diff options
Diffstat (limited to 'tools')
413 files changed, 17590 insertions, 5081 deletions
diff --git a/tools/hv/Makefile b/tools/hv/Makefile index bd22f786a60c..99ffe61051a7 100644 --- a/tools/hv/Makefile +++ b/tools/hv/Makefile @@ -5,9 +5,9 @@ PTHREAD_LIBS = -lpthread WARNINGS = -Wall -Wextra CFLAGS = $(WARNINGS) -g $(PTHREAD_LIBS) -all: hv_kvp_daemon hv_vss_daemon +all: hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon %: %.c $(CC) $(CFLAGS) -o $@ $^ clean: - $(RM) hv_kvp_daemon hv_vss_daemon + $(RM) hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c index 8f96b3ee0724..9445d8f264a4 100644 --- a/tools/hv/hv_fcopy_daemon.c +++ b/tools/hv/hv_fcopy_daemon.c @@ -33,6 +33,7 @@ #include <sys/stat.h> #include <fcntl.h> #include <dirent.h> +#include <getopt.h> static int target_fd; static char target_fname[W_MAX_PATH]; @@ -42,15 +43,9 @@ static int hv_start_fcopy(struct hv_start_fcopy *smsg) int error = HV_E_FAIL; char *q, *p; - /* - * If possile append a path seperator to the path. - */ - if (strlen((char *)smsg->path_name) < (W_MAX_PATH - 2)) - strcat((char *)smsg->path_name, "/"); - p = (char *)smsg->path_name; snprintf(target_fname, sizeof(target_fname), "%s/%s", - (char *)smsg->path_name, smsg->file_name); + (char *)smsg->path_name, (char *)smsg->file_name); syslog(LOG_INFO, "Target file name: %s", target_fname); /* @@ -126,15 +121,43 @@ static int hv_copy_cancel(void) } -int main(void) +void print_usage(char *argv[]) +{ + fprintf(stderr, "Usage: %s [options]\n" + "Options are:\n" + " -n, --no-daemon stay in foreground, don't daemonize\n" + " -h, --help print this help\n", argv[0]); +} + +int main(int argc, char *argv[]) { - int fd, fcopy_fd, len; + int fcopy_fd, len; int error; + int daemonize = 1, long_index = 0, opt; int version = FCOPY_CURRENT_VERSION; char *buffer[4096 * 2]; struct hv_fcopy_hdr *in_msg; - if (daemon(1, 0)) { + static struct option long_options[] = { + {"help", no_argument, 0, 'h' }, + {"no-daemon", no_argument, 0, 'n' }, + {0, 0, 0, 0 } + }; + + while ((opt = getopt_long(argc, argv, "hn", long_options, + &long_index)) != -1) { + switch (opt) { + case 'n': + daemonize = 0; + break; + case 'h': + default: + print_usage(argv); + exit(EXIT_FAILURE); + } + } + + if (daemonize && daemon(1, 0)) { syslog(LOG_ERR, "daemon() failed; error: %s", strerror(errno)); exit(EXIT_FAILURE); } diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index 4088b816a3ee..408bb076a234 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -43,6 +43,7 @@ #include <fcntl.h> #include <dirent.h> #include <net/if.h> +#include <getopt.h> /* * KVP protocol: The user mode component first registers with the @@ -146,7 +147,6 @@ static void kvp_release_lock(int pool) static void kvp_update_file(int pool) { FILE *filep; - size_t bytes_written; /* * We are going to write our in-memory registry out to @@ -162,8 +162,7 @@ static void kvp_update_file(int pool) exit(EXIT_FAILURE); } - bytes_written = fwrite(kvp_file_info[pool].records, - sizeof(struct kvp_record), + fwrite(kvp_file_info[pool].records, sizeof(struct kvp_record), kvp_file_info[pool].num_records, filep); if (ferror(filep) || fclose(filep)) { @@ -309,7 +308,7 @@ static int kvp_file_init(void) return 0; } -static int kvp_key_delete(int pool, const char *key, int key_size) +static int kvp_key_delete(int pool, const __u8 *key, int key_size) { int i; int j, k; @@ -352,8 +351,8 @@ static int kvp_key_delete(int pool, const char *key, int key_size) return 1; } -static int kvp_key_add_or_modify(int pool, const char *key, int key_size, const char *value, - int value_size) +static int kvp_key_add_or_modify(int pool, const __u8 *key, int key_size, + const __u8 *value, int value_size) { int i; int num_records; @@ -406,7 +405,7 @@ static int kvp_key_add_or_modify(int pool, const char *key, int key_size, const return 0; } -static int kvp_get_value(int pool, const char *key, int key_size, char *value, +static int kvp_get_value(int pool, const __u8 *key, int key_size, __u8 *value, int value_size) { int i; @@ -438,8 +437,8 @@ static int kvp_get_value(int pool, const char *key, int key_size, char *value, return 1; } -static int kvp_pool_enumerate(int pool, int index, char *key, int key_size, - char *value, int value_size) +static int kvp_pool_enumerate(int pool, int index, __u8 *key, int key_size, + __u8 *value, int value_size) { struct kvp_record *record; @@ -660,7 +659,7 @@ static char *kvp_if_name_to_mac(char *if_name) char *p, *x; char buf[256]; char addr_file[256]; - int i; + unsigned int i; char *mac_addr = NULL; snprintf(addr_file, sizeof(addr_file), "%s%s%s", "/sys/class/net/", @@ -699,7 +698,7 @@ static char *kvp_mac_to_if_name(char *mac) char buf[256]; char *kvp_net_dir = "/sys/class/net/"; char dev_id[256]; - int i; + unsigned int i; dir = opendir(kvp_net_dir); if (dir == NULL) @@ -749,7 +748,7 @@ static char *kvp_mac_to_if_name(char *mac) static void kvp_process_ipconfig_file(char *cmd, - char *config_buf, int len, + char *config_buf, unsigned int len, int element_size, int offset) { char buf[256]; @@ -767,7 +766,7 @@ static void kvp_process_ipconfig_file(char *cmd, if (offset == 0) memset(config_buf, 0, len); while ((p = fgets(buf, sizeof(buf), file)) != NULL) { - if ((len - strlen(config_buf)) < (element_size + 1)) + if (len < strlen(config_buf) + element_size + 1) break; x = strchr(p, '\n'); @@ -915,7 +914,7 @@ static int kvp_process_ip_address(void *addrp, static int kvp_get_ip_info(int family, char *if_name, int op, - void *out_buffer, int length) + void *out_buffer, unsigned int length) { struct ifaddrs *ifap; struct ifaddrs *curp; @@ -1018,8 +1017,7 @@ kvp_get_ip_info(int family, char *if_name, int op, weight += hweight32(&w[i]); sprintf(cidr_mask, "/%d", weight); - if ((length - sn_offset) < - (strlen(cidr_mask) + 1)) + if (length < sn_offset + strlen(cidr_mask) + 1) goto gather_ipaddr; if (sn_offset == 0) @@ -1307,16 +1305,17 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) if (error) goto setval_error; + /* + * The dhcp_enabled flag is only for IPv4. In the case the host only + * injects an IPv6 address, the flag is true, but we still need to + * proceed to parse and pass the IPv6 information to the + * disto-specific script hv_set_ifconfig. + */ if (new_val->dhcp_enabled) { error = kvp_write_file(file, "BOOTPROTO", "", "dhcp"); if (error) goto setval_error; - /* - * We are done!. - */ - goto setval_done; - } else { error = kvp_write_file(file, "BOOTPROTO", "", "none"); if (error) @@ -1344,7 +1343,6 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) if (error) goto setval_error; -setval_done: fclose(file); /* @@ -1417,7 +1415,15 @@ netlink_send(int fd, struct cn_msg *msg) return sendmsg(fd, &message, 0); } -int main(void) +void print_usage(char *argv[]) +{ + fprintf(stderr, "Usage: %s [options]\n" + "Options are:\n" + " -n, --no-daemon stay in foreground, don't daemonize\n" + " -h, --help print this help\n", argv[0]); +} + +int main(int argc, char *argv[]) { int fd, len, nl_group; int error; @@ -1435,9 +1441,30 @@ int main(void) struct hv_kvp_ipaddr_value *kvp_ip_val; char *kvp_recv_buffer; size_t kvp_recv_buffer_len; + int daemonize = 1, long_index = 0, opt; + + static struct option long_options[] = { + {"help", no_argument, 0, 'h' }, + {"no-daemon", no_argument, 0, 'n' }, + {0, 0, 0, 0 } + }; + + while ((opt = getopt_long(argc, argv, "hn", long_options, + &long_index)) != -1) { + switch (opt) { + case 'n': + daemonize = 0; + break; + case 'h': + default: + print_usage(argv); + exit(EXIT_FAILURE); + } + } - if (daemon(1, 0)) + if (daemonize && daemon(1, 0)) return 1; + openlog("KVP", 0, LOG_USER); syslog(LOG_INFO, "KVP starting; pid is:%d", getpid()); @@ -1529,8 +1556,15 @@ int main(void) addr_p, &addr_l); if (len < 0) { + int saved_errno = errno; syslog(LOG_ERR, "recvfrom failed; pid:%u error:%d %s", addr.nl_pid, errno, strerror(errno)); + + if (saved_errno == ENOBUFS) { + syslog(LOG_ERR, "receive error: ignored"); + continue; + } + close(fd); return -1; } @@ -1733,8 +1767,15 @@ kvp_done: len = netlink_send(fd, incoming_cn_msg); if (len < 0) { + int saved_errno = errno; syslog(LOG_ERR, "net_link send failed; error: %d %s", errno, strerror(errno)); + + if (saved_errno == ENOMEM || saved_errno == ENOBUFS) { + syslog(LOG_ERR, "send error: ignored"); + continue; + } + exit(EXIT_FAILURE); } } diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c index 6a213b8cd7b9..5e63f70bd956 100644 --- a/tools/hv/hv_vss_daemon.c +++ b/tools/hv/hv_vss_daemon.c @@ -36,6 +36,7 @@ #include <linux/hyperv.h> #include <linux/netlink.h> #include <syslog.h> +#include <getopt.h> static struct sockaddr_nl addr; @@ -44,35 +45,51 @@ static struct sockaddr_nl addr; #endif -static int vss_do_freeze(char *dir, unsigned int cmd, char *fs_op) +/* Don't use syslog() in the function since that can cause write to disk */ +static int vss_do_freeze(char *dir, unsigned int cmd) { int ret, fd = open(dir, O_RDONLY); if (fd < 0) return 1; + ret = ioctl(fd, cmd, 0); - syslog(LOG_INFO, "VSS: %s of %s: %s\n", fs_op, dir, strerror(errno)); + + /* + * If a partition is mounted more than once, only the first + * FREEZE/THAW can succeed and the later ones will get + * EBUSY/EINVAL respectively: there could be 2 cases: + * 1) a user may mount the same partition to differnt directories + * by mistake or on purpose; + * 2) The subvolume of btrfs appears to have the same partition + * mounted more than once. + */ + if (ret) { + if ((cmd == FIFREEZE && errno == EBUSY) || + (cmd == FITHAW && errno == EINVAL)) { + close(fd); + return 0; + } + } + close(fd); return !!ret; } static int vss_operate(int operation) { - char *fs_op; char match[] = "/dev/"; FILE *mounts; struct mntent *ent; unsigned int cmd; - int error = 0, root_seen = 0; + int error = 0, root_seen = 0, save_errno = 0; switch (operation) { case VSS_OP_FREEZE: cmd = FIFREEZE; - fs_op = "freeze"; break; case VSS_OP_THAW: cmd = FITHAW; - fs_op = "thaw"; break; default: return -1; @@ -85,7 +102,7 @@ static int vss_operate(int operation) while ((ent = getmntent(mounts))) { if (strncmp(ent->mnt_fsname, match, strlen(match))) continue; - if (strcmp(ent->mnt_type, "iso9660") == 0) + if (hasmntopt(ent, MNTOPT_RO) != NULL) continue; if (strcmp(ent->mnt_type, "vfat") == 0) continue; @@ -93,14 +110,30 @@ static int vss_operate(int operation) root_seen = 1; continue; } - error |= vss_do_freeze(ent->mnt_dir, cmd, fs_op); + error |= vss_do_freeze(ent->mnt_dir, cmd); + if (error && operation == VSS_OP_FREEZE) + goto err; } - endmntent(mounts); if (root_seen) { - error |= vss_do_freeze("/", cmd, fs_op); + error |= vss_do_freeze("/", cmd); + if (error && operation == VSS_OP_FREEZE) + goto err; } + goto out; +err: + save_errno = errno; + vss_operate(VSS_OP_THAW); + /* Call syslog after we thaw all filesystems */ + if (ent) + syslog(LOG_ERR, "FREEZE of %s failed; error:%d %s", + ent->mnt_dir, save_errno, strerror(save_errno)); + else + syslog(LOG_ERR, "FREEZE of / failed; error:%d %s", save_errno, + strerror(save_errno)); +out: + endmntent(mounts); return error; } @@ -131,7 +164,15 @@ static int netlink_send(int fd, struct cn_msg *msg) return sendmsg(fd, &message, 0); } -int main(void) +void print_usage(char *argv[]) +{ + fprintf(stderr, "Usage: %s [options]\n" + "Options are:\n" + " -n, --no-daemon stay in foreground, don't daemonize\n" + " -h, --help print this help\n", argv[0]); +} + +int main(int argc, char *argv[]) { int fd, len, nl_group; int error; @@ -143,8 +184,28 @@ int main(void) struct hv_vss_msg *vss_msg; char *vss_recv_buffer; size_t vss_recv_buffer_len; + int daemonize = 1, long_index = 0, opt; + + static struct option long_options[] = { + {"help", no_argument, 0, 'h' }, + {"no-daemon", no_argument, 0, 'n' }, + {0, 0, 0, 0 } + }; + + while ((opt = getopt_long(argc, argv, "hn", long_options, + &long_index)) != -1) { + switch (opt) { + case 'n': + daemonize = 0; + break; + case 'h': + default: + print_usage(argv); + exit(EXIT_FAILURE); + } + } - if (daemon(1, 0)) + if (daemonize && daemon(1, 0)) return 1; openlog("Hyper-V VSS", 0, LOG_USER); @@ -249,8 +310,16 @@ int main(void) case VSS_OP_FREEZE: case VSS_OP_THAW: error = vss_operate(op); - if (error) + syslog(LOG_INFO, "VSS: op=%s: %s\n", + op == VSS_OP_FREEZE ? "FREEZE" : "THAW", + error ? "failed" : "succeeded"); + + if (error) { error = HV_E_FAIL; + syslog(LOG_ERR, "op=%d failed!", op); + syslog(LOG_ERR, "report it with these files:"); + syslog(LOG_ERR, "/etc/fstab and /proc/mounts"); + } break; default: syslog(LOG_ERR, "Illegal op:%d\n", op); diff --git a/tools/iio/Makefile b/tools/iio/Makefile new file mode 100644 index 000000000000..bf7ae6d6612a --- /dev/null +++ b/tools/iio/Makefile @@ -0,0 +1,16 @@ +CC = gcc +CFLAGS = -Wall -g -D_GNU_SOURCE + +all: iio_event_monitor lsiio generic_buffer + +iio_event_monitor: iio_event_monitor.o iio_utils.o + +lsiio: lsiio.o iio_utils.o + +generic_buffer: generic_buffer.o iio_utils.o + +%.o: %.c iio_utils.h + +.PHONY: clean +clean: + rm -f *.o iio_event_monitor lsiio generic_buffer diff --git a/tools/iio/generic_buffer.c b/tools/iio/generic_buffer.c new file mode 100644 index 000000000000..f805493be3eb --- /dev/null +++ b/tools/iio/generic_buffer.c @@ -0,0 +1,359 @@ +/* Industrialio buffer test code. + * + * Copyright (c) 2008 Jonathan Cameron + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is primarily intended as an example application. + * Reads the current buffer setup from sysfs and starts a short capture + * from the specified device, pretty printing the result after appropriate + * conversion. + * + * Command line parameters + * generic_buffer -n <device_name> -t <trigger_name> + * If trigger name is not specified the program assumes you want a dataready + * trigger associated with the device and goes looking for it. + * + */ + +#include <unistd.h> +#include <stdlib.h> +#include <dirent.h> +#include <fcntl.h> +#include <stdio.h> +#include <errno.h> +#include <sys/stat.h> +#include <sys/dir.h> +#include <linux/types.h> +#include <string.h> +#include <poll.h> +#include <endian.h> +#include <getopt.h> +#include <inttypes.h> +#include "iio_utils.h" + +/** + * size_from_channelarray() - calculate the storage size of a scan + * @channels: the channel info array + * @num_channels: number of channels + * + * Has the side effect of filling the channels[i].location values used + * in processing the buffer output. + **/ +int size_from_channelarray(struct iio_channel_info *channels, int num_channels) +{ + int bytes = 0; + int i = 0; + + while (i < num_channels) { + if (bytes % channels[i].bytes == 0) + channels[i].location = bytes; + else + channels[i].location = bytes - bytes%channels[i].bytes + + channels[i].bytes; + bytes = channels[i].location + channels[i].bytes; + i++; + } + return bytes; +} + +void print2byte(int input, struct iio_channel_info *info) +{ + /* First swap if incorrect endian */ + if (info->be) + input = be16toh((uint16_t)input); + else + input = le16toh((uint16_t)input); + + /* + * Shift before conversion to avoid sign extension + * of left aligned data + */ + input >>= info->shift; + if (info->is_signed) { + int16_t val = input; + + val &= (1 << info->bits_used) - 1; + val = (int16_t)(val << (16 - info->bits_used)) >> + (16 - info->bits_used); + printf("%05f ", ((float)val + info->offset)*info->scale); + } else { + uint16_t val = input; + + val &= (1 << info->bits_used) - 1; + printf("%05f ", ((float)val + info->offset)*info->scale); + } +} +/** + * process_scan() - print out the values in SI units + * @data: pointer to the start of the scan + * @channels: information about the channels. Note + * size_from_channelarray must have been called first to fill the + * location offsets. + * @num_channels: number of channels + **/ +void process_scan(char *data, + struct iio_channel_info *channels, + int num_channels) +{ + int k; + + for (k = 0; k < num_channels; k++) + switch (channels[k].bytes) { + /* only a few cases implemented so far */ + case 2: + print2byte(*(uint16_t *)(data + channels[k].location), + &channels[k]); + break; + case 4: + if (!channels[k].is_signed) { + uint32_t val = *(uint32_t *) + (data + channels[k].location); + printf("%05f ", ((float)val + + channels[k].offset)* + channels[k].scale); + + } + break; + case 8: + if (channels[k].is_signed) { + int64_t val = *(int64_t *) + (data + + channels[k].location); + if ((val >> channels[k].bits_used) & 1) + val = (val & channels[k].mask) | + ~channels[k].mask; + /* special case for timestamp */ + if (channels[k].scale == 1.0f && + channels[k].offset == 0.0f) + printf("%" PRId64 " ", val); + else + printf("%05f ", ((float)val + + channels[k].offset)* + channels[k].scale); + } + break; + default: + break; + } + printf("\n"); +} + +int main(int argc, char **argv) +{ + unsigned long num_loops = 2; + unsigned long timedelay = 1000000; + unsigned long buf_len = 128; + + int ret, c, i, j, toread; + int fp; + + int num_channels; + char *trigger_name = NULL, *device_name = NULL; + char *dev_dir_name, *buf_dir_name; + + int datardytrigger = 1; + char *data; + ssize_t read_size; + int dev_num, trig_num; + char *buffer_access; + int scan_size; + int noevents = 0; + int notrigger = 0; + char *dummy; + + struct iio_channel_info *channels; + + while ((c = getopt(argc, argv, "l:w:c:et:n:g")) != -1) { + switch (c) { + case 'n': + device_name = optarg; + break; + case 't': + trigger_name = optarg; + datardytrigger = 0; + break; + case 'e': + noevents = 1; + break; + case 'c': + num_loops = strtoul(optarg, &dummy, 10); + break; + case 'w': + timedelay = strtoul(optarg, &dummy, 10); + break; + case 'l': + buf_len = strtoul(optarg, &dummy, 10); + break; + case 'g': + notrigger = 1; + break; + case '?': + return -1; + } + } + + if (device_name == NULL) + return -1; + + /* Find the device requested */ + dev_num = find_type_by_name(device_name, "iio:device"); + if (dev_num < 0) { + printf("Failed to find the %s\n", device_name); + ret = -ENODEV; + goto error_ret; + } + printf("iio device number being used is %d\n", dev_num); + + asprintf(&dev_dir_name, "%siio:device%d", iio_dir, dev_num); + + if (!notrigger) { + if (trigger_name == NULL) { + /* + * Build the trigger name. If it is device associated + * its name is <device_name>_dev[n] where n matches + * the device number found above. + */ + ret = asprintf(&trigger_name, + "%s-dev%d", device_name, dev_num); + if (ret < 0) { + ret = -ENOMEM; + goto error_ret; + } + } + + /* Verify the trigger exists */ + trig_num = find_type_by_name(trigger_name, "trigger"); + if (trig_num < 0) { + printf("Failed to find the trigger %s\n", trigger_name); + ret = -ENODEV; + goto error_free_triggername; + } + printf("iio trigger number being used is %d\n", trig_num); + } else + printf("trigger-less mode selected\n"); + + /* + * Parse the files in scan_elements to identify what channels are + * present + */ + ret = build_channel_array(dev_dir_name, &channels, &num_channels); + if (ret) { + printf("Problem reading scan element information\n"); + printf("diag %s\n", dev_dir_name); + goto error_free_triggername; + } + + /* + * Construct the directory name for the associated buffer. + * As we know that the lis3l02dq has only one buffer this may + * be built rather than found. + */ + ret = asprintf(&buf_dir_name, + "%siio:device%d/buffer", iio_dir, dev_num); + if (ret < 0) { + ret = -ENOMEM; + goto error_free_triggername; + } + + if (!notrigger) { + printf("%s %s\n", dev_dir_name, trigger_name); + /* Set the device trigger to be the data ready trigger found + * above */ + ret = write_sysfs_string_and_verify("trigger/current_trigger", + dev_dir_name, + trigger_name); + if (ret < 0) { + printf("Failed to write current_trigger file\n"); + goto error_free_buf_dir_name; + } + } + + /* Setup ring buffer parameters */ + ret = write_sysfs_int("length", buf_dir_name, buf_len); + if (ret < 0) + goto error_free_buf_dir_name; + + /* Enable the buffer */ + ret = write_sysfs_int("enable", buf_dir_name, 1); + if (ret < 0) + goto error_free_buf_dir_name; + scan_size = size_from_channelarray(channels, num_channels); + data = malloc(scan_size*buf_len); + if (!data) { + ret = -ENOMEM; + goto error_free_buf_dir_name; + } + + ret = asprintf(&buffer_access, "/dev/iio:device%d", dev_num); + if (ret < 0) { + ret = -ENOMEM; + goto error_free_data; + } + + /* Attempt to open non blocking the access dev */ + fp = open(buffer_access, O_RDONLY | O_NONBLOCK); + if (fp == -1) { /* If it isn't there make the node */ + printf("Failed to open %s\n", buffer_access); + ret = -errno; + goto error_free_buffer_access; + } + + /* Wait for events 10 times */ + for (j = 0; j < num_loops; j++) { + if (!noevents) { + struct pollfd pfd = { + .fd = fp, + .events = POLLIN, + }; + + poll(&pfd, 1, -1); + toread = buf_len; + + } else { + usleep(timedelay); + toread = 64; + } + + read_size = read(fp, + data, + toread*scan_size); + if (read_size < 0) { + if (errno == -EAGAIN) { + printf("nothing available\n"); + continue; + } else + break; + } + for (i = 0; i < read_size/scan_size; i++) + process_scan(data + scan_size*i, + channels, + num_channels); + } + + /* Stop the buffer */ + ret = write_sysfs_int("enable", buf_dir_name, 0); + if (ret < 0) + goto error_close_buffer_access; + + if (!notrigger) + /* Disconnect the trigger - just write a dummy name. */ + write_sysfs_string("trigger/current_trigger", + dev_dir_name, "NULL"); + +error_close_buffer_access: + close(fp); +error_free_data: + free(data); +error_free_buffer_access: + free(buffer_access); +error_free_buf_dir_name: + free(buf_dir_name); +error_free_triggername: + if (datardytrigger) + free(trigger_name); +error_ret: + return ret; +} diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c new file mode 100644 index 000000000000..427c271ac0d6 --- /dev/null +++ b/tools/iio/iio_event_monitor.c @@ -0,0 +1,308 @@ +/* Industrialio event test code. + * + * Copyright (c) 2011-2012 Lars-Peter Clausen <lars@metafoo.de> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is primarily intended as an example application. + * Reads the current buffer setup from sysfs and starts a short capture + * from the specified device, pretty printing the result after appropriate + * conversion. + * + * Usage: + * iio_event_monitor <device_name> + * + */ + +#include <unistd.h> +#include <stdlib.h> +#include <stdbool.h> +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <poll.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include "iio_utils.h" +#include <linux/iio/events.h> +#include <linux/iio/types.h> + +static const char * const iio_chan_type_name_spec[] = { + [IIO_VOLTAGE] = "voltage", + [IIO_CURRENT] = "current", + [IIO_POWER] = "power", + [IIO_ACCEL] = "accel", + [IIO_ANGL_VEL] = "anglvel", + [IIO_MAGN] = "magn", + [IIO_LIGHT] = "illuminance", + [IIO_INTENSITY] = "intensity", + [IIO_PROXIMITY] = "proximity", + [IIO_TEMP] = "temp", + [IIO_INCLI] = "incli", + [IIO_ROT] = "rot", + [IIO_ANGL] = "angl", + [IIO_TIMESTAMP] = "timestamp", + [IIO_CAPACITANCE] = "capacitance", + [IIO_ALTVOLTAGE] = "altvoltage", + [IIO_CCT] = "cct", + [IIO_PRESSURE] = "pressure", + [IIO_HUMIDITYRELATIVE] = "humidityrelative", + [IIO_ACTIVITY] = "activity", + [IIO_STEPS] = "steps", +}; + +static const char * const iio_ev_type_text[] = { + [IIO_EV_TYPE_THRESH] = "thresh", + [IIO_EV_TYPE_MAG] = "mag", + [IIO_EV_TYPE_ROC] = "roc", + [IIO_EV_TYPE_THRESH_ADAPTIVE] = "thresh_adaptive", + [IIO_EV_TYPE_MAG_ADAPTIVE] = "mag_adaptive", + [IIO_EV_TYPE_CHANGE] = "change", +}; + +static const char * const iio_ev_dir_text[] = { + [IIO_EV_DIR_EITHER] = "either", + [IIO_EV_DIR_RISING] = "rising", + [IIO_EV_DIR_FALLING] = "falling" +}; + +static const char * const iio_modifier_names[] = { + [IIO_MOD_X] = "x", + [IIO_MOD_Y] = "y", + [IIO_MOD_Z] = "z", + [IIO_MOD_X_AND_Y] = "x&y", + [IIO_MOD_X_AND_Z] = "x&z", + [IIO_MOD_Y_AND_Z] = "y&z", + [IIO_MOD_X_AND_Y_AND_Z] = "x&y&z", + [IIO_MOD_X_OR_Y] = "x|y", + [IIO_MOD_X_OR_Z] = "x|z", + [IIO_MOD_Y_OR_Z] = "y|z", + [IIO_MOD_X_OR_Y_OR_Z] = "x|y|z", + [IIO_MOD_LIGHT_BOTH] = "both", + [IIO_MOD_LIGHT_IR] = "ir", + [IIO_MOD_ROOT_SUM_SQUARED_X_Y] = "sqrt(x^2+y^2)", + [IIO_MOD_SUM_SQUARED_X_Y_Z] = "x^2+y^2+z^2", + [IIO_MOD_LIGHT_CLEAR] = "clear", + [IIO_MOD_LIGHT_RED] = "red", + [IIO_MOD_LIGHT_GREEN] = "green", + [IIO_MOD_LIGHT_BLUE] = "blue", + [IIO_MOD_QUATERNION] = "quaternion", + [IIO_MOD_TEMP_AMBIENT] = "ambient", + [IIO_MOD_TEMP_OBJECT] = "object", + [IIO_MOD_NORTH_MAGN] = "from_north_magnetic", + [IIO_MOD_NORTH_TRUE] = "from_north_true", + [IIO_MOD_NORTH_MAGN_TILT_COMP] = "from_north_magnetic_tilt_comp", + [IIO_MOD_NORTH_TRUE_TILT_COMP] = "from_north_true_tilt_comp", + [IIO_MOD_RUNNING] = "running", + [IIO_MOD_JOGGING] = "jogging", + [IIO_MOD_WALKING] = "walking", + [IIO_MOD_STILL] = "still", +}; + +static bool event_is_known(struct iio_event_data *event) +{ + enum iio_chan_type type = IIO_EVENT_CODE_EXTRACT_CHAN_TYPE(event->id); + enum iio_modifier mod = IIO_EVENT_CODE_EXTRACT_MODIFIER(event->id); + enum iio_event_type ev_type = IIO_EVENT_CODE_EXTRACT_TYPE(event->id); + enum iio_event_direction dir = IIO_EVENT_CODE_EXTRACT_DIR(event->id); + + switch (type) { + case IIO_VOLTAGE: + case IIO_CURRENT: + case IIO_POWER: + case IIO_ACCEL: + case IIO_ANGL_VEL: + case IIO_MAGN: + case IIO_LIGHT: + case IIO_INTENSITY: + case IIO_PROXIMITY: + case IIO_TEMP: + case IIO_INCLI: + case IIO_ROT: + case IIO_ANGL: + case IIO_TIMESTAMP: + case IIO_CAPACITANCE: + case IIO_ALTVOLTAGE: + case IIO_CCT: + case IIO_PRESSURE: + case IIO_HUMIDITYRELATIVE: + case IIO_ACTIVITY: + case IIO_STEPS: + break; + default: + return false; + } + + switch (mod) { + case IIO_NO_MOD: + case IIO_MOD_X: + case IIO_MOD_Y: + case IIO_MOD_Z: + case IIO_MOD_X_AND_Y: + case IIO_MOD_X_AND_Z: + case IIO_MOD_Y_AND_Z: + case IIO_MOD_X_AND_Y_AND_Z: + case IIO_MOD_X_OR_Y: + case IIO_MOD_X_OR_Z: + case IIO_MOD_Y_OR_Z: + case IIO_MOD_X_OR_Y_OR_Z: + case IIO_MOD_LIGHT_BOTH: + case IIO_MOD_LIGHT_IR: + case IIO_MOD_ROOT_SUM_SQUARED_X_Y: + case IIO_MOD_SUM_SQUARED_X_Y_Z: + case IIO_MOD_LIGHT_CLEAR: + case IIO_MOD_LIGHT_RED: + case IIO_MOD_LIGHT_GREEN: + case IIO_MOD_LIGHT_BLUE: + case IIO_MOD_QUATERNION: + case IIO_MOD_TEMP_AMBIENT: + case IIO_MOD_TEMP_OBJECT: + case IIO_MOD_NORTH_MAGN: + case IIO_MOD_NORTH_TRUE: + case IIO_MOD_NORTH_MAGN_TILT_COMP: + case IIO_MOD_NORTH_TRUE_TILT_COMP: + case IIO_MOD_RUNNING: + case IIO_MOD_JOGGING: + case IIO_MOD_WALKING: + case IIO_MOD_STILL: + break; + default: + return false; + } + + switch (ev_type) { + case IIO_EV_TYPE_THRESH: + case IIO_EV_TYPE_MAG: + case IIO_EV_TYPE_ROC: + case IIO_EV_TYPE_THRESH_ADAPTIVE: + case IIO_EV_TYPE_MAG_ADAPTIVE: + case IIO_EV_TYPE_CHANGE: + break; + default: + return false; + } + + switch (dir) { + case IIO_EV_DIR_EITHER: + case IIO_EV_DIR_RISING: + case IIO_EV_DIR_FALLING: + case IIO_EV_DIR_NONE: + break; + default: + return false; + } + + return true; +} + +static void print_event(struct iio_event_data *event) +{ + enum iio_chan_type type = IIO_EVENT_CODE_EXTRACT_CHAN_TYPE(event->id); + enum iio_modifier mod = IIO_EVENT_CODE_EXTRACT_MODIFIER(event->id); + enum iio_event_type ev_type = IIO_EVENT_CODE_EXTRACT_TYPE(event->id); + enum iio_event_direction dir = IIO_EVENT_CODE_EXTRACT_DIR(event->id); + int chan = IIO_EVENT_CODE_EXTRACT_CHAN(event->id); + int chan2 = IIO_EVENT_CODE_EXTRACT_CHAN2(event->id); + bool diff = IIO_EVENT_CODE_EXTRACT_DIFF(event->id); + + if (!event_is_known(event)) { + printf("Unknown event: time: %lld, id: %llx\n", + event->timestamp, event->id); + return; + } + + printf("Event: time: %lld, ", event->timestamp); + + if (mod != IIO_NO_MOD) { + printf("type: %s(%s), ", + iio_chan_type_name_spec[type], + iio_modifier_names[mod]); + } else { + printf("type: %s, ", + iio_chan_type_name_spec[type]); + } + + if (diff && chan >= 0 && chan2 >= 0) + printf("channel: %d-%d, ", chan, chan2); + else if (chan >= 0) + printf("channel: %d, ", chan); + + printf("evtype: %s", iio_ev_type_text[ev_type]); + + if (dir != IIO_EV_DIR_NONE) + printf(", direction: %s", iio_ev_dir_text[dir]); + printf("\n"); +} + +int main(int argc, char **argv) +{ + struct iio_event_data event; + const char *device_name; + char *chrdev_name; + int ret; + int dev_num; + int fd, event_fd; + + if (argc <= 1) { + printf("Usage: %s <device_name>\n", argv[0]); + return -1; + } + + device_name = argv[1]; + + dev_num = find_type_by_name(device_name, "iio:device"); + if (dev_num >= 0) { + printf("Found IIO device with name %s with device number %d\n", + device_name, dev_num); + ret = asprintf(&chrdev_name, "/dev/iio:device%d", dev_num); + if (ret < 0) { + ret = -ENOMEM; + goto error_ret; + } + } else { + /* If we can't find a IIO device by name assume device_name is a + IIO chrdev */ + chrdev_name = strdup(device_name); + } + + fd = open(chrdev_name, 0); + if (fd == -1) { + fprintf(stdout, "Failed to open %s\n", chrdev_name); + ret = -errno; + goto error_free_chrdev_name; + } + + ret = ioctl(fd, IIO_GET_EVENT_FD_IOCTL, &event_fd); + + close(fd); + + if (ret == -1 || event_fd == -1) { + fprintf(stdout, "Failed to retrieve event fd\n"); + ret = -errno; + goto error_free_chrdev_name; + } + + while (true) { + ret = read(event_fd, &event, sizeof(event)); + if (ret == -1) { + if (errno == EAGAIN) { + printf("nothing available\n"); + continue; + } else { + perror("Failed to read event from device"); + ret = -errno; + break; + } + } + + print_event(&event); + } + + close(event_fd); +error_free_chrdev_name: + free(chrdev_name); +error_ret: + return ret; +} diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c new file mode 100644 index 000000000000..6f6452167b67 --- /dev/null +++ b/tools/iio/iio_utils.c @@ -0,0 +1,669 @@ +/* IIO - useful set of util functionality + * + * Copyright (c) 2008 Jonathan Cameron + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ +#ifndef _IIO_UTILS_H +#define _IIO_UTILS_H + +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include <stdint.h> +#include <dirent.h> +#include <errno.h> +#include <ctype.h> +#include "iio_utils.h" + +const char *iio_dir = "/sys/bus/iio/devices/"; + +static char * const iio_direction[] = { + "in", + "out", +}; + +/** + * iioutils_break_up_name() - extract generic name from full channel name + * @full_name: the full channel name + * @generic_name: the output generic channel name + **/ +int iioutils_break_up_name(const char *full_name, + char **generic_name) +{ + char *current; + char *w, *r; + char *working, *prefix = ""; + int i; + + for (i = 0; i < sizeof(iio_direction) / sizeof(iio_direction[0]); i++) + if (!strncmp(full_name, iio_direction[i], + strlen(iio_direction[i]))) { + prefix = iio_direction[i]; + break; + } + + current = strdup(full_name + strlen(prefix) + 1); + working = strtok(current, "_\0"); + + w = working; + r = working; + + while (*r != '\0') { + if (!isdigit(*r)) { + *w = *r; + w++; + } + r++; + } + *w = '\0'; + asprintf(generic_name, "%s_%s", prefix, working); + free(current); + + return 0; +} + +/** + * iioutils_get_type() - find and process _type attribute data + * @is_signed: output whether channel is signed + * @bytes: output how many bytes the channel storage occupies + * @mask: output a bit mask for the raw data + * @be: big endian + * @device_dir: the iio device directory + * @name: the channel name + * @generic_name: the channel type name + **/ +int iioutils_get_type(unsigned *is_signed, + unsigned *bytes, + unsigned *bits_used, + unsigned *shift, + uint64_t *mask, + unsigned *be, + const char *device_dir, + const char *name, + const char *generic_name) +{ + FILE *sysfsfp; + int ret; + DIR *dp; + char *scan_el_dir, *builtname, *builtname_generic, *filename = 0; + char signchar, endianchar; + unsigned padint; + const struct dirent *ent; + + ret = asprintf(&scan_el_dir, FORMAT_SCAN_ELEMENTS_DIR, device_dir); + if (ret < 0) { + ret = -ENOMEM; + goto error_ret; + } + ret = asprintf(&builtname, FORMAT_TYPE_FILE, name); + if (ret < 0) { + ret = -ENOMEM; + goto error_free_scan_el_dir; + } + ret = asprintf(&builtname_generic, FORMAT_TYPE_FILE, generic_name); + if (ret < 0) { + ret = -ENOMEM; + goto error_free_builtname; + } + + dp = opendir(scan_el_dir); + if (dp == NULL) { + ret = -errno; + goto error_free_builtname_generic; + } + while (ent = readdir(dp), ent != NULL) + /* + * Do we allow devices to override a generic name with + * a specific one? + */ + if ((strcmp(builtname, ent->d_name) == 0) || + (strcmp(builtname_generic, ent->d_name) == 0)) { + ret = asprintf(&filename, + "%s/%s", scan_el_dir, ent->d_name); + if (ret < 0) { + ret = -ENOMEM; + goto error_closedir; + } + sysfsfp = fopen(filename, "r"); + if (sysfsfp == NULL) { + printf("failed to open %s\n", filename); + ret = -errno; + goto error_free_filename; + } + + ret = fscanf(sysfsfp, + "%ce:%c%u/%u>>%u", + &endianchar, + &signchar, + bits_used, + &padint, shift); + if (ret < 0) { + printf("failed to pass scan type description\n"); + ret = -errno; + goto error_close_sysfsfp; + } + *be = (endianchar == 'b'); + *bytes = padint / 8; + if (*bits_used == 64) + *mask = ~0; + else + *mask = (1 << *bits_used) - 1; + if (signchar == 's') + *is_signed = 1; + else + *is_signed = 0; + fclose(sysfsfp); + free(filename); + + filename = 0; + sysfsfp = 0; + } +error_close_sysfsfp: + if (sysfsfp) + fclose(sysfsfp); +error_free_filename: + if (filename) + free(filename); +error_closedir: + closedir(dp); +error_free_builtname_generic: + free(builtname_generic); +error_free_builtname: + free(builtname); +error_free_scan_el_dir: + free(scan_el_dir); +error_ret: + return ret; +} + +int iioutils_get_param_float(float *output, + const char *param_name, + const char *device_dir, + const char *name, + const char *generic_name) +{ + FILE *sysfsfp; + int ret; + DIR *dp; + char *builtname, *builtname_generic; + char *filename = NULL; + const struct dirent *ent; + + ret = asprintf(&builtname, "%s_%s", name, param_name); + if (ret < 0) { + ret = -ENOMEM; + goto error_ret; + } + ret = asprintf(&builtname_generic, + "%s_%s", generic_name, param_name); + if (ret < 0) { + ret = -ENOMEM; + goto error_free_builtname; + } + dp = opendir(device_dir); + if (dp == NULL) { + ret = -errno; + goto error_free_builtname_generic; + } + while (ent = readdir(dp), ent != NULL) + if ((strcmp(builtname, ent->d_name) == 0) || + (strcmp(builtname_generic, ent->d_name) == 0)) { + ret = asprintf(&filename, + "%s/%s", device_dir, ent->d_name); + if (ret < 0) { + ret = -ENOMEM; + goto error_closedir; + } + sysfsfp = fopen(filename, "r"); + if (!sysfsfp) { + ret = -errno; + goto error_free_filename; + } + fscanf(sysfsfp, "%f", output); + break; + } +error_free_filename: + if (filename) + free(filename); +error_closedir: + closedir(dp); +error_free_builtname_generic: + free(builtname_generic); +error_free_builtname: + free(builtname); +error_ret: + return ret; +} + +/** + * bsort_channel_array_by_index() - reorder so that the array is in index order + * + **/ + +void bsort_channel_array_by_index(struct iio_channel_info **ci_array, + int cnt) +{ + + struct iio_channel_info temp; + int x, y; + + for (x = 0; x < cnt; x++) + for (y = 0; y < (cnt - 1); y++) + if ((*ci_array)[y].index > (*ci_array)[y+1].index) { + temp = (*ci_array)[y + 1]; + (*ci_array)[y + 1] = (*ci_array)[y]; + (*ci_array)[y] = temp; + } +} + +/** + * build_channel_array() - function to figure out what channels are present + * @device_dir: the IIO device directory in sysfs + * @ + **/ +int build_channel_array(const char *device_dir, + struct iio_channel_info **ci_array, + int *counter) +{ + DIR *dp; + FILE *sysfsfp; + int count, i; + struct iio_channel_info *current; + int ret; + const struct dirent *ent; + char *scan_el_dir; + char *filename; + + *counter = 0; + ret = asprintf(&scan_el_dir, FORMAT_SCAN_ELEMENTS_DIR, device_dir); + if (ret < 0) { + ret = -ENOMEM; + goto error_ret; + } + dp = opendir(scan_el_dir); + if (dp == NULL) { + ret = -errno; + goto error_free_name; + } + while (ent = readdir(dp), ent != NULL) + if (strcmp(ent->d_name + strlen(ent->d_name) - strlen("_en"), + "_en") == 0) { + ret = asprintf(&filename, + "%s/%s", scan_el_dir, ent->d_name); + if (ret < 0) { + ret = -ENOMEM; + goto error_close_dir; + } + sysfsfp = fopen(filename, "r"); + if (sysfsfp == NULL) { + ret = -errno; + free(filename); + goto error_close_dir; + } + fscanf(sysfsfp, "%i", &ret); + if (ret == 1) + (*counter)++; + fclose(sysfsfp); + free(filename); + } + *ci_array = malloc(sizeof(**ci_array) * (*counter)); + if (*ci_array == NULL) { + ret = -ENOMEM; + goto error_close_dir; + } + seekdir(dp, 0); + count = 0; + while (ent = readdir(dp), ent != NULL) { + if (strcmp(ent->d_name + strlen(ent->d_name) - strlen("_en"), + "_en") == 0) { + int current_enabled = 0; + + current = &(*ci_array)[count++]; + ret = asprintf(&filename, + "%s/%s", scan_el_dir, ent->d_name); + if (ret < 0) { + ret = -ENOMEM; + /* decrement count to avoid freeing name */ + count--; + goto error_cleanup_array; + } + sysfsfp = fopen(filename, "r"); + if (sysfsfp == NULL) { + free(filename); + ret = -errno; + goto error_cleanup_array; + } + fscanf(sysfsfp, "%i", ¤t_enabled); + fclose(sysfsfp); + + if (!current_enabled) { + free(filename); + count--; + continue; + } + + current->scale = 1.0; + current->offset = 0; + current->name = strndup(ent->d_name, + strlen(ent->d_name) - + strlen("_en")); + if (current->name == NULL) { + free(filename); + ret = -ENOMEM; + goto error_cleanup_array; + } + /* Get the generic and specific name elements */ + ret = iioutils_break_up_name(current->name, + ¤t->generic_name); + if (ret) { + free(filename); + goto error_cleanup_array; + } + ret = asprintf(&filename, + "%s/%s_index", + scan_el_dir, + current->name); + if (ret < 0) { + free(filename); + ret = -ENOMEM; + goto error_cleanup_array; + } + sysfsfp = fopen(filename, "r"); + fscanf(sysfsfp, "%u", ¤t->index); + fclose(sysfsfp); + free(filename); + /* Find the scale */ + ret = iioutils_get_param_float(¤t->scale, + "scale", + device_dir, + current->name, + current->generic_name); + if (ret < 0) + goto error_cleanup_array; + ret = iioutils_get_param_float(¤t->offset, + "offset", + device_dir, + current->name, + current->generic_name); + if (ret < 0) + goto error_cleanup_array; + ret = iioutils_get_type(¤t->is_signed, + ¤t->bytes, + ¤t->bits_used, + ¤t->shift, + ¤t->mask, + ¤t->be, + device_dir, + current->name, + current->generic_name); + } + } + + closedir(dp); + /* reorder so that the array is in index order */ + bsort_channel_array_by_index(ci_array, *counter); + + return 0; + +error_cleanup_array: + for (i = count - 1; i >= 0; i--) + free((*ci_array)[i].name); + free(*ci_array); +error_close_dir: + closedir(dp); +error_free_name: + free(scan_el_dir); +error_ret: + return ret; +} + +/** + * find_type_by_name() - function to match top level types by name + * @name: top level type instance name + * @type: the type of top level instance being sort + * + * Typical types this is used for are device and trigger. + **/ +int find_type_by_name(const char *name, const char *type) +{ + const struct dirent *ent; + int number, numstrlen; + + FILE *nameFile; + DIR *dp; + char thisname[IIO_MAX_NAME_LENGTH]; + char *filename; + + dp = opendir(iio_dir); + if (dp == NULL) { + printf("No industrialio devices available\n"); + return -ENODEV; + } + + while (ent = readdir(dp), ent != NULL) { + if (strcmp(ent->d_name, ".") != 0 && + strcmp(ent->d_name, "..") != 0 && + strlen(ent->d_name) > strlen(type) && + strncmp(ent->d_name, type, strlen(type)) == 0) { + numstrlen = sscanf(ent->d_name + strlen(type), + "%d", + &number); + /* verify the next character is not a colon */ + if (strncmp(ent->d_name + strlen(type) + numstrlen, + ":", + 1) != 0) { + filename = malloc(strlen(iio_dir) + + strlen(type) + + numstrlen + + 6); + if (filename == NULL) { + closedir(dp); + return -ENOMEM; + } + sprintf(filename, "%s%s%d/name", + iio_dir, + type, + number); + nameFile = fopen(filename, "r"); + if (!nameFile) { + free(filename); + continue; + } + free(filename); + fscanf(nameFile, "%s", thisname); + fclose(nameFile); + if (strcmp(name, thisname) == 0) { + closedir(dp); + return number; + } + } + } + } + closedir(dp); + return -ENODEV; +} + +int _write_sysfs_int(char *filename, char *basedir, int val, int verify) +{ + int ret = 0; + FILE *sysfsfp; + int test; + char *temp = malloc(strlen(basedir) + strlen(filename) + 2); + + if (temp == NULL) + return -ENOMEM; + sprintf(temp, "%s/%s", basedir, filename); + sysfsfp = fopen(temp, "w"); + if (sysfsfp == NULL) { + printf("failed to open %s\n", temp); + ret = -errno; + goto error_free; + } + fprintf(sysfsfp, "%d", val); + fclose(sysfsfp); + if (verify) { + sysfsfp = fopen(temp, "r"); + if (sysfsfp == NULL) { + printf("failed to open %s\n", temp); + ret = -errno; + goto error_free; + } + fscanf(sysfsfp, "%d", &test); + fclose(sysfsfp); + if (test != val) { + printf("Possible failure in int write %d to %s%s\n", + val, + basedir, + filename); + ret = -1; + } + } +error_free: + free(temp); + return ret; +} + +int write_sysfs_int(char *filename, char *basedir, int val) +{ + return _write_sysfs_int(filename, basedir, val, 0); +} + +int write_sysfs_int_and_verify(char *filename, char *basedir, int val) +{ + return _write_sysfs_int(filename, basedir, val, 1); +} + +int _write_sysfs_string(char *filename, char *basedir, char *val, int verify) +{ + int ret = 0; + FILE *sysfsfp; + char *temp = malloc(strlen(basedir) + strlen(filename) + 2); + + if (temp == NULL) { + printf("Memory allocation failed\n"); + return -ENOMEM; + } + sprintf(temp, "%s/%s", basedir, filename); + sysfsfp = fopen(temp, "w"); + if (sysfsfp == NULL) { + printf("Could not open %s\n", temp); + ret = -errno; + goto error_free; + } + fprintf(sysfsfp, "%s", val); + fclose(sysfsfp); + if (verify) { + sysfsfp = fopen(temp, "r"); + if (sysfsfp == NULL) { + printf("could not open file to verify\n"); + ret = -errno; + goto error_free; + } + fscanf(sysfsfp, "%s", temp); + fclose(sysfsfp); + if (strcmp(temp, val) != 0) { + printf("Possible failure in string write of %s " + "Should be %s " + "written to %s\%s\n", + temp, + val, + basedir, + filename); + ret = -1; + } + } +error_free: + free(temp); + + return ret; +} + +/** + * write_sysfs_string_and_verify() - string write, readback and verify + * @filename: name of file to write to + * @basedir: the sysfs directory in which the file is to be found + * @val: the string to write + **/ +int write_sysfs_string_and_verify(char *filename, char *basedir, char *val) +{ + return _write_sysfs_string(filename, basedir, val, 1); +} + +int write_sysfs_string(char *filename, char *basedir, char *val) +{ + return _write_sysfs_string(filename, basedir, val, 0); +} + +int read_sysfs_posint(char *filename, char *basedir) +{ + int ret; + FILE *sysfsfp; + char *temp = malloc(strlen(basedir) + strlen(filename) + 2); + + if (temp == NULL) { + printf("Memory allocation failed"); + return -ENOMEM; + } + sprintf(temp, "%s/%s", basedir, filename); + sysfsfp = fopen(temp, "r"); + if (sysfsfp == NULL) { + ret = -errno; + goto error_free; + } + fscanf(sysfsfp, "%d\n", &ret); + fclose(sysfsfp); +error_free: + free(temp); + return ret; +} + +int read_sysfs_float(char *filename, char *basedir, float *val) +{ + int ret = 0; + FILE *sysfsfp; + char *temp = malloc(strlen(basedir) + strlen(filename) + 2); + + if (temp == NULL) { + printf("Memory allocation failed"); + return -ENOMEM; + } + sprintf(temp, "%s/%s", basedir, filename); + sysfsfp = fopen(temp, "r"); + if (sysfsfp == NULL) { + ret = -errno; + goto error_free; + } + fscanf(sysfsfp, "%f\n", val); + fclose(sysfsfp); +error_free: + free(temp); + return ret; +} + +int read_sysfs_string(const char *filename, const char *basedir, char *str) +{ + int ret = 0; + FILE *sysfsfp; + char *temp = malloc(strlen(basedir) + strlen(filename) + 2); + + if (temp == NULL) { + printf("Memory allocation failed"); + return -ENOMEM; + } + sprintf(temp, "%s/%s", basedir, filename); + sysfsfp = fopen(temp, "r"); + if (sysfsfp == NULL) { + ret = -errno; + goto error_free; + } + fscanf(sysfsfp, "%s\n", str); + fclose(sysfsfp); +error_free: + free(temp); + return ret; +} + +#endif /* _IIO_UTILS_H */ diff --git a/tools/iio/iio_utils.h b/tools/iio/iio_utils.h new file mode 100644 index 000000000000..1bc837b2d769 --- /dev/null +++ b/tools/iio/iio_utils.h @@ -0,0 +1,71 @@ +#ifndef _IIO_UTILS_H_ +#define _IIO_UTILS_H_ + +/* IIO - useful set of util functionality + * + * Copyright (c) 2008 Jonathan Cameron + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <stdint.h> + +/* Made up value to limit allocation sizes */ +#define IIO_MAX_NAME_LENGTH 30 + +#define FORMAT_SCAN_ELEMENTS_DIR "%s/scan_elements" +#define FORMAT_TYPE_FILE "%s_type" + +extern const char *iio_dir; + +/** + * struct iio_channel_info - information about a given channel + * @name: channel name + * @generic_name: general name for channel type + * @scale: scale factor to be applied for conversion to si units + * @offset: offset to be applied for conversion to si units + * @index: the channel index in the buffer output + * @bytes: number of bytes occupied in buffer output + * @mask: a bit mask for the raw output + * @is_signed: is the raw value stored signed + * @enabled: is this channel enabled + **/ +struct iio_channel_info { + char *name; + char *generic_name; + float scale; + float offset; + unsigned index; + unsigned bytes; + unsigned bits_used; + unsigned shift; + uint64_t mask; + unsigned be; + unsigned is_signed; + unsigned location; +}; + +int iioutils_break_up_name(const char *full_name, char **generic_name); +int iioutils_get_type(unsigned *is_signed, unsigned *bytes, + unsigned *bits_used, unsigned *shift, + uint64_t *mask, unsigned *be, + const char *device_dir, const char *name, + const char *generic_name); +int iioutils_get_param_float(float *output, const char *param_name, + const char *device_dir, const char *name, + const char *generic_name); +void bsort_channel_array_by_index(struct iio_channel_info **ci_array, int cnt); +int build_channel_array(const char *device_dir, + struct iio_channel_info **ci_array, int *counter); +int find_type_by_name(const char *name, const char *type); +int write_sysfs_int(char *filename, char *basedir, int val); +int write_sysfs_int_and_verify(char *filename, char *basedir, int val); +int write_sysfs_string_and_verify(char *filename, char *basedir, char *val); +int write_sysfs_string(char *filename, char *basedir, char *val); +int read_sysfs_posint(char *filename, char *basedir); +int read_sysfs_float(char *filename, char *basedir, float *val); +int read_sysfs_string(const char *filename, const char *basedir, char *str); + +#endif /* _IIO_UTILS_H_ */ diff --git a/tools/iio/lsiio.c b/tools/iio/lsiio.c new file mode 100644 index 000000000000..c585440f864e --- /dev/null +++ b/tools/iio/lsiio.c @@ -0,0 +1,158 @@ +/* + * Industrial I/O utilities - lsiio.c + * + * Copyright (c) 2010 Manuel Stahl <manuel.stahl@iis.fraunhofer.de> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <string.h> +#include <dirent.h> +#include <stdio.h> +#include <errno.h> +#include <stdint.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/dir.h> +#include "iio_utils.h" + + +static enum verbosity { + VERBLEVEL_DEFAULT, /* 0 gives lspci behaviour */ + VERBLEVEL_SENSORS, /* 1 lists sensors */ +} verblevel = VERBLEVEL_DEFAULT; + +const char *type_device = "iio:device"; +const char *type_trigger = "trigger"; + + +static inline int check_prefix(const char *str, const char *prefix) +{ + return strlen(str) > strlen(prefix) && + strncmp(str, prefix, strlen(prefix)) == 0; +} + +static inline int check_postfix(const char *str, const char *postfix) +{ + return strlen(str) > strlen(postfix) && + strcmp(str + strlen(str) - strlen(postfix), postfix) == 0; +} + +static int dump_channels(const char *dev_dir_name) +{ + DIR *dp; + const struct dirent *ent; + + dp = opendir(dev_dir_name); + if (dp == NULL) + return -errno; + while (ent = readdir(dp), ent != NULL) + if (check_prefix(ent->d_name, "in_") && + check_postfix(ent->d_name, "_raw")) { + printf(" %-10s\n", ent->d_name); + } + + return 0; +} + +static int dump_one_device(const char *dev_dir_name) +{ + char name[IIO_MAX_NAME_LENGTH]; + int dev_idx; + int retval; + + retval = sscanf(dev_dir_name + strlen(iio_dir) + strlen(type_device), + "%i", &dev_idx); + if (retval != 1) + return -EINVAL; + read_sysfs_string("name", dev_dir_name, name); + printf("Device %03d: %s\n", dev_idx, name); + + if (verblevel >= VERBLEVEL_SENSORS) + return dump_channels(dev_dir_name); + return 0; +} + +static int dump_one_trigger(const char *dev_dir_name) +{ + char name[IIO_MAX_NAME_LENGTH]; + int dev_idx; + int retval; + + retval = sscanf(dev_dir_name + strlen(iio_dir) + strlen(type_trigger), + "%i", &dev_idx); + if (retval != 1) + return -EINVAL; + read_sysfs_string("name", dev_dir_name, name); + printf("Trigger %03d: %s\n", dev_idx, name); + return 0; +} + +static void dump_devices(void) +{ + const struct dirent *ent; + DIR *dp; + + dp = opendir(iio_dir); + if (dp == NULL) { + printf("No industrial I/O devices available\n"); + return; + } + + while (ent = readdir(dp), ent != NULL) { + if (check_prefix(ent->d_name, type_device)) { + char *dev_dir_name; + + asprintf(&dev_dir_name, "%s%s", iio_dir, ent->d_name); + dump_one_device(dev_dir_name); + free(dev_dir_name); + if (verblevel >= VERBLEVEL_SENSORS) + printf("\n"); + } + } + rewinddir(dp); + while (ent = readdir(dp), ent != NULL) { + if (check_prefix(ent->d_name, type_trigger)) { + char *dev_dir_name; + + asprintf(&dev_dir_name, "%s%s", iio_dir, ent->d_name); + dump_one_trigger(dev_dir_name); + free(dev_dir_name); + } + } + closedir(dp); +} + +int main(int argc, char **argv) +{ + int c, err = 0; + + while ((c = getopt(argc, argv, "d:D:v")) != EOF) { + switch (c) { + case 'v': + verblevel++; + break; + + case '?': + default: + err++; + break; + } + } + if (err || argc > optind) { + fprintf(stderr, "Usage: lsiio [options]...\n" + "List industrial I/O devices\n" + " -v, --verbose\n" + " Increase verbosity (may be given multiple times)\n" + ); + exit(1); + } + + dump_devices(); + + return 0; +} diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h new file mode 100644 index 000000000000..653d1bad77de --- /dev/null +++ b/tools/include/asm-generic/bitops.h @@ -0,0 +1,29 @@ +#ifndef __TOOLS_ASM_GENERIC_BITOPS_H +#define __TOOLS_ASM_GENERIC_BITOPS_H + +/* + * tools/ copied this from include/asm-generic/bitops.h, bit by bit as it needed + * some functions. + * + * For the benefit of those who are trying to port Linux to another + * architecture, here are some C-language equivalents. You should + * recode these in the native assembly language, if at all possible. + * + * C language equivalents written by Theodore Ts'o, 9/26/92 + */ + +#include <asm-generic/bitops/__ffs.h> +#include <asm-generic/bitops/fls.h> +#include <asm-generic/bitops/__fls.h> +#include <asm-generic/bitops/fls64.h> +#include <asm-generic/bitops/find.h> + +#ifndef _TOOLS_LINUX_BITOPS_H_ +#error only <linux/bitops.h> can be included directly +#endif + +#include <asm-generic/bitops/hweight.h> + +#include <asm-generic/bitops/atomic.h> + +#endif /* __TOOLS_ASM_GENERIC_BITOPS_H */ diff --git a/tools/include/asm-generic/bitops/__ffs.h b/tools/include/asm-generic/bitops/__ffs.h new file mode 100644 index 000000000000..c94175015a82 --- /dev/null +++ b/tools/include/asm-generic/bitops/__ffs.h @@ -0,0 +1,43 @@ +#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_ +#define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_ + +#include <asm/types.h> + +/** + * __ffs - find first bit in word. + * @word: The word to search + * + * Undefined if no bit exists, so code should check against 0 first. + */ +static __always_inline unsigned long __ffs(unsigned long word) +{ + int num = 0; + +#if __BITS_PER_LONG == 64 + if ((word & 0xffffffff) == 0) { + num += 32; + word >>= 32; + } +#endif + if ((word & 0xffff) == 0) { + num += 16; + word >>= 16; + } + if ((word & 0xff) == 0) { + num += 8; + word >>= 8; + } + if ((word & 0xf) == 0) { + num += 4; + word >>= 4; + } + if ((word & 0x3) == 0) { + num += 2; + word >>= 2; + } + if ((word & 0x1) == 0) + num += 1; + return num; +} + +#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_ */ diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h new file mode 100644 index 000000000000..2218b9add4c1 --- /dev/null +++ b/tools/include/asm-generic/bitops/__fls.h @@ -0,0 +1 @@ +#include <../../../../include/asm-generic/bitops/__fls.h> diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h new file mode 100644 index 000000000000..318bb2b202b0 --- /dev/null +++ b/tools/include/asm-generic/bitops/arch_hweight.h @@ -0,0 +1 @@ +#include "../../../../include/asm-generic/bitops/arch_hweight.h" diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h new file mode 100644 index 000000000000..4bccd7c3d5d6 --- /dev/null +++ b/tools/include/asm-generic/bitops/atomic.h @@ -0,0 +1,22 @@ +#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ +#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ + +#include <asm/types.h> + +static inline void set_bit(int nr, unsigned long *addr) +{ + addr[nr / __BITS_PER_LONG] |= 1UL << (nr % __BITS_PER_LONG); +} + +static inline void clear_bit(int nr, unsigned long *addr) +{ + addr[nr / __BITS_PER_LONG] &= ~(1UL << (nr % __BITS_PER_LONG)); +} + +static __always_inline int test_bit(unsigned int nr, const unsigned long *addr) +{ + return ((1UL << (nr % __BITS_PER_LONG)) & + (((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0; +} + +#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */ diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h new file mode 100644 index 000000000000..0afd644aff83 --- /dev/null +++ b/tools/include/asm-generic/bitops/const_hweight.h @@ -0,0 +1 @@ +#include "../../../../include/asm-generic/bitops/const_hweight.h" diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h new file mode 100644 index 000000000000..31f51547fcd4 --- /dev/null +++ b/tools/include/asm-generic/bitops/find.h @@ -0,0 +1,33 @@ +#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ +#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ + +#ifndef find_next_bit +/** + * find_next_bit - find the next set bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +extern unsigned long find_next_bit(const unsigned long *addr, unsigned long + size, unsigned long offset); +#endif + +#ifndef find_first_bit + +/** + * find_first_bit - find the first set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * + * Returns the bit number of the first set bit. + * If no bits are set, returns @size. + */ +extern unsigned long find_first_bit(const unsigned long *addr, + unsigned long size); + +#endif /* find_first_bit */ + +#endif /*_TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ */ diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h new file mode 100644 index 000000000000..dbf711a28f71 --- /dev/null +++ b/tools/include/asm-generic/bitops/fls.h @@ -0,0 +1 @@ +#include <../../../../include/asm-generic/bitops/fls.h> diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h new file mode 100644 index 000000000000..980b1f63c047 --- /dev/null +++ b/tools/include/asm-generic/bitops/fls64.h @@ -0,0 +1 @@ +#include <../../../../include/asm-generic/bitops/fls64.h> diff --git a/tools/include/asm-generic/bitops/hweight.h b/tools/include/asm-generic/bitops/hweight.h new file mode 100644 index 000000000000..290120c01a8e --- /dev/null +++ b/tools/include/asm-generic/bitops/hweight.h @@ -0,0 +1,7 @@ +#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ +#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ + +#include <asm-generic/bitops/arch_hweight.h> +#include <asm-generic/bitops/const_hweight.h> + +#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h new file mode 100644 index 000000000000..5ad9ee1dd7f6 --- /dev/null +++ b/tools/include/linux/bitops.h @@ -0,0 +1,58 @@ +#ifndef _TOOLS_LINUX_BITOPS_H_ +#define _TOOLS_LINUX_BITOPS_H_ + +#include <asm/types.h> +#include <linux/kernel.h> +#include <linux/compiler.h> + +#ifndef __WORDSIZE +#define __WORDSIZE (__SIZEOF_LONG__ * 8) +#endif + +#define BITS_PER_LONG __WORDSIZE + +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BITS_PER_BYTE 8 +#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) +#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64)) +#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) +#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE) + +extern unsigned int __sw_hweight8(unsigned int w); +extern unsigned int __sw_hweight16(unsigned int w); +extern unsigned int __sw_hweight32(unsigned int w); +extern unsigned long __sw_hweight64(__u64 w); + +/* + * Include this here because some architectures need generic_ffs/fls in + * scope + * + * XXX: this needs to be asm/bitops.h, when we get to per arch optimizations + */ +#include <asm-generic/bitops.h> + +#define for_each_set_bit(bit, addr, size) \ + for ((bit) = find_first_bit((addr), (size)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + +/* same as for_each_set_bit() but use bit as value to start with */ +#define for_each_set_bit_from(bit, addr, size) \ + for ((bit) = find_next_bit((addr), (size), (bit)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + +static inline unsigned long hweight_long(unsigned long w) +{ + return sizeof(w) == 4 ? hweight32(w) : hweight64(w); +} + +static inline unsigned fls_long(unsigned long l) +{ + if (sizeof(l) == 4) + return fls(l); + return fls64(l); +} + +#endif diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h new file mode 100644 index 000000000000..41446668ccce --- /dev/null +++ b/tools/include/linux/log2.h @@ -0,0 +1,185 @@ +/* Integer base 2 logarithm calculation + * + * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _TOOLS_LINUX_LOG2_H +#define _TOOLS_LINUX_LOG2_H + +/* + * deal with unrepresentable constant logarithms + */ +extern __attribute__((const, noreturn)) +int ____ilog2_NaN(void); + +/* + * non-constant log of base 2 calculators + * - the arch may override these in asm/bitops.h if they can be implemented + * more efficiently than using fls() and fls64() + * - the arch is not required to handle n==0 if implementing the fallback + */ +static inline __attribute__((const)) +int __ilog2_u32(u32 n) +{ + return fls(n) - 1; +} + +static inline __attribute__((const)) +int __ilog2_u64(u64 n) +{ + return fls64(n) - 1; +} + +/* + * Determine whether some value is a power of two, where zero is + * *not* considered a power of two. + */ + +static inline __attribute__((const)) +bool is_power_of_2(unsigned long n) +{ + return (n != 0 && ((n & (n - 1)) == 0)); +} + +/* + * round up to nearest power of two + */ +static inline __attribute__((const)) +unsigned long __roundup_pow_of_two(unsigned long n) +{ + return 1UL << fls_long(n - 1); +} + +/* + * round down to nearest power of two + */ +static inline __attribute__((const)) +unsigned long __rounddown_pow_of_two(unsigned long n) +{ + return 1UL << (fls_long(n) - 1); +} + +/** + * ilog2 - log of base 2 of 32-bit or a 64-bit unsigned value + * @n - parameter + * + * constant-capable log of base 2 calculation + * - this can be used to initialise global variables from constant data, hence + * the massive ternary operator construction + * + * selects the appropriately-sized optimised version depending on sizeof(n) + */ +#define ilog2(n) \ +( \ + __builtin_constant_p(n) ? ( \ + (n) < 1 ? ____ilog2_NaN() : \ + (n) & (1ULL << 63) ? 63 : \ + (n) & (1ULL << 62) ? 62 : \ + (n) & (1ULL << 61) ? 61 : \ + (n) & (1ULL << 60) ? 60 : \ + (n) & (1ULL << 59) ? 59 : \ + (n) & (1ULL << 58) ? 58 : \ + (n) & (1ULL << 57) ? 57 : \ + (n) & (1ULL << 56) ? 56 : \ + (n) & (1ULL << 55) ? 55 : \ + (n) & (1ULL << 54) ? 54 : \ + (n) & (1ULL << 53) ? 53 : \ + (n) & (1ULL << 52) ? 52 : \ + (n) & (1ULL << 51) ? 51 : \ + (n) & (1ULL << 50) ? 50 : \ + (n) & (1ULL << 49) ? 49 : \ + (n) & (1ULL << 48) ? 48 : \ + (n) & (1ULL << 47) ? 47 : \ + (n) & (1ULL << 46) ? 46 : \ + (n) & (1ULL << 45) ? 45 : \ + (n) & (1ULL << 44) ? 44 : \ + (n) & (1ULL << 43) ? 43 : \ + (n) & (1ULL << 42) ? 42 : \ + (n) & (1ULL << 41) ? 41 : \ + (n) & (1ULL << 40) ? 40 : \ + (n) & (1ULL << 39) ? 39 : \ + (n) & (1ULL << 38) ? 38 : \ + (n) & (1ULL << 37) ? 37 : \ + (n) & (1ULL << 36) ? 36 : \ + (n) & (1ULL << 35) ? 35 : \ + (n) & (1ULL << 34) ? 34 : \ + (n) & (1ULL << 33) ? 33 : \ + (n) & (1ULL << 32) ? 32 : \ + (n) & (1ULL << 31) ? 31 : \ + (n) & (1ULL << 30) ? 30 : \ + (n) & (1ULL << 29) ? 29 : \ + (n) & (1ULL << 28) ? 28 : \ + (n) & (1ULL << 27) ? 27 : \ + (n) & (1ULL << 26) ? 26 : \ + (n) & (1ULL << 25) ? 25 : \ + (n) & (1ULL << 24) ? 24 : \ + (n) & (1ULL << 23) ? 23 : \ + (n) & (1ULL << 22) ? 22 : \ + (n) & (1ULL << 21) ? 21 : \ + (n) & (1ULL << 20) ? 20 : \ + (n) & (1ULL << 19) ? 19 : \ + (n) & (1ULL << 18) ? 18 : \ + (n) & (1ULL << 17) ? 17 : \ + (n) & (1ULL << 16) ? 16 : \ + (n) & (1ULL << 15) ? 15 : \ + (n) & (1ULL << 14) ? 14 : \ + (n) & (1ULL << 13) ? 13 : \ + (n) & (1ULL << 12) ? 12 : \ + (n) & (1ULL << 11) ? 11 : \ + (n) & (1ULL << 10) ? 10 : \ + (n) & (1ULL << 9) ? 9 : \ + (n) & (1ULL << 8) ? 8 : \ + (n) & (1ULL << 7) ? 7 : \ + (n) & (1ULL << 6) ? 6 : \ + (n) & (1ULL << 5) ? 5 : \ + (n) & (1ULL << 4) ? 4 : \ + (n) & (1ULL << 3) ? 3 : \ + (n) & (1ULL << 2) ? 2 : \ + (n) & (1ULL << 1) ? 1 : \ + (n) & (1ULL << 0) ? 0 : \ + ____ilog2_NaN() \ + ) : \ + (sizeof(n) <= 4) ? \ + __ilog2_u32(n) : \ + __ilog2_u64(n) \ + ) + +/** + * roundup_pow_of_two - round the given value up to nearest power of two + * @n - parameter + * + * round the given value up to the nearest power of two + * - the result is undefined when n == 0 + * - this can be used to initialise global variables from constant data + */ +#define roundup_pow_of_two(n) \ +( \ + __builtin_constant_p(n) ? ( \ + (n == 1) ? 1 : \ + (1UL << (ilog2((n) - 1) + 1)) \ + ) : \ + __roundup_pow_of_two(n) \ + ) + +/** + * rounddown_pow_of_two - round the given value down to nearest power of two + * @n - parameter + * + * round the given value down to the nearest power of two + * - the result is undefined when n == 0 + * - this can be used to initialise global variables from constant data + */ +#define rounddown_pow_of_two(n) \ +( \ + __builtin_constant_p(n) ? ( \ + (1UL << ilog2(n))) : \ + __rounddown_pow_of_two(n) \ + ) + +#endif /* _TOOLS_LINUX_LOG2_H */ diff --git a/tools/lguest/Makefile b/tools/lguest/Makefile index 97bca4871ea3..a107b5e4da13 100644 --- a/tools/lguest/Makefile +++ b/tools/lguest/Makefile @@ -1,7 +1,13 @@ # This creates the demonstration utility "lguest" which runs a Linux guest. -CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE +CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE -Iinclude all: lguest +include/linux/virtio_types.h: ../../include/uapi/linux/virtio_types.h + mkdir -p include/linux 2>&1 || true + ln -sf ../../../../include/uapi/linux/virtio_types.h $@ + +lguest: include/linux/virtio_types.h + clean: rm -f lguest diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c index 32cf2ce15d69..e44052483ed9 100644 --- a/tools/lguest/lguest.c +++ b/tools/lguest/lguest.c @@ -41,6 +41,8 @@ #include <signal.h> #include <pwd.h> #include <grp.h> +#include <sys/user.h> +#include <linux/pci_regs.h> #ifndef VIRTIO_F_ANY_LAYOUT #define VIRTIO_F_ANY_LAYOUT 27 @@ -61,12 +63,19 @@ typedef uint16_t u16; typedef uint8_t u8; /*:*/ -#include <linux/virtio_config.h> -#include <linux/virtio_net.h> -#include <linux/virtio_blk.h> -#include <linux/virtio_console.h> -#include <linux/virtio_rng.h> +#define VIRTIO_CONFIG_NO_LEGACY +#define VIRTIO_PCI_NO_LEGACY +#define VIRTIO_BLK_NO_LEGACY +#define VIRTIO_NET_NO_LEGACY + +/* Use in-kernel ones, which defines VIRTIO_F_VERSION_1 */ +#include "../../include/uapi/linux/virtio_config.h" +#include "../../include/uapi/linux/virtio_net.h" +#include "../../include/uapi/linux/virtio_blk.h" +#include "../../include/uapi/linux/virtio_console.h" +#include "../../include/uapi/linux/virtio_rng.h" #include <linux/virtio_ring.h> +#include "../../include/uapi/linux/virtio_pci.h" #include <asm/bootparam.h> #include "../../include/linux/lguest_launcher.h" @@ -91,13 +100,16 @@ static bool verbose; /* The pointer to the start of guest memory. */ static void *guest_base; /* The maximum guest physical address allowed, and maximum possible. */ -static unsigned long guest_limit, guest_max; +static unsigned long guest_limit, guest_max, guest_mmio; /* The /dev/lguest file descriptor. */ static int lguest_fd; /* a per-cpu variable indicating whose vcpu is currently running */ static unsigned int __thread cpu_id; +/* 5 bit device number in the PCI_CONFIG_ADDR => 32 only */ +#define MAX_PCI_DEVICES 32 + /* This is our list of devices. */ struct device_list { /* Counter to assign interrupt numbers. */ @@ -106,30 +118,50 @@ struct device_list { /* Counter to print out convenient device numbers. */ unsigned int device_num; - /* The descriptor page for the devices. */ - u8 *descpage; - - /* A single linked list of devices. */ - struct device *dev; - /* And a pointer to the last device for easy append. */ - struct device *lastdev; + /* PCI devices. */ + struct device *pci[MAX_PCI_DEVICES]; }; /* The list of Guest devices, based on command line arguments. */ static struct device_list devices; -/* The device structure describes a single device. */ -struct device { - /* The linked-list pointer. */ - struct device *next; +struct virtio_pci_cfg_cap { + struct virtio_pci_cap cap; + u32 pci_cfg_data; /* Data for BAR access. */ +}; - /* The device's descriptor, as mapped into the Guest. */ - struct lguest_device_desc *desc; +struct virtio_pci_mmio { + struct virtio_pci_common_cfg cfg; + u16 notify; + u8 isr; + u8 padding; + /* Device-specific configuration follows this. */ +}; - /* We can't trust desc values once Guest has booted: we use these. */ - unsigned int feature_len; - unsigned int num_vq; +/* This is the layout (little-endian) of the PCI config space. */ +struct pci_config { + u16 vendor_id, device_id; + u16 command, status; + u8 revid, prog_if, subclass, class; + u8 cacheline_size, lat_timer, header_type, bist; + u32 bar[6]; + u32 cardbus_cis_ptr; + u16 subsystem_vendor_id, subsystem_device_id; + u32 expansion_rom_addr; + u8 capabilities, reserved1[3]; + u32 reserved2; + u8 irq_line, irq_pin, min_grant, max_latency; + + /* Now, this is the linked capability list. */ + struct virtio_pci_cap common; + struct virtio_pci_notify_cap notify; + struct virtio_pci_cap isr; + struct virtio_pci_cap device; + struct virtio_pci_cfg_cap cfg_access; +}; +/* The device structure describes a single device. */ +struct device { /* The name of this device, for --verbose. */ const char *name; @@ -139,6 +171,25 @@ struct device { /* Is it operational */ bool running; + /* Has it written FEATURES_OK but not re-checked it? */ + bool wrote_features_ok; + + /* PCI configuration */ + union { + struct pci_config config; + u32 config_words[sizeof(struct pci_config) / sizeof(u32)]; + }; + + /* Features we offer, and those accepted. */ + u64 features, features_accepted; + + /* Device-specific config hangs off the end of this. */ + struct virtio_pci_mmio *mmio; + + /* PCI MMIO resources (all in BAR0) */ + size_t mmio_size; + u32 mmio_addr; + /* Device-specific data. */ void *priv; }; @@ -150,12 +201,15 @@ struct virtqueue { /* Which device owns me. */ struct device *dev; - /* The configuration for this queue. */ - struct lguest_vqconfig config; + /* Name for printing errors. */ + const char *name; /* The actual ring of buffers. */ struct vring vring; + /* The information about this virtqueue (we only use queue_size on) */ + struct virtio_pci_common_cfg pci_config; + /* Last available index we saw. */ u16 last_avail_idx; @@ -199,6 +253,16 @@ static struct termios orig_term; #define le32_to_cpu(v32) (v32) #define le64_to_cpu(v64) (v64) +/* + * A real device would ignore weird/non-compliant driver behaviour. We + * stop and flag it, to help debugging Linux problems. + */ +#define bad_driver(d, fmt, ...) \ + errx(1, "%s: bad driver: " fmt, (d)->name, ## __VA_ARGS__) +#define bad_driver_vq(vq, fmt, ...) \ + errx(1, "%s vq %s: bad driver: " fmt, (vq)->dev->name, \ + vq->name, ## __VA_ARGS__) + /* Is this iovec empty? */ static bool iov_empty(const struct iovec iov[], unsigned int num_iov) { @@ -211,7 +275,8 @@ static bool iov_empty(const struct iovec iov[], unsigned int num_iov) } /* Take len bytes from the front of this iovec. */ -static void iov_consume(struct iovec iov[], unsigned num_iov, +static void iov_consume(struct device *d, + struct iovec iov[], unsigned num_iov, void *dest, unsigned len) { unsigned int i; @@ -229,14 +294,7 @@ static void iov_consume(struct iovec iov[], unsigned num_iov, len -= used; } if (len != 0) - errx(1, "iovec too short!"); -} - -/* The device virtqueue descriptors are followed by feature bitmasks. */ -static u8 *get_feature_bits(struct device *dev) -{ - return (u8 *)(dev->desc + 1) - + dev->num_vq * sizeof(struct lguest_vqconfig); + bad_driver(d, "iovec too short!"); } /*L:100 @@ -309,14 +367,20 @@ static void *map_zeroed_pages(unsigned int num) return addr + getpagesize(); } -/* Get some more pages for a device. */ -static void *get_pages(unsigned int num) +/* Get some bytes which won't be mapped into the guest. */ +static unsigned long get_mmio_region(size_t size) { - void *addr = from_guest_phys(guest_limit); + unsigned long addr = guest_mmio; + size_t i; + + if (!size) + return addr; + + /* Size has to be a power of 2 (and multiple of 16) */ + for (i = 1; i < size; i <<= 1); + + guest_mmio += i; - guest_limit += num * getpagesize(); - if (guest_limit > guest_max) - errx(1, "Not enough memory for devices"); return addr; } @@ -547,9 +611,11 @@ static void tell_kernel(unsigned long start) { unsigned long args[] = { LHREQ_INITIALIZE, (unsigned long)guest_base, - guest_limit / getpagesize(), start }; - verbose("Guest: %p - %p (%#lx)\n", - guest_base, guest_base + guest_limit, guest_limit); + guest_limit / getpagesize(), start, + (guest_mmio+getpagesize()-1) / getpagesize() }; + verbose("Guest: %p - %p (%#lx, MMIO %#lx)\n", + guest_base, guest_base + guest_limit, + guest_limit, guest_mmio); lguest_fd = open_or_die("/dev/lguest", O_RDWR); if (write(lguest_fd, args, sizeof(args)) < 0) err(1, "Writing to /dev/lguest"); @@ -564,7 +630,8 @@ static void tell_kernel(unsigned long start) * we have a convenient routine which checks it and exits with an error message * if something funny is going on: */ -static void *_check_pointer(unsigned long addr, unsigned int size, +static void *_check_pointer(struct device *d, + unsigned long addr, unsigned int size, unsigned int line) { /* @@ -572,7 +639,8 @@ static void *_check_pointer(unsigned long addr, unsigned int size, * or addr + size wraps around. */ if ((addr + size) > guest_limit || (addr + size) < addr) - errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr); + bad_driver(d, "%s:%i: Invalid address %#lx", + __FILE__, line, addr); /* * We return a pointer for the caller's convenience, now we know it's * safe to use. @@ -580,14 +648,14 @@ static void *_check_pointer(unsigned long addr, unsigned int size, return from_guest_phys(addr); } /* A macro which transparently hands the line number to the real function. */ -#define check_pointer(addr,size) _check_pointer(addr, size, __LINE__) +#define check_pointer(d,addr,size) _check_pointer(d, addr, size, __LINE__) /* * Each buffer in the virtqueues is actually a chain of descriptors. This * function returns the next descriptor in the chain, or vq->vring.num if we're * at the end. */ -static unsigned next_desc(struct vring_desc *desc, +static unsigned next_desc(struct device *d, struct vring_desc *desc, unsigned int i, unsigned int max) { unsigned int next; @@ -602,7 +670,7 @@ static unsigned next_desc(struct vring_desc *desc, wmb(); if (next >= max) - errx(1, "Desc next is %u", next); + bad_driver(d, "Desc next is %u", next); return next; } @@ -613,21 +681,48 @@ static unsigned next_desc(struct vring_desc *desc, */ static void trigger_irq(struct virtqueue *vq) { - unsigned long buf[] = { LHREQ_IRQ, vq->config.irq }; + unsigned long buf[] = { LHREQ_IRQ, vq->dev->config.irq_line }; /* Don't inform them if nothing used. */ if (!vq->pending_used) return; vq->pending_used = 0; - /* If they don't want an interrupt, don't send one... */ + /* + * 2.4.7.1: + * + * If the VIRTIO_F_EVENT_IDX feature bit is not negotiated: + * The driver MUST set flags to 0 or 1. + */ + if (vq->vring.avail->flags > 1) + bad_driver_vq(vq, "avail->flags = %u\n", vq->vring.avail->flags); + + /* + * 2.4.7.2: + * + * If the VIRTIO_F_EVENT_IDX feature bit is not negotiated: + * + * - The device MUST ignore the used_event value. + * - After the device writes a descriptor index into the used ring: + * - If flags is 1, the device SHOULD NOT send an interrupt. + * - If flags is 0, the device MUST send an interrupt. + */ if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) { return; } + /* + * 4.1.4.5.1: + * + * If MSI-X capability is disabled, the device MUST set the Queue + * Interrupt bit in ISR status before sending a virtqueue notification + * to the driver. + */ + vq->dev->mmio->isr = 0x1; + /* Send the Guest an interrupt tell them we used something up. */ if (write(lguest_fd, buf, sizeof(buf)) != 0) - err(1, "Triggering irq %i", vq->config.irq); + err(1, "Triggering irq %i", vq->dev->config.irq_line); } /* @@ -646,6 +741,14 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, struct vring_desc *desc; u16 last_avail = lg_last_avail(vq); + /* + * 2.4.7.1: + * + * The driver MUST handle spurious interrupts from the device. + * + * That's why this is a while loop. + */ + /* There's nothing available? */ while (last_avail == vq->vring.avail->idx) { u64 event; @@ -679,8 +782,8 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, /* Check it isn't doing very strange things with descriptor numbers. */ if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num) - errx(1, "Guest moved used index from %u to %u", - last_avail, vq->vring.avail->idx); + bad_driver_vq(vq, "Guest moved used index from %u to %u", + last_avail, vq->vring.avail->idx); /* * Make sure we read the descriptor number *after* we read the ring @@ -697,7 +800,7 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, /* If their number is silly, that's a fatal mistake. */ if (head >= vq->vring.num) - errx(1, "Guest says index %u is available", head); + bad_driver_vq(vq, "Guest says index %u is available", head); /* When we start there are none of either input nor output. */ *out_num = *in_num = 0; @@ -712,24 +815,73 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, * that: no rmb() required. */ - /* - * If this is an indirect entry, then this buffer contains a descriptor - * table which we handle as if it's any normal descriptor chain. - */ - if (desc[i].flags & VRING_DESC_F_INDIRECT) { - if (desc[i].len % sizeof(struct vring_desc)) - errx(1, "Invalid size for indirect buffer table"); + do { + /* + * If this is an indirect entry, then this buffer contains a + * descriptor table which we handle as if it's any normal + * descriptor chain. + */ + if (desc[i].flags & VRING_DESC_F_INDIRECT) { + /* 2.4.5.3.1: + * + * The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT + * flag unless the VIRTIO_F_INDIRECT_DESC feature was + * negotiated. + */ + if (!(vq->dev->features_accepted & + (1<<VIRTIO_RING_F_INDIRECT_DESC))) + bad_driver_vq(vq, "vq indirect not negotiated"); - max = desc[i].len / sizeof(struct vring_desc); - desc = check_pointer(desc[i].addr, desc[i].len); - i = 0; - } + /* + * 2.4.5.3.1: + * + * The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT + * flag within an indirect descriptor (ie. only one + * table per descriptor). + */ + if (desc != vq->vring.desc) + bad_driver_vq(vq, "Indirect within indirect"); + + /* + * Proposed update VIRTIO-134 spells this out: + * + * A driver MUST NOT set both VIRTQ_DESC_F_INDIRECT + * and VIRTQ_DESC_F_NEXT in flags. + */ + if (desc[i].flags & VRING_DESC_F_NEXT) + bad_driver_vq(vq, "indirect and next together"); + + if (desc[i].len % sizeof(struct vring_desc)) + bad_driver_vq(vq, + "Invalid size for indirect table"); + /* + * 2.4.5.3.2: + * + * The device MUST ignore the write-only flag + * (flags&VIRTQ_DESC_F_WRITE) in the descriptor that + * refers to an indirect table. + * + * We ignore it here: :) + */ + + max = desc[i].len / sizeof(struct vring_desc); + desc = check_pointer(vq->dev, desc[i].addr, desc[i].len); + i = 0; + + /* 2.4.5.3.1: + * + * A driver MUST NOT create a descriptor chain longer + * than the Queue Size of the device. + */ + if (max > vq->pci_config.queue_size) + bad_driver_vq(vq, + "indirect has too many entries"); + } - do { /* Grab the first descriptor, and check it's OK. */ iov[*out_num + *in_num].iov_len = desc[i].len; iov[*out_num + *in_num].iov_base - = check_pointer(desc[i].addr, desc[i].len); + = check_pointer(vq->dev, desc[i].addr, desc[i].len); /* If this is an input descriptor, increment that count. */ if (desc[i].flags & VRING_DESC_F_WRITE) (*in_num)++; @@ -739,14 +891,15 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, * to come before any input descriptors. */ if (*in_num) - errx(1, "Descriptor has out after in"); + bad_driver_vq(vq, + "Descriptor has out after in"); (*out_num)++; } /* If we've got too many, that implies a descriptor loop. */ if (*out_num + *in_num > max) - errx(1, "Looped descriptor"); - } while ((i = next_desc(desc, i, max)) != max); + bad_driver_vq(vq, "Looped descriptor"); + } while ((i = next_desc(vq->dev, desc, i, max)) != max); return head; } @@ -803,7 +956,7 @@ static void console_input(struct virtqueue *vq) /* Make sure there's a descriptor available. */ head = wait_for_vq_desc(vq, iov, &out_num, &in_num); if (out_num) - errx(1, "Output buffers in console in queue?"); + bad_driver_vq(vq, "Output buffers in console in queue?"); /* Read into it. This is where we usually wait. */ len = readv(STDIN_FILENO, iov, in_num); @@ -856,7 +1009,7 @@ static void console_output(struct virtqueue *vq) /* We usually wait in here, for the Guest to give us something. */ head = wait_for_vq_desc(vq, iov, &out, &in); if (in) - errx(1, "Input buffers in console output queue?"); + bad_driver_vq(vq, "Input buffers in console output queue?"); /* writev can return a partial write, so we loop here. */ while (!iov_empty(iov, out)) { @@ -865,7 +1018,7 @@ static void console_output(struct virtqueue *vq) warn("Write to stdout gave %i (%d)", len, errno); break; } - iov_consume(iov, out, NULL, len); + iov_consume(vq->dev, iov, out, NULL, len); } /* @@ -894,7 +1047,7 @@ static void net_output(struct virtqueue *vq) /* We usually wait in here for the Guest to give us a packet. */ head = wait_for_vq_desc(vq, iov, &out, &in); if (in) - errx(1, "Input buffers in net output queue?"); + bad_driver_vq(vq, "Input buffers in net output queue?"); /* * Send the whole thing through to /dev/net/tun. It expects the exact * same format: what a coincidence! @@ -942,7 +1095,7 @@ static void net_input(struct virtqueue *vq) */ head = wait_for_vq_desc(vq, iov, &out, &in); if (out) - errx(1, "Output buffers in net input queue?"); + bad_driver_vq(vq, "Output buffers in net input queue?"); /* * If it looks like we'll block reading from the tun device, send them @@ -986,6 +1139,12 @@ static void kill_launcher(int signal) kill(0, SIGTERM); } +static void reset_vq_pci_config(struct virtqueue *vq) +{ + vq->pci_config.queue_size = VIRTQUEUE_NUM; + vq->pci_config.queue_enable = 0; +} + static void reset_device(struct device *dev) { struct virtqueue *vq; @@ -993,53 +1152,705 @@ static void reset_device(struct device *dev) verbose("Resetting device %s\n", dev->name); /* Clear any features they've acked. */ - memset(get_feature_bits(dev) + dev->feature_len, 0, dev->feature_len); + dev->features_accepted = 0; /* We're going to be explicitly killing threads, so ignore them. */ signal(SIGCHLD, SIG_IGN); - /* Zero out the virtqueues, get rid of their threads */ + /* + * 4.1.4.3.1: + * + * The device MUST present a 0 in queue_enable on reset. + * + * This means we set it here, and reset the saved ones in every vq. + */ + dev->mmio->cfg.queue_enable = 0; + + /* Get rid of the virtqueue threads */ for (vq = dev->vq; vq; vq = vq->next) { + vq->last_avail_idx = 0; + reset_vq_pci_config(vq); if (vq->thread != (pid_t)-1) { kill(vq->thread, SIGTERM); waitpid(vq->thread, NULL, 0); vq->thread = (pid_t)-1; } - memset(vq->vring.desc, 0, - vring_size(vq->config.num, LGUEST_VRING_ALIGN)); - lg_last_avail(vq) = 0; } dev->running = false; + dev->wrote_features_ok = false; /* Now we care if threads die. */ signal(SIGCHLD, (void *)kill_launcher); } +static void cleanup_devices(void) +{ + unsigned int i; + + for (i = 1; i < MAX_PCI_DEVICES; i++) { + struct device *d = devices.pci[i]; + if (!d) + continue; + reset_device(d); + } + + /* If we saved off the original terminal settings, restore them now. */ + if (orig_term.c_lflag & (ISIG|ICANON|ECHO)) + tcsetattr(STDIN_FILENO, TCSANOW, &orig_term); +} + +/*L:217 + * We do PCI. This is mainly done to let us test the kernel virtio PCI + * code. + */ + +/* Linux expects a PCI host bridge: ours is a dummy, and first on the bus. */ +static struct device pci_host_bridge; + +static void init_pci_host_bridge(void) +{ + pci_host_bridge.name = "PCI Host Bridge"; + pci_host_bridge.config.class = 0x06; /* bridge */ + pci_host_bridge.config.subclass = 0; /* host bridge */ + devices.pci[0] = &pci_host_bridge; +} + +/* The IO ports used to read the PCI config space. */ +#define PCI_CONFIG_ADDR 0xCF8 +#define PCI_CONFIG_DATA 0xCFC + +/* + * Not really portable, but does help readability: this is what the Guest + * writes to the PCI_CONFIG_ADDR IO port. + */ +union pci_config_addr { + struct { + unsigned mbz: 2; + unsigned offset: 6; + unsigned funcnum: 3; + unsigned devnum: 5; + unsigned busnum: 8; + unsigned reserved: 7; + unsigned enabled : 1; + } bits; + u32 val; +}; + +/* + * We cache what they wrote to the address port, so we know what they're + * talking about when they access the data port. + */ +static union pci_config_addr pci_config_addr; + +static struct device *find_pci_device(unsigned int index) +{ + return devices.pci[index]; +} + +/* PCI can do 1, 2 and 4 byte reads; we handle that here. */ +static void ioread(u16 off, u32 v, u32 mask, u32 *val) +{ + assert(off < 4); + assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF); + *val = (v >> (off * 8)) & mask; +} + +/* PCI can do 1, 2 and 4 byte writes; we handle that here. */ +static void iowrite(u16 off, u32 v, u32 mask, u32 *dst) +{ + assert(off < 4); + assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF); + *dst &= ~(mask << (off * 8)); + *dst |= (v & mask) << (off * 8); +} + +/* + * Where PCI_CONFIG_DATA accesses depends on the previous write to + * PCI_CONFIG_ADDR. + */ +static struct device *dev_and_reg(u32 *reg) +{ + if (!pci_config_addr.bits.enabled) + return NULL; + + if (pci_config_addr.bits.funcnum != 0) + return NULL; + + if (pci_config_addr.bits.busnum != 0) + return NULL; + + if (pci_config_addr.bits.offset * 4 >= sizeof(struct pci_config)) + return NULL; + + *reg = pci_config_addr.bits.offset; + return find_pci_device(pci_config_addr.bits.devnum); +} + +/* + * We can get invalid combinations of values while they're writing, so we + * only fault if they try to write with some invalid bar/offset/length. + */ +static bool valid_bar_access(struct device *d, + struct virtio_pci_cfg_cap *cfg_access) +{ + /* We only have 1 bar (BAR0) */ + if (cfg_access->cap.bar != 0) + return false; + + /* Check it's within BAR0. */ + if (cfg_access->cap.offset >= d->mmio_size + || cfg_access->cap.offset + cfg_access->cap.length > d->mmio_size) + return false; + + /* Check length is 1, 2 or 4. */ + if (cfg_access->cap.length != 1 + && cfg_access->cap.length != 2 + && cfg_access->cap.length != 4) + return false; + + /* + * 4.1.4.7.2: + * + * The driver MUST NOT write a cap.offset which is not a multiple of + * cap.length (ie. all accesses MUST be aligned). + */ + if (cfg_access->cap.offset % cfg_access->cap.length != 0) + return false; + + /* Return pointer into word in BAR0. */ + return true; +} + +/* Is this accessing the PCI config address port?. */ +static bool is_pci_addr_port(u16 port) +{ + return port >= PCI_CONFIG_ADDR && port < PCI_CONFIG_ADDR + 4; +} + +static bool pci_addr_iowrite(u16 port, u32 mask, u32 val) +{ + iowrite(port - PCI_CONFIG_ADDR, val, mask, + &pci_config_addr.val); + verbose("PCI%s: %#x/%x: bus %u dev %u func %u reg %u\n", + pci_config_addr.bits.enabled ? "" : " DISABLED", + val, mask, + pci_config_addr.bits.busnum, + pci_config_addr.bits.devnum, + pci_config_addr.bits.funcnum, + pci_config_addr.bits.offset); + return true; +} + +static void pci_addr_ioread(u16 port, u32 mask, u32 *val) +{ + ioread(port - PCI_CONFIG_ADDR, pci_config_addr.val, mask, val); +} + +/* Is this accessing the PCI config data port?. */ +static bool is_pci_data_port(u16 port) +{ + return port >= PCI_CONFIG_DATA && port < PCI_CONFIG_DATA + 4; +} + +static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask); + +static bool pci_data_iowrite(u16 port, u32 mask, u32 val) +{ + u32 reg, portoff; + struct device *d = dev_and_reg(®); + + /* Complain if they don't belong to a device. */ + if (!d) + return false; + + /* They can do 1 byte writes, etc. */ + portoff = port - PCI_CONFIG_DATA; + + /* + * PCI uses a weird way to determine the BAR size: the OS + * writes all 1's, and sees which ones stick. + */ + if (&d->config_words[reg] == &d->config.bar[0]) { + int i; + + iowrite(portoff, val, mask, &d->config.bar[0]); + for (i = 0; (1 << i) < d->mmio_size; i++) + d->config.bar[0] &= ~(1 << i); + return true; + } else if ((&d->config_words[reg] > &d->config.bar[0] + && &d->config_words[reg] <= &d->config.bar[6]) + || &d->config_words[reg] == &d->config.expansion_rom_addr) { + /* Allow writing to any other BAR, or expansion ROM */ + iowrite(portoff, val, mask, &d->config_words[reg]); + return true; + /* We let them overide latency timer and cacheline size */ + } else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) { + /* Only let them change the first two fields. */ + if (mask == 0xFFFFFFFF) + mask = 0xFFFF; + iowrite(portoff, val, mask, &d->config_words[reg]); + return true; + } else if (&d->config_words[reg] == (void *)&d->config.command + && mask == 0xFFFF) { + /* Ignore command writes. */ + return true; + } else if (&d->config_words[reg] + == (void *)&d->config.cfg_access.cap.bar + || &d->config_words[reg] + == &d->config.cfg_access.cap.length + || &d->config_words[reg] + == &d->config.cfg_access.cap.offset) { + + /* + * The VIRTIO_PCI_CAP_PCI_CFG capability + * provides a backdoor to access the MMIO + * regions without mapping them. Weird, but + * useful. + */ + iowrite(portoff, val, mask, &d->config_words[reg]); + return true; + } else if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) { + u32 write_mask; + + /* + * 4.1.4.7.1: + * + * Upon detecting driver write access to pci_cfg_data, the + * device MUST execute a write access at offset cap.offset at + * BAR selected by cap.bar using the first cap.length bytes + * from pci_cfg_data. + */ + + /* Must be bar 0 */ + if (!valid_bar_access(d, &d->config.cfg_access)) + return false; + + iowrite(portoff, val, mask, &d->config.cfg_access.pci_cfg_data); + + /* + * Now emulate a write. The mask we use is set by + * len, *not* this write! + */ + write_mask = (1ULL<<(8*d->config.cfg_access.cap.length)) - 1; + verbose("Window writing %#x/%#x to bar %u, offset %u len %u\n", + d->config.cfg_access.pci_cfg_data, write_mask, + d->config.cfg_access.cap.bar, + d->config.cfg_access.cap.offset, + d->config.cfg_access.cap.length); + + emulate_mmio_write(d, d->config.cfg_access.cap.offset, + d->config.cfg_access.pci_cfg_data, + write_mask); + return true; + } + + /* + * 4.1.4.1: + * + * The driver MUST NOT write into any field of the capability + * structure, with the exception of those with cap_type + * VIRTIO_PCI_CAP_PCI_CFG... + */ + return false; +} + +static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask); + +static void pci_data_ioread(u16 port, u32 mask, u32 *val) +{ + u32 reg; + struct device *d = dev_and_reg(®); + + if (!d) + return; + + /* Read through the PCI MMIO access window is special */ + if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) { + u32 read_mask; + + /* + * 4.1.4.7.1: + * + * Upon detecting driver read access to pci_cfg_data, the + * device MUST execute a read access of length cap.length at + * offset cap.offset at BAR selected by cap.bar and store the + * first cap.length bytes in pci_cfg_data. + */ + /* Must be bar 0 */ + if (!valid_bar_access(d, &d->config.cfg_access)) + bad_driver(d, + "Invalid cfg_access to bar%u, offset %u len %u", + d->config.cfg_access.cap.bar, + d->config.cfg_access.cap.offset, + d->config.cfg_access.cap.length); + + /* + * Read into the window. The mask we use is set by + * len, *not* this read! + */ + read_mask = (1ULL<<(8*d->config.cfg_access.cap.length))-1; + d->config.cfg_access.pci_cfg_data + = emulate_mmio_read(d, + d->config.cfg_access.cap.offset, + read_mask); + verbose("Window read %#x/%#x from bar %u, offset %u len %u\n", + d->config.cfg_access.pci_cfg_data, read_mask, + d->config.cfg_access.cap.bar, + d->config.cfg_access.cap.offset, + d->config.cfg_access.cap.length); + } + ioread(port - PCI_CONFIG_DATA, d->config_words[reg], mask, val); +} + /*L:216 - * This actually creates the thread which services the virtqueue for a device. + * This is where we emulate a handful of Guest instructions. It's ugly + * and we used to do it in the kernel but it grew over time. + */ + +/* + * We use the ptrace syscall's pt_regs struct to talk about registers + * to lguest: these macros convert the names to the offsets. + */ +#define getreg(name) getreg_off(offsetof(struct user_regs_struct, name)) +#define setreg(name, val) \ + setreg_off(offsetof(struct user_regs_struct, name), (val)) + +static u32 getreg_off(size_t offset) +{ + u32 r; + unsigned long args[] = { LHREQ_GETREG, offset }; + + if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0) + err(1, "Getting register %u", offset); + if (pread(lguest_fd, &r, sizeof(r), cpu_id) != sizeof(r)) + err(1, "Reading register %u", offset); + + return r; +} + +static void setreg_off(size_t offset, u32 val) +{ + unsigned long args[] = { LHREQ_SETREG, offset, val }; + + if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0) + err(1, "Setting register %u", offset); +} + +/* Get register by instruction encoding */ +static u32 getreg_num(unsigned regnum, u32 mask) +{ + /* 8 bit ops use regnums 4-7 for high parts of word */ + if (mask == 0xFF && (regnum & 0x4)) + return getreg_num(regnum & 0x3, 0xFFFF) >> 8; + + switch (regnum) { + case 0: return getreg(eax) & mask; + case 1: return getreg(ecx) & mask; + case 2: return getreg(edx) & mask; + case 3: return getreg(ebx) & mask; + case 4: return getreg(esp) & mask; + case 5: return getreg(ebp) & mask; + case 6: return getreg(esi) & mask; + case 7: return getreg(edi) & mask; + } + abort(); +} + +/* Set register by instruction encoding */ +static void setreg_num(unsigned regnum, u32 val, u32 mask) +{ + /* Don't try to set bits out of range */ + assert(~(val & ~mask)); + + /* 8 bit ops use regnums 4-7 for high parts of word */ + if (mask == 0xFF && (regnum & 0x4)) { + /* Construct the 16 bits we want. */ + val = (val << 8) | getreg_num(regnum & 0x3, 0xFF); + setreg_num(regnum & 0x3, val, 0xFFFF); + return; + } + + switch (regnum) { + case 0: setreg(eax, val | (getreg(eax) & ~mask)); return; + case 1: setreg(ecx, val | (getreg(ecx) & ~mask)); return; + case 2: setreg(edx, val | (getreg(edx) & ~mask)); return; + case 3: setreg(ebx, val | (getreg(ebx) & ~mask)); return; + case 4: setreg(esp, val | (getreg(esp) & ~mask)); return; + case 5: setreg(ebp, val | (getreg(ebp) & ~mask)); return; + case 6: setreg(esi, val | (getreg(esi) & ~mask)); return; + case 7: setreg(edi, val | (getreg(edi) & ~mask)); return; + } + abort(); +} + +/* Get bytes of displacement appended to instruction, from r/m encoding */ +static u32 insn_displacement_len(u8 mod_reg_rm) +{ + /* Switch on the mod bits */ + switch (mod_reg_rm >> 6) { + case 0: + /* If mod == 0, and r/m == 101, 16-bit displacement follows */ + if ((mod_reg_rm & 0x7) == 0x5) + return 2; + /* Normally, mod == 0 means no literal displacement */ + return 0; + case 1: + /* One byte displacement */ + return 1; + case 2: + /* Four byte displacement */ + return 4; + case 3: + /* Register mode */ + return 0; + } + abort(); +} + +static void emulate_insn(const u8 insn[]) +{ + unsigned long args[] = { LHREQ_TRAP, 13 }; + unsigned int insnlen = 0, in = 0, small_operand = 0, byte_access; + unsigned int eax, port, mask; + /* + * Default is to return all-ones on IO port reads, which traditionally + * means "there's nothing there". + */ + u32 val = 0xFFFFFFFF; + + /* + * This must be the Guest kernel trying to do something, not userspace! + * The bottom two bits of the CS segment register are the privilege + * level. + */ + if ((getreg(xcs) & 3) != 0x1) + goto no_emulate; + + /* Decoding x86 instructions is icky. */ + + /* + * Around 2.6.33, the kernel started using an emulation for the + * cmpxchg8b instruction in early boot on many configurations. This + * code isn't paravirtualized, and it tries to disable interrupts. + * Ignore it, which will Mostly Work. + */ + if (insn[insnlen] == 0xfa) { + /* "cli", or Clear Interrupt Enable instruction. Skip it. */ + insnlen = 1; + goto skip_insn; + } + + /* + * 0x66 is an "operand prefix". It means a 16, not 32 bit in/out. + */ + if (insn[insnlen] == 0x66) { + small_operand = 1; + /* The instruction is 1 byte so far, read the next byte. */ + insnlen = 1; + } + + /* If the lower bit isn't set, it's a single byte access */ + byte_access = !(insn[insnlen] & 1); + + /* + * Now we can ignore the lower bit and decode the 4 opcodes + * we need to emulate. + */ + switch (insn[insnlen] & 0xFE) { + case 0xE4: /* in <next byte>,%al */ + port = insn[insnlen+1]; + insnlen += 2; + in = 1; + break; + case 0xEC: /* in (%dx),%al */ + port = getreg(edx) & 0xFFFF; + insnlen += 1; + in = 1; + break; + case 0xE6: /* out %al,<next byte> */ + port = insn[insnlen+1]; + insnlen += 2; + break; + case 0xEE: /* out %al,(%dx) */ + port = getreg(edx) & 0xFFFF; + insnlen += 1; + break; + default: + /* OK, we don't know what this is, can't emulate. */ + goto no_emulate; + } + + /* Set a mask of the 1, 2 or 4 bytes, depending on size of IO */ + if (byte_access) + mask = 0xFF; + else if (small_operand) + mask = 0xFFFF; + else + mask = 0xFFFFFFFF; + + /* + * If it was an "IN" instruction, they expect the result to be read + * into %eax, so we change %eax. + */ + eax = getreg(eax); + + if (in) { + /* This is the PS/2 keyboard status; 1 means ready for output */ + if (port == 0x64) + val = 1; + else if (is_pci_addr_port(port)) + pci_addr_ioread(port, mask, &val); + else if (is_pci_data_port(port)) + pci_data_ioread(port, mask, &val); + + /* Clear the bits we're about to read */ + eax &= ~mask; + /* Copy bits in from val. */ + eax |= val & mask; + /* Now update the register. */ + setreg(eax, eax); + } else { + if (is_pci_addr_port(port)) { + if (!pci_addr_iowrite(port, mask, eax)) + goto bad_io; + } else if (is_pci_data_port(port)) { + if (!pci_data_iowrite(port, mask, eax)) + goto bad_io; + } + /* There are many other ports, eg. CMOS clock, serial + * and parallel ports, so we ignore them all. */ + } + + verbose("IO %s of %x to %u: %#08x\n", + in ? "IN" : "OUT", mask, port, eax); +skip_insn: + /* Finally, we've "done" the instruction, so move past it. */ + setreg(eip, getreg(eip) + insnlen); + return; + +bad_io: + warnx("Attempt to %s port %u (%#x mask)", + in ? "read from" : "write to", port, mask); + +no_emulate: + /* Inject trap into Guest. */ + if (write(lguest_fd, args, sizeof(args)) < 0) + err(1, "Reinjecting trap 13 for fault at %#x", getreg(eip)); +} + +static struct device *find_mmio_region(unsigned long paddr, u32 *off) +{ + unsigned int i; + + for (i = 1; i < MAX_PCI_DEVICES; i++) { + struct device *d = devices.pci[i]; + + if (!d) + continue; + if (paddr < d->mmio_addr) + continue; + if (paddr >= d->mmio_addr + d->mmio_size) + continue; + *off = paddr - d->mmio_addr; + return d; + } + return NULL; +} + +/* FIXME: Use vq array. */ +static struct virtqueue *vq_by_num(struct device *d, u32 num) +{ + struct virtqueue *vq = d->vq; + + while (num-- && vq) + vq = vq->next; + + return vq; +} + +static void save_vq_config(const struct virtio_pci_common_cfg *cfg, + struct virtqueue *vq) +{ + vq->pci_config = *cfg; +} + +static void restore_vq_config(struct virtio_pci_common_cfg *cfg, + struct virtqueue *vq) +{ + /* Only restore the per-vq part */ + size_t off = offsetof(struct virtio_pci_common_cfg, queue_size); + + memcpy((void *)cfg + off, (void *)&vq->pci_config + off, + sizeof(*cfg) - off); +} + +/* + * 4.1.4.3.2: + * + * The driver MUST configure the other virtqueue fields before + * enabling the virtqueue with queue_enable. + * + * When they enable the virtqueue, we check that their setup is valid. */ -static void create_thread(struct virtqueue *vq) +static void check_virtqueue(struct device *d, struct virtqueue *vq) +{ + /* Because lguest is 32 bit, all the descriptor high bits must be 0 */ + if (vq->pci_config.queue_desc_hi + || vq->pci_config.queue_avail_hi + || vq->pci_config.queue_used_hi) + bad_driver_vq(vq, "invalid 64-bit queue address"); + + /* + * 2.4.1: + * + * The driver MUST ensure that the physical address of the first byte + * of each virtqueue part is a multiple of the specified alignment + * value in the above table. + */ + if (vq->pci_config.queue_desc_lo % 16 + || vq->pci_config.queue_avail_lo % 2 + || vq->pci_config.queue_used_lo % 4) + bad_driver_vq(vq, "invalid alignment in queue addresses"); + + /* Initialize the virtqueue and check they're all in range. */ + vq->vring.num = vq->pci_config.queue_size; + vq->vring.desc = check_pointer(vq->dev, + vq->pci_config.queue_desc_lo, + sizeof(*vq->vring.desc) * vq->vring.num); + vq->vring.avail = check_pointer(vq->dev, + vq->pci_config.queue_avail_lo, + sizeof(*vq->vring.avail) + + (sizeof(vq->vring.avail->ring[0]) + * vq->vring.num)); + vq->vring.used = check_pointer(vq->dev, + vq->pci_config.queue_used_lo, + sizeof(*vq->vring.used) + + (sizeof(vq->vring.used->ring[0]) + * vq->vring.num)); + + /* + * 2.4.9.1: + * + * The driver MUST initialize flags in the used ring to 0 + * when allocating the used ring. + */ + if (vq->vring.used->flags != 0) + bad_driver_vq(vq, "invalid initial used.flags %#x", + vq->vring.used->flags); +} + +static void start_virtqueue(struct virtqueue *vq) { /* * Create stack for thread. Since the stack grows upwards, we point * the stack pointer to the end of this region. */ char *stack = malloc(32768); - unsigned long args[] = { LHREQ_EVENTFD, - vq->config.pfn*getpagesize(), 0 }; /* Create a zero-initialized eventfd. */ vq->eventfd = eventfd(0, 0); if (vq->eventfd < 0) err(1, "Creating eventfd"); - args[2] = vq->eventfd; - - /* - * Attach an eventfd to this virtqueue: it will go off when the Guest - * does an LHCALL_NOTIFY for this vq. - */ - if (write(lguest_fd, &args, sizeof(args)) != 0) - err(1, "Attaching eventfd"); /* * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so @@ -1048,167 +1859,531 @@ static void create_thread(struct virtqueue *vq) vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq); if (vq->thread == (pid_t)-1) err(1, "Creating clone"); - - /* We close our local copy now the child has it. */ - close(vq->eventfd); } -static void start_device(struct device *dev) +static void start_virtqueues(struct device *d) { - unsigned int i; struct virtqueue *vq; - verbose("Device %s OK: offered", dev->name); - for (i = 0; i < dev->feature_len; i++) - verbose(" %02x", get_feature_bits(dev)[i]); - verbose(", accepted"); - for (i = 0; i < dev->feature_len; i++) - verbose(" %02x", get_feature_bits(dev) - [dev->feature_len+i]); - - for (vq = dev->vq; vq; vq = vq->next) { - if (vq->service) - create_thread(vq); + for (vq = d->vq; vq; vq = vq->next) { + if (vq->pci_config.queue_enable) + start_virtqueue(vq); } - dev->running = true; } -static void cleanup_devices(void) +static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask) { - struct device *dev; + struct virtqueue *vq; - for (dev = devices.dev; dev; dev = dev->next) - reset_device(dev); + switch (off) { + case offsetof(struct virtio_pci_mmio, cfg.device_feature_select): + /* + * 4.1.4.3.1: + * + * The device MUST present the feature bits it is offering in + * device_feature, starting at bit device_feature_select ∗ 32 + * for any device_feature_select written by the driver + */ + if (val == 0) + d->mmio->cfg.device_feature = d->features; + else if (val == 1) + d->mmio->cfg.device_feature = (d->features >> 32); + else + d->mmio->cfg.device_feature = 0; + goto feature_write_through32; + case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select): + if (val > 1) + bad_driver(d, "Unexpected driver select %u", val); + goto feature_write_through32; + case offsetof(struct virtio_pci_mmio, cfg.guest_feature): + if (d->mmio->cfg.guest_feature_select == 0) { + d->features_accepted &= ~((u64)0xFFFFFFFF); + d->features_accepted |= val; + } else { + assert(d->mmio->cfg.guest_feature_select == 1); + d->features_accepted &= 0xFFFFFFFF; + d->features_accepted |= ((u64)val) << 32; + } + /* + * 2.2.1: + * + * The driver MUST NOT accept a feature which the device did + * not offer + */ + if (d->features_accepted & ~d->features) + bad_driver(d, "over-accepted features %#llx of %#llx", + d->features_accepted, d->features); + goto feature_write_through32; + case offsetof(struct virtio_pci_mmio, cfg.device_status): { + u8 prev; + + verbose("%s: device status -> %#x\n", d->name, val); + /* + * 4.1.4.3.1: + * + * The device MUST reset when 0 is written to device_status, + * and present a 0 in device_status once that is done. + */ + if (val == 0) { + reset_device(d); + goto write_through8; + } - /* If we saved off the original terminal settings, restore them now. */ - if (orig_term.c_lflag & (ISIG|ICANON|ECHO)) - tcsetattr(STDIN_FILENO, TCSANOW, &orig_term); -} + /* 2.1.1: The driver MUST NOT clear a device status bit. */ + if (d->mmio->cfg.device_status & ~val) + bad_driver(d, "unset of device status bit %#x -> %#x", + d->mmio->cfg.device_status, val); -/* When the Guest tells us they updated the status field, we handle it. */ -static void update_device_status(struct device *dev) -{ - /* A zero status is a reset, otherwise it's a set of flags. */ - if (dev->desc->status == 0) - reset_device(dev); - else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) { - warnx("Device %s configuration FAILED", dev->name); - if (dev->running) - reset_device(dev); - } else { - if (dev->running) - err(1, "Device %s features finalized twice", dev->name); - start_device(dev); + /* + * 2.1.2: + * + * The device MUST NOT consume buffers or notify the driver + * before DRIVER_OK. + */ + if (val & VIRTIO_CONFIG_S_DRIVER_OK + && !(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK)) + start_virtqueues(d); + + /* + * 3.1.1: + * + * The driver MUST follow this sequence to initialize a device: + * - Reset the device. + * - Set the ACKNOWLEDGE status bit: the guest OS has + * notice the device. + * - Set the DRIVER status bit: the guest OS knows how + * to drive the device. + * - Read device feature bits, and write the subset + * of feature bits understood by the OS and driver + * to the device. During this step the driver MAY + * read (but MUST NOT write) the device-specific + * configuration fields to check that it can + * support the device before accepting it. + * - Set the FEATURES_OK status bit. The driver + * MUST not accept new feature bits after this + * step. + * - Re-read device status to ensure the FEATURES_OK + * bit is still set: otherwise, the device does + * not support our subset of features and the + * device is unusable. + * - Perform device-specific setup, including + * discovery of virtqueues for the device, + * optional per-bus setup, reading and possibly + * writing the device’s virtio configuration + * space, and population of virtqueues. + * - Set the DRIVER_OK status bit. At this point the + * device is “live”. + */ + prev = 0; + switch (val & ~d->mmio->cfg.device_status) { + case VIRTIO_CONFIG_S_DRIVER_OK: + prev |= VIRTIO_CONFIG_S_FEATURES_OK; /* fall thru */ + case VIRTIO_CONFIG_S_FEATURES_OK: + prev |= VIRTIO_CONFIG_S_DRIVER; /* fall thru */ + case VIRTIO_CONFIG_S_DRIVER: + prev |= VIRTIO_CONFIG_S_ACKNOWLEDGE; /* fall thru */ + case VIRTIO_CONFIG_S_ACKNOWLEDGE: + break; + default: + bad_driver(d, "unknown device status bit %#x -> %#x", + d->mmio->cfg.device_status, val); + } + if (d->mmio->cfg.device_status != prev) + bad_driver(d, "unexpected status transition %#x -> %#x", + d->mmio->cfg.device_status, val); + + /* If they just wrote FEATURES_OK, we make sure they read */ + switch (val & ~d->mmio->cfg.device_status) { + case VIRTIO_CONFIG_S_FEATURES_OK: + d->wrote_features_ok = true; + break; + case VIRTIO_CONFIG_S_DRIVER_OK: + if (d->wrote_features_ok) + bad_driver(d, "did not re-read FEATURES_OK"); + break; + } + goto write_through8; } -} + case offsetof(struct virtio_pci_mmio, cfg.queue_select): + vq = vq_by_num(d, val); + /* + * 4.1.4.3.1: + * + * The device MUST present a 0 in queue_size if the virtqueue + * corresponding to the current queue_select is unavailable. + */ + if (!vq) { + d->mmio->cfg.queue_size = 0; + goto write_through16; + } + /* Save registers for old vq, if it was a valid vq */ + if (d->mmio->cfg.queue_size) + save_vq_config(&d->mmio->cfg, + vq_by_num(d, d->mmio->cfg.queue_select)); + /* Restore the registers for the queue they asked for */ + restore_vq_config(&d->mmio->cfg, vq); + goto write_through16; + case offsetof(struct virtio_pci_mmio, cfg.queue_size): + /* + * 4.1.4.3.2: + * + * The driver MUST NOT write a value which is not a power of 2 + * to queue_size. + */ + if (val & (val-1)) + bad_driver(d, "invalid queue size %u", val); + if (d->mmio->cfg.queue_enable) + bad_driver(d, "changing queue size on live device"); + goto write_through16; + case offsetof(struct virtio_pci_mmio, cfg.queue_msix_vector): + bad_driver(d, "attempt to set MSIX vector to %u", val); + case offsetof(struct virtio_pci_mmio, cfg.queue_enable): { + struct virtqueue *vq = vq_by_num(d, d->mmio->cfg.queue_select); -/*L:215 - * This is the generic routine we call when the Guest uses LHCALL_NOTIFY. In - * particular, it's used to notify us of device status changes during boot. - */ -static void handle_output(unsigned long addr) -{ - struct device *i; + /* + * 4.1.4.3.2: + * + * The driver MUST NOT write a 0 to queue_enable. + */ + if (val != 1) + bad_driver(d, "setting queue_enable to %u", val); - /* Check each device. */ - for (i = devices.dev; i; i = i->next) { - struct virtqueue *vq; + /* + * 3.1.1: + * + * 7. Perform device-specific setup, including discovery of + * virtqueues for the device, optional per-bus setup, + * reading and possibly writing the device’s virtio + * configuration space, and population of virtqueues. + * 8. Set the DRIVER_OK status bit. + * + * All our devices require all virtqueues to be enabled, so + * they should have done that before setting DRIVER_OK. + */ + if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK) + bad_driver(d, "enabling vq after DRIVER_OK"); + d->mmio->cfg.queue_enable = val; + save_vq_config(&d->mmio->cfg, vq); + check_virtqueue(d, vq); + goto write_through16; + } + case offsetof(struct virtio_pci_mmio, cfg.queue_notify_off): + bad_driver(d, "attempt to write to queue_notify_off"); + case offsetof(struct virtio_pci_mmio, cfg.queue_desc_lo): + case offsetof(struct virtio_pci_mmio, cfg.queue_desc_hi): + case offsetof(struct virtio_pci_mmio, cfg.queue_avail_lo): + case offsetof(struct virtio_pci_mmio, cfg.queue_avail_hi): + case offsetof(struct virtio_pci_mmio, cfg.queue_used_lo): + case offsetof(struct virtio_pci_mmio, cfg.queue_used_hi): /* - * Notifications to device descriptors mean they updated the - * device status. + * 4.1.4.3.2: + * + * The driver MUST configure the other virtqueue fields before + * enabling the virtqueue with queue_enable. */ - if (from_guest_phys(addr) == i->desc) { - update_device_status(i); - return; - } + if (d->mmio->cfg.queue_enable) + bad_driver(d, "changing queue on live device"); + + /* + * 3.1.1: + * + * The driver MUST follow this sequence to initialize a device: + *... + * 5. Set the FEATURES_OK status bit. The driver MUST not + * accept new feature bits after this step. + */ + if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK)) + bad_driver(d, "setting up vq before FEATURES_OK"); - /* Devices should not be used before features are finalized. */ - for (vq = i->vq; vq; vq = vq->next) { - if (addr != vq->config.pfn*getpagesize()) - continue; - errx(1, "Notification on %s before setup!", i->name); + /* + * 6. Re-read device status to ensure the FEATURES_OK bit is + * still set... + */ + if (d->wrote_features_ok) + bad_driver(d, "didn't re-read FEATURES_OK before setup"); + + goto write_through32; + case offsetof(struct virtio_pci_mmio, notify): + vq = vq_by_num(d, val); + if (!vq) + bad_driver(d, "Invalid vq notification on %u", val); + /* Notify the process handling this vq by adding 1 to eventfd */ + write(vq->eventfd, "\1\0\0\0\0\0\0\0", 8); + goto write_through16; + case offsetof(struct virtio_pci_mmio, isr): + bad_driver(d, "Unexpected write to isr"); + /* Weird corner case: write to emerg_wr of console */ + case sizeof(struct virtio_pci_mmio) + + offsetof(struct virtio_console_config, emerg_wr): + if (strcmp(d->name, "console") == 0) { + char c = val; + write(STDOUT_FILENO, &c, 1); + goto write_through32; } + /* Fall through... */ + default: + /* + * 4.1.4.3.2: + * + * The driver MUST NOT write to device_feature, num_queues, + * config_generation or queue_notify_off. + */ + bad_driver(d, "Unexpected write to offset %u", off); } +feature_write_through32: /* - * Early console write is done using notify on a nul-terminated string - * in Guest memory. It's also great for hacking debugging messages - * into a Guest. + * 3.1.1: + * + * The driver MUST follow this sequence to initialize a device: + *... + * - Set the DRIVER status bit: the guest OS knows how + * to drive the device. + * - Read device feature bits, and write the subset + * of feature bits understood by the OS and driver + * to the device. + *... + * - Set the FEATURES_OK status bit. The driver MUST not + * accept new feature bits after this step. */ - if (addr >= guest_limit) - errx(1, "Bad NOTIFY %#lx", addr); + if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER)) + bad_driver(d, "feature write before VIRTIO_CONFIG_S_DRIVER"); + if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK) + bad_driver(d, "feature write after VIRTIO_CONFIG_S_FEATURES_OK"); - write(STDOUT_FILENO, from_guest_phys(addr), - strnlen(from_guest_phys(addr), guest_limit - addr)); + /* + * 4.1.3.1: + * + * The driver MUST access each field using the “natural” access + * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for + * 16-bit fields and 8-bit accesses for 8-bit fields. + */ +write_through32: + if (mask != 0xFFFFFFFF) { + bad_driver(d, "non-32-bit write to offset %u (%#x)", + off, getreg(eip)); + return; + } + memcpy((char *)d->mmio + off, &val, 4); + return; + +write_through16: + if (mask != 0xFFFF) + bad_driver(d, "non-16-bit write to offset %u (%#x)", + off, getreg(eip)); + memcpy((char *)d->mmio + off, &val, 2); + return; + +write_through8: + if (mask != 0xFF) + bad_driver(d, "non-8-bit write to offset %u (%#x)", + off, getreg(eip)); + memcpy((char *)d->mmio + off, &val, 1); + return; } -/*L:190 - * Device Setup - * - * All devices need a descriptor so the Guest knows it exists, and a "struct - * device" so the Launcher can keep track of it. We have common helper - * routines to allocate and manage them. - */ - -/* - * The layout of the device page is a "struct lguest_device_desc" followed by a - * number of virtqueue descriptors, then two sets of feature bits, then an - * array of configuration bytes. This routine returns the configuration - * pointer. - */ -static u8 *device_config(const struct device *dev) +static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask) { - return (void *)(dev->desc + 1) - + dev->num_vq * sizeof(struct lguest_vqconfig) - + dev->feature_len * 2; + u8 isr; + u32 val = 0; + + switch (off) { + case offsetof(struct virtio_pci_mmio, cfg.device_feature_select): + case offsetof(struct virtio_pci_mmio, cfg.device_feature): + case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select): + case offsetof(struct virtio_pci_mmio, cfg.guest_feature): + /* + * 3.1.1: + * + * The driver MUST follow this sequence to initialize a device: + *... + * - Set the DRIVER status bit: the guest OS knows how + * to drive the device. + * - Read device feature bits, and write the subset + * of feature bits understood by the OS and driver + * to the device. + */ + if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER)) + bad_driver(d, + "feature read before VIRTIO_CONFIG_S_DRIVER"); + goto read_through32; + case offsetof(struct virtio_pci_mmio, cfg.msix_config): + bad_driver(d, "read of msix_config"); + case offsetof(struct virtio_pci_mmio, cfg.num_queues): + goto read_through16; + case offsetof(struct virtio_pci_mmio, cfg.device_status): + /* As they did read, any write of FEATURES_OK is now fine. */ + d->wrote_features_ok = false; + goto read_through8; + case offsetof(struct virtio_pci_mmio, cfg.config_generation): + /* + * 4.1.4.3.1: + * + * The device MUST present a changed config_generation after + * the driver has read a device-specific configuration value + * which has changed since any part of the device-specific + * configuration was last read. + * + * This is simple: none of our devices change config, so this + * is always 0. + */ + goto read_through8; + case offsetof(struct virtio_pci_mmio, notify): + /* + * 3.1.1: + * + * The driver MUST NOT notify the device before setting + * DRIVER_OK. + */ + if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK)) + bad_driver(d, "notify before VIRTIO_CONFIG_S_DRIVER_OK"); + goto read_through16; + case offsetof(struct virtio_pci_mmio, isr): + if (mask != 0xFF) + bad_driver(d, "non-8-bit read from offset %u (%#x)", + off, getreg(eip)); + isr = d->mmio->isr; + /* + * 4.1.4.5.1: + * + * The device MUST reset ISR status to 0 on driver read. + */ + d->mmio->isr = 0; + return isr; + case offsetof(struct virtio_pci_mmio, padding): + bad_driver(d, "read from padding (%#x)", getreg(eip)); + default: + /* Read from device config space, beware unaligned overflow */ + if (off > d->mmio_size - 4) + bad_driver(d, "read past end (%#x)", getreg(eip)); + + /* + * 3.1.1: + * The driver MUST follow this sequence to initialize a device: + *... + * 3. Set the DRIVER status bit: the guest OS knows how to + * drive the device. + * 4. Read device feature bits, and write the subset of + * feature bits understood by the OS and driver to the + * device. During this step the driver MAY read (but MUST NOT + * write) the device-specific configuration fields to check + * that it can support the device before accepting it. + */ + if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER)) + bad_driver(d, + "config read before VIRTIO_CONFIG_S_DRIVER"); + + if (mask == 0xFFFFFFFF) + goto read_through32; + else if (mask == 0xFFFF) + goto read_through16; + else + goto read_through8; + } + + /* + * 4.1.3.1: + * + * The driver MUST access each field using the “natural” access + * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for + * 16-bit fields and 8-bit accesses for 8-bit fields. + */ +read_through32: + if (mask != 0xFFFFFFFF) + bad_driver(d, "non-32-bit read to offset %u (%#x)", + off, getreg(eip)); + memcpy(&val, (char *)d->mmio + off, 4); + return val; + +read_through16: + if (mask != 0xFFFF) + bad_driver(d, "non-16-bit read to offset %u (%#x)", + off, getreg(eip)); + memcpy(&val, (char *)d->mmio + off, 2); + return val; + +read_through8: + if (mask != 0xFF) + bad_driver(d, "non-8-bit read to offset %u (%#x)", + off, getreg(eip)); + memcpy(&val, (char *)d->mmio + off, 1); + return val; } -/* - * This routine allocates a new "struct lguest_device_desc" from descriptor - * table page just above the Guest's normal memory. It returns a pointer to - * that descriptor. - */ -static struct lguest_device_desc *new_dev_desc(u16 type) +static void emulate_mmio(unsigned long paddr, const u8 *insn) { - struct lguest_device_desc d = { .type = type }; - void *p; + u32 val, off, mask = 0xFFFFFFFF, insnlen = 0; + struct device *d = find_mmio_region(paddr, &off); + unsigned long args[] = { LHREQ_TRAP, 14 }; - /* Figure out where the next device config is, based on the last one. */ - if (devices.lastdev) - p = device_config(devices.lastdev) - + devices.lastdev->desc->config_len; - else - p = devices.descpage; + if (!d) { + warnx("MMIO touching %#08lx (not a device)", paddr); + goto reinject; + } + + /* Prefix makes it a 16 bit op */ + if (insn[0] == 0x66) { + mask = 0xFFFF; + insnlen++; + } - /* We only have one page for all the descriptors. */ - if (p + sizeof(d) > (void *)devices.descpage + getpagesize()) - errx(1, "Too many devices"); + /* iowrite */ + if (insn[insnlen] == 0x89) { + /* Next byte is r/m byte: bits 3-5 are register. */ + val = getreg_num((insn[insnlen+1] >> 3) & 0x7, mask); + emulate_mmio_write(d, off, val, mask); + insnlen += 2 + insn_displacement_len(insn[insnlen+1]); + } else if (insn[insnlen] == 0x8b) { /* ioread */ + /* Next byte is r/m byte: bits 3-5 are register. */ + val = emulate_mmio_read(d, off, mask); + setreg_num((insn[insnlen+1] >> 3) & 0x7, val, mask); + insnlen += 2 + insn_displacement_len(insn[insnlen+1]); + } else if (insn[0] == 0x88) { /* 8-bit iowrite */ + mask = 0xff; + /* Next byte is r/m byte: bits 3-5 are register. */ + val = getreg_num((insn[1] >> 3) & 0x7, mask); + emulate_mmio_write(d, off, val, mask); + insnlen = 2 + insn_displacement_len(insn[1]); + } else if (insn[0] == 0x8a) { /* 8-bit ioread */ + mask = 0xff; + val = emulate_mmio_read(d, off, mask); + setreg_num((insn[1] >> 3) & 0x7, val, mask); + insnlen = 2 + insn_displacement_len(insn[1]); + } else { + warnx("Unknown MMIO instruction touching %#08lx:" + " %02x %02x %02x %02x at %u", + paddr, insn[0], insn[1], insn[2], insn[3], getreg(eip)); + reinject: + /* Inject trap into Guest. */ + if (write(lguest_fd, args, sizeof(args)) < 0) + err(1, "Reinjecting trap 14 for fault at %#x", + getreg(eip)); + return; + } - /* p might not be aligned, so we memcpy in. */ - return memcpy(p, &d, sizeof(d)); + /* Finally, we've "done" the instruction, so move past it. */ + setreg(eip, getreg(eip) + insnlen); } -/* - * Each device descriptor is followed by the description of its virtqueues. We - * specify how many descriptors the virtqueue is to have. +/*L:190 + * Device Setup + * + * All devices need a descriptor so the Guest knows it exists, and a "struct + * device" so the Launcher can keep track of it. We have common helper + * routines to allocate and manage them. */ -static void add_virtqueue(struct device *dev, unsigned int num_descs, - void (*service)(struct virtqueue *)) +static void add_pci_virtqueue(struct device *dev, + void (*service)(struct virtqueue *), + const char *name) { - unsigned int pages; struct virtqueue **i, *vq = malloc(sizeof(*vq)); - void *p; - - /* First we need some memory for this virtqueue. */ - pages = (vring_size(num_descs, LGUEST_VRING_ALIGN) + getpagesize() - 1) - / getpagesize(); - p = get_pages(pages); /* Initialize the virtqueue */ vq->next = NULL; vq->last_avail_idx = 0; vq->dev = dev; + vq->name = name; /* * This is the routine the service thread will run, and its Process ID @@ -1218,25 +2393,11 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, vq->thread = (pid_t)-1; /* Initialize the configuration. */ - vq->config.num = num_descs; - vq->config.irq = devices.next_irq++; - vq->config.pfn = to_guest_phys(p) / getpagesize(); - - /* Initialize the vring. */ - vring_init(&vq->vring, num_descs, p, LGUEST_VRING_ALIGN); - - /* - * Append virtqueue to this device's descriptor. We use - * device_config() to get the end of the device's current virtqueues; - * we check that we haven't added any config or feature information - * yet, otherwise we'd be overwriting them. - */ - assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0); - memcpy(device_config(dev), &vq->config, sizeof(vq->config)); - dev->num_vq++; - dev->desc->num_vq++; + reset_vq_pci_config(vq); + vq->pci_config.queue_notify_off = 0; - verbose("Virtqueue page %#lx\n", to_guest_phys(p)); + /* Add one to the number of queues */ + vq->dev->mmio->cfg.num_queues++; /* * Add to tail of list, so dev->vq is first vq, dev->vq->next is @@ -1246,73 +2407,239 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, *i = vq; } -/* - * The first half of the feature bitmask is for us to advertise features. The - * second half is for the Guest to accept features. - */ -static void add_feature(struct device *dev, unsigned bit) +/* The Guest accesses the feature bits via the PCI common config MMIO region */ +static void add_pci_feature(struct device *dev, unsigned bit) { - u8 *features = get_feature_bits(dev); + dev->features |= (1ULL << bit); +} - /* We can't extend the feature bits once we've added config bytes */ - if (dev->desc->feature_len <= bit / CHAR_BIT) { - assert(dev->desc->config_len == 0); - dev->feature_len = dev->desc->feature_len = (bit/CHAR_BIT) + 1; - } +/* For devices with no config. */ +static void no_device_config(struct device *dev) +{ + dev->mmio_addr = get_mmio_region(dev->mmio_size); - features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT)); + dev->config.bar[0] = dev->mmio_addr; + /* Bottom 4 bits must be zero */ + assert(~(dev->config.bar[0] & 0xF)); +} + +/* This puts the device config into BAR0 */ +static void set_device_config(struct device *dev, const void *conf, size_t len) +{ + /* Set up BAR 0 */ + dev->mmio_size += len; + dev->mmio = realloc(dev->mmio, dev->mmio_size); + memcpy(dev->mmio + 1, conf, len); + + /* + * 4.1.4.6: + * + * The device MUST present at least one VIRTIO_PCI_CAP_DEVICE_CFG + * capability for any device type which has a device-specific + * configuration. + */ + /* Hook up device cfg */ + dev->config.cfg_access.cap.cap_next + = offsetof(struct pci_config, device); + + /* + * 4.1.4.6.1: + * + * The offset for the device-specific configuration MUST be 4-byte + * aligned. + */ + assert(dev->config.cfg_access.cap.cap_next % 4 == 0); + + /* Fix up device cfg field length. */ + dev->config.device.length = len; + + /* The rest is the same as the no-config case */ + no_device_config(dev); +} + +static void init_cap(struct virtio_pci_cap *cap, size_t caplen, int type, + size_t bar_offset, size_t bar_bytes, u8 next) +{ + cap->cap_vndr = PCI_CAP_ID_VNDR; + cap->cap_next = next; + cap->cap_len = caplen; + cap->cfg_type = type; + cap->bar = 0; + memset(cap->padding, 0, sizeof(cap->padding)); + cap->offset = bar_offset; + cap->length = bar_bytes; } /* - * This routine sets the configuration fields for an existing device's - * descriptor. It only works for the last device, but that's OK because that's - * how we use it. + * This sets up the pci_config structure, as defined in the virtio 1.0 + * standard (and PCI standard). */ -static void set_config(struct device *dev, unsigned len, const void *conf) +static void init_pci_config(struct pci_config *pci, u16 type, + u8 class, u8 subclass) { - /* Check we haven't overflowed our single page. */ - if (device_config(dev) + len > devices.descpage + getpagesize()) - errx(1, "Too many devices"); + size_t bar_offset, bar_len; + + /* + * 4.1.4.4.1: + * + * The device MUST either present notify_off_multiplier as an even + * power of 2, or present notify_off_multiplier as 0. + * + * 2.1.2: + * + * The device MUST initialize device status to 0 upon reset. + */ + memset(pci, 0, sizeof(*pci)); + + /* 4.1.2.1: Devices MUST have the PCI Vendor ID 0x1AF4 */ + pci->vendor_id = 0x1AF4; + /* 4.1.2.1: ... PCI Device ID calculated by adding 0x1040 ... */ + pci->device_id = 0x1040 + type; + + /* + * PCI have specific codes for different types of devices. + * Linux doesn't care, but it's a good clue for people looking + * at the device. + */ + pci->class = class; + pci->subclass = subclass; + + /* + * 4.1.2.1: + * + * Non-transitional devices SHOULD have a PCI Revision ID of 1 or + * higher + */ + pci->revid = 1; + + /* + * 4.1.2.1: + * + * Non-transitional devices SHOULD have a PCI Subsystem Device ID of + * 0x40 or higher. + */ + pci->subsystem_device_id = 0x40; + + /* We use our dummy interrupt controller, and irq_line is the irq */ + pci->irq_line = devices.next_irq++; + pci->irq_pin = 0; + + /* Support for extended capabilities. */ + pci->status = (1 << 4); + + /* Link them in. */ + /* + * 4.1.4.3.1: + * + * The device MUST present at least one common configuration + * capability. + */ + pci->capabilities = offsetof(struct pci_config, common); + + /* 4.1.4.3.1 ... offset MUST be 4-byte aligned. */ + assert(pci->capabilities % 4 == 0); + + bar_offset = offsetof(struct virtio_pci_mmio, cfg); + bar_len = sizeof(((struct virtio_pci_mmio *)0)->cfg); + init_cap(&pci->common, sizeof(pci->common), VIRTIO_PCI_CAP_COMMON_CFG, + bar_offset, bar_len, + offsetof(struct pci_config, notify)); + + /* + * 4.1.4.4.1: + * + * The device MUST present at least one notification capability. + */ + bar_offset += bar_len; + bar_len = sizeof(((struct virtio_pci_mmio *)0)->notify); + + /* + * 4.1.4.4.1: + * + * The cap.offset MUST be 2-byte aligned. + */ + assert(pci->common.cap_next % 2 == 0); + + /* FIXME: Use a non-zero notify_off, for per-queue notification? */ + /* + * 4.1.4.4.1: + * + * The value cap.length presented by the device MUST be at least 2 and + * MUST be large enough to support queue notification offsets for all + * supported queues in all possible configurations. + */ + assert(bar_len >= 2); + + init_cap(&pci->notify.cap, sizeof(pci->notify), + VIRTIO_PCI_CAP_NOTIFY_CFG, + bar_offset, bar_len, + offsetof(struct pci_config, isr)); + + bar_offset += bar_len; + bar_len = sizeof(((struct virtio_pci_mmio *)0)->isr); + /* + * 4.1.4.5.1: + * + * The device MUST present at least one VIRTIO_PCI_CAP_ISR_CFG + * capability. + */ + init_cap(&pci->isr, sizeof(pci->isr), + VIRTIO_PCI_CAP_ISR_CFG, + bar_offset, bar_len, + offsetof(struct pci_config, cfg_access)); + + /* + * 4.1.4.7.1: + * + * The device MUST present at least one VIRTIO_PCI_CAP_PCI_CFG + * capability. + */ + /* This doesn't have any presence in the BAR */ + init_cap(&pci->cfg_access.cap, sizeof(pci->cfg_access), + VIRTIO_PCI_CAP_PCI_CFG, + 0, 0, 0); - /* Copy in the config information, and store the length. */ - memcpy(device_config(dev), conf, len); - dev->desc->config_len = len; + bar_offset += bar_len + sizeof(((struct virtio_pci_mmio *)0)->padding); + assert(bar_offset == sizeof(struct virtio_pci_mmio)); - /* Size must fit in config_len field (8 bits)! */ - assert(dev->desc->config_len == len); + /* + * This gets sewn in and length set in set_device_config(). + * Some devices don't have a device configuration interface, so + * we never expose this if we don't call set_device_config(). + */ + init_cap(&pci->device, sizeof(pci->device), VIRTIO_PCI_CAP_DEVICE_CFG, + bar_offset, 0, 0); } /* - * This routine does all the creation and setup of a new device, including - * calling new_dev_desc() to allocate the descriptor and device memory. We - * don't actually start the service threads until later. + * This routine does all the creation and setup of a new device, but we don't + * actually place the MMIO region until we know the size (if any) of the + * device-specific config. And we don't actually start the service threads + * until later. * * See what I mean about userspace being boring? */ -static struct device *new_device(const char *name, u16 type) +static struct device *new_pci_device(const char *name, u16 type, + u8 class, u8 subclass) { struct device *dev = malloc(sizeof(*dev)); /* Now we populate the fields one at a time. */ - dev->desc = new_dev_desc(type); dev->name = name; dev->vq = NULL; - dev->feature_len = 0; - dev->num_vq = 0; dev->running = false; - dev->next = NULL; + dev->wrote_features_ok = false; + dev->mmio_size = sizeof(struct virtio_pci_mmio); + dev->mmio = calloc(1, dev->mmio_size); + dev->features = (u64)1 << VIRTIO_F_VERSION_1; + dev->features_accepted = 0; - /* - * Append to device list. Prepending to a single-linked list is - * easier, but the user expects the devices to be arranged on the bus - * in command-line order. The first network device on the command line - * is eth0, the first block device /dev/vda, etc. - */ - if (devices.lastdev) - devices.lastdev->next = dev; - else - devices.dev = dev; - devices.lastdev = dev; + if (devices.device_num + 1 >= MAX_PCI_DEVICES) + errx(1, "Can only handle 31 PCI devices"); + + init_pci_config(&dev->config, type, class, subclass); + assert(!devices.pci[devices.device_num+1]); + devices.pci[++devices.device_num] = dev; return dev; } @@ -1324,6 +2651,7 @@ static struct device *new_device(const char *name, u16 type) static void setup_console(void) { struct device *dev; + struct virtio_console_config conf; /* If we can save the initial standard input settings... */ if (tcgetattr(STDIN_FILENO, &orig_term) == 0) { @@ -1336,7 +2664,7 @@ static void setup_console(void) tcsetattr(STDIN_FILENO, TCSANOW, &term); } - dev = new_device("console", VIRTIO_ID_CONSOLE); + dev = new_pci_device("console", VIRTIO_ID_CONSOLE, 0x07, 0x00); /* We store the console state in dev->priv, and initialize it. */ dev->priv = malloc(sizeof(struct console_abort)); @@ -1348,10 +2676,14 @@ static void setup_console(void) * stdin. When they put something in the output queue, we write it to * stdout. */ - add_virtqueue(dev, VIRTQUEUE_NUM, console_input); - add_virtqueue(dev, VIRTQUEUE_NUM, console_output); + add_pci_virtqueue(dev, console_input, "input"); + add_pci_virtqueue(dev, console_output, "output"); + + /* We need a configuration area for the emerg_wr early writes. */ + add_pci_feature(dev, VIRTIO_CONSOLE_F_EMERG_WRITE); + set_device_config(dev, &conf, sizeof(conf)); - verbose("device %u: console\n", ++devices.device_num); + verbose("device %u: console\n", devices.device_num); } /*:*/ @@ -1449,6 +2781,7 @@ static void configure_device(int fd, const char *tapif, u32 ipaddr) static int get_tun_device(char tapif[IFNAMSIZ]) { struct ifreq ifr; + int vnet_hdr_sz; int netfd; /* Start with this zeroed. Messy but sure. */ @@ -1476,6 +2809,18 @@ static int get_tun_device(char tapif[IFNAMSIZ]) */ ioctl(netfd, TUNSETNOCSUM, 1); + /* + * In virtio before 1.0 (aka legacy virtio), we added a 16-bit + * field at the end of the network header iff + * VIRTIO_NET_F_MRG_RXBUF was negotiated. For virtio 1.0, + * that became the norm, but we need to tell the tun device + * about our expanded header (which is called + * virtio_net_hdr_mrg_rxbuf in the legacy system). + */ + vnet_hdr_sz = sizeof(struct virtio_net_hdr_v1); + if (ioctl(netfd, TUNSETVNETHDRSZ, &vnet_hdr_sz) != 0) + err(1, "Setting tun header size to %u", vnet_hdr_sz); + memcpy(tapif, ifr.ifr_name, IFNAMSIZ); return netfd; } @@ -1499,12 +2844,12 @@ static void setup_tun_net(char *arg) net_info->tunfd = get_tun_device(tapif); /* First we create a new network device. */ - dev = new_device("net", VIRTIO_ID_NET); + dev = new_pci_device("net", VIRTIO_ID_NET, 0x02, 0x00); dev->priv = net_info; /* Network devices need a recv and a send queue, just like console. */ - add_virtqueue(dev, VIRTQUEUE_NUM, net_input); - add_virtqueue(dev, VIRTQUEUE_NUM, net_output); + add_pci_virtqueue(dev, net_input, "rx"); + add_pci_virtqueue(dev, net_output, "tx"); /* * We need a socket to perform the magic network ioctls to bring up the @@ -1524,7 +2869,7 @@ static void setup_tun_net(char *arg) p = strchr(arg, ':'); if (p) { str2mac(p+1, conf.mac); - add_feature(dev, VIRTIO_NET_F_MAC); + add_pci_feature(dev, VIRTIO_NET_F_MAC); *p = '\0'; } @@ -1538,25 +2883,21 @@ static void setup_tun_net(char *arg) configure_device(ipfd, tapif, ip); /* Expect Guest to handle everything except UFO */ - add_feature(dev, VIRTIO_NET_F_CSUM); - add_feature(dev, VIRTIO_NET_F_GUEST_CSUM); - add_feature(dev, VIRTIO_NET_F_GUEST_TSO4); - add_feature(dev, VIRTIO_NET_F_GUEST_TSO6); - add_feature(dev, VIRTIO_NET_F_GUEST_ECN); - add_feature(dev, VIRTIO_NET_F_HOST_TSO4); - add_feature(dev, VIRTIO_NET_F_HOST_TSO6); - add_feature(dev, VIRTIO_NET_F_HOST_ECN); + add_pci_feature(dev, VIRTIO_NET_F_CSUM); + add_pci_feature(dev, VIRTIO_NET_F_GUEST_CSUM); + add_pci_feature(dev, VIRTIO_NET_F_GUEST_TSO4); + add_pci_feature(dev, VIRTIO_NET_F_GUEST_TSO6); + add_pci_feature(dev, VIRTIO_NET_F_GUEST_ECN); + add_pci_feature(dev, VIRTIO_NET_F_HOST_TSO4); + add_pci_feature(dev, VIRTIO_NET_F_HOST_TSO6); + add_pci_feature(dev, VIRTIO_NET_F_HOST_ECN); /* We handle indirect ring entries */ - add_feature(dev, VIRTIO_RING_F_INDIRECT_DESC); - /* We're compliant with the damn spec. */ - add_feature(dev, VIRTIO_F_ANY_LAYOUT); - set_config(dev, sizeof(conf), &conf); + add_pci_feature(dev, VIRTIO_RING_F_INDIRECT_DESC); + set_device_config(dev, &conf, sizeof(conf)); /* We don't need the socket any more; setup is done. */ close(ipfd); - devices.device_num++; - if (bridging) verbose("device %u: tun %s attached to bridge: %s\n", devices.device_num, tapif, arg); @@ -1607,7 +2948,7 @@ static void blk_request(struct virtqueue *vq) head = wait_for_vq_desc(vq, iov, &out_num, &in_num); /* Copy the output header from the front of the iov (adjusts iov) */ - iov_consume(iov, out_num, &out, sizeof(out)); + iov_consume(vq->dev, iov, out_num, &out, sizeof(out)); /* Find and trim end of iov input array, for our status byte. */ in = NULL; @@ -1619,7 +2960,7 @@ static void blk_request(struct virtqueue *vq) } } if (!in) - errx(1, "Bad virtblk cmd with no room for status"); + bad_driver_vq(vq, "Bad virtblk cmd with no room for status"); /* * For historical reasons, block operations are expressed in 512 byte @@ -1627,15 +2968,7 @@ static void blk_request(struct virtqueue *vq) */ off = out.sector * 512; - /* - * In general the virtio block driver is allowed to try SCSI commands. - * It'd be nice if we supported eject, for example, but we don't. - */ - if (out.type & VIRTIO_BLK_T_SCSI_CMD) { - fprintf(stderr, "Scsi commands unsupported\n"); - *in = VIRTIO_BLK_S_UNSUPP; - wlen = sizeof(*in); - } else if (out.type & VIRTIO_BLK_T_OUT) { + if (out.type & VIRTIO_BLK_T_OUT) { /* * Write * @@ -1657,7 +2990,7 @@ static void blk_request(struct virtqueue *vq) /* Trim it back to the correct length */ ftruncate64(vblk->fd, vblk->len); /* Die, bad Guest, die. */ - errx(1, "Write past end %llu+%u", off, ret); + bad_driver_vq(vq, "Write past end %llu+%u", off, ret); } wlen = sizeof(*in); @@ -1699,11 +3032,11 @@ static void setup_block_file(const char *filename) struct vblk_info *vblk; struct virtio_blk_config conf; - /* Creat the device. */ - dev = new_device("block", VIRTIO_ID_BLOCK); + /* Create the device. */ + dev = new_pci_device("block", VIRTIO_ID_BLOCK, 0x01, 0x80); /* The device has one virtqueue, where the Guest places requests. */ - add_virtqueue(dev, VIRTQUEUE_NUM, blk_request); + add_pci_virtqueue(dev, blk_request, "request"); /* Allocate the room for our own bookkeeping */ vblk = dev->priv = malloc(sizeof(*vblk)); @@ -1712,9 +3045,6 @@ static void setup_block_file(const char *filename) vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE); vblk->len = lseek64(vblk->fd, 0, SEEK_END); - /* We support FLUSH. */ - add_feature(dev, VIRTIO_BLK_F_FLUSH); - /* Tell Guest how many sectors this device has. */ conf.capacity = cpu_to_le64(vblk->len / 512); @@ -1722,20 +3052,19 @@ static void setup_block_file(const char *filename) * Tell Guest not to put in too many descriptors at once: two are used * for the in and out elements. */ - add_feature(dev, VIRTIO_BLK_F_SEG_MAX); + add_pci_feature(dev, VIRTIO_BLK_F_SEG_MAX); conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2); - /* Don't try to put whole struct: we have 8 bit limit. */ - set_config(dev, offsetof(struct virtio_blk_config, geometry), &conf); + set_device_config(dev, &conf, sizeof(struct virtio_blk_config)); verbose("device %u: virtblock %llu sectors\n", - ++devices.device_num, le64_to_cpu(conf.capacity)); + devices.device_num, le64_to_cpu(conf.capacity)); } /*L:211 - * Our random number generator device reads from /dev/random into the Guest's + * Our random number generator device reads from /dev/urandom into the Guest's * input buffers. The usual case is that the Guest doesn't want random numbers - * and so has no buffers although /dev/random is still readable, whereas + * and so has no buffers although /dev/urandom is still readable, whereas * console is the reverse. * * The same logic applies, however. @@ -1754,7 +3083,7 @@ static void rng_input(struct virtqueue *vq) /* First we need a buffer from the Guests's virtqueue. */ head = wait_for_vq_desc(vq, iov, &out_num, &in_num); if (out_num) - errx(1, "Output buffers in rng?"); + bad_driver_vq(vq, "Output buffers in rng?"); /* * Just like the console write, we loop to cover the whole iovec. @@ -1763,8 +3092,8 @@ static void rng_input(struct virtqueue *vq) while (!iov_empty(iov, in_num)) { len = readv(rng_info->rfd, iov, in_num); if (len <= 0) - err(1, "Read from /dev/random gave %i", len); - iov_consume(iov, in_num, NULL, len); + err(1, "Read from /dev/urandom gave %i", len); + iov_consume(vq->dev, iov, in_num, NULL, len); totlen += len; } @@ -1780,17 +3109,20 @@ static void setup_rng(void) struct device *dev; struct rng_info *rng_info = malloc(sizeof(*rng_info)); - /* Our device's privat info simply contains the /dev/random fd. */ - rng_info->rfd = open_or_die("/dev/random", O_RDONLY); + /* Our device's private info simply contains the /dev/urandom fd. */ + rng_info->rfd = open_or_die("/dev/urandom", O_RDONLY); /* Create the new device. */ - dev = new_device("rng", VIRTIO_ID_RNG); + dev = new_pci_device("rng", VIRTIO_ID_RNG, 0xff, 0); dev->priv = rng_info; /* The device has one virtqueue, where the Guest places inbufs. */ - add_virtqueue(dev, VIRTQUEUE_NUM, rng_input); + add_pci_virtqueue(dev, rng_input, "input"); - verbose("device %u: rng\n", devices.device_num++); + /* We don't have any configuration space */ + no_device_config(dev); + + verbose("device %u: rng\n", devices.device_num); } /* That's the end of device setup. */ @@ -1820,17 +3152,23 @@ static void __attribute__((noreturn)) restart_guest(void) static void __attribute__((noreturn)) run_guest(void) { for (;;) { - unsigned long notify_addr; + struct lguest_pending notify; int readval; /* We read from the /dev/lguest device to run the Guest. */ - readval = pread(lguest_fd, ¬ify_addr, - sizeof(notify_addr), cpu_id); - - /* One unsigned long means the Guest did HCALL_NOTIFY */ - if (readval == sizeof(notify_addr)) { - verbose("Notify on address %#lx\n", notify_addr); - handle_output(notify_addr); + readval = pread(lguest_fd, ¬ify, sizeof(notify), cpu_id); + if (readval == sizeof(notify)) { + if (notify.trap == 13) { + verbose("Emulating instruction at %#x\n", + getreg(eip)); + emulate_insn(notify.insn); + } else if (notify.trap == 14) { + verbose("Emulating MMIO at %#x\n", + getreg(eip)); + emulate_mmio(notify.addr, notify.insn); + } else + errx(1, "Unknown trap %i addr %#08x\n", + notify.trap, notify.addr); /* ENOENT means the Guest died. Reading tells us why. */ } else if (errno == ENOENT) { char reason[1024] = { 0 }; @@ -1893,11 +3231,9 @@ int main(int argc, char *argv[]) main_args = argv; /* - * First we initialize the device list. We keep a pointer to the last - * device, and the next interrupt number to use for devices (1: - * remember that 0 is used by the timer). + * First we initialize the device list. We remember next interrupt + * number to use for devices (1: remember that 0 is used by the timer). */ - devices.lastdev = NULL; devices.next_irq = 1; /* We're CPU 0. In fact, that's the only CPU possible right now. */ @@ -1921,12 +3257,14 @@ int main(int argc, char *argv[]) guest_base = map_zeroed_pages(mem / getpagesize() + DEVICE_PAGES); guest_limit = mem; - guest_max = mem + DEVICE_PAGES*getpagesize(); - devices.descpage = get_pages(1); + guest_max = guest_mmio = mem + DEVICE_PAGES*getpagesize(); break; } } + /* We always have a console device, and it's always device 1. */ + setup_console(); + /* The options are fairly straight-forward */ while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) { switch (c) { @@ -1967,8 +3305,8 @@ int main(int argc, char *argv[]) verbose("Guest base is at %p\n", guest_base); - /* We always have a console device */ - setup_console(); + /* Initialize the (fake) PCI host bridge device. */ + init_pci_host_bridge(); /* Now we load the kernel */ start = load_kernel(open_or_die(argv[optind+1], O_RDONLY)); diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c index a74fba6d7743..d2b18e887071 100644 --- a/tools/lib/api/fs/debugfs.c +++ b/tools/lib/api/fs/debugfs.c @@ -1,3 +1,4 @@ +#define _GNU_SOURCE #include <errno.h> #include <stdio.h> #include <stdlib.h> @@ -67,7 +68,7 @@ int debugfs_valid_mountpoint(const char *debugfs) if (statfs(debugfs, &st_fs) < 0) return -ENOENT; - else if (st_fs.f_type != (long) DEBUGFS_MAGIC) + else if ((long)st_fs.f_type != (long)DEBUGFS_MAGIC) return -ENOENT; return 0; @@ -98,3 +99,45 @@ char *debugfs_mount(const char *mountpoint) out: return debugfs_mountpoint; } + +int debugfs__strerror_open(int err, char *buf, size_t size, const char *filename) +{ + char sbuf[128]; + + switch (err) { + case ENOENT: + if (debugfs_found) { + snprintf(buf, size, + "Error:\tFile %s/%s not found.\n" + "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n", + debugfs_mountpoint, filename); + break; + } + snprintf(buf, size, "%s", + "Error:\tUnable to find debugfs\n" + "Hint:\tWas your kernel compiled with debugfs support?\n" + "Hint:\tIs the debugfs filesystem mounted?\n" + "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'"); + break; + case EACCES: + snprintf(buf, size, + "Error:\tNo permissions to read %s/%s\n" + "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n", + debugfs_mountpoint, filename, debugfs_mountpoint); + break; + default: + snprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf))); + break; + } + + return 0; +} + +int debugfs__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name) +{ + char path[PATH_MAX]; + + snprintf(path, PATH_MAX, "tracing/events/%s/%s", sys, name ?: "*"); + + return debugfs__strerror_open(err, buf, size, path); +} diff --git a/tools/lib/api/fs/debugfs.h b/tools/lib/api/fs/debugfs.h index f19d3df9609d..0739881a9897 100644 --- a/tools/lib/api/fs/debugfs.h +++ b/tools/lib/api/fs/debugfs.h @@ -26,4 +26,7 @@ char *debugfs_mount(const char *mountpoint); extern char debugfs_mountpoint[]; +int debugfs__strerror_open(int err, char *buf, size_t size, const char *filename); +int debugfs__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name); + #endif /* __API_DEBUGFS_H__ */ diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index c1b49c36a951..128ef6332a6b 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -7,6 +7,10 @@ #include <stdlib.h> #include <string.h> #include <sys/vfs.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> #include "debugfs.h" #include "fs.h" @@ -75,7 +79,7 @@ static int fs__valid_mount(const char *fs, long magic) if (statfs(fs, &st_fs) < 0) return -ENOENT; - else if (st_fs.f_type != magic) + else if ((long)st_fs.f_type != magic) return -ENOENT; return 0; @@ -163,3 +167,33 @@ const char *name##__mountpoint(void) \ FS__MOUNTPOINT(sysfs, FS__SYSFS); FS__MOUNTPOINT(procfs, FS__PROCFS); + +int filename__read_int(const char *filename, int *value) +{ + char line[64]; + int fd = open(filename, O_RDONLY), err = -1; + + if (fd < 0) + return -1; + + if (read(fd, line, sizeof(line)) > 0) { + *value = atoi(line); + err = 0; + } + + close(fd); + return err; +} + +int sysctl__read_int(const char *sysctl, int *value) +{ + char path[PATH_MAX]; + const char *procfs = procfs__mountpoint(); + + if (!procfs) + return -1; + + snprintf(path, sizeof(path), "%s/sys/%s", procfs, sysctl); + + return filename__read_int(path, value); +} diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h index cb7049551f33..6caa2bbc6cec 100644 --- a/tools/lib/api/fs/fs.h +++ b/tools/lib/api/fs/fs.h @@ -11,4 +11,7 @@ const char *sysfs__mountpoint(void); const char *procfs__mountpoint(void); + +int filename__read_int(const char *filename, int *value); +int sysctl__read_int(const char *sysctl, int *value); #endif /* __API_FS__ */ diff --git a/tools/lib/lockdep/.gitignore b/tools/lib/lockdep/.gitignore new file mode 100644 index 000000000000..cc0e7a9f99e3 --- /dev/null +++ b/tools/lib/lockdep/.gitignore @@ -0,0 +1 @@ +liblockdep.so.* diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile index 52f9279c6c13..4b866c54f624 100644 --- a/tools/lib/lockdep/Makefile +++ b/tools/lib/lockdep/Makefile @@ -104,7 +104,7 @@ N = export Q VERBOSE -INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES) +INCLUDES = -I. -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES) # Set compile option CFLAGS if not set elsewhere CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c index 6f803609e498..0b0112c80f22 100644 --- a/tools/lib/lockdep/preload.c +++ b/tools/lib/lockdep/preload.c @@ -317,7 +317,7 @@ int pthread_mutex_destroy(pthread_mutex_t *mutex) * * TODO: Hook into free() and add that check there as well. */ - debug_check_no_locks_freed(mutex, mutex + sizeof(*mutex)); + debug_check_no_locks_freed(mutex, sizeof(*mutex)); __del_lock(__get_lock(mutex)); return ll_pthread_mutex_destroy(mutex); } @@ -341,7 +341,7 @@ int pthread_rwlock_destroy(pthread_rwlock_t *rwlock) { try_init_preload(); - debug_check_no_locks_freed(rwlock, rwlock + sizeof(*rwlock)); + debug_check_no_locks_freed(rwlock, sizeof(*rwlock)); __del_lock(__get_lock(rwlock)); return ll_pthread_rwlock_destroy(rwlock); } diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index cf3a44bf1ec3..afe20ed9fac8 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -32,6 +32,7 @@ #include <stdint.h> #include <limits.h> +#include <netinet/ip6.h> #include "event-parse.h" #include "event-utils.h" @@ -4149,6 +4150,324 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size, trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3], buf[4], buf[5]); } +static void print_ip4_addr(struct trace_seq *s, char i, unsigned char *buf) +{ + const char *fmt; + + if (i == 'i') + fmt = "%03d.%03d.%03d.%03d"; + else + fmt = "%d.%d.%d.%d"; + + trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3]); +} + +static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) +{ + return ((unsigned long)(a->s6_addr32[0] | a->s6_addr32[1]) | + (unsigned long)(a->s6_addr32[2] ^ htonl(0x0000ffff))) == 0UL; +} + +static inline bool ipv6_addr_is_isatap(const struct in6_addr *addr) +{ + return (addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE); +} + +static void print_ip6c_addr(struct trace_seq *s, unsigned char *addr) +{ + int i, j, range; + unsigned char zerolength[8]; + int longest = 1; + int colonpos = -1; + uint16_t word; + uint8_t hi, lo; + bool needcolon = false; + bool useIPv4; + struct in6_addr in6; + + memcpy(&in6, addr, sizeof(struct in6_addr)); + + useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); + + memset(zerolength, 0, sizeof(zerolength)); + + if (useIPv4) + range = 6; + else + range = 8; + + /* find position of longest 0 run */ + for (i = 0; i < range; i++) { + for (j = i; j < range; j++) { + if (in6.s6_addr16[j] != 0) + break; + zerolength[i]++; + } + } + for (i = 0; i < range; i++) { + if (zerolength[i] > longest) { + longest = zerolength[i]; + colonpos = i; + } + } + if (longest == 1) /* don't compress a single 0 */ + colonpos = -1; + + /* emit address */ + for (i = 0; i < range; i++) { + if (i == colonpos) { + if (needcolon || i == 0) + trace_seq_printf(s, ":"); + trace_seq_printf(s, ":"); + needcolon = false; + i += longest - 1; + continue; + } + if (needcolon) { + trace_seq_printf(s, ":"); + needcolon = false; + } + /* hex u16 without leading 0s */ + word = ntohs(in6.s6_addr16[i]); + hi = word >> 8; + lo = word & 0xff; + if (hi) + trace_seq_printf(s, "%x%02x", hi, lo); + else + trace_seq_printf(s, "%x", lo); + + needcolon = true; + } + + if (useIPv4) { + if (needcolon) + trace_seq_printf(s, ":"); + print_ip4_addr(s, 'I', &in6.s6_addr[12]); + } + + return; +} + +static void print_ip6_addr(struct trace_seq *s, char i, unsigned char *buf) +{ + int j; + + for (j = 0; j < 16; j += 2) { + trace_seq_printf(s, "%02x%02x", buf[j], buf[j+1]); + if (i == 'I' && j < 14) + trace_seq_printf(s, ":"); + } +} + +/* + * %pi4 print an IPv4 address with leading zeros + * %pI4 print an IPv4 address without leading zeros + * %pi6 print an IPv6 address without colons + * %pI6 print an IPv6 address with colons + * %pI6c print an IPv6 address in compressed form with colons + * %pISpc print an IP address based on sockaddr; p adds port. + */ +static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i, + void *data, int size, struct event_format *event, + struct print_arg *arg) +{ + unsigned char *buf; + + if (arg->type == PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return 0; + } + + if (arg->type != PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return 0; + } + + if (!arg->field.field) { + arg->field.field = + pevent_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return 0; + } + } + + buf = data + arg->field.field->offset; + + if (arg->field.field->size != 4) { + trace_seq_printf(s, "INVALIDIPv4"); + return 0; + } + print_ip4_addr(s, i, buf); + + return 0; +} + +static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i, + void *data, int size, struct event_format *event, + struct print_arg *arg) +{ + char have_c = 0; + unsigned char *buf; + int rc = 0; + + /* pI6c */ + if (i == 'I' && *ptr == 'c') { + have_c = 1; + ptr++; + rc++; + } + + if (arg->type == PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return rc; + } + + if (arg->type != PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return rc; + } + + if (!arg->field.field) { + arg->field.field = + pevent_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return rc; + } + } + + buf = data + arg->field.field->offset; + + if (arg->field.field->size != 16) { + trace_seq_printf(s, "INVALIDIPv6"); + return rc; + } + + if (have_c) + print_ip6c_addr(s, buf); + else + print_ip6_addr(s, i, buf); + + return rc; +} + +static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i, + void *data, int size, struct event_format *event, + struct print_arg *arg) +{ + char have_c = 0, have_p = 0; + unsigned char *buf; + struct sockaddr_storage *sa; + int rc = 0; + + /* pISpc */ + if (i == 'I') { + if (*ptr == 'p') { + have_p = 1; + ptr++; + rc++; + } + if (*ptr == 'c') { + have_c = 1; + ptr++; + rc++; + } + } + + if (arg->type == PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return rc; + } + + if (arg->type != PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return rc; + } + + if (!arg->field.field) { + arg->field.field = + pevent_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return rc; + } + } + + sa = (struct sockaddr_storage *) (data + arg->field.field->offset); + + if (sa->ss_family == AF_INET) { + struct sockaddr_in *sa4 = (struct sockaddr_in *) sa; + + if (arg->field.field->size < sizeof(struct sockaddr_in)) { + trace_seq_printf(s, "INVALIDIPv4"); + return rc; + } + + print_ip4_addr(s, i, (unsigned char *) &sa4->sin_addr); + if (have_p) + trace_seq_printf(s, ":%d", ntohs(sa4->sin_port)); + + + } else if (sa->ss_family == AF_INET6) { + struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) sa; + + if (arg->field.field->size < sizeof(struct sockaddr_in6)) { + trace_seq_printf(s, "INVALIDIPv6"); + return rc; + } + + if (have_p) + trace_seq_printf(s, "["); + + buf = (unsigned char *) &sa6->sin6_addr; + if (have_c) + print_ip6c_addr(s, buf); + else + print_ip6_addr(s, i, buf); + + if (have_p) + trace_seq_printf(s, "]:%d", ntohs(sa6->sin6_port)); + } + + return rc; +} + +static int print_ip_arg(struct trace_seq *s, const char *ptr, + void *data, int size, struct event_format *event, + struct print_arg *arg) +{ + char i = *ptr; /* 'i' or 'I' */ + char ver; + int rc = 0; + + ptr++; + rc++; + + ver = *ptr; + ptr++; + rc++; + + switch (ver) { + case '4': + rc += print_ipv4_arg(s, ptr, i, data, size, event, arg); + break; + case '6': + rc += print_ipv6_arg(s, ptr, i, data, size, event, arg); + break; + case 'S': + rc += print_ipsa_arg(s, ptr, i, data, size, event, arg); + break; + default: + return 0; + } + + return rc; +} + static int is_printable_array(char *p, unsigned int len) { unsigned int i; @@ -4337,6 +4656,15 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event ptr++; arg = arg->next; break; + } else if (*(ptr+1) == 'I' || *(ptr+1) == 'i') { + int n; + + n = print_ip_arg(s, ptr+1, data, size, event, arg); + if (n > 0) { + ptr += n; + arg = arg->next; + break; + } } /* fall through */ diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c index eda326fc8620..3727de48c8d5 100644 --- a/tools/lib/traceevent/plugin_scsi.c +++ b/tools/lib/traceevent/plugin_scsi.c @@ -85,8 +85,9 @@ typedef unsigned int u32; #define MOVE_MEDIUM 0xa5 #define EXCHANGE_MEDIUM 0xa6 #define READ_12 0xa8 +#define SERVICE_ACTION_OUT_12 0xa9 #define WRITE_12 0xaa -#define READ_MEDIA_SERIAL_NUMBER 0xab +#define SERVICE_ACTION_IN_12 0xab #define WRITE_VERIFY_12 0xae #define VERIFY_12 0xaf #define SEARCH_HIGH_12 0xb0 @@ -107,7 +108,9 @@ typedef unsigned int u32; #define VERIFY_16 0x8f #define SYNCHRONIZE_CACHE_16 0x91 #define WRITE_SAME_16 0x93 -#define SERVICE_ACTION_IN 0x9e +#define SERVICE_ACTION_BIDIRECTIONAL 0x9d +#define SERVICE_ACTION_IN_16 0x9e +#define SERVICE_ACTION_OUT_16 0x9f /* values for service action in */ #define SAI_READ_CAPACITY_16 0x10 #define SAI_GET_LBA_STATUS 0x12 @@ -393,7 +396,7 @@ scsi_trace_parse_cdb(struct trace_seq *p, unsigned char *cdb, int len) return scsi_trace_rw16(p, cdb, len); case UNMAP: return scsi_trace_unmap(p, cdb, len); - case SERVICE_ACTION_IN: + case SERVICE_ACTION_IN_16: return scsi_trace_service_action_in(p, cdb, len); case VARIABLE_LENGTH_CMD: return scsi_trace_varlen(p, cdb, len); diff --git a/tools/lib/util/find_next_bit.c b/tools/lib/util/find_next_bit.c new file mode 100644 index 000000000000..41b44f65a79e --- /dev/null +++ b/tools/lib/util/find_next_bit.c @@ -0,0 +1,89 @@ +/* find_next_bit.c: fallback find next bit implementation + * + * Copied from lib/find_next_bit.c to tools/lib/next_bit.c + * + * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/bitops.h> +#include <asm/types.h> +#include <asm/byteorder.h> + +#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) + +#ifndef find_next_bit +/* + * Find the next set bit in a memory region. + */ +unsigned long find_next_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + const unsigned long *p = addr + BITOP_WORD(offset); + unsigned long result = offset & ~(BITS_PER_LONG-1); + unsigned long tmp; + + if (offset >= size) + return size; + size -= result; + offset %= BITS_PER_LONG; + if (offset) { + tmp = *(p++); + tmp &= (~0UL << offset); + if (size < BITS_PER_LONG) + goto found_first; + if (tmp) + goto found_middle; + size -= BITS_PER_LONG; + result += BITS_PER_LONG; + } + while (size & ~(BITS_PER_LONG-1)) { + if ((tmp = *(p++))) + goto found_middle; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = *p; + +found_first: + tmp &= (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found_middle: + return result + __ffs(tmp); +} +#endif + +#ifndef find_first_bit +/* + * Find the first set bit in a memory region. + */ +unsigned long find_first_bit(const unsigned long *addr, unsigned long size) +{ + const unsigned long *p = addr; + unsigned long result = 0; + unsigned long tmp; + + while (size & ~(BITS_PER_LONG-1)) { + if ((tmp = *(p++))) + goto found; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + + tmp = (*p) & (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found: + return result + __ffs(tmp); +} +#endif diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 717221e98450..40399c3d97d6 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -2,6 +2,8 @@ PERF-CFLAGS PERF-GUI-VARS PERF-VERSION-FILE perf +perf-read-vdso32 +perf-read-vdsox32 perf-help perf-record perf-report diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index fd77d81ea748..0294c57b1f5e 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -38,7 +38,7 @@ OPTIONS --remove=:: Remove specified file from the cache. -M:: ---missing=:: +--missing=:: List missing build ids in the cache for the specified file. -u:: --update:: diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index cbb4f743d921..3e2aec94f806 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -89,6 +89,19 @@ raw encoding of 0x1A8 can be used: You should refer to the processor specific documentation for getting these details. Some of them are referenced in the SEE ALSO section below. +PARAMETERIZED EVENTS +-------------------- + +Some pmu events listed by 'perf-list' will be displayed with '?' in them. For +example: + + hv_gpci/dtbp_ptitc,phys_processor_idx=?/ + +This means that when provided as an event, a value for '?' must +also be supplied. For example: + + perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ... + OPTIONS ------- diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 1d78a4064da4..43310d8661fe 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -12,11 +12,12 @@ SYNOPSIS DESCRIPTION ----------- -"perf mem -t <TYPE> record" runs a command and gathers memory operation data +"perf mem record" runs a command and gathers memory operation data from it, into perf.data. Perf record options are accepted and are passed through. -"perf mem -t <TYPE> report" displays the result. It invokes perf report with the -right set of options to display a memory access profile. +"perf mem report" displays the result. It invokes perf report with the +right set of options to display a memory access profile. By default, loads +and stores are sampled. Use the -t option to limit to loads or stores. Note that on Intel systems the memory latency reported is the use-latency, not the pure load (or store latency). Use latency includes any pipeline @@ -29,7 +30,7 @@ OPTIONS -t:: --type=:: - Select the memory operation type: load or store (default: load) + Select the memory operation type: load or store (default: load,store) -D:: --dump-raw-samples=:: diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 398f8d53bd6d..31e977459c51 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -33,12 +33,27 @@ OPTIONS - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. - - a hardware breakpoint event in the form of '\mem:addr[:access]' + - a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where + 'param1', 'param2', etc are defined as formats for the PMU in + /sys/bus/event_sources/devices/<pmu>/format/*. + + - a symbolically formed event like 'pmu/config=M,config1=N,config3=K/' + + where M, N, K are numbers (in decimal, hex, octal format). Acceptable + values for each of 'config', 'config1' and 'config2' are defined by + corresponding entries in /sys/bus/event_sources/devices/<pmu>/format/* + param1 and param2 are defined as formats for the PMU in: + /sys/bus/event_sources/devices/<pmu>/format/* + + - a hardware breakpoint event in the form of '\mem:addr[/len][:access]' where addr is the address in memory you want to break in. Access is the memory access type (read, write, execute) it can - be passed as follows: '\mem:addr[:[r][w][x]]'. + be passed as follows: '\mem:addr[:[r][w][x]]'. len is the range, + number of bytes from specified addr, which the breakpoint will cover. If you want to profile read-write accesses in 0x1000, just set 'mem:0x1000:rw'. + If you want to profile write accesses in [0x1000~1008), just set + 'mem:0x1000/8:w'. --filter=<filter>:: Event filter. @@ -214,6 +229,12 @@ if combined with -a or -C options. After starting the program, wait msecs before measuring. This is useful to filter out the startup phase of the program, which is often very different. +-I:: +--intr-regs:: +Capture machine state (registers) at interrupt, i.e., on counter overflows for +each sample. List of captured registers depends on the architecture. This option +is off by default. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 0927bf4e6c2a..dd7cccdde498 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -159,7 +159,7 @@ OPTIONS --dump-raw-trace:: Dump raw trace in ASCII. --g [type,min[,limit],order[,key]]:: +-g [type,min[,limit],order[,key][,branch]]:: --call-graph:: Display call chains using type, min percent threshold, optional print limit and order. @@ -177,6 +177,11 @@ OPTIONS - function: compare on functions - address: compare on individual code addresses + branch can be: + - branch: include last branch information in callgraph + when available. Usually more convenient to use --branch-history + for this. + Default: fractal,0.5,callee,function. --children:: @@ -266,6 +271,11 @@ OPTIONS branch stacks and it will automatically switch to the branch view mode, unless --no-branch-stack is used. +--branch-history:: + Add the addresses of sampled taken branches to the callstack. + This allows to examine the path the program took to each sample. + The data collection must have used -b (or -j) and -g. + --objdump=<path>:: Path to objdump binary. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 21494806c0ab..a21eec05bc42 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -125,46 +125,46 @@ OPTIONS is equivalent to: perf script -f trace:<fields> -f sw:<fields> -f hw:<fields> - + i.e., the specified fields apply to all event types if the type string is not given. - + The arguments are processed in the order received. A later usage can reset a prior request. e.g.: - + -f trace: -f comm,tid,time,ip,sym - + The first -f suppresses trace events (field list is ""), but then the second invocation sets the fields to comm,tid,time,ip,sym. In this case a warning is given to the user: - + "Overriding previous field request for all events." - + Alternatively, consider the order: - + -f comm,tid,time,ip,sym -f trace: - + The first -f sets the fields for all events and the second -f suppresses trace events. The user is given a warning message about the override, and the result of the above is that only S/W and H/W events are displayed with the given fields. - + For the 'wildcard' option if a user selected field is invalid for an event type, a message is displayed to the user that the option is ignored for that type. For example: - + $ perf script -f comm,tid,trace 'trace' not valid for hardware events. Ignoring. 'trace' not valid for software events. Ignoring. - + Alternatively, if the type is given an invalid field is specified it is an error. For example: - + perf script -v -f sw:comm,tid,trace 'trace' not valid for software events. - + At this point usage is displayed, and perf-script exits. - + Finally, a user may not set fields to none for all event types. i.e., -f "" is not allowed. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 29ee857c09c6..04e150d83e7d 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -25,10 +25,22 @@ OPTIONS -e:: --event=:: - Select the PMU event. Selection can be a symbolic event name - (use 'perf list' to list all events) or a raw PMU - event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + Select the PMU event. Selection can be: + + - a symbolic event name (use 'perf list' to list all events) + + - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + + - a symbolically formed event like 'pmu/param1=0x3,param2/' where + param1 and param2 are defined as formats for the PMU in + /sys/bus/event_sources/devices/<pmu>/format/* + + - a symbolically formed event like 'pmu/config=M,config1=N,config2=K/' + where M, N, K are numbers (in decimal, hex, octal format). + Acceptable values for each of 'config', 'config1' and 'config2' + parameters are defined by corresponding entries in + /sys/bus/event_sources/devices/<pmu>/format/* -i:: --no-inherit:: diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index d240bb2e5b22..1e8e400b4493 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -18,6 +18,10 @@ OPTIONS --debug verbose # sets verbose = 1 --debug verbose=2 # sets verbose = 2 +--buildid-dir:: + Setup buildid cache directory. It has higher priority than + buildid.dir config file option. + DESCRIPTION ----------- Performance counters for Linux are a new kernel-based subsystem diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 344c4d3d0a4a..fbbfdc39271d 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -4,17 +4,37 @@ tools/lib/traceevent tools/lib/api tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h +tools/lib/util/find_next_bit.c tools/include/asm/bug.h +tools/include/asm-generic/bitops/arch_hweight.h +tools/include/asm-generic/bitops/atomic.h +tools/include/asm-generic/bitops/const_hweight.h +tools/include/asm-generic/bitops/__ffs.h +tools/include/asm-generic/bitops/__fls.h +tools/include/asm-generic/bitops/find.h +tools/include/asm-generic/bitops/fls64.h +tools/include/asm-generic/bitops/fls.h +tools/include/asm-generic/bitops/hweight.h +tools/include/asm-generic/bitops.h +tools/include/linux/bitops.h tools/include/linux/compiler.h -tools/include/linux/hash.h tools/include/linux/export.h +tools/include/linux/hash.h +tools/include/linux/log2.h tools/include/linux/types.h +include/asm-generic/bitops/arch_hweight.h +include/asm-generic/bitops/const_hweight.h +include/asm-generic/bitops/fls64.h +include/asm-generic/bitops/__fls.h +include/asm-generic/bitops/fls.h include/linux/const.h include/linux/perf_event.h include/linux/rbtree.h include/linux/list.h include/linux/hash.h include/linux/stringify.h +lib/find_next_bit.c +lib/hweight.c lib/rbtree.c include/linux/swab.h arch/*/include/asm/unistd*.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 262916f4a377..aa6a50447c32 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -60,6 +60,15 @@ include config/utilities.mak # # Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support # for dwarf backtrace post unwind. +# +# Define NO_PERF_READ_VDSO32 if you do not want to build perf-read-vdso32 +# for reading the 32-bit compatibility VDSO in 64-bit mode +# +# Define NO_PERF_READ_VDSOX32 if you do not want to build perf-read-vdsox32 +# for reading the x32 mode 32-bit compatibility VDSO in 64-bit mode +# +# Define NO_ZLIB if you do not want to support compressed kernel modules + ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(shell pwd))) @@ -171,11 +180,16 @@ $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) -# -# Single 'perf' binary right now: -# PROGRAMS += $(OUTPUT)perf +ifndef NO_PERF_READ_VDSO32 +PROGRAMS += $(OUTPUT)perf-read-vdso32 +endif + +ifndef NO_PERF_READ_VDSOX32 +PROGRAMS += $(OUTPUT)perf-read-vdsox32 +endif + # what 'all' will build and 'install' will install, in perfexecdir ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS) @@ -217,8 +231,19 @@ LIB_H += ../../include/uapi/linux/const.h LIB_H += ../include/linux/hash.h LIB_H += ../../include/linux/stringify.h LIB_H += util/include/linux/bitmap.h -LIB_H += util/include/linux/bitops.h +LIB_H += ../include/linux/bitops.h +LIB_H += ../include/asm-generic/bitops/arch_hweight.h +LIB_H += ../include/asm-generic/bitops/atomic.h +LIB_H += ../include/asm-generic/bitops/const_hweight.h +LIB_H += ../include/asm-generic/bitops/find.h +LIB_H += ../include/asm-generic/bitops/fls64.h +LIB_H += ../include/asm-generic/bitops/fls.h +LIB_H += ../include/asm-generic/bitops/__ffs.h +LIB_H += ../include/asm-generic/bitops/__fls.h +LIB_H += ../include/asm-generic/bitops/hweight.h +LIB_H += ../include/asm-generic/bitops.h LIB_H += ../include/linux/compiler.h +LIB_H += ../include/linux/log2.h LIB_H += util/include/linux/const.h LIB_H += util/include/linux/ctype.h LIB_H += util/include/linux/kernel.h @@ -233,7 +258,6 @@ LIB_H += util/include/linux/linkage.h LIB_H += util/include/asm/asm-offsets.h LIB_H += ../include/asm/bug.h LIB_H += util/include/asm/byteorder.h -LIB_H += util/include/asm/hweight.h LIB_H += util/include/asm/swab.h LIB_H += util/include/asm/system.h LIB_H += util/include/asm/uaccess.h @@ -247,12 +271,14 @@ LIB_H += util/annotate.h LIB_H += util/cache.h LIB_H += util/callchain.h LIB_H += util/build-id.h +LIB_H += util/db-export.h LIB_H += util/debug.h LIB_H += util/pmu.h LIB_H += util/event.h LIB_H += util/evsel.h LIB_H += util/evlist.h LIB_H += util/exec_cmd.h +LIB_H += util/find-vdso-map.c LIB_H += util/levenshtein.h LIB_H += util/machine.h LIB_H += util/map.h @@ -304,6 +330,7 @@ LIB_H += ui/util.h LIB_H += ui/ui.h LIB_H += util/data.h LIB_H += util/kvm-stat.h +LIB_H += util/thread-stack.h LIB_OBJS += $(OUTPUT)util/abspath.o LIB_OBJS += $(OUTPUT)util/alias.o @@ -311,12 +338,14 @@ LIB_OBJS += $(OUTPUT)util/annotate.o LIB_OBJS += $(OUTPUT)util/build-id.o LIB_OBJS += $(OUTPUT)util/config.o LIB_OBJS += $(OUTPUT)util/ctype.o +LIB_OBJS += $(OUTPUT)util/db-export.o LIB_OBJS += $(OUTPUT)util/pmu.o LIB_OBJS += $(OUTPUT)util/environment.o LIB_OBJS += $(OUTPUT)util/event.o LIB_OBJS += $(OUTPUT)util/evlist.o LIB_OBJS += $(OUTPUT)util/evsel.o LIB_OBJS += $(OUTPUT)util/exec_cmd.o +LIB_OBJS += $(OUTPUT)util/find_next_bit.o LIB_OBJS += $(OUTPUT)util/help.o LIB_OBJS += $(OUTPUT)util/kallsyms.o LIB_OBJS += $(OUTPUT)util/levenshtein.o @@ -380,6 +409,7 @@ LIB_OBJS += $(OUTPUT)util/srcline.o LIB_OBJS += $(OUTPUT)util/data.o LIB_OBJS += $(OUTPUT)util/tsc.o LIB_OBJS += $(OUTPUT)util/cloexec.o +LIB_OBJS += $(OUTPUT)util/thread-stack.o LIB_OBJS += $(OUTPUT)ui/setup.o LIB_OBJS += $(OUTPUT)ui/helpline.o @@ -434,12 +464,13 @@ BUILTIN_OBJS += $(OUTPUT)builtin-bench.o # Benchmark modules BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o -ifeq ($(RAW_ARCH),x86_64) +ifeq ($(ARCH), x86) +ifeq ($(IS_64_BIT), 1) BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o endif +endif BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o -BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o @@ -478,8 +509,6 @@ ifneq ($(OUTPUT),) endif ifdef NO_LIBELF -EXTLIBS := $(filter-out -lelf,$(EXTLIBS)) - # Remove ELF/DWARF dependent codes LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS)) LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS)) @@ -568,6 +597,10 @@ ifndef NO_LIBNUMA BUILTIN_OBJS += $(OUTPUT)bench/numa.o endif +ifndef NO_ZLIB + LIB_OBJS += $(OUTPUT)util/zlib.o +endif + ifdef ASCIIDOC8 export ASCIIDOC8 endif @@ -714,6 +747,12 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +$(OUTPUT)util/hweight.o: ../../lib/hweight.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + +$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $< @@ -732,6 +771,16 @@ $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Uti $(OUTPUT)perf-%: %.o $(PERFLIBS) $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS) +ifndef NO_PERF_READ_VDSO32 +$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-vdso-map.c + $(QUIET_CC)$(CC) -m32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c +endif + +ifndef NO_PERF_READ_VDSOX32 +$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c + $(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c +endif + $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H) $(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) @@ -876,6 +925,14 @@ install-bin: all install-gtk $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \ $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \ $(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace' +ifndef NO_PERF_READ_VDSO32 + $(call QUIET_INSTALL, perf-read-vdso32) \ + $(INSTALL) $(OUTPUT)perf-read-vdso32 '$(DESTDIR_SQ)$(bindir_SQ)'; +endif +ifndef NO_PERF_READ_VDSOX32 + $(call QUIET_INSTALL, perf-read-vdsox32) \ + $(INSTALL) $(OUTPUT)perf-read-vdsox32 '$(DESTDIR_SQ)$(bindir_SQ)'; +endif $(call QUIET_INSTALL, libexec) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' $(call QUIET_INSTALL, perf-archive) \ @@ -928,7 +985,7 @@ config-clean: clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS) - $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf + $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(python-clean) diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index d73ef8bb08c7..0c370f81e002 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -103,7 +103,7 @@ static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc) return NULL; } - result = dwarf_cfi_addrframe(cfi, pc, &frame); + result = dwarf_cfi_addrframe(cfi, pc-bias, &frame); if (result) { pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); return NULL; @@ -128,7 +128,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc) return NULL; } - result = dwarf_cfi_addrframe(cfi, pc, &frame); + result = dwarf_cfi_addrframe(cfi, pc-bias, &frame); if (result) { pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); return NULL; @@ -145,7 +145,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc) * yet used) * -1 in case of errors */ -static int check_return_addr(const char *exec_file, Dwarf_Addr pc) +static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc) { int rc = -1; Dwfl *dwfl; @@ -155,16 +155,31 @@ static int check_return_addr(const char *exec_file, Dwarf_Addr pc) Dwarf_Addr start = pc; Dwarf_Addr end = pc; bool signalp; + const char *exec_file = dso->long_name; - dwfl = dwfl_begin(&offline_callbacks); - if (!dwfl) { - pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1)); - return -1; - } + dwfl = dso->dwfl; - if (dwfl_report_offline(dwfl, "", exec_file, -1) == NULL) { - pr_debug("dwfl_report_offline() failed %s\n", dwarf_errmsg(-1)); - goto out; + if (!dwfl) { + dwfl = dwfl_begin(&offline_callbacks); + if (!dwfl) { + pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1)); + return -1; + } + + mod = dwfl_report_elf(dwfl, exec_file, exec_file, -1, + map_start, false); + if (!mod) { + pr_debug("dwfl_report_elf() failed %s\n", + dwarf_errmsg(-1)); + /* + * We normally cache the DWARF debug info and never + * call dwfl_end(). But to prevent fd leak, free in + * case of error. + */ + dwfl_end(dwfl); + goto out; + } + dso->dwfl = dwfl; } mod = dwfl_addrmodule(dwfl, pc); @@ -194,7 +209,6 @@ static int check_return_addr(const char *exec_file, Dwarf_Addr pc) rc = check_return_reg(ra_regno, frame); out: - dwfl_end(dwfl); return rc; } @@ -221,8 +235,7 @@ out: * index: of callchain entry that needs to be ignored (if any) * -1 if no entry needs to be ignored or in case of errors */ -int arch_skip_callchain_idx(struct machine *machine, struct thread *thread, - struct ip_callchain *chain) +int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) { struct addr_location al; struct dso *dso = NULL; @@ -235,7 +248,7 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread, ip = chain->ips[2]; - thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER, + thread__find_addr_location(thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); if (al.map) @@ -246,10 +259,10 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread, return skip_slot; } - rc = check_return_addr(dso->long_name, ip); + rc = check_return_addr(dso, al.map->start, ip); - pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n", - dso->long_name, chain->nr, ip, rc); + pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n", + dso->long_name, al.sym->name, ip, rc); if (rc == 0) { /* diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h index 71f2844cf97f..7ed22ff1e1ac 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -68,4 +68,17 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak val, opflags); } +#ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP +#include <pthread.h> +static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr, + size_t cpusetsize, + cpu_set_t *cpuset) +{ + attr = attr; + cpusetsize = cpusetsize; + cpuset = cpuset; + return 0; +} +#endif + #endif /* _FUTEX_H */ diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h index d66ab799b35f..8c0c1a2770c8 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h @@ -1,12 +1,12 @@ -MEMCPY_FN(__memcpy, +MEMCPY_FN(memcpy_orig, "x86-64-unrolled", "unrolled memcpy() in arch/x86/lib/memcpy_64.S") -MEMCPY_FN(memcpy_c, +MEMCPY_FN(__memcpy, "x86-64-movsq", "movsq-based memcpy() in arch/x86/lib/memcpy_64.S") -MEMCPY_FN(memcpy_c_e, +MEMCPY_FN(memcpy_erms, "x86-64-movsb", "movsb-based memcpy() in arch/x86/lib/memcpy_64.S") diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index fcd9cf00600a..e4c2c30143b9 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -1,8 +1,6 @@ #define memcpy MEMCPY /* don't hide glibc's memcpy() */ #define altinstr_replacement text #define globl p2align 4; .globl -#define Lmemcpy_c globl memcpy_c; memcpy_c -#define Lmemcpy_c_e globl memcpy_c_e; memcpy_c_e #include "../../../arch/x86/lib/memcpy_64.S" /* * We need to provide note.GNU-stack section, saying that we want diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 2465141b554b..d3dfb7936dcd 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -13,6 +13,7 @@ #include "../util/cloexec.h" #include "bench.h" #include "mem-memcpy-arch.h" +#include "mem-memset-arch.h" #include <stdio.h> #include <stdlib.h> @@ -35,7 +36,7 @@ static const struct option options[] = { "Specify length of memory to copy. " "Available units: B, KB, MB, GB and TB (upper and lower)"), OPT_STRING('r', "routine", &routine, "default", - "Specify routine to copy"), + "Specify routine to copy, \"all\" runs all available routines"), OPT_INTEGER('i', "iterations", &iterations, "repeat memcpy() invocation this number of times"), OPT_BOOLEAN('c', "cycle", &use_cycle, @@ -48,20 +49,24 @@ static const struct option options[] = { }; typedef void *(*memcpy_t)(void *, const void *, size_t); +typedef void *(*memset_t)(void *, int, size_t); struct routine { const char *name; const char *desc; - memcpy_t fn; + union { + memcpy_t memcpy; + memset_t memset; + } fn; }; -struct routine routines[] = { - { "default", - "Default memcpy() provided by glibc", - memcpy }, +struct routine memcpy_routines[] = { + { .name = "default", + .desc = "Default memcpy() provided by glibc", + .fn.memcpy = memcpy }, #ifdef HAVE_ARCH_X86_64_SUPPORT -#define MEMCPY_FN(fn, name, desc) { name, desc, fn }, +#define MEMCPY_FN(_fn, _name, _desc) {.name = _name, .desc = _desc, .fn.memcpy = _fn}, #include "mem-memcpy-x86-64-asm-def.h" #undef MEMCPY_FN @@ -69,7 +74,7 @@ struct routine routines[] = { { NULL, NULL, - NULL } + {NULL} } }; static const char * const bench_mem_memcpy_usage[] = { @@ -110,63 +115,6 @@ static double timeval2double(struct timeval *ts) (double)ts->tv_usec / (double)1000000; } -static void alloc_mem(void **dst, void **src, size_t length) -{ - *dst = zalloc(length); - if (!*dst) - die("memory allocation failed - maybe length is too large?\n"); - - *src = zalloc(length); - if (!*src) - die("memory allocation failed - maybe length is too large?\n"); - /* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */ - memset(*src, 0, length); -} - -static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault) -{ - u64 cycle_start = 0ULL, cycle_end = 0ULL; - void *src = NULL, *dst = NULL; - int i; - - alloc_mem(&src, &dst, len); - - if (prefault) - fn(dst, src, len); - - cycle_start = get_cycle(); - for (i = 0; i < iterations; ++i) - fn(dst, src, len); - cycle_end = get_cycle(); - - free(src); - free(dst); - return cycle_end - cycle_start; -} - -static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault) -{ - struct timeval tv_start, tv_end, tv_diff; - void *src = NULL, *dst = NULL; - int i; - - alloc_mem(&src, &dst, len); - - if (prefault) - fn(dst, src, len); - - BUG_ON(gettimeofday(&tv_start, NULL)); - for (i = 0; i < iterations; ++i) - fn(dst, src, len); - BUG_ON(gettimeofday(&tv_end, NULL)); - - timersub(&tv_end, &tv_start, &tv_diff); - - free(src); - free(dst); - return (double)((double)len / timeval2double(&tv_diff)); -} - #define pf (no_prefault ? 0 : 1) #define print_bps(x) do { \ @@ -180,52 +128,23 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault) printf(" %14lf GB/Sec", x / K / K / K); \ } while (0) -int bench_mem_memcpy(int argc, const char **argv, - const char *prefix __maybe_unused) +struct bench_mem_info { + const struct routine *routines; + u64 (*do_cycle)(const struct routine *r, size_t len, bool prefault); + double (*do_gettimeofday)(const struct routine *r, size_t len, bool prefault); + const char *const *usage; +}; + +static void __bench_mem_routine(struct bench_mem_info *info, int r_idx, size_t len, double totallen) { - int i; - size_t len; + const struct routine *r = &info->routines[r_idx]; double result_bps[2]; u64 result_cycle[2]; - argc = parse_options(argc, argv, options, - bench_mem_memcpy_usage, 0); - - if (no_prefault && only_prefault) { - fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n"); - return 1; - } - - if (use_cycle) - init_cycle(); - - len = (size_t)perf_atoll((char *)length_str); - result_cycle[0] = result_cycle[1] = 0ULL; result_bps[0] = result_bps[1] = 0.0; - if ((s64)len <= 0) { - fprintf(stderr, "Invalid length:%s\n", length_str); - return 1; - } - - /* same to without specifying either of prefault and no-prefault */ - if (only_prefault && no_prefault) - only_prefault = no_prefault = false; - - for (i = 0; routines[i].name; i++) { - if (!strcmp(routines[i].name, routine)) - break; - } - if (!routines[i].name) { - printf("Unknown routine:%s\n", routine); - printf("Available routines...\n"); - for (i = 0; routines[i].name; i++) { - printf("\t%s ... %s\n", - routines[i].name, routines[i].desc); - } - return 1; - } + printf("Routine %s (%s)\n", r->name, r->desc); if (bench_format == BENCH_FORMAT_DEFAULT) printf("# Copying %s Bytes ...\n\n", length_str); @@ -233,28 +152,17 @@ int bench_mem_memcpy(int argc, const char **argv, if (!only_prefault && !no_prefault) { /* show both of results */ if (use_cycle) { - result_cycle[0] = - do_memcpy_cycle(routines[i].fn, len, false); - result_cycle[1] = - do_memcpy_cycle(routines[i].fn, len, true); + result_cycle[0] = info->do_cycle(r, len, false); + result_cycle[1] = info->do_cycle(r, len, true); } else { - result_bps[0] = - do_memcpy_gettimeofday(routines[i].fn, - len, false); - result_bps[1] = - do_memcpy_gettimeofday(routines[i].fn, - len, true); + result_bps[0] = info->do_gettimeofday(r, len, false); + result_bps[1] = info->do_gettimeofday(r, len, true); } } else { - if (use_cycle) { - result_cycle[pf] = - do_memcpy_cycle(routines[i].fn, - len, only_prefault); - } else { - result_bps[pf] = - do_memcpy_gettimeofday(routines[i].fn, - len, only_prefault); - } + if (use_cycle) + result_cycle[pf] = info->do_cycle(r, len, only_prefault); + else + result_bps[pf] = info->do_gettimeofday(r, len, only_prefault); } switch (bench_format) { @@ -263,10 +171,10 @@ int bench_mem_memcpy(int argc, const char **argv, if (use_cycle) { printf(" %14lf Cycle/Byte\n", (double)result_cycle[0] - / (double)len); + / totallen); printf(" %14lf Cycle/Byte (with prefault)\n", (double)result_cycle[1] - / (double)len); + / totallen); } else { print_bps(result_bps[0]); printf("\n"); @@ -277,7 +185,7 @@ int bench_mem_memcpy(int argc, const char **argv, if (use_cycle) { printf(" %14lf Cycle/Byte", (double)result_cycle[pf] - / (double)len); + / totallen); } else print_bps(result_bps[pf]); @@ -288,8 +196,8 @@ int bench_mem_memcpy(int argc, const char **argv, if (!only_prefault && !no_prefault) { if (use_cycle) { printf("%lf %lf\n", - (double)result_cycle[0] / (double)len, - (double)result_cycle[1] / (double)len); + (double)result_cycle[0] / totallen, + (double)result_cycle[1] / totallen); } else { printf("%lf %lf\n", result_bps[0], result_bps[1]); @@ -297,7 +205,7 @@ int bench_mem_memcpy(int argc, const char **argv, } else { if (use_cycle) { printf("%lf\n", (double)result_cycle[pf] - / (double)len); + / totallen); } else printf("%lf\n", result_bps[pf]); } @@ -307,6 +215,220 @@ int bench_mem_memcpy(int argc, const char **argv, die("unknown format: %d\n", bench_format); break; } +} + +static int bench_mem_common(int argc, const char **argv, + const char *prefix __maybe_unused, + struct bench_mem_info *info) +{ + int i; + size_t len; + double totallen; + + argc = parse_options(argc, argv, options, + info->usage, 0); + + if (no_prefault && only_prefault) { + fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n"); + return 1; + } + + if (use_cycle) + init_cycle(); + + len = (size_t)perf_atoll((char *)length_str); + totallen = (double)len * iterations; + + if ((s64)len <= 0) { + fprintf(stderr, "Invalid length:%s\n", length_str); + return 1; + } + + /* same to without specifying either of prefault and no-prefault */ + if (only_prefault && no_prefault) + only_prefault = no_prefault = false; + + if (!strncmp(routine, "all", 3)) { + for (i = 0; info->routines[i].name; i++) + __bench_mem_routine(info, i, len, totallen); + return 0; + } + + for (i = 0; info->routines[i].name; i++) { + if (!strcmp(info->routines[i].name, routine)) + break; + } + if (!info->routines[i].name) { + printf("Unknown routine:%s\n", routine); + printf("Available routines...\n"); + for (i = 0; info->routines[i].name; i++) { + printf("\t%s ... %s\n", + info->routines[i].name, info->routines[i].desc); + } + return 1; + } + + __bench_mem_routine(info, i, len, totallen); return 0; } + +static void memcpy_alloc_mem(void **dst, void **src, size_t length) +{ + *dst = zalloc(length); + if (!*dst) + die("memory allocation failed - maybe length is too large?\n"); + + *src = zalloc(length); + if (!*src) + die("memory allocation failed - maybe length is too large?\n"); + /* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */ + memset(*src, 0, length); +} + +static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault) +{ + u64 cycle_start = 0ULL, cycle_end = 0ULL; + void *src = NULL, *dst = NULL; + memcpy_t fn = r->fn.memcpy; + int i; + + memcpy_alloc_mem(&dst, &src, len); + + if (prefault) + fn(dst, src, len); + + cycle_start = get_cycle(); + for (i = 0; i < iterations; ++i) + fn(dst, src, len); + cycle_end = get_cycle(); + + free(src); + free(dst); + return cycle_end - cycle_start; +} + +static double do_memcpy_gettimeofday(const struct routine *r, size_t len, + bool prefault) +{ + struct timeval tv_start, tv_end, tv_diff; + memcpy_t fn = r->fn.memcpy; + void *src = NULL, *dst = NULL; + int i; + + memcpy_alloc_mem(&dst, &src, len); + + if (prefault) + fn(dst, src, len); + + BUG_ON(gettimeofday(&tv_start, NULL)); + for (i = 0; i < iterations; ++i) + fn(dst, src, len); + BUG_ON(gettimeofday(&tv_end, NULL)); + + timersub(&tv_end, &tv_start, &tv_diff); + + free(src); + free(dst); + return (double)(((double)len * iterations) / timeval2double(&tv_diff)); +} + +int bench_mem_memcpy(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + struct bench_mem_info info = { + .routines = memcpy_routines, + .do_cycle = do_memcpy_cycle, + .do_gettimeofday = do_memcpy_gettimeofday, + .usage = bench_mem_memcpy_usage, + }; + + return bench_mem_common(argc, argv, prefix, &info); +} + +static void memset_alloc_mem(void **dst, size_t length) +{ + *dst = zalloc(length); + if (!*dst) + die("memory allocation failed - maybe length is too large?\n"); +} + +static u64 do_memset_cycle(const struct routine *r, size_t len, bool prefault) +{ + u64 cycle_start = 0ULL, cycle_end = 0ULL; + memset_t fn = r->fn.memset; + void *dst = NULL; + int i; + + memset_alloc_mem(&dst, len); + + if (prefault) + fn(dst, -1, len); + + cycle_start = get_cycle(); + for (i = 0; i < iterations; ++i) + fn(dst, i, len); + cycle_end = get_cycle(); + + free(dst); + return cycle_end - cycle_start; +} + +static double do_memset_gettimeofday(const struct routine *r, size_t len, + bool prefault) +{ + struct timeval tv_start, tv_end, tv_diff; + memset_t fn = r->fn.memset; + void *dst = NULL; + int i; + + memset_alloc_mem(&dst, len); + + if (prefault) + fn(dst, -1, len); + + BUG_ON(gettimeofday(&tv_start, NULL)); + for (i = 0; i < iterations; ++i) + fn(dst, i, len); + BUG_ON(gettimeofday(&tv_end, NULL)); + + timersub(&tv_end, &tv_start, &tv_diff); + + free(dst); + return (double)(((double)len * iterations) / timeval2double(&tv_diff)); +} + +static const char * const bench_mem_memset_usage[] = { + "perf bench mem memset <options>", + NULL +}; + +static const struct routine memset_routines[] = { + { .name ="default", + .desc = "Default memset() provided by glibc", + .fn.memset = memset }, +#ifdef HAVE_ARCH_X86_64_SUPPORT + +#define MEMSET_FN(_fn, _name, _desc) { .name = _name, .desc = _desc, .fn.memset = _fn }, +#include "mem-memset-x86-64-asm-def.h" +#undef MEMSET_FN + +#endif + + { .name = NULL, + .desc = NULL, + .fn.memset = NULL } +}; + +int bench_mem_memset(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + struct bench_mem_info info = { + .routines = memset_routines, + .do_cycle = do_memset_cycle, + .do_gettimeofday = do_memset_gettimeofday, + .usage = bench_mem_memset_usage, + }; + + return bench_mem_common(argc, argv, prefix, &info); +} diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h index a71dff97c1f5..f02d028771d9 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h @@ -1,12 +1,12 @@ -MEMSET_FN(__memset, +MEMSET_FN(memset_orig, "x86-64-unrolled", "unrolled memset() in arch/x86/lib/memset_64.S") -MEMSET_FN(memset_c, +MEMSET_FN(__memset, "x86-64-stosq", "movsq-based memset() in arch/x86/lib/memset_64.S") -MEMSET_FN(memset_c_e, +MEMSET_FN(memset_erms, "x86-64-stosb", "movsb-based memset() in arch/x86/lib/memset_64.S") diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index 9e5af89ed13a..de278784c866 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,8 +1,6 @@ #define memset MEMSET /* don't hide glibc's memset() */ #define altinstr_replacement text #define globl p2align 4; .globl -#define Lmemset_c globl memset_c; memset_c -#define Lmemset_c_e globl memset_c_e; memset_c_e #include "../../../arch/x86/lib/memset_64.S" /* diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c deleted file mode 100644 index 75fc3e65fb2a..000000000000 --- a/tools/perf/bench/mem-memset.c +++ /dev/null @@ -1,304 +0,0 @@ -/* - * mem-memset.c - * - * memset: Simple memory set in various ways - * - * Trivial clone of mem-memcpy.c. - */ - -#include "../perf.h" -#include "../util/util.h" -#include "../util/parse-options.h" -#include "../util/header.h" -#include "../util/cloexec.h" -#include "bench.h" -#include "mem-memset-arch.h" - -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <sys/time.h> -#include <errno.h> - -#define K 1024 - -static const char *length_str = "1MB"; -static const char *routine = "default"; -static int iterations = 1; -static bool use_cycle; -static int cycle_fd; -static bool only_prefault; -static bool no_prefault; - -static const struct option options[] = { - OPT_STRING('l', "length", &length_str, "1MB", - "Specify length of memory to set. " - "Available units: B, KB, MB, GB and TB (upper and lower)"), - OPT_STRING('r', "routine", &routine, "default", - "Specify routine to set"), - OPT_INTEGER('i', "iterations", &iterations, - "repeat memset() invocation this number of times"), - OPT_BOOLEAN('c', "cycle", &use_cycle, - "Use cycles event instead of gettimeofday() for measuring"), - OPT_BOOLEAN('o', "only-prefault", &only_prefault, - "Show only the result with page faults before memset()"), - OPT_BOOLEAN('n', "no-prefault", &no_prefault, - "Show only the result without page faults before memset()"), - OPT_END() -}; - -typedef void *(*memset_t)(void *, int, size_t); - -struct routine { - const char *name; - const char *desc; - memset_t fn; -}; - -static const struct routine routines[] = { - { "default", - "Default memset() provided by glibc", - memset }, -#ifdef HAVE_ARCH_X86_64_SUPPORT - -#define MEMSET_FN(fn, name, desc) { name, desc, fn }, -#include "mem-memset-x86-64-asm-def.h" -#undef MEMSET_FN - -#endif - - { NULL, - NULL, - NULL } -}; - -static const char * const bench_mem_memset_usage[] = { - "perf bench mem memset <options>", - NULL -}; - -static struct perf_event_attr cycle_attr = { - .type = PERF_TYPE_HARDWARE, - .config = PERF_COUNT_HW_CPU_CYCLES -}; - -static void init_cycle(void) -{ - cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, - perf_event_open_cloexec_flag()); - - if (cycle_fd < 0 && errno == ENOSYS) - die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); - else - BUG_ON(cycle_fd < 0); -} - -static u64 get_cycle(void) -{ - int ret; - u64 clk; - - ret = read(cycle_fd, &clk, sizeof(u64)); - BUG_ON(ret != sizeof(u64)); - - return clk; -} - -static double timeval2double(struct timeval *ts) -{ - return (double)ts->tv_sec + - (double)ts->tv_usec / (double)1000000; -} - -static void alloc_mem(void **dst, size_t length) -{ - *dst = zalloc(length); - if (!*dst) - die("memory allocation failed - maybe length is too large?\n"); -} - -static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault) -{ - u64 cycle_start = 0ULL, cycle_end = 0ULL; - void *dst = NULL; - int i; - - alloc_mem(&dst, len); - - if (prefault) - fn(dst, -1, len); - - cycle_start = get_cycle(); - for (i = 0; i < iterations; ++i) - fn(dst, i, len); - cycle_end = get_cycle(); - - free(dst); - return cycle_end - cycle_start; -} - -static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault) -{ - struct timeval tv_start, tv_end, tv_diff; - void *dst = NULL; - int i; - - alloc_mem(&dst, len); - - if (prefault) - fn(dst, -1, len); - - BUG_ON(gettimeofday(&tv_start, NULL)); - for (i = 0; i < iterations; ++i) - fn(dst, i, len); - BUG_ON(gettimeofday(&tv_end, NULL)); - - timersub(&tv_end, &tv_start, &tv_diff); - - free(dst); - return (double)((double)len / timeval2double(&tv_diff)); -} - -#define pf (no_prefault ? 0 : 1) - -#define print_bps(x) do { \ - if (x < K) \ - printf(" %14lf B/Sec", x); \ - else if (x < K * K) \ - printf(" %14lfd KB/Sec", x / K); \ - else if (x < K * K * K) \ - printf(" %14lf MB/Sec", x / K / K); \ - else \ - printf(" %14lf GB/Sec", x / K / K / K); \ - } while (0) - -int bench_mem_memset(int argc, const char **argv, - const char *prefix __maybe_unused) -{ - int i; - size_t len; - double result_bps[2]; - u64 result_cycle[2]; - - argc = parse_options(argc, argv, options, - bench_mem_memset_usage, 0); - - if (no_prefault && only_prefault) { - fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n"); - return 1; - } - - if (use_cycle) - init_cycle(); - - len = (size_t)perf_atoll((char *)length_str); - - result_cycle[0] = result_cycle[1] = 0ULL; - result_bps[0] = result_bps[1] = 0.0; - - if ((s64)len <= 0) { - fprintf(stderr, "Invalid length:%s\n", length_str); - return 1; - } - - /* same to without specifying either of prefault and no-prefault */ - if (only_prefault && no_prefault) - only_prefault = no_prefault = false; - - for (i = 0; routines[i].name; i++) { - if (!strcmp(routines[i].name, routine)) - break; - } - if (!routines[i].name) { - printf("Unknown routine:%s\n", routine); - printf("Available routines...\n"); - for (i = 0; routines[i].name; i++) { - printf("\t%s ... %s\n", - routines[i].name, routines[i].desc); - } - return 1; - } - - if (bench_format == BENCH_FORMAT_DEFAULT) - printf("# Copying %s Bytes ...\n\n", length_str); - - if (!only_prefault && !no_prefault) { - /* show both of results */ - if (use_cycle) { - result_cycle[0] = - do_memset_cycle(routines[i].fn, len, false); - result_cycle[1] = - do_memset_cycle(routines[i].fn, len, true); - } else { - result_bps[0] = - do_memset_gettimeofday(routines[i].fn, - len, false); - result_bps[1] = - do_memset_gettimeofday(routines[i].fn, - len, true); - } - } else { - if (use_cycle) { - result_cycle[pf] = - do_memset_cycle(routines[i].fn, - len, only_prefault); - } else { - result_bps[pf] = - do_memset_gettimeofday(routines[i].fn, - len, only_prefault); - } - } - - switch (bench_format) { - case BENCH_FORMAT_DEFAULT: - if (!only_prefault && !no_prefault) { - if (use_cycle) { - printf(" %14lf Cycle/Byte\n", - (double)result_cycle[0] - / (double)len); - printf(" %14lf Cycle/Byte (with prefault)\n ", - (double)result_cycle[1] - / (double)len); - } else { - print_bps(result_bps[0]); - printf("\n"); - print_bps(result_bps[1]); - printf(" (with prefault)\n"); - } - } else { - if (use_cycle) { - printf(" %14lf Cycle/Byte", - (double)result_cycle[pf] - / (double)len); - } else - print_bps(result_bps[pf]); - - printf("%s\n", only_prefault ? " (with prefault)" : ""); - } - break; - case BENCH_FORMAT_SIMPLE: - if (!only_prefault && !no_prefault) { - if (use_cycle) { - printf("%lf %lf\n", - (double)result_cycle[0] / (double)len, - (double)result_cycle[1] / (double)len); - } else { - printf("%lf %lf\n", - result_bps[0], result_bps[1]); - } - } else { - if (use_cycle) { - printf("%lf\n", (double)result_cycle[pf] - / (double)len); - } else - printf("%lf\n", result_bps[pf]); - } - break; - default: - /* reaching this means there's some disaster: */ - die("unknown format: %d\n", bench_format); - break; - } - - return 0; -} diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 07a8d7646a15..005cc283790c 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -19,12 +19,12 @@ #include <stdlib.h> #include <signal.h> #include <sys/wait.h> -#include <linux/unistd.h> #include <string.h> #include <errno.h> #include <assert.h> #include <sys/time.h> #include <sys/types.h> +#include <sys/syscall.h> #include <pthread.h> diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index e7417fe97a97..747f86103599 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -232,7 +232,7 @@ static int __cmd_annotate(struct perf_annotate *ann) if (nr_samples > 0) { total_nr_samples += nr_samples; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (symbol_conf.event_group && !perf_evsel__is_group_leader(pos)) diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 70385756da63..50e6b66aea1f 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -236,10 +236,10 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) if (errno == ENOENT) return false; - pr_warning("Problems with %s file, consider removing it from the cache\n", + pr_warning("Problems with %s file, consider removing it from the cache\n", filename); } else if (memcmp(dso->build_id, build_id, sizeof(dso->build_id))) { - pr_warning("Problems with %s file, consider removing it from the cache\n", + pr_warning("Problems with %s file, consider removing it from the cache\n", filename); } @@ -285,12 +285,11 @@ int cmd_buildid_cache(int argc, const char **argv, struct str_node *pos; int ret = 0; bool force = false; - char debugdir[PATH_MAX]; char const *add_name_list_str = NULL, *remove_name_list_str = NULL, *missing_filename = NULL, *update_name_list_str = NULL, - *kcore_filename; + *kcore_filename = NULL; char sbuf[STRERR_BUFSIZE]; struct perf_data_file file = { @@ -335,13 +334,11 @@ int cmd_buildid_cache(int argc, const char **argv, setup_pager(); - snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); - if (add_name_list_str) { list = strlist__new(true, add_name_list_str); if (list) { strlist__for_each(pos, list) - if (build_id_cache__add_file(pos->s, debugdir)) { + if (build_id_cache__add_file(pos->s, buildid_dir)) { if (errno == EEXIST) { pr_debug("%s already in the cache\n", pos->s); @@ -359,7 +356,7 @@ int cmd_buildid_cache(int argc, const char **argv, list = strlist__new(true, remove_name_list_str); if (list) { strlist__for_each(pos, list) - if (build_id_cache__remove_file(pos->s, debugdir)) { + if (build_id_cache__remove_file(pos->s, buildid_dir)) { if (errno == ENOENT) { pr_debug("%s wasn't in the cache\n", pos->s); @@ -380,7 +377,7 @@ int cmd_buildid_cache(int argc, const char **argv, list = strlist__new(true, update_name_list_str); if (list) { strlist__for_each(pos, list) - if (build_id_cache__update_file(pos->s, debugdir)) { + if (build_id_cache__update_file(pos->s, buildid_dir)) { if (errno == ENOENT) { pr_debug("%s wasn't in the cache\n", pos->s); @@ -395,7 +392,7 @@ int cmd_buildid_cache(int argc, const char **argv, } if (kcore_filename && - build_id_cache__add_kcore(kcore_filename, debugdir, force)) + build_id_cache__add_kcore(kcore_filename, buildid_dir, force)) pr_warning("Couldn't add %s\n", kcore_filename); out: diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 25114c9a6801..74aada554b12 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -357,6 +357,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, static struct perf_tool tool = { .sample = diff__process_sample_event, .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .exit = perf_event__process_exit, .fork = perf_event__process_fork, @@ -389,6 +390,15 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist) } } +static struct data__file *fmt_to_data_file(struct perf_hpp_fmt *fmt) +{ + struct diff_hpp_fmt *dfmt = container_of(fmt, struct diff_hpp_fmt, fmt); + void *ptr = dfmt - dfmt->idx; + struct data__file *d = container_of(ptr, struct data__file, fmt); + + return d; +} + static struct hist_entry* get_pair_data(struct hist_entry *he, struct data__file *d) { @@ -406,8 +416,7 @@ get_pair_data(struct hist_entry *he, struct data__file *d) static struct hist_entry* get_pair_fmt(struct hist_entry *he, struct diff_hpp_fmt *dfmt) { - void *ptr = dfmt - dfmt->idx; - struct data__file *d = container_of(ptr, struct data__file, fmt); + struct data__file *d = fmt_to_data_file(&dfmt->fmt); return get_pair_data(he, d); } @@ -429,7 +438,7 @@ static void hists__baseline_only(struct hists *hists) next = rb_next(&he->rb_node_in); if (!hist_entry__next_pair(he)) { rb_erase(&he->rb_node_in, root); - hist_entry__free(he); + hist_entry__delete(he); } } } @@ -447,26 +456,30 @@ static void hists__precompute(struct hists *hists) next = rb_first(root); while (next != NULL) { struct hist_entry *he, *pair; + struct data__file *d; + int i; he = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&he->rb_node_in); - pair = get_pair_data(he, &data__files[sort_compute]); - if (!pair) - continue; + data__for_each_file_new(i, d) { + pair = get_pair_data(he, d); + if (!pair) + continue; - switch (compute) { - case COMPUTE_DELTA: - compute_delta(he, pair); - break; - case COMPUTE_RATIO: - compute_ratio(he, pair); - break; - case COMPUTE_WEIGHTED_DIFF: - compute_wdiff(he, pair); - break; - default: - BUG_ON(1); + switch (compute) { + case COMPUTE_DELTA: + compute_delta(he, pair); + break; + case COMPUTE_RATIO: + compute_ratio(he, pair); + break; + case COMPUTE_WEIGHTED_DIFF: + compute_wdiff(he, pair); + break; + default: + BUG_ON(1); + } } } } @@ -516,7 +529,7 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, static int64_t hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, - int c) + int c, int sort_idx) { bool pairs_left = hist_entry__has_pairs(left); bool pairs_right = hist_entry__has_pairs(right); @@ -528,8 +541,8 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, if (!pairs_left || !pairs_right) return pairs_left ? -1 : 1; - p_left = get_pair_data(left, &data__files[sort_compute]); - p_right = get_pair_data(right, &data__files[sort_compute]); + p_left = get_pair_data(left, &data__files[sort_idx]); + p_right = get_pair_data(right, &data__files[sort_idx]); if (!p_left && !p_right) return 0; @@ -544,55 +557,103 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, return __hist_entry__cmp_compute(p_left, p_right, c); } -static void insert_hist_entry_by_compute(struct rb_root *root, - struct hist_entry *he, - int c) +static int64_t +hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right, + int c, int sort_idx) { - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct hist_entry *iter; - - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); - if (hist_entry__cmp_compute(he, iter, c) < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; + struct hist_entry *p_right, *p_left; + + p_left = get_pair_data(left, &data__files[sort_idx]); + p_right = get_pair_data(right, &data__files[sort_idx]); + + if (!p_left && !p_right) + return 0; + + if (!p_left || !p_right) + return p_left ? -1 : 1; + + if (c != COMPUTE_DELTA) { + /* + * The delta can be computed without the baseline, but + * others are not. Put those entries which have no + * values below. + */ + if (left->dummy && right->dummy) + return 0; + + if (left->dummy || right->dummy) + return left->dummy ? 1 : -1; } - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, root); + return __hist_entry__cmp_compute(p_left, p_right, c); } -static void hists__compute_resort(struct hists *hists) +static int64_t +hist_entry__cmp_nop(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left __maybe_unused, + struct hist_entry *right __maybe_unused) { - struct rb_root *root; - struct rb_node *next; + return 0; +} - if (sort__need_collapse) - root = &hists->entries_collapsed; - else - root = hists->entries_in; +static int64_t +hist_entry__cmp_baseline(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + if (left->stat.period == right->stat.period) + return 0; + return left->stat.period > right->stat.period ? 1 : -1; +} - hists->entries = RB_ROOT; - next = rb_first(root); +static int64_t +hist_entry__cmp_delta(struct perf_hpp_fmt *fmt, + struct hist_entry *left, struct hist_entry *right) +{ + struct data__file *d = fmt_to_data_file(fmt); - hists__reset_stats(hists); - hists__reset_col_len(hists); + return hist_entry__cmp_compute(right, left, COMPUTE_DELTA, d->idx); +} - while (next != NULL) { - struct hist_entry *he; +static int64_t +hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt, + struct hist_entry *left, struct hist_entry *right) +{ + struct data__file *d = fmt_to_data_file(fmt); - he = rb_entry(next, struct hist_entry, rb_node_in); - next = rb_next(&he->rb_node_in); + return hist_entry__cmp_compute(right, left, COMPUTE_RATIO, d->idx); +} + +static int64_t +hist_entry__cmp_wdiff(struct perf_hpp_fmt *fmt, + struct hist_entry *left, struct hist_entry *right) +{ + struct data__file *d = fmt_to_data_file(fmt); - insert_hist_entry_by_compute(&hists->entries, he, compute); - hists__inc_stats(hists, he); + return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF, d->idx); +} - if (!he->filtered) - hists__calc_col_len(hists, he); - } +static int64_t +hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA, + sort_compute); +} + +static int64_t +hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_compute_idx(right, left, COMPUTE_RATIO, + sort_compute); +} + +static int64_t +hist_entry__cmp_wdiff_idx(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_compute_idx(right, left, COMPUTE_WEIGHTED_DIFF, + sort_compute); } static void hists__process(struct hists *hists) @@ -600,12 +661,8 @@ static void hists__process(struct hists *hists) if (show_baseline_only) hists__baseline_only(hists); - if (sort_compute) { - hists__precompute(hists); - hists__compute_resort(hists); - } else { - hists__output_resort(hists); - } + hists__precompute(hists); + hists__output_resort(hists, NULL); hists__fprintf(hists, true, 0, 0, 0, stdout); } @@ -804,7 +861,7 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt, char pfmt[20] = " "; if (!pair) - goto dummy_print; + goto no_print; switch (comparison_method) { case COMPUTE_DELTA: @@ -813,8 +870,6 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt, else diff = compute_delta(he, pair); - if (fabs(diff) < 0.01) - goto dummy_print; scnprintf(pfmt, 20, "%%%+d.2f%%%%", dfmt->header_width - 1); return percent_color_snprintf(hpp->buf, hpp->size, pfmt, diff); @@ -846,6 +901,9 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt, } dummy_print: return scnprintf(hpp->buf, hpp->size, "%*s", + dfmt->header_width, "N/A"); +no_print: + return scnprintf(hpp->buf, hpp->size, "%*s", dfmt->header_width, pfmt); } @@ -895,14 +953,15 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair, else diff = compute_delta(he, pair); - if (fabs(diff) >= 0.01) - scnprintf(buf, size, "%+4.2F%%", diff); + scnprintf(buf, size, "%+4.2F%%", diff); break; case PERF_HPP_DIFF__RATIO: /* No point for ratio number if we are dummy.. */ - if (he->dummy) + if (he->dummy) { + scnprintf(buf, size, "N/A"); break; + } if (pair->diff.computed) ratio = pair->diff.period_ratio; @@ -915,8 +974,10 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair, case PERF_HPP_DIFF__WEIGHTED_DIFF: /* No point for wdiff number if we are dummy.. */ - if (he->dummy) + if (he->dummy) { + scnprintf(buf, size, "N/A"); break; + } if (pair->diff.computed) wdiff = pair->diff.wdiff; @@ -1037,32 +1098,41 @@ static void data__hpp_register(struct data__file *d, int idx) fmt->header = hpp__header; fmt->width = hpp__width; fmt->entry = hpp__entry_global; + fmt->cmp = hist_entry__cmp_nop; + fmt->collapse = hist_entry__cmp_nop; /* TODO more colors */ switch (idx) { case PERF_HPP_DIFF__BASELINE: fmt->color = hpp__color_baseline; + fmt->sort = hist_entry__cmp_baseline; break; case PERF_HPP_DIFF__DELTA: fmt->color = hpp__color_delta; + fmt->sort = hist_entry__cmp_delta; break; case PERF_HPP_DIFF__RATIO: fmt->color = hpp__color_ratio; + fmt->sort = hist_entry__cmp_ratio; break; case PERF_HPP_DIFF__WEIGHTED_DIFF: fmt->color = hpp__color_wdiff; + fmt->sort = hist_entry__cmp_wdiff; break; default: + fmt->sort = hist_entry__cmp_nop; break; } init_header(d, dfmt); perf_hpp__column_register(fmt); + perf_hpp__register_sort_field(fmt); } -static void ui_init(void) +static int ui_init(void) { struct data__file *d; + struct perf_hpp_fmt *fmt; int i; data__for_each_file(i, d) { @@ -1092,6 +1162,46 @@ static void ui_init(void) data__hpp_register(d, i ? PERF_HPP_DIFF__PERIOD : PERF_HPP_DIFF__PERIOD_BASELINE); } + + if (!sort_compute) + return 0; + + /* + * Prepend an fmt to sort on columns at 'sort_compute' first. + * This fmt is added only to the sort list but not to the + * output fields list. + * + * Note that this column (data) can be compared twice - one + * for this 'sort_compute' fmt and another for the normal + * diff_hpp_fmt. But it shouldn't a problem as most entries + * will be sorted out by first try or baseline and comparing + * is not a costly operation. + */ + fmt = zalloc(sizeof(*fmt)); + if (fmt == NULL) { + pr_err("Memory allocation failed\n"); + return -1; + } + + fmt->cmp = hist_entry__cmp_nop; + fmt->collapse = hist_entry__cmp_nop; + + switch (compute) { + case COMPUTE_DELTA: + fmt->sort = hist_entry__cmp_delta_idx; + break; + case COMPUTE_RATIO: + fmt->sort = hist_entry__cmp_ratio_idx; + break; + case COMPUTE_WEIGHTED_DIFF: + fmt->sort = hist_entry__cmp_wdiff_idx; + break; + default: + BUG_ON(1); + } + + list_add(&fmt->sort_list, &perf_hpp__sort_list); + return 0; } static int data_init(int argc, const char **argv) @@ -1157,7 +1267,8 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) if (data_init(argc, argv) < 0) return -1; - ui_init(); + if (ui_init() < 0) + return -1; sort__mode = SORT_MODE__DIFF; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index de99ca1bb942..a13641e066f5 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -217,8 +217,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, goto repipe; } - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->ip, &al); + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al); if (al.map != NULL) { if (!al.map->dso->hit) { @@ -344,6 +343,7 @@ static int __cmd_inject(struct perf_inject *inject) int ret = -EINVAL; struct perf_session *session = inject->session; struct perf_data_file *file_out = &inject->output; + int fd = perf_data_file__fd(file_out); signal(SIGINT, sig_handler); @@ -377,7 +377,7 @@ static int __cmd_inject(struct perf_inject *inject) } if (!file_out->is_pipe) - lseek(file_out->fd, session->header.data_offset, SEEK_SET); + lseek(fd, session->header.data_offset, SEEK_SET); ret = perf_session__process_events(session, &inject->tool); @@ -386,7 +386,7 @@ static int __cmd_inject(struct perf_inject *inject) perf_header__set_feat(&session->header, HEADER_BUILD_ID); session->header.data_size = inject->bytes_written; - perf_session__write_header(session, session->evlist, file_out->fd, true); + perf_session__write_header(session, session->evlist, fd, true); } return ret; @@ -410,6 +410,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .tracing_data = perf_event__repipe_op2_synth, .finished_round = perf_event__repipe_op2_synth, .build_id = perf_event__repipe_op2_synth, + .id_index = perf_event__repipe_op2_synth, }, .input_name = "-", .samples = LIST_HEAD_INIT(inject.samples), diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index b65eb0507b38..0894a817f67e 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1132,6 +1132,10 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) "-m", "1024", "-c", "1", }; + const char * const kvm_stat_record_usage[] = { + "perf kvm stat record [<options>]", + NULL + }; const char * const *events_tp; events_tp_size = 0; @@ -1159,6 +1163,27 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) for (j = 1; j < (unsigned int)argc; j++, i++) rec_argv[i] = argv[j]; + set_option_flag(record_options, 'e', "event", PARSE_OPT_HIDDEN); + set_option_flag(record_options, 0, "filter", PARSE_OPT_HIDDEN); + set_option_flag(record_options, 'R', "raw-samples", PARSE_OPT_HIDDEN); + + set_option_flag(record_options, 'F', "freq", PARSE_OPT_DISABLED); + set_option_flag(record_options, 0, "group", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'g', NULL, PARSE_OPT_DISABLED); + set_option_flag(record_options, 0, "call-graph", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'd', "data", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'T', "timestamp", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'P', "period", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'n', "no-samples", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'N', "no-buildid-cache", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'B', "no-buildid", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'G', "cgroup", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'b', "branch-any", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'j', "branch-filter", PARSE_OPT_DISABLED); + set_option_flag(record_options, 'W', "weight", PARSE_OPT_DISABLED); + set_option_flag(record_options, 0, "transaction", PARSE_OPT_DISABLED); + + record_usage = kvm_stat_record_usage; return cmd_record(i, rec_argv, NULL); } @@ -1268,7 +1293,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, OPT_UINTEGER('d', "display", &kvm->display_time, "time in seconds between display updates"), OPT_STRING(0, "event", &kvm->report_event, "report event", - "event for reporting: vmexit, mmio, ioport"), + "event for reporting: " + "vmexit, mmio (x86 only), ioport (x86 only)"), OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu, "vcpu id to report"), OPT_STRING('k', "key", &kvm->sort_key, "sort-key", diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 011195e38f21..198f3c3aff95 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -19,7 +19,9 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) { int i; - const struct option list_options[] = { + bool raw_dump = false; + struct option list_options[] = { + OPT_BOOLEAN(0, "raw-dump", &raw_dump, "Dump raw events"), OPT_END() }; const char * const list_usage[] = { @@ -27,11 +29,18 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; + set_option_flag(list_options, 0, "raw-dump", PARSE_OPT_HIDDEN); + argc = parse_options(argc, argv, list_options, list_usage, PARSE_OPT_STOP_AT_NON_OPTION); setup_pager(); + if (raw_dump) { + print_events(NULL, true); + return 0; + } + if (argc == 0) { print_events(NULL, false); return 0; @@ -53,8 +62,6 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) print_hwcache_events(NULL, false); else if (strcmp(argv[i], "pmu") == 0) print_pmu_events(NULL, false); - else if (strcmp(argv[i], "--raw-dump") == 0) - print_events(NULL, true); else { char *sep = strchr(argv[i], ':'), *s; int sep_idx; diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 24db6ffe2957..9b5663950a4d 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -7,44 +7,47 @@ #include "util/session.h" #include "util/data.h" -#define MEM_OPERATION_LOAD "load" -#define MEM_OPERATION_STORE "store" - -static const char *mem_operation = MEM_OPERATION_LOAD; +#define MEM_OPERATION_LOAD 0x1 +#define MEM_OPERATION_STORE 0x2 struct perf_mem { struct perf_tool tool; char const *input_name; bool hide_unresolved; bool dump_raw; + int operation; const char *cpu_list; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; -static int __cmd_record(int argc, const char **argv) +static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) { int rec_argc, i = 0, j; const char **rec_argv; - char event[64]; int ret; - rec_argc = argc + 4; + rec_argc = argc + 7; /* max number of arguments */ rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (!rec_argv) return -1; - rec_argv[i++] = strdup("record"); - if (!strcmp(mem_operation, MEM_OPERATION_LOAD)) - rec_argv[i++] = strdup("-W"); - rec_argv[i++] = strdup("-d"); - rec_argv[i++] = strdup("-e"); + rec_argv[i++] = "record"; - if (strcmp(mem_operation, MEM_OPERATION_LOAD)) - sprintf(event, "cpu/mem-stores/pp"); - else - sprintf(event, "cpu/mem-loads/pp"); + if (mem->operation & MEM_OPERATION_LOAD) + rec_argv[i++] = "-W"; + + rec_argv[i++] = "-d"; + + if (mem->operation & MEM_OPERATION_LOAD) { + rec_argv[i++] = "-e"; + rec_argv[i++] = "cpu/mem-loads/pp"; + } + + if (mem->operation & MEM_OPERATION_STORE) { + rec_argv[i++] = "-e"; + rec_argv[i++] = "cpu/mem-stores/pp"; + } - rec_argv[i++] = strdup(event); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -162,17 +165,17 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem) if (!rep_argv) return -1; - rep_argv[i++] = strdup("report"); - rep_argv[i++] = strdup("--mem-mode"); - rep_argv[i++] = strdup("-n"); /* display number of samples */ + rep_argv[i++] = "report"; + rep_argv[i++] = "--mem-mode"; + rep_argv[i++] = "-n"; /* display number of samples */ /* * there is no weight (cost) associated with stores, so don't print * the column */ - if (strcmp(mem_operation, MEM_OPERATION_LOAD)) - rep_argv[i++] = strdup("--sort=mem,sym,dso,symbol_daddr," - "dso_daddr,tlb,locked"); + if (!(mem->operation & MEM_OPERATION_LOAD)) + rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr," + "dso_daddr,tlb,locked"; for (j = 1; j < argc; j++, i++) rep_argv[i] = argv[j]; @@ -182,6 +185,75 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem) return ret; } +struct mem_mode { + const char *name; + int mode; +}; + +#define MEM_OPT(n, m) \ + { .name = n, .mode = (m) } + +#define MEM_END { .name = NULL } + +static const struct mem_mode mem_modes[]={ + MEM_OPT("load", MEM_OPERATION_LOAD), + MEM_OPT("store", MEM_OPERATION_STORE), + MEM_END +}; + +static int +parse_mem_ops(const struct option *opt, const char *str, int unset) +{ + int *mode = (int *)opt->value; + const struct mem_mode *m; + char *s, *os = NULL, *p; + int ret = -1; + + if (unset) + return 0; + + /* str may be NULL in case no arg is passed to -t */ + if (str) { + /* because str is read-only */ + s = os = strdup(str); + if (!s) + return -1; + + /* reset mode */ + *mode = 0; + + for (;;) { + p = strchr(s, ','); + if (p) + *p = '\0'; + + for (m = mem_modes; m->name; m++) { + if (!strcasecmp(s, m->name)) + break; + } + if (!m->name) { + fprintf(stderr, "unknown sampling op %s," + " check man page\n", s); + goto error; + } + + *mode |= m->mode; + + if (!p) + break; + + s = p + 1; + } + } + ret = 0; + + if (*mode == 0) + *mode = MEM_OPERATION_LOAD; +error: + free(os); + return ret; +} + int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) { struct stat st; @@ -197,10 +269,15 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) .ordered_events = true, }, .input_name = "perf.data", + /* + * default to both load an store sampling + */ + .operation = MEM_OPERATION_LOAD | MEM_OPERATION_STORE, }; const struct option mem_options[] = { - OPT_STRING('t', "type", &mem_operation, - "type", "memory operations(load/store)"), + OPT_CALLBACK('t', "type", &mem.operation, + "type", "memory operations(load,store) Default load,store", + parse_mem_ops), OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw, "dump raw samples in ASCII"), OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved, @@ -225,7 +302,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands, mem_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation)) + if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation)) usage_with_options(mem_usage, mem_options); if (!mem.input_name || !strlen(mem.input_name)) { @@ -236,7 +313,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) } if (!strncmp(argv[0], "rec", 3)) - return __cmd_record(argc, argv); + return __cmd_record(argc, argv, &mem); else if (!strncmp(argv[0], "rep", 3)) return report_events(argc, argv, &mem); else diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 7af26acf06d9..921bb6942503 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -55,6 +55,7 @@ static struct { bool show_funcs; bool mod_events; bool uprobes; + bool quiet; int nevents; struct perf_probe_event events[MAX_PROBES]; struct strlist *dellist; @@ -312,9 +313,11 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) #endif NULL }; - const struct option options[] = { + struct option options[] = { OPT_INCR('v', "verbose", &verbose, "be more verbose (show parsed arguments, etc)"), + OPT_BOOLEAN('q', "quiet", ¶ms.quiet, + "be quiet (do not show any mesages)"), OPT_BOOLEAN('l', "list", ¶ms.list_events, "list up current probe events"), OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.", @@ -382,6 +385,14 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) }; int ret; + set_option_flag(options, 'a', "add", PARSE_OPT_EXCLUSIVE); + set_option_flag(options, 'd', "del", PARSE_OPT_EXCLUSIVE); + set_option_flag(options, 'l', "list", PARSE_OPT_EXCLUSIVE); +#ifdef HAVE_DWARF_SUPPORT + set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE); + set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE); +#endif + argc = parse_options(argc, argv, options, probe_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (argc > 0) { @@ -396,6 +407,14 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) } } + if (params.quiet) { + if (verbose != 0) { + pr_err(" Error: -v and -q are exclusive.\n"); + return -EINVAL; + } + verbose = -1; + } + if (params.max_probe_points == 0) params.max_probe_points = MAX_PROBES; @@ -409,22 +428,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); if (params.list_events) { - if (params.mod_events) { - pr_err(" Error: Don't use --list with --add/--del.\n"); - usage_with_options(probe_usage, options); - } - if (params.show_lines) { - pr_err(" Error: Don't use --list with --line.\n"); - usage_with_options(probe_usage, options); - } - if (params.show_vars) { - pr_err(" Error: Don't use --list with --vars.\n"); - usage_with_options(probe_usage, options); - } - if (params.show_funcs) { - pr_err(" Error: Don't use --list with --funcs.\n"); - usage_with_options(probe_usage, options); - } if (params.uprobes) { pr_warning(" Error: Don't use --list with --exec.\n"); usage_with_options(probe_usage, options); @@ -435,19 +438,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) return ret; } if (params.show_funcs) { - if (params.nevents != 0 || params.dellist) { - pr_err(" Error: Don't use --funcs with" - " --add/--del.\n"); - usage_with_options(probe_usage, options); - } - if (params.show_lines) { - pr_err(" Error: Don't use --funcs with --line.\n"); - usage_with_options(probe_usage, options); - } - if (params.show_vars) { - pr_err(" Error: Don't use --funcs with --vars.\n"); - usage_with_options(probe_usage, options); - } if (!params.filter) params.filter = strfilter__new(DEFAULT_FUNC_FILTER, NULL); @@ -462,16 +452,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) #ifdef HAVE_DWARF_SUPPORT if (params.show_lines) { - if (params.mod_events) { - pr_err(" Error: Don't use --line with" - " --add/--del.\n"); - usage_with_options(probe_usage, options); - } - if (params.show_vars) { - pr_err(" Error: Don't use --line with --vars.\n"); - usage_with_options(probe_usage, options); - } - ret = show_line_range(¶ms.line_range, params.target, params.uprobes); if (ret < 0) @@ -479,11 +459,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) return ret; } if (params.show_vars) { - if (params.mod_events) { - pr_err(" Error: Don't use --vars with" - " --add/--del.\n"); - usage_with_options(probe_usage, options); - } if (!params.filter) params.filter = strfilter__new(DEFAULT_VAR_FILTER, NULL); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 2583a9b04317..404ab3434052 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -190,19 +190,42 @@ out: return rc; } +static int process_sample_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + struct record *rec = container_of(tool, struct record, tool); + + rec->samples++; + + return build_id__mark_dso_hit(tool, event, sample, evsel, machine); +} + static int process_buildids(struct record *rec) { struct perf_data_file *file = &rec->file; struct perf_session *session = rec->session; - u64 start = session->header.data_offset; - u64 size = lseek(file->fd, 0, SEEK_CUR); + u64 size = lseek(perf_data_file__fd(file), 0, SEEK_CUR); if (size == 0) return 0; - return __perf_session__process_events(session, start, - size - start, - size, &build_id__mark_dso_hit_ops); + file->size = size; + + /* + * During this process, it'll load kernel map and replace the + * dso->long_name to a real pathname it found. In this case + * we prefer the vmlinux path like + * /lib/modules/3.16.4/build/vmlinux + * + * rather than build-id path (in debug directory). + * $HOME/.debug/.build-id/f0/6e17aa50adf4d00b88925e03775de107611551 + */ + symbol_conf.ignore_vmlinux_buildid = true; + + return perf_session__process_events(session, &rec->tool); } static void perf_event__synthesize_guest_os(struct machine *machine, void *data) @@ -311,6 +334,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) struct perf_data_file *file = &rec->file; struct perf_session *session; bool disabled = false, draining = false; + int fd; rec->progname = argv[0]; @@ -325,6 +349,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) return -1; } + fd = perf_data_file__fd(file); rec->session = session; record__init_features(rec); @@ -349,12 +374,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) perf_header__clear_feat(&session->header, HEADER_GROUP_DESC); if (file->is_pipe) { - err = perf_header__write_pipe(file->fd); + err = perf_header__write_pipe(fd); if (err < 0) goto out_child; } else { - err = perf_session__write_header(session, rec->evlist, - file->fd, false); + err = perf_session__write_header(session, rec->evlist, fd, false); if (err < 0) goto out_child; } @@ -386,7 +410,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * return this more properly and also * propagate errors that now are calling die() */ - err = perf_event__synthesize_tracing_data(tool, file->fd, rec->evlist, + err = perf_event__synthesize_tracing_data(tool, fd, rec->evlist, process_synthesized_event); if (err <= 0) { pr_err("Couldn't record tracing data.\n"); @@ -493,19 +517,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_child; } - if (!quiet) { + if (!quiet) fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking); - /* - * Approximate RIP event size: 24 bytes. - */ - fprintf(stderr, - "[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n", - (double)rec->bytes_written / 1024.0 / 1024.0, - file->path, - rec->bytes_written / 24); - } - out_child: if (forks) { int exit_status; @@ -524,13 +538,29 @@ out_child: } else status = err; + /* this will be recalculated during process_buildids() */ + rec->samples = 0; + if (!err && !file->is_pipe) { rec->session->header.data_size += rec->bytes_written; if (!rec->no_buildid) process_buildids(rec); - perf_session__write_header(rec->session, rec->evlist, - file->fd, true); + perf_session__write_header(rec->session, rec->evlist, fd, true); + } + + if (!err && !quiet) { + char samples[128]; + + if (rec->samples) + scnprintf(samples, sizeof(samples), + " (%" PRIu64 " samples)", rec->samples); + else + samples[0] = '\0'; + + fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s ]\n", + perf_data_file__size(file) / 1024.0 / 1024.0, + file->path, samples); } out_delete_session: @@ -680,11 +710,12 @@ static int perf_record_config(const char *var, const char *value, void *cb) return perf_default_config(var, value, cb); } -static const char * const record_usage[] = { +static const char * const __record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", NULL }; +const char * const *record_usage = __record_usage; /* * XXX Ideally would be local to cmd_record() and passed to a record__new @@ -708,6 +739,13 @@ static struct record record = { .default_per_cpu = true, }, }, + .tool = { + .sample = process_sample_event, + .fork = perf_event__process_fork, + .comm = perf_event__process_comm, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + }, }; #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: " @@ -725,7 +763,7 @@ const char record_callchain_help[] = CALLCHAIN_HELP "fp"; * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record', * using pipes, etc. */ -const struct option record_options[] = { +struct option __record_options[] = { OPT_CALLBACK('e', "event", &record.evlist, "event", "event selector. use 'perf list' to list available events", parse_events_option), @@ -799,9 +837,13 @@ const struct option record_options[] = { "sample transaction flags (special events only)"), OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread, "use per-thread mmaps"), + OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs, + "Sample machine registers on interrupt"), OPT_END() }; +struct option *record_options = __record_options; + int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) { int err = -ENOMEM; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 140a6cd88351..2f91094e228b 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -86,17 +86,6 @@ static int report__config(const char *var, const char *value, void *cb) return perf_default_config(var, value, cb); } -static void report__inc_stats(struct report *rep, struct hist_entry *he) -{ - /* - * The @he is either of a newly created one or an existing one - * merging current sample. We only want to count a new one so - * checking ->nr_events being 1. - */ - if (he->stat.nr_events == 1) - rep->nr_entries++; -} - static int hist_iter__report_callback(struct hist_entry_iter *iter, struct addr_location *al, bool single, void *arg) @@ -108,8 +97,6 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter, struct mem_info *mi; struct branch_info *bi; - report__inc_stats(rep, he); - if (!ui__has_annotation()) return 0; @@ -226,8 +213,9 @@ static int report__setup_sample_type(struct report *rep) return -EINVAL; } if (symbol_conf.use_callchain) { - ui__error("Selected -g but no callchain data. Did " - "you call 'perf record' without -g?\n"); + ui__error("Selected -g or --branch-history but no " + "callchain data. Did\n" + "you call 'perf record' without -g?\n"); return -1; } } else if (!rep->dont_use_callchains && @@ -456,6 +444,19 @@ static void report__collapse_hists(struct report *rep) ui_progress__finish(); } +static void report__output_resort(struct report *rep) +{ + struct ui_progress prog; + struct perf_evsel *pos; + + ui_progress__init(&prog, rep->nr_entries, "Sorting events for output..."); + + evlist__for_each(rep->session->evlist, pos) + hists__output_resort(evsel__hists(pos), &prog); + + ui_progress__finish(); +} + static int __cmd_report(struct report *rep) { int ret; @@ -485,6 +486,9 @@ static int __cmd_report(struct report *rep) report__warn_kptr_restrict(rep); + evlist__for_each(session->evlist, pos) + rep->nr_entries += evsel__hists(pos)->nr_entries; + if (use_browser == 0) { if (verbose > 3) perf_session__fprintf(session, stdout); @@ -504,13 +508,20 @@ static int __cmd_report(struct report *rep) if (session_done()) return 0; + /* + * recalculate number of entries after collapsing since it + * might be changed during the collapse phase. + */ + rep->nr_entries = 0; + evlist__for_each(session->evlist, pos) + rep->nr_entries += evsel__hists(pos)->nr_entries; + if (rep->nr_entries == 0) { ui__error("The %s file has no samples!\n", file->path); return 0; } - evlist__for_each(session->evlist, pos) - hists__output_resort(evsel__hists(pos)); + report__output_resort(rep); return report__browse_hists(rep); } @@ -575,6 +586,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) struct stat st; bool has_br_stack = false; int branch_mode = -1; + bool branch_call_mode = false; char callchain_default_opt[] = "fractal,0.5,callee"; const char * const report_usage[] = { "perf report [<options>]", @@ -637,8 +649,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "regex filter to identify parent, see: '--sort parent'"), OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other, "Only display entries with parent-match"), - OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order", - "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). " + OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order[,branch]", + "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address), add branches. " "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt), OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain, "Accumulate callchains of children and show total overhead as well"), @@ -684,7 +696,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "group", &symbol_conf.event_group, "Show event group information together"), OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "", - "use branch records for histogram filling", parse_branch_mode), + "use branch records for per branch histogram filling", + parse_branch_mode), + OPT_BOOLEAN(0, "branch-history", &branch_call_mode, + "add last branch records to call history"), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, @@ -745,10 +760,24 @@ repeat: has_br_stack = perf_header__has_feat(&session->header, HEADER_BRANCH_STACK); - if ((branch_mode == -1 && has_br_stack) || branch_mode == 1) { + /* + * Branch mode is a tristate: + * -1 means default, so decide based on the file having branch data. + * 0/1 means the user chose a mode. + */ + if (((branch_mode == -1 && has_br_stack) || branch_mode == 1) && + branch_call_mode == -1) { sort__mode = SORT_MODE__BRANCH; symbol_conf.cumulate_callchain = false; } + if (branch_call_mode) { + callchain_param.key = CCKEY_ADDRESS; + callchain_param.branch_callstack = 1; + symbol_conf.use_callchain = true; + callchain_register_param(&callchain_param); + if (sort_order == NULL) + sort_order = "srcline,symbol,dso"; + } if (report.mem_mode) { if (sort__mode == SORT_MODE__BRANCH) { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 9708a1290571..ce304dfd962a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -23,7 +23,6 @@ static char const *generate_script_lang; static bool debug_mode; static u64 last_timestamp; static u64 nr_unordered; -extern const struct option record_options[]; static bool no_callchain; static bool latency_format; static bool system_wide; @@ -379,7 +378,6 @@ static void print_sample_start(struct perf_sample *sample, static void print_sample_addr(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct thread *thread, struct perf_event_attr *attr) { @@ -390,7 +388,7 @@ static void print_sample_addr(union perf_event *event, if (!sample_addr_correlates_sym(attr)) return; - perf_event__preprocess_sample_addr(event, sample, machine, thread, &al); + perf_event__preprocess_sample_addr(event, sample, thread, &al); if (PRINT_FIELD(SYM)) { printf(" "); @@ -438,7 +436,7 @@ static void print_sample_bts(union perf_event *event, ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && !output[attr->type].user_set)) { printf(" => "); - print_sample_addr(event, sample, al->machine, thread, attr); + print_sample_addr(event, sample, thread, attr); } if (print_srcline_last) @@ -475,7 +473,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample, event_format__print(evsel->tp_format, sample->cpu, sample->raw_data, sample->raw_size); if (PRINT_FIELD(ADDR)) - print_sample_addr(event, sample, al->machine, thread, attr); + print_sample_addr(event, sample, thread, attr); if (PRINT_FIELD(IP)) { if (!symbol_conf.use_callchain) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 055ce9232c9e..e598e4e98170 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -388,20 +388,102 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count) update_stats(&runtime_itlb_cache_stats[0], count[0]); } +static void zero_per_pkg(struct perf_evsel *counter) +{ + if (counter->per_pkg_mask) + memset(counter->per_pkg_mask, 0, MAX_NR_CPUS); +} + +static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip) +{ + unsigned long *mask = counter->per_pkg_mask; + struct cpu_map *cpus = perf_evsel__cpus(counter); + int s; + + *skip = false; + + if (!counter->per_pkg) + return 0; + + if (cpu_map__empty(cpus)) + return 0; + + if (!mask) { + mask = zalloc(MAX_NR_CPUS); + if (!mask) + return -ENOMEM; + + counter->per_pkg_mask = mask; + } + + s = cpu_map__get_socket(cpus, cpu); + if (s < 0) + return -1; + + *skip = test_and_set_bit(s, mask) == 1; + return 0; +} + +static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, + struct perf_counts_values *count) +{ + struct perf_counts_values *aggr = &evsel->counts->aggr; + static struct perf_counts_values zero; + bool skip = false; + + if (check_per_pkg(evsel, cpu, &skip)) { + pr_err("failed to read per-pkg counter\n"); + return -1; + } + + if (skip) + count = &zero; + + switch (aggr_mode) { + case AGGR_CORE: + case AGGR_SOCKET: + case AGGR_NONE: + if (!evsel->snapshot) + perf_evsel__compute_deltas(evsel, cpu, count); + perf_counts_values__scale(count, scale, NULL); + evsel->counts->cpu[cpu] = *count; + update_shadow_stats(evsel, count->values); + break; + case AGGR_GLOBAL: + aggr->val += count->val; + if (scale) { + aggr->ena += count->ena; + aggr->run += count->run; + } + default: + break; + } + + return 0; +} + +static int read_counter(struct perf_evsel *counter); + /* * Read out the results of a single counter: * aggregate counts across CPUs in system-wide mode */ static int read_counter_aggr(struct perf_evsel *counter) { + struct perf_counts_values *aggr = &counter->counts->aggr; struct perf_stat *ps = counter->priv; u64 *count = counter->counts->aggr.values; int i; - if (__perf_evsel__read(counter, perf_evsel__nr_cpus(counter), - thread_map__nr(evsel_list->threads), scale) < 0) + aggr->val = aggr->ena = aggr->run = 0; + + if (read_counter(counter)) return -1; + if (!counter->snapshot) + perf_evsel__compute_deltas(counter, -1, aggr); + perf_counts_values__scale(aggr, scale, &counter->counts->scaled); + for (i = 0; i < 3; i++) update_stats(&ps->res_stats[i], count[i]); @@ -424,16 +506,21 @@ static int read_counter_aggr(struct perf_evsel *counter) */ static int read_counter(struct perf_evsel *counter) { - u64 *count; - int cpu; + int nthreads = thread_map__nr(evsel_list->threads); + int ncpus = perf_evsel__nr_cpus(counter); + int cpu, thread; - for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0) - return -1; + if (counter->system_wide) + nthreads = 1; - count = counter->counts->cpu[cpu].values; + if (counter->per_pkg) + zero_per_pkg(counter); - update_shadow_stats(counter, count); + for (thread = 0; thread < nthreads; thread++) { + for (cpu = 0; cpu < ncpus; cpu++) { + if (perf_evsel__read_cb(counter, cpu, thread, read_cb)) + return -1; + } } return 0; @@ -1643,7 +1730,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) "detailed run - start a lot of events"), OPT_BOOLEAN('S', "sync", &sync_run, "call sync() before starting a run"), - OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, + OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, "print large numbers with thousands\' separators", stat__set_big_num), OPT_STRING('C', "cpu", &target.cpu_list, "cpu", diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 35b425b6293f..f3bb1a4bf060 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -528,7 +528,7 @@ static const char *cat_backtrace(union perf_event *event, } tal.filtered = 0; - thread__find_addr_location(al.thread, machine, cpumode, + thread__find_addr_location(al.thread, cpumode, MAP__FUNCTION, ip, &tal); if (tal.sym) @@ -1963,7 +1963,7 @@ int cmd_timechart(int argc, const char **argv, NULL }; - const struct option record_options[] = { + const struct option timechart_record_options[] = { OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"), OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, "output processes data only"), @@ -1972,7 +1972,7 @@ int cmd_timechart(int argc, const char **argv, OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"), OPT_END() }; - const char * const record_usage[] = { + const char * const timechart_record_usage[] = { "perf timechart record [<options>]", NULL }; @@ -1985,7 +1985,8 @@ int cmd_timechart(int argc, const char **argv, } if (argc && !strncmp(argv[0], "rec", 3)) { - argc = parse_options(argc, argv, record_options, record_usage, + argc = parse_options(argc, argv, timechart_record_options, + timechart_record_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (tchart.power_only && tchart.tasks_only) { diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 0aa7747ff139..c4c7eac69de4 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -66,7 +66,6 @@ #include <sys/utsname.h> #include <sys/mman.h> -#include <linux/unistd.h> #include <linux/types.h> static volatile int done; @@ -166,7 +165,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) err ? "[unknown]" : uts.release, perf_version_string); if (use_browser <= 0) sleep(5); - + map->erange_warned = true; } @@ -285,7 +284,7 @@ static void perf_top__print_sym_table(struct perf_top *top) } hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); @@ -554,7 +553,7 @@ static void perf_top__sort_new_samples(void *arg) } hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); } static void *display_thread_tui(void *arg) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index fb126459b134..7e935f1083ec 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -929,66 +929,66 @@ static struct syscall_fmt { .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, }, { .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), }, { .name = "close", .errmsg = true, - .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, { .name = "connect", .errmsg = true, }, { .name = "dup", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "dup2", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "dup3", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), }, { .name = "eventfd2", .errmsg = true, .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, }, { .name = "faccessat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "fadvise64", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fallocate", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fchdir", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fchmod", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fchmodat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "fchown", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fchownat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "fcntl", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ [1] = SCA_STRARRAY, /* cmd */ }, .arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, }, { .name = "fdatasync", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "flock", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ [1] = SCA_FLOCK, /* cmd */ }, }, { .name = "fsetxattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fstat", .errmsg = true, .alias = "newfstat", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fstatat", .errmsg = true, .alias = "newfstatat", - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "fstatfs", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fsync", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "ftruncate", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "futex", .errmsg = true, .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, }, { .name = "futimesat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "getdents", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "getdents64", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), }, { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "ioctl", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ + .arg_scnprintf = { [0] = SCA_FD, /* fd */ #if defined(__i386__) || defined(__x86_64__) /* * FIXME: Make this available to all arches. @@ -1002,7 +1002,7 @@ static struct syscall_fmt { { .name = "kill", .errmsg = true, .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, { .name = "linkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "lseek", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ [2] = SCA_STRARRAY, /* whence */ }, @@ -1012,9 +1012,9 @@ static struct syscall_fmt { .arg_scnprintf = { [0] = SCA_HEX, /* start */ [2] = SCA_MADV_BHV, /* behavior */ }, }, { .name = "mkdirat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "mknodat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "mlock", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, { .name = "mlockall", .errmsg = true, @@ -1036,9 +1036,9 @@ static struct syscall_fmt { { .name = "munmap", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, { .name = "name_to_handle_at", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "newfstatat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "open", .errmsg = true, .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, }, { .name = "open_by_handle_at", .errmsg = true, @@ -1052,20 +1052,20 @@ static struct syscall_fmt { { .name = "poll", .errmsg = true, .timeout = true, }, { .name = "ppoll", .errmsg = true, .timeout = true, }, { .name = "pread", .errmsg = true, .alias = "pread64", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "preadv", .errmsg = true, .alias = "pread", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resources), }, { .name = "pwrite", .errmsg = true, .alias = "pwrite64", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "pwritev", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "read", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "readlinkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "readv", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "recvfrom", .errmsg = true, .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "recvmmsg", .errmsg = true, @@ -1073,7 +1073,7 @@ static struct syscall_fmt { { .name = "recvmsg", .errmsg = true, .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "renameat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "rt_sigaction", .errmsg = true, .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, }, { .name = "rt_sigprocmask", .errmsg = true, STRARRAY(0, how, sighow), }, @@ -1091,7 +1091,7 @@ static struct syscall_fmt { { .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), }, { .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "shutdown", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "socket", .errmsg = true, .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */ [1] = SCA_SK_TYPE, /* type */ }, @@ -1102,7 +1102,7 @@ static struct syscall_fmt { .arg_parm = { [0] = &strarray__socket_families, /* family */ }, }, { .name = "stat", .errmsg = true, .alias = "newstat", }, { .name = "symlinkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "tgkill", .errmsg = true, .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, }, { .name = "tkill", .errmsg = true, @@ -1113,9 +1113,9 @@ static struct syscall_fmt { { .name = "utimensat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, }, { .name = "write", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "writev", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, }; static int syscall_fmt__cmp(const void *name, const void *fmtp) @@ -1191,7 +1191,7 @@ static struct thread_trace *thread__trace(struct thread *thread, FILE *fp) if (thread__priv(thread) == NULL) thread__set_priv(thread, thread_trace__new()); - + if (thread__priv(thread) == NULL) goto fail; @@ -1846,7 +1846,7 @@ static int trace__pgfault(struct trace *trace, if (trace->summary_only) return 0; - thread__find_addr_location(thread, trace->host, cpumode, MAP__FUNCTION, + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, sample->ip, &al); trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output); @@ -1859,11 +1859,11 @@ static int trace__pgfault(struct trace *trace, fprintf(trace->output, "] => "); - thread__find_addr_location(thread, trace->host, cpumode, MAP__VARIABLE, + thread__find_addr_location(thread, cpumode, MAP__VARIABLE, sample->addr, &al); if (!al.map) { - thread__find_addr_location(thread, trace->host, cpumode, + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, sample->addr, &al); if (al.map) @@ -2045,7 +2045,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv) unsigned long before; const bool forks = argc > 0; bool draining = false; - char sbuf[STRERR_BUFSIZE]; trace->live = true; @@ -2057,23 +2056,24 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (trace->trace_syscalls && perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit)) - goto out_error_tp; + goto out_error_raw_syscalls; if (trace->trace_syscalls) perf_evlist__add_vfs_getname(evlist); if ((trace->trace_pgfaults & TRACE_PFMAJ) && - perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ)) - goto out_error_tp; + perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ)) { + goto out_error_mem; + } if ((trace->trace_pgfaults & TRACE_PFMIN) && perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN)) - goto out_error_tp; + goto out_error_mem; if (trace->sched && - perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime", - trace__sched_stat_runtime)) - goto out_error_tp; + perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime", + trace__sched_stat_runtime)) + goto out_error_sched_stat_runtime; err = perf_evlist__create_maps(evlist, &trace->opts.target); if (err < 0) { @@ -2106,11 +2106,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_error_open; err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false); - if (err < 0) { - fprintf(trace->output, "Couldn't mmap the events: %s\n", - strerror_r(errno, sbuf, sizeof(sbuf))); - goto out_delete_evlist; - } + if (err < 0) + goto out_error_mmap; perf_evlist__enable(evlist); @@ -2206,8 +2203,16 @@ out: { char errbuf[BUFSIZ]; -out_error_tp: - perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf)); +out_error_sched_stat_runtime: + debugfs__strerror_open_tp(errno, errbuf, sizeof(errbuf), "sched", "sched_stat_runtime"); + goto out_error; + +out_error_raw_syscalls: + debugfs__strerror_open_tp(errno, errbuf, sizeof(errbuf), "raw_syscalls", "sys_(enter|exit)"); + goto out_error; + +out_error_mmap: + perf_evlist__strerror_mmap(evlist, errno, errbuf, sizeof(errbuf)); goto out_error; out_error_open: @@ -2217,6 +2222,9 @@ out_error: fprintf(trace->output, "%s\n", errbuf); goto out_delete_evlist; } +out_error_mem: + fprintf(trace->output, "Not enough memory to run!\n"); + goto out_delete_evlist; } static int trace__replay(struct trace *trace) @@ -2485,7 +2493,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, .no_buffering = true, - .mmap_pages = 1024, + .mmap_pages = UINT_MAX, }, .output = stdout, .show_comm = true, diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 58f609198c6d..cc224080b525 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -20,7 +20,7 @@ NO_PERF_REGS := 1 # Additional ARCH settings for x86 ifeq ($(ARCH),x86) - ifeq (${IS_X86_64}, 1) + ifeq (${IS_64_BIT}, 1) CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 @@ -150,7 +150,7 @@ CFLAGS += -std=gnu99 # adding assembler files missing the .GNU-stack linker note. LDFLAGS += -Wl,-z,noexecstack -EXTLIBS = -lelf -lpthread -lrt -lm -ldl +EXTLIBS = -lpthread -lrt -lm -ldl ifneq ($(OUTPUT),) OUTPUT_FEATURES = $(OUTPUT)config/feature-checks/ @@ -198,9 +198,11 @@ CORE_FEATURE_TESTS = \ libpython-version \ libslang \ libunwind \ + pthread-attr-setaffinity-np \ stackprotector-all \ timerfd \ - libdw-dwarf-unwind + libdw-dwarf-unwind \ + zlib LIB_FEATURE_TESTS = \ dwarf \ @@ -214,7 +216,8 @@ LIB_FEATURE_TESTS = \ libpython \ libslang \ libunwind \ - libdw-dwarf-unwind + libdw-dwarf-unwind \ + zlib VF_FEATURE_TESTS = \ backtrace \ @@ -224,13 +227,16 @@ VF_FEATURE_TESTS = \ libelf-getphdrnum \ libelf-mmap \ libpython-version \ + pthread-attr-setaffinity-np \ stackprotector-all \ timerfd \ libunwind-debug-frame \ bionic \ liberty \ liberty-z \ - cplus-demangle + cplus-demangle \ + compile-32 \ + compile-x32 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features. # If in the future we need per-feature checks/flags for features not @@ -297,6 +303,10 @@ ifeq ($(feature-sync-compare-and-swap), 1) CFLAGS += -DHAVE_SYNC_COMPARE_AND_SWAP_SUPPORT endif +ifeq ($(feature-pthread-attr-setaffinity-np), 1) + CFLAGS += -DHAVE_PTHREAD_ATTR_SETAFFINITY_NP +endif + ifndef NO_BIONIC $(call feature_check,bionic) ifeq ($(feature-bionic), 1) @@ -350,6 +360,7 @@ endif # NO_LIBELF ifndef NO_LIBELF CFLAGS += -DHAVE_LIBELF_SUPPORT + EXTLIBS += -lelf ifeq ($(feature-libelf-mmap), 1) CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT @@ -369,7 +380,7 @@ ifndef NO_LIBELF else CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS) LDFLAGS += $(LIBDW_LDFLAGS) - EXTLIBS += -lelf -ldw + EXTLIBS += -ldw endif # PERF_HAVE_DWARF_REGS endif # NO_DWARF endif # NO_LIBELF @@ -602,6 +613,15 @@ ifneq ($(filter -lbfd,$(EXTLIBS)),) CFLAGS += -DHAVE_LIBBFD_SUPPORT endif +ifndef NO_ZLIB + ifeq ($(feature-zlib), 1) + CFLAGS += -DHAVE_ZLIB_SUPPORT + EXTLIBS += -lz + else + NO_ZLIB := 1 + endif +endif + ifndef NO_BACKTRACE ifeq ($(feature-backtrace), 1) CFLAGS += -DHAVE_BACKTRACE_SUPPORT @@ -622,6 +642,31 @@ ifdef HAVE_KVM_STAT_SUPPORT CFLAGS += -DHAVE_KVM_STAT_SUPPORT endif +ifeq (${IS_64_BIT}, 1) + ifndef NO_PERF_READ_VDSO32 + $(call feature_check,compile-32) + ifeq ($(feature-compile-32), 1) + CFLAGS += -DHAVE_PERF_READ_VDSO32 + else + NO_PERF_READ_VDSO32 := 1 + endif + endif + ifneq (${IS_X86_64}, 1) + NO_PERF_READ_VDSOX32 := 1 + endif + ifndef NO_PERF_READ_VDSOX32 + $(call feature_check,compile-x32) + ifeq ($(feature-compile-x32), 1) + CFLAGS += -DHAVE_PERF_READ_VDSOX32 + else + NO_PERF_READ_VDSOX32 := 1 + endif + endif +else + NO_PERF_READ_VDSO32 := 1 + NO_PERF_READ_VDSOX32 := 1 +endif + # Among the variables below, these: # perfexecdir # template_dir diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch index 4b06719ee984..ac8721ffa6c8 100644 --- a/tools/perf/config/Makefile.arch +++ b/tools/perf/config/Makefile.arch @@ -1,7 +1,7 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ +RAW_ARCH := $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/arm.*/arm/ -e s/sa110/arm/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ @@ -9,15 +9,27 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/tile.*/tile/ ) # Additional ARCH settings for x86 -ifeq ($(ARCH),i386) - override ARCH := x86 +ifeq ($(RAW_ARCH),i386) + ARCH ?= x86 endif -ifeq ($(ARCH),x86_64) - override ARCH := x86 - IS_X86_64 := 0 - ifeq (, $(findstring m32,$(CFLAGS))) - IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1) - RAW_ARCH := x86_64 +ifeq ($(RAW_ARCH),x86_64) + ARCH ?= x86 + + ifneq (, $(findstring m32,$(CFLAGS))) + RAW_ARCH := x86_32 endif endif + +ifeq ($(RAW_ARCH),sparc64) + ARCH ?= sparc +endif + +ARCH ?= $(RAW_ARCH) + +LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) +ifeq ($(LP64), 1) + IS_64_BIT := 1 +else + IS_64_BIT := 0 +endif diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile index 72ab2984718e..b32ff3372514 100644 --- a/tools/perf/config/feature-checks/Makefile +++ b/tools/perf/config/feature-checks/Makefile @@ -25,9 +25,13 @@ FILES= \ test-libslang.bin \ test-libunwind.bin \ test-libunwind-debug-frame.bin \ + test-pthread-attr-setaffinity-np.bin \ test-stackprotector-all.bin \ test-timerfd.bin \ - test-libdw-dwarf-unwind.bin + test-libdw-dwarf-unwind.bin \ + test-compile-32.bin \ + test-compile-x32.bin \ + test-zlib.bin CC := $(CROSS_COMPILE)gcc -MD PKG_CONFIG := $(CROSS_COMPILE)pkg-config @@ -39,11 +43,14 @@ BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS) ############################### test-all.bin: - $(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl + $(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz test-hello.bin: $(BUILD) +test-pthread-attr-setaffinity-np.bin: + $(BUILD) -D_GNU_SOURCE -Werror -lpthread + test-stackprotector-all.bin: $(BUILD) -Werror -fstack-protector-all @@ -131,6 +138,15 @@ test-libdw-dwarf-unwind.bin: test-sync-compare-and-swap.bin: $(BUILD) -Werror +test-compile-32.bin: + $(CC) -m32 -o $(OUTPUT)$@ test-compile.c + +test-compile-x32.bin: + $(CC) -mx32 -o $(OUTPUT)$@ test-compile.c + +test-zlib.bin: + $(BUILD) -lz + -include *.d ############################### diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c index a7d022e161c0..6d4d09323922 100644 --- a/tools/perf/config/feature-checks/test-all.c +++ b/tools/perf/config/feature-checks/test-all.c @@ -93,6 +93,14 @@ # include "test-sync-compare-and-swap.c" #undef main +#define main main_test_zlib +# include "test-zlib.c" +#undef main + +#define main main_test_pthread_attr_setaffinity_np +# include "test-pthread_attr_setaffinity_np.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -116,6 +124,8 @@ int main(int argc, char *argv[]) main_test_stackprotector_all(); main_test_libdw_dwarf_unwind(); main_test_sync_compare_and_swap(argc, argv); + main_test_zlib(); + main_test_pthread_attr_setaffinity_np(); return 0; } diff --git a/tools/perf/config/feature-checks/test-compile.c b/tools/perf/config/feature-checks/test-compile.c new file mode 100644 index 000000000000..31dbf45bf99c --- /dev/null +++ b/tools/perf/config/feature-checks/test-compile.c @@ -0,0 +1,4 @@ +int main(void) +{ + return 0; +} diff --git a/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c new file mode 100644 index 000000000000..2b81b72eca23 --- /dev/null +++ b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c @@ -0,0 +1,15 @@ +#include <stdint.h> +#include <pthread.h> + +int main(void) +{ + int ret = 0; + pthread_attr_t thread_attr; + cpu_set_t cs; + + pthread_attr_init(&thread_attr); + /* don't care abt exact args, just the API itself in libpthread */ + ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cs), &cs); + + return ret; +} diff --git a/tools/perf/config/feature-checks/test-zlib.c b/tools/perf/config/feature-checks/test-zlib.c new file mode 100644 index 000000000000..e111fff6240e --- /dev/null +++ b/tools/perf/config/feature-checks/test-zlib.c @@ -0,0 +1,9 @@ +#include <zlib.h> + +int main(void) +{ + z_stream zs; + + inflateInit(&zs); + return 0; +} diff --git a/tools/perf/perf-read-vdso.c b/tools/perf/perf-read-vdso.c new file mode 100644 index 000000000000..764e2547c25a --- /dev/null +++ b/tools/perf/perf-read-vdso.c @@ -0,0 +1,34 @@ +#include <stdio.h> +#include <string.h> + +#define VDSO__MAP_NAME "[vdso]" + +/* + * Include definition of find_vdso_map() also used in util/vdso.c for + * building perf. + */ +#include "util/find-vdso-map.c" + +int main(void) +{ + void *start, *end; + size_t size, written; + + if (find_vdso_map(&start, &end)) + return 1; + + size = end - start; + + while (size) { + written = fwrite(start, 1, size, stdout); + if (!written) + return 1; + start += written; + size -= written; + } + + if (fflush(stdout)) + return 1; + + return 0; +} diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h index a3b13d7dc1d4..6ef68165c9db 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -6,7 +6,6 @@ #include <sys/syscall.h> #include <linux/types.h> #include <linux/perf_event.h> -#include <asm/unistd.h> #if defined(__i386__) #define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 452a8474d29d..3700a7faca6c 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -200,6 +200,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) *envchanged = 1; (*argv)++; (*argc)--; + } else if (!strcmp(cmd, "--buildid-dir")) { + if (*argc < 2) { + fprintf(stderr, "No directory given for --buildid-dir.\n"); + usage(perf_usage_string); + } + set_buildid_dir((*argv)[1]); + if (envchanged) + *envchanged = 1; + (*argv)++; + (*argc)--; } else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) { perf_debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR)); fprintf(stderr, "dir: %s\n", debugfs_mountpoint); @@ -499,7 +509,7 @@ int main(int argc, const char **argv) } if (!prefixcmp(cmd, "trace")) { #ifdef HAVE_LIBAUDIT_SUPPORT - set_buildid_dir(); + set_buildid_dir(NULL); setup_path(); argv[0] = "trace"; return cmd_trace(argc, argv, NULL); @@ -514,7 +524,7 @@ int main(int argc, const char **argv) argc--; handle_options(&argv, &argc, NULL); commit_pager_choice(); - set_buildid_dir(); + set_buildid_dir(NULL); if (argc > 0) { if (!prefixcmp(argv[0], "--")) diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 220d44e44c1b..1dabb8553499 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -52,6 +52,7 @@ struct record_opts { bool sample_weight; bool sample_time; bool period; + bool sample_intr_regs; unsigned int freq; unsigned int mmap_pages; unsigned int user_freq; @@ -62,4 +63,7 @@ struct record_opts { unsigned initial_delay; }; +struct option; +extern const char * const *record_usage; +extern struct option *record_options; #endif diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c index 790ceba6ad3f..28431d1bbcf5 100644 --- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c +++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c @@ -5,7 +5,10 @@ * ANY CHANGES MADE HERE WILL BE LOST! * */ - +#include <stdbool.h> +#ifndef HAS_BOOL +# define HAS_BOOL 1 +#endif #line 1 "Context.xs" /* * Context.xs. XS interfaces for perf script. diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-record b/tools/perf/scripts/python/bin/export-to-postgresql-record new file mode 100644 index 000000000000..221d66e05713 --- /dev/null +++ b/tools/perf/scripts/python/bin/export-to-postgresql-record @@ -0,0 +1,8 @@ +#!/bin/bash + +# +# export perf data to a postgresql database. Can cover +# perf ip samples (excluding the tracepoints). No special +# record requirements, just record what you want to export. +# +perf record $@ diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-report b/tools/perf/scripts/python/bin/export-to-postgresql-report new file mode 100644 index 000000000000..cd335b6e2a01 --- /dev/null +++ b/tools/perf/scripts/python/bin/export-to-postgresql-report @@ -0,0 +1,29 @@ +#!/bin/bash +# description: export perf data to a postgresql database +# args: [database name] [columns] [calls] +n_args=0 +for i in "$@" +do + if expr match "$i" "-" > /dev/null ; then + break + fi + n_args=$(( $n_args + 1 )) +done +if [ "$n_args" -gt 3 ] ; then + echo "usage: export-to-postgresql-report [database name] [columns] [calls]" + exit +fi +if [ "$n_args" -gt 2 ] ; then + dbname=$1 + columns=$2 + calls=$3 + shift 3 +elif [ "$n_args" -gt 1 ] ; then + dbname=$1 + columns=$2 + shift 2 +elif [ "$n_args" -gt 0 ] ; then + dbname=$1 + shift +fi +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns $calls diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py new file mode 100644 index 000000000000..4cdafd880074 --- /dev/null +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -0,0 +1,444 @@ +# export-to-postgresql.py: export perf data to a postgresql database +# Copyright (c) 2014, Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope it will be useful, but WITHOUT +# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. + +import os +import sys +import struct +import datetime + +from PySide.QtSql import * + +# Need to access PostgreSQL C library directly to use COPY FROM STDIN +from ctypes import * +libpq = CDLL("libpq.so.5") +PQconnectdb = libpq.PQconnectdb +PQconnectdb.restype = c_void_p +PQfinish = libpq.PQfinish +PQstatus = libpq.PQstatus +PQexec = libpq.PQexec +PQexec.restype = c_void_p +PQresultStatus = libpq.PQresultStatus +PQputCopyData = libpq.PQputCopyData +PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ] +PQputCopyEnd = libpq.PQputCopyEnd +PQputCopyEnd.argtypes = [ c_void_p, c_void_p ] + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +# These perf imports are not used at present +#from perf_trace_context import * +#from Core import * + +perf_db_export_mode = True +perf_db_export_calls = False + +def usage(): + print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>]" + print >> sys.stderr, "where: columns 'all' or 'branches'" + print >> sys.stderr, " calls 'calls' => create calls table" + raise Exception("Too few arguments") + +if (len(sys.argv) < 2): + usage() + +dbname = sys.argv[1] + +if (len(sys.argv) >= 3): + columns = sys.argv[2] +else: + columns = "all" + +if columns not in ("all", "branches"): + usage() + +branches = (columns == "branches") + +if (len(sys.argv) >= 4): + if (sys.argv[3] == "calls"): + perf_db_export_calls = True + else: + usage() + +output_dir_name = os.getcwd() + "/" + dbname + "-perf-data" +os.mkdir(output_dir_name) + +def do_query(q, s): + if (q.exec_(s)): + return + raise Exception("Query failed: " + q.lastError().text()) + +print datetime.datetime.today(), "Creating database..." + +db = QSqlDatabase.addDatabase('QPSQL') +query = QSqlQuery(db) +db.setDatabaseName('postgres') +db.open() +try: + do_query(query, 'CREATE DATABASE ' + dbname) +except: + os.rmdir(output_dir_name) + raise +query.finish() +query.clear() +db.close() + +db.setDatabaseName(dbname) +db.open() + +query = QSqlQuery(db) +do_query(query, 'SET client_min_messages TO WARNING') + +do_query(query, 'CREATE TABLE selected_events (' + 'id bigint NOT NULL,' + 'name varchar(80))') +do_query(query, 'CREATE TABLE machines (' + 'id bigint NOT NULL,' + 'pid integer,' + 'root_dir varchar(4096))') +do_query(query, 'CREATE TABLE threads (' + 'id bigint NOT NULL,' + 'machine_id bigint,' + 'process_id bigint,' + 'pid integer,' + 'tid integer)') +do_query(query, 'CREATE TABLE comms (' + 'id bigint NOT NULL,' + 'comm varchar(16))') +do_query(query, 'CREATE TABLE comm_threads (' + 'id bigint NOT NULL,' + 'comm_id bigint,' + 'thread_id bigint)') +do_query(query, 'CREATE TABLE dsos (' + 'id bigint NOT NULL,' + 'machine_id bigint,' + 'short_name varchar(256),' + 'long_name varchar(4096),' + 'build_id varchar(64))') +do_query(query, 'CREATE TABLE symbols (' + 'id bigint NOT NULL,' + 'dso_id bigint,' + 'sym_start bigint,' + 'sym_end bigint,' + 'binding integer,' + 'name varchar(2048))') +do_query(query, 'CREATE TABLE branch_types (' + 'id integer NOT NULL,' + 'name varchar(80))') + +if branches: + do_query(query, 'CREATE TABLE samples (' + 'id bigint NOT NULL,' + 'evsel_id bigint,' + 'machine_id bigint,' + 'thread_id bigint,' + 'comm_id bigint,' + 'dso_id bigint,' + 'symbol_id bigint,' + 'sym_offset bigint,' + 'ip bigint,' + 'time bigint,' + 'cpu integer,' + 'to_dso_id bigint,' + 'to_symbol_id bigint,' + 'to_sym_offset bigint,' + 'to_ip bigint,' + 'branch_type integer,' + 'in_tx boolean)') +else: + do_query(query, 'CREATE TABLE samples (' + 'id bigint NOT NULL,' + 'evsel_id bigint,' + 'machine_id bigint,' + 'thread_id bigint,' + 'comm_id bigint,' + 'dso_id bigint,' + 'symbol_id bigint,' + 'sym_offset bigint,' + 'ip bigint,' + 'time bigint,' + 'cpu integer,' + 'to_dso_id bigint,' + 'to_symbol_id bigint,' + 'to_sym_offset bigint,' + 'to_ip bigint,' + 'period bigint,' + 'weight bigint,' + 'transaction bigint,' + 'data_src bigint,' + 'branch_type integer,' + 'in_tx boolean)') + +if perf_db_export_calls: + do_query(query, 'CREATE TABLE call_paths (' + 'id bigint NOT NULL,' + 'parent_id bigint,' + 'symbol_id bigint,' + 'ip bigint)') + do_query(query, 'CREATE TABLE calls (' + 'id bigint NOT NULL,' + 'thread_id bigint,' + 'comm_id bigint,' + 'call_path_id bigint,' + 'call_time bigint,' + 'return_time bigint,' + 'branch_count bigint,' + 'call_id bigint,' + 'return_id bigint,' + 'parent_call_path_id bigint,' + 'flags integer)') + +do_query(query, 'CREATE VIEW samples_view AS ' + 'SELECT ' + 'id,' + 'time,' + 'cpu,' + '(SELECT pid FROM threads WHERE id = thread_id) AS pid,' + '(SELECT tid FROM threads WHERE id = thread_id) AS tid,' + '(SELECT comm FROM comms WHERE id = comm_id) AS command,' + '(SELECT name FROM selected_events WHERE id = evsel_id) AS event,' + 'to_hex(ip) AS ip_hex,' + '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,' + 'sym_offset,' + '(SELECT short_name FROM dsos WHERE id = dso_id) AS dso_short_name,' + 'to_hex(to_ip) AS to_ip_hex,' + '(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,' + 'to_sym_offset,' + '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,' + '(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,' + 'in_tx' + ' FROM samples') + + +file_header = struct.pack("!11sii", "PGCOPY\n\377\r\n\0", 0, 0) +file_trailer = "\377\377" + +def open_output_file(file_name): + path_name = output_dir_name + "/" + file_name + file = open(path_name, "w+") + file.write(file_header) + return file + +def close_output_file(file): + file.write(file_trailer) + file.close() + +def copy_output_file_direct(file, table_name): + close_output_file(file) + sql = "COPY " + table_name + " FROM '" + file.name + "' (FORMAT 'binary')" + do_query(query, sql) + +# Use COPY FROM STDIN because security may prevent postgres from accessing the files directly +def copy_output_file(file, table_name): + conn = PQconnectdb("dbname = " + dbname) + if (PQstatus(conn)): + raise Exception("COPY FROM STDIN PQconnectdb failed") + file.write(file_trailer) + file.seek(0) + sql = "COPY " + table_name + " FROM STDIN (FORMAT 'binary')" + res = PQexec(conn, sql) + if (PQresultStatus(res) != 4): + raise Exception("COPY FROM STDIN PQexec failed") + data = file.read(65536) + while (len(data)): + ret = PQputCopyData(conn, data, len(data)) + if (ret != 1): + raise Exception("COPY FROM STDIN PQputCopyData failed, error " + str(ret)) + data = file.read(65536) + ret = PQputCopyEnd(conn, None) + if (ret != 1): + raise Exception("COPY FROM STDIN PQputCopyEnd failed, error " + str(ret)) + PQfinish(conn) + +def remove_output_file(file): + name = file.name + file.close() + os.unlink(name) + +evsel_file = open_output_file("evsel_table.bin") +machine_file = open_output_file("machine_table.bin") +thread_file = open_output_file("thread_table.bin") +comm_file = open_output_file("comm_table.bin") +comm_thread_file = open_output_file("comm_thread_table.bin") +dso_file = open_output_file("dso_table.bin") +symbol_file = open_output_file("symbol_table.bin") +branch_type_file = open_output_file("branch_type_table.bin") +sample_file = open_output_file("sample_table.bin") +if perf_db_export_calls: + call_path_file = open_output_file("call_path_table.bin") + call_file = open_output_file("call_table.bin") + +def trace_begin(): + print datetime.datetime.today(), "Writing to intermediate files..." + # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs + evsel_table(0, "unknown") + machine_table(0, 0, "unknown") + thread_table(0, 0, 0, -1, -1) + comm_table(0, "unknown") + dso_table(0, 0, "unknown", "unknown", "") + symbol_table(0, 0, 0, 0, 0, "unknown") + sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) + if perf_db_export_calls: + call_path_table(0, 0, 0, 0) + +unhandled_count = 0 + +def trace_end(): + print datetime.datetime.today(), "Copying to database..." + copy_output_file(evsel_file, "selected_events") + copy_output_file(machine_file, "machines") + copy_output_file(thread_file, "threads") + copy_output_file(comm_file, "comms") + copy_output_file(comm_thread_file, "comm_threads") + copy_output_file(dso_file, "dsos") + copy_output_file(symbol_file, "symbols") + copy_output_file(branch_type_file, "branch_types") + copy_output_file(sample_file, "samples") + if perf_db_export_calls: + copy_output_file(call_path_file, "call_paths") + copy_output_file(call_file, "calls") + + print datetime.datetime.today(), "Removing intermediate files..." + remove_output_file(evsel_file) + remove_output_file(machine_file) + remove_output_file(thread_file) + remove_output_file(comm_file) + remove_output_file(comm_thread_file) + remove_output_file(dso_file) + remove_output_file(symbol_file) + remove_output_file(branch_type_file) + remove_output_file(sample_file) + if perf_db_export_calls: + remove_output_file(call_path_file) + remove_output_file(call_file) + os.rmdir(output_dir_name) + print datetime.datetime.today(), "Adding primary keys" + do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE machines ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE threads ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE comms ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE comm_threads ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE dsos ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE symbols ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE branch_types ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE samples ADD PRIMARY KEY (id)') + if perf_db_export_calls: + do_query(query, 'ALTER TABLE call_paths ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)') + + print datetime.datetime.today(), "Adding foreign keys" + do_query(query, 'ALTER TABLE threads ' + 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id),' + 'ADD CONSTRAINT processfk FOREIGN KEY (process_id) REFERENCES threads (id)') + do_query(query, 'ALTER TABLE comm_threads ' + 'ADD CONSTRAINT commfk FOREIGN KEY (comm_id) REFERENCES comms (id),' + 'ADD CONSTRAINT threadfk FOREIGN KEY (thread_id) REFERENCES threads (id)') + do_query(query, 'ALTER TABLE dsos ' + 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id)') + do_query(query, 'ALTER TABLE symbols ' + 'ADD CONSTRAINT dsofk FOREIGN KEY (dso_id) REFERENCES dsos (id)') + do_query(query, 'ALTER TABLE samples ' + 'ADD CONSTRAINT evselfk FOREIGN KEY (evsel_id) REFERENCES selected_events (id),' + 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id),' + 'ADD CONSTRAINT threadfk FOREIGN KEY (thread_id) REFERENCES threads (id),' + 'ADD CONSTRAINT commfk FOREIGN KEY (comm_id) REFERENCES comms (id),' + 'ADD CONSTRAINT dsofk FOREIGN KEY (dso_id) REFERENCES dsos (id),' + 'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id),' + 'ADD CONSTRAINT todsofk FOREIGN KEY (to_dso_id) REFERENCES dsos (id),' + 'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols (id)') + if perf_db_export_calls: + do_query(query, 'ALTER TABLE call_paths ' + 'ADD CONSTRAINT parentfk FOREIGN KEY (parent_id) REFERENCES call_paths (id),' + 'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id)') + do_query(query, 'ALTER TABLE calls ' + 'ADD CONSTRAINT threadfk FOREIGN KEY (thread_id) REFERENCES threads (id),' + 'ADD CONSTRAINT commfk FOREIGN KEY (comm_id) REFERENCES comms (id),' + 'ADD CONSTRAINT call_pathfk FOREIGN KEY (call_path_id) REFERENCES call_paths (id),' + 'ADD CONSTRAINT callfk FOREIGN KEY (call_id) REFERENCES samples (id),' + 'ADD CONSTRAINT returnfk FOREIGN KEY (return_id) REFERENCES samples (id),' + 'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)') + do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)') + + if (unhandled_count): + print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events" + print datetime.datetime.today(), "Done" + +def trace_unhandled(event_name, context, event_fields_dict): + global unhandled_count + unhandled_count += 1 + +def sched__sched_switch(*x): + pass + +def evsel_table(evsel_id, evsel_name, *x): + n = len(evsel_name) + fmt = "!hiqi" + str(n) + "s" + value = struct.pack(fmt, 2, 8, evsel_id, n, evsel_name) + evsel_file.write(value) + +def machine_table(machine_id, pid, root_dir, *x): + n = len(root_dir) + fmt = "!hiqiii" + str(n) + "s" + value = struct.pack(fmt, 3, 8, machine_id, 4, pid, n, root_dir) + machine_file.write(value) + +def thread_table(thread_id, machine_id, process_id, pid, tid, *x): + value = struct.pack("!hiqiqiqiiii", 5, 8, thread_id, 8, machine_id, 8, process_id, 4, pid, 4, tid) + thread_file.write(value) + +def comm_table(comm_id, comm_str, *x): + n = len(comm_str) + fmt = "!hiqi" + str(n) + "s" + value = struct.pack(fmt, 2, 8, comm_id, n, comm_str) + comm_file.write(value) + +def comm_thread_table(comm_thread_id, comm_id, thread_id, *x): + fmt = "!hiqiqiq" + value = struct.pack(fmt, 3, 8, comm_thread_id, 8, comm_id, 8, thread_id) + comm_thread_file.write(value) + +def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x): + n1 = len(short_name) + n2 = len(long_name) + n3 = len(build_id) + fmt = "!hiqiqi" + str(n1) + "si" + str(n2) + "si" + str(n3) + "s" + value = struct.pack(fmt, 5, 8, dso_id, 8, machine_id, n1, short_name, n2, long_name, n3, build_id) + dso_file.write(value) + +def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x): + n = len(symbol_name) + fmt = "!hiqiqiqiqiii" + str(n) + "s" + value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name) + symbol_file.write(value) + +def branch_type_table(branch_type, name, *x): + n = len(name) + fmt = "!hiii" + str(n) + "s" + value = struct.pack(fmt, 2, 4, branch_type, n, name) + branch_type_file.write(value) + +def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, *x): + if branches: + value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiB", 17, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx) + else: + value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx) + sample_file.write(value) + +def call_path_table(cp_id, parent_id, symbol_id, ip, *x): + fmt = "!hiqiqiqiq" + value = struct.pack(fmt, 4, 8, cp_id, 8, parent_id, 8, symbol_id, 8, ip) + call_path_file.write(value) + +def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, *x): + fmt = "!hiqiqiqiqiqiqiqiqiqiqii" + value = struct.pack(fmt, 11, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags) + call_file.write(value) diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index c9b4b6269b51..1091bd47adfd 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -104,7 +104,6 @@ class Event(dict): continue if not self.compare_data(self[t], other[t]): log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) - # Test file description needs to have following sections: # [config] diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index f710b92ccff6..d3095dafed36 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0|1 -size=96 +size=104 config=0 sample_period=4000 sample_type=263 diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index dc3ada2470c0..872ed7e24c7c 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0 -size=96 +size=104 config=0 sample_period=0 sample_type=0 diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 162c978f1491..4b7d9ab0f049 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -85,7 +85,7 @@ static struct test { .func = test__hists_link, }, { - .desc = "Try 'use perf' in python, checking link problems", + .desc = "Try 'import perf' in python, checking link problems", .func = test__python_use, }, { diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 67f2d6323558..f671ec37a7c4 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -133,8 +133,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf, } static int read_object_code(u64 addr, size_t len, u8 cpumode, - struct thread *thread, struct machine *machine, - struct state *state) + struct thread *thread, struct state *state) { struct addr_location al; unsigned char buf1[BUFSZ]; @@ -145,8 +144,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, addr, - &al); + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al); if (!al.map || !al.map->dso) { pr_debug("thread__find_addr_map failed\n"); return -1; @@ -170,8 +168,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, len = al.map->end - addr; /* Read the object code using perf */ - ret_len = dso__data_read_offset(al.map->dso, machine, al.addr, buf1, - len); + ret_len = dso__data_read_offset(al.map->dso, thread->mg->machine, + al.addr, buf1, len); if (ret_len != len) { pr_debug("dso__data_read_offset failed\n"); return -1; @@ -264,8 +262,7 @@ static int process_sample_event(struct machine *machine, cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - return read_object_code(sample.ip, READLEN, cpumode, thread, machine, - state); + return read_object_code(sample.ip, READLEN, cpumode, thread, state); } static int process_event(struct machine *machine, struct perf_evlist *evlist, diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index fc25e57f4a5d..0bf06bec68c7 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -11,6 +11,9 @@ #include "thread.h" #include "callchain.h" +/* For bsearch. We try to unwind functions in shared object. */ +#include <stdlib.h> + static int mmap_handler(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -28,7 +31,7 @@ static int init_live_machine(struct machine *machine) mmap_handler, machine, true); } -#define MAX_STACK 6 +#define MAX_STACK 8 static int unwind_entry(struct unwind_entry *entry, void *arg) { @@ -37,6 +40,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) static const char *funcs[MAX_STACK] = { "test__arch_unwind_sample", "unwind_thread", + "compare", + "bsearch", "krava_3", "krava_2", "krava_1", @@ -59,7 +64,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) } __attribute__ ((noinline)) -static int unwind_thread(struct thread *thread, struct machine *machine) +static int unwind_thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -72,7 +77,7 @@ static int unwind_thread(struct thread *thread, struct machine *machine) goto out; } - err = unwind__get_entries(unwind_entry, &cnt, machine, thread, + err = unwind__get_entries(unwind_entry, &cnt, thread, &sample, MAX_STACK); if (err) pr_debug("unwind failed\n"); @@ -88,22 +93,49 @@ static int unwind_thread(struct thread *thread, struct machine *machine) return err; } +static int global_unwind_retval = -INT_MAX; + +__attribute__ ((noinline)) +static int compare(void *p1, void *p2) +{ + /* Any possible value should be 'thread' */ + struct thread *thread = *(struct thread **)p1; + + if (global_unwind_retval == -INT_MAX) + global_unwind_retval = unwind_thread(thread); + + return p1 - p2; +} + __attribute__ ((noinline)) -static int krava_3(struct thread *thread, struct machine *machine) +static int krava_3(struct thread *thread) { - return unwind_thread(thread, machine); + struct thread *array[2] = {thread, thread}; + void *fp = &bsearch; + /* + * make _bsearch a volatile function pointer to + * prevent potential optimization, which may expand + * bsearch and call compare directly from this function, + * instead of libc shared object. + */ + void *(*volatile _bsearch)(void *, void *, size_t, + size_t, int (*)(void *, void *)); + + _bsearch = fp; + _bsearch(array, &thread, 2, sizeof(struct thread **), compare); + return global_unwind_retval; } __attribute__ ((noinline)) -static int krava_2(struct thread *thread, struct machine *machine) +static int krava_2(struct thread *thread) { - return krava_3(thread, machine); + return krava_3(thread); } __attribute__ ((noinline)) -static int krava_1(struct thread *thread, struct machine *machine) +static int krava_1(struct thread *thread) { - return krava_2(thread, machine); + return krava_2(thread); } int test__dwarf_unwind(void) @@ -137,7 +169,7 @@ int test__dwarf_unwind(void) goto out; } - err = krava_1(thread, machine); + err = krava_1(thread); out: machine__delete_threads(machine); diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 614d5c4978ab..18619966454c 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -140,7 +140,7 @@ static void del_hist_entries(struct hists *hists) he = rb_entry(node, struct hist_entry, rb_node); rb_erase(node, root_out); rb_erase(&he->rb_node_in, root_in); - hist_entry__free(he); + hist_entry__delete(he); } } @@ -187,7 +187,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec * function since TEST_ASSERT_VAL() returns in case of failure. */ hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("use callchain: %d, cumulate callchain: %d\n", @@ -454,12 +454,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) * 30.00% 10.00% perf perf [.] cmd_record * 20.00% 0.00% bash libc [.] malloc * 10.00% 10.00% bash [kernel] [k] page_fault - * 10.00% 10.00% perf [kernel] [k] schedule - * 10.00% 0.00% perf [kernel] [k] sys_perf_event_open + * 10.00% 10.00% bash bash [.] xmalloc * 10.00% 10.00% perf [kernel] [k] page_fault - * 10.00% 10.00% perf libc [.] free * 10.00% 10.00% perf libc [.] malloc - * 10.00% 10.00% bash bash [.] xmalloc + * 10.00% 10.00% perf [kernel] [k] schedule + * 10.00% 10.00% perf libc [.] free + * 10.00% 0.00% perf [kernel] [k] sys_perf_event_open */ struct result expected[] = { { 7000, 2000, "perf", "perf", "main" }, @@ -468,12 +468,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) { 3000, 1000, "perf", "perf", "cmd_record" }, { 2000, 0, "bash", "libc", "malloc" }, { 1000, 1000, "bash", "[kernel]", "page_fault" }, - { 1000, 1000, "perf", "[kernel]", "schedule" }, - { 1000, 0, "perf", "[kernel]", "sys_perf_event_open" }, + { 1000, 1000, "bash", "bash", "xmalloc" }, { 1000, 1000, "perf", "[kernel]", "page_fault" }, + { 1000, 1000, "perf", "[kernel]", "schedule" }, { 1000, 1000, "perf", "libc", "free" }, { 1000, 1000, "perf", "libc", "malloc" }, - { 1000, 1000, "bash", "bash", "xmalloc" }, + { 1000, 0, "perf", "[kernel]", "sys_perf_event_open" }, }; symbol_conf.use_callchain = false; @@ -537,10 +537,13 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) * malloc * main * - * 10.00% 10.00% perf [kernel] [k] schedule + * 10.00% 10.00% bash bash [.] xmalloc * | - * --- schedule - * run_command + * --- xmalloc + * malloc + * xmalloc <--- NOTE: there's a cycle + * malloc + * xmalloc * main * * 10.00% 0.00% perf [kernel] [k] sys_perf_event_open @@ -556,6 +559,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) * run_command * main * + * 10.00% 10.00% perf [kernel] [k] schedule + * | + * --- schedule + * run_command + * main + * * 10.00% 10.00% perf libc [.] free * | * --- free @@ -570,15 +579,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) * run_command * main * - * 10.00% 10.00% bash bash [.] xmalloc - * | - * --- xmalloc - * malloc - * xmalloc <--- NOTE: there's a cycle - * malloc - * xmalloc - * main - * */ struct result expected[] = { { 7000, 2000, "perf", "perf", "main" }, @@ -587,12 +587,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) { 3000, 1000, "perf", "perf", "cmd_record" }, { 2000, 0, "bash", "libc", "malloc" }, { 1000, 1000, "bash", "[kernel]", "page_fault" }, - { 1000, 1000, "perf", "[kernel]", "schedule" }, + { 1000, 1000, "bash", "bash", "xmalloc" }, { 1000, 0, "perf", "[kernel]", "sys_perf_event_open" }, { 1000, 1000, "perf", "[kernel]", "page_fault" }, + { 1000, 1000, "perf", "[kernel]", "schedule" }, { 1000, 1000, "perf", "libc", "free" }, { 1000, 1000, "perf", "libc", "malloc" }, - { 1000, 1000, "bash", "bash", "xmalloc" }, }; struct callchain_result expected_callchain[] = { { @@ -622,9 +622,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) { "bash", "main" }, }, }, { - 3, { { "[kernel]", "schedule" }, - { "perf", "run_command" }, - { "perf", "main" }, }, + 6, { { "bash", "xmalloc" }, + { "libc", "malloc" }, + { "bash", "xmalloc" }, + { "libc", "malloc" }, + { "bash", "xmalloc" }, + { "bash", "main" }, }, }, { 3, { { "[kernel]", "sys_perf_event_open" }, @@ -638,6 +641,11 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) { "perf", "main" }, }, }, { + 3, { { "[kernel]", "schedule" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { 4, { { "libc", "free" }, { "perf", "cmd_record" }, { "perf", "run_command" }, @@ -649,14 +657,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) { "perf", "run_command" }, { "perf", "main" }, }, }, - { - 6, { { "bash", "xmalloc" }, - { "libc", "malloc" }, - { "bash", "xmalloc" }, - { "libc", "malloc" }, - { "bash", "xmalloc" }, - { "bash", "main" }, }, - }, }; symbol_conf.use_callchain = true; diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 5a31787cc6b9..59e53db7914c 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -43,7 +43,7 @@ static struct sample fake_samples[] = { }; static int add_hist_entries(struct perf_evlist *evlist, - struct machine *machine __maybe_unused) + struct machine *machine) { struct perf_evsel *evsel; struct addr_location al; @@ -138,7 +138,7 @@ int test__hists_filter(void) struct hists *hists = evsel__hists(evsel); hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("Normal histogram\n"); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index a748f2be1222..b52c9faea224 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -106,7 +106,7 @@ static void del_hist_entries(struct hists *hists) he = rb_entry(node, struct hist_entry, rb_node); rb_erase(node, root_out); rb_erase(&he->rb_node_in, root_in); - hist_entry__free(he); + hist_entry__delete(he); } } @@ -152,7 +152,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -252,7 +252,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -306,7 +306,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -384,7 +384,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -487,7 +487,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 69a71ff84e01..75709d2b17b4 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -222,7 +222,6 @@ tarpkg: @cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \ echo "- $@: $$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1 - all: $(run) $(run_O) tarpkg @echo OK diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 4a456fef66ca..2113f1c8611f 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -187,7 +187,7 @@ static int mmap_events(synth_cb synth) pr_debug("looking for map %p\n", td->map); - thread__find_addr_map(thread, machine, + thread__find_addr_map(thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, (unsigned long) (td->map + 1), &al); diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 7f2f51f93619..1cdab0ce00e2 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1145,6 +1145,49 @@ static int test__pinned_group(struct perf_evlist *evlist) return 0; } +static int test__checkevent_breakpoint_len(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) == + evsel->attr.bp_type); + TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_1 == + evsel->attr.bp_len); + + return 0; +} + +static int test__checkevent_breakpoint_len_w(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_W == + evsel->attr.bp_type); + TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_2 == + evsel->attr.bp_len); + + return 0; +} + +static int +test__checkevent_breakpoint_len_rw_modifier(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + + return test__checkevent_breakpoint_rw(evlist); +} + static int count_tracepoints(void) { char events_path[PATH_MAX]; @@ -1420,6 +1463,21 @@ static struct evlist_test test__events[] = { .check = test__pinned_group, .id = 41, }, + { + .name = "mem:0/1", + .check = test__checkevent_breakpoint_len, + .id = 42, + }, + { + .name = "mem:0/2:w", + .check = test__checkevent_breakpoint_len_w, + .id = 43, + }, + { + .name = "mem:0/4:rw:u", + .check = test__checkevent_breakpoint_len_rw_modifier, + .id = 44 + }, #if defined(__s390x__) { .name = "kvm-s390:kvm_s390_create_vm", @@ -1471,7 +1529,7 @@ static int test_event(struct evlist_test *e) } else { ret = e->check(evlist); } - + perf_evlist__delete(evlist); return ret; diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index ca292f9a4ae2..30c02181e78b 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -110,7 +110,7 @@ static bool samples_same(const struct perf_sample *s1, if (type & PERF_SAMPLE_STACK_USER) { COMP(user_stack.size); - if (memcmp(s1->user_stack.data, s1->user_stack.data, + if (memcmp(s1->user_stack.data, s2->user_stack.data, s1->user_stack.size)) { pr_debug("Samples differ at 'user_stack'\n"); return false; @@ -126,16 +126,28 @@ static bool samples_same(const struct perf_sample *s1, if (type & PERF_SAMPLE_TRANSACTION) COMP(transaction); + if (type & PERF_SAMPLE_REGS_INTR) { + size_t sz = hweight_long(s1->intr_regs.mask) * sizeof(u64); + + COMP(intr_regs.mask); + COMP(intr_regs.abi); + if (s1->intr_regs.abi && + (!s1->intr_regs.regs || !s2->intr_regs.regs || + memcmp(s1->intr_regs.regs, s2->intr_regs.regs, sz))) { + pr_debug("Samples differ at 'intr_regs'\n"); + return false; + } + } + return true; } -static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) +static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) { struct perf_evsel evsel = { .needs_swap = false, .attr = { .sample_type = sample_type, - .sample_regs_user = sample_regs_user, .read_format = read_format, }, }; @@ -154,7 +166,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) /* 1 branch_entry */ .data = {1, 211, 212, 213}, }; - u64 user_regs[64]; + u64 regs[64]; const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL}; const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL}; struct perf_sample sample = { @@ -176,8 +188,8 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) .branch_stack = &branch_stack.branch_stack, .user_regs = { .abi = PERF_SAMPLE_REGS_ABI_64, - .mask = sample_regs_user, - .regs = user_regs, + .mask = sample_regs, + .regs = regs, }, .user_stack = { .size = sizeof(data), @@ -187,14 +199,25 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) .time_enabled = 0x030a59d664fca7deULL, .time_running = 0x011b6ae553eb98edULL, }, + .intr_regs = { + .abi = PERF_SAMPLE_REGS_ABI_64, + .mask = sample_regs, + .regs = regs, + }, }; struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},}; struct perf_sample sample_out; size_t i, sz, bufsz; int err, ret = -1; - for (i = 0; i < sizeof(user_regs); i++) - *(i + (u8 *)user_regs) = i & 0xfe; + if (sample_type & PERF_SAMPLE_REGS_USER) + evsel.attr.sample_regs_user = sample_regs; + + if (sample_type & PERF_SAMPLE_REGS_INTR) + evsel.attr.sample_regs_intr = sample_regs; + + for (i = 0; i < sizeof(regs); i++) + *(i + (u8 *)regs) = i & 0xfe; if (read_format & PERF_FORMAT_GROUP) { sample.read.group.nr = 4; @@ -271,7 +294,7 @@ int test__sample_parsing(void) { const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15}; u64 sample_type; - u64 sample_regs_user; + u64 sample_regs; size_t i; int err; @@ -280,7 +303,7 @@ int test__sample_parsing(void) * were added. Please actually update the test rather than just change * the condition below. */ - if (PERF_SAMPLE_MAX > PERF_SAMPLE_TRANSACTION << 1) { + if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) { pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n"); return -1; } @@ -297,22 +320,24 @@ int test__sample_parsing(void) } continue; } + sample_regs = 0; if (sample_type == PERF_SAMPLE_REGS_USER) - sample_regs_user = 0x3fff; - else - sample_regs_user = 0; + sample_regs = 0x3fff; + + if (sample_type == PERF_SAMPLE_REGS_INTR) + sample_regs = 0xff0fff; - err = do_test(sample_type, sample_regs_user, 0); + err = do_test(sample_type, sample_regs, 0); if (err) return err; } /* Test all sample format bits together */ sample_type = PERF_SAMPLE_MAX - 1; - sample_regs_user = 0x3fff; + sample_regs = 0x3fff; /* shared yb intr and user regs */ for (i = 0; i < ARRAY_SIZE(rf); i++) { - err = do_test(sample_type, sample_regs_user, rf[i]); + err = do_test(sample_type, sample_regs, rf[i]); if (err) return err; } diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index f0697a3aede0..9d32e3c0cfee 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -27,6 +27,7 @@ static struct annotate_browser_opt { bool hide_src_code, use_offset, jump_arrows, + show_linenr, show_nr_jumps; } annotate_browser__opts = { .use_offset = true, @@ -128,7 +129,11 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int if (!*dl->line) slsmg_write_nstring(" ", width - pcnt_width); else if (dl->offset == -1) { - printed = scnprintf(bf, sizeof(bf), "%*s ", + if (dl->line_nr && annotate_browser__opts.show_linenr) + printed = scnprintf(bf, sizeof(bf), "%-*d ", + ab->addr_width + 1, dl->line_nr); + else + printed = scnprintf(bf, sizeof(bf), "%*s ", ab->addr_width, " "); slsmg_write_nstring(bf, printed); slsmg_write_nstring(dl->line, width - printed - pcnt_width + 1); @@ -512,7 +517,7 @@ static bool annotate_browser__jump(struct annotate_browser *browser) } annotate_browser__set_top(browser, dl, idx); - + return true; } @@ -733,6 +738,7 @@ static int annotate_browser__run(struct annotate_browser *browser, "o Toggle disassembler output/simplified view\n" "s Toggle source code view\n" "/ Search string\n" + "k Toggle line numbers\n" "r Run available scripts\n" "? Search string backwards\n"); continue; @@ -741,6 +747,10 @@ static int annotate_browser__run(struct annotate_browser *browser, script_browse(NULL); continue; } + case 'k': + annotate_browser__opts.show_linenr = + !annotate_browser__opts.show_linenr; + break; case 'H': nd = browser->curr_hot; break; @@ -857,7 +867,6 @@ static void annotate_browser__mark_jump_targets(struct annotate_browser *browser ++browser->nr_jumps; } - } static inline int width_jumps(int n) @@ -984,6 +993,7 @@ static struct annotate_config { } annotate__configs[] = { ANNOTATE_CFG(hide_src_code), ANNOTATE_CFG(jump_arrows), + ANNOTATE_CFG(show_linenr), ANNOTATE_CFG(show_nr_jumps), ANNOTATE_CFG(use_offset), }; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index cfb976b3de3a..788506eef567 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -227,10 +227,14 @@ static void callchain_node__init_have_children_rb_tree(struct callchain_node *no } } -static void callchain_node__init_have_children(struct callchain_node *node) +static void callchain_node__init_have_children(struct callchain_node *node, + bool has_sibling) { struct callchain_list *chain; + chain = list_entry(node->val.next, struct callchain_list, list); + chain->ms.has_children = has_sibling; + if (!list_empty(&node->val)) { chain = list_entry(node->val.prev, struct callchain_list, list); chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root); @@ -241,11 +245,12 @@ static void callchain_node__init_have_children(struct callchain_node *node) static void callchain__init_have_children(struct rb_root *root) { - struct rb_node *nd; + struct rb_node *nd = rb_first(root); + bool has_sibling = nd && rb_next(nd); for (nd = rb_first(root); nd; nd = rb_next(nd)) { struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); - callchain_node__init_have_children(node); + callchain_node__init_have_children(node, has_sibling); } } @@ -463,23 +468,6 @@ out: return key; } -static char *callchain_list__sym_name(struct callchain_list *cl, - char *bf, size_t bfsize, bool show_dso) -{ - int printed; - - if (cl->ms.sym) - printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name); - else - printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip); - - if (show_dso) - scnprintf(bf + printed, bfsize - printed, " %s", - cl->ms.map ? cl->ms.map->dso->short_name : "unknown"); - - return bf; -} - struct callchain_print_arg { /* for hists browser */ off_t row_offset; @@ -559,8 +547,11 @@ static int hist_browser__show_callchain(struct hist_browser *browser, struct rb_node *node; int first_row = row, offset = level * LEVEL_OFFSET_STEP; u64 new_total; + bool need_percent; node = rb_first(root); + need_percent = node && rb_next(node); + while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); struct rb_node *next = rb_next(node); @@ -577,7 +568,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser, if (first) first = false; - else if (level > 1) + else if (need_percent) extra_offset = LEVEL_OFFSET_STEP; folded_sign = callchain_list__folded(chain); @@ -590,7 +581,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser, str = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso); - if (was_first && level > 1) { + if (was_first && need_percent) { double percent = cumul * 100.0 / total; if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0) @@ -807,6 +798,13 @@ static int hist_browser__show_entry(struct hist_browser *browser, .is_current_entry = current_entry, }; + if (callchain_param.mode == CHAIN_GRAPH_REL) { + if (symbol_conf.cumulate_callchain) + total = entry->stat_acc->period; + else + total = entry->stat.period; + } + printed += hist_browser__show_callchain(browser, &entry->sorted_chain, 1, row, total, hist_browser__show_callchain_entry, &arg, @@ -1254,7 +1252,7 @@ static int hists__browser_title(struct hists *hists, nr_samples = convert_unit(nr_samples, &unit); printed = scnprintf(bf, size, - "Samples: %lu%c of event '%s', Event count (approx.): %lu", + "Samples: %lu%c of event '%s', Event count (approx.): %" PRIu64, nr_samples, unit, ev_name, nr_events); diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index fc654fb77ace..4b3585eed1e8 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -89,15 +89,6 @@ void perf_gtk__init_hpp(void) perf_gtk__hpp_color_overhead_acc; } -static void callchain_list__sym_name(struct callchain_list *cl, - char *bf, size_t bfsize) -{ - if (cl->ms.sym) - scnprintf(bf, bfsize, "%s", cl->ms.sym->name); - else - scnprintf(bf, bfsize, "%#" PRIx64, cl->ip); -} - static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store, GtkTreeIter *parent, int col, u64 total) { @@ -128,7 +119,7 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store, scnprintf(buf, sizeof(buf), "%5.2f%%", percent); gtk_tree_store_set(store, &iter, 0, buf, -1); - callchain_list__sym_name(chain, buf, sizeof(buf)); + callchain_list__sym_name(chain, buf, sizeof(buf), false); gtk_tree_store_set(store, &iter, col, buf, -1); if (need_new_parent) { diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 2af18376b077..25d608394d74 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -162,8 +162,8 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b, return ret; nr_members = evsel->nr_members; - fields_a = calloc(sizeof(*fields_a), nr_members); - fields_b = calloc(sizeof(*fields_b), nr_members); + fields_a = calloc(nr_members, sizeof(*fields_a)); + fields_b = calloc(nr_members, sizeof(*fields_b)); if (!fields_a || !fields_b) goto out; @@ -204,6 +204,9 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b, if (ret) return ret; + if (a->thread != b->thread || !symbol_conf.use_callchain) + return 0; + ret = b->callchain->max_depth - a->callchain->max_depth; } return ret; @@ -282,7 +285,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ } #define __HPP_SORT_FN(_type, _field) \ -static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ +static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct hist_entry *a, struct hist_entry *b) \ { \ return __hpp__sort(a, b, he_get_##_field); \ } @@ -309,7 +313,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ } #define __HPP_SORT_ACC_FN(_type, _field) \ -static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ +static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct hist_entry *a, struct hist_entry *b) \ { \ return __hpp__sort_acc(a, b, he_get_acc_##_field); \ } @@ -328,7 +333,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ } #define __HPP_SORT_RAW_FN(_type, _field) \ -static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ +static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct hist_entry *a, struct hist_entry *b) \ { \ return __hpp__sort(a, b, he_get_raw_##_field); \ } @@ -358,7 +364,8 @@ HPP_PERCENT_ACC_FNS(overhead_acc, period) HPP_RAW_FNS(samples, nr_events) HPP_RAW_FNS(period, period) -static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused, +static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *a __maybe_unused, struct hist_entry *b __maybe_unused) { return 0; diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h index f34f89eb607c..717d39d3052b 100644 --- a/tools/perf/ui/progress.h +++ b/tools/perf/ui/progress.h @@ -4,12 +4,12 @@ #include <linux/types.h> void ui_progress__finish(void); - + struct ui_progress { const char *title; u64 curr, next, step, total; }; - + void ui_progress__init(struct ui_progress *p, u64 total, const char *title); void ui_progress__update(struct ui_progress *p, u64 adv); diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 15b451acbde6..dfcbc90146ef 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -41,6 +41,7 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, { int i; size_t ret = 0; + char bf[1024]; ret += callchain__fprintf_left_margin(fp, left_margin); for (i = 0; i < depth; i++) { @@ -56,11 +57,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, } else ret += fprintf(fp, "%s", " "); } - if (chain->ms.sym) - ret += fprintf(fp, "%s\n", chain->ms.sym->name); - else - ret += fprintf(fp, "0x%0" PRIx64 "\n", chain->ip); - + fputs(callchain_list__sym_name(chain, bf, sizeof(bf), false), fp); + fputc('\n', fp); return ret; } @@ -168,6 +166,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, struct rb_node *node; int i = 0; int ret = 0; + char bf[1024]; /* * If have one single callchain root, don't bother printing @@ -196,10 +195,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, } else ret += callchain__fprintf_left_margin(fp, left_margin); - if (chain->ms.sym) - ret += fprintf(fp, " %s\n", chain->ms.sym->name); - else - ret += fprintf(fp, " %p\n", (void *)(long)chain->ip); + ret += fprintf(fp, "%s\n", callchain_list__sym_name(chain, bf, sizeof(bf), + false)); if (++entries_printed == callchain_param.print_limit) break; @@ -219,6 +216,7 @@ static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node, { struct callchain_list *chain; size_t ret = 0; + char bf[1024]; if (!node) return 0; @@ -229,11 +227,8 @@ static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node, list_for_each_entry(chain, &node->val, list) { if (chain->ip >= PERF_CONTEXT_MAX) continue; - if (chain->ms.sym) - ret += fprintf(fp, " %s\n", chain->ms.sym->name); - else - ret += fprintf(fp, " %p\n", - (void *)(long)chain->ip); + ret += fprintf(fp, " %s\n", callchain_list__sym_name(chain, + bf, sizeof(bf), false)); } return ret; diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c index 1c8b9afd5d6e..88f5143a5981 100644 --- a/tools/perf/ui/tui/helpline.c +++ b/tools/perf/ui/tui/helpline.c @@ -9,6 +9,7 @@ #include "../libslang.h" char ui_helpline__last_msg[1024]; +bool tui_helpline__set; static void tui_helpline__pop(void) { @@ -35,6 +36,8 @@ static int tui_helpline__show(const char *format, va_list ap) sizeof(ui_helpline__last_msg) - backlog, format, ap); backlog += ret; + tui_helpline__set = true; + if (ui_helpline__last_msg[backlog - 1] == '\n') { ui_helpline__puts(ui_helpline__last_msg); SLsmg_refresh(); diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index 2f612562978c..b77e1d771363 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -1,5 +1,8 @@ #include <signal.h> #include <stdbool.h> +#ifdef HAVE_BACKTRACE_SUPPORT +#include <execinfo.h> +#endif #include "../../util/cache.h" #include "../../util/debug.h" @@ -14,6 +17,7 @@ static volatile int ui__need_resize; extern struct perf_error_ops perf_tui_eops; +extern bool tui_helpline__set; extern void hist_browser__init_hpp(void); @@ -88,6 +92,25 @@ int ui__getch(int delay_secs) return SLkp_getkey(); } +#ifdef HAVE_BACKTRACE_SUPPORT +static void ui__signal_backtrace(int sig) +{ + void *stackdump[32]; + size_t size; + + ui__exit(false); + psignal(sig, "perf"); + + printf("-------- backtrace --------\n"); + size = backtrace(stackdump, ARRAY_SIZE(stackdump)); + backtrace_symbols_fd(stackdump, size, STDOUT_FILENO); + + exit(0); +} +#else +# define ui__signal_backtrace ui__signal +#endif + static void ui__signal(int sig) { ui__exit(false); @@ -122,8 +145,8 @@ int ui__init(void) ui_browser__init(); tui_progress__init(); - signal(SIGSEGV, ui__signal); - signal(SIGFPE, ui__signal); + signal(SIGSEGV, ui__signal_backtrace); + signal(SIGFPE, ui__signal_backtrace); signal(SIGINT, ui__signal); signal(SIGQUIT, ui__signal); signal(SIGTERM, ui__signal); @@ -137,7 +160,7 @@ out: void ui__exit(bool wait_for_ok) { - if (wait_for_ok) + if (wait_for_ok && tui_helpline__set) ui__question_window("Fatal Error", ui_helpline__last_msg, "Press any key...", 0); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 7dabde14ea54..9d9db3b296dd 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -17,17 +17,21 @@ #include "debug.h" #include "annotate.h" #include "evsel.h" +#include <regex.h> #include <pthread.h> #include <linux/bitops.h> const char *disassembler_style; const char *objdump_path; +static regex_t file_lineno; static struct ins *ins__find(const char *name); static int disasm_line__parse(char *line, char **namep, char **rawp); static void ins__delete(struct ins_operands *ops) { + if (ops == NULL) + return; zfree(&ops->source.raw); zfree(&ops->source.name); zfree(&ops->target.raw); @@ -175,14 +179,17 @@ static int lock__parse(struct ins_operands *ops) goto out_free_ops; ops->locked.ins = ins__find(name); + free(name); + if (ops->locked.ins == NULL) goto out_free_ops; if (!ops->locked.ins->ops) return 0; - if (ops->locked.ins->ops->parse) - ops->locked.ins->ops->parse(ops->locked.ops); + if (ops->locked.ins->ops->parse && + ops->locked.ins->ops->parse(ops->locked.ops) < 0) + goto out_free_ops; return 0; @@ -206,6 +213,13 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size, static void lock__delete(struct ins_operands *ops) { + struct ins *ins = ops->locked.ins; + + if (ins && ins->ops->free) + ins->ops->free(ops->locked.ops); + else + ins__delete(ops->locked.ops); + zfree(&ops->locked.ops); zfree(&ops->target.raw); zfree(&ops->target.name); @@ -227,7 +241,7 @@ static int mov__parse(struct ins_operands *ops) *s = '\0'; ops->source.raw = strdup(ops->raw); *s = ','; - + if (ops->source.raw == NULL) return -1; @@ -529,8 +543,8 @@ static void disasm_line__init_ins(struct disasm_line *dl) if (!dl->ins->ops) return; - if (dl->ins->ops->parse) - dl->ins->ops->parse(&dl->ops); + if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops) < 0) + dl->ins = NULL; } static int disasm_line__parse(char *line, char **namep, char **rawp) @@ -570,13 +584,15 @@ out_free_name: return -1; } -static struct disasm_line *disasm_line__new(s64 offset, char *line, size_t privsize) +static struct disasm_line *disasm_line__new(s64 offset, char *line, + size_t privsize, int line_nr) { struct disasm_line *dl = zalloc(sizeof(*dl) + privsize); if (dl != NULL) { dl->offset = offset; dl->line = strdup(line); + dl->line_nr = line_nr; if (dl->line == NULL) goto out_delete; @@ -788,13 +804,15 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st * The ops.raw part will be parsed further according to type of the instruction. */ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, - FILE *file, size_t privsize) + FILE *file, size_t privsize, + int *line_nr) { struct annotation *notes = symbol__annotation(sym); struct disasm_line *dl; char *line = NULL, *parsed_line, *tmp, *tmp2, *c; size_t line_len; s64 line_ip, offset = -1; + regmatch_t match[2]; if (getline(&line, &line_len, file) < 0) return -1; @@ -812,6 +830,12 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, line_ip = -1; parsed_line = line; + /* /filename:linenr ? Save line number and ignore. */ + if (regexec(&file_lineno, line, 2, match, 0) == 0) { + *line_nr = atoi(line + match[1].rm_so); + return 0; + } + /* * Strip leading spaces: */ @@ -842,8 +866,9 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, parsed_line = tmp2 + 1; } - dl = disasm_line__new(offset, parsed_line, privsize); + dl = disasm_line__new(offset, parsed_line, privsize, *line_nr); free(line); + (*line_nr)++; if (dl == NULL) return -1; @@ -869,6 +894,11 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, return 0; } +static __attribute__((constructor)) void symbol__init_regexpr(void) +{ + regcomp(&file_lineno, "^/[^:]+:([0-9]+)", REG_EXTENDED); +} + static void delete_last_nop(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); @@ -904,6 +934,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) char symfs_filename[PATH_MAX]; struct kcore_extract kce; bool delete_extract = false; + int lineno = 0; if (filename) symbol__join_symfs(symfs_filename, filename); @@ -915,6 +946,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) return -ENOMEM; } goto fallback; + } else if (dso__is_kcore(dso)) { + goto fallback; } else if (readlink(symfs_filename, command, sizeof(command)) < 0 || strstr(command, "[kernel.kallsyms]") || access(symfs_filename, R_OK)) { @@ -982,7 +1015,7 @@ fallback: snprintf(command, sizeof(command), "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -d %s %s -C %s 2>/dev/null|grep -v %s|expand", + " -l -d %s %s -C %s 2>/dev/null|grep -v %s|expand", objdump_path ? objdump_path : "objdump", disassembler_style ? "-M " : "", disassembler_style ? disassembler_style : "", @@ -999,7 +1032,8 @@ fallback: goto out_free_filename; while (!feof(file)) - if (symbol__parse_objdump_line(sym, map, file, privsize) < 0) + if (symbol__parse_objdump_line(sym, map, file, privsize, + &lineno) < 0) break; /* @@ -1170,7 +1204,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, goto next; offset = start + i; - src_line->path = get_srcline(map->dso, offset); + src_line->path = get_srcline(map->dso, offset, NULL, false); insert_source_line(&tmp_root, src_line); next: diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 112d6e268150..cadbdc90a5cb 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -58,6 +58,7 @@ struct disasm_line { char *line; char *name; struct ins *ins; + int line_nr; struct ins_operands ops; }; @@ -115,11 +116,6 @@ struct annotation { struct annotated_source *src; }; -struct sannotation { - struct annotation annotation; - struct symbol symbol; -}; - static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx) { return (((void *)¬es->src->histograms) + @@ -128,8 +124,7 @@ static inline struct sym_hist *annotation__histogram(struct annotation *notes, i static inline struct annotation *symbol__annotation(struct symbol *sym) { - struct sannotation *a = container_of(sym, struct sannotation, symbol); - return &a->annotation; + return (void *)sym - symbol_conf.priv_size; } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx); diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index a904a4cfe7d3..0c72680a977f 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -15,6 +15,11 @@ #include "debug.h" #include "session.h" #include "tool.h" +#include "header.h" +#include "vdso.h" + + +static bool no_buildid_cache; int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, union perf_event *event, @@ -33,8 +38,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, return -1; } - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->ip, &al); + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al); if (al.map != NULL) al.map->dso->hit = 1; @@ -106,3 +110,340 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) build_id_hex, build_id_hex + 2); return bf; } + +#define dsos__for_each_with_build_id(pos, head) \ + list_for_each_entry(pos, head, node) \ + if (!pos->has_build_id) \ + continue; \ + else + +static int write_buildid(const char *name, size_t name_len, u8 *build_id, + pid_t pid, u16 misc, int fd) +{ + int err; + struct build_id_event b; + size_t len; + + len = name_len + 1; + len = PERF_ALIGN(len, NAME_ALIGN); + + memset(&b, 0, sizeof(b)); + memcpy(&b.build_id, build_id, BUILD_ID_SIZE); + b.pid = pid; + b.header.misc = misc; + b.header.size = sizeof(b) + len; + + err = writen(fd, &b, sizeof(b)); + if (err < 0) + return err; + + return write_padded(fd, name, name_len + 1, len); +} + +static int __dsos__write_buildid_table(struct list_head *head, + struct machine *machine, + pid_t pid, u16 misc, int fd) +{ + char nm[PATH_MAX]; + struct dso *pos; + + dsos__for_each_with_build_id(pos, head) { + int err; + const char *name; + size_t name_len; + + if (!pos->hit) + continue; + + if (dso__is_vdso(pos)) { + name = pos->short_name; + name_len = pos->short_name_len + 1; + } else if (dso__is_kcore(pos)) { + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + name_len = strlen(nm) + 1; + } else { + name = pos->long_name; + name_len = pos->long_name_len + 1; + } + + err = write_buildid(name, name_len, pos->build_id, + pid, misc, fd); + if (err) + return err; + } + + return 0; +} + +static int machine__write_buildid_table(struct machine *machine, int fd) +{ + int err; + u16 kmisc = PERF_RECORD_MISC_KERNEL, + umisc = PERF_RECORD_MISC_USER; + + if (!machine__is_host(machine)) { + kmisc = PERF_RECORD_MISC_GUEST_KERNEL; + umisc = PERF_RECORD_MISC_GUEST_USER; + } + + err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine, + machine->pid, kmisc, fd); + if (err == 0) + err = __dsos__write_buildid_table(&machine->user_dsos.head, + machine, machine->pid, umisc, + fd); + return err; +} + +int perf_session__write_buildid_table(struct perf_session *session, int fd) +{ + struct rb_node *nd; + int err = machine__write_buildid_table(&session->machines.host, fd); + + if (err) + return err; + + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + err = machine__write_buildid_table(pos, fd); + if (err) + break; + } + return err; +} + +static int __dsos__hit_all(struct list_head *head) +{ + struct dso *pos; + + list_for_each_entry(pos, head, node) + pos->hit = true; + + return 0; +} + +static int machine__hit_all_dsos(struct machine *machine) +{ + int err; + + err = __dsos__hit_all(&machine->kernel_dsos.head); + if (err) + return err; + + return __dsos__hit_all(&machine->user_dsos.head); +} + +int dsos__hit_all(struct perf_session *session) +{ + struct rb_node *nd; + int err; + + err = machine__hit_all_dsos(&session->machines.host); + if (err) + return err; + + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + + err = machine__hit_all_dsos(pos); + if (err) + return err; + } + + return 0; +} + +void disable_buildid_cache(void) +{ + no_buildid_cache = true; +} + +int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, + const char *name, bool is_kallsyms, bool is_vdso) +{ + const size_t size = PATH_MAX; + char *realname, *filename = zalloc(size), + *linkname = zalloc(size), *targetname; + int len, err = -1; + bool slash = is_kallsyms || is_vdso; + + if (is_kallsyms) { + if (symbol_conf.kptr_restrict) { + pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n"); + err = 0; + goto out_free; + } + realname = (char *) name; + } else + realname = realpath(name, NULL); + + if (realname == NULL || filename == NULL || linkname == NULL) + goto out_free; + + len = scnprintf(filename, size, "%s%s%s", + debugdir, slash ? "/" : "", + is_vdso ? DSO__NAME_VDSO : realname); + if (mkdir_p(filename, 0755)) + goto out_free; + + snprintf(filename + len, size - len, "/%s", sbuild_id); + + if (access(filename, F_OK)) { + if (is_kallsyms) { + if (copyfile("/proc/kallsyms", filename)) + goto out_free; + } else if (link(realname, filename) && copyfile(name, filename)) + goto out_free; + } + + len = scnprintf(linkname, size, "%s/.build-id/%.2s", + debugdir, sbuild_id); + + if (access(linkname, X_OK) && mkdir_p(linkname, 0755)) + goto out_free; + + snprintf(linkname + len, size - len, "/%s", sbuild_id + 2); + targetname = filename + strlen(debugdir) - 5; + memcpy(targetname, "../..", 5); + + if (symlink(targetname, linkname) == 0) + err = 0; +out_free: + if (!is_kallsyms) + free(realname); + free(filename); + free(linkname); + return err; +} + +static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, + const char *name, const char *debugdir, + bool is_kallsyms, bool is_vdso) +{ + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + + build_id__sprintf(build_id, build_id_size, sbuild_id); + + return build_id_cache__add_s(sbuild_id, debugdir, name, + is_kallsyms, is_vdso); +} + +int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) +{ + const size_t size = PATH_MAX; + char *filename = zalloc(size), + *linkname = zalloc(size); + int err = -1; + + if (filename == NULL || linkname == NULL) + goto out_free; + + snprintf(linkname, size, "%s/.build-id/%.2s/%s", + debugdir, sbuild_id, sbuild_id + 2); + + if (access(linkname, F_OK)) + goto out_free; + + if (readlink(linkname, filename, size - 1) < 0) + goto out_free; + + if (unlink(linkname)) + goto out_free; + + /* + * Since the link is relative, we must make it absolute: + */ + snprintf(linkname, size, "%s/.build-id/%.2s/%s", + debugdir, sbuild_id, filename); + + if (unlink(linkname)) + goto out_free; + + err = 0; +out_free: + free(filename); + free(linkname); + return err; +} + +static int dso__cache_build_id(struct dso *dso, struct machine *machine, + const char *debugdir) +{ + bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; + bool is_vdso = dso__is_vdso(dso); + const char *name = dso->long_name; + char nm[PATH_MAX]; + + if (dso__is_kcore(dso)) { + is_kallsyms = true; + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + } + return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, + debugdir, is_kallsyms, is_vdso); +} + +static int __dsos__cache_build_ids(struct list_head *head, + struct machine *machine, const char *debugdir) +{ + struct dso *pos; + int err = 0; + + dsos__for_each_with_build_id(pos, head) + if (dso__cache_build_id(pos, machine, debugdir)) + err = -1; + + return err; +} + +static int machine__cache_build_ids(struct machine *machine, const char *debugdir) +{ + int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine, + debugdir); + ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine, + debugdir); + return ret; +} + +int perf_session__cache_build_ids(struct perf_session *session) +{ + struct rb_node *nd; + int ret; + + if (no_buildid_cache) + return 0; + + if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST) + return -1; + + ret = machine__cache_build_ids(&session->machines.host, buildid_dir); + + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + ret |= machine__cache_build_ids(pos, buildid_dir); + } + return ret ? -1 : 0; +} + +static bool machine__read_build_ids(struct machine *machine, bool with_hits) +{ + bool ret; + + ret = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits); + ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits); + return ret; +} + +bool perf_session__read_build_ids(struct perf_session *session, bool with_hits) +{ + struct rb_node *nd; + bool ret = machine__read_build_ids(&session->machines.host, with_hits); + + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + ret |= machine__read_build_ids(pos, with_hits); + } + + return ret; +} diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index ae392561470b..8236319514d5 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -15,4 +15,16 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size); int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine); + +int dsos__hit_all(struct perf_session *session); + +bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); +int perf_session__write_buildid_table(struct perf_session *session, int fd); +int perf_session__cache_build_ids(struct perf_session *session); + +int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, + const char *name, bool is_kallsyms, bool is_vdso); +int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir); +void disable_buildid_cache(void); + #endif diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 5cf9e1b5989d..d04d770d90f6 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -71,7 +71,9 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2 extern char *perf_pathdup(const char *fmt, ...) __attribute__((format (printf, 1, 2))); +#ifndef __UCLIBC__ /* Matches the libc/libbsd function attribute so we declare this unconditionally: */ extern size_t strlcpy(char *dest, const char *src, size_t size); +#endif #endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index c84d3f8dcb75..14e7a123d43b 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -77,7 +77,7 @@ int parse_callchain_record_opt(const char *arg) ret = 0; } else pr_err("callchain: No more arguments " - "needed for -g fp\n"); + "needed for --call-graph fp\n"); break; #ifdef HAVE_DWARF_UNWIND_SUPPORT @@ -149,6 +149,10 @@ static int parse_callchain_sort_key(const char *value) callchain_param.key = CCKEY_ADDRESS; return 0; } + if (!strncmp(value, "branch", strlen(value))) { + callchain_param.branch_callstack = 1; + return 0; + } return -1; } @@ -754,8 +758,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain || sort__has_parent) { - return machine__resolve_callchain(al->machine, evsel, al->thread, - sample, parent, al, max_stack); + return thread__resolve_callchain(al->thread, evsel, sample, + parent, al, max_stack); } return 0; } @@ -808,3 +812,62 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * out: return 1; } + +char *callchain_list__sym_name(struct callchain_list *cl, + char *bf, size_t bfsize, bool show_dso) +{ + int printed; + + if (cl->ms.sym) { + if (callchain_param.key == CCKEY_ADDRESS && + cl->ms.map && !cl->srcline) + cl->srcline = get_srcline(cl->ms.map->dso, + map__rip_2objdump(cl->ms.map, + cl->ip), + cl->ms.sym, false); + if (cl->srcline) + printed = scnprintf(bf, bfsize, "%s %s", + cl->ms.sym->name, cl->srcline); + else + printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name); + } else + printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip); + + if (show_dso) + scnprintf(bf + printed, bfsize - printed, " %s", + cl->ms.map ? + cl->ms.map->dso->short_name : + "unknown"); + + return bf; +} + +static void free_callchain_node(struct callchain_node *node) +{ + struct callchain_list *list, *tmp; + struct callchain_node *child; + struct rb_node *n; + + list_for_each_entry_safe(list, tmp, &node->val, list) { + list_del(&list->list); + free(list); + } + + n = rb_first(&node->rb_root_in); + while (n) { + child = container_of(n, struct callchain_node, rb_node_in); + n = rb_next(n); + rb_erase(&child->rb_node_in, &node->rb_root_in); + + free_callchain_node(child); + free(child); + } +} + +void free_callchain(struct callchain_root *root) +{ + if (!symbol_conf.use_callchain) + return; + + free_callchain_node(&root->node); +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 94cfefddf4db..c0ec1acc38e4 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -63,6 +63,7 @@ struct callchain_param { sort_chain_func_t sort; enum chain_order order; enum chain_key key; + bool branch_callstack; }; extern struct callchain_param callchain_param; @@ -70,6 +71,7 @@ extern struct callchain_param callchain_param; struct callchain_list { u64 ip; struct map_symbol ms; + char *srcline; struct list_head list; }; @@ -184,15 +186,18 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest, } #ifdef HAVE_SKIP_CALLCHAIN_IDX -extern int arch_skip_callchain_idx(struct machine *machine, - struct thread *thread, struct ip_callchain *chain); +extern int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain); #else -static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused, - struct thread *thread __maybe_unused, +static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused, struct ip_callchain *chain __maybe_unused) { return -1; } #endif +char *callchain_list__sym_name(struct callchain_list *cl, + char *bf, size_t bfsize, bool show_dso); + +void free_callchain(struct callchain_root *root); + #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index 47b78b3f0325..6da965bdbc2c 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -25,6 +25,10 @@ static int perf_flag_probe(void) if (cpu < 0) cpu = 0; + /* + * Using -1 for the pid is a workaround to avoid gratuitous jump label + * changes. + */ while (1) { /* check cloexec flag */ fd = sys_perf_event_open(&attr, pid, cpu, -1, @@ -47,16 +51,24 @@ static int perf_flag_probe(void) err, strerror_r(err, sbuf, sizeof(sbuf))); /* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */ - fd = sys_perf_event_open(&attr, pid, cpu, -1, 0); + while (1) { + fd = sys_perf_event_open(&attr, pid, cpu, -1, 0); + if (fd < 0 && pid == -1 && errno == EACCES) { + pid = 0; + continue; + } + break; + } err = errno; + if (fd >= 0) + close(fd); + if (WARN_ONCE(fd < 0 && err != EBUSY, "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n", err, strerror_r(err, sbuf, sizeof(sbuf)))) return -1; - close(fd); - return 0; } diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index f4654183d391..55355b3d4f85 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -5,132 +5,6 @@ int perf_use_color_default = -1; -static int parse_color(const char *name, int len) -{ - static const char * const color_names[] = { - "normal", "black", "red", "green", "yellow", - "blue", "magenta", "cyan", "white" - }; - char *end; - int i; - - for (i = 0; i < (int)ARRAY_SIZE(color_names); i++) { - const char *str = color_names[i]; - if (!strncasecmp(name, str, len) && !str[len]) - return i - 1; - } - i = strtol(name, &end, 10); - if (end - name == len && i >= -1 && i <= 255) - return i; - return -2; -} - -static int parse_attr(const char *name, int len) -{ - static const int attr_values[] = { 1, 2, 4, 5, 7 }; - static const char * const attr_names[] = { - "bold", "dim", "ul", "blink", "reverse" - }; - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(attr_names); i++) { - const char *str = attr_names[i]; - if (!strncasecmp(name, str, len) && !str[len]) - return attr_values[i]; - } - return -1; -} - -void color_parse(const char *value, const char *var, char *dst) -{ - color_parse_mem(value, strlen(value), var, dst); -} - -void color_parse_mem(const char *value, int value_len, const char *var, - char *dst) -{ - const char *ptr = value; - int len = value_len; - int attr = -1; - int fg = -2; - int bg = -2; - - if (!strncasecmp(value, "reset", len)) { - strcpy(dst, PERF_COLOR_RESET); - return; - } - - /* [fg [bg]] [attr] */ - while (len > 0) { - const char *word = ptr; - int val, wordlen = 0; - - while (len > 0 && !isspace(word[wordlen])) { - wordlen++; - len--; - } - - ptr = word + wordlen; - while (len > 0 && isspace(*ptr)) { - ptr++; - len--; - } - - val = parse_color(word, wordlen); - if (val >= -1) { - if (fg == -2) { - fg = val; - continue; - } - if (bg == -2) { - bg = val; - continue; - } - goto bad; - } - val = parse_attr(word, wordlen); - if (val < 0 || attr != -1) - goto bad; - attr = val; - } - - if (attr >= 0 || fg >= 0 || bg >= 0) { - int sep = 0; - - *dst++ = '\033'; - *dst++ = '['; - if (attr >= 0) { - *dst++ = '0' + attr; - sep++; - } - if (fg >= 0) { - if (sep++) - *dst++ = ';'; - if (fg < 8) { - *dst++ = '3'; - *dst++ = '0' + fg; - } else { - dst += sprintf(dst, "38;5;%d", fg); - } - } - if (bg >= 0) { - if (sep++) - *dst++ = ';'; - if (bg < 8) { - *dst++ = '4'; - *dst++ = '0' + bg; - } else { - dst += sprintf(dst, "48;5;%d", bg); - } - } - *dst++ = 'm'; - } - *dst = 0; - return; -bad: - die("bad color value '%.*s' for variable '%s'", value_len, value, var); -} - int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty) { if (value) { diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 0a594b8a0c26..38146f922c54 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -30,8 +30,6 @@ extern int perf_use_color_default; int perf_color_default_config(const char *var, const char *value, void *cb); int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty); -void color_parse(const char *value, const char *var, char *dst); -void color_parse_mem(const char *value, int len, const char *var, char *dst); int color_vsnprintf(char *bf, size_t size, const char *color, const char *fmt, va_list args); int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args); diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h index 51c10ab257f8..71c9c39340d4 100644 --- a/tools/perf/util/comm.h +++ b/tools/perf/util/comm.h @@ -12,6 +12,10 @@ struct comm { u64 start; struct list_head list; bool exec; + union { /* Tool specific area */ + void *priv; + u64 db_id; + }; }; void comm__free(struct comm *comm); diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 57ff826f150b..e18f653cd7db 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -522,7 +522,7 @@ static int buildid_dir_command_config(const char *var, const char *value, const char *v; /* same dir for all commands */ - if (!prefixcmp(var, "buildid.") && !strcmp(var + 8, "dir")) { + if (!strcmp(var, "buildid.dir")) { v = perf_config_dirname(var, value); if (!v) return -1; @@ -539,12 +539,14 @@ static void check_buildid_dir_config(void) perf_config(buildid_dir_command_config, &c); } -void set_buildid_dir(void) +void set_buildid_dir(const char *dir) { - buildid_dir[0] = '\0'; + if (dir) + scnprintf(buildid_dir, MAXPATHLEN-1, "%s", dir); /* try config file */ - check_buildid_dir_config(); + if (buildid_dir[0] == '\0') + check_buildid_dir_config(); /* default to $HOME/.debug */ if (buildid_dir[0] == '\0') { diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c new file mode 100644 index 000000000000..c81dae399763 --- /dev/null +++ b/tools/perf/util/db-export.c @@ -0,0 +1,428 @@ +/* + * db-export.c: Support for exporting data suitable for import to a database + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#include <errno.h> + +#include "evsel.h" +#include "machine.h" +#include "thread.h" +#include "comm.h" +#include "symbol.h" +#include "event.h" +#include "util.h" +#include "thread-stack.h" +#include "db-export.h" + +struct deferred_export { + struct list_head node; + struct comm *comm; +}; + +static int db_export__deferred(struct db_export *dbe) +{ + struct deferred_export *de; + int err; + + while (!list_empty(&dbe->deferred)) { + de = list_entry(dbe->deferred.next, struct deferred_export, + node); + err = dbe->export_comm(dbe, de->comm); + list_del(&de->node); + free(de); + if (err) + return err; + } + + return 0; +} + +static void db_export__free_deferred(struct db_export *dbe) +{ + struct deferred_export *de; + + while (!list_empty(&dbe->deferred)) { + de = list_entry(dbe->deferred.next, struct deferred_export, + node); + list_del(&de->node); + free(de); + } +} + +static int db_export__defer_comm(struct db_export *dbe, struct comm *comm) +{ + struct deferred_export *de; + + de = zalloc(sizeof(struct deferred_export)); + if (!de) + return -ENOMEM; + + de->comm = comm; + list_add_tail(&de->node, &dbe->deferred); + + return 0; +} + +int db_export__init(struct db_export *dbe) +{ + memset(dbe, 0, sizeof(struct db_export)); + INIT_LIST_HEAD(&dbe->deferred); + return 0; +} + +int db_export__flush(struct db_export *dbe) +{ + return db_export__deferred(dbe); +} + +void db_export__exit(struct db_export *dbe) +{ + db_export__free_deferred(dbe); + call_return_processor__free(dbe->crp); + dbe->crp = NULL; +} + +int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel) +{ + if (evsel->db_id) + return 0; + + evsel->db_id = ++dbe->evsel_last_db_id; + + if (dbe->export_evsel) + return dbe->export_evsel(dbe, evsel); + + return 0; +} + +int db_export__machine(struct db_export *dbe, struct machine *machine) +{ + if (machine->db_id) + return 0; + + machine->db_id = ++dbe->machine_last_db_id; + + if (dbe->export_machine) + return dbe->export_machine(dbe, machine); + + return 0; +} + +int db_export__thread(struct db_export *dbe, struct thread *thread, + struct machine *machine, struct comm *comm) +{ + u64 main_thread_db_id = 0; + int err; + + if (thread->db_id) + return 0; + + thread->db_id = ++dbe->thread_last_db_id; + + if (thread->pid_ != -1) { + struct thread *main_thread; + + if (thread->pid_ == thread->tid) { + main_thread = thread; + } else { + main_thread = machine__findnew_thread(machine, + thread->pid_, + thread->pid_); + if (!main_thread) + return -ENOMEM; + err = db_export__thread(dbe, main_thread, machine, + comm); + if (err) + return err; + if (comm) { + err = db_export__comm_thread(dbe, comm, thread); + if (err) + return err; + } + } + main_thread_db_id = main_thread->db_id; + } + + if (dbe->export_thread) + return dbe->export_thread(dbe, thread, main_thread_db_id, + machine); + + return 0; +} + +int db_export__comm(struct db_export *dbe, struct comm *comm, + struct thread *main_thread) +{ + int err; + + if (comm->db_id) + return 0; + + comm->db_id = ++dbe->comm_last_db_id; + + if (dbe->export_comm) { + if (main_thread->comm_set) + err = dbe->export_comm(dbe, comm); + else + err = db_export__defer_comm(dbe, comm); + if (err) + return err; + } + + return db_export__comm_thread(dbe, comm, main_thread); +} + +int db_export__comm_thread(struct db_export *dbe, struct comm *comm, + struct thread *thread) +{ + u64 db_id; + + db_id = ++dbe->comm_thread_last_db_id; + + if (dbe->export_comm_thread) + return dbe->export_comm_thread(dbe, db_id, comm, thread); + + return 0; +} + +int db_export__dso(struct db_export *dbe, struct dso *dso, + struct machine *machine) +{ + if (dso->db_id) + return 0; + + dso->db_id = ++dbe->dso_last_db_id; + + if (dbe->export_dso) + return dbe->export_dso(dbe, dso, machine); + + return 0; +} + +int db_export__symbol(struct db_export *dbe, struct symbol *sym, + struct dso *dso) +{ + u64 *sym_db_id = symbol__priv(sym); + + if (*sym_db_id) + return 0; + + *sym_db_id = ++dbe->symbol_last_db_id; + + if (dbe->export_symbol) + return dbe->export_symbol(dbe, sym, dso); + + return 0; +} + +static struct thread *get_main_thread(struct machine *machine, struct thread *thread) +{ + if (thread->pid_ == thread->tid) + return thread; + + if (thread->pid_ == -1) + return NULL; + + return machine__find_thread(machine, thread->pid_, thread->pid_); +} + +static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, + u64 *dso_db_id, u64 *sym_db_id, u64 *offset) +{ + int err; + + if (al->map) { + struct dso *dso = al->map->dso; + + err = db_export__dso(dbe, dso, al->machine); + if (err) + return err; + *dso_db_id = dso->db_id; + + if (!al->sym) { + al->sym = symbol__new(al->addr, 0, 0, "unknown"); + if (al->sym) + symbols__insert(&dso->symbols[al->map->type], + al->sym); + } + + if (al->sym) { + u64 *db_id = symbol__priv(al->sym); + + err = db_export__symbol(dbe, al->sym, dso); + if (err) + return err; + *sym_db_id = *db_id; + *offset = al->addr - al->sym->start; + } + } + + return 0; +} + +int db_export__branch_type(struct db_export *dbe, u32 branch_type, + const char *name) +{ + if (dbe->export_branch_type) + return dbe->export_branch_type(dbe, branch_type, name); + + return 0; +} + +int db_export__sample(struct db_export *dbe, union perf_event *event, + struct perf_sample *sample, struct perf_evsel *evsel, + struct thread *thread, struct addr_location *al) +{ + struct export_sample es = { + .event = event, + .sample = sample, + .evsel = evsel, + .thread = thread, + .al = al, + }; + struct thread *main_thread; + struct comm *comm = NULL; + int err; + + err = db_export__evsel(dbe, evsel); + if (err) + return err; + + err = db_export__machine(dbe, al->machine); + if (err) + return err; + + main_thread = get_main_thread(al->machine, thread); + if (main_thread) + comm = machine__thread_exec_comm(al->machine, main_thread); + + err = db_export__thread(dbe, thread, al->machine, comm); + if (err) + return err; + + if (comm) { + err = db_export__comm(dbe, comm, main_thread); + if (err) + return err; + es.comm_db_id = comm->db_id; + } + + es.db_id = ++dbe->sample_last_db_id; + + err = db_ids_from_al(dbe, al, &es.dso_db_id, &es.sym_db_id, &es.offset); + if (err) + return err; + + if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && + sample_addr_correlates_sym(&evsel->attr)) { + struct addr_location addr_al; + + perf_event__preprocess_sample_addr(event, sample, thread, &addr_al); + err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id, + &es.addr_sym_db_id, &es.addr_offset); + if (err) + return err; + if (dbe->crp) { + err = thread_stack__process(thread, comm, sample, al, + &addr_al, es.db_id, + dbe->crp); + if (err) + return err; + } + } + + if (dbe->export_sample) + return dbe->export_sample(dbe, &es); + + return 0; +} + +static struct { + u32 branch_type; + const char *name; +} branch_types[] = { + {0, "no branch"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "conditional jump"}, + {PERF_IP_FLAG_BRANCH, "unconditional jump"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, + "software interrupt"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, + "return from interrupt"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, + "system call"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, + "return from system call"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "asynchronous branch"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | + PERF_IP_FLAG_INTERRUPT, "hardware interrupt"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "transaction abort"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "trace begin"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "trace end"}, + {0, NULL} +}; + +int db_export__branch_types(struct db_export *dbe) +{ + int i, err = 0; + + for (i = 0; branch_types[i].name ; i++) { + err = db_export__branch_type(dbe, branch_types[i].branch_type, + branch_types[i].name); + if (err) + break; + } + return err; +} + +int db_export__call_path(struct db_export *dbe, struct call_path *cp) +{ + int err; + + if (cp->db_id) + return 0; + + if (cp->parent) { + err = db_export__call_path(dbe, cp->parent); + if (err) + return err; + } + + cp->db_id = ++dbe->call_path_last_db_id; + + if (dbe->export_call_path) + return dbe->export_call_path(dbe, cp); + + return 0; +} + +int db_export__call_return(struct db_export *dbe, struct call_return *cr) +{ + int err; + + if (cr->db_id) + return 0; + + err = db_export__call_path(dbe, cr->cp); + if (err) + return err; + + cr->db_id = ++dbe->call_return_last_db_id; + + if (dbe->export_call_return) + return dbe->export_call_return(dbe, cr); + + return 0; +} diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h new file mode 100644 index 000000000000..adbd22d66798 --- /dev/null +++ b/tools/perf/util/db-export.h @@ -0,0 +1,107 @@ +/* + * db-export.h: Support for exporting data suitable for import to a database + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#ifndef __PERF_DB_EXPORT_H +#define __PERF_DB_EXPORT_H + +#include <linux/types.h> +#include <linux/list.h> + +struct perf_evsel; +struct machine; +struct thread; +struct comm; +struct dso; +struct perf_sample; +struct addr_location; +struct call_return_processor; +struct call_path; +struct call_return; + +struct export_sample { + union perf_event *event; + struct perf_sample *sample; + struct perf_evsel *evsel; + struct thread *thread; + struct addr_location *al; + u64 db_id; + u64 comm_db_id; + u64 dso_db_id; + u64 sym_db_id; + u64 offset; /* ip offset from symbol start */ + u64 addr_dso_db_id; + u64 addr_sym_db_id; + u64 addr_offset; /* addr offset from symbol start */ +}; + +struct db_export { + int (*export_evsel)(struct db_export *dbe, struct perf_evsel *evsel); + int (*export_machine)(struct db_export *dbe, struct machine *machine); + int (*export_thread)(struct db_export *dbe, struct thread *thread, + u64 main_thread_db_id, struct machine *machine); + int (*export_comm)(struct db_export *dbe, struct comm *comm); + int (*export_comm_thread)(struct db_export *dbe, u64 db_id, + struct comm *comm, struct thread *thread); + int (*export_dso)(struct db_export *dbe, struct dso *dso, + struct machine *machine); + int (*export_symbol)(struct db_export *dbe, struct symbol *sym, + struct dso *dso); + int (*export_branch_type)(struct db_export *dbe, u32 branch_type, + const char *name); + int (*export_sample)(struct db_export *dbe, struct export_sample *es); + int (*export_call_path)(struct db_export *dbe, struct call_path *cp); + int (*export_call_return)(struct db_export *dbe, + struct call_return *cr); + struct call_return_processor *crp; + u64 evsel_last_db_id; + u64 machine_last_db_id; + u64 thread_last_db_id; + u64 comm_last_db_id; + u64 comm_thread_last_db_id; + u64 dso_last_db_id; + u64 symbol_last_db_id; + u64 sample_last_db_id; + u64 call_path_last_db_id; + u64 call_return_last_db_id; + struct list_head deferred; +}; + +int db_export__init(struct db_export *dbe); +int db_export__flush(struct db_export *dbe); +void db_export__exit(struct db_export *dbe); +int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel); +int db_export__machine(struct db_export *dbe, struct machine *machine); +int db_export__thread(struct db_export *dbe, struct thread *thread, + struct machine *machine, struct comm *comm); +int db_export__comm(struct db_export *dbe, struct comm *comm, + struct thread *main_thread); +int db_export__comm_thread(struct db_export *dbe, struct comm *comm, + struct thread *thread); +int db_export__dso(struct db_export *dbe, struct dso *dso, + struct machine *machine); +int db_export__symbol(struct db_export *dbe, struct symbol *sym, + struct dso *dso); +int db_export__branch_type(struct db_export *dbe, u32 branch_type, + const char *name); +int db_export__sample(struct db_export *dbe, union perf_event *event, + struct perf_sample *sample, struct perf_evsel *evsel, + struct thread *thread, struct addr_location *al); + +int db_export__branch_types(struct db_export *dbe); + +int db_export__call_path(struct db_export *dbe, struct call_path *cp); +int db_export__call_return(struct db_export *dbe, struct call_return *cr); + +#endif diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index ba357f3226c6..ad60b2f20258 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -19,13 +19,14 @@ int verbose; bool dump_trace = false, quiet = false; int debug_ordered_events; +static int redirect_to_stderr; static int _eprintf(int level, int var, const char *fmt, va_list args) { int ret = 0; if (var >= level) { - if (use_browser >= 1) + if (use_browser >= 1 && !redirect_to_stderr) ui_helpline__vshow(fmt, args); else ret = vfprintf(stderr, fmt, args); @@ -145,6 +146,7 @@ static struct debug_variable { } debug_variables[] = { { .name = "verbose", .ptr = &verbose }, { .name = "ordered-events", .ptr = &debug_ordered_events}, + { .name = "stderr", .ptr = &redirect_to_stderr}, { .name = NULL, } }; diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 0247acfdfaca..c2f7d3b90966 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -21,8 +21,10 @@ char dso__symtab_origin(const struct dso *dso) [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b', [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd', [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K', + [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP] = 'm', [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g', [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', + [DSO_BINARY_TYPE__GUEST_KMODULE_COMP] = 'M', [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', }; @@ -112,11 +114,13 @@ int dso__read_binary_type_filename(const struct dso *dso, break; case DSO_BINARY_TYPE__GUEST_KMODULE: + case DSO_BINARY_TYPE__GUEST_KMODULE_COMP: path__join3(filename, size, symbol_conf.symfs, root_dir, dso->long_name); break; case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: __symbol__join_symfs(filename, size, dso->long_name); break; @@ -137,6 +141,73 @@ int dso__read_binary_type_filename(const struct dso *dso, return ret; } +static const struct { + const char *fmt; + int (*decompress)(const char *input, int output); +} compressions[] = { +#ifdef HAVE_ZLIB_SUPPORT + { "gz", gzip_decompress_to_file }, +#endif + { NULL, NULL }, +}; + +bool is_supported_compression(const char *ext) +{ + unsigned i; + + for (i = 0; compressions[i].fmt; i++) { + if (!strcmp(ext, compressions[i].fmt)) + return true; + } + return false; +} + +bool is_kmodule_extension(const char *ext) +{ + if (strncmp(ext, "ko", 2)) + return false; + + if (ext[2] == '\0' || (ext[2] == '.' && is_supported_compression(ext+3))) + return true; + + return false; +} + +bool is_kernel_module(const char *pathname, bool *compressed) +{ + const char *ext = strrchr(pathname, '.'); + + if (ext == NULL) + return false; + + if (is_supported_compression(ext + 1)) { + if (compressed) + *compressed = true; + ext -= 3; + } else if (compressed) + *compressed = false; + + return is_kmodule_extension(ext + 1); +} + +bool decompress_to_file(const char *ext, const char *filename, int output_fd) +{ + unsigned i; + + for (i = 0; compressions[i].fmt; i++) { + if (!strcmp(ext, compressions[i].fmt)) + return !compressions[i].decompress(filename, + output_fd); + } + return false; +} + +bool dso__needs_decompress(struct dso *dso) +{ + return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; +} + /* * Global list of open DSOs and the counter. */ @@ -461,12 +532,8 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size) break; cache_offset = offset & DSO__DATA_CACHE_MASK; - ret = -EINVAL; - - if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET)) - break; - ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE); + ret = pread(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE, cache_offset); if (ret <= 0) break; diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index acb651acc7fd..ced92841ff97 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -22,7 +22,9 @@ enum dso_binary_type { DSO_BINARY_TYPE__BUILDID_DEBUGINFO, DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, + DSO_BINARY_TYPE__GUEST_KMODULE_COMP, DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP, DSO_BINARY_TYPE__KCORE, DSO_BINARY_TYPE__GUEST_KCORE, DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, @@ -127,6 +129,7 @@ struct dso { const char *long_name; u16 long_name_len; u16 short_name_len; + void *dwfl; /* DWARF debug info */ /* dso data file */ struct { @@ -136,8 +139,14 @@ struct dso { u32 status_seen; size_t file_size; struct list_head open_entry; + u64 frame_offset; } data; + union { /* Tool specific area */ + void *priv; + u64 db_id; + }; + char name[0]; }; @@ -179,6 +188,11 @@ int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir); char dso__symtab_origin(const struct dso *dso); int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, char *root_dir, char *filename, size_t size); +bool is_supported_compression(const char *ext); +bool is_kmodule_extension(const char *ext); +bool is_kernel_module(const char *pathname, bool *compressed); +bool decompress_to_file(const char *ext, const char *filename, int output_fd); +bool dso__needs_decompress(struct dso *dso); /* * The dso__data_* external interface provides following functions: diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 4af6b279e34a..6c6d044e959a 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -28,6 +28,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", [PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID", [PERF_RECORD_FINISHED_ROUND] = "FINISHED_ROUND", + [PERF_RECORD_ID_INDEX] = "ID_INDEX", }; const char *perf_event__name(unsigned int id) @@ -730,12 +731,12 @@ int perf_event__process(struct perf_tool *tool __maybe_unused, return machine__process_event(machine, event, sample); } -void thread__find_addr_map(struct thread *thread, - struct machine *machine, u8 cpumode, +void thread__find_addr_map(struct thread *thread, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al) { struct map_groups *mg = thread->mg; + struct machine *machine = mg->machine; bool load_map = false; al->machine = machine; @@ -806,14 +807,14 @@ try_again: } } -void thread__find_addr_location(struct thread *thread, struct machine *machine, +void thread__find_addr_location(struct thread *thread, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al) { - thread__find_addr_map(thread, machine, cpumode, type, addr, al); + thread__find_addr_map(thread, cpumode, type, addr, al); if (al->map != NULL) al->sym = map__find_symbol(al->map, al->addr, - machine->symbol_filter); + thread->mg->machine->symbol_filter); else al->sym = NULL; } @@ -842,8 +843,7 @@ int perf_event__preprocess_sample(const union perf_event *event, machine->vmlinux_maps[MAP__FUNCTION] == NULL) machine__create_kernel_maps(machine); - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->ip, al); + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); @@ -902,16 +902,14 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr) void perf_event__preprocess_sample_addr(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct thread *thread, struct addr_location *al) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->addr, al); + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->addr, al); if (!al->map) - thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE, + thread__find_addr_map(thread, cpumode, MAP__VARIABLE, sample->addr, al); al->cpu = sample->cpu; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 5699e7e2a790..c4ffe2bd0738 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -143,6 +143,32 @@ struct branch_stack { struct branch_entry entries[0]; }; +enum { + PERF_IP_FLAG_BRANCH = 1ULL << 0, + PERF_IP_FLAG_CALL = 1ULL << 1, + PERF_IP_FLAG_RETURN = 1ULL << 2, + PERF_IP_FLAG_CONDITIONAL = 1ULL << 3, + PERF_IP_FLAG_SYSCALLRET = 1ULL << 4, + PERF_IP_FLAG_ASYNC = 1ULL << 5, + PERF_IP_FLAG_INTERRUPT = 1ULL << 6, + PERF_IP_FLAG_TX_ABORT = 1ULL << 7, + PERF_IP_FLAG_TRACE_BEGIN = 1ULL << 8, + PERF_IP_FLAG_TRACE_END = 1ULL << 9, + PERF_IP_FLAG_IN_TX = 1ULL << 10, +}; + +#define PERF_BRANCH_MASK (\ + PERF_IP_FLAG_BRANCH |\ + PERF_IP_FLAG_CALL |\ + PERF_IP_FLAG_RETURN |\ + PERF_IP_FLAG_CONDITIONAL |\ + PERF_IP_FLAG_SYSCALLRET |\ + PERF_IP_FLAG_ASYNC |\ + PERF_IP_FLAG_INTERRUPT |\ + PERF_IP_FLAG_TX_ABORT |\ + PERF_IP_FLAG_TRACE_BEGIN |\ + PERF_IP_FLAG_TRACE_END) + struct perf_sample { u64 ip; u32 pid, tid; @@ -162,6 +188,7 @@ struct perf_sample { struct ip_callchain *callchain; struct branch_stack *branch_stack; struct regs_dump user_regs; + struct regs_dump intr_regs; struct stack_dump user_stack; struct sample_read read; }; @@ -187,6 +214,7 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_HEADER_TRACING_DATA = 66, PERF_RECORD_HEADER_BUILD_ID = 67, PERF_RECORD_FINISHED_ROUND = 68, + PERF_RECORD_ID_INDEX = 69, PERF_RECORD_HEADER_MAX }; @@ -214,6 +242,7 @@ struct events_stats { u32 nr_invalid_chains; u32 nr_unknown_id; u32 nr_unprocessable_samples; + u32 nr_unordered_events; }; struct attr_event { @@ -239,6 +268,19 @@ struct tracing_data_event { u32 size; }; +struct id_index_entry { + u64 id; + u64 idx; + u64 cpu; + u64 tid; +}; + +struct id_index_event { + struct perf_event_header header; + u64 nr; + struct id_index_entry entries[0]; +}; + union perf_event { struct perf_event_header header; struct mmap_event mmap; @@ -253,6 +295,7 @@ union perf_event { struct event_type_event event_type; struct tracing_data_event tracing_data; struct build_id_event build_id; + struct id_index_event id_index; }; void perf_event__print_totals(void); @@ -322,7 +365,6 @@ bool is_bts_event(struct perf_event_attr *attr); bool sample_addr_correlates_sym(struct perf_event_attr *attr); void perf_event__preprocess_sample_addr(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct thread *thread, struct addr_location *al); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 3c9e77d6b4c2..28b8ce86bf12 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -8,6 +8,7 @@ */ #include "util.h" #include <api/fs/debugfs.h> +#include <api/fs/fs.h> #include <poll.h> #include "cpumap.h" #include "thread_map.h" @@ -24,6 +25,7 @@ #include <linux/bitops.h> #include <linux/hash.h> +#include <linux/log2.h> static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx); static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx); @@ -413,7 +415,7 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) int nfds = 0; struct perf_evsel *evsel; - list_for_each_entry(evsel, &evlist->entries, node) { + evlist__for_each(evlist, evsel) { if (evsel->system_wide) nfds += nr_cpus; else @@ -527,6 +529,22 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist, return 0; } +static void perf_evlist__set_sid_idx(struct perf_evlist *evlist, + struct perf_evsel *evsel, int idx, int cpu, + int thread) +{ + struct perf_sample_id *sid = SID(evsel, cpu, thread); + sid->idx = idx; + if (evlist->cpus && cpu >= 0) + sid->cpu = evlist->cpus->map[cpu]; + else + sid->cpu = -1; + if (!evsel->system_wide && evlist->threads && thread >= 0) + sid->tid = evlist->threads->map[thread]; + else + sid->tid = -1; +} + struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id) { struct hlist_head *head; @@ -800,14 +818,26 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, perf_evlist__mmap_get(evlist, idx); } - if (__perf_evlist__add_pollfd(evlist, fd, idx) < 0) { + /* + * The system_wide flag causes a selected event to be opened + * always without a pid. Consequently it will never get a + * POLLHUP, but it is used for tracking in combination with + * other events, so it should not need to be polled anyway. + * Therefore don't add it for polling. + */ + if (!evsel->system_wide && + __perf_evlist__add_pollfd(evlist, fd, idx) < 0) { perf_evlist__mmap_put(evlist, idx); return -1; } - if ((evsel->attr.read_format & PERF_FORMAT_ID) && - perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) - return -1; + if (evsel->attr.read_format & PERF_FORMAT_ID) { + if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread, + fd) < 0) + return -1; + perf_evlist__set_sid_idx(evlist, evsel, idx, cpu, + thread); + } } return 0; @@ -864,10 +894,24 @@ out_unmap: static size_t perf_evlist__mmap_size(unsigned long pages) { - /* 512 kiB: default amount of unprivileged mlocked memory */ - if (pages == UINT_MAX) - pages = (512 * 1024) / page_size; - else if (!is_power_of_2(pages)) + if (pages == UINT_MAX) { + int max; + + if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) { + /* + * Pick a once upon a time good value, i.e. things look + * strange since we can't read a sysctl value, but lets not + * die yet... + */ + max = 512; + } else { + max -= (page_size / 1024); + } + + pages = (max * 1024) / page_size; + if (!is_power_of_2(pages)) + pages = rounddown_pow_of_two(pages); + } else if (!is_power_of_2(pages)) return 0; return (pages + 1) * page_size; @@ -904,7 +948,7 @@ static long parse_pages_arg(const char *str, unsigned long min, /* leave number of pages at 0 */ } else if (!is_power_of_2(pages)) { /* round pages up to next power of 2 */ - pages = next_pow2_l(pages); + pages = roundup_pow_of_two(pages); if (!pages) return -EINVAL; pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n", @@ -1392,33 +1436,6 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) return printed + fprintf(fp, "\n"); } -int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused, - int err, char *buf, size_t size) -{ - char sbuf[128]; - - switch (err) { - case ENOENT: - scnprintf(buf, size, "%s", - "Error:\tUnable to find debugfs\n" - "Hint:\tWas your kernel was compiled with debugfs support?\n" - "Hint:\tIs the debugfs filesystem mounted?\n" - "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'"); - break; - case EACCES: - scnprintf(buf, size, - "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n" - "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n", - debugfs_mountpoint, debugfs_mountpoint); - break; - default: - scnprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf))); - break; - } - - return 0; -} - int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, int err, char *buf, size_t size) { @@ -1455,6 +1472,37 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, return 0; } +int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size) +{ + char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf)); + int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0; + + switch (err) { + case EPERM: + sysctl__read_int("kernel/perf_event_mlock_kb", &pages_max_per_user); + printed += scnprintf(buf + printed, size - printed, + "Error:\t%s.\n" + "Hint:\tCheck /proc/sys/kernel/perf_event_mlock_kb (%d kB) setting.\n" + "Hint:\tTried using %zd kB.\n", + emsg, pages_max_per_user, pages_attempted); + + if (pages_attempted >= pages_max_per_user) { + printed += scnprintf(buf + printed, size - printed, + "Hint:\tTry 'sudo sh -c \"echo %d > /proc/sys/kernel/perf_event_mlock_kb\"', or\n", + pages_max_per_user + pages_attempted); + } + + printed += scnprintf(buf + printed, size - printed, + "Hint:\tTry using a smaller -m/--mmap-pages value."); + break; + default: + scnprintf(buf, size, "%s", emsg); + break; + } + + return 0; +} + void perf_evlist__to_front(struct perf_evlist *evlist, struct perf_evsel *move_evsel) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 649b0c597283..e99a67632831 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -28,7 +28,7 @@ struct perf_mmap { int mask; int refcnt; unsigned int prev; - char event_copy[PERF_SAMPLE_MAX_SIZE]; + char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8))); }; struct perf_evlist { @@ -183,8 +183,8 @@ static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); -int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size); int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size); +int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size); static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 2f9e68025ede..ea51a90e20a0 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -658,9 +658,22 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->mmap_data = track; } + /* + * We don't allow user space callchains for function trace + * event, due to issues with page faults while tracing page + * fault handler and its overall trickiness nature. + */ + if (perf_evsel__is_function_event(evsel)) + evsel->attr.exclude_callchain_user = 1; + if (callchain_param.enabled && !evsel->no_aux_samples) perf_evsel__config_callgraph(evsel); + if (opts->sample_intr_regs) { + attr->sample_regs_intr = PERF_REGS_MASK; + perf_evsel__set_sample_bit(evsel, REGS_INTR); + } + if (target__has_cpu(&opts->target)) perf_evsel__set_sample_bit(evsel, CPU); @@ -696,6 +709,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (opts->sample_weight) perf_evsel__set_sample_bit(evsel, WEIGHT); + attr->task = track; attr->mmap = track; attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; @@ -784,6 +798,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads) int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) { + if (ncpus == 0 || nthreads == 0) + return 0; + if (evsel->system_wide) nthreads = 1; @@ -853,8 +870,6 @@ void perf_evsel__exit(struct perf_evsel *evsel) perf_evsel__free_id(evsel); close_cgroup(evsel->cgrp); zfree(&evsel->group_name); - if (evsel->tp_format) - pevent_free_format(evsel->tp_format); zfree(&evsel->name); perf_evsel__object.fini(evsel); } @@ -865,9 +880,8 @@ void perf_evsel__delete(struct perf_evsel *evsel) free(evsel); } -static inline void compute_deltas(struct perf_evsel *evsel, - int cpu, - struct perf_counts_values *count) +void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, + struct perf_counts_values *count) { struct perf_counts_values tmp; @@ -887,81 +901,60 @@ static inline void compute_deltas(struct perf_evsel *evsel, count->run = count->run - tmp.run; } -int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, - int cpu, int thread, bool scale) +void perf_counts_values__scale(struct perf_counts_values *count, + bool scale, s8 *pscaled) { - struct perf_counts_values count; - size_t nv = scale ? 3 : 1; - - if (FD(evsel, cpu, thread) < 0) - return -EINVAL; - - if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0) - return -ENOMEM; - - if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) - return -errno; - - compute_deltas(evsel, cpu, &count); + s8 scaled = 0; if (scale) { - if (count.run == 0) - count.val = 0; - else if (count.run < count.ena) - count.val = (u64)((double)count.val * count.ena / count.run + 0.5); + if (count->run == 0) { + scaled = -1; + count->val = 0; + } else if (count->run < count->ena) { + scaled = 1; + count->val = (u64)((double) count->val * count->ena / count->run + 0.5); + } } else - count.ena = count.run = 0; + count->ena = count->run = 0; - evsel->counts->cpu[cpu] = count; - return 0; + if (pscaled) + *pscaled = scaled; } -int __perf_evsel__read(struct perf_evsel *evsel, - int ncpus, int nthreads, bool scale) +int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread, + perf_evsel__read_cb_t cb) { - size_t nv = scale ? 3 : 1; - int cpu, thread; - struct perf_counts_values *aggr = &evsel->counts->aggr, count; + struct perf_counts_values count; - if (evsel->system_wide) - nthreads = 1; + memset(&count, 0, sizeof(count)); - aggr->val = aggr->ena = aggr->run = 0; + if (FD(evsel, cpu, thread) < 0) + return -EINVAL; - for (cpu = 0; cpu < ncpus; cpu++) { - for (thread = 0; thread < nthreads; thread++) { - if (FD(evsel, cpu, thread) < 0) - continue; + if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0) + return -errno; - if (readn(FD(evsel, cpu, thread), - &count, nv * sizeof(u64)) < 0) - return -errno; + return cb(evsel, cpu, thread, &count); +} - aggr->val += count.val; - if (scale) { - aggr->ena += count.ena; - aggr->run += count.run; - } - } - } +int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, + int cpu, int thread, bool scale) +{ + struct perf_counts_values count; + size_t nv = scale ? 3 : 1; - compute_deltas(evsel, -1, aggr); + if (FD(evsel, cpu, thread) < 0) + return -EINVAL; - evsel->counts->scaled = 0; - if (scale) { - if (aggr->run == 0) { - evsel->counts->scaled = -1; - aggr->val = 0; - return 0; - } + if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0) + return -ENOMEM; - if (aggr->run < aggr->ena) { - evsel->counts->scaled = 1; - aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5); - } - } else - aggr->ena = aggr->run = 0; + if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) + return -errno; + perf_evsel__compute_deltas(evsel, cpu, &count); + perf_counts_values__scale(&count, scale, NULL); + evsel->counts->cpu[cpu] = count; return 0; } @@ -1039,6 +1032,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) ret += PRINT_ATTR_X64(branch_sample_type); ret += PRINT_ATTR_X64(sample_regs_user); ret += PRINT_ATTR_U32(sample_stack_user); + ret += PRINT_ATTR_X64(sample_regs_intr); ret += fprintf(fp, "%.60s\n", graph_dotted_line); @@ -1538,6 +1532,23 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; } + data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE; + if (type & PERF_SAMPLE_REGS_INTR) { + OVERFLOW_CHECK_u64(array); + data->intr_regs.abi = *array; + array++; + + if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { + u64 mask = evsel->attr.sample_regs_intr; + + sz = hweight_long(mask) * sizeof(u64); + OVERFLOW_CHECK(array, sz, max_size); + data->intr_regs.mask = mask; + data->intr_regs.regs = (u64 *)array; + array = (void *)array + sz; + } + } + return 0; } @@ -1633,6 +1644,16 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_TRANSACTION) result += sizeof(u64); + if (type & PERF_SAMPLE_REGS_INTR) { + if (sample->intr_regs.abi) { + result += sizeof(u64); + sz = hweight_long(sample->intr_regs.mask) * sizeof(u64); + result += sz; + } else { + result += sizeof(u64); + } + } + return result; } @@ -1811,6 +1832,17 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, array++; } + if (type & PERF_SAMPLE_REGS_INTR) { + if (sample->intr_regs.abi) { + *array++ = sample->intr_regs.abi; + sz = hweight_long(sample->intr_regs.mask) * sizeof(u64); + memcpy(array, sample->intr_regs.regs, sz); + array = (void *)array + sz; + } else { + *array++ = 0; + } + } + return 0; } @@ -1940,7 +1972,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value) bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), - bit_name(IDENTIFIER), + bit_name(IDENTIFIER), bit_name(REGS_INTR), { .name = NULL, } }; #undef bit_name diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 163c5604e5d1..38622747d130 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -36,6 +36,9 @@ struct perf_sample_id { struct hlist_node node; u64 id; struct perf_evsel *evsel; + int idx; + int cpu; + pid_t tid; /* Holds total ID period value for PERF_SAMPLE_READ processing. */ u64 period; @@ -54,6 +57,7 @@ struct cgroup_sel; * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or * PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all * is used there is an id sample appended to non-sample events + * @priv: And what is in its containing unnamed union are tool specific */ struct perf_evsel { struct list_head node; @@ -69,10 +73,12 @@ struct perf_evsel { char *name; double scale; const char *unit; + bool snapshot; struct event_format *tp_format; union { void *priv; off_t id_offset; + u64 db_id; }; struct cgroup_sel *cgrp; void *handler; @@ -86,6 +92,8 @@ struct perf_evsel { bool immediate; bool system_wide; bool tracking; + bool per_pkg; + unsigned long *per_pkg_mask; /* parse modifier helper */ int exclude_GH; int nr_members; @@ -105,6 +113,12 @@ struct thread_map; struct perf_evlist; struct record_opts; +void perf_counts_values__scale(struct perf_counts_values *count, + bool scale, s8 *pscaled); + +void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, + struct perf_counts_values *count); + int perf_evsel__object_config(size_t object_size, int (*init)(struct perf_evsel *evsel), void (*fini)(struct perf_evsel *evsel)); @@ -222,6 +236,13 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1, (a)->attr.type == (b)->attr.type && \ (a)->attr.config == (b)->attr.config) +typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel, + int cpu, int thread, + struct perf_counts_values *count); + +int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread, + perf_evsel__read_cb_t cb); + int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale); @@ -251,35 +272,6 @@ static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel, return __perf_evsel__read_on_cpu(evsel, cpu, thread, true); } -int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads, - bool scale); - -/** - * perf_evsel__read - Read the aggregate results on all CPUs - * - * @evsel - event selector to read value - * @ncpus - Number of cpus affected, from zero - * @nthreads - Number of threads affected, from zero - */ -static inline int perf_evsel__read(struct perf_evsel *evsel, - int ncpus, int nthreads) -{ - return __perf_evsel__read(evsel, ncpus, nthreads, false); -} - -/** - * perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled - * - * @evsel - event selector to read value - * @ncpus - Number of cpus affected, from zero - * @nthreads - Number of threads affected, from zero - */ -static inline int perf_evsel__read_scaled(struct perf_evsel *evsel, - int ncpus, int nthreads) -{ - return __perf_evsel__read(evsel, ncpus, nthreads, true); -} - int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample); diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-vdso-map.c new file mode 100644 index 000000000000..95ef1cffc056 --- /dev/null +++ b/tools/perf/util/find-vdso-map.c @@ -0,0 +1,30 @@ +static int find_vdso_map(void **start, void **end) +{ + FILE *maps; + char line[128]; + int found = 0; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) { + fprintf(stderr, "vdso: cannot open maps\n"); + return -1; + } + + while (!found && fgets(line, sizeof(line), maps)) { + int m = -1; + + /* We care only about private r-x mappings. */ + if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n", + start, end, &m)) + continue; + if (m < 0) + continue; + + if (!strncmp(&line[m], VDSO__MAP_NAME, + sizeof(VDSO__MAP_NAME) - 1)) + found = 1; + } + + fclose(maps); + return !found; +} diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 26f5b2fe5dc8..1f407f7352a7 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -24,8 +24,6 @@ #include "build-id.h" #include "data.h" -static bool no_buildid_cache = false; - static u32 header_argc; static const char **header_argv; @@ -79,10 +77,7 @@ static int do_write(int fd, const void *buf, size_t size) return 0; } -#define NAME_ALIGN 64 - -static int write_padded(int fd, const void *bf, size_t count, - size_t count_aligned) +int write_padded(int fd, const void *bf, size_t count, size_t count_aligned) { static const char zero_buf[NAME_ALIGN]; int err = do_write(fd, bf, count); @@ -171,340 +166,6 @@ perf_header__set_cmdline(int argc, const char **argv) return 0; } -#define dsos__for_each_with_build_id(pos, head) \ - list_for_each_entry(pos, head, node) \ - if (!pos->has_build_id) \ - continue; \ - else - -static int write_buildid(const char *name, size_t name_len, u8 *build_id, - pid_t pid, u16 misc, int fd) -{ - int err; - struct build_id_event b; - size_t len; - - len = name_len + 1; - len = PERF_ALIGN(len, NAME_ALIGN); - - memset(&b, 0, sizeof(b)); - memcpy(&b.build_id, build_id, BUILD_ID_SIZE); - b.pid = pid; - b.header.misc = misc; - b.header.size = sizeof(b) + len; - - err = do_write(fd, &b, sizeof(b)); - if (err < 0) - return err; - - return write_padded(fd, name, name_len + 1, len); -} - -static int __dsos__hit_all(struct list_head *head) -{ - struct dso *pos; - - list_for_each_entry(pos, head, node) - pos->hit = true; - - return 0; -} - -static int machine__hit_all_dsos(struct machine *machine) -{ - int err; - - err = __dsos__hit_all(&machine->kernel_dsos.head); - if (err) - return err; - - return __dsos__hit_all(&machine->user_dsos.head); -} - -int dsos__hit_all(struct perf_session *session) -{ - struct rb_node *nd; - int err; - - err = machine__hit_all_dsos(&session->machines.host); - if (err) - return err; - - for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - - err = machine__hit_all_dsos(pos); - if (err) - return err; - } - - return 0; -} - -static int __dsos__write_buildid_table(struct list_head *head, - struct machine *machine, - pid_t pid, u16 misc, int fd) -{ - char nm[PATH_MAX]; - struct dso *pos; - - dsos__for_each_with_build_id(pos, head) { - int err; - const char *name; - size_t name_len; - - if (!pos->hit) - continue; - - if (dso__is_vdso(pos)) { - name = pos->short_name; - name_len = pos->short_name_len + 1; - } else if (dso__is_kcore(pos)) { - machine__mmap_name(machine, nm, sizeof(nm)); - name = nm; - name_len = strlen(nm) + 1; - } else { - name = pos->long_name; - name_len = pos->long_name_len + 1; - } - - err = write_buildid(name, name_len, pos->build_id, - pid, misc, fd); - if (err) - return err; - } - - return 0; -} - -static int machine__write_buildid_table(struct machine *machine, int fd) -{ - int err; - u16 kmisc = PERF_RECORD_MISC_KERNEL, - umisc = PERF_RECORD_MISC_USER; - - if (!machine__is_host(machine)) { - kmisc = PERF_RECORD_MISC_GUEST_KERNEL; - umisc = PERF_RECORD_MISC_GUEST_USER; - } - - err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine, - machine->pid, kmisc, fd); - if (err == 0) - err = __dsos__write_buildid_table(&machine->user_dsos.head, - machine, machine->pid, umisc, - fd); - return err; -} - -static int dsos__write_buildid_table(struct perf_header *header, int fd) -{ - struct perf_session *session = container_of(header, - struct perf_session, header); - struct rb_node *nd; - int err = machine__write_buildid_table(&session->machines.host, fd); - - if (err) - return err; - - for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - err = machine__write_buildid_table(pos, fd); - if (err) - break; - } - return err; -} - -int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, - const char *name, bool is_kallsyms, bool is_vdso) -{ - const size_t size = PATH_MAX; - char *realname, *filename = zalloc(size), - *linkname = zalloc(size), *targetname; - int len, err = -1; - bool slash = is_kallsyms || is_vdso; - - if (is_kallsyms) { - if (symbol_conf.kptr_restrict) { - pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n"); - err = 0; - goto out_free; - } - realname = (char *) name; - } else - realname = realpath(name, NULL); - - if (realname == NULL || filename == NULL || linkname == NULL) - goto out_free; - - len = scnprintf(filename, size, "%s%s%s", - debugdir, slash ? "/" : "", - is_vdso ? DSO__NAME_VDSO : realname); - if (mkdir_p(filename, 0755)) - goto out_free; - - snprintf(filename + len, size - len, "/%s", sbuild_id); - - if (access(filename, F_OK)) { - if (is_kallsyms) { - if (copyfile("/proc/kallsyms", filename)) - goto out_free; - } else if (link(realname, filename) && copyfile(name, filename)) - goto out_free; - } - - len = scnprintf(linkname, size, "%s/.build-id/%.2s", - debugdir, sbuild_id); - - if (access(linkname, X_OK) && mkdir_p(linkname, 0755)) - goto out_free; - - snprintf(linkname + len, size - len, "/%s", sbuild_id + 2); - targetname = filename + strlen(debugdir) - 5; - memcpy(targetname, "../..", 5); - - if (symlink(targetname, linkname) == 0) - err = 0; -out_free: - if (!is_kallsyms) - free(realname); - free(filename); - free(linkname); - return err; -} - -static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, - const char *name, const char *debugdir, - bool is_kallsyms, bool is_vdso) -{ - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - - build_id__sprintf(build_id, build_id_size, sbuild_id); - - return build_id_cache__add_s(sbuild_id, debugdir, name, - is_kallsyms, is_vdso); -} - -int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) -{ - const size_t size = PATH_MAX; - char *filename = zalloc(size), - *linkname = zalloc(size); - int err = -1; - - if (filename == NULL || linkname == NULL) - goto out_free; - - snprintf(linkname, size, "%s/.build-id/%.2s/%s", - debugdir, sbuild_id, sbuild_id + 2); - - if (access(linkname, F_OK)) - goto out_free; - - if (readlink(linkname, filename, size - 1) < 0) - goto out_free; - - if (unlink(linkname)) - goto out_free; - - /* - * Since the link is relative, we must make it absolute: - */ - snprintf(linkname, size, "%s/.build-id/%.2s/%s", - debugdir, sbuild_id, filename); - - if (unlink(linkname)) - goto out_free; - - err = 0; -out_free: - free(filename); - free(linkname); - return err; -} - -static int dso__cache_build_id(struct dso *dso, struct machine *machine, - const char *debugdir) -{ - bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; - bool is_vdso = dso__is_vdso(dso); - const char *name = dso->long_name; - char nm[PATH_MAX]; - - if (dso__is_kcore(dso)) { - is_kallsyms = true; - machine__mmap_name(machine, nm, sizeof(nm)); - name = nm; - } - return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, - debugdir, is_kallsyms, is_vdso); -} - -static int __dsos__cache_build_ids(struct list_head *head, - struct machine *machine, const char *debugdir) -{ - struct dso *pos; - int err = 0; - - dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, machine, debugdir)) - err = -1; - - return err; -} - -static int machine__cache_build_ids(struct machine *machine, const char *debugdir) -{ - int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine, - debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine, - debugdir); - return ret; -} - -static int perf_session__cache_build_ids(struct perf_session *session) -{ - struct rb_node *nd; - int ret; - char debugdir[PATH_MAX]; - - snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); - - if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) - return -1; - - ret = machine__cache_build_ids(&session->machines.host, debugdir); - - for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret |= machine__cache_build_ids(pos, debugdir); - } - return ret ? -1 : 0; -} - -static bool machine__read_build_ids(struct machine *machine, bool with_hits) -{ - bool ret; - - ret = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits); - ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits); - return ret; -} - -static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits) -{ - struct rb_node *nd; - bool ret = machine__read_build_ids(&session->machines.host, with_hits); - - for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret |= machine__read_build_ids(pos, with_hits); - } - - return ret; -} - static int write_tracing_data(int fd, struct perf_header *h __maybe_unused, struct perf_evlist *evlist) { @@ -523,13 +184,12 @@ static int write_build_id(int fd, struct perf_header *h, if (!perf_session__read_build_ids(session, true)) return -1; - err = dsos__write_buildid_table(h, fd); + err = perf_session__write_buildid_table(session, fd); if (err < 0) { pr_debug("failed to write buildid table\n"); return err; } - if (!no_buildid_cache) - perf_session__cache_build_ids(session); + perf_session__cache_build_ids(session); return 0; } @@ -601,8 +261,10 @@ static int __write_cpudesc(int fd, const char *cpuinfo_proc) break; } - if (ret) + if (ret) { + ret = -1; goto done; + } s = buf; @@ -965,7 +627,8 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused, n = sscanf(buf, "%*s %"PRIu64, &mem); if (n == 1) ret = do_write(fd, &mem, sizeof(mem)); - } + } else + ret = -1; free(buf); fclose(fp); return ret; @@ -1603,7 +1266,7 @@ static int __event_process_build_id(struct build_id_event *bev, dso__set_build_id(dso, &bev->build_id); - if (filename[0] == '[') + if (!is_kernel_module(filename, NULL)) dso->kernel = dso_type; build_id__sprintf(dso->build_id, sizeof(dso->build_id), @@ -2477,6 +2140,7 @@ static const int attr_file_abi_sizes[] = { [1] = PERF_ATTR_SIZE_VER1, [2] = PERF_ATTR_SIZE_VER2, [3] = PERF_ATTR_SIZE_VER3, + [4] = PERF_ATTR_SIZE_VER4, 0, }; @@ -2573,6 +2237,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, * - unique number to identify actual perf.data files * - encode endianness of file */ + ph->version = PERF_HEADER_VERSION_2; /* check magic number with one endianness */ if (magic == __perf_magic2) @@ -2583,7 +2248,6 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, return -1; ph->needs_swap = true; - ph->version = PERF_HEADER_VERSION_2; return 0; } @@ -3124,8 +2788,3 @@ int perf_event__process_build_id(struct perf_tool *tool __maybe_unused, session); return 0; } - -void disable_buildid_cache(void) -{ - no_buildid_cache = true; -} diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 8f5cbaea64a5..3bb90ac172a1 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -122,10 +122,6 @@ int perf_header__process_sections(struct perf_header *header, int fd, int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full); -int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, - const char *name, bool is_kallsyms, bool is_vdso); -int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir); - int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process); @@ -151,7 +147,9 @@ int perf_event__process_build_id(struct perf_tool *tool, struct perf_session *session); bool is_perf_magic(u64 magic); -int dsos__hit_all(struct perf_session *session); +#define NAME_ALIGN 64 + +int write_padded(int fd, const void *bf, size_t count, size_t count_aligned); /* * arch specific callback diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 6e88b9e395df..70b48a65064c 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -6,6 +6,7 @@ #include "evlist.h" #include "evsel.h" #include "annotate.h" +#include "ui/progress.h" #include <math.h> static bool hists__filter_entry_by_dso(struct hists *hists, @@ -240,6 +241,20 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) return he->stat.period == 0; } +static void hists__delete_entry(struct hists *hists, struct hist_entry *he) +{ + rb_erase(&he->rb_node, &hists->entries); + + if (sort__need_collapse) + rb_erase(&he->rb_node_in, &hists->entries_collapsed); + + --hists->nr_entries; + if (!he->filtered) + --hists->nr_non_filtered_entries; + + hist_entry__delete(he); +} + void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) { struct rb_node *next = rb_first(&hists->entries); @@ -257,16 +272,7 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) (zap_kernel && n->level != '.') || hists__decay_entry(hists, n)) && !n->used) { - rb_erase(&n->rb_node, &hists->entries); - - if (sort__need_collapse) - rb_erase(&n->rb_node_in, &hists->entries_collapsed); - - --hists->nr_entries; - if (!n->filtered) - --hists->nr_non_filtered_entries; - - hist_entry__free(n); + hists__delete_entry(hists, n); } } } @@ -280,16 +286,7 @@ void hists__delete_entries(struct hists *hists) n = rb_entry(next, struct hist_entry, rb_node); next = rb_next(&n->rb_node); - rb_erase(&n->rb_node, &hists->entries); - - if (sort__need_collapse) - rb_erase(&n->rb_node_in, &hists->entries_collapsed); - - --hists->nr_entries; - if (!n->filtered) - --hists->nr_non_filtered_entries; - - hist_entry__free(n); + hists__delete_entry(hists, n); } } @@ -303,7 +300,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, size_t callchain_size = 0; struct hist_entry *he; - if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) + if (symbol_conf.use_callchain) callchain_size = sizeof(struct callchain_root); he = zalloc(sizeof(*he) + callchain_size); @@ -432,6 +429,8 @@ static struct hist_entry *add_hist_entry(struct hists *hists, if (!he) return NULL; + hists->nr_entries++; + rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, hists->entries_in); out: @@ -736,7 +735,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, iter->he = he; he_cache[iter->curr++] = he; - callchain_append(he->callchain, &callchain_cursor, sample->period); + hist_entry__append_callchain(he, sample); /* * We need to re-initialize the cursor since callchain_append() @@ -809,7 +808,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, iter->he = he; he_cache[iter->curr++] = he; - callchain_append(he->callchain, &cursor, sample->period); + if (symbol_conf.use_callchain) + callchain_append(he->callchain, &cursor, sample->period); return 0; } @@ -913,7 +913,7 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) if (perf_hpp__should_skip(fmt)) continue; - cmp = fmt->cmp(left, right); + cmp = fmt->cmp(fmt, left, right); if (cmp) break; } @@ -931,7 +931,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) if (perf_hpp__should_skip(fmt)) continue; - cmp = fmt->collapse(left, right); + cmp = fmt->collapse(fmt, left, right); if (cmp) break; } @@ -939,12 +939,13 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) return cmp; } -void hist_entry__free(struct hist_entry *he) +void hist_entry__delete(struct hist_entry *he) { zfree(&he->branch_info); zfree(&he->mem_info); zfree(&he->stat_acc); free_srcline(he->srcline); + free_callchain(he->callchain); free(he); } @@ -978,7 +979,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, iter->callchain, he->callchain); } - hist_entry__free(he); + hist_entry__delete(he); return false; } @@ -987,6 +988,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, else p = &(*p)->rb_right; } + hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, root); @@ -1024,7 +1026,10 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) if (!sort__need_collapse) return; + hists->nr_entries = 0; + root = hists__get_rotate_entries_in(hists); + next = rb_first(root); while (next) { @@ -1056,7 +1061,7 @@ static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) if (perf_hpp__should_skip(fmt)) continue; - cmp = fmt->sort(a, b); + cmp = fmt->sort(fmt, a, b); if (cmp) break; } @@ -1119,7 +1124,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, rb_insert_color(&he->rb_node, entries); } -void hists__output_resort(struct hists *hists) +void hists__output_resort(struct hists *hists, struct ui_progress *prog) { struct rb_root *root; struct rb_node *next; @@ -1148,6 +1153,9 @@ void hists__output_resort(struct hists *hists) if (!n->filtered) hists__calc_col_len(hists, n); + + if (prog) + ui_progress__update(prog, 1); } } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index d0ef9a19a744..2b690d028907 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -119,9 +119,9 @@ int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); int hist_entry__transaction_len(void); int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size, struct hists *hists); -void hist_entry__free(struct hist_entry *); +void hist_entry__delete(struct hist_entry *he); -void hists__output_resort(struct hists *hists); +void hists__output_resort(struct hists *hists, struct ui_progress *prog); void hists__collapse_resort(struct hists *hists, struct ui_progress *prog); void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); @@ -195,9 +195,12 @@ struct perf_hpp_fmt { struct hist_entry *he); int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he); - int64_t (*cmp)(struct hist_entry *a, struct hist_entry *b); - int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b); - int64_t (*sort)(struct hist_entry *a, struct hist_entry *b); + int64_t (*cmp)(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b); + int64_t (*collapse)(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b); + int64_t (*sort)(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b); struct list_head list; struct list_head sort_list; diff --git a/tools/perf/util/hweight.c b/tools/perf/util/hweight.c deleted file mode 100644 index 5c1d0d099f0d..000000000000 --- a/tools/perf/util/hweight.c +++ /dev/null @@ -1,31 +0,0 @@ -#include <linux/bitops.h> - -/** - * hweightN - returns the hamming weight of a N-bit word - * @x: the word to weigh - * - * The Hamming Weight of a number is the total number of bits set in it. - */ - -unsigned int hweight32(unsigned int w) -{ - unsigned int res = w - ((w >> 1) & 0x55555555); - res = (res & 0x33333333) + ((res >> 2) & 0x33333333); - res = (res + (res >> 4)) & 0x0F0F0F0F; - res = res + (res >> 8); - return (res + (res >> 16)) & 0x000000FF; -} - -unsigned long hweight64(__u64 w) -{ -#if BITS_PER_LONG == 32 - return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w); -#elif BITS_PER_LONG == 64 - __u64 res = w - ((w >> 1) & 0x5555555555555555ul); - res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul); - res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful; - res = res + (res >> 8); - res = res + (res >> 16); - return (res + (res >> 32)) & 0x00000000000000FFul; -#endif -} diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h index 6789d788d494..3a3a0f16456a 100644 --- a/tools/perf/util/include/asm/alternative-asm.h +++ b/tools/perf/util/include/asm/alternative-asm.h @@ -4,5 +4,6 @@ /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ #define altinstruction_entry # +#define ALTERNATIVE_2 # #endif diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h deleted file mode 100644 index d82b170bb216..000000000000 --- a/tools/perf/util/include/asm/hash.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_GENERIC_HASH_H -#define __ASM_GENERIC_HASH_H - -/* Stub */ - -#endif /* __ASM_GENERIC_HASH_H */ diff --git a/tools/perf/util/include/asm/hweight.h b/tools/perf/util/include/asm/hweight.h deleted file mode 100644 index 36cf26d434a5..000000000000 --- a/tools/perf/util/include/asm/hweight.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef PERF_HWEIGHT_H -#define PERF_HWEIGHT_H - -#include <linux/types.h> -unsigned int hweight32(unsigned int w); -unsigned long hweight64(__u64 w); - -#endif /* PERF_HWEIGHT_H */ diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h index 01ffd12dc791..40bd21488032 100644 --- a/tools/perf/util/include/linux/bitmap.h +++ b/tools/perf/util/include/linux/bitmap.h @@ -46,4 +46,21 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, __bitmap_or(dst, src1, src2, nbits); } +/** + * test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + */ +static inline int test_and_set_bit(int nr, unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + unsigned long old; + + old = *p; + *p = old | mask; + + return (old & mask) != 0; +} + #endif /* _PERF_BITOPS_H */ diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h deleted file mode 100644 index dadfa7e54287..000000000000 --- a/tools/perf/util/include/linux/bitops.h +++ /dev/null @@ -1,160 +0,0 @@ -#ifndef _PERF_LINUX_BITOPS_H_ -#define _PERF_LINUX_BITOPS_H_ - -#include <linux/kernel.h> -#include <linux/compiler.h> -#include <asm/hweight.h> - -#ifndef __WORDSIZE -#define __WORDSIZE (__SIZEOF_LONG__ * 8) -#endif - -#define BITS_PER_LONG __WORDSIZE -#define BITS_PER_BYTE 8 -#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) -#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64)) -#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) -#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE) - -#define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_first_bit((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -/* same as for_each_set_bit() but use bit as value to start with */ -#define for_each_set_bit_from(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -static inline void set_bit(int nr, unsigned long *addr) -{ - addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG); -} - -static inline void clear_bit(int nr, unsigned long *addr) -{ - addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG)); -} - -static __always_inline int test_bit(unsigned int nr, const unsigned long *addr) -{ - return ((1UL << (nr % BITS_PER_LONG)) & - (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0; -} - -static inline unsigned long hweight_long(unsigned long w) -{ - return sizeof(w) == 4 ? hweight32(w) : hweight64(w); -} - -#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) - -/** - * __ffs - find first bit in word. - * @word: The word to search - * - * Undefined if no bit exists, so code should check against 0 first. - */ -static __always_inline unsigned long __ffs(unsigned long word) -{ - int num = 0; - -#if BITS_PER_LONG == 64 - if ((word & 0xffffffff) == 0) { - num += 32; - word >>= 32; - } -#endif - if ((word & 0xffff) == 0) { - num += 16; - word >>= 16; - } - if ((word & 0xff) == 0) { - num += 8; - word >>= 8; - } - if ((word & 0xf) == 0) { - num += 4; - word >>= 4; - } - if ((word & 0x3) == 0) { - num += 2; - word >>= 2; - } - if ((word & 0x1) == 0) - num += 1; - return num; -} - -typedef const unsigned long __attribute__((__may_alias__)) long_alias_t; - -/* - * Find the first set bit in a memory region. - */ -static inline unsigned long -find_first_bit(const unsigned long *addr, unsigned long size) -{ - long_alias_t *p = (long_alias_t *) addr; - unsigned long result = 0; - unsigned long tmp; - - while (size & ~(BITS_PER_LONG-1)) { - if ((tmp = *(p++))) - goto found; - result += BITS_PER_LONG; - size -= BITS_PER_LONG; - } - if (!size) - return result; - - tmp = (*p) & (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ -found: - return result + __ffs(tmp); -} - -/* - * Find the next set bit in a memory region. - */ -static inline unsigned long -find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) -{ - const unsigned long *p = addr + BITOP_WORD(offset); - unsigned long result = offset & ~(BITS_PER_LONG-1); - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset %= BITS_PER_LONG; - if (offset) { - tmp = *(p++); - tmp &= (~0UL << offset); - if (size < BITS_PER_LONG) - goto found_first; - if (tmp) - goto found_middle; - size -= BITS_PER_LONG; - result += BITS_PER_LONG; - } - while (size & ~(BITS_PER_LONG-1)) { - if ((tmp = *(p++))) - goto found_middle; - result += BITS_PER_LONG; - size -= BITS_PER_LONG; - } - if (!size) - return result; - tmp = *p; - -found_first: - tmp &= (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ -found_middle: - return result + __ffs(tmp); -} - -#endif diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 34fc7c8672e4..1bca3a9f2b16 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -12,6 +12,7 @@ #include <stdbool.h> #include <symbol/kallsyms.h> #include "unwind.h" +#include "linux/hash.h" static void dsos__init(struct dsos *dsos) { @@ -21,7 +22,7 @@ static void dsos__init(struct dsos *dsos) int machine__init(struct machine *machine, const char *root_dir, pid_t pid) { - map_groups__init(&machine->kmaps); + map_groups__init(&machine->kmaps, machine); RB_CLEAR_NODE(&machine->rb_node); dsos__init(&machine->user_dsos); dsos__init(&machine->kernel_dsos); @@ -32,7 +33,6 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->vdso_info = NULL; - machine->kmaps.machine = machine; machine->pid = pid; machine->symbol_filter = NULL; @@ -319,7 +319,7 @@ static void machine__update_thread_pid(struct machine *machine, goto out_err; if (!leader->mg) - leader->mg = map_groups__new(); + leader->mg = map_groups__new(machine); if (!leader->mg) goto out_err; @@ -389,7 +389,6 @@ static struct thread *__machine__findnew_thread(struct machine *machine, if (th != NULL) { rb_link_node(&th->rb_node, parent, p); rb_insert_color(&th->rb_node, &machine->threads); - machine->last_match = th; /* * We have to initialize map_groups separately @@ -400,9 +399,12 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * leader and that would screwed the rb tree. */ if (thread__init_map_groups(th, machine)) { + rb_erase(&th->rb_node, &machine->threads); thread__delete(th); return NULL; } + + machine->last_match = th; } return th; @@ -465,6 +467,7 @@ struct map *machine__new_module(struct machine *machine, u64 start, { struct map *map; struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename); + bool compressed; if (dso == NULL) return NULL; @@ -477,6 +480,11 @@ struct map *machine__new_module(struct machine *machine, u64 start, dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; else dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; + + /* _KMODULE_COMP should be next to _KMODULE */ + if (is_kernel_module(filename, &compressed) && compressed) + dso->symtab_type++; + map_groups__insert(&machine->kmaps, map); return map; } @@ -862,8 +870,14 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, struct map *map; char *long_name; - if (dot == NULL || strcmp(dot, ".ko")) + if (dot == NULL) continue; + + /* On some system, modules are compressed like .ko.gz */ + if (is_supported_compression(dot + 1) && + is_kmodule_extension(dot - 2)) + dot -= 3; + snprintf(dso_name, sizeof(dso_name), "[%.*s]", (int)(dot - dent->d_name), dent->d_name); @@ -1045,6 +1059,11 @@ static int machine__process_kernel_mmap_event(struct machine *machine, dot = strrchr(name, '.'); if (dot == NULL) goto out_problem; + /* On some system, modules are compressed like .ko.gz */ + if (is_supported_compression(dot + 1)) + dot -= 3; + if (!is_kmodule_extension(dot + 1)) + goto out_problem; snprintf(short_module_name, sizeof(short_module_name), "[%.*s]", (int)(dot - name), name); strxfrchar(short_module_name, '-', '_'); @@ -1069,8 +1088,20 @@ static int machine__process_kernel_mmap_event(struct machine *machine, * Should be there already, from the build-id table in * the header. */ - struct dso *kernel = __dsos__findnew(&machine->kernel_dsos, - kmmap_prefix); + struct dso *kernel = NULL; + struct dso *dso; + + list_for_each_entry(dso, &machine->kernel_dsos.head, node) { + if (is_kernel_module(dso->long_name, NULL)) + continue; + + kernel = dso; + break; + } + + if (kernel == NULL) + kernel = __dsos__findnew(&machine->kernel_dsos, + kmmap_prefix); if (kernel == NULL) goto out_problem; @@ -1078,6 +1109,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (__machine__create_kernel_maps(machine, kernel) < 0) goto out_problem; + if (strstr(kernel->long_name, "vmlinux")) + dso__set_short_name(kernel, "[kernel.vmlinux]", false); + machine__set_kernel_mmap_len(machine, event); /* @@ -1290,7 +1324,7 @@ static bool symbol__match_regex(struct symbol *sym, regex_t *regex) return 0; } -static void ip__resolve_ams(struct machine *machine, struct thread *thread, +static void ip__resolve_ams(struct thread *thread, struct addr_map_symbol *ams, u64 ip) { @@ -1304,7 +1338,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread, * Thus, we have to try consecutively until we find a match * or else, the symbol is unknown */ - thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al); + thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al); ams->addr = ip; ams->al_addr = al.addr; @@ -1312,23 +1346,21 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread, ams->map = al.map; } -static void ip__resolve_data(struct machine *machine, struct thread *thread, +static void ip__resolve_data(struct thread *thread, u8 m, struct addr_map_symbol *ams, u64 addr) { struct addr_location al; memset(&al, 0, sizeof(al)); - thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, - &al); + thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al); if (al.map == NULL) { /* * some shared data regions have execute bit set which puts * their mapping in the MAP__FUNCTION type array. * Check there as a fallback option before dropping the sample. */ - thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr, - &al); + thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al); } ams->addr = addr; @@ -1345,14 +1377,72 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, if (!mi) return NULL; - ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip); - ip__resolve_data(al->machine, al->thread, al->cpumode, - &mi->daddr, sample->addr); + ip__resolve_ams(al->thread, &mi->iaddr, sample->ip); + ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr); mi->data_src.val = sample->data_src; return mi; } +static int add_callchain_ip(struct thread *thread, + struct symbol **parent, + struct addr_location *root_al, + bool branch_history, + u64 ip) +{ + struct addr_location al; + + al.filtered = 0; + al.sym = NULL; + if (branch_history) + thread__find_cpumode_addr_location(thread, MAP__FUNCTION, + ip, &al); + else { + u8 cpumode = PERF_RECORD_MISC_USER; + + if (ip >= PERF_CONTEXT_MAX) { + switch (ip) { + case PERF_CONTEXT_HV: + cpumode = PERF_RECORD_MISC_HYPERVISOR; + break; + case PERF_CONTEXT_KERNEL: + cpumode = PERF_RECORD_MISC_KERNEL; + break; + case PERF_CONTEXT_USER: + cpumode = PERF_RECORD_MISC_USER; + break; + default: + pr_debug("invalid callchain context: " + "%"PRId64"\n", (s64) ip); + /* + * It seems the callchain is corrupted. + * Discard all. + */ + callchain_cursor_reset(&callchain_cursor); + return 1; + } + return 0; + } + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, + ip, &al); + } + + if (al.sym != NULL) { + if (sort__has_parent && !*parent && + symbol__match_regex(al.sym, &parent_regex)) + *parent = al.sym; + else if (have_ignore_callees && root_al && + symbol__match_regex(al.sym, &ignore_callees_regex)) { + /* Treat this symbol as the root, + forgetting its callees. */ + *root_al = al; + callchain_cursor_reset(&callchain_cursor); + } + } + + return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym); +} + struct branch_info *sample__resolve_bstack(struct perf_sample *sample, struct addr_location *al) { @@ -1364,43 +1454,140 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, return NULL; for (i = 0; i < bs->nr; i++) { - ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to); - ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from); + ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to); + ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from); bi[i].flags = bs->entries[i].flags; } return bi; } -static int machine__resolve_callchain_sample(struct machine *machine, - struct thread *thread, +#define CHASHSZ 127 +#define CHASHBITS 7 +#define NO_ENTRY 0xff + +#define PERF_MAX_BRANCH_DEPTH 127 + +/* Remove loops. */ +static int remove_loops(struct branch_entry *l, int nr) +{ + int i, j, off; + unsigned char chash[CHASHSZ]; + + memset(chash, NO_ENTRY, sizeof(chash)); + + BUG_ON(PERF_MAX_BRANCH_DEPTH > 255); + + for (i = 0; i < nr; i++) { + int h = hash_64(l[i].from, CHASHBITS) % CHASHSZ; + + /* no collision handling for now */ + if (chash[h] == NO_ENTRY) { + chash[h] = i; + } else if (l[chash[h]].from == l[i].from) { + bool is_loop = true; + /* check if it is a real loop */ + off = 0; + for (j = chash[h]; j < i && i + off < nr; j++, off++) + if (l[j].from != l[i + off].from) { + is_loop = false; + break; + } + if (is_loop) { + memmove(l + i, l + i + off, + (nr - (i + off)) * sizeof(*l)); + nr -= off; + } + } + } + return nr; +} + +static int thread__resolve_callchain_sample(struct thread *thread, struct ip_callchain *chain, + struct branch_stack *branch, struct symbol **parent, struct addr_location *root_al, int max_stack) { - u8 cpumode = PERF_RECORD_MISC_USER; int chain_nr = min(max_stack, (int)chain->nr); - int i; - int j; - int err; - int skip_idx __maybe_unused; + int i, j, err; + int skip_idx = -1; + int first_call = 0; + + /* + * Based on DWARF debug information, some architectures skip + * a callchain entry saved by the kernel. + */ + if (chain->nr < PERF_MAX_STACK_DEPTH) + skip_idx = arch_skip_callchain_idx(thread, chain); callchain_cursor_reset(&callchain_cursor); + /* + * Add branches to call stack for easier browsing. This gives + * more context for a sample than just the callers. + * + * This uses individual histograms of paths compared to the + * aggregated histograms the normal LBR mode uses. + * + * Limitations for now: + * - No extra filters + * - No annotations (should annotate somehow) + */ + + if (branch && callchain_param.branch_callstack) { + int nr = min(max_stack, (int)branch->nr); + struct branch_entry be[nr]; + + if (branch->nr > PERF_MAX_BRANCH_DEPTH) { + pr_warning("corrupted branch chain. skipping...\n"); + goto check_calls; + } + + for (i = 0; i < nr; i++) { + if (callchain_param.order == ORDER_CALLEE) { + be[i] = branch->entries[i]; + /* + * Check for overlap into the callchain. + * The return address is one off compared to + * the branch entry. To adjust for this + * assume the calling instruction is not longer + * than 8 bytes. + */ + if (i == skip_idx || + chain->ips[first_call] >= PERF_CONTEXT_MAX) + first_call++; + else if (be[i].from < chain->ips[first_call] && + be[i].from >= chain->ips[first_call] - 8) + first_call++; + } else + be[i] = branch->entries[branch->nr - i - 1]; + } + + nr = remove_loops(be, nr); + + for (i = 0; i < nr; i++) { + err = add_callchain_ip(thread, parent, root_al, + true, be[i].to); + if (!err) + err = add_callchain_ip(thread, parent, root_al, + true, be[i].from); + if (err == -EINVAL) + break; + if (err) + return err; + } + chain_nr -= nr; + } + +check_calls: if (chain->nr > PERF_MAX_STACK_DEPTH) { pr_warning("corrupted callchain. skipping...\n"); return 0; } - /* - * Based on DWARF debug information, some architectures skip - * a callchain entry saved by the kernel. - */ - skip_idx = arch_skip_callchain_idx(machine, thread, chain); - - for (i = 0; i < chain_nr; i++) { + for (i = first_call; i < chain_nr; i++) { u64 ip; - struct addr_location al; if (callchain_param.order == ORDER_CALLEE) j = i; @@ -1413,50 +1600,10 @@ static int machine__resolve_callchain_sample(struct machine *machine, #endif ip = chain->ips[j]; - if (ip >= PERF_CONTEXT_MAX) { - switch (ip) { - case PERF_CONTEXT_HV: - cpumode = PERF_RECORD_MISC_HYPERVISOR; - break; - case PERF_CONTEXT_KERNEL: - cpumode = PERF_RECORD_MISC_KERNEL; - break; - case PERF_CONTEXT_USER: - cpumode = PERF_RECORD_MISC_USER; - break; - default: - pr_debug("invalid callchain context: " - "%"PRId64"\n", (s64) ip); - /* - * It seems the callchain is corrupted. - * Discard all. - */ - callchain_cursor_reset(&callchain_cursor); - return 0; - } - continue; - } + err = add_callchain_ip(thread, parent, root_al, false, ip); - al.filtered = 0; - thread__find_addr_location(thread, machine, cpumode, - MAP__FUNCTION, ip, &al); - if (al.sym != NULL) { - if (sort__has_parent && !*parent && - symbol__match_regex(al.sym, &parent_regex)) - *parent = al.sym; - else if (have_ignore_callees && root_al && - symbol__match_regex(al.sym, &ignore_callees_regex)) { - /* Treat this symbol as the root, - forgetting its callees. */ - *root_al = al; - callchain_cursor_reset(&callchain_cursor); - } - } - - err = callchain_cursor_append(&callchain_cursor, - ip, al.map, al.sym); if (err) - return err; + return (err < 0) ? err : 0; } return 0; @@ -1469,19 +1616,16 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) entry->map, entry->sym); } -int machine__resolve_callchain(struct machine *machine, - struct perf_evsel *evsel, - struct thread *thread, - struct perf_sample *sample, - struct symbol **parent, - struct addr_location *root_al, - int max_stack) +int thread__resolve_callchain(struct thread *thread, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack) { - int ret; - - ret = machine__resolve_callchain_sample(machine, thread, - sample->callchain, parent, - root_al, max_stack); + int ret = thread__resolve_callchain_sample(thread, sample->callchain, + sample->branch_stack, + parent, root_al, max_stack); if (ret) return ret; @@ -1495,7 +1639,7 @@ int machine__resolve_callchain(struct machine *machine, (!sample->user_stack.size)) return 0; - return unwind__get_entries(unwind_entry, &callchain_cursor, machine, + return unwind__get_entries(unwind_entry, &callchain_cursor, thread, sample, max_stack); } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 2b651a7f5d0d..e8b7779a0a3f 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -40,6 +40,10 @@ struct machine { u64 kernel_start; symbol_filter_t symbol_filter; pid_t *current_tid; + union { /* Tool specific area */ + void *priv; + u64 db_id; + }; }; static inline @@ -122,13 +126,12 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, struct addr_location *al); struct mem_info *sample__resolve_mem(struct perf_sample *sample, struct addr_location *al); -int machine__resolve_callchain(struct machine *machine, - struct perf_evsel *evsel, - struct thread *thread, - struct perf_sample *sample, - struct symbol **parent, - struct addr_location *root_al, - int max_stack); +int thread__resolve_callchain(struct thread *thread, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack); /* * Default guest kernel is defined by parameter --guestkallsyms diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 2137c4596ec7..62ca9f2607d5 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -360,7 +360,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, if (map && map->dso) { srcline = get_srcline(map->dso, - map__rip_2objdump(map, addr)); + map__rip_2objdump(map, addr), NULL, true); if (srcline != SRCLINE_UNKNOWN) ret = fprintf(fp, "%s%s", prefix, srcline); free_srcline(srcline); @@ -413,14 +413,14 @@ u64 map__objdump_2mem(struct map *map, u64 ip) return ip + map->reloc; } -void map_groups__init(struct map_groups *mg) +void map_groups__init(struct map_groups *mg, struct machine *machine) { int i; for (i = 0; i < MAP__NR_TYPES; ++i) { mg->maps[i] = RB_ROOT; INIT_LIST_HEAD(&mg->removed_maps[i]); } - mg->machine = NULL; + mg->machine = machine; mg->refcnt = 1; } @@ -471,12 +471,12 @@ bool map_groups__empty(struct map_groups *mg) return true; } -struct map_groups *map_groups__new(void) +struct map_groups *map_groups__new(struct machine *machine) { struct map_groups *mg = malloc(sizeof(*mg)); if (mg != NULL) - map_groups__init(mg); + map_groups__init(mg, machine); return mg; } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 2f83954af050..0e42438b1e59 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -64,7 +64,7 @@ struct map_groups { int refcnt; }; -struct map_groups *map_groups__new(void); +struct map_groups *map_groups__new(struct machine *machine); void map_groups__delete(struct map_groups *mg); bool map_groups__empty(struct map_groups *mg); @@ -116,6 +116,22 @@ struct thread; #define map__for_each_symbol(map, pos, n) \ dso__for_each_symbol(map->dso, pos, n, map->type) +/* map__for_each_symbol_with_name - iterate over the symbols in the given map + * that have the given name + * + * @map: the 'struct map *' in which symbols itereated + * @sym_name: the symbol name + * @pos: the 'struct symbol *' to use as a loop cursor + * @filter: to use when loading the DSO + */ +#define __map__for_each_symbol_by_name(map, sym_name, pos, filter) \ + for (pos = map__find_symbol_by_name(map, sym_name, filter); \ + pos && strcmp(pos->name, sym_name) == 0; \ + pos = symbol__next_by_name(pos)) + +#define map__for_each_symbol_by_name(map, sym_name, pos) \ + __map__for_each_symbol_by_name(map, sym_name, (pos), NULL) + typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *map, enum map_type type, @@ -150,7 +166,7 @@ void maps__remove(struct rb_root *maps, struct map *map); struct map *maps__find(struct rb_root *maps, u64 addr); struct map *maps__first(struct rb_root *maps); struct map *maps__next(struct map *map); -void map_groups__init(struct map_groups *mg); +void map_groups__init(struct map_groups *mg, struct machine *machine); void map_groups__exit(struct map_groups *mg); int map_groups__clone(struct map_groups *mg, struct map_groups *parent, enum map_type type); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index c659a3ca1283..7f8ec6ce2823 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -526,7 +526,7 @@ do { \ } int parse_events_add_breakpoint(struct list_head *list, int *idx, - void *ptr, char *type) + void *ptr, char *type, u64 len) { struct perf_event_attr attr; @@ -536,14 +536,15 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, if (parse_breakpoint_type(type, &attr)) return -EINVAL; - /* - * We should find a nice way to override the access length - * Provide some defaults for now - */ - if (attr.bp_type == HW_BREAKPOINT_X) - attr.bp_len = sizeof(long); - else - attr.bp_len = HW_BREAKPOINT_LEN_4; + /* Provide some defaults if len is not specified */ + if (!len) { + if (attr.bp_type == HW_BREAKPOINT_X) + len = sizeof(long); + else + len = HW_BREAKPOINT_LEN_4; + } + + attr.bp_len = len; attr.type = PERF_TYPE_BREAKPOINT; attr.sample_period = 1; @@ -681,6 +682,8 @@ int parse_events_add_pmu(struct list_head *list, int *idx, if (evsel) { evsel->unit = info.unit; evsel->scale = info.scale; + evsel->per_pkg = info.per_pkg; + evsel->snapshot = info.snapshot; } return evsel ? 0 : -ENOMEM; @@ -1119,7 +1122,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, return; for_each_subsystem(sys_dir, sys_dirent, sys_next) { - if (subsys_glob != NULL && + if (subsys_glob != NULL && !strglobmatch(sys_dirent.d_name, subsys_glob)) continue; @@ -1130,7 +1133,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, continue; for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { - if (event_glob != NULL && + if (event_glob != NULL && !strglobmatch(evt_dirent.d_name, event_glob)) continue; @@ -1303,7 +1306,7 @@ static void print_symbol_events(const char *event_glob, unsigned type, for (i = 0; i < max; i++, syms++) { - if (event_glob != NULL && + if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) || (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; @@ -1364,7 +1367,7 @@ void print_events(const char *event_glob, bool name_only) printf("\n"); printf(" %-50s [%s]\n", - "mem:<addr>[:access]", + "mem:<addr>[/len][:access]", event_type_descriptors[PERF_TYPE_BREAKPOINT]); printf("\n"); } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index db2cf78ff0f3..ff6e1fa4111e 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -71,6 +71,7 @@ struct parse_events_term { int type_val; int type_term; struct list_head list; + bool used; }; struct parse_events_evlist { @@ -104,7 +105,7 @@ int parse_events_add_numeric(struct list_head *list, int *idx, int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2); int parse_events_add_breakpoint(struct list_head *list, int *idx, - void *ptr, char *type); + void *ptr, char *type, u64 len); int parse_events_add_pmu(struct list_head *list, int *idx, char *pmu , struct list_head *head_config); enum perf_pmu_event_symbol_type diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 906630bbf8eb..94eacb6c1ef7 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -159,6 +159,7 @@ branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE <mem>{ {modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); } : { return ':'; } +"/" { return '/'; } {num_dec} { return value(yyscanner, 10); } {num_hex} { return value(yyscanner, 16); } /* diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 93c4c9fbc922..72def077dbbf 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -326,6 +326,28 @@ PE_NAME_CACHE_TYPE } event_legacy_mem: +PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + (void *) $2, $6, $4)); + $$ = list; +} +| +PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + (void *) $2, NULL, $4)); + $$ = list; +} +| PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { struct parse_events_evlist *data = _data; @@ -333,7 +355,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc ALLOC_LIST(list); ABORT_ON(parse_events_add_breakpoint(list, &data->idx, - (void *) $2, $4)); + (void *) $2, $4, 0)); $$ = list; } | @@ -344,7 +366,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc ALLOC_LIST(list); ABORT_ON(parse_events_add_breakpoint(list, &data->idx, - (void *) $2, NULL)); + (void *) $2, NULL, 0)); $$ = list; } diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index bf48092983c6..4a015f77e2b5 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -42,7 +42,26 @@ static int get_value(struct parse_opt_ctx_t *p, return opterror(opt, "takes no value", flags); if (unset && (opt->flags & PARSE_OPT_NONEG)) return opterror(opt, "isn't available", flags); - + if (opt->flags & PARSE_OPT_DISABLED) + return opterror(opt, "is not usable", flags); + + if (opt->flags & PARSE_OPT_EXCLUSIVE) { + if (p->excl_opt && p->excl_opt != opt) { + char msg[128]; + + if (((flags & OPT_SHORT) && p->excl_opt->short_name) || + p->excl_opt->long_name == NULL) { + scnprintf(msg, sizeof(msg), "cannot be used with switch `%c'", + p->excl_opt->short_name); + } else { + scnprintf(msg, sizeof(msg), "cannot be used with %s", + p->excl_opt->long_name); + } + opterror(opt, msg, flags); + return -3; + } + p->excl_opt = opt; + } if (!(flags & OPT_SHORT) && p->opt) { switch (opt->type) { case OPTION_CALLBACK: @@ -343,13 +362,14 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, const char * const usagestr[]) { int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP); + int excl_short_opt = 1; + const char *arg; /* we must reset ->opt, unknown short option leave it dangling */ ctx->opt = NULL; for (; ctx->argc; ctx->argc--, ctx->argv++) { - const char *arg = ctx->argv[0]; - + arg = ctx->argv[0]; if (*arg != '-' || !arg[1]) { if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION) break; @@ -358,19 +378,21 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, } if (arg[1] != '-') { - ctx->opt = arg + 1; + ctx->opt = ++arg; if (internal_help && *ctx->opt == 'h') return usage_with_options_internal(usagestr, options, 0); switch (parse_short_opt(ctx, options)) { case -1: - return parse_options_usage(usagestr, options, arg + 1, 1); + return parse_options_usage(usagestr, options, arg, 1); case -2: goto unknown; + case -3: + goto exclusive; default: break; } if (ctx->opt) - check_typos(arg + 1, options); + check_typos(arg, options); while (ctx->opt) { if (internal_help && *ctx->opt == 'h') return usage_with_options_internal(usagestr, options, 0); @@ -387,6 +409,8 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, ctx->argv[0] = strdup(ctx->opt - 1); *(char *)ctx->argv[0] = '-'; goto unknown; + case -3: + goto exclusive; default: break; } @@ -402,19 +426,23 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, break; } - if (internal_help && !strcmp(arg + 2, "help-all")) + arg += 2; + if (internal_help && !strcmp(arg, "help-all")) return usage_with_options_internal(usagestr, options, 1); - if (internal_help && !strcmp(arg + 2, "help")) + if (internal_help && !strcmp(arg, "help")) return usage_with_options_internal(usagestr, options, 0); - if (!strcmp(arg + 2, "list-opts")) + if (!strcmp(arg, "list-opts")) return PARSE_OPT_LIST_OPTS; - if (!strcmp(arg + 2, "list-cmds")) + if (!strcmp(arg, "list-cmds")) return PARSE_OPT_LIST_SUBCMDS; - switch (parse_long_opt(ctx, arg + 2, options)) { + switch (parse_long_opt(ctx, arg, options)) { case -1: - return parse_options_usage(usagestr, options, arg + 2, 0); + return parse_options_usage(usagestr, options, arg, 0); case -2: goto unknown; + case -3: + excl_short_opt = 0; + goto exclusive; default: break; } @@ -426,6 +454,17 @@ unknown: ctx->opt = NULL; } return PARSE_OPT_DONE; + +exclusive: + parse_options_usage(usagestr, options, arg, excl_short_opt); + if ((excl_short_opt && ctx->excl_opt->short_name) || + ctx->excl_opt->long_name == NULL) { + char opt = ctx->excl_opt->short_name; + parse_options_usage(NULL, options, &opt, 1); + } else { + parse_options_usage(NULL, options, ctx->excl_opt->long_name, 0); + } + return PARSE_OPT_HELP; } int parse_options_end(struct parse_opt_ctx_t *ctx) @@ -509,6 +548,8 @@ static void print_option_help(const struct option *opts, int full) } if (!full && (opts->flags & PARSE_OPT_HIDDEN)) return; + if (opts->flags & PARSE_OPT_DISABLED) + return; pos = fprintf(stderr, " "); if (opts->short_name) @@ -679,3 +720,16 @@ int parse_opt_verbosity_cb(const struct option *opt, } return 0; } + +void set_option_flag(struct option *opts, int shortopt, const char *longopt, + int flag) +{ + for (; opts->type != OPTION_END; opts++) { + if ((shortopt && opts->short_name == shortopt) || + (opts->long_name && longopt && + !strcmp(opts->long_name, longopt))) { + opts->flags |= flag; + break; + } + } +} diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index b59ba858e73d..97b153fb4999 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -38,6 +38,8 @@ enum parse_opt_option_flags { PARSE_OPT_NONEG = 4, PARSE_OPT_HIDDEN = 8, PARSE_OPT_LASTARG_DEFAULT = 16, + PARSE_OPT_DISABLED = 32, + PARSE_OPT_EXCLUSIVE = 64, }; struct option; @@ -173,6 +175,7 @@ struct parse_opt_ctx_t { const char **out; int argc, cpidx; const char *opt; + const struct option *excl_opt; int flags; }; @@ -211,4 +214,5 @@ extern int parse_opt_verbosity_cb(const struct option *, const char *, int); extern const char *parse_options_fix_filename(const char *prefix, const char *file); +void set_option_flag(struct option *opts, int sopt, const char *lopt, int flag); #endif /* __PERF_PARSE_OPTIONS_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index e243ad962a4d..48411674da0f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -163,6 +163,41 @@ error: return -1; } +static int +perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name) +{ + char path[PATH_MAX]; + int fd; + + snprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name); + + fd = open(path, O_RDONLY); + if (fd == -1) + return -1; + + close(fd); + + alias->per_pkg = true; + return 0; +} + +static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, + char *dir, char *name) +{ + char path[PATH_MAX]; + int fd; + + snprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name); + + fd = open(path, O_RDONLY); + if (fd == -1) + return -1; + + alias->snapshot = true; + close(fd); + return 0; +} + static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file) { struct perf_pmu_alias *alias; @@ -181,6 +216,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI INIT_LIST_HEAD(&alias->terms); alias->scale = 1.0; alias->unit[0] = '\0'; + alias->per_pkg = false; ret = parse_events_terms(&alias->terms, buf); if (ret) { @@ -194,6 +230,8 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI */ perf_pmu__parse_unit(alias, dir, name); perf_pmu__parse_scale(alias, dir, name); + perf_pmu__parse_per_pkg(alias, dir, name); + perf_pmu__parse_snapshot(alias, dir, name); list_add_tail(&alias->list, list); @@ -209,6 +247,10 @@ static inline bool pmu_alias_info_file(char *name) return true; if (len > 6 && !strcmp(name + len - 6, ".scale")) return true; + if (len > 8 && !strcmp(name + len - 8, ".per-pkg")) + return true; + if (len > 9 && !strcmp(name + len - 9, ".snapshot")) + return true; return false; } @@ -509,31 +551,68 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, } /* + * Term is a string term, and might be a param-term. Try to look up it's value + * in the remaining terms. + * - We have a term like "base-or-format-term=param-term", + * - We need to find the value supplied for "param-term" (with param-term named + * in a config string) later on in the term list. + */ +static int pmu_resolve_param_term(struct parse_events_term *term, + struct list_head *head_terms, + __u64 *value) +{ + struct parse_events_term *t; + + list_for_each_entry(t, head_terms, list) { + if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { + if (!strcmp(t->config, term->config)) { + t->used = true; + *value = t->val.num; + return 0; + } + } + } + + if (verbose) + printf("Required parameter '%s' not specified\n", term->config); + + return -1; +} + +/* * Setup one of config[12] attr members based on the * user input data - term parameter. */ static int pmu_config_term(struct list_head *formats, struct perf_event_attr *attr, struct parse_events_term *term, + struct list_head *head_terms, bool zero) { struct perf_pmu_format *format; __u64 *vp; + __u64 val; + + /* + * If this is a parameter we've already used for parameterized-eval, + * skip it in normal eval. + */ + if (term->used) + return 0; /* - * Support only for hardcoded and numnerial terms. * Hardcoded terms should be already in, so nothing * to be done for them. */ if (parse_events__is_hardcoded_term(term)) return 0; - if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) - return -EINVAL; - format = pmu_find_format(formats, term->config); - if (!format) + if (!format) { + if (verbose) + printf("Invalid event/parameter '%s'\n", term->config); return -EINVAL; + } switch (format->value) { case PERF_PMU_FORMAT_VALUE_CONFIG: @@ -550,11 +629,25 @@ static int pmu_config_term(struct list_head *formats, } /* - * XXX If we ever decide to go with string values for - * non-hardcoded terms, here's the place to translate - * them into value. + * Either directly use a numeric term, or try to translate string terms + * using event parameters. */ - pmu_format_value(format->bits, term->val.num, vp, zero); + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) + val = term->val.num; + else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { + if (strcmp(term->val.str, "?")) { + if (verbose) + pr_info("Invalid sysfs entry %s=%s\n", + term->config, term->val.str); + return -EINVAL; + } + + if (pmu_resolve_param_term(term, head_terms, &val)) + return -EINVAL; + } else + return -EINVAL; + + pmu_format_value(format->bits, val, vp, zero); return 0; } @@ -565,9 +658,10 @@ int perf_pmu__config_terms(struct list_head *formats, { struct parse_events_term *term; - list_for_each_entry(term, head_terms, list) - if (pmu_config_term(formats, attr, term, zero)) + list_for_each_entry(term, head_terms, list) { + if (pmu_config_term(formats, attr, term, head_terms, zero)) return -EINVAL; + } return 0; } @@ -617,23 +711,27 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu, } -static int check_unit_scale(struct perf_pmu_alias *alias, - const char **unit, double *scale) +static int check_info_data(struct perf_pmu_alias *alias, + struct perf_pmu_info *info) { /* * Only one term in event definition can - * define unit and scale, fail if there's - * more than one. + * define unit, scale and snapshot, fail + * if there's more than one. */ - if ((*unit && alias->unit) || - (*scale && alias->scale)) + if ((info->unit && alias->unit) || + (info->scale && alias->scale) || + (info->snapshot && alias->snapshot)) return -EINVAL; if (alias->unit) - *unit = alias->unit; + info->unit = alias->unit; if (alias->scale) - *scale = alias->scale; + info->scale = alias->scale; + + if (alias->snapshot) + info->snapshot = alias->snapshot; return 0; } @@ -649,12 +747,15 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, struct perf_pmu_alias *alias; int ret; + info->per_pkg = false; + /* * Mark unit and scale as not set * (different from default values, see below) */ - info->unit = NULL; - info->scale = 0.0; + info->unit = NULL; + info->scale = 0.0; + info->snapshot = false; list_for_each_entry_safe(term, h, head_terms, list) { alias = pmu_find_alias(pmu, term); @@ -664,10 +765,13 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, if (ret) return ret; - ret = check_unit_scale(alias, &info->unit, &info->scale); + ret = check_info_data(alias, info); if (ret) return ret; + if (alias->per_pkg) + info->per_pkg = true; + list_del(&term->list); free(term); } @@ -715,10 +819,36 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to) set_bit(b, bits); } +static int sub_non_neg(int a, int b) +{ + if (b > a) + return 0; + return a - b; +} + static char *format_alias(char *buf, int len, struct perf_pmu *pmu, struct perf_pmu_alias *alias) { - snprintf(buf, len, "%s/%s/", pmu->name, alias->name); + struct parse_events_term *term; + int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name); + + list_for_each_entry(term, &alias->terms, list) { + if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) + used += snprintf(buf + used, sub_non_neg(len, used), + ",%s=%s", term->config, + term->val.str); + } + + if (sub_non_neg(len, used) > 0) { + buf[used] = '/'; + used++; + } + if (sub_non_neg(len, used) > 0) { + buf[used] = '\0'; + used++; + } else + buf[len - 1] = '\0'; + return buf; } @@ -747,15 +877,18 @@ void print_pmu_events(const char *event_glob, bool name_only) pmu = NULL; len = 0; - while ((pmu = perf_pmu__scan(pmu)) != NULL) + while ((pmu = perf_pmu__scan(pmu)) != NULL) { list_for_each_entry(alias, &pmu->aliases, list) len++; - aliases = malloc(sizeof(char *) * len); + if (pmu->selectable) + len++; + } + aliases = zalloc(sizeof(char *) * len); if (!aliases) - return; + goto out_enomem; pmu = NULL; j = 0; - while ((pmu = perf_pmu__scan(pmu)) != NULL) + while ((pmu = perf_pmu__scan(pmu)) != NULL) { list_for_each_entry(alias, &pmu->aliases, list) { char *name = format_alias(buf, sizeof(buf), pmu, alias); bool is_cpu = !strcmp(pmu->name, "cpu"); @@ -765,13 +898,23 @@ void print_pmu_events(const char *event_glob, bool name_only) (!is_cpu && strglobmatch(alias->name, event_glob)))) continue; - aliases[j] = name; + if (is_cpu && !name_only) - aliases[j] = format_alias_or(buf, sizeof(buf), - pmu, alias); - aliases[j] = strdup(aliases[j]); + name = format_alias_or(buf, sizeof(buf), pmu, alias); + + aliases[j] = strdup(name); + if (aliases[j] == NULL) + goto out_enomem; + j++; + } + if (pmu->selectable) { + char *s; + if (asprintf(&s, "%s//", pmu->name) < 0) + goto out_enomem; + aliases[j] = s; j++; } + } len = j; qsort(aliases, len, sizeof(char *), cmp_string); for (j = 0; j < len; j++) { @@ -780,12 +923,20 @@ void print_pmu_events(const char *event_glob, bool name_only) continue; } printf(" %-50s [Kernel PMU event]\n", aliases[j]); - zfree(&aliases[j]); printed++; } if (printed) printf("\n"); - free(aliases); +out_free: + for (j = 0; j < len; j++) + zfree(&aliases[j]); + zfree(&aliases); + return; + +out_enomem: + printf("FATAL: not enough memory to print PMU events\n"); + if (aliases) + goto out_free; } bool pmu_have_event(const char *pname, const char *name) diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index fe9dfbee8eed..6b1249fbdb5f 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -18,6 +18,7 @@ struct perf_event_attr; struct perf_pmu { char *name; __u32 type; + bool selectable; struct perf_event_attr *default_config; struct cpu_map *cpus; struct list_head format; /* HEAD struct perf_pmu_format -> list */ @@ -28,6 +29,8 @@ struct perf_pmu { struct perf_pmu_info { const char *unit; double scale; + bool per_pkg; + bool snapshot; }; #define UNIT_MAX_LEN 31 /* max length for event unit name */ @@ -38,6 +41,8 @@ struct perf_pmu_alias { struct list_head list; /* ELEM */ char unit[UNIT_MAX_LEN+1]; double scale; + bool per_pkg; + bool snapshot; }; struct perf_pmu *perf_pmu__find(const char *name); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index c150ca4343eb..919937eb0be2 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -446,7 +446,7 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs, } for (i = 0; i < ntevs; i++) { - if (tevs[i].point.address) { + if (tevs[i].point.address && !tevs[i].point.retprobe) { tmp = strdup(reloc_sym->name); if (!tmp) return -ENOMEM; @@ -495,9 +495,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, } if (ntevs == 0) { /* No error but failed to find probe point. */ - pr_warning("Probe point '%s' not found.\n", + pr_warning("Probe point '%s' not found in debuginfo.\n", synthesize_perf_probe_point(&pev->point)); - return -ENOENT; + if (need_dwarf) + return -ENOENT; + return 0; } /* Error path : ntevs < 0 */ pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs); @@ -1910,21 +1912,21 @@ static int show_perf_probe_event(struct perf_probe_event *pev, if (ret < 0) return ret; - printf(" %-20s (on %s", buf, place); + pr_info(" %-20s (on %s", buf, place); if (module) - printf(" in %s", module); + pr_info(" in %s", module); if (pev->nargs > 0) { - printf(" with"); + pr_info(" with"); for (i = 0; i < pev->nargs; i++) { ret = synthesize_perf_probe_arg(&pev->args[i], buf, 128); if (ret < 0) break; - printf(" %s", buf); + pr_info(" %s", buf); } } - printf(")\n"); + pr_info(")\n"); free(place); return ret; } @@ -2050,9 +2052,11 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev) pr_debug("Writing event: %s\n", buf); if (!probe_event_dry_run) { ret = write(fd, buf, strlen(buf)); - if (ret <= 0) + if (ret <= 0) { + ret = -errno; pr_warning("Failed to write event: %s\n", strerror_r(errno, sbuf, sizeof(sbuf))); + } } free(buf); return ret; @@ -2124,7 +2128,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, } ret = 0; - printf("Added new event%s\n", (ntevs > 1) ? "s:" : ":"); + pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":"); for (i = 0; i < ntevs; i++) { tev = &tevs[i]; if (pev->event) @@ -2179,8 +2183,8 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, if (ret >= 0) { /* Show how to use the event. */ - printf("\nYou can now use it in all perf tools, such as:\n\n"); - printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group, + pr_info("\nYou can now use it in all perf tools, such as:\n\n"); + pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group, tev->event); } @@ -2189,18 +2193,17 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, return ret; } -static char *looking_function_name; -static int num_matched_functions; - -static int probe_function_filter(struct map *map __maybe_unused, - struct symbol *sym) +static int find_probe_functions(struct map *map, char *name) { - if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) && - strcmp(looking_function_name, sym->name) == 0) { - num_matched_functions++; - return 0; + int found = 0; + struct symbol *sym; + + map__for_each_symbol_by_name(map, name, sym) { + if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) + found++; } - return 1; + + return found; } #define strdup_or_goto(str, label) \ @@ -2218,10 +2221,10 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, struct kmap *kmap = NULL; struct ref_reloc_sym *reloc_sym = NULL; struct symbol *sym; - struct rb_node *nd; struct probe_trace_event *tev; struct perf_probe_point *pp = &pev->point; struct probe_trace_point *tp; + int num_matched_functions; int ret, i; /* Init maps of given executable or kernel */ @@ -2238,10 +2241,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, * Load matched symbols: Since the different local symbols may have * same name but different addresses, this lists all the symbols. */ - num_matched_functions = 0; - looking_function_name = pp->function; - ret = map__load(map, probe_function_filter); - if (ret || num_matched_functions == 0) { + num_matched_functions = find_probe_functions(map, pp->function); + if (num_matched_functions == 0) { pr_err("Failed to find symbol %s in %s\n", pp->function, target ? : "kernel"); ret = -ENOENT; @@ -2253,7 +2254,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, goto out; } - if (!pev->uprobes) { + if (!pev->uprobes && !pp->retprobe) { kmap = map__kmap(map); reloc_sym = kmap->ref_reloc_sym; if (!reloc_sym) { @@ -2271,7 +2272,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } ret = 0; - map__for_each_symbol(map, sym, nd) { + + map__for_each_symbol_by_name(map, pp->function, sym) { tev = (*tevs) + ret; tp = &tev->point; if (ret == num_matched_functions) { @@ -2444,7 +2446,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent) goto error; } - printf("Removed event: %s\n", ent->s); + pr_info("Removed event: %s\n", ent->s); return 0; error: pr_warning("Failed to delete event: %s\n", diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 1cb1ef765ca0..d32cf93565da 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -989,8 +989,24 @@ static int debuginfo__find_probes(struct debuginfo *dbg, int ret = 0; #if _ELFUTILS_PREREQ(0, 142) + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + /* Get the call frame information from this dwarf */ - pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg)); + elf = dwarf_getelf(dbg->dbg); + if (elf == NULL) + return -EINVAL; + + if (gelf_getehdr(elf, &ehdr) == NULL) + return -EINVAL; + + if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) && + shdr.sh_type == SHT_PROGBITS) { + pf->cfi = dwarf_getcfi_elf(elf); + } else { + pf->cfi = dwarf_getcfi(dbg->dbg); + } #endif off = 0; diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 16a475a7d492..6c6a6953fa93 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,7 +10,7 @@ util/ctype.c util/evlist.c util/evsel.c util/cpumap.c -util/hweight.c +../../lib/hweight.c util/thread_map.c util/util.c util/xyarray.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 3dda85ca50c1..d906d0ad5d40 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -768,7 +768,7 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, Py_DECREF(file); goto free_list; } - + Py_DECREF(file); } diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index cf69325b985f..8acd0df88b5c 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -137,16 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) static int get_max_rate(unsigned int *rate) { - char path[PATH_MAX]; - const char *procfs = procfs__mountpoint(); - - if (!procfs) - return -1; - - snprintf(path, PATH_MAX, - "%s/sys/kernel/perf_event_max_sample_rate", procfs); - - return filename__read_int(path, (int *) rate); + return sysctl__read_int("kernel/perf_event_max_sample_rate", (int *)rate); } static int record_opts__config_freq(struct record_opts *opts) diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 0a01bac4ce02..22ebc46226e7 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -24,6 +24,7 @@ #include <string.h> #include <ctype.h> #include <errno.h> +#include <linux/bitmap.h> #include "../util.h" #include <EXTERN.h> @@ -57,7 +58,7 @@ INTERP my_perl; #define FTRACE_MAX_EVENT \ ((1 << (sizeof(unsigned short) * 8)) - 1) -struct event_format *events[FTRACE_MAX_EVENT]; +static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT); extern struct scripting_context *scripting_context; @@ -238,35 +239,15 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } -static inline struct event_format *find_cache_event(struct perf_evsel *evsel) -{ - static char ev_name[256]; - struct event_format *event; - int type = evsel->attr.config; - - if (events[type]) - return events[type]; - - events[type] = event = evsel->tp_format; - if (!event) - return NULL; - - sprintf(ev_name, "%s::%s", event->system, event->name); - - define_event_symbols(event, ev_name, event->print_fmt.args); - - return event; -} - static void perl_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread) { + struct event_format *event = evsel->tp_format; struct format_field *field; static char handler[256]; unsigned long long val; unsigned long s, ns; - struct event_format *event; int pid; int cpu = sample->cpu; void *data = sample->raw_data; @@ -278,7 +259,6 @@ static void perl_process_tracepoint(struct perf_sample *sample, if (evsel->attr.type != PERF_TYPE_TRACEPOINT) return; - event = find_cache_event(evsel); if (!event) die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); @@ -286,6 +266,9 @@ static void perl_process_tracepoint(struct perf_sample *sample, sprintf(handler, "%s::%s", event->system, event->name); + if (!test_and_set_bit(event->id, events_defined)) + define_event_symbols(event, handler, event->print_fmt.args); + s = nsecs / NSECS_PER_SEC; ns = nsecs - s * NSECS_PER_SEC; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 496f21cadd97..0c815a40a6e8 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -24,7 +24,9 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <stdbool.h> #include <errno.h> +#include <linux/bitmap.h> #include "../../perf.h" #include "../debug.h" @@ -33,6 +35,10 @@ #include "../util.h" #include "../event.h" #include "../thread.h" +#include "../comm.h" +#include "../machine.h" +#include "../db-export.h" +#include "../thread-stack.h" #include "../trace-event.h" #include "../machine.h" @@ -41,7 +47,7 @@ PyMODINIT_FUNC initperf_trace_context(void); #define FTRACE_MAX_EVENT \ ((1 << (sizeof(unsigned short) * 8)) - 1) -struct event_format *events[FTRACE_MAX_EVENT]; +static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT); #define MAX_FIELDS 64 #define N_COMMON_FIELDS 7 @@ -53,6 +59,24 @@ static int zero_flag_atom; static PyObject *main_module, *main_dict; +struct tables { + struct db_export dbe; + PyObject *evsel_handler; + PyObject *machine_handler; + PyObject *thread_handler; + PyObject *comm_handler; + PyObject *comm_thread_handler; + PyObject *dso_handler; + PyObject *symbol_handler; + PyObject *branch_type_handler; + PyObject *sample_handler; + PyObject *call_path_handler; + PyObject *call_return_handler; + bool db_export_mode; +}; + +static struct tables tables_global; + static void handler_call_die(const char *handler_name) NORETURN; static void handler_call_die(const char *handler_name) { @@ -65,7 +89,7 @@ static void handler_call_die(const char *handler_name) /* * Insert val into into the dictionary and decrement the reference counter. - * This is necessary for dictionaries since PyDict_SetItemString() does not + * This is necessary for dictionaries since PyDict_SetItemString() does not * steal a reference, as opposed to PyTuple_SetItem(). */ static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val) @@ -232,31 +256,6 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } -static inline struct event_format *find_cache_event(struct perf_evsel *evsel) -{ - static char ev_name[256]; - struct event_format *event; - int type = evsel->attr.config; - - /* - * XXX: Do we really need to cache this since now we have evsel->tp_format - * cached already? Need to re-read this "cache" routine that as well calls - * define_event_symbols() :-\ - */ - if (events[type]) - return events[type]; - - events[type] = event = evsel->tp_format; - if (!event) - return NULL; - - sprintf(ev_name, "%s__%s", event->system, event->name); - - define_event_symbols(event, ev_name, event->print_fmt.args); - - return event; -} - static PyObject *get_field_numeric_entry(struct event_format *event, struct format_field *field, void *data) { @@ -312,9 +311,9 @@ static PyObject *python_process_callchain(struct perf_sample *sample, if (!symbol_conf.use_callchain || !sample->callchain) goto exit; - if (machine__resolve_callchain(al->machine, evsel, al->thread, - sample, NULL, NULL, - PERF_MAX_STACK_DEPTH) != 0) { + if (thread__resolve_callchain(al->thread, evsel, + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { pr_err("Failed to resolve callchain. Skipping\n"); goto exit; } @@ -380,12 +379,12 @@ static void python_process_tracepoint(struct perf_sample *sample, struct thread *thread, struct addr_location *al) { + struct event_format *event = evsel->tp_format; PyObject *handler, *context, *t, *obj, *callchain; PyObject *dict = NULL; static char handler_name[256]; struct format_field *field; unsigned long s, ns; - struct event_format *event; unsigned n = 0; int pid; int cpu = sample->cpu; @@ -397,7 +396,6 @@ static void python_process_tracepoint(struct perf_sample *sample, if (!t) Py_FatalError("couldn't create Python tuple"); - event = find_cache_event(evsel); if (!event) die("ug! no event found for type %d", (int)evsel->attr.config); @@ -405,6 +403,9 @@ static void python_process_tracepoint(struct perf_sample *sample, sprintf(handler_name, "%s__%s", event->system, event->name); + if (!test_and_set_bit(event->id, events_defined)) + define_event_symbols(event, handler_name, event->print_fmt.args); + handler = get_handler(handler_name); if (!handler) { dict = PyDict_New(); @@ -475,6 +476,289 @@ static void python_process_tracepoint(struct perf_sample *sample, Py_DECREF(t); } +static PyObject *tuple_new(unsigned int sz) +{ + PyObject *t; + + t = PyTuple_New(sz); + if (!t) + Py_FatalError("couldn't create Python tuple"); + return t; +} + +static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val) +{ +#if BITS_PER_LONG == 64 + return PyTuple_SetItem(t, pos, PyInt_FromLong(val)); +#endif +#if BITS_PER_LONG == 32 + return PyTuple_SetItem(t, pos, PyLong_FromLongLong(val)); +#endif +} + +static int tuple_set_s32(PyObject *t, unsigned int pos, s32 val) +{ + return PyTuple_SetItem(t, pos, PyInt_FromLong(val)); +} + +static int tuple_set_string(PyObject *t, unsigned int pos, const char *s) +{ + return PyTuple_SetItem(t, pos, PyString_FromString(s)); +} + +static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + PyObject *t; + + t = tuple_new(2); + + tuple_set_u64(t, 0, evsel->db_id); + tuple_set_string(t, 1, perf_evsel__name(evsel)); + + call_object(tables->evsel_handler, t, "evsel_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_export_machine(struct db_export *dbe, + struct machine *machine) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + PyObject *t; + + t = tuple_new(3); + + tuple_set_u64(t, 0, machine->db_id); + tuple_set_s32(t, 1, machine->pid); + tuple_set_string(t, 2, machine->root_dir ? machine->root_dir : ""); + + call_object(tables->machine_handler, t, "machine_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_export_thread(struct db_export *dbe, struct thread *thread, + u64 main_thread_db_id, struct machine *machine) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + PyObject *t; + + t = tuple_new(5); + + tuple_set_u64(t, 0, thread->db_id); + tuple_set_u64(t, 1, machine->db_id); + tuple_set_u64(t, 2, main_thread_db_id); + tuple_set_s32(t, 3, thread->pid_); + tuple_set_s32(t, 4, thread->tid); + + call_object(tables->thread_handler, t, "thread_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_export_comm(struct db_export *dbe, struct comm *comm) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + PyObject *t; + + t = tuple_new(2); + + tuple_set_u64(t, 0, comm->db_id); + tuple_set_string(t, 1, comm__str(comm)); + + call_object(tables->comm_handler, t, "comm_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_export_comm_thread(struct db_export *dbe, u64 db_id, + struct comm *comm, struct thread *thread) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + PyObject *t; + + t = tuple_new(3); + + tuple_set_u64(t, 0, db_id); + tuple_set_u64(t, 1, comm->db_id); + tuple_set_u64(t, 2, thread->db_id); + + call_object(tables->comm_thread_handler, t, "comm_thread_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_export_dso(struct db_export *dbe, struct dso *dso, + struct machine *machine) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + PyObject *t; + + build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + + t = tuple_new(5); + + tuple_set_u64(t, 0, dso->db_id); + tuple_set_u64(t, 1, machine->db_id); + tuple_set_string(t, 2, dso->short_name); + tuple_set_string(t, 3, dso->long_name); + tuple_set_string(t, 4, sbuild_id); + + call_object(tables->dso_handler, t, "dso_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_export_symbol(struct db_export *dbe, struct symbol *sym, + struct dso *dso) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + u64 *sym_db_id = symbol__priv(sym); + PyObject *t; + + t = tuple_new(6); + + tuple_set_u64(t, 0, *sym_db_id); + tuple_set_u64(t, 1, dso->db_id); + tuple_set_u64(t, 2, sym->start); + tuple_set_u64(t, 3, sym->end); + tuple_set_s32(t, 4, sym->binding); + tuple_set_string(t, 5, sym->name); + + call_object(tables->symbol_handler, t, "symbol_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_export_branch_type(struct db_export *dbe, u32 branch_type, + const char *name) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + PyObject *t; + + t = tuple_new(2); + + tuple_set_s32(t, 0, branch_type); + tuple_set_string(t, 1, name); + + call_object(tables->branch_type_handler, t, "branch_type_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_export_sample(struct db_export *dbe, + struct export_sample *es) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + PyObject *t; + + t = tuple_new(21); + + tuple_set_u64(t, 0, es->db_id); + tuple_set_u64(t, 1, es->evsel->db_id); + tuple_set_u64(t, 2, es->al->machine->db_id); + tuple_set_u64(t, 3, es->thread->db_id); + tuple_set_u64(t, 4, es->comm_db_id); + tuple_set_u64(t, 5, es->dso_db_id); + tuple_set_u64(t, 6, es->sym_db_id); + tuple_set_u64(t, 7, es->offset); + tuple_set_u64(t, 8, es->sample->ip); + tuple_set_u64(t, 9, es->sample->time); + tuple_set_s32(t, 10, es->sample->cpu); + tuple_set_u64(t, 11, es->addr_dso_db_id); + tuple_set_u64(t, 12, es->addr_sym_db_id); + tuple_set_u64(t, 13, es->addr_offset); + tuple_set_u64(t, 14, es->sample->addr); + tuple_set_u64(t, 15, es->sample->period); + tuple_set_u64(t, 16, es->sample->weight); + tuple_set_u64(t, 17, es->sample->transaction); + tuple_set_u64(t, 18, es->sample->data_src); + tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK); + tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX)); + + call_object(tables->sample_handler, t, "sample_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_export_call_path(struct db_export *dbe, struct call_path *cp) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + PyObject *t; + u64 parent_db_id, sym_db_id; + + parent_db_id = cp->parent ? cp->parent->db_id : 0; + sym_db_id = cp->sym ? *(u64 *)symbol__priv(cp->sym) : 0; + + t = tuple_new(4); + + tuple_set_u64(t, 0, cp->db_id); + tuple_set_u64(t, 1, parent_db_id); + tuple_set_u64(t, 2, sym_db_id); + tuple_set_u64(t, 3, cp->ip); + + call_object(tables->call_path_handler, t, "call_path_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_export_call_return(struct db_export *dbe, + struct call_return *cr) +{ + struct tables *tables = container_of(dbe, struct tables, dbe); + u64 comm_db_id = cr->comm ? cr->comm->db_id : 0; + PyObject *t; + + t = tuple_new(11); + + tuple_set_u64(t, 0, cr->db_id); + tuple_set_u64(t, 1, cr->thread->db_id); + tuple_set_u64(t, 2, comm_db_id); + tuple_set_u64(t, 3, cr->cp->db_id); + tuple_set_u64(t, 4, cr->call_time); + tuple_set_u64(t, 5, cr->return_time); + tuple_set_u64(t, 6, cr->branch_count); + tuple_set_u64(t, 7, cr->call_ref); + tuple_set_u64(t, 8, cr->return_ref); + tuple_set_u64(t, 9, cr->cp->parent->db_id); + tuple_set_s32(t, 10, cr->flags); + + call_object(tables->call_return_handler, t, "call_return_table"); + + Py_DECREF(t); + + return 0; +} + +static int python_process_call_return(struct call_return *cr, void *data) +{ + struct db_export *dbe = data; + + return db_export__call_return(dbe, cr); +} + static void python_process_general_event(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, @@ -551,19 +835,25 @@ exit: Py_DECREF(t); } -static void python_process_event(union perf_event *event __maybe_unused, +static void python_process_event(union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, struct addr_location *al) { + struct tables *tables = &tables_global; + switch (evsel->attr.type) { case PERF_TYPE_TRACEPOINT: python_process_tracepoint(sample, evsel, thread, al); break; /* Reserve for future process_hw/sw/raw APIs */ default: - python_process_general_event(sample, evsel, thread, al); + if (tables->db_export_mode) + db_export__sample(&tables->dbe, event, sample, evsel, + thread, al); + else + python_process_general_event(sample, evsel, thread, al); } } @@ -589,11 +879,79 @@ error: return -1; } +#define SET_TABLE_HANDLER_(name, handler_name, table_name) do { \ + tables->handler_name = get_handler(#table_name); \ + if (tables->handler_name) \ + tables->dbe.export_ ## name = python_export_ ## name; \ +} while (0) + +#define SET_TABLE_HANDLER(name) \ + SET_TABLE_HANDLER_(name, name ## _handler, name ## _table) + +static void set_table_handlers(struct tables *tables) +{ + const char *perf_db_export_mode = "perf_db_export_mode"; + const char *perf_db_export_calls = "perf_db_export_calls"; + PyObject *db_export_mode, *db_export_calls; + bool export_calls = false; + int ret; + + memset(tables, 0, sizeof(struct tables)); + if (db_export__init(&tables->dbe)) + Py_FatalError("failed to initialize export"); + + db_export_mode = PyDict_GetItemString(main_dict, perf_db_export_mode); + if (!db_export_mode) + return; + + ret = PyObject_IsTrue(db_export_mode); + if (ret == -1) + handler_call_die(perf_db_export_mode); + if (!ret) + return; + + tables->dbe.crp = NULL; + db_export_calls = PyDict_GetItemString(main_dict, perf_db_export_calls); + if (db_export_calls) { + ret = PyObject_IsTrue(db_export_calls); + if (ret == -1) + handler_call_die(perf_db_export_calls); + export_calls = !!ret; + } + + if (export_calls) { + tables->dbe.crp = + call_return_processor__new(python_process_call_return, + &tables->dbe); + if (!tables->dbe.crp) + Py_FatalError("failed to create calls processor"); + } + + tables->db_export_mode = true; + /* + * Reserve per symbol space for symbol->db_id via symbol__priv() + */ + symbol_conf.priv_size = sizeof(u64); + + SET_TABLE_HANDLER(evsel); + SET_TABLE_HANDLER(machine); + SET_TABLE_HANDLER(thread); + SET_TABLE_HANDLER(comm); + SET_TABLE_HANDLER(comm_thread); + SET_TABLE_HANDLER(dso); + SET_TABLE_HANDLER(symbol); + SET_TABLE_HANDLER(branch_type); + SET_TABLE_HANDLER(sample); + SET_TABLE_HANDLER(call_path); + SET_TABLE_HANDLER(call_return); +} + /* * Start trace script */ static int python_start_script(const char *script, int argc, const char **argv) { + struct tables *tables = &tables_global; const char **command_line; char buf[PATH_MAX]; int i, err = 0; @@ -632,6 +990,14 @@ static int python_start_script(const char *script, int argc, const char **argv) free(command_line); + set_table_handlers(tables); + + if (tables->db_export_mode) { + err = db_export__branch_types(&tables->dbe); + if (err) + goto error; + } + return err; error: Py_Finalize(); @@ -642,7 +1008,9 @@ error: static int python_flush_script(void) { - return 0; + struct tables *tables = &tables_global; + + return db_export__flush(&tables->dbe); } /* @@ -650,8 +1018,12 @@ static int python_flush_script(void) */ static int python_stop_script(void) { + struct tables *tables = &tables_global; + try_call_object("trace_end", NULL); + db_export__exit(&tables->dbe); + Py_XDECREF(main_dict); Py_XDECREF(main_module); Py_Finalize(); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 6702ac28754b..0baf75f12b7c 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -228,6 +228,15 @@ static int process_finished_round(struct perf_tool *tool, union perf_event *event, struct perf_session *session); +static int process_id_index_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *perf_session + __maybe_unused) +{ + dump_printf(": unhandled!\n"); + return 0; +} + void perf_tool__fill_defaults(struct perf_tool *tool) { if (tool->sample == NULL) @@ -262,8 +271,10 @@ void perf_tool__fill_defaults(struct perf_tool *tool) else tool->finished_round = process_finished_round_stub; } + if (tool->id_index == NULL) + tool->id_index = process_id_index_stub; } - + static void swap_sample_id_all(union perf_event *event, void *data) { void *end = (void *) event + event->header.size; @@ -460,6 +471,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap, [PERF_RECORD_HEADER_BUILD_ID] = NULL, + [PERF_RECORD_ID_INDEX] = perf_event__all64_swap, [PERF_RECORD_HEADER_MAX] = NULL, }; @@ -521,15 +533,11 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, return -ETIME; if (timestamp < oe->last_flush) { - WARN_ONCE(1, "Timestamp below last timeslice flush\n"); - - pr_oe_time(timestamp, "out of order event"); + pr_oe_time(timestamp, "out of order event\n"); pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n", oe->last_flush_type); - /* We could get out of order messages after forced flush. */ - if (oe->last_flush_type != OE_FLUSH__HALF) - return -EINVAL; + s->stats.nr_unordered_events++; } new = ordered_events__new(oe, timestamp, event); @@ -580,15 +588,46 @@ static void regs_dump__printf(u64 mask, u64 *regs) } } +static const char *regs_abi[] = { + [PERF_SAMPLE_REGS_ABI_NONE] = "none", + [PERF_SAMPLE_REGS_ABI_32] = "32-bit", + [PERF_SAMPLE_REGS_ABI_64] = "64-bit", +}; + +static inline const char *regs_dump_abi(struct regs_dump *d) +{ + if (d->abi > PERF_SAMPLE_REGS_ABI_64) + return "unknown"; + + return regs_abi[d->abi]; +} + +static void regs__printf(const char *type, struct regs_dump *regs) +{ + u64 mask = regs->mask; + + printf("... %s regs: mask 0x%" PRIx64 " ABI %s\n", + type, + mask, + regs_dump_abi(regs)); + + regs_dump__printf(mask, regs->regs); +} + static void regs_user__printf(struct perf_sample *sample) { struct regs_dump *user_regs = &sample->user_regs; - if (user_regs->regs) { - u64 mask = user_regs->mask; - printf("... user regs: mask 0x%" PRIx64 "\n", mask); - regs_dump__printf(mask, user_regs->regs); - } + if (user_regs->regs) + regs__printf("user", user_regs); +} + +static void regs_intr__printf(struct perf_sample *sample) +{ + struct regs_dump *intr_regs = &sample->intr_regs; + + if (intr_regs->regs) + regs__printf("intr", intr_regs); } static void stack_user__printf(struct stack_dump *dump) @@ -687,6 +726,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_REGS_USER) regs_user__printf(sample); + if (sample_type & PERF_SAMPLE_REGS_INTR) + regs_intr__printf(sample); + if (sample_type & PERF_SAMPLE_STACK_USER) stack_user__printf(&sample->user_stack); @@ -888,11 +930,26 @@ static s64 perf_session__process_user_event(struct perf_session *session, return tool->build_id(tool, event, session); case PERF_RECORD_FINISHED_ROUND: return tool->finished_round(tool, event, session); + case PERF_RECORD_ID_INDEX: + return tool->id_index(tool, event, session); default: return -EINVAL; } } +int perf_session__deliver_synth_event(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool) +{ + events_stats__inc(&session->stats, event->header.type); + + if (event->header.type >= PERF_RECORD_USER_TYPE_START) + return perf_session__process_user_event(session, event, tool, 0); + + return perf_session__deliver_event(session, event, sample, tool, 0); +} + static void event_swap(union perf_event *event, bool sample_id_all) { perf_event__swap_op swap; @@ -1057,6 +1114,9 @@ static void perf_session__warn_about_errors(const struct perf_session *session, "Do you have a KVM guest running and not using 'perf kvm'?\n", session->stats.nr_unprocessable_samples); } + + if (session->stats.nr_unordered_events != 0) + ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events); } volatile int session_done; @@ -1191,9 +1251,9 @@ fetch_mmaped_event(struct perf_session *session, #define NUM_MMAPS 128 #endif -int __perf_session__process_events(struct perf_session *session, - u64 data_offset, u64 data_size, - u64 file_size, struct perf_tool *tool) +static int __perf_session__process_events(struct perf_session *session, + u64 data_offset, u64 data_size, + u64 file_size, struct perf_tool *tool) { int fd = perf_data_file__fd(session->file); u64 head, page_offset, file_offset, file_pos, size; @@ -1417,9 +1477,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample, if (symbol_conf.use_callchain && sample->callchain) { struct addr_location node_al; - if (machine__resolve_callchain(al->machine, evsel, al->thread, - sample, NULL, NULL, - PERF_MAX_STACK_DEPTH) != 0) { + if (thread__resolve_callchain(al->thread, evsel, + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); return; @@ -1594,3 +1654,111 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, out: return err; } + +int perf_event__process_id_index(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session) +{ + struct perf_evlist *evlist = session->evlist; + struct id_index_event *ie = &event->id_index; + size_t i, nr, max_nr; + + max_nr = (ie->header.size - sizeof(struct id_index_event)) / + sizeof(struct id_index_entry); + nr = ie->nr; + if (nr > max_nr) + return -EINVAL; + + if (dump_trace) + fprintf(stdout, " nr: %zu\n", nr); + + for (i = 0; i < nr; i++) { + struct id_index_entry *e = &ie->entries[i]; + struct perf_sample_id *sid; + + if (dump_trace) { + fprintf(stdout, " ... id: %"PRIu64, e->id); + fprintf(stdout, " idx: %"PRIu64, e->idx); + fprintf(stdout, " cpu: %"PRId64, e->cpu); + fprintf(stdout, " tid: %"PRId64"\n", e->tid); + } + + sid = perf_evlist__id2sid(evlist, e->id); + if (!sid) + return -ENOENT; + sid->idx = e->idx; + sid->cpu = e->cpu; + sid->tid = e->tid; + } + return 0; +} + +int perf_event__synthesize_id_index(struct perf_tool *tool, + perf_event__handler_t process, + struct perf_evlist *evlist, + struct machine *machine) +{ + union perf_event *ev; + struct perf_evsel *evsel; + size_t nr = 0, i = 0, sz, max_nr, n; + int err; + + pr_debug2("Synthesizing id index\n"); + + max_nr = (UINT16_MAX - sizeof(struct id_index_event)) / + sizeof(struct id_index_entry); + + evlist__for_each(evlist, evsel) + nr += evsel->ids; + + n = nr > max_nr ? max_nr : nr; + sz = sizeof(struct id_index_event) + n * sizeof(struct id_index_entry); + ev = zalloc(sz); + if (!ev) + return -ENOMEM; + + ev->id_index.header.type = PERF_RECORD_ID_INDEX; + ev->id_index.header.size = sz; + ev->id_index.nr = n; + + evlist__for_each(evlist, evsel) { + u32 j; + + for (j = 0; j < evsel->ids; j++) { + struct id_index_entry *e; + struct perf_sample_id *sid; + + if (i >= n) { + err = process(tool, ev, NULL, machine); + if (err) + goto out_err; + nr -= n; + i = 0; + } + + e = &ev->id_index.entries[i++]; + + e->id = evsel->id[j]; + + sid = perf_evlist__id2sid(evlist, e->id); + if (!sid) { + free(ev); + return -ENOENT; + } + + e->idx = sid->idx; + e->cpu = sid->cpu; + e->tid = sid->tid; + } + } + + sz = sizeof(struct id_index_event) + nr * sizeof(struct id_index_entry); + ev->id_index.header.size = sz; + ev->id_index.nr = nr; + + err = process(tool, ev, NULL, machine); +out_err: + free(ev); + + return err; +} diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index a4be851f1a90..6d663dc76404 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -49,9 +49,6 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, union perf_event **event_ptr, struct perf_sample *sample); -int __perf_session__process_events(struct perf_session *session, - u64 data_offset, u64 data_size, u64 size, - struct perf_tool *tool); int perf_session__process_events(struct perf_session *session, struct perf_tool *tool); @@ -126,4 +123,19 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, extern volatile int session_done; #define session_done() ACCESS_ONCE(session_done) + +int perf_session__deliver_synth_event(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool); + +int perf_event__process_id_index(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session); + +int perf_event__synthesize_id_index(struct perf_tool *tool, + perf_event__handler_t process, + struct perf_evlist *evlist, + struct machine *machine); + #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 9402885a77f3..7a39c1ed8d37 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -291,7 +291,8 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) else { struct map *map = left->ms.map; left->srcline = get_srcline(map->dso, - map__rip_2objdump(map, left->ip)); + map__rip_2objdump(map, left->ip), + left->ms.sym, true); } } if (!right->srcline) { @@ -300,7 +301,8 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) else { struct map *map = right->ms.map; right->srcline = get_srcline(map->dso, - map__rip_2objdump(map, right->ip)); + map__rip_2objdump(map, right->ip), + right->ms.sym, true); } } return strcmp(right->srcline, left->srcline); @@ -309,7 +311,7 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*.*-s", width, width, he->srcline); + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline); } struct sort_entry sort_srcline = { @@ -1302,6 +1304,37 @@ static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, return hse->se->se_snprintf(he, hpp->buf, hpp->size, len); } +static int64_t __sort__hpp_cmp(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b) +{ + struct hpp_sort_entry *hse; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + return hse->se->se_cmp(a, b); +} + +static int64_t __sort__hpp_collapse(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b) +{ + struct hpp_sort_entry *hse; + int64_t (*collapse_fn)(struct hist_entry *, struct hist_entry *); + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + collapse_fn = hse->se->se_collapse ?: hse->se->se_cmp; + return collapse_fn(a, b); +} + +static int64_t __sort__hpp_sort(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b) +{ + struct hpp_sort_entry *hse; + int64_t (*sort_fn)(struct hist_entry *, struct hist_entry *); + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + sort_fn = hse->se->se_sort ?: hse->se->se_cmp; + return sort_fn(a, b); +} + static struct hpp_sort_entry * __sort_dimension__alloc_hpp(struct sort_dimension *sd) { @@ -1320,9 +1353,9 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) hse->hpp.entry = __sort__hpp_entry; hse->hpp.color = NULL; - hse->hpp.cmp = sd->entry->se_cmp; - hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp; - hse->hpp.sort = sd->entry->se_sort ? : hse->hpp.collapse; + hse->hpp.cmp = __sort__hpp_cmp; + hse->hpp.collapse = __sort__hpp_collapse; + hse->hpp.sort = __sort__hpp_sort; INIT_LIST_HEAD(&hse->hpp.list); INIT_LIST_HEAD(&hse->hpp.sort_list); diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index f3e4bc5fe5d2..c93fb0c5bd0b 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -8,6 +8,8 @@ #include "util/util.h" #include "util/debug.h" +#include "symbol.h" + #ifdef HAVE_LIBBFD_SUPPORT /* @@ -18,7 +20,7 @@ struct a2l_data { const char *input; - unsigned long addr; + u64 addr; bool found; const char *filename; @@ -145,7 +147,7 @@ static void addr2line_cleanup(struct a2l_data *a2l) free(a2l); } -static int addr2line(const char *dso_name, unsigned long addr, +static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line, struct dso *dso) { int ret = 0; @@ -191,7 +193,7 @@ void dso__free_a2l(struct dso *dso) #else /* HAVE_LIBBFD_SUPPORT */ -static int addr2line(const char *dso_name, unsigned long addr, +static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line_nr, struct dso *dso __maybe_unused) { @@ -250,7 +252,8 @@ void dso__free_a2l(struct dso *dso __maybe_unused) */ #define A2L_FAIL_LIMIT 123 -char *get_srcline(struct dso *dso, unsigned long addr) +char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, + bool show_sym) { char *file = NULL; unsigned line = 0; @@ -258,7 +261,7 @@ char *get_srcline(struct dso *dso, unsigned long addr) const char *dso_name; if (!dso->has_srcline) - return SRCLINE_UNKNOWN; + goto out; if (dso->symsrc_filename) dso_name = dso->symsrc_filename; @@ -274,7 +277,7 @@ char *get_srcline(struct dso *dso, unsigned long addr) if (!addr2line(dso_name, addr, &file, &line, dso)) goto out; - if (asprintf(&srcline, "%s:%u", file, line) < 0) { + if (asprintf(&srcline, "%s:%u", basename(file), line) < 0) { free(file); goto out; } @@ -289,7 +292,13 @@ out: dso->has_srcline = 0; dso__free_a2l(dso); } - return SRCLINE_UNKNOWN; + if (sym) { + if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "", + addr - sym->start) < 0) + return SRCLINE_UNKNOWN; + } else if (asprintf(&srcline, "%s[%" PRIx64 "]", dso->short_name, addr) < 0) + return SRCLINE_UNKNOWN; + return srcline; } void free_srcline(char *srcline) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 1e23a5bfb044..33b7a2aef713 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -11,6 +11,32 @@ #include <symbol/kallsyms.h> #include "debug.h" +#ifndef EM_AARCH64 +#define EM_AARCH64 183 /* ARM 64 bit */ +#endif + + +#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT +extern char *cplus_demangle(const char *, int); + +static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i) +{ + return cplus_demangle(c, i); +} +#else +#ifdef NO_DEMANGLE +static inline char *bfd_demangle(void __maybe_unused *v, + const char __maybe_unused *c, + int __maybe_unused i) +{ + return NULL; +} +#else +#define PACKAGE 'perf' +#include <bfd.h> +#endif +#endif + #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT static int elf_getphdrnum(Elf *elf, size_t *dst) { @@ -546,6 +572,38 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata) return 0; } +static int decompress_kmodule(struct dso *dso, const char *name, + enum dso_binary_type type) +{ + int fd; + const char *ext = strrchr(name, '.'); + char tmpbuf[] = "/tmp/perf-kmod-XXXXXX"; + + if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP && + type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP && + type != DSO_BINARY_TYPE__BUILD_ID_CACHE) + return -1; + + if (!ext || !is_supported_compression(ext + 1)) { + ext = strrchr(dso->name, '.'); + if (!ext || !is_supported_compression(ext + 1)) + return -1; + } + + fd = mkstemp(tmpbuf); + if (fd < 0) + return -1; + + if (!decompress_to_file(ext + 1, name, fd)) { + close(fd); + fd = -1; + } + + unlink(tmpbuf); + + return fd; +} + bool symsrc__possibly_runtime(struct symsrc *ss) { return ss->dynsym || ss->opdsec; @@ -571,7 +629,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, Elf *elf; int fd; - fd = open(name, O_RDONLY); + if (dso__needs_decompress(dso)) + fd = decompress_kmodule(dso, name, type); + else + fd = open(name, O_RDONLY); + if (fd < 0) return -1; diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index c9541fea9514..d7efb03b3f9a 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -129,6 +129,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { void *tmp; + long offset; if (need_swap) { phdr->p_type = bswap_32(phdr->p_type); @@ -140,12 +141,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) continue; buf_size = phdr->p_filesz; + offset = phdr->p_offset; tmp = realloc(buf, buf_size); if (tmp == NULL) goto out_free; buf = tmp; - fseek(fp, phdr->p_offset, SEEK_SET); + fseek(fp, offset, SEEK_SET); if (fread(buf, buf_size, 1, fp) != 1) goto out_free; @@ -178,6 +180,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { void *tmp; + long offset; if (need_swap) { phdr->p_type = bswap_32(phdr->p_type); @@ -189,12 +192,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) continue; buf_size = phdr->p_filesz; + offset = phdr->p_offset; tmp = realloc(buf, buf_size); if (tmp == NULL) goto out_free; buf = tmp; - fseek(fp, phdr->p_offset, SEEK_SET); + fseek(fp, offset, SEEK_SET); if (fread(buf, buf_size, 1, fp) != 1) goto out_free; @@ -341,7 +345,6 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) { dso__set_build_id(dso, build_id); - return 1; } return 0; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 078331140d8c..a69066865a55 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -51,7 +51,9 @@ static enum dso_binary_type binary_type_symtab[] = { DSO_BINARY_TYPE__BUILDID_DEBUGINFO, DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, + DSO_BINARY_TYPE__GUEST_KMODULE_COMP, DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP, DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, DSO_BINARY_TYPE__NOT_FOUND, }; @@ -394,6 +396,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, const char *name) { struct rb_node *n; + struct symbol_name_rb_node *s; if (symbols == NULL) return NULL; @@ -401,7 +404,6 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, n = symbols->rb_node; while (n) { - struct symbol_name_rb_node *s; int cmp; s = rb_entry(n, struct symbol_name_rb_node, rb_node); @@ -412,10 +414,24 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, else if (cmp > 0) n = n->rb_right; else - return &s->sym; + break; } - return NULL; + if (n == NULL) + return NULL; + + /* return first symbol that has same name (if any) */ + for (n = rb_prev(n); n; n = rb_prev(n)) { + struct symbol_name_rb_node *tmp; + + tmp = rb_entry(n, struct symbol_name_rb_node, rb_node); + if (strcmp(tmp->sym.name, s->sym.name)) + break; + + s = tmp; + } + + return &s->sym; } struct symbol *dso__find_symbol(struct dso *dso, @@ -434,6 +450,17 @@ struct symbol *dso__next_symbol(struct symbol *sym) return symbols__next(sym); } +struct symbol *symbol__next_by_name(struct symbol *sym) +{ + struct symbol_name_rb_node *s = container_of(sym, struct symbol_name_rb_node, sym); + struct rb_node *n = rb_next(&s->rb_node); + + return n ? &rb_entry(n, struct symbol_name_rb_node, rb_node)->sym : NULL; +} + + /* + * Teturns first symbol that matched with @name. + */ struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name) { @@ -658,7 +685,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta, struct machine *machine = kmaps->machine; struct map *curr_map = map; struct symbol *pos; - int count = 0, moved = 0; + int count = 0, moved = 0; struct rb_root *root = &dso->symbols[map->type]; struct rb_node *next = rb_first(root); int kernel_range = 0; @@ -1300,7 +1327,9 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, return dso->kernel == DSO_TYPE_GUEST_KERNEL; case DSO_BINARY_TYPE__GUEST_KMODULE: + case DSO_BINARY_TYPE__GUEST_KMODULE_COMP: case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: /* * kernel modules know their symtab type - it's set when * creating a module dso in machine__new_module(). @@ -1368,7 +1397,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) return -1; kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || - dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; + dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; /* * Iterate over candidate debug images. @@ -1505,12 +1536,10 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, symbol_filter_t filter) { int i, err = 0; - char *filename; - - pr_debug("Looking at the vmlinux_path (%d entries long)\n", - vmlinux_path__nr_entries + 1); + char *filename = NULL; - filename = dso__build_id_filename(dso, NULL, 0); + if (!symbol_conf.ignore_vmlinux_buildid) + filename = dso__build_id_filename(dso, NULL, 0); if (filename != NULL) { err = dso__load_vmlinux(dso, map, filename, true, filter); if (err > 0) @@ -1518,6 +1547,9 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, free(filename); } + pr_debug("Looking at the vmlinux_path (%d entries long)\n", + vmlinux_path__nr_entries + 1); + for (i = 0; i < vmlinux_path__nr_entries; ++i) { err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter); if (err > 0) diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index eb2c19bf8d90..1650dcb3a67b 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -23,27 +23,6 @@ #include "dso.h" -#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT -extern char *cplus_demangle(const char *, int); - -static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i) -{ - return cplus_demangle(c, i); -} -#else -#ifdef NO_DEMANGLE -static inline char *bfd_demangle(void __maybe_unused *v, - const char __maybe_unused *c, - int __maybe_unused i) -{ - return NULL; -} -#else -#define PACKAGE 'perf' -#include <bfd.h> -#endif -#endif - /* * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP; * for newer versions we can use mmap to reduce memory usage: @@ -105,6 +84,7 @@ struct symbol_conf { unsigned short nr_events; bool try_vmlinux_path, ignore_vmlinux, + ignore_vmlinux_buildid, show_kernel_path, use_modules, sort_by_name, @@ -122,7 +102,8 @@ struct symbol_conf { demangle, demangle_kernel, filter_relative, - show_hist_headers; + show_hist_headers, + branch_callstack; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -250,6 +231,7 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name); +struct symbol *symbol__next_by_name(struct symbol *sym); struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); struct symbol *dso__next_symbol(struct symbol *sym); diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c new file mode 100644 index 000000000000..9ed59a452d1f --- /dev/null +++ b/tools/perf/util/thread-stack.c @@ -0,0 +1,747 @@ +/* + * thread-stack.c: Synthesize a thread's stack using call / return events + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#include <linux/rbtree.h> +#include <linux/list.h> +#include "thread.h" +#include "event.h" +#include "machine.h" +#include "util.h" +#include "debug.h" +#include "symbol.h" +#include "comm.h" +#include "thread-stack.h" + +#define CALL_PATH_BLOCK_SHIFT 8 +#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT) +#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1) + +struct call_path_block { + struct call_path cp[CALL_PATH_BLOCK_SIZE]; + struct list_head node; +}; + +/** + * struct call_path_root - root of all call paths. + * @call_path: root call path + * @blocks: list of blocks to store call paths + * @next: next free space + * @sz: number of spaces + */ +struct call_path_root { + struct call_path call_path; + struct list_head blocks; + size_t next; + size_t sz; +}; + +/** + * struct call_return_processor - provides a call-back to consume call-return + * information. + * @cpr: call path root + * @process: call-back that accepts call/return information + * @data: anonymous data for call-back + */ +struct call_return_processor { + struct call_path_root *cpr; + int (*process)(struct call_return *cr, void *data); + void *data; +}; + +#define STACK_GROWTH 2048 + +/** + * struct thread_stack_entry - thread stack entry. + * @ret_addr: return address + * @timestamp: timestamp (if known) + * @ref: external reference (e.g. db_id of sample) + * @branch_count: the branch count when the entry was created + * @cp: call path + * @no_call: a 'call' was not seen + */ +struct thread_stack_entry { + u64 ret_addr; + u64 timestamp; + u64 ref; + u64 branch_count; + struct call_path *cp; + bool no_call; +}; + +/** + * struct thread_stack - thread stack constructed from 'call' and 'return' + * branch samples. + * @stack: array that holds the stack + * @cnt: number of entries in the stack + * @sz: current maximum stack size + * @trace_nr: current trace number + * @branch_count: running branch count + * @kernel_start: kernel start address + * @last_time: last timestamp + * @crp: call/return processor + * @comm: current comm + */ +struct thread_stack { + struct thread_stack_entry *stack; + size_t cnt; + size_t sz; + u64 trace_nr; + u64 branch_count; + u64 kernel_start; + u64 last_time; + struct call_return_processor *crp; + struct comm *comm; +}; + +static int thread_stack__grow(struct thread_stack *ts) +{ + struct thread_stack_entry *new_stack; + size_t sz, new_sz; + + new_sz = ts->sz + STACK_GROWTH; + sz = new_sz * sizeof(struct thread_stack_entry); + + new_stack = realloc(ts->stack, sz); + if (!new_stack) + return -ENOMEM; + + ts->stack = new_stack; + ts->sz = new_sz; + + return 0; +} + +static struct thread_stack *thread_stack__new(struct thread *thread, + struct call_return_processor *crp) +{ + struct thread_stack *ts; + + ts = zalloc(sizeof(struct thread_stack)); + if (!ts) + return NULL; + + if (thread_stack__grow(ts)) { + free(ts); + return NULL; + } + + if (thread->mg && thread->mg->machine) + ts->kernel_start = machine__kernel_start(thread->mg->machine); + else + ts->kernel_start = 1ULL << 63; + ts->crp = crp; + + return ts; +} + +static int thread_stack__push(struct thread_stack *ts, u64 ret_addr) +{ + int err = 0; + + if (ts->cnt == ts->sz) { + err = thread_stack__grow(ts); + if (err) { + pr_warning("Out of memory: discarding thread stack\n"); + ts->cnt = 0; + } + } + + ts->stack[ts->cnt++].ret_addr = ret_addr; + + return err; +} + +static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr) +{ + size_t i; + + /* + * In some cases there may be functions which are not seen to return. + * For example when setjmp / longjmp has been used. Or the perf context + * switch in the kernel which doesn't stop and start tracing in exactly + * the same code path. When that happens the return address will be + * further down the stack. If the return address is not found at all, + * we assume the opposite (i.e. this is a return for a call that wasn't + * seen for some reason) and leave the stack alone. + */ + for (i = ts->cnt; i; ) { + if (ts->stack[--i].ret_addr == ret_addr) { + ts->cnt = i; + return; + } + } +} + +static bool thread_stack__in_kernel(struct thread_stack *ts) +{ + if (!ts->cnt) + return false; + + return ts->stack[ts->cnt - 1].cp->in_kernel; +} + +static int thread_stack__call_return(struct thread *thread, + struct thread_stack *ts, size_t idx, + u64 timestamp, u64 ref, bool no_return) +{ + struct call_return_processor *crp = ts->crp; + struct thread_stack_entry *tse; + struct call_return cr = { + .thread = thread, + .comm = ts->comm, + .db_id = 0, + }; + + tse = &ts->stack[idx]; + cr.cp = tse->cp; + cr.call_time = tse->timestamp; + cr.return_time = timestamp; + cr.branch_count = ts->branch_count - tse->branch_count; + cr.call_ref = tse->ref; + cr.return_ref = ref; + if (tse->no_call) + cr.flags |= CALL_RETURN_NO_CALL; + if (no_return) + cr.flags |= CALL_RETURN_NO_RETURN; + + return crp->process(&cr, crp->data); +} + +static int thread_stack__flush(struct thread *thread, struct thread_stack *ts) +{ + struct call_return_processor *crp = ts->crp; + int err; + + if (!crp) { + ts->cnt = 0; + return 0; + } + + while (ts->cnt) { + err = thread_stack__call_return(thread, ts, --ts->cnt, + ts->last_time, 0, true); + if (err) { + pr_err("Error flushing thread stack!\n"); + ts->cnt = 0; + return err; + } + } + + return 0; +} + +int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip, + u64 to_ip, u16 insn_len, u64 trace_nr) +{ + if (!thread) + return -EINVAL; + + if (!thread->ts) { + thread->ts = thread_stack__new(thread, NULL); + if (!thread->ts) { + pr_warning("Out of memory: no thread stack\n"); + return -ENOMEM; + } + thread->ts->trace_nr = trace_nr; + } + + /* + * When the trace is discontinuous, the trace_nr changes. In that case + * the stack might be completely invalid. Better to report nothing than + * to report something misleading, so flush the stack. + */ + if (trace_nr != thread->ts->trace_nr) { + if (thread->ts->trace_nr) + thread_stack__flush(thread, thread->ts); + thread->ts->trace_nr = trace_nr; + } + + /* Stop here if thread_stack__process() is in use */ + if (thread->ts->crp) + return 0; + + if (flags & PERF_IP_FLAG_CALL) { + u64 ret_addr; + + if (!to_ip) + return 0; + ret_addr = from_ip + insn_len; + if (ret_addr == to_ip) + return 0; /* Zero-length calls are excluded */ + return thread_stack__push(thread->ts, ret_addr); + } else if (flags & PERF_IP_FLAG_RETURN) { + if (!from_ip) + return 0; + thread_stack__pop(thread->ts, to_ip); + } + + return 0; +} + +void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr) +{ + if (!thread || !thread->ts) + return; + + if (trace_nr != thread->ts->trace_nr) { + if (thread->ts->trace_nr) + thread_stack__flush(thread, thread->ts); + thread->ts->trace_nr = trace_nr; + } +} + +void thread_stack__free(struct thread *thread) +{ + if (thread->ts) { + thread_stack__flush(thread, thread->ts); + zfree(&thread->ts->stack); + zfree(&thread->ts); + } +} + +void thread_stack__sample(struct thread *thread, struct ip_callchain *chain, + size_t sz, u64 ip) +{ + size_t i; + + if (!thread || !thread->ts) + chain->nr = 1; + else + chain->nr = min(sz, thread->ts->cnt + 1); + + chain->ips[0] = ip; + + for (i = 1; i < chain->nr; i++) + chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr; +} + +static void call_path__init(struct call_path *cp, struct call_path *parent, + struct symbol *sym, u64 ip, bool in_kernel) +{ + cp->parent = parent; + cp->sym = sym; + cp->ip = sym ? 0 : ip; + cp->db_id = 0; + cp->in_kernel = in_kernel; + RB_CLEAR_NODE(&cp->rb_node); + cp->children = RB_ROOT; +} + +static struct call_path_root *call_path_root__new(void) +{ + struct call_path_root *cpr; + + cpr = zalloc(sizeof(struct call_path_root)); + if (!cpr) + return NULL; + call_path__init(&cpr->call_path, NULL, NULL, 0, false); + INIT_LIST_HEAD(&cpr->blocks); + return cpr; +} + +static void call_path_root__free(struct call_path_root *cpr) +{ + struct call_path_block *pos, *n; + + list_for_each_entry_safe(pos, n, &cpr->blocks, node) { + list_del(&pos->node); + free(pos); + } + free(cpr); +} + +static struct call_path *call_path__new(struct call_path_root *cpr, + struct call_path *parent, + struct symbol *sym, u64 ip, + bool in_kernel) +{ + struct call_path_block *cpb; + struct call_path *cp; + size_t n; + + if (cpr->next < cpr->sz) { + cpb = list_last_entry(&cpr->blocks, struct call_path_block, + node); + } else { + cpb = zalloc(sizeof(struct call_path_block)); + if (!cpb) + return NULL; + list_add_tail(&cpb->node, &cpr->blocks); + cpr->sz += CALL_PATH_BLOCK_SIZE; + } + + n = cpr->next++ & CALL_PATH_BLOCK_MASK; + cp = &cpb->cp[n]; + + call_path__init(cp, parent, sym, ip, in_kernel); + + return cp; +} + +static struct call_path *call_path__findnew(struct call_path_root *cpr, + struct call_path *parent, + struct symbol *sym, u64 ip, u64 ks) +{ + struct rb_node **p; + struct rb_node *node_parent = NULL; + struct call_path *cp; + bool in_kernel = ip >= ks; + + if (sym) + ip = 0; + + if (!parent) + return call_path__new(cpr, parent, sym, ip, in_kernel); + + p = &parent->children.rb_node; + while (*p != NULL) { + node_parent = *p; + cp = rb_entry(node_parent, struct call_path, rb_node); + + if (cp->sym == sym && cp->ip == ip) + return cp; + + if (sym < cp->sym || (sym == cp->sym && ip < cp->ip)) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + cp = call_path__new(cpr, parent, sym, ip, in_kernel); + if (!cp) + return NULL; + + rb_link_node(&cp->rb_node, node_parent, p); + rb_insert_color(&cp->rb_node, &parent->children); + + return cp; +} + +struct call_return_processor * +call_return_processor__new(int (*process)(struct call_return *cr, void *data), + void *data) +{ + struct call_return_processor *crp; + + crp = zalloc(sizeof(struct call_return_processor)); + if (!crp) + return NULL; + crp->cpr = call_path_root__new(); + if (!crp->cpr) + goto out_free; + crp->process = process; + crp->data = data; + return crp; + +out_free: + free(crp); + return NULL; +} + +void call_return_processor__free(struct call_return_processor *crp) +{ + if (crp) { + call_path_root__free(crp->cpr); + free(crp); + } +} + +static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr, + u64 timestamp, u64 ref, struct call_path *cp, + bool no_call) +{ + struct thread_stack_entry *tse; + int err; + + if (ts->cnt == ts->sz) { + err = thread_stack__grow(ts); + if (err) + return err; + } + + tse = &ts->stack[ts->cnt++]; + tse->ret_addr = ret_addr; + tse->timestamp = timestamp; + tse->ref = ref; + tse->branch_count = ts->branch_count; + tse->cp = cp; + tse->no_call = no_call; + + return 0; +} + +static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts, + u64 ret_addr, u64 timestamp, u64 ref, + struct symbol *sym) +{ + int err; + + if (!ts->cnt) + return 1; + + if (ts->cnt == 1) { + struct thread_stack_entry *tse = &ts->stack[0]; + + if (tse->cp->sym == sym) + return thread_stack__call_return(thread, ts, --ts->cnt, + timestamp, ref, false); + } + + if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) { + return thread_stack__call_return(thread, ts, --ts->cnt, + timestamp, ref, false); + } else { + size_t i = ts->cnt - 1; + + while (i--) { + if (ts->stack[i].ret_addr != ret_addr) + continue; + i += 1; + while (ts->cnt > i) { + err = thread_stack__call_return(thread, ts, + --ts->cnt, + timestamp, ref, + true); + if (err) + return err; + } + return thread_stack__call_return(thread, ts, --ts->cnt, + timestamp, ref, false); + } + } + + return 1; +} + +static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts, + struct perf_sample *sample, + struct addr_location *from_al, + struct addr_location *to_al, u64 ref) +{ + struct call_path_root *cpr = ts->crp->cpr; + struct call_path *cp; + struct symbol *sym; + u64 ip; + + if (sample->ip) { + ip = sample->ip; + sym = from_al->sym; + } else if (sample->addr) { + ip = sample->addr; + sym = to_al->sym; + } else { + return 0; + } + + cp = call_path__findnew(cpr, &cpr->call_path, sym, ip, + ts->kernel_start); + if (!cp) + return -ENOMEM; + + return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp, + true); +} + +static int thread_stack__no_call_return(struct thread *thread, + struct thread_stack *ts, + struct perf_sample *sample, + struct addr_location *from_al, + struct addr_location *to_al, u64 ref) +{ + struct call_path_root *cpr = ts->crp->cpr; + struct call_path *cp, *parent; + u64 ks = ts->kernel_start; + int err; + + if (sample->ip >= ks && sample->addr < ks) { + /* Return to userspace, so pop all kernel addresses */ + while (thread_stack__in_kernel(ts)) { + err = thread_stack__call_return(thread, ts, --ts->cnt, + sample->time, ref, + true); + if (err) + return err; + } + + /* If the stack is empty, push the userspace address */ + if (!ts->cnt) { + cp = call_path__findnew(cpr, &cpr->call_path, + to_al->sym, sample->addr, + ts->kernel_start); + if (!cp) + return -ENOMEM; + return thread_stack__push_cp(ts, 0, sample->time, ref, + cp, true); + } + } else if (thread_stack__in_kernel(ts) && sample->ip < ks) { + /* Return to userspace, so pop all kernel addresses */ + while (thread_stack__in_kernel(ts)) { + err = thread_stack__call_return(thread, ts, --ts->cnt, + sample->time, ref, + true); + if (err) + return err; + } + } + + if (ts->cnt) + parent = ts->stack[ts->cnt - 1].cp; + else + parent = &cpr->call_path; + + /* This 'return' had no 'call', so push and pop top of stack */ + cp = call_path__findnew(cpr, parent, from_al->sym, sample->ip, + ts->kernel_start); + if (!cp) + return -ENOMEM; + + err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp, + true); + if (err) + return err; + + return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref, + to_al->sym); +} + +static int thread_stack__trace_begin(struct thread *thread, + struct thread_stack *ts, u64 timestamp, + u64 ref) +{ + struct thread_stack_entry *tse; + int err; + + if (!ts->cnt) + return 0; + + /* Pop trace end */ + tse = &ts->stack[ts->cnt - 1]; + if (tse->cp->sym == NULL && tse->cp->ip == 0) { + err = thread_stack__call_return(thread, ts, --ts->cnt, + timestamp, ref, false); + if (err) + return err; + } + + return 0; +} + +static int thread_stack__trace_end(struct thread_stack *ts, + struct perf_sample *sample, u64 ref) +{ + struct call_path_root *cpr = ts->crp->cpr; + struct call_path *cp; + u64 ret_addr; + + /* No point having 'trace end' on the bottom of the stack */ + if (!ts->cnt || (ts->cnt == 1 && ts->stack[0].ref == ref)) + return 0; + + cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, NULL, 0, + ts->kernel_start); + if (!cp) + return -ENOMEM; + + ret_addr = sample->ip + sample->insn_len; + + return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp, + false); +} + +int thread_stack__process(struct thread *thread, struct comm *comm, + struct perf_sample *sample, + struct addr_location *from_al, + struct addr_location *to_al, u64 ref, + struct call_return_processor *crp) +{ + struct thread_stack *ts = thread->ts; + int err = 0; + + if (ts) { + if (!ts->crp) { + /* Supersede thread_stack__event() */ + thread_stack__free(thread); + thread->ts = thread_stack__new(thread, crp); + if (!thread->ts) + return -ENOMEM; + ts = thread->ts; + ts->comm = comm; + } + } else { + thread->ts = thread_stack__new(thread, crp); + if (!thread->ts) + return -ENOMEM; + ts = thread->ts; + ts->comm = comm; + } + + /* Flush stack on exec */ + if (ts->comm != comm && thread->pid_ == thread->tid) { + err = thread_stack__flush(thread, ts); + if (err) + return err; + ts->comm = comm; + } + + /* If the stack is empty, put the current symbol on the stack */ + if (!ts->cnt) { + err = thread_stack__bottom(thread, ts, sample, from_al, to_al, + ref); + if (err) + return err; + } + + ts->branch_count += 1; + ts->last_time = sample->time; + + if (sample->flags & PERF_IP_FLAG_CALL) { + struct call_path_root *cpr = ts->crp->cpr; + struct call_path *cp; + u64 ret_addr; + + if (!sample->ip || !sample->addr) + return 0; + + ret_addr = sample->ip + sample->insn_len; + if (ret_addr == sample->addr) + return 0; /* Zero-length calls are excluded */ + + cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, + to_al->sym, sample->addr, + ts->kernel_start); + if (!cp) + return -ENOMEM; + err = thread_stack__push_cp(ts, ret_addr, sample->time, ref, + cp, false); + } else if (sample->flags & PERF_IP_FLAG_RETURN) { + if (!sample->ip || !sample->addr) + return 0; + + err = thread_stack__pop_cp(thread, ts, sample->addr, + sample->time, ref, from_al->sym); + if (err) { + if (err < 0) + return err; + err = thread_stack__no_call_return(thread, ts, sample, + from_al, to_al, ref); + } + } else if (sample->flags & PERF_IP_FLAG_TRACE_BEGIN) { + err = thread_stack__trace_begin(thread, ts, sample->time, ref); + } else if (sample->flags & PERF_IP_FLAG_TRACE_END) { + err = thread_stack__trace_end(ts, sample, ref); + } + + return err; +} diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h new file mode 100644 index 000000000000..b843bbef8ba2 --- /dev/null +++ b/tools/perf/util/thread-stack.h @@ -0,0 +1,111 @@ +/* + * thread-stack.h: Synthesize a thread's stack using call / return events + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#ifndef __PERF_THREAD_STACK_H +#define __PERF_THREAD_STACK_H + +#include <sys/types.h> + +#include <linux/types.h> +#include <linux/rbtree.h> + +struct thread; +struct comm; +struct ip_callchain; +struct symbol; +struct dso; +struct call_return_processor; +struct comm; +struct perf_sample; +struct addr_location; + +/* + * Call/Return flags. + * + * CALL_RETURN_NO_CALL: 'return' but no matching 'call' + * CALL_RETURN_NO_RETURN: 'call' but no matching 'return' + */ +enum { + CALL_RETURN_NO_CALL = 1 << 0, + CALL_RETURN_NO_RETURN = 1 << 1, +}; + +/** + * struct call_return - paired call/return information. + * @thread: thread in which call/return occurred + * @comm: comm in which call/return occurred + * @cp: call path + * @call_time: timestamp of call (if known) + * @return_time: timestamp of return (if known) + * @branch_count: number of branches seen between call and return + * @call_ref: external reference to 'call' sample (e.g. db_id) + * @return_ref: external reference to 'return' sample (e.g. db_id) + * @db_id: id used for db-export + * @flags: Call/Return flags + */ +struct call_return { + struct thread *thread; + struct comm *comm; + struct call_path *cp; + u64 call_time; + u64 return_time; + u64 branch_count; + u64 call_ref; + u64 return_ref; + u64 db_id; + u32 flags; +}; + +/** + * struct call_path - node in list of calls leading to a function call. + * @parent: call path to the parent function call + * @sym: symbol of function called + * @ip: only if sym is null, the ip of the function + * @db_id: id used for db-export + * @in_kernel: whether function is a in the kernel + * @rb_node: node in parent's tree of called functions + * @children: tree of call paths of functions called + * + * In combination with the call_return structure, the call_path structure + * defines a context-sensitve call-graph. + */ +struct call_path { + struct call_path *parent; + struct symbol *sym; + u64 ip; + u64 db_id; + bool in_kernel; + struct rb_node rb_node; + struct rb_root children; +}; + +int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip, + u64 to_ip, u16 insn_len, u64 trace_nr); +void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr); +void thread_stack__sample(struct thread *thread, struct ip_callchain *chain, + size_t sz, u64 ip); +void thread_stack__free(struct thread *thread); + +struct call_return_processor * +call_return_processor__new(int (*process)(struct call_return *cr, void *data), + void *data); +void call_return_processor__free(struct call_return_processor *crp); +int thread_stack__process(struct thread *thread, struct comm *comm, + struct perf_sample *sample, + struct addr_location *from_al, + struct addr_location *to_al, u64 ref, + struct call_return_processor *crp); + +#endif diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index c41411726c7a..9ebc8b1f9be5 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -4,6 +4,7 @@ #include <string.h> #include "session.h" #include "thread.h" +#include "thread-stack.h" #include "util.h" #include "debug.h" #include "comm.h" @@ -15,7 +16,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine) pid_t pid = thread->pid_; if (pid == thread->tid || pid == -1) { - thread->mg = map_groups__new(); + thread->mg = map_groups__new(machine); } else { leader = machine__findnew_thread(machine, pid, pid); if (leader) @@ -66,6 +67,8 @@ void thread__delete(struct thread *thread) { struct comm *comm, *tmp; + thread_stack__free(thread); + if (thread->mg) { map_groups__put(thread->mg); thread->mg = NULL; @@ -100,15 +103,14 @@ struct comm *thread__exec_comm(const struct thread *thread) return last; } -/* CHECKME: time should always be 0 if event aren't ordered */ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, bool exec) { struct comm *new, *curr = thread__comm(thread); int err; - /* Override latest entry if it had no specific time coverage */ - if (!curr->start && !curr->exec) { + /* Override the default :tid entry */ + if (!thread->comm_set) { err = comm__override(curr, str, timestamp, exec); if (err) return err; @@ -198,7 +200,6 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) } void thread__find_cpumode_addr_location(struct thread *thread, - struct machine *machine, enum map_type type, u64 addr, struct addr_location *al) { @@ -211,8 +212,7 @@ void thread__find_cpumode_addr_location(struct thread *thread, }; for (i = 0; i < ARRAY_SIZE(cpumodes); i++) { - thread__find_addr_location(thread, machine, cpumodes[i], type, - addr, al); + thread__find_addr_location(thread, cpumodes[i], type, addr, al); if (al->map) break; } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 8c75fa774706..160fd066a7d1 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -8,6 +8,8 @@ #include "symbol.h" #include <strlist.h> +struct thread_stack; + struct thread { union { struct rb_node rb_node; @@ -23,8 +25,10 @@ struct thread { bool dead; /* if set thread has exited */ struct list_head comm_list; int comm_len; + u64 db_id; void *priv; + struct thread_stack *ts; }; struct machine; @@ -54,16 +58,15 @@ void thread__insert_map(struct thread *thread, struct map *map); int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp); size_t thread__fprintf(struct thread *thread, FILE *fp); -void thread__find_addr_map(struct thread *thread, struct machine *machine, +void thread__find_addr_map(struct thread *thread, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al); -void thread__find_addr_location(struct thread *thread, struct machine *machine, +void thread__find_addr_location(struct thread *thread, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al); void thread__find_cpumode_addr_location(struct thread *thread, - struct machine *machine, enum map_type type, u64 addr, struct addr_location *al); diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index f11636966a0f..bb2708bbfaca 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -39,7 +39,8 @@ struct perf_tool { event_attr_op attr; event_op2 tracing_data; event_op2 finished_round, - build_id; + build_id, + id_index; bool ordered_events; bool ordering_requires_timestamps; }; diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 7419768c38b1..2dcfe9a7c8d0 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -26,7 +26,7 @@ static int __report_module(struct addr_location *al, u64 ip, Dwfl_Module *mod; struct dso *dso = NULL; - thread__find_addr_location(ui->thread, ui->machine, + thread__find_addr_location(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, al); @@ -89,7 +89,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, struct addr_location al; ssize_t size; - thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, addr, &al); if (!al.map) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); @@ -164,14 +164,14 @@ frame_callback(Dwfl_Frame *state, void *arg) } int unwind__get_entries(unwind_entry_cb_t cb, void *arg, - struct machine *machine, struct thread *thread, + struct thread *thread, struct perf_sample *data, int max_stack) { struct unwind_info ui = { .sample = data, .thread = thread, - .machine = machine, + .machine = thread->mg->machine, .cb = cb, .arg = arg, .max_stack = max_stack, diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 4d45c0dfe343..e3c40a520a25 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -185,6 +185,28 @@ static u64 elf_section_offset(int fd, const char *name) return offset; } +#ifndef NO_LIBUNWIND_DEBUG_FRAME +static int elf_is_exec(int fd, const char *name) +{ + Elf *elf; + GElf_Ehdr ehdr; + int retval = 0; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + return 0; + if (gelf_getehdr(elf, &ehdr) == NULL) + goto out; + + retval = (ehdr.e_type == ET_EXEC); + +out: + elf_end(elf); + pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval); + return retval; +} +#endif + struct table_entry { u32 start_ip_offset; u32 fde_offset; @@ -244,14 +266,17 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, u64 *fde_count) { int ret = -EINVAL, fd; - u64 offset; + u64 offset = dso->data.frame_offset; - fd = dso__data_fd(dso, machine); - if (fd < 0) - return -EINVAL; + if (offset == 0) { + fd = dso__data_fd(dso, machine); + if (fd < 0) + return -EINVAL; - /* Check the .eh_frame section for unwinding info */ - offset = elf_section_offset(fd, ".eh_frame_hdr"); + /* Check the .eh_frame section for unwinding info */ + offset = elf_section_offset(fd, ".eh_frame_hdr"); + dso->data.frame_offset = offset; + } if (offset) ret = unwind_spec_ehframe(dso, machine, offset, @@ -265,14 +290,20 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, static int read_unwind_spec_debug_frame(struct dso *dso, struct machine *machine, u64 *offset) { - int fd = dso__data_fd(dso, machine); + int fd; + u64 ofs = dso->data.frame_offset; - if (fd < 0) - return -EINVAL; + if (ofs == 0) { + fd = dso__data_fd(dso, machine); + if (fd < 0) + return -EINVAL; - /* Check the .debug_frame section for unwinding info */ - *offset = elf_section_offset(fd, ".debug_frame"); + /* Check the .debug_frame section for unwinding info */ + ofs = elf_section_offset(fd, ".debug_frame"); + dso->data.frame_offset = ofs; + } + *offset = ofs; if (*offset) return 0; @@ -284,7 +315,7 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui) { struct addr_location al; - thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); return al.map; } @@ -322,8 +353,12 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, #ifndef NO_LIBUNWIND_DEBUG_FRAME /* Check the .debug_frame section for unwinding info */ if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) { + int fd = dso__data_fd(map->dso, ui->machine); + int is_exec = elf_is_exec(fd, map->dso->name); + unw_word_t base = is_exec ? 0 : map->start; + memset(&di, 0, sizeof(di)); - if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name, + if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name, map->start, map->end)) return dwarf_search_unwind_table(as, ip, &di, pi, need_unwind_info, arg); @@ -374,7 +409,7 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, struct addr_location al; ssize_t size; - thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, addr, &al); if (!al.map) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); @@ -476,14 +511,13 @@ static void put_unwind_info(unw_addr_space_t __maybe_unused as, pr_debug("unwind: put_unwind_info called\n"); } -static int entry(u64 ip, struct thread *thread, struct machine *machine, +static int entry(u64 ip, struct thread *thread, unwind_entry_cb_t cb, void *arg) { struct unwind_entry e; struct addr_location al; - thread__find_addr_location(thread, machine, - PERF_RECORD_MISC_USER, + thread__find_addr_location(thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); e.ip = ip; @@ -586,21 +620,21 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, unw_word_t ip; unw_get_reg(&c, UNW_REG_IP, &ip); - ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0; + ret = ip ? entry(ip, ui->thread, cb, arg) : 0; } return ret; } int unwind__get_entries(unwind_entry_cb_t cb, void *arg, - struct machine *machine, struct thread *thread, + struct thread *thread, struct perf_sample *data, int max_stack) { u64 ip; struct unwind_info ui = { .sample = data, .thread = thread, - .machine = machine, + .machine = thread->mg->machine, }; int ret; @@ -611,7 +645,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (ret) return ret; - ret = entry(ip, thread, machine, cb, arg); + ret = entry(ip, thread, cb, arg); if (ret) return -ENOMEM; diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index f50b737235eb..12790cf94618 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -16,7 +16,6 @@ typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); #ifdef HAVE_DWARF_UNWIND_SUPPORT int unwind__get_entries(unwind_entry_cb_t cb, void *arg, - struct machine *machine, struct thread *thread, struct perf_sample *data, int max_stack); /* libunwind specific */ @@ -38,7 +37,6 @@ static inline void unwind__finish_access(struct thread *thread __maybe_unused) { static inline int unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, - struct machine *machine __maybe_unused, struct thread *thread __maybe_unused, struct perf_sample *data __maybe_unused, int max_stack __maybe_unused) diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index d5eab3f3323f..b86744f29eef 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -442,23 +442,6 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags) return (unsigned long) -1; } -int filename__read_int(const char *filename, int *value) -{ - char line[64]; - int fd = open(filename, O_RDONLY), err = -1; - - if (fd < 0) - return -1; - - if (read(fd, line, sizeof(line)) > 0) { - *value = atoi(line); - err = 0; - } - - close(fd); - return err; -} - int filename__read_str(const char *filename, char **buf, size_t *sizep) { size_t size = 0, alloc_size = 0; @@ -523,16 +506,9 @@ const char *get_filename_for_perf_kvm(void) int perf_event_paranoid(void) { - char path[PATH_MAX]; - const char *procfs = procfs__mountpoint(); int value; - if (!procfs) - return INT_MAX; - - scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs); - - if (filename__read_int(path, &value)) + if (sysctl__read_int("kernel/perf_event_paranoid", &value)) return INT_MAX; return value; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 80bfdaa0e2a4..027a5153495c 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -153,8 +153,7 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2))) extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN); extern int prefixcmp(const char *str, const char *prefix); -extern void set_buildid_dir(void); -extern void disable_buildid_cache(void); +extern void set_buildid_dir(const char *dir); static inline const char *skip_prefix(const char *str, const char *prefix) { @@ -270,35 +269,6 @@ void event_attr_init(struct perf_event_attr *attr); #define _STR(x) #x #define STR(x) _STR(x) -/* - * Determine whether some value is a power of two, where zero is - * *not* considered a power of two. - */ - -static inline __attribute__((const)) -bool is_power_of_2(unsigned long n) -{ - return (n != 0 && ((n & (n - 1)) == 0)); -} - -static inline unsigned next_pow2(unsigned x) -{ - if (!x) - return 1; - return 1ULL << (32 - __builtin_clz(x - 1)); -} - -static inline unsigned long next_pow2_l(unsigned long x) -{ -#if BITS_PER_LONG == 64 - if (x <= (1UL << 31)) - return next_pow2(x); - return (unsigned long)next_pow2(x >> 32) << 32; -#else - return next_pow2(x); -#endif -} - size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); @@ -338,11 +308,12 @@ static inline int path__join3(char *bf, size_t size, } struct dso; +struct symbol; -char *get_srcline(struct dso *dso, unsigned long addr); +char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, + bool show_sym); void free_srcline(char *srcline); -int filename__read_int(const char *filename, int *value); int filename__read_str(const char *filename, char **buf, size_t *sizep); int perf_event_paranoid(void); @@ -351,4 +322,9 @@ void mem_bswap_32(void *src, int byte_size); const char *get_filename_for_perf_kvm(void); bool find_process(const char *name); + +#ifdef HAVE_ZLIB_SUPPORT +int gzip_decompress_to_file(const char *input, int output_fd); +#endif + #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index adca69384fcc..5c7dd796979d 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -12,9 +12,16 @@ #include "util.h" #include "symbol.h" #include "machine.h" +#include "thread.h" #include "linux/string.h" #include "debug.h" +/* + * Include definition of find_vdso_map() also used in perf-read-vdso.c for + * building perf-read-vdso32 and perf-read-vdsox32. + */ +#include "find-vdso-map.c" + #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX" struct vdso_file { @@ -22,10 +29,15 @@ struct vdso_file { bool error; char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)]; const char *dso_name; + const char *read_prog; }; struct vdso_info { struct vdso_file vdso; +#if BITS_PER_LONG == 64 + struct vdso_file vdso32; + struct vdso_file vdsox32; +#endif }; static struct vdso_info *vdso_info__new(void) @@ -35,42 +47,23 @@ static struct vdso_info *vdso_info__new(void) .temp_file_name = VDSO__TEMP_FILE_NAME, .dso_name = DSO__NAME_VDSO, }, +#if BITS_PER_LONG == 64 + .vdso32 = { + .temp_file_name = VDSO__TEMP_FILE_NAME, + .dso_name = DSO__NAME_VDSO32, + .read_prog = "perf-read-vdso32", + }, + .vdsox32 = { + .temp_file_name = VDSO__TEMP_FILE_NAME, + .dso_name = DSO__NAME_VDSOX32, + .read_prog = "perf-read-vdsox32", + }, +#endif }; return memdup(&vdso_info_init, sizeof(vdso_info_init)); } -static int find_vdso_map(void **start, void **end) -{ - FILE *maps; - char line[128]; - int found = 0; - - maps = fopen("/proc/self/maps", "r"); - if (!maps) { - pr_err("vdso: cannot open maps\n"); - return -1; - } - - while (!found && fgets(line, sizeof(line), maps)) { - int m = -1; - - /* We care only about private r-x mappings. */ - if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n", - start, end, &m)) - continue; - if (m < 0) - continue; - - if (!strncmp(&line[m], VDSO__MAP_NAME, - sizeof(VDSO__MAP_NAME) - 1)) - found = 1; - } - - fclose(maps); - return !found; -} - static char *get_file(struct vdso_file *vdso_file) { char *vdso = NULL; @@ -117,6 +110,12 @@ void vdso__exit(struct machine *machine) if (vdso_info->vdso.found) unlink(vdso_info->vdso.temp_file_name); +#if BITS_PER_LONG == 64 + if (vdso_info->vdso32.found) + unlink(vdso_info->vdso32.temp_file_name); + if (vdso_info->vdsox32.found) + unlink(vdso_info->vdsox32.temp_file_name); +#endif zfree(&machine->vdso_info); } @@ -135,6 +134,153 @@ static struct dso *vdso__new(struct machine *machine, const char *short_name, return dso; } +#if BITS_PER_LONG == 64 + +static enum dso_type machine__thread_dso_type(struct machine *machine, + struct thread *thread) +{ + enum dso_type dso_type = DSO__TYPE_UNKNOWN; + struct map *map; + struct dso *dso; + + map = map_groups__first(thread->mg, MAP__FUNCTION); + for (; map ; map = map_groups__next(map)) { + dso = map->dso; + if (!dso || dso->long_name[0] != '/') + continue; + dso_type = dso__type(dso, machine); + if (dso_type != DSO__TYPE_UNKNOWN) + break; + } + + return dso_type; +} + +static int vdso__do_copy_compat(FILE *f, int fd) +{ + char buf[4096]; + size_t count; + + while (1) { + count = fread(buf, 1, sizeof(buf), f); + if (ferror(f)) + return -errno; + if (feof(f)) + break; + if (count && writen(fd, buf, count) != (ssize_t)count) + return -errno; + } + + return 0; +} + +static int vdso__copy_compat(const char *prog, int fd) +{ + FILE *f; + int err; + + f = popen(prog, "r"); + if (!f) + return -errno; + + err = vdso__do_copy_compat(f, fd); + + if (pclose(f) == -1) + return -errno; + + return err; +} + +static int vdso__create_compat_file(const char *prog, char *temp_name) +{ + int fd, err; + + fd = mkstemp(temp_name); + if (fd < 0) + return -errno; + + err = vdso__copy_compat(prog, fd); + + if (close(fd) == -1) + return -errno; + + return err; +} + +static const char *vdso__get_compat_file(struct vdso_file *vdso_file) +{ + int err; + + if (vdso_file->found) + return vdso_file->temp_file_name; + + if (vdso_file->error) + return NULL; + + err = vdso__create_compat_file(vdso_file->read_prog, + vdso_file->temp_file_name); + if (err) { + pr_err("%s failed, error %d\n", vdso_file->read_prog, err); + vdso_file->error = true; + return NULL; + } + + vdso_file->found = true; + + return vdso_file->temp_file_name; +} + +static struct dso *vdso__findnew_compat(struct machine *machine, + struct vdso_file *vdso_file) +{ + const char *file_name; + struct dso *dso; + + dso = dsos__find(&machine->user_dsos, vdso_file->dso_name, true); + if (dso) + return dso; + + file_name = vdso__get_compat_file(vdso_file); + if (!file_name) + return NULL; + + return vdso__new(machine, vdso_file->dso_name, file_name); +} + +static int vdso__dso_findnew_compat(struct machine *machine, + struct thread *thread, + struct vdso_info *vdso_info, + struct dso **dso) +{ + enum dso_type dso_type; + + dso_type = machine__thread_dso_type(machine, thread); + +#ifndef HAVE_PERF_READ_VDSO32 + if (dso_type == DSO__TYPE_32BIT) + return 0; +#endif +#ifndef HAVE_PERF_READ_VDSOX32 + if (dso_type == DSO__TYPE_X32BIT) + return 0; +#endif + + switch (dso_type) { + case DSO__TYPE_32BIT: + *dso = vdso__findnew_compat(machine, &vdso_info->vdso32); + return 1; + case DSO__TYPE_X32BIT: + *dso = vdso__findnew_compat(machine, &vdso_info->vdsox32); + return 1; + case DSO__TYPE_UNKNOWN: + case DSO__TYPE_64BIT: + default: + return 0; + } +} + +#endif + struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread __maybe_unused) { @@ -148,6 +294,11 @@ struct dso *vdso__dso_findnew(struct machine *machine, if (!vdso_info) return NULL; +#if BITS_PER_LONG == 64 + if (vdso__dso_findnew_compat(machine, thread, vdso_info, &dso)) + return dso; +#endif + dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true); if (!dso) { char *file; @@ -164,5 +315,7 @@ struct dso *vdso__dso_findnew(struct machine *machine, bool dso__is_vdso(struct dso *dso) { - return !strcmp(dso->short_name, DSO__NAME_VDSO); + return !strcmp(dso->short_name, DSO__NAME_VDSO) || + !strcmp(dso->short_name, DSO__NAME_VDSO32) || + !strcmp(dso->short_name, DSO__NAME_VDSOX32); } diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h index af9d6929a215..d97da1616f0c 100644 --- a/tools/perf/util/vdso.h +++ b/tools/perf/util/vdso.h @@ -7,7 +7,9 @@ #define VDSO__MAP_NAME "[vdso]" -#define DSO__NAME_VDSO "[vdso]" +#define DSO__NAME_VDSO "[vdso]" +#define DSO__NAME_VDSO32 "[vdso32]" +#define DSO__NAME_VDSOX32 "[vdsox32]" static inline bool is_vdso_map(const char *filename) { diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c new file mode 100644 index 000000000000..495a449fc25c --- /dev/null +++ b/tools/perf/util/zlib.c @@ -0,0 +1,78 @@ +#include <stdio.h> +#include <unistd.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <zlib.h> + +#include "util/util.h" +#include "util/debug.h" + + +#define CHUNK_SIZE 16384 + +int gzip_decompress_to_file(const char *input, int output_fd) +{ + int ret = Z_STREAM_ERROR; + int input_fd; + void *ptr; + int len; + struct stat stbuf; + unsigned char buf[CHUNK_SIZE]; + z_stream zs = { + .zalloc = Z_NULL, + .zfree = Z_NULL, + .opaque = Z_NULL, + .avail_in = 0, + .next_in = Z_NULL, + }; + + input_fd = open(input, O_RDONLY); + if (input_fd < 0) + return -1; + + if (fstat(input_fd, &stbuf) < 0) + goto out_close; + + ptr = mmap(NULL, stbuf.st_size, PROT_READ, MAP_PRIVATE, input_fd, 0); + if (ptr == MAP_FAILED) + goto out_close; + + if (inflateInit2(&zs, 16 + MAX_WBITS) != Z_OK) + goto out_unmap; + + zs.next_in = ptr; + zs.avail_in = stbuf.st_size; + + do { + zs.next_out = buf; + zs.avail_out = CHUNK_SIZE; + + ret = inflate(&zs, Z_NO_FLUSH); + switch (ret) { + case Z_NEED_DICT: + ret = Z_DATA_ERROR; + /* fall through */ + case Z_DATA_ERROR: + case Z_MEM_ERROR: + goto out; + default: + break; + } + + len = CHUNK_SIZE - zs.avail_out; + if (writen(output_fd, buf, len) != len) { + ret = Z_DATA_ERROR; + goto out; + } + + } while (ret != Z_STREAM_END); + +out: + inflateEnd(&zs); +out_unmap: + munmap(ptr, stbuf.st_size); +out_close: + close(input_fd); + + return ret == Z_STREAM_END ? 0 : -1; +} diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c index f4b953354ff7..eec688041500 100644 --- a/tools/power/acpi/common/cmfsize.c +++ b/tools/power/acpi/common/cmfsize.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c index 2f0f34a36db4..5da129e10aa2 100644 --- a/tools/power/acpi/common/getopt.c +++ b/tools/power/acpi/common/getopt.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/oslibcfs.c b/tools/power/acpi/os_specific/service_layers/oslibcfs.c index c13ff9c51d74..b51e40a9a120 100644 --- a/tools/power/acpi/os_specific/service_layers/oslibcfs.c +++ b/tools/power/acpi/os_specific/service_layers/oslibcfs.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c index 0dc2485dedf5..92f1fd700344 100644 --- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c +++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c index 733f9e490fc4..e153fcb12b1a 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixdir.c +++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c index 99b47b6194a3..3853a7350440 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixmap.c +++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c index 7ccb073f8316..6858c0893c91 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixxf.c +++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h index a2d37d610639..84bdef0136cb 100644 --- a/tools/power/acpi/tools/acpidump/acpidump.h +++ b/tools/power/acpi/tools/acpidump/acpidump.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c index 24d32968802d..c736adf5fb55 100644 --- a/tools/power/acpi/tools/acpidump/apdump.c +++ b/tools/power/acpi/tools/acpidump/apdump.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c index d470046a6d81..8f2fe168228e 100644 --- a/tools/power/acpi/tools/acpidump/apfiles.c +++ b/tools/power/acpi/tools/acpidump/apfiles.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index 853b4da22c3e..d0ba6535f5af 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/cpupower/utils/cpupower.c b/tools/power/cpupower/utils/cpupower.c index 7cdcf88659c7..9ea914378985 100644 --- a/tools/power/cpupower/utils/cpupower.c +++ b/tools/power/cpupower/utils/cpupower.c @@ -199,7 +199,7 @@ int main(int argc, const char *argv[]) } get_cpu_info(0, &cpupower_cpu_info); - run_as_root = !getuid(); + run_as_root = !geteuid(); if (run_as_root) { ret = uname(&uts); if (!ret && !strcmp(uts.machine, "x86_64") && diff --git a/tools/power/cpupower/utils/helpers/sysfs.c b/tools/power/cpupower/utils/helpers/sysfs.c index 09afe5d87f2b..4e8fe2c7b054 100644 --- a/tools/power/cpupower/utils/helpers/sysfs.c +++ b/tools/power/cpupower/utils/helpers/sysfs.c @@ -361,7 +361,7 @@ unsigned int sysfs_get_idlestate_count(unsigned int cpu) snprintf(file, SYSFS_PATH_MAX, PATH_TO_CPU "cpuidle"); if (stat(file, &statbuf) != 0 || !S_ISDIR(statbuf.st_mode)) - return -ENODEV; + return 0; snprintf(file, SYSFS_PATH_MAX, PATH_TO_CPU "cpu%u/cpuidle/state0", cpu); if (stat(file, &statbuf) != 0 || !S_ISDIR(statbuf.st_mode)) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 56bfb523c5bb..feea7ad9500b 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -9,40 +9,50 @@ turbostat \- Report processor frequency and idle statistics .br .B turbostat .RB [ Options ] -.RB [ "\-i interval_sec" ] +.RB [ "\--interval seconds" ] .SH DESCRIPTION \fBturbostat \fP reports processor topology, frequency, -idle power-state statistics, temperature and power on modern X86 processors. -Either \fBcommand\fP is forked and statistics are printed -upon its completion, or statistics are printed periodically. - -\fBturbostat \fP -must be run on root, and -minimally requires that the processor -supports an "invariant" TSC, plus the APERF and MPERF MSRs. -Additional information is reported depending on hardware counter support. - +idle power-state statistics, temperature and power on X86 processors. +There are two ways to invoke turbostat. +The first method is to supply a +\fBcommand\fP, which is forked and statistics are printed +upon its completion. +The second method is to omit the command, +and turbostat displays statistics every 5 seconds. +The 5-second interval can be changed using the --interval option. + +Some information is not available on older processors. .SS Options -The \fB-p\fP option limits output to the 1st thread in 1st core of each package. +\fB--Counter MSR#\fP shows the delta of the specified 64-bit MSR counter. +.PP +\fB--counter MSR#\fP shows the delta of the specified 32-bit MSR counter. +.PP +\fB--Dump\fP displays the raw counter values. +.PP +\fB--debug\fP displays additional system configuration information. Invoking this parameter +more than once may also enable internal turbostat debug information. +.PP +\fB--interval seconds\fP overrides the default 5-second measurement interval. +.PP +\fB--help\fP displays usage for the most common parameters. .PP -The \fB-P\fP option limits output to the 1st thread in each Package. +\fB--Joules\fP displays energy in Joules, rather than dividing Joules by time to print power in Watts. .PP -The \fB-S\fP option limits output to a 1-line System Summary for each interval. +\fB--MSR MSR#\fP shows the specified 64-bit MSR value. .PP -The \fB-v\fP option increases verbosity. +\fB--msr MSR#\fP shows the specified 32-bit MSR value. .PP -The \fB-c MSR#\fP option includes the delta of the specified 32-bit MSR counter. +\fB--Package\fP limits output to the system summary plus the 1st thread in each Package. .PP -The \fB-C MSR#\fP option includes the delta of the specified 64-bit MSR counter. +\fB--processor\fP limits output to the system summary plus the 1st thread in each processor of each package. Ie. it skips hyper-threaded siblings. .PP -The \fB-m MSR#\fP option includes the the specified 32-bit MSR value. +\fB--Summary\fP limits output to a 1-line System Summary for each interval. .PP -The \fB-M MSR#\fP option includes the the specified 64-bit MSR value. +\fB--TCC temperature\fP sets the Thermal Control Circuit temperature for systems which do not export that value. This is used for making sense of the Digital Thermal Sensor outputs, as they return degrees Celsius below the TCC activation temperature. .PP -The \fB-i interval_sec\fP option prints statistics every \fiinterval_sec\fP seconds. -The default is 5 seconds. +\fB--version\fP displays the version. .PP -The \fBcommand\fP parameter forks \fBcommand\fP and upon its exit, +The \fBcommand\fP parameter forks \fBcommand\fP, and upon its exit, displays the statistics gathered since it was forked. .PP .SH FIELD DESCRIPTIONS @@ -52,7 +62,7 @@ displays the statistics gathered since it was forked. \fBCPU\fP Linux CPU (logical processor) number. Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology. \fBAVG_MHz\fP number of cycles executed divided by time elapsed. -\fB%Buzy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state. +\fB%Busy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state. \fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state). \fBTSC_MHz\fP average MHz that the TSC ran during the entire interval. \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. @@ -68,7 +78,7 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T .fi .PP .SH EXAMPLE -Without any parameters, turbostat prints out counters ever 5 seconds. +Without any parameters, turbostat displays statistics ever 5 seconds. (override interval with "-i sec" option, or specify a command for turbostat to fork). @@ -91,19 +101,19 @@ Subsequent rows show per-CPU statistics. 3 3 3 0.20 1596 3492 0 0.44 0.00 99.37 0.00 23 3 7 5 0.31 1596 3492 0 0.33 .fi -.SH VERBOSE EXAMPLE -The "-v" option adds verbosity to the output: +.SH DEBUG EXAMPLE +The "--debug" option prints additional system information before measurements: .nf -[root@ivy]# turbostat -v -turbostat v3.0 November 23, 2012 - Len Brown <lenb@kernel.org> +turbostat version 4.0 10-Feb, 2015 - Len Brown <lenb@kernel.org> CPUID(0): GenuineIntel 13 CPUID levels; family:model:stepping 0x6:3a:9 (6:58:9) CPUID(6): APERF, DTS, PTM, EPB -RAPL: 851 sec. Joule Counter Range +RAPL: 851 sec. Joule Counter Range, at 77 Watts cpu0: MSR_NHM_PLATFORM_INFO: 0x81010f0012300 16 * 100 = 1600 MHz max efficiency 35 * 100 = 3500 MHz TSC frequency -cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e008402 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, locked: pkg-cstate-limit=2: pc6-noret) +cpu0: MSR_IA32_POWER_CTL: 0x0014005d (C1E auto-promotion: DISabled) +cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e008402 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, locked: pkg-cstate-limit=2: pc6n) cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x25262727 37 * 100 = 3700 MHz max turbo 4 active cores 38 * 100 = 3800 MHz max turbo 3 active cores @@ -112,9 +122,9 @@ cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x25262727 cpu0: MSR_IA32_ENERGY_PERF_BIAS: 0x00000006 (balanced) cpu0: MSR_RAPL_POWER_UNIT: 0x000a1003 (0.125000 Watts, 0.000015 Joules, 0.000977 sec.) cpu0: MSR_PKG_POWER_INFO: 0x01e00268 (77 W TDP, RAPL 60 - 0 W, 0.000000 sec.) -cpu0: MSR_PKG_POWER_LIMIT: 0x830000148268 (UNlocked) +cpu0: MSR_PKG_POWER_LIMIT: 0x30000148268 (UNlocked) cpu0: PKG Limit #1: ENabled (77.000000 Watts, 1.000000 sec, clamp DISabled) -cpu0: PKG Limit #2: ENabled (96.000000 Watts, 0.000977* sec, clamp DISabled) +cpu0: PKG Limit #2: DISabled (96.000000 Watts, 0.000977* sec, clamp DISabled) cpu0: MSR_PP0_POLICY: 0 cpu0: MSR_PP0_POWER_LIMIT: 0x00000000 (UNlocked) cpu0: Cores Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled) @@ -123,19 +133,20 @@ cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked) cpu0: GFX Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled) cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x00691400 (105 C) cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884e0000 (27 C) -cpu0: MSR_IA32_THERM_STATUS: 0x88560000 (19 C +/- 1) -cpu1: MSR_IA32_THERM_STATUS: 0x88560000 (19 C +/- 1) -cpu2: MSR_IA32_THERM_STATUS: 0x88540000 (21 C +/- 1) +cpu0: MSR_IA32_THERM_STATUS: 0x88580000 (17 C +/- 1) +cpu1: MSR_IA32_THERM_STATUS: 0x885a0000 (15 C +/- 1) +cpu2: MSR_IA32_THERM_STATUS: 0x88570000 (18 C +/- 1) cpu3: MSR_IA32_THERM_STATUS: 0x884e0000 (27 C +/- 1) ... .fi The \fBmax efficiency\fP frequency, a.k.a. Low Frequency Mode, is the frequency -available at the minimum package voltage. The \fBTSC frequency\fP is the nominal -maximum frequency of the processor if turbo-mode were not available. This frequency +available at the minimum package voltage. The \fBTSC frequency\fP is the base +frequency of the processor -- this should match the brand string +in /proc/cpuinfo. This base frequency should be sustainable on all CPUs indefinitely, given nominal power and cooling. The remaining rows show what maximum turbo frequency is possible -depending on the number of idle cores. Note that this information is -not available on all processors. +depending on the number of idle cores. Note that not all information is +available on all processors. .SH FORK EXAMPLE If turbostat is invoked with a command, it will fork that command and output the statistics gathered when the command exits. @@ -176,6 +187,11 @@ not including any non-busy idle time. .B "turbostat " must be run as root. +Alternatively, non-root users can be enabled to run turbostat this way: + +# setcap cap_sys_rawio=ep ./turbostat + +# chmod +r /dev/cpu/*/msr .B "turbostat " reads hardware counters, but doesn't write them. @@ -184,15 +200,33 @@ multiple invocations of itself. \fBturbostat \fP may work poorly on Linux-2.6.20 through 2.6.29, -as \fBacpi-cpufreq \fPperiodically cleared the APERF and MPERF +as \fBacpi-cpufreq \fPperiodically cleared the APERF and MPERF MSRs in those kernels. -If the TSC column does not make sense, then -the other numbers will also make no sense. -Turbostat is lightweight, and its data collection is not atomic. -These issues are usually caused by an extremely short measurement -interval (much less than 1 second), or system activity that prevents -turbostat from being able to run on all CPUS to quickly collect data. +AVG_MHz = APERF_delta/measurement_interval. This is the actual +number of elapsed cycles divided by the entire sample interval -- +including idle time. Note that this calculation is resilient +to systems lacking a non-stop TSC. + +TSC_MHz = TSC_delta/measurement_interval. +On a system with an invariant TSC, this value will be constant +and will closely match the base frequency value shown +in the brand string in /proc/cpuinfo. On a system where +the TSC stops in idle, TSC_MHz will drop +below the processor's base frequency. + +%Busy = MPERF_delta/TSC_delta + +Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval + +Note that these calculations depend on TSC_delta, so they +are not reliable during intervals when TSC_MHz is not running at the base frequency. + +Turbostat data collection is not atomic. +Extremely short measurement intervals (much less than 1 second), +or system activity that prevents turbostat from being able +to run on all CPUS to quickly collect data, will result in +inconsistent results. The APERF, MPERF MSRs are defined to count non-halted cycles. Although it is not guaranteed by the architecture, turbostat assumes diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 5b1b807265a1..2d089cac8580 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -33,24 +33,29 @@ #include <signal.h> #include <sys/time.h> #include <stdlib.h> +#include <getopt.h> #include <dirent.h> #include <string.h> #include <ctype.h> #include <sched.h> #include <cpuid.h> +#include <linux/capability.h> +#include <errno.h> char *proc_stat = "/proc/stat"; -unsigned int interval_sec = 5; /* set with -i interval_sec */ -unsigned int verbose; /* set with -v */ -unsigned int rapl_verbose; /* set with -R */ -unsigned int rapl_joules; /* set with -J */ -unsigned int thermal_verbose; /* set with -T */ -unsigned int summary_only; /* set with -S */ -unsigned int dump_only; /* set with -s */ +unsigned int interval_sec = 5; +unsigned int debug; +unsigned int rapl_joules; +unsigned int summary_only; +unsigned int dump_only; unsigned int skip_c0; unsigned int skip_c1; unsigned int do_nhm_cstates; unsigned int do_snb_cstates; +unsigned int do_pc2; +unsigned int do_pc3; +unsigned int do_pc6; +unsigned int do_pc7; unsigned int do_c8_c9_c10; unsigned int do_slm_cstates; unsigned int use_c1_residency_msr; @@ -59,8 +64,8 @@ unsigned int has_epb; unsigned int units = 1000000; /* MHz etc */ unsigned int genuine_intel; unsigned int has_invariant_tsc; -unsigned int do_nehalem_platform_info; -unsigned int do_nehalem_turbo_ratio_limit; +unsigned int do_nhm_platform_info; +unsigned int do_nhm_turbo_ratio_limit; unsigned int do_ivt_turbo_ratio_limit; unsigned int extra_msr_offset32; unsigned int extra_msr_offset64; @@ -81,6 +86,9 @@ unsigned int tcc_activation_temp; unsigned int tcc_activation_temp_override; double rapl_power_units, rapl_energy_units, rapl_time_units; double rapl_joule_counter_range; +unsigned int do_core_perf_limit_reasons; +unsigned int do_gfx_perf_limit_reasons; +unsigned int do_ring_perf_limit_reasons; #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -251,15 +259,13 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) sprintf(pathname, "/dev/cpu/%d/msr", cpu); fd = open(pathname, O_RDONLY); if (fd < 0) - return -1; + err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); retval = pread(fd, msr, sizeof *msr, offset); close(fd); - if (retval != sizeof *msr) { - fprintf(stderr, "%s offset 0x%llx read failed\n", pathname, (unsigned long long)offset); - return -1; - } + if (retval != sizeof *msr) + err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset); return 0; } @@ -281,7 +287,7 @@ void print_header(void) outp += sprintf(outp, " CPU"); if (has_aperf) outp += sprintf(outp, " Avg_MHz"); - if (do_nhm_cstates) + if (has_aperf) outp += sprintf(outp, " %%Busy"); if (has_aperf) outp += sprintf(outp, " Bzy_MHz"); @@ -310,13 +316,13 @@ void print_header(void) if (do_ptm) outp += sprintf(outp, " PkgTmp"); - if (do_snb_cstates) + if (do_pc2) outp += sprintf(outp, " Pkg%%pc2"); - if (do_nhm_cstates && !do_slm_cstates) + if (do_pc3) outp += sprintf(outp, " Pkg%%pc3"); - if (do_nhm_cstates && !do_slm_cstates) + if (do_pc6) outp += sprintf(outp, " Pkg%%pc6"); - if (do_snb_cstates) + if (do_pc7) outp += sprintf(outp, " Pkg%%pc7"); if (do_c8_c9_c10) { outp += sprintf(outp, " Pkg%%pc8"); @@ -337,7 +343,7 @@ void print_header(void) outp += sprintf(outp, " PKG_%%"); if (do_rapl & RAPL_DRAM_PERF_STATUS) outp += sprintf(outp, " RAM_%%"); - } else { + } else if (do_rapl && rapl_joules) { if (do_rapl & RAPL_PKG) outp += sprintf(outp, " Pkg_J"); if (do_rapl & RAPL_CORES) @@ -391,9 +397,12 @@ int dump_counters(struct thread_data *t, struct core_data *c, if (p) { outp += sprintf(outp, "package: %d\n", p->package_id); outp += sprintf(outp, "pc2: %016llX\n", p->pc2); - outp += sprintf(outp, "pc3: %016llX\n", p->pc3); - outp += sprintf(outp, "pc6: %016llX\n", p->pc6); - outp += sprintf(outp, "pc7: %016llX\n", p->pc7); + if (do_pc3) + outp += sprintf(outp, "pc3: %016llX\n", p->pc3); + if (do_pc6) + outp += sprintf(outp, "pc6: %016llX\n", p->pc6); + if (do_pc7) + outp += sprintf(outp, "pc7: %016llX\n", p->pc7); outp += sprintf(outp, "pc8: %016llX\n", p->pc8); outp += sprintf(outp, "pc9: %016llX\n", p->pc9); outp += sprintf(outp, "pc10: %016llX\n", p->pc10); @@ -457,25 +466,25 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "%8d", t->cpu_id); } - /* AvgMHz */ + /* Avg_MHz */ if (has_aperf) outp += sprintf(outp, "%8.0f", 1.0 / units * t->aperf / interval_float); - /* %c0 */ - if (do_nhm_cstates) { + /* %Busy */ + if (has_aperf) { if (!skip_c0) outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc); else outp += sprintf(outp, "********"); } - /* BzyMHz */ + /* Bzy_MHz */ if (has_aperf) outp += sprintf(outp, "%8.0f", 1.0 * t->tsc / units * t->aperf / t->mperf / interval_float); - /* TSC */ + /* TSC_MHz */ outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float); /* SMI */ @@ -525,13 +534,13 @@ int format_counters(struct thread_data *t, struct core_data *c, if (do_ptm) outp += sprintf(outp, "%8d", p->pkg_temp_c); - if (do_snb_cstates) + if (do_pc2) outp += sprintf(outp, "%8.2f", 100.0 * p->pc2/t->tsc); - if (do_nhm_cstates && !do_slm_cstates) + if (do_pc3) outp += sprintf(outp, "%8.2f", 100.0 * p->pc3/t->tsc); - if (do_nhm_cstates && !do_slm_cstates) + if (do_pc6) outp += sprintf(outp, "%8.2f", 100.0 * p->pc6/t->tsc); - if (do_snb_cstates) + if (do_pc7) outp += sprintf(outp, "%8.2f", 100.0 * p->pc7/t->tsc); if (do_c8_c9_c10) { outp += sprintf(outp, "%8.2f", 100.0 * p->pc8/t->tsc); @@ -561,7 +570,7 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); if (do_rapl & RAPL_DRAM_PERF_STATUS) outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); - } else { + } else if (do_rapl && rapl_joules) { if (do_rapl & RAPL_PKG) outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units); @@ -578,8 +587,8 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); if (do_rapl & RAPL_DRAM_PERF_STATUS) outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); - outp += sprintf(outp, fmt8, interval_float); + outp += sprintf(outp, fmt8, interval_float); } done: outp += sprintf(outp, "\n"); @@ -628,9 +637,12 @@ void delta_package(struct pkg_data *new, struct pkg_data *old) { old->pc2 = new->pc2 - old->pc2; - old->pc3 = new->pc3 - old->pc3; - old->pc6 = new->pc6 - old->pc6; - old->pc7 = new->pc7 - old->pc7; + if (do_pc3) + old->pc3 = new->pc3 - old->pc3; + if (do_pc6) + old->pc6 = new->pc6 - old->pc6; + if (do_pc7) + old->pc7 = new->pc7 - old->pc7; old->pc8 = new->pc8 - old->pc8; old->pc9 = new->pc9 - old->pc9; old->pc10 = new->pc10 - old->pc10; @@ -670,24 +682,26 @@ delta_thread(struct thread_data *new, struct thread_data *old, old->c1 = new->c1 - old->c1; - if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) { - old->aperf = new->aperf - old->aperf; - old->mperf = new->mperf - old->mperf; - } else { + if (has_aperf) { + if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) { + old->aperf = new->aperf - old->aperf; + old->mperf = new->mperf - old->mperf; + } else { - if (!aperf_mperf_unstable) { - fprintf(stderr, "%s: APERF or MPERF went backwards *\n", progname); - fprintf(stderr, "* Frequency results do not cover entire interval *\n"); - fprintf(stderr, "* fix this by running Linux-2.6.30 or later *\n"); + if (!aperf_mperf_unstable) { + fprintf(stderr, "%s: APERF or MPERF went backwards *\n", progname); + fprintf(stderr, "* Frequency results do not cover entire interval *\n"); + fprintf(stderr, "* fix this by running Linux-2.6.30 or later *\n"); - aperf_mperf_unstable = 1; + aperf_mperf_unstable = 1; + } + /* + * mperf delta is likely a huge "positive" number + * can not use it for calculating c0 time + */ + skip_c0 = 1; + skip_c1 = 1; } - /* - * mperf delta is likely a huge "positive" number - * can not use it for calculating c0 time - */ - skip_c0 = 1; - skip_c1 = 1; } @@ -712,7 +726,7 @@ delta_thread(struct thread_data *new, struct thread_data *old, } if (old->mperf == 0) { - if (verbose > 1) fprintf(stderr, "cpu%d MPERF 0!\n", old->cpu_id); + if (debug > 1) fprintf(stderr, "cpu%d MPERF 0!\n", old->cpu_id); old->mperf = 1; /* divide by 0 protection */ } @@ -769,9 +783,12 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data c->core_temp_c = 0; p->pc2 = 0; - p->pc3 = 0; - p->pc6 = 0; - p->pc7 = 0; + if (do_pc3) + p->pc3 = 0; + if (do_pc6) + p->pc6 = 0; + if (do_pc7) + p->pc7 = 0; p->pc8 = 0; p->pc9 = 0; p->pc10 = 0; @@ -810,9 +827,12 @@ int sum_counters(struct thread_data *t, struct core_data *c, return 0; average.packages.pc2 += p->pc2; - average.packages.pc3 += p->pc3; - average.packages.pc6 += p->pc6; - average.packages.pc7 += p->pc7; + if (do_pc3) + average.packages.pc3 += p->pc3; + if (do_pc6) + average.packages.pc6 += p->pc6; + if (do_pc7) + average.packages.pc7 += p->pc7; average.packages.pc8 += p->pc8; average.packages.pc9 += p->pc9; average.packages.pc10 += p->pc10; @@ -854,9 +874,12 @@ void compute_average(struct thread_data *t, struct core_data *c, average.cores.c7 /= topo.num_cores; average.packages.pc2 /= topo.num_packages; - average.packages.pc3 /= topo.num_packages; - average.packages.pc6 /= topo.num_packages; - average.packages.pc7 /= topo.num_packages; + if (do_pc3) + average.packages.pc3 /= topo.num_packages; + if (do_pc6) + average.packages.pc6 /= topo.num_packages; + if (do_pc7) + average.packages.pc7 /= topo.num_packages; average.packages.pc8 /= topo.num_packages; average.packages.pc9 /= topo.num_packages; @@ -956,18 +979,18 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) return 0; - if (do_nhm_cstates && !do_slm_cstates) { + if (do_pc3) if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3)) return -9; + if (do_pc6) if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6)) return -10; - } - if (do_snb_cstates) { + if (do_pc2) if (get_msr(cpu, MSR_PKG_C2_RESIDENCY, &p->pc2)) return -11; + if (do_pc7) if (get_msr(cpu, MSR_PKG_C7_RESIDENCY, &p->pc7)) return -12; - } if (do_c8_c9_c10) { if (get_msr(cpu, MSR_PKG_C8_RESIDENCY, &p->pc8)) return -13; @@ -1014,12 +1037,43 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; } +/* + * MSR_PKG_CST_CONFIG_CONTROL decoding for pkg_cstate_limit: + * If you change the values, note they are used both in comparisons + * (>= PCL__7) and to index pkg_cstate_limit_strings[]. + */ + +#define PCLUKN 0 /* Unknown */ +#define PCLRSV 1 /* Reserved */ +#define PCL__0 2 /* PC0 */ +#define PCL__1 3 /* PC1 */ +#define PCL__2 4 /* PC2 */ +#define PCL__3 5 /* PC3 */ +#define PCL__4 6 /* PC4 */ +#define PCL__6 7 /* PC6 */ +#define PCL_6N 8 /* PC6 No Retention */ +#define PCL_6R 9 /* PC6 Retention */ +#define PCL__7 10 /* PC7 */ +#define PCL_7S 11 /* PC7 Shrink */ +#define PCLUNL 12 /* Unlimited */ + +int pkg_cstate_limit = PCLUKN; +char *pkg_cstate_limit_strings[] = { "reserved", "unknown", "pc0", "pc1", "pc2", + "pc3", "pc4", "pc6", "pc6n", "pc6r", "pc7", "pc7s", "unlimited"}; + +int nhm_pkg_cstate_limits[8] = {PCL__0, PCL__1, PCL__3, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLUNL}; +int snb_pkg_cstate_limits[8] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCL__7, PCL_7S, PCLRSV, PCLUNL}; +int hsw_pkg_cstate_limits[8] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S, PCLRSV, PCLUNL}; +int slv_pkg_cstate_limits[8] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7}; +int amt_pkg_cstate_limits[8] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7}; +int phi_pkg_cstate_limits[8] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL}; + void print_verbose_header(void) { unsigned long long msr; unsigned int ratio; - if (!do_nehalem_platform_info) + if (!do_nhm_platform_info) return; get_msr(0, MSR_NHM_PLATFORM_INFO, &msr); @@ -1093,46 +1147,16 @@ print_nhm_turbo_ratio_limits: fprintf(stderr, "cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", msr); - fprintf(stderr, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: ", + fprintf(stderr, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n", (msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "", (msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "", (msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "", (msr & NHM_C1_AUTO_DEMOTE) ? "demote-C1, " : "", (msr & (1 << 15)) ? "" : "UN", - (unsigned int)msr & 7); - - - switch(msr & 0x7) { - case 0: - fprintf(stderr, do_slm_cstates ? "no pkg states" : "pc0"); - break; - case 1: - fprintf(stderr, do_slm_cstates ? "no pkg states" : do_snb_cstates ? "pc2" : "pc0"); - break; - case 2: - fprintf(stderr, do_slm_cstates ? "invalid" : do_snb_cstates ? "pc6-noret" : "pc3"); - break; - case 3: - fprintf(stderr, do_slm_cstates ? "invalid" : "pc6"); - break; - case 4: - fprintf(stderr, do_slm_cstates ? "pc4" : "pc7"); - break; - case 5: - fprintf(stderr, do_slm_cstates ? "invalid" : do_snb_cstates ? "pc7s" : "invalid"); - break; - case 6: - fprintf(stderr, do_slm_cstates ? "pc6" : "invalid"); - break; - case 7: - fprintf(stderr, do_slm_cstates ? "pc7" : "unlimited"); - break; - default: - fprintf(stderr, "invalid"); - } - fprintf(stderr, ")\n"); + (unsigned int)msr & 7, + pkg_cstate_limit_strings[pkg_cstate_limit]); - if (!do_nehalem_turbo_ratio_limit) + if (!do_nhm_turbo_ratio_limit) return; get_msr(0, MSR_NHM_TURBO_RATIO_LIMIT, &msr); @@ -1178,6 +1202,7 @@ print_nhm_turbo_ratio_limits: if (ratio) fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 1 active cores\n", ratio, bclk, ratio * bclk); + } void free_all_buffers(void) @@ -1458,18 +1483,66 @@ void check_dev_msr() struct stat sb; if (stat("/dev/cpu/0/msr", &sb)) - err(-5, "no /dev/cpu/0/msr\n" - "Try \"# modprobe msr\""); + err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" "); } -void check_super_user() +void check_permissions() { - if (getuid() != 0) - errx(-6, "must be root"); + struct __user_cap_header_struct cap_header_data; + cap_user_header_t cap_header = &cap_header_data; + struct __user_cap_data_struct cap_data_data; + cap_user_data_t cap_data = &cap_data_data; + extern int capget(cap_user_header_t hdrp, cap_user_data_t datap); + int do_exit = 0; + + /* check for CAP_SYS_RAWIO */ + cap_header->pid = getpid(); + cap_header->version = _LINUX_CAPABILITY_VERSION; + if (capget(cap_header, cap_data) < 0) + err(-6, "capget(2) failed"); + + if ((cap_data->effective & (1 << CAP_SYS_RAWIO)) == 0) { + do_exit++; + warnx("capget(CAP_SYS_RAWIO) failed," + " try \"# setcap cap_sys_rawio=ep %s\"", progname); + } + + /* test file permissions */ + if (euidaccess("/dev/cpu/0/msr", R_OK)) { + do_exit++; + warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr"); + } + + /* if all else fails, thell them to be root */ + if (do_exit) + if (getuid() != 0) + warnx("... or simply run as root"); + + if (do_exit) + exit(-6); } -int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model) +/* + * NHM adds support for additional MSRs: + * + * MSR_SMI_COUNT 0x00000034 + * + * MSR_NHM_PLATFORM_INFO 0x000000ce + * MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 + * + * MSR_PKG_C3_RESIDENCY 0x000003f8 + * MSR_PKG_C6_RESIDENCY 0x000003f9 + * MSR_CORE_C3_RESIDENCY 0x000003fc + * MSR_CORE_C6_RESIDENCY 0x000003fd + * + * Side effect: + * sets global pkg_cstate_limit to decode MSR_NHM_SNB_PKG_CST_CFG_CTL + */ +int probe_nhm_msrs(unsigned int family, unsigned int model) { + unsigned long long msr; + int *pkg_cstate_limits; + if (!genuine_intel) return 0; @@ -1482,24 +1555,54 @@ int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model) case 0x1F: /* Core i7 and i5 Processor - Nehalem */ case 0x25: /* Westmere Client - Clarkdale, Arrandale */ case 0x2C: /* Westmere EP - Gulftown */ + case 0x2E: /* Nehalem-EX Xeon - Beckton */ + case 0x2F: /* Westmere-EX Xeon - Eagleton */ + pkg_cstate_limits = nhm_pkg_cstate_limits; + break; case 0x2A: /* SNB */ case 0x2D: /* SNB Xeon */ case 0x3A: /* IVB */ case 0x3E: /* IVB Xeon */ + pkg_cstate_limits = snb_pkg_cstate_limits; + break; case 0x3C: /* HSW */ case 0x3F: /* HSX */ case 0x45: /* HSW */ case 0x46: /* HSW */ - case 0x37: /* BYT */ - case 0x4D: /* AVN */ case 0x3D: /* BDW */ + case 0x47: /* BDW */ case 0x4F: /* BDX */ case 0x56: /* BDX-DE */ - return 1; + pkg_cstate_limits = hsw_pkg_cstate_limits; + break; + case 0x37: /* BYT */ + case 0x4D: /* AVN */ + pkg_cstate_limits = slv_pkg_cstate_limits; + break; + case 0x4C: /* AMT */ + pkg_cstate_limits = amt_pkg_cstate_limits; + break; + case 0x57: /* PHI */ + pkg_cstate_limits = phi_pkg_cstate_limits; + break; + default: + return 0; + } + get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); + + pkg_cstate_limit = pkg_cstate_limits[msr & 0x7]; + + return 1; +} +int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model) +{ + switch (model) { + /* Nehalem compatible, but do not include turbo-ratio limit support */ case 0x2E: /* Nehalem-EX Xeon - Beckton */ case 0x2F: /* Westmere-EX Xeon - Eagleton */ - default: return 0; + default: + return 1; } } int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model) @@ -1564,6 +1667,103 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; } +/* + * print_perf_limit() + */ +int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + unsigned long long msr; + int cpu; + + cpu = t->cpu_id; + + /* per-package */ + if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + return 0; + + if (cpu_migrate(cpu)) { + fprintf(stderr, "Could not migrate to CPU %d\n", cpu); + return -1; + } + + if (do_core_perf_limit_reasons) { + get_msr(cpu, MSR_CORE_PERF_LIMIT_REASONS, &msr); + fprintf(stderr, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr); + fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)", + (msr & 1 << 0) ? "PROCHOT, " : "", + (msr & 1 << 1) ? "ThermStatus, " : "", + (msr & 1 << 2) ? "bit2, " : "", + (msr & 1 << 4) ? "Graphics, " : "", + (msr & 1 << 5) ? "Auto-HWP, " : "", + (msr & 1 << 6) ? "VR-Therm, " : "", + (msr & 1 << 8) ? "Amps, " : "", + (msr & 1 << 9) ? "CorePwr, " : "", + (msr & 1 << 10) ? "PkgPwrL1, " : "", + (msr & 1 << 11) ? "PkgPwrL2, " : "", + (msr & 1 << 12) ? "MultiCoreTurbo, " : "", + (msr & 1 << 13) ? "Transitions, " : "", + (msr & 1 << 14) ? "bit14, " : "", + (msr & 1 << 15) ? "bit15, " : ""); + fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)\n", + (msr & 1 << 16) ? "PROCHOT, " : "", + (msr & 1 << 17) ? "ThermStatus, " : "", + (msr & 1 << 18) ? "bit18, " : "", + (msr & 1 << 20) ? "Graphics, " : "", + (msr & 1 << 21) ? "Auto-HWP, " : "", + (msr & 1 << 22) ? "VR-Therm, " : "", + (msr & 1 << 24) ? "Amps, " : "", + (msr & 1 << 25) ? "CorePwr, " : "", + (msr & 1 << 26) ? "PkgPwrL1, " : "", + (msr & 1 << 27) ? "PkgPwrL2, " : "", + (msr & 1 << 28) ? "MultiCoreTurbo, " : "", + (msr & 1 << 29) ? "Transitions, " : "", + (msr & 1 << 30) ? "bit30, " : "", + (msr & 1 << 31) ? "bit31, " : ""); + + } + if (do_gfx_perf_limit_reasons) { + get_msr(cpu, MSR_GFX_PERF_LIMIT_REASONS, &msr); + fprintf(stderr, "cpu%d: MSR_GFX_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr); + fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s)", + (msr & 1 << 0) ? "PROCHOT, " : "", + (msr & 1 << 1) ? "ThermStatus, " : "", + (msr & 1 << 4) ? "Graphics, " : "", + (msr & 1 << 6) ? "VR-Therm, " : "", + (msr & 1 << 8) ? "Amps, " : "", + (msr & 1 << 9) ? "GFXPwr, " : "", + (msr & 1 << 10) ? "PkgPwrL1, " : "", + (msr & 1 << 11) ? "PkgPwrL2, " : ""); + fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s)\n", + (msr & 1 << 16) ? "PROCHOT, " : "", + (msr & 1 << 17) ? "ThermStatus, " : "", + (msr & 1 << 20) ? "Graphics, " : "", + (msr & 1 << 22) ? "VR-Therm, " : "", + (msr & 1 << 24) ? "Amps, " : "", + (msr & 1 << 25) ? "GFXPwr, " : "", + (msr & 1 << 26) ? "PkgPwrL1, " : "", + (msr & 1 << 27) ? "PkgPwrL2, " : ""); + } + if (do_ring_perf_limit_reasons) { + get_msr(cpu, MSR_RING_PERF_LIMIT_REASONS, &msr); + fprintf(stderr, "cpu%d: MSR_RING_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr); + fprintf(stderr, " (Active: %s%s%s%s%s%s)", + (msr & 1 << 0) ? "PROCHOT, " : "", + (msr & 1 << 1) ? "ThermStatus, " : "", + (msr & 1 << 6) ? "VR-Therm, " : "", + (msr & 1 << 8) ? "Amps, " : "", + (msr & 1 << 10) ? "PkgPwrL1, " : "", + (msr & 1 << 11) ? "PkgPwrL2, " : ""); + fprintf(stderr, " (Logged: %s%s%s%s%s%s)\n", + (msr & 1 << 16) ? "PROCHOT, " : "", + (msr & 1 << 17) ? "ThermStatus, " : "", + (msr & 1 << 22) ? "VR-Therm, " : "", + (msr & 1 << 24) ? "Amps, " : "", + (msr & 1 << 26) ? "PkgPwrL1, " : "", + (msr & 1 << 27) ? "PkgPwrL2, " : ""); + } + return 0; +} + #define RAPL_POWER_GRANULARITY 0x7FFF /* 15 bit power granularity */ #define RAPL_TIME_GRANULARITY 0x3F /* 6 bit time granularity */ @@ -1609,6 +1809,7 @@ void rapl_probe(unsigned int family, unsigned int model) case 0x45: /* HSW */ case 0x46: /* HSW */ case 0x3D: /* BDW */ + case 0x47: /* BDW */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO; break; case 0x3F: /* HSX */ @@ -1647,12 +1848,33 @@ void rapl_probe(unsigned int family, unsigned int model) tdp = get_tdp(model); rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; - if (verbose) + if (debug) fprintf(stderr, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp); return; } +void perf_limit_reasons_probe(family, model) +{ + if (!genuine_intel) + return; + + if (family != 6) + return; + + switch (model) { + case 0x3C: /* HSW */ + case 0x45: /* HSW */ + case 0x46: /* HSW */ + do_gfx_perf_limit_reasons = 1; + case 0x3F: /* HSX */ + do_core_perf_limit_reasons = 1; + do_ring_perf_limit_reasons = 1; + default: + return; + } +} + int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p) { unsigned long long msr; @@ -1751,7 +1973,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr)) return -1; - if (verbose) { + if (debug) { fprintf(stderr, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx " "(%f Watts, %f Joules, %f sec.)\n", cpu, msr, rapl_power_units, rapl_energy_units, rapl_time_units); @@ -1808,7 +2030,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) print_power_limit_msr(cpu, msr, "DRAM Limit"); } if (do_rapl & RAPL_CORE_POLICY) { - if (verbose) { + if (debug) { if (get_msr(cpu, MSR_PP0_POLICY, &msr)) return -7; @@ -1816,7 +2038,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) } } if (do_rapl & RAPL_CORES) { - if (verbose) { + if (debug) { if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr)) return -9; @@ -1826,7 +2048,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) } } if (do_rapl & RAPL_GFX) { - if (verbose) { + if (debug) { if (get_msr(cpu, MSR_PP1_POLICY, &msr)) return -8; @@ -1842,8 +2064,15 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; } +/* + * SNB adds support for additional MSRs: + * + * MSR_PKG_C7_RESIDENCY 0x000003fa + * MSR_CORE_C7_RESIDENCY 0x000003fe + * MSR_PKG_C2_RESIDENCY 0x0000060d + */ -int is_snb(unsigned int family, unsigned int model) +int has_snb_msrs(unsigned int family, unsigned int model) { if (!genuine_intel) return 0; @@ -1858,6 +2087,7 @@ int is_snb(unsigned int family, unsigned int model) case 0x45: /* HSW */ case 0x46: /* HSW */ case 0x3D: /* BDW */ + case 0x47: /* BDW */ case 0x4F: /* BDX */ case 0x56: /* BDX-DE */ return 1; @@ -1865,7 +2095,14 @@ int is_snb(unsigned int family, unsigned int model) return 0; } -int has_c8_c9_c10(unsigned int family, unsigned int model) +/* + * HSW adds support for additional MSRs: + * + * MSR_PKG_C8_RESIDENCY 0x00000630 + * MSR_PKG_C9_RESIDENCY 0x00000631 + * MSR_PKG_C10_RESIDENCY 0x00000632 + */ +int has_hsw_msrs(unsigned int family, unsigned int model) { if (!genuine_intel) return 0; @@ -1917,7 +2154,7 @@ double slm_bclk(void) double discover_bclk(unsigned int family, unsigned int model) { - if (is_snb(family, model)) + if (has_snb_msrs(family, model)) return 100.00; else if (is_slm(family, model)) return slm_bclk(); @@ -1965,7 +2202,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk } /* Temperature Target MSR is Nehalem and newer only */ - if (!do_nehalem_platform_info) + if (!do_nhm_platform_info) goto guess; if (get_msr(0, MSR_IA32_TEMPERATURE_TARGET, &msr)) @@ -1973,7 +2210,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk target_c_local = (msr >> 16) & 0xFF; - if (verbose) + if (debug) fprintf(stderr, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", cpu, msr, target_c_local); @@ -2003,7 +2240,7 @@ void check_cpuid() if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e) genuine_intel = 1; - if (verbose) + if (debug) fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ", (char *)&ebx, (char *)&edx, (char *)&ecx); @@ -2014,7 +2251,7 @@ void check_cpuid() if (family == 6 || family == 0xf) model += ((fms >> 16) & 0xf) << 4; - if (verbose) + if (debug) fprintf(stderr, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", max_level, family, model, stepping, family, model, stepping); @@ -2029,18 +2266,15 @@ void check_cpuid() ebx = ecx = edx = 0; __get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx); - if (max_level < 0x80000007) - errx(1, "CPUID: no invariant TSC (max_level 0x%x)", max_level); + if (max_level >= 0x80000007) { - /* - * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8 - * this check is valid for both Intel and AMD - */ - __get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx); - has_invariant_tsc = edx & (1 << 8); - - if (!has_invariant_tsc) - errx(1, "No invariant TSC"); + /* + * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8 + * this check is valid for both Intel and AMD + */ + __get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx); + has_invariant_tsc = edx & (1 << 8); + } /* * APERF/MPERF is advertised by CPUID.EAX=0x6: ECX.bit0 @@ -2053,36 +2287,51 @@ void check_cpuid() do_ptm = eax & (1 << 6); has_epb = ecx & (1 << 3); - if (verbose) - fprintf(stderr, "CPUID(6): %s%s%s%s\n", - has_aperf ? "APERF" : "No APERF!", - do_dts ? ", DTS" : "", - do_ptm ? ", PTM": "", - has_epb ? ", EPB": ""); - - if (!has_aperf) - errx(-1, "No APERF"); - - do_nehalem_platform_info = genuine_intel && has_invariant_tsc; - do_nhm_cstates = genuine_intel; /* all Intel w/ non-stop TSC have NHM counters */ - do_smi = do_nhm_cstates; - do_snb_cstates = is_snb(family, model); - do_c8_c9_c10 = has_c8_c9_c10(family, model); + if (debug) + fprintf(stderr, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sEPB\n", + has_aperf ? "" : "No ", + do_dts ? "" : "No ", + do_ptm ? "" : "No ", + has_epb ? "" : "No "); + + do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model); + do_snb_cstates = has_snb_msrs(family, model); + do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2); + do_pc3 = (pkg_cstate_limit >= PCL__3); + do_pc6 = (pkg_cstate_limit >= PCL__6); + do_pc7 = do_snb_cstates && (pkg_cstate_limit >= PCL__7); + do_c8_c9_c10 = has_hsw_msrs(family, model); do_slm_cstates = is_slm(family, model); bclk = discover_bclk(family, model); - do_nehalem_turbo_ratio_limit = has_nehalem_turbo_ratio_limit(family, model); + do_nhm_turbo_ratio_limit = do_nhm_platform_info && has_nhm_turbo_ratio_limit(family, model); do_ivt_turbo_ratio_limit = has_ivt_turbo_ratio_limit(family, model); rapl_probe(family, model); + perf_limit_reasons_probe(family, model); return; } -void usage() +void help() { - errx(1, "%s: [-v][-R][-T][-p|-P|-S][-c MSR#][-C MSR#][-m MSR#][-M MSR#][-i interval_sec | command ...]\n", - progname); + fprintf(stderr, + "Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n" + "\n" + "Turbostat forks the specified COMMAND and prints statistics\n" + "when COMMAND completes.\n" + "If no COMMAND is specified, turbostat wakes every 5-seconds\n" + "to print statistics, until interrupted.\n" + "--debug run in \"debug\" mode\n" + "--interval sec Override default 5-second measurement interval\n" + "--help print this help message\n" + "--counter msr print 32-bit counter at address \"msr\"\n" + "--Counter msr print 64-bit Counter at address \"msr\"\n" + "--msr msr print 32-bit value at address \"msr\"\n" + "--MSR msr print 64-bit Value at address \"msr\"\n" + "--version print version information\n" + "\n" + "For more help, run \"man turbostat\"\n"); } @@ -2121,7 +2370,7 @@ void topology_probe() if (!summary_only && topo.num_cpus > 1) show_cpu = 1; - if (verbose > 1) + if (debug > 1) fprintf(stderr, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num); cpus = calloc(1, (topo.max_cpu_num + 1) * sizeof(struct cpu_topology)); @@ -2156,7 +2405,7 @@ void topology_probe() int siblings; if (cpu_is_not_present(i)) { - if (verbose > 1) + if (debug > 1) fprintf(stderr, "cpu%d NOT PRESENT\n", i); continue; } @@ -2171,26 +2420,26 @@ void topology_probe() siblings = get_num_ht_siblings(i); if (siblings > max_siblings) max_siblings = siblings; - if (verbose > 1) + if (debug > 1) fprintf(stderr, "cpu %d pkg %d core %d\n", i, cpus[i].physical_package_id, cpus[i].core_id); } topo.num_cores_per_pkg = max_core_id + 1; - if (verbose > 1) + if (debug > 1) fprintf(stderr, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.num_cores_per_pkg); if (!summary_only && topo.num_cores_per_pkg > 1) show_core = 1; topo.num_packages = max_package_id + 1; - if (verbose > 1) + if (debug > 1) fprintf(stderr, "max_package_id %d, sizing for %d packages\n", max_package_id, topo.num_packages); if (!summary_only && topo.num_packages > 1) show_pkg = 1; topo.num_threads_per_core = max_siblings; - if (verbose > 1) + if (debug > 1) fprintf(stderr, "max_siblings %d\n", max_siblings); free(cpus); @@ -2299,25 +2548,27 @@ void setup_all_buffers(void) void turbostat_init() { - check_cpuid(); - check_dev_msr(); - check_super_user(); + check_permissions(); + check_cpuid(); setup_all_buffers(); - if (verbose) + if (debug) print_verbose_header(); - if (verbose) + if (debug) for_all_cpus(print_epb, ODD_COUNTERS); - if (verbose) + if (debug) + for_all_cpus(print_perf_limit, ODD_COUNTERS); + + if (debug) for_all_cpus(print_rapl, ODD_COUNTERS); for_all_cpus(set_temperature_target, ODD_COUNTERS); - if (verbose) + if (debug) for_all_cpus(print_thermal, ODD_COUNTERS); } @@ -2382,56 +2633,82 @@ int get_and_dump_counters(void) return status; } +void print_version() { + fprintf(stderr, "turbostat version 4.1 10-Feb, 2015" + " - Len Brown <lenb@kernel.org>\n"); +} + void cmdline(int argc, char **argv) { int opt; + int option_index = 0; + static struct option long_options[] = { + {"Counter", required_argument, 0, 'C'}, + {"counter", required_argument, 0, 'c'}, + {"Dump", no_argument, 0, 'D'}, + {"debug", no_argument, 0, 'd'}, + {"interval", required_argument, 0, 'i'}, + {"help", no_argument, 0, 'h'}, + {"Joules", no_argument, 0, 'J'}, + {"MSR", required_argument, 0, 'M'}, + {"msr", required_argument, 0, 'm'}, + {"Package", no_argument, 0, 'p'}, + {"processor", no_argument, 0, 'p'}, + {"Summary", no_argument, 0, 'S'}, + {"TCC", required_argument, 0, 'T'}, + {"version", no_argument, 0, 'v' }, + {0, 0, 0, 0 } + }; progname = argv[0]; - while ((opt = getopt(argc, argv, "+pPsSvi:c:C:m:M:RJT:")) != -1) { + while ((opt = getopt_long_only(argc, argv, "C:c:Ddhi:JM:m:PpST:v", + long_options, &option_index)) != -1) { switch (opt) { - case 'p': - show_core_only++; + case 'C': + sscanf(optarg, "%x", &extra_delta_offset64); break; - case 'P': - show_pkg_only++; + case 'c': + sscanf(optarg, "%x", &extra_delta_offset32); break; - case 's': + case 'D': dump_only++; break; - case 'S': - summary_only++; - break; - case 'v': - verbose++; + case 'd': + debug++; break; + case 'h': + default: + help(); + exit(1); case 'i': interval_sec = atoi(optarg); break; - case 'c': - sscanf(optarg, "%x", &extra_delta_offset32); + case 'J': + rapl_joules++; break; - case 'C': - sscanf(optarg, "%x", &extra_delta_offset64); + case 'M': + sscanf(optarg, "%x", &extra_msr_offset64); break; case 'm': sscanf(optarg, "%x", &extra_msr_offset32); break; - case 'M': - sscanf(optarg, "%x", &extra_msr_offset64); + case 'P': + show_pkg_only++; break; - case 'R': - rapl_verbose++; + case 'p': + show_core_only++; + break; + case 'S': + summary_only++; break; case 'T': tcc_activation_temp_override = atoi(optarg); break; - case 'J': - rapl_joules++; + case 'v': + print_version(); + exit(0); break; - - default: - usage(); } } } @@ -2440,9 +2717,8 @@ int main(int argc, char **argv) { cmdline(argc, argv); - if (verbose) - fprintf(stderr, "turbostat v3.7 Feb 6, 2014" - " - Len Brown <lenb@kernel.org>\n"); + if (debug) + print_version(); turbostat_init(); diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index bf1398180785..d08e214ec6e7 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -178,6 +178,7 @@ my $checkout; my $localversion; my $iteration = 0; my $successes = 0; +my $stty_orig; my $bisect_good; my $bisect_bad; @@ -197,6 +198,11 @@ my $patchcheck_start; my $patchcheck_cherry; my $patchcheck_end; +my $build_time; +my $install_time; +my $reboot_time; +my $test_time; + # set when a test is something other that just building or install # which would require more options. my $buildonly = 1; @@ -554,6 +560,66 @@ sub get_mandatory_config { } } +sub show_time { + my ($time) = @_; + + my $hours = 0; + my $minutes = 0; + + if ($time > 3600) { + $hours = int($time / 3600); + $time -= $hours * 3600; + } + if ($time > 60) { + $minutes = int($time / 60); + $time -= $minutes * 60; + } + + if ($hours > 0) { + doprint "$hours hour"; + doprint "s" if ($hours > 1); + doprint " "; + } + + if ($minutes > 0) { + doprint "$minutes minute"; + doprint "s" if ($minutes > 1); + doprint " "; + } + + doprint "$time second"; + doprint "s" if ($time != 1); +} + +sub print_times { + doprint "\n"; + if ($build_time) { + doprint "Build time: "; + show_time($build_time); + doprint "\n"; + } + if ($install_time) { + doprint "Install time: "; + show_time($install_time); + doprint "\n"; + } + if ($reboot_time) { + doprint "Reboot time: "; + show_time($reboot_time); + doprint "\n"; + } + if ($test_time) { + doprint "Test time: "; + show_time($test_time); + doprint "\n"; + } + # reset for iterations like bisect + $build_time = 0; + $install_time = 0; + $reboot_time = 0; + $test_time = 0; +} + sub get_mandatory_configs { get_mandatory_config("MACHINE"); get_mandatory_config("BUILD_DIR"); @@ -684,11 +750,8 @@ sub set_value { } ${$overrides}{$lvalue} = $prvalue; } - if ($rvalue =~ /^\s*$/) { - delete $opt{$lvalue}; - } else { - $opt{$lvalue} = $prvalue; - } + + $opt{$lvalue} = $prvalue; } sub set_eval { @@ -1344,23 +1407,83 @@ sub dodie { print " See $opt{LOG_FILE} for more info.\n"; } + if ($monitor_cnt) { + # restore terminal settings + system("stty $stty_orig"); + } + die @_, "\n"; } +sub create_pty { + my ($ptm, $pts) = @_; + my $tmp; + my $TIOCSPTLCK = 0x40045431; + my $TIOCGPTN = 0x80045430; + + sysopen($ptm, "/dev/ptmx", O_RDWR | O_NONBLOCK) or + dodie "Cant open /dev/ptmx"; + + # unlockpt() + $tmp = pack("i", 0); + ioctl($ptm, $TIOCSPTLCK, $tmp) or + dodie "ioctl TIOCSPTLCK for /dev/ptmx failed"; + + # ptsname() + ioctl($ptm, $TIOCGPTN, $tmp) or + dodie "ioctl TIOCGPTN for /dev/ptmx failed"; + $tmp = unpack("i", $tmp); + + sysopen($pts, "/dev/pts/$tmp", O_RDWR | O_NONBLOCK) or + dodie "Can't open /dev/pts/$tmp"; +} + +sub exec_console { + my ($ptm, $pts) = @_; + + close($ptm); + + close(\*STDIN); + close(\*STDOUT); + close(\*STDERR); + + open(\*STDIN, '<&', $pts); + open(\*STDOUT, '>&', $pts); + open(\*STDERR, '>&', $pts); + + close($pts); + + exec $console or + die "Can't open console $console"; +} + sub open_console { - my ($fp) = @_; + my ($ptm) = @_; + my $pts = \*PTSFD; + my $pid; + + # save terminal settings + $stty_orig = `stty -g`; - my $flags; + # place terminal in cbreak mode so that stdin can be read one character at + # a time without having to wait for a newline + system("stty -icanon -echo -icrnl"); - my $pid = open($fp, "$console|") or - dodie "Can't open console $console"; + create_pty($ptm, $pts); + + $pid = fork; + + if (!$pid) { + # child + exec_console($ptm, $pts) + } - $flags = fcntl($fp, F_GETFL, 0) or - dodie "Can't get flags for the socket: $!"; - $flags = fcntl($fp, F_SETFL, $flags | O_NONBLOCK) or - dodie "Can't set flags for the socket: $!"; + # parent + close($pts); return $pid; + + open(PTSFD, "Stop perl from warning about single use of PTSFD"); } sub close_console { @@ -1371,6 +1494,9 @@ sub close_console { print "closing!\n"; close($fp); + + # restore terminal settings + system("stty $stty_orig"); } sub start_monitor { @@ -1522,6 +1648,8 @@ sub fail { $name = " ($test_name)"; } + print_times; + doprint "%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n"; doprint "%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n"; doprint "KTEST RESULT: TEST $i$name Failed: ", @_, "\n"; @@ -1537,10 +1665,14 @@ sub fail { sub run_command { my ($command, $redirect) = @_; + my $start_time; + my $end_time; my $dolog = 0; my $dord = 0; my $pid; + $start_time = time; + $command =~ s/\$SSH_USER/$ssh_user/g; $command =~ s/\$MACHINE/$machine/g; @@ -1573,6 +1705,15 @@ sub run_command { close(LOG) if ($dolog); close(RD) if ($dord); + $end_time = time; + my $delta = $end_time - $start_time; + + if ($delta == 1) { + doprint "[1 second] "; + } else { + doprint "[$delta seconds] "; + } + if ($failed) { doprint "FAILED!\n"; } else { @@ -1697,7 +1838,9 @@ sub wait_for_input { my ($fp, $time) = @_; my $rin; - my $ready; + my $rout; + my $nr; + my $buf; my $line; my $ch; @@ -1707,21 +1850,36 @@ sub wait_for_input $rin = ''; vec($rin, fileno($fp), 1) = 1; - ($ready, $time) = select($rin, undef, undef, $time); + vec($rin, fileno(\*STDIN), 1) = 1; - $line = ""; + while (1) { + $nr = select($rout=$rin, undef, undef, $time); - # try to read one char at a time - while (sysread $fp, $ch, 1) { - $line .= $ch; - last if ($ch eq "\n"); - } + if ($nr <= 0) { + return undef; + } - if (!length($line)) { - return undef; - } + # copy data from stdin to the console + if (vec($rout, fileno(\*STDIN), 1) == 1) { + sysread(\*STDIN, $buf, 1000); + syswrite($fp, $buf, 1000); + next; + } - return $line; + $line = ""; + + # try to read one char at a time + while (sysread $fp, $ch, 1) { + $line .= $ch; + last if ($ch eq "\n"); + } + + if (!length($line)) { + return undef; + } + + return $line; + } } sub reboot_to { @@ -1769,6 +1927,8 @@ sub monitor { my $skip_call_trace = 0; my $loops; + my $start_time = time; + wait_for_monitor 5; my $line; @@ -1893,6 +2053,9 @@ sub monitor { } } + my $end_time = time; + $reboot_time = $end_time - $start_time; + close(DMESG); if ($bug) { @@ -1941,6 +2104,8 @@ sub install { return if ($no_install); + my $start_time = time; + if (defined($pre_install)) { my $cp_pre_install = eval_kernel_version $pre_install; run_command "$cp_pre_install" or @@ -1972,6 +2137,8 @@ sub install { if (!$install_mods) { do_post_install; doprint "No modules needed\n"; + my $end_time = time; + $install_time = $end_time - $start_time; return; } @@ -1999,19 +2166,22 @@ sub install { run_ssh "rm -f /tmp/$modtar"; do_post_install; + + my $end_time = time; + $install_time = $end_time - $start_time; } sub get_version { # get the release name return if ($have_version); doprint "$make kernelrelease ... "; - $version = `$make kernelrelease | tail -1`; + $version = `$make -s kernelrelease | tail -1`; chomp($version); doprint "$version\n"; $have_version = 1; } -sub start_monitor_and_boot { +sub start_monitor_and_install { # Make sure the stable kernel has finished booting # Install bisects, don't need console @@ -2211,6 +2381,8 @@ sub build { unlink $buildlog; + my $start_time = time; + # Failed builds should not reboot the target my $save_no_reboot = $no_reboot; $no_reboot = 1; @@ -2296,6 +2468,9 @@ sub build { $no_reboot = $save_no_reboot; + my $end_time = time; + $build_time = $end_time - $start_time; + return 1; } @@ -2326,6 +2501,8 @@ sub success { $name = " ($test_name)"; } + print_times; + doprint "\n\n*******************************************\n"; doprint "*******************************************\n"; doprint "KTEST RESULT: TEST $i$name SUCCESS!!!! **\n"; @@ -2386,6 +2563,8 @@ sub do_run_test { my $bug = 0; my $bug_ignored = 0; + my $start_time = time; + wait_for_monitor 1; doprint "run test $run_test\n"; @@ -2452,6 +2631,9 @@ sub do_run_test { waitpid $child_pid, 0; $child_exit = $?; + my $end_time = time; + $test_time = $end_time - $start_time; + if (!$bug && $in_bisect) { if (defined($bisect_ret_good)) { if ($child_exit == $bisect_ret_good) { @@ -2552,7 +2734,7 @@ sub run_bisect_test { dodie "Failed on build" if $failed; # Now boot the box - start_monitor_and_boot or $failed = 1; + start_monitor_and_install or $failed = 1; if ($type ne "boot") { if ($failed && $bisect_skip) { @@ -2758,6 +2940,7 @@ sub bisect { do { $result = run_bisect $type; $test = run_git_bisect "git bisect $result"; + print_times; } while ($test); run_command "git bisect log" or @@ -3171,6 +3354,7 @@ sub config_bisect { do { $ret = run_config_bisect \%good_configs, \%bad_configs; + print_times; } while (!$ret); return $ret if ($ret < 0); @@ -3263,7 +3447,7 @@ sub patchcheck { my $sha1 = $item; $sha1 =~ s/^([[:xdigit:]]+).*/$1/; - doprint "\nProcessing commit $item\n\n"; + doprint "\nProcessing commit \"$item\"\n\n"; run_command "git checkout $sha1" or die "Failed to checkout $sha1"; @@ -3294,16 +3478,18 @@ sub patchcheck { my $failed = 0; - start_monitor_and_boot or $failed = 1; + start_monitor_and_install or $failed = 1; if (!$failed && $type ne "boot"){ do_run_test or $failed = 1; } end_monitor; - return 0 if ($failed); - + if ($failed) { + print_times; + return 0; + } patchcheck_reboot; - + print_times; } $in_patchcheck = 0; success $i; @@ -3571,7 +3757,9 @@ sub test_this_config { undef %configs; assign_configs \%configs, $output_config; - return $config if (!defined($configs{$config})); + if (!defined($configs{$config}) || $configs{$config} =~ /^#/) { + return $config; + } doprint "disabling config $config did not change .config\n"; @@ -3754,7 +3942,7 @@ sub make_min_config { my $failed = 0; build "oldconfig" or $failed = 1; if (!$failed) { - start_monitor_and_boot or $failed = 1; + start_monitor_and_install or $failed = 1; if ($type eq "test" && !$failed) { do_run_test or $failed = 1; @@ -3945,12 +4133,22 @@ for (my $i = 0, my $repeat = 1; $i <= $opt{"NUM_TESTS"}; $i += $repeat) { } } +sub option_defined { + my ($option) = @_; + + if (defined($opt{$option}) && $opt{$option} !~ /^\s*$/) { + return 1; + } + + return 0; +} + sub __set_test_option { my ($name, $i) = @_; my $option = "$name\[$i\]"; - if (defined($opt{$option})) { + if (option_defined($option)) { return $opt{$option}; } @@ -3958,13 +4156,13 @@ sub __set_test_option { if ($i >= $test && $i < $test + $repeat_tests{$test}) { $option = "$name\[$test\]"; - if (defined($opt{$option})) { + if (option_defined($option)) { return $opt{$option}; } } } - if (defined($opt{$name})) { + if (option_defined($name)) { return $opt{$name}; } @@ -3991,6 +4189,11 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) { $iteration = $i; + $build_time = 0; + $install_time = 0; + $reboot_time = 0; + $test_time = 0; + undef %force_config; my $makecmd = set_test_option("MAKE_CMD", $i); @@ -4077,8 +4280,14 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) { my $installme = ""; $installme = " no_install" if ($no_install); + my $name = ""; + + if (defined($test_name)) { + $name = " ($test_name)"; + } + doprint "\n\n"; - doprint "RUNNING TEST $i of $opt{NUM_TESTS} with option $test_type $run_type$installme\n\n"; + doprint "RUNNING TEST $i of $opt{NUM_TESTS}$name with option $test_type $run_type$installme\n\n"; if (defined($pre_test)) { run_command $pre_test; @@ -4142,15 +4351,20 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) { if ($test_type ne "build") { my $failed = 0; - start_monitor_and_boot or $failed = 1; + start_monitor_and_install or $failed = 1; if (!$failed && $test_type ne "boot" && defined($run_test)) { do_run_test or $failed = 1; } end_monitor; - next if ($failed); + if ($failed) { + print_times; + next; + } } + print_times; + success $i; } diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 45f145c6f843..95abddcd7839 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,24 +1,36 @@ TARGETS = breakpoints TARGETS += cpu-hotplug TARGETS += efivarfs +TARGETS += exec +TARGETS += firmware +TARGETS += ftrace TARGETS += kcmp TARGETS += memfd TARGETS += memory-hotplug -TARGETS += mqueue TARGETS += mount +TARGETS += mqueue TARGETS += net +TARGETS += powerpc TARGETS += ptrace +TARGETS += size +TARGETS += sysctl TARGETS += timers -TARGETS += vm -TARGETS += powerpc TARGETS += user -TARGETS += sysctl -TARGETS += firmware -TARGETS += ftrace +TARGETS += vm +TARGETS += x86 +#Please keep the TARGETS list alphabetically sorted TARGETS_HOTPLUG = cpu-hotplug TARGETS_HOTPLUG += memory-hotplug +# Clear LDFLAGS and MAKEFLAGS if called from main +# Makefile to avoid test build failures when test +# Makefile doesn't have explicit build rules. +ifeq (1,$(MAKELEVEL)) +undefine LDFLAGS +override MAKEFLAGS = +endif + all: for TARGET in $(TARGETS); do \ make -C $$TARGET; \ @@ -44,7 +56,40 @@ clean_hotplug: make -C $$TARGET clean; \ done; +INSTALL_PATH ?= install +INSTALL_PATH := $(abspath $(INSTALL_PATH)) +ALL_SCRIPT := $(INSTALL_PATH)/run_kselftest.sh + +install: +ifdef INSTALL_PATH + @# Ask all targets to install their files + mkdir -p $(INSTALL_PATH) + for TARGET in $(TARGETS); do \ + mkdir -p $(INSTALL_PATH)/$$TARGET ; \ + make -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ + done; + + @# Ask all targets to emit their test scripts + echo "#!/bin/bash" > $(ALL_SCRIPT) + echo "cd \$$(dirname \$$0)" >> $(ALL_SCRIPT) + echo "ROOT=\$$PWD" >> $(ALL_SCRIPT) + + for TARGET in $(TARGETS); do \ + echo "echo ; echo Running tests in $$TARGET" >> $(ALL_SCRIPT); \ + echo "echo ========================================" >> $(ALL_SCRIPT); \ + echo "cd $$TARGET" >> $(ALL_SCRIPT); \ + make -s --no-print-directory -C $$TARGET emit_tests >> $(ALL_SCRIPT); \ + echo "cd \$$ROOT" >> $(ALL_SCRIPT); \ + done; + + chmod u+x $(ALL_SCRIPT) +else + $(error Error: set INSTALL_PATH to use install) +endif + clean: for TARGET in $(TARGETS); do \ make -C $$TARGET clean; \ done; + +.PHONY: install diff --git a/tools/testing/selftests/README.txt b/tools/testing/selftests/README.txt deleted file mode 100644 index 2660d5ff9179..000000000000 --- a/tools/testing/selftests/README.txt +++ /dev/null @@ -1,61 +0,0 @@ -Linux Kernel Selftests - -The kernel contains a set of "self tests" under the tools/testing/selftests/ -directory. These are intended to be small unit tests to exercise individual -code paths in the kernel. - -On some systems, hot-plug tests could hang forever waiting for cpu and -memory to be ready to be offlined. A special hot-plug target is created -to run full range of hot-plug tests. In default mode, hot-plug tests run -in safe mode with a limited scope. In limited mode, cpu-hotplug test is -run on a single cpu as opposed to all hotplug capable cpus, and memory -hotplug test is run on 2% of hotplug capable memory instead of 10%. - -Running the selftests (hotplug tests are run in limited mode) -============================================================= - -To build the tests: - - $ make -C tools/testing/selftests - - -To run the tests: - - $ make -C tools/testing/selftests run_tests - -- note that some tests will require root privileges. - -To run only tests targeted for a single subsystem: (including -hotplug targets in limited mode) - - $ make -C tools/testing/selftests TARGETS=cpu-hotplug run_tests - -See the top-level tools/testing/selftests/Makefile for the list of all possible -targets. - -Running the full range hotplug selftests -======================================== - -To build the tests: - - $ make -C tools/testing/selftests hotplug - -To run the tests: - - $ make -C tools/testing/selftests run_hotplug - -- note that some tests will require root privileges. - -Contributing new tests -====================== - -In general, the rules for for selftests are - - * Do as much as you can if you're not root; - - * Don't take too long; - - * Don't break the build on any architecture, and - - * Don't cause the top-level "make run_tests" to fail if your feature is - unconfigured. diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile index e18b42b254af..182235640209 100644 --- a/tools/testing/selftests/breakpoints/Makefile +++ b/tools/testing/selftests/breakpoints/Makefile @@ -16,8 +16,9 @@ else echo "Not an x86 target, can't build breakpoints selftests" endif -run_tests: - @./breakpoint_test || echo "breakpoints selftests: [FAIL]" +TEST_PROGS := breakpoint_test + +include ../lib.mk clean: rm -fr breakpoint_test diff --git a/tools/testing/selftests/breakpoints/breakpoint_test.c b/tools/testing/selftests/breakpoints/breakpoint_test.c index a0743f3b2b57..120895ab5505 100644 --- a/tools/testing/selftests/breakpoints/breakpoint_test.c +++ b/tools/testing/selftests/breakpoints/breakpoint_test.c @@ -17,6 +17,8 @@ #include <sys/types.h> #include <sys/wait.h> +#include "../kselftest.h" + /* Breakpoint access modes */ enum { @@ -42,7 +44,7 @@ static void set_breakpoint_addr(void *addr, int n) offsetof(struct user, u_debugreg[n]), addr); if (ret) { perror("Can't set breakpoint addr\n"); - exit(-1); + ksft_exit_fail(); } } @@ -105,7 +107,7 @@ static void toggle_breakpoint(int n, int type, int len, offsetof(struct user, u_debugreg[7]), dr7); if (ret) { perror("Can't set dr7"); - exit(-1); + ksft_exit_fail(); } } @@ -275,7 +277,7 @@ static void check_success(const char *msg) msg2 = "Ok"; if (ptrace(PTRACE_POKEDATA, child_pid, &trapped, 1)) { perror("Can't poke\n"); - exit(-1); + ksft_exit_fail(); } } @@ -390,5 +392,5 @@ int main(int argc, char **argv) wait(NULL); - return 0; + return ksft_exit_pass(); } diff --git a/tools/testing/selftests/cpu-hotplug/Makefile b/tools/testing/selftests/cpu-hotplug/Makefile index e9c28d8dc84b..fe1f99101c5d 100644 --- a/tools/testing/selftests/cpu-hotplug/Makefile +++ b/tools/testing/selftests/cpu-hotplug/Makefile @@ -1,9 +1,10 @@ all: -run_tests: - @/bin/bash ./on-off-test.sh || echo "cpu-hotplug selftests: [FAIL]" +TEST_PROGS := cpu-on-off-test.sh + +include ../lib.mk run_full_test: - @/bin/bash ./on-off-test.sh -a || echo "cpu-hotplug selftests: [FAIL]" + @/bin/bash ./cpu-on-off-test.sh -a || echo "cpu-hotplug selftests: [FAIL]" clean: diff --git a/tools/testing/selftests/cpu-hotplug/on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh index 98b1d6565f2c..98b1d6565f2c 100644..100755 --- a/tools/testing/selftests/cpu-hotplug/on-off-test.sh +++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh diff --git a/tools/testing/selftests/efivarfs/Makefile b/tools/testing/selftests/efivarfs/Makefile index 29e8c6bc81b0..736c3ddfc787 100644 --- a/tools/testing/selftests/efivarfs/Makefile +++ b/tools/testing/selftests/efivarfs/Makefile @@ -1,12 +1,13 @@ -CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall test_objs = open-unlink create-read all: $(test_objs) -run_tests: all - @/bin/bash ./efivarfs.sh || echo "efivarfs selftests: [FAIL]" +TEST_PROGS := efivarfs.sh +TEST_FILES := $(test_objs) + +include ../lib.mk clean: rm -f $(test_objs) diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh index 77edcdcc016b..77edcdcc016b 100644..100755 --- a/tools/testing/selftests/efivarfs/efivarfs.sh +++ b/tools/testing/selftests/efivarfs/efivarfs.sh diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore new file mode 100644 index 000000000000..64073e050c6a --- /dev/null +++ b/tools/testing/selftests/exec/.gitignore @@ -0,0 +1,9 @@ +subdir* +script* +execveat +execveat.symlink +execveat.moved +execveat.path.ephemeral +execveat.ephemeral +execveat.denatured +xxxxxxxx*
\ No newline at end of file diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile new file mode 100644 index 000000000000..4edb7d0da29b --- /dev/null +++ b/tools/testing/selftests/exec/Makefile @@ -0,0 +1,28 @@ +CFLAGS = -Wall +BINARIES = execveat +DEPS = execveat.symlink execveat.denatured script subdir +all: $(BINARIES) $(DEPS) + +subdir: + mkdir -p $@ +script: + echo '#!/bin/sh' > $@ + echo 'exit $$*' >> $@ + chmod +x $@ +execveat.symlink: execveat + ln -s -f $< $@ +execveat.denatured: execveat + cp $< $@ + chmod -x $@ +%: %.c + $(CC) $(CFLAGS) -o $@ $^ + +TEST_PROGS := execveat +TEST_FILES := $(DEPS) + +include ../lib.mk + +override EMIT_TESTS := echo "mkdir -p subdir; (./execveat && echo \"selftests: execveat [PASS]\") || echo \"selftests: execveat [FAIL]\"" + +clean: + rm -rf $(BINARIES) $(DEPS) subdir.moved execveat.moved xxxxx* diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c new file mode 100644 index 000000000000..8d5d1d2ee7c1 --- /dev/null +++ b/tools/testing/selftests/exec/execveat.c @@ -0,0 +1,412 @@ +/* + * Copyright (c) 2014 Google, Inc. + * + * Licensed under the terms of the GNU GPL License version 2 + * + * Selftests for execveat(2). + */ + +#define _GNU_SOURCE /* to get O_PATH, AT_EMPTY_PATH */ +#include <sys/sendfile.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +static char longpath[2 * PATH_MAX] = ""; +static char *envp[] = { "IN_TEST=yes", NULL, NULL }; +static char *argv[] = { "execveat", "99", NULL }; + +static int execveat_(int fd, const char *path, char **argv, char **envp, + int flags) +{ +#ifdef __NR_execveat + return syscall(__NR_execveat, fd, path, argv, envp, flags); +#else + errno = ENOSYS; + return -1; +#endif +} + +#define check_execveat_fail(fd, path, flags, errno) \ + _check_execveat_fail(fd, path, flags, errno, #errno) +static int _check_execveat_fail(int fd, const char *path, int flags, + int expected_errno, const char *errno_str) +{ + int rc; + + errno = 0; + printf("Check failure of execveat(%d, '%s', %d) with %s... ", + fd, path?:"(null)", flags, errno_str); + rc = execveat_(fd, path, argv, envp, flags); + + if (rc > 0) { + printf("[FAIL] (unexpected success from execveat(2))\n"); + return 1; + } + if (errno != expected_errno) { + printf("[FAIL] (expected errno %d (%s) not %d (%s)\n", + expected_errno, strerror(expected_errno), + errno, strerror(errno)); + return 1; + } + printf("[OK]\n"); + return 0; +} + +static int check_execveat_invoked_rc(int fd, const char *path, int flags, + int expected_rc, int expected_rc2) +{ + int status; + int rc; + pid_t child; + int pathlen = path ? strlen(path) : 0; + + if (pathlen > 40) + printf("Check success of execveat(%d, '%.20s...%s', %d)... ", + fd, path, (path + pathlen - 20), flags); + else + printf("Check success of execveat(%d, '%s', %d)... ", + fd, path?:"(null)", flags); + child = fork(); + if (child < 0) { + printf("[FAIL] (fork() failed)\n"); + return 1; + } + if (child == 0) { + /* Child: do execveat(). */ + rc = execveat_(fd, path, argv, envp, flags); + printf("[FAIL]: execveat() failed, rc=%d errno=%d (%s)\n", + rc, errno, strerror(errno)); + exit(1); /* should not reach here */ + } + /* Parent: wait for & check child's exit status. */ + rc = waitpid(child, &status, 0); + if (rc != child) { + printf("[FAIL] (waitpid(%d,...) returned %d)\n", child, rc); + return 1; + } + if (!WIFEXITED(status)) { + printf("[FAIL] (child %d did not exit cleanly, status=%08x)\n", + child, status); + return 1; + } + if ((WEXITSTATUS(status) != expected_rc) && + (WEXITSTATUS(status) != expected_rc2)) { + printf("[FAIL] (child %d exited with %d not %d nor %d)\n", + child, WEXITSTATUS(status), expected_rc, expected_rc2); + return 1; + } + printf("[OK]\n"); + return 0; +} + +static int check_execveat(int fd, const char *path, int flags) +{ + return check_execveat_invoked_rc(fd, path, flags, 99, 99); +} + +static char *concat(const char *left, const char *right) +{ + char *result = malloc(strlen(left) + strlen(right) + 1); + + strcpy(result, left); + strcat(result, right); + return result; +} + +static int open_or_die(const char *filename, int flags) +{ + int fd = open(filename, flags); + + if (fd < 0) { + printf("Failed to open '%s'; " + "check prerequisites are available\n", filename); + exit(1); + } + return fd; +} + +static void exe_cp(const char *src, const char *dest) +{ + int in_fd = open_or_die(src, O_RDONLY); + int out_fd = open(dest, O_RDWR|O_CREAT|O_TRUNC, 0755); + struct stat info; + + fstat(in_fd, &info); + sendfile(out_fd, in_fd, NULL, info.st_size); + close(in_fd); + close(out_fd); +} + +#define XX_DIR_LEN 200 +static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script) +{ + int fail = 0; + int ii, count, len; + char longname[XX_DIR_LEN + 1]; + int fd; + + if (*longpath == '\0') { + /* Create a filename close to PATH_MAX in length */ + memset(longname, 'x', XX_DIR_LEN - 1); + longname[XX_DIR_LEN - 1] = '/'; + longname[XX_DIR_LEN] = '\0'; + count = (PATH_MAX - 3) / XX_DIR_LEN; + for (ii = 0; ii < count; ii++) { + strcat(longpath, longname); + mkdir(longpath, 0755); + } + len = (PATH_MAX - 3) - (count * XX_DIR_LEN); + if (len <= 0) + len = 1; + memset(longname, 'y', len); + longname[len] = '\0'; + strcat(longpath, longname); + } + exe_cp(src, longpath); + + /* + * Execute as a pre-opened file descriptor, which works whether this is + * a script or not (because the interpreter sees a filename like + * "/dev/fd/20"). + */ + fd = open(longpath, O_RDONLY); + if (fd > 0) { + printf("Invoke copy of '%s' via filename of length %zu:\n", + src, strlen(longpath)); + fail += check_execveat(fd, "", AT_EMPTY_PATH); + } else { + printf("Failed to open length %zu filename, errno=%d (%s)\n", + strlen(longpath), errno, strerror(errno)); + fail++; + } + + /* + * Execute as a long pathname relative to ".". If this is a script, + * the interpreter will launch but fail to open the script because its + * name ("/dev/fd/5/xxx....") is bigger than PATH_MAX. + * + * The failure code is usually 127 (POSIX: "If a command is not found, + * the exit status shall be 127."), but some systems give 126 (POSIX: + * "If the command name is found, but it is not an executable utility, + * the exit status shall be 126."), so allow either. + */ + if (is_script) + fail += check_execveat_invoked_rc(dot_dfd, longpath, 0, + 127, 126); + else + fail += check_execveat(dot_dfd, longpath, 0); + + return fail; +} + +static int run_tests(void) +{ + int fail = 0; + char *fullname = realpath("execveat", NULL); + char *fullname_script = realpath("script", NULL); + char *fullname_symlink = concat(fullname, ".symlink"); + int subdir_dfd = open_or_die("subdir", O_DIRECTORY|O_RDONLY); + int subdir_dfd_ephemeral = open_or_die("subdir.ephemeral", + O_DIRECTORY|O_RDONLY); + int dot_dfd = open_or_die(".", O_DIRECTORY|O_RDONLY); + int dot_dfd_path = open_or_die(".", O_DIRECTORY|O_RDONLY|O_PATH); + int dot_dfd_cloexec = open_or_die(".", O_DIRECTORY|O_RDONLY|O_CLOEXEC); + int fd = open_or_die("execveat", O_RDONLY); + int fd_path = open_or_die("execveat", O_RDONLY|O_PATH); + int fd_symlink = open_or_die("execveat.symlink", O_RDONLY); + int fd_denatured = open_or_die("execveat.denatured", O_RDONLY); + int fd_denatured_path = open_or_die("execveat.denatured", + O_RDONLY|O_PATH); + int fd_script = open_or_die("script", O_RDONLY); + int fd_ephemeral = open_or_die("execveat.ephemeral", O_RDONLY); + int fd_ephemeral_path = open_or_die("execveat.path.ephemeral", + O_RDONLY|O_PATH); + int fd_script_ephemeral = open_or_die("script.ephemeral", O_RDONLY); + int fd_cloexec = open_or_die("execveat", O_RDONLY|O_CLOEXEC); + int fd_script_cloexec = open_or_die("script", O_RDONLY|O_CLOEXEC); + + /* Check if we have execveat at all, and bail early if not */ + errno = 0; + execveat_(-1, NULL, NULL, NULL, 0); + if (errno == ENOSYS) { + printf("[FAIL] ENOSYS calling execveat - no kernel support?\n"); + return 1; + } + + /* Change file position to confirm it doesn't affect anything */ + lseek(fd, 10, SEEK_SET); + + /* Normal executable file: */ + /* dfd + path */ + fail += check_execveat(subdir_dfd, "../execveat", 0); + fail += check_execveat(dot_dfd, "execveat", 0); + fail += check_execveat(dot_dfd_path, "execveat", 0); + /* absolute path */ + fail += check_execveat(AT_FDCWD, fullname, 0); + /* absolute path with nonsense dfd */ + fail += check_execveat(99, fullname, 0); + /* fd + no path */ + fail += check_execveat(fd, "", AT_EMPTY_PATH); + /* O_CLOEXEC fd + no path */ + fail += check_execveat(fd_cloexec, "", AT_EMPTY_PATH); + /* O_PATH fd */ + fail += check_execveat(fd_path, "", AT_EMPTY_PATH); + + /* Mess with executable file that's already open: */ + /* fd + no path to a file that's been renamed */ + rename("execveat.ephemeral", "execveat.moved"); + fail += check_execveat(fd_ephemeral, "", AT_EMPTY_PATH); + /* fd + no path to a file that's been deleted */ + unlink("execveat.moved"); /* remove the file now fd open */ + fail += check_execveat(fd_ephemeral, "", AT_EMPTY_PATH); + + /* Mess with executable file that's already open with O_PATH */ + /* fd + no path to a file that's been deleted */ + unlink("execveat.path.ephemeral"); + fail += check_execveat(fd_ephemeral_path, "", AT_EMPTY_PATH); + + /* Invalid argument failures */ + fail += check_execveat_fail(fd, "", 0, ENOENT); + fail += check_execveat_fail(fd, NULL, AT_EMPTY_PATH, EFAULT); + + /* Symlink to executable file: */ + /* dfd + path */ + fail += check_execveat(dot_dfd, "execveat.symlink", 0); + fail += check_execveat(dot_dfd_path, "execveat.symlink", 0); + /* absolute path */ + fail += check_execveat(AT_FDCWD, fullname_symlink, 0); + /* fd + no path, even with AT_SYMLINK_NOFOLLOW (already followed) */ + fail += check_execveat(fd_symlink, "", AT_EMPTY_PATH); + fail += check_execveat(fd_symlink, "", + AT_EMPTY_PATH|AT_SYMLINK_NOFOLLOW); + + /* Symlink fails when AT_SYMLINK_NOFOLLOW set: */ + /* dfd + path */ + fail += check_execveat_fail(dot_dfd, "execveat.symlink", + AT_SYMLINK_NOFOLLOW, ELOOP); + fail += check_execveat_fail(dot_dfd_path, "execveat.symlink", + AT_SYMLINK_NOFOLLOW, ELOOP); + /* absolute path */ + fail += check_execveat_fail(AT_FDCWD, fullname_symlink, + AT_SYMLINK_NOFOLLOW, ELOOP); + + /* Shell script wrapping executable file: */ + /* dfd + path */ + fail += check_execveat(subdir_dfd, "../script", 0); + fail += check_execveat(dot_dfd, "script", 0); + fail += check_execveat(dot_dfd_path, "script", 0); + /* absolute path */ + fail += check_execveat(AT_FDCWD, fullname_script, 0); + /* fd + no path */ + fail += check_execveat(fd_script, "", AT_EMPTY_PATH); + fail += check_execveat(fd_script, "", + AT_EMPTY_PATH|AT_SYMLINK_NOFOLLOW); + /* O_CLOEXEC fd fails for a script (as script file inaccessible) */ + fail += check_execveat_fail(fd_script_cloexec, "", AT_EMPTY_PATH, + ENOENT); + fail += check_execveat_fail(dot_dfd_cloexec, "script", 0, ENOENT); + + /* Mess with script file that's already open: */ + /* fd + no path to a file that's been renamed */ + rename("script.ephemeral", "script.moved"); + fail += check_execveat(fd_script_ephemeral, "", AT_EMPTY_PATH); + /* fd + no path to a file that's been deleted */ + unlink("script.moved"); /* remove the file while fd open */ + fail += check_execveat(fd_script_ephemeral, "", AT_EMPTY_PATH); + + /* Rename a subdirectory in the path: */ + rename("subdir.ephemeral", "subdir.moved"); + fail += check_execveat(subdir_dfd_ephemeral, "../script", 0); + fail += check_execveat(subdir_dfd_ephemeral, "script", 0); + /* Remove the subdir and its contents */ + unlink("subdir.moved/script"); + unlink("subdir.moved"); + /* Shell loads via deleted subdir OK because name starts with .. */ + fail += check_execveat(subdir_dfd_ephemeral, "../script", 0); + fail += check_execveat_fail(subdir_dfd_ephemeral, "script", 0, ENOENT); + + /* Flag values other than AT_SYMLINK_NOFOLLOW => EINVAL */ + fail += check_execveat_fail(dot_dfd, "execveat", 0xFFFF, EINVAL); + /* Invalid path => ENOENT */ + fail += check_execveat_fail(dot_dfd, "no-such-file", 0, ENOENT); + fail += check_execveat_fail(dot_dfd_path, "no-such-file", 0, ENOENT); + fail += check_execveat_fail(AT_FDCWD, "no-such-file", 0, ENOENT); + /* Attempt to execute directory => EACCES */ + fail += check_execveat_fail(dot_dfd, "", AT_EMPTY_PATH, EACCES); + /* Attempt to execute non-executable => EACCES */ + fail += check_execveat_fail(dot_dfd, "Makefile", 0, EACCES); + fail += check_execveat_fail(fd_denatured, "", AT_EMPTY_PATH, EACCES); + fail += check_execveat_fail(fd_denatured_path, "", AT_EMPTY_PATH, + EACCES); + /* Attempt to execute nonsense FD => EBADF */ + fail += check_execveat_fail(99, "", AT_EMPTY_PATH, EBADF); + fail += check_execveat_fail(99, "execveat", 0, EBADF); + /* Attempt to execute relative to non-directory => ENOTDIR */ + fail += check_execveat_fail(fd, "execveat", 0, ENOTDIR); + + fail += check_execveat_pathmax(dot_dfd, "execveat", 0); + fail += check_execveat_pathmax(dot_dfd, "script", 1); + return fail; +} + +static void prerequisites(void) +{ + int fd; + const char *script = "#!/bin/sh\nexit $*\n"; + + /* Create ephemeral copies of files */ + exe_cp("execveat", "execveat.ephemeral"); + exe_cp("execveat", "execveat.path.ephemeral"); + exe_cp("script", "script.ephemeral"); + mkdir("subdir.ephemeral", 0755); + + fd = open("subdir.ephemeral/script", O_RDWR|O_CREAT|O_TRUNC, 0755); + write(fd, script, strlen(script)); + close(fd); +} + +int main(int argc, char **argv) +{ + int ii; + int rc; + const char *verbose = getenv("VERBOSE"); + + if (argc >= 2) { + /* If we are invoked with an argument, don't run tests. */ + const char *in_test = getenv("IN_TEST"); + + if (verbose) { + printf(" invoked with:"); + for (ii = 0; ii < argc; ii++) + printf(" [%d]='%s'", ii, argv[ii]); + printf("\n"); + } + + /* Check expected environment transferred. */ + if (!in_test || strcmp(in_test, "yes") != 0) { + printf("[FAIL] (no IN_TEST=yes in env)\n"); + return 1; + } + + /* Use the final argument as an exit code. */ + rc = atoi(argv[argc - 1]); + fflush(stdout); + } else { + prerequisites(); + if (verbose) + envp[1] = "VERBOSE=1"; + rc = run_tests(); + if (rc > 0) + printf("%d tests failed\n", rc); + } + return rc; +} diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile index e23cce0bbc3a..9bf82234855b 100644 --- a/tools/testing/selftests/firmware/Makefile +++ b/tools/testing/selftests/firmware/Makefile @@ -3,25 +3,9 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests" all: -fw_filesystem: - @if /bin/sh ./fw_filesystem.sh ; then \ - echo "fw_filesystem: ok"; \ - else \ - echo "fw_filesystem: [FAIL]"; \ - exit 1; \ - fi +TEST_PROGS := fw_filesystem.sh fw_userhelper.sh -fw_userhelper: - @if /bin/sh ./fw_userhelper.sh ; then \ - echo "fw_userhelper: ok"; \ - else \ - echo "fw_userhelper: [FAIL]"; \ - exit 1; \ - fi - -run_tests: all fw_filesystem fw_userhelper +include ../lib.mk # Nothing to clean up. clean: - -.PHONY: all clean run_tests fw_filesystem fw_userhelper diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh index 3fc6c10c2479..3fc6c10c2479 100644..100755 --- a/tools/testing/selftests/firmware/fw_filesystem.sh +++ b/tools/testing/selftests/firmware/fw_filesystem.sh diff --git a/tools/testing/selftests/firmware/fw_userhelper.sh b/tools/testing/selftests/firmware/fw_userhelper.sh index 6efbade12139..6efbade12139 100644..100755 --- a/tools/testing/selftests/firmware/fw_userhelper.sh +++ b/tools/testing/selftests/firmware/fw_userhelper.sh diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index 76cc9f156267..346720639d1d 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,8 @@ all: -run_tests: - @/bin/sh ./ftracetest || echo "ftrace selftests: [FAIL]" +TEST_PROGS := ftracetest + +include ../lib.mk clean: rm -rf logs/* diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 515247601df4..da48812ab95e 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -13,6 +13,7 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" +echo " -v|--verbose Show all stdout messages in testcases" echo " -d|--debug Debug mode (trace all shell commands)" exit $1 } @@ -37,7 +38,7 @@ abspath() { } find_testcases() { #directory - echo `find $1 -name \*.tc` + echo `find $1 -name \*.tc | sort` } parse_opts() { # opts @@ -53,6 +54,10 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; + --verbose|-v) + VERBOSE=1 + shift 1 + ;; --debug|-d) DEBUG=1 shift 1 @@ -90,6 +95,7 @@ TEST_CASES=`find_testcases $TEST_DIR` LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ KEEP_LOG=0 DEBUG=0 +VERBOSE=0 # Parse command-line options parse_opts $* @@ -135,15 +141,12 @@ TOTAL_RESULT=0 CASENO=0 testcase() { # testfile CASENO=$((CASENO+1)) - prlog -n "[$CASENO]"`grep "^#[ \t]*description:" $1 | cut -f2 -d:` + desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:` + prlog -n "[$CASENO]$desc" } -eval_result() { # retval sigval - local retval=$2 - if [ $2 -eq 0 ]; then - test $1 -ne 0 && retval=$FAIL - fi - case $retval in +eval_result() { # sigval + case $1 in $PASS) prlog " [PASS]" PASSED_CASES="$PASSED_CASES $CASENO" @@ -187,6 +190,9 @@ SIG_RESULT= SIG_BASE=36 # Use realtime signals SIG_PID=$$ +SIG_FAIL=$((SIG_BASE + FAIL)) +trap 'SIG_RESULT=$FAIL' $SIG_FAIL + SIG_UNRESOLVED=$((SIG_BASE + UNRESOLVED)) exit_unresolved () { kill -s $SIG_UNRESOLVED $SIG_PID @@ -215,17 +221,25 @@ exit_xfail () { } trap 'SIG_RESULT=$XFAIL' $SIG_XFAIL +__run_test() { # testfile + # setup PID and PPID, $$ is not updated. + (cd $TRACING_DIR; read PID _ < /proc/self/stat ; set -e; set -x; . $1) + [ $? -ne 0 ] && kill -s $SIG_FAIL $SIG_PID +} + # Run one test case run_test() { # testfile local testname=`basename $1` - local testlog=`mktemp --tmpdir=$LOG_DIR ${testname}-XXXXXX.log` + local testlog=`mktemp $LOG_DIR/${testname}-log.XXXXXX` testcase $1 echo "execute: "$1 > $testlog SIG_RESULT=0 - # setup PID and PPID, $$ is not updated. - (cd $TRACING_DIR; read PID _ < /proc/self/stat ; - set -e; set -x; . $1) >> $testlog 2>&1 - eval_result $? $SIG_RESULT + if [ $VERBOSE -ne 0 ]; then + __run_test $1 2>> $testlog | tee -a $testlog + else + __run_test $1 >> $testlog 2>&1 + fi + eval_result $SIG_RESULT if [ $? -eq 0 ]; then # Remove test log if the test was done as it was expected. [ $KEEP_LOG -eq 0 ] && rm $testlog @@ -235,6 +249,9 @@ run_test() { # testfile fi } +# load in the helper functions +. $TEST_DIR/functions + # Main loop for t in $TEST_CASES; do run_test $t diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc new file mode 100644 index 000000000000..aa51f6c17359 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc @@ -0,0 +1,5 @@ +#!/bin/sh +# description: Basic event tracing check +test -f available_events -a -f set_event -a -d events +# check scheduler events are available +grep -q sched available_events && exit 0 || exit $FAIL diff --git a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc new file mode 100644 index 000000000000..87eb9d6dd4ca --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc @@ -0,0 +1,60 @@ +#!/bin/sh +# description: event tracing - enable/disable with event level files + +do_reset() { + echo > set_event + clear_trace +} + +fail() { #msg + do_reset + echo $1 + exit $FAIL +} + +yield() { + ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1 +} + +if [ ! -f set_event -o ! -d events/sched ]; then + echo "event tracing is not supported" + exit_unsupported +fi + +reset_tracer +do_reset + +echo 'sched:sched_switch' > set_event + +yield + +count=`cat trace | grep sched_switch | wc -l` +if [ $count -eq 0 ]; then + fail "sched_switch events are not recorded" +fi + +do_reset + +echo 1 > events/sched/sched_switch/enable + +yield + +count=`cat trace | grep sched_switch | wc -l` +if [ $count -eq 0 ]; then + fail "sched_switch events are not recorded" +fi + +do_reset + +echo 0 > events/sched/sched_switch/enable + +yield + +count=`cat trace | grep sched_switch | wc -l` +if [ $count -ne 0 ]; then + fail "sched_switch events should not be recorded" +fi + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc new file mode 100644 index 000000000000..ced27ef0638f --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -0,0 +1,60 @@ +#!/bin/sh +# description: event tracing - enable/disable with subsystem level files + +do_reset() { + echo > set_event + clear_trace +} + +fail() { #msg + do_reset + echo $1 + exit $FAIL +} + +yield() { + ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1 +} + +if [ ! -f set_event -o ! -d events/sched ]; then + echo "event tracing is not supported" + exit_unsupported +fi + +reset_tracer +do_reset + +echo 'sched:*' > set_event + +yield + +count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +if [ $count -lt 3 ]; then + fail "at least fork, exec and exit events should be recorded" +fi + +do_reset + +echo 1 > events/sched/enable + +yield + +count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +if [ $count -lt 3 ]; then + fail "at least fork, exec and exit events should be recorded" +fi + +do_reset + +echo 0 > events/sched/enable + +yield + +count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +if [ $count -ne 0 ]; then + fail "any of scheduler events should not be recorded" +fi + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc new file mode 100644 index 000000000000..0bb5df3c00d4 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc @@ -0,0 +1,60 @@ +#!/bin/sh +# description: event tracing - enable/disable with top level files + +do_reset() { + echo > set_event + clear_trace +} + +fail() { #msg + do_reset + echo $1 + exit $FAIL +} + +yield() { + ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1 +} + +if [ ! -f available_events -o ! -f set_event -o ! -d events ]; then + echo "event tracing is not supported" + exit_unsupported +fi + +reset_tracer +do_reset + +echo '*:*' > set_event + +yield + +count=`cat trace | grep -v ^# | wc -l` +if [ $count -eq 0 ]; then + fail "none of events are recorded" +fi + +do_reset + +echo 1 > events/enable + +yield + +count=`cat trace | grep -v ^# | wc -l` +if [ $count -eq 0 ]; then + fail "none of events are recorded" +fi + +do_reset + +echo 0 > events/enable + +yield + +count=`cat trace | grep -v ^# | wc -l` +if [ $count -ne 0 ]; then + fail "any of events should not be recorded" +fi + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc new file mode 100644 index 000000000000..15c2dba06ea2 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc @@ -0,0 +1,91 @@ +#!/bin/sh +# description: ftrace - function graph filters with stack tracer + +# Make sure that function graph filtering works, and is not +# affected by other tracers enabled (like stack tracer) + +if ! grep -q function_graph available_tracers; then + echo "no function graph tracer configured" + exit_unsupported +fi + +if [ ! -f set_ftrace_filter ]; then + echo "set_ftrace_filter not found? Is dynamic ftrace not set?" + exit_unsupported +fi + +do_reset() { + reset_tracer + if [ -e /proc/sys/kernel/stack_tracer_enabled ]; then + echo 0 > /proc/sys/kernel/stack_tracer_enabled + fi + enable_tracing + clear_trace + echo > set_ftrace_filter +} + +fail() { # msg + do_reset + echo $1 + exit $FAIL +} + +disable_tracing +clear_trace; + +# filter something, schedule is always good +if ! echo "schedule" > set_ftrace_filter; then + # test for powerpc 64 + if ! echo ".schedule" > set_ftrace_filter; then + fail "can not enable schedule filter" + fi +fi + +echo function_graph > current_tracer + +if [ ! -f stack_trace ]; then + echo "Stack tracer not configured" + do_reset + exit_unsupported; +fi + +echo "Now testing with stack tracer" + +echo 1 > /proc/sys/kernel/stack_tracer_enabled + +disable_tracing +clear_trace +enable_tracing +sleep 1 + +count=`cat trace | grep '()' | grep -v schedule | wc -l` + +if [ $count -ne 0 ]; then + fail "Graph filtering not working with stack tracer?" +fi + +# Make sure we did find something +count=`cat trace | grep 'schedule()' | wc -l` +if [ $count -eq 0 ]; then + fail "No schedule traces found?" +fi + +echo 0 > /proc/sys/kernel/stack_tracer_enabled +clear_trace +sleep 1 + + +count=`cat trace | grep '()' | grep -v schedule | wc -l` + +if [ $count -ne 0 ]; then + fail "Graph filtering not working after stack tracer disabled?" +fi + +count=`cat trace | grep 'schedule()' | wc -l` +if [ $count -eq 0 ]; then + fail "No schedule traces found?" +fi + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc new file mode 100644 index 000000000000..0ab2189613ef --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc @@ -0,0 +1,52 @@ +#!/bin/sh +# description: ftrace - function graph filters + +# Make sure that function graph filtering works + +if ! grep -q function_graph available_tracers; then + echo "no function graph tracer configured" + exit_unsupported +fi + +do_reset() { + reset_tracer + enable_tracing + clear_trace +} + +fail() { # msg + do_reset + echo $1 + exit $FAIL +} + +disable_tracing +clear_trace + +# filter something, schedule is always good +if ! echo "schedule" > set_ftrace_filter; then + # test for powerpc 64 + if ! echo ".schedule" > set_ftrace_filter; then + fail "can not enable schedule filter" + fi +fi + +echo function_graph > current_tracer +enable_tracing +sleep 1 +# search for functions (has "()" on the line), and make sure +# that only the schedule function was found +count=`cat trace | grep '()' | grep -v schedule | wc -l` +if [ $count -ne 0 ]; then + fail "Graph filtering not working by itself?" +fi + +# Make sure we did find something +count=`cat trace | grep 'schedule()' | wc -l` +if [ $count -eq 0 ]; then + fail "No schedule traces found?" +fi + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc new file mode 100644 index 000000000000..7808336d6f50 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc @@ -0,0 +1,80 @@ +#!/bin/sh +# description: ftrace - function profiler with function tracing + +# There was a bug after a rewrite of the ftrace infrastructure that +# caused the function_profiler not to be able to run with the function +# tracer, because the function_profiler used the function_graph tracer +# and it was assumed the two could not run simultaneously. +# +# There was another related bug where the solution to the first bug +# broke the way filtering of the function tracer worked. +# +# This test triggers those bugs on those kernels. +# +# We need function_graph and profiling to to run this test +if ! grep -q function_graph available_tracers; then + echo "no function graph tracer configured" + exit_unsupported; +fi + +if [ ! -f set_ftrace_filter ]; then + echo "set_ftrace_filter not found? Is dynamic ftrace not set?" + exit_unsupported +fi + +if [ ! -f function_profile_enabled ]; then + echo "function_profile_enabled not found, function profiling enabled?" + exit_unsupported +fi + +fail() { # mesg + reset_tracer + echo > set_ftrace_filter + echo $1 + exit $FAIL +} + +echo "Testing function tracer with profiler:" +echo "enable function tracer" +echo function > current_tracer +echo "enable profiler" +echo 1 > function_profile_enabled + +sleep 1 + +echo "Now filter on just schedule" +echo '*schedule' > set_ftrace_filter +clear_trace + +echo "Now disable function profiler" +echo 0 > function_profile_enabled + +sleep 1 + +# make sure only schedule functions exist + +echo "testing if only schedule is being traced" +if grep -v -e '^#' -e 'schedule' trace; then + fail "more than schedule was found" +fi + +echo "Make sure schedule was traced" +if ! grep -e 'schedule' trace > /dev/null; then + cat trace + fail "can not find schedule in trace" +fi + +echo > set_ftrace_filter +clear_trace + +sleep 1 + +echo "make sure something other than scheduler is being traced" +if ! grep -v -e '^#' -e 'schedule' trace > /dev/null; then + cat trace + fail "no other functions besides schedule was found" +fi + +reset_tracer + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions new file mode 100644 index 000000000000..5d8cd06d920f --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -0,0 +1,16 @@ + +clear_trace() { # reset trace output + echo > trace +} + +disable_tracing() { # stop trace recording + echo 0 > tracing_on +} + +enable_tracing() { # start trace recording + echo 1 > tracing_on +} + +reset_tracer() { # reset the current tracer + echo nop > current_tracer +} diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc index 1b8b665ab2b3..a5a426211129 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc @@ -9,3 +9,4 @@ echo p:myevent do_fork > kprobe_events grep myevent kprobe_events test -d events/kprobes/myevent echo > kprobe_events +clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc index b55c84003587..d8c7bb6581fe 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc @@ -11,3 +11,4 @@ echo 1 > events/kprobes/myevent/enable echo > kprobe_events && exit 1 # this must fail echo 0 > events/kprobes/myevent/enable echo > kprobe_events # this must succeed +clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc index a603d3f8db7b..c45ee2761354 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc @@ -12,5 +12,6 @@ echo 1 > events/kprobes/testprobe/enable ( echo "forked") echo 0 > events/kprobes/testprobe/enable echo "-:testprobe" >> kprobe_events +clear_trace test -d events/kprobes/testprobe && exit 1 || exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc new file mode 100644 index 000000000000..ab41d2b29841 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc @@ -0,0 +1,55 @@ +#!/bin/sh +# description: Kprobe dynamic event with function tracer + +[ -f kprobe_events ] || exit_unsupported # this is configurable +grep function available_tracers || exit_unsupported # this is configurable + +# prepare +echo nop > current_tracer +echo do_fork > set_ftrace_filter +echo 0 > events/enable +echo > kprobe_events +echo 'p:testprobe do_fork' > kprobe_events + +# kprobe on / ftrace off +echo 1 > events/kprobes/testprobe/enable +echo > trace +( echo "forked") +grep testprobe trace +! grep 'do_fork <-' trace + +# kprobe on / ftrace on +echo function > current_tracer +echo > trace +( echo "forked") +grep testprobe trace +grep 'do_fork <-' trace + +# kprobe off / ftrace on +echo 0 > events/kprobes/testprobe/enable +echo > trace +( echo "forked") +! grep testprobe trace +grep 'do_fork <-' trace + +# kprobe on / ftrace on +echo 1 > events/kprobes/testprobe/enable +echo function > current_tracer +echo > trace +( echo "forked") +grep testprobe trace +grep 'do_fork <-' trace + +# kprobe on / ftrace off +echo nop > current_tracer +echo > trace +( echo "forked") +grep testprobe trace +! grep 'do_fork <-' trace + +# cleanup +echo nop > current_tracer +echo > set_ftrace_filter +echo 0 > events/kprobes/testprobe/enable +echo > kprobe_events +echo > trace diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc index 283c29e7f7c4..31717985acc7 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc @@ -12,4 +12,5 @@ echo 1 > events/kprobes/testprobe2/enable ( echo "forked") echo 0 > events/kprobes/testprobe2/enable echo '-:testprobe2' >> kprobe_events +clear_trace test -d events/kprobes/testprobe2 && exit 1 || exit 0 diff --git a/tools/testing/selftests/gen_kselftest_tar.sh b/tools/testing/selftests/gen_kselftest_tar.sh new file mode 100755 index 000000000000..17d5bd0c0936 --- /dev/null +++ b/tools/testing/selftests/gen_kselftest_tar.sh @@ -0,0 +1,55 @@ +#!/bin/bash +# +# gen_kselftest_tar +# Generate kselftest tarball +# Author: Shuah Khan <shuahkh@osg.samsung.com> +# Copyright (C) 2015 Samsung Electronics Co., Ltd. + +# This software may be freely redistributed under the terms of the GNU +# General Public License (GPLv2). + +# main +main() +{ + if [ "$#" -eq 0 ]; then + echo "$0: Generating default compression gzip" + copts="cvzf" + ext=".tar.gz" + else + case "$1" in + tar) + copts="cvf" + ext=".tar" + ;; + targz) + copts="cvzf" + ext=".tar.gz" + ;; + tarbz2) + copts="cvjf" + ext=".tar.bz2" + ;; + tarxz) + copts="cvJf" + ext=".tar.xz" + ;; + *) + echo "Unknown tarball format $1" + exit 1 + ;; + esac + fi + + install_dir=./kselftest + +# Run install using INSTALL_KSFT_PATH override to generate install +# directory +./kselftest_install.sh +tar $copts kselftest${ext} $install_dir +echo "Kselftest archive kselftest${ext} created!" + +# clean up install directory +rm -rf kselftest +} + +main "$@" diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile index 74bbefdeaf4c..25d2e702c68a 100644 --- a/tools/testing/selftests/ipc/Makefile +++ b/tools/testing/selftests/ipc/Makefile @@ -12,14 +12,11 @@ endif CFLAGS += -I../../../../usr/include/ all: -ifeq ($(ARCH),x86) - gcc $(CFLAGS) msgque.c -o msgque_test -else - echo "Not an x86 target, can't build msgque selftest" -endif + $(CC) $(CFLAGS) msgque.c -o msgque_test + +TEST_PROGS := msgque_test -run_tests: all - ./msgque_test +include ../lib.mk clean: rm -fr ./msgque_test diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c index 552f0810bffb..1b2ce334bb3f 100644 --- a/tools/testing/selftests/ipc/msgque.c +++ b/tools/testing/selftests/ipc/msgque.c @@ -5,6 +5,8 @@ #include <linux/msg.h> #include <fcntl.h> +#include "../kselftest.h" + #define MAX_MSG_SIZE 32 struct msg1 { @@ -195,58 +197,58 @@ int main(int argc, char **argv) if (getuid() != 0) { printf("Please run the test as root - Exiting.\n"); - exit(1); + return ksft_exit_fail(); } msgque.key = ftok(argv[0], 822155650); if (msgque.key == -1) { - printf("Can't make key\n"); - return -errno; + printf("Can't make key: %d\n", -errno); + return ksft_exit_fail(); } msgque.msq_id = msgget(msgque.key, IPC_CREAT | IPC_EXCL | 0666); if (msgque.msq_id == -1) { err = -errno; - printf("Can't create queue\n"); + printf("Can't create queue: %d\n", err); goto err_out; } err = fill_msgque(&msgque); if (err) { - printf("Failed to fill queue\n"); + printf("Failed to fill queue: %d\n", err); goto err_destroy; } err = dump_queue(&msgque); if (err) { - printf("Failed to dump queue\n"); + printf("Failed to dump queue: %d\n", err); goto err_destroy; } err = check_and_destroy_queue(&msgque); if (err) { - printf("Failed to check and destroy queue\n"); + printf("Failed to check and destroy queue: %d\n", err); goto err_out; } err = restore_queue(&msgque); if (err) { - printf("Failed to restore queue\n"); + printf("Failed to restore queue: %d\n", err); goto err_destroy; } err = check_and_destroy_queue(&msgque); if (err) { - printf("Failed to test queue\n"); + printf("Failed to test queue: %d\n", err); goto err_out; } - return 0; + return ksft_exit_pass(); err_destroy: if (msgctl(msgque.msq_id, IPC_RMID, 0)) { printf("Failed to destroy queue: %d\n", -errno); - return -errno; + return ksft_exit_fail(); } err_out: - return err; + return ksft_exit_fail(); } diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile index 8aabd82db9e4..2ae7450a9a89 100644 --- a/tools/testing/selftests/kcmp/Makefile +++ b/tools/testing/selftests/kcmp/Makefile @@ -1,28 +1,10 @@ -uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/) -ifeq ($(ARCH),i386) - ARCH := x86 - CFLAGS := -DCONFIG_X86_32 -D__i386__ -endif -ifeq ($(ARCH),x86_64) - ARCH := x86 - CFLAGS := -DCONFIG_X86_64 -D__x86_64__ -endif - -CFLAGS += -I../../../../arch/x86/include/generated/ -CFLAGS += -I../../../../include/ CFLAGS += -I../../../../usr/include/ -CFLAGS += -I../../../../arch/x86/include/ -all: -ifeq ($(ARCH),x86) - gcc $(CFLAGS) kcmp_test.c -o kcmp_test -else - echo "Not an x86 target, can't build kcmp selftest" -endif +all: kcmp_test + +TEST_PROGS := kcmp_test -run_tests: all - @./kcmp_test || echo "kcmp_test: [FAIL]" +include ../lib.mk clean: $(RM) kcmp_test kcmp-test-file diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c index dbba4084869c..a5a4da856dfe 100644 --- a/tools/testing/selftests/kcmp/kcmp_test.c +++ b/tools/testing/selftests/kcmp/kcmp_test.c @@ -17,6 +17,8 @@ #include <sys/stat.h> #include <sys/wait.h> +#include "../kselftest.h" + static long sys_kcmp(int pid1, int pid2, int type, int fd1, int fd2) { return syscall(__NR_kcmp, pid1, pid2, type, fd1, fd2); @@ -34,13 +36,13 @@ int main(int argc, char **argv) if (fd1 < 0) { perror("Can't create file"); - exit(1); + ksft_exit_fail(); } pid2 = fork(); if (pid2 < 0) { perror("fork failed"); - exit(1); + ksft_exit_fail(); } if (!pid2) { @@ -50,7 +52,7 @@ int main(int argc, char **argv) fd2 = open(kpath, O_RDWR, 0644); if (fd2 < 0) { perror("Can't open file"); - exit(1); + ksft_exit_fail(); } /* An example of output and arguments */ @@ -74,23 +76,34 @@ int main(int argc, char **argv) if (ret) { printf("FAIL: 0 expected but %d returned (%s)\n", ret, strerror(errno)); + ksft_inc_fail_cnt(); ret = -1; - } else + } else { printf("PASS: 0 returned as expected\n"); + ksft_inc_pass_cnt(); + } /* Compare with self */ ret = sys_kcmp(pid1, pid1, KCMP_VM, 0, 0); if (ret) { printf("FAIL: 0 expected but %d returned (%s)\n", ret, strerror(errno)); + ksft_inc_fail_cnt(); ret = -1; - } else + } else { printf("PASS: 0 returned as expected\n"); + ksft_inc_pass_cnt(); + } + + ksft_print_cnts(); - exit(ret); + if (ret) + ksft_exit_fail(); + else + ksft_exit_pass(); } waitpid(pid2, &status, P_ALL); - return 0; + return ksft_exit_pass(); } diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h new file mode 100644 index 000000000000..572c8888167a --- /dev/null +++ b/tools/testing/selftests/kselftest.h @@ -0,0 +1,62 @@ +/* + * kselftest.h: kselftest framework return codes to include from + * selftests. + * + * Copyright (c) 2014 Shuah Khan <shuahkh@osg.samsung.com> + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * + * This file is released under the GPLv2. + */ +#ifndef __KSELFTEST_H +#define __KSELFTEST_H + +#include <stdlib.h> +#include <unistd.h> + +/* counters */ +struct ksft_count { + unsigned int ksft_pass; + unsigned int ksft_fail; + unsigned int ksft_xfail; + unsigned int ksft_xpass; + unsigned int ksft_xskip; +}; + +static struct ksft_count ksft_cnt; + +static inline void ksft_inc_pass_cnt(void) { ksft_cnt.ksft_pass++; } +static inline void ksft_inc_fail_cnt(void) { ksft_cnt.ksft_fail++; } +static inline void ksft_inc_xfail_cnt(void) { ksft_cnt.ksft_xfail++; } +static inline void ksft_inc_xpass_cnt(void) { ksft_cnt.ksft_xpass++; } +static inline void ksft_inc_xskip_cnt(void) { ksft_cnt.ksft_xskip++; } + +static inline void ksft_print_cnts(void) +{ + printf("Pass: %d Fail: %d Xfail: %d Xpass: %d, Xskip: %d\n", + ksft_cnt.ksft_pass, ksft_cnt.ksft_fail, + ksft_cnt.ksft_xfail, ksft_cnt.ksft_xpass, + ksft_cnt.ksft_xskip); +} + +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +static inline int ksft_exit_xfail(void) +{ + exit(2); +} +static inline int ksft_exit_xpass(void) +{ + exit(3); +} +static inline int ksft_exit_skip(void) +{ + exit(4); +} + +#endif /* __KSELFTEST_H */ diff --git a/tools/testing/selftests/kselftest_install.sh b/tools/testing/selftests/kselftest_install.sh new file mode 100755 index 000000000000..1555fbdb08da --- /dev/null +++ b/tools/testing/selftests/kselftest_install.sh @@ -0,0 +1,37 @@ +#!/bin/bash +# +# Kselftest Install +# Install kselftest tests +# Author: Shuah Khan <shuahkh@osg.samsung.com> +# Copyright (C) 2015 Samsung Electronics Co., Ltd. + +# This software may be freely redistributed under the terms of the GNU +# General Public License (GPLv2). + +install_loc=`pwd` + +main() +{ + if [ $(basename $install_loc) != "selftests" ]; then + echo "$0: Please run it in selftests directory ..." + exit 1; + fi + if [ "$#" -eq 0 ]; then + echo "$0: Installing in default location - $install_loc ..." + elif [ ! -d "$1" ]; then + echo "$0: $1 doesn't exist!!" + exit 1; + else + install_loc=$1 + echo "$0: Installing in specified location - $install_loc ..." + fi + + install_dir=$install_loc/kselftest + +# Create install directory + mkdir -p $install_dir +# Build tests + INSTALL_PATH=$install_dir make install +} + +main "$@" diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk new file mode 100644 index 000000000000..2194155ae62a --- /dev/null +++ b/tools/testing/selftests/lib.mk @@ -0,0 +1,35 @@ +# This mimics the top-level Makefile. We do it explicitly here so that this +# Makefile can operate with or without the kbuild infrastructure. +CC := $(CROSS_COMPILE)gcc + +define RUN_TESTS + @for TEST in $(TEST_PROGS); do \ + (./$$TEST && echo "selftests: $$TEST [PASS]") || echo "selftests: $$TEST [FAIL]"; \ + done; +endef + +run_tests: all + $(RUN_TESTS) + +define INSTALL_RULE + mkdir -p $(INSTALL_PATH) + install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) +endef + +install: all +ifdef INSTALL_PATH + $(INSTALL_RULE) +else + $(error Error: set INSTALL_PATH to use install) +endif + +define EMIT_TESTS + @for TEST in $(TEST_PROGS); do \ + echo "(./$$TEST && echo \"selftests: $$TEST [PASS]\") || echo \"selftests: $$TEST [FAIL]\""; \ + done; +endef + +emit_tests: + $(EMIT_TESTS) + +.PHONY: run_tests all clean install emit_tests diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index b80cd10d53ba..3e7eb7972511 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -1,17 +1,19 @@ +CC = $(CROSS_COMPILE)gcc CFLAGS += -D_FILE_OFFSET_BITS=64 CFLAGS += -I../../../../include/uapi/ CFLAGS += -I../../../../include/ +CFLAGS += -I../../../../usr/include/ all: - gcc $(CFLAGS) memfd_test.c -o memfd_test + $(CC) $(CFLAGS) memfd_test.c -o memfd_test -run_tests: all - gcc $(CFLAGS) memfd_test.c -o memfd_test - @./memfd_test || echo "memfd_test: [FAIL]" +TEST_PROGS := memfd_test + +include ../lib.mk build_fuse: - gcc $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt - gcc $(CFLAGS) fuse_test.c -o fuse_test + $(CC) $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt + $(CC) $(CFLAGS) fuse_test.c -o fuse_test run_fuse: build_fuse @./run_fuse_test.sh || echo "fuse_test: [FAIL]" diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile index d46b8d489cd2..afb2624c7048 100644 --- a/tools/testing/selftests/memory-hotplug/Makefile +++ b/tools/testing/selftests/memory-hotplug/Makefile @@ -1,9 +1,12 @@ all: -run_tests: - @/bin/bash ./on-off-test.sh -r 2 || echo "memory-hotplug selftests: [FAIL]" +include ../lib.mk + +TEST_PROGS := mem-on-off-test.sh +override RUN_TESTS := ./mem-on-off-test.sh -r 2 || echo "selftests: memory-hotplug [FAIL]" +override EMIT_TESTS := echo "$(RUN_TESTS)" run_full_test: - @/bin/bash ./on-off-test.sh || echo "memory-hotplug selftests: [FAIL]" + @/bin/bash ./mem-on-off-test.sh || echo "memory-hotplug selftests: [FAIL]" clean: diff --git a/tools/testing/selftests/memory-hotplug/on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh index 6cddde0b96f8..6cddde0b96f8 100644..100755 --- a/tools/testing/selftests/memory-hotplug/on-off-test.sh +++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh diff --git a/tools/testing/selftests/mount/.gitignore b/tools/testing/selftests/mount/.gitignore new file mode 100644 index 000000000000..856ad4107eb3 --- /dev/null +++ b/tools/testing/selftests/mount/.gitignore @@ -0,0 +1 @@ +unprivileged-remount-test diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile index 337d853c2b72..95580a97326e 100644 --- a/tools/testing/selftests/mount/Makefile +++ b/tools/testing/selftests/mount/Makefile @@ -1,17 +1,16 @@ # Makefile for mount selftests. - +CFLAGS = -Wall \ + -O2 all: unprivileged-remount-test unprivileged-remount-test: unprivileged-remount-test.c - gcc -Wall -O2 unprivileged-remount-test.c -o unprivileged-remount-test + $(CC) $(CFLAGS) unprivileged-remount-test.c -o unprivileged-remount-test -# Allow specific tests to be selected. -test_unprivileged_remount: unprivileged-remount-test - @if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi +include ../lib.mk -run_tests: all test_unprivileged_remount +TEST_PROGS := unprivileged-remount-test +override RUN_TESTS := if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi +override EMIT_TESTS := echo "$(RUN_TESTS)" clean: rm -f unprivileged-remount-test - -.PHONY: all test_unprivileged_remount diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c index 1b3ff2fda4d0..517785052f1c 100644 --- a/tools/testing/selftests/mount/unprivileged-remount-test.c +++ b/tools/testing/selftests/mount/unprivileged-remount-test.c @@ -6,6 +6,8 @@ #include <sys/types.h> #include <sys/mount.h> #include <sys/wait.h> +#include <sys/vfs.h> +#include <sys/statvfs.h> #include <stdlib.h> #include <unistd.h> #include <fcntl.h> @@ -32,11 +34,14 @@ # define CLONE_NEWPID 0x20000000 #endif +#ifndef MS_REC +# define MS_REC 16384 +#endif #ifndef MS_RELATIME -#define MS_RELATIME (1 << 21) +# define MS_RELATIME (1 << 21) #endif #ifndef MS_STRICTATIME -#define MS_STRICTATIME (1 << 24) +# define MS_STRICTATIME (1 << 24) #endif static void die(char *fmt, ...) @@ -48,17 +53,14 @@ static void die(char *fmt, ...) exit(EXIT_FAILURE); } -static void write_file(char *filename, char *fmt, ...) +static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap) { char buf[4096]; int fd; ssize_t written; int buf_len; - va_list ap; - va_start(ap, fmt); buf_len = vsnprintf(buf, sizeof(buf), fmt, ap); - va_end(ap); if (buf_len < 0) { die("vsnprintf failed: %s\n", strerror(errno)); @@ -69,6 +71,8 @@ static void write_file(char *filename, char *fmt, ...) fd = open(filename, O_WRONLY); if (fd < 0) { + if ((errno == ENOENT) && enoent_ok) + return; die("open of %s failed: %s\n", filename, strerror(errno)); } @@ -87,6 +91,65 @@ static void write_file(char *filename, char *fmt, ...) } } +static void maybe_write_file(char *filename, char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vmaybe_write_file(true, filename, fmt, ap); + va_end(ap); + +} + +static void write_file(char *filename, char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vmaybe_write_file(false, filename, fmt, ap); + va_end(ap); + +} + +static int read_mnt_flags(const char *path) +{ + int ret; + struct statvfs stat; + int mnt_flags; + + ret = statvfs(path, &stat); + if (ret != 0) { + die("statvfs of %s failed: %s\n", + path, strerror(errno)); + } + if (stat.f_flag & ~(ST_RDONLY | ST_NOSUID | ST_NODEV | \ + ST_NOEXEC | ST_NOATIME | ST_NODIRATIME | ST_RELATIME | \ + ST_SYNCHRONOUS | ST_MANDLOCK)) { + die("Unrecognized mount flags\n"); + } + mnt_flags = 0; + if (stat.f_flag & ST_RDONLY) + mnt_flags |= MS_RDONLY; + if (stat.f_flag & ST_NOSUID) + mnt_flags |= MS_NOSUID; + if (stat.f_flag & ST_NODEV) + mnt_flags |= MS_NODEV; + if (stat.f_flag & ST_NOEXEC) + mnt_flags |= MS_NOEXEC; + if (stat.f_flag & ST_NOATIME) + mnt_flags |= MS_NOATIME; + if (stat.f_flag & ST_NODIRATIME) + mnt_flags |= MS_NODIRATIME; + if (stat.f_flag & ST_RELATIME) + mnt_flags |= MS_RELATIME; + if (stat.f_flag & ST_SYNCHRONOUS) + mnt_flags |= MS_SYNCHRONOUS; + if (stat.f_flag & ST_MANDLOCK) + mnt_flags |= ST_MANDLOCK; + + return mnt_flags; +} + static void create_and_enter_userns(void) { uid_t uid; @@ -100,13 +163,10 @@ static void create_and_enter_userns(void) strerror(errno)); } + maybe_write_file("/proc/self/setgroups", "deny"); write_file("/proc/self/uid_map", "0 %d 1", uid); write_file("/proc/self/gid_map", "0 %d 1", gid); - if (setgroups(0, NULL) != 0) { - die("setgroups failed: %s\n", - strerror(errno)); - } if (setgid(0) != 0) { die ("setgid(0) failed %s\n", strerror(errno)); @@ -118,7 +178,8 @@ static void create_and_enter_userns(void) } static -bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags) +bool test_unpriv_remount(const char *fstype, const char *mount_options, + int mount_flags, int remount_flags, int invalid_flags) { pid_t child; @@ -151,9 +212,11 @@ bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags) strerror(errno)); } - if (mount("testing", "/tmp", "ramfs", mount_flags, NULL) != 0) { - die("mount of /tmp failed: %s\n", - strerror(errno)); + if (mount("testing", "/tmp", fstype, mount_flags, mount_options) != 0) { + die("mount of %s with options '%s' on /tmp failed: %s\n", + fstype, + mount_options? mount_options : "", + strerror(errno)); } create_and_enter_userns(); @@ -181,62 +244,127 @@ bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags) static bool test_unpriv_remount_simple(int mount_flags) { - return test_unpriv_remount(mount_flags, mount_flags, 0); + return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, 0); } static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags) { - return test_unpriv_remount(mount_flags, mount_flags, invalid_flags); + return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, + invalid_flags); +} + +static bool test_priv_mount_unpriv_remount(void) +{ + pid_t child; + int ret; + const char *orig_path = "/dev"; + const char *dest_path = "/tmp"; + int orig_mnt_flags, remount_mnt_flags; + + child = fork(); + if (child == -1) { + die("fork failed: %s\n", + strerror(errno)); + } + if (child != 0) { /* parent */ + pid_t pid; + int status; + pid = waitpid(child, &status, 0); + if (pid == -1) { + die("waitpid failed: %s\n", + strerror(errno)); + } + if (pid != child) { + die("waited for %d got %d\n", + child, pid); + } + if (!WIFEXITED(status)) { + die("child did not terminate cleanly\n"); + } + return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false; + } + + orig_mnt_flags = read_mnt_flags(orig_path); + + create_and_enter_userns(); + ret = unshare(CLONE_NEWNS); + if (ret != 0) { + die("unshare(CLONE_NEWNS) failed: %s\n", + strerror(errno)); + } + + ret = mount(orig_path, dest_path, "bind", MS_BIND | MS_REC, NULL); + if (ret != 0) { + die("recursive bind mount of %s onto %s failed: %s\n", + orig_path, dest_path, strerror(errno)); + } + + ret = mount(dest_path, dest_path, "none", + MS_REMOUNT | MS_BIND | orig_mnt_flags , NULL); + if (ret != 0) { + /* system("cat /proc/self/mounts"); */ + die("remount of /tmp failed: %s\n", + strerror(errno)); + } + + remount_mnt_flags = read_mnt_flags(dest_path); + if (orig_mnt_flags != remount_mnt_flags) { + die("Mount flags unexpectedly changed during remount of %s originally mounted on %s\n", + dest_path, orig_path); + } + exit(EXIT_SUCCESS); } int main(int argc, char **argv) { - if (!test_unpriv_remount_simple(MS_RDONLY|MS_NODEV)) { + if (!test_unpriv_remount_simple(MS_RDONLY)) { die("MS_RDONLY malfunctions\n"); } - if (!test_unpriv_remount_simple(MS_NODEV)) { + if (!test_unpriv_remount("devpts", "newinstance", MS_NODEV, MS_NODEV, 0)) { die("MS_NODEV malfunctions\n"); } - if (!test_unpriv_remount_simple(MS_NOSUID|MS_NODEV)) { + if (!test_unpriv_remount_simple(MS_NOSUID)) { die("MS_NOSUID malfunctions\n"); } - if (!test_unpriv_remount_simple(MS_NOEXEC|MS_NODEV)) { + if (!test_unpriv_remount_simple(MS_NOEXEC)) { die("MS_NOEXEC malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODEV, - MS_NOATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_RELATIME, + MS_NOATIME)) { die("MS_RELATIME malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODEV, - MS_NOATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_STRICTATIME, + MS_NOATIME)) { die("MS_STRICTATIME malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODEV, - MS_STRICTATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_NOATIME, + MS_STRICTATIME)) { - die("MS_RELATIME malfunctions\n"); + die("MS_NOATIME malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME|MS_NODEV, - MS_NOATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME, + MS_NOATIME)) { - die("MS_RELATIME malfunctions\n"); + die("MS_RELATIME|MS_NODIRATIME malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME|MS_NODEV, - MS_NOATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME, + MS_NOATIME)) { - die("MS_RELATIME malfunctions\n"); + die("MS_STRICTATIME|MS_NODIRATIME malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME|MS_NODEV, - MS_STRICTATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME, + MS_STRICTATIME)) { - die("MS_RELATIME malfunctions\n"); + die("MS_NOATIME|MS_DIRATIME malfunctions\n"); } - if (!test_unpriv_remount(MS_STRICTATIME|MS_NODEV, MS_NODEV, - MS_NOATIME|MS_NODEV)) + if (!test_unpriv_remount("ramfs", NULL, MS_STRICTATIME, 0, MS_NOATIME)) { die("Default atime malfunctions\n"); } + if (!test_priv_mount_unpriv_remount()) { + die("Mount flags unexpectedly changed after remount\n"); + } return EXIT_SUCCESS; } diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile index 8056e2e68fa4..0e3b41eb85cd 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -1,10 +1,22 @@ +CFLAGS = -O2 + all: - gcc -O2 mq_open_tests.c -o mq_open_tests -lrt - gcc -O2 -o mq_perf_tests mq_perf_tests.c -lrt -lpthread -lpopt + $(CC) $(CFLAGS) mq_open_tests.c -o mq_open_tests -lrt + $(CC) $(CFLAGS) -o mq_perf_tests mq_perf_tests.c -lrt -lpthread -lpopt + +include ../lib.mk + +override define RUN_TESTS + @./mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" + @./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" +endef + +TEST_PROGS := mq_open_tests mq_perf_tests -run_tests: - @./mq_open_tests /test1 || echo "mq_open_tests: [FAIL]" - @./mq_perf_tests || echo "mq_perf_tests: [FAIL]" +override define EMIT_TESTS + echo "./mq_open_tests /test1 || echo \"selftests: mq_open_tests [FAIL]\"" + echo "./mq_perf_tests || echo \"selftests: mq_perf_tests [FAIL]\"" +endef clean: rm -f mq_open_tests mq_perf_tests diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c index 94dae65eea41..8519e9ee97e3 100644 --- a/tools/testing/selftests/mqueue/mq_perf_tests.c +++ b/tools/testing/selftests/mqueue/mq_perf_tests.c @@ -536,10 +536,9 @@ int main(int argc, char *argv[]) { struct mq_attr attr; char *option, *next_option; - int i, cpu; + int i, cpu, rc; struct sigaction sa; poptContext popt_context; - char rc; void *retval; main_thread = pthread_self(); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index c7493b8f9b0e..fac4782c51d8 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -1,6 +1,5 @@ # Makefile for net selftests -CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall -O2 -g CFLAGS += -I../../../../usr/include/ @@ -11,15 +10,10 @@ all: $(NET_PROGS) %: %.c $(CC) $(CFLAGS) -o $@ $^ -run_tests: all - @/bin/sh ./run_netsocktests || echo "sockettests: [FAIL]" - @/bin/sh ./run_afpackettests || echo "afpackettests: [FAIL]" - @if /sbin/modprobe test_bpf ; then \ - /sbin/rmmod test_bpf; \ - echo "test_bpf: ok"; \ - else \ - echo "test_bpf: [FAIL]"; \ - exit 1; \ - fi +TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh +TEST_FILES := $(NET_PROGS) + +include ../lib.mk + clean: $(RM) $(NET_PROGS) diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 5246e782d6e8..5246e782d6e8 100644..100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests index c09a682df56a..c09a682df56a 100644..100755 --- a/tools/testing/selftests/net/run_netsocktests +++ b/tools/testing/selftests/net/run_netsocktests diff --git a/tools/testing/selftests/net/test_bpf.sh b/tools/testing/selftests/net/test_bpf.sh new file mode 100755 index 000000000000..8b29796d46aa --- /dev/null +++ b/tools/testing/selftests/net/test_bpf.sh @@ -0,0 +1,10 @@ +#!/bin/sh +# Runs bpf test using test_bpf kernel module + +if /sbin/modprobe -q test_bpf ; then + /sbin/modprobe -q -r test_bpf; + echo "test_bpf: ok"; +else + echo "test_bpf: [FAIL]"; + exit 1; +fi diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index f6ff90a76bd7..2958fe9a74e9 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -8,12 +8,11 @@ ifeq ($(ARCH),powerpc) GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown") -CC := $(CROSS_COMPILE)$(CC) CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS) -export CC CFLAGS +export CFLAGS -TARGETS = pmu copyloops mm tm primitives +TARGETS = pmu copyloops mm tm primitives stringloops endif @@ -22,10 +21,25 @@ all: $(TARGETS) $(TARGETS): $(MAKE) -k -C $@ all -run_tests: all +include ../lib.mk + +override define RUN_TESTS @for TARGET in $(TARGETS); do \ $(MAKE) -C $$TARGET run_tests; \ done; +endef + +override define INSTALL_RULE + @for TARGET in $(TARGETS); do \ + $(MAKE) -C $$TARGET install; \ + done; +endef + +override define EMIT_TESTS + @for TARGET in $(TARGETS); do \ + $(MAKE) -s -C $$TARGET emit_tests; \ + done; +endef clean: @for TARGET in $(TARGETS); do \ @@ -36,4 +50,4 @@ clean: tags: find . -name '*.c' -o -name '*.h' | xargs ctags -.PHONY: all run_tests clean tags $(TARGETS) +.PHONY: tags $(TARGETS) diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore new file mode 100644 index 000000000000..25a192f62c4d --- /dev/null +++ b/tools/testing/selftests/powerpc/copyloops/.gitignore @@ -0,0 +1,4 @@ +copyuser_64 +copyuser_power7 +memcpy_64 +memcpy_power7 diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile index 6f2d3be227f9..c05023514ce8 100644 --- a/tools/testing/selftests/powerpc/copyloops/Makefile +++ b/tools/testing/selftests/powerpc/copyloops/Makefile @@ -6,24 +6,19 @@ CFLAGS += -D SELFTEST # Use our CFLAGS for the implicit .S rule ASFLAGS = $(CFLAGS) -PROGS := copyuser_64 copyuser_power7 memcpy_64 memcpy_power7 +TEST_PROGS := copyuser_64 copyuser_power7 memcpy_64 memcpy_power7 EXTRA_SOURCES := validate.c ../harness.c -all: $(PROGS) +all: $(TEST_PROGS) copyuser_64: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_base copyuser_power7: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_power7 memcpy_64: CPPFLAGS += -D COPY_LOOP=test_memcpy memcpy_power7: CPPFLAGS += -D COPY_LOOP=test_memcpy_power7 -$(PROGS): $(EXTRA_SOURCES) +$(TEST_PROGS): $(EXTRA_SOURCES) -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk clean: - rm -f $(PROGS) *.o - -.PHONY: all run_tests clean + rm -f $(TEST_PROGS) *.o diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore new file mode 100644 index 000000000000..b43ade0ec861 --- /dev/null +++ b/tools/testing/selftests/powerpc/mm/.gitignore @@ -0,0 +1,3 @@ +hugetlb_vs_thp_test +subpage_prot +tempfile diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index 357ccbd6bad9..41cc3ed66818 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -1,18 +1,16 @@ noarg: $(MAKE) -C ../ -PROGS := hugetlb_vs_thp_test +TEST_PROGS := hugetlb_vs_thp_test subpage_prot -all: $(PROGS) +all: $(TEST_PROGS) tempfile -$(PROGS): ../harness.c +$(TEST_PROGS): ../harness.c -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk -clean: - rm -f $(PROGS) +tempfile: + dd if=/dev/zero of=tempfile bs=64k count=1 -.PHONY: all run_tests clean +clean: + rm -f $(TEST_PROGS) tempfile diff --git a/tools/testing/selftests/powerpc/mm/subpage_prot.c b/tools/testing/selftests/powerpc/mm/subpage_prot.c new file mode 100644 index 000000000000..440180ff8089 --- /dev/null +++ b/tools/testing/selftests/powerpc/mm/subpage_prot.c @@ -0,0 +1,220 @@ +/* + * Copyright IBM Corp. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ + +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <signal.h> +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/ptrace.h> +#include <sys/syscall.h> +#include <ucontext.h> +#include <unistd.h> + +#include "utils.h" + +char *file_name; + +int in_test; +volatile int faulted; +volatile void *dar; +int errors; + +static void segv(int signum, siginfo_t *info, void *ctxt_v) +{ + ucontext_t *ctxt = (ucontext_t *)ctxt_v; + struct pt_regs *regs = ctxt->uc_mcontext.regs; + + if (!in_test) { + fprintf(stderr, "Segfault outside of test !\n"); + exit(1); + } + + faulted = 1; + dar = (void *)regs->dar; + regs->nip += 4; +} + +static inline void do_read(const volatile void *addr) +{ + int ret; + + asm volatile("lwz %0,0(%1); twi 0,%0,0; isync;\n" + : "=r" (ret) : "r" (addr) : "memory"); +} + +static inline void do_write(const volatile void *addr) +{ + int val = 0x1234567; + + asm volatile("stw %0,0(%1); sync; \n" + : : "r" (val), "r" (addr) : "memory"); +} + +static inline void check_faulted(void *addr, long page, long subpage, int write) +{ + int want_fault = (subpage == ((page + 3) % 16)); + + if (write) + want_fault |= (subpage == ((page + 1) % 16)); + + if (faulted != want_fault) { + printf("Failed at 0x%p (p=%ld,sp=%ld,w=%d), want=%s, got=%s !\n", + addr, page, subpage, write, + want_fault ? "fault" : "pass", + faulted ? "fault" : "pass"); + ++errors; + } + + if (faulted) { + if (dar != addr) { + printf("Fault expected at 0x%p and happened at 0x%p !\n", + addr, dar); + } + faulted = 0; + asm volatile("sync" : : : "memory"); + } +} + +static int run_test(void *addr, unsigned long size) +{ + unsigned int *map; + long i, j, pages, err; + + pages = size / 0x10000; + map = malloc(pages * 4); + assert(map); + + /* + * for each page, mark subpage i % 16 read only and subpage + * (i + 3) % 16 inaccessible + */ + for (i = 0; i < pages; i++) { + map[i] = (0x40000000 >> (((i + 1) * 2) % 32)) | + (0xc0000000 >> (((i + 3) * 2) % 32)); + } + + err = syscall(__NR_subpage_prot, addr, size, map); + if (err) { + perror("subpage_perm"); + return 1; + } + free(map); + + in_test = 1; + errors = 0; + for (i = 0; i < pages; i++) { + for (j = 0; j < 16; j++, addr += 0x1000) { + do_read(addr); + check_faulted(addr, i, j, 0); + do_write(addr); + check_faulted(addr, i, j, 1); + } + } + + in_test = 0; + if (errors) { + printf("%d errors detected\n", errors); + return 1; + } + + return 0; +} + +int test_anon(void) +{ + unsigned long align; + struct sigaction act = { + .sa_sigaction = segv, + .sa_flags = SA_SIGINFO + }; + void *mallocblock; + unsigned long mallocsize; + + if (getpagesize() != 0x10000) { + fprintf(stderr, "Kernel page size must be 64K!\n"); + return 1; + } + + sigaction(SIGSEGV, &act, NULL); + + mallocsize = 4 * 16 * 1024 * 1024; + + FAIL_IF(posix_memalign(&mallocblock, 64 * 1024, mallocsize)); + + align = (unsigned long)mallocblock; + if (align & 0xffff) + align = (align | 0xffff) + 1; + + mallocblock = (void *)align; + + printf("allocated malloc block of 0x%lx bytes at 0x%p\n", + mallocsize, mallocblock); + + printf("testing malloc block...\n"); + + return run_test(mallocblock, mallocsize); +} + +int test_file(void) +{ + struct sigaction act = { + .sa_sigaction = segv, + .sa_flags = SA_SIGINFO + }; + void *fileblock; + off_t filesize; + int fd; + + fd = open(file_name, O_RDWR); + if (fd == -1) { + perror("failed to open file"); + return 1; + } + sigaction(SIGSEGV, &act, NULL); + + filesize = lseek(fd, 0, SEEK_END); + if (filesize & 0xffff) + filesize &= ~0xfffful; + + fileblock = mmap(NULL, filesize, PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + if (fileblock == MAP_FAILED) { + perror("failed to map file"); + return 1; + } + printf("allocated %s for 0x%lx bytes at 0x%p\n", + file_name, filesize, fileblock); + + printf("testing file map...\n"); + + return run_test(fileblock, filesize); +} + +int main(int argc, char *argv[]) +{ + test_harness(test_anon, "subpage_prot_anon"); + + if (argc > 1) + file_name = argv[1]; + else + file_name = "tempfile"; + + test_harness(test_file, "subpage_prot_file"); + + return 0; +} diff --git a/tools/testing/selftests/powerpc/pmu/.gitignore b/tools/testing/selftests/powerpc/pmu/.gitignore new file mode 100644 index 000000000000..e748f336eed3 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/.gitignore @@ -0,0 +1,3 @@ +count_instructions +l3_bank_test +per_event_excludes diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index c9f4263906a5..5a161175bbd4 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -1,38 +1,42 @@ noarg: $(MAKE) -C ../ -PROGS := count_instructions l3_bank_test per_event_excludes +TEST_PROGS := count_instructions l3_bank_test per_event_excludes EXTRA_SOURCES := ../harness.c event.c lib.c -SUB_TARGETS = ebb +all: $(TEST_PROGS) ebb -all: $(PROGS) $(SUB_TARGETS) - -$(PROGS): $(EXTRA_SOURCES) +$(TEST_PROGS): $(EXTRA_SOURCES) # loop.S can only be built 64-bit count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES) $(CC) $(CFLAGS) -m64 -o $@ $^ -run_tests: all sub_run_tests - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk -clean: sub_clean - rm -f $(PROGS) loop.o +DEFAULT_RUN_TESTS := $(RUN_TESTS) +override define RUN_TESTS + $(DEFAULT_RUN_TESTS) + $(MAKE) -C ebb run_tests +endef -$(SUB_TARGETS): - $(MAKE) -k -C $@ all +DEFAULT_EMIT_TESTS := $(EMIT_TESTS) +override define EMIT_TESTS + $(DEFAULT_EMIT_TESTS) + $(MAKE) -s -C ebb emit_tests +endef -sub_run_tests: all - @for TARGET in $(SUB_TARGETS); do \ - $(MAKE) -C $$TARGET run_tests; \ - done; +DEFAULT_INSTALL := $(INSTALL_RULE) +override define INSTALL_RULE + $(DEFAULT_INSTALL_RULE) + $(MAKE) -C ebb install +endef -sub_clean: - @for TARGET in $(SUB_TARGETS); do \ - $(MAKE) -C $$TARGET clean; \ - done; +clean: + rm -f $(TEST_PROGS) loop.o + $(MAKE) -C ebb clean + +ebb: + $(MAKE) -k -C $@ all -.PHONY: all run_tests clean sub_run_tests sub_clean $(SUB_TARGETS) +.PHONY: all run_tests clean ebb diff --git a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore new file mode 100644 index 000000000000..42bddbed8b64 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore @@ -0,0 +1,22 @@ +reg_access_test +event_attributes_test +cycles_test +cycles_with_freeze_test +pmc56_overflow_test +ebb_vs_cpu_event_test +cpu_event_vs_ebb_test +cpu_event_pinned_vs_ebb_test +task_event_vs_ebb_test +task_event_pinned_vs_ebb_test +multi_ebb_procs_test +multi_counter_test +pmae_handling_test +close_clears_pmcc_test +instruction_count_test +fork_cleanup_test +ebb_on_child_test +ebb_on_willing_child_test +back_to_back_ebbs_test +lost_exception_test +no_handler_test +cycles_with_mmcr2_test diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index 3dc4332698cb..5cdc9dbf2b27 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -4,7 +4,7 @@ noarg: # The EBB handler is 64-bit code and everything links against it CFLAGS += -m64 -PROGS := reg_access_test event_attributes_test cycles_test \ +TEST_PROGS := reg_access_test event_attributes_test cycles_test \ cycles_with_freeze_test pmc56_overflow_test \ ebb_vs_cpu_event_test cpu_event_vs_ebb_test \ cpu_event_pinned_vs_ebb_test task_event_vs_ebb_test \ @@ -16,18 +16,15 @@ PROGS := reg_access_test event_attributes_test cycles_test \ lost_exception_test no_handler_test \ cycles_with_mmcr2_test -all: $(PROGS) +all: $(TEST_PROGS) -$(PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c busy_loop.S +$(TEST_PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c busy_loop.S instruction_count_test: ../loop.S lost_exception_test: ../lib.c -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../../lib.mk clean: - rm -f $(PROGS) + rm -f $(TEST_PROGS) diff --git a/tools/testing/selftests/powerpc/primitives/.gitignore b/tools/testing/selftests/powerpc/primitives/.gitignore new file mode 100644 index 000000000000..4cc4e31bed1d --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/.gitignore @@ -0,0 +1 @@ +load_unaligned_zeropad diff --git a/tools/testing/selftests/powerpc/primitives/Makefile b/tools/testing/selftests/powerpc/primitives/Makefile index ea737ca01732..b68c6221d3d1 100644 --- a/tools/testing/selftests/powerpc/primitives/Makefile +++ b/tools/testing/selftests/powerpc/primitives/Makefile @@ -1,17 +1,12 @@ CFLAGS += -I$(CURDIR) -PROGS := load_unaligned_zeropad +TEST_PROGS := load_unaligned_zeropad -all: $(PROGS) +all: $(TEST_PROGS) -$(PROGS): ../harness.c +$(TEST_PROGS): ../harness.c -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk clean: - rm -f $(PROGS) *.o - -.PHONY: all run_tests clean + rm -f $(TEST_PROGS) *.o diff --git a/tools/testing/selftests/powerpc/stringloops/.gitignore b/tools/testing/selftests/powerpc/stringloops/.gitignore new file mode 100644 index 000000000000..0b43da74ee46 --- /dev/null +++ b/tools/testing/selftests/powerpc/stringloops/.gitignore @@ -0,0 +1 @@ +memcmp diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile new file mode 100644 index 000000000000..2a728f4d2873 --- /dev/null +++ b/tools/testing/selftests/powerpc/stringloops/Makefile @@ -0,0 +1,15 @@ +# The loops are all 64-bit code +CFLAGS += -m64 +CFLAGS += -I$(CURDIR) + +TEST_PROGS := memcmp +EXTRA_SOURCES := memcmp_64.S ../harness.c + +all: $(TEST_PROGS) + +$(TEST_PROGS): $(EXTRA_SOURCES) + +include ../../lib.mk + +clean: + rm -f $(TEST_PROGS) *.o diff --git a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h new file mode 100644 index 000000000000..11bece87e880 --- /dev/null +++ b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h @@ -0,0 +1,7 @@ +#include <ppc-asm.h> + +#ifndef r1 +#define r1 sp +#endif + +#define _GLOBAL(A) FUNC_START(test_ ## A) diff --git a/tools/testing/selftests/powerpc/stringloops/memcmp.c b/tools/testing/selftests/powerpc/stringloops/memcmp.c new file mode 100644 index 000000000000..17417dd70708 --- /dev/null +++ b/tools/testing/selftests/powerpc/stringloops/memcmp.c @@ -0,0 +1,103 @@ +#include <malloc.h> +#include <stdlib.h> +#include <string.h> +#include "../utils.h" + +#define SIZE 256 +#define ITERATIONS 10000 + +int test_memcmp(const void *s1, const void *s2, size_t n); + +/* test all offsets and lengths */ +static void test_one(char *s1, char *s2) +{ + unsigned long offset, size; + + for (offset = 0; offset < SIZE; offset++) { + for (size = 0; size < (SIZE-offset); size++) { + int x, y; + unsigned long i; + + y = memcmp(s1+offset, s2+offset, size); + x = test_memcmp(s1+offset, s2+offset, size); + + if (((x ^ y) < 0) && /* Trick to compare sign */ + ((x | y) != 0)) { /* check for zero */ + printf("memcmp returned %d, should have returned %d (offset %ld size %ld)\n", x, y, offset, size); + + for (i = offset; i < offset+size; i++) + printf("%02x ", s1[i]); + printf("\n"); + + for (i = offset; i < offset+size; i++) + printf("%02x ", s2[i]); + printf("\n"); + abort(); + } + } + } +} + +static int testcase(void) +{ + char *s1; + char *s2; + unsigned long i; + + s1 = memalign(128, SIZE); + if (!s1) { + perror("memalign"); + exit(1); + } + + s2 = memalign(128, SIZE); + if (!s2) { + perror("memalign"); + exit(1); + } + + srandom(1); + + for (i = 0; i < ITERATIONS; i++) { + unsigned long j; + unsigned long change; + + for (j = 0; j < SIZE; j++) + s1[j] = random(); + + memcpy(s2, s1, SIZE); + + /* change one byte */ + change = random() % SIZE; + s2[change] = random() & 0xff; + + test_one(s1, s2); + } + + srandom(1); + + for (i = 0; i < ITERATIONS; i++) { + unsigned long j; + unsigned long change; + + for (j = 0; j < SIZE; j++) + s1[j] = random(); + + memcpy(s2, s1, SIZE); + + /* change multiple bytes, 1/8 of total */ + for (j = 0; j < SIZE / 8; j++) { + change = random() % SIZE; + s2[change] = random() & 0xff; + } + + test_one(s1, s2); + } + + return 0; +} + +int main(void) +{ + return test_harness(testcase, "memcmp"); +} diff --git a/tools/testing/selftests/powerpc/stringloops/memcmp_64.S b/tools/testing/selftests/powerpc/stringloops/memcmp_64.S new file mode 120000 index 000000000000..9bc87e438ae9 --- /dev/null +++ b/tools/testing/selftests/powerpc/stringloops/memcmp_64.S @@ -0,0 +1 @@ +../../../../../arch/powerpc/lib/memcmp_64.S
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore new file mode 100644 index 000000000000..33d02cc54a3e --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/.gitignore @@ -0,0 +1 @@ +tm-resched-dscr diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index 2cede239a074..34f2ec634b40 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -1,15 +1,10 @@ -PROGS := tm-resched-dscr +TEST_PROGS := tm-resched-dscr -all: $(PROGS) +all: $(TEST_PROGS) -$(PROGS): ../harness.c +$(TEST_PROGS): ../harness.c -run_tests: all - @-for PROG in $(PROGS); do \ - ./$$PROG; \ - done; +include ../../lib.mk clean: - rm -f $(PROGS) *.o - -.PHONY: all run_tests clean + rm -f $(TEST_PROGS) *.o diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile index 47ae2d385ce8..453927fea90c 100644 --- a/tools/testing/selftests/ptrace/Makefile +++ b/tools/testing/selftests/ptrace/Makefile @@ -6,5 +6,6 @@ all: peeksiginfo clean: rm -f peeksiginfo -run_tests: all - @./peeksiginfo || echo "peeksiginfo selftests: [FAIL]" +TEST_PROGS := peeksiginfo + +include ../lib.mk diff --git a/tools/testing/selftests/rcutorture/bin/cpus2use.sh b/tools/testing/selftests/rcutorture/bin/cpus2use.sh index abe14b7f36e9..bb99cde3f5f9 100755 --- a/tools/testing/selftests/rcutorture/bin/cpus2use.sh +++ b/tools/testing/selftests/rcutorture/bin/cpus2use.sh @@ -24,7 +24,7 @@ ncpus=`grep '^processor' /proc/cpuinfo | wc -l` idlecpus=`mpstat | tail -1 | \ - awk -v ncpus=$ncpus '{ print ncpus * ($7 + $12) / 100 }'` + awk -v ncpus=$ncpus '{ print ncpus * ($7 + $NF) / 100 }'` awk -v ncpus=$ncpus -v idlecpus=$idlecpus < /dev/null ' BEGIN { cpus2use = idlecpus; diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index d6cc07fc137f..559e01ac86be 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -30,6 +30,7 @@ else echo Unreadable results directory: $i exit 1 fi +. tools/testing/selftests/rcutorture/bin/functions.sh configfile=`echo $i | sed -e 's/^.*\///'` ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'` @@ -48,4 +49,21 @@ else title="$title ($ngpsps per second)" fi echo $title + nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'` + if test -z "$nclosecalls" + then + exit 0 + fi + if test "$nclosecalls" -eq 0 + then + exit 0 + fi + # Compute number of close calls per tenth of an hour + nclosecalls10=`awk -v nclosecalls=$nclosecalls -v dur=$dur 'BEGIN { print int(nclosecalls * 36000 / dur) }' < /dev/null` + if test $nclosecalls10 -gt 5 -a $nclosecalls -gt 1 + then + print_bug $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i + else + print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i + fi fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index f6b2b4771b78..5236e073919d 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -8,9 +8,9 @@ # # Usage: kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args # -# qemu-args defaults to "-nographic", along with arguments specifying the -# number of CPUs and other options generated from -# the underlying CPU architecture. +# qemu-args defaults to "-enable-kvm -soundhw pcspk -nographic", along with +# arguments specifying the number of CPUs and other +# options generated from the underlying CPU architecture. # boot_args defaults to value returned by the per_version_boot_params # shell function. # @@ -45,7 +45,7 @@ trap 'rm -rf $T' 0 touch $T . $KVM/bin/functions.sh -. $KVPATH/ver_functions.sh +. $CONFIGFRAG/ver_functions.sh config_template=${1} config_dir=`echo $config_template | sed -e 's,/[^/]*$,,'` @@ -138,7 +138,7 @@ then fi # Generate -smp qemu argument. -qemu_args="-nographic $qemu_args" +qemu_args="-enable-kvm -soundhw pcspk -nographic $qemu_args" cpu_count=`configNR_CPUS.sh $config_template` cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"` vcpus=`identify_qemu_vcpus` @@ -168,8 +168,9 @@ then touch $resdir/buildonly exit 0 fi -echo $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd -( $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) & +echo "NOTE: $QEMU either did not run or was interactive" > $builddir/console.log +echo $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd +( $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) & qemu_pid=$! commandcompleted=0 echo Monitoring qemu job at pid $qemu_pid diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index e527dc952eb0..368d64ac779e 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -47,7 +47,6 @@ resdir="" configs="" cpus=0 ds=`date +%Y.%m.%d-%H:%M:%S` -kversion="" . functions.sh @@ -64,7 +63,6 @@ usage () { echo " --duration minutes" echo " --interactive" echo " --kmake-arg kernel-make-arguments" - echo " --kversion vN.NN" echo " --mac nn:nn:nn:nn:nn:nn" echo " --no-initrd" echo " --qemu-args qemu-system-..." @@ -128,11 +126,6 @@ do TORTURE_KMAKE_ARG="$2" shift ;; - --kversion) - checkarg --kversion "(kernel version)" $# "$2" '^v[0-9.]*$' '^error' - kversion=$2 - shift - ;; --mac) checkarg --mac "(MAC address)" $# "$2" '^\([0-9a-fA-F]\{2\}:\)\{5\}[0-9a-fA-F]\{2\}$' error TORTURE_QEMU_MAC=$2 @@ -170,11 +163,10 @@ do done CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG -KVPATH=${CONFIGFRAG}/$kversion; export KVPATH if test -z "$configs" then - configs="`cat $CONFIGFRAG/$kversion/CFLIST`" + configs="`cat $CONFIGFRAG/CFLIST`" fi if test -z "$resdir" @@ -186,10 +178,10 @@ fi touch $T/cfgcpu for CF in $configs do - if test -f "$CONFIGFRAG/$kversion/$CF" + if test -f "$CONFIGFRAG/$CF" then - cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF` - cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$kversion/$CF" "$cpu_count"` + cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF` + cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF" "$cpu_count"` echo $CF $cpu_count >> $T/cfgcpu else echo "The --configs file $CF does not exist, terminating." @@ -252,7 +244,6 @@ END { cat << ___EOF___ > $T/script CONFIGFRAG="$CONFIGFRAG"; export CONFIGFRAG KVM="$KVM"; export KVM -KVPATH="$KVPATH"; export KVPATH PATH="$PATH"; export PATH TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE TORTURE_BUILDONLY="$TORTURE_BUILDONLY"; export TORTURE_BUILDONLY @@ -285,7 +276,7 @@ then fi ___EOF___ awk < $T/cfgcpu.pack \ - -v CONFIGDIR="$CONFIGFRAG/$kversion/" \ + -v CONFIGDIR="$CONFIGFRAG/" \ -v KVM="$KVM" \ -v ncpus=$cpus \ -v rd=$resdir/$ds/ \ diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh index 499d1e598e42..a6b57622c2e5 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-build.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh @@ -26,12 +26,15 @@ # # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> -T=$1 +F=$1 title=$2 +T=/tmp/parse-build.sh.$$ +trap 'rm -rf $T' 0 +mkdir $T . functions.sh -if grep -q CC < $T +if grep -q CC < $F then : else @@ -39,18 +42,21 @@ else exit 1 fi -if grep -q "error:" < $T +if grep -q "error:" < $F then print_bug $title build errors: - grep "error:" < $T + grep "error:" < $F exit 2 fi -exit 0 -if egrep -q "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T +grep warning: < $F > $T/warnings +grep "include/linux/*rcu*\.h:" $T/warnings > $T/hwarnings +grep "kernel/rcu/[^/]*:" $T/warnings > $T/cwarnings +cat $T/hwarnings $T/cwarnings > $T/rcuwarnings +if test -s $T/rcuwarnings then print_warning $title build errors: - egrep "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T + cat $T/rcuwarnings exit 2 fi exit 0 diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index f962ba4cf68b..d8f35cf116be 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -36,7 +36,7 @@ if grep -Pq '\x00' < $file then print_warning Console output contains nul bytes, old qemu still running? fi -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T if test -s $T then print_warning Assertion failure in $file $title diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 index f4feaee40776..36e41df3d27a 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 @@ -7,6 +7,8 @@ CONFIG_HZ_PERIODIC=y CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=n CONFIG_RCU_TRACE=y +CONFIG_PROVE_LOCKING=y +CONFIG_PROVE_RCU=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_PREEMPT_COUNT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot new file mode 100644 index 000000000000..0f0802730014 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot @@ -0,0 +1,2 @@ +rcupdate.rcu_self_test=1 +rcupdate.rcu_self_test_bh=1 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 38e3895759dd..f8a10a7500c6 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -2,7 +2,7 @@ CONFIG_SMP=y CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n @@ -14,6 +14,5 @@ CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ZERO=y CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_CPU_STALL_INFO=n -CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 index ea119ba2f7d4..629122fb8b4a 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 @@ -3,7 +3,7 @@ CONFIG_NR_CPUS=8 CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n @@ -19,6 +19,5 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n CONFIG_RCU_CPU_STALL_INFO=n -CONFIG_RCU_CPU_STALL_VERBOSE=y CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T index 19cf9485f48a..a25de47888a4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T @@ -3,7 +3,7 @@ CONFIG_NR_CPUS=8 CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n @@ -19,6 +19,5 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n CONFIG_RCU_CPU_STALL_INFO=n -CONFIG_RCU_CPU_STALL_VERBOSE=y CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 index f4567fb3e332..53f24e0a0ab6 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 @@ -3,7 +3,7 @@ CONFIG_NR_CPUS=8 CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=y CONFIG_HZ_PERIODIC=y CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=n @@ -15,7 +15,6 @@ CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_CPU_STALL_INFO=n -CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 +CONFIG_RCU_KTHREAD_PRIO=2 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 0a262fbb0c12..0f84db35b36d 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -19,5 +19,4 @@ CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_RCU_CPU_STALL_VERBOSE=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index 3a06b97e9a73..212e3bfd2b2a 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -19,5 +19,4 @@ CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y CONFIG_PROVE_RCU=y CONFIG_RCU_CPU_STALL_INFO=n -CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot index 3b42b8b033cd..15b3e1a86f74 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot @@ -1 +1,2 @@ rcutorture.torture_type=sched +rcupdate.rcu_self_test_sched=1 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index 8f084cca91bf..7eee63b44218 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -20,5 +20,4 @@ CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y CONFIG_PROVE_RCU=y CONFIG_RCU_CPU_STALL_INFO=n -CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot new file mode 100644 index 000000000000..da9a03a398db --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot @@ -0,0 +1,3 @@ +rcupdate.rcu_self_test=1 +rcupdate.rcu_self_test_bh=1 +rcupdate.rcu_self_test_sched=1 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index 8f1017666aa7..92a97fa97dec 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -19,5 +19,4 @@ CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 index 69a2e255bf98..5812027d6f9f 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 @@ -3,7 +3,7 @@ CONFIG_NR_CPUS=16 CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n @@ -18,7 +18,8 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=y +CONFIG_PROVE_RCU=y CONFIG_RCU_CPU_STALL_INFO=n -CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T index a0f32fb8f17e..3eaeccacb083 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T @@ -3,7 +3,7 @@ CONFIG_NR_CPUS=16 CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n @@ -19,6 +19,5 @@ CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_CPU_STALL_INFO=n -CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot index 3b42b8b033cd..2561daf605ad 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot @@ -1 +1,3 @@ rcutorture.torture_type=sched +rcupdate.rcu_self_test=1 +rcupdate.rcu_self_test_sched=1 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 index b7a62a540ad1..6076b36f6c0b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 @@ -3,7 +3,7 @@ CONFIG_NR_CPUS=1 CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n @@ -14,6 +14,5 @@ CONFIG_HIBERNATION=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_CPU_STALL_INFO=n -CONFIG_RCU_CPU_STALL_VERBOSE=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/CFLIST deleted file mode 100644 index 18223947bbcb..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/CFLIST +++ /dev/null @@ -1,14 +0,0 @@ -P1-S-T-NH-SD-SMP-HP -P2-2-t-nh-sd-SMP-hp -P3-3-T-nh-SD-SMP-hp -P4-A-t-NH-sd-SMP-HP -P5-U-T-NH-sd-SMP-hp -N1-S-T-NH-SD-SMP-HP -N2-2-t-nh-sd-SMP-hp -N3-3-T-nh-SD-SMP-hp -N4-A-t-NH-sd-SMP-HP -N5-U-T-NH-sd-SMP-hp -PT1-nh -PT2-NH -NT1-nh -NT3-NH diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N1-S-T-NH-SD-SMP-HP deleted file mode 100644 index d3ef873eb6e7..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N1-S-T-NH-SD-SMP-HP +++ /dev/null @@ -1,18 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=8 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N2-2-t-nh-sd-SMP-hp deleted file mode 100644 index 02e418572b1b..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N2-2-t-nh-sd-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=4 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N3-3-T-nh-SD-SMP-hp deleted file mode 100644 index b3100f69c8cf..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N3-3-T-nh-SD-SMP-hp +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N4-A-t-NH-sd-SMP-HP deleted file mode 100644 index c56b44530725..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N4-A-t-NH-sd-SMP-HP +++ /dev/null @@ -1,18 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N5-U-T-NH-sd-SMP-hp deleted file mode 100644 index 90d924fea9e9..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/N5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_DEBUG_KERNEL=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT1-nh deleted file mode 100644 index 023f312a931c..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT1-nh +++ /dev/null @@ -1,23 +0,0 @@ -#CHECK#CONFIG_TINY_RCU=y -CONFIG_RCU_TRACE=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=n -# -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT3-NH deleted file mode 100644 index 6fd0235dae73..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/NT3-NH +++ /dev/null @@ -1,20 +0,0 @@ -#CHECK#CONFIG_TINY_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=y -# -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP deleted file mode 100644 index f72402d7c13d..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP +++ /dev/null @@ -1,19 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=8 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp deleted file mode 100644 index 0f3b667d2a9f..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=4 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp deleted file mode 100644 index b035e141bf2a..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP deleted file mode 100644 index 3ccf6a9447f5..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_RT_MUTEXES=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp deleted file mode 100644 index a55c00877fe4..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,27 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_OBJECTS=y -CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_RT_MUTEXES=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT1-nh deleted file mode 100644 index e3361c3894a1..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT1-nh +++ /dev/null @@ -1,23 +0,0 @@ -CONFIG_TINY_PREEMPT_RCU=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_RCU_TRACE=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=n -# -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT2-NH deleted file mode 100644 index 64abfc3b4d94..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/PT2-NH +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_TINY_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=y -# -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh deleted file mode 100644 index 5ace37a89780..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/ver_functions.sh +++ /dev/null @@ -1,33 +0,0 @@ -#!/bin/bash -# -# Kernel-version-dependent shell functions for the rest of the scripts. -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, you can access it online at -# http://www.gnu.org/licenses/gpl-2.0.html. -# -# Copyright (C) IBM Corporation, 2013 -# -# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> - -# per_version_boot_params bootparam-string config-file seconds -# -# Adds per-version torture-module parameters to kernels supporting them. -# Which old kernels do not. -per_version_boot_params () { - echo rcutorture.stat_interval=15 \ - rcutorture.shutdown_secs=$3 \ - rcutorture.rcutorture_runnable=1 \ - rcutorture.test_no_idle_hz=1 \ - rcutorture.verbose=1 -} diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/CFLIST deleted file mode 100644 index da4cbc668f2a..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/CFLIST +++ /dev/null @@ -1,17 +0,0 @@ -sysidleY.2013.06.19a -sysidleN.2013.06.19a -P1-S-T-NH-SD-SMP-HP -P2-2-t-nh-sd-SMP-hp -P3-3-T-nh-SD-SMP-hp -P4-A-t-NH-sd-SMP-HP -P5-U-T-NH-sd-SMP-hp -P6---t-nh-SD-smp-hp -N1-S-T-NH-SD-SMP-HP -N2-2-t-nh-sd-SMP-hp -N3-3-T-nh-SD-SMP-hp -N4-A-t-NH-sd-SMP-HP -N5-U-T-NH-sd-SMP-hp -PT1-nh -PT2-NH -NT1-nh -NT3-NH diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N1-S-T-NH-SD-SMP-HP deleted file mode 100644 index d81e11d280aa..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N1-S-T-NH-SD-SMP-HP +++ /dev/null @@ -1,19 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_FAST_NO_HZ=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=8 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N2-2-t-nh-sd-SMP-hp deleted file mode 100644 index 02e418572b1b..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N2-2-t-nh-sd-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=4 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N3-3-T-nh-SD-SMP-hp deleted file mode 100644 index b3100f69c8cf..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N3-3-T-nh-SD-SMP-hp +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N4-A-t-NH-sd-SMP-HP deleted file mode 100644 index c56b44530725..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N4-A-t-NH-sd-SMP-HP +++ /dev/null @@ -1,18 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N5-U-T-NH-sd-SMP-hp deleted file mode 100644 index 90d924fea9e9..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_DEBUG_KERNEL=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N6---t-nh-SD-smp-hp deleted file mode 100644 index 0ccc36d72738..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N6---t-nh-SD-smp-hp +++ /dev/null @@ -1,19 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_NR_CPUS=1 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N7-4-T-NH-SD-SMP-HP deleted file mode 100644 index 3f640cf84973..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N7-4-T-NH-SD-SMP-HP +++ /dev/null @@ -1,26 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_DEBUG_KERNEL=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=16 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_NONE=y -CONFIG_RCU_NOCB_CPU_ZERO=n -CONFIG_RCU_NOCB_CPU_ALL=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N8-2-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N8-2-T-NH-SD-SMP-HP deleted file mode 100644 index 285da2dd8ac3..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/N8-2-T-NH-SD-SMP-HP +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_DEBUG_KERNEL=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=14 -CONFIG_NR_CPUS=16 -CONFIG_RCU_FANOUT_EXACT=y -CONFIG_HOTPLUG_CPU=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT1-nh deleted file mode 100644 index 023f312a931c..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT1-nh +++ /dev/null @@ -1,23 +0,0 @@ -#CHECK#CONFIG_TINY_RCU=y -CONFIG_RCU_TRACE=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=n -# -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT3-NH deleted file mode 100644 index 6fd0235dae73..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/NT3-NH +++ /dev/null @@ -1,20 +0,0 @@ -#CHECK#CONFIG_TINY_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=y -# -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP deleted file mode 100644 index 9647c44cf4b7..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_RCU_FAST_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=8 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp deleted file mode 100644 index 0f3b667d2a9f..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=4 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp deleted file mode 100644 index b035e141bf2a..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP deleted file mode 100644 index 3ccf6a9447f5..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_RT_MUTEXES=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp deleted file mode 100644 index a55c00877fe4..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,27 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_OBJECTS=y -CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_RT_MUTEXES=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp deleted file mode 100644 index f4c9175828bf..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp +++ /dev/null @@ -1,18 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=n -CONFIG_SMP=n -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP deleted file mode 100644 index 77a8c5b75763..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP +++ /dev/null @@ -1,30 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=16 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_NONE=n -CONFIG_RCU_NOCB_CPU_ZERO=n -CONFIG_RCU_NOCB_CPU_ALL=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_OBJECTS=y -CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_SLUB=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all deleted file mode 100644 index 0eecebc6e95f..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all +++ /dev/null @@ -1,30 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=16 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_NONE=y -CONFIG_RCU_NOCB_CPU_ZERO=n -CONFIG_RCU_NOCB_CPU_ALL=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_OBJECTS=y -CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_SLUB=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none deleted file mode 100644 index 0eecebc6e95f..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none +++ /dev/null @@ -1,30 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=16 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_NONE=y -CONFIG_RCU_NOCB_CPU_ZERO=n -CONFIG_RCU_NOCB_CPU_ALL=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_OBJECTS=y -CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_SLUB=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp deleted file mode 100644 index 588bc70420cd..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp +++ /dev/null @@ -1,30 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=16 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_NONE=n -CONFIG_RCU_NOCB_CPU_ZERO=y -CONFIG_RCU_NOCB_CPU_ALL=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_OBJECTS=y -CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_SLUB=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT1-nh deleted file mode 100644 index e3361c3894a1..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT1-nh +++ /dev/null @@ -1,23 +0,0 @@ -CONFIG_TINY_PREEMPT_RCU=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_RCU_TRACE=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=n -# -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT2-NH deleted file mode 100644 index 64abfc3b4d94..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/PT2-NH +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_TINY_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=y -# -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/CFLIST deleted file mode 100644 index 18223947bbcb..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/CFLIST +++ /dev/null @@ -1,14 +0,0 @@ -P1-S-T-NH-SD-SMP-HP -P2-2-t-nh-sd-SMP-hp -P3-3-T-nh-SD-SMP-hp -P4-A-t-NH-sd-SMP-HP -P5-U-T-NH-sd-SMP-hp -N1-S-T-NH-SD-SMP-HP -N2-2-t-nh-sd-SMP-hp -N3-3-T-nh-SD-SMP-hp -N4-A-t-NH-sd-SMP-HP -N5-U-T-NH-sd-SMP-hp -PT1-nh -PT2-NH -NT1-nh -NT3-NH diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N1-S-T-NH-SD-SMP-HP deleted file mode 100644 index d81e11d280aa..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N1-S-T-NH-SD-SMP-HP +++ /dev/null @@ -1,19 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_FAST_NO_HZ=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=8 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N2-2-t-nh-sd-SMP-hp deleted file mode 100644 index 02e418572b1b..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N2-2-t-nh-sd-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=4 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N3-3-T-nh-SD-SMP-hp deleted file mode 100644 index b3100f69c8cf..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N3-3-T-nh-SD-SMP-hp +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N4-A-t-NH-sd-SMP-HP deleted file mode 100644 index c56b44530725..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N4-A-t-NH-sd-SMP-HP +++ /dev/null @@ -1,18 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N5-U-T-NH-sd-SMP-hp deleted file mode 100644 index 90d924fea9e9..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/N5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_DEBUG_KERNEL=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT1-nh deleted file mode 100644 index 023f312a931c..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT1-nh +++ /dev/null @@ -1,23 +0,0 @@ -#CHECK#CONFIG_TINY_RCU=y -CONFIG_RCU_TRACE=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=n -# -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT3-NH deleted file mode 100644 index 6fd0235dae73..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/NT3-NH +++ /dev/null @@ -1,20 +0,0 @@ -#CHECK#CONFIG_TINY_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=y -# -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP deleted file mode 100644 index 9647c44cf4b7..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_RCU_FAST_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=8 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp deleted file mode 100644 index 0f3b667d2a9f..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=4 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp deleted file mode 100644 index b035e141bf2a..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP deleted file mode 100644 index 3ccf6a9447f5..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_RT_MUTEXES=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp deleted file mode 100644 index a55c00877fe4..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,27 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_OBJECTS=y -CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_RT_MUTEXES=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT1-nh deleted file mode 100644 index e3361c3894a1..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT1-nh +++ /dev/null @@ -1,23 +0,0 @@ -CONFIG_TINY_PREEMPT_RCU=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_RCU_TRACE=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=n -# -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT2-NH deleted file mode 100644 index 64abfc3b4d94..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/PT2-NH +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_TINY_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=y -# -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh deleted file mode 100644 index bae55692ce6e..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/ver_functions.sh +++ /dev/null @@ -1,44 +0,0 @@ -#!/bin/bash -# -# Kernel-version-dependent shell functions for the rest of the scripts. -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, you can access it online at -# http://www.gnu.org/licenses/gpl-2.0.html. -# -# Copyright (C) IBM Corporation, 2013 -# -# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> - -# rcutorture_param_onoff bootparam-string config-file -# -# Adds onoff rcutorture module parameters to kernels having it. -rcutorture_param_onoff () { - if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2" - then - echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2 - echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30 - fi -} - -# per_version_boot_params bootparam-string config-file seconds -# -# Adds per-version torture-module parameters to kernels supporting them. -per_version_boot_params () { - echo $1 `rcutorture_param_onoff "$1" "$2"` \ - rcutorture.stat_interval=15 \ - rcutorture.shutdown_secs=$3 \ - rcutorture.rcutorture_runnable=1 \ - rcutorture.test_no_idle_hz=1 \ - rcutorture.verbose=1 -} diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/CFLIST deleted file mode 100644 index 18223947bbcb..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/CFLIST +++ /dev/null @@ -1,14 +0,0 @@ -P1-S-T-NH-SD-SMP-HP -P2-2-t-nh-sd-SMP-hp -P3-3-T-nh-SD-SMP-hp -P4-A-t-NH-sd-SMP-HP -P5-U-T-NH-sd-SMP-hp -N1-S-T-NH-SD-SMP-HP -N2-2-t-nh-sd-SMP-hp -N3-3-T-nh-SD-SMP-hp -N4-A-t-NH-sd-SMP-HP -N5-U-T-NH-sd-SMP-hp -PT1-nh -PT2-NH -NT1-nh -NT3-NH diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N1-S-T-NH-SD-SMP-HP deleted file mode 100644 index d81e11d280aa..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N1-S-T-NH-SD-SMP-HP +++ /dev/null @@ -1,19 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_FAST_NO_HZ=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=8 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N2-2-t-nh-sd-SMP-hp deleted file mode 100644 index 02e418572b1b..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N2-2-t-nh-sd-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=4 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N3-3-T-nh-SD-SMP-hp deleted file mode 100644 index b3100f69c8cf..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N3-3-T-nh-SD-SMP-hp +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N4-A-t-NH-sd-SMP-HP deleted file mode 100644 index c56b44530725..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N4-A-t-NH-sd-SMP-HP +++ /dev/null @@ -1,18 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N5-U-T-NH-sd-SMP-hp deleted file mode 100644 index 90d924fea9e9..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/N5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_DEBUG_KERNEL=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -#CHECK#CONFIG_TREE_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT1-nh deleted file mode 100644 index 023f312a931c..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT1-nh +++ /dev/null @@ -1,23 +0,0 @@ -#CHECK#CONFIG_TINY_RCU=y -CONFIG_RCU_TRACE=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=n -# -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT3-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT3-NH deleted file mode 100644 index 6fd0235dae73..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/NT3-NH +++ /dev/null @@ -1,20 +0,0 @@ -#CHECK#CONFIG_TINY_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=y -# -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=n -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP deleted file mode 100644 index 9647c44cf4b7..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_RCU_FAST_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=8 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp deleted file mode 100644 index 0f3b667d2a9f..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=4 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp deleted file mode 100644 index b035e141bf2a..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp +++ /dev/null @@ -1,20 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_NO_HZ=n -CONFIG_SMP=y -CONFIG_RCU_FANOUT=2 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP deleted file mode 100644 index 3ccf6a9447f5..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_RCU_TRACE=n -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=n -CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_RT_MUTEXES=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp deleted file mode 100644 index a55c00877fe4..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,27 +0,0 @@ -CONFIG_RCU_TRACE=y -CONFIG_RCU_CPU_STALL_INFO=y -CONFIG_NO_HZ=y -CONFIG_SMP=y -CONFIG_RCU_FANOUT=6 -CONFIG_NR_CPUS=8 -CONFIG_RCU_FANOUT_EXACT=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_TREE_PREEMPT_RCU=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_OBJECTS=y -CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_RT_MUTEXES=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT1-nh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT1-nh deleted file mode 100644 index e3361c3894a1..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT1-nh +++ /dev/null @@ -1,23 +0,0 @@ -CONFIG_TINY_PREEMPT_RCU=y -CONFIG_RCU_BOOST=y -CONFIG_RCU_BOOST_PRIO=2 -CONFIG_RCU_TRACE=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=n -# -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT2-NH b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT2-NH deleted file mode 100644 index 64abfc3b4d94..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/PT2-NH +++ /dev/null @@ -1,22 +0,0 @@ -CONFIG_TINY_PREEMPT_RCU=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_MODULE_UNLOAD=y -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -# -CONFIG_SMP=n -# -CONFIG_HOTPLUG_CPU=n -# -CONFIG_NO_HZ=y -# -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU=y -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_PRINTK_TIME=y - diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh deleted file mode 100644 index 8977d8d31b19..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/ver_functions.sh +++ /dev/null @@ -1,57 +0,0 @@ -#!/bin/bash -# -# Kernel-version-dependent shell functions for the rest of the scripts. -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, you can access it online at -# http://www.gnu.org/licenses/gpl-2.0.html. -# -# Copyright (C) IBM Corporation, 2013 -# -# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> - -# rcutorture_param_n_barrier_cbs bootparam-string -# -# Adds n_barrier_cbs rcutorture module parameter to kernels having it. -rcutorture_param_n_barrier_cbs () { - if echo $1 | grep -q "rcutorture\.n_barrier_cbs" - then - : - else - echo rcutorture.n_barrier_cbs=4 - fi -} - -# rcutorture_param_onoff bootparam-string config-file -# -# Adds onoff rcutorture module parameters to kernels having it. -rcutorture_param_onoff () { - if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2" - then - echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2 - echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30 - fi -} - -# per_version_boot_params bootparam-string config-file seconds -# -# Adds per-version torture-module parameters to kernels supporting them. -per_version_boot_params () { - echo $1 `rcutorture_param_onoff "$1" "$2"` \ - `rcutorture_param_n_barrier_cbs "$1"` \ - rcutorture.stat_interval=15 \ - rcutorture.shutdown_secs=$3 \ - rcutorture.rcutorture_runnable=1 \ - rcutorture.test_no_idle_hz=1 \ - rcutorture.verbose=1 -} diff --git a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt index 28db67b54e55..9ef33a743b73 100644 --- a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt +++ b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt @@ -34,7 +34,7 @@ CONFIG_PREEMPT CONFIG_PREEMPT_RCU CONFIG_SMP CONFIG_TINY_RCU -CONFIG_TREE_PREEMPT_RCU +CONFIG_PREEMPT_RCU CONFIG_TREE_RCU All forced by CONFIG_TINY_RCU. diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index 3e588db86a17..ec03c883db00 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -1,5 +1,5 @@ This document gives a brief rationale for the TREE_RCU-related test -cases, a group that includes TREE_PREEMPT_RCU. +cases, a group that includes PREEMPT_RCU. Kconfig Parameters: @@ -14,10 +14,9 @@ CONFIG_NO_HZ_FULL_SYSIDLE -- Do one. CONFIG_PREEMPT -- Do half. (First three and #8.) CONFIG_PROVE_LOCKING -- Do all but two, covering CONFIG_PROVE_RCU and not. CONFIG_PROVE_RCU -- Do all but one under CONFIG_PROVE_LOCKING. -CONFIG_RCU_BOOST -- one of TREE_PREEMPT_RCU. -CONFIG_RCU_BOOST_PRIO -- set to 2 for _BOOST testing. -CONFIG_RCU_CPU_STALL_INFO -- do one with and without _VERBOSE. -CONFIG_RCU_CPU_STALL_VERBOSE -- do one with and without _INFO. +CONFIG_RCU_BOOST -- one of PREEMPT_RCU. +CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing. +CONFIG_RCU_CPU_STALL_INFO -- Do one. CONFIG_RCU_FANOUT -- Cover hierarchy as currently, but overlap with others. CONFIG_RCU_FANOUT_EXACT -- Do one. CONFIG_RCU_FANOUT_LEAF -- Do one non-default. @@ -27,7 +26,7 @@ CONFIG_RCU_NOCB_CPU_ALL -- Do one. CONFIG_RCU_NOCB_CPU_NONE -- Do one. CONFIG_RCU_NOCB_CPU_ZERO -- Do one. CONFIG_RCU_TRACE -- Do half. -CONFIG_SMP -- Need one !SMP for TREE_PREEMPT_RCU. +CONFIG_SMP -- Need one !SMP for PREEMPT_RCU. RCU-bh: Do one with PREEMPT and one with !PREEMPT. RCU-sched: Do one with PREEMPT but not BOOST. @@ -77,7 +76,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT CONFIG_RCU_STALL_COMMON - Implied by TREE_RCU and TREE_PREEMPT_RCU. + Implied by TREE_RCU and PREEMPT_RCU. CONFIG_RCU_TORTURE_TEST CONFIG_RCU_TORTURE_TEST_RUNNABLE @@ -88,7 +87,7 @@ CONFIG_RCU_USER_QS Redundant with CONFIG_NO_HZ_FULL. -CONFIG_TREE_PREEMPT_RCU +CONFIG_PREEMPT_RCU CONFIG_TREE_RCU These are controlled by CONFIG_PREEMPT. diff --git a/tools/testing/selftests/size/.gitignore b/tools/testing/selftests/size/.gitignore new file mode 100644 index 000000000000..189b7818de34 --- /dev/null +++ b/tools/testing/selftests/size/.gitignore @@ -0,0 +1 @@ +get_size diff --git a/tools/testing/selftests/size/Makefile b/tools/testing/selftests/size/Makefile new file mode 100644 index 000000000000..bbd0b5398b61 --- /dev/null +++ b/tools/testing/selftests/size/Makefile @@ -0,0 +1,11 @@ +all: get_size + +get_size: get_size.c + $(CC) -static -ffreestanding -nostartfiles -s $< -o $@ + +TEST_PROGS := get_size + +include ../lib.mk + +clean: + $(RM) get_size diff --git a/tools/testing/selftests/size/get_size.c b/tools/testing/selftests/size/get_size.c new file mode 100644 index 000000000000..2d1af7cca463 --- /dev/null +++ b/tools/testing/selftests/size/get_size.c @@ -0,0 +1,100 @@ +/* + * Copyright 2014 Sony Mobile Communications Inc. + * + * Licensed under the terms of the GNU GPL License version 2 + * + * Selftest for runtime system size + * + * Prints the amount of RAM that the currently running system is using. + * + * This program tries to be as small as possible itself, to + * avoid perturbing the system memory utilization with its + * own execution. It also attempts to have as few dependencies + * on kernel features as possible. + * + * It should be statically linked, with startup libs avoided. + * It uses no library calls, and only the following 3 syscalls: + * sysinfo(), write(), and _exit() + * + * For output, it avoids printf (which in some C libraries + * has large external dependencies) by implementing it's own + * number output and print routines, and using __builtin_strlen() + */ + +#include <sys/sysinfo.h> +#include <unistd.h> + +#define STDOUT_FILENO 1 + +static int print(const char *s) +{ + return write(STDOUT_FILENO, s, __builtin_strlen(s)); +} + +static inline char *num_to_str(unsigned long num, char *buf, int len) +{ + unsigned int digit; + + /* put digits in buffer from back to front */ + buf += len - 1; + *buf = 0; + do { + digit = num % 10; + *(--buf) = digit + '0'; + num /= 10; + } while (num > 0); + + return buf; +} + +static int print_num(unsigned long num) +{ + char num_buf[30]; + + return print(num_to_str(num, num_buf, sizeof(num_buf))); +} + +static int print_k_value(const char *s, unsigned long num, unsigned long units) +{ + unsigned long long temp; + int ccode; + + print(s); + + temp = num; + temp = (temp * units)/1024; + num = temp; + ccode = print_num(num); + print("\n"); + return ccode; +} + +/* this program has no main(), as startup libraries are not used */ +void _start(void) +{ + int ccode; + struct sysinfo info; + unsigned long used; + + print("Testing system size.\n"); + print("1..1\n"); + + ccode = sysinfo(&info); + if (ccode < 0) { + print("not ok 1 get runtime memory use\n"); + print("# could not get sysinfo\n"); + _exit(ccode); + } + /* ignore cache complexities for now */ + used = info.totalram - info.freeram - info.bufferram; + print_k_value("ok 1 get runtime memory use # size = ", used, + info.mem_unit); + + print("# System runtime memory report (units in Kilobytes):\n"); + print_k_value("# Total: ", info.totalram, info.mem_unit); + print_k_value("# Free: ", info.freeram, info.mem_unit); + print_k_value("# Buffer: ", info.bufferram, info.mem_unit); + print_k_value("# In use: ", used, info.mem_unit); + + _exit(0); +} diff --git a/tools/testing/selftests/sysctl/Makefile b/tools/testing/selftests/sysctl/Makefile index 0a92adaf0865..b3c33e071f10 100644 --- a/tools/testing/selftests/sysctl/Makefile +++ b/tools/testing/selftests/sysctl/Makefile @@ -4,16 +4,10 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests". all: -# Allow specific tests to be selected. -test_num: - @/bin/sh ./run_numerictests +TEST_PROGS := run_numerictests run_stringtests +TEST_FILES := common_tests -test_string: - @/bin/sh ./run_stringtests - -run_tests: all test_num test_string +include ../lib.mk # Nothing to clean up. clean: - -.PHONY: all run_tests clean test_num test_string diff --git a/tools/testing/selftests/sysctl/run_numerictests b/tools/testing/selftests/sysctl/run_numerictests index 8510f93f2d14..8510f93f2d14 100644..100755 --- a/tools/testing/selftests/sysctl/run_numerictests +++ b/tools/testing/selftests/sysctl/run_numerictests diff --git a/tools/testing/selftests/sysctl/run_stringtests b/tools/testing/selftests/sysctl/run_stringtests index 90a9293d520c..90a9293d520c 100644..100755 --- a/tools/testing/selftests/sysctl/run_stringtests +++ b/tools/testing/selftests/sysctl/run_stringtests diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index eb2859f4ad21..89a3f44bf355 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -1,8 +1,36 @@ -all: - gcc posix_timers.c -o posix_timers -lrt +CC = $(CROSS_COMPILE)gcc +BUILD_FLAGS = -DKTEST +CFLAGS += -O3 -Wl,-no-as-needed -Wall $(BUILD_FLAGS) +LDFLAGS += -lrt -lpthread -run_tests: all - ./posix_timers +# these are all "safe" tests that don't modify +# system time or require escalated privledges +TEST_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \ + inconsistency-check raw_skew threadtest rtctest + +TEST_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex change_skew \ + skew_consistency clocksource-switch leap-a-day \ + leapcrash set-tai set-2038 + +bins = $(TEST_PROGS) $(TEST_PROGS_EXTENDED) + +all: ${bins} + +include ../lib.mk + +# these tests require escalated privledges +# and may modify the system time or trigger +# other behavior like suspend +run_destructive_tests: run_tests + ./alarmtimer-suspend + ./valid-adjtimex + ./change_skew + ./skew_consistency + ./clocksource-switch + ./leap-a-day -s -i 10 + ./leapcrash + ./set-tai + ./set-2038 clean: - rm -f ./posix_timers + rm -f ${bins} diff --git a/tools/testing/selftests/timers/alarmtimer-suspend.c b/tools/testing/selftests/timers/alarmtimer-suspend.c new file mode 100644 index 000000000000..aaffbde1d5ee --- /dev/null +++ b/tools/testing/selftests/timers/alarmtimer-suspend.c @@ -0,0 +1,185 @@ +/* alarmtimer suspend test + * John Stultz (john.stultz@linaro.org) + * (C) Copyright Linaro 2013 + * Licensed under the GPLv2 + * + * This test makes sure the alarmtimer & RTC wakeup code is + * functioning. + * + * To build: + * $ gcc alarmtimer-suspend.c -o alarmtimer-suspend -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <unistd.h> +#include <time.h> +#include <string.h> +#include <signal.h> +#include <stdlib.h> +#include <pthread.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define CLOCK_REALTIME 0 +#define CLOCK_MONOTONIC 1 +#define CLOCK_PROCESS_CPUTIME_ID 2 +#define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 +#define CLOCK_BOOTTIME 7 +#define CLOCK_REALTIME_ALARM 8 +#define CLOCK_BOOTTIME_ALARM 9 +#define CLOCK_HWSPECIFIC 10 +#define CLOCK_TAI 11 +#define NR_CLOCKIDS 12 + + +#define NSEC_PER_SEC 1000000000ULL +#define UNREASONABLE_LAT (NSEC_PER_SEC * 4) /* hopefully we resume in 4secs */ + +#define SUSPEND_SECS 15 +int alarmcount; +int alarm_clock_id; +struct timespec start_time; + + +char *clockstring(int clockid) +{ + switch (clockid) { + case CLOCK_REALTIME: + return "CLOCK_REALTIME"; + case CLOCK_MONOTONIC: + return "CLOCK_MONOTONIC"; + case CLOCK_PROCESS_CPUTIME_ID: + return "CLOCK_PROCESS_CPUTIME_ID"; + case CLOCK_THREAD_CPUTIME_ID: + return "CLOCK_THREAD_CPUTIME_ID"; + case CLOCK_MONOTONIC_RAW: + return "CLOCK_MONOTONIC_RAW"; + case CLOCK_REALTIME_COARSE: + return "CLOCK_REALTIME_COARSE"; + case CLOCK_MONOTONIC_COARSE: + return "CLOCK_MONOTONIC_COARSE"; + case CLOCK_BOOTTIME: + return "CLOCK_BOOTTIME"; + case CLOCK_REALTIME_ALARM: + return "CLOCK_REALTIME_ALARM"; + case CLOCK_BOOTTIME_ALARM: + return "CLOCK_BOOTTIME_ALARM"; + case CLOCK_TAI: + return "CLOCK_TAI"; + }; + return "UNKNOWN_CLOCKID"; +} + + +long long timespec_sub(struct timespec a, struct timespec b) +{ + long long ret = NSEC_PER_SEC * b.tv_sec + b.tv_nsec; + + ret -= NSEC_PER_SEC * a.tv_sec + a.tv_nsec; + return ret; +} + +int final_ret = 0; + +void sigalarm(int signo) +{ + long long delta_ns; + struct timespec ts; + + clock_gettime(alarm_clock_id, &ts); + alarmcount++; + + delta_ns = timespec_sub(start_time, ts); + delta_ns -= NSEC_PER_SEC * SUSPEND_SECS * alarmcount; + + printf("ALARM(%i): %ld:%ld latency: %lld ns ", alarmcount, ts.tv_sec, + ts.tv_nsec, delta_ns); + + if (delta_ns > UNREASONABLE_LAT) { + printf("[FAIL]\n"); + final_ret = -1; + } else + printf("[OK]\n"); + +} + +int main(void) +{ + timer_t tm1; + struct itimerspec its1, its2; + struct sigevent se; + struct sigaction act; + int signum = SIGRTMAX; + + /* Set up signal handler: */ + sigfillset(&act.sa_mask); + act.sa_flags = 0; + act.sa_handler = sigalarm; + sigaction(signum, &act, NULL); + + /* Set up timer: */ + memset(&se, 0, sizeof(se)); + se.sigev_notify = SIGEV_SIGNAL; + se.sigev_signo = signum; + se.sigev_value.sival_int = 0; + + for (alarm_clock_id = CLOCK_REALTIME_ALARM; + alarm_clock_id <= CLOCK_BOOTTIME_ALARM; + alarm_clock_id++) { + + alarmcount = 0; + timer_create(alarm_clock_id, &se, &tm1); + + clock_gettime(alarm_clock_id, &start_time); + printf("Start time (%s): %ld:%ld\n", clockstring(alarm_clock_id), + start_time.tv_sec, start_time.tv_nsec); + printf("Setting alarm for every %i seconds\n", SUSPEND_SECS); + its1.it_value = start_time; + its1.it_value.tv_sec += SUSPEND_SECS; + its1.it_interval.tv_sec = SUSPEND_SECS; + its1.it_interval.tv_nsec = 0; + + timer_settime(tm1, TIMER_ABSTIME, &its1, &its2); + + while (alarmcount < 5) + sleep(1); /* First 5 alarms, do nothing */ + + printf("Starting suspend loops\n"); + while (alarmcount < 10) { + int ret; + + sleep(1); + ret = system("echo mem > /sys/power/state"); + if (ret) + break; + } + timer_delete(tm1); + } + if (final_ret) + return ksft_exit_fail(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/change_skew.c b/tools/testing/selftests/timers/change_skew.c new file mode 100644 index 000000000000..cb1968977c04 --- /dev/null +++ b/tools/testing/selftests/timers/change_skew.c @@ -0,0 +1,107 @@ +/* ADJ_FREQ Skew change test + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2012 + * Licensed under the GPLv2 + * + * NOTE: This is a meta-test which cranks the ADJ_FREQ knob and + * then uses other tests to detect problems. Thus this test requires + * that the raw_skew, inconsistency-check and nanosleep tests be + * present in the same directory it is run from. + * + * To build: + * $ gcc change_skew.c -o change_skew -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <stdlib.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <time.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000LL + + +int change_skew_test(int ppm) +{ + struct timex tx; + int ret; + + tx.modes = ADJ_FREQUENCY; + tx.freq = ppm << 16; + + ret = adjtimex(&tx); + if (ret < 0) { + printf("Error adjusting freq\n"); + return ret; + } + + ret = system("./raw_skew"); + ret |= system("./inconsistency-check"); + ret |= system("./nanosleep"); + + return ret; +} + + +int main(int argv, char **argc) +{ + struct timex tx; + int i, ret; + + int ppm[5] = {0, 250, 500, -250, -500}; + + /* Kill ntpd */ + ret = system("killall -9 ntpd"); + + /* Make sure there's no offset adjustment going on */ + tx.modes = ADJ_OFFSET; + tx.offset = 0; + ret = adjtimex(&tx); + + if (ret < 0) { + printf("Maybe you're not running as root?\n"); + return -1; + } + + for (i = 0; i < 5; i++) { + printf("Using %i ppm adjustment\n", ppm[i]); + ret = change_skew_test(ppm[i]); + if (ret) + break; + } + + /* Set things back */ + tx.modes = ADJ_FREQUENCY; + tx.offset = 0; + adjtimex(&tx); + + if (ret) { + printf("[FAIL]"); + return ksft_exit_fail(); + } + printf("[OK]"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/clocksource-switch.c b/tools/testing/selftests/timers/clocksource-switch.c new file mode 100644 index 000000000000..627ec7425f78 --- /dev/null +++ b/tools/testing/selftests/timers/clocksource-switch.c @@ -0,0 +1,179 @@ +/* Clocksource change test + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2012 + * Licensed under the GPLv2 + * + * NOTE: This is a meta-test which quickly changes the clocksourc and + * then uses other tests to detect problems. Thus this test requires + * that the inconsistency-check and nanosleep tests be present in the + * same directory it is run from. + * + * To build: + * $ gcc clocksource-switch.c -o clocksource-switch -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <time.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <string.h> +#include <sys/wait.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + + +int get_clocksources(char list[][30]) +{ + int fd, i; + size_t size; + char buf[512]; + char *head, *tmp; + + fd = open("/sys/devices/system/clocksource/clocksource0/available_clocksource", O_RDONLY); + + size = read(fd, buf, 512); + + close(fd); + + for (i = 0; i < 30; i++) + list[i][0] = '\0'; + + head = buf; + i = 0; + while (head - buf < size) { + /* Find the next space */ + for (tmp = head; *tmp != ' '; tmp++) { + if (*tmp == '\n') + break; + if (*tmp == '\0') + break; + } + *tmp = '\0'; + strcpy(list[i], head); + head = tmp + 1; + i++; + } + + return i-1; +} + +int get_cur_clocksource(char *buf, size_t size) +{ + int fd; + + fd = open("/sys/devices/system/clocksource/clocksource0/current_clocksource", O_RDONLY); + + size = read(fd, buf, size); + + return 0; +} + +int change_clocksource(char *clocksource) +{ + int fd; + size_t size; + + fd = open("/sys/devices/system/clocksource/clocksource0/current_clocksource", O_WRONLY); + + if (fd < 0) + return -1; + + size = write(fd, clocksource, strlen(clocksource)); + + if (size < 0) + return -1; + + close(fd); + return 0; +} + + +int run_tests(int secs) +{ + int ret; + char buf[255]; + + sprintf(buf, "./inconsistency-check -t %i", secs); + ret = system(buf); + if (ret) + return ret; + ret = system("./nanosleep"); + return ret; +} + + +char clocksource_list[10][30]; + +int main(int argv, char **argc) +{ + char orig_clk[512]; + int count, i, status; + pid_t pid; + + get_cur_clocksource(orig_clk, 512); + + count = get_clocksources(clocksource_list); + + if (change_clocksource(clocksource_list[0])) { + printf("Error: You probably need to run this as root\n"); + return -1; + } + + /* Check everything is sane before we start switching asyncrhonously */ + for (i = 0; i < count; i++) { + printf("Validating clocksource %s\n", clocksource_list[i]); + if (change_clocksource(clocksource_list[i])) { + status = -1; + goto out; + } + if (run_tests(5)) { + status = -1; + goto out; + } + } + + + printf("Running Asyncrhonous Switching Tests...\n"); + pid = fork(); + if (!pid) + return run_tests(60); + + while (pid != waitpid(pid, &status, WNOHANG)) + for (i = 0; i < count; i++) + if (change_clocksource(clocksource_list[i])) { + status = -1; + goto out; + } +out: + change_clocksource(orig_clk); + + if (status) + return ksft_exit_fail(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/inconsistency-check.c b/tools/testing/selftests/timers/inconsistency-check.c new file mode 100644 index 000000000000..caf1bc9257c4 --- /dev/null +++ b/tools/testing/selftests/timers/inconsistency-check.c @@ -0,0 +1,204 @@ +/* Time inconsistency check test + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2003, 2004, 2005, 2012 + * (C) Copyright Linaro Limited 2015 + * Licensed under the GPLv2 + * + * To build: + * $ gcc inconsistency-check.c -o inconsistency-check -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + + +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define CALLS_PER_LOOP 64 +#define NSEC_PER_SEC 1000000000ULL + +#define CLOCK_REALTIME 0 +#define CLOCK_MONOTONIC 1 +#define CLOCK_PROCESS_CPUTIME_ID 2 +#define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 +#define CLOCK_BOOTTIME 7 +#define CLOCK_REALTIME_ALARM 8 +#define CLOCK_BOOTTIME_ALARM 9 +#define CLOCK_HWSPECIFIC 10 +#define CLOCK_TAI 11 +#define NR_CLOCKIDS 12 + +char *clockstring(int clockid) +{ + switch (clockid) { + case CLOCK_REALTIME: + return "CLOCK_REALTIME"; + case CLOCK_MONOTONIC: + return "CLOCK_MONOTONIC"; + case CLOCK_PROCESS_CPUTIME_ID: + return "CLOCK_PROCESS_CPUTIME_ID"; + case CLOCK_THREAD_CPUTIME_ID: + return "CLOCK_THREAD_CPUTIME_ID"; + case CLOCK_MONOTONIC_RAW: + return "CLOCK_MONOTONIC_RAW"; + case CLOCK_REALTIME_COARSE: + return "CLOCK_REALTIME_COARSE"; + case CLOCK_MONOTONIC_COARSE: + return "CLOCK_MONOTONIC_COARSE"; + case CLOCK_BOOTTIME: + return "CLOCK_BOOTTIME"; + case CLOCK_REALTIME_ALARM: + return "CLOCK_REALTIME_ALARM"; + case CLOCK_BOOTTIME_ALARM: + return "CLOCK_BOOTTIME_ALARM"; + case CLOCK_TAI: + return "CLOCK_TAI"; + }; + return "UNKNOWN_CLOCKID"; +} + +/* returns 1 if a <= b, 0 otherwise */ +static inline int in_order(struct timespec a, struct timespec b) +{ + /* use unsigned to avoid false positives on 2038 rollover */ + if ((unsigned long)a.tv_sec < (unsigned long)b.tv_sec) + return 1; + if ((unsigned long)a.tv_sec > (unsigned long)b.tv_sec) + return 0; + if (a.tv_nsec > b.tv_nsec) + return 0; + return 1; +} + + + +int consistency_test(int clock_type, unsigned long seconds) +{ + struct timespec list[CALLS_PER_LOOP]; + int i, inconsistent; + long now, then; + time_t t; + char *start_str; + + clock_gettime(clock_type, &list[0]); + now = then = list[0].tv_sec; + + /* timestamp start of test */ + t = time(0); + start_str = ctime(&t); + + while (seconds == -1 || now - then < seconds) { + inconsistent = 0; + + /* Fill list */ + for (i = 0; i < CALLS_PER_LOOP; i++) + clock_gettime(clock_type, &list[i]); + + /* Check for inconsistencies */ + for (i = 0; i < CALLS_PER_LOOP - 1; i++) + if (!in_order(list[i], list[i+1])) + inconsistent = i; + + /* display inconsistency */ + if (inconsistent) { + unsigned long long delta; + + printf("\%s\n", start_str); + for (i = 0; i < CALLS_PER_LOOP; i++) { + if (i == inconsistent) + printf("--------------------\n"); + printf("%lu:%lu\n", list[i].tv_sec, + list[i].tv_nsec); + if (i == inconsistent + 1) + printf("--------------------\n"); + } + delta = list[inconsistent].tv_sec * NSEC_PER_SEC; + delta += list[inconsistent].tv_nsec; + delta -= list[inconsistent+1].tv_sec * NSEC_PER_SEC; + delta -= list[inconsistent+1].tv_nsec; + printf("Delta: %llu ns\n", delta); + fflush(0); + /* timestamp inconsistency*/ + t = time(0); + printf("%s\n", ctime(&t)); + printf("[FAILED]\n"); + return -1; + } + now = list[0].tv_sec; + } + printf("[OK]\n"); + return 0; +} + + +int main(int argc, char *argv[]) +{ + int clockid, opt; + int userclock = CLOCK_REALTIME; + int maxclocks = NR_CLOCKIDS; + int runtime = 10; + struct timespec ts; + + /* Process arguments */ + while ((opt = getopt(argc, argv, "t:c:")) != -1) { + switch (opt) { + case 't': + runtime = atoi(optarg); + break; + case 'c': + userclock = atoi(optarg); + maxclocks = userclock + 1; + break; + default: + printf("Usage: %s [-t <secs>] [-c <clockid>]\n", argv[0]); + printf(" -t: Number of seconds to run\n"); + printf(" -c: clockid to use (default, all clockids)\n"); + exit(-1); + } + } + + setbuf(stdout, NULL); + + for (clockid = userclock; clockid < maxclocks; clockid++) { + + if (clockid == CLOCK_HWSPECIFIC) + continue; + + if (!clock_gettime(clockid, &ts)) { + printf("Consistent %-30s ", clockstring(clockid)); + if (consistency_test(clockid, runtime)) + return ksft_exit_fail(); + } + } + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/leap-a-day.c b/tools/testing/selftests/timers/leap-a-day.c new file mode 100644 index 000000000000..b8272e6c4b3b --- /dev/null +++ b/tools/testing/selftests/timers/leap-a-day.c @@ -0,0 +1,319 @@ +/* Leap second stress test + * by: John Stultz (john.stultz@linaro.org) + * (C) Copyright IBM 2012 + * (C) Copyright 2013, 2015 Linaro Limited + * Licensed under the GPLv2 + * + * This test signals the kernel to insert a leap second + * every day at midnight GMT. This allows for stessing the + * kernel's leap-second behavior, as well as how well applications + * handle the leap-second discontinuity. + * + * Usage: leap-a-day [-s] [-i <num>] + * + * Options: + * -s: Each iteration, set the date to 10 seconds before midnight GMT. + * This speeds up the number of leapsecond transitions tested, + * but because it calls settimeofday frequently, advancing the + * time by 24 hours every ~16 seconds, it may cause application + * disruption. + * + * -i: Number of iterations to run (default: infinite) + * + * Other notes: Disabling NTP prior to running this is advised, as the two + * may conflict in their commands to the kernel. + * + * To build: + * $ gcc leap-a-day.c -o leap-a-day -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000ULL +#define CLOCK_TAI 11 + +/* returns 1 if a <= b, 0 otherwise */ +static inline int in_order(struct timespec a, struct timespec b) +{ + if (a.tv_sec < b.tv_sec) + return 1; + if (a.tv_sec > b.tv_sec) + return 0; + if (a.tv_nsec > b.tv_nsec) + return 0; + return 1; +} + +struct timespec timespec_add(struct timespec ts, unsigned long long ns) +{ + ts.tv_nsec += ns; + while (ts.tv_nsec >= NSEC_PER_SEC) { + ts.tv_nsec -= NSEC_PER_SEC; + ts.tv_sec++; + } + return ts; +} + +char *time_state_str(int state) +{ + switch (state) { + case TIME_OK: return "TIME_OK"; + case TIME_INS: return "TIME_INS"; + case TIME_DEL: return "TIME_DEL"; + case TIME_OOP: return "TIME_OOP"; + case TIME_WAIT: return "TIME_WAIT"; + case TIME_BAD: return "TIME_BAD"; + } + return "ERROR"; +} + +/* clear NTP time_status & time_state */ +int clear_time_state(void) +{ + struct timex tx; + int ret; + + /* + * We have to call adjtime twice here, as kernels + * prior to 6b1859dba01c7 (included in 3.5 and + * -stable), had an issue with the state machine + * and wouldn't clear the STA_INS/DEL flag directly. + */ + tx.modes = ADJ_STATUS; + tx.status = STA_PLL; + ret = adjtimex(&tx); + + /* Clear maxerror, as it can cause UNSYNC to be set */ + tx.modes = ADJ_MAXERROR; + tx.maxerror = 0; + ret = adjtimex(&tx); + + /* Clear the status */ + tx.modes = ADJ_STATUS; + tx.status = 0; + ret = adjtimex(&tx); + + return ret; +} + +/* Make sure we cleanup on ctrl-c */ +void handler(int unused) +{ + clear_time_state(); + exit(0); +} + +/* Test for known hrtimer failure */ +void test_hrtimer_failure(void) +{ + struct timespec now, target; + + clock_gettime(CLOCK_REALTIME, &now); + target = timespec_add(now, NSEC_PER_SEC/2); + clock_nanosleep(CLOCK_REALTIME, TIMER_ABSTIME, &target, NULL); + clock_gettime(CLOCK_REALTIME, &now); + + if (!in_order(target, now)) + printf("ERROR: hrtimer early expiration failure observed.\n"); +} + +int main(int argc, char **argv) +{ + int settime = 0; + int tai_time = 0; + int insert = 1; + int iterations = -1; + int opt; + + /* Process arguments */ + while ((opt = getopt(argc, argv, "sti:")) != -1) { + switch (opt) { + case 's': + printf("Setting time to speed up testing\n"); + settime = 1; + break; + case 'i': + iterations = atoi(optarg); + break; + case 't': + tai_time = 1; + break; + default: + printf("Usage: %s [-s] [-i <iterations>]\n", argv[0]); + printf(" -s: Set time to right before leap second each iteration\n"); + printf(" -i: Number of iterations\n"); + printf(" -t: Print TAI time\n"); + exit(-1); + } + } + + /* Make sure TAI support is present if -t was used */ + if (tai_time) { + struct timespec ts; + + if (clock_gettime(CLOCK_TAI, &ts)) { + printf("System doesn't support CLOCK_TAI\n"); + ksft_exit_fail(); + } + } + + signal(SIGINT, handler); + signal(SIGKILL, handler); + + if (iterations < 0) + printf("This runs continuously. Press ctrl-c to stop\n"); + else + printf("Running for %i iterations. Press ctrl-c to stop\n", iterations); + + printf("\n"); + while (1) { + int ret; + struct timespec ts; + struct timex tx; + time_t now, next_leap; + + /* Get the current time */ + clock_gettime(CLOCK_REALTIME, &ts); + + /* Calculate the next possible leap second 23:59:60 GMT */ + next_leap = ts.tv_sec; + next_leap += 86400 - (next_leap % 86400); + + if (settime) { + struct timeval tv; + + tv.tv_sec = next_leap - 10; + tv.tv_usec = 0; + settimeofday(&tv, NULL); + printf("Setting time to %s", ctime(&tv.tv_sec)); + } + + /* Reset NTP time state */ + clear_time_state(); + + /* Set the leap second insert flag */ + tx.modes = ADJ_STATUS; + if (insert) + tx.status = STA_INS; + else + tx.status = STA_DEL; + ret = adjtimex(&tx); + if (ret < 0) { + printf("Error: Problem setting STA_INS/STA_DEL!: %s\n", + time_state_str(ret)); + return ksft_exit_fail(); + } + + /* Validate STA_INS was set */ + tx.modes = 0; + ret = adjtimex(&tx); + if (tx.status != STA_INS && tx.status != STA_DEL) { + printf("Error: STA_INS/STA_DEL not set!: %s\n", + time_state_str(ret)); + return ksft_exit_fail(); + } + + if (tai_time) { + printf("Using TAI time," + " no inconsistencies should be seen!\n"); + } + + printf("Scheduling leap second for %s", ctime(&next_leap)); + + /* Wake up 3 seconds before leap */ + ts.tv_sec = next_leap - 3; + ts.tv_nsec = 0; + + while (clock_nanosleep(CLOCK_REALTIME, TIMER_ABSTIME, &ts, NULL)) + printf("Something woke us up, returning to sleep\n"); + + /* Validate STA_INS is still set */ + tx.modes = 0; + ret = adjtimex(&tx); + if (tx.status != STA_INS && tx.status != STA_DEL) { + printf("Something cleared STA_INS/STA_DEL, setting it again.\n"); + tx.modes = ADJ_STATUS; + if (insert) + tx.status = STA_INS; + else + tx.status = STA_DEL; + ret = adjtimex(&tx); + } + + /* Check adjtimex output every half second */ + now = tx.time.tv_sec; + while (now < next_leap + 2) { + char buf[26]; + struct timespec tai; + + tx.modes = 0; + ret = adjtimex(&tx); + + if (tai_time) { + clock_gettime(CLOCK_TAI, &tai); + printf("%ld sec, %9ld ns\t%s\n", + tai.tv_sec, + tai.tv_nsec, + time_state_str(ret)); + } else { + ctime_r(&tx.time.tv_sec, buf); + buf[strlen(buf)-1] = 0; /*remove trailing\n */ + + printf("%s + %6ld us (%i)\t%s\n", + buf, + tx.time.tv_usec, + tx.tai, + time_state_str(ret)); + } + now = tx.time.tv_sec; + /* Sleep for another half second */ + ts.tv_sec = 0; + ts.tv_nsec = NSEC_PER_SEC / 2; + clock_nanosleep(CLOCK_MONOTONIC, 0, &ts, NULL); + } + /* Switch to using other mode */ + insert = !insert; + + /* Note if kernel has known hrtimer failure */ + test_hrtimer_failure(); + + printf("Leap complete\n\n"); + + if ((iterations != -1) && !(--iterations)) + break; + } + + clear_time_state(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/leapcrash.c b/tools/testing/selftests/timers/leapcrash.c new file mode 100644 index 000000000000..a1071bdbdeb7 --- /dev/null +++ b/tools/testing/selftests/timers/leapcrash.c @@ -0,0 +1,120 @@ +/* Demo leapsecond deadlock + * by: John Stultz (john.stultz@linaro.org) + * (C) Copyright IBM 2012 + * (C) Copyright 2013, 2015 Linaro Limited + * Licensed under the GPL + * + * This test demonstrates leapsecond deadlock that is possibe + * on kernels from 2.6.26 to 3.3. + * + * WARNING: THIS WILL LIKELY HARDHANG SYSTEMS AND MAY LOSE DATA + * RUN AT YOUR OWN RISK! + * To build: + * $ gcc leapcrash.c -o leapcrash -lrt + */ + + + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + + + +/* clear NTP time_status & time_state */ +int clear_time_state(void) +{ + struct timex tx; + int ret; + + /* + * We have to call adjtime twice here, as kernels + * prior to 6b1859dba01c7 (included in 3.5 and + * -stable), had an issue with the state machine + * and wouldn't clear the STA_INS/DEL flag directly. + */ + tx.modes = ADJ_STATUS; + tx.status = STA_PLL; + ret = adjtimex(&tx); + + tx.modes = ADJ_STATUS; + tx.status = 0; + ret = adjtimex(&tx); + + return ret; +} + +/* Make sure we cleanup on ctrl-c */ +void handler(int unused) +{ + clear_time_state(); + exit(0); +} + + +int main(void) +{ + struct timex tx; + struct timespec ts; + time_t next_leap; + int count = 0; + + setbuf(stdout, NULL); + + signal(SIGINT, handler); + signal(SIGKILL, handler); + printf("This runs for a few minutes. Press ctrl-c to stop\n"); + + clear_time_state(); + + + /* Get the current time */ + clock_gettime(CLOCK_REALTIME, &ts); + + /* Calculate the next possible leap second 23:59:60 GMT */ + next_leap = ts.tv_sec; + next_leap += 86400 - (next_leap % 86400); + + for (count = 0; count < 20; count++) { + struct timeval tv; + + + /* set the time to 2 seconds before the leap */ + tv.tv_sec = next_leap - 2; + tv.tv_usec = 0; + if (settimeofday(&tv, NULL)) { + printf("Error: You're likely not running with proper (ie: root) permissions\n"); + return ksft_exit_fail(); + } + tx.modes = 0; + adjtimex(&tx); + + /* hammer on adjtime w/ STA_INS */ + while (tx.time.tv_sec < next_leap + 1) { + /* Set the leap second insert flag */ + tx.modes = ADJ_STATUS; + tx.status = STA_INS; + adjtimex(&tx); + } + clear_time_state(); + printf("."); + } + printf("[OK]\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/mqueue-lat.c b/tools/testing/selftests/timers/mqueue-lat.c new file mode 100644 index 000000000000..a2a3924d0b41 --- /dev/null +++ b/tools/testing/selftests/timers/mqueue-lat.c @@ -0,0 +1,124 @@ +/* Measure mqueue timeout latency + * by: john stultz (john.stultz@linaro.org) + * (C) Copyright Linaro 2013 + * + * Inspired with permission from example test by: + * Romain Francoise <romain@orebokech.com> + * Licensed under the GPLv2 + * + * To build: + * $ gcc mqueue-lat.c -o mqueue-lat -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#include <errno.h> +#include <mqueue.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000ULL + +#define TARGET_TIMEOUT 100000000 /* 100ms in nanoseconds */ +#define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ + + +long long timespec_sub(struct timespec a, struct timespec b) +{ + long long ret = NSEC_PER_SEC * b.tv_sec + b.tv_nsec; + + ret -= NSEC_PER_SEC * a.tv_sec + a.tv_nsec; + return ret; +} + +struct timespec timespec_add(struct timespec ts, unsigned long long ns) +{ + ts.tv_nsec += ns; + while (ts.tv_nsec >= NSEC_PER_SEC) { + ts.tv_nsec -= NSEC_PER_SEC; + ts.tv_sec++; + } + return ts; +} + +int mqueue_lat_test(void) +{ + + mqd_t q; + struct mq_attr attr; + struct timespec start, end, now, target; + int i, count, ret; + + q = mq_open("/foo", O_CREAT | O_RDONLY, 0666, NULL); + if (q < 0) { + perror("mq_open"); + return -1; + } + mq_getattr(q, &attr); + + + count = 100; + clock_gettime(CLOCK_MONOTONIC, &start); + + for (i = 0; i < count; i++) { + char buf[attr.mq_msgsize]; + + clock_gettime(CLOCK_REALTIME, &now); + target = now; + target = timespec_add(now, TARGET_TIMEOUT); /* 100ms */ + + ret = mq_timedreceive(q, buf, sizeof(buf), NULL, &target); + if (ret < 0 && errno != ETIMEDOUT) { + perror("mq_timedreceive"); + return -1; + } + } + clock_gettime(CLOCK_MONOTONIC, &end); + + mq_close(q); + + if ((timespec_sub(start, end)/count) > TARGET_TIMEOUT + UNRESONABLE_LATENCY) + return -1; + + return 0; +} + +int main(int argc, char **argv) +{ + int ret; + + printf("Mqueue latency : "); + + ret = mqueue_lat_test(); + if (ret < 0) { + printf("[FAILED]\n"); + return ksft_exit_fail(); + } + printf("[OK]\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c new file mode 100644 index 000000000000..8a3c29de7d49 --- /dev/null +++ b/tools/testing/selftests/timers/nanosleep.c @@ -0,0 +1,174 @@ +/* Make sure timers don't return early + * by: john stultz (johnstul@us.ibm.com) + * John Stultz (john.stultz@linaro.org) + * (C) Copyright IBM 2012 + * (C) Copyright Linaro 2013 2015 + * Licensed under the GPLv2 + * + * To build: + * $ gcc nanosleep.c -o nanosleep -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000ULL + +#define CLOCK_REALTIME 0 +#define CLOCK_MONOTONIC 1 +#define CLOCK_PROCESS_CPUTIME_ID 2 +#define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 +#define CLOCK_BOOTTIME 7 +#define CLOCK_REALTIME_ALARM 8 +#define CLOCK_BOOTTIME_ALARM 9 +#define CLOCK_HWSPECIFIC 10 +#define CLOCK_TAI 11 +#define NR_CLOCKIDS 12 + +#define UNSUPPORTED 0xf00f + +char *clockstring(int clockid) +{ + switch (clockid) { + case CLOCK_REALTIME: + return "CLOCK_REALTIME"; + case CLOCK_MONOTONIC: + return "CLOCK_MONOTONIC"; + case CLOCK_PROCESS_CPUTIME_ID: + return "CLOCK_PROCESS_CPUTIME_ID"; + case CLOCK_THREAD_CPUTIME_ID: + return "CLOCK_THREAD_CPUTIME_ID"; + case CLOCK_MONOTONIC_RAW: + return "CLOCK_MONOTONIC_RAW"; + case CLOCK_REALTIME_COARSE: + return "CLOCK_REALTIME_COARSE"; + case CLOCK_MONOTONIC_COARSE: + return "CLOCK_MONOTONIC_COARSE"; + case CLOCK_BOOTTIME: + return "CLOCK_BOOTTIME"; + case CLOCK_REALTIME_ALARM: + return "CLOCK_REALTIME_ALARM"; + case CLOCK_BOOTTIME_ALARM: + return "CLOCK_BOOTTIME_ALARM"; + case CLOCK_TAI: + return "CLOCK_TAI"; + }; + return "UNKNOWN_CLOCKID"; +} + +/* returns 1 if a <= b, 0 otherwise */ +static inline int in_order(struct timespec a, struct timespec b) +{ + if (a.tv_sec < b.tv_sec) + return 1; + if (a.tv_sec > b.tv_sec) + return 0; + if (a.tv_nsec > b.tv_nsec) + return 0; + return 1; +} + +struct timespec timespec_add(struct timespec ts, unsigned long long ns) +{ + ts.tv_nsec += ns; + while (ts.tv_nsec >= NSEC_PER_SEC) { + ts.tv_nsec -= NSEC_PER_SEC; + ts.tv_sec++; + } + return ts; +} + +int nanosleep_test(int clockid, long long ns) +{ + struct timespec now, target, rel; + + /* First check abs time */ + if (clock_gettime(clockid, &now)) + return UNSUPPORTED; + target = timespec_add(now, ns); + + if (clock_nanosleep(clockid, TIMER_ABSTIME, &target, NULL)) + return UNSUPPORTED; + clock_gettime(clockid, &now); + + if (!in_order(target, now)) + return -1; + + /* Second check reltime */ + clock_gettime(clockid, &now); + rel.tv_sec = 0; + rel.tv_nsec = 0; + rel = timespec_add(rel, ns); + target = timespec_add(now, ns); + clock_nanosleep(clockid, 0, &rel, NULL); + clock_gettime(clockid, &now); + + if (!in_order(target, now)) + return -1; + return 0; +} + +int main(int argc, char **argv) +{ + long long length; + int clockid, ret; + + for (clockid = CLOCK_REALTIME; clockid < NR_CLOCKIDS; clockid++) { + + /* Skip cputime clockids since nanosleep won't increment cputime */ + if (clockid == CLOCK_PROCESS_CPUTIME_ID || + clockid == CLOCK_THREAD_CPUTIME_ID || + clockid == CLOCK_HWSPECIFIC) + continue; + + printf("Nanosleep %-31s ", clockstring(clockid)); + + length = 10; + while (length <= (NSEC_PER_SEC * 10)) { + ret = nanosleep_test(clockid, length); + if (ret == UNSUPPORTED) { + printf("[UNSUPPORTED]\n"); + goto next; + } + if (ret < 0) { + printf("[FAILED]\n"); + return ksft_exit_fail(); + } + length *= 100; + } + printf("[OK]\n"); +next: + ret = 0; + } + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/nsleep-lat.c b/tools/testing/selftests/timers/nsleep-lat.c new file mode 100644 index 000000000000..2d7898fda0f1 --- /dev/null +++ b/tools/testing/selftests/timers/nsleep-lat.c @@ -0,0 +1,190 @@ +/* Measure nanosleep timer latency + * by: john stultz (john.stultz@linaro.org) + * (C) Copyright Linaro 2013 + * Licensed under the GPLv2 + * + * To build: + * $ gcc nsleep-lat.c -o nsleep-lat -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000ULL + +#define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ + + +#define CLOCK_REALTIME 0 +#define CLOCK_MONOTONIC 1 +#define CLOCK_PROCESS_CPUTIME_ID 2 +#define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 +#define CLOCK_BOOTTIME 7 +#define CLOCK_REALTIME_ALARM 8 +#define CLOCK_BOOTTIME_ALARM 9 +#define CLOCK_HWSPECIFIC 10 +#define CLOCK_TAI 11 +#define NR_CLOCKIDS 12 + +#define UNSUPPORTED 0xf00f + +char *clockstring(int clockid) +{ + switch (clockid) { + case CLOCK_REALTIME: + return "CLOCK_REALTIME"; + case CLOCK_MONOTONIC: + return "CLOCK_MONOTONIC"; + case CLOCK_PROCESS_CPUTIME_ID: + return "CLOCK_PROCESS_CPUTIME_ID"; + case CLOCK_THREAD_CPUTIME_ID: + return "CLOCK_THREAD_CPUTIME_ID"; + case CLOCK_MONOTONIC_RAW: + return "CLOCK_MONOTONIC_RAW"; + case CLOCK_REALTIME_COARSE: + return "CLOCK_REALTIME_COARSE"; + case CLOCK_MONOTONIC_COARSE: + return "CLOCK_MONOTONIC_COARSE"; + case CLOCK_BOOTTIME: + return "CLOCK_BOOTTIME"; + case CLOCK_REALTIME_ALARM: + return "CLOCK_REALTIME_ALARM"; + case CLOCK_BOOTTIME_ALARM: + return "CLOCK_BOOTTIME_ALARM"; + case CLOCK_TAI: + return "CLOCK_TAI"; + }; + return "UNKNOWN_CLOCKID"; +} + +struct timespec timespec_add(struct timespec ts, unsigned long long ns) +{ + ts.tv_nsec += ns; + while (ts.tv_nsec >= NSEC_PER_SEC) { + ts.tv_nsec -= NSEC_PER_SEC; + ts.tv_sec++; + } + return ts; +} + + +long long timespec_sub(struct timespec a, struct timespec b) +{ + long long ret = NSEC_PER_SEC * b.tv_sec + b.tv_nsec; + + ret -= NSEC_PER_SEC * a.tv_sec + a.tv_nsec; + return ret; +} + +int nanosleep_lat_test(int clockid, long long ns) +{ + struct timespec start, end, target; + long long latency = 0; + int i, count; + + target.tv_sec = ns/NSEC_PER_SEC; + target.tv_nsec = ns%NSEC_PER_SEC; + + if (clock_gettime(clockid, &start)) + return UNSUPPORTED; + if (clock_nanosleep(clockid, 0, &target, NULL)) + return UNSUPPORTED; + + count = 10; + + /* First check relative latency */ + clock_gettime(clockid, &start); + for (i = 0; i < count; i++) + clock_nanosleep(clockid, 0, &target, NULL); + clock_gettime(clockid, &end); + + if (((timespec_sub(start, end)/count)-ns) > UNRESONABLE_LATENCY) { + printf("Large rel latency: %lld ns :", (timespec_sub(start, end)/count)-ns); + return -1; + } + + /* Next check absolute latency */ + for (i = 0; i < count; i++) { + clock_gettime(clockid, &start); + target = timespec_add(start, ns); + clock_nanosleep(clockid, TIMER_ABSTIME, &target, NULL); + clock_gettime(clockid, &end); + latency += timespec_sub(target, end); + } + + if (latency/count > UNRESONABLE_LATENCY) { + printf("Large abs latency: %lld ns :", latency/count); + return -1; + } + + return 0; +} + + + +int main(int argc, char **argv) +{ + long long length; + int clockid, ret; + + for (clockid = CLOCK_REALTIME; clockid < NR_CLOCKIDS; clockid++) { + + /* Skip cputime clockids since nanosleep won't increment cputime */ + if (clockid == CLOCK_PROCESS_CPUTIME_ID || + clockid == CLOCK_THREAD_CPUTIME_ID || + clockid == CLOCK_HWSPECIFIC) + continue; + + printf("nsleep latency %-26s ", clockstring(clockid)); + + length = 10; + while (length <= (NSEC_PER_SEC * 10)) { + ret = nanosleep_lat_test(clockid, length); + if (ret) + break; + length *= 100; + + } + + if (ret == UNSUPPORTED) { + printf("[UNSUPPORTED]\n"); + continue; + } + if (ret < 0) { + printf("[FAILED]\n"); + return ksft_exit_fail(); + } + printf("[OK]\n"); + } + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 41bd85559d4b..5a246a02dff3 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -15,6 +15,8 @@ #include <time.h> #include <pthread.h> +#include "../kselftest.h" + #define DELAY 2 #define USECS_PER_SEC 1000000 @@ -33,10 +35,11 @@ static void user_loop(void) static void kernel_loop(void) { void *addr = sbrk(0); + int err = 0; - while (!done) { - brk(addr + 4096); - brk(addr); + while (!done && !err) { + err = brk(addr + 4096); + err |= brk(addr); } } @@ -188,22 +191,20 @@ static int check_timer_create(int which) int main(int argc, char **argv) { - int err; - printf("Testing posix timers. False negative may happen on CPU execution \n"); printf("based timers if other threads run on the CPU...\n"); if (check_itimer(ITIMER_VIRTUAL) < 0) - return -1; + return ksft_exit_fail(); if (check_itimer(ITIMER_PROF) < 0) - return -1; + return ksft_exit_fail(); if (check_itimer(ITIMER_REAL) < 0) - return -1; + return ksft_exit_fail(); if (check_timer_create(CLOCK_THREAD_CPUTIME_ID) < 0) - return -1; + return ksft_exit_fail(); /* * It's unfortunately hard to reliably test a timer expiration @@ -215,7 +216,7 @@ int main(int argc, char **argv) * find a better solution. */ if (check_timer_create(CLOCK_PROCESS_CPUTIME_ID) < 0) - return -1; + return ksft_exit_fail(); - return 0; + return ksft_exit_pass(); } diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c new file mode 100644 index 000000000000..30906bfd9c1b --- /dev/null +++ b/tools/testing/selftests/timers/raw_skew.c @@ -0,0 +1,154 @@ +/* CLOCK_MONOTONIC vs CLOCK_MONOTONIC_RAW skew test + * by: john stultz (johnstul@us.ibm.com) + * John Stultz <john.stultz@linaro.org> + * (C) Copyright IBM 2012 + * (C) Copyright Linaro Limited 2015 + * Licensed under the GPLv2 + * + * To build: + * $ gcc raw_skew.c -o raw_skew -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <time.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + + +#define CLOCK_MONOTONIC_RAW 4 +#define NSEC_PER_SEC 1000000000LL + +#define shift_right(x, s) ({ \ + __typeof__(x) __x = (x); \ + __typeof__(s) __s = (s); \ + __x < 0 ? -(-__x >> __s) : __x >> __s; \ +}) + +long long llabs(long long val) +{ + if (val < 0) + val = -val; + return val; +} + +unsigned long long ts_to_nsec(struct timespec ts) +{ + return ts.tv_sec * NSEC_PER_SEC + ts.tv_nsec; +} + +struct timespec nsec_to_ts(long long ns) +{ + struct timespec ts; + + ts.tv_sec = ns/NSEC_PER_SEC; + ts.tv_nsec = ns%NSEC_PER_SEC; + return ts; +} + +long long diff_timespec(struct timespec start, struct timespec end) +{ + long long start_ns, end_ns; + + start_ns = ts_to_nsec(start); + end_ns = ts_to_nsec(end); + return end_ns - start_ns; +} + +void get_monotonic_and_raw(struct timespec *mon, struct timespec *raw) +{ + struct timespec start, mid, end; + long long diff = 0, tmp; + int i; + + for (i = 0; i < 3; i++) { + long long newdiff; + + clock_gettime(CLOCK_MONOTONIC, &start); + clock_gettime(CLOCK_MONOTONIC_RAW, &mid); + clock_gettime(CLOCK_MONOTONIC, &end); + + newdiff = diff_timespec(start, end); + if (diff == 0 || newdiff < diff) { + diff = newdiff; + *raw = mid; + tmp = (ts_to_nsec(start) + ts_to_nsec(end))/2; + *mon = nsec_to_ts(tmp); + } + } +} + +int main(int argv, char **argc) +{ + struct timespec mon, raw, start, end; + long long delta1, delta2, interval, eppm, ppm; + struct timex tx1, tx2; + + setbuf(stdout, NULL); + + if (clock_gettime(CLOCK_MONOTONIC_RAW, &raw)) { + printf("ERR: NO CLOCK_MONOTONIC_RAW\n"); + return -1; + } + + tx1.modes = 0; + adjtimex(&tx1); + get_monotonic_and_raw(&mon, &raw); + start = mon; + delta1 = diff_timespec(mon, raw); + + if (tx1.offset) + printf("WARNING: ADJ_OFFSET in progress, this will cause inaccurate results\n"); + + printf("Estimating clock drift: "); + sleep(120); + + get_monotonic_and_raw(&mon, &raw); + end = mon; + tx2.modes = 0; + adjtimex(&tx2); + delta2 = diff_timespec(mon, raw); + + interval = diff_timespec(start, end); + + /* calculate measured ppm between MONOTONIC and MONOTONIC_RAW */ + eppm = ((delta2-delta1)*NSEC_PER_SEC)/interval; + eppm = -eppm; + printf("%lld.%i(est)", eppm/1000, abs((int)(eppm%1000))); + + /* Avg the two actual freq samples adjtimex gave us */ + ppm = (tx1.freq + tx2.freq) * 1000 / 2; + ppm = (long long)tx1.freq * 1000; + ppm = shift_right(ppm, 16); + printf(" %lld.%i(act)", ppm/1000, abs((int)(ppm%1000))); + + if (llabs(eppm - ppm) > 1000) { + printf(" [FAILED]\n"); + return ksft_exit_fail(); + } + printf(" [OK]\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/rtctest.c b/tools/testing/selftests/timers/rtctest.c new file mode 100644 index 000000000000..d80ae852334d --- /dev/null +++ b/tools/testing/selftests/timers/rtctest.c @@ -0,0 +1,271 @@ +/* + * Real Time Clock Driver Test/Example Program + * + * Compile with: + * gcc -s -Wall -Wstrict-prototypes rtctest.c -o rtctest + * + * Copyright (C) 1996, Paul Gortmaker. + * + * Released under the GNU General Public License, version 2, + * included herein by reference. + * + */ + +#include <stdio.h> +#include <linux/rtc.h> +#include <sys/ioctl.h> +#include <sys/time.h> +#include <sys/types.h> +#include <fcntl.h> +#include <unistd.h> +#include <stdlib.h> +#include <errno.h> + + +/* + * This expects the new RTC class driver framework, working with + * clocks that will often not be clones of what the PC-AT had. + * Use the command line to specify another RTC if you need one. + */ +static const char default_rtc[] = "/dev/rtc0"; + + +int main(int argc, char **argv) +{ + int i, fd, retval, irqcount = 0; + unsigned long tmp, data; + struct rtc_time rtc_tm; + const char *rtc = default_rtc; + struct timeval start, end, diff; + + switch (argc) { + case 2: + rtc = argv[1]; + /* FALLTHROUGH */ + case 1: + break; + default: + fprintf(stderr, "usage: rtctest [rtcdev]\n"); + return 1; + } + + fd = open(rtc, O_RDONLY); + + if (fd == -1) { + perror(rtc); + exit(errno); + } + + fprintf(stderr, "\n\t\t\tRTC Driver Test Example.\n\n"); + + /* Turn on update interrupts (one per second) */ + retval = ioctl(fd, RTC_UIE_ON, 0); + if (retval == -1) { + if (errno == ENOTTY) { + fprintf(stderr, + "\n...Update IRQs not supported.\n"); + goto test_READ; + } + perror("RTC_UIE_ON ioctl"); + exit(errno); + } + + fprintf(stderr, "Counting 5 update (1/sec) interrupts from reading %s:", + rtc); + fflush(stderr); + for (i=1; i<6; i++) { + /* This read will block */ + retval = read(fd, &data, sizeof(unsigned long)); + if (retval == -1) { + perror("read"); + exit(errno); + } + fprintf(stderr, " %d",i); + fflush(stderr); + irqcount++; + } + + fprintf(stderr, "\nAgain, from using select(2) on /dev/rtc:"); + fflush(stderr); + for (i=1; i<6; i++) { + struct timeval tv = {5, 0}; /* 5 second timeout on select */ + fd_set readfds; + + FD_ZERO(&readfds); + FD_SET(fd, &readfds); + /* The select will wait until an RTC interrupt happens. */ + retval = select(fd+1, &readfds, NULL, NULL, &tv); + if (retval == -1) { + perror("select"); + exit(errno); + } + /* This read won't block unlike the select-less case above. */ + retval = read(fd, &data, sizeof(unsigned long)); + if (retval == -1) { + perror("read"); + exit(errno); + } + fprintf(stderr, " %d",i); + fflush(stderr); + irqcount++; + } + + /* Turn off update interrupts */ + retval = ioctl(fd, RTC_UIE_OFF, 0); + if (retval == -1) { + perror("RTC_UIE_OFF ioctl"); + exit(errno); + } + +test_READ: + /* Read the RTC time/date */ + retval = ioctl(fd, RTC_RD_TIME, &rtc_tm); + if (retval == -1) { + perror("RTC_RD_TIME ioctl"); + exit(errno); + } + + fprintf(stderr, "\n\nCurrent RTC date/time is %d-%d-%d, %02d:%02d:%02d.\n", + rtc_tm.tm_mday, rtc_tm.tm_mon + 1, rtc_tm.tm_year + 1900, + rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec); + + /* Set the alarm to 5 sec in the future, and check for rollover */ + rtc_tm.tm_sec += 5; + if (rtc_tm.tm_sec >= 60) { + rtc_tm.tm_sec %= 60; + rtc_tm.tm_min++; + } + if (rtc_tm.tm_min == 60) { + rtc_tm.tm_min = 0; + rtc_tm.tm_hour++; + } + if (rtc_tm.tm_hour == 24) + rtc_tm.tm_hour = 0; + + retval = ioctl(fd, RTC_ALM_SET, &rtc_tm); + if (retval == -1) { + if (errno == ENOTTY) { + fprintf(stderr, + "\n...Alarm IRQs not supported.\n"); + goto test_PIE; + } + perror("RTC_ALM_SET ioctl"); + exit(errno); + } + + /* Read the current alarm settings */ + retval = ioctl(fd, RTC_ALM_READ, &rtc_tm); + if (retval == -1) { + perror("RTC_ALM_READ ioctl"); + exit(errno); + } + + fprintf(stderr, "Alarm time now set to %02d:%02d:%02d.\n", + rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec); + + /* Enable alarm interrupts */ + retval = ioctl(fd, RTC_AIE_ON, 0); + if (retval == -1) { + perror("RTC_AIE_ON ioctl"); + exit(errno); + } + + fprintf(stderr, "Waiting 5 seconds for alarm..."); + fflush(stderr); + /* This blocks until the alarm ring causes an interrupt */ + retval = read(fd, &data, sizeof(unsigned long)); + if (retval == -1) { + perror("read"); + exit(errno); + } + irqcount++; + fprintf(stderr, " okay. Alarm rang.\n"); + + /* Disable alarm interrupts */ + retval = ioctl(fd, RTC_AIE_OFF, 0); + if (retval == -1) { + perror("RTC_AIE_OFF ioctl"); + exit(errno); + } + +test_PIE: + /* Read periodic IRQ rate */ + retval = ioctl(fd, RTC_IRQP_READ, &tmp); + if (retval == -1) { + /* not all RTCs support periodic IRQs */ + if (errno == ENOTTY) { + fprintf(stderr, "\nNo periodic IRQ support\n"); + goto done; + } + perror("RTC_IRQP_READ ioctl"); + exit(errno); + } + fprintf(stderr, "\nPeriodic IRQ rate is %ldHz.\n", tmp); + + fprintf(stderr, "Counting 20 interrupts at:"); + fflush(stderr); + + /* The frequencies 128Hz, 256Hz, ... 8192Hz are only allowed for root. */ + for (tmp=2; tmp<=64; tmp*=2) { + + retval = ioctl(fd, RTC_IRQP_SET, tmp); + if (retval == -1) { + /* not all RTCs can change their periodic IRQ rate */ + if (errno == ENOTTY) { + fprintf(stderr, + "\n...Periodic IRQ rate is fixed\n"); + goto done; + } + perror("RTC_IRQP_SET ioctl"); + exit(errno); + } + + fprintf(stderr, "\n%ldHz:\t", tmp); + fflush(stderr); + + /* Enable periodic interrupts */ + retval = ioctl(fd, RTC_PIE_ON, 0); + if (retval == -1) { + perror("RTC_PIE_ON ioctl"); + exit(errno); + } + + for (i=1; i<21; i++) { + gettimeofday(&start, NULL); + /* This blocks */ + retval = read(fd, &data, sizeof(unsigned long)); + if (retval == -1) { + perror("read"); + exit(errno); + } + gettimeofday(&end, NULL); + timersub(&end, &start, &diff); + if (diff.tv_sec > 0 || + diff.tv_usec > ((1000000L / tmp) * 1.10)) { + fprintf(stderr, "\nPIE delta error: %ld.%06ld should be close to 0.%06ld\n", + diff.tv_sec, diff.tv_usec, + (1000000L / tmp)); + fflush(stdout); + exit(-1); + } + + fprintf(stderr, " %d",i); + fflush(stderr); + irqcount++; + } + + /* Disable periodic interrupts */ + retval = ioctl(fd, RTC_PIE_OFF, 0); + if (retval == -1) { + perror("RTC_PIE_OFF ioctl"); + exit(errno); + } + } + +done: + fprintf(stderr, "\n\n\t\t\t *** Test complete ***\n"); + + close(fd); + + return 0; +} diff --git a/tools/testing/selftests/timers/set-2038.c b/tools/testing/selftests/timers/set-2038.c new file mode 100644 index 000000000000..c8a7e14446b1 --- /dev/null +++ b/tools/testing/selftests/timers/set-2038.c @@ -0,0 +1,144 @@ +/* Time bounds setting test + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2012 + * Licensed under the GPLv2 + * + * NOTE: This is a meta-test which sets the time to edge cases then + * uses other tests to detect problems. Thus this test requires that + * the inconsistency-check and nanosleep tests be present in the same + * directory it is run from. + * + * To build: + * $ gcc set-2038.c -o set-2038 -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <time.h> +#include <sys/time.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000LL + +#define KTIME_MAX ((long long)~((unsigned long long)1 << 63)) +#define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) + +#define YEAR_1901 (-0x7fffffffL) +#define YEAR_1970 1 +#define YEAR_2038 0x7fffffffL /*overflows 32bit time_t */ +#define YEAR_2262 KTIME_SEC_MAX /*overflows 64bit ktime_t */ +#define YEAR_MAX ((long long)((1ULL<<63)-1)) /*overflows 64bit time_t */ + +int is32bits(void) +{ + return (sizeof(long) == 4); +} + +int settime(long long time) +{ + struct timeval now; + int ret; + + now.tv_sec = (time_t)time; + now.tv_usec = 0; + + ret = settimeofday(&now, NULL); + + printf("Setting time to 0x%lx: %d\n", (long)time, ret); + return ret; +} + +int do_tests(void) +{ + int ret; + + ret = system("date"); + ret = system("./inconsistency-check -c 0 -t 20"); + ret |= system("./nanosleep"); + ret |= system("./nsleep-lat"); + return ret; + +} + +int main(int argc, char *argv[]) +{ + int ret = 0; + int opt, dangerous = 0; + time_t start; + + /* Process arguments */ + while ((opt = getopt(argc, argv, "d")) != -1) { + switch (opt) { + case 'd': + dangerous = 1; + } + } + + start = time(0); + + /* First test that crazy values don't work */ + if (!settime(YEAR_1901)) { + ret = -1; + goto out; + } + if (!settime(YEAR_MAX)) { + ret = -1; + goto out; + } + if (!is32bits() && !settime(YEAR_2262)) { + ret = -1; + goto out; + } + + /* Now test behavior near edges */ + settime(YEAR_1970); + ret = do_tests(); + if (ret) + goto out; + + settime(YEAR_2038 - 600); + ret = do_tests(); + if (ret) + goto out; + + /* The rest of the tests can blowup on 32bit systems */ + if (is32bits() && !dangerous) + goto out; + /* Test rollover behavior 32bit edge */ + settime(YEAR_2038 - 10); + ret = do_tests(); + if (ret) + goto out; + + settime(YEAR_2262 - 600); + ret = do_tests(); + +out: + /* restore clock */ + settime(start); + if (ret) + return ksft_exit_fail(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/set-tai.c b/tools/testing/selftests/timers/set-tai.c new file mode 100644 index 000000000000..dc88dbc8831f --- /dev/null +++ b/tools/testing/selftests/timers/set-tai.c @@ -0,0 +1,79 @@ +/* Set tai offset + * by: John Stultz <john.stultz@linaro.org> + * (C) Copyright Linaro 2013 + * Licensed under the GPLv2 + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +int set_tai(int offset) +{ + struct timex tx; + + memset(&tx, 0, sizeof(tx)); + + tx.modes = ADJ_TAI; + tx.constant = offset; + + return adjtimex(&tx); +} + +int get_tai(void) +{ + struct timex tx; + + memset(&tx, 0, sizeof(tx)); + + adjtimex(&tx); + return tx.tai; +} + +int main(int argc, char **argv) +{ + int i, ret; + + ret = get_tai(); + printf("tai offset started at %i\n", ret); + + printf("Checking tai offsets can be properly set: "); + for (i = 1; i <= 60; i++) { + ret = set_tai(i); + ret = get_tai(); + if (ret != i) { + printf("[FAILED] expected: %i got %i\n", i, ret); + return ksft_exit_fail(); + } + } + printf("[OK]\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c new file mode 100644 index 000000000000..4fc98c5b0899 --- /dev/null +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -0,0 +1,216 @@ +/* set_timer latency test + * John Stultz (john.stultz@linaro.org) + * (C) Copyright Linaro 2014 + * Licensed under the GPLv2 + * + * This test makes sure the set_timer api is correct + * + * To build: + * $ gcc set-timer-lat.c -o set-timer-lat -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <unistd.h> +#include <time.h> +#include <string.h> +#include <signal.h> +#include <stdlib.h> +#include <pthread.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define CLOCK_REALTIME 0 +#define CLOCK_MONOTONIC 1 +#define CLOCK_PROCESS_CPUTIME_ID 2 +#define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 +#define CLOCK_BOOTTIME 7 +#define CLOCK_REALTIME_ALARM 8 +#define CLOCK_BOOTTIME_ALARM 9 +#define CLOCK_HWSPECIFIC 10 +#define CLOCK_TAI 11 +#define NR_CLOCKIDS 12 + + +#define NSEC_PER_SEC 1000000000ULL +#define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ + +#define TIMER_SECS 1 +int alarmcount; +int clock_id; +struct timespec start_time; +long long max_latency_ns; + +char *clockstring(int clockid) +{ + switch (clockid) { + case CLOCK_REALTIME: + return "CLOCK_REALTIME"; + case CLOCK_MONOTONIC: + return "CLOCK_MONOTONIC"; + case CLOCK_PROCESS_CPUTIME_ID: + return "CLOCK_PROCESS_CPUTIME_ID"; + case CLOCK_THREAD_CPUTIME_ID: + return "CLOCK_THREAD_CPUTIME_ID"; + case CLOCK_MONOTONIC_RAW: + return "CLOCK_MONOTONIC_RAW"; + case CLOCK_REALTIME_COARSE: + return "CLOCK_REALTIME_COARSE"; + case CLOCK_MONOTONIC_COARSE: + return "CLOCK_MONOTONIC_COARSE"; + case CLOCK_BOOTTIME: + return "CLOCK_BOOTTIME"; + case CLOCK_REALTIME_ALARM: + return "CLOCK_REALTIME_ALARM"; + case CLOCK_BOOTTIME_ALARM: + return "CLOCK_BOOTTIME_ALARM"; + case CLOCK_TAI: + return "CLOCK_TAI"; + }; + return "UNKNOWN_CLOCKID"; +} + + +long long timespec_sub(struct timespec a, struct timespec b) +{ + long long ret = NSEC_PER_SEC * b.tv_sec + b.tv_nsec; + + ret -= NSEC_PER_SEC * a.tv_sec + a.tv_nsec; + return ret; +} + + +void sigalarm(int signo) +{ + long long delta_ns; + struct timespec ts; + + clock_gettime(clock_id, &ts); + alarmcount++; + + delta_ns = timespec_sub(start_time, ts); + delta_ns -= NSEC_PER_SEC * TIMER_SECS * alarmcount; + + if (delta_ns < 0) + printf("%s timer fired early: FAIL\n", clockstring(clock_id)); + + if (delta_ns > max_latency_ns) + max_latency_ns = delta_ns; +} + +int do_timer(int clock_id, int flags) +{ + struct sigevent se; + timer_t tm1; + struct itimerspec its1, its2; + int err; + + /* Set up timer: */ + memset(&se, 0, sizeof(se)); + se.sigev_notify = SIGEV_SIGNAL; + se.sigev_signo = SIGRTMAX; + se.sigev_value.sival_int = 0; + + max_latency_ns = 0; + alarmcount = 0; + + err = timer_create(clock_id, &se, &tm1); + if (err) { + if ((clock_id == CLOCK_REALTIME_ALARM) || + (clock_id == CLOCK_BOOTTIME_ALARM)) { + printf("%-22s %s missing CAP_WAKE_ALARM? : [UNSUPPORTED]\n", + clockstring(clock_id), + flags ? "ABSTIME":"RELTIME"); + return 0; + } + printf("%s - timer_create() failed\n", clockstring(clock_id)); + return -1; + } + + clock_gettime(clock_id, &start_time); + if (flags) { + its1.it_value = start_time; + its1.it_value.tv_sec += TIMER_SECS; + } else { + its1.it_value.tv_sec = TIMER_SECS; + its1.it_value.tv_nsec = 0; + } + its1.it_interval.tv_sec = TIMER_SECS; + its1.it_interval.tv_nsec = 0; + + err = timer_settime(tm1, flags, &its1, &its2); + if (err) { + printf("%s - timer_settime() failed\n", clockstring(clock_id)); + return -1; + } + + while (alarmcount < 5) + sleep(1); + + printf("%-22s %s max latency: %10lld ns : ", + clockstring(clock_id), + flags ? "ABSTIME":"RELTIME", + max_latency_ns); + + timer_delete(tm1); + if (max_latency_ns < UNRESONABLE_LATENCY) { + printf("[OK]\n"); + return 0; + } + printf("[FAILED]\n"); + return -1; +} + +int main(void) +{ + struct sigaction act; + int signum = SIGRTMAX; + int ret = 0; + + /* Set up signal handler: */ + sigfillset(&act.sa_mask); + act.sa_flags = 0; + act.sa_handler = sigalarm; + sigaction(signum, &act, NULL); + + printf("Setting timers for every %i seconds\n", TIMER_SECS); + for (clock_id = 0; clock_id < NR_CLOCKIDS; clock_id++) { + + if ((clock_id == CLOCK_PROCESS_CPUTIME_ID) || + (clock_id == CLOCK_THREAD_CPUTIME_ID) || + (clock_id == CLOCK_MONOTONIC_RAW) || + (clock_id == CLOCK_REALTIME_COARSE) || + (clock_id == CLOCK_MONOTONIC_COARSE) || + (clock_id == CLOCK_HWSPECIFIC)) + continue; + + ret |= do_timer(clock_id, TIMER_ABSTIME); + ret |= do_timer(clock_id, 0); + } + if (ret) + return ksft_exit_fail(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/skew_consistency.c b/tools/testing/selftests/timers/skew_consistency.c new file mode 100644 index 000000000000..5562f84ee07c --- /dev/null +++ b/tools/testing/selftests/timers/skew_consistency.c @@ -0,0 +1,89 @@ +/* ADJ_FREQ Skew consistency test + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2012 + * Licensed under the GPLv2 + * + * NOTE: This is a meta-test which cranks the ADJ_FREQ knob back + * and forth and watches for consistency problems. Thus this test requires + * that the inconsistency-check tests be present in the same directory it + * is run from. + * + * To build: + * $ gcc skew_consistency.c -o skew_consistency -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <time.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <stdlib.h> +#include <string.h> +#include <sys/wait.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000LL + +int main(int argv, char **argc) +{ + struct timex tx; + int ret, ppm; + pid_t pid; + + + printf("Running Asyncrhonous Frequency Changing Tests...\n"); + + pid = fork(); + if (!pid) + return system("./inconsistency-check -c 1 -t 600"); + + ppm = 500; + ret = 0; + + while (pid != waitpid(pid, &ret, WNOHANG)) { + ppm = -ppm; + tx.modes = ADJ_FREQUENCY; + tx.freq = ppm << 16; + adjtimex(&tx); + usleep(500000); + } + + /* Set things back */ + tx.modes = ADJ_FREQUENCY; + tx.offset = 0; + adjtimex(&tx); + + + if (ret) { + printf("[FAILED]\n"); + return ksft_exit_fail(); + } + printf("[OK]\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/threadtest.c b/tools/testing/selftests/timers/threadtest.c new file mode 100644 index 000000000000..e632e116f05e --- /dev/null +++ b/tools/testing/selftests/timers/threadtest.c @@ -0,0 +1,204 @@ +/* threadtest.c + * by: john stultz (johnstul@us.ibm.com) + * (C) Copyright IBM 2004, 2005, 2006, 2012 + * Licensed under the GPLv2 + * + * To build: + * $ gcc threadtest.c -o threadtest -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <sys/time.h> +#include <pthread.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + + +/* serializes shared list access */ +pthread_mutex_t list_lock = PTHREAD_MUTEX_INITIALIZER; +/* serializes console output */ +pthread_mutex_t print_lock = PTHREAD_MUTEX_INITIALIZER; + + +#define MAX_THREADS 128 +#define LISTSIZE 128 + +int done = 0; + +struct timespec global_list[LISTSIZE]; +int listcount = 0; + + +void checklist(struct timespec *list, int size) +{ + int i, j; + struct timespec *a, *b; + + /* scan the list */ + for (i = 0; i < size-1; i++) { + a = &list[i]; + b = &list[i+1]; + + /* look for any time inconsistencies */ + if ((b->tv_sec <= a->tv_sec) && + (b->tv_nsec < a->tv_nsec)) { + + /* flag other threads */ + done = 1; + + /*serialize printing to avoid junky output*/ + pthread_mutex_lock(&print_lock); + + /* dump the list */ + printf("\n"); + for (j = 0; j < size; j++) { + if (j == i) + printf("---------------\n"); + printf("%lu:%lu\n", list[j].tv_sec, list[j].tv_nsec); + if (j == i+1) + printf("---------------\n"); + } + printf("[FAILED]\n"); + + pthread_mutex_unlock(&print_lock); + } + } +} + +/* The shared thread shares a global list + * that each thread fills while holding the lock. + * This stresses clock syncronization across cpus. + */ +void *shared_thread(void *arg) +{ + while (!done) { + /* protect the list */ + pthread_mutex_lock(&list_lock); + + /* see if we're ready to check the list */ + if (listcount >= LISTSIZE) { + checklist(global_list, LISTSIZE); + listcount = 0; + } + clock_gettime(CLOCK_MONOTONIC, &global_list[listcount++]); + + pthread_mutex_unlock(&list_lock); + } + return NULL; +} + + +/* Each independent thread fills in its own + * list. This stresses clock_gettime() lock contention. + */ +void *independent_thread(void *arg) +{ + struct timespec my_list[LISTSIZE]; + int count; + + while (!done) { + /* fill the list */ + for (count = 0; count < LISTSIZE; count++) + clock_gettime(CLOCK_MONOTONIC, &my_list[count]); + checklist(my_list, LISTSIZE); + } + return NULL; +} + +#define DEFAULT_THREAD_COUNT 8 +#define DEFAULT_RUNTIME 30 + +int main(int argc, char **argv) +{ + int thread_count, i; + time_t start, now, runtime; + char buf[255]; + pthread_t pth[MAX_THREADS]; + int opt; + void *tret; + int ret = 0; + void *(*thread)(void *) = shared_thread; + + thread_count = DEFAULT_THREAD_COUNT; + runtime = DEFAULT_RUNTIME; + + /* Process arguments */ + while ((opt = getopt(argc, argv, "t:n:i")) != -1) { + switch (opt) { + case 't': + runtime = atoi(optarg); + break; + case 'n': + thread_count = atoi(optarg); + break; + case 'i': + thread = independent_thread; + printf("using independent threads\n"); + break; + default: + printf("Usage: %s [-t <secs>] [-n <numthreads>] [-i]\n", argv[0]); + printf(" -t: time to run\n"); + printf(" -n: number of threads\n"); + printf(" -i: use independent threads\n"); + return -1; + } + } + + if (thread_count > MAX_THREADS) + thread_count = MAX_THREADS; + + + setbuf(stdout, NULL); + + start = time(0); + strftime(buf, 255, "%a, %d %b %Y %T %z", localtime(&start)); + printf("%s\n", buf); + printf("Testing consistency with %i threads for %ld seconds: ", thread_count, runtime); + + /* spawn */ + for (i = 0; i < thread_count; i++) + pthread_create(&pth[i], 0, thread, 0); + + while (time(&now) < start + runtime) { + sleep(1); + if (done) { + ret = 1; + strftime(buf, 255, "%a, %d %b %Y %T %z", localtime(&now)); + printf("%s\n", buf); + goto out; + } + } + printf("[OK]\n"); + done = 1; + +out: + /* wait */ + for (i = 0; i < thread_count; i++) + pthread_join(pth[i], &tret); + + /* die */ + if (ret) + ksft_exit_fail(); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c new file mode 100644 index 000000000000..e86d937cc22c --- /dev/null +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -0,0 +1,202 @@ +/* valid adjtimex test + * by: John Stultz <john.stultz@linaro.org> + * (C) Copyright Linaro 2015 + * Licensed under the GPLv2 + * + * This test validates adjtimex interface with valid + * and invalid test data. + * + * Usage: valid-adjtimex + * + * To build: + * $ gcc valid-adjtimex.c -o valid-adjtimex -lrt + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + + + +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <sys/time.h> +#include <sys/timex.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#ifdef KTEST +#include "../kselftest.h" +#else +static inline int ksft_exit_pass(void) +{ + exit(0); +} +static inline int ksft_exit_fail(void) +{ + exit(1); +} +#endif + +#define NSEC_PER_SEC 1000000000L + +/* clear NTP time_status & time_state */ +int clear_time_state(void) +{ + struct timex tx; + int ret; + + tx.modes = ADJ_STATUS; + tx.status = 0; + ret = adjtimex(&tx); + return ret; +} + +#define NUM_FREQ_VALID 32 +#define NUM_FREQ_OUTOFRANGE 4 +#define NUM_FREQ_INVALID 2 + +long valid_freq[NUM_FREQ_VALID] = { + -499<<16, + -450<<16, + -400<<16, + -350<<16, + -300<<16, + -250<<16, + -200<<16, + -150<<16, + -100<<16, + -75<<16, + -50<<16, + -25<<16, + -10<<16, + -5<<16, + -1<<16, + -1000, + 1<<16, + 5<<16, + 10<<16, + 25<<16, + 50<<16, + 75<<16, + 100<<16, + 150<<16, + 200<<16, + 250<<16, + 300<<16, + 350<<16, + 400<<16, + 450<<16, + 499<<16, +}; + +long outofrange_freq[NUM_FREQ_OUTOFRANGE] = { + -1000<<16, + -550<<16, + 550<<16, + 1000<<16, +}; + +#define LONG_MAX (~0UL>>1) +#define LONG_MIN (-LONG_MAX - 1) + +long invalid_freq[NUM_FREQ_INVALID] = { + LONG_MAX, + LONG_MIN, +}; + +int validate_freq(void) +{ + struct timex tx; + int ret, pass = 0; + int i; + + clear_time_state(); + + memset(&tx, 0, sizeof(struct timex)); + /* Set the leap second insert flag */ + + printf("Testing ADJ_FREQ... "); + for (i = 0; i < NUM_FREQ_VALID; i++) { + tx.modes = ADJ_FREQUENCY; + tx.freq = valid_freq[i]; + + ret = adjtimex(&tx); + if (ret < 0) { + printf("[FAIL]\n"); + printf("Error: adjtimex(ADJ_FREQ, %ld - %ld ppm\n", + valid_freq[i], valid_freq[i]>>16); + pass = -1; + goto out; + } + tx.modes = 0; + ret = adjtimex(&tx); + if (tx.freq != valid_freq[i]) { + printf("Warning: freq value %ld not what we set it (%ld)!\n", + tx.freq, valid_freq[i]); + } + } + for (i = 0; i < NUM_FREQ_OUTOFRANGE; i++) { + tx.modes = ADJ_FREQUENCY; + tx.freq = outofrange_freq[i]; + + ret = adjtimex(&tx); + if (ret < 0) { + printf("[FAIL]\n"); + printf("Error: adjtimex(ADJ_FREQ, %ld - %ld ppm\n", + outofrange_freq[i], outofrange_freq[i]>>16); + pass = -1; + goto out; + } + tx.modes = 0; + ret = adjtimex(&tx); + if (tx.freq == outofrange_freq[i]) { + printf("[FAIL]\n"); + printf("ERROR: out of range value %ld actually set!\n", + tx.freq); + pass = -1; + goto out; + } + } + + + if (sizeof(long) == 8) { /* this case only applies to 64bit systems */ + for (i = 0; i < NUM_FREQ_INVALID; i++) { + tx.modes = ADJ_FREQUENCY; + tx.freq = invalid_freq[i]; + ret = adjtimex(&tx); + if (ret >= 0) { + printf("[FAIL]\n"); + printf("Error: No failure on invalid ADJ_FREQUENCY %ld\n", + invalid_freq[i]); + pass = -1; + goto out; + } + } + } + + printf("[OK]\n"); +out: + /* reset freq to zero */ + tx.modes = ADJ_FREQUENCY; + tx.freq = 0; + ret = adjtimex(&tx); + + return pass; +} + + +int main(int argc, char **argv) +{ + if (validate_freq()) + return ksft_exit_fail(); + + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/user/Makefile b/tools/testing/selftests/user/Makefile index 396255bd720e..d401b63c5b1a 100644 --- a/tools/testing/selftests/user/Makefile +++ b/tools/testing/selftests/user/Makefile @@ -3,11 +3,6 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests" all: -run_tests: all - @if /sbin/modprobe test_user_copy ; then \ - rmmod test_user_copy; \ - echo "user_copy: ok"; \ - else \ - echo "user_copy: [FAIL]"; \ - exit 1; \ - fi +TEST_PROGS := test_user_copy.sh + +include ../lib.mk diff --git a/tools/testing/selftests/user/test_user_copy.sh b/tools/testing/selftests/user/test_user_copy.sh new file mode 100755 index 000000000000..350107f40c1d --- /dev/null +++ b/tools/testing/selftests/user/test_user_copy.sh @@ -0,0 +1,10 @@ +#!/bin/sh +# Runs copy_to/from_user infrastructure using test_user_copy kernel module + +if /sbin/modprobe -q test_user_copy; then + /sbin/modprobe -q -r test_user_copy + echo "user_copy: ok" +else + echo "user_copy: [FAIL]" + exit 1 +fi diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 4c4b1f631ecf..a5ce9534eb15 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,16 +1,17 @@ # Makefile for vm selftests -CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall BINARIES = hugepage-mmap hugepage-shm map_hugetlb thuge-gen hugetlbfstest BINARIES += transhuge-stress all: $(BINARIES) %: %.c - $(CC) $(CFLAGS) -o $@ $^ + $(CC) $(CFLAGS) -o $@ $^ -lrt -run_tests: all - @/bin/sh ./run_vmtests || (echo "vmtests: [FAIL]"; exit 1) +TEST_PROGS := run_vmtests +TEST_FILES := $(BINARIES) + +include ../lib.mk clean: $(RM) $(BINARIES) diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index c87b6812300d..c87b6812300d 100644..100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests diff --git a/tools/testing/selftests/x86/.gitignore b/tools/testing/selftests/x86/.gitignore new file mode 100644 index 000000000000..15034fef9698 --- /dev/null +++ b/tools/testing/selftests/x86/.gitignore @@ -0,0 +1,2 @@ +*_32 +*_64 diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile new file mode 100644 index 000000000000..f0a7918178dd --- /dev/null +++ b/tools/testing/selftests/x86/Makefile @@ -0,0 +1,48 @@ +.PHONY: all all_32 all_64 check_build32 clean run_tests + +TARGETS_C_BOTHBITS := sigreturn + +BINARIES_32 := $(TARGETS_C_BOTHBITS:%=%_32) +BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64) + +CFLAGS := -O2 -g -std=gnu99 -pthread -Wall + +UNAME_P := $(shell uname -p) + +# Always build 32-bit tests +all: all_32 + +# If we're on a 64-bit host, build 64-bit tests as well +ifeq ($(shell uname -p),x86_64) +all: all_64 +endif + +all_32: check_build32 $(BINARIES_32) + +all_64: $(BINARIES_64) + +clean: + $(RM) $(BINARIES_32) $(BINARIES_64) + +run_tests: + ./run_x86_tests.sh + +$(TARGETS_C_BOTHBITS:%=%_32): %_32: %.c + $(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl + +$(TARGETS_C_BOTHBITS:%=%_64): %_64: %.c + $(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl + +check_build32: + @if ! $(CC) -m32 -o /dev/null trivial_32bit_program.c; then \ + echo "Warning: you seem to have a broken 32-bit build" 2>&1; \ + echo "environment. If you are using a Debian-like"; \ + echo " distribution, try:"; \ + echo ""; \ + echo " apt-get install gcc-multilib libc6-i386 libc6-dev-i386"; \ + echo ""; \ + echo "If you are using a Fedora-like distribution, try:"; \ + echo ""; \ + echo " yum install glibc-devel.*i686"; \ + exit 1; \ + fi diff --git a/tools/testing/selftests/x86/run_x86_tests.sh b/tools/testing/selftests/x86/run_x86_tests.sh new file mode 100644 index 000000000000..3d3ec65f3e7c --- /dev/null +++ b/tools/testing/selftests/x86/run_x86_tests.sh @@ -0,0 +1,11 @@ +#!/bin/bash + +# This is deliberately minimal. IMO kselftests should provide a standard +# script here. +./sigreturn_32 || exit 1 + +if [[ "$uname -p" -eq "x86_64" ]]; then + ./sigreturn_64 || exit 1 +fi + +exit 0 diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c new file mode 100644 index 000000000000..b5aa1bab7416 --- /dev/null +++ b/tools/testing/selftests/x86/sigreturn.c @@ -0,0 +1,684 @@ +/* + * sigreturn.c - tests for x86 sigreturn(2) and exit-to-userspace + * Copyright (c) 2014-2015 Andrew Lutomirski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * This is a series of tests that exercises the sigreturn(2) syscall and + * the IRET / SYSRET paths in the kernel. + * + * For now, this focuses on the effects of unusual CS and SS values, + * and it has a bunch of tests to make sure that ESP/RSP is restored + * properly. + * + * The basic idea behind these tests is to raise(SIGUSR1) to create a + * sigcontext frame, plug in the values to be tested, and then return, + * which implicitly invokes sigreturn(2) and programs the user context + * as desired. + * + * For tests for which we expect sigreturn and the subsequent return to + * user mode to succeed, we return to a short trampoline that generates + * SIGTRAP so that the meat of the tests can be ordinary C code in a + * SIGTRAP handler. + * + * The inner workings of each test is documented below. + * + * Do not run on outdated, unpatched kernels at risk of nasty crashes. + */ + +#define _GNU_SOURCE + +#include <sys/time.h> +#include <time.h> +#include <stdlib.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <stdio.h> +#include <string.h> +#include <inttypes.h> +#include <sys/mman.h> +#include <sys/signal.h> +#include <sys/ucontext.h> +#include <asm/ldt.h> +#include <err.h> +#include <setjmp.h> +#include <stddef.h> +#include <stdbool.h> +#include <sys/ptrace.h> +#include <sys/user.h> + +/* + * In principle, this test can run on Linux emulation layers (e.g. + * Illumos "LX branded zones"). Solaris-based kernels reserve LDT + * entries 0-5 for their own internal purposes, so start our LDT + * allocations above that reservation. (The tests don't pass on LX + * branded zones, but at least this lets them run.) + */ +#define LDT_OFFSET 6 + +/* An aligned stack accessible through some of our segments. */ +static unsigned char stack16[65536] __attribute__((aligned(4096))); + +/* + * An aligned int3 instruction used as a trampoline. Some of the tests + * want to fish out their ss values, so this trampoline copies ss to eax + * before the int3. + */ +asm (".pushsection .text\n\t" + ".type int3, @function\n\t" + ".align 4096\n\t" + "int3:\n\t" + "mov %ss,%eax\n\t" + "int3\n\t" + ".size int3, . - int3\n\t" + ".align 4096, 0xcc\n\t" + ".popsection"); +extern char int3[4096]; + +/* + * At startup, we prepapre: + * + * - ldt_nonexistent_sel: An LDT entry that doesn't exist (all-zero + * descriptor or out of bounds). + * - code16_sel: A 16-bit LDT code segment pointing to int3. + * - data16_sel: A 16-bit LDT data segment pointing to stack16. + * - npcode32_sel: A 32-bit not-present LDT code segment pointing to int3. + * - npdata32_sel: A 32-bit not-present LDT data segment pointing to stack16. + * - gdt_data16_idx: A 16-bit GDT data segment pointing to stack16. + * - gdt_npdata32_idx: A 32-bit not-present GDT data segment pointing to + * stack16. + * + * For no particularly good reason, xyz_sel is a selector value with the + * RPL and LDT bits filled in, whereas xyz_idx is just an index into the + * descriptor table. These variables will be zero if their respective + * segments could not be allocated. + */ +static unsigned short ldt_nonexistent_sel; +static unsigned short code16_sel, data16_sel, npcode32_sel, npdata32_sel; + +static unsigned short gdt_data16_idx, gdt_npdata32_idx; + +static unsigned short GDT3(int idx) +{ + return (idx << 3) | 3; +} + +static unsigned short LDT3(int idx) +{ + return (idx << 3) | 7; +} + +/* Our sigaltstack scratch space. */ +static char altstack_data[SIGSTKSZ]; + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void add_ldt(const struct user_desc *desc, unsigned short *var, + const char *name) +{ + if (syscall(SYS_modify_ldt, 1, desc, sizeof(*desc)) == 0) { + *var = LDT3(desc->entry_number); + } else { + printf("[NOTE]\tFailed to create %s segment\n", name); + *var = 0; + } +} + +static void setup_ldt(void) +{ + if ((unsigned long)stack16 > (1ULL << 32) - sizeof(stack16)) + errx(1, "stack16 is too high\n"); + if ((unsigned long)int3 > (1ULL << 32) - sizeof(int3)) + errx(1, "int3 is too high\n"); + + ldt_nonexistent_sel = LDT3(LDT_OFFSET + 2); + + const struct user_desc code16_desc = { + .entry_number = LDT_OFFSET + 0, + .base_addr = (unsigned long)int3, + .limit = 4095, + .seg_32bit = 0, + .contents = 2, /* Code, not conforming */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 0, + .useable = 0 + }; + add_ldt(&code16_desc, &code16_sel, "code16"); + + const struct user_desc data16_desc = { + .entry_number = LDT_OFFSET + 1, + .base_addr = (unsigned long)stack16, + .limit = 0xffff, + .seg_32bit = 0, + .contents = 0, /* Data, grow-up */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 0, + .useable = 0 + }; + add_ldt(&data16_desc, &data16_sel, "data16"); + + const struct user_desc npcode32_desc = { + .entry_number = LDT_OFFSET + 3, + .base_addr = (unsigned long)int3, + .limit = 4095, + .seg_32bit = 1, + .contents = 2, /* Code, not conforming */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 1, + .useable = 0 + }; + add_ldt(&npcode32_desc, &npcode32_sel, "npcode32"); + + const struct user_desc npdata32_desc = { + .entry_number = LDT_OFFSET + 4, + .base_addr = (unsigned long)stack16, + .limit = 0xffff, + .seg_32bit = 1, + .contents = 0, /* Data, grow-up */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 1, + .useable = 0 + }; + add_ldt(&npdata32_desc, &npdata32_sel, "npdata32"); + + struct user_desc gdt_data16_desc = { + .entry_number = -1, + .base_addr = (unsigned long)stack16, + .limit = 0xffff, + .seg_32bit = 0, + .contents = 0, /* Data, grow-up */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 0, + .useable = 0 + }; + + if (syscall(SYS_set_thread_area, &gdt_data16_desc) == 0) { + /* + * This probably indicates vulnerability to CVE-2014-8133. + * Merely getting here isn't definitive, though, and we'll + * diagnose the problem for real later on. + */ + printf("[WARN]\tset_thread_area allocated data16 at index %d\n", + gdt_data16_desc.entry_number); + gdt_data16_idx = gdt_data16_desc.entry_number; + } else { + printf("[OK]\tset_thread_area refused 16-bit data\n"); + } + + struct user_desc gdt_npdata32_desc = { + .entry_number = -1, + .base_addr = (unsigned long)stack16, + .limit = 0xffff, + .seg_32bit = 1, + .contents = 0, /* Data, grow-up */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 1, + .useable = 0 + }; + + if (syscall(SYS_set_thread_area, &gdt_npdata32_desc) == 0) { + /* + * As a hardening measure, newer kernels don't allow this. + */ + printf("[WARN]\tset_thread_area allocated npdata32 at index %d\n", + gdt_npdata32_desc.entry_number); + gdt_npdata32_idx = gdt_npdata32_desc.entry_number; + } else { + printf("[OK]\tset_thread_area refused 16-bit data\n"); + } +} + +/* State used by our signal handlers. */ +static gregset_t initial_regs, requested_regs, resulting_regs; + +/* Instructions for the SIGUSR1 handler. */ +static volatile unsigned short sig_cs, sig_ss; +static volatile sig_atomic_t sig_trapped, sig_err, sig_trapno; + +/* Abstractions for some 32-bit vs 64-bit differences. */ +#ifdef __x86_64__ +# define REG_IP REG_RIP +# define REG_SP REG_RSP +# define REG_AX REG_RAX + +struct selectors { + unsigned short cs, gs, fs, ss; +}; + +static unsigned short *ssptr(ucontext_t *ctx) +{ + struct selectors *sels = (void *)&ctx->uc_mcontext.gregs[REG_CSGSFS]; + return &sels->ss; +} + +static unsigned short *csptr(ucontext_t *ctx) +{ + struct selectors *sels = (void *)&ctx->uc_mcontext.gregs[REG_CSGSFS]; + return &sels->cs; +} +#else +# define REG_IP REG_EIP +# define REG_SP REG_ESP +# define REG_AX REG_EAX + +static greg_t *ssptr(ucontext_t *ctx) +{ + return &ctx->uc_mcontext.gregs[REG_SS]; +} + +static greg_t *csptr(ucontext_t *ctx) +{ + return &ctx->uc_mcontext.gregs[REG_CS]; +} +#endif + +/* Number of errors in the current test case. */ +static volatile sig_atomic_t nerrs; + +/* + * SIGUSR1 handler. Sets CS and SS as requested and points IP to the + * int3 trampoline. Sets SP to a large known value so that we can see + * whether the value round-trips back to user mode correctly. + */ +static void sigusr1(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t)); + + *csptr(ctx) = sig_cs; + *ssptr(ctx) = sig_ss; + + ctx->uc_mcontext.gregs[REG_IP] = + sig_cs == code16_sel ? 0 : (unsigned long)&int3; + ctx->uc_mcontext.gregs[REG_SP] = (unsigned long)0x8badf00d5aadc0deULL; + ctx->uc_mcontext.gregs[REG_AX] = 0; + + memcpy(&requested_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t)); + requested_regs[REG_AX] = *ssptr(ctx); /* The asm code does this. */ + + return; +} + +/* + * Called after a successful sigreturn. Restores our state so that + * the original raise(SIGUSR1) returns. + */ +static void sigtrap(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + sig_err = ctx->uc_mcontext.gregs[REG_ERR]; + sig_trapno = ctx->uc_mcontext.gregs[REG_TRAPNO]; + + unsigned short ss; + asm ("mov %%ss,%0" : "=r" (ss)); + + greg_t asm_ss = ctx->uc_mcontext.gregs[REG_AX]; + if (asm_ss != sig_ss && sig == SIGTRAP) { + /* Sanity check failure. */ + printf("[FAIL]\tSIGTRAP: ss = %hx, frame ss = %hx, ax = %llx\n", + ss, *ssptr(ctx), (unsigned long long)asm_ss); + nerrs++; + } + + memcpy(&resulting_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t)); + memcpy(&ctx->uc_mcontext.gregs, &initial_regs, sizeof(gregset_t)); + + sig_trapped = sig; +} + +/* + * Checks a given selector for its code bitness or returns -1 if it's not + * a usable code segment selector. + */ +int cs_bitness(unsigned short cs) +{ + uint32_t valid = 0, ar; + asm ("lar %[cs], %[ar]\n\t" + "jnz 1f\n\t" + "mov $1, %[valid]\n\t" + "1:" + : [ar] "=r" (ar), [valid] "+rm" (valid) + : [cs] "r" (cs)); + + if (!valid) + return -1; + + bool db = (ar & (1 << 22)); + bool l = (ar & (1 << 21)); + + if (!(ar & (1<<11))) + return -1; /* Not code. */ + + if (l && !db) + return 64; + else if (!l && db) + return 32; + else if (!l && !db) + return 16; + else + return -1; /* Unknown bitness. */ +} + +/* Finds a usable code segment of the requested bitness. */ +int find_cs(int bitness) +{ + unsigned short my_cs; + + asm ("mov %%cs,%0" : "=r" (my_cs)); + + if (cs_bitness(my_cs) == bitness) + return my_cs; + if (cs_bitness(my_cs + (2 << 3)) == bitness) + return my_cs + (2 << 3); + if (my_cs > (2<<3) && cs_bitness(my_cs - (2 << 3)) == bitness) + return my_cs - (2 << 3); + if (cs_bitness(code16_sel) == bitness) + return code16_sel; + + printf("[WARN]\tCould not find %d-bit CS\n", bitness); + return -1; +} + +static int test_valid_sigreturn(int cs_bits, bool use_16bit_ss, int force_ss) +{ + int cs = find_cs(cs_bits); + if (cs == -1) { + printf("[SKIP]\tCode segment unavailable for %d-bit CS, %d-bit SS\n", + cs_bits, use_16bit_ss ? 16 : 32); + return 0; + } + + if (force_ss != -1) { + sig_ss = force_ss; + } else { + if (use_16bit_ss) { + if (!data16_sel) { + printf("[SKIP]\tData segment unavailable for %d-bit CS, 16-bit SS\n", + cs_bits); + return 0; + } + sig_ss = data16_sel; + } else { + asm volatile ("mov %%ss,%0" : "=r" (sig_ss)); + } + } + + sig_cs = cs; + + printf("[RUN]\tValid sigreturn: %d-bit CS (%hx), %d-bit SS (%hx%s)\n", + cs_bits, sig_cs, use_16bit_ss ? 16 : 32, sig_ss, + (sig_ss & 4) ? "" : ", GDT"); + + raise(SIGUSR1); + + nerrs = 0; + + /* + * Check that each register had an acceptable value when the + * int3 trampoline was invoked. + */ + for (int i = 0; i < NGREG; i++) { + greg_t req = requested_regs[i], res = resulting_regs[i]; + if (i == REG_TRAPNO || i == REG_IP) + continue; /* don't care */ + if (i == REG_SP) { + printf("\tSP: %llx -> %llx\n", (unsigned long long)req, + (unsigned long long)res); + + /* + * In many circumstances, the high 32 bits of rsp + * are zeroed. For example, we could be a real + * 32-bit program, or we could hit any of a number + * of poorly-documented IRET or segmented ESP + * oddities. If this happens, it's okay. + */ + if (res == (req & 0xFFFFFFFF)) + continue; /* OK; not expected to work */ + } + + bool ignore_reg = false; +#if __i386__ + if (i == REG_UESP) + ignore_reg = true; +#else + if (i == REG_CSGSFS) { + struct selectors *req_sels = + (void *)&requested_regs[REG_CSGSFS]; + struct selectors *res_sels = + (void *)&resulting_regs[REG_CSGSFS]; + if (req_sels->cs != res_sels->cs) { + printf("[FAIL]\tCS mismatch: requested 0x%hx; got 0x%hx\n", + req_sels->cs, res_sels->cs); + nerrs++; + } + + if (req_sels->ss != res_sels->ss) { + printf("[FAIL]\tSS mismatch: requested 0x%hx; got 0x%hx\n", + req_sels->ss, res_sels->ss); + nerrs++; + } + + continue; + } +#endif + + /* Sanity check on the kernel */ + if (i == REG_AX && requested_regs[i] != resulting_regs[i]) { + printf("[FAIL]\tAX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n", + (unsigned long long)requested_regs[i], + (unsigned long long)resulting_regs[i]); + nerrs++; + continue; + } + + if (requested_regs[i] != resulting_regs[i] && !ignore_reg) { + /* + * SP is particularly interesting here. The + * usual cause of failures is that we hit the + * nasty IRET case of returning to a 16-bit SS, + * in which case bits 16:31 of the *kernel* + * stack pointer persist in ESP. + */ + printf("[FAIL]\tReg %d mismatch: requested 0x%llx; got 0x%llx\n", + i, (unsigned long long)requested_regs[i], + (unsigned long long)resulting_regs[i]); + nerrs++; + } + } + + if (nerrs == 0) + printf("[OK]\tall registers okay\n"); + + return nerrs; +} + +static int test_bad_iret(int cs_bits, unsigned short ss, int force_cs) +{ + int cs = force_cs == -1 ? find_cs(cs_bits) : force_cs; + if (cs == -1) + return 0; + + sig_cs = cs; + sig_ss = ss; + + printf("[RUN]\t%d-bit CS (%hx), bogus SS (%hx)\n", + cs_bits, sig_cs, sig_ss); + + sig_trapped = 0; + raise(SIGUSR1); + if (sig_trapped) { + char errdesc[32] = ""; + if (sig_err) { + const char *src = (sig_err & 1) ? " EXT" : ""; + const char *table; + if ((sig_err & 0x6) == 0x0) + table = "GDT"; + else if ((sig_err & 0x6) == 0x4) + table = "LDT"; + else if ((sig_err & 0x6) == 0x2) + table = "IDT"; + else + table = "???"; + + sprintf(errdesc, "%s%s index %d, ", + table, src, sig_err >> 3); + } + + char trapname[32]; + if (sig_trapno == 13) + strcpy(trapname, "GP"); + else if (sig_trapno == 11) + strcpy(trapname, "NP"); + else if (sig_trapno == 12) + strcpy(trapname, "SS"); + else if (sig_trapno == 32) + strcpy(trapname, "IRET"); /* X86_TRAP_IRET */ + else + sprintf(trapname, "%d", sig_trapno); + + printf("[OK]\tGot #%s(0x%lx) (i.e. %s%s)\n", + trapname, (unsigned long)sig_err, + errdesc, strsignal(sig_trapped)); + return 0; + } else { + printf("[FAIL]\tDid not get SIGSEGV\n"); + return 1; + } +} + +int main() +{ + int total_nerrs = 0; + unsigned short my_cs, my_ss; + + asm volatile ("mov %%cs,%0" : "=r" (my_cs)); + asm volatile ("mov %%ss,%0" : "=r" (my_ss)); + setup_ldt(); + + stack_t stack = { + .ss_sp = altstack_data, + .ss_size = SIGSTKSZ, + }; + if (sigaltstack(&stack, NULL) != 0) + err(1, "sigaltstack"); + + sethandler(SIGUSR1, sigusr1, 0); + sethandler(SIGTRAP, sigtrap, SA_ONSTACK); + + /* Easy cases: return to a 32-bit SS in each possible CS bitness. */ + total_nerrs += test_valid_sigreturn(64, false, -1); + total_nerrs += test_valid_sigreturn(32, false, -1); + total_nerrs += test_valid_sigreturn(16, false, -1); + + /* + * Test easy espfix cases: return to a 16-bit LDT SS in each possible + * CS bitness. NB: with a long mode CS, the SS bitness is irrelevant. + * + * This catches the original missing-espfix-on-64-bit-kernels issue + * as well as CVE-2014-8134. + */ + total_nerrs += test_valid_sigreturn(64, true, -1); + total_nerrs += test_valid_sigreturn(32, true, -1); + total_nerrs += test_valid_sigreturn(16, true, -1); + + if (gdt_data16_idx) { + /* + * For performance reasons, Linux skips espfix if SS points + * to the GDT. If we were able to allocate a 16-bit SS in + * the GDT, see if it leaks parts of the kernel stack pointer. + * + * This tests for CVE-2014-8133. + */ + total_nerrs += test_valid_sigreturn(64, true, + GDT3(gdt_data16_idx)); + total_nerrs += test_valid_sigreturn(32, true, + GDT3(gdt_data16_idx)); + total_nerrs += test_valid_sigreturn(16, true, + GDT3(gdt_data16_idx)); + } + + /* + * We're done testing valid sigreturn cases. Now we test states + * for which sigreturn itself will succeed but the subsequent + * entry to user mode will fail. + * + * Depending on the failure mode and the kernel bitness, these + * entry failures can generate SIGSEGV, SIGBUS, or SIGILL. + */ + clearhandler(SIGTRAP); + sethandler(SIGSEGV, sigtrap, SA_ONSTACK); + sethandler(SIGBUS, sigtrap, SA_ONSTACK); + sethandler(SIGILL, sigtrap, SA_ONSTACK); /* 32-bit kernels do this */ + + /* Easy failures: invalid SS, resulting in #GP(0) */ + test_bad_iret(64, ldt_nonexistent_sel, -1); + test_bad_iret(32, ldt_nonexistent_sel, -1); + test_bad_iret(16, ldt_nonexistent_sel, -1); + + /* These fail because SS isn't a data segment, resulting in #GP(SS) */ + test_bad_iret(64, my_cs, -1); + test_bad_iret(32, my_cs, -1); + test_bad_iret(16, my_cs, -1); + + /* Try to return to a not-present code segment, triggering #NP(SS). */ + test_bad_iret(32, my_ss, npcode32_sel); + + /* + * Try to return to a not-present but otherwise valid data segment. + * This will cause IRET to fail with #SS on the espfix stack. This + * exercises CVE-2014-9322. + * + * Note that, if espfix is enabled, 64-bit Linux will lose track + * of the actual cause of failure and report #GP(0) instead. + * This would be very difficult for Linux to avoid, because + * espfix64 causes IRET failures to be promoted to #DF, so the + * original exception frame is never pushed onto the stack. + */ + test_bad_iret(32, npdata32_sel, -1); + + /* + * Try to return to a not-present but otherwise valid data + * segment without invoking espfix. Newer kernels don't allow + * this to happen in the first place. On older kernels, though, + * this can trigger CVE-2014-9322. + */ + if (gdt_npdata32_idx) + test_bad_iret(32, GDT3(gdt_npdata32_idx), -1); + + return total_nerrs ? 1 : 0; +} diff --git a/tools/testing/selftests/x86/trivial_32bit_program.c b/tools/testing/selftests/x86/trivial_32bit_program.c new file mode 100644 index 000000000000..2e231beb0a39 --- /dev/null +++ b/tools/testing/selftests/x86/trivial_32bit_program.c @@ -0,0 +1,14 @@ +/* + * Trivial program to check that we have a valid 32-bit build environment. + * Copyright (c) 2015 Andy Lutomirski + * GPL v2 + */ + +#include <stdio.h> + +int main() +{ + printf("\n"); + + return 0; +} diff --git a/tools/thermal/tmon/.gitignore b/tools/thermal/tmon/.gitignore new file mode 100644 index 000000000000..06e96be65276 --- /dev/null +++ b/tools/thermal/tmon/.gitignore @@ -0,0 +1 @@ +/tmon diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile index e775adcbd29f..0788621c8d76 100644 --- a/tools/thermal/tmon/Makefile +++ b/tools/thermal/tmon/Makefile @@ -2,8 +2,8 @@ VERSION = 1.0 BINDIR=usr/bin WARNFLAGS=-Wall -Wshadow -W -Wformat -Wimplicit-function-declaration -Wimplicit-int -CFLAGS= -O1 ${WARNFLAGS} -fstack-protector -CC=gcc +CFLAGS+= -O1 ${WARNFLAGS} -fstack-protector +CC=$(CROSS_COMPILE)gcc CFLAGS+=-D VERSION=\"$(VERSION)\" LDFLAGS+= @@ -16,12 +16,21 @@ INSTALL_CONFIGFILE=install -m 644 -p CONFIG_FILE= CONFIG_PATH= +# Static builds might require -ltinfo, for instance +ifneq ($(findstring -static, $(LDFLAGS)),) +STATIC := --static +endif + +TMON_LIBS=-lm -lpthread +TMON_LIBS += $(shell pkg-config --libs $(STATIC) panelw ncursesw 2> /dev/null || \ + pkg-config --libs $(STATIC) panel ncurses 2> /dev/null || \ + echo -lpanel -lncurses) OBJS = tmon.o tui.o sysfs.o pid.o OBJS += tmon: $(OBJS) Makefile tmon.h - $(CC) ${CFLAGS} $(LDFLAGS) $(OBJS) -o $(TARGET) -lm -lpanel -lncursesw -ltinfo -lpthread + $(CC) $(CFLAGS) $(LDFLAGS) $(OBJS) -o $(TARGET) $(TMON_LIBS) valgrind: tmon sudo valgrind -v --track-origins=yes --tool=memcheck --leak-check=yes --show-reachable=yes --num-callers=20 --track-fds=yes ./$(TARGET) 1> /dev/null diff --git a/tools/thermal/tmon/sysfs.c b/tools/thermal/tmon/sysfs.c index dfe454855cd2..1c12536f2081 100644 --- a/tools/thermal/tmon/sysfs.c +++ b/tools/thermal/tmon/sysfs.c @@ -446,7 +446,7 @@ int probe_thermal_sysfs(void) return -1; } - ptdata.tzi = calloc(sizeof(struct tz_info), ptdata.max_tz_instance+1); + ptdata.tzi = calloc(ptdata.max_tz_instance+1, sizeof(struct tz_info)); if (!ptdata.tzi) { fprintf(stderr, "Err: allocate tz_info\n"); return -1; @@ -454,8 +454,8 @@ int probe_thermal_sysfs(void) /* we still show thermal zone information if there is no cdev */ if (ptdata.nr_cooling_dev) { - ptdata.cdi = calloc(sizeof(struct cdev_info), - ptdata.max_cdev_instance + 1); + ptdata.cdi = calloc(ptdata.max_cdev_instance + 1, + sizeof(struct cdev_info)); if (!ptdata.cdi) { free(ptdata.tzi); fprintf(stderr, "Err: allocate cdev_info\n"); diff --git a/tools/thermal/tmon/tmon.8 b/tools/thermal/tmon/tmon.8 index 0be727cb9892..02d5179803aa 100644 --- a/tools/thermal/tmon/tmon.8 +++ b/tools/thermal/tmon/tmon.8 @@ -55,6 +55,8 @@ The \fB-l --log\fP option write data to /var/tmp/tmon.log .PP The \fB-t --time-interval\fP option sets the polling interval in seconds .PP +The \fB-T --target-temp\fP option sets the initial target temperature +.PP The \fB-v --version\fP option shows the version of \fBtmon \fP .PP The \fB-z --zone\fP option sets the target therma zone instance to be controlled diff --git a/tools/thermal/tmon/tmon.c b/tools/thermal/tmon/tmon.c index 09b7c3218334..9aa19652e8e8 100644 --- a/tools/thermal/tmon/tmon.c +++ b/tools/thermal/tmon/tmon.c @@ -64,6 +64,7 @@ void usage() printf(" -h, --help show this help message\n"); printf(" -l, --log log data to /var/tmp/tmon.log\n"); printf(" -t, --time-interval sampling time interval, > 1 sec.\n"); + printf(" -T, --target-temp initial target temperature\n"); printf(" -v, --version show version\n"); printf(" -z, --zone target thermal zone id\n"); @@ -219,6 +220,7 @@ static struct option opts[] = { { "control", 1, NULL, 'c' }, { "daemon", 0, NULL, 'd' }, { "time-interval", 1, NULL, 't' }, + { "target-temp", 1, NULL, 'T' }, { "log", 0, NULL, 'l' }, { "help", 0, NULL, 'h' }, { "version", 0, NULL, 'v' }, @@ -231,7 +233,7 @@ int main(int argc, char **argv) { int err = 0; int id2 = 0, c; - double yk = 0.0; /* controller output */ + double yk = 0.0, temp; /* controller output */ int target_tz_index; if (geteuid() != 0) { @@ -239,7 +241,7 @@ int main(int argc, char **argv) exit(EXIT_FAILURE); } - while ((c = getopt_long(argc, argv, "c:dlht:vgz:", opts, &id2)) != -1) { + while ((c = getopt_long(argc, argv, "c:dlht:T:vgz:", opts, &id2)) != -1) { switch (c) { case 'c': no_control = 0; @@ -254,6 +256,14 @@ int main(int argc, char **argv) if (ticktime < 1) ticktime = 1; break; + case 'T': + temp = strtod(optarg, NULL); + if (temp < 0) { + fprintf(stderr, "error: temperature must be positive\n"); + return 1; + } + target_temp_user = temp; + break; case 'l': printf("Logging data to /var/tmp/tmon.log\n"); logging = 1; diff --git a/tools/thermal/tmon/tui.c b/tools/thermal/tmon/tui.c index 89f8ef0e15c8..b5d1c6b22dd3 100644 --- a/tools/thermal/tmon/tui.c +++ b/tools/thermal/tmon/tui.c @@ -30,6 +30,18 @@ #include "tmon.h" +#define min(x, y) ({ \ + typeof(x) _min1 = (x); \ + typeof(y) _min2 = (y); \ + (void) (&_min1 == &_min2); \ + _min1 < _min2 ? _min1 : _min2; }) + +#define max(x, y) ({ \ + typeof(x) _max1 = (x); \ + typeof(y) _max2 = (y); \ + (void) (&_max1 == &_max2); \ + _max1 > _max2 ? _max1 : _max2; }) + static PANEL *data_panel; static PANEL *dialogue_panel; static PANEL *top; @@ -98,6 +110,18 @@ void write_status_bar(int x, char *line) wrefresh(status_bar_window); } +/* wrap at 5 */ +#define DIAG_DEV_ROWS 5 +/* + * list cooling devices + "set temp" entry; wraps after 5 rows, if they fit + */ +static int diag_dev_rows(void) +{ + int entries = ptdata.nr_cooling_dev + 1; + int rows = max(DIAG_DEV_ROWS, (entries + 1) / 2); + return min(rows, entries); +} + void setup_windows(void) { int y_begin = 1; @@ -122,7 +146,7 @@ void setup_windows(void) * dialogue window is a pop-up, when needed it lays on top of cdev win */ - dialogue_window = subwin(stdscr, ptdata.nr_cooling_dev+5, maxx-50, + dialogue_window = subwin(stdscr, diag_dev_rows() + 5, maxx-50, DIAG_Y, DIAG_X); thermal_data_window = subwin(stdscr, ptdata.nr_tz_sensor * @@ -258,21 +282,26 @@ void show_cooling_device(void) } const char DIAG_TITLE[] = "[ TUNABLES ]"; -#define DIAG_DEV_ROWS 5 void show_dialogue(void) { int j, x = 0, y = 0; + int rows, cols; WINDOW *w = dialogue_window; if (tui_disabled || !w) return; + getmaxyx(w, rows, cols); + + /* Silence compiler 'unused' warnings */ + (void)cols; + werase(w); box(w, 0, 0); mvwprintw(w, 0, maxx/4, DIAG_TITLE); /* list all the available tunables */ for (j = 0; j <= ptdata.nr_cooling_dev; j++) { - y = j % DIAG_DEV_ROWS; + y = j % diag_dev_rows(); if (y == 0 && j != 0) x += 20; if (j == ptdata.nr_cooling_dev) @@ -283,12 +312,10 @@ void show_dialogue(void) ptdata.cdi[j].type, ptdata.cdi[j].instance); } wattron(w, A_BOLD); - mvwprintw(w, DIAG_DEV_ROWS+1, 1, "Enter Choice [A-Z]?"); + mvwprintw(w, diag_dev_rows()+1, 1, "Enter Choice [A-Z]?"); wattroff(w, A_BOLD); - /* y size of dialogue win is nr cdev + 5, so print legend - * at the bottom line - */ - mvwprintw(w, ptdata.nr_cooling_dev+3, 1, + /* print legend at the bottom line */ + mvwprintw(w, rows - 2, 1, "Legend: A=Active, P=Passive, C=Critical"); wrefresh(dialogue_window); @@ -437,7 +464,7 @@ static void handle_input_choice(int ch) snprintf(buf, sizeof(buf), "New Value for %.10s-%2d: ", ptdata.cdi[cdev_id].type, ptdata.cdi[cdev_id].instance); - write_dialogue_win(buf, DIAG_DEV_ROWS+2, 2); + write_dialogue_win(buf, diag_dev_rows() + 2, 2); handle_input_val(cdev_id); } else { snprintf(buf, sizeof(buf), "Invalid selection %d", ch); diff --git a/tools/usb/ffs-aio-example/multibuff/host_app/test.c b/tools/usb/ffs-aio-example/multibuff/host_app/test.c index daa3abe6bebd..2cbcce6e8dd7 100644 --- a/tools/usb/ffs-aio-example/multibuff/host_app/test.c +++ b/tools/usb/ffs-aio-example/multibuff/host_app/test.c @@ -33,11 +33,6 @@ #define VENDOR 0x1d6b #define PRODUCT 0x0105 -/* endpoints indexes */ - -#define EP_BULK_IN (1 | LIBUSB_ENDPOINT_IN) -#define EP_BULK_OUT (2 | LIBUSB_ENDPOINT_OUT) - #define BUF_LEN 8192 /* @@ -159,14 +154,21 @@ void test_exit(struct test_state *state) int main(void) { struct test_state state; + struct libusb_config_descriptor *conf; + struct libusb_interface_descriptor const *iface; + unsigned char addr; if (test_init(&state)) return 1; + libusb_get_config_descriptor(state.found, 0, &conf); + iface = &conf->interface[0].altsetting[0]; + addr = iface->endpoint[0].bEndpointAddress; + while (1) { static unsigned char buffer[BUF_LEN]; int bytes; - libusb_bulk_transfer(state.handle, EP_BULK_IN, buffer, BUF_LEN, + libusb_bulk_transfer(state.handle, addr, buffer, BUF_LEN, &bytes, 500); } test_exit(&state); diff --git a/tools/usb/ffs-aio-example/simple/device_app/aio_simple.c b/tools/usb/ffs-aio-example/simple/device_app/aio_simple.c index adc310a6d489..1f44a29818bf 100644 --- a/tools/usb/ffs-aio-example/simple/device_app/aio_simple.c +++ b/tools/usb/ffs-aio-example/simple/device_app/aio_simple.c @@ -103,12 +103,14 @@ static const struct { .bDescriptorType = USB_DT_ENDPOINT, .bEndpointAddress = 1 | USB_DIR_IN, .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = htole16(512), }, .bulk_source = { .bLength = sizeof(descriptors.hs_descs.bulk_source), .bDescriptorType = USB_DT_ENDPOINT, .bEndpointAddress = 2 | USB_DIR_OUT, .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = htole16(512), }, }, }; diff --git a/tools/usb/ffs-aio-example/simple/host_app/test.c b/tools/usb/ffs-aio-example/simple/host_app/test.c index acd6332811f3..aed86ffff280 100644 --- a/tools/usb/ffs-aio-example/simple/host_app/test.c +++ b/tools/usb/ffs-aio-example/simple/host_app/test.c @@ -33,11 +33,6 @@ #define VENDOR 0x1d6b #define PRODUCT 0x0105 -/* endpoints indexes */ - -#define EP_BULK_IN (1 | LIBUSB_ENDPOINT_IN) -#define EP_BULK_OUT (2 | LIBUSB_ENDPOINT_OUT) - #define BUF_LEN 8192 /* @@ -159,16 +154,24 @@ void test_exit(struct test_state *state) int main(void) { struct test_state state; + struct libusb_config_descriptor *conf; + struct libusb_interface_descriptor const *iface; + unsigned char in_addr, out_addr; if (test_init(&state)) return 1; + libusb_get_config_descriptor(state.found, 0, &conf); + iface = &conf->interface[0].altsetting[0]; + in_addr = iface->endpoint[0].bEndpointAddress; + out_addr = iface->endpoint[1].bEndpointAddress; + while (1) { static unsigned char buffer[BUF_LEN]; int bytes; - libusb_bulk_transfer(state.handle, EP_BULK_IN, buffer, BUF_LEN, + libusb_bulk_transfer(state.handle, in_addr, buffer, BUF_LEN, &bytes, 500); - libusb_bulk_transfer(state.handle, EP_BULK_OUT, buffer, BUF_LEN, + libusb_bulk_transfer(state.handle, out_addr, buffer, BUF_LEN, &bytes, 500); } test_exit(&state); diff --git a/tools/usb/usbip/src/usbipd.c b/tools/usb/usbip/src/usbipd.c index 2f87f2d348ba..2a7cd2b8d966 100644 --- a/tools/usb/usbip/src/usbipd.c +++ b/tools/usb/usbip/src/usbipd.c @@ -91,7 +91,6 @@ static void usbipd_help(void) static int recv_request_import(int sockfd) { struct op_import_request req; - struct op_common reply; struct usbip_exported_device *edev; struct usbip_usb_device pdu_udev; struct list_head *i; @@ -100,7 +99,6 @@ static int recv_request_import(int sockfd) int rc; memset(&req, 0, sizeof(req)); - memset(&reply, 0, sizeof(reply)); rc = usbip_net_recv(sockfd, &req, sizeof(req)); if (rc < 0) { diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile index 9325f4693821..505ad51b3b51 100644 --- a/tools/virtio/Makefile +++ b/tools/virtio/Makefile @@ -3,7 +3,7 @@ test: virtio_test vringh_test virtio_test: virtio_ring.o virtio_test.o vringh_test: vringh_test.o vringh.o virtio_ring.o -CFLAGS += -g -O2 -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE +CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE vpath %.c ../../drivers/virtio ../../drivers/vhost mod: ${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index 5a2d1f0f6bc7..a3e07016a440 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -6,31 +6,12 @@ /* TODO: empty stubs for now. Broken but enough for virtio_ring.c */ #define list_add_tail(a, b) do {} while (0) #define list_del(a) do {} while (0) - -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BITS_PER_BYTE 8 -#define BITS_PER_LONG (sizeof(long) * BITS_PER_BYTE) -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) - -/* TODO: Not atomic as it should be: - * we don't use this for anything important. */ -static inline void clear_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p &= ~mask; -} - -static inline int test_bit(int nr, const volatile unsigned long *addr) -{ - return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); -} +#define list_for_each_entry(a, b, c) while (0) /* end of stubs */ struct virtio_device { void *dev; - unsigned long features[1]; + u64 features; }; struct virtqueue { diff --git a/tools/virtio/linux/virtio_byteorder.h b/tools/virtio/linux/virtio_byteorder.h new file mode 100644 index 000000000000..9de9e6ac1d10 --- /dev/null +++ b/tools/virtio/linux/virtio_byteorder.h @@ -0,0 +1,8 @@ +#ifndef _LINUX_VIRTIO_BYTEORDER_STUB_H +#define _LINUX_VIRTIO_BYTEORDER_STUB_H + +#include <asm/byteorder.h> +#include "../../include/linux/byteorder/generic.h" +#include "../../include/linux/virtio_byteorder.h" + +#endif diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h index 5049967f99f7..806d683ab107 100644 --- a/tools/virtio/linux/virtio_config.h +++ b/tools/virtio/linux/virtio_config.h @@ -1,6 +1,72 @@ -#define VIRTIO_TRANSPORT_F_START 28 -#define VIRTIO_TRANSPORT_F_END 32 +#include <linux/virtio_byteorder.h> +#include <linux/virtio.h> +#include <uapi/linux/virtio_config.h> + +/* + * __virtio_test_bit - helper to test feature bits. For use by transports. + * Devices should normally use virtio_has_feature, + * which includes more checks. + * @vdev: the device + * @fbit: the feature bit + */ +static inline bool __virtio_test_bit(const struct virtio_device *vdev, + unsigned int fbit) +{ + return vdev->features & (1ULL << fbit); +} + +/** + * __virtio_set_bit - helper to set feature bits. For use by transports. + * @vdev: the device + * @fbit: the feature bit + */ +static inline void __virtio_set_bit(struct virtio_device *vdev, + unsigned int fbit) +{ + vdev->features |= (1ULL << fbit); +} + +/** + * __virtio_clear_bit - helper to clear feature bits. For use by transports. + * @vdev: the device + * @fbit: the feature bit + */ +static inline void __virtio_clear_bit(struct virtio_device *vdev, + unsigned int fbit) +{ + vdev->features &= ~(1ULL << fbit); +} #define virtio_has_feature(dev, feature) \ - test_bit((feature), (dev)->features) + (__virtio_test_bit((dev), feature)) + +static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val) +{ + return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); +} + +static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val) +{ + return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); +} + +static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val) +{ + return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); +} + +static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val) +{ + return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); +} + +static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val) +{ + return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); +} + +static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) +{ + return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); +} diff --git a/tools/virtio/uapi/linux/virtio_types.h b/tools/virtio/uapi/linux/virtio_types.h new file mode 100644 index 000000000000..e7a1096e7c97 --- /dev/null +++ b/tools/virtio/uapi/linux/virtio_types.h @@ -0,0 +1 @@ +#include "../../include/uapi/linux/virtio_types.h" diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index 00ea679b3826..e0445898f08f 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -11,6 +11,7 @@ #include <sys/types.h> #include <fcntl.h> #include <stdbool.h> +#include <linux/virtio_types.h> #include <linux/vhost.h> #include <linux/virtio.h> #include <linux/virtio_ring.h> @@ -60,7 +61,7 @@ void vhost_vq_setup(struct vdev_info *dev, struct vq_info *info) { struct vhost_vring_state state = { .index = info->idx }; struct vhost_vring_file file = { .index = info->idx }; - unsigned long long features = dev->vdev.features[0]; + unsigned long long features = dev->vdev.features; struct vhost_vring_addr addr = { .index = info->idx, .desc_user_addr = (uint64_t)(unsigned long)info->vring.desc, @@ -113,8 +114,7 @@ static void vdev_info_init(struct vdev_info* dev, unsigned long long features) { int r; memset(dev, 0, sizeof *dev); - dev->vdev.features[0] = features; - dev->vdev.features[1] = features >> 32; + dev->vdev.features = features; dev->buf_size = 1024; dev->buf = malloc(dev->buf_size); assert(dev->buf); @@ -228,6 +228,14 @@ const struct option longopts[] = { .val = 'i', }, { + .name = "virtio-1", + .val = '1', + }, + { + .name = "no-virtio-1", + .val = '0', + }, + { .name = "delayed-interrupt", .val = 'D', }, @@ -244,6 +252,7 @@ static void help(void) fprintf(stderr, "Usage: virtio_test [--help]" " [--no-indirect]" " [--no-event-idx]" + " [--no-virtio-1]" " [--delayed-interrupt]" "\n"); } @@ -252,7 +261,7 @@ int main(int argc, char **argv) { struct vdev_info dev; unsigned long long features = (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | - (1ULL << VIRTIO_RING_F_EVENT_IDX); + (1ULL << VIRTIO_RING_F_EVENT_IDX) | (1ULL << VIRTIO_F_VERSION_1); int o; bool delayed = false; @@ -273,6 +282,9 @@ int main(int argc, char **argv) case 'i': features &= ~(1ULL << VIRTIO_RING_F_INDIRECT_DESC); break; + case '0': + features &= ~(1ULL << VIRTIO_F_VERSION_1); + break; case 'D': delayed = true; break; diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c index 14a4f4cab5b9..5f94f5105678 100644 --- a/tools/virtio/vringh_test.c +++ b/tools/virtio/vringh_test.c @@ -7,6 +7,7 @@ #include <linux/virtio.h> #include <linux/vringh.h> #include <linux/virtio_ring.h> +#include <linux/virtio_config.h> #include <linux/uaccess.h> #include <sys/types.h> #include <sys/stat.h> @@ -131,7 +132,7 @@ static inline int vringh_get_head(struct vringh *vrh, u16 *head) return 1; } -static int parallel_test(unsigned long features, +static int parallel_test(u64 features, bool (*getrange)(struct vringh *vrh, u64 addr, struct vringh_range *r), bool fast_vringh) @@ -304,7 +305,7 @@ static int parallel_test(unsigned long features, close(to_guest[1]); close(to_host[0]); - gvdev.vdev.features[0] = features; + gvdev.vdev.features = features; gvdev.to_host_fd = to_host[1]; gvdev.notifies = 0; @@ -449,13 +450,15 @@ int main(int argc, char *argv[]) bool fast_vringh = false, parallel = false; getrange = getrange_iov; - vdev.features[0] = 0; + vdev.features = 0; while (argv[1]) { if (strcmp(argv[1], "--indirect") == 0) - vdev.features[0] |= (1 << VIRTIO_RING_F_INDIRECT_DESC); + __virtio_set_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC); else if (strcmp(argv[1], "--eventidx") == 0) - vdev.features[0] |= (1 << VIRTIO_RING_F_EVENT_IDX); + __virtio_set_bit(&vdev, VIRTIO_RING_F_EVENT_IDX); + else if (strcmp(argv[1], "--virtio-1") == 0) + __virtio_set_bit(&vdev, VIRTIO_F_VERSION_1); else if (strcmp(argv[1], "--slow-range") == 0) getrange = getrange_slow; else if (strcmp(argv[1], "--fast-vringh") == 0) @@ -468,7 +471,7 @@ int main(int argc, char *argv[]) } if (parallel) - return parallel_test(vdev.features[0], getrange, fast_vringh); + return parallel_test(vdev.features, getrange, fast_vringh); if (posix_memalign(&__user_addr_min, PAGE_SIZE, USER_MEM) != 0) abort(); @@ -483,7 +486,7 @@ int main(int argc, char *argv[]) /* Set up host side. */ vring_init(&vrh.vring, RINGSIZE, __user_addr_min, ALIGN); - vringh_init_user(&vrh, vdev.features[0], RINGSIZE, true, + vringh_init_user(&vrh, vdev.features, RINGSIZE, true, vrh.vring.desc, vrh.vring.avail, vrh.vring.used); /* No descriptor to get yet... */ @@ -652,13 +655,13 @@ int main(int argc, char *argv[]) } /* Test weird (but legal!) indirect. */ - if (vdev.features[0] & (1 << VIRTIO_RING_F_INDIRECT_DESC)) { + if (__virtio_test_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC)) { char *data = __user_addr_max - USER_MEM/4; struct vring_desc *d = __user_addr_max - USER_MEM/2; struct vring vring; /* Force creation of direct, which we modify. */ - vdev.features[0] &= ~(1 << VIRTIO_RING_F_INDIRECT_DESC); + __virtio_clear_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC); vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true, __user_addr_min, never_notify_host, diff --git a/tools/vm/Makefile b/tools/vm/Makefile index 3d907dacf2ac..ac884b65a072 100644 --- a/tools/vm/Makefile +++ b/tools/vm/Makefile @@ -1,6 +1,6 @@ # Makefile for vm tools # -TARGETS=page-types slabinfo +TARGETS=page-types slabinfo page_owner_sort LIB_DIR = ../lib/api LIBS = $(LIB_DIR)/libapikfs.a @@ -18,5 +18,5 @@ $(LIBS): $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) clean: - $(RM) page-types slabinfo + $(RM) page-types slabinfo page_owner_sort make -C $(LIB_DIR) clean diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 264fbc297e0b..8bdf16b8ba60 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -133,6 +133,7 @@ static const char * const page_flag_names[] = { [KPF_KSM] = "x:ksm", [KPF_THP] = "t:thp", [KPF_BALLOON] = "o:balloon", + [KPF_ZERO_PAGE] = "z:zero_page", [KPF_RESERVED] = "r:reserved", [KPF_MLOCKED] = "m:mlocked", diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c new file mode 100644 index 000000000000..77147b42d598 --- /dev/null +++ b/tools/vm/page_owner_sort.c @@ -0,0 +1,144 @@ +/* + * User-space helper to sort the output of /sys/kernel/debug/page_owner + * + * Example use: + * cat /sys/kernel/debug/page_owner > page_owner_full.txt + * grep -v ^PFN page_owner_full.txt > page_owner.txt + * ./sort page_owner.txt sorted_page_owner.txt +*/ + +#include <stdio.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> +#include <string.h> + +struct block_list { + char *txt; + int len; + int num; +}; + + +static struct block_list *list; +static int list_size; +static int max_size; + +struct block_list *block_head; + +int read_block(char *buf, int buf_size, FILE *fin) +{ + char *curr = buf, *const buf_end = buf + buf_size; + + while (buf_end - curr > 1 && fgets(curr, buf_end - curr, fin)) { + if (*curr == '\n') /* empty line */ + return curr - buf; + curr += strlen(curr); + } + + return -1; /* EOF or no space left in buf. */ +} + +static int compare_txt(const void *p1, const void *p2) +{ + const struct block_list *l1 = p1, *l2 = p2; + + return strcmp(l1->txt, l2->txt); +} + +static int compare_num(const void *p1, const void *p2) +{ + const struct block_list *l1 = p1, *l2 = p2; + + return l2->num - l1->num; +} + +static void add_list(char *buf, int len) +{ + if (list_size != 0 && + len == list[list_size-1].len && + memcmp(buf, list[list_size-1].txt, len) == 0) { + list[list_size-1].num++; + return; + } + if (list_size == max_size) { + printf("max_size too small??\n"); + exit(1); + } + list[list_size].txt = malloc(len+1); + list[list_size].len = len; + list[list_size].num = 1; + memcpy(list[list_size].txt, buf, len); + list[list_size].txt[len] = 0; + list_size++; + if (list_size % 1000 == 0) { + printf("loaded %d\r", list_size); + fflush(stdout); + } +} + +#define BUF_SIZE 1024 + +int main(int argc, char **argv) +{ + FILE *fin, *fout; + char buf[BUF_SIZE]; + int ret, i, count; + struct block_list *list2; + struct stat st; + + if (argc < 3) { + printf("Usage: ./program <input> <output>\n"); + perror("open: "); + exit(1); + } + + fin = fopen(argv[1], "r"); + fout = fopen(argv[2], "w"); + if (!fin || !fout) { + printf("Usage: ./program <input> <output>\n"); + perror("open: "); + exit(1); + } + + fstat(fileno(fin), &st); + max_size = st.st_size / 100; /* hack ... */ + + list = malloc(max_size * sizeof(*list)); + + for ( ; ; ) { + ret = read_block(buf, BUF_SIZE, fin); + if (ret < 0) + break; + + add_list(buf, ret); + } + + printf("loaded %d\n", list_size); + + printf("sorting ....\n"); + + qsort(list, list_size, sizeof(list[0]), compare_txt); + + list2 = malloc(sizeof(*list) * list_size); + + printf("culling\n"); + + for (i = count = 0; i < list_size; i++) { + if (count == 0 || + strcmp(list2[count-1].txt, list[i].txt) != 0) { + list2[count++] = list[i]; + } else { + list2[count-1].num += list[i].num; + } + } + + qsort(list2, count, sizeof(list[0]), compare_num); + + for (i = 0; i < count; i++) + fprintf(fout, "%d times:\n%s\n", list2[i].num, list2[i].txt); + + return 0; +} |