(field)) + +#undef __get_rel_dynamic_array +#define __get_rel_dynamic_array(field) \ + ((void *)__entry + \ + offsetof(typeof(*__entry), __rel_loc_##field) + \ + sizeof(__entry->__rel_loc_##field) + \ + (__entry->__rel_loc_##field & 0xffff)) + +#undef __get_rel_dynamic_array_len +#define __get_rel_dynamic_array_len(field) \ + ((__entry->__rel_loc_##field >> 16) & 0xffff) + +#undef __get_rel_str +#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field)) + +#undef __get_bitmask +#define __get_bitmask(field) \ + ({ \ + void *__bitmask = __get_dynamic_array(field); \ + unsigned int __bitmask_size; \ + __bitmask_size = __get_dynamic_array_len(field); \ + trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ + }) + +#undef __get_rel_bitmask +#define __get_rel_bitmask(field) \ + ({ \ + void *__bitmask = __get_rel_dynamic_array(field); \ + unsigned int __bitmask_size; \ + __bitmask_size = __get_rel_dynamic_array_len(field); \ + trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ + }) + +#undef __print_flags +#define __print_flags(flag, delim, flag_array...) \ + ({ \ + static const struct trace_print_flags __flags[] = \ + { flag_array, { -1, NULL }}; \ + trace_print_flags_seq(p, delim, flag, __flags); \ + }) + +#undef __print_symbolic +#define __print_symbolic(value, symbol_array...) \ + ({ \ + static const struct trace_print_flags symbols[] = \ + { symbol_array, { -1, NULL }}; \ + trace_print_symbols_seq(p, value, symbols); \ + }) + +#undef __print_flags_u64 +#undef __print_symbolic_u64 +#if BITS_PER_LONG == 32 +#define __print_flags_u64(flag, delim, flag_array...) \ + ({ \ + static const struct trace_print_flags_u64 __flags[] = \ + { flag_array, { -1, NULL } }; \ + trace_print_flags_seq_u64(p, delim, flag, __flags); \ + }) + +#define __print_symbolic_u64(value, symbol_array...) \ + ({ \ + static const struct trace_print_flags_u64 symbols[] = \ + { symbol_array, { -1, NULL } }; \ + trace_print_symbols_seq_u64(p, value, symbols); \ + }) +#else +#define __print_flags_u64(flag, delim, flag_array...) \ + __print_flags(flag, delim, flag_array) + +#define __print_symbolic_u64(value, symbol_array...) \ + __print_symbolic(value, symbol_array) +#endif + +#undef __print_hex +#define __print_hex(buf, buf_len) \ + trace_print_hex_seq(p, buf, buf_len, false) + +#undef __print_hex_str +#define __print_hex_str(buf, buf_len) \ + trace_print_hex_seq(p, buf, buf_len, true) + +#undef __print_array +#define __print_array(array, count, el_size) \ + ({ \ + BUILD_BUG_ON(el_size != 1 && el_size != 2 && \ + el_size != 4 && el_size != 8); \ + trace_print_array_seq(p, array, count, el_size); \ + }) + +#undef __print_hex_dump +#define __print_hex_dump(prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii) \ + trace_print_hex_dump_seq(p, prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii) + +#undef __print_ns_to_secs +#define __print_ns_to_secs(value) \ + ({ \ + u64 ____val = (u64)(value); \ + do_div(____val, NSEC_PER_SEC); \ + ____val; \ + }) + +#undef __print_ns_without_secs +#define __print_ns_without_secs(value) \ + ({ \ + u64 ____val = (u64)(value); \ + (u32) do_div(____val, NSEC_PER_SEC); \ + }) diff --git a/include/trace/stages/stage4_defines.h b/include/trace/stages/stage4_defines.h new file mode 100644 index 000000000000..780a10fa5279 --- /dev/null +++ b/include/trace/stages/stage4_defines.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 4 definitions for creating trace events */ + +#undef __field_ext +#define __field_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = _filter_type }, + +#undef __field_struct_ext +#define __field_struct_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + 0, .filter_type = _filter_type }, + +#undef __field +#define __field(type, item) __field_ext(type, item, FILTER_OTHER) + +#undef __field_struct +#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER) + +#undef __array +#define __array(_type, _item, _len) { \ + .type = #_type"["__stringify(_len)"]", .name = #_item, \ + .size = sizeof(_type[_len]), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, + +#undef __dynamic_array +#define __dynamic_array(_type, _item, _len) { \ + .type = "__data_loc " #_type "[]", .name = #_item, \ + .size = 4, .align = 4, \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(_type, _item, _len) { \ + .type = "__rel_loc " #_type "[]", .name = #_item, \ + .size = 4, .align = 4, \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) diff --git a/include/trace/stages/stage5_defines.h b/include/trace/stages/stage5_defines.h new file mode 100644 index 000000000000..fb15394aae31 --- /dev/null +++ b/include/trace/stages/stage5_defines.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 5 definitions for creating trace events */ + +/* + * remember the offset of each array from the beginning of the event. + */ + +#undef __entry +#define __entry entry + +#undef __field +#define __field(type, item) + +#undef __field_ext +#define __field_ext(type, item, filter_type) + +#undef __field_struct +#define __field_struct(type, item) + +#undef __field_struct_ext +#define __field_struct_ext(type, item, filter_type) + +#undef __array +#define __array(type, item, len) + +#undef __dynamic_array +#define __dynamic_array(type, item, len) \ + __item_length = (len) * sizeof(type); \ + __data_offsets->item = __data_size + \ + offsetof(typeof(*entry), __data); \ + __data_offsets->item |= __item_length << 16; \ + __data_size += __item_length; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, \ + strlen((src) ? (const char *)(src) : "(null)") + 1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) \ + __item_length = (len) * sizeof(type); \ + __data_offsets->item = __data_size + \ + offsetof(typeof(*entry), __data) - \ + offsetof(typeof(*entry), __rel_loc_##item) - \ + sizeof(u32); \ + __data_offsets->item |= __item_length << 16; \ + __data_size += __item_length; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, \ + strlen((src) ? (const char *)(src) : "(null)") + 1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1) +/* + * __bitmask_size_in_bytes_raw is the number of bytes needed to hold + * num_possible_cpus(). + */ +#define __bitmask_size_in_bytes_raw(nr_bits) \ + (((nr_bits) + 7) / 8) + +#define __bitmask_size_in_longs(nr_bits) \ + ((__bitmask_size_in_bytes_raw(nr_bits) + \ + ((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8)) + +/* + * __bitmask_size_in_bytes is the number of bytes needed to hold + * num_possible_cpus() padded out to the nearest long. This is what + * is saved in the buffer, just to be consistent. + */ +#define __bitmask_size_in_bytes(nr_bits) \ + (__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8)) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, \ + __bitmask_size_in_longs(nr_bits)) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, \ + __bitmask_size_in_longs(nr_bits)) diff --git a/include/trace/stages/stage6_defines.h b/include/trace/stages/stage6_defines.h new file mode 100644 index 000000000000..b3a1f26026be --- /dev/null +++ b/include/trace/stages/stage6_defines.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 6 definitions for creating trace events */ + +#undef __entry +#define __entry entry + +#undef __field +#define __field(type, item) + +#undef __field_struct +#define __field_struct(type, item) + +#undef __array +#define __array(type, item, len) + +#undef __dynamic_array +#define __dynamic_array(type, item, len) \ + __entry->__data_loc_##item = __data_offsets.item; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __assign_str +#define __assign_str(dst, src) \ + strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)"); + +#undef __assign_str_len +#define __assign_str_len(dst, src, len) \ + do { \ + memcpy(__get_str(dst), (src), (len)); \ + __get_str(dst)[len] = '\0'; \ + } while(0) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) + +#undef __get_bitmask +#define __get_bitmask(field) (char *)__get_dynamic_array(field) + +#undef __assign_bitmask +#define __assign_bitmask(dst, src, nr_bits) \ + memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) \ + __entry->__rel_loc_##item = __data_offsets.item; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __assign_rel_str +#define __assign_rel_str(dst, src) \ + strcpy(__get_rel_str(dst), (src) ? (const char *)(src) : "(null)"); + +#undef __assign_rel_str_len +#define __assign_rel_str_len(dst, src, len) \ + do { \ + memcpy(__get_rel_str(dst), (src), (len)); \ + __get_rel_str(dst)[len] = '\0'; \ + } while (0) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) + +#undef __get_rel_bitmask +#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field) + +#undef __assign_rel_bitmask +#define __assign_rel_bitmask(dst, src, nr_bits) \ + memcpy(__get_rel_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) + +#undef TP_fast_assign +#define TP_fast_assign(args...) args + +#undef __perf_count +#define __perf_count(c) (c) + +#undef __perf_task +#define __perf_task(t) (t) diff --git a/include/trace/stages/stage7_defines.h b/include/trace/stages/stage7_defines.h new file mode 100644 index 000000000000..d65445328f18 --- /dev/null +++ b/include/trace/stages/stage7_defines.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 7 definitions for creating trace events */ + +#undef __entry +#define __entry REC + +#undef __print_flags +#undef __print_symbolic +#undef __print_hex +#undef __print_hex_str +#undef __get_dynamic_array +#undef __get_dynamic_array_len +#undef __get_str +#undef __get_bitmask +#undef __get_rel_dynamic_array +#undef __get_rel_dynamic_array_len +#undef __get_rel_str +#undef __get_rel_bitmask +#undef __print_array +#undef __print_hex_dump + +/* + * The below is not executed in the kernel. It is only what is + * displayed in the print format for userspace to parse. + */ +#undef __print_ns_to_secs +#define __print_ns_to_secs(val) (val) / 1000000000UL + +#undef __print_ns_without_secs +#define __print_ns_without_secs(val) (val) % 1000000000UL + +#undef TP_printk +#define TP_printk(fmt, args...) "\"" fmt "\", " __stringify(args) diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 3d29919045af..8a8cd66cc6d5 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -24,42 +24,7 @@ #define TRACE_SYSTEM_VAR TRACE_SYSTEM #endif -#define __app__(x, y) str__##x##y -#define __app(x, y) __app__(x, y) - -#define TRACE_SYSTEM_STRING __app(TRACE_SYSTEM_VAR,__trace_system_name) - -#define TRACE_MAKE_SYSTEM_STR() \ - static const char TRACE_SYSTEM_STRING[] = \ - __stringify(TRACE_SYSTEM) - -TRACE_MAKE_SYSTEM_STR(); - -#undef TRACE_DEFINE_ENUM -#define TRACE_DEFINE_ENUM(a) \ - static struct trace_eval_map __used __initdata \ - __##TRACE_SYSTEM##_##a = \ - { \ - .system = TRACE_SYSTEM_STRING, \ - .eval_string = #a, \ - .eval_value = a \ - }; \ - static struct trace_eval_map __used \ - __section("_ftrace_eval_map") \ - *TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a - -#undef TRACE_DEFINE_SIZEOF -#define TRACE_DEFINE_SIZEOF(a) \ - static struct trace_eval_map __used __initdata \ - __##TRACE_SYSTEM##_##a = \ - { \ - .system = TRACE_SYSTEM_STRING, \ - .eval_string = "sizeof(" #a ")", \ - .eval_value = sizeof(a) \ - }; \ - static struct trace_eval_map __used \ - __section("_ftrace_eval_map") \ - *TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a +#include "stages/init.h" /* * DECLARE_EVENT_CLASS can be used to add a generic function @@ -80,48 +45,7 @@ TRACE_MAKE_SYSTEM_STR(); PARAMS(print)); \ DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args)); - -#undef __field -#define __field(type, item) type item; - -#undef __field_ext -#define __field_ext(type, item, filter_type) type item; - -#undef __field_struct -#define __field_struct(type, item) type item; - -#undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) type item; - -#undef __array -#define __array(type, item, len) type item[len]; - -#undef __dynamic_array -#define __dynamic_array(type, item, len) u32 __data_loc_##item; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) u32 __rel_loc_##item; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(char, item, -1) - -#undef TP_STRUCT__entry -#define TP_STRUCT__entry(args...) args +#include "stages/stage1_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print) \ @@ -185,50 +109,7 @@ TRACE_MAKE_SYSTEM_STR(); * The size of an array is also encoded, in the higher 16 bits of . */ -#undef TRACE_DEFINE_ENUM -#define TRACE_DEFINE_ENUM(a) - -#undef TRACE_DEFINE_SIZEOF -#define TRACE_DEFINE_SIZEOF(a) - -#undef __field -#define __field(type, item) - -#undef __field_ext -#define __field_ext(type, item, filter_type) - -#undef __field_struct -#define __field_struct(type, item) - -#undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) - -#undef __array -#define __array(type, item, len) - -#undef __dynamic_array -#define __dynamic_array(type, item, len) u32 item; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) u32 item; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) +#include "stages/stage2_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -300,131 +181,7 @@ TRACE_MAKE_SYSTEM_STR(); * in binary. */ -#undef __entry -#define __entry field - -#undef TP_printk -#define TP_printk(fmt, args...) fmt "\n", args - -#undef __get_dynamic_array -#define __get_dynamic_array(field) \ - ((void *)__entry + (__entry->__data_loc_##field & 0xffff)) - -#undef __get_dynamic_array_len -#define __get_dynamic_array_len(field) \ - ((__entry->__data_loc_##field >> 16) & 0xffff) - -#undef __get_str -#define __get_str(field) ((char *)__get_dynamic_array(field)) - -#undef __get_rel_dynamic_array -#define __get_rel_dynamic_array(field) \ - ((void *)__entry + \ - offsetof(typeof(*__entry), __rel_loc_##field) + \ - sizeof(__entry->__rel_loc_##field) + \ - (__entry->__rel_loc_##field & 0xffff)) - -#undef __get_rel_dynamic_array_len -#define __get_rel_dynamic_array_len(field) \ - ((__entry->__rel_loc_##field >> 16) & 0xffff) - -#undef __get_rel_str -#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field)) - -#undef __get_bitmask -#define __get_bitmask(field) \ - ({ \ - void *__bitmask = __get_dynamic_array(field); \ - unsigned int __bitmask_size; \ - __bitmask_size = __get_dynamic_array_len(field); \ - trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ - }) - -#undef __get_rel_bitmask -#define __get_rel_bitmask(field) \ - ({ \ - void *__bitmask = __get_rel_dynamic_array(field); \ - unsigned int __bitmask_size; \ - __bitmask_size = __get_rel_dynamic_array_len(field); \ - trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ - }) - -#undef __print_flags -#define __print_flags(flag, delim, flag_array...) \ - ({ \ - static const struct trace_print_flags __flags[] = \ - { flag_array, { -1, NULL }}; \ - trace_print_flags_seq(p, delim, flag, __flags); \ - }) - -#undef __print_symbolic -#define __print_symbolic(value, symbol_array...) \ - ({ \ - static const struct trace_print_flags symbols[] = \ - { symbol_array, { -1, NULL }}; \ - trace_print_symbols_seq(p, value, symbols); \ - }) - -#undef __print_flags_u64 -#undef __print_symbolic_u64 -#if BITS_PER_LONG == 32 -#define __print_flags_u64(flag, delim, flag_array...) \ - ({ \ - static const struct trace_print_flags_u64 __flags[] = \ - { flag_array, { -1, NULL } }; \ - trace_print_flags_seq_u64(p, delim, flag, __flags); \ - }) - -#define __print_symbolic_u64(value, symbol_array...) \ - ({ \ - static const struct trace_print_flags_u64 symbols[] = \ - { symbol_array, { -1, NULL } }; \ - trace_print_symbols_seq_u64(p, value, symbols); \ - }) -#else -#define __print_flags_u64(flag, delim, flag_array...) \ - __print_flags(flag, delim, flag_array) - -#define __print_symbolic_u64(value, symbol_array...) \ - __print_symbolic(value, symbol_array) -#endif - -#undef __print_hex -#define __print_hex(buf, buf_len) \ - trace_print_hex_seq(p, buf, buf_len, false) - -#undef __print_hex_str -#define __print_hex_str(buf, buf_len) \ - trace_print_hex_seq(p, buf, buf_len, true) - -#undef __print_array -#define __print_array(array, count, el_size) \ - ({ \ - BUILD_BUG_ON(el_size != 1 && el_size != 2 && \ - el_size != 4 && el_size != 8); \ - trace_print_array_seq(p, array, count, el_size); \ - }) - -#undef __print_hex_dump -#define __print_hex_dump(prefix_str, prefix_type, \ - rowsize, groupsize, buf, len, ascii) \ - trace_print_hex_dump_seq(p, prefix_str, prefix_type, \ - rowsize, groupsize, buf, len, ascii) - -#undef __print_ns_to_secs -#define __print_ns_to_secs(value) \ - ({ \ - u64 ____val = (u64)(value); \ - do_div(____val, NSEC_PER_SEC); \ - ____val; \ - }) - -#undef __print_ns_without_secs -#define __print_ns_without_secs(value) \ - ({ \ - u64 ____val = (u64)(value); \ - (u32) do_div(____val, NSEC_PER_SEC); \ - }) +#include "stages/stage3_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -479,59 +236,7 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#undef __field_ext -#define __field_ext(_type, _item, _filter_type) { \ - .type = #_type, .name = #_item, \ - .size = sizeof(_type), .align = __alignof__(_type), \ - .is_signed = is_signed_type(_type), .filter_type = _filter_type }, - -#undef __field_struct_ext -#define __field_struct_ext(_type, _item, _filter_type) { \ - .type = #_type, .name = #_item, \ - .size = sizeof(_type), .align = __alignof__(_type), \ - 0, .filter_type = _filter_type }, - -#undef __field -#define __field(type, item) __field_ext(type, item, FILTER_OTHER) - -#undef __field_struct -#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER) - -#undef __array -#define __array(_type, _item, _len) { \ - .type = #_type"["__stringify(_len)"]", .name = #_item, \ - .size = sizeof(_type[_len]), .align = __alignof__(_type), \ - .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, - -#undef __dynamic_array -#define __dynamic_array(_type, _item, _len) { \ - .type = "__data_loc " #_type "[]", .name = #_item, \ - .size = 4, .align = 4, \ - .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(_type, _item, _len) { \ - .type = "__rel_loc " #_type "[]", .name = #_item, \ - .size = 4, .align = 4, \ - .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) +#include "stages/stage4_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \ @@ -544,85 +249,7 @@ static struct trace_event_fields trace_event_fields_##call[] = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -/* - * remember the offset of each array from the beginning of the event. - */ - -#undef __entry -#define __entry entry - -#undef __field -#define __field(type, item) - -#undef __field_ext -#define __field_ext(type, item, filter_type) - -#undef __field_struct -#define __field_struct(type, item) - -#undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) - -#undef __array -#define __array(type, item, len) - -#undef __dynamic_array -#define __dynamic_array(type, item, len) \ - __item_length = (len) * sizeof(type); \ - __data_offsets->item = __data_size + \ - offsetof(typeof(*entry), __data); \ - __data_offsets->item |= __item_length << 16; \ - __data_size += __item_length; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, \ - strlen((src) ? (const char *)(src) : "(null)") + 1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) \ - __item_length = (len) * sizeof(type); \ - __data_offsets->item = __data_size + \ - offsetof(typeof(*entry), __data) - \ - offsetof(typeof(*entry), __rel_loc_##item) - \ - sizeof(u32); \ - __data_offsets->item |= __item_length << 16; \ - __data_size += __item_length; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, \ - strlen((src) ? (const char *)(src) : "(null)") + 1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1) -/* - * __bitmask_size_in_bytes_raw is the number of bytes needed to hold - * num_possible_cpus(). - */ -#define __bitmask_size_in_bytes_raw(nr_bits) \ - (((nr_bits) + 7) / 8) - -#define __bitmask_size_in_longs(nr_bits) \ - ((__bitmask_size_in_bytes_raw(nr_bits) + \ - ((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8)) - -/* - * __bitmask_size_in_bytes is the number of bytes needed to hold - * num_possible_cpus() padded out to the nearest long. This is what - * is saved in the buffer, just to be consistent. - */ -#define __bitmask_size_in_bytes(nr_bits) \ - (__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8)) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, \ - __bitmask_size_in_longs(nr_bits)) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, \ - __bitmask_size_in_longs(nr_bits)) +#include "stages/stage5_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -745,88 +372,7 @@ static inline notrace int trace_event_get_offsets_##call( \ #define _TRACE_PERF_INIT(call) #endif /* CONFIG_PERF_EVENTS */ -#undef __entry -#define __entry entry - -#undef __field -#define __field(type, item) - -#undef __field_struct -#define __field_struct(type, item) - -#undef __array -#define __array(type, item, len) - -#undef __dynamic_array -#define __dynamic_array(type, item, len) \ - __entry->__data_loc_##item = __data_offsets.item; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __assign_str -#define __assign_str(dst, src) \ - strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)"); - -#undef __assign_str_len -#define __assign_str_len(dst, src, len) \ - do { \ - memcpy(__get_str(dst), (src), (len)); \ - __get_str(dst)[len] = '\0'; \ - } while(0) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) - -#undef __get_bitmask -#define __get_bitmask(field) (char *)__get_dynamic_array(field) - -#undef __assign_bitmask -#define __assign_bitmask(dst, src, nr_bits) \ - memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) \ - __entry->__rel_loc_##item = __data_offsets.item; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __assign_rel_str -#define __assign_rel_str(dst, src) \ - strcpy(__get_rel_str(dst), (src) ? (const char *)(src) : "(null)"); - -#undef __assign_rel_str_len -#define __assign_rel_str_len(dst, src, len) \ - do { \ - memcpy(__get_rel_str(dst), (src), (len)); \ - __get_rel_str(dst)[len] = '\0'; \ - } while (0) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) - -#undef __get_rel_bitmask -#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field) - -#undef __assign_rel_bitmask -#define __assign_rel_bitmask(dst, src, nr_bits) \ - memcpy(__get_rel_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) - -#undef TP_fast_assign -#define TP_fast_assign(args...) args - -#undef __perf_count -#define __perf_count(c) (c) - -#undef __perf_task -#define __perf_task(t) (t) +#include "stages/stage6_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -872,36 +418,7 @@ static inline void ftrace_test_probe_##call(void) \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#undef __entry -#define __entry REC - -#undef __print_flags -#undef __print_symbolic -#undef __print_hex -#undef __print_hex_str -#undef __get_dynamic_array -#undef __get_dynamic_array_len -#undef __get_str -#undef __get_bitmask -#undef __get_rel_dynamic_array -#undef __get_rel_dynamic_array_len -#undef __get_rel_str -#undef __get_rel_bitmask -#undef __print_array -#undef __print_hex_dump - -/* - * The below is not executed in the kernel. It is only what is - * displayed in the print format for userspace to parse. - */ -#undef __print_ns_to_secs -#define __print_ns_to_secs(val) (val) / 1000000000UL - -#undef __print_ns_without_secs -#define __print_ns_without_secs(val) (val) % 1000000000UL - -#undef TP_printk -#define TP_printk(fmt, args...) "\"" fmt "\", " __stringify(args) +#include "stages/stage7_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ -- cgit v1.2.3 From 3a73333fb370f7b65de9d94c53df503642bda789 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 3 Mar 2022 17:05:34 -0500 Subject: tracing: Add TRACE_CUSTOM_EVENT() macro To make it really easy to add custom events from modules, add a TRACE_CUSTOM_EVENT() macro that acts just like the TRACE_EVENT() macro, but creates a custom event to an already existing tracepoint. The trace_custom_sched.[ch] has been updated to use this new macro to show how simple it is. Link: https://lkml.kernel.org/r/20220303220625.738622494@goodmis.org Cc: Ingo Molnar Cc: Andrew Morton Cc: Joel Fernandes Cc: Peter Zijlstra Cc: Masami Hiramatsu Cc: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 24 ++- include/trace/define_custom_trace.h | 77 +++++++++ include/trace/trace_custom_events.h | 221 +++++++++++++++++++++++++ samples/trace_events/Makefile | 2 +- samples/trace_events/trace_custom_sched.c | 259 +++--------------------------- samples/trace_events/trace_custom_sched.h | 95 +++++++++++ 6 files changed, 441 insertions(+), 237 deletions(-) create mode 100644 include/trace/define_custom_trace.h create mode 100644 include/trace/trace_custom_events.h create mode 100644 samples/trace_events/trace_custom_sched.h (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 70c069aef02c..9b09fd633d48 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -315,6 +315,7 @@ enum { TRACE_EVENT_FL_KPROBE_BIT, TRACE_EVENT_FL_UPROBE_BIT, TRACE_EVENT_FL_EPROBE_BIT, + TRACE_EVENT_FL_CUSTOM_BIT, }; /* @@ -328,6 +329,9 @@ enum { * KPROBE - Event is a kprobe * UPROBE - Event is a uprobe * EPROBE - Event is an event probe + * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) + * This is set when the custom event has not been attached + * to a tracepoint yet, then it is cleared when it is. */ enum { TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), @@ -339,6 +343,7 @@ enum { TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), TRACE_EVENT_FL_UPROBE = (1 << TRACE_EVENT_FL_UPROBE_BIT), TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), + TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) @@ -440,7 +445,9 @@ static inline bool bpf_prog_array_valid(struct trace_event_call *call) static inline const char * trace_event_name(struct trace_event_call *call) { - if (call->flags & TRACE_EVENT_FL_TRACEPOINT) + if (call->flags & TRACE_EVENT_FL_CUSTOM) + return call->name; + else if (call->flags & TRACE_EVENT_FL_TRACEPOINT) return call->tp ? call->tp->name : NULL; else return call->name; @@ -901,3 +908,18 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type, #endif #endif /* _LINUX_TRACE_EVENT_H */ + +/* + * Note: we keep the TRACE_CUSTOM_EVENT outside the include file ifdef protection. + * This is due to the way trace custom events work. If a file includes two + * trace event headers under one "CREATE_CUSTOM_TRACE_EVENTS" the first include + * will override the TRACE_CUSTOM_EVENT and break the second include. + */ + +#ifndef TRACE_CUSTOM_EVENT + +#define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print) +#define DEFINE_CUSTOM_EVENT(template, name, proto, args) +#define TRACE_CUSTOM_EVENT(name, proto, args, struct, assign, print) + +#endif /* ifdef TRACE_CUSTOM_EVENT (see note above) */ diff --git a/include/trace/define_custom_trace.h b/include/trace/define_custom_trace.h new file mode 100644 index 000000000000..5827a4c92c74 --- /dev/null +++ b/include/trace/define_custom_trace.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Trace files that want to automate creation of all tracepoints defined + * in their file should include this file. The following are macros that the + * trace file may define: + * + * TRACE_SYSTEM defines the system the tracepoint is for + * + * TRACE_INCLUDE_FILE if the file name is something other than TRACE_SYSTEM.h + * This macro may be defined to tell define_trace.h what file to include. + * Note, leave off the ".h". + * + * TRACE_INCLUDE_PATH if the path is something other than core kernel include/trace + * then this macro can define the path to use. Note, the path is relative to + * define_trace.h, not the file including it. Full path names for out of tree + * modules must be used. + */ + +#ifdef CREATE_CUSTOM_TRACE_EVENTS + +/* Prevent recursion */ +#undef CREATE_CUSTOM_TRACE_EVENTS + +#include + +#undef TRACE_CUSTOM_EVENT +#define TRACE_CUSTOM_EVENT(name, proto, args, tstruct, assign, print) + +#undef DEFINE_CUSTOM_EVENT +#define DEFINE_CUSTOM_EVENT(template, name, proto, args) + +#undef TRACE_INCLUDE +#undef __TRACE_INCLUDE + +#ifndef TRACE_INCLUDE_FILE +# define TRACE_INCLUDE_FILE TRACE_SYSTEM +# define UNDEF_TRACE_INCLUDE_FILE +#endif + +#ifndef TRACE_INCLUDE_PATH +# define __TRACE_INCLUDE(system) +# define UNDEF_TRACE_INCLUDE_PATH +#else +# define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h) +#endif + +# define TRACE_INCLUDE(system) __TRACE_INCLUDE(system) + +/* Let the trace headers be reread */ +#define TRACE_CUSTOM_MULTI_READ + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +#ifdef TRACEPOINTS_ENABLED +#include +#endif + +#undef TRACE_CUSTOM_EVENT +#undef DECLARE_CUSTOM_EVENT_CLASS +#undef DEFINE_CUSTOM_EVENT +#undef TRACE_CUSTOM_MULTI_READ + +/* Only undef what we defined in this file */ +#ifdef UNDEF_TRACE_INCLUDE_FILE +# undef TRACE_INCLUDE_FILE +# undef UNDEF_TRACE_INCLUDE_FILE +#endif + +#ifdef UNDEF_TRACE_INCLUDE_PATH +# undef TRACE_INCLUDE_PATH +# undef UNDEF_TRACE_INCLUDE_PATH +#endif + +/* We may be processing more files */ +#define CREATE_CUSTOM_TRACE_POINTS + +#endif /* CREATE_CUSTOM_TRACE_POINTS */ diff --git a/include/trace/trace_custom_events.h b/include/trace/trace_custom_events.h new file mode 100644 index 000000000000..b567c7202339 --- /dev/null +++ b/include/trace/trace_custom_events.h @@ -0,0 +1,221 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This is similar to the trace_events.h file, but is to only + * create custom trace events to be attached to existing tracepoints. + * Where as the TRACE_EVENT() macro (from trace_events.h) will create + * both the trace event and the tracepoint it will attach the event to, + * TRACE_CUSTOM_EVENT() is to create only a custom version of an existing + * trace event (created by TRACE_EVENT() or DEFINE_EVENT()), and will + * be placed in the "custom" system. + */ + +#include + +/* All custom events are placed in the custom group */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM custom + +#ifndef TRACE_SYSTEM_VAR +#define TRACE_SYSTEM_VAR TRACE_SYSTEM +#endif + +/* The init stage creates the system string and enum mappings */ + +#include "stages/init.h" + +#undef TRACE_CUSTOM_EVENT +#define TRACE_CUSTOM_EVENT(name, proto, args, tstruct, assign, print) \ + DECLARE_CUSTOM_EVENT_CLASS(name, \ + PARAMS(proto), \ + PARAMS(args), \ + PARAMS(tstruct), \ + PARAMS(assign), \ + PARAMS(print)); \ + DEFINE_CUSTOM_EVENT(name, name, PARAMS(proto), PARAMS(args)); + +/* Stage 1 creates the structure of the recorded event layout */ + +#include "stages/stage1_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print) \ + struct trace_custom_event_raw_##name { \ + struct trace_entry ent; \ + tstruct \ + char __data[]; \ + }; \ + \ + static struct trace_event_class custom_event_class_##name; + +#undef DEFINE_CUSTOM_EVENT +#define DEFINE_CUSTOM_EVENT(template, name, proto, args) \ + static struct trace_event_call __used \ + __attribute__((__aligned__(4))) custom_event_##name + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 2 creates the custom class */ + +#include "stages/stage2_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ + struct trace_custom_event_data_offsets_##call { \ + tstruct; \ + }; + +#undef DEFINE_CUSTOM_EVENT +#define DEFINE_CUSTOM_EVENT(template, name, proto, args) + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 3 create the way to print the custom event */ + +#include "stages/stage3_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +static notrace enum print_line_t \ +trace_custom_raw_output_##call(struct trace_iterator *iter, int flags, \ + struct trace_event *trace_event) \ +{ \ + struct trace_seq *s = &iter->seq; \ + struct trace_seq __maybe_unused *p = &iter->tmp_seq; \ + struct trace_custom_event_raw_##call *field; \ + int ret; \ + \ + field = (typeof(field))iter->ent; \ + \ + ret = trace_raw_output_prep(iter, trace_event); \ + if (ret != TRACE_TYPE_HANDLED) \ + return ret; \ + \ + trace_event_printf(iter, print); \ + \ + return trace_handle_return(s); \ +} \ +static struct trace_event_functions trace_custom_event_type_funcs_##call = { \ + .trace = trace_custom_raw_output_##call, \ +}; + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 4 creates the offset layout for the fields */ + +#include "stages/stage4_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, func, print) \ +static struct trace_event_fields trace_custom_event_fields_##call[] = { \ + tstruct \ + {} }; + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 5 creates the helper function for dynamic fields */ + +#include "stages/stage5_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +static inline notrace int trace_custom_event_get_offsets_##call( \ + struct trace_custom_event_data_offsets_##call *__data_offsets, proto) \ +{ \ + int __data_size = 0; \ + int __maybe_unused __item_length; \ + struct trace_custom_event_raw_##call __maybe_unused *entry; \ + \ + tstruct; \ + \ + return __data_size; \ +} + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 6 creates the probe function that records the event */ + +#include "stages/stage6_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ + \ +static notrace void \ +trace_custom_event_raw_event_##call(void *__data, proto) \ +{ \ + struct trace_event_file *trace_file = __data; \ + struct trace_custom_event_data_offsets_##call __maybe_unused __data_offsets; \ + struct trace_event_buffer fbuffer; \ + struct trace_custom_event_raw_##call *entry; \ + int __data_size; \ + \ + if (trace_trigger_soft_disabled(trace_file)) \ + return; \ + \ + __data_size = trace_custom_event_get_offsets_##call(&__data_offsets, args); \ + \ + entry = trace_event_buffer_reserve(&fbuffer, trace_file, \ + sizeof(*entry) + __data_size); \ + \ + if (!entry) \ + return; \ + \ + tstruct \ + \ + { assign; } \ + \ + trace_event_buffer_commit(&fbuffer); \ +} +/* + * The ftrace_test_custom_probe is compiled out, it is only here as a build time check + * to make sure that if the tracepoint handling changes, the ftrace probe will + * fail to compile unless it too is updated. + */ + +#undef DEFINE_CUSTOM_EVENT +#define DEFINE_CUSTOM_EVENT(template, call, proto, args) \ +static inline void ftrace_test_custom_probe_##call(void) \ +{ \ + check_trace_callback_type_##call(trace_custom_event_raw_event_##template); \ +} + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 7 creates the actual class and event structure for the custom event */ + +#include "stages/stage7_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +static char custom_print_fmt_##call[] = print; \ +static struct trace_event_class __used __refdata custom_event_class_##call = { \ + .system = TRACE_SYSTEM_STRING, \ + .fields_array = trace_custom_event_fields_##call, \ + .fields = LIST_HEAD_INIT(custom_event_class_##call.fields),\ + .raw_init = trace_event_raw_init, \ + .probe = trace_custom_event_raw_event_##call, \ + .reg = trace_event_reg, \ +}; + +#undef DEFINE_CUSTOM_EVENT +#define DEFINE_CUSTOM_EVENT(template, call, proto, args) \ + \ +static struct trace_event_call __used custom_event_##call = { \ + .name = #call, \ + .class = &custom_event_class_##template, \ + .event.funcs = &trace_custom_event_type_funcs_##template, \ + .print_fmt = custom_print_fmt_##template, \ + .flags = TRACE_EVENT_FL_CUSTOM, \ +}; \ +static inline int trace_custom_event_##call##_update(struct tracepoint *tp) \ +{ \ + if (tp->name && strcmp(tp->name, #call) == 0) { \ + custom_event_##call.tp = tp; \ + custom_event_##call.flags = TRACE_EVENT_FL_TRACEPOINT; \ + return 1; \ + } \ + return 0; \ +} \ +static struct trace_event_call __used \ +__section("_ftrace_events") *__custom_event_##call = &custom_event_##call + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) diff --git a/samples/trace_events/Makefile b/samples/trace_events/Makefile index e98afc447fe1..b3808bb4cf8b 100644 --- a/samples/trace_events/Makefile +++ b/samples/trace_events/Makefile @@ -11,7 +11,7 @@ # Here trace-events-sample.c does the CREATE_TRACE_POINTS. # CFLAGS_trace-events-sample.o := -I$(src) +CFLAGS_trace_custom_sched.o := -I$(src) obj-$(CONFIG_SAMPLE_TRACE_EVENTS) += trace-events-sample.o - obj-$(CONFIG_SAMPLE_TRACE_CUSTOM_EVENTS) += trace_custom_sched.o diff --git a/samples/trace_events/trace_custom_sched.c b/samples/trace_events/trace_custom_sched.c index 70a12c32ff99..b99d9ab7db85 100644 --- a/samples/trace_events/trace_custom_sched.c +++ b/samples/trace_events/trace_custom_sched.c @@ -11,256 +11,45 @@ #include #include #include -#include - -#define THIS_SYSTEM "custom_sched" - -#define SCHED_PRINT_FMT \ - C("prev_prio=%d next_pid=%d next_prio=%d", REC->prev_prio, REC->next_pid, \ - REC->next_prio) - -#define SCHED_WAKING_FMT \ - C("pid=%d prio=%d", REC->pid, REC->prio) - -#undef C -#define C(a, b...) a, b - -static struct trace_event_fields sched_switch_fields[] = { - { - .type = "unsigned short", - .name = "prev_prio", - .size = sizeof(short), - .align = __alignof__(short), - .is_signed = 0, - .filter_type = FILTER_OTHER, - }, - { - .type = "unsigned short", - .name = "next_prio", - .size = sizeof(short), - .align = __alignof__(short), - .is_signed = 0, - .filter_type = FILTER_OTHER, - }, - { - .type = "unsigned int", - .name = "next_prio", - .size = sizeof(int), - .align = __alignof__(int), - .is_signed = 0, - .filter_type = FILTER_OTHER, - }, - {} -}; - -struct sched_event { - struct trace_entry ent; - unsigned short prev_prio; - unsigned short next_prio; - unsigned int next_pid; -}; - -static struct trace_event_fields sched_waking_fields[] = { - { - .type = "unsigned int", - .name = "pid", - .size = sizeof(int), - .align = __alignof__(int), - .is_signed = 0, - .filter_type = FILTER_OTHER, - }, - { - .type = "unsigned short", - .name = "prio", - .size = sizeof(short), - .align = __alignof__(short), - .is_signed = 0, - .filter_type = FILTER_OTHER, - }, - {} -}; - -struct wake_event { - struct trace_entry ent; - unsigned int pid; - unsigned short prio; -}; - -static void sched_switch_probe(void *data, bool preempt, struct task_struct *prev, - struct task_struct *next) -{ - struct trace_event_file *trace_file = data; - struct trace_event_buffer fbuffer; - struct sched_event *entry; - - if (trace_trigger_soft_disabled(trace_file)) - return; - - entry = trace_event_buffer_reserve(&fbuffer, trace_file, - sizeof(*entry)); - - if (!entry) - return; - - entry->prev_prio = prev->prio; - entry->next_prio = next->prio; - entry->next_pid = next->pid; - - trace_event_buffer_commit(&fbuffer); -} - -static struct trace_event_class sched_switch_class = { - .system = THIS_SYSTEM, - .reg = trace_event_reg, - .fields_array = sched_switch_fields, - .fields = LIST_HEAD_INIT(sched_switch_class.fields), - .probe = sched_switch_probe, -}; - -static void sched_waking_probe(void *data, struct task_struct *t) -{ - struct trace_event_file *trace_file = data; - struct trace_event_buffer fbuffer; - struct wake_event *entry; - - if (trace_trigger_soft_disabled(trace_file)) - return; - - entry = trace_event_buffer_reserve(&fbuffer, trace_file, - sizeof(*entry)); - - if (!entry) - return; - - entry->prio = t->prio; - entry->pid = t->pid; - - trace_event_buffer_commit(&fbuffer); -} - -static struct trace_event_class sched_waking_class = { - .system = THIS_SYSTEM, - .reg = trace_event_reg, - .fields_array = sched_waking_fields, - .fields = LIST_HEAD_INIT(sched_waking_class.fields), - .probe = sched_waking_probe, -}; - -static enum print_line_t sched_switch_output(struct trace_iterator *iter, int flags, - struct trace_event *trace_event) -{ - struct trace_seq *s = &iter->seq; - struct sched_event *REC = (struct sched_event *)iter->ent; - int ret; - - ret = trace_raw_output_prep(iter, trace_event); - if (ret != TRACE_TYPE_HANDLED) - return ret; - - trace_seq_printf(s, SCHED_PRINT_FMT); - trace_seq_putc(s, '\n'); - return trace_handle_return(s); -} - -static struct trace_event_functions sched_switch_funcs = { - .trace = sched_switch_output, -}; - -static enum print_line_t sched_waking_output(struct trace_iterator *iter, int flags, - struct trace_event *trace_event) -{ - struct trace_seq *s = &iter->seq; - struct wake_event *REC = (struct wake_event *)iter->ent; - int ret; - - ret = trace_raw_output_prep(iter, trace_event); - if (ret != TRACE_TYPE_HANDLED) - return ret; - - trace_seq_printf(s, SCHED_WAKING_FMT); - trace_seq_putc(s, '\n'); - - return trace_handle_return(s); -} - -static struct trace_event_functions sched_waking_funcs = { - .trace = sched_waking_output, -}; - -#undef C -#define C(a, b...) #a "," __stringify(b) +/* + * Must include the event header that the custom event will attach to, + * from the C file, and not in the custom header file. + */ +#include -static struct trace_event_call sched_switch_call = { - .class = &sched_switch_class, - .event = { - .funcs = &sched_switch_funcs, - }, - .print_fmt = SCHED_PRINT_FMT, - .module = THIS_MODULE, - .flags = TRACE_EVENT_FL_TRACEPOINT, -}; +/* Declare CREATE_CUSTOM_TRACE_EVENTS before including custom header */ +#define CREATE_CUSTOM_TRACE_EVENTS -static struct trace_event_call sched_waking_call = { - .class = &sched_waking_class, - .event = { - .funcs = &sched_waking_funcs, - }, - .print_fmt = SCHED_WAKING_FMT, - .module = THIS_MODULE, - .flags = TRACE_EVENT_FL_TRACEPOINT, -}; +#include "trace_custom_sched.h" +/* + * As the trace events are not exported to modules, the use of + * for_each_kernel_tracepoint() is needed to find the trace event + * to attach to. The fct() function below, is a callback that + * will be called for every event. + * + * Helper functions are created by the TRACE_CUSTOM_EVENT() macro + * update the event. Those are of the form: + * + * trace_custom_event__update() + * + * Where is the event to attach. + */ static void fct(struct tracepoint *tp, void *priv) { - if (tp->name && strcmp(tp->name, "sched_switch") == 0) - sched_switch_call.tp = tp; - else if (tp->name && strcmp(tp->name, "sched_waking") == 0) - sched_waking_call.tp = tp; -} - -static int add_event(struct trace_event_call *call) -{ - int ret; - - ret = register_trace_event(&call->event); - if (WARN_ON(!ret)) - return -ENODEV; - - ret = trace_add_event_call(call); - if (WARN_ON(ret)) - unregister_trace_event(&call->event); - - return ret; + trace_custom_event_sched_switch_update(tp); + trace_custom_event_sched_waking_update(tp); } static int __init trace_sched_init(void) { - int ret; - - check_trace_callback_type_sched_switch(sched_switch_probe); - check_trace_callback_type_sched_waking(sched_waking_probe); - for_each_kernel_tracepoint(fct, NULL); - - ret = add_event(&sched_switch_call); - if (ret) - return ret; - - ret = add_event(&sched_waking_call); - if (ret) - trace_remove_event_call(&sched_switch_call); - - return ret; + return 0; } static void __exit trace_sched_exit(void) { - trace_set_clr_event(THIS_SYSTEM, "sched_switch", 0); - trace_set_clr_event(THIS_SYSTEM, "sched_waking", 0); - - trace_remove_event_call(&sched_switch_call); - trace_remove_event_call(&sched_waking_call); } module_init(trace_sched_init); diff --git a/samples/trace_events/trace_custom_sched.h b/samples/trace_events/trace_custom_sched.h new file mode 100644 index 000000000000..a3d14de6a2e5 --- /dev/null +++ b/samples/trace_events/trace_custom_sched.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Like the headers that use TRACE_EVENT(), the TRACE_CUSTOM_EVENT() + * needs a header that allows for multiple inclusions. + * + * Test for a unique name (here we have _TRACE_CUSTOM_SCHED_H), + * also allowing to continue if TRACE_CUSTOM_MULTI_READ is defined. + */ +#if !defined(_TRACE_CUSTOM_SCHED_H) || defined(TRACE_CUSTOM_MULTI_READ) +#define _TRACE_CUSTOM_SCHED_H + +/* Include linux/trace_events.h for initial defines of TRACE_CUSTOM_EVENT() */ +#include + +/* + * TRACE_CUSTOM_EVENT() is just like TRACE_EVENT(). The first parameter + * is the event name of an existing event where the TRACE_EVENT has been included + * in the C file before including this file. + */ +TRACE_CUSTOM_EVENT(sched_switch, + + /* + * The TP_PROTO() and TP_ARGS must match the trace event + * that the custom event is using. + */ + TP_PROTO(bool preempt, + struct task_struct *prev, + struct task_struct *next), + + TP_ARGS(preempt, prev, next), + + /* + * The next fields are where the customization happens. + * The TP_STRUCT__entry() defines what will be recorded + * in the ring buffer when the custom event triggers. + * + * The rest is just like the TRACE_EVENT() macro except that + * it uses the custom entry. + */ + TP_STRUCT__entry( + __field( unsigned short, prev_prio ) + __field( unsigned short, next_prio ) + __field( pid_t, next_pid ) + ), + + TP_fast_assign( + __entry->prev_prio = prev->prio; + __entry->next_pid = next->pid; + __entry->next_prio = next->prio; + ), + + TP_printk("prev_prio=%d next_pid=%d next_prio=%d", + __entry->prev_prio, __entry->next_pid, __entry->next_prio) +) + + +TRACE_CUSTOM_EVENT(sched_waking, + + TP_PROTO(struct task_struct *p), + + TP_ARGS(p), + + TP_STRUCT__entry( + __field( pid_t, pid ) + __field( unsigned short, prio ) + ), + + TP_fast_assign( + __entry->pid = p->pid; + __entry->prio = p->prio; + ), + + TP_printk("pid=%d prio=%d", __entry->pid, __entry->prio) +) +#endif +/* + * Just like the headers that create TRACE_EVENTs, the below must + * be outside the protection of the above #if block. + */ + +/* + * It is required that the Makefile includes: + * CFLAGS_.o := -I$(src) + */ +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_PATH . + +/* + * It is requred that the TRACE_INCLUDE_FILE be the same + * as this file without the ".h". + */ +#define TRACE_INCLUDE_FILE trace_custom_sched +#include -- cgit v1.2.3 From 380af29b8d7670c445965bd573ab219aff0c4c11 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 10 Mar 2022 21:37:09 -0500 Subject: tracing: Add snapshot at end of kernel boot up Add ftrace_boot_snapshot kernel parameter that will take a snapshot at the end of boot up just before switching over to user space (it happens during the kernel freeing of init memory). This is useful when there's interesting data that can be collected from kernel start up, but gets overridden by user space start up code. With this option, the ring buffer content from the boot up traces gets saved in the snapshot at the end of boot up. This trace can be read from: /sys/kernel/tracing/snapshot Signed-off-by: Steven Rostedt (Google) --- Documentation/admin-guide/kernel-parameters.txt | 8 ++++++++ include/linux/ftrace.h | 11 ++++++++++- kernel/trace/ftrace.c | 2 ++ kernel/trace/trace.c | 18 ++++++++++++++++++ 4 files changed, 38 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f5a27f067db9..f6b7ee64ace8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1435,6 +1435,14 @@ as early as possible in order to facilitate early boot debugging. + ftrace_boot_snapshot + [FTRACE] On boot up, a snapshot will be taken of the + ftrace ring buffer that can be read at: + /sys/kernel/tracing/snapshot. + This is useful if you need tracing information from kernel + boot up that is likely to be overridden by user space + start up functionality. + ftrace_dump_on_oops[=orig_cpu] [FTRACE] will dump the trace buffers on oops. If no parameter is passed, ftrace will dump diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9999e29187de..37b619185ec9 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -30,6 +30,12 @@ #define ARCH_SUPPORTS_FTRACE_OPS 0 #endif +#ifdef CONFIG_TRACING +extern void ftrace_boot_snapshot(void); +#else +static inline void ftrace_boot_snapshot(void) { } +#endif + #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops; struct ftrace_regs; @@ -215,7 +221,10 @@ struct ftrace_ops_hash { void ftrace_free_init_mem(void); void ftrace_free_mem(struct module *mod, void *start, void *end); #else -static inline void ftrace_free_init_mem(void) { } +static inline void ftrace_free_init_mem(void) +{ + ftrace_boot_snapshot(); +} static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } #endif diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f9feb197b2da..4e29bd1cf151 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7096,6 +7096,8 @@ void __init ftrace_free_init_mem(void) void *start = (void *)(&__init_begin); void *end = (void *)(&__init_end); + ftrace_boot_snapshot(); + ftrace_free_mem(NULL, start, end); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 7c85ce9ffdc3..eaf7d30ca6f1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -185,6 +185,7 @@ static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; static bool allocate_snapshot; +static bool snapshot_at_boot; static int __init set_cmdline_ftrace(char *str) { @@ -230,6 +231,15 @@ static int __init boot_alloc_snapshot(char *str) __setup("alloc_snapshot", boot_alloc_snapshot); +static int __init boot_snapshot(char *str) +{ + snapshot_at_boot = true; + boot_alloc_snapshot(str); + return 1; +} +__setup("ftrace_boot_snapshot", boot_snapshot); + + static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static int __init set_trace_boot_options(char *str) @@ -10149,6 +10159,14 @@ out: return ret; } +void __init ftrace_boot_snapshot(void) +{ + if (snapshot_at_boot) { + tracing_snapshot(); + internal_trace_puts("** Boot snapshot taken **\n"); + } +} + void __init early_trace_init(void) { if (tracepoint_printk) { -- cgit v1.2.3