From 1581a884b7ca5592270caa010a910f2ed4f7b5f5 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 27 Jan 2022 15:44:19 -0600 Subject: tracing: Remove size restriction on tracing_log_err cmd strings Currently, tracing_log_err.cmd strings are restricted to a length of MAX_FILTER_STR_VAL (256), which is too short for some commands already seen in the wild (with cmd strings longer than that showing up truncated). Remove the restriction so that no command string is ever truncated. Link: https://lkml.kernel.org/r/ca965f23256b350ebd94b3dc1a319f28e8267f5f.1643319703.git.zanussi@kernel.org Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 55 +++++++++++++++++++++++++++++++++++++++------------- kernel/trace/trace.h | 2 +- 2 files changed, 43 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 7c2578efde26..7c85ce9ffdc3 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7723,7 +7723,7 @@ const struct file_operations trace_min_max_fops = { struct err_info { const char **errs; /* ptr to loc-specific array of err strings */ u8 type; /* index into errs -> specific err string */ - u8 pos; /* MAX_FILTER_STR_VAL = 256 */ + u16 pos; /* caret position */ u64 ts; }; @@ -7731,26 +7731,52 @@ struct tracing_log_err { struct list_head list; struct err_info info; char loc[TRACING_LOG_LOC_MAX]; /* err location */ - char cmd[MAX_FILTER_STR_VAL]; /* what caused err */ + char *cmd; /* what caused err */ }; static DEFINE_MUTEX(tracing_err_log_lock); -static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr) +static struct tracing_log_err *alloc_tracing_log_err(int len) +{ + struct tracing_log_err *err; + + err = kzalloc(sizeof(*err), GFP_KERNEL); + if (!err) + return ERR_PTR(-ENOMEM); + + err->cmd = kzalloc(len, GFP_KERNEL); + if (!err->cmd) { + kfree(err); + return ERR_PTR(-ENOMEM); + } + + return err; +} + +static void free_tracing_log_err(struct tracing_log_err *err) +{ + kfree(err->cmd); + kfree(err); +} + +static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr, + int len) { struct tracing_log_err *err; if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) { - err = kzalloc(sizeof(*err), GFP_KERNEL); - if (!err) - err = ERR_PTR(-ENOMEM); - else + err = alloc_tracing_log_err(len); + if (PTR_ERR(err) != -ENOMEM) tr->n_err_log_entries++; return err; } err = list_first_entry(&tr->err_log, struct tracing_log_err, list); + kfree(err->cmd); + err->cmd = kzalloc(len, GFP_KERNEL); + if (!err->cmd) + return ERR_PTR(-ENOMEM); list_del(&err->list); return err; @@ -7811,22 +7837,25 @@ unsigned int err_pos(char *cmd, const char *str) */ void tracing_log_err(struct trace_array *tr, const char *loc, const char *cmd, - const char **errs, u8 type, u8 pos) + const char **errs, u8 type, u16 pos) { struct tracing_log_err *err; + int len = 0; if (!tr) tr = &global_trace; + len += sizeof(CMD_PREFIX) + 2 * sizeof("\n") + strlen(cmd) + 1; + mutex_lock(&tracing_err_log_lock); - err = get_tracing_log_err(tr); + err = get_tracing_log_err(tr, len); if (PTR_ERR(err) == -ENOMEM) { mutex_unlock(&tracing_err_log_lock); return; } snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc); - snprintf(err->cmd, MAX_FILTER_STR_VAL,"\n" CMD_PREFIX "%s\n", cmd); + snprintf(err->cmd, len, "\n" CMD_PREFIX "%s\n", cmd); err->info.errs = errs; err->info.type = type; @@ -7844,7 +7873,7 @@ static void clear_tracing_err_log(struct trace_array *tr) mutex_lock(&tracing_err_log_lock); list_for_each_entry_safe(err, next, &tr->err_log, list) { list_del(&err->list); - kfree(err); + free_tracing_log_err(err); } tr->n_err_log_entries = 0; @@ -7872,9 +7901,9 @@ static void tracing_err_log_seq_stop(struct seq_file *m, void *v) mutex_unlock(&tracing_err_log_lock); } -static void tracing_err_log_show_pos(struct seq_file *m, u8 pos) +static void tracing_err_log_show_pos(struct seq_file *m, u16 pos) { - u8 i; + u16 i; for (i = 0; i < sizeof(CMD_PREFIX) - 1; i++) seq_putc(m, ' '); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index d038ddbf1bea..0f5e22238cd2 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1878,7 +1878,7 @@ extern ssize_t trace_parse_run_command(struct file *file, extern unsigned int err_pos(char *cmd, const char *str); extern void tracing_log_err(struct trace_array *tr, const char *loc, const char *cmd, - const char **errs, u8 type, u8 pos); + const char **errs, u8 type, u16 pos); /* * Normal trace_printk() and friends allocates special buffers -- cgit v1.2.3 From edfeed318d59ff242e895bf906223fc0b915117c Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Fri, 28 Jan 2022 14:08:26 -0600 Subject: tracing: Remove size restriction on hist trigger cmd error logging Currently, hist trigger command error strings are restricted to a length of MAX_FILTER_STR_VAL (256), which is too short for some commands already seen in the wild (with cmd strings longer than that showing up truncated in err_log). Remove the restriction so that no hist trigger command error string is ever truncated. Link: https://lkml.kernel.org/r/0f9d46407222eaf6632cd3b417bc50a11f401b71.1643399022.git.zanussi@kernel.org Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_hist.c | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index ada87bfb5bb8..5e8970624bce 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -727,11 +727,16 @@ static struct track_data *track_data_alloc(unsigned int key_len, return data; } -static char last_cmd[MAX_FILTER_STR_VAL]; +#define HIST_PREFIX "hist:" + +static char *last_cmd; static char last_cmd_loc[MAX_FILTER_STR_VAL]; static int errpos(char *str) { + if (!str || !last_cmd) + return 0; + return err_pos(last_cmd, str); } @@ -739,12 +744,19 @@ static void last_cmd_set(struct trace_event_file *file, char *str) { const char *system = NULL, *name = NULL; struct trace_event_call *call; + int len = 0; if (!str) return; - strcpy(last_cmd, "hist:"); - strncat(last_cmd, str, MAX_FILTER_STR_VAL - 1 - sizeof("hist:")); + len += sizeof(HIST_PREFIX) + strlen(str) + 1; + kfree(last_cmd); + last_cmd = kzalloc(len, GFP_KERNEL); + if (!last_cmd) + return; + + strcpy(last_cmd, HIST_PREFIX); + strncat(last_cmd, str, len - sizeof(HIST_PREFIX)); if (file) { call = file->event_call; @@ -757,18 +769,22 @@ static void last_cmd_set(struct trace_event_file *file, char *str) } if (system) - snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, "hist:%s:%s", system, name); + snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, HIST_PREFIX "%s:%s", system, name); } -static void hist_err(struct trace_array *tr, u8 err_type, u8 err_pos) +static void hist_err(struct trace_array *tr, u8 err_type, u16 err_pos) { + if (!last_cmd) + return; + tracing_log_err(tr, last_cmd_loc, last_cmd, err_text, err_type, err_pos); } static void hist_err_clear(void) { - last_cmd[0] = '\0'; + if (last_cmd) + last_cmd[0] = '\0'; last_cmd_loc[0] = '\0'; } @@ -5610,7 +5626,7 @@ static int event_hist_trigger_print(struct seq_file *m, bool have_var = false; unsigned int i; - seq_puts(m, "hist:"); + seq_puts(m, HIST_PREFIX); if (data->name) seq_printf(m, "%s:", data->name); -- cgit v1.2.3 From 27c888da9867725784bad3d6455d6e53b425fa2b Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Fri, 28 Jan 2022 14:08:27 -0600 Subject: tracing: Remove size restriction on synthetic event cmd error logging Currently, synthetic event command error strings are restricted to a length of MAX_FILTER_STR_VAL (256), which is too short for some commands already seen in the wild (with cmd strings longer than that showing up truncated in err_log). Remove the restriction so that no synthetic event command error string is ever truncated. Link: https://lkml.kernel.org/r/0376692396a81d0b795127c66ea92ca5bf60f481.1643399022.git.zanussi@kernel.org Signed-off-by: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_synth.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 154db74dadbc..fdd79e07e2fc 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -42,10 +42,13 @@ enum { ERRORS }; static const char *err_text[] = { ERRORS }; -static char last_cmd[MAX_FILTER_STR_VAL]; +static char *last_cmd; static int errpos(const char *str) { + if (!str || !last_cmd) + return 0; + return err_pos(last_cmd, str); } @@ -54,11 +57,19 @@ static void last_cmd_set(const char *str) if (!str) return; - strncpy(last_cmd, str, MAX_FILTER_STR_VAL - 1); + kfree(last_cmd); + last_cmd = kzalloc(strlen(str) + 1, GFP_KERNEL); + if (!last_cmd) + return; + + strncpy(last_cmd, str, strlen(str) + 1); } -static void synth_err(u8 err_type, u8 err_pos) +static void synth_err(u8 err_type, u16 err_pos) { + if (!last_cmd) + return; + tracing_log_err(NULL, "synthetic_events", last_cmd, err_text, err_type, err_pos); } -- cgit v1.2.3 From 55bc8384d3deadce48923d8329c1434494c52273 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 10 Feb 2022 19:36:05 -0500 Subject: tracing: Save both wakee and current on wakeup events Use the sched_switch function to save both the wakee and the waker comms in the saved cmdlines list when sched_wakeup is done. Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_sched_switch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index e304196d7c28..5cd33be2031b 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -44,7 +44,7 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee) if (!flags) return; - tracing_record_taskinfo(current, flags); + tracing_record_taskinfo_sched_switch(current, wakee, flags); } static int tracing_sched_register(void) -- cgit v1.2.3 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) --- kernel/trace/Kconfig | 14 + kernel/trace/Makefile | 1 + kernel/trace/trace_events_user.c | 1187 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 1202 insertions(+) create mode 100644 kernel/trace/trace_events_user.c (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index a5eb5e7fd624..16a52a71732d 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -737,6 +737,20 @@ config SYNTH_EVENTS If in doubt, say N. +config USER_EVENTS + bool "User trace events" + select TRACING + select DYNAMIC_EVENTS + help + User trace events are user-defined trace events that + can be used like an existing kernel trace event. User trace + events are generated by writing to a tracefs file. User + processes can determine if their tracing events should be + generated by memory mapping a tracefs file and checking for + an associated byte being non-zero. + + If in doubt, say N. + config HIST_TRIGGERS bool "Histogram triggers" depends on ARCH_HAVE_NMI_SAFE_CMPXCHG diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index bedc5caceec7..19ef3758da95 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -82,6 +82,7 @@ obj-$(CONFIG_PROBE_EVENTS) += trace_eprobe.o obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o +obj-$(CONFIG_USER_EVENTS) += trace_events_user.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c new file mode 100644 index 000000000000..77105233115e --- /dev/null +++ b/kernel/trace/trace_events_user.c @@ -0,0 +1,1187 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021, Microsoft Corporation. + * + * Authors: + * Beau Belgrave + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "trace.h" +#include "trace_dynevent.h" + +#define USER_EVENTS_PREFIX_LEN (sizeof(USER_EVENTS_PREFIX)-1) + +#define FIELD_DEPTH_TYPE 0 +#define FIELD_DEPTH_NAME 1 +#define FIELD_DEPTH_SIZE 2 + +/* + * Limits how many trace_event calls user processes can create: + * Must be multiple of PAGE_SIZE. + */ +#define MAX_PAGES 1 +#define MAX_EVENTS (MAX_PAGES * PAGE_SIZE) + +/* Limit how long of an event name plus args within the subsystem. */ +#define MAX_EVENT_DESC 512 +#define EVENT_NAME(user_event) ((user_event)->tracepoint.name) +#define MAX_FIELD_ARRAY_SIZE 1024 + +static char *register_page_data; + +static DEFINE_MUTEX(reg_mutex); +static DEFINE_HASHTABLE(register_table, 4); +static DECLARE_BITMAP(page_bitmap, MAX_EVENTS); + +/* + * Stores per-event properties, as users register events + * within a file a user_event might be created if it does not + * already exist. These are globally used and their lifetime + * is tied to the refcnt member. These cannot go away until the + * refcnt reaches zero. + */ +struct user_event { + struct tracepoint tracepoint; + struct trace_event_call call; + struct trace_event_class class; + struct dyn_event devent; + struct hlist_node node; + struct list_head fields; + atomic_t refcnt; + int index; + int flags; +}; + +/* + * Stores per-file events references, as users register events + * within a file this structure is modified and freed via RCU. + * The lifetime of this struct is tied to the lifetime of the file. + * These are not shared and only accessible by the file that created it. + */ +struct user_event_refs { + struct rcu_head rcu; + int count; + struct user_event *events[]; +}; + +typedef void (*user_event_func_t) (struct user_event *user, + void *data, u32 datalen, + void *tpdata); + +static int user_event_parse(char *name, char *args, char *flags, + struct user_event **newuser); + +static u32 user_event_key(char *name) +{ + return jhash(name, strlen(name), 0); +} + +static struct list_head *user_event_get_fields(struct trace_event_call *call) +{ + struct user_event *user = (struct user_event *)call->data; + + return &user->fields; +} + +/* + * Parses a register command for user_events + * Format: event_name[:FLAG1[,FLAG2...]] [field1[;field2...]] + * + * Example event named 'test' with a 20 char 'msg' field with an unsigned int + * 'id' field after: + * test char[20] msg;unsigned int id + * + * NOTE: Offsets are from the user data perspective, they are not from the + * trace_entry/buffer perspective. We automatically add the common properties + * sizes to the offset for the user. + */ +static int user_event_parse_cmd(char *raw_command, struct user_event **newuser) +{ + char *name = raw_command; + char *args = strpbrk(name, " "); + char *flags; + + if (args) + *args++ = '\0'; + + flags = strpbrk(name, ":"); + + if (flags) + *flags++ = '\0'; + + return user_event_parse(name, args, flags, newuser); +} + +static int user_field_array_size(const char *type) +{ + const char *start = strchr(type, '['); + char val[8]; + char *bracket; + int size = 0; + + if (start == NULL) + return -EINVAL; + + if (strscpy(val, start + 1, sizeof(val)) <= 0) + return -EINVAL; + + bracket = strchr(val, ']'); + + if (!bracket) + return -EINVAL; + + *bracket = '\0'; + + if (kstrtouint(val, 0, &size)) + return -EINVAL; + + if (size > MAX_FIELD_ARRAY_SIZE) + return -EINVAL; + + return size; +} + +static int user_field_size(const char *type) +{ + /* long is not allowed from a user, since it's ambigious in size */ + if (strcmp(type, "s64") == 0) + return sizeof(s64); + if (strcmp(type, "u64") == 0) + return sizeof(u64); + if (strcmp(type, "s32") == 0) + return sizeof(s32); + if (strcmp(type, "u32") == 0) + return sizeof(u32); + if (strcmp(type, "int") == 0) + return sizeof(int); + if (strcmp(type, "unsigned int") == 0) + return sizeof(unsigned int); + if (strcmp(type, "s16") == 0) + return sizeof(s16); + if (strcmp(type, "u16") == 0) + return sizeof(u16); + if (strcmp(type, "short") == 0) + return sizeof(short); + if (strcmp(type, "unsigned short") == 0) + return sizeof(unsigned short); + if (strcmp(type, "s8") == 0) + return sizeof(s8); + if (strcmp(type, "u8") == 0) + return sizeof(u8); + if (strcmp(type, "char") == 0) + return sizeof(char); + if (strcmp(type, "unsigned char") == 0) + return sizeof(unsigned char); + if (str_has_prefix(type, "char[")) + return user_field_array_size(type); + if (str_has_prefix(type, "unsigned char[")) + return user_field_array_size(type); + if (str_has_prefix(type, "__data_loc ")) + return sizeof(u32); + if (str_has_prefix(type, "__rel_loc ")) + return sizeof(u32); + + /* Uknown basic type, error */ + return -EINVAL; +} + +static void user_event_destroy_fields(struct user_event *user) +{ + struct ftrace_event_field *field, *next; + struct list_head *head = &user->fields; + + list_for_each_entry_safe(field, next, head, link) { + list_del(&field->link); + kfree(field); + } +} + +static int user_event_add_field(struct user_event *user, const char *type, + const char *name, int offset, int size, + int is_signed, int filter_type) +{ + struct ftrace_event_field *field; + + field = kmalloc(sizeof(*field), GFP_KERNEL); + + if (!field) + return -ENOMEM; + + field->type = type; + field->name = name; + field->offset = offset; + field->size = size; + field->is_signed = is_signed; + field->filter_type = filter_type; + + list_add(&field->link, &user->fields); + + return 0; +} + +/* + * Parses the values of a field within the description + * Format: type name [size] + */ +static int user_event_parse_field(char *field, struct user_event *user, + u32 *offset) +{ + char *part, *type, *name; + u32 depth = 0, saved_offset = *offset; + int len, size = -EINVAL; + bool is_struct = false; + + field = skip_spaces(field); + + if (*field == '\0') + return 0; + + /* Handle types that have a space within */ + len = str_has_prefix(field, "unsigned "); + if (len) + goto skip_next; + + len = str_has_prefix(field, "struct "); + if (len) { + is_struct = true; + goto skip_next; + } + + len = str_has_prefix(field, "__data_loc unsigned "); + if (len) + goto skip_next; + + len = str_has_prefix(field, "__data_loc "); + if (len) + goto skip_next; + + len = str_has_prefix(field, "__rel_loc unsigned "); + if (len) + goto skip_next; + + len = str_has_prefix(field, "__rel_loc "); + if (len) + goto skip_next; + + goto parse; +skip_next: + type = field; + field = strpbrk(field + len, " "); + + if (field == NULL) + return -EINVAL; + + *field++ = '\0'; + depth++; +parse: + while ((part = strsep(&field, " ")) != NULL) { + switch (depth++) { + case FIELD_DEPTH_TYPE: + type = part; + break; + case FIELD_DEPTH_NAME: + name = part; + break; + case FIELD_DEPTH_SIZE: + if (!is_struct) + return -EINVAL; + + if (kstrtou32(part, 10, &size)) + return -EINVAL; + break; + default: + return -EINVAL; + } + } + + if (depth < FIELD_DEPTH_SIZE) + return -EINVAL; + + if (depth == FIELD_DEPTH_SIZE) + size = user_field_size(type); + + if (size == 0) + return -EINVAL; + + if (size < 0) + return size; + + *offset = saved_offset + size; + + return user_event_add_field(user, type, name, saved_offset, size, + type[0] != 'u', FILTER_OTHER); +} + +static void user_event_parse_flags(struct user_event *user, char *flags) +{ + char *flag; + + if (flags == NULL) + return; + + while ((flag = strsep(&flags, ",")) != NULL) { + if (strcmp(flag, "BPF_ITER") == 0) + user->flags |= FLAG_BPF_ITER; + } +} + +static int user_event_parse_fields(struct user_event *user, char *args) +{ + char *field; + u32 offset = sizeof(struct trace_entry); + int ret = -EINVAL; + + if (args == NULL) + return 0; + + while ((field = strsep(&args, ";")) != NULL) { + ret = user_event_parse_field(field, user, &offset); + + if (ret) + break; + } + + return ret; +} + +static struct trace_event_fields user_event_fields_array[1]; + +static enum print_line_t user_event_print_trace(struct trace_iterator *iter, + int flags, + struct trace_event *event) +{ + /* Unsafe to try to decode user provided print_fmt, use hex */ + trace_print_hex_dump_seq(&iter->seq, "", DUMP_PREFIX_OFFSET, 16, + 1, iter->ent, iter->ent_size, true); + + return trace_handle_return(&iter->seq); +} + +static struct trace_event_functions user_event_funcs = { + .trace = user_event_print_trace, +}; + +static int destroy_user_event(struct user_event *user) +{ + int ret = 0; + + /* Must destroy fields before call removal */ + user_event_destroy_fields(user); + + ret = trace_remove_event_call(&user->call); + + if (ret) + return ret; + + dyn_event_remove(&user->devent); + + register_page_data[user->index] = 0; + clear_bit(user->index, page_bitmap); + hash_del(&user->node); + + kfree(EVENT_NAME(user)); + kfree(user); + + return ret; +} + +static struct user_event *find_user_event(char *name, u32 *outkey) +{ + struct user_event *user; + u32 key = user_event_key(name); + + *outkey = key; + + hash_for_each_possible(register_table, user, node, key) + if (!strcmp(EVENT_NAME(user), name)) + return user; + + return NULL; +} + +/* + * Writes the user supplied payload out to a trace file. + */ +static void user_event_ftrace(struct user_event *user, void *data, u32 datalen, + void *tpdata) +{ + struct trace_event_file *file; + struct trace_entry *entry; + struct trace_event_buffer event_buffer; + + file = (struct trace_event_file *)tpdata; + + if (!file || + !(file->flags & EVENT_FILE_FL_ENABLED) || + trace_trigger_soft_disabled(file)) + return; + + /* Allocates and fills trace_entry, + 1 of this is data payload */ + entry = trace_event_buffer_reserve(&event_buffer, file, + sizeof(*entry) + datalen); + + if (unlikely(!entry)) + return; + + memcpy(entry + 1, data, datalen); + + trace_event_buffer_commit(&event_buffer); +} + +/* + * Update the register page that is shared between user processes. + */ +static void update_reg_page_for(struct user_event *user) +{ + struct tracepoint *tp = &user->tracepoint; + char status = 0; + + if (atomic_read(&tp->key.enabled) > 0) { + struct tracepoint_func *probe_func_ptr; + user_event_func_t probe_func; + + rcu_read_lock_sched(); + + probe_func_ptr = rcu_dereference_sched(tp->funcs); + + if (probe_func_ptr) { + do { + probe_func = probe_func_ptr->func; + + if (probe_func == user_event_ftrace) + status |= EVENT_STATUS_FTRACE; + else + status |= EVENT_STATUS_OTHER; + } while ((++probe_func_ptr)->func); + } + + rcu_read_unlock_sched(); + } + + register_page_data[user->index] = status; +} + +/* + * Register callback for our events from tracing sub-systems. + */ +static int user_event_reg(struct trace_event_call *call, + enum trace_reg type, + void *data) +{ + struct user_event *user = (struct user_event *)call->data; + int ret = 0; + + if (!user) + return -ENOENT; + + switch (type) { + case TRACE_REG_REGISTER: + ret = tracepoint_probe_register(call->tp, + call->class->probe, + data); + if (!ret) + goto inc; + break; + + case TRACE_REG_UNREGISTER: + tracepoint_probe_unregister(call->tp, + call->class->probe, + data); + goto dec; + + default: + break; + } + + return ret; +inc: + atomic_inc(&user->refcnt); + update_reg_page_for(user); + return 0; +dec: + update_reg_page_for(user); + atomic_dec(&user->refcnt); + return 0; +} + +static int user_event_create(const char *raw_command) +{ + struct user_event *user; + char *name; + int ret; + + if (!str_has_prefix(raw_command, USER_EVENTS_PREFIX)) + return -ECANCELED; + + raw_command += USER_EVENTS_PREFIX_LEN; + raw_command = skip_spaces(raw_command); + + name = kstrdup(raw_command, GFP_KERNEL); + + if (!name) + return -ENOMEM; + + mutex_lock(®_mutex); + ret = user_event_parse_cmd(name, &user); + mutex_unlock(®_mutex); + + if (ret) + kfree(name); + + return ret; +} + +static int user_event_show(struct seq_file *m, struct dyn_event *ev) +{ + struct user_event *user = container_of(ev, struct user_event, devent); + struct ftrace_event_field *field, *next; + struct list_head *head; + int depth = 0; + + seq_printf(m, "%s%s", USER_EVENTS_PREFIX, EVENT_NAME(user)); + + head = trace_get_fields(&user->call); + + list_for_each_entry_safe_reverse(field, next, head, link) { + if (depth == 0) + seq_puts(m, " "); + else + seq_puts(m, "; "); + + seq_printf(m, "%s %s", field->type, field->name); + + if (str_has_prefix(field->type, "struct ")) + seq_printf(m, " %d", field->size); + + depth++; + } + + seq_puts(m, "\n"); + + return 0; +} + +static bool user_event_is_busy(struct dyn_event *ev) +{ + struct user_event *user = container_of(ev, struct user_event, devent); + + return atomic_read(&user->refcnt) != 0; +} + +static int user_event_free(struct dyn_event *ev) +{ + struct user_event *user = container_of(ev, struct user_event, devent); + + if (atomic_read(&user->refcnt) != 0) + return -EBUSY; + + return destroy_user_event(user); +} + +static bool user_event_match(const char *system, const char *event, + int argc, const char **argv, struct dyn_event *ev) +{ + struct user_event *user = container_of(ev, struct user_event, devent); + + return strcmp(EVENT_NAME(user), event) == 0 && + (!system || strcmp(system, USER_EVENTS_SYSTEM) == 0); +} + +static struct dyn_event_operations user_event_dops = { + .create = user_event_create, + .show = user_event_show, + .is_busy = user_event_is_busy, + .free = user_event_free, + .match = user_event_match, +}; + +static int user_event_trace_register(struct user_event *user) +{ + int ret; + + ret = register_trace_event(&user->call.event); + + if (!ret) + return -ENODEV; + + ret = trace_add_event_call(&user->call); + + if (ret) + unregister_trace_event(&user->call.event); + + return ret; +} + +/* + * Parses the event name, arguments and flags then registers if successful. + * The name buffer lifetime is owned by this method for success cases only. + */ +static int user_event_parse(char *name, char *args, char *flags, + struct user_event **newuser) +{ + int ret; + int index; + u32 key; + struct user_event *user = find_user_event(name, &key); + + if (user) { + *newuser = user; + /* + * Name is allocated by caller, free it since it already exists. + * Caller only worries about failure cases for freeing. + */ + kfree(name); + return 0; + } + + index = find_first_zero_bit(page_bitmap, MAX_EVENTS); + + if (index == MAX_EVENTS) + return -EMFILE; + + user = kzalloc(sizeof(*user), GFP_KERNEL); + + if (!user) + return -ENOMEM; + + INIT_LIST_HEAD(&user->class.fields); + INIT_LIST_HEAD(&user->fields); + + user->tracepoint.name = name; + + user_event_parse_flags(user, flags); + + ret = user_event_parse_fields(user, args); + + if (ret) + goto put_user; + + /* Minimal print format */ + user->call.print_fmt = "\"\""; + + user->call.data = user; + user->call.class = &user->class; + user->call.name = name; + user->call.flags = TRACE_EVENT_FL_TRACEPOINT; + user->call.tp = &user->tracepoint; + user->call.event.funcs = &user_event_funcs; + + user->class.system = USER_EVENTS_SYSTEM; + user->class.fields_array = user_event_fields_array; + user->class.get_fields = user_event_get_fields; + user->class.reg = user_event_reg; + user->class.probe = user_event_ftrace; + + mutex_lock(&event_mutex); + ret = user_event_trace_register(user); + mutex_unlock(&event_mutex); + + if (ret) + goto put_user; + + user->index = index; + dyn_event_init(&user->devent, &user_event_dops); + dyn_event_add(&user->devent, &user->call); + set_bit(user->index, page_bitmap); + hash_add(register_table, &user->node, key); + + *newuser = user; + return 0; +put_user: + user_event_destroy_fields(user); + kfree(user); + return ret; +} + +/* + * Deletes a previously created event if it is no longer being used. + */ +static int delete_user_event(char *name) +{ + u32 key; + int ret; + struct user_event *user = find_user_event(name, &key); + + if (!user) + return -ENOENT; + + if (atomic_read(&user->refcnt) != 0) + return -EBUSY; + + mutex_lock(&event_mutex); + ret = destroy_user_event(user); + mutex_unlock(&event_mutex); + + return ret; +} + +/* + * Validates the user payload and writes via iterator. + */ +static ssize_t user_events_write_core(struct file *file, struct iov_iter *i) +{ + struct user_event_refs *refs; + struct user_event *user = NULL; + struct tracepoint *tp; + ssize_t ret = i->count; + int idx; + + if (unlikely(copy_from_iter(&idx, sizeof(idx), i) != sizeof(idx))) + return -EFAULT; + + rcu_read_lock_sched(); + + refs = rcu_dereference_sched(file->private_data); + + /* + * The refs->events array is protected by RCU, and new items may be + * added. But the user retrieved from indexing into the events array + * shall be immutable while the file is opened. + */ + if (likely(refs && idx < refs->count)) + user = refs->events[idx]; + + rcu_read_unlock_sched(); + + if (unlikely(user == NULL)) + return -ENOENT; + + tp = &user->tracepoint; + + /* + * It's possible key.enabled disables after this check, however + * we don't mind if a few events are included in this condition. + */ + if (likely(atomic_read(&tp->key.enabled) > 0)) { + struct tracepoint_func *probe_func_ptr; + user_event_func_t probe_func; + void *tpdata; + void *kdata; + u32 datalen; + + kdata = kmalloc(i->count, GFP_KERNEL); + + if (unlikely(!kdata)) + return -ENOMEM; + + datalen = copy_from_iter(kdata, i->count, i); + + rcu_read_lock_sched(); + + probe_func_ptr = rcu_dereference_sched(tp->funcs); + + if (probe_func_ptr) { + do { + probe_func = probe_func_ptr->func; + tpdata = probe_func_ptr->data; + probe_func(user, kdata, datalen, tpdata); + } while ((++probe_func_ptr)->func); + } + + rcu_read_unlock_sched(); + + kfree(kdata); + } + + return ret; +} + +static ssize_t user_events_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct iovec iov; + struct iov_iter i; + + if (unlikely(*ppos != 0)) + return -EFAULT; + + if (unlikely(import_single_range(READ, (char *)ubuf, count, &iov, &i))) + return -EFAULT; + + return user_events_write_core(file, &i); +} + +static ssize_t user_events_write_iter(struct kiocb *kp, struct iov_iter *i) +{ + return user_events_write_core(kp->ki_filp, i); +} + +static int user_events_ref_add(struct file *file, struct user_event *user) +{ + struct user_event_refs *refs, *new_refs; + int i, size, count = 0; + + refs = rcu_dereference_protected(file->private_data, + lockdep_is_held(®_mutex)); + + if (refs) { + count = refs->count; + + for (i = 0; i < count; ++i) + if (refs->events[i] == user) + return i; + } + + size = struct_size(refs, events, count + 1); + + new_refs = kzalloc(size, GFP_KERNEL); + + if (!new_refs) + return -ENOMEM; + + new_refs->count = count + 1; + + for (i = 0; i < count; ++i) + new_refs->events[i] = refs->events[i]; + + new_refs->events[i] = user; + + atomic_inc(&user->refcnt); + + rcu_assign_pointer(file->private_data, new_refs); + + if (refs) + kfree_rcu(refs, rcu); + + return i; +} + +static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg) +{ + u32 size; + long ret; + + ret = get_user(size, &ureg->size); + + if (ret) + return ret; + + if (size > PAGE_SIZE) + return -E2BIG; + + return copy_struct_from_user(kreg, sizeof(*kreg), ureg, size); +} + +/* + * Registers a user_event on behalf of a user process. + */ +static long user_events_ioctl_reg(struct file *file, unsigned long uarg) +{ + struct user_reg __user *ureg = (struct user_reg __user *)uarg; + struct user_reg reg; + struct user_event *user; + char *name; + long ret; + + ret = user_reg_get(ureg, ®); + + if (ret) + return ret; + + name = strndup_user((const char __user *)(uintptr_t)reg.name_args, + MAX_EVENT_DESC); + + if (IS_ERR(name)) { + ret = PTR_ERR(name); + return ret; + } + + ret = user_event_parse_cmd(name, &user); + + if (ret) { + kfree(name); + return ret; + } + + ret = user_events_ref_add(file, user); + + /* Positive number is index and valid */ + if (ret < 0) + return ret; + + put_user((u32)ret, &ureg->write_index); + put_user(user->index, &ureg->status_index); + + return 0; +} + +/* + * Deletes a user_event on behalf of a user process. + */ +static long user_events_ioctl_del(struct file *file, unsigned long uarg) +{ + void __user *ubuf = (void __user *)uarg; + char *name; + long ret; + + name = strndup_user(ubuf, MAX_EVENT_DESC); + + if (IS_ERR(name)) + return PTR_ERR(name); + + ret = delete_user_event(name); + + kfree(name); + + return ret; +} + +/* + * Handles the ioctl from user mode to register or alter operations. + */ +static long user_events_ioctl(struct file *file, unsigned int cmd, + unsigned long uarg) +{ + long ret = -ENOTTY; + + switch (cmd) { + case DIAG_IOCSREG: + mutex_lock(®_mutex); + ret = user_events_ioctl_reg(file, uarg); + mutex_unlock(®_mutex); + break; + + case DIAG_IOCSDEL: + mutex_lock(®_mutex); + ret = user_events_ioctl_del(file, uarg); + mutex_unlock(®_mutex); + break; + } + + return ret; +} + +/* + * Handles the final close of the file from user mode. + */ +static int user_events_release(struct inode *node, struct file *file) +{ + struct user_event_refs *refs; + struct user_event *user; + int i; + + /* + * Ensure refs cannot change under any situation by taking the + * register mutex during the final freeing of the references. + */ + mutex_lock(®_mutex); + + refs = file->private_data; + + if (!refs) + goto out; + + /* + * The lifetime of refs has reached an end, it's tied to this file. + * The underlying user_events are ref counted, and cannot be freed. + * After this decrement, the user_events may be freed elsewhere. + */ + for (i = 0; i < refs->count; ++i) { + user = refs->events[i]; + + if (user) + atomic_dec(&user->refcnt); + } +out: + file->private_data = NULL; + + mutex_unlock(®_mutex); + + kfree(refs); + + return 0; +} + +static const struct file_operations user_data_fops = { + .write = user_events_write, + .write_iter = user_events_write_iter, + .unlocked_ioctl = user_events_ioctl, + .release = user_events_release, +}; + +/* + * Maps the shared page into the user process for checking if event is enabled. + */ +static int user_status_mmap(struct file *file, struct vm_area_struct *vma) +{ + unsigned long size = vma->vm_end - vma->vm_start; + + if (size != MAX_EVENTS) + return -EINVAL; + + return remap_pfn_range(vma, vma->vm_start, + virt_to_phys(register_page_data) >> PAGE_SHIFT, + size, vm_get_page_prot(VM_READ)); +} + +static void *user_seq_start(struct seq_file *m, loff_t *pos) +{ + if (*pos) + return NULL; + + return (void *)1; +} + +static void *user_seq_next(struct seq_file *m, void *p, loff_t *pos) +{ + ++*pos; + return NULL; +} + +static void user_seq_stop(struct seq_file *m, void *p) +{ +} + +static int user_seq_show(struct seq_file *m, void *p) +{ + struct user_event *user; + char status; + int i, active = 0, busy = 0, flags; + + mutex_lock(®_mutex); + + hash_for_each(register_table, i, user, node) { + status = register_page_data[user->index]; + flags = user->flags; + + seq_printf(m, "%d:%s", user->index, EVENT_NAME(user)); + + if (flags != 0 || status != 0) + seq_puts(m, " #"); + + if (status != 0) { + seq_puts(m, " Used by"); + if (status & EVENT_STATUS_FTRACE) + seq_puts(m, " ftrace"); + if (status & EVENT_STATUS_PERF) + seq_puts(m, " perf"); + if (status & EVENT_STATUS_OTHER) + seq_puts(m, " other"); + busy++; + } + + if (flags & FLAG_BPF_ITER) + seq_puts(m, " FLAG:BPF_ITER"); + + seq_puts(m, "\n"); + active++; + } + + mutex_unlock(®_mutex); + + seq_puts(m, "\n"); + seq_printf(m, "Active: %d\n", active); + seq_printf(m, "Busy: %d\n", busy); + seq_printf(m, "Max: %ld\n", MAX_EVENTS); + + return 0; +} + +static const struct seq_operations user_seq_ops = { + .start = user_seq_start, + .next = user_seq_next, + .stop = user_seq_stop, + .show = user_seq_show, +}; + +static int user_status_open(struct inode *node, struct file *file) +{ + return seq_open(file, &user_seq_ops); +} + +static const struct file_operations user_status_fops = { + .open = user_status_open, + .mmap = user_status_mmap, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* + * Creates a set of tracefs files to allow user mode interactions. + */ +static int create_user_tracefs(void) +{ + struct dentry *edata, *emmap; + + edata = tracefs_create_file("user_events_data", TRACE_MODE_WRITE, + NULL, NULL, &user_data_fops); + + if (!edata) { + pr_warn("Could not create tracefs 'user_events_data' entry\n"); + goto err; + } + + /* mmap with MAP_SHARED requires writable fd */ + emmap = tracefs_create_file("user_events_status", TRACE_MODE_WRITE, + NULL, NULL, &user_status_fops); + + if (!emmap) { + tracefs_remove(edata); + pr_warn("Could not create tracefs 'user_events_mmap' entry\n"); + goto err; + } + + return 0; +err: + return -ENODEV; +} + +static void set_page_reservations(bool set) +{ + int page; + + for (page = 0; page < MAX_PAGES; ++page) { + void *addr = register_page_data + (PAGE_SIZE * page); + + if (set) + SetPageReserved(virt_to_page(addr)); + else + ClearPageReserved(virt_to_page(addr)); + } +} + +static int __init trace_events_user_init(void) +{ + int ret; + + /* Zero all bits beside 0 (which is reserved for failures) */ + bitmap_zero(page_bitmap, MAX_EVENTS); + set_bit(0, page_bitmap); + + register_page_data = kzalloc(MAX_EVENTS, GFP_KERNEL); + + if (!register_page_data) + return -ENOMEM; + + set_page_reservations(true); + + ret = create_user_tracefs(); + + if (ret) { + pr_warn("user_events could not register with tracefs\n"); + set_page_reservations(false); + kfree(register_page_data); + return ret; + } + + if (dyn_event_register(&user_event_dops)) + pr_warn("user_events could not register with dyn_events\n"); + + return 0; +} + +fs_initcall(trace_events_user_init); -- cgit v1.2.3 From aa3b2b4c669205200615dd8a2cc4af4f81fd0335 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 18 Jan 2022 12:43:16 -0800 Subject: user_events: Add print_fmt generation support for basic types Addes print_fmt format generation for basic types that are supported for user processes. Only supports sizes that are the same on 32 and 64 bit. Link: https://lkml.kernel.org/r/20220118204326.2169-3-beaub@linux.microsoft.com Acked-by: Masami Hiramatsu Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 115 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 113 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 77105233115e..ddc5c3cf1bf8 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -359,6 +359,114 @@ static int user_event_parse_fields(struct user_event *user, char *args) static struct trace_event_fields user_event_fields_array[1]; +static const char *user_field_format(const char *type) +{ + if (strcmp(type, "s64") == 0) + return "%lld"; + if (strcmp(type, "u64") == 0) + return "%llu"; + if (strcmp(type, "s32") == 0) + return "%d"; + if (strcmp(type, "u32") == 0) + return "%u"; + if (strcmp(type, "int") == 0) + return "%d"; + if (strcmp(type, "unsigned int") == 0) + return "%u"; + if (strcmp(type, "s16") == 0) + return "%d"; + if (strcmp(type, "u16") == 0) + return "%u"; + if (strcmp(type, "short") == 0) + return "%d"; + if (strcmp(type, "unsigned short") == 0) + return "%u"; + if (strcmp(type, "s8") == 0) + return "%d"; + if (strcmp(type, "u8") == 0) + return "%u"; + if (strcmp(type, "char") == 0) + return "%d"; + if (strcmp(type, "unsigned char") == 0) + return "%u"; + if (strstr(type, "char[") != 0) + return "%s"; + + /* Unknown, likely struct, allowed treat as 64-bit */ + return "%llu"; +} + +static bool user_field_is_dyn_string(const char *type, const char **str_func) +{ + if (str_has_prefix(type, "__data_loc ")) { + *str_func = "__get_str"; + goto check; + } + + if (str_has_prefix(type, "__rel_loc ")) { + *str_func = "__get_rel_str"; + goto check; + } + + return false; +check: + return strstr(type, "char") != 0; +} + +#define LEN_OR_ZERO (len ? len - pos : 0) +static int user_event_set_print_fmt(struct user_event *user, char *buf, int len) +{ + struct ftrace_event_field *field, *next; + struct list_head *head = &user->fields; + int pos = 0, depth = 0; + const char *str_func; + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\""); + + list_for_each_entry_safe_reverse(field, next, head, link) { + if (depth != 0) + pos += snprintf(buf + pos, LEN_OR_ZERO, " "); + + pos += snprintf(buf + pos, LEN_OR_ZERO, "%s=%s", + field->name, user_field_format(field->type)); + + depth++; + } + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\""); + + list_for_each_entry_safe_reverse(field, next, head, link) { + if (user_field_is_dyn_string(field->type, &str_func)) + pos += snprintf(buf + pos, LEN_OR_ZERO, + ", %s(%s)", str_func, field->name); + else + pos += snprintf(buf + pos, LEN_OR_ZERO, + ", REC->%s", field->name); + } + + return pos + 1; +} +#undef LEN_OR_ZERO + +static int user_event_create_print_fmt(struct user_event *user) +{ + char *print_fmt; + int len; + + len = user_event_set_print_fmt(user, NULL, 0); + + print_fmt = kmalloc(len, GFP_KERNEL); + + if (!print_fmt) + return -ENOMEM; + + user_event_set_print_fmt(user, print_fmt, len); + + user->call.print_fmt = print_fmt; + + return 0; +} + static enum print_line_t user_event_print_trace(struct trace_iterator *iter, int flags, struct trace_event *event) @@ -392,6 +500,7 @@ static int destroy_user_event(struct user_event *user) clear_bit(user->index, page_bitmap); hash_del(&user->node); + kfree(user->call.print_fmt); kfree(EVENT_NAME(user)); kfree(user); @@ -669,8 +778,10 @@ static int user_event_parse(char *name, char *args, char *flags, if (ret) goto put_user; - /* Minimal print format */ - user->call.print_fmt = "\"\""; + ret = user_event_create_print_fmt(user); + + if (ret) + goto put_user; user->call.data = user; user->call.class = &user->class; -- cgit v1.2.3 From 9aed4e157d1ffe4aeebc005b4eceede1ed5a403a Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 18 Jan 2022 12:43:17 -0800 Subject: user_events: Handle matching arguments from dyn_events Ensures that when dynamic events requests a match with arguments that they match what is in the user_event. Link: https://lkml.kernel.org/r/20220118204326.2169-4-beaub@linux.microsoft.com Acked-by: Masami Hiramatsu Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 77 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 76 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index ddc5c3cf1bf8..a6794cb1f586 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -39,6 +39,7 @@ #define MAX_EVENT_DESC 512 #define EVENT_NAME(user_event) ((user_event)->tracepoint.name) #define MAX_FIELD_ARRAY_SIZE 1024 +#define MAX_FIELD_ARG_NAME 256 static char *register_page_data; @@ -700,13 +701,87 @@ static int user_event_free(struct dyn_event *ev) return destroy_user_event(user); } +static bool user_field_match(struct ftrace_event_field *field, int argc, + const char **argv, int *iout) +{ + char *field_name, *arg_name; + int len, pos, i = *iout; + bool colon = false, match = false; + + if (i >= argc) + return false; + + len = MAX_FIELD_ARG_NAME; + field_name = kmalloc(len, GFP_KERNEL); + arg_name = kmalloc(len, GFP_KERNEL); + + if (!arg_name || !field_name) + goto out; + + pos = 0; + + for (; i < argc; ++i) { + if (i != *iout) + pos += snprintf(arg_name + pos, len - pos, " "); + + pos += snprintf(arg_name + pos, len - pos, argv[i]); + + if (strchr(argv[i], ';')) { + ++i; + colon = true; + break; + } + } + + pos = 0; + + pos += snprintf(field_name + pos, len - pos, field->type); + pos += snprintf(field_name + pos, len - pos, " "); + pos += snprintf(field_name + pos, len - pos, field->name); + + if (colon) + pos += snprintf(field_name + pos, len - pos, ";"); + + *iout = i; + + match = strcmp(arg_name, field_name) == 0; +out: + kfree(arg_name); + kfree(field_name); + + return match; +} + +static bool user_fields_match(struct user_event *user, int argc, + const char **argv) +{ + struct ftrace_event_field *field, *next; + struct list_head *head = &user->fields; + int i = 0; + + list_for_each_entry_safe_reverse(field, next, head, link) + if (!user_field_match(field, argc, argv, &i)) + return false; + + if (i != argc) + return false; + + return true; +} + static bool user_event_match(const char *system, const char *event, int argc, const char **argv, struct dyn_event *ev) { struct user_event *user = container_of(ev, struct user_event, devent); + bool match; - return strcmp(EVENT_NAME(user), event) == 0 && + match = strcmp(EVENT_NAME(user), event) == 0 && (!system || strcmp(system, USER_EVENTS_SYSTEM) == 0); + + if (match && argc > 0) + match = user_fields_match(user, argc, argv); + + return match; } static struct dyn_event_operations user_event_dops = { -- cgit v1.2.3 From 3207d0459ef3789c7efa801b57123c8a79d05694 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 18 Jan 2022 12:43:18 -0800 Subject: user_events: Add basic perf and eBPF support Adds support to write out user_event data to perf_probe/perf files as well as to any attached eBPF program. Link: https://lkml.kernel.org/r/20220118204326.2169-5-beaub@linux.microsoft.com Acked-by: Masami Hiramatsu Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 72 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 71 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index a6794cb1f586..371f31472156 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -551,6 +551,50 @@ static void user_event_ftrace(struct user_event *user, void *data, u32 datalen, trace_event_buffer_commit(&event_buffer); } +#ifdef CONFIG_PERF_EVENTS +/* + * Writes the user supplied payload out to perf ring buffer or eBPF program. + */ +static void user_event_perf(struct user_event *user, void *data, u32 datalen, + void *tpdata) +{ + struct hlist_head *perf_head; + + if (bpf_prog_array_valid(&user->call)) { + struct user_bpf_context context = {0}; + + context.data_len = datalen; + context.data_type = USER_BPF_DATA_KERNEL; + context.kdata = data; + + trace_call_bpf(&user->call, &context); + } + + perf_head = this_cpu_ptr(user->call.perf_events); + + if (perf_head && !hlist_empty(perf_head)) { + struct trace_entry *perf_entry; + struct pt_regs *regs; + size_t size = sizeof(*perf_entry) + datalen; + int context; + + perf_entry = perf_trace_buf_alloc(ALIGN(size, 8), + ®s, &context); + + if (unlikely(!perf_entry)) + return; + + perf_fetch_caller_regs(regs); + + memcpy(perf_entry + 1, data, datalen); + + perf_trace_buf_submit(perf_entry, size, context, + user->call.event.type, 1, regs, + perf_head, NULL); + } +} +#endif + /* * Update the register page that is shared between user processes. */ @@ -573,6 +617,10 @@ static void update_reg_page_for(struct user_event *user) if (probe_func == user_event_ftrace) status |= EVENT_STATUS_FTRACE; +#ifdef CONFIG_PERF_EVENTS + else if (probe_func == user_event_perf) + status |= EVENT_STATUS_PERF; +#endif else status |= EVENT_STATUS_OTHER; } while ((++probe_func_ptr)->func); @@ -612,8 +660,27 @@ static int user_event_reg(struct trace_event_call *call, data); goto dec; - default: +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + ret = tracepoint_probe_register(call->tp, + call->class->perf_probe, + data); + if (!ret) + goto inc; + break; + + case TRACE_REG_PERF_UNREGISTER: + tracepoint_probe_unregister(call->tp, + call->class->perf_probe, + data); + goto dec; + + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: break; +#endif } return ret; @@ -870,6 +937,9 @@ static int user_event_parse(char *name, char *args, char *flags, user->class.get_fields = user_event_get_fields; user->class.reg = user_event_reg; user->class.probe = user_event_ftrace; +#ifdef CONFIG_PERF_EVENTS + user->class.perf_probe = user_event_perf; +#endif mutex_lock(&event_mutex); ret = user_event_trace_register(user); -- cgit v1.2.3 From 0279400ad38d858ed68f5d787385f6122d4170b2 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 18 Jan 2022 12:43:19 -0800 Subject: user_events: Optimize writing events by only copying data once Pass iterator through to probes to allow copying data directly to the probe buffers instead of taking multiple copies. Enables eBPF user and raw iterator types out to programs for no-copy scenarios. Link: https://lkml.kernel.org/r/20220118204326.2169-6-beaub@linux.microsoft.com Acked-by: Masami Hiramatsu Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 115 +++++++++++++++++++++++++++++---------- 1 file changed, 85 insertions(+), 30 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 371f31472156..78b6b96c4cfa 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -41,6 +41,9 @@ #define MAX_FIELD_ARRAY_SIZE 1024 #define MAX_FIELD_ARG_NAME 256 +#define MAX_BPF_COPY_SIZE PAGE_SIZE +#define MAX_STACK_BPF_DATA 512 + static char *register_page_data; static DEFINE_MUTEX(reg_mutex); @@ -78,8 +81,7 @@ struct user_event_refs { struct user_event *events[]; }; -typedef void (*user_event_func_t) (struct user_event *user, - void *data, u32 datalen, +typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i, void *tpdata); static int user_event_parse(char *name, char *args, char *flags, @@ -90,6 +92,20 @@ static u32 user_event_key(char *name) return jhash(name, strlen(name), 0); } +static __always_inline __must_check +size_t copy_nofault(void *addr, size_t bytes, struct iov_iter *i) +{ + size_t ret; + + pagefault_disable(); + + ret = copy_from_iter_nocache(addr, bytes, i); + + pagefault_enable(); + + return ret; +} + static struct list_head *user_event_get_fields(struct trace_event_call *call) { struct user_event *user = (struct user_event *)call->data; @@ -525,7 +541,7 @@ static struct user_event *find_user_event(char *name, u32 *outkey) /* * Writes the user supplied payload out to a trace file. */ -static void user_event_ftrace(struct user_event *user, void *data, u32 datalen, +static void user_event_ftrace(struct user_event *user, struct iov_iter *i, void *tpdata) { struct trace_event_file *file; @@ -541,41 +557,83 @@ static void user_event_ftrace(struct user_event *user, void *data, u32 datalen, /* Allocates and fills trace_entry, + 1 of this is data payload */ entry = trace_event_buffer_reserve(&event_buffer, file, - sizeof(*entry) + datalen); + sizeof(*entry) + i->count); if (unlikely(!entry)) return; - memcpy(entry + 1, data, datalen); - - trace_event_buffer_commit(&event_buffer); + if (unlikely(!copy_nofault(entry + 1, i->count, i))) + __trace_event_discard_commit(event_buffer.buffer, + event_buffer.event); + else + trace_event_buffer_commit(&event_buffer); } #ifdef CONFIG_PERF_EVENTS +static void user_event_bpf(struct user_event *user, struct iov_iter *i) +{ + struct user_bpf_context context; + struct user_bpf_iter bpf_i; + char fast_data[MAX_STACK_BPF_DATA]; + void *temp = NULL; + + if ((user->flags & FLAG_BPF_ITER) && iter_is_iovec(i)) { + /* Raw iterator */ + context.data_type = USER_BPF_DATA_ITER; + context.data_len = i->count; + context.iter = &bpf_i; + + bpf_i.iov_offset = i->iov_offset; + bpf_i.iov = i->iov; + bpf_i.nr_segs = i->nr_segs; + } else if (i->nr_segs == 1 && iter_is_iovec(i)) { + /* Single buffer from user */ + context.data_type = USER_BPF_DATA_USER; + context.data_len = i->count; + context.udata = i->iov->iov_base + i->iov_offset; + } else { + /* Multi buffer from user */ + struct iov_iter copy = *i; + size_t copy_size = min_t(size_t, i->count, MAX_BPF_COPY_SIZE); + + context.data_type = USER_BPF_DATA_KERNEL; + context.kdata = fast_data; + + if (unlikely(copy_size > sizeof(fast_data))) { + temp = kmalloc(copy_size, GFP_NOWAIT); + + if (temp) + context.kdata = temp; + else + copy_size = sizeof(fast_data); + } + + context.data_len = copy_nofault(context.kdata, + copy_size, ©); + } + + trace_call_bpf(&user->call, &context); + + kfree(temp); +} + /* * Writes the user supplied payload out to perf ring buffer or eBPF program. */ -static void user_event_perf(struct user_event *user, void *data, u32 datalen, +static void user_event_perf(struct user_event *user, struct iov_iter *i, void *tpdata) { struct hlist_head *perf_head; - if (bpf_prog_array_valid(&user->call)) { - struct user_bpf_context context = {0}; - - context.data_len = datalen; - context.data_type = USER_BPF_DATA_KERNEL; - context.kdata = data; - - trace_call_bpf(&user->call, &context); - } + if (bpf_prog_array_valid(&user->call)) + user_event_bpf(user, i); perf_head = this_cpu_ptr(user->call.perf_events); if (perf_head && !hlist_empty(perf_head)) { struct trace_entry *perf_entry; struct pt_regs *regs; - size_t size = sizeof(*perf_entry) + datalen; + size_t size = sizeof(*perf_entry) + i->count; int context; perf_entry = perf_trace_buf_alloc(ALIGN(size, 8), @@ -586,7 +644,10 @@ static void user_event_perf(struct user_event *user, void *data, u32 datalen, perf_fetch_caller_regs(regs); - memcpy(perf_entry + 1, data, datalen); + if (unlikely(!copy_nofault(perf_entry + 1, i->count, i))) { + perf_swevent_put_recursion_context(context); + return; + } perf_trace_buf_submit(perf_entry, size, context, user->call.event.type, 1, regs, @@ -1024,16 +1085,11 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i) if (likely(atomic_read(&tp->key.enabled) > 0)) { struct tracepoint_func *probe_func_ptr; user_event_func_t probe_func; + struct iov_iter copy; void *tpdata; - void *kdata; - u32 datalen; - kdata = kmalloc(i->count, GFP_KERNEL); - - if (unlikely(!kdata)) - return -ENOMEM; - - datalen = copy_from_iter(kdata, i->count, i); + if (unlikely(fault_in_iov_iter_readable(i, i->count))) + return -EFAULT; rcu_read_lock_sched(); @@ -1041,15 +1097,14 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i) if (probe_func_ptr) { do { + copy = *i; probe_func = probe_func_ptr->func; tpdata = probe_func_ptr->data; - probe_func(user, kdata, datalen, tpdata); + probe_func(user, ©, tpdata); } while ((++probe_func_ptr)->func); } rcu_read_unlock_sched(); - - kfree(kdata); } return ret; -- cgit v1.2.3 From 2467cda1b5c97a58776a8aebfa5d76543e47479d Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 18 Jan 2022 12:43:20 -0800 Subject: user_events: Validate user payloads for size and null termination Add validation to ensure data is at or greater than the min size for the fields of the event. If a dynamic array is used and is a type of char, ensure null termination of the array exists. Link: https://lkml.kernel.org/r/20220118204326.2169-7-beaub@linux.microsoft.com Acked-by: Masami Hiramatsu Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 147 +++++++++++++++++++++++++++++++++++---- 1 file changed, 133 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 78b6b96c4cfa..2b5e9fdb63a0 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -64,9 +64,11 @@ struct user_event { struct dyn_event devent; struct hlist_node node; struct list_head fields; + struct list_head validators; atomic_t refcnt; int index; int flags; + int min_size; }; /* @@ -81,8 +83,17 @@ struct user_event_refs { struct user_event *events[]; }; +#define VALIDATOR_ENSURE_NULL (1 << 0) +#define VALIDATOR_REL (1 << 1) + +struct user_event_validator { + struct list_head link; + int offset; + int flags; +}; + typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i, - void *tpdata); + void *tpdata, bool *faulted); static int user_event_parse(char *name, char *args, char *flags, struct user_event **newuser); @@ -215,6 +226,17 @@ static int user_field_size(const char *type) return -EINVAL; } +static void user_event_destroy_validators(struct user_event *user) +{ + struct user_event_validator *validator, *next; + struct list_head *head = &user->validators; + + list_for_each_entry_safe(validator, next, head, link) { + list_del(&validator->link); + kfree(validator); + } +} + static void user_event_destroy_fields(struct user_event *user) { struct ftrace_event_field *field, *next; @@ -230,13 +252,43 @@ static int user_event_add_field(struct user_event *user, const char *type, const char *name, int offset, int size, int is_signed, int filter_type) { + struct user_event_validator *validator; struct ftrace_event_field *field; + int validator_flags = 0; field = kmalloc(sizeof(*field), GFP_KERNEL); if (!field) return -ENOMEM; + if (str_has_prefix(type, "__data_loc ")) + goto add_validator; + + if (str_has_prefix(type, "__rel_loc ")) { + validator_flags |= VALIDATOR_REL; + goto add_validator; + } + + goto add_field; + +add_validator: + if (strstr(type, "char") != 0) + validator_flags |= VALIDATOR_ENSURE_NULL; + + validator = kmalloc(sizeof(*validator), GFP_KERNEL); + + if (!validator) { + kfree(field); + return -ENOMEM; + } + + validator->flags = validator_flags; + validator->offset = offset; + + /* Want sequential access when validating */ + list_add_tail(&validator->link, &user->validators); + +add_field: field->type = type; field->name = name; field->offset = offset; @@ -246,6 +298,12 @@ static int user_event_add_field(struct user_event *user, const char *type, list_add(&field->link, &user->fields); + /* + * Min size from user writes that are required, this does not include + * the size of trace_entry (common fields). + */ + user->min_size = (offset + size) - sizeof(struct trace_entry); + return 0; } @@ -517,6 +575,7 @@ static int destroy_user_event(struct user_event *user) clear_bit(user->index, page_bitmap); hash_del(&user->node); + user_event_destroy_validators(user); kfree(user->call.print_fmt); kfree(EVENT_NAME(user)); kfree(user); @@ -538,15 +597,49 @@ static struct user_event *find_user_event(char *name, u32 *outkey) return NULL; } +static i