From patchwork Tue Jan 8 15:00:15 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Slavomir Kaslev X-Patchwork-Id: 10760241 Return-Path: Received: from mail-pg1-f193.google.com ([209.85.215.193]:41376 "EHLO mail-pg1-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728265AbfAHPAi (ORCPT ); Tue, 8 Jan 2019 10:00:38 -0500 Received: by mail-pg1-f193.google.com with SMTP id m1so1840861pgq.8 for ; Tue, 08 Jan 2019 07:00:35 -0800 (PST) From: Slavomir Kaslev To: linux-trace-devel@vger.kernel.org Cc: rostedt@goodmis.org, ykaradzhov@vmware.com, tstoyanov@vmware.com Subject: [PATCH v2 6/6] trace-cmd: Add VM kernel tracing using vsock socket for transport Date: Tue, 8 Jan 2019 17:00:15 +0200 Message-Id: <20190108150015.21327-7-kaslevs@vmware.com> In-Reply-To: <20190108150015.21327-1-kaslevs@vmware.com> References: <20190108150015.21327-1-kaslevs@vmware.com> MIME-Version: 1.0 Sender: linux-trace-devel-owner@vger.kernel.org List-ID: Content-Length: 40869 To test, start a VM and assign it a valid (> 2) unused CID: you@host # qemu-system-x86_64 \ -name guest2 --uuid 7edfdf4a-cb9e-11e8-b38a-173b58342476 \ -m 4096 -boot d -enable-kvm -smp 3 -net nic -net user -hda $HOME/vm/guest2.img \ -device vhost-vsock-pci,id=vhost-vsock-pci0,guest-cid=3 and start `trace-cmd agent` on the guest as root: you@guest2 # trace-cmd agent Finally, start `trace-cmd record` on the host (running as root is only necessary if the host will be traced too): you@host $ trace-cmd record -A guest2 -e irq -e sched Signed-off-by: Slavomir Kaslev --- tracecmd/Makefile | 1 + tracecmd/include/trace-local.h | 19 + tracecmd/trace-agent.c | 228 ++++++++++ tracecmd/trace-cmd.c | 1 + tracecmd/trace-record.c | 733 ++++++++++++++++++++++++++++----- tracecmd/trace-usage.c | 11 +- 6 files changed, 895 insertions(+), 98 deletions(-) create mode 100644 tracecmd/trace-agent.c diff --git a/tracecmd/Makefile b/tracecmd/Makefile index 3a11024..6f2e405 100644 --- a/tracecmd/Makefile +++ b/tracecmd/Makefile @@ -17,6 +17,7 @@ TRACE_CMD_OBJS += trace-record.o TRACE_CMD_OBJS += trace-read.o TRACE_CMD_OBJS += trace-split.o TRACE_CMD_OBJS += trace-listen.o +TRACE_CMD_OBJS += trace-agent.o TRACE_CMD_OBJS += trace-stack.o TRACE_CMD_OBJS += trace-hist.o TRACE_CMD_OBJS += trace-mem.o diff --git a/tracecmd/include/trace-local.h b/tracecmd/include/trace-local.h index a1a06e9..5072d8e 100644 --- a/tracecmd/include/trace-local.h +++ b/tracecmd/include/trace-local.h @@ -12,6 +12,8 @@ #include "trace-cmd.h" #include "event-utils.h" +#define TRACE_AGENT_DEFAULT_PORT 823 + extern int debug; extern int quiet; @@ -64,6 +66,8 @@ void trace_split(int argc, char **argv); void trace_listen(int argc, char **argv); +void trace_agent(int argc, char **argv); + void trace_restore(int argc, char **argv); void trace_clear(int argc, char **argv); @@ -88,6 +92,10 @@ void trace_list(int argc, char **argv); void trace_usage(int argc, char **argv); +int trace_record_agent(struct tracecmd_msg_handle *msg_handle, + int cpus, int *fds, + int argc, char **argv); + struct hook_list; void trace_init_profile(struct tracecmd_input *handle, struct hook_list *hooks, @@ -149,6 +157,8 @@ char *strstrip(char *str); enum buffer_instance_flags { BUFFER_FL_KEEP = 1 << 0, BUFFER_FL_PROFILE = 1 << 1, + BUFFER_FL_GUEST = 1 << 2, + BUFFER_FL_AGENT = 1 << 3, }; struct func_list { @@ -174,6 +184,7 @@ struct buffer_instance { struct func_list *notrace_funcs; const char *clock; + int *client_ports; struct trace_seq *s_save; struct trace_seq *s_print; @@ -188,6 +199,14 @@ struct buffer_instance { int tracing_on_fd; int buffer_size; int cpu_count; + + int argc; + char **argv; + int argv_cap; + + int cid; + int port; + int *fds; }; extern struct buffer_instance top_instance; diff --git a/tracecmd/trace-agent.c b/tracecmd/trace-agent.c new file mode 100644 index 0000000..b34d757 --- /dev/null +++ b/tracecmd/trace-agent.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Copyright (C) 2018 VMware Inc, Slavomir Kaslev + * + * based on prior implementation by Yoshihiro Yunomae + * Copyright (C) 2013 Hitachi, Ltd. + * Yoshihiro YUNOMAE + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "trace-local.h" +#include "trace-msg.h" + +static int make_vsock(unsigned port) +{ + struct sockaddr_vm addr = { + .svm_family = AF_VSOCK, + .svm_cid = VMADDR_CID_ANY, + .svm_port = port, + }; + int sd; + + sd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (sd < 0) + return -1; + + setsockopt(sd, SOL_SOCKET, SO_REUSEADDR, &(int){1}, sizeof(int)); + + if (bind(sd, (struct sockaddr *)&addr, sizeof(addr))) + return -1; + + if (listen(sd, SOMAXCONN)) + return -1; + + return sd; +} + +static int get_vsock_port(int sd) +{ + struct sockaddr_vm addr; + socklen_t addr_len = sizeof(addr); + + if (getsockname(sd, (struct sockaddr *)&addr, &addr_len)) + return -1; + + if (addr.svm_family != AF_VSOCK) + return -1; + + return addr.svm_port; +} + +static void make_vsocks(int nr, int **fds, int **ports) +{ + int i, fd, port; + + *fds = calloc(nr, sizeof(*fds)); + *ports = calloc(nr, sizeof(*ports)); + if (!*fds || !*ports) + die("Failed to allocate memory"); + + for (i = 0; i < nr; i++) { + fd = make_vsock(VMADDR_PORT_ANY); + if (fd < 0) + die("Failed to open vsock socket"); + + port = get_vsock_port(fd); + if (port < 0) + die("Failed to get vsock socket address"); + + (*fds)[i] = fd; + (*ports)[i] = port; + } +} + +static void free_vsocks(int nr, int *fds, int *ports) +{ + int i; + + for (i = 0; i < nr; i++) + close(fds[i]); + free(fds); + free(ports); +} + +static void agent_handle(int sd, int nr_cpus, int page_size) +{ + struct tracecmd_msg_handle *msg_handle; + int *fds, *ports; + char **argv = NULL; + int argc = 0; + + msg_handle = tracecmd_msg_handle_alloc(sd, TRACECMD_MSG_FL_CLIENT); + if (!msg_handle) + die("Failed to allocate message handle"); + + if (tracecmd_msg_recv_trace_req(msg_handle, &argc, &argv)) + die("Failed to receive trace request"); + + make_vsocks(nr_cpus, &fds, &ports); + + if (tracecmd_msg_send_trace_resp(msg_handle, nr_cpus, page_size, ports)) + die("Failed to send trace response"); + + trace_record_agent(msg_handle, nr_cpus, fds, argc, argv); + + free_vsocks(nr_cpus, fds, ports); + free(argv[0]); + free(argv); + tracecmd_msg_handle_close(msg_handle); + exit(0); +} + +static volatile pid_t handler_pid; + +static void handle_sigchld(int sig) +{ + int wstatus; + pid_t pid; + + for (;;) { + pid = waitpid(-1, &wstatus, WNOHANG); + if (pid <= 0) + break; + + if (pid == handler_pid) + handler_pid = 0; + } +} + +static void agent_serve(unsigned port) +{ + int sd, cd, nr_cpus; + pid_t pid; + + signal(SIGCHLD, handle_sigchld); + + nr_cpus = count_cpus(); + page_size = getpagesize(); + + sd = make_vsock(port); + if (sd < 0) + die("Failed to open vsock socket"); + + for (;;) { + cd = accept(sd, NULL, NULL); + if (cd < 0) { + if (errno == EINTR) + continue; + die("accept"); + } + + if (handler_pid) + goto busy; + + pid = fork(); + if (pid == 0) { + signal(SIGCHLD, SIG_DFL); + agent_handle(cd, nr_cpus, page_size); + } + if (pid > 0) + handler_pid = pid; + + busy: + close(cd); + } + + close(sd); + signal(SIGCHLD, SIG_DFL); +} + +void trace_agent(int argc, char **argv) +{ + bool do_daemon = false; + unsigned port = TRACE_AGENT_DEFAULT_PORT; + + if (argc < 2) + usage(argv); + + if (strcmp(argv[1], "agent") != 0) + usage(argv); + + for (;;) { + int c, option_index = 0; + static struct option long_options[] = { + {"port", required_argument, NULL, 'p'}, + {"help", no_argument, NULL, '?'}, + {NULL, 0, NULL, 0} + }; + + c = getopt_long(argc-1, argv+1, "+hp:D", + long_options, &option_index); + if (c == -1) + break; + switch (c) { + case 'h': + usage(argv); + break; + case 'p': + port = atoi(optarg); + break; + case 'D': + do_daemon = true; + break; + default: + usage(argv); + } + } + + if ((argc - optind) >= 2) + usage(argv); + + if (do_daemon && daemon(1, 0)) + die("daemon"); + + agent_serve(port); +} diff --git a/tracecmd/trace-cmd.c b/tracecmd/trace-cmd.c index 797b303..2d4fc1b 100644 --- a/tracecmd/trace-cmd.c +++ b/tracecmd/trace-cmd.c @@ -83,6 +83,7 @@ struct command commands[] = { {"hist", trace_hist}, {"mem", trace_mem}, {"listen", trace_listen}, + {"agent", trace_agent}, {"split", trace_split}, {"restore", trace_restore}, {"stack", trace_stack}, diff --git a/tracecmd/trace-record.c b/tracecmd/trace-record.c index e45a1f8..1783875 100644 --- a/tracecmd/trace-record.c +++ b/tracecmd/trace-record.c @@ -32,6 +32,7 @@ #include #include #include +#include #include "trace-local.h" #include "trace-msg.h" @@ -73,8 +74,6 @@ static int buffers; static int clear_function_filters; static char *host; -static int *client_ports; -static int sfd; /* Max size to let a per cpu file get */ static int max_kb; @@ -170,6 +169,15 @@ static struct tracecmd_recorder *recorder; static int ignore_event_not_found = 0; +static inline size_t grow_cap(size_t old_cap) +{ + size_t cap = 3 * old_cap / 2; + + if (cap < 16) + cap = 16; + return cap; +} + static inline int is_top_instance(struct buffer_instance *instance) { return instance == &top_instance; @@ -190,6 +198,36 @@ enum { RESET_HIGH_PRIO = 100000, }; +enum trace_cmd { + CMD_extract, + CMD_start, + CMD_stream, + CMD_profile, + CMD_record, + CMD_record_agent, +}; + +struct common_record_context { + enum trace_cmd curr_cmd; + struct buffer_instance *instance; + const char *output; + char *date2ts; + char *max_graph_depth; + int data_flags; + + int record_all; + int total_disable; + int disable; + int events; + int global; + int filtered; + int date; + int manual; + int topt; + int do_child; + int run_command; +}; + static void add_reset_file(const char *file, const char *val, int prio) { struct reset_file *reset; @@ -487,6 +525,36 @@ static char *get_temp_file(struct buffer_instance *instance, int cpu) return file; } +static char *get_guest_file(const char *file, const char *guest) +{ + size_t guest_len = strlen(guest); + size_t file_len = strlen(file); + size_t base_len, idx = 0; + const char *p; + char *out; + + out = malloc(file_len + guest_len + 2 /* dash and \0 */); + if (!out) + return NULL; + + p = strrchr(file, '.'); + if (p && p != file) + base_len = p - file; + else + base_len = file_len; + + memcpy(out, file, base_len); + idx += base_len; + out[idx++] = '-'; + memcpy(out + idx, guest, guest_len); + idx += guest_len; + memcpy(out + idx, p, file_len - base_len); + idx += file_len - base_len; + out[idx] = '\0'; + + return out; +} + static void put_temp_file(char *file) { free(file); @@ -592,6 +660,16 @@ static void delete_thread_data(void) } } +static void tell_guests_to_stop(void) +{ + struct buffer_instance *instance; + + for_all_instances(instance) { + if (instance->flags & BUFFER_FL_GUEST) + tracecmd_msg_handle_close(instance->msg_handle); + } +} + static void stop_threads(enum trace_type type) { struct timeval tv = { 0, 0 }; @@ -601,6 +679,8 @@ static void stop_threads(enum trace_type type) if (!recorder_threads) return; + tell_guests_to_stop(); + /* Tell all threads to finish up */ for (i = 0; i < recorder_threads; i++) { if (pids[i].pid > 0) { @@ -750,6 +830,9 @@ static void __clear_trace(struct buffer_instance *instance) FILE *fp; char *path; + if (instance->flags & BUFFER_FL_GUEST) + return; + /* reset the trace */ path = get_instance_file(instance, "trace"); fp = fopen(path, "w"); @@ -1233,6 +1316,9 @@ set_plugin_instance(struct buffer_instance *instance, const char *name) char *path; char zero = '0'; + if (instance->flags & BUFFER_FL_GUEST) + return; + path = get_instance_file(instance, "current_tracer"); fp = fopen(path, "w"); if (!fp) { @@ -1329,6 +1415,9 @@ static void disable_func_stack_trace_instance(struct buffer_instance *instance) int size; int ret; + if (instance->flags & BUFFER_FL_GUEST) + return; + path = get_instance_file(instance, "current_tracer"); ret = stat(path, &st); tracecmd_put_tracing_file(path); @@ -1522,6 +1611,9 @@ reset_events_instance(struct buffer_instance *instance) int i; int ret; + if (instance->flags & BUFFER_FL_GUEST) + return; + if (use_old_event_method()) { /* old way only had top instance */ if (!is_top_instance(instance)) @@ -1873,6 +1965,9 @@ static void write_tracing_on(struct buffer_instance *instance, int on) int ret; int fd; + if (instance->flags & BUFFER_FL_GUEST) + return; + fd = open_tracing_on(instance); if (fd < 0) return; @@ -1892,6 +1987,9 @@ static int read_tracing_on(struct buffer_instance *instance) char buf[10]; int ret; + if (instance->flags & BUFFER_FL_GUEST) + return -1; + fd = open_tracing_on(instance); if (fd < 0) return fd; @@ -2125,6 +2223,9 @@ static void set_mask(struct buffer_instance *instance) int fd; int ret; + if (instance->flags & BUFFER_FL_GUEST) + return; + if (!instance->cpumask) return; @@ -2155,6 +2256,9 @@ static void enable_events(struct buffer_instance *instance) { struct event_list *event; + if (instance->flags & BUFFER_FL_GUEST) + return; + for (event = instance->events; event; event = event->next) { if (!event->neg) update_event(event, event->filter, 0, '1'); @@ -2178,6 +2282,9 @@ static void set_clock(struct buffer_instance *instance) char *content; char *str; + if (instance->flags & BUFFER_FL_GUEST) + return; + if (!instance->clock) return; @@ -2207,6 +2314,9 @@ static void set_max_graph_depth(struct buffer_instance *instance, char *max_grap char *path; int ret; + if (instance->flags & BUFFER_FL_GUEST) + return; + path = get_instance_file(instance, "max_graph_depth"); reset_save_file(path, RESET_DEFAULT_PRIO); tracecmd_put_tracing_file(path); @@ -2432,6 +2542,9 @@ static void expand_event_instance(struct buffer_instance *instance) struct event_list *compressed_list = instance->events; struct event_list *event; + if (instance->flags & BUFFER_FL_GUEST) + return; + reset_event_list(instance); while (compressed_list) { @@ -2507,14 +2620,14 @@ static void flush(int sig) tracecmd_stop_recording(recorder); } -static void connect_port(int cpu) +static int connect_port(const char *host, unsigned port) { struct addrinfo hints; struct addrinfo *results, *rp; - int s; + int s, sfd; char buf[BUFSIZ]; - snprintf(buf, BUFSIZ, "%d", client_ports[cpu]); + snprintf(buf, BUFSIZ, "%d", port); memset(&hints, 0, sizeof(hints)); hints.ai_family = AF_UNSPEC; @@ -2541,7 +2654,182 @@ static void connect_port(int cpu) freeaddrinfo(results); - client_ports[cpu] = sfd; + return sfd; +} + +static int open_vsock(unsigned cid, unsigned port) +{ + struct sockaddr_vm addr = { + .svm_family = AF_VSOCK, + .svm_cid = cid, + .svm_port = port, + }; + int sd; + + sd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (sd < 0) + return -1; + + if (connect(sd, (struct sockaddr *)&addr, sizeof(addr))) + return -1; + + return sd; +} + +static int do_accept(int sd) +{ + int cd; + + for (;;) { + cd = accept(sd, NULL, NULL); + if (cd < 0) { + if (errno == EINTR) + continue; + die("accept"); + } + + return cd; + } + + return -1; +} + +static bool is_digits(const char *s) +{ + const char *p; + + for (p = s; *p; p++) + if (!isdigit(*p)) + return false; + + return true; +} + +struct guest { + char *name; + int cid; + int pid; +}; + +static size_t guests_cap, guests_len; +static struct guest *guests; + +static char *get_qemu_guest_name(char *arg) +{ + char *tok, *end = arg; + + while ((tok = strsep(&end, ","))) { + if (strncmp(tok, "guest=", 6) == 0) + return tok + 6; + } + + return arg; +} + +static void read_qemu_guests(void) +{ + static bool initialized = false; + struct dirent *entry; + char path[PATH_MAX]; + DIR *dir; + + if (initialized) + return; + + initialized = true; + dir = opendir("/proc"); + if (!dir) + die("opendir"); + + for (entry = readdir(dir); entry; entry = readdir(dir)) { + bool is_qemu = false, last_was_name = false; + struct guest guest = {}; + char *p, *arg = NULL; + size_t arg_size = 0; + FILE *f; + + if (!(entry->d_type == DT_DIR && is_digits(entry->d_name))) + continue; + + guest.pid = atoi(entry->d_name); + snprintf(path, sizeof(path), "/proc/%s/cmdline", entry->d_name); + f = fopen(path, "r"); + if (!f) + continue; + + while (getdelim(&arg, &arg_size, 0, f) != -1) { + if (!is_qemu && strstr(arg, "qemu-system-")) { + is_qemu = true; + continue; + } + + if (!is_qemu) + continue; + + if (strcmp(arg, "-name") == 0) { + last_was_name = true; + continue; + } + + if (last_was_name) { + guest.name = strdup(get_qemu_guest_name(arg)); + last_was_name = false; + continue; + } + + p = strstr(arg, "guest-cid="); + if (p) { + guest.cid = atoi(p + 10); + continue; + } + } + + if (is_qemu) { + if (guests_cap == guests_len) { + guests_cap = grow_cap(guests_cap); + guests = realloc(guests, + guests_cap * sizeof(*guests)); + } + guests[guests_len++] = guest; + } + + free(arg); + fclose(f); + } + + closedir(dir); +} + +static char *parse_guest_name(char *guest, int *cid, int *port) +{ + size_t i; + char *p; + + *port = -1; + p = strrchr(guest, ':'); + if (p) { + *p = '\0'; + *port = atoi(p + 1); + } + + *cid = -1; + p = strrchr(guest, '@'); + if (p) { + *p = '\0'; + *cid = atoi(p + 1); + } else if (is_digits(guest)) + *cid = atoi(guest); + + read_qemu_guests(); + for (i = 0; i < guests_len; i++) { + if ((*cid > 0 && *cid == guests[i].cid) || + strcmp(guest, guests[i].name) == 0) { + *cid = guests[i].cid; + return guests[i].name; + } + } + + return guest; } static void set_prio(int prio) @@ -2588,6 +2876,16 @@ create_recorder_instance(struct buffer_instance *instance, const char *file, int struct tracecmd_recorder *record; char *path; + if (instance->flags & BUFFER_FL_GUEST) { + int sd; + + sd = open_vsock(instance->cid, instance->client_ports[cpu]); + if (sd < 0) + die("Failed to connect to agent"); + + return tracecmd_create_recorder_virt(file, cpu, sd); + } + if (brass) return create_recorder_instance_pipe(instance, cpu, brass); @@ -2612,7 +2910,7 @@ static int create_recorder(struct buffer_instance *instance, int cpu, { long ret; char *file; - int pid; + pid_t pid; if (type != TRACE_TYPE_EXTRACT) { signal(SIGUSR1, flush); @@ -2631,19 +2929,26 @@ static int create_recorder(struct buffer_instance *instance, int cpu, instance->cpu_count = 0; } - if (client_ports) { - char *path; + if ((instance->client_ports && !(instance->flags & BUFFER_FL_GUEST)) || + (instance->flags & BUFFER_FL_AGENT)) { + unsigned flags = recorder_flags; + char *path = NULL; + int fd; - connect_port(cpu); - if (instance->name) + if (instance->flags & BUFFER_FL_AGENT) { + fd = do_accept(instance->fds[cpu]); + flags |= TRACECMD_RECORD_NOSPLICE; + } else { + fd = connect_port(host, instance->client_ports[cpu]); + } + if (fd < 0) + die("Failed connecting to client"); + if (instance->name && !(instance->flags & BUFFER_FL_AGENT)) path = get_instance_dir(instance); else path = tracecmd_find_tracing_dir(); - recorder = tracecmd_create_buffer_recorder_fd(client_ports[cpu], - cpu, recorder_flags, - path); - if (instance->name) - tracecmd_put_tracing_file(path); + recorder = tracecmd_create_buffer_recorder_fd(fd, cpu, flags, path); + tracecmd_put_tracing_file(path); } else { file = get_temp_file(instance, cpu); recorder = create_recorder_instance(instance, file, cpu, brass); @@ -2681,7 +2986,8 @@ static void check_first_msg_from_server(struct tracecmd_msg_handle *msg_handle) die("server not tracecmd server"); } -static void communicate_with_listener_v1(struct tracecmd_msg_handle *msg_handle) +static void communicate_with_listener_v1(struct tracecmd_msg_handle *msg_handle, + int **client_ports) { char buf[BUFSIZ]; ssize_t n; @@ -2724,8 +3030,8 @@ static void communicate_with_listener_v1(struct tracecmd_msg_handle *msg_handle) /* No options */ write(msg_handle->fd, "0", 2); - client_ports = malloc(sizeof(int) * local_cpu_count); - if (!client_ports) + *client_ports = malloc(sizeof(int) * local_cpu_count); + if (!*client_ports) die("Failed to allocate client ports for %d cpus", local_cpu_count); /* @@ -2743,13 +3049,14 @@ static void communicate_with_listener_v1(struct tracecmd_msg_handle *msg_handle) if (i == BUFSIZ) die("read bad port number"); buf[i] = 0; - client_ports[cpu] = atoi(buf); + (*client_ports)[cpu] = atoi(buf); } } -static void communicate_with_listener_v3(struct tracecmd_msg_handle *msg_handle) +static void communicate_with_listener_v3(struct tracecmd_msg_handle *msg_handle, + int **client_ports) { - if (tracecmd_msg_send_init_data(msg_handle, &client_ports) < 0) + if (tracecmd_msg_send_init_data(msg_handle, client_ports) < 0) die("Cannot communicate with server"); } @@ -2800,7 +3107,7 @@ static void check_protocol_version(struct tracecmd_msg_handle *msg_handle) } } -static struct tracecmd_msg_handle *setup_network(void) +static struct tracecmd_msg_handle *setup_network(struct buffer_instance *instance) { struct tracecmd_msg_handle *msg_handle = NULL; struct addrinfo hints; @@ -2870,29 +3177,29 @@ again: close(sfd); goto again; } - communicate_with_listener_v3(msg_handle); + communicate_with_listener_v3(msg_handle, &instance->client_ports); } if (msg_handle->version == V1_PROTOCOL) - communicate_with_listener_v1(msg_handle); + communicate_with_listener_v1(msg_handle, &instance->client_ports); return msg_handle; } -static void add_options(struct tracecmd_output *handle, char *date2ts, int flags); +static void add_options(struct tracecmd_output *handle, struct common_record_context *ctx); static struct tracecmd_msg_handle * -setup_connection(struct buffer_instance *instance, char *date2ts, int flags) +setup_connection(struct buffer_instance *instance, struct common_record_context *ctx) { struct tracecmd_msg_handle *msg_handle; struct tracecmd_output *network_handle; - msg_handle = setup_network(); + msg_handle = setup_network(instance); /* Now create the handle through this socket */ if (msg_handle->version == V3_PROTOCOL) { network_handle = tracecmd_create_init_fd_msg(msg_handle, listed_events); - add_options(network_handle, date2ts, flags); + add_options(network_handle, ctx); tracecmd_write_cpus(network_handle, instance->cpu_count); tracecmd_write_options(network_handle); tracecmd_msg_finish_sending_data(msg_handle); @@ -2911,32 +3218,99 @@ static void finish_network(struct tracecmd_msg_handle *msg_handle) if (msg_handle->version == V3_PROTOCOL) tracecmd_msg_send_close_msg(msg_handle); tracecmd_msg_handle_close(msg_handle); - free(host); } -void start_threads(enum trace_type type, int global, char *date2ts, int flags) +static void connect_to_agent(struct buffer_instance *instance) +{ + struct tracecmd_msg_handle *msg_handle; + int sd, nr_cpus, page_size, *ports; + + sd = open_vsock(instance->cid, instance->port); + if (sd < 0) + die("Failed to connect to vsock socket @%d:%d", + instance->cid, instance->port); + + msg_handle = tracecmd_msg_handle_alloc(sd, TRACECMD_MSG_FL_SERVER); + if (!msg_handle) + die("Failed to allocate message handle"); + + if (tracecmd_msg_send_trace_req(msg_handle, instance->argc, instance->argv)) + die("Failed to send trace request"); + + if (tracecmd_msg_recv_trace_resp(msg_handle, &nr_cpus, &page_size, &ports)) + die("Failed to receive trace response"); + + instance->client_ports = ports; + instance->cpu_count = nr_cpus; + + /* the msg_handle now points to the guest fd */ + instance->msg_handle = msg_handle; +} + +static void setup_guest(struct buffer_instance *instance) +{ + struct tracecmd_msg_handle *msg_handle = instance->msg_handle; + char *file; + int fd; + + /* Create a place to store the guest meta data */ + file = get_guest_file(output_file, instance->name); + if (!file) + die("Failed to allocate memory"); + + fd = open(file, O_CREAT|O_WRONLY|O_TRUNC, 0644); + put_temp_file(file); + if (fd < 0) + die("Failed to open", file); + + /* Start reading the fds here */ + if (tracecmd_msg_read_data(msg_handle, fd)) + die("Failed receiving metadata"); + close(fd); +} + +static void setup_agent(struct buffer_instance *instance, struct common_record_context *ctx) +{ + struct tracecmd_output *network_handle; + + network_handle = tracecmd_create_init_fd_msg(instance->msg_handle, + listed_events); + add_options(network_handle, ctx); + tracecmd_write_cpus(network_handle, instance->cpu_count); + tracecmd_write_options(network_handle); + tracecmd_msg_finish_sending_data(instance->msg_handle); + instance->network_handle = network_handle; +} + +void start_threads(enum trace_type type, struct common_record_context *ctx) { struct buffer_instance *instance; - int *brass = NULL; int total_cpu_count = 0; int i = 0; int ret; - for_all_instances(instance) + for_all_instances(instance) { + /* Start the connection now to find out how many CPUs we need */ + if (instance->flags & BUFFER_FL_GUEST) + connect_to_agent(instance); total_cpu_count += instance->cpu_count; + } /* make a thread for every CPU we have */ - pids = malloc(sizeof(*pids) * total_cpu_count * (buffers + 1)); + pids = calloc(total_cpu_count * (buffers + 1), sizeof(*pids)); if (!pids) - die("Failed to allocat pids for %d cpus", total_cpu_count); - - memset(pids, 0, sizeof(*pids) * total_cpu_count * (buffers + 1)); + die("Failed to allocate pids for %d cpus", total_cpu_count); for_all_instances(instance) { + int *brass = NULL; int x, pid; - if (host) { - instance->msg_handle = setup_connection(instance, date2ts, flags); + if (instance->flags & BUFFER_FL_AGENT) { + setup_agent(instance, ctx); + } else if (instance->flags & BUFFER_FL_GUEST) { + setup_guest(instance); + } else if (host) { + instance->msg_handle = setup_connection(instance, ctx); if (!instance->msg_handle) die("Failed to make connection"); } @@ -2951,7 +3325,7 @@ void start_threads(enum trace_type type, int global, char *date2ts, int flags) brass[0], instance->cpu_count, hooks, handle_init, - global); + ctx->global); if (!pids[i].stream) die("Creating stream for %d", i); } else @@ -3075,13 +3449,14 @@ static void print_stat(struct buffer_instance *instance) { int cpu; + if (quiet) + return; + if (!is_top_instance(instance)) - if (!quiet) - printf("\nBuffer: %s\n\n", instance->name); + printf("\nBuffer: %s\n\n", instance->name); for (cpu = 0; cpu < instance->cpu_count; cpu++) - if (!quiet) - trace_seq_do_printf(&instance->s_print[cpu]); + trace_seq_do_printf(&instance->s_print[cpu]); } enum { @@ -3090,27 +3465,64 @@ enum { DATA_FL_OFFSET = 2, }; -static void add_options(struct tracecmd_output *handle, char *date2ts, int flags) +static void add_options(struct tracecmd_output *handle, struct common_record_context *ctx) { int type = 0; - if (date2ts) { - if (flags & DATA_FL_DATE) + if (ctx->date2ts) { + if (ctx->data_flags & DATA_FL_DATE) type = TRACECMD_OPTION_DATE; - else if (flags & DATA_FL_OFFSET) + else if (ctx->data_flags & DATA_FL_OFFSET) type = TRACECMD_OPTION_OFFSET; } if (type) - tracecmd_add_option(handle, type, strlen(date2ts)+1, date2ts); + tracecmd_add_option(handle, type, strlen(ctx->date2ts)+1, ctx->date2ts); tracecmd_add_option(handle, TRACECMD_OPTION_TRACECLOCK, 0, NULL); add_option_hooks(handle); add_uname(handle); +} + +static void write_guest_file(struct buffer_instance *instance) +{ + struct tracecmd_output *handle; + int cpu_count = instance->cpu_count; + char *file; + char **temp_files; + int i, fd; + + file = get_guest_file(output_file, instance->name); + fd = open(file, O_RDWR); + if (fd < 0) + die("error opening %s", file); + put_temp_file(file); + + handle = tracecmd_get_output_handle_fd(fd); + if (!handle) + die("error writing to %s", file); + + temp_files = malloc(sizeof(*temp_files) * cpu_count); + if (!temp_files) + die("failed to allocate temp_files for %d cpus", + cpu_count); + + for (i = 0; i < cpu_count; i++) { + temp_files[i] = get_temp_file(instance, i); + if (!temp_files[i]) + die("failed to allocate memory"); + } + + if (tracecmd_write_cpu_data(handle, cpu_count, temp_files) < 0) + die("failed to write CPU data"); + tracecmd_output_close(handle); + for (i = 0; i < cpu_count; i++) + put_temp_file(temp_files[i]); + free(temp_files); } -static void record_data(char *date2ts, int flags) +static void record_data(struct common_record_context *ctx) { struct tracecmd_option **buffer_options; struct tracecmd_output *handle; @@ -3121,7 +3533,9 @@ static void record_data(char *date2ts, int flags) int i; for_all_instances(instance) { - if (instance->msg_handle) + if (instance->flags & BUFFER_FL_GUEST) + write_guest_file(instance); + else if (host && instance->msg_handle) finish_network(instance->msg_handle); else local = true; @@ -3165,7 +3579,7 @@ static void record_data(char *date2ts, int flags) if (!handle) die("Error creating output file"); - add_options(handle, date2ts, flags); + add_options(handle, ctx); /* Only record the top instance under TRACECMD_OPTION_CPUSTAT*/ if (!no_top_instance() && !top_instance.msg_handle) { @@ -3305,6 +3719,9 @@ static void set_funcs(struct buffer_instance *instance) int set_notrace = 0; int ret; + if (instance->flags & BUFFER_FL_GUEST) + return; + ret = write_func_file(instance, "set_ftrace_filter", &instance->filter_funcs); if (ret < 0) die("set_ftrace_filter does not exist. Can not filter functions"); @@ -3600,6 +4017,9 @@ static void set_buffer_size_instance(struct buffer_instance *instance) int ret; int fd; + if (instance->flags & BUFFER_FL_GUEST) + return; + if (!buffer_size) return; @@ -3797,6 +4217,9 @@ static void make_instances(void) int ret; for_each_instance(instance) { + if (instance->flags & BUFFER_FL_GUEST) + continue; + path = get_instance_dir(instance); ret = stat(path, &st); if (ret < 0) { @@ -3818,7 +4241,7 @@ void tracecmd_remove_instances(void) for_each_instance(instance) { /* Only delete what we created */ - if (instance->flags & BUFFER_FL_KEEP) + if (instance->flags & (BUFFER_FL_KEEP | BUFFER_FL_GUEST)) continue; if (instance->tracing_on_fd > 0) { close(instance->tracing_on_fd); @@ -3900,7 +4323,7 @@ static void check_function_plugin(void) static int __check_doing_something(struct buffer_instance *instance) { - return (instance->flags & BUFFER_FL_PROFILE) || + return (instance->flags & (BUFFER_FL_PROFILE | BUFFER_FL_GUEST)) || instance->plugin || instance->events; } @@ -3922,6 +4345,9 @@ update_plugin_instance(struct buffer_instance *instance, { const char *plugin = instance->plugin; + if (instance->flags & BUFFER_FL_GUEST) + return; + if (!plugin) return; @@ -4021,6 +4447,9 @@ static void record_stats(void) int cpu; for_all_instances(instance) { + if (instance->flags & BUFFER_FL_GUEST) + continue; + s_save = instance->s_save; s_print = instance->s_print; for (cpu = 0; cpu < instance->cpu_count; cpu++) { @@ -4047,6 +4476,9 @@ static void destroy_stats(void) int cpu; for_all_instances(instance) { + if (instance->flags & BUFFER_FL_GUEST) + continue; + for (cpu = 0; cpu < instance->cpu_count; cpu++) { trace_seq_destroy(&instance->s_save[cpu]); trace_seq_destroy(&instance->s_print[cpu]); @@ -4321,6 +4753,7 @@ void trace_stop(int argc, char **argv) c = getopt(argc-1, argv+1, "hatB:"); if (c == -1) break; + switch (c) { case 'h': usage(argv); @@ -4467,35 +4900,6 @@ void trace_reset(int argc, char **argv) exit(0); } -enum trace_cmd { - CMD_extract, - CMD_start, - CMD_stream, - CMD_profile, - CMD_record -}; - -struct common_record_context { - enum trace_cmd curr_cmd; - struct buffer_instance *instance; - const char *output; - char *date2ts; - char *max_graph_depth; - int data_flags; - - int record_all; - int total_disable; - int disable; - int events; - int global; - int filtered; - int date; - int manual; - int topt; - int do_child; - int run_command; -}; - static void init_common_record_context(struct common_record_context *ctx, enum trace_cmd curr_cmd) { @@ -4512,6 +4916,60 @@ static void init_common_record_context(struct common_record_context *ctx, #define IS_STREAM(ctx) ((ctx)->curr_cmd == CMD_stream) #define IS_PROFILE(ctx) ((ctx)->curr_cmd == CMD_profile) #define IS_RECORD(ctx) ((ctx)->curr_cmd == CMD_record) +#define IS_AGENT(ctx) ((ctx)->curr_cmd == CMD_record_agent) + +static void add_argv(struct buffer_instance *instance, char *arg) +{ + if (instance->argv_cap == instance->argc) { + instance->argv_cap = grow_cap(instance->argv_cap); + instance->argv = realloc(instance->argv, + instance->argv_cap * sizeof(char *)); + if (!instance->argv) + die("Can not allocate buffer args"); + } + instance->argv[instance->argc] = arg; + instance->argc++; +} + +static void add_arg(struct buffer_instance *instance, + int c, const char *opts, + struct option *long_options, char *optarg) +{ + char *ptr; + char *arg; + int ret; + int i; + + /* Short or long arg */ + if (!(c & 0x80)) { + ret = asprintf(&arg, "-%c", c); + if (ret < 0) + die("Can not allocate argument"); + ptr = strstr(opts, arg+1); + if (!ptr) + return; /* Not found? */ + add_argv(instance, arg); + if (ptr[1] == ':') + add_argv(instance, optarg); + return; + } + for (i = 0; long_options[i].name; i++) { + if (c == long_options[i].val) { + ret = asprintf(&arg, "--%s", long_options[i].name); + if (ret < 0) + die("Can not allocate argument"); + add_argv(instance, arg); + if (long_options[i].has_arg) { + arg = strdup(optarg); + if (!arg) + die("Can not allocate arguments"); + add_argv(instance, arg); + return; + } + } + } + /* Not found? */ +} static void parse_record_options(int argc, char **argv, @@ -4553,10 +5011,20 @@ static void parse_record_options(int argc, if (IS_EXTRACT(ctx)) opts = "+haf:Fp:co:O:sr:g:l:n:P:N:tb:B:ksiT"; else - opts = "+hae:f:Fp:cC:dDGo:O:s:r:vg:l:n:P:N:tb:R:B:ksSiTm:M:H:q"; + opts = "+hae:f:FA:p:cC:dDGo:O:s:r:vg:l:n:P:N:tb:R:B:ksSiTm:M:H:q"; c = getopt_long (argc-1, argv+1, opts, long_options, &option_index); if (c == -1) break; + + /* + * If the current instance is to record a guest, then save + * all the arguments for this instance. + */ + if (c != 'B' && c != 'A' && ctx->instance->flags & BUFFER_FL_GUEST) { + add_arg(ctx->instance, c, opts, long_options, optarg); + continue; + } + switch (c) { case 'h': usage(argv); @@ -4609,6 +5077,26 @@ static void parse_record_options(int argc, add_trigger(event, optarg); break; + case 'A': { + char *name = NULL; + int cid = -1, port = -1; + + if (!IS_RECORD(ctx)) + die("-A is only allowed for record operations"); + + name = parse_guest_name(optarg, &cid, &port); + if (!name || cid == -1) + die("guest %s not found", optarg); + if (port == -1) + port = TRACE_AGENT_DEFAULT_PORT; + + ctx->instance = create_instance(name); + ctx->instance->flags |= BUFFER_FL_GUEST; + ctx->instance->cid = cid; + ctx->instance->port = port; + add_instance(ctx->instance, 0); + break; + } case 'F': test_set_event_pid(); filter_task = 1; @@ -4679,6 +5167,8 @@ static void parse_record_options(int argc, ctx->disable = 1; break; case 'o': + if (IS_AGENT(ctx)) + die("-o incompatible with agent recording"); if (host) die("-o incompatible with -N"); if (IS_START(ctx)) @@ -4740,6 +5230,8 @@ static void parse_record_options(int argc, case 'N': if (!IS_RECORD(ctx)) die("-N only available with record"); + if (IS_AGENT(ctx)) + die("-N incompatible with agent recording"); if (ctx->output) die("-N incompatible with -o"); host = optarg; @@ -4866,7 +5358,8 @@ static enum trace_type get_trace_cmd_type(enum trace_cmd cmd) {CMD_stream, TRACE_TYPE_STREAM}, {CMD_extract, TRACE_TYPE_EXTRACT}, {CMD_profile, TRACE_TYPE_STREAM}, - {CMD_start, TRACE_TYPE_START} + {CMD_start, TRACE_TYPE_START}, + {CMD_record_agent, TRACE_TYPE_RECORD} }; for (int i = 0; i < ARRAY_SIZE(trace_type_per_command); i++) { @@ -4898,6 +5391,8 @@ static void finalize_record_trace(struct common_record_context *ctx) if (instance->flags & BUFFER_FL_KEEP) write_tracing_on(instance, instance->tracing_on_init_val); + if (instance->flags & BUFFER_FL_AGENT) + tracecmd_output_close(instance->network_handle); } if (host) @@ -4932,7 +5427,6 @@ static void record_trace(int argc, char **argv, /* Save the state of tracing_on before starting */ for_all_instances(instance) { - if (!ctx->manual && instance->flags & BUFFER_FL_PROFILE) enable_profile(instance); @@ -4949,14 +5443,16 @@ static void record_trace(int argc, char **argv, page_size = getpagesize(); - fset = set_ftrace(!ctx->disable, ctx->total_disable); + if (!(ctx->instance->flags & BUFFER_FL_GUEST)) + fset = set_ftrace(!ctx->disable, ctx->total_disable); tracecmd_disable_all_tracing(1); for_all_instances(instance) set_clock(instance); /* Record records the date first */ - if (IS_RECORD(ctx) && ctx->date) + if (((IS_RECORD(ctx) && !(ctx->instance->flags & BUFFER_FL_GUEST)) || + IS_AGENT(ctx)) && ctx->date) ctx->date2ts = get_date_to_ts(); for_all_instances(instance) { @@ -4984,16 +5480,20 @@ static void record_trace(int argc, char **argv, if (type & (TRACE_TYPE_RECORD | TRACE_TYPE_STREAM)) { signal(SIGINT, finish); if (!latency) - start_threads(type, ctx->global, ctx->date2ts, ctx->data_flags); + start_threads(type, ctx); } else { update_task_filter(); tracecmd_enable_tracing(); exit(0); } - if (ctx->run_command) + if (ctx->run_command) { run_cmd(type, (argc - optind) - 1, &argv[optind + 1]); - else { + } else if (ctx->instance && (ctx->instance->flags & BUFFER_FL_AGENT)) { + update_task_filter(); + tracecmd_enable_tracing(); + tracecmd_msg_wait_close(ctx->instance->msg_handle); + } else { update_task_filter(); tracecmd_enable_tracing(); /* We don't ptrace ourself */ @@ -5014,11 +5514,13 @@ static void record_trace(int argc, char **argv, if (!keep) tracecmd_disable_all_tracing(0); - if (IS_RECORD(ctx)) { - record_data(ctx->date2ts, ctx->data_flags); - delete_thread_data(); - } else - print_stats(); + if (!IS_AGENT(ctx)) { + if (IS_RECORD(ctx)) { + record_data(ctx); + delete_thread_data(); + } else + print_stats(); + } destroy_stats(); finalize_record_trace(ctx); @@ -5095,7 +5597,7 @@ void trace_extract(int argc, char **argv) ctx.date2ts = get_date_to_ts(); } - record_data(ctx.date2ts, ctx.data_flags); + record_data(&ctx); delete_thread_data(); destroy_stats(); finalize_record_trace(&ctx); @@ -5148,3 +5650,40 @@ void trace_record(int argc, char **argv) record_trace(argc, argv, &ctx); exit(0); } + +int trace_record_agent(struct tracecmd_msg_handle *msg_handle, + int cpus, int *fds, + int argc, char **argv) +{ + struct common_record_context ctx; + char **argv_plus; + + /* Reset optind for getopt_long */ + optind = 1; + /* + * argc is the number of elements in argv, but we need to convert + * argc and argv into "trace-cmd", "record", argv. + * where argc needs to grow by two. + */ + argv_plus = calloc(argc + 2, sizeof(char *)); + if (!argv_plus) + return -ENOMEM; + + argv_plus[0] = "trace-cmd"; + argv_plus[1] = "record"; + memcpy(argv_plus + 2, argv, argc * sizeof(char *)); + argc += 2; + + parse_record_options(argc, argv_plus, CMD_record_agent, &ctx); + if (ctx.run_command) + return -EINVAL; + + ctx.instance->fds = fds; + ctx.instance->flags |= BUFFER_FL_AGENT; + ctx.instance->msg_handle = msg_handle; + msg_handle->version = V3_PROTOCOL; + record_trace(argc, argv, &ctx); + + free(argv_plus); + return 0; +} diff --git a/tracecmd/trace-usage.c b/tracecmd/trace-usage.c index 9ea1906..db8389d 100644 --- a/tracecmd/trace-usage.c +++ b/tracecmd/trace-usage.c @@ -231,11 +231,20 @@ static struct usage_help usage_help[] = { "listen on a network socket for trace clients", " %s listen -p port[-D][-o file][-d dir][-l logfile]\n" " Creates a socket to listen for clients.\n" - " -D create it in daemon mode.\n" + " -p port number to listen on.\n" + " -D run in daemon mode.\n" " -o file name to use for clients.\n" " -d directory to store client files.\n" " -l logfile to write messages to.\n" }, + { + "agent", + "listen on a vsock socket for trace clients", + " %s agent -p port[-D]\n" + " Creates a vsock socket to listen for clients.\n" + " -p port number to listen on.\n" + " -D run in daemon mode.\n" + }, { "list", "list the available events, plugins or options",