diff options
Diffstat (limited to 'tools')
530 files changed, 27152 insertions, 6999 deletions
diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c index fba1c75..f437d73 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]; @@ -88,7 +89,8 @@ static int hv_start_fcopy(struct hv_start_fcopy *smsg) } } - target_fd = open(target_fname, O_RDWR | O_CREAT | O_CLOEXEC, 0744); + target_fd = open(target_fname, + O_RDWR | O_CREAT | O_TRUNC | O_CLOEXEC, 0744); if (target_fd == -1) { syslog(LOG_INFO, "Open Failed: %s", strerror(errno)); goto done; @@ -125,15 +127,43 @@ 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 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 4088b81..6a6432a 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 @@ -1417,7 +1418,15 @@ 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 +1444,30 @@ 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 +1559,15 @@ 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 +1770,15 @@ 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 6a213b8..5e63f70 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/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h new file mode 100644 index 0000000..6eedba1 --- /dev/null +++ b/tools/include/asm-generic/bitops.h @@ -0,0 +1,27 @@ +#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/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 0000000..c941750 --- /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 0000000..2218b9a --- /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/atomic.h b/tools/include/asm-generic/bitops/atomic.h new file mode 100644 index 0000000..4bccd7c3 --- /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/find.h b/tools/include/asm-generic/bitops/find.h new file mode 100644 index 0000000..31f5154 --- /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 0000000..dbf711a --- /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 0000000..980b1f6 --- /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/linux/bitops.h b/tools/include/linux/bitops.h new file mode 100644 index 0000000..26005a15 --- /dev/null +++ b/tools/include/linux/bitops.h @@ -0,0 +1,53 @@ +#ifndef _TOOLS_LINUX_BITOPS_H_ +#define _TOOLS_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 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) + +/* + * 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 0000000..4144666 --- /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/include/tools/endian.h b/tools/include/tools/endian.h new file mode 100644 index 0000000..8001194 --- /dev/null +++ b/tools/include/tools/endian.h @@ -0,0 +1,56 @@ +#ifndef _TOOLS_ENDIAN_H +#define _TOOLS_ENDIAN_H + +#include <byteswap.h> + +#if __BYTE_ORDER == __LITTLE_ENDIAN + +#ifndef htole16 +#define htole16(x) (x) +#endif +#ifndef htole32 +#define htole32(x) (x) +#endif +#ifndef htole64 +#define htole64(x) (x) +#endif + +#ifndef le16toh +#define le16toh(x) (x) +#endif + +#ifndef le32toh +#define le32toh(x) (x) +#endif + +#ifndef le64toh +#define le64toh(x) (x) +#endif + +#else /* __BYTE_ORDER */ + +#ifndef htole16 +#define htole16(x) __bswap_16(x) +#endif +#ifndef htole32 +#define htole32(x) __bswap_32(x) +#endif +#ifndef htole64 +#define htole64(x) __bswap_64(x) +#endif + +#ifndef le16toh +#define le16toh(x) __bswap_16(x) +#endif + +#ifndef le32toh +#define le32toh(x) __bswap_32(x) +#endif + +#ifndef le64toh +#define le64toh(x) __bswap_64(x) +#endif + +#endif + +#endif /* _TOOLS_ENDIAN_H */ diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile index ce00f7e..36c08b1 100644 --- a/tools/lib/api/Makefile +++ b/tools/lib/api/Makefile @@ -10,9 +10,14 @@ LIB_OBJS= LIB_H += fs/debugfs.h LIB_H += fs/fs.h +# See comment below about piggybacking... +LIB_H += fd/array.h LIB_OBJS += $(OUTPUT)fs/debugfs.o LIB_OBJS += $(OUTPUT)fs/fs.o +# XXX piggybacking here, need to introduce libapikfd, or rename this +# to plain libapik.a and make it have it all api goodies +LIB_OBJS += $(OUTPUT)fd/array.o LIBFILE = libapikfs.a @@ -29,7 +34,7 @@ $(LIBFILE): $(LIB_OBJS) $(LIB_OBJS): $(LIB_H) libapi_dirs: - $(QUIET_MKDIR)mkdir -p $(OUTPUT)fs/ + $(QUIET_MKDIR)mkdir -p $(OUTPUT)fd $(OUTPUT)fs $(OUTPUT)%.o: %.c libapi_dirs $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $< diff --git a/tools/lib/api/fd/array.c b/tools/lib/api/fd/array.c new file mode 100644 index 0000000..0e636c4 --- /dev/null +++ b/tools/lib/api/fd/array.c @@ -0,0 +1,127 @@ +/* + * Copyright (C) 2014, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Released under the GPL v2. (and only v2, not any later version) + */ +#include "array.h" +#include <errno.h> +#include <fcntl.h> +#include <poll.h> +#include <stdlib.h> +#include <unistd.h> + +void fdarray__init(struct fdarray *fda, int nr_autogrow) +{ + fda->entries = NULL; + fda->priv = NULL; + fda->nr = fda->nr_alloc = 0; + fda->nr_autogrow = nr_autogrow; +} + +int fdarray__grow(struct fdarray *fda, int nr) +{ + void *priv; + int nr_alloc = fda->nr_alloc + nr; + size_t psize = sizeof(fda->priv[0]) * nr_alloc; + size_t size = sizeof(struct pollfd) * nr_alloc; + struct pollfd *entries = realloc(fda->entries, size); + + if (entries == NULL) + return -ENOMEM; + + priv = realloc(fda->priv, psize); + if (priv == NULL) { + free(entries); + return -ENOMEM; + } + + fda->nr_alloc = nr_alloc; + fda->entries = entries; + fda->priv = priv; + return 0; +} + +struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow) +{ + struct fdarray *fda = calloc(1, sizeof(*fda)); + + if (fda != NULL) { + if (fdarray__grow(fda, nr_alloc)) { + free(fda); + fda = NULL; + } else { + fda->nr_autogrow = nr_autogrow; + } + } + + return fda; +} + +void fdarray__exit(struct fdarray *fda) +{ + free(fda->entries); + free(fda->priv); + fdarray__init(fda, 0); +} + +void fdarray__delete(struct fdarray *fda) +{ + fdarray__exit(fda); + free(fda); +} + +int fdarray__add(struct fdarray *fda, int fd, short revents) +{ + int pos = fda->nr; + + if (fda->nr == fda->nr_alloc && + fdarray__grow(fda, fda->nr_autogrow) < 0) + return -ENOMEM; + + fda->entries[fda->nr].fd = fd; + fda->entries[fda->nr].events = revents; + fda->nr++; + return pos; +} + +int fdarray__filter(struct fdarray *fda, short revents, + void (*entry_destructor)(struct fdarray *fda, int fd)) +{ + int fd, nr = 0; + + if (fda->nr == 0) + return 0; + + for (fd = 0; fd < fda->nr; ++fd) { + if (fda->entries[fd].revents & revents) { + if (entry_destructor) + entry_destructor(fda, fd); + + continue; + } + + if (fd != nr) { + fda->entries[nr] = fda->entries[fd]; + fda->priv[nr] = fda->priv[fd]; + } + + ++nr; + } + + return fda->nr = nr; +} + +int fdarray__poll(struct fdarray *fda, int timeout) +{ + return poll(fda->entries, fda->nr, timeout); +} + +int fdarray__fprintf(struct fdarray *fda, FILE *fp) +{ + int fd, printed = fprintf(fp, "%d [ ", fda->nr); + + for (fd = 0; fd < fda->nr; ++fd) + printed += fprintf(fp, "%s%d", fd ? ", " : "", fda->entries[fd].fd); + + return printed + fprintf(fp, " ]"); +} diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h new file mode 100644 index 0000000..45db018 --- /dev/null +++ b/tools/lib/api/fd/array.h @@ -0,0 +1,46 @@ +#ifndef __API_FD_ARRAY__ +#define __API_FD_ARRAY__ + +#include <stdio.h> + +struct pollfd; + +/** + * struct fdarray: Array of file descriptors + * + * @priv: Per array entry priv area, users should access just its contents, + * not set it to anything, as it is kept in synch with @entries, being + * realloc'ed, * for instance, in fdarray__{grow,filter}. + * + * I.e. using 'fda->priv[N].idx = * value' where N < fda->nr is ok, + * but doing 'fda->priv = malloc(M)' is not allowed. + */ +struct fdarray { + int nr; + int nr_alloc; + int nr_autogrow; + struct pollfd *entries; + union { + int idx; + } *priv; +}; + +void fdarray__init(struct fdarray *fda, int nr_autogrow); +void fdarray__exit(struct fdarray *fda); + +struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow); +void fdarray__delete(struct fdarray *fda); + +int fdarray__add(struct fdarray *fda, int fd, short revents); +int fdarray__poll(struct fdarray *fda, int timeout); +int fdarray__filter(struct fdarray *fda, short revents, + void (*entry_destructor)(struct fdarray *fda, int fd)); +int fdarray__grow(struct fdarray *fda, int extra); +int fdarray__fprintf(struct fdarray *fda, FILE *fp); + +static inline int fdarray__available_entries(struct fdarray *fda) +{ + return fda->nr_alloc - fda->nr; +} + +#endif /* __API_FD_ARRAY__ */ diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index c1b49c3..65d9be3 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" @@ -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 cb70495..6caa2bb 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/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 93825a1..cf3a44b 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2395,7 +2395,7 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok) { struct print_arg *field; enum event_type type; - char *token; + char *token = NULL; memset(arg, 0, sizeof(*arg)); arg->type = PRINT_FLAGS; @@ -2448,7 +2448,7 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok) { struct print_arg *field; enum event_type type; - char *token; + char *token = NULL; memset(arg, 0, sizeof(*arg)); arg->type = PRINT_SYMBOL; @@ -2487,7 +2487,7 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok) { struct print_arg *field; enum event_type type; - char *token; + char *token = NULL; memset(arg, 0, sizeof(*arg)); arg->type = PRINT_HEX; diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c index c066b25..4592d84 100644 --- a/tools/lib/traceevent/plugin_cfg80211.c +++ b/tools/lib/traceevent/plugin_cfg80211.c @@ -5,8 +5,7 @@ #include "event-parse.h" static unsigned long long -process___le16_to_cpup(struct trace_seq *s, - unsigned long long *args) +process___le16_to_cpup(struct trace_seq *s, unsigned long long *args) { uint16_t *val = (uint16_t *) (unsigned long) args[0]; return val ? (long long) le16toh(*val) : 0; diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c index 0db714c..5c23d5b 100644 --- a/tools/lib/traceevent/plugin_jbd2.c +++ b/tools/lib/traceevent/plugin_jbd2.c @@ -30,8 +30,7 @@ #define MINOR(dev) ((unsigned int) ((dev) & MINORMASK)) static unsigned long long -process_jbd2_dev_to_name(struct trace_seq *s, - unsigned long long *args) +process_jbd2_dev_to_name(struct trace_seq *s, unsigned long long *args) { unsigned int dev = args[0]; @@ -40,8 +39,7 @@ process_jbd2_dev_to_name(struct trace_seq *s, } static unsigned long long -process_jiffies_to_msecs(struct trace_seq *s, - unsigned long long *args) +process_jiffies_to_msecs(struct trace_seq *s, unsigned long long *args) { unsigned long long jiffies = args[0]; diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c index 9e0e8c6..88fe83d 100644 --- a/tools/lib/traceevent/plugin_kvm.c +++ b/tools/lib/traceevent/plugin_kvm.c @@ -240,25 +240,38 @@ static const char *find_exit_reason(unsigned isa, int val) for (i = 0; strings[i].val >= 0; i++) if (strings[i].val == val) break; - if (strings[i].str) - return strings[i].str; - return "UNKNOWN"; + + return strings[i].str; } -static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record, - struct event_format *event, void *context) +static int print_exit_reason(struct trace_seq *s, struct pevent_record *record, + struct event_format *event, const char *field) { unsigned long long isa; unsigned long long val; - unsigned long long info1 = 0, info2 = 0; + const char *reason; - if (pevent_get_field_val(s, event, "exit_reason", record, &val, 1) < 0) + if (pevent_get_field_val(s, event, field, record, &val, 1) < 0) return -1; if (pevent_get_field_val(s, event, "isa", record, &isa, 0) < 0) isa = 1; - trace_seq_printf(s, "reason %s", find_exit_reason(isa, val)); + reason = find_exit_reason(isa, val); + if (reason) + trace_seq_printf(s, "reason %s", reason); + else + trace_seq_printf(s, "reason UNKNOWN (%llu)", val); + return 0; +} + +static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record, + struct event_format *event, void *context) +{ + unsigned long long info1 = 0, info2 = 0; + + if (print_exit_reason(s, record, event, "exit_reason") < 0) + return -1; pevent_print_num_field(s, " rip 0x%lx", event, "guest_rip", record, 1); @@ -313,6 +326,29 @@ static int kvm_emulate_insn_handler(struct trace_seq *s, return 0; } + +static int kvm_nested_vmexit_inject_handler(struct trace_seq *s, struct pevent_record *record, + struct event_format *event, void *context) +{ + if (print_exit_reason(s, record, event, "exit_code") < 0) + return -1; + + pevent_print_num_field(s, " info1 %llx", event, "exit_info1", record, 1); + pevent_print_num_field(s, " info2 %llx", event, "exit_info2", record, 1); + pevent_print_num_field(s, " int_info %llx", event, "exit_int_info", record, 1); + pevent_print_num_field(s, " int_info_err %llx", event, "exit_int_info_err", record, 1); + + return 0; +} + +static int kvm_nested_vmexit_handler(struct trace_seq *s, struct pevent_record *record, + struct event_format *event, void *context) +{ + pevent_print_num_field(s, "rip %llx ", event, "rip", record, 1); + + return kvm_nested_vmexit_inject_handler(s, record, event, context); +} + union kvm_mmu_page_role { unsigned word; struct { @@ -409,6 +445,12 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent) pevent_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn", kvm_emulate_insn_handler, NULL); + pevent_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit", + kvm_nested_vmexit_handler, NULL); + + pevent_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject", + kvm_nested_vmexit_inject_handler, NULL); + pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page", kvm_mmu_get_page_handler, NULL); @@ -443,6 +485,12 @@ void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent) pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn", kvm_emulate_insn_handler, NULL); + pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit", + kvm_nested_vmexit_handler, NULL); + + pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject", + kvm_nested_vmexit_inject_handler, NULL); + pevent_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page", kvm_mmu_get_page_handler, NULL); diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c index eda326f..3727de4 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 0000000..41b44f6 --- /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 782d86e..40399c3 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 @@ -15,6 +17,7 @@ perf.data perf.data.old output.svg perf-archive +perf-with-kcore tags TAGS cscope* diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt index 4464ad7..f6480cb 100644 --- a/tools/perf/Documentation/perf-bench.txt +++ b/tools/perf/Documentation/perf-bench.txt @@ -16,6 +16,10 @@ This 'perf bench' command is a general framework for benchmark suites. COMMON OPTIONS -------------- +-r:: +--repeat=:: +Specify amount of times to repeat the run (default 10). + -f:: --format=:: Specify format style. diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index b3b8aba..e463caa 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -196,10 +196,10 @@ If specified the 'Weighted diff' column is displayed with value 'd' computed as: - period being the hist entry period value - - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option + - WEIGHT-A/WEIGHT-B being user supplied weights in the the '-c' option behind ':' separator like '-c wdiff:1,2'. - - WIEGHT-A being the weight of the data file - - WIEGHT-B being the weight of the baseline data file + - WEIGHT-A being the weight of the data file + - WEIGHT-B being the weight of the baseline data file SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt index a00a342..dc7442c 100644 --- a/tools/perf/Documentation/perf-inject.txt +++ b/tools/perf/Documentation/perf-inject.txt @@ -41,6 +41,9 @@ OPTIONS tasks slept. sched_switch contains a callchain where a task slept and sched_stat contains a timeslice how long a task slept. +--kallsyms=<file>:: + kallsyms pathname + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1] diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt index 52276a6..6252e77 100644 --- a/tools/perf/Documentation/perf-kvm.txt +++ b/tools/perf/Documentation/perf-kvm.txt @@ -51,9 +51,9 @@ There are a couple of variants of perf kvm: 'perf kvm stat <command>' to run a command and gather performance counter statistics. Especially, perf 'kvm stat record/report' generates a statistical analysis - of KVM events. Currently, vmexit, mmio and ioport events are supported. - 'perf kvm stat record <command>' records kvm events and the events between - start and end <command>. + of KVM events. Currently, vmexit, mmio (x86 only) and ioport (x86 only) + events are supported. 'perf kvm stat record <command>' records kvm events + and the events between start and end <command>. And this command produces a file which contains tracing results of kvm events. @@ -100,11 +100,11 @@ OPTIONS STAT REPORT OPTIONS ------------------- --vcpu=<value>:: - analyze events which occures on this vcpu. (default: all vcpus) + analyze events which occur on this vcpu. (default: all vcpus) --event=<value>:: - event to be analyzed. Possible values: vmexit, mmio, ioport. - (default: vmexit) + event to be analyzed. Possible values: vmexit, mmio (x86 only), + ioport (x86 only). (default: vmexit) -k:: --key=<value>:: Sorting key. Possible values: sample (default, sort by samples @@ -134,11 +134,12 @@ STAT LIVE OPTIONS Analyze events only for given process ID(s) (comma separated list). --vcpu=<value>:: - analyze events which occures on this vcpu. (default: all vcpus) + analyze events which occur on this vcpu. (default: all vcpus) --event=<value>:: - event to be analyzed. Possible values: vmexit, mmio, ioport. + event to be analyzed. Possible values: vmexit, + mmio (x86 only), ioport (x86 only). (default: vmexit) -k:: @@ -147,7 +148,8 @@ STAT LIVE OPTIONS number), time (sort by average time). --duration=<value>:: - Show events other than HLT that take longer than duration usecs. + Show events other than HLT (x86 only) or Wait state (s390 only) + that take longer than duration usecs. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 6fce6a6..cbb4f74 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -19,7 +19,7 @@ various perf commands with the -e option. EVENT MODIFIERS --------------- -Events can optionally have a modifer by appending a colon and one or +Events can optionally have a modifier by appending a colon and one or more modifiers. Modifiers allow the user to restrict the events to be counted. The following modifiers exist: diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 1513935..aaa869b 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -104,6 +104,9 @@ OPTIONS Specify path to the executable or shared library file for user space tracing. Can also be used with --funcs option. +--demangle-kernel:: + Demangle kernel symbols. + In absence of -m/-x options, perf probe checks if the first argument after the options is an absolute path name. If its an absolute path, perf probe uses it as a target module/target user space binary to probe. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index d460049..af9a54e 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -146,7 +146,7 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. -N:: --no-buildid-cache:: -Do not update the builid cache. This saves some overhead in situations +Do not update the buildid cache. This saves some overhead in situations where the information in the perf.data file (which includes buildids) is sufficient. @@ -214,6 +214,12 @@ 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 d2b59af..dd7cccd 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -147,7 +147,7 @@ OPTIONS -w:: --column-widths=<width[,width...]>:: Force each column width to the provided list, for large terminal - readability. + readability. 0 means no limit (default behavior). -t:: --field-separator=:: @@ -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. @@ -276,6 +286,9 @@ OPTIONS Demangle symbol names to human readable form. It's enabled by default, disable with --no-demangle. +--demangle-kernel:: + Demangle kernel symbol names to human readable form (for C++ kernels). + --mem-mode:: Use the data addresses of samples in addition to instruction addresses to build the histograms. To generate meaningful output, the perf.data diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index d00bef2..dfbb506 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -181,8 +181,8 @@ strings for flag and symbolic fields. These correspond to the strings and values parsed from the 'print fmt' fields of the event format files: - flag_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the flag field $field_name of event $event_name - symbol_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the symbolic field $field_name of event $event_name + flag_str($event_name, $field_name, $field_value) - returns the string representation corresponding to $field_value for the flag field $field_name of event $event_name + symbol_str($event_name, $field_name, $field_value) - returns the string representation corresponding to $field_value for the symbolic field $field_name of event $event_name Perf::Trace::Context Module ~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 9f1f054..54acba2 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -263,7 +263,7 @@ and having the counts we've tallied as values. The print_syscall_totals() function iterates over the entries in the dictionary and displays a line for each entry containing the syscall -name (the dictonary keys contain the syscall ids, which are passed to +name (the dictionary keys contain the syscall ids, which are passed to the Util function syscall_name(), which translates the raw syscall numbers to the corresponding syscall name strings). The output is displayed after all the events in the trace have been processed, by @@ -576,8 +576,8 @@ strings for flag and symbolic fields. These correspond to the strings and values parsed from the 'print fmt' fields of the event format files: - flag_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the flag field field_name of event event_name - symbol_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the symbolic field field_name of event event_name + flag_str(event_name, field_name, field_value) - returns the string representation corresponding to field_value for the flag field field_name of event event_name + symbol_str(event_name, field_name, field_value) - returns the string representation corresponding to field_value for the symbolic field field_name of event event_name The *autodict* function returns a special kind of Python dictionary that implements Perl's 'autovivifying' hashes in Python diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 05f9a0a..2149480 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -115,7 +115,7 @@ OPTIONS -f:: --fields:: Comma separated list of fields to print. Options are: - comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline. + comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -f sw:comm,tid,time,ip,sym and -f trace:time,cpu,trace @@ -140,7 +140,7 @@ OPTIONS "Overriding previous field request for all events." - Alternativey, consider the order: + Alternatively, consider the order: -f comm,tid,time,ip,sym -f trace: diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt index d1d3e5121..31a5c3e 100644 --- a/tools/perf/Documentation/perf-test.txt +++ b/tools/perf/Documentation/perf-test.txt @@ -25,7 +25,7 @@ OPTIONS ------- -s:: --skip:: - Tests to skip (comma separater numeric list). + Tests to skip (comma separated numeric list). -v:: --verbose:: diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt index 5e0f986..df98d1c 100644 --- a/tools/perf/Documentation/perf-timechart.txt +++ b/tools/perf/Documentation/perf-timechart.txt @@ -15,10 +15,20 @@ DESCRIPTION There are two variants of perf timechart: 'perf timechart record <command>' to record the system level events - of an arbitrary workload. + of an arbitrary workload. By default timechart records only scheduler + and CPU events (task switches, running times, CPU power states, etc), + but it's possible to record IO (disk, network) activity using -I argument. 'perf timechart' to turn a trace into a Scalable Vector Graphics file, - that can be viewed with popular SVG viewers such as 'Inkscape'. + that can be viewed with popular SVG viewers such as 'Inkscape'. Depending + on the events in the perf.data file, timechart will contain scheduler/cpu + events or IO events. + + In IO mode, every bar has two charts: upper and lower. + Upper bar shows incoming events (disk reads, ingress network packets). + Lower bar shows outgoing events (disk writes, egress network packets). + There are also poll bars which show how much time application spent + in poll/epoll/select syscalls. TIMECHART OPTIONS ----------------- @@ -54,6 +64,19 @@ TIMECHART OPTIONS duration or tasks with given name. If number is given it's interpreted as number of nanoseconds. If non-numeric string is given it's interpreted as task name. +--io-skip-eagain:: + Don't draw EAGAIN IO events. +--io-min-time=<nsecs>:: + Draw small events as if they lasted min-time. Useful when you need + to see very small and fast IO. It's possible to specify ms or us + suffix to specify time in milliseconds or microseconds. + Default value is 1ms. +--io-merge-dist=<nsecs>:: + Merge events that are merge-dist nanoseconds apart. + Reduces number of figures on the SVG and makes it more render-friendly. + It's possible to specify ms or us suffix to specify time in + milliseconds or microseconds. + Default value is 1us. RECORD OPTIONS -------------- @@ -63,6 +86,9 @@ RECORD OPTIONS -T:: --tasks-only:: Record only tasks-related events +-I:: +--io-only:: + Record only io-related events -g:: --callchain:: Do call-graph (stack chain/backtrace) recording @@ -87,6 +113,14 @@ Record system-wide timechart: $ perf timechart --highlight gcc +Record system-wide IO events: + + $ perf timechart record -I + + then generate timechart: + + $ perf timechart + SEE ALSO -------- linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 180ae02..3265b10 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -98,6 +98,9 @@ Default is to monitor all CPUS. --hide_user_symbols:: Hide user symbols. +--demangle-kernel:: + Demangle kernel symbols. + -D:: --dump-symtab:: Dump the symbol table used for profiling. @@ -193,6 +196,12 @@ Default is to monitor all CPUS. sum of shown entries will be always 100%. "absolute" means it retains the original value before and after the filter is applied. +-w:: +--column-widths=<width[,width...]>:: + Force each column width to the provided list, for large terminal + readability. 0 means no limit (default behavior). + + INTERACTIVE PROMPTING KEYS -------------------------- diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index fae38d9..7e1b1f2 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -20,7 +20,7 @@ scheduling events, etc. This is a live mode tool in addition to working with perf.data files like the other perf tools. Files can be generated using the 'perf record' command but the session needs to include the raw_syscalls events (-e 'raw_syscalls:*'). -Alernatively, the 'perf trace record' can be used as a shortcut to +Alternatively, 'perf trace record' can be used as a shortcut to automatically include the raw_syscalls events when writing events to a file. The following options apply to perf trace; options to perf trace record are @@ -107,6 +107,52 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. Show tool stats such as number of times fd->pathname was discovered thru hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc. +-F=[all|min|maj]:: +--pf=[all|min|maj]:: + Trace pagefaults. Optionally, you can specify whether you want minor, + major or all pagefaults. Default value is maj. + +--syscalls:: + Trace system calls. This options is enabled by default. + +PAGEFAULTS +---------- + +When tracing pagefaults, the format of the trace is as follows: + +<min|maj>fault [<ip.symbol>+<ip.offset>] => <addr.dso@addr.offset> (<map type><addr level>). + +- min/maj indicates whether fault event is minor or major; +- ip.symbol shows symbol for instruction pointer (the code that generated the + fault); if no debug symbols available, perf trace will print raw IP; +- addr.dso shows DSO for the faulted address; +- map type is either 'd' for non-executable maps or 'x' for executable maps; +- addr level is either 'k' for kernel dso or '.' for user dso. + +For symbols resolution you may need to install debugging symbols. + +Please be aware that duration is currently always 0 and doesn't reflect actual +time it took for fault to be handled! + +When --verbose specified, perf trace tries to print all available information +for both IP and fault address in the form of dso@symbol+offset. + +EXAMPLES +-------- + +Trace only major pagefaults: + + $ perf trace --no-syscalls -F + +Trace syscalls, major and minor pagefaults: + + $ perf trace -F all + + 1416.547 ( 0.000 ms): python/20235 majfault [CRYPTO_push_info_+0x0] => /lib/x86_64-linux-gnu/libcrypto.so.1.0.0@0x61be0 (x.) + + As you can see, there was major pagefault in python process, from + CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script[1] diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 0eeb247..1e8e400 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -8,7 +8,19 @@ perf - Performance analysis tools for Linux SYNOPSIS -------- [verse] -'perf' [--version] [--help] COMMAND [ARGS] +'perf' [--version] [--help] [OPTIONS] COMMAND [ARGS] + +OPTIONS +------- +--debug:: + Setup debug variable (just verbose for now) in value + range (0, 10). Use like: + --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 ----------- diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 45da209..83e2887 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -4,17 +4,31 @@ 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/atomic.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.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/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/rbtree.c include/linux/swab.h arch/*/include/asm/unistd*.h @@ -37,3 +51,6 @@ arch/x86/include/asm/kvm_host.h arch/x86/include/uapi/asm/svm.h arch/x86/include/uapi/asm/vmx.h arch/x86/include/uapi/asm/kvm.h +arch/x86/include/uapi/asm/kvm_perf.h +arch/s390/include/uapi/asm/sie.h +arch/s390/include/uapi/asm/kvm_perf.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 9670a16..67a03a82 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))) @@ -126,6 +135,7 @@ PYRF_OBJS = SCRIPT_SH = SCRIPT_SH += perf-archive.sh +SCRIPT_SH += perf-with-kcore.sh grep-libs = $(filter -l%,$(1)) strip-libs = $(filter-out -l%,$(1)) @@ -170,11 +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) @@ -216,8 +231,16 @@ 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/atomic.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.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 @@ -246,12 +269,14 @@ 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 @@ -263,6 +288,7 @@ LIB_H += util/xyarray.h LIB_H += util/header.h LIB_H += util/help.h LIB_H += util/session.h +LIB_H += util/ordered-events.h LIB_H += util/strbuf.h LIB_H += util/strlist.h LIB_H += util/strfilter.h @@ -295,11 +321,14 @@ LIB_H += util/intlist.h LIB_H += util/perf_regs.h LIB_H += util/unwind.h LIB_H += util/vdso.h +LIB_H += util/tsc.h LIB_H += ui/helpline.h LIB_H += ui/progress.h 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 @@ -307,12 +336,14 @@ 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 @@ -345,6 +376,7 @@ LIB_OBJS += $(OUTPUT)util/machine.o LIB_OBJS += $(OUTPUT)util/map.o LIB_OBJS += $(OUTPUT)util/pstack.o LIB_OBJS += $(OUTPUT)util/session.o +LIB_OBJS += $(OUTPUT)util/ordered-events.o LIB_OBJS += $(OUTPUT)util/comm.o LIB_OBJS += $(OUTPUT)util/thread.o LIB_OBJS += $(OUTPUT)util/thread_map.o @@ -373,6 +405,9 @@ LIB_OBJS += $(OUTPUT)util/stat.o LIB_OBJS += $(OUTPUT)util/record.o 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 @@ -395,6 +430,7 @@ LIB_OBJS += $(OUTPUT)tests/perf-record.o LIB_OBJS += $(OUTPUT)tests/rdpmc.o LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o +LIB_OBJS += $(OUTPUT)tests/fdarray.o LIB_OBJS += $(OUTPUT)tests/pmu.o LIB_OBJS += $(OUTPUT)tests/hists_common.o LIB_OBJS += $(OUTPUT)tests/hists_link.o @@ -419,6 +455,7 @@ endif endif LIB_OBJS += $(OUTPUT)tests/mmap-thread-lookup.o LIB_OBJS += $(OUTPUT)tests/thread-mg-share.o +LIB_OBJS += $(OUTPUT)tests/switch-tracking.o BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o BUILTIN_OBJS += $(OUTPUT)builtin-bench.o @@ -430,7 +467,6 @@ BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o 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 += $(OUTPUT)bench/futex-requeue.o @@ -469,8 +505,6 @@ ifneq ($(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)) @@ -559,6 +593,10 @@ 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 @@ -705,6 +743,9 @@ $(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/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 $< @@ -723,6 +764,16 @@ $(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) @@ -761,7 +812,7 @@ $(LIBTRACEEVENT)-clean: install-traceevent-plugins: $(LIBTRACEEVENT) $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins -LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch]) +LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch] $(LIB_PATH)fd/*.[ch]) # if subdir is set, we've been called from above so target has been built # already @@ -867,10 +918,20 @@ 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) \ $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' + $(call QUIET_INSTALL, perf-with-kcore) \ + $(INSTALL) $(OUTPUT)perf-with-kcore -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' ifndef NO_LIBPERL $(call QUIET_INSTALL, perl-scripts) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \ @@ -916,8 +977,8 @@ config-clean: @$(MAKE) -C config/feature-checks clean >/dev/null clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean - $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS) - $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf + $(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 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/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c index 9f870d2..62eff84 100644 --- a/tools/perf/arch/arm/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm/tests/dwarf-unwind.c @@ -3,6 +3,7 @@ #include "thread.h" #include "map.h" #include "event.h" +#include "debug.h" #include "tests/tests.h" #define STACK_SIZE 8192 diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c index 729ed69..62c397e 100644 --- a/tools/perf/arch/arm/util/unwind-libunwind.c +++ b/tools/perf/arch/arm/util/unwind-libunwind.c @@ -3,6 +3,7 @@ #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" +#include "../../util/debug.h" int libunwind__arch_reg_id(int regnum) { diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h index e9441b9..1d3f39c 100644 --- a/tools/perf/arch/arm64/include/perf_regs.h +++ b/tools/perf/arch/arm64/include/perf_regs.h @@ -6,6 +6,8 @@ #include <asm/perf_regs.h> #define PERF_REGS_MASK ((1ULL << PERF_REG_ARM64_MAX) - 1) +#define PERF_REGS_MAX PERF_REG_ARM64_MAX + #define PERF_REG_IP PERF_REG_ARM64_PC #define PERF_REG_SP PERF_REG_ARM64_SP diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c index 436ee43..a87afa9 100644 --- a/tools/perf/arch/arm64/util/unwind-libunwind.c +++ b/tools/perf/arch/arm64/util/unwind-libunwind.c @@ -3,6 +3,7 @@ #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" +#include "../../util/debug.h" int libunwind__arch_reg_id(int regnum) { diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index 42faf36..49776f1 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -12,6 +12,11 @@ const char *const arm_triplets[] = { NULL }; +const char *const arm64_triplets[] = { + "aarch64-linux-android-", + NULL +}; + const char *const powerpc_triplets[] = { "powerpc-unknown-linux-gnu-", "powerpc64-unknown-linux-gnu-", @@ -105,6 +110,8 @@ static const char *normalize_arch(char *arch) return "x86"; if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5)) return "sparc"; + if (!strcmp(arch, "aarch64") || !strcmp(arch, "arm64")) + return "arm64"; if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110")) return "arm"; if (!strncmp(arch, "s390", 4)) @@ -159,6 +166,8 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env, if (!strcmp(arch, "arm")) path_list = arm_triplets; + else if (!strcmp(arch, "arm64")) + path_list = arm64_triplets; else if (!strcmp(arch, "powerpc")) path_list = powerpc_triplets; else if (!strcmp(arch, "sh")) diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index 744e629..6f7782b 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -1,5 +1,6 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o endif LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index 2f7073d..6c1b8a7 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -5,9 +5,7 @@ #include <string.h> #include "../../util/header.h" - -#define __stringify_1(x) #x -#define __stringify(x) __stringify_1(x) +#include "../../util/util.h" #define mfspr(rn) ({unsigned long rval; \ asm volatile("mfspr %0," __stringify(rn) \ diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c new file mode 100644 index 0000000..3bb50ea --- /dev/null +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -0,0 +1,277 @@ +/* + * Use DWARF Debug information to skip unnecessary callchain entries. + * + * Copyright (C) 2014 Sukadev Bhattiprolu, IBM Corporation. + * Copyright (C) 2014 Ulrich Weigand, IBM Corporation. + * + * 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 <inttypes.h> +#include <dwarf.h> +#include <elfutils/libdwfl.h> + +#include "util/thread.h" +#include "util/callchain.h" +#include "util/debug.h" + +/* + * When saving the callchain on Power, the kernel conservatively saves + * excess entries in the callchain. A few of these entries are needed + * in some cases but not others. If the unnecessary entries are not + * ignored, we end up with duplicate arcs in the call-graphs. Use + * DWARF debug information to skip over any unnecessary callchain + * entries. + * + * See function header for arch_adjust_callchain() below for more details. + * + * The libdwfl code in this file is based on code from elfutils + * (libdwfl/argp-std.c, libdwfl/tests/addrcfi.c, etc). + */ +static char *debuginfo_path; + +static const Dwfl_Callbacks offline_callbacks = { + .debuginfo_path = &debuginfo_path, + .find_debuginfo = dwfl_standard_find_debuginfo, + .section_address = dwfl_offline_section_address, +}; + + +/* + * Use the DWARF expression for the Call-frame-address and determine + * if return address is in LR and if a new frame was allocated. + */ +static int check_return_reg(int ra_regno, Dwarf_Frame *frame) +{ + Dwarf_Op ops_mem[2]; + Dwarf_Op dummy; + Dwarf_Op *ops = &dummy; + size_t nops; + int result; + + result = dwarf_frame_register(frame, ra_regno, ops_mem, &ops, &nops); + if (result < 0) { + pr_debug("dwarf_frame_register() %s\n", dwarf_errmsg(-1)); + return -1; + } + + /* + * Check if return address is on the stack. + */ + if (nops != 0 || ops != NULL) + return 0; + + /* + * Return address is in LR. Check if a frame was allocated + * but not-yet used. + */ + result = dwarf_frame_cfa(frame, &ops, &nops); + if (result < 0) { + pr_debug("dwarf_frame_cfa() returns %d, %s\n", result, + dwarf_errmsg(-1)); + return -1; + } + + /* + * If call frame address is in r1, no new frame was allocated. + */ + if (nops == 1 && ops[0].atom == DW_OP_bregx && ops[0].number == 1 && + ops[0].number2 == 0) + return 1; + + /* + * A new frame was allocated but has not yet been used. + */ + return 2; +} + +/* + * Get the DWARF frame from the .eh_frame section. + */ +static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc) +{ + int result; + Dwarf_Addr bias; + Dwarf_CFI *cfi; + Dwarf_Frame *frame; + + cfi = dwfl_module_eh_cfi(mod, &bias); + if (!cfi) { + pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + result = dwarf_cfi_addrframe(cfi, pc, &frame); + if (result) { + pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + return frame; +} + +/* + * Get the DWARF frame from the .debug_frame section. + */ +static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc) +{ + Dwarf_CFI *cfi; + Dwarf_Addr bias; + Dwarf_Frame *frame; + int result; + + cfi = dwfl_module_dwarf_cfi(mod, &bias); + if (!cfi) { + pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + result = dwarf_cfi_addrframe(cfi, pc, &frame); + if (result) { + pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + return frame; +} + +/* + * Return: + * 0 if return address for the program counter @pc is on stack + * 1 if return address is in LR and no new stack frame was allocated + * 2 if return address is in LR and a new frame was allocated (but not + * yet used) + * -1 in case of errors + */ +static int check_return_addr(struct dso *dso, Dwarf_Addr pc) +{ + int rc = -1; + Dwfl *dwfl; + Dwfl_Module *mod; + Dwarf_Frame *frame; + int ra_regno; + Dwarf_Addr start = pc; + Dwarf_Addr end = pc; + bool signalp; + + dwfl = dso->dwfl; + + if (!dwfl) { + dwfl = dwfl_begin(&offline_callbacks); + if (!dwfl) { + pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1)); + return -1; + } + + if (dwfl_report_offline(dwfl, "", dso->long_name, -1) == NULL) { + pr_debug("dwfl_report_offline() 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); + if (!mod) { + pr_debug("dwfl_addrmodule() failed, %s\n", dwarf_errmsg(-1)); + goto out; + } + + /* + * To work with split debug info files (eg: glibc), check both + * .eh_frame and .debug_frame sections of the ELF header. + */ + frame = get_eh_frame(mod, pc); + if (!frame) { + frame = get_dwarf_frame(mod, pc); + if (!frame) + goto out; + } + + ra_regno = dwarf_frame_info(frame, &start, &end, &signalp); + if (ra_regno < 0) { + pr_debug("Return address register unavailable: %s\n", + dwarf_errmsg(-1)); + goto out; + } + + rc = check_return_reg(ra_regno, frame); + +out: + return rc; +} + +/* + * The callchain saved by the kernel always includes the link register (LR). + * + * 0: PERF_CONTEXT_USER + * 1: Program counter (Next instruction pointer) + * 2: LR value + * 3: Caller's caller + * 4: ... + * + * The value in LR is only needed when it holds a return address. If the + * return address is on the stack, we should ignore the LR value. + * + * Further, when the return address is in the LR, if a new frame was just + * allocated but the LR was not saved into it, then the LR contains the + * caller, slot 4: contains the caller's caller and the contents of slot 3: + * (chain->ips[3]) is undefined and must be ignored. + * + * Use DWARF debug information to determine if any entries need to be skipped. + * + * Return: + * 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 thread *thread, struct ip_callchain *chain) +{ + struct addr_location al; + struct dso *dso = NULL; + int rc; + u64 ip; + u64 skip_slot = -1; + + if (chain->nr < 3) + return skip_slot; + + ip = chain->ips[2]; + + thread__find_addr_location(thread, PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, &al); + + if (al.map) + dso = al.map->dso; + + if (!dso) { + pr_debug("%" PRIx64 " dso is NULL\n", ip); + return skip_slot; + } + + rc = check_return_addr(dso, ip); + + pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n", + dso->long_name, chain->nr, ip, rc); + + if (rc == 0) { + /* + * Return address on stack. Ignore LR value in callchain + */ + skip_slot = 2; + } else if (rc == 2) { + /* + * New frame allocated but return address still in LR. + * Ignore the caller's caller entry in callchain. + */ + skip_slot = 3; + } + return skip_slot; +} diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 15130b50..798ac73 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -2,3 +2,6 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o +HAVE_KVM_STAT_SUPPORT := 1 +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c new file mode 100644 index 0000000..9fa6c3e --- /dev/null +++ b/tools/perf/arch/s390/util/header.c @@ -0,0 +1,28 @@ +/* + * Implementation of get_cpuid(). + * + * Copyright 2014 IBM Corp. + * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ + +#include <sys/types.h> +#include <unistd.h> +#include <stdio.h> +#include <string.h> + +#include "../../util/header.h" + +int get_cpuid(char *buffer, size_t sz) +{ + const char *cpuid = "IBM/S390"; + + if (strlen(cpuid) + 1 > sz) + return -1; + + strcpy(buffer, cpuid); + return 0; +} diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c new file mode 100644 index 0000000..a5dbc07 --- /dev/null +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -0,0 +1,105 @@ +/* + * Arch specific functions for perf kvm stat. + * + * Copyright 2014 IBM Corp. + * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ + +#include "../../util/kvm-stat.h" +#include <asm/kvm_perf.h> + +define_exit_reasons_table(sie_exit_reasons, sie_intercept_code); +define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes); +define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes); +define_exit_reasons_table(sie_diagnose_codes, diagnose_codes); +define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes); + +static void event_icpt_insn_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + unsigned long insn; + + insn = perf_evsel__intval(evsel, sample, "instruction"); + key->key = icpt_insn_decoder(insn); + key->exit_reasons = sie_icpt_insn_codes; +} + +static void event_sigp_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "order_code"); + key->exit_reasons = sie_sigp_order_codes; +} + +static void event_diag_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "code"); + key->exit_reasons = sie_diagnose_codes; +} + +static void event_icpt_prog_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "code"); + key->exit_reasons = sie_icpt_prog_codes; +} + +static struct child_event_ops child_events[] = { + { .name = "kvm:kvm_s390_intercept_instruction", + .get_key = event_icpt_insn_get_key }, + { .name = "kvm:kvm_s390_handle_sigp", + .get_key = event_sigp_get_key }, + { .name = "kvm:kvm_s390_handle_diag", + .get_key = event_diag_get_key }, + { .name = "kvm:kvm_s390_intercept_prog", + .get_key = event_icpt_prog_get_key }, + { NULL, NULL }, +}; + +static struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .child_ops = child_events, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +const char * const kvm_events_tp[] = { + "kvm:kvm_s390_sie_enter", + "kvm:kvm_s390_sie_exit", + "kvm:kvm_s390_intercept_instruction", + "kvm:kvm_s390_handle_sigp", + "kvm:kvm_s390_handle_diag", + "kvm:kvm_s390_intercept_prog", + NULL, +}; + +struct kvm_reg_events_ops kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events }, + { NULL, NULL }, +}; + +const char * const kvm_skip_events[] = { + "Wait state", + NULL, +}; + +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid) +{ + if (strstr(cpuid, "IBM/S390")) { + kvm->exit_reasons = sie_exit_reasons; + kvm->exit_reasons_isa = "SIE"; + } else + return -ENOTSUP; + + return 0; +} diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 1641542..9b21881 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -15,3 +15,5 @@ endif LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o LIB_H += arch/$(ARCH)/util/tsc.h +HAVE_KVM_STAT_SUPPORT := 1 +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 9f89f89..d8bbf7a 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -3,6 +3,7 @@ #include "thread.h" #include "map.h" #include "event.h" +#include "debug.h" #include "tests/tests.h" #define STACK_SIZE 8192 diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c new file mode 100644 index 0000000..14e4e66 --- /dev/null +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -0,0 +1,156 @@ +#include "../../util/kvm-stat.h" +#include <asm/kvm_perf.h> + +define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS); +define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS); + +static struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +/* + * For the mmio events, we treat: + * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry + * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). + */ +static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "gpa"); + key->info = perf_evsel__intval(evsel, sample, "type"); +} + +#define KVM_TRACE_MMIO_READ_UNSATISFIED 0 +#define KVM_TRACE_MMIO_READ 1 +#define KVM_TRACE_MMIO_WRITE 2 + +static bool mmio_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + /* MMIO read begin event in kernel. */ + if (kvm_exit_event(evsel)) + return true; + + /* MMIO write begin event in kernel. */ + if (!strcmp(evsel->name, "kvm:kvm_mmio") && + perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) { + mmio_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, + struct event_key *key) +{ + /* MMIO write end event in kernel. */ + if (kvm_entry_event(evsel)) + return true; + + /* MMIO read end event in kernel.*/ + if (!strcmp(evsel->name, "kvm:kvm_mmio") && + perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) { + mmio_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + scnprintf(decode, DECODE_STR_LEN, "%#lx:%s", + (unsigned long)key->key, + key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); +} + +static struct kvm_events_ops mmio_events = { + .is_begin_event = mmio_event_begin, + .is_end_event = mmio_event_end, + .decode_key = mmio_event_decode_key, + .name = "MMIO Access" +}; + + /* The time of emulation pio access is from kvm_pio to kvm_entry. */ +static void ioport_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "port"); + key->info = perf_evsel__intval(evsel, sample, "rw"); +} + +static bool ioport_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + if (!strcmp(evsel->name, "kvm:kvm_pio")) { + ioport_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static bool ioport_event_end(struct perf_evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return kvm_entry_event(evsel); +} + +static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + scnprintf(decode, DECODE_STR_LEN, "%#llx:%s", + (unsigned long long)key->key, + key->info ? "POUT" : "PIN"); +} + +static struct kvm_events_ops ioport_events = { + .is_begin_event = ioport_event_begin, + .is_end_event = ioport_event_end, + .decode_key = ioport_event_decode_key, + .name = "IO Port Access" +}; + +const char * const kvm_events_tp[] = { + "kvm:kvm_entry", + "kvm:kvm_exit", + "kvm:kvm_mmio", + "kvm:kvm_pio", + NULL, +}; + +struct kvm_reg_events_ops kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events }, + { .name = "mmio", .ops = &mmio_events }, + { .name = "ioport", .ops = &ioport_events }, + { NULL, NULL }, +}; + +const char * const kvm_skip_events[] = { + "HLT", + NULL, +}; + +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid) +{ + if (strstr(cpuid, "Intel")) { + kvm->exit_reasons = vmx_exit_reasons; + kvm->exit_reasons_isa = "VMX"; + } else if (strstr(cpuid, "AMD")) { + kvm->exit_reasons = svm_exit_reasons; + kvm->exit_reasons_isa = "SVM"; + } else + return -ENOTSUP; + + return 0; +} diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 40021fa..fd28684 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -6,29 +6,9 @@ #include "../../perf.h" #include <linux/types.h> #include "../../util/debug.h" +#include "../../util/tsc.h" #include "tsc.h" -u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc) -{ - u64 t, quot, rem; - - t = ns - tc->time_zero; - quot = t / tc->time_mult; - rem = t % tc->time_mult; - return (quot << tc->time_shift) + - (rem << tc->time_shift) / tc->time_mult; -} - -u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) -{ - u64 quot, rem; - - quot = cyc >> tc->time_shift; - rem = cyc & ((1 << tc->time_shift) - 1); - return tc->time_zero + quot * tc->time_mult + - ((rem * tc->time_mult) >> tc->time_shift); -} - int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) { @@ -57,3 +37,12 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, return 0; } + +u64 rdtsc(void) +{ + unsigned int low, high; + + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + + return low | ((u64)high) << 32; +} diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h index 2affe03..2edc4d3 100644 --- a/tools/perf/arch/x86/util/tsc.h +++ b/tools/perf/arch/x86/util/tsc.h @@ -14,7 +14,4 @@ struct perf_event_mmap_page; int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc); -u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); -u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); - #endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */ diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c index 3261f68..db25e93 100644 --- a/tools/perf/arch/x86/util/unwind-libunwind.c +++ b/tools/perf/arch/x86/util/unwind-libunwind.c @@ -3,6 +3,7 @@ #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" +#include "../../util/debug.h" #ifdef HAVE_ARCH_X86_64_SUPPORT int libunwind__arch_reg_id(int regnum) diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index eba46709..3c4dd44 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -43,5 +43,6 @@ extern int bench_futex_requeue(int argc, const char **argv, const char *prefix); #define BENCH_FORMAT_UNKNOWN -1 extern int bench_format; +extern unsigned int bench_repeat; #endif diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index a84206e..fc9bebd 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -26,6 +26,7 @@ static unsigned int nsecs = 10; /* amount of futexes per thread */ static unsigned int nfutexes = 1024; static bool fshared = false, done = false, silent = false; +static int futex_flag = 0; struct timeval start, end, runtime; static pthread_mutex_t thread_lock; @@ -75,8 +76,7 @@ static void *workerfn(void *arg) * such as internal waitqueue handling, thus enlarging * the critical region protected by hb->lock. */ - ret = futex_wait(&w->futex[i], 1234, NULL, - fshared ? 0 : FUTEX_PRIVATE_FLAG); + ret = futex_wait(&w->futex[i], 1234, NULL, futex_flag); if (!silent && (!ret || errno != EAGAIN || errno != EWOULDBLOCK)) warn("Non-expected futex return call"); @@ -135,6 +135,9 @@ int bench_futex_hash(int argc, const char **argv, if (!worker) goto errmem; + if (!fshared) + futex_flag = FUTEX_PRIVATE_FLAG; + printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n", getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs); diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index a1625587..bedff6b 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -29,25 +29,19 @@ static u_int32_t futex1 = 0, futex2 = 0; */ static unsigned int nrequeue = 1; -/* - * There can be significant variance from run to run, - * the more repeats, the more exact the overall avg and - * the better idea of the futex latency. - */ -static unsigned int repeat = 10; - static pthread_t *worker; -static bool done = 0, silent = 0; +static bool done = false, silent = false, fshared = false; static pthread_mutex_t thread_lock; static pthread_cond_t thread_parent, thread_worker; static struct stats requeuetime_stats, requeued_stats; static unsigned int ncpus, threads_starting, nthreads = 0; +static int futex_flag = 0; static const struct option options[] = { OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"), - OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"), OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), + OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"), OPT_END() }; @@ -78,7 +72,7 @@ static void *workerfn(void *arg __maybe_unused) pthread_cond_wait(&thread_worker, &thread_lock); pthread_mutex_unlock(&thread_lock); - futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG); + futex_wait(&futex1, 0, NULL, futex_flag); return NULL; } @@ -135,9 +129,12 @@ int bench_futex_requeue(int argc, const char **argv, if (!worker) err(EXIT_FAILURE, "calloc"); - printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), " - "%d at a time.\n\n", - getpid(), nthreads, &futex1, &futex2, nrequeue); + if (!fshared) + futex_flag = FUTEX_PRIVATE_FLAG; + + printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), " + "%d at a time.\n\n", getpid(), nthreads, + fshared ? "shared":"private", &futex1, &futex2, nrequeue); init_stats(&requeued_stats); init_stats(&requeuetime_stats); @@ -146,7 +143,7 @@ int bench_futex_requeue(int argc, const char **argv, pthread_cond_init(&thread_parent, NULL); pthread_cond_init(&thread_worker, NULL); - for (j = 0; j < repeat && !done; j++) { + for (j = 0; j < bench_repeat && !done; j++) { unsigned int nrequeued = 0; struct timeval start, end, runtime; @@ -164,16 +161,20 @@ int bench_futex_requeue(int argc, const char **argv, /* Ok, all threads are patiently blocked, start requeueing */ gettimeofday(&start, NULL); - for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) + for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) { /* * Do not wakeup any tasks blocked on futex1, allowing * us to really measure futex_wait functionality. */ - futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue, - FUTEX_PRIVATE_FLAG); + futex_cmp_requeue(&futex1, 0, &futex2, 0, + nrequeue, futex_flag); + } gettimeofday(&end, NULL); timersub(&end, &start, &runtime); + if (nrequeued > nthreads) + nrequeued = nthreads; + update_stats(&requeued_stats, nrequeued); update_stats(&requeuetime_stats, runtime.tv_usec); @@ -183,7 +184,7 @@ int bench_futex_requeue(int argc, const char **argv, } /* everybody should be blocked on futex2, wake'em up */ - nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG); + nrequeued = futex_wake(&futex2, nthreads, futex_flag); if (nthreads != nrequeued) warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads); @@ -192,7 +193,6 @@ int bench_futex_requeue(int argc, const char **argv, if (ret) err(EXIT_FAILURE, "pthread_join"); } - } /* cleanup & report results */ diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index d096169..929f762 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -30,25 +30,19 @@ static u_int32_t futex1 = 0; */ static unsigned int nwakes = 1; -/* - * There can be significant variance from run to run, - * the more repeats, the more exact the overall avg and - * the better idea of the futex latency. - */ -static unsigned int repeat = 10; - pthread_t *worker; -static bool done = 0, silent = 0; +static bool done = false, silent = false, fshared = false; static pthread_mutex_t thread_lock; static pthread_cond_t thread_parent, thread_worker; static struct stats waketime_stats, wakeup_stats; static unsigned int ncpus, threads_starting, nthreads = 0; +static int futex_flag = 0; static const struct option options[] = { OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), OPT_UINTEGER('w', "nwakes", &nwakes, "Specify amount of threads to wake at once"), - OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"), OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), + OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"), OPT_END() }; @@ -66,7 +60,7 @@ static void *workerfn(void *arg __maybe_unused) pthread_cond_wait(&thread_worker, &thread_lock); pthread_mutex_unlock(&thread_lock); - futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG); + futex_wait(&futex1, 0, NULL, futex_flag); return NULL; } @@ -138,9 +132,12 @@ int bench_futex_wake(int argc, const char **argv, if (!worker) err(EXIT_FAILURE, "calloc"); - printf("Run summary [PID %d]: blocking on %d threads (at futex %p), " + if (!fshared) + futex_flag = FUTEX_PRIVATE_FLAG; + + printf("Run summary [PID %d]: blocking on %d threads (at [%s] futex %p), " "waking up %d at a time.\n\n", - getpid(), nthreads, &futex1, nwakes); + getpid(), nthreads, fshared ? "shared":"private", &futex1, nwakes); init_stats(&wakeup_stats); init_stats(&waketime_stats); @@ -149,7 +146,7 @@ int bench_futex_wake(int argc, const char **argv, pthread_cond_init(&thread_parent, NULL); pthread_cond_init(&thread_worker, NULL); - for (j = 0; j < repeat && !done; j++) { + for (j = 0; j < bench_repeat && !done; j++) { unsigned int nwoken = 0; struct timeval start, end, runtime; @@ -168,7 +165,7 @@ int bench_futex_wake(int argc, const char **argv, /* Ok, all threads are patiently blocked, start waking folks up */ gettimeofday(&start, NULL); while (nwoken != nthreads) - nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG); + nwoken += futex_wake(&futex1, nwakes, futex_flag); gettimeofday(&end, NULL); timersub(&end, &start, &runtime); diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 5ce71d3..6c14afe 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -10,8 +10,10 @@ #include "../util/util.h" #include "../util/parse-options.h" #include "../util/header.h" +#include "../util/cloexec.h" #include "bench.h" #include "mem-memcpy-arch.h" +#include "mem-memset-arch.h" #include <stdio.h> #include <stdlib.h> @@ -47,20 +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 @@ -68,7 +74,7 @@ struct routine routines[] = { { NULL, NULL, - NULL } + {NULL} } }; static const char * const bench_mem_memcpy_usage[] = { @@ -83,7 +89,8 @@ static struct perf_event_attr cycle_attr = { static void init_cycle(void) { - cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0); + 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"); @@ -108,63 +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 { \ @@ -178,21 +128,36 @@ 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 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; double result_bps[2]; u64 result_cycle[2]; argc = parse_options(argc, argv, options, - bench_mem_memcpy_usage, 0); + 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; result_cycle[0] = result_cycle[1] = 0ULL; result_bps[0] = result_bps[1] = 0.0; @@ -206,16 +171,16 @@ int bench_mem_memcpy(int argc, const char **argv, if (only_prefault && no_prefault) only_prefault = no_prefault = false; - for (i = 0; routines[i].name; i++) { - if (!strcmp(routines[i].name, routine)) + for (i = 0; info->routines[i].name; i++) { + if (!strcmp(info->routines[i].name, routine)) break; } - if (!routines[i].name) { + if (!info->routines[i].name) { printf("Unknown routine:%s\n", routine); printf("Available routines...\n"); - for (i = 0; routines[i].name; i++) { + for (i = 0; info->routines[i].name; i++) { printf("\t%s ... %s\n", - routines[i].name, routines[i].desc); + info->routines[i].name, info->routines[i].desc); } return 1; } @@ -227,25 +192,25 @@ int bench_mem_memcpy(int argc, const char **argv, /* show both of results */ if (use_cycle) { result_cycle[0] = - do_memcpy_cycle(routines[i].fn, len, false); + info->do_cycle(&info->routines[i], len, false); result_cycle[1] = - do_memcpy_cycle(routines[i].fn, len, true); + info->do_cycle(&info->routines[i], len, true); } else { result_bps[0] = - do_memcpy_gettimeofday(routines[i].fn, + info->do_gettimeofday(&info->routines[i], len, false); result_bps[1] = - do_memcpy_gettimeofday(routines[i].fn, + info->do_gettimeofday(&info->routines[i], len, true); } } else { if (use_cycle) { result_cycle[pf] = - do_memcpy_cycle(routines[i].fn, + info->do_cycle(&info->routines[i], len, only_prefault); } else { result_bps[pf] = - do_memcpy_gettimeofday(routines[i].fn, + info->do_gettimeofday(&info->routines[i], len, only_prefault); } } @@ -256,10 +221,10 @@ 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"); @@ -270,7 +235,7 @@ 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]); @@ -281,8 +246,8 @@ 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]); @@ -290,7 +255,7 @@ 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]); } @@ -303,3 +268,163 @@ int bench_mem_memcpy(int argc, const char **argv, 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(&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(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(&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 * 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.c b/tools/perf/bench/mem-memset.c deleted file mode 100644 index 9af79d2..0000000 --- a/tools/perf/bench/mem-memset.c +++ /dev/null @@ -1,297 +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 "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, 0); - - 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 (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-messaging.c b/tools/perf/bench/sched-messaging.c index cc1190a..d7f281c 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -26,8 +26,9 @@ #include <sys/socket.h> #include <sys/wait.h> #include <sys/time.h> -#include <sys/poll.h> +#include <poll.h> #include <limits.h> +#include <err.h> #define DATASIZE 100 @@ -50,12 +51,6 @@ struct receiver_context { int wakefd; }; -static void barf(const char *msg) -{ - fprintf(stderr, "%s (error: %s)\n", msg, strerror(errno)); - exit(1); -} - static void fdpair(int fds[2]) { if (use_pipes) { @@ -66,7 +61,7 @@ static void fdpair(int fds[2]) return; } - barf(use_pipes ? "pipe()" : "socketpair()"); + err(EXIT_FAILURE, use_pipes ? "pipe()" : "socketpair()"); } /* Block until we're ready to go */ @@ -77,11 +72,11 @@ static void ready(int ready_out, int wakefd) /* Tell them we're ready. */ if (write(ready_out, &dummy, 1) != 1) - barf("CLIENT: ready write"); + err(EXIT_FAILURE, "CLIENT: ready write"); /* Wait for "GO" signal */ if (poll(&pollfd, 1, -1) != 1) - barf("poll"); + err(EXIT_FAILURE, "poll"); } /* Sender sprays loops messages down each file descriptor */ @@ -101,7 +96,7 @@ again: ret = write(ctx->out_fds[j], data + done, sizeof(data)-done); if (ret < 0) - barf("SENDER: write"); + err(EXIT_FAILURE, "SENDER: write"); done += ret; if (done < DATASIZE) goto again; @@ -131,7 +126,7 @@ static void *receiver(struct receiver_context* ctx) again: ret = read(ctx->in_fds[0], data + done, DATASIZE - done); if (ret < 0) - barf("SERVER: read"); + err(EXIT_FAILURE, "SERVER: read"); done += ret; if (done < DATASIZE) goto again; @@ -144,14 +139,14 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *)) { pthread_attr_t attr; pthread_t childid; - int err; + int ret; if (!thread_mode) { /* process mode */ /* Fork the receiver. */ switch (fork()) { case -1: - barf("fork()"); + err(EXIT_FAILURE, "fork()"); break; case 0: (*func) (ctx); @@ -165,19 +160,17 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *)) } if (pthread_attr_init(&attr) != 0) - barf("pthread_attr_init:"); + err(EXIT_FAILURE, "pthread_attr_init:"); #ifndef __ia64__ if (pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN) != 0) - barf("pthread_attr_setstacksize"); + err(EXIT_FAILURE, "pthread_attr_setstacksize"); #endif - err = pthread_create(&childid, &attr, func, ctx); - if (err != 0) { - fprintf(stderr, "pthread_create failed: %s (%d)\n", - strerror(err), err); - exit(-1); - } + ret = pthread_create(&childid, &attr, func, ctx); + if (ret != 0) + err(EXIT_FAILURE, "pthread_create failed"); + return childid; } @@ -207,14 +200,14 @@ static unsigned int group(pthread_t *pth, + num_fds * sizeof(int)); if (!snd_ctx) - barf("malloc()"); + err(EXIT_FAILURE, "malloc()"); for (i = 0; i < num_fds; i++) { int fds[2]; struct receiver_context *ctx = malloc(sizeof(*ctx)); if (!ctx) - barf("malloc()"); + err(EXIT_FAILURE, "malloc()"); /* Create the pipe between client and server */ @@ -281,7 +274,7 @@ int bench_sched_messaging(int argc, const char **argv, pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t)); if (!pth_tab) - barf("main:malloc()"); + err(EXIT_FAILURE, "main:malloc()"); fdpair(readyfds); fdpair(wakefds); @@ -294,13 +287,13 @@ int bench_sched_messaging(int argc, const char **argv, /* Wait for everyone to be ready */ for (i = 0; i < total_children; i++) if (read(readyfds[0], &dummy, 1) != 1) - barf("Reading for readyfds"); + err(EXIT_FAILURE, "Reading for readyfds"); gettimeofday(&start, NULL); /* Kick them off */ if (write(wakefds[1], &dummy, 1) != 1) - barf("Writing to start them"); + err(EXIT_FAILURE, "Writing to start them"); /* Reap them all */ for (i = 0; i < total_children; i++) @@ -332,5 +325,7 @@ int bench_sched_messaging(int argc, const char **argv, break; } + free(pth_tab); + return 0; } diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 1ec429f..e7417fe 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -36,7 +36,8 @@ struct perf_annotate { struct perf_tool tool; - bool force, use_tui, use_stdio, use_gtk; + struct perf_session *session; + bool use_tui, use_stdio, use_gtk; bool full_paths; bool print_line; bool skip_missing; @@ -50,6 +51,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, struct addr_location *al, struct perf_annotate *ann) { + struct hists *hists = evsel__hists(evsel); struct hist_entry *he; int ret; @@ -65,13 +67,12 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, return 0; } - he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0, - true); + he = __hists__add_entry(hists, al, NULL, NULL, NULL, 1, 1, 0, true); if (he == NULL) return -ENOMEM; ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - hists__inc_nr_samples(&evsel->hists, true); + hists__inc_nr_samples(hists, true); return ret; } @@ -188,18 +189,9 @@ find_next: static int __cmd_annotate(struct perf_annotate *ann) { int ret; - struct perf_session *session; + struct perf_session *session = ann->session; struct perf_evsel *pos; u64 total_nr_samples; - struct perf_data_file file = { - .path = input_name, - .mode = PERF_DATA_MODE_READ, - .force = ann->force, - }; - - session = perf_session__new(&file, false, &ann->tool); - if (session == NULL) - return -ENOMEM; machines__set_symbol_filter(&session->machines, symbol__annotate_init); @@ -207,22 +199,23 @@ static int __cmd_annotate(struct perf_annotate *ann) ret = perf_session__cpu_bitmap(session, ann->cpu_list, ann->cpu_bitmap); if (ret) - goto out_delete; + goto out; } if (!objdump_path) { ret = perf_session_env__lookup_objdump(&session->header.env); if (ret) - goto out_delete; + goto out; } ret = perf_session__process_events(session, &ann->tool); if (ret) - goto out_delete; + goto out; if (dump_trace) { perf_session__fprintf_nr_events(session, stdout); - goto out_delete; + perf_evlist__fprintf_nr_events(session->evlist, stdout); + goto out; } if (verbose > 3) @@ -233,7 +226,7 @@ static int __cmd_annotate(struct perf_annotate *ann) total_nr_samples = 0; evlist__for_each(session->evlist, pos) { - struct hists *hists = &pos->hists; + struct hists *hists = evsel__hists(pos); u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; if (nr_samples > 0) { @@ -250,8 +243,8 @@ static int __cmd_annotate(struct perf_annotate *ann) } if (total_nr_samples == 0) { - ui__error("The %s file has no samples!\n", file.path); - goto out_delete; + ui__error("The %s file has no samples!\n", session->file->path); + goto out; } if (use_browser == 2) { @@ -261,24 +254,12 @@ static int __cmd_annotate(struct perf_annotate *ann) "perf_gtk__show_annotations"); if (show_annotations == NULL) { ui__error("GTK browser not found!\n"); - goto out_delete; + goto out; } show_annotations(); } -out_delete: - /* - * Speed up the exit process, for large files this can - * take quite a while. - * - * XXX Enable this when using valgrind or if we ever - * librarize this command. - * - * Also experiment with obstacks to see how much speed - * up we'll get here. - * - * perf_session__delete(session); - */ +out: return ret; } @@ -297,10 +278,14 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) .comm = perf_event__process_comm, .exit = perf_event__process_exit, .fork = perf_event__process_fork, - .ordered_samples = true, + .ordered_events = true, .ordering_requires_timestamps = true, }, }; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -308,7 +293,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) "only consider symbols in these dsos"), OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol", "symbol to annotate"), - OPT_BOOLEAN('f', "force", &annotate.force, "don't complain, do it"), + OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, @@ -341,6 +326,10 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) "Show event group information together"), OPT_END() }; + int ret = hists__init(); + + if (ret < 0) + return ret; argc = parse_options(argc, argv, options, annotate_usage, 0); @@ -353,11 +342,16 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) setup_browser(true); + annotate.session = perf_session__new(&file, false, &annotate.tool); + if (annotate.session == NULL) + return -1; + symbol_conf.priv_size = sizeof(struct annotation); symbol_conf.try_vmlinux_path = true; - if (symbol__init() < 0) - return -1; + ret = symbol__init(&annotate.session->header.env); + if (ret < 0) + goto out_delete; if (setup_sorting() < 0) usage_with_options(annotate_usage, options); @@ -373,5 +367,20 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) annotate.sym_hist_filter = argv[0]; } - return __cmd_annotate(&annotate); + ret = __cmd_annotate(&annotate); + +out_delete: + /* + * Speed up the exit process, for large files this can + * take quite a while. + * + * XXX Enable this when using valgrind or if we ever + * librarize this command. + * + * Also experiment with obstacks to see how much speed + * up we'll get here. + * + * perf_session__delete(session); + */ + return ret; } diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index 1e6e777..b9a56fa 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -104,9 +104,11 @@ static const char *bench_format_str; /* Output/formatting style, exported to benchmark modules: */ int bench_format = BENCH_FORMAT_DEFAULT; +unsigned int bench_repeat = 10; /* default number of times to repeat the run */ static const struct option bench_options[] = { OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"), + OPT_UINTEGER('r', "repeat", &bench_repeat, "Specify amount of times to repeat the run"), OPT_END() }; @@ -226,6 +228,11 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) goto end; } + if (bench_repeat == 0) { + printf("Invalid repeat option: Must specify a positive value\n"); + goto end; + } + if (argc < 1) { print_usage(); goto end; diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index b22dbb1..77d5cae 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -125,7 +125,8 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir, return ret; } -static int build_id_cache__add_kcore(const char *filename, const char *debugdir) +static int build_id_cache__add_kcore(const char *filename, const char *debugdir, + bool force) { char dir[32], sbuildid[BUILD_ID_SIZE * 2 + 1]; char from_dir[PATH_MAX], to_dir[PATH_MAX]; @@ -144,7 +145,8 @@ static int build_id_cache__add_kcore(const char *filename, const char *debugdir) scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s", debugdir, sbuildid); - if (!build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) { + if (!force && + !build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) { pr_debug("same kcore found in %s\n", to_dir); return 0; } @@ -244,20 +246,9 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) return true; } -static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp) +static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *fp) { - struct perf_data_file file = { - .path = filename, - .mode = PERF_DATA_MODE_READ, - .force = force, - }; - struct perf_session *session = perf_session__new(&file, false, NULL); - if (session == NULL) - return -1; - perf_session__fprintf_dsos_buildid(session, fp, dso__missing_buildid_cache, 0); - perf_session__delete(session); - return 0; } @@ -294,12 +285,17 @@ 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 = { + .mode = PERF_DATA_MODE_READ, + }; + struct perf_session *session = NULL; const struct option buildid_cache_options[] = { OPT_STRING('a', "add", &add_name_list_str, @@ -324,25 +320,32 @@ int cmd_buildid_cache(int argc, const char **argv, argc = parse_options(argc, argv, buildid_cache_options, buildid_cache_usage, 0); - if (symbol__init() < 0) - return -1; + if (missing_filename) { + file.path = missing_filename; + file.force = force; - setup_pager(); + session = perf_session__new(&file, false, NULL); + if (session == NULL) + return -1; + } + + if (symbol__init(session ? &session->header.env : NULL) < 0) + goto out; - snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); + setup_pager(); 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); continue; } pr_warning("Couldn't add %s: %s\n", - pos->s, strerror(errno)); + pos->s, strerror_r(errno, sbuf, sizeof(sbuf))); } strlist__delete(list); @@ -353,14 +356,14 @@ 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); continue; } pr_warning("Couldn't remove %s: %s\n", - pos->s, strerror(errno)); + pos->s, strerror_r(errno, sbuf, sizeof(sbuf))); } strlist__delete(list); @@ -368,20 +371,20 @@ int cmd_buildid_cache(int argc, const char **argv, } if (missing_filename) - ret = build_id_cache__fprintf_missing(missing_filename, force, stdout); + ret = build_id_cache__fprintf_missing(session, stdout); if (update_name_list_str) { 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); continue; } pr_warning("Couldn't update %s: %s\n", - pos->s, strerror(errno)); + pos->s, strerror_r(errno, sbuf, sizeof(sbuf))); } strlist__delete(list); @@ -389,8 +392,12 @@ int cmd_buildid_cache(int argc, const char **argv, } if (kcore_filename && - build_id_cache__add_kcore(kcore_filename, debugdir)) + build_id_cache__add_kcore(kcore_filename, buildid_dir, force)) pr_warning("Couldn't add %s\n", kcore_filename); +out: + if (session) + perf_session__delete(session); + return ret; } diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 9a5a035..1ce425d 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -327,6 +327,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, struct machine *machine) { struct addr_location al; + struct hists *hists = evsel__hists(evsel); if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { pr_warning("problem processing %d event, skipping it.\n", @@ -334,7 +335,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, return -1; } - if (hists__add_entry(&evsel->hists, &al, sample->period, + if (hists__add_entry(hists, &al, sample->period, sample->weight, sample->transaction)) { pr_warning("problem incrementing symbol period, skipping event\n"); return -1; @@ -346,9 +347,9 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, * hists__output_resort() and precompute needs the total * period in order to sort entries by percentage delta. */ - evsel->hists.stats.total_period += sample->period; + hists->stats.total_period += sample->period; if (!al.filtered) - evsel->hists.stats.total_non_filtered_period += sample->period; + hists->stats.total_non_filtered_period += sample->period; return 0; } @@ -356,11 +357,12 @@ 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, .lost = perf_event__process_lost, - .ordered_samples = true, + .ordered_events = true, .ordering_requires_timestamps = true, }; @@ -382,7 +384,7 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist) struct perf_evsel *evsel; evlist__for_each(evlist, evsel) { - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); hists__collapse_resort(hists, NULL); } @@ -631,24 +633,26 @@ static void data_process(void) bool first = true; evlist__for_each(evlist_base, evsel_base) { + struct hists *hists_base = evsel__hists(evsel_base); struct data__file *d; int i; data__for_each_file_new(i, d) { struct perf_evlist *evlist = d->session->evlist; struct perf_evsel *evsel; + struct hists *hists; evsel = evsel_match(evsel_base, evlist); if (!evsel) continue; - d->hists = &evsel->hists; + hists = evsel__hists(evsel); + d->hists = hists; - hists__match(&evsel_base->hists, &evsel->hists); + hists__match(hists_base, hists); if (!show_baseline_only) - hists__link(&evsel_base->hists, - &evsel->hists); + hists__link(hists_base, hists); } fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n", @@ -659,7 +663,7 @@ static void data_process(void) if (verbose || data__files_cnt > 2) data__fprintf(); - hists__process(&evsel_base->hists); + hists__process(hists_base); } } @@ -683,7 +687,7 @@ static int __cmd_diff(void) d->session = perf_session__new(&d->file, false, &tool); if (!d->session) { pr_err("Failed to open %s\n", d->file.path); - ret = -ENOMEM; + ret = -1; goto out_delete; } @@ -1139,11 +1143,16 @@ static int data_init(int argc, const char **argv) int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) { + int ret = hists__init(); + + if (ret < 0) + return ret; + perf_config(perf_default_config, NULL); argc = parse_options(argc, argv, options, diff_usage, 0); - if (symbol__init() < 0) + if (symbol__init(NULL) < 0) return -1; if (data_init(argc, argv) < 0) diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index c99e0de..0f93f85 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -15,6 +15,7 @@ #include "util/parse-options.h" #include "util/session.h" #include "util/data.h" +#include "util/debug.h" static int __cmd_evlist(const char *file_name, struct perf_attr_details *details) { @@ -27,7 +28,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details session = perf_session__new(&file, 0, NULL); if (session == NULL) - return -ENOMEM; + return -1; evlist__for_each(session->evlist, pos) perf_evsel__fprintf(pos, details, stdout); diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 178b88a..25d2062 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -11,6 +11,7 @@ #include "util/parse-options.h" #include "util/run-command.h" #include "util/help.h" +#include "util/debug.h" static struct man_viewer_list { struct man_viewer_list *next; @@ -102,6 +103,8 @@ static int check_emacsclient_version(void) static void exec_woman_emacs(const char *path, const char *page) { + char sbuf[STRERR_BUFSIZE]; + if (!check_emacsclient_version()) { /* This works only with emacsclient version >= 22. */ struct strbuf man_page = STRBUF_INIT; @@ -110,16 +113,19 @@ static void exec_woman_emacs(const char *path, const char *page) path = "emacsclient"; strbuf_addf(&man_page, "(woman \"%s\")", page); execlp(path, "emacsclient", "-e", man_page.buf, NULL); - warning("failed to exec '%s': %s", path, strerror(errno)); + warning("failed to exec '%s': %s", path, + strerror_r(errno, sbuf, sizeof(sbuf))); } } static void exec_man_konqueror(const char *path, const char *page) { const char *display = getenv("DISPLAY"); + if (display && *display) { struct strbuf man_page = STRBUF_INIT; const char *filename = "kfmclient"; + char sbuf[STRERR_BUFSIZE]; /* It's simpler to launch konqueror using kfmclient. */ if (path) { @@ -138,24 +144,31 @@ static void exec_man_konqueror(const char *path, const char *page) path = "kfmclient"; strbuf_addf(&man_page, "man:%s(1)", page); execlp(path, filename, "newTab", man_page.buf, NULL); - warning("failed to exec '%s': %s", path, strerror(errno)); + warning("failed to exec '%s': %s", path, + strerror_r(errno, sbuf, sizeof(sbuf))); } } static void exec_man_man(const char *path, const char *page) { + char sbuf[STRERR_BUFSIZE]; + if (!path) path = "man"; execlp(path, "man", page, NULL); - warning("failed to exec '%s': %s", path, strerror(errno)); + warning("failed to exec '%s': %s", path, + strerror_r(errno, sbuf, sizeof(sbuf))); } static void exec_man_cmd(const char *cmd, const char *page) { struct strbuf shell_cmd = STRBUF_INIT; + char sbuf[STRERR_BUFSIZE]; + strbuf_addf(&shell_cmd, "%s %s", cmd, page); execl("/bin/sh", "sh", "-c", shell_cmd.buf, NULL); - warning("failed to exec '%s': %s", cmd, strerror(errno)); + warning("failed to exec '%s': %s", cmd, + strerror_r(errno, sbuf, sizeof(sbuf))); } static void add_man_viewer(const char *name) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 16c7c11..84df2de 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -23,6 +23,7 @@ struct perf_inject { struct perf_tool tool; + struct perf_session *session; bool build_ids; bool sched_stat; const char *input_name; @@ -216,8 +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) { @@ -340,12 +340,8 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel, static int __cmd_inject(struct perf_inject *inject) { - struct perf_session *session; int ret = -EINVAL; - struct perf_data_file file = { - .path = inject->input_name, - .mode = PERF_DATA_MODE_READ, - }; + struct perf_session *session = inject->session; struct perf_data_file *file_out = &inject->output; signal(SIGINT, sig_handler); @@ -357,16 +353,12 @@ static int __cmd_inject(struct perf_inject *inject) inject->tool.tracing_data = perf_event__repipe_tracing_data; } - session = perf_session__new(&file, true, &inject->tool); - if (session == NULL) - return -ENOMEM; - if (inject->build_ids) { inject->tool.sample = perf_event__inject_buildid; } else if (inject->sched_stat) { struct perf_evsel *evsel; - inject->tool.ordered_samples = true; + inject->tool.ordered_events = true; evlist__for_each(session->evlist, evsel) { const char *name = perf_evsel__name(evsel); @@ -389,12 +381,13 @@ static int __cmd_inject(struct perf_inject *inject) ret = perf_session__process_events(session, &inject->tool); if (!file_out->is_pipe) { + if (inject->build_ids) + 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__delete(session); - return ret; } @@ -416,6 +409,7 @@ 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), @@ -424,6 +418,11 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .mode = PERF_DATA_MODE_WRITE, }, }; + struct perf_data_file file = { + .mode = PERF_DATA_MODE_READ, + }; + int ret; + const struct option options[] = { OPT_BOOLEAN('b', "build-ids", &inject.build_ids, "Inject build-ids into the output stream"), @@ -436,6 +435,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) "where and how long tasks slept"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show build ids, etc)"), + OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file", + "kallsyms pathname"), OPT_END() }; const char * const inject_usage[] = { @@ -456,8 +457,17 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } - if (symbol__init() < 0) + file.path = inject.input_name; + inject.session = perf_session__new(&file, true, &inject.tool); + if (inject.session == NULL) + return -1; + + if (symbol__init(&inject.session->header.env) < 0) return -1; - return __cmd_inject(&inject); + ret = __cmd_inject(&inject); + + perf_session__delete(inject.session); + + return ret; } diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index bef3376..f295141 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -256,7 +256,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, static struct perf_tool perf_kmem = { .sample = process_sample_event, .comm = perf_event__process_comm, - .ordered_samples = true, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + .ordered_events = true, }; static double fragmentation(unsigned long n_req, unsigned long n_alloc) @@ -403,10 +405,9 @@ static void sort_result(void) __sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort); } -static int __cmd_kmem(void) +static int __cmd_kmem(struct perf_session *session) { int err = -EINVAL; - struct perf_session *session; const struct perf_evsel_str_handler kmem_tracepoints[] = { { "kmem:kmalloc", perf_evsel__process_alloc_event, }, { "kmem:kmem_cache_alloc", perf_evsel__process_alloc_event, }, @@ -415,34 +416,22 @@ static int __cmd_kmem(void) { "kmem:kfree", perf_evsel__process_free_event, }, { "kmem:kmem_cache_free", perf_evsel__process_free_event, }, }; - struct perf_data_file file = { - .path = input_name, - .mode = PERF_DATA_MODE_READ, - }; - - session = perf_session__new(&file, false, &perf_kmem); - if (session == NULL) - return -ENOMEM; - - if (perf_session__create_kernel_maps(session) < 0) - goto out_delete; if (!perf_session__has_traces(session, "kmem record")) - goto out_delete; + goto out; if (perf_session__set_tracepoints_handlers(session, kmem_tracepoints)) { pr_err("Initializing perf session tracepoint handlers failed\n"); - return -1; + goto out; } setup_pager(); err = perf_session__process_events(session, &perf_kmem); if (err != 0) - goto out_delete; + goto out; sort_result(); print_result(session); -out_delete: - perf_session__delete(session); +out: return err; } @@ -689,29 +678,46 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) NULL, NULL }; + struct perf_session *session; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; + int ret = -1; + argc = parse_options_subcommand(argc, argv, kmem_options, kmem_subcommands, kmem_usage, 0); if (!argc) usage_with_options(kmem_usage, kmem_options); - symbol__init(); - if (!strncmp(argv[0], "rec", 3)) { + symbol__init(NULL); return __cmd_record(argc, argv); - } else if (!strcmp(argv[0], "stat")) { + } + + session = perf_session__new(&file, false, &perf_kmem); + if (session == NULL) + return -1; + + symbol__init(&session->header.env); + + if (!strcmp(argv[0], "stat")) { if (cpu__setup_cpunode_map()) - return -1; + goto out_delete; if (list_empty(&caller_sort)) setup_sorting(&caller_sort, default_sort_order); if (list_empty(&alloc_sort)) setup_sorting(&alloc_sort, default_sort_order); - return __cmd_kmem(); + ret = __cmd_kmem(session); } else usage_with_options(kmem_usage, kmem_options); - return 0; +out_delete: + perf_session__delete(session); + + return ret; } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 0f1e5a2..0894a81 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -29,114 +29,25 @@ #include <pthread.h> #include <math.h> -#if defined(__i386__) || defined(__x86_64__) -#include <asm/svm.h> -#include <asm/vmx.h> -#include <asm/kvm.h> - -struct event_key { - #define INVALID_KEY (~0ULL) - u64 key; - int info; -}; - -struct kvm_event_stats { - u64 time; - struct stats stats; -}; - -struct kvm_event { - struct list_head hash_entry; - struct rb_node rb; - - struct event_key key; - - struct kvm_event_stats total; - - #define DEFAULT_VCPU_NUM 8 - int max_vcpu; - struct kvm_event_stats *vcpu; -}; - -typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); - -struct kvm_event_key { - const char *name; - key_cmp_fun key; -}; - - -struct perf_kvm_stat; - -struct kvm_events_ops { - bool (*is_begin_event)(struct perf_evsel *evsel, - struct perf_sample *sample, - struct event_key *key); - bool (*is_end_event)(struct perf_evsel *evsel, - struct perf_sample *sample, struct event_key *key); - void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key, - char decode[20]); - const char *name; -}; - -struct exit_reasons_table { - unsigned long exit_code; - const char *reason; -}; - -#define EVENTS_BITS 12 -#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) - -struct perf_kvm_stat { - struct perf_tool tool; - struct record_opts opts; - struct perf_evlist *evlist; - struct perf_session *session; - - const char *file_name; - const char *report_event; - const char *sort_key; - int trace_vcpu; +#ifdef HAVE_KVM_STAT_SUPPORT +#include <asm/kvm_perf.h> +#include "util/kvm-stat.h" - struct exit_reasons_table *exit_reasons; - int exit_reasons_size; - const char *exit_reasons_isa; - - struct kvm_events_ops *events_ops; - key_cmp_fun compare; - struct list_head kvm_events_cache[EVENTS_CACHE_SIZE]; - - u64 total_time; - u64 total_count; - u64 lost_events; - u64 duration; - - const char *pid_str; - struct intlist *pid_list; - - struct rb_root result; - - int timerfd; - unsigned int display_time; - bool live; -}; - - -static void exit_event_get_key(struct perf_evsel *evsel, - struct perf_sample *sample, - struct event_key *key) +void exit_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) { key->info = 0; - key->key = perf_evsel__intval(evsel, sample, "exit_reason"); + key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON); } -static bool kvm_exit_event(struct perf_evsel *evsel) +bool kvm_exit_event(struct perf_evsel *evsel) { - return !strcmp(evsel->name, "kvm:kvm_exit"); + return !strcmp(evsel->name, KVM_EXIT_TRACE); } -static bool exit_event_begin(struct perf_evsel *evsel, - struct perf_sample *sample, struct event_key *key) +bool exit_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key) { if (kvm_exit_event(evsel)) { exit_event_get_key(evsel, sample, key); @@ -146,32 +57,23 @@ static bool exit_event_begin(struct perf_evsel *evsel, return false; } -static bool kvm_entry_event(struct perf_evsel *evsel) +bool kvm_entry_event(struct perf_evsel *evsel) { - return !strcmp(evsel->name, "kvm:kvm_entry"); + return !strcmp(evsel->name, KVM_ENTRY_TRACE); } -static bool exit_event_end(struct perf_evsel *evsel, - struct perf_sample *sample __maybe_unused, - struct event_key *key __maybe_unused) +bool exit_event_end(struct perf_evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) { return kvm_entry_event(evsel); } -static struct exit_reasons_table vmx_exit_reasons[] = { - VMX_EXIT_REASONS -}; - -static struct exit_reasons_table svm_exit_reasons[] = { - SVM_EXIT_REASONS -}; - -static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code) +static const char *get_exit_reason(struct perf_kvm_stat *kvm, + struct exit_reasons_table *tbl, + u64 exit_code) { - int i = kvm->exit_reasons_size; - struct exit_reasons_table *tbl = kvm->exit_reasons; - - while (i--) { + while (tbl->reason != NULL) { if (tbl->exit_code == exit_code) return tbl->reason; tbl++; @@ -182,148 +84,30 @@ static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code) return "UNKNOWN"; } -static void exit_event_decode_key(struct perf_kvm_stat *kvm, - struct event_key *key, - char decode[20]) +void exit_event_decode_key(struct perf_kvm_stat *kvm, + struct event_key *key, + char *decode) { - const char *exit_reason = get_exit_reason(kvm, key->key); - - scnprintf(decode, 20, "%s", exit_reason); -} + const char *exit_reason = get_exit_reason(kvm, key->exit_reasons, + key->key); -static struct kvm_events_ops exit_events = { - .is_begin_event = exit_event_begin, - .is_end_event = exit_event_end, - .decode_key = exit_event_decode_key, - .name = "VM-EXIT" -}; - -/* - * For the mmio events, we treat: - * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry - * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). - */ -static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, - struct event_key *key) -{ - key->key = perf_evsel__intval(evsel, sample, "gpa"); - key->info = perf_evsel__intval(evsel, sample, "type"); + scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason); } -#define KVM_TRACE_MMIO_READ_UNSATISFIED 0 -#define KVM_TRACE_MMIO_READ 1 -#define KVM_TRACE_MMIO_WRITE 2 - -static bool mmio_event_begin(struct perf_evsel *evsel, - struct perf_sample *sample, struct event_key *key) -{ - /* MMIO read begin event in kernel. */ - if (kvm_exit_event(evsel)) - return true; - - /* MMIO write begin event in kernel. */ - if (!strcmp(evsel->name, "kvm:kvm_mmio") && - perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) { - mmio_event_get_key(evsel, sample, key); - return true; - } - - return false; -} - -static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, - struct event_key *key) -{ - /* MMIO write end event in kernel. */ - if (kvm_entry_event(evsel)) - return true; - - /* MMIO read end event in kernel.*/ - if (!strcmp(evsel->name, "kvm:kvm_mmio") && - perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) { - mmio_event_get_key(evsel, sample, key); - return true; - } - - return false; -} - -static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, - struct event_key *key, - char decode[20]) -{ - scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key, - key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); -} - -static struct kvm_events_ops mmio_events = { - .is_begin_event = mmio_event_begin, - .is_end_event = mmio_event_end, - .decode_key = mmio_event_decode_key, - .name = "MMIO Access" -}; - - /* The time of emulation pio access is from kvm_pio to kvm_entry. */ -static void ioport_event_get_key(struct perf_evsel *evsel, - struct perf_sample *sample, - struct event_key *key) +static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) { - key->key = perf_evsel__intval(evsel, sample, "port"); - key->info = perf_evsel__intval(evsel, sample, "rw"); -} + struct kvm_reg_events_ops *events_ops = kvm_reg_events_ops; -static bool ioport_event_begin(struct perf_evsel *evsel, - struct perf_sample *sample, - struct event_key *key) -{ - if (!strcmp(evsel->name, "kvm:kvm_pio")) { - ioport_event_get_key(evsel, sample, key); - return true; + for (events_ops = kvm_reg_events_ops; events_ops->name; events_ops++) { + if (!strcmp(events_ops->name, kvm->report_event)) { + kvm->events_ops = events_ops->ops; + return true; + } } return false; } -static bool ioport_event_end(struct perf_evsel *evsel, - struct perf_sample *sample __maybe_unused, - struct event_key *key __maybe_unused) -{ - return kvm_entry_event(evsel); -} - -static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, - struct event_key *key, - char decode[20]) -{ - scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key, - key->info ? "POUT" : "PIN"); -} - -static struct kvm_events_ops ioport_events = { - .is_begin_event = ioport_event_begin, - .is_end_event = ioport_event_end, - .decode_key = ioport_event_decode_key, - .name = "IO Port Access" -}; - -static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) -{ - bool ret = true; - - if (!strcmp(kvm->report_event, "vmexit")) - kvm->events_ops = &exit_events; - else if (!strcmp(kvm->report_event, "mmio")) - kvm->events_ops = &mmio_events; - else if (!strcmp(kvm->report_event, "ioport")) - kvm->events_ops = &ioport_events; - else { - pr_err("Unknown report event:%s\n", kvm->report_event); - ret = false; - } - - return ret; -} - struct vcpu_event_record { int vcpu_id; u64 start_time; @@ -477,6 +261,54 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id, return true; } +static bool is_child_event(struct perf_kvm_stat *kvm, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + struct child_event_ops *child_ops; + + child_ops = kvm->events_ops->child_ops; + + if (!child_ops) + return false; + + for (; child_ops->name; child_ops++) { + if (!strcmp(evsel->name, child_ops->name)) { + child_ops->get_key(evsel, sample, key); + return true; + } + } + + return false; +} + +static bool handle_child_event(struct perf_kvm_stat *kvm, + struct vcpu_event_record *vcpu_record, + struct event_key *key, + struct perf_sample *sample __maybe_unused) +{ + struct kvm_event *event = NULL; + + if (key->key != INVALID_KEY) + event = find_create_kvm_event(kvm, key); + + vcpu_record->last_event = event; + + return true; +} + +static bool skip_event(const char *event) +{ + const char * const *skip_events; + + for (skip_events = kvm_skip_events; *skip_events; skip_events++) + if (!strcmp(event, *skip_events)) + return true; + + return false; +} + static bool handle_end_event(struct perf_kvm_stat *kvm, struct vcpu_event_record *vcpu_record, struct event_key *key, @@ -525,10 +357,10 @@ static bool handle_end_event(struct perf_kvm_stat *kvm, time_diff = sample->time - time_begin; if (kvm->duration && time_diff > kvm->duration) { - char decode[32]; + char decode[DECODE_STR_LEN]; kvm->events_ops->decode_key(kvm, &event->key, decode); - if (strcmp(decode, "HLT")) { + if (!skip_event(decode)) { pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n", sample->time, sample->pid, vcpu_record->vcpu_id, decode, time_diff/1000); @@ -544,7 +376,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread, struct perf_sample *sample) { /* Only kvm_entry records vcpu id. */ - if (!thread->priv && kvm_entry_event(evsel)) { + if (!thread__priv(thread) && kvm_entry_event(evsel)) { struct vcpu_event_record *vcpu_record; vcpu_record = zalloc(sizeof(*vcpu_record)); @@ -553,11 +385,11 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread, return NULL; } - vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id"); - thread->priv = vcpu_record; + vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID); + thread__set_priv(thread, vcpu_record); } - return thread->priv; + return thread__priv(thread); } static bool handle_kvm_event(struct perf_kvm_stat *kvm, @@ -566,7 +398,8 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm, struct perf_sample *sample) { struct vcpu_event_record *vcpu_record; - struct event_key key = {.key = INVALID_KEY}; + struct event_key key = { .key = INVALID_KEY, + .exit_reasons = kvm->exit_reasons }; vcpu_record = per_vcpu_record(thread, evsel, sample); if (!vcpu_record) @@ -580,6 +413,9 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm, if (kvm->events_ops->is_begin_event(evsel, sample, &key)) return handle_begin_event(kvm, vcpu_record, &key, sample->time); + if (is_child_event(kvm, evsel, sample, &key)) + return handle_child_event(kvm, vcpu_record, &key, sample); + if (kvm->events_ops->is_end_event(evsel, sample, &key)) return handle_end_event(kvm, vcpu_record, &key, sample); @@ -707,14 +543,12 @@ static void print_vcpu_info(struct perf_kvm_stat *kvm) pr_info("Analyze events for "); - if (kvm->live) { - if (kvm->opts.target.system_wide) - pr_info("all VMs, "); - else if (kvm->opts.target.pid) - pr_info("pid(s) %s, ", kvm->opts.target.pid); - else - pr_info("dazed and confused on what is monitored, "); - } + if (kvm->opts.target.system_wide) + pr_info("all VMs, "); + else if (kvm->opts.target.pid) + pr_info("pid(s) %s, ", kvm->opts.target.pid); + else + pr_info("dazed and confused on what is monitored, "); if (vcpu == -1) pr_info("all VCPUs:\n\n"); @@ -740,7 +574,7 @@ static void show_timeofday(void) static void print_result(struct perf_kvm_stat *kvm) { - char decode[20]; + char decode[DECODE_STR_LEN]; struct kvm_event *event; int vcpu = kvm->trace_vcpu; @@ -751,13 +585,13 @@ static void print_result(struct perf_kvm_stat *kvm) pr_info("\n\n"); print_vcpu_info(kvm); - pr_info("%20s ", kvm->events_ops->name); + pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name); pr_info("%10s ", "Samples"); pr_info("%9s ", "Samples%"); pr_info("%9s ", "Time%"); - pr_info("%10s ", "Min Time"); - pr_info("%10s ", "Max Time"); + pr_info("%11s ", "Min Time"); + pr_info("%11s ", "Max Time"); pr_info("%16s ", "Avg time"); pr_info("\n\n"); @@ -770,12 +604,12 @@ static void print_result(struct perf_kvm_stat *kvm) min = get_event_min(event, vcpu); kvm->events_ops->decode_key(kvm, &event->key, decode); - pr_info("%20s ", decode); + pr_info("%*s ", DECODE_STR_LEN, decode); pr_info("%10llu ", (unsigned long long)ecount); pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100); pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100); - pr_info("%8" PRIu64 "us ", min / 1000); - pr_info("%8" PRIu64 "us ", max / 1000); + pr_info("%9.2fus ", (double)min / 1e3); + pr_info("%9.2fus ", (double)max / 1e3); pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3, kvm_event_rel_stddev(vcpu, event)); pr_info("\n"); @@ -839,34 +673,28 @@ static int process_sample_event(struct perf_tool *tool, static int cpu_isa_config(struct perf_kvm_stat *kvm) { char buf[64], *cpuid; - int err, isa; + int err; if (kvm->live) { err = get_cpuid(buf, sizeof(buf)); if (err != 0) { - pr_err("Failed to look up CPU type (Intel or AMD)\n"); + pr_err("Failed to look up CPU type\n"); return err; } cpuid = buf; } else cpuid = kvm->session->header.env.cpuid; - if (strstr(cpuid, "Intel")) - isa = 1; - else if (strstr(cpuid, "AMD")) - isa = 0; - else { - pr_err("CPU %s is not supported.\n", cpuid); - return -ENOTSUP; + if (!cpuid) { + pr_err("Failed to look up CPU type\n"); + return -EINVAL; } - if (isa == 1) { - kvm->exit_reasons = vmx_exit_reasons; - kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons); - kvm->exit_reasons_isa = "VMX"; - } + err = cpu_isa_init(kvm, cpuid); + if (err == -ENOTSUP) + pr_err("CPU %s is not supported.\n", cpuid); - return 0; + return err; } static bool verify_vcpu(int vcpu) @@ -902,7 +730,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, return -1; } - err = perf_session_queue_event(kvm->session, event, &sample, 0); + err = perf_session_queue_event(kvm->session, event, &kvm->tool, &sample, 0); /* * FIXME: Here we can't consume the event, as perf_session_queue_event will * point to it, and it'll get possibly overwritten by the kernel. @@ -955,7 +783,7 @@ static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm) /* flush queue after each round in which we processed events */ if (ntotal) { - kvm->session->ordered_samples.next_flush = flush_time; + kvm->session->ordered_events.next_flush = flush_time; err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session); if (err) { if (kvm->lost_events) @@ -1055,15 +883,11 @@ static int fd_set_nonblock(int fd) return 0; } -static -int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save) +static int perf_kvm__handle_stdin(void) { int c; - tcsetattr(0, TCSANOW, tc_now); c = getc(stdin); - tcsetattr(0, TCSAFLUSH, tc_save); - if (c == 'q') return 1; @@ -1072,9 +896,8 @@ int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save) static int kvm_events_live_report(struct perf_kvm_stat *kvm) { - struct pollfd *pollfds = NULL; - int nr_fds, nr_stdin, ret, err = -EINVAL; - struct termios tc, save; + int nr_stdin, ret, err = -EINVAL; + struct termios save; /* live flag must be set first */ kvm->live = true; @@ -1089,41 +912,25 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) goto out; } + set_term_quiet_input(&save); init_kvm_event_record(kvm); - tcgetattr(0, &save); - tc = save; - tc.c_lflag &= ~(ICANON | ECHO); - tc.c_cc[VMIN] = 0; - tc.c_cc[VTIME] = 0; - signal(SIGINT, sig_handler); signal(SIGTERM, sig_handler); - /* copy pollfds -- need to add timerfd and stdin */ - nr_fds = kvm->evlist->nr_fds; - pollfds = zalloc(sizeof(struct pollfd) * (nr_fds + 2)); - if (!pollfds) { - err = -ENOMEM; - goto out; - } - memcpy(pollfds, kvm->evlist->pollfd, - sizeof(struct pollfd) * kvm->evlist->nr_fds); - /* add timer fd */ if (perf_kvm__timerfd_create(kvm) < 0) { err = -1; goto out; } - pollfds[nr_fds].fd = kvm->timerfd; - pollfds[nr_fds].events = POLLIN; - nr_fds++; + if (perf_evlist__add_pollfd(kvm->evlist, kvm->timerfd) < 0) + goto out; + + nr_stdin = perf_evlist__add_pollfd(kvm->evlist, fileno(stdin)); + if (nr_stdin < 0) + goto out; - pollfds[nr_fds].fd = fileno(stdin); - pollfds[nr_fds].events = POLLIN; - nr_stdin = nr_fds; - nr_fds++; if (fd_set_nonblock(fileno(stdin)) != 0) goto out; @@ -1131,6 +938,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) perf_evlist__enable(kvm->evlist); while (!done) { + struct fdarray *fda = &kvm->evlist->pollfd; int rc; rc = perf_kvm__mmap_read(kvm); @@ -1141,11 +949,11 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) if (err) goto out; - if (pollfds[nr_stdin].revents & POLLIN) - done = perf_kvm__handle_stdin(&tc, &save); + if (fda->entries[nr_stdin].revents & POLLIN) + done = perf_kvm__handle_stdin(); if (!rc && !done) - err = poll(pollfds, nr_fds, 100); + err = fdarray__poll(fda, 100); } perf_evlist__disable(kvm->evlist); @@ -1159,7 +967,7 @@ out: if (kvm->timerfd >= 0) close(kvm->timerfd); - free(pollfds); + tcsetattr(0, TCSAFLUSH, &save); return err; } @@ -1168,6 +976,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm) int err, rc = -1; struct perf_evsel *pos; struct perf_evlist *evlist = kvm->evlist; + char sbuf[STRERR_BUFSIZE]; perf_evlist__config(evlist, &kvm->opts); @@ -1204,12 +1013,14 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm) err = perf_evlist__open(evlist); if (err < 0) { - printf("Couldn't create the events: %s\n", strerror(errno)); + printf("Couldn't create the events: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); goto out; } if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) { - ui__error("Failed to mmap the events: %s\n", strerror(errno)); + ui__error("Failed to mmap the events: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); perf_evlist__close(evlist); goto out; } @@ -1228,7 +1039,7 @@ static int read_events(struct perf_kvm_stat *kvm) struct perf_tool eops = { .sample = process_sample_event, .comm = perf_event__process_comm, - .ordered_samples = true, + .ordered_events = true, }; struct perf_data_file file = { .path = kvm->file_name, @@ -1239,9 +1050,11 @@ static int read_events(struct perf_kvm_stat *kvm) kvm->session = perf_session__new(&file, false, &kvm->tool); if (!kvm->session) { pr_err("Initializing perf session failed\n"); - return -EINVAL; + return -1; } + symbol__init(&kvm->session->header.env); + if (!perf_session__has_traces(kvm->session, "kvm record")) return -EINVAL; @@ -1258,8 +1071,8 @@ static int read_events(struct perf_kvm_stat *kvm) static int parse_target_str(struct perf_kvm_stat *kvm) { - if (kvm->pid_str) { - kvm->pid_list = intlist__new(kvm->pid_str); + if (kvm->opts.target.pid) { + kvm->pid_list = intlist__new(kvm->opts.target.pid); if (kvm->pid_list == NULL) { pr_err("Error parsing process id string\n"); return -EINVAL; @@ -1300,13 +1113,6 @@ exit: return ret; } -static const char * const kvm_events_tp[] = { - "kvm:kvm_entry", - "kvm:kvm_exit", - "kvm:kvm_mmio", - "kvm:kvm_pio", -}; - #define STRDUP_FAIL_EXIT(s) \ ({ char *_p; \ _p = strdup(s); \ @@ -1318,7 +1124,7 @@ static const char * const kvm_events_tp[] = { static int kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) { - unsigned int rec_argc, i, j; + unsigned int rec_argc, i, j, events_tp_size; const char **rec_argv; const char * const record_args[] = { "record", @@ -1326,9 +1132,18 @@ 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; + + for (events_tp = kvm_events_tp; *events_tp; events_tp++) + events_tp_size++; rec_argc = ARRAY_SIZE(record_args) + argc + 2 + - 2 * ARRAY_SIZE(kvm_events_tp); + 2 * events_tp_size; rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (rec_argv == NULL) @@ -1337,7 +1152,7 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(record_args); i++) rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]); - for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) { + for (j = 0; j < events_tp_size; j++) { rec_argv[i++] = "-e"; rec_argv[i++] = STRDUP_FAIL_EXIT(kvm_events_tp[j]); } @@ -1348,6 +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); } @@ -1356,13 +1192,14 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) { const struct option kvm_events_report_options[] = { 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", "key for sorting: sample(sort by samples number)" " time (sort by avg time)"), - OPT_STRING('p', "pid", &kvm->pid_str, "pid", + OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid", "analyze events only for given process id(s)"), OPT_END() }; @@ -1372,8 +1209,6 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) NULL }; - symbol__init(); - if (argc) { argc = parse_options(argc, argv, kvm_events_report_options, @@ -1383,6 +1218,9 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) kvm_events_report_options); } + if (!kvm->opts.target.pid) + kvm->opts.target.system_wide = true; + return kvm_events_report_vcpu(kvm); } @@ -1391,16 +1229,16 @@ static struct perf_evlist *kvm_live_event_list(void) { struct perf_evlist *evlist; char *tp, *name, *sys; - unsigned int j; int err = -1; + const char * const *events_tp; evlist = perf_evlist__new(); if (evlist == NULL) return NULL; - for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) { + for (events_tp = kvm_events_tp; *events_tp; events_tp++) { - tp = strdup(kvm_events_tp[j]); + tp = strdup(*events_tp); if (tp == NULL) goto out; @@ -1409,7 +1247,7 @@ static struct perf_evlist *kvm_live_event_list(void) name = strchr(tp, ':'); if (name == NULL) { pr_err("Error parsing %s tracepoint: subsystem delimiter not found\n", - kvm_events_tp[j]); + *events_tp); free(tp); goto out; } @@ -1417,7 +1255,7 @@ static struct perf_evlist *kvm_live_event_list(void) name++; if (perf_evlist__add_newtp(evlist, sys, name, NULL)) { - pr_err("Failed to add %s tracepoint to the list\n", kvm_events_tp[j]); + pr_err("Failed to add %s tracepoint to the list\n", *events_tp); free(tp); goto out; } @@ -1455,14 +1293,17 @@ 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", "key for sorting: sample(sort by samples number)" " time (sort by avg time)"), OPT_U64(0, "duration", &kvm->duration, - "show events other than HALT that take longer than duration usecs"), + "show events other than" + " HLT (x86 only) or Wait state (s390 only)" + " that take longer than duration usecs"), OPT_END() }; const char * const live_usage[] = { @@ -1480,7 +1321,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, kvm->tool.exit = perf_event__process_exit; kvm->tool.fork = perf_event__process_fork; kvm->tool.lost = process_lost_event; - kvm->tool.ordered_samples = true; + kvm->tool.ordered_events = true; perf_tool__fill_defaults(&kvm->tool); /* set defaults */ @@ -1491,7 +1332,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, kvm->opts.target.uid_str = NULL; kvm->opts.target.uid = UINT_MAX; - symbol__init(); + symbol__init(NULL); disable_buildid_cache(); use_browser = 0; @@ -1538,11 +1379,12 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, */ kvm->session = perf_session__new(&file, false, &kvm->tool); if (kvm->session == NULL) { - err = -ENOMEM; + err = -1; goto out; } kvm->session->evlist = kvm->evlist; perf_session__set_id_hdr_size(kvm->session); + ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true); machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target, kvm->evlist->threads, false); err = kvm_live_open_events(kvm); @@ -1585,9 +1427,6 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv) .report_event = "vmexit", .sort_key = "sample", - .exit_reasons = svm_exit_reasons, - .exit_reasons_size = ARRAY_SIZE(svm_exit_reasons), - .exit_reasons_isa = "SVM", }; if (argc == 1) { @@ -1609,7 +1448,7 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv) perf_stat: return cmd_stat(argc, argv, NULL); } -#endif +#endif /* HAVE_KVM_STAT_SUPPORT */ static int __cmd_record(const char *file_name, int argc, const char **argv) { @@ -1726,7 +1565,7 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) return cmd_top(argc, argv, NULL); else if (!strncmp(argv[0], "buildid-list", 12)) return __cmd_buildid_list(file_name, argc, argv); -#if defined(__i386__) || defined(__x86_64__) +#ifdef HAVE_KVM_STAT_SUPPORT else if (!strncmp(argv[0], "stat", 4)) return kvm_cmd_stat(file_name, argc, argv); #endif diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 6148afc..e7ec715 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -852,7 +852,7 @@ static int __cmd_report(bool display_info) struct perf_tool eops = { .sample = process_sample_event, .comm = perf_event__process_comm, - .ordered_samples = true, + .ordered_events = true, }; struct perf_data_file file = { .path = input_name, @@ -862,9 +862,11 @@ static int __cmd_report(bool display_info) session = perf_session__new(&file, false, &eops); if (!session) { pr_err("Initializing perf session failed\n"); - return -ENOMEM; + return -1; } + symbol__init(&session->header.env); + if (!perf_session__has_traces(session, "lock record")) goto out_delete; @@ -974,7 +976,6 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) unsigned int i; int rc = 0; - symbol__init(); for (i = 0; i < LOCKHASH_SIZE; i++) INIT_LIST_HEAD(lockhash_table + i); diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 4a1a6c9..24db6ff 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -124,7 +124,7 @@ static int report_raw_events(struct perf_mem *mem) &mem->tool); if (session == NULL) - return -ENOMEM; + return -1; if (mem->cpu_list) { ret = perf_session__cpu_bitmap(session, mem->cpu_list, @@ -133,7 +133,7 @@ static int report_raw_events(struct perf_mem *mem) goto out_delete; } - if (symbol__init() < 0) + if (symbol__init(&session->header.env) < 0) return -1; printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n"); @@ -194,7 +194,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) .lost = perf_event__process_lost, .fork = perf_event__process_fork, .build_id = perf_event__process_build_id, - .ordered_samples = true, + .ordered_events = true, }, .input_name = "perf.data", }; diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index c63fa29..921bb69 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; @@ -290,8 +291,11 @@ static void cleanup_params(void) static void pr_err_with_code(const char *msg, int err) { + char sbuf[STRERR_BUFSIZE]; + pr_err("%s", msg); - pr_debug(" Reason: %s (Code: %d)", strerror(-err), err); + pr_debug(" Reason: %s (Code: %d)", + strerror_r(-err, sbuf, sizeof(sbuf)), err); pr_err("\n"); } @@ -309,9 +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.", @@ -372,11 +378,21 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK('x', "exec", NULL, "executable|path", "target executable name or path", opt_set_target), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, - "Disable symbol demangling"), + "Enable symbol demangling"), + OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, + "Enable kernel symbol demangling"), OPT_END() }; 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) { @@ -391,6 +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; @@ -404,22 +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); @@ -430,19 +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); @@ -457,27 +452,13 @@ __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); + ret = show_line_range(¶ms.line_range, params.target, + params.uprobes); if (ret < 0) pr_err_with_code(" Error: Failed to show lines.", ret); 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 378b85b..8648c6d 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -14,6 +14,8 @@ #include "util/parse-options.h" #include "util/parse-events.h" +#include "util/callchain.h" +#include "util/cgroup.h" #include "util/header.h" #include "util/event.h" #include "util/evlist.h" @@ -65,8 +67,9 @@ static int process_synthesized_event(struct perf_tool *tool, return record__write(rec, event, event->header.size); } -static int record__mmap_read(struct record *rec, struct perf_mmap *md) +static int record__mmap_read(struct record *rec, int idx) { + struct perf_mmap *md = &rec->evlist->mmap[idx]; unsigned int head = perf_mmap__read_head(md); unsigned int old = md->prev; unsigned char *data = md->base + page_size; @@ -102,8 +105,7 @@ static int record__mmap_read(struct record *rec, struct perf_mmap *md) } md->prev = old; - perf_mmap__write_tail(md, old); - + perf_evlist__mmap_consume(rec->evlist, idx); out: return rc; } @@ -161,7 +163,7 @@ try_again: if (perf_evlist__apply_filters(evlist)) { error("failed to set filter with %d (%s)\n", errno, - strerror(errno)); + strerror_r(errno, msg, sizeof(msg))); rc = -1; goto out; } @@ -175,7 +177,8 @@ try_again: "(current value: %u)\n", opts->mmap_pages); rc = -errno; } else { - pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno)); + pr_err("failed to mmap with %d (%s)\n", errno, + strerror_r(errno, msg, sizeof(msg))); rc = -errno; } goto out; @@ -197,6 +200,17 @@ static int process_buildids(struct record *rec) if (size == 0) return 0; + /* + * 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, start, size - start, size, &build_id__mark_dso_hit_ops); @@ -238,19 +252,24 @@ static struct perf_event_header finished_round_event = { static int record__mmap_read_all(struct record *rec) { + u64 bytes_written = rec->bytes_written; int i; int rc = 0; for (i = 0; i < rec->evlist->nr_mmaps; i++) { if (rec->evlist->mmap[i].base) { - if (record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) { + if (record__mmap_read(rec, i) != 0) { rc = -1; goto out; } } } - if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA)) + /* + * Mark the round finished in case we wrote + * at least one event. + */ + if (bytes_written != rec->bytes_written) rc = record__write(rec, &finished_round_event, sizeof(finished_round_event)); out: @@ -302,7 +321,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) struct record_opts *opts = &rec->opts; struct perf_data_file *file = &rec->file; struct perf_session *session; - bool disabled = false; + bool disabled = false, draining = false; rec->progname = argv[0]; @@ -451,9 +470,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } if (hits == rec->samples) { - if (done) + if (done || draining) break; - err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1); + err = perf_evlist__poll(rec->evlist, -1); /* * Propagate error, only if there's any. Ignore positive * number of returned events and interrupt error. @@ -461,6 +480,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (err > 0 || (err < 0 && errno == EINTR)) err = 0; waking++; + + if (perf_evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0) + draining = true; } /* @@ -475,7 +497,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } if (forks && workload_exec_errno) { - char msg[512]; + char msg[STRERR_BUFSIZE]; const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg)); pr_err("Workload failed: %s\n", emsg); err = -1; @@ -615,154 +637,66 @@ error: return ret; } -#ifdef HAVE_DWARF_UNWIND_SUPPORT -static int get_stack_size(char *str, unsigned long *_size) -{ - char *endptr; - unsigned long size; - unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); - - size = strtoul(str, &endptr, 0); - - do { - if (*endptr) - break; - - size = round_up(size, sizeof(u64)); - if (!size || size > max_size) - break; - - *_size = size; - return 0; - - } while (0); - - pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", - max_size, str); - return -1; -} -#endif /* HAVE_DWARF_UNWIND_SUPPORT */ - -int record_parse_callchain(const char *arg, struct record_opts *opts) -{ - char *tok, *name, *saveptr = NULL; - char *buf; - int ret = -1; - - /* We need buffer that we know we can write to. */ - buf = malloc(strlen(arg) + 1); - if (!buf) - return -ENOMEM; - - strcpy(buf, arg); - - tok = strtok_r((char *)buf, ",", &saveptr); - name = tok ? : (char *)buf; - - do { - /* Framepointer style */ - if (!strncmp(name, "fp", sizeof("fp"))) { - if (!strtok_r(NULL, ",", &saveptr)) { - opts->call_graph = CALLCHAIN_FP; - ret = 0; - } else - pr_err("callchain: No more arguments " - "needed for -g fp\n"); - break; - -#ifdef HAVE_DWARF_UNWIND_SUPPORT - /* Dwarf style */ - } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { - const unsigned long default_stack_dump_size = 8192; - - ret = 0; - opts->call_graph = CALLCHAIN_DWARF; - opts->stack_dump_size = default_stack_dump_size; - - tok = strtok_r(NULL, ",", &saveptr); - if (tok) { - unsigned long size = 0; - - ret = get_stack_size(tok, &size); - opts->stack_dump_size = size; - } -#endif /* HAVE_DWARF_UNWIND_SUPPORT */ - } else { - pr_err("callchain: Unknown --call-graph option " - "value: %s\n", arg); - break; - } - - } while (0); - - free(buf); - return ret; -} - -static void callchain_debug(struct record_opts *opts) +static void callchain_debug(void) { static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" }; - pr_debug("callchain: type %s\n", str[opts->call_graph]); + pr_debug("callchain: type %s\n", str[callchain_param.record_mode]); - if (opts->call_graph == CALLCHAIN_DWARF) + if (callchain_param.record_mode == CALLCHAIN_DWARF) pr_debug("callchain: stack dump size %d\n", - opts->stack_dump_size); + callchain_param.dump_size); } -int record_parse_callchain_opt(const struct option *opt, +int record_parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, int unset) { - struct record_opts *opts = opt->value; int ret; - opts->call_graph_enabled = !unset; + callchain_param.enabled = !unset; /* --no-call-graph */ if (unset) { - opts->call_graph = CALLCHAIN_NONE; + callchain_param.record_mode = CALLCHAIN_NONE; pr_debug("callchain: disabled\n"); return 0; } - ret = record_parse_callchain(arg, opts); + ret = parse_callchain_record_opt(arg); if (!ret) - callchain_debug(opts); + callchain_debug(); return ret; } -int record_callchain_opt(const struct option *opt, +int record_callchain_opt(const struct option *opt __maybe_unused, const char *arg __maybe_unused, int unset __maybe_unused) { - struct record_opts *opts = opt->value; - - opts->call_graph_enabled = !unset; + callchain_param.enabled = true; - if (opts->call_graph == CALLCHAIN_NONE) - opts->call_graph = CALLCHAIN_FP; + if (callchain_param.record_mode == CALLCHAIN_NONE) + callchain_param.record_mode = CALLCHAIN_FP; - callchain_debug(opts); + callchain_debug(); return 0; } static int perf_record_config(const char *var, const char *value, void *cb) { - struct record *rec = cb; - if (!strcmp(var, "record.call-graph")) - return record_parse_callchain(value, &rec->opts); + var = "call-graph.record-mode"; /* fall-through */ 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 @@ -776,6 +710,7 @@ static const char * const record_usage[] = { */ static struct record record = { .opts = { + .sample_time = true, .mmap_pages = UINT_MAX, .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, @@ -802,7 +737,7 @@ 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), @@ -876,9 +811,13 @@ 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; @@ -902,7 +841,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) usage_with_options(record_usage, record_options); } - symbol__init(); + symbol__init(NULL); if (symbol_conf.kptr_restrict) pr_warning( diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 21d830b..3936760 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -58,17 +58,19 @@ struct report { const char *symbol_filter_str; float min_percent; u64 nr_entries; + u64 queue_size; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; static int report__config(const char *var, const char *value, void *cb) { + struct report *rep = cb; + if (!strcmp(var, "report.group")) { symbol_conf.event_group = perf_config_bool(var, value); return 0; } if (!strcmp(var, "report.percent-limit")) { - struct report *rep = cb; rep->min_percent = strtof(value, NULL); return 0; } @@ -76,6 +78,10 @@ static int report__config(const char *var, const char *value, void *cb) symbol_conf.cumulate_callchain = perf_config_bool(var, value); return 0; } + if (!strcmp(var, "report.queue-size")) { + rep->queue_size = perf_config_u64(var, value); + return 0; + } return perf_default_config(var, value, cb); } @@ -220,8 +226,9 @@ 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 && @@ -251,6 +258,13 @@ static int report__setup_sample_type(struct report *rep) } } + if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) { + if ((sample_type & PERF_SAMPLE_REGS_USER) && + (sample_type & PERF_SAMPLE_STACK_USER)) + callchain_param.record_mode = CALLCHAIN_DWARF; + else + callchain_param.record_mode = CALLCHAIN_FP; + } return 0; } @@ -282,12 +296,14 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report evname = buf; for_each_group_member(pos, evsel) { + const struct hists *pos_hists = evsel__hists(pos); + if (symbol_conf.filter_relative) { - nr_samples += pos->hists.stats.nr_non_filtered_samples; - nr_events += pos->hists.stats.total_non_filtered_period; + nr_samples += pos_hists->stats.nr_non_filtered_samples; + nr_events += pos_hists->stats.total_non_filtered_period; } else { - nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; - nr_events += pos->hists.stats.total_period; + nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE]; + nr_events += pos_hists->stats.total_period; } } } @@ -312,7 +328,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, struct perf_evsel *pos; evlist__for_each(evlist, pos) { - struct hists *hists = &pos->hists; + struct hists *hists = evsel__hists(pos); const char *evname = perf_evsel__name(pos); if (symbol_conf.event_group && @@ -421,7 +437,7 @@ static void report__collapse_hists(struct report *rep) ui_progress__init(&prog, rep->nr_entries, "Merging related events..."); evlist__for_each(rep->session->evlist, pos) { - struct hists *hists = &pos->hists; + struct hists *hists = evsel__hists(pos); if (pos->idx == 0) hists->symbol_filter_str = rep->symbol_filter_str; @@ -431,7 +447,7 @@ static void report__collapse_hists(struct report *rep) /* Non-group events are considered as leader */ if (symbol_conf.event_group && !perf_evsel__is_group_leader(pos)) { - struct hists *leader_hists = &pos->leader->hists; + struct hists *leader_hists = evsel__hists(pos->leader); hists__match(leader_hists, hists); hists__link(leader_hists, hists); @@ -479,6 +495,7 @@ static int __cmd_report(struct report *rep) if (dump_trace) { perf_session__fprintf_nr_events(session, stdout); + perf_evlist__fprintf_nr_events(session->evlist, stdout); return 0; } } @@ -494,7 +511,7 @@ static int __cmd_report(struct report *rep) } evlist__for_each(session->evlist, pos) - hists__output_resort(&pos->hists); + hists__output_resort(evsel__hists(pos)); return report__browse_hists(rep); } @@ -559,7 +576,7 @@ 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; - int ret = -1; + bool branch_call_mode = false; char callchain_default_opt[] = "fractal,0.5,callee"; const char * const report_usage[] = { "perf report [<options>]", @@ -578,7 +595,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .attr = perf_event__process_attr, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, - .ordered_samples = true, + .ordered_events = true, .ordering_requires_timestamps = true, }, .max_stack = PERF_MAX_STACK_DEPTH, @@ -622,8 +639,8 @@ 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"), @@ -669,11 +686,16 @@ 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, "Disable symbol demangling"), + OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, + "Enable kernel symbol demangling"), OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"), OPT_CALLBACK(0, "percent-limit", &report, "percent", "Don't show entries under that percent", parse_percent_limit), @@ -684,6 +706,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) struct perf_data_file file = { .mode = PERF_DATA_MODE_READ, }; + int ret = hists__init(); + + if (ret < 0) + return ret; perf_config(report__config, &report); @@ -712,17 +738,36 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) repeat: session = perf_session__new(&file, false, &report.tool); if (session == NULL) - return -ENOMEM; + return -1; + + if (report.queue_size) { + ordered_events__set_alloc_size(&session->ordered_events, + report.queue_size); + } report.session = session; has_br_stack = perf_header__has_feat(&session->header, HEADER_BRANCH_STACK); - if (branch_mode == -1 && has_br_stack) { + /* + * 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) { @@ -787,7 +832,7 @@ repeat: } } - if (symbol__init() < 0) + if (symbol__init(&session->header.env) < 0) goto error; if (argc) { diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index c38d06c..891c393 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -10,6 +10,7 @@ #include "util/header.h" #include "util/session.h" #include "util/tool.h" +#include "util/cloexec.h" #include "util/parse-options.h" #include "util/trace-event.h" @@ -427,6 +428,7 @@ static u64 get_cpu_usage_nsec_parent(void) static int self_open_counters(void) { struct perf_event_attr attr; + char sbuf[STRERR_BUFSIZE]; int fd; memset(&attr, 0, sizeof(attr)); @@ -434,11 +436,13 @@ static int self_open_counters(void) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_TASK_CLOCK; - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + fd = sys_perf_event_open(&attr, 0, -1, -1, + perf_event_open_cloexec_flag()); if (fd < 0) pr_err("Error: sys_perf_event_open() syscall returned " - "with %d (%s)\n", fd, strerror(errno)); + "with %d (%s)\n", fd, + strerror_r(errno, sbuf, sizeof(sbuf))); return fd; } @@ -935,8 +939,8 @@ static int latency_switch_event(struct perf_sched *sched, return -1; } - sched_out = machine__findnew_thread(machine, 0, prev_pid); - sched_in = machine__findnew_thread(machine, 0, next_pid); + sched_out = machine__findnew_thread(machine, -1, prev_pid); + sched_in = machine__findnew_thread(machine, -1, next_pid); out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); if (!out_events) { @@ -979,7 +983,7 @@ static int latency_runtime_event(struct perf_sched *sched, { const u32 pid = perf_evsel__intval(evsel, sample, "pid"); const u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); - struct thread *thread = machine__findnew_thread(machine, 0, pid); + struct thread *thread = machine__findnew_thread(machine, -1, pid); struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); u64 timestamp = sample->time; int cpu = sample->cpu; @@ -1012,7 +1016,7 @@ static int latency_wakeup_event(struct perf_sched *sched, struct thread *wakee; u64 timestamp = sample->time; - wakee = machine__findnew_thread(machine, 0, pid); + wakee = machine__findnew_thread(machine, -1, pid); atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, wakee)) @@ -1072,7 +1076,7 @@ static int latency_migrate_task_event(struct perf_sched *sched, if (sched->profile_cpu == -1) return 0; - migrant = machine__findnew_thread(machine, 0, pid); + migrant = machine__findnew_thread(machine, -1, pid); atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, migrant)) @@ -1290,7 +1294,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, return -1; } - sched_in = machine__findnew_thread(machine, 0, next_pid); + sched_in = machine__findnew_thread(machine, -1, next_pid); sched->curr_thread[this_cpu] = sched_in; @@ -1427,9 +1431,6 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_ { int err = 0; - evsel->hists.stats.total_period += sample->period; - hists__inc_nr_samples(&evsel->hists, true); - if (evsel->handler != NULL) { tracepoint_handler f = evsel->handler; err = f(tool, evsel, sample, machine); @@ -1460,6 +1461,8 @@ static int perf_sched__read_events(struct perf_sched *sched, return -1; } + symbol__init(&session->header.env); + if (perf_session__set_tracepoints_handlers(session, handlers)) goto out_delete; @@ -1660,7 +1663,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) .comm = perf_event__process_comm, .lost = perf_event__process_lost, .fork = perf_sched__process_fork_event, - .ordered_samples = true, + .ordered_events = true, }, .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid), .sort_list = LIST_HEAD_INIT(sched.sort_list), @@ -1745,7 +1748,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) if (!strcmp(argv[0], "script")) return cmd_script(argc, argv, prefix); - symbol__init(); if (!strncmp(argv[0], "rec", 3)) { return __cmd_record(argc, argv); } else if (!strncmp(argv[0], "lat", 3)) { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 9e9c91f..ce304df 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; @@ -44,6 +43,7 @@ enum perf_output_field { PERF_OUTPUT_ADDR = 1U << 10, PERF_OUTPUT_SYMOFFSET = 1U << 11, PERF_OUTPUT_SRCLINE = 1U << 12, + PERF_OUTPUT_PERIOD = 1U << 13, }; struct output_option { @@ -63,6 +63,7 @@ struct output_option { {.str = "addr", .field = PERF_OUTPUT_ADDR}, {.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET}, {.str = "srcline", .field = PERF_OUTPUT_SRCLINE}, + {.str = "period", .field = PERF_OUTPUT_PERIOD}, }; /* default set to maintain compatibility with current format */ @@ -80,7 +81,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO, + PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | + PERF_OUTPUT_PERIOD, .invalid_fields = PERF_OUTPUT_TRACE, }, @@ -91,7 +93,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO, + PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | + PERF_OUTPUT_PERIOD, .invalid_fields = PERF_OUTPUT_TRACE, }, @@ -110,7 +113,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO, + PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | + PERF_OUTPUT_PERIOD, .invalid_fields = PERF_OUTPUT_TRACE, }, @@ -184,10 +188,6 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP", PERF_OUTPUT_IP)) return -EINVAL; - - if (!no_callchain && - !(attr->sample_type & PERF_SAMPLE_CALLCHAIN)) - symbol_conf.use_callchain = false; } if (PRINT_FIELD(ADDR) && @@ -233,6 +233,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, PERF_OUTPUT_CPU)) return -EINVAL; + if (PRINT_FIELD(PERIOD) && + perf_evsel__check_stype(evsel, PERF_SAMPLE_PERIOD, "PERIOD", + PERF_OUTPUT_PERIOD)) + return -EINVAL; + return 0; } @@ -290,6 +295,19 @@ static int perf_session__check_output_opt(struct perf_session *session) set_print_ip_opts(&evsel->attr); } + if (!no_callchain) { + bool use_callchain = false; + + evlist__for_each(session->evlist, evsel) { + if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { + use_callchain = true; + break; + } + } + if (!use_callchain) + symbol_conf.use_callchain = false; + } + /* * set default for tracepoints to print symbols only * if callchains are present @@ -358,52 +376,19 @@ static void print_sample_start(struct perf_sample *sample, } } -static bool is_bts_event(struct perf_event_attr *attr) -{ - return ((attr->type == PERF_TYPE_HARDWARE) && - (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) && - (attr->sample_period == 1)); -} - -static bool sample_addr_correlates_sym(struct perf_event_attr *attr) -{ - if ((attr->type == PERF_TYPE_SOFTWARE) && - ((attr->config == PERF_COUNT_SW_PAGE_FAULTS) || - (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN) || - (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ))) - return true; - - if (is_bts_event(attr)) - return true; - - return false; -} - static void print_sample_addr(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct thread *thread, struct perf_event_attr *attr) { struct addr_location al; - u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; printf("%16" PRIx64, sample->addr); if (!sample_addr_correlates_sym(attr)) return; - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->addr, &al); - if (!al.map) - thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE, - sample->addr, &al); - - al.cpu = sample->cpu; - al.sym = NULL; - - if (al.map) - al.sym = map__find_symbol(al.map, al.addr, NULL); + perf_event__preprocess_sample_addr(event, sample, thread, &al); if (PRINT_FIELD(SYM)) { printf(" "); @@ -427,25 +412,35 @@ static void print_sample_bts(union perf_event *event, struct addr_location *al) { struct perf_event_attr *attr = &evsel->attr; + bool print_srcline_last = false; /* print branch_from information */ if (PRINT_FIELD(IP)) { - if (!symbol_conf.use_callchain) - printf(" "); - else + unsigned int print_opts = output[attr->type].print_ip_opts; + + if (symbol_conf.use_callchain && sample->callchain) { printf("\n"); - perf_evsel__print_ip(evsel, sample, al, - output[attr->type].print_ip_opts, + } else { + printf(" "); + if (print_opts & PRINT_IP_OPT_SRCLINE) { + print_srcline_last = true; + print_opts &= ~PRINT_IP_OPT_SRCLINE; + } + } + perf_evsel__print_ip(evsel, sample, al, print_opts, PERF_MAX_STACK_DEPTH); } - printf(" => "); - /* print branch_to information */ if (PRINT_FIELD(ADDR) || ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && - !output[attr->type].user_set)) - print_sample_addr(event, sample, al->machine, thread, attr); + !output[attr->type].user_set)) { + printf(" => "); + print_sample_addr(event, sample, thread, attr); + } + + if (print_srcline_last) + map__fprintf_srcline(al->map, al->addr, "\n ", stdout); printf("\n"); } @@ -461,6 +456,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample, print_sample_start(sample, thread, evsel); + if (PRINT_FIELD(PERIOD)) + printf("%10" PRIu64 " ", sample->period); + if (PRINT_FIELD(EVNAME)) { const char *evname = perf_evsel__name(evsel); printf("%s: ", evname ? evname : "[unknown]"); @@ -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) @@ -498,6 +496,11 @@ static int default_start_script(const char *script __maybe_unused, return 0; } +static int default_flush_script(void) +{ + return 0; +} + static int default_stop_script(void) { return 0; @@ -511,6 +514,7 @@ static int default_generate_script(struct pevent *pevent __maybe_unused, static struct scripting_ops default_scripting_ops = { .start_script = default_start_script, + .flush_script = default_flush_script, .stop_script = default_stop_script, .process_event = process_event, .generate_script = default_generate_script, @@ -526,6 +530,11 @@ static void setup_scripting(void) scripting_ops = &default_scripting_ops; } +static int flush_scripting(void) +{ + return scripting_ops->flush_script(); +} + static int cleanup_scripting(void) { pr_debug("\nperf script stopped\n"); @@ -574,7 +583,6 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, scripting_ops->process_event(event, sample, evsel, thread, &al); - evsel->hists.stats.total_period += sample->period; return 0; } @@ -1493,12 +1501,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) bool show_full_info = false; bool header = false; bool header_only = false; + bool script_started = false; char *rec_script_path = NULL; char *rep_script_path = NULL; struct perf_session *session; char *script_path = NULL; const char **__argv; - int i, j, err; + int i, j, err = 0; struct perf_script script = { .tool = { .sample = process_sample_event, @@ -1510,7 +1519,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .attr = process_attr, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, - .ordered_samples = true, + .ordered_events = true, .ordering_requires_timestamps = true, }, }; @@ -1545,7 +1554,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "comma separated output fields prepend with 'type:'. " "Valid types: hw,sw,trace,raw. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," - "addr,symoff", parse_output_fields), + "addr,symoff,period", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", @@ -1740,26 +1749,28 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) exit(-1); } - if (symbol__init() < 0) - return -1; if (!script_name) setup_pager(); session = perf_session__new(&file, false, &script.tool); if (session == NULL) - return -ENOMEM; + return -1; if (header || header_only) { perf_session__fprintf_info(session, stdout, show_full_info); if (header_only) - return 0; + goto out_delete; } + if (symbol__init(&session->header.env) < 0) + goto out_delete; + script.session = session; if (cpu_list) { - if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap)) - return -1; + err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap); + if (err < 0) + goto out_delete; } if (!no_callchain) @@ -1774,53 +1785,62 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) if (output_set_by_user()) { fprintf(stderr, "custom fields not supported for generated scripts"); - return -1; + err = -EINVAL; + goto out_delete; } input = open(file.path, O_RDONLY); /* input_name */ if (input < 0) { + err = -errno; perror("failed to open file"); - return -1; + goto out_delete; } err = fstat(input, &perf_stat); if (err < 0) { perror("failed to stat file"); - return -1; + goto out_delete; } if (!perf_stat.st_size) { fprintf(stderr, "zero-sized file, nothing to do!\n"); - return 0; + goto out_delete; } scripting_ops = script_spec__lookup(generate_script_lang); if (!scripting_ops) { fprintf(stderr, "invalid language specifier"); - return -1; + err = -ENOENT; + goto out_delete; } err = scripting_ops->generate_script(session->tevent.pevent, "perf-script"); - goto out; + goto out_delete; } if (script_name) { err = scripting_ops->start_script(script_name, argc, argv); if (err) - goto out; + goto out_delete; pr_debug("perf script started with script %s\n\n", script_name); + script_started = true; } err = perf_session__check_output_opt(session); if (err < 0) - goto out; + goto out_delete; err = __cmd_script(&script); + flush_scripting(); + +out_delete: perf_session__delete(session); - cleanup_scripting(); + + if (script_started) + cleanup_scripting(); out: return err; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 65a151e..8910863 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -43,6 +43,7 @@ #include "perf.h" #include "builtin.h" +#include "util/cgroup.h" #include "util/util.h" #include "util/parse-options.h" #include "util/parse-events.h" @@ -184,7 +185,7 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { evsel->priv = zalloc(sizeof(struct perf_stat)); - if (evsel == NULL) + if (evsel->priv == NULL) return -ENOMEM; perf_evsel__reset_stat_priv(evsel); return 0; @@ -387,20 +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]); @@ -423,16 +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; @@ -593,7 +681,7 @@ static int __run_perf_stat(int argc, const char **argv) if (perf_evlist__apply_filters(evsel_list)) { error("failed to set filter with %d (%s)\n", errno, - strerror(errno)); + strerror_r(errno, msg, sizeof(msg))); return -1; } @@ -732,7 +820,7 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr) } } -static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) +static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) { double msecs = avg / 1e6; const char *fmt_v, *fmt_n; @@ -741,7 +829,7 @@ static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) fmt_v = csv_output ? "%.6f%s" : "%18.6f%s"; fmt_n = csv_output ? "%s" : "%-25s"; - aggr_printout(evsel, cpu, nr); + aggr_printout(evsel, id, nr); scnprintf(name, sizeof(name), "%s%s", perf_evsel__name(evsel), csv_output ? "" : " (msec)"); @@ -947,11 +1035,12 @@ static void print_ll_cache_misses(int cpu, fprintf(output, " of all LL-cache hits "); } -static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) +static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) { double total, ratio = 0.0, total2; double sc = evsel->scale; const char *fmt; + int cpu = cpu_map__id_to_cpu(id); if (csv_output) { fmt = sc != 1.0 ? "%.2f%s" : "%.0f%s"; @@ -962,7 +1051,7 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s"; } - aggr_printout(evsel, cpu, nr); + aggr_printout(evsel, id, nr); if (aggr_mode == AGGR_GLOBAL) cpu = 0; diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 74db256..f3bb1a4 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -37,6 +37,7 @@ #include "util/svghelper.h" #include "util/tool.h" #include "util/data.h" +#include "util/debug.h" #define SUPPORT_OLD_POWER_EVENTS 1 #define PWR_EVENT_EXIT -1 @@ -60,10 +61,17 @@ struct timechart { tasks_only, with_backtrace, topology; + /* IO related settings */ + u64 io_events; + bool io_only, + skip_eagain; + u64 min_time, + merge_dist; }; struct per_pidcomm; struct cpu_sample; +struct io_sample; /* * Datastructure layout: @@ -84,6 +92,7 @@ struct per_pid { u64 start_time; u64 end_time; u64 total_time; + u64 total_bytes; int display; struct per_pidcomm *all; @@ -97,6 +106,8 @@ struct per_pidcomm { u64 start_time; u64 end_time; u64 total_time; + u64 max_bytes; + u64 total_bytes; int Y; int display; @@ -107,6 +118,7 @@ struct per_pidcomm { char *comm; struct cpu_sample *samples; + struct io_sample *io_samples; }; struct sample_wrapper { @@ -131,6 +143,27 @@ struct cpu_sample { const char *backtrace; }; +enum { + IOTYPE_READ, + IOTYPE_WRITE, + IOTYPE_SYNC, + IOTYPE_TX, + IOTYPE_RX, + IOTYPE_POLL, +}; + +struct io_sample { + struct io_sample *next; + + u64 start_time; + u64 end_time; + u64 bytes; + int type; + int fd; + int err; + int merges; +}; + #define CSTATE 1 #define PSTATE 2 @@ -213,7 +246,7 @@ static void pid_fork(struct timechart *tchart, int pid, int ppid, u64 timestamp) pid_set_comm(tchart, pid, pp->current->comm); p->start_time = timestamp; - if (p->current) { + if (p->current && !p->current->start_time) { p->current->start_time = timestamp; p->current->state_since = timestamp; } @@ -495,7 +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) @@ -682,6 +715,249 @@ static void end_sample_processing(struct timechart *tchart) } } +static int pid_begin_io_sample(struct timechart *tchart, int pid, int type, + u64 start, int fd) +{ + struct per_pid *p = find_create_pid(tchart, pid); + struct per_pidcomm *c = p->current; + struct io_sample *sample; + struct io_sample *prev; + + if (!c) { + c = zalloc(sizeof(*c)); + if (!c) + return -ENOMEM; + p->current = c; + c->next = p->all; + p->all = c; + } + + prev = c->io_samples; + + if (prev && prev->start_time && !prev->end_time) { + pr_warning("Skip invalid start event: " + "previous event already started!\n"); + + /* remove previous event that has been started, + * we are not sure we will ever get an end for it */ + c->io_samples = prev->next; + free(prev); + return 0; + } + + sample = zalloc(sizeof(*sample)); + if (!sample) + return -ENOMEM; + sample->start_time = start; + sample->type = type; + sample->fd = fd; + sample->next = c->io_samples; + c->io_samples = sample; + + if (c->start_time == 0 || c->start_time > start) + c->start_time = start; + + return 0; +} + +static int pid_end_io_sample(struct timechart *tchart, int pid, int type, + u64 end, long ret) +{ + struct per_pid *p = find_create_pid(tchart, pid); + struct per_pidcomm *c = p->current; + struct io_sample *sample, *prev; + + if (!c) { + pr_warning("Invalid pidcomm!\n"); + return -1; + } + + sample = c->io_samples; + + if (!sample) /* skip partially captured events */ + return 0; + + if (sample->end_time) { + pr_warning("Skip invalid end event: " + "previous event already ended!\n"); + return 0; + } + + if (sample->type != type) { + pr_warning("Skip invalid end event: invalid event type!\n"); + return 0; + } + + sample->end_time = end; + prev = sample->next; + + /* we want to be able to see small and fast transfers, so make them + * at least min_time long, but don't overlap them */ + if (sample->end_time - sample->start_time < tchart->min_time) + sample->end_time = sample->start_time + tchart->min_time; + if (prev && sample->start_time < prev->end_time) { + if (prev->err) /* try to make errors more visible */ + sample->start_time = prev->end_time; + else + prev->end_time = sample->start_time; + } + + if (ret < 0) { + sample->err = ret; + } else if (type == IOTYPE_READ || type == IOTYPE_WRITE || + type == IOTYPE_TX || type == IOTYPE_RX) { + + if ((u64)ret > c->max_bytes) + c->max_bytes = ret; + + c->total_bytes += ret; + p->total_bytes += ret; + sample->bytes = ret; + } + + /* merge two requests to make svg smaller and render-friendly */ + if (prev && + prev->type == sample->type && + prev->err == sample->err && + prev->fd == sample->fd && + prev->end_time + tchart->merge_dist >= sample->start_time) { + + sample->bytes += prev->bytes; + sample->merges += prev->merges + 1; + + sample->start_time = prev->start_time; + sample->next = prev->next; + free(prev); + + if (!sample->err && sample->bytes > c->max_bytes) + c->max_bytes = sample->bytes; + } + + tchart->io_events++; + + return 0; +} + +static int +process_enter_read(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_READ, + sample->time, fd); +} + +static int +process_exit_read(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_READ, + sample->time, ret); +} + +static int +process_enter_write(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_WRITE, + sample->time, fd); +} + +static int +process_exit_write(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_WRITE, + sample->time, ret); +} + +static int +process_enter_sync(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_SYNC, + sample->time, fd); +} + +static int +process_exit_sync(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_SYNC, + sample->time, ret); +} + +static int +process_enter_tx(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_TX, + sample->time, fd); +} + +static int +process_exit_tx(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_TX, + sample->time, ret); +} + +static int +process_enter_rx(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_RX, + sample->time, fd); +} + +static int +process_exit_rx(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_RX, + sample->time, ret); +} + +static int +process_enter_poll(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long fd = perf_evsel__intval(evsel, sample, "fd"); + return pid_begin_io_sample(tchart, sample->tid, IOTYPE_POLL, + sample->time, fd); +} + +static int +process_exit_poll(struct timechart *tchart, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + long ret = perf_evsel__intval(evsel, sample, "ret"); + return pid_end_io_sample(tchart, sample->tid, IOTYPE_POLL, + sample->time, ret); +} + /* * Sort the pid datastructure */ @@ -852,6 +1128,121 @@ static void draw_cpu_usage(struct timechart *tchart) } } +static void draw_io_bars(struct timechart *tchart) +{ + const char *suf; + double bytes; + char comm[256]; + struct per_pid *p; + struct per_pidcomm *c; + struct io_sample *sample; + int Y = 1; + + p = tchart->all_data; + while (p) { + c = p->all; + while (c) { + if (!c->display) { + c->Y = 0; + c = c->next; + continue; + } + + svg_box(Y, c->start_time, c->end_time, "process3"); + sample = c->io_samples; + for (sample = c->io_samples; sample; sample = sample->next) { + double h = (double)sample->bytes / c->max_bytes; + + if (tchart->skip_eagain && + sample->err == -EAGAIN) + continue; + + if (sample->err) + h = 1; + + if (sample->type == IOTYPE_SYNC) + svg_fbox(Y, + sample->start_time, + sample->end_time, + 1, + sample->err ? "error" : "sync", + sample->fd, + sample->err, + sample->merges); + else if (sample->type == IOTYPE_POLL) + svg_fbox(Y, + sample->start_time, + sample->end_time, + 1, + sample->err ? "error" : "poll", + sample->fd, + sample->err, + sample->merges); + else if (sample->type == IOTYPE_READ) + svg_ubox(Y, + sample->start_time, + sample->end_time, + h, + sample->err ? "error" : "disk", + sample->fd, + sample->err, + sample->merges); + else if (sample->type == IOTYPE_WRITE) + svg_lbox(Y, + sample->start_time, + sample->end_time, + h, + sample->err ? "error" : "disk", + sample->fd, + sample->err, + sample->merges); + else if (sample->type == IOTYPE_RX) + svg_ubox(Y, + sample->start_time, + sample->end_time, + h, + sample->err ? "error" : "net", + sample->fd, + sample->err, + sample->merges); + else if (sample->type == IOTYPE_TX) + svg_lbox(Y, + sample->start_time, + sample->end_time, + h, + sample->err ? "error" : "net", + sample->fd, + sample->err, + sample->merges); + } + + suf = ""; + bytes = c->total_bytes; + if (bytes > 1024) { + bytes = bytes / 1024; + suf = "K"; + } + if (bytes > 1024) { + bytes = bytes / 1024; + suf = "M"; + } + if (bytes > 1024) { + bytes = bytes / 1024; + suf = "G"; + } + + + sprintf(comm, "%s:%i (%3.1f %sbytes)", c->comm ?: "", p->pid, bytes, suf); + svg_text(Y, c->start_time, comm); + + c->Y = Y; + Y++; + c = c->next; + } + p = p->next; + } +} + static void draw_process_bars(struct timechart *tchart) { struct per_pid *p; @@ -987,9 +1378,6 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold) struct per_pidcomm *c; int count = 0; - if (process_filter) - return determine_display_tasks_filtered(tchart); - p = tchart->all_data; while (p) { p->display = 0; @@ -1025,15 +1413,46 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold) return count; } +static int determine_display_io_tasks(struct timechart *timechart, u64 threshold) +{ + struct per_pid *p; + struct per_pidcomm *c; + int count = 0; + p = timechart->all_data; + while (p) { + /* no exit marker, task kept running to the end */ + if (p->end_time == 0) + p->end_time = timechart->last_time; + + c = p->all; + while (c) { + c->display = 0; + + if (c->total_bytes >= threshold) { + c->display = 1; + count++; + } + + if (c->end_time == 0) + c->end_time = timechart->last_time; + + c = c->next; + } + p = p->next; + } + return count; +} + +#define BYTES_THRESH (1 * 1024 * 1024) #define TIME_THRESH 10000000 static void write_svg_file(struct timechart *tchart, const char *filename) { u64 i; int count; - int thresh = TIME_THRESH; + int thresh = tchart->io_events ? BYTES_THRESH : TIME_THRESH; if (tchart->power_only) tchart->proc_num = 0; @@ -1041,28 +1460,43 @@ static void write_svg_file(struct timechart *tchart, const char *filename) /* We'd like to show at least proc_num tasks; * be less picky if we have fewer */ do { - count = determine_display_tasks(tchart, thresh); + if (process_filter) + count = determine_display_tasks_filtered(tchart); + else if (tchart->io_events) + count = determine_display_io_tasks(tchart, thresh); + else + count = determine_display_tasks(tchart, thresh); thresh /= 10; } while (!process_filter && thresh && count < tchart->proc_num); if (!tchart->proc_num) count = 0; - open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time); + if (tchart->io_events) { + open_svg(filename, 0, count, tchart->first_time, tchart->last_time); + + svg_time_grid(0.5); + svg_io_legenda(); - svg_time_grid(); - svg_legenda(); + draw_io_bars(tchart); + } else { + open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time); + + svg_time_grid(0); - for (i = 0; i < tchart->numcpus; i++) - svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency); + svg_legenda(); - draw_cpu_usage(tchart); - if (tchart->proc_num) - draw_process_bars(tchart); - if (!tchart->tasks_only) - draw_c_p_states(tchart); - if (tchart->proc_num) - draw_wakeups(tchart); + for (i = 0; i < tchart->numcpus; i++) + svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency); + + draw_cpu_usage(tchart); + if (tchart->proc_num) + draw_process_bars(tchart); + if (!tchart->tasks_only) + draw_c_p_states(tchart); + if (tchart->proc_num) + draw_wakeups(tchart); + } svg_close(); } @@ -1110,6 +1544,56 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name) { "power:power_end", process_sample_power_end }, { "power:power_frequency", process_sample_power_frequency }, #endif + + { "syscalls:sys_enter_read", process_enter_read }, + { "syscalls:sys_enter_pread64", process_enter_read }, + { "syscalls:sys_enter_readv", process_enter_read }, + { "syscalls:sys_enter_preadv", process_enter_read }, + { "syscalls:sys_enter_write", process_enter_write }, + { "syscalls:sys_enter_pwrite64", process_enter_write }, + { "syscalls:sys_enter_writev", process_enter_write }, + { "syscalls:sys_enter_pwritev", process_enter_write }, + { "syscalls:sys_enter_sync", process_enter_sync }, + { "syscalls:sys_enter_sync_file_range", process_enter_sync }, + { "syscalls:sys_enter_fsync", process_enter_sync }, + { "syscalls:sys_enter_msync", process_enter_sync }, + { "syscalls:sys_enter_recvfrom", process_enter_rx }, + { "syscalls:sys_enter_recvmmsg", process_enter_rx }, + { "syscalls:sys_enter_recvmsg", process_enter_rx }, + { "syscalls:sys_enter_sendto", process_enter_tx }, + { "syscalls:sys_enter_sendmsg", process_enter_tx }, + { "syscalls:sys_enter_sendmmsg", process_enter_tx }, + { "syscalls:sys_enter_epoll_pwait", process_enter_poll }, + { "syscalls:sys_enter_epoll_wait", process_enter_poll }, + { "syscalls:sys_enter_poll", process_enter_poll }, + { "syscalls:sys_enter_ppoll", process_enter_poll }, + { "syscalls:sys_enter_pselect6", process_enter_poll }, + { "syscalls:sys_enter_select", process_enter_poll }, + + { "syscalls:sys_exit_read", process_exit_read }, + { "syscalls:sys_exit_pread64", process_exit_read }, + { "syscalls:sys_exit_readv", process_exit_read }, + { "syscalls:sys_exit_preadv", process_exit_read }, + { "syscalls:sys_exit_write", process_exit_write }, + { "syscalls:sys_exit_pwrite64", process_exit_write }, + { "syscalls:sys_exit_writev", process_exit_write }, + { "syscalls:sys_exit_pwritev", process_exit_write }, + { "syscalls:sys_exit_sync", process_exit_sync }, + { "syscalls:sys_exit_sync_file_range", process_exit_sync }, + { "syscalls:sys_exit_fsync", process_exit_sync }, + { "syscalls:sys_exit_msync", process_exit_sync }, + { "syscalls:sys_exit_recvfrom", process_exit_rx }, + { "syscalls:sys_exit_recvmmsg", process_exit_rx }, + { "syscalls:sys_exit_recvmsg", process_exit_rx }, + { "syscalls:sys_exit_sendto", process_exit_tx }, + { "syscalls:sys_exit_sendmsg", process_exit_tx }, + { "syscalls:sys_exit_sendmmsg", process_exit_tx }, + { "syscalls:sys_exit_epoll_pwait", process_exit_poll }, + { "syscalls:sys_exit_epoll_wait", process_exit_poll }, + { "syscalls:sys_exit_poll", process_exit_poll }, + { "syscalls:sys_exit_ppoll", process_exit_poll }, + { "syscalls:sys_exit_pselect6", process_exit_poll }, + { "syscalls:sys_exit_select", process_exit_poll }, }; struct perf_data_file file = { .path = input_name, @@ -1121,7 +1605,9 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name) int ret = -EINVAL; if (session == NULL) - return -ENOMEM; + return -1; + + symbol__init(&session->header.env); (void)perf_header__process_sections(&session->header, perf_data_file__fd(session->file), @@ -1154,6 +1640,139 @@ out_delete: return ret; } +static int timechart__io_record(int argc, const char **argv) +{ + unsigned int rec_argc, i; + const char **rec_argv; + const char **p; + char *filter = NULL; + + const char * const common_args[] = { + "record", "-a", "-R", "-c", "1", + }; + unsigned int common_args_nr = ARRAY_SIZE(common_args); + + const char * const disk_events[] = { + "syscalls:sys_enter_read", + "syscalls:sys_enter_pread64", + "syscalls:sys_enter_readv", + "syscalls:sys_enter_preadv", + "syscalls:sys_enter_write", + "syscalls:sys_enter_pwrite64", + "syscalls:sys_enter_writev", + "syscalls:sys_enter_pwritev", + "syscalls:sys_enter_sync", + "syscalls:sys_enter_sync_file_range", + "syscalls:sys_enter_fsync", + "syscalls:sys_enter_msync", + + "syscalls:sys_exit_read", + "syscalls:sys_exit_pread64", + "syscalls:sys_exit_readv", + "syscalls:sys_exit_preadv", + "syscalls:sys_exit_write", + "syscalls:sys_exit_pwrite64", + "syscalls:sys_exit_writev", + "syscalls:sys_exit_pwritev", + "syscalls:sys_exit_sync", + "syscalls:sys_exit_sync_file_range", + "syscalls:sys_exit_fsync", + "syscalls:sys_exit_msync", + }; + unsigned int disk_events_nr = ARRAY_SIZE(disk_events); + + const char * const net_events[] = { + "syscalls:sys_enter_recvfrom", + "syscalls:sys_enter_recvmmsg", + "syscalls:sys_enter_recvmsg", + "syscalls:sys_enter_sendto", + "syscalls:sys_enter_sendmsg", + "syscalls:sys_enter_sendmmsg", + + "syscalls:sys_exit_recvfrom", + "syscalls:sys_exit_recvmmsg", + "syscalls:sys_exit_recvmsg", + "syscalls:sys_exit_sendto", + "syscalls:sys_exit_sendmsg", + "syscalls:sys_exit_sendmmsg", + }; + unsigned int net_events_nr = ARRAY_SIZE(net_events); + + const char * const poll_events[] = { + "syscalls:sys_enter_epoll_pwait", + "syscalls:sys_enter_epoll_wait", + "syscalls:sys_enter_poll", + "syscalls:sys_enter_ppoll", + "syscalls:sys_enter_pselect6", + "syscalls:sys_enter_select", + + "syscalls:sys_exit_epoll_pwait", + "syscalls:sys_exit_epoll_wait", + "syscalls:sys_exit_poll", + "syscalls:sys_exit_ppoll", + "syscalls:sys_exit_pselect6", + "syscalls:sys_exit_select", + }; + unsigned int poll_events_nr = ARRAY_SIZE(poll_events); + + rec_argc = common_args_nr + + disk_events_nr * 4 + + net_events_nr * 4 + + poll_events_nr * 4 + + argc; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + + if (rec_argv == NULL) + return -ENOMEM; + + if (asprintf(&filter, "common_pid != %d", getpid()) < 0) + return -ENOMEM; + + p = rec_argv; + for (i = 0; i < common_args_nr; i++) + *p++ = strdup(common_args[i]); + + for (i = 0; i < disk_events_nr; i++) { + if (!is_valid_tracepoint(disk_events[i])) { + rec_argc -= 4; + continue; + } + + *p++ = "-e"; + *p++ = strdup(disk_events[i]); + *p++ = "--filter"; + *p++ = filter; + } + for (i = 0; i < net_events_nr; i++) { + if (!is_valid_tracepoint(net_events[i])) { + rec_argc -= 4; + continue; + } + + *p++ = "-e"; + *p++ = strdup(net_events[i]); + *p++ = "--filter"; + *p++ = filter; + } + for (i = 0; i < poll_events_nr; i++) { + if (!is_valid_tracepoint(poll_events[i])) { + rec_argc -= 4; + continue; + } + + *p++ = "-e"; + *p++ = strdup(poll_events[i]); + *p++ = "--filter"; + *p++ = filter; + } + + for (i = 0; i < (unsigned int)argc; i++) + *p++ = argv[i]; + + return cmd_record(rec_argc, rec_argv, NULL); +} + + static int timechart__record(struct timechart *tchart, int argc, const char **argv) { unsigned int rec_argc, i, j; @@ -1270,6 +1889,30 @@ parse_highlight(const struct option *opt __maybe_unused, const char *arg, return 0; } +static int +parse_time(const struct option *opt, const char *arg, int __maybe_unused unset) +{ + char unit = 'n'; + u64 *value = opt->value; + + if (sscanf(arg, "%" PRIu64 "%cs", value, &unit) > 0) { + switch (unit) { + case 'm': + *value *= 1000000; + break; + case 'u': + *value *= 1000; + break; + case 'n': + break; + default: + return -1; + } + } + + return 0; +} + int cmd_timechart(int argc, const char **argv, const char *prefix __maybe_unused) { @@ -1279,9 +1922,11 @@ int cmd_timechart(int argc, const char **argv, .fork = process_fork_event, .exit = process_exit_event, .sample = process_sample_event, - .ordered_samples = true, + .ordered_events = true, }, .proc_num = 15, + .min_time = 1000000, + .merge_dist = 1000, }; const char *output_name = "output.svg"; const struct option timechart_options[] = { @@ -1303,6 +1948,14 @@ int cmd_timechart(int argc, const char **argv, "min. number of tasks to print"), OPT_BOOLEAN('t', "topology", &tchart.topology, "sort CPUs according to topology"), + OPT_BOOLEAN(0, "io-skip-eagain", &tchart.skip_eagain, + "skip EAGAIN errors"), + OPT_CALLBACK(0, "io-min-time", &tchart.min_time, "time", + "all IO faster than min-time will visually appear longer", + parse_time), + OPT_CALLBACK(0, "io-merge-dist", &tchart.merge_dist, "time", + "merge events that are merge-dist us apart", + parse_time), OPT_END() }; const char * const timechart_usage[] = { @@ -1310,14 +1963,16 @@ 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"), + OPT_BOOLEAN('I', "io-only", &tchart.io_only, + "record only IO data"), 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 }; @@ -1329,10 +1984,9 @@ int cmd_timechart(int argc, const char **argv, return -1; } - symbol__init(); - 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) { @@ -1340,7 +1994,10 @@ int cmd_timechart(int argc, const char **argv, return -1; } - return timechart__record(&tchart, argc, argv); + if (tchart.io_only) + return timechart__io_record(argc, argv); + else + return timechart__record(&tchart, argc, argv); } else if (argc) usage_with_options(timechart_usage, timechart_options); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 377971d..0aa7747 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -59,7 +59,7 @@ #include <sys/syscall.h> #include <sys/ioctl.h> -#include <sys/poll.h> +#include <poll.h> #include <sys/prctl.h> #include <sys/wait.h> #include <sys/uio.h> @@ -251,6 +251,7 @@ static void perf_top__print_sym_table(struct perf_top *top) char bf[160]; int printed = 0; const int win_width = top->winsize.ws_col - 1; + struct hists *hists = evsel__hists(top->sym_evsel); puts(CONSOLE_CLEAR); @@ -261,13 +262,13 @@ static void perf_top__print_sym_table(struct perf_top *top) printf("%-*.*s\n", win_width, win_width, graph_dotted_line); - if (top->sym_evsel->hists.stats.nr_lost_warned != - top->sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST]) { - top->sym_evsel->hists.stats.nr_lost_warned = - top->sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST]; + if (hists->stats.nr_lost_warned != + hists->stats.nr_events[PERF_RECORD_LOST]) { + hists->stats.nr_lost_warned = + hists->stats.nr_events[PERF_RECORD_LOST]; color_fprintf(stdout, PERF_COLOR_RED, "WARNING: LOST %d chunks, Check IO/CPU overload", - top->sym_evsel->hists.stats.nr_lost_warned); + hists->stats.nr_lost_warned); ++printed; } @@ -276,16 +277,19 @@ static void perf_top__print_sym_table(struct perf_top *top) return; } - hists__collapse_resort(&top->sym_evsel->hists, NULL); - hists__output_resort(&top->sym_evsel->hists); - hists__decay_entries(&top->sym_evsel->hists, - top->hide_user_symbols, - top->hide_kernel_symbols); - hists__output_recalc_col_len(&top->sym_evsel->hists, - top->print_entries - printed); + if (top->zero) { + hists__delete_entries(hists); + } else { + hists__decay_entries(hists, top->hide_user_symbols, + top->hide_kernel_symbols); + } + + hists__collapse_resort(hists, NULL); + hists__output_resort(hists); + + hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); - hists__fprintf(&top->sym_evsel->hists, false, - top->print_entries - printed, win_width, + hists__fprintf(hists, false, top->print_entries - printed, win_width, top->min_percent, stdout); } @@ -328,6 +332,7 @@ static void perf_top__prompt_symbol(struct perf_top *top, const char *msg) { char *buf = malloc(0), *p; struct hist_entry *syme = top->sym_filter_entry, *n, *found = NULL; + struct hists *hists = evsel__hists(top->sym_evsel); struct rb_node *next; size_t dummy = 0; @@ -345,7 +350,7 @@ static void perf_top__prompt_symbol(struct perf_top *top, const char *msg) if (p) *p = 0; - next = rb_first(&top->sym_evsel->hists.entries); + next = rb_first(&hists->entries); while (next) { n = rb_entry(next, struct hist_entry, rb_node); if (n->ms.sym && !strcmp(buf, n->ms.sym->name)) { @@ -427,18 +432,13 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) if (!perf_top__key_mapped(top, c)) { struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; - struct termios tc, save; + struct termios save; perf_top__print_mapped_keys(top); fprintf(stdout, "\nEnter selection, or unmapped key to continue: "); fflush(stdout); - tcgetattr(0, &save); - tc = save; - tc.c_lflag &= ~(ICANON | ECHO); - tc.c_cc[VMIN] = 0; - tc.c_cc[VTIME] = 0; - tcsetattr(0, TCSANOW, &tc); + set_term_quiet_input(&save); poll(&stdin_poll, 1, -1); c = getc(stdin); @@ -537,16 +537,24 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) static void perf_top__sort_new_samples(void *arg) { struct perf_top *t = arg; + struct hists *hists; + perf_top__reset_sample_counters(t); if (t->evlist->selected != NULL) t->sym_evsel = t->evlist->selected; - hists__collapse_resort(&t->sym_evsel->hists, NULL); - hists__output_resort(&t->sym_evsel->hists); - hists__decay_entries(&t->sym_evsel->hists, - t->hide_user_symbols, - t->hide_kernel_symbols); + hists = evsel__hists(t->sym_evsel); + + if (t->zero) { + hists__delete_entries(hists); + } else { + hists__decay_entries(hists, t->hide_user_symbols, + t->hide_kernel_symbols); + } + + hists__collapse_resort(hists, NULL); + hists__output_resort(hists); } static void *display_thread_tui(void *arg) @@ -567,8 +575,10 @@ static void *display_thread_tui(void *arg) * Zooming in/out UIDs. For now juse use whatever the user passed * via --uid. */ - evlist__for_each(top->evlist, pos) - pos->hists.uid_filter_str = top->record_opts.target.uid_str; + evlist__for_each(top->evlist, pos) { + struct hists *hists = evsel__hists(pos); + hists->uid_filter_str = top->record_opts.target.uid_str; + } perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, &top->session->header.env); @@ -577,23 +587,32 @@ static void *display_thread_tui(void *arg) return NULL; } +static void display_sig(int sig __maybe_unused) +{ + done = 1; +} + +static void display_setup_sig(void) +{ + signal(SIGSEGV, display_sig); + signal(SIGFPE, display_sig); + signal(SIGINT, display_sig); + signal(SIGQUIT, display_sig); + signal(SIGTERM, display_sig); +} + static void *display_thread(void *arg) { struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; - struct termios tc, save; + struct termios save; struct perf_top *top = arg; int delay_msecs, c; - tcgetattr(0, &save); - tc = save; - tc.c_lflag &= ~(ICANON | ECHO); - tc.c_cc[VMIN] = 0; - tc.c_cc[VTIME] = 0; - + display_setup_sig(); pthread__unblock_sigwinch(); repeat: delay_msecs = top->delay_secs * 1000; - tcsetattr(0, TCSANOW, &tc); + set_term_quiet_input(&save); /* trash return*/ getc(stdin); @@ -620,13 +639,16 @@ repeat: } } + tcsetattr(0, TCSAFLUSH, &save); return NULL; } -static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym) +static int symbol_filter(struct map *map, struct symbol *sym) { const char *name = sym->name; + if (!map->dso->kernel) + return 0; /* * ppc64 uses function descriptors and appends a '.' to the * start of every instruction address. Remove it. @@ -750,6 +772,7 @@ static void perf_event__process_sample(struct perf_tool *tool, } if (al.sym == NULL || !al.sym->ignore) { + struct hists *hists = evsel__hists(evsel); struct hist_entry_iter iter = { .add_entry_cb = hist_iter__top_callback, }; @@ -759,14 +782,14 @@ static void perf_event__process_sample(struct perf_tool *tool, else iter.ops = &hist_iter_normal; - pthread_mutex_lock(&evsel->hists.lock); + pthread_mutex_lock(&hists->lock); err = hist_entry_iter__add(&iter, &al, evsel, sample, top->max_stack, top); if (err < 0) pr_err("Problem incrementing symbol period, skipping event\n"); - pthread_mutex_unlock(&evsel->hists.lock); + pthread_mutex_unlock(&hists->lock); } return; @@ -831,7 +854,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) perf_event__process_sample(&top->tool, event, evsel, &sample, machine); } else if (event->header.type < PERF_RECORD_MAX) { - hists__inc_nr_events(&evsel->hists, event->header.type); + hists__inc_nr_events(evsel__hists(evsel), event->header.type); machine__process_event(machine, event, &sample); } else ++session->stats.nr_unknown_events; @@ -876,7 +899,7 @@ try_again: if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) { ui__error("Failed to mmap with %d (%s)\n", - errno, strerror(errno)); + errno, strerror_r(errno, msg, sizeof(msg))); goto out_err; } @@ -911,7 +934,7 @@ static int __cmd_top(struct perf_top *top) top->session = perf_session__new(NULL, false, NULL); if (top->session == NULL) - return -ENOMEM; + return -1; machines__set_symbol_filter(&top->session->machines, symbol_filter); @@ -946,7 +969,7 @@ static int __cmd_top(struct perf_top *top) perf_evlist__enable(top->evlist); /* Wait for a minimal set of events before starting the snapshot */ - poll(top->evlist->pollfd, top->evlist->nr_fds, 100); + perf_evlist__poll(top->evlist, 100); perf_top__mmap_read(top); @@ -963,7 +986,7 @@ static int __cmd_top(struct perf_top *top) param.sched_priority = top->realtime_prio; if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { ui__error("Could not set realtime priority.\n"); - goto out_delete; + goto out_join; } } @@ -973,10 +996,12 @@ static int __cmd_top(struct perf_top *top) perf_top__mmap_read(top); if (hits == top->samples) - ret = poll(top->evlist->pollfd, top->evlist->nr_fds, 100); + ret = perf_evlist__poll(top->evlist, 100); } ret = 0; +out_join: + pthread_join(thread, NULL); out_delete: perf_session__delete(top->session); top->session = NULL; @@ -1000,10 +1025,8 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) static int perf_top_config(const char *var, const char *value, void *cb) { - struct perf_top *top = cb; - if (!strcmp(var, "top.call-graph")) - return record_parse_callchain(value, &top->record_opts); + var = "call-graph.record-mode"; /* fall-through */ if (!strcmp(var, "top.children")) { symbol_conf.cumulate_callchain = perf_config_bool(var, value); return 0; @@ -1024,7 +1047,6 @@ parse_percent_limit(const struct option *opt, const char *arg, int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) { - int status = -1; char errbuf[BUFSIZ]; struct perf_top top = { .count_filter = 5, @@ -1122,6 +1144,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "Interleave source code with assembly code (default)"), OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw, "Display raw encoding of assembly instructions (default)"), + OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, + "Enable kernel symbol demangling"), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", @@ -1131,12 +1155,19 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "Don't show entries under that percent", parse_percent_limit), OPT_CALLBACK(0, "percentage", NULL, "relative|absolute", "How to display percentage of filtered entries", parse_filter_percentage), + OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str, + "width[,width...]", + "don't try to adjust column width, use these fixed values"), OPT_END() }; const char * const top_usage[] = { "perf top [<options>]", NULL }; + int status = hists__init(); + + if (status < 0) + return status; top.evlist = perf_evlist__new(); if (top.evlist == NULL) @@ -1217,7 +1248,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) symbol_conf.priv_size = sizeof(struct annotation); symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); - if (symbol__init() < 0) + if (symbol__init(NULL) < 0) return -1; sort__setup_elide(stdout); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f954c26..badfabc 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -402,6 +402,31 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags +static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_MREMAP_FLAG(n) \ + if (flags & MREMAP_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~MREMAP_##n; \ + } + + P_MREMAP_FLAG(MAYMOVE); +#ifdef MREMAP_FIXED + P_MREMAP_FLAG(FIXED); +#endif +#undef P_MREMAP_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags + static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size, struct syscall_arg *arg) { @@ -1004,6 +1029,7 @@ static struct syscall_fmt { [2] = SCA_MMAP_PROT, /* prot */ }, }, { .name = "mremap", .hexret = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ + [3] = SCA_MREMAP_FLAGS, /* flags */ [4] = SCA_HEX, /* new_addr */ }, }, { .name = "munlock", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, @@ -1108,6 +1134,7 @@ struct syscall { struct event_format *tp_format; const char *name; bool filtered; + bool is_exit; struct syscall_fmt *fmt; size_t (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg); void **arg_parm; @@ -1132,6 +1159,7 @@ struct thread_trace { u64 exit_time; bool entry_pending; unsigned long nr_events; + unsigned long pfmaj, pfmin; char *entry_str; double runtime_ms; struct { @@ -1161,13 +1189,13 @@ static struct thread_trace *thread__trace(struct thread *thread, FILE *fp) if (thread == NULL) goto fail; - if (thread->priv == NULL) - thread->priv = thread_trace__new(); + if (thread__priv(thread) == NULL) + thread__set_priv(thread, thread_trace__new()); - if (thread->priv == NULL) + if (thread__priv(thread) == NULL) goto fail; - ttrace = thread->priv; + ttrace = thread__priv(thread); ++ttrace->nr_events; return ttrace; @@ -1177,6 +1205,9 @@ fail: return NULL; } +#define TRACE_PFMAJ (1 << 0) +#define TRACE_PFMIN (1 << 1) + struct trace { struct perf_tool tool; struct { @@ -1211,11 +1242,13 @@ struct trace { bool summary_only; bool show_comm; bool show_tool_stats; + bool trace_syscalls; + int trace_pgfaults; }; static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname) { - struct thread_trace *ttrace = thread->priv; + struct thread_trace *ttrace = thread__priv(thread); if (fd > ttrace->paths.max) { char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *)); @@ -1268,7 +1301,7 @@ static int thread__read_fd_path(struct thread *thread, int fd) static const char *thread__fd_path(struct thread *thread, int fd, struct trace *trace) { - struct thread_trace *ttrace = thread->priv; + struct thread_trace *ttrace = thread__priv(thread); if (ttrace == NULL) return NULL; @@ -1276,11 +1309,11 @@ static const char *thread__fd_path(struct thread *thread, int fd, if (fd < 0) return NULL; - if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) + if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) { if (!trace->live) return NULL; ++trace->stats.proc_getname; - if (thread__read_fd_path(thread, fd)) { + if (thread__read_fd_path(thread, fd)) return NULL; } @@ -1305,7 +1338,7 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size, { int fd = arg->val; size_t printed = syscall_arg__scnprintf_fd(bf, size, arg); - struct thread_trace *ttrace = arg->thread->priv; + struct thread_trace *ttrace = thread__priv(arg->thread); if (ttrace && fd >= 0 && fd <= ttrace->paths.max) zfree(&ttrace->paths.table[fd]); @@ -1378,7 +1411,7 @@ static int trace__tool_process(struct perf_tool *tool, static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) { - int err = symbol__init(); + int err = symbol__init(NULL); if (err) return err; @@ -1473,6 +1506,8 @@ static int trace__read_syscall_info(struct trace *trace, int id) if (sc->tp_format == NULL) return -1; + sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit"); + return syscall__set_arg_fmts(sc); } @@ -1535,6 +1570,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, } typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event, struct perf_sample *sample); static struct syscall *trace__syscall_info(struct trace *trace, @@ -1607,6 +1643,7 @@ static void thread__update_stats(struct thread_trace *ttrace, } static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event __maybe_unused, struct perf_sample *sample) { char *msg; @@ -1629,7 +1666,6 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, return -1; args = perf_evsel__sc_tp_ptr(evsel, args, sample); - ttrace = thread->priv; if (ttrace->entry_str == NULL) { ttrace->entry_str = malloc(1024); @@ -1644,7 +1680,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed, args, trace, thread); - if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) { + if (sc->is_exit) { if (!trace->duration_filter && !trace->summary_only) { trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output); fprintf(trace->output, "%-70s\n", ttrace->entry_str); @@ -1656,9 +1692,10 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, } static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event __maybe_unused, struct perf_sample *sample) { - int ret; + long ret; u64 duration = 0; struct thread *thread; int id = perf_evsel__sc_tp_uint(evsel, id, sample); @@ -1687,8 +1724,6 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, ++trace->stats.vfs_getname; } - ttrace = thread->priv; - ttrace->exit_time = sample->time; if (ttrace->entry_time) { @@ -1713,9 +1748,9 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, if (sc->fmt == NULL) { signed_print: - fprintf(trace->output, ") = %d", ret); + fprintf(trace->output, ") = %ld", ret); } else if (ret < 0 && sc->fmt->errmsg) { - char bf[256]; + char bf[STRERR_BUFSIZE]; const char *emsg = strerror_r(-ret, bf, sizeof(bf)), *e = audit_errno_to_name(-ret); @@ -1723,7 +1758,7 @@ signed_print: } else if (ret == 0 && sc->fmt->timeout) fprintf(trace->output, ") = 0 Timeout"); else if (sc->fmt->hexret) - fprintf(trace->output, ") = %#x", ret); + fprintf(trace->output, ") = %#lx", ret); else goto signed_print; @@ -1735,6 +1770,7 @@ out: } static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event __maybe_unused, struct perf_sample *sample) { trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname"); @@ -1742,6 +1778,7 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, } static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event __maybe_unused, struct perf_sample *sample) { u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); @@ -1768,6 +1805,80 @@ out_dump: return 0; } +static void print_location(FILE *f, struct perf_sample *sample, + struct addr_location *al, + bool print_dso, bool print_sym) +{ + + if ((verbose || print_dso) && al->map) + fprintf(f, "%s@", al->map->dso->long_name); + + if ((verbose || print_sym) && al->sym) + fprintf(f, "%s+0x%" PRIx64, al->sym->name, + al->addr - al->sym->start); + else if (al->map) + fprintf(f, "0x%" PRIx64, al->addr); + else + fprintf(f, "0x%" PRIx64, sample->addr); +} + +static int trace__pgfault(struct trace *trace, + struct perf_evsel *evsel, + union perf_event *event, + struct perf_sample *sample) +{ + struct thread *thread; + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct addr_location al; + char map_type = 'd'; + struct thread_trace *ttrace; + + thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); + ttrace = thread__trace(thread, trace->output); + if (ttrace == NULL) + return -1; + + if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ) + ttrace->pfmaj++; + else + ttrace->pfmin++; + + if (trace->summary_only) + return 0; + + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, + sample->ip, &al); + + trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output); + + fprintf(trace->output, "%sfault [", + evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ? + "maj" : "min"); + + print_location(trace->output, sample, &al, false, true); + + fprintf(trace->output, "] => "); + + thread__find_addr_location(thread, cpumode, MAP__VARIABLE, + sample->addr, &al); + + if (!al.map) { + thread__find_addr_location(thread, cpumode, + MAP__FUNCTION, sample->addr, &al); + + if (al.map) + map_type = 'x'; + else + map_type = '?'; + } + + print_location(trace->output, sample, &al, true, false); + + fprintf(trace->output, " (%c%c)\n", map_type, al.level); + + return 0; +} + static bool skip_sample(struct trace *trace, struct perf_sample *sample) { if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) || @@ -1781,7 +1892,7 @@ static bool skip_sample(struct trace *trace, struct perf_sample *sample) } static int trace__process_sample(struct perf_tool *tool, - union perf_event *event __maybe_unused, + union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __maybe_unused) @@ -1799,7 +1910,7 @@ static int trace__process_sample(struct perf_tool *tool, if (handler) { ++trace->nr_events; - handler(trace, evsel, sample); + handler(trace, evsel, event, sample); } return err; @@ -1826,7 +1937,7 @@ static int parse_target_str(struct trace *trace) return 0; } -static int trace__record(int argc, const char **argv) +static int trace__record(struct trace *trace, int argc, const char **argv) { unsigned int rec_argc, i, j; const char **rec_argv; @@ -1835,34 +1946,54 @@ static int trace__record(int argc, const char **argv) "-R", "-m", "1024", "-c", "1", - "-e", }; + const char * const sc_args[] = { "-e", }; + unsigned int sc_args_nr = ARRAY_SIZE(sc_args); + const char * const majpf_args[] = { "-e", "major-faults" }; + unsigned int majpf_args_nr = ARRAY_SIZE(majpf_args); + const char * const minpf_args[] = { "-e", "minor-faults" }; + unsigned int minpf_args_nr = ARRAY_SIZE(minpf_args); + /* +1 is for the event string below */ - rec_argc = ARRAY_SIZE(record_args) + 1 + argc; + rec_argc = ARRAY_SIZE(record_args) + sc_args_nr + 1 + + majpf_args_nr + minpf_args_nr + argc; rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (rec_argv == NULL) return -ENOMEM; + j = 0; for (i = 0; i < ARRAY_SIZE(record_args); i++) - rec_argv[i] = record_args[i]; - - /* event string may be different for older kernels - e.g., RHEL6 */ - if (is_valid_tracepoint("raw_syscalls:sys_enter")) - rec_argv[i] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit"; - else if (is_valid_tracepoint("syscalls:sys_enter")) - rec_argv[i] = "syscalls:sys_enter,syscalls:sys_exit"; - else { - pr_err("Neither raw_syscalls nor syscalls events exist.\n"); - return -1; + rec_argv[j++] = record_args[i]; + + if (trace->trace_syscalls) { + for (i = 0; i < sc_args_nr; i++) + rec_argv[j++] = sc_args[i]; + + /* event string may be different for older kernels - e.g., RHEL6 */ + if (is_valid_tracepoint("raw_syscalls:sys_enter")) + rec_argv[j++] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit"; + else if (is_valid_tracepoint("syscalls:sys_enter")) + rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit"; + else { + pr_err("Neither raw_syscalls nor syscalls events exist.\n"); + return -1; + } } - i++; - for (j = 0; j < (unsigned int)argc; j++, i++) - rec_argv[i] = argv[j]; + if (trace->trace_pgfaults & TRACE_PFMAJ) + for (i = 0; i < majpf_args_nr; i++) + rec_argv[j++] = majpf_args[i]; - return cmd_record(i, rec_argv, NULL); + if (trace->trace_pgfaults & TRACE_PFMIN) + for (i = 0; i < minpf_args_nr; i++) + rec_argv[j++] = minpf_args[i]; + + for (i = 0; i < (unsigned int)argc; i++) + rec_argv[j++] = argv[i]; + + return cmd_record(j, rec_argv, NULL); } static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); @@ -1882,6 +2013,30 @@ static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist) perf_evlist__add(evlist, evsel); } +static int perf_evlist__add_pgfault(struct perf_evlist *evlist, + u64 config) +{ + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .mmap_data = 1, + }; + + attr.config = config; + attr.sample_period = 1; + + event_attr_init(&attr); + + evsel = perf_evsel__new(&attr); + if (!evsel) + return -ENOMEM; + + evsel->handler = trace__pgfault; + perf_evlist__add(evlist, evsel); + + return 0; +} + static int trace__run(struct trace *trace, int argc, const char **argv) { struct perf_evlist *evlist = perf_evlist__new(); @@ -1889,6 +2044,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) int err = -1, i; unsigned long before; const bool forks = argc > 0; + bool draining = false; trace->live = true; @@ -1897,10 +2053,21 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out; } - if (perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit)) + if (trace->trace_syscalls && + perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, + trace__sys_exit)) + goto out_error_tp; + + 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_vfs_getname(evlist); + if ((trace->trace_pgfaults & TRACE_PFMIN) && + perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN)) + goto out_error_tp; if (trace->sched && perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime", @@ -1938,10 +2105,8 @@ 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(errno)); - goto out_delete_evlist; - } + if (err < 0) + goto out_error_mmap; perf_evlist__enable(evlist); @@ -1982,7 +2147,8 @@ again: goto next_event; } - if (sample.raw_data == NULL) { + if (evsel->attr.type == PERF_TYPE_TRACEPOINT && + sample.raw_data == NULL) { fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", perf_evsel__name(evsel), sample.tid, sample.cpu, sample.raw_size); @@ -1990,7 +2156,7 @@ again: } handler = evsel->handler; - handler(trace, evsel, &sample); + handler(trace, evsel, event, &sample); next_event: perf_evlist__mmap_consume(evlist, i); @@ -2002,8 +2168,12 @@ next_event: if (trace->nr_events == before) { int timeout = done ? 100 : -1; - if (poll(evlist->pollfd, evlist->nr_fds, timeout) > 0) + if (!draining && perf_evlist__poll(evlist, timeout) > 0) { + if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0) + draining = true; + goto again; + } } else { goto again; } @@ -2036,6 +2206,10 @@ out_error_tp: perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf)); goto out_error; +out_error_mmap: + perf_evlist__strerror_mmap(evlist, errno, errbuf, sizeof(errbuf)); + goto out_error; + out_error_open: perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf)); @@ -2068,18 +2242,18 @@ static int trace__replay(struct trace *trace) trace->tool.tracing_data = perf_event__process_tracing_data; trace->tool.build_id = perf_event__process_build_id; - trace->tool.ordered_samples = true; + trace->tool.ordered_events = true; trace->tool.ordering_requires_timestamps = true; /* add tid to output */ trace->multiple_threads = true; - if (symbol__init() < 0) - return -1; - session = perf_session__new(&file, false, &trace->tool); if (session == NULL) - return -ENOMEM; + return -1; + + if (symbol__init(&session->header.env) < 0) + goto out; trace->host = &session->machines.host; @@ -2093,13 +2267,10 @@ static int trace__replay(struct trace *trace) if (evsel == NULL) evsel = perf_evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_enter"); - if (evsel == NULL) { - pr_err("Data file does not have raw_syscalls:sys_enter event\n"); - goto out; - } - if (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 || - perf_evsel__init_sc_tp_ptr_field(evsel, args)) { + if (evsel && + (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 || + perf_evsel__init_sc_tp_ptr_field(evsel, args))) { pr_err("Error during initialize raw_syscalls:sys_enter event\n"); goto out; } @@ -2109,15 +2280,19 @@ static int trace__replay(struct trace *trace) if (evsel == NULL) evsel = perf_evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_exit"); - if (evsel == NULL) { - pr_err("Data file does not have raw_syscalls:sys_exit event\n"); + if (evsel && + (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 || + perf_evsel__init_sc_tp_uint_field(evsel, ret))) { + pr_err("Error during initialize raw_syscalls:sys_exit event\n"); goto out; } - if (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 || - perf_evsel__init_sc_tp_uint_field(evsel, ret)) { - pr_err("Error during initialize raw_syscalls:sys_exit event\n"); - goto out; + evlist__for_each(session->evlist, evsel) { + if (evsel->attr.type == PERF_TYPE_SOFTWARE && + (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ || + evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN || + evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS)) + evsel->handler = trace__pgfault; } err = parse_target_str(trace); @@ -2206,7 +2381,7 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv) FILE *fp = data->fp; size_t printed = data->printed; struct trace *trace = data->trace; - struct thread_trace *ttrace = thread->priv; + struct thread_trace *ttrace = thread__priv(thread); double ratio; if (ttrace == NULL) @@ -2217,6 +2392,10 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv) printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid); printed += fprintf(fp, "%lu events, ", ttrace->nr_events); printed += fprintf(fp, "%.1f%%", ratio); + if (ttrace->pfmaj) + printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj); + if (ttrace->pfmin) + printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin); printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms); printed += thread__dump_stats(ttrace, trace, fp); @@ -2264,6 +2443,23 @@ static int trace__open_output(struct trace *trace, const char *filename) return trace->output == NULL ? -errno : 0; } +static int parse_pagefaults(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + int *trace_pgfaults = opt->value; + + if (strcmp(str, "all") == 0) + *trace_pgfaults |= TRACE_PFMAJ | TRACE_PFMIN; + else if (strcmp(str, "maj") == 0) + *trace_pgfaults |= TRACE_PFMAJ; + else if (strcmp(str, "min") == 0) + *trace_pgfaults |= TRACE_PFMIN; + else + return -1; + + return 0; +} + int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) { const char * const trace_usage[] = { @@ -2289,10 +2485,11 @@ 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, + .trace_syscalls = true, }; const char *output_name = NULL; const char *ev_qualifier_str = NULL; @@ -2330,20 +2527,34 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) "Show only syscall summary with statistics"), OPT_BOOLEAN('S', "with-summary", &trace.summary, "Show all syscalls and summary with statistics"), + OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min", + "Trace pagefaults", parse_pagefaults, "maj"), + OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"), OPT_END() }; int err; char bf[BUFSIZ]; - if ((argc > 1) && (strcmp(argv[1], "record") == 0)) - return trace__record(argc-2, &argv[2]); + argc = parse_options(argc, argv, trace_options, trace_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + if (trace.trace_pgfaults) { + trace.opts.sample_address = true; + trace.opts.sample_time = true; + } - argc = parse_options(argc, argv, trace_options, trace_usage, 0); + if ((argc >= 1) && (strcmp(argv[0], "record") == 0)) + return trace__record(&trace, argc-1, &argv[1]); /* summary_only implies summary option, but don't overwrite summary if set */ if (trace.summary_only) trace.summary = trace.summary_only; + if (!trace.trace_syscalls && !trace.trace_pgfaults) { + pr_err("Please specify something to trace.\n"); + return -1; + } + if (output_name != NULL) { err = trace__open_output(&trace, output_name); if (err < 0) { diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index f30ac5e..5d4b039 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -116,6 +116,29 @@ ifdef PARSER_DEBUG CFLAGS += -DPARSER_DEBUG endif +ifndef NO_LIBPYTHON + # Try different combinations to accommodate systems that only have + # python[2][-config] in weird combinations but always preferring + # python2 and python2-config as per pep-0394. If we catch a + # python[-config] in version 3, the version check will kill it. + PYTHON2 := $(if $(call get-executable,python2),python2,python) + override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2)) + PYTHON2_CONFIG := \ + $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config) + override PYTHON_CONFIG := \ + $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG)) + + PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) + + PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) + PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) + + FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) + FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) + FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS) + FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) +endif + CFLAGS += -fno-omit-frame-pointer CFLAGS += -ggdb3 CFLAGS += -funwind-tables @@ -127,7 +150,7 @@ CFLAGS += -std=gnu99 # adding assembler files missing the .GNU-stack linker note. LDFLAGS += -Wl,-z,noexecstack -EXTLIBS = -lelf -lpthread -lrt -lm -ldl +EXTLIBS = -lpthread -lrt -lm -ldl ifneq ($(OUTPUT),) OUTPUT_FEATURES = $(OUTPUT)config/feature-checks/ @@ -160,6 +183,7 @@ CORE_FEATURE_TESTS = \ backtrace \ dwarf \ fortify-source \ + sync-compare-and-swap \ glibc \ gtk2 \ gtk2-infobar \ @@ -176,7 +200,8 @@ CORE_FEATURE_TESTS = \ libunwind \ stackprotector-all \ timerfd \ - libdw-dwarf-unwind + libdw-dwarf-unwind \ + zlib LIB_FEATURE_TESTS = \ dwarf \ @@ -190,11 +215,13 @@ LIB_FEATURE_TESTS = \ libpython \ libslang \ libunwind \ - libdw-dwarf-unwind + libdw-dwarf-unwind \ + zlib VF_FEATURE_TESTS = \ backtrace \ fortify-source \ + sync-compare-and-swap \ gtk2-infobar \ libelf-getphdrnum \ libelf-mmap \ @@ -205,7 +232,9 @@ VF_FEATURE_TESTS = \ bionic \ liberty \ liberty-z \ - cplus-demangle + cplus-demangle \ + compile-32 \ + compile-x32 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features. # If in the future we need per-feature checks/flags for features not @@ -268,6 +297,10 @@ CFLAGS += -I$(LIB_INCLUDE) CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE +ifeq ($(feature-sync-compare-and-swap), 1) + CFLAGS += -DHAVE_SYNC_COMPARE_AND_SWAP_SUPPORT +endif + ifndef NO_BIONIC $(call feature_check,bionic) ifeq ($(feature-bionic), 1) @@ -321,6 +354,7 @@ endif # NO_LIBELF ifndef NO_LIBELF CFLAGS += -DHAVE_LIBELF_SUPPORT + EXTLIBS += -lelf ifeq ($(feature-libelf-mmap), 1) CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT @@ -340,11 +374,17 @@ ifndef NO_LIBELF else CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS) LDFLAGS += $(LIBDW_LDFLAGS) - EXTLIBS += -lelf -ldw + EXTLIBS += -ldw endif # PERF_HAVE_DWARF_REGS endif # NO_DWARF endif # NO_LIBELF +ifeq ($(ARCH),powerpc) + ifndef NO_DWARF + CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX + endif +endif + ifndef NO_LIBUNWIND ifneq ($(feature-libunwind), 1) msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR); @@ -472,21 +512,14 @@ define disable-python_code NO_LIBPYTHON := 1 endef -override PYTHON := \ - $(call get-executable-or-default,PYTHON,python) - -ifndef PYTHON - $(call disable-python,python interpreter) +ifdef NO_LIBPYTHON + $(call disable-python) else - PYTHON_WORD := $(call shell-wordify,$(PYTHON)) - - ifdef NO_LIBPYTHON - $(call disable-python) + ifndef PYTHON + $(call disable-python,python interpreter) else - - override PYTHON_CONFIG := \ - $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config) + PYTHON_WORD := $(call shell-wordify,$(PYTHON)) ifndef PYTHON_CONFIG $(call disable-python,python-config tool) @@ -574,6 +607,15 @@ ifneq ($(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 ($(feature-backtrace), 1) CFLAGS += -DHAVE_BACKTRACE_SUPPORT @@ -590,6 +632,35 @@ ifndef NO_LIBNUMA endif endif +ifdef HAVE_KVM_STAT_SUPPORT + CFLAGS += -DHAVE_KVM_STAT_SUPPORT +endif + +ifeq (${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 @@ -621,11 +692,13 @@ else sysconfdir = $(prefix)/etc ETC_PERFCONFIG = etc/perfconfig endif +ifndef lib ifeq ($(IS_X86_64),1) lib = lib64 else lib = lib endif +endif # lib libdir = $(prefix)/$(lib) # Shell quote (do not use $(call) to accommodate ancient setups); diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch index 4b06719..851cd01 100644 --- a/tools/perf/config/Makefile.arch +++ b/tools/perf/config/Makefile.arch @@ -21,3 +21,11 @@ ifeq ($(ARCH),x86_64) RAW_ARCH := x86_64 endif endif + +ifeq (${IS_X86_64}, 1) + IS_64_BIT := 1 +else ifeq ($(ARCH),x86) + IS_64_BIT := 0 +else + IS_64_BIT := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) +endif diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile index 64c84e5..53f19b5 100644 --- a/tools/perf/config/feature-checks/Makefile +++ b/tools/perf/config/feature-checks/Makefile @@ -5,6 +5,7 @@ FILES= \ test-bionic.bin \ test-dwarf.bin \ test-fortify-source.bin \ + test-sync-compare-and-swap.bin \ test-glibc.bin \ test-gtk2.bin \ test-gtk2-infobar.bin \ @@ -26,7 +27,10 @@ FILES= \ test-libunwind-debug-frame.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 @@ -38,7 +42,7 @@ 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: $(BUILD) @@ -100,25 +104,11 @@ FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) test-libperl.bin: $(BUILD) $(FLAGS_PERL_EMBED) -override PYTHON := python -override PYTHON_CONFIG := python-config - -escape-for-shell-sq = $(subst ','\'',$(1)) -shell-sq = '$(escape-for-shell-sq)' - -PYTHON_CONFIG_SQ = $(call shell-sq,$(PYTHON_CONFIG)) - -PYTHON_EMBED_LDOPTS = $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) -PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) -PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -PYTHON_EMBED_CCOPTS = $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) -FLAGS_PYTHON_EMBED = $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) - test-libpython.bin: - $(BUILD) $(FLAGS_PYTHON_EMBED) + $(BUILD) test-libpython-version.bin: - $(BUILD) $(FLAGS_PYTHON_EMBED) + $(BUILD) test-libbfd.bin: $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl @@ -141,6 +131,18 @@ test-timerfd.bin: test-libdw-dwarf-unwind.bin: $(BUILD) +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 fe5c1e5..652e009 100644 --- a/tools/perf/config/feature-checks/test-all.c +++ b/tools/perf/config/feature-checks/test-all.c @@ -89,6 +89,14 @@ # include "test-libdw-dwarf-unwind.c" #undef main +#define main main_test_sync_compare_and_swap +# include "test-sync-compare-and-swap.c" +#undef main + +#define main main_test_zlib +# include "test-zlib.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -111,6 +119,8 @@ int main(int argc, char *argv[]) main_test_timerfd(); main_test_stackprotector_all(); main_test_libdw_dwarf_unwind(); + main_test_sync_compare_and_swap(argc, argv); + main_test_zlib(); 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 0000000..31dbf45 --- /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-sync-compare-and-swap.c b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c new file mode 100644 index 0000000..c34d4ca --- /dev/null +++ b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c @@ -0,0 +1,14 @@ +#include <stdint.h> + +volatile uint64_t x; + +int main(int argc, char *argv[]) +{ + uint64_t old, new = argc; + + argv = argv; + do { + old = __sync_val_compare_and_swap(&x, 0, 0); + } while (!__sync_bool_compare_and_swap(&x, old, new)); + return old == new; +} 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 0000000..e111fff --- /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/config/utilities.mak b/tools/perf/config/utilities.mak index 4d985e0..7076a62 100644 --- a/tools/perf/config/utilities.mak +++ b/tools/perf/config/utilities.mak @@ -132,7 +132,7 @@ endef # # Usage: bool-value = $(call is-absolute,path) # -is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y) +is-absolute = $(shell echo $(shell-sq) | grep -q ^/ && echo y) # lookup # diff --git a/tools/perf/perf-read-vdso.c b/tools/perf/perf-read-vdso.c new file mode 100644 index 0000000..764e254 --- /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 5268a14..a3b13d7 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -13,7 +13,7 @@ #define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #define cpu_relax() asm volatile("rep; nop" ::: "memory"); -#define CPUINFO_PROC "model name" +#define CPUINFO_PROC {"model name"} #ifndef __NR_perf_event_open # define __NR_perf_event_open 336 #endif @@ -30,7 +30,7 @@ #define wmb() asm volatile("sfence" ::: "memory") #define rmb() asm volatile("lfence" ::: "memory") #define cpu_relax() asm volatile("rep; nop" ::: "memory"); -#define CPUINFO_PROC "model name" +#define CPUINFO_PROC {"model name"} #ifndef __NR_perf_event_open # define __NR_perf_event_open 298 #endif @@ -47,13 +47,14 @@ #define mb() asm volatile ("sync" ::: "memory") #define wmb() asm volatile ("sync" ::: "memory") #define rmb() asm volatile ("sync" ::: "memory") -#define CPUINFO_PROC "cpu" +#define CPUINFO_PROC {"cpu"} #endif #ifdef __s390__ #define mb() asm volatile("bcr 15,0" ::: "memory") #define wmb() asm volatile("bcr 15,0" ::: "memory") #define rmb() asm volatile("bcr 15,0" ::: "memory") +#define CPUINFO_PROC {"vendor_id"} #endif #ifdef __sh__ @@ -66,14 +67,14 @@ # define wmb() asm volatile("" ::: "memory") # define rmb() asm volatile("" ::: "memory") #endif -#define CPUINFO_PROC "cpu type" +#define CPUINFO_PROC {"cpu type"} #endif #ifdef __hppa__ #define mb() asm volatile("" ::: "memory") #define wmb() asm volatile("" ::: "memory") #define rmb() asm volatile("" ::: "memory") -#define CPUINFO_PROC "cpu" +#define CPUINFO_PROC {"cpu"} #endif #ifdef __sparc__ @@ -86,14 +87,14 @@ #endif #define wmb() asm volatile("":::"memory") #define rmb() asm volatile("":::"memory") -#define CPUINFO_PROC "cpu" +#define CPUINFO_PROC {"cpu"} #endif #ifdef __alpha__ #define mb() asm volatile("mb" ::: "memory") #define wmb() asm volatile("wmb" ::: "memory") #define rmb() asm volatile("mb" ::: "memory") -#define CPUINFO_PROC "cpu model" +#define CPUINFO_PROC {"cpu model"} #endif #ifdef __ia64__ @@ -101,7 +102,7 @@ #define wmb() asm volatile ("mf" ::: "memory") #define rmb() asm volatile ("mf" ::: "memory") #define cpu_relax() asm volatile ("hint @pause" ::: "memory") -#define CPUINFO_PROC "model name" +#define CPUINFO_PROC {"model name"} #endif #ifdef __arm__ @@ -112,7 +113,7 @@ #define mb() ((void(*)(void))0xffff0fa0)() #define wmb() ((void(*)(void))0xffff0fa0)() #define rmb() ((void(*)(void))0xffff0fa0)() -#define CPUINFO_PROC "Processor" +#define CPUINFO_PROC {"model name", "Processor"} #endif #ifdef __aarch64__ @@ -132,28 +133,28 @@ : "memory") #define wmb() mb() #define rmb() mb() -#define CPUINFO_PROC "cpu model" +#define CPUINFO_PROC {"cpu model"} #endif #ifdef __arc__ #define mb() asm volatile("" ::: "memory") #define wmb() asm volatile("" ::: "memory") #define rmb() asm volatile("" ::: "memory") -#define CPUINFO_PROC "Processor" +#define CPUINFO_PROC {"Processor"} #endif #ifdef __metag__ #define mb() asm volatile("" ::: "memory") #define wmb() asm volatile("" ::: "memory") #define rmb() asm volatile("" ::: "memory") -#define CPUINFO_PROC "CPU" +#define CPUINFO_PROC {"CPU"} #endif #ifdef __xtensa__ #define mb() asm volatile("memw" ::: "memory") #define wmb() asm volatile("memw" ::: "memory") #define rmb() asm volatile("" ::: "memory") -#define CPUINFO_PROC "core ID" +#define CPUINFO_PROC {"core ID"} #endif #ifdef __tile__ @@ -161,7 +162,7 @@ #define wmb() asm volatile ("mf" ::: "memory") #define rmb() asm volatile ("mf" ::: "memory") #define cpu_relax() asm volatile ("mfspr zero, PASS" ::: "memory") -#define CPUINFO_PROC "model name" +#define CPUINFO_PROC {"model name"} #endif #define barrier() asm volatile ("" ::: "memory") diff --git a/tools/perf/perf-with-kcore.sh b/tools/perf/perf-with-kcore.sh new file mode 100644 index 0000000..c7ff90a --- /dev/null +++ b/tools/perf/perf-with-kcore.sh @@ -0,0 +1,259 @@ +#!/bin/bash +# perf-with-kcore: use perf with a copy of kcore +# 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. + +set -e + +usage() +{ + echo "Usage: perf-with-kcore <perf sub-command> <perf.data directory> [<sub-command options> [ -- <workload>]]" >&2 + echo " <perf sub-command> can be record, script, report or inject" >&2 + echo " or: perf-with-kcore fix_buildid_cache_permissions" >&2 + exit 1 +} + +find_perf() +{ + if [ -n "$PERF" ] ; then + return + fi + PERF=`which perf || true` + if [ -z "$PERF" ] ; then + echo "Failed to find perf" >&2 + exit 1 + fi + if [ ! -x "$PERF" ] ; then + echo "Failed to find perf" >&2 + exit 1 + fi + echo "Using $PERF" + "$PERF" version +} + +copy_kcore() +{ + echo "Copying kcore" + + if [ $EUID -eq 0 ] ; then + SUDO="" + else + SUDO="sudo" + fi + + rm -f perf.data.junk + ("$PERF" record -o perf.data.junk $PERF_OPTIONS -- sleep 60) >/dev/null 2>/dev/null & + PERF_PID=$! + + # Need to make sure that perf has started + sleep 1 + + KCORE=$(($SUDO "$PERF" buildid-cache -v -f -k /proc/kcore >/dev/null) 2>&1) + case "$KCORE" in + "kcore added to build-id cache directory "*) + KCORE_DIR=${KCORE#"kcore added to build-id cache directory "} + ;; + *) + kill $PERF_PID + wait >/dev/null 2>/dev/null || true + rm perf.data.junk + echo "$KCORE" + echo "Failed to find kcore" >&2 + exit 1 + ;; + esac + + kill $PERF_PID + wait >/dev/null 2>/dev/null || true + rm perf.data.junk + + $SUDO cp -a "$KCORE_DIR" "$(pwd)/$PERF_DATA_DIR" + $SUDO rm -f "$KCORE_DIR/kcore" + $SUDO rm -f "$KCORE_DIR/kallsyms" + $SUDO rm -f "$KCORE_DIR/modules" + $SUDO rmdir "$KCORE_DIR" + + KCORE_DIR_BASENAME=$(basename "$KCORE_DIR") + KCORE_DIR="$(pwd)/$PERF_DATA_DIR/$KCORE_DIR_BASENAME" + + $SUDO chown $UID "$KCORE_DIR" + $SUDO chown $UID "$KCORE_DIR/kcore" + $SUDO chown $UID "$KCORE_DIR/kallsyms" + $SUDO chown $UID "$KCORE_DIR/modules" + + $SUDO chgrp $GROUPS "$KCORE_DIR" + $SUDO chgrp $GROUPS "$KCORE_DIR/kcore" + $SUDO chgrp $GROUPS "$KCORE_DIR/kallsyms" + $SUDO chgrp $GROUPS "$KCORE_DIR/modules" + + ln -s "$KCORE_DIR_BASENAME" "$PERF_DATA_DIR/kcore_dir" +} + +fix_buildid_cache_permissions() +{ + if [ $EUID -ne 0 ] ; then + echo "This script must be run as root via sudo " >&2 + exit 1 + fi + + if [ -z "$SUDO_USER" ] ; then + echo "This script must be run via sudo" >&2 + exit 1 + fi + + USER_HOME=$(bash <<< "echo ~$SUDO_USER") + + if [ "$HOME" != "$USER_HOME" ] ; then + echo "Fix unnecessary because root has a home: $HOME" >&2 + exit 1 + fi + + echo "Fixing buildid cache permissions" + + find "$USER_HOME/.debug" -xdev -type d ! -user "$SUDO_USER" -ls -exec chown "$SUDO_USER" \{\} \; + find "$USER_HOME/.debug" -xdev -type f -links 1 ! -user "$SUDO_USER" -ls -exec chown "$SUDO_USER" \{\} \; + find "$USER_HOME/.debug" -xdev -type l ! -user "$SUDO_USER" -ls -exec chown -h "$SUDO_USER" \{\} \; + + if [ -n "$SUDO_GID" ] ; then + find "$USER_HOME/.debug" -xdev -type d ! -group "$SUDO_GID" -ls -exec chgrp "$SUDO_GID" \{\} \; + find "$USER_HOME/.debug" -xdev -type f -links 1 ! -group "$SUDO_GID" -ls -exec chgrp "$SUDO_GID" \{\} \; + find "$USER_HOME/.debug" -xdev -type l ! -group "$SUDO_GID" -ls -exec chgrp -h "$SUDO_GID" \{\} \; + fi + + echo "Done" +} + +check_buildid_cache_permissions() +{ + if [ $EUID -eq 0 ] ; then + return + fi + + PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d ! -user "$USER" -print -quit) + PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -user "$USER" -print -quit) + PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l ! -user "$USER" -print -quit) + + PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d ! -group "$GROUPS" -print -quit) + PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -group "$GROUPS" -print -quit) + PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l ! -group "$GROUPS" -print -quit) + + if [ -n "$PERMISSIONS_OK" ] ; then + echo "*** WARNING *** buildid cache permissions may need fixing" >&2 + fi +} + +record() +{ + echo "Recording" + + if [ $EUID -ne 0 ] ; then + + if [ "$(cat /proc/sys/kernel/kptr_restrict)" -ne 0 ] ; then + echo "*** WARNING *** /proc/sys/kernel/kptr_restrict prevents access to kernel addresses" >&2 + fi + + if echo "$PERF_OPTIONS" | grep -q ' -a \|^-a \| -a$\|^-a$\| --all-cpus \|^--all-cpus \| --all-cpus$\|^--all-cpus$' ; then + echo "*** WARNING *** system-wide tracing without root access will not be able to read all necessary information from /proc" >&2 + fi + + if echo "$PERF_OPTIONS" | grep -q 'intel_pt\|intel_bts\| -I\|^-I' ; then + if [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt -1 ] ; then + echo "*** WARNING *** /proc/sys/kernel/perf_event_paranoid restricts buffer size and tracepoint (sched_switch) use" >&2 + fi + + if echo "$PERF_OPTIONS" | grep -q ' --per-thread \|^--per-thread \| --per-thread$\|^--per-thread$' ; then + true + elif echo "$PERF_OPTIONS" | grep -q ' -t \|^-t \| -t$\|^-t$' ; then + true + elif [ ! -r /sys/kernel/debug -o ! -x /sys/kernel/debug ] ; then + echo "*** WARNING *** /sys/kernel/debug permissions prevent tracepoint (sched_switch) use" >&2 + fi + fi + fi + + if [ -z "$1" ] ; then + echo "Workload is required for recording" >&2 + usage + fi + + if [ -e "$PERF_DATA_DIR" ] ; then + echo "'$PERF_DATA_DIR' exists" >&2 + exit 1 + fi + + find_perf + + mkdir "$PERF_DATA_DIR" + + echo "$PERF record -o $PERF_DATA_DIR/perf.data $PERF_OPTIONS -- $*" + "$PERF" record -o "$PERF_DATA_DIR/perf.data" $PERF_OPTIONS -- $* || true + + if rmdir "$PERF_DATA_DIR" > /dev/null 2>/dev/null ; then + exit 1 + fi + + copy_kcore + + echo "Done" +} + +subcommand() +{ + find_perf + check_buildid_cache_permissions + echo "$PERF $PERF_SUB_COMMAND -i $PERF_DATA_DIR/perf.data --kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms $*" + "$PERF" $PERF_SUB_COMMAND -i "$PERF_DATA_DIR/perf.data" "--kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms" $* +} + +if [ "$1" = "fix_buildid_cache_permissions" ] ; then + fix_buildid_cache_permissions + exit 0 +fi + +PERF_SUB_COMMAND=$1 +PERF_DATA_DIR=$2 +shift || true +shift || true + +if [ -z "$PERF_SUB_COMMAND" ] ; then + usage +fi + +if [ -z "$PERF_DATA_DIR" ] ; then + usage +fi + +case "$PERF_SUB_COMMAND" in +"record") + while [ "$1" != "--" ] ; do + PERF_OPTIONS+="$1 " + shift || break + done + if [ "$1" != "--" ] ; then + echo "Options and workload are required for recording" >&2 + usage + fi + shift + record $* +;; +"script") + subcommand $* +;; +"report") + subcommand $* +;; +"inject") + subcommand $* +;; +*) + usage +;; +esac diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 95c58fc..3700a7f 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -13,11 +13,12 @@ #include "util/quote.h" #include "util/run-command.h" #include "util/parse-events.h" +#include "util/debug.h" #include <api/fs/debugfs.h> #include <pthread.h> const char perf_usage_string[] = - "perf [--version] [--help] COMMAND [ARGS]"; + "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]"; const char perf_more_info_string[] = "See 'perf help COMMAND' for more information on a specific command."; @@ -199,6 +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); @@ -212,6 +223,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) printf("%s ", p->cmd); } exit(0); + } else if (!strcmp(cmd, "--debug")) { + if (*argc < 2) { + fprintf(stderr, "No variable specified for --debug.\n"); + usage(perf_usage_string); + } + if (perf_debug_option((*argv)[1])) + usage(perf_usage_string); + + (*argv)++; + (*argc)--; } else { fprintf(stderr, "Unknown option: %s\n", cmd); usage(perf_usage_string); @@ -302,6 +323,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) int status; struct stat st; const char *prefix; + char sbuf[STRERR_BUFSIZE]; prefix = NULL; if (p->option & RUN_SETUP) @@ -332,7 +354,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) status = 1; /* Check for ENOSPC and EIO errors.. */ if (fflush(stdout)) { - fprintf(stderr, "write failure on standard output: %s", strerror(errno)); + fprintf(stderr, "write failure on standard output: %s", + strerror_r(errno, sbuf, sizeof(sbuf))); goto out; } if (ferror(stdout)) { @@ -340,7 +363,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) goto out; } if (fclose(stdout)) { - fprintf(stderr, "close failed on standard output: %s", strerror(errno)); + fprintf(stderr, "close failed on standard output: %s", + strerror_r(errno, sbuf, sizeof(sbuf))); goto out; } status = 0; @@ -455,6 +479,7 @@ void pthread__unblock_sigwinch(void) int main(int argc, const char **argv) { const char *cmd; + char sbuf[STRERR_BUFSIZE]; /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); @@ -484,7 +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); @@ -499,7 +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], "--")) @@ -550,7 +575,7 @@ int main(int argc, const char **argv) } fprintf(stderr, "Failed to run command '%s': %s\n", - cmd, strerror(errno)); + cmd, strerror_r(errno, sbuf, sizeof(sbuf))); out: return 1; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 510c65f..1dabb85 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -41,8 +41,6 @@ void pthread__unblock_sigwinch(void); struct record_opts { struct target target; - int call_graph; - bool call_graph_enabled; bool group; bool inherit_stat; bool no_buffering; @@ -54,15 +52,18 @@ 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; u64 branch_stack; u64 default_interval; u64 user_interval; - u16 stack_dump_size; bool sample_transaction; unsigned initial_delay; }; +struct option; +extern const char * const *record_usage; +extern struct option *record_options; #endif diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record index 8104895..74685f3 100644 --- a/tools/perf/scripts/perl/bin/failed-syscalls-record +++ b/tools/perf/scripts/perl/bin/failed-syscalls-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -e raw_syscalls:sys_exit $@ +(perf record -e raw_syscalls:sys_exit $@ || \ + perf record -e syscalls:sys_exit $@) 2> /dev/null diff --git a/tools/perf/scripts/perl/failed-syscalls.pl b/tools/perf/scripts/perl/failed-syscalls.pl index 94bc25a..55e7ae4 100644 --- a/tools/perf/scripts/perl/failed-syscalls.pl +++ b/tools/perf/scripts/perl/failed-syscalls.pl @@ -26,6 +26,11 @@ sub raw_syscalls::sys_exit } } +sub syscalls::sys_exit +{ + raw_syscalls::sys_exit(@_) +} + sub trace_end { printf("\nfailed syscalls by comm:\n\n"); diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py index de7211e..38dfb72 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py @@ -107,12 +107,13 @@ def taskState(state): class EventHeaders: def __init__(self, common_cpu, common_secs, common_nsecs, - common_pid, common_comm): + common_pid, common_comm, common_callchain): self.cpu = common_cpu self.secs = common_secs self.nsecs = common_nsecs self.pid = common_pid self.comm = common_comm + self.callchain = common_callchain def ts(self): return (self.secs * (10 ** 9)) + self.nsecs 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 0000000..221d66e --- /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 $@ diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-report b/tools/perf/scripts/python/bin/export-to-postgresql-report new file mode 100644 index 0000000..cd335b6 --- /dev/null +++ b/tools/perf/scripts/python/bin/export-to-postgresql-report @@ -0,0 +1,29 @@ +#!/bin/bash +# description: export perf data to a postgresql database +# args: [database name] [columns] [calls] +n_args=0 +for i in "$@" +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/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record index 8104895..74685f3 100644 --- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record +++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -e raw_syscalls:sys_exit $@ +(perf record -e raw_syscalls:sys_exit $@ || \ + perf record -e syscalls:sys_exit $@) 2> /dev/null diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record index 4efbfaa..d694084 100644 --- a/tools/perf/scripts/python/bin/sctop-record +++ b/tools/perf/scripts/python/bin/sctop-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -e raw_syscalls:sys_enter $@ +(perf record -e raw_syscalls:sys_enter $@ || \ + perf record -e syscalls:sys_enter $@) 2> /dev/null diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record index 4efbfaa..d694084 100644 --- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record +++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -e raw_syscalls:sys_enter $@ +(perf record -e raw_syscalls:sys_enter $@ || \ + perf record -e syscalls:sys_enter $@) 2> /dev/null diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record index 4efbfaa..d694084 100644 --- a/tools/perf/scripts/python/bin/syscall-counts-record +++ b/tools/perf/scripts/python/bin/syscall-counts-record @@ -1,2 +1,3 @@ #!/bin/bash -perf record -e raw_syscalls:sys_enter $@ +(perf record -e raw_syscalls:sys_enter $@ || \ + perf record -e syscalls:sys_enter $@) 2> /dev/null diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py index 4647a76..334599c 100644 --- a/tools/perf/scripts/python/check-perf-trace.py +++ b/tools/perf/scripts/python/check-perf-trace.py @@ -27,7 +27,7 @@ def trace_end(): def irq__softirq_entry(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - vec): + common_callchain, vec): print_header(event_name, common_cpu, common_secs, common_nsecs, common_pid, common_comm) @@ -38,7 +38,7 @@ def irq__softirq_entry(event_name, context, common_cpu, def kmem__kmalloc(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - call_site, ptr, bytes_req, bytes_alloc, + common_callchain, call_site, ptr, bytes_req, bytes_alloc, gfp_flags): print_header(event_name, common_cpu, common_secs, common_nsecs, common_pid, common_comm) 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 0000000..4cdafd8 --- /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/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py index 85805fa..cafeff3 100644 --- a/tools/perf/scripts/python/failed-syscalls-by-pid.py +++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py @@ -39,7 +39,7 @@ def trace_end(): def raw_syscalls__sys_exit(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, ret): + common_callchain, id, ret): if (for_comm and common_comm != for_comm) or \ (for_pid and common_pid != for_pid ): return @@ -50,6 +50,11 @@ def raw_syscalls__sys_exit(event_name, context, common_cpu, except TypeError: syscalls[common_comm][common_pid][id][ret] = 1 +def syscalls__sys_exit(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, ret): + raw_syscalls__sys_exit(**locals()) + def print_error_totals(): if for_comm is not None: print "\nsyscall errors for %s:\n\n" % (for_comm), diff --git a/tools/perf/scripts/python/futex-contention.py b/tools/perf/scripts/python/futex-contention.py index 11e70a3..0f5cf43 100644 --- a/tools/perf/scripts/python/futex-contention.py +++ b/tools/perf/scripts/python/futex-contention.py @@ -21,7 +21,7 @@ thread_blocktime = {} lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time process_names = {} # long-lived pid-to-execname mapping -def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, +def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, callchain, nr, uaddr, op, val, utime, uaddr2, val3): cmd = op & FUTEX_CMD_MASK if cmd != FUTEX_WAIT: @@ -31,7 +31,7 @@ def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, thread_thislock[tid] = uaddr thread_blocktime[tid] = nsecs(s, ns) -def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, +def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, callchain, nr, ret): if thread_blocktime.has_key(tid): elapsed = nsecs(s, ns) - thread_blocktime[tid] diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py index b574059..0b6ce8c 100755 --- a/tools/perf/scripts/python/net_dropmonitor.py +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -66,7 +66,7 @@ def trace_end(): print_drop_table() # called from perf, when it finds a correspoinding event -def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, +def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, location, protocol): slocation = str(location) try: diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py index 9aa0a32..4d21ef2 100644 --- a/tools/perf/scripts/python/netdev-times.py +++ b/tools/perf/scripts/python/netdev-times.py @@ -224,75 +224,75 @@ def trace_end(): (len(rx_skb_list), of_count_rx_skb_list) # called from perf, when it finds a correspoinding event -def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, vec): +def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, callchain, vec): if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": return event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) all_event_list.append(event_info) -def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, vec): +def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, callchain, vec): if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": return event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) all_event_list.append(event_info) -def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, vec): +def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, callchain, vec): if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": return event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) all_event_list.append(event_info) def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm, - irq, irq_name): + callchain, irq, irq_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, irq_name) all_event_list.append(event_info) -def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, irq, ret): +def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, callchain, irq, ret): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret) all_event_list.append(event_info) -def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, napi, dev_name): +def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, napi, dev_name) all_event_list.append(event_info) -def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr, +def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, dev_name) all_event_list.append(event_info) -def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, skbaddr, +def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, dev_name) all_event_list.append(event_info) -def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, +def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, dev_name) all_event_list.append(event_info) -def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, +def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, rc, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, rc ,dev_name) all_event_list.append(event_info) -def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, +def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, protocol, location): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, protocol, location) all_event_list.append(event_info) -def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr): +def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr) all_event_list.append(event_info) -def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, +def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen) diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py index 74d55ec..de66cb3 100644 --- a/tools/perf/scripts/python/sched-migration.py +++ b/tools/perf/scripts/python/sched-migration.py @@ -369,93 +369,92 @@ def trace_end(): def sched__sched_stat_runtime(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, runtime, vruntime): + common_callchain, comm, pid, runtime, vruntime): pass def sched__sched_stat_iowait(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, delay): + common_callchain, comm, pid, delay): pass def sched__sched_stat_sleep(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, delay): + common_callchain, comm, pid, delay): pass def sched__sched_stat_wait(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, delay): + common_callchain, comm, pid, delay): pass def sched__sched_process_fork(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - parent_comm, parent_pid, child_comm, child_pid): + common_callchain, parent_comm, parent_pid, child_comm, child_pid): pass def sched__sched_process_wait(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_process_exit(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_process_free(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_migrate_task(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio, orig_cpu, + common_callchain, comm, pid, prio, orig_cpu, dest_cpu): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.migrate(headers, pid, prio, orig_cpu, dest_cpu) def sched__sched_switch(event_name, context, common_cpu, - common_secs, common_nsecs, common_pid, common_comm, + common_secs, common_nsecs, common_pid, common_comm, common_callchain, prev_comm, prev_pid, prev_prio, prev_state, next_comm, next_pid, next_prio): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.sched_switch(headers, prev_comm, prev_pid, prev_prio, prev_state, next_comm, next_pid, next_prio) def sched__sched_wakeup_new(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio, success, + common_callchain, comm, pid, prio, success, target_cpu): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.wake_up(headers, comm, pid, success, target_cpu, 1) def sched__sched_wakeup(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio, success, + common_callchain, comm, pid, prio, success, target_cpu): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.wake_up(headers, comm, pid, success, target_cpu, 0) def sched__sched_wait_task(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_kthread_stop_ret(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - ret): + common_callchain, ret): pass def sched__sched_kthread_stop(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid): + common_callchain, comm, pid): pass -def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs, - common_pid, common_comm): +def trace_unhandled(event_name, context, event_fields_dict): pass diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py index 42c267e..61621b9 100644 --- a/tools/perf/scripts/python/sctop.py +++ b/tools/perf/scripts/python/sctop.py @@ -44,7 +44,7 @@ def trace_begin(): def raw_syscalls__sys_enter(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, args): + common_callchain, id, args): if for_comm is not None: if common_comm != for_comm: return @@ -53,6 +53,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu, except TypeError: syscalls[id] = 1 +def syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, args): + raw_syscalls__sys_enter(**locals()) + def print_syscall_totals(interval): while 1: clear_term() diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py index c64d1c5..daf314c 100644 --- a/tools/perf/scripts/python/syscall-counts-by-pid.py +++ b/tools/perf/scripts/python/syscall-counts-by-pid.py @@ -38,7 +38,7 @@ def trace_end(): def raw_syscalls__sys_enter(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, args): + common_callchain, id, args): if (for_comm and common_comm != for_comm) or \ (for_pid and common_pid != for_pid ): @@ -48,6 +48,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu, except TypeError: syscalls[common_comm][common_pid][id] = 1 +def syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, args): + raw_syscalls__sys_enter(**locals()) + def print_syscall_totals(): if for_comm is not None: print "\nsyscall events for %s:\n\n" % (for_comm), diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py index b435d3f..e66a773 100644 --- a/tools/perf/scripts/python/syscall-counts.py +++ b/tools/perf/scripts/python/syscall-counts.py @@ -35,7 +35,7 @@ def trace_end(): def raw_syscalls__sys_enter(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, args): + common_callchain, id, args): if for_comm is not None: if common_comm != for_comm: return @@ -44,6 +44,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu, except TypeError: syscalls[id] = 1 +def syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, args): + raw_syscalls__sys_enter(**locals()) + def print_syscall_totals(): if for_comm is not None: print "\nsyscall events for %s:\n\n" % (for_comm), diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index e9bd639..d3095da 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -1,10 +1,11 @@ [event] fd=1 group_fd=-1 -flags=0 +# 0 or PERF_FLAG_FD_CLOEXEC flag +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 91cd48b..872ed7e 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -1,10 +1,11 @@ [event] fd=1 group_fd=-1 -flags=0 +# 0 or PERF_FLAG_FD_CLOEXEC flag +flags=0|8 cpu=* type=0 -size=96 +size=104 config=0 sample_period=0 sample_type=0 diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index aba0954..a02b035 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -25,6 +25,7 @@ #include "tests.h" #include "debug.h" #include "perf.h" +#include "cloexec.h" static int fd1; static int fd2; @@ -78,7 +79,8 @@ static int bp_event(void *fn, int setup_signal) pe.exclude_kernel = 1; pe.exclude_hv = 1; - fd = sys_perf_event_open(&pe, 0, -1, -1, 0); + fd = sys_perf_event_open(&pe, 0, -1, -1, + perf_event_open_cloexec_flag()); if (fd < 0) { pr_debug("failed opening event %llx\n", pe.config); return TEST_FAIL; diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c index 44ac821..e765377 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -24,6 +24,7 @@ #include "tests.h" #include "debug.h" #include "perf.h" +#include "cloexec.h" static int overflows; @@ -91,7 +92,8 @@ int test__bp_signal_overflow(void) pe.exclude_kernel = 1; pe.exclude_hv = 1; - fd = sys_perf_event_open(&pe, 0, -1, -1, 0); + fd = sys_perf_event_open(&pe, 0, -1, -1, + perf_event_open_cloexec_flag()); if (fd < 0) { pr_debug("failed opening event %llx\n", pe.config); return TEST_FAIL; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 6f8b01b..4b7d9ab 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -6,6 +6,7 @@ #include <unistd.h> #include <string.h> #include "builtin.h" +#include "hist.h" #include "intlist.h" #include "tests.h" #include "debug.h" @@ -84,7 +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, }, { @@ -154,6 +155,18 @@ static struct test { .func = test__hists_cumulate, }, { + .desc = "Test tracking with sched_switch", + .func = test__switch_tracking, + }, + { + .desc = "Filter fds with revents mask in a fdarray", + .func = test__fdarray__filter, + }, + { + .desc = "Add fd to a fdarray, making it autogrow", + .func = test__fdarray__add, + }, + { .func = NULL, }, }; @@ -185,9 +198,11 @@ static bool perf_test__matches(int curr, int argc, const char *argv[]) static int run_test(struct test *test) { int status, err = -1, child = fork(); + char sbuf[STRERR_BUFSIZE]; if (child < 0) { - pr_err("failed to fork test: %s\n", strerror(errno)); + pr_err("failed to fork test: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); return -1; } @@ -288,6 +303,10 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) OPT_END() }; struct intlist *skiplist = NULL; + int ret = hists__init(); + + if (ret < 0) + return ret; argc = parse_options(argc, argv, test_options, test_usage, 0); if (argc >= 1 && !strcmp(argv[0], "list")) @@ -297,7 +316,7 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) symbol_conf.sort_by_name = true; symbol_conf.try_vmlinux_path = true; - if (symbol__init() < 0) + if (symbol__init(NULL) < 0) return -1; if (skip != NULL) diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 67f2d63..f671ec3 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/dso-data.c b/tools/perf/tests/dso-data.c index 630808c..caaf37f 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -10,6 +10,7 @@ #include "machine.h" #include "symbol.h" #include "tests.h" +#include "debug.h" static char *test_file(int size) { diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 96adb73..ab28cca 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -9,6 +9,7 @@ #include "perf_regs.h" #include "map.h" #include "thread.h" +#include "callchain.h" static int mmap_handler(struct perf_tool *tool __maybe_unused, union perf_event *event, @@ -58,7 +59,7 @@ 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; @@ -71,7 +72,7 @@ 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"); @@ -88,21 +89,21 @@ static int unwind_thread(struct thread *thread, struct machine *machine) } __attribute__ ((noinline)) -static int krava_3(struct thread *thread, struct machine *machine) +static int krava_3(struct thread *thread) { - return unwind_thread(thread, machine); + return unwind_thread(thread); } __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) @@ -120,6 +121,8 @@ int test__dwarf_unwind(void) return -1; } + callchain_param.record_mode = CALLCHAIN_DWARF; + if (init_live_machine(machine)) { pr_err("Could not init machine\n"); goto out; @@ -134,7 +137,7 @@ 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/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 465cdbc..b8d8341 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -2,6 +2,7 @@ #include "evsel.h" #include "parse-events.h" #include "tests.h" +#include "debug.h" static int perf_evsel__roundtrip_cache_name_test(void) { diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 35d7fdb..5216242 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -1,6 +1,7 @@ #include <traceevent/event-parse.h> #include "evsel.h" #include "tests.h" +#include "debug.h" static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, int size, bool should_be_signed) diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c new file mode 100644 index 0000000..d24b837 --- /dev/null +++ b/tools/perf/tests/fdarray.c @@ -0,0 +1,174 @@ +#include <api/fd/array.h> +#include "util/debug.h" +#include "tests/tests.h" + +static void fdarray__init_revents(struct fdarray *fda, short revents) +{ + int fd; + + fda->nr = fda->nr_alloc; + + for (fd = 0; fd < fda->nr; ++fd) { + fda->entries[fd].fd = fda->nr - fd; + fda->entries[fd].revents = revents; + } +} + +static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE *fp) +{ + int printed = 0; + + if (!verbose) + return 0; + + printed += fprintf(fp, "\n%s: ", prefix); + return printed + fdarray__fprintf(fda, fp); +} + +int test__fdarray__filter(void) +{ + int nr_fds, expected_fd[2], fd, err = TEST_FAIL; + struct fdarray *fda = fdarray__new(5, 5); + + if (fda == NULL) { + pr_debug("\nfdarray__new() failed!"); + goto out; + } + + fdarray__init_revents(fda, POLLIN); + nr_fds = fdarray__filter(fda, POLLHUP, NULL); + if (nr_fds != fda->nr_alloc) { + pr_debug("\nfdarray__filter()=%d != %d shouldn't have filtered anything", + nr_fds, fda->nr_alloc); + goto out_delete; + } + + fdarray__init_revents(fda, POLLHUP); + nr_fds = fdarray__filter(fda, POLLHUP, NULL); + if (nr_fds != 0) { + pr_debug("\nfdarray__filter()=%d != %d, should have filtered all fds", + nr_fds, fda->nr_alloc); + goto out_delete; + } + + fdarray__init_revents(fda, POLLHUP); + fda->entries[2].revents = POLLIN; + expected_fd[0] = fda->entries[2].fd; + + pr_debug("\nfiltering all but fda->entries[2]:"); + fdarray__fprintf_prefix(fda, "before", stderr); + nr_fds = fdarray__filter(fda, POLLHUP, NULL); + fdarray__fprintf_prefix(fda, " after", stderr); + if (nr_fds != 1) { + pr_debug("\nfdarray__filter()=%d != 1, should have left just one event", nr_fds); + goto out_delete; + } + + if (fda->entries[0].fd != expected_fd[0]) { + pr_debug("\nfda->entries[0].fd=%d != %d\n", + fda->entries[0].fd, expected_fd[0]); + goto out_delete; + } + + fdarray__init_revents(fda, POLLHUP); + fda->entries[0].revents = POLLIN; + expected_fd[0] = fda->entries[0].fd; + fda->entries[3].revents = POLLIN; + expected_fd[1] = fda->entries[3].fd; + + pr_debug("\nfiltering all but (fda->entries[0], fda->entries[3]):"); + fdarray__fprintf_prefix(fda, "before", stderr); + nr_fds = fdarray__filter(fda, POLLHUP, NULL); + fdarray__fprintf_prefix(fda, " after", stderr); + if (nr_fds != 2) { + pr_debug("\nfdarray__filter()=%d != 2, should have left just two events", + nr_fds); + goto out_delete; + } + + for (fd = 0; fd < 2; ++fd) { + if (fda->entries[fd].fd != expected_fd[fd]) { + pr_debug("\nfda->entries[%d].fd=%d != %d\n", fd, + fda->entries[fd].fd, expected_fd[fd]); + goto out_delete; + } + } + + pr_debug("\n"); + + err = 0; +out_delete: + fdarray__delete(fda); +out: + return err; +} + +int test__fdarray__add(void) +{ + int err = TEST_FAIL; + struct fdarray *fda = fdarray__new(2, 2); + + if (fda == NULL) { + pr_debug("\nfdarray__new() failed!"); + goto out; + } + +#define FDA_CHECK(_idx, _fd, _revents) \ + if (fda->entries[_idx].fd != _fd) { \ + pr_debug("\n%d: fda->entries[%d](%d) != %d!", \ + __LINE__, _idx, fda->entries[1].fd, _fd); \ + goto out_delete; \ + } \ + if (fda->entries[_idx].events != (_revents)) { \ + pr_debug("\n%d: fda->entries[%d].revents(%d) != %d!", \ + __LINE__, _idx, fda->entries[_idx].fd, _revents); \ + goto out_delete; \ + } + +#define FDA_ADD(_idx, _fd, _revents, _nr) \ + if (fdarray__add(fda, _fd, _revents) < 0) { \ + pr_debug("\n%d: fdarray__add(fda, %d, %d) failed!", \ + __LINE__,_fd, _revents); \ + goto out_delete; \ + } \ + if (fda->nr != _nr) { \ + pr_debug("\n%d: fdarray__add(fda, %d, %d)=%d != %d", \ + __LINE__,_fd, _revents, fda->nr, _nr); \ + goto out_delete; \ + } \ + FDA_CHECK(_idx, _fd, _revents) + + FDA_ADD(0, 1, POLLIN, 1); + FDA_ADD(1, 2, POLLERR, 2); + + fdarray__fprintf_prefix(fda, "before growing array", stderr); + + FDA_ADD(2, 35, POLLHUP, 3); + + if (fda->entries == NULL) { + pr_debug("\nfdarray__add(fda, 35, POLLHUP) should have allocated fda->pollfd!"); + goto out_delete; + } + + fdarray__fprintf_prefix(fda, "after 3rd add", stderr); + + FDA_ADD(3, 88, POLLIN | POLLOUT, 4); + + fdarray__fprintf_prefix(fda, "after 4th add", stderr); + + FDA_CHECK(0, 1, POLLIN); + FDA_CHECK(1, 2, POLLERR); + FDA_CHECK(2, 35, POLLHUP); + FDA_CHECK(3, 88, POLLIN | POLLOUT); + +#undef FDA_ADD +#undef FDA_CHECK + + pr_debug("\n"); + + err = 0; +out_delete: + fdarray__delete(fda); +out: + return err; +} diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 0ac240d..614d5c4 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -245,7 +245,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec static int test1(struct perf_evsel *evsel, struct machine *machine) { int err; - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); /* * expected output: * @@ -295,7 +295,7 @@ out: static int test2(struct perf_evsel *evsel, struct machine *machine) { int err; - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); /* * expected output: * @@ -442,7 +442,7 @@ out: static int test3(struct perf_evsel *evsel, struct machine *machine) { int err; - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); /* * expected output: * @@ -498,7 +498,7 @@ out: static int test4(struct perf_evsel *evsel, struct machine *machine) { int err; - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); /* * expected output: * diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 821f581..74f257a 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; @@ -66,11 +66,12 @@ static int add_hist_entries(struct perf_evlist *evlist, .ops = &hist_iter_normal, .hide_unresolved = false, }; + struct hists *hists = evsel__hists(evsel); /* make sure it has no filter at first */ - evsel->hists.thread_filter = NULL; - evsel->hists.dso_filter = NULL; - evsel->hists.symbol_filter_str = NULL; + hists->thread_filter = NULL; + hists->dso_filter = NULL; + hists->symbol_filter_str = NULL; sample.pid = fake_samples[i].pid; sample.tid = fake_samples[i].pid; @@ -134,7 +135,7 @@ int test__hists_filter(void) goto out; evlist__for_each(evlist, evsel) { - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); hists__collapse_resort(hists, NULL); hists__output_resort(hists); @@ -160,7 +161,7 @@ int test__hists_filter(void) hists->stats.total_non_filtered_period); /* now applying thread filter for 'bash' */ - evsel->hists.thread_filter = fake_samples[9].thread; + hists->thread_filter = fake_samples[9].thread; hists__filter_by_thread(hists); if (verbose > 2) { @@ -185,11 +186,11 @@ int test__hists_filter(void) hists->stats.total_non_filtered_period == 400); /* remove thread filter first */ - evsel->hists.thread_filter = NULL; + hists->thread_filter = NULL; hists__filter_by_thread(hists); /* now applying dso filter for 'kernel' */ - evsel->hists.dso_filter = fake_samples[0].map->dso; + hists->dso_filter = fake_samples[0].map->dso; hists__filter_by_dso(hists); if (verbose > 2) { @@ -214,7 +215,7 @@ int test__hists_filter(void) hists->stats.total_non_filtered_period == 300); /* remove dso filter first */ - evsel->hists.dso_filter = NULL; + hists->dso_filter = NULL; hists__filter_by_dso(hists); /* @@ -224,7 +225,7 @@ int test__hists_filter(void) * be counted as a separate entry but the sample count and * total period will be remained. */ - evsel->hists.symbol_filter_str = "main"; + hists->symbol_filter_str = "main"; hists__filter_by_symbol(hists); if (verbose > 2) { @@ -249,8 +250,8 @@ int test__hists_filter(void) hists->stats.total_non_filtered_period == 300); /* now applying all filters at once. */ - evsel->hists.thread_filter = fake_samples[1].thread; - evsel->hists.dso_filter = fake_samples[1].map->dso; + hists->thread_filter = fake_samples[1].thread; + hists->dso_filter = fake_samples[1].map->dso; hists__filter_by_thread(hists); hists__filter_by_dso(hists); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index d4b34b0..278ba834 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -73,6 +73,8 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) * "bash [libc] malloc" so total 9 entries will be in the tree. */ evlist__for_each(evlist, evsel) { + struct hists *hists = evsel__hists(evsel); + for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) { const union perf_event event = { .header = { @@ -87,7 +89,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) &sample) < 0) goto out; - he = __hists__add_entry(&evsel->hists, &al, NULL, + he = __hists__add_entry(hists, &al, NULL, NULL, NULL, 1, 1, 0, true); if (he == NULL) goto out; @@ -111,7 +113,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) &sample) < 0) goto out; - he = __hists__add_entry(&evsel->hists, &al, NULL, + he = __hists__add_entry(hists, &al, NULL, NULL, NULL, 1, 1, 0, true); if (he == NULL) goto out; @@ -271,6 +273,7 @@ static int validate_link(struct hists *leader, struct hists *other) int test__hists_link(void) { int err = -1; + struct hists *hists, *first_hists; struct machines machines; struct machine *machine = NULL; struct perf_evsel *evsel, *first; @@ -306,24 +309,28 @@ int test__hists_link(void) goto out; evlist__for_each(evlist, evsel) { - hists__collapse_resort(&evsel->hists, NULL); + hists = evsel__hists(evsel); + hists__collapse_resort(hists, NULL); if (verbose > 2) - print_hists_in(&evsel->hists); + print_hists_in(hists); } first = perf_evlist__first(evlist); evsel = perf_evlist__last(evlist); + first_hists = evsel__hists(first); + hists = evsel__hists(evsel); + /* match common entries */ - hists__match(&first->hists, &evsel->hists); - err = validate_match(&first->hists, &evsel->hists); + hists__match(first_hists, hists); + err = validate_match(first_hists, hists); if (err) goto out; /* link common and/or dummy entries */ - hists__link(&first->hists, &evsel->hists); - err = validate_link(&first->hists, &evsel->hists); + hists__link(first_hists, hists); + err = validate_link(first_hists, hists); if (err) goto out; diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index e3bbd6c..a748f2b 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -122,7 +122,7 @@ typedef int (*test_fn_t)(struct perf_evsel *, struct machine *); static int test1(struct perf_evsel *evsel, struct machine *machine) { int err; - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); struct hist_entry *he; struct rb_root *root; struct rb_node *node; @@ -159,7 +159,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) print_hists_out(hists); } - root = &evsel->hists.entries; + root = &hists->entries; node = rb_first(root); he = rb_entry(node, struct hist_entry, rb_node); TEST_ASSERT_VAL("Invalid hist entry", @@ -224,7 +224,7 @@ out: static int test2(struct perf_evsel *evsel, struct machine *machine) { int err; - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); struct hist_entry *he; struct rb_root *root; struct rb_node *node; @@ -259,7 +259,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) print_hists_out(hists); } - root = &evsel->hists.entries; + root = &hists->entries; node = rb_first(root); he = rb_entry(node, struct hist_entry, rb_node); TEST_ASSERT_VAL("Invalid hist entry", @@ -280,7 +280,7 @@ out: static int test3(struct perf_evsel *evsel, struct machine *machine) { int err; - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); struct hist_entry *he; struct rb_root *root; struct rb_node *node; @@ -313,7 +313,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) print_hists_out(hists); } - root = &evsel->hists.entries; + root = &hists->entries; node = rb_first(root); he = rb_entry(node, struct hist_entry, rb_node); TEST_ASSERT_VAL("Invalid hist entry", @@ -354,7 +354,7 @@ out: static int test4(struct perf_evsel *evsel, struct machine *machine) { int err; - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); struct hist_entry *he; struct rb_root *root; struct rb_node *node; @@ -391,7 +391,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) print_hists_out(hists); } - root = &evsel->hists.entries; + root = &hists->entries; node = rb_first(root); he = rb_entry(node, struct hist_entry, rb_node); TEST_ASSERT_VAL("Invalid hist entry", @@ -456,7 +456,7 @@ out: static int test5(struct perf_evsel *evsel, struct machine *machine) { int err; - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); struct hist_entry *he; struct rb_root *root; struct rb_node *node; @@ -494,7 +494,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine) print_hists_out(hists); } - root = &evsel->hists.entries; + root = &hists->entries; node = rb_first(root); he = rb_entry(node, struct hist_entry, rb_node); diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 1422634..9b9622a3 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -31,6 +31,7 @@ int test__basic_mmap(void) unsigned int nr_events[nsyscalls], expected_nr_events[nsyscalls], i, j; struct perf_evsel *evsels[nsyscalls], *evsel; + char sbuf[STRERR_BUFSIZE]; threads = thread_map__new(-1, getpid(), UINT_MAX); if (threads == NULL) { @@ -49,7 +50,7 @@ int test__basic_mmap(void) sched_setaffinity(0, sizeof(cpu_set), &cpu_set); if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { pr_debug("sched_setaffinity() failed on CPU %d: %s ", - cpus->map[0], strerror(errno)); + cpus->map[0], strerror_r(errno, sbuf, sizeof(sbuf))); goto out_free_cpus; } @@ -79,7 +80,7 @@ int test__basic_mmap(void) if (perf_evsel__open(evsels[i], cpus, threads) < 0) { pr_debug("failed to open counter: %s, " "tweak /proc/sys/kernel/perf_event_paranoid?\n", - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } @@ -89,7 +90,7 @@ int test__basic_mmap(void) if (perf_evlist__mmap(evlist, 128, true) < 0) { pr_debug("failed to mmap events: %d (%s)\n", errno, - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 4a456fe..2113f1c 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/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c index 5fecdbd..8fa82d1 100644 --- a/tools/perf/tests/open-syscall-all-cpus.c +++ b/tools/perf/tests/open-syscall-all-cpus.c @@ -12,6 +12,7 @@ int test__open_syscall_event_on_all_cpus(void) unsigned int nr_open_calls = 111, i; cpu_set_t cpu_set; struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX); + char sbuf[STRERR_BUFSIZE]; if (threads == NULL) { pr_debug("thread_map__new\n"); @@ -35,7 +36,7 @@ int test__open_syscall_event_on_all_cpus(void) if (perf_evsel__open(evsel, cpus, threads) < 0) { pr_debug("failed to open counter: %s, " "tweak /proc/sys/kernel/perf_event_paranoid?\n", - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_evsel_delete; } @@ -56,7 +57,7 @@ int test__open_syscall_event_on_all_cpus(void) if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { pr_debug("sched_setaffinity() failed on CPU %d: %s ", cpus->map[cpu], - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_close_fd; } for (i = 0; i < ncalls; ++i) { diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c index c505ef2..127dcae 100644 --- a/tools/perf/tests/open-syscall-tp-fields.c +++ b/tools/perf/tests/open-syscall-tp-fields.c @@ -3,6 +3,7 @@ #include "evsel.h" #include "thread_map.h" #include "tests.h" +#include "debug.h" int test__syscall_open_tp_fields(void) { @@ -21,6 +22,7 @@ int test__syscall_open_tp_fields(void) struct perf_evlist *evlist = perf_evlist__new(); struct perf_evsel *evsel; int err = -1, i, nr_events = 0, nr_polls = 0; + char sbuf[STRERR_BUFSIZE]; if (evlist == NULL) { pr_debug("%s: perf_evlist__new\n", __func__); @@ -47,13 +49,15 @@ int test__syscall_open_tp_fields(void) err = perf_evlist__open(evlist); if (err < 0) { - pr_debug("perf_evlist__open: %s\n", strerror(errno)); + pr_debug("perf_evlist__open: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } err = perf_evlist__mmap(evlist, UINT_MAX, false); if (err < 0) { - pr_debug("perf_evlist__mmap: %s\n", strerror(errno)); + pr_debug("perf_evlist__mmap: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } @@ -101,7 +105,7 @@ int test__syscall_open_tp_fields(void) } if (nr_events == before) - poll(evlist->pollfd, evlist->nr_fds, 10); + perf_evlist__poll(evlist, 10); if (++nr_polls > 5) { pr_debug("%s: no events!\n", __func__); diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c index c1dc7d2..a33b2da 100644 --- a/tools/perf/tests/open-syscall.c +++ b/tools/perf/tests/open-syscall.c @@ -9,6 +9,7 @@ int test__open_syscall_event(void) struct perf_evsel *evsel; unsigned int nr_open_calls = 111, i; struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX); + char sbuf[STRERR_BUFSIZE]; if (threads == NULL) { pr_debug("thread_map__new\n"); @@ -24,7 +25,7 @@ int test__open_syscall_event(void) if (perf_evsel__open_per_thread(evsel, threads) < 0) { pr_debug("failed to open counter: %s, " "tweak /proc/sys/kernel/perf_event_paranoid?\n", - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_evsel_delete; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index deba669..7f2f51f 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -5,6 +5,7 @@ #include <api/fs/fs.h> #include <api/fs/debugfs.h> #include "tests.h" +#include "debug.h" #include <linux/hw_breakpoint.h> #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \ @@ -456,6 +457,36 @@ static int test__checkevent_pmu_events(struct perf_evlist *evlist) return 0; } + +static int test__checkevent_pmu_events_mix(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + /* pmu-event:u */ + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + 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); + TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned); + + /* cpu/pmu-event/u*/ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); + 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); + TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned); + + return 0; +} + static int test__checkterms_simple(struct list_head *terms) { struct parse_events_term *term; @@ -1553,6 +1584,12 @@ static int test_pmu_events(void) e.check = test__checkevent_pmu_events; ret = test_event(&e); + if (ret) + break; + snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name); + e.name = name; + e.check = test__checkevent_pmu_events_mix; + ret = test_event(&e); #undef MAX_NAME } diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 905019f..2c63ea6 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -7,6 +7,7 @@ #include "evlist.h" #include "header.h" #include "util.h" +#include "debug.h" static int process_event(struct perf_evlist **pevlist, union perf_event *event) { diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index aca1a83..7a228a2 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -59,6 +59,7 @@ int test__PERF_RECORD(void) int err = -1, errs = 0, i, wakeups = 0; u32 cpu; int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, }; + char sbuf[STRERR_BUFSIZE]; if (evlist == NULL || argv == NULL) { pr_debug("Not enough memory to create evlist\n"); @@ -100,7 +101,8 @@ int test__PERF_RECORD(void) err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask); if (err < 0) { - pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno)); + pr_debug("sched__get_first_possible_cpu: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } @@ -110,7 +112,8 @@ int test__PERF_RECORD(void) * So that we can check perf_sample.cpu on all the samples. */ if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) { - pr_debug("sched_setaffinity: %s\n", strerror(errno)); + pr_debug("sched_setaffinity: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } @@ -120,7 +123,8 @@ int test__PERF_RECORD(void) */ err = perf_evlist__open(evlist); if (err < 0) { - pr_debug("perf_evlist__open: %s\n", strerror(errno)); + pr_debug("perf_evlist__open: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } @@ -131,7 +135,8 @@ int test__PERF_RECORD(void) */ err = perf_evlist__mmap(evlist, opts.mmap_pages, false); if (err < 0) { - pr_debug("perf_evlist__mmap: %s\n", strerror(errno)); + pr_debug("perf_evlist__mmap: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } @@ -263,7 +268,7 @@ int test__PERF_RECORD(void) * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does. */ if (total_events == before && false) - poll(evlist->pollfd, evlist->nr_fds, -1); + perf_evlist__poll(evlist, -1); sleep(1); if (++wakeups > 5) { diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 3b7cd4d..f238442 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -8,10 +8,9 @@ #include "evsel.h" #include "thread_map.h" #include "cpumap.h" +#include "tsc.h" #include "tests.h" -#include "../arch/x86/util/tsc.h" - #define CHECK__(x) { \ while ((x) < 0) { \ pr_debug(#x " failed!\n"); \ @@ -26,15 +25,6 @@ } \ } -static u64 rdtsc(void) -{ - unsigned int low, high; - - asm volatile("rdtsc" : "=a" (low), "=d" (high)); - - return low | ((u64)high) << 32; -} - /** * test__perf_time_to_tsc - test converting perf time to TSC. * diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 12b322f..eeb68bb1 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -152,7 +152,7 @@ int test__pmu(void) if (ret) break; - ret = perf_pmu__config_terms(&formats, &attr, terms); + ret = perf_pmu__config_terms(&formats, &attr, terms, false); if (ret) break; diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c index e59143f..d31f2c4 100644 --- a/tools/perf/tests/rdpmc.c +++ b/tools/perf/tests/rdpmc.c @@ -6,6 +6,7 @@ #include "perf.h" #include "debug.h" #include "tests.h" +#include "cloexec.h" #if defined(__x86_64__) || defined(__i386__) @@ -99,22 +100,25 @@ static int __test__rdpmc(void) }; u64 delta_sum = 0; struct sigaction sa; + char sbuf[STRERR_BUFSIZE]; sigfillset(&sa.sa_mask); sa.sa_sigaction = segfault_handler; sigaction(SIGSEGV, &sa, NULL); - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + fd = sys_perf_event_open(&attr, 0, -1, -1, + perf_event_open_cloexec_flag()); if (fd < 0) { pr_err("Error: sys_perf_event_open() syscall returned " - "with %d (%s)\n", fd, strerror(errno)); + "with %d (%s)\n", fd, + strerror_r(errno, sbuf, sizeof(sbuf))); return -1; } addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0); if (addr == (void *)(-1)) { pr_err("Error: mmap() syscall returned with (%s)\n", - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_close; } diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 7ae8d17..4908c64 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -4,6 +4,7 @@ #include "util.h" #include "event.h" #include "evsel.h" +#include "debug.h" #include "tests.h" @@ -125,16 +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, }, }; @@ -153,7 +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 = { @@ -175,8 +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), @@ -186,14 +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; @@ -270,7 +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; @@ -279,7 +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; } @@ -296,22 +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/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 983d6b8..1aa21c9 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -22,6 +22,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) volatile int tmp = 0; u64 total_periods = 0; int nr_samples = 0; + char sbuf[STRERR_BUFSIZE]; union perf_event *event; struct perf_evsel *evsel; struct perf_evlist *evlist; @@ -62,14 +63,15 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) err = -errno; pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n", - strerror(errno), knob, (u64)attr.sample_freq); + strerror_r(errno, sbuf, sizeof(sbuf)), + knob, (u64)attr.sample_freq); goto out_delete_evlist; } err = perf_evlist__mmap(evlist, 128, true); if (err < 0) { pr_debug("failed to mmap event: %d (%s)\n", errno, - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c new file mode 100644 index 0000000..cc68648 --- /dev/null +++ b/tools/perf/tests/switch-tracking.c @@ -0,0 +1,572 @@ +#include <sys/time.h> +#include <sys/prctl.h> +#include <time.h> +#include <stdlib.h> + +#include "parse-events.h" +#include "evlist.h" +#include "evsel.h" +#include "thread_map.h" +#include "cpumap.h" +#include "tests.h" + +static int spin_sleep(void) +{ + struct timeval start, now, diff, maxtime; + struct timespec ts; + int err, i; + + maxtime.tv_sec = 0; + maxtime.tv_usec = 50000; + + err = gettimeofday(&start, NULL); + if (err) + return err; + + /* Spin for 50ms */ + while (1) { + for (i = 0; i < 1000; i++) + barrier(); + + err = gettimeofday(&now, NULL); + if (err) + return err; + + timersub(&now, &start, &diff); + if (timercmp(&diff, &maxtime, > /* For checkpatch */)) + break; + } + + ts.tv_nsec = 50 * 1000 * 1000; + ts.tv_sec = 0; + + /* Sleep for 50ms */ + err = nanosleep(&ts, NULL); + if (err == EINTR) + err = 0; + + return err; +} + +struct switch_tracking { + struct perf_evsel *switch_evsel; + struct perf_evsel *cycles_evsel; + pid_t *tids; + int nr_tids; + int comm_seen[4]; + int cycles_before_comm_1; + int cycles_between_comm_2_and_comm_3; + int cycles_after_comm_4; +}; + +static int check_comm(struct switch_tracking *switch_tracking, + union perf_event *event, const char *comm, int nr) +{ + if (event->header.type == PERF_RECORD_COMM && + (pid_t)event->comm.pid == getpid() && + (pid_t)event->comm.tid == getpid() && + strcmp(event->comm.comm, comm) == 0) { + if (switch_tracking->comm_seen[nr]) { + pr_debug("Duplicate comm event\n"); + return -1; + } + switch_tracking->comm_seen[nr] = 1; + pr_debug3("comm event: %s nr: %d\n", event->comm.comm, nr); + return 1; + } + return 0; +} + +static int check_cpu(struct switch_tracking *switch_tracking, int cpu) +{ + int i, nr = cpu + 1; + + if (cpu < 0) + return -1; + + if (!switch_tracking->tids) { + switch_tracking->tids = calloc(nr, sizeof(pid_t)); + if (!switch_tracking->tids) + return -1; + for (i = 0; i < nr; i++) + switch_tracking->tids[i] = -1; + switch_tracking->nr_tids = nr; + return 0; + } + + if (cpu >= switch_tracking->nr_tids) { + void *addr; + + addr = realloc(switch_tracking->tids, nr * sizeof(pid_t)); + if (!addr) + return -1; + switch_tracking->tids = addr; + for (i = switch_tracking->nr_tids; i < nr; i++) + switch_tracking->tids[i] = -1; + switch_tracking->nr_tids = nr; + return 0; + } + + return 0; +} + +static int process_sample_event(struct perf_evlist *evlist, + union perf_event *event, + struct switch_tracking *switch_tracking) +{ + struct perf_sample sample; + struct perf_evsel *evsel; + pid_t next_tid, prev_tid; + int cpu, err; + + if (perf_evlist__parse_sample(evlist, event, &sample)) { + pr_debug("perf_evlist__parse_sample failed\n"); + return -1; + } + + evsel = perf_evlist__id2evsel(evlist, sample.id); + if (evsel == switch_tracking->switch_evsel) { + next_tid = perf_evsel__intval(evsel, &sample, "next_pid"); + prev_tid = perf_evsel__intval(evsel, &sample, "prev_pid"); + cpu = sample.cpu; + pr_debug3("sched_switch: cpu: %d prev_tid %d next_tid %d\n", + cpu, prev_tid, next_tid); + err = check_cpu(switch_tracking, cpu); + if (err) + return err; + /* + * Check for no missing sched_switch events i.e. that the + * evsel->system_wide flag has worked. + */ + if (switch_tracking->tids[cpu] != -1 && + switch_tracking->tids[cpu] != prev_tid) { + pr_debug("Missing sched_switch events\n"); + return -1; + } + switch_tracking->tids[cpu] = next_tid; + } + + if (evsel == switch_tracking->cycles_evsel) { + pr_debug3("cycles event\n"); + if (!switch_tracking->comm_seen[0]) + switch_tracking->cycles_before_comm_1 = 1; + if (switch_tracking->comm_seen[1] && + !switch_tracking->comm_seen[2]) + switch_tracking->cycles_between_comm_2_and_comm_3 = 1; + if (switch_tracking->comm_seen[3]) + switch_tracking->cycles_after_comm_4 = 1; + } + + return 0; +} + +static int process_event(struct perf_evlist *evlist, union perf_event *event, + struct switch_tracking *switch_tracking) +{ + if (event->header.type == PERF_RECORD_SAMPLE) + return process_sample_event(evlist, event, switch_tracking); + + if (event->header.type == PERF_RECORD_COMM) { + int err, done = 0; + + err = check_comm(switch_tracking, event, "Test COMM 1", 0); + if (err < 0) + return -1; + done += err; + err = check_comm(switch_tracking, event, "Test COMM 2", 1); + if (err < 0) + return -1; + done += err; + err = check_comm(switch_tracking, event, "Test COMM 3", 2); + if (err < 0) + return -1; + done += err; + err = check_comm(switch_tracking, event, "Test COMM 4", 3); + if (err < 0) + return -1; + done += err; + if (done != 1) { + pr_debug("Unexpected comm event\n"); + return -1; + } + } + + return 0; +} + +struct event_node { + struct list_head list; + union perf_event *event; + u64 event_time; +}; + +static int add_event(struct perf_evlist *evlist, struct list_head *events, + union perf_event *event) +{ + struct perf_sample sample; + struct event_node *node; + + node = malloc(sizeof(struct event_node)); + if (!node) { + pr_debug("malloc failed\n"); + return -1; + } + node->event = event; + list_add(&node->list, events); + + if (perf_evlist__parse_sample(evlist, event, &sample)) { + pr_debug("perf_evlist__parse_sample failed\n"); + return -1; + } + + if (!sample.time) { + pr_debug("event with no time\n"); + return -1; + } + + node->event_time = sample.time; + + return 0; +} + +static void free_event_nodes(struct list_head *events) +{ + struct event_node *node; + + while (!list_empty(events)) { + node = list_entry(events->next, struct event_node, list); + list_del(&node->list); + free(node); + } +} + +static int compar(const void *a, const void *b) +{ + const struct event_node *nodea = a; + const struct event_node *nodeb = b; + s64 cmp = nodea->event_time - nodeb->event_time; + + return cmp; +} + +static int process_events(struct perf_evlist *evlist, + struct switch_tracking *switch_tracking) +{ + union perf_event *event; + unsigned pos, cnt = 0; + LIST_HEAD(events); + struct event_node *events_array, *node; + int i, ret; + + for (i = 0; i < evlist->nr_mmaps; i++) { + while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + cnt += 1; + ret = add_event(evlist, &events, event); + perf_evlist__mmap_consume(evlist, i); + if (ret < 0) + goto out_free_nodes; + } + } + + events_array = calloc(cnt, sizeof(struct event_node)); + if (!events_array) { + pr_debug("calloc failed\n"); + ret = -1; + goto out_free_nodes; + } + + pos = 0; + list_for_each_entry(node, &events, list) + events_array[pos++] = *node; + + qsort(events_array, cnt, sizeof(struct event_node), compar); + + for (pos = 0; pos < cnt; pos++) { + ret = process_event(evlist, events_array[pos].event, + switch_tracking); + if (ret < 0) + goto out_free; + } + + ret = 0; +out_free: + pr_debug("%u events recorded\n", cnt); + free(events_array); +out_free_nodes: + free_event_nodes(&events); + return ret; +} + +/** + * test__switch_tracking - test using sched_switch and tracking events. + * + * This function implements a test that checks that sched_switch events and + * tracking events can be recorded for a workload (current process) using the + * evsel->system_wide and evsel->tracking flags (respectively) with other events + * sometimes enabled or disabled. + */ +int test__switch_tracking(void) +{ + const char *sched_switch = "sched:sched_switch"; + struct switch_tracking switch_tracking = { .tids = NULL, }; + struct record_opts opts = { + .mmap_pages = UINT_MAX, + .user_freq = UINT_MAX, + .user_interval = ULLONG_MAX, + .freq = 4000, + .target = { + .uses_mmap = true, + }, + }; + struct thread_map *threads = NULL; + struct cpu_map *cpus = NULL; + struct perf_evlist *evlist = NULL; + struct perf_evsel *evsel, *cpu_clocks_evsel, *cycles_evsel; + struct perf_evsel *switch_evsel, *tracking_evsel; + const char *comm; + int err = -1; + + threads = thread_map__new(-1, getpid(), UINT_MAX); + if (!threads) { + pr_debug("thread_map__new failed!\n"); + goto out_err; + } + + cpus = cpu_map__new(NULL); + if (!cpus) { + pr_debug("cpu_map__new failed!\n"); + goto out_err; + } + + evlist = perf_evlist__new(); + if (!evlist) { + pr_debug("perf_evlist__new failed!\n"); + goto out_err; + } + + perf_evlist__set_maps(evlist, cpus, threads); + + /* First event */ + err = parse_events(evlist, "cpu-clock:u"); + if (err) { + pr_debug("Failed to parse event dummy:u\n"); + goto out_err; + } + + cpu_clocks_evsel = perf_evlist__last(evlist); + + /* Second event */ + err = parse_events(evlist, "cycles:u"); + if (err) { + pr_debug("Failed to parse event cycles:u\n"); + goto out_err; + } + + cycles_evsel = perf_evlist__last(evlist); + + /* Third event */ + if (!perf_evlist__can_select_event(evlist, sched_switch)) { + fprintf(stderr, " (no sched_switch)"); + err = 0; + goto out; + } + + err = parse_events(evlist, sched_switch); + if (err) { + pr_debug("Failed to parse event %s\n", sched_switch); + goto out_err; + } + + switch_evsel = perf_evlist__last(evlist); + + perf_evsel__set_sample_bit(switch_evsel, CPU); + perf_evsel__set_sample_bit(switch_evsel, TIME); + + switch_evsel->system_wide = true; + switch_evsel->no_aux_samples = true; + switch_evsel->immediate = true; + + /* Test moving an event to the front */ + if (cycles_evsel == perf_evlist__first(evlist)) { + pr_debug("cycles event already at front"); + goto out_err; + } + perf_evlist__to_front(evlist, cycles_evsel); + if (cycles_evsel != perf_evlist__first(evlist)) { + pr_debug("Failed to move cycles event to front"); + goto out_err; + } + + perf_evsel__set_sample_bit(cycles_evsel, CPU); + perf_evsel__set_sample_bit(cycles_evsel, TIME); + + /* Fourth event */ + err = parse_events(evlist, "dummy:u"); + if (err) { + pr_debug("Failed to parse event dummy:u\n"); + goto out_err; + } + + tracking_evsel = perf_evlist__last(evlist); + + perf_evlist__set_tracking_event(evlist, tracking_evsel); + + tracking_evsel->attr.freq = 0; + tracking_evsel->attr.sample_period = 1; + + perf_evsel__set_sample_bit(tracking_evsel, TIME); + + /* Config events */ + perf_evlist__config(evlist, &opts); + + /* Check moved event is still at the front */ + if (cycles_evsel != perf_evlist__first(evlist)) { + pr_debug("Front event no longer at front"); + goto out_err; + } + + /* Check tracking event is tracking */ + if (!tracking_evsel->attr.mmap || !tracking_evsel->attr.comm) { + pr_debug("Tracking event not tracking\n"); + goto out_err; + } + + /* Check non-tracking events are not tracking */ + evlist__for_each(evlist, evsel) { + if (evsel != tracking_evsel) { + if (evsel->attr.mmap || evsel->attr.comm) { + pr_debug("Non-tracking event is tracking\n"); + goto out_err; + } + } + } + + if (perf_evlist__open(evlist) < 0) { + fprintf(stderr, " (not supported)"); + err = 0; + goto out; + } + + err = perf_evlist__mmap(evlist, UINT_MAX, false); + if (err) { + pr_debug("perf_evlist__mmap failed!\n"); + goto out_err; + } + + perf_evlist__enable(evlist); + + err = perf_evlist__disable_event(evlist, cpu_clocks_evsel); + if (err) { + pr_debug("perf_evlist__disable_event failed!\n"); + goto out_err; + } + + err = spin_sleep(); + if (err) { + pr_debug("spin_sleep failed!\n"); + goto out_err; + } + + comm = "Test COMM 1"; + err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0); + if (err) { + pr_debug("PR_SET_NAME failed!\n"); + goto out_err; + } + + err = perf_evlist__disable_event(evlist, cycles_evsel); + if (err) { + pr_debug("perf_evlist__disable_event failed!\n"); + goto out_err; + } + + comm = "Test COMM 2"; + err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0); + if (err) { + pr_debug("PR_SET_NAME failed!\n"); + goto out_err; + } + + err = spin_sleep(); + if (err) { + pr_debug("spin_sleep failed!\n"); + goto out_err; + } + + comm = "Test COMM 3"; + err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0); + if (err) { + pr_debug("PR_SET_NAME failed!\n"); + goto out_err; + } + + err = perf_evlist__enable_event(evlist, cycles_evsel); + if (err) { + pr_debug("perf_evlist__disable_event failed!\n"); + goto out_err; + } + + comm = "Test COMM 4"; + err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0); + if (err) { + pr_debug("PR_SET_NAME failed!\n"); + goto out_err; + } + + err = spin_sleep(); + if (err) { + pr_debug("spin_sleep failed!\n"); + goto out_err; + } + + perf_evlist__disable(evlist); + + switch_tracking.switch_evsel = switch_evsel; + switch_tracking.cycles_evsel = cycles_evsel; + + err = process_events(evlist, &switch_tracking); + + zfree(&switch_tracking.tids); + + if (err) + goto out_err; + + /* Check all 4 comm events were seen i.e. that evsel->tracking works */ + if (!switch_tracking.comm_seen[0] || !switch_tracking.comm_seen[1] || + !switch_tracking.comm_seen[2] || !switch_tracking.comm_seen[3]) { + pr_debug("Missing comm events\n"); + goto out_err; + } + + /* Check cycles event got enabled */ + if (!switch_tracking.cycles_before_comm_1) { + pr_debug("Missing cycles events\n"); + goto out_err; + } + + /* Check cycles event got disabled */ + if (switch_tracking.cycles_between_comm_2_and_comm_3) { + pr_debug("cycles events even though event was disabled\n"); + goto out_err; + } + + /* Check cycles event got enabled again */ + if (!switch_tracking.cycles_after_comm_4) { + pr_debug("Missing cycles events\n"); + goto out_err; + } +out: + if (evlist) { + perf_evlist__disable(evlist); + perf_evlist__delete(evlist); + } else { + cpu_map__delete(cpus); + thread_map__delete(threads); + } + + return err; + +out_err: + err = -1; + goto out; +} diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 5ff3db3..3a8fedef 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -42,6 +42,7 @@ int test__task_exit(void) .uses_mmap = true, }; const char *argv[] = { "true", NULL }; + char sbuf[STRERR_BUFSIZE]; signal(SIGCHLD, sig_handler); @@ -82,13 +83,14 @@ int test__task_exit(void) err = perf_evlist__open(evlist); if (err < 0) { - pr_debug("Couldn't open the evlist: %s\n", strerror(-err)); + pr_debug("Couldn't open the evlist: %s\n", + strerror_r(-err, sbuf, sizeof(sbuf))); goto out_delete_evlist; } if (perf_evlist__mmap(evlist, 128, true) < 0) { pr_debug("failed to mmap events: %d (%s)\n", errno, - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } @@ -103,7 +105,7 @@ retry: } if (!exited || !nr_exit) { - poll(evlist->pollfd, evlist->nr_fds, -1); + perf_evlist__poll(evlist, -1); goto retry; } diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index ed64790..00e776a 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -48,6 +48,9 @@ int test__mmap_thread_lookup(void); int test__thread_mg_share(void); int test__hists_output(void); int test__hists_cumulate(void); +int test__switch_tracking(void); +int test__fdarray__filter(void); +int test__fdarray__add(void); #if defined(__x86_64__) || defined(__i386__) || defined(__arm__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c index 2b2e0db..b028499 100644 --- a/tools/perf/tests/thread-mg-share.c +++ b/tools/perf/tests/thread-mg-share.c @@ -2,6 +2,7 @@ #include "machine.h" #include "thread.h" #include "map.h" +#include "debug.h" int test__thread_mg_share(void) { diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 3ccf6e1..6680fa5 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -150,7 +150,7 @@ unsigned int ui_browser__rb_tree_refresh(struct ui_browser *browser) while (nd != NULL) { ui_browser__gotorc(browser, row, 0); browser->write(browser, nd, row); - if (++row == browser->height) + if (++row == browser->rows) break; nd = rb_next(nd); } @@ -166,7 +166,7 @@ bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row) void ui_browser__refresh_dimensions(struct ui_browser *browser) { browser->width = SLtt_Screen_Cols - 1; - browser->height = SLtt_Screen_Rows - 2; + browser->height = browser->rows = SLtt_Screen_Rows - 2; browser->y = 1; browser->x = 0; } @@ -250,7 +250,10 @@ int ui_browser__show(struct ui_browser *browser, const char *title, int err; va_list ap; - ui_browser__refresh_dimensions(browser); + if (browser->refresh_dimensions == NULL) + browser->refresh_dimensions = ui_browser__refresh_dimensions; + + browser->refresh_dimensions(browser); pthread_mutex_lock(&ui__lock); __ui_browser__show_title(browser, title); @@ -279,7 +282,7 @@ static void ui_browser__scrollbar_set(struct ui_browser *browser) { int height = browser->height, h = 0, pct = 0, col = browser->width, - row = browser->y - 1; + row = 0; if (browser->nr_entries > 1) { pct = ((browser->index * (browser->height - 1)) / @@ -367,7 +370,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs) if (key == K_RESIZE) { ui__refresh_dimensions(false); - ui_browser__refresh_dimensions(browser); + browser->refresh_dimensions(browser); __ui_browser__show_title(browser, browser->title); ui_helpline__puts(browser->helpline); continue; @@ -389,7 +392,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs) if (browser->index == browser->nr_entries - 1) break; ++browser->index; - if (browser->index == browser->top_idx + browser->height) { + if (browser->index == browser->top_idx + browser->rows) { ++browser->top_idx; browser->seek(browser, +1, SEEK_CUR); } @@ -405,10 +408,10 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs) break; case K_PGDN: case ' ': - if (browser->top_idx + browser->height > browser->nr_entries - 1) + if (browser->top_idx + browser->rows > browser->nr_entries - 1) break; - offset = browser->height; + offset = browser->rows; if (browser->index + offset > browser->nr_entries - 1) offset = browser->nr_entries - 1 - browser->index; browser->index += offset; @@ -419,10 +422,10 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs) if (browser->top_idx == 0) break; - if (browser->top_idx < browser->height) + if (browser->top_idx < browser->rows) offset = browser->top_idx; else - offset = browser->height; + offset = browser->rows; browser->index -= offset; browser->top_idx -= offset; @@ -432,7 +435,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs) ui_browser__reset_index(browser); break; case K_END: - offset = browser->height - 1; + offset = browser->rows - 1; if (offset >= browser->nr_entries) offset = browser->nr_entries - 1; @@ -462,7 +465,7 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *browser) if (!browser->filter || !browser->filter(browser, pos)) { ui_browser__gotorc(browser, row, 0); browser->write(browser, pos, row); - if (++row == browser->height) + if (++row == browser->rows) break; } } @@ -587,7 +590,7 @@ unsigned int ui_browser__argv_refresh(struct ui_browser *browser) if (!browser->filter || !browser->filter(browser, *pos)) { ui_browser__gotorc(browser, row, 0); browser->write(browser, pos, row); - if (++row == browser->height) + if (++row == browser->rows) break; } @@ -623,7 +626,7 @@ static void __ui_browser__line_arrow_up(struct ui_browser *browser, SLsmg_set_char_set(1); - if (start < browser->top_idx + browser->height) { + if (start < browser->top_idx + browser->rows) { row = start - browser->top_idx; ui_browser__gotorc(browser, row, column); SLsmg_write_char(SLSMG_LLCORN_CHAR); @@ -633,7 +636,7 @@ static void __ui_browser__line_arrow_up(struct ui_browser *browser, if (row-- == 0) goto out; } else - row = browser->height - 1; + row = browser->rows - 1; if (end > browser->top_idx) end_row = end - browser->top_idx; @@ -675,8 +678,8 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser, } else row = 0; - if (end >= browser->top_idx + browser->height) - end_row = browser->height - 1; + if (end >= browser->top_idx + browser->rows) + end_row = browser->rows - 1; else end_row = end - browser->top_idx; @@ -684,7 +687,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser, SLsmg_draw_vline(end_row - row + 1); ui_browser__gotorc(browser, end_row, column); - if (end < browser->top_idx + browser->height) { + if (end < browser->top_idx + browser->rows) { SLsmg_write_char(SLSMG_LLCORN_CHAR); ui_browser__gotorc(browser, end_row, column + 1); SLsmg_write_char(SLSMG_HLINE_CHAR); diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 03d4d62..92ae721 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -14,11 +14,12 @@ struct ui_browser { u64 index, top_idx; void *top, *entries; - u16 y, x, width, height; + u16 y, x, width, height, rows; int current_color; void *priv; const char *title; char *helpline; + void (*refresh_dimensions)(struct ui_browser *browser); unsigned int (*refresh)(struct ui_browser *browser); void (*write)(struct ui_browser *browser, void *entry, int row); void (*seek)(struct ui_browser *browser, off_t offset, int whence); diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index f0697a3..1e0a2fd 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); @@ -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; @@ -984,6 +994,7 @@ 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/header.c b/tools/perf/ui/browsers/header.c index 89c16b9..e8278c5 100644 --- a/tools/perf/ui/browsers/header.c +++ b/tools/perf/ui/browsers/header.c @@ -1,6 +1,7 @@ #include "util/cache.h" #include "util/debug.h" #include "ui/browser.h" +#include "ui/keysyms.h" #include "ui/ui.h" #include "ui/util.h" #include "ui/libslang.h" diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 04a229a..e6bb04b 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -10,6 +10,7 @@ #include "../../util/pstack.h" #include "../../util/sort.h" #include "../../util/util.h" +#include "../../util/top.h" #include "../../arch/common.h" #include "../browser.h" @@ -26,6 +27,7 @@ struct hist_browser { struct map_symbol *selection; int print_seq; bool show_dso; + bool show_headers; float min_pcnt; u64 nr_non_filtered_entries; u64 nr_callchain_rows; @@ -33,8 +35,9 @@ struct hist_browser { extern void hist_browser__init_hpp(void); -static int hists__browser_title(struct hists *hists, char *bf, size_t size, - const char *ev_name); +static int hists__browser_title(struct hists *hists, + struct hist_browser_timer *hbt, + char *bf, size_t size); static void hist_browser__update_nr_entries(struct hist_browser *hb); static struct rb_node *hists__filter_entries(struct rb_node *nd, @@ -57,11 +60,42 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb) return nr_entries + hb->nr_callchain_rows; } -static void hist_browser__refresh_dimensions(struct hist_browser *browser) +static void hist_browser__update_rows(struct hist_browser *hb) { + struct ui_browser *browser = &hb->b; + u16 header_offset = hb->show_headers ? 1 : 0, index_row; + + browser->rows = browser->height - header_offset; + /* + * Verify if we were at the last line and that line isn't + * visibe because we now show the header line(s). + */ + index_row = browser->index - browser->top_idx; + if (index_row >= browser->rows) + browser->index -= index_row - browser->rows + 1; +} + +static void hist_browser__refresh_dimensions(struct ui_browser *browser) +{ + struct hist_browser *hb = container_of(browser, struct hist_browser, b); + /* 3 == +/- toggle symbol before actual hist_entry rendering */ - browser->b.width = 3 + (hists__sort_list_width(browser->hists) + - sizeof("[k]")); + browser->width = 3 + (hists__sort_list_width(hb->hists) + sizeof("[k]")); + /* + * FIXME: Just keeping existing behaviour, but this really should be + * before updating browser->width, as it will invalidate the + * calculation above. Fix this and the fallout in another + * changeset. + */ + ui_browser__refresh_dimensions(browser); + hist_browser__update_rows(hb); +} + +static void hist_browser__gotorc(struct hist_browser *browser, int row, int column) +{ + u16 header_offset = browser->show_headers ? 1 : 0; + + ui_browser__gotorc(&browser->b, row + header_offset, column); } static void hist_browser__reset(struct hist_browser *browser) @@ -74,7 +108,7 @@ static void hist_browser__reset(struct hist_browser *browser) hist_browser__update_nr_entries(browser); browser->b.nr_entries = hist_browser__nr_entries(browser); - hist_browser__refresh_dimensions(browser); + hist_browser__refresh_dimensions(&browser->b); ui_browser__reset_index(&browser->b); } @@ -193,23 +227,30 @@ 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; - list_for_each_entry(chain, &node->val, list) + 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); + } callchain_node__init_have_children_rb_tree(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); } } @@ -346,7 +387,7 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser) "Or reduce the sampling frequency."); } -static int hist_browser__run(struct hist_browser *browser, const char *ev_name, +static int hist_browser__run(struct hist_browser *browser, struct hist_browser_timer *hbt) { int key; @@ -356,8 +397,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, browser->b.entries = &browser->hists->entries; browser->b.nr_entries = hist_browser__nr_entries(browser); - hist_browser__refresh_dimensions(browser); - hists__browser_title(browser->hists, title, sizeof(title), ev_name); + hists__browser_title(browser->hists, hbt, title, sizeof(title)); if (ui_browser__show(&browser->b, title, "Press '?' for help on key bindings") < 0) @@ -384,7 +424,8 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, ui_browser__warn_lost_events(&browser->b); } - hists__browser_title(browser->hists, title, sizeof(title), ev_name); + hists__browser_title(browser->hists, + hbt, title, sizeof(title)); ui_browser__show_title(&browser->b, title); continue; } @@ -393,10 +434,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, struct hist_entry *h = rb_entry(browser->b.top, struct hist_entry, rb_node); ui_helpline__pop(); - ui_helpline__fpush("%d: nr_ent=(%d,%d), height=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", + ui_helpline__fpush("%d: nr_ent=(%d,%d), rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", seq++, browser->b.nr_entries, browser->hists->nr_entries, - browser->b.height, + browser->b.rows, browser->b.index, browser->b.top_idx, h->row_offset, h->nr_rows); @@ -410,6 +451,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, /* Expand the whole world. */ hist_browser__set_folding(browser, true); break; + case 'H': + browser->show_headers = !browser->show_headers; + hist_browser__update_rows(browser); + break; case K_ENTER: if (hist_browser__toggle_fold(browser)) break; @@ -423,43 +468,90 @@ out: return key; } -static char *callchain_list__sym_name(struct callchain_list *cl, - char *bf, size_t bfsize, bool show_dso) +struct callchain_print_arg { + /* for hists browser */ + off_t row_offset; + bool is_current_entry; + + /* for file dump */ + FILE *fp; + int printed; +}; + +typedef void (*print_callchain_entry_fn)(struct hist_browser *browser, + struct callchain_list *chain, + const char *str, int offset, + unsigned short row, + struct callchain_print_arg *arg); + +static void hist_browser__show_callchain_entry(struct hist_browser *browser, + struct callchain_list *chain, + const char *str, int offset, + unsigned short row, + struct callchain_print_arg *arg) { - int printed; + int color, width; + char folded_sign = callchain_list__folded(chain); + + color = HE_COLORSET_NORMAL; + width = browser->b.width - (offset + 2); + if (ui_browser__is_current_entry(&browser->b, row)) { + browser->selection = &chain->ms; + color = HE_COLORSET_SELECTED; + arg->is_current_entry = true; + } - if (cl->ms.sym) - printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name); - else - printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip); + ui_browser__set_color(&browser->b, color); + hist_browser__gotorc(browser, row, 0); + slsmg_write_nstring(" ", offset); + slsmg_printf("%c ", folded_sign); + slsmg_write_nstring(str, width); +} + +static void hist_browser__fprintf_callchain_entry(struct hist_browser *b __maybe_unused, + struct callchain_list *chain, + const char *str, int offset, + unsigned short row __maybe_unused, + struct callchain_print_arg *arg) +{ + char folded_sign = callchain_list__folded(chain); - if (show_dso) - scnprintf(bf + printed, bfsize - printed, " %s", - cl->ms.map ? cl->ms.map->dso->short_name : "unknown"); + arg->printed += fprintf(arg->fp, "%*s%c %s\n", offset, " ", + folded_sign, str); +} + +typedef bool (*check_output_full_fn)(struct hist_browser *browser, + unsigned short row); - return bf; +static bool hist_browser__check_output_full(struct hist_browser *browser, + unsigned short row) +{ + return browser->b.rows == row; +} + +static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_unused, + unsigned short row __maybe_unused) +{ + return false; } #define LEVEL_OFFSET_STEP 3 -static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browser, - struct callchain_node *chain_node, - u64 total, int level, - unsigned short row, - off_t *row_offset, - bool *is_current_entry) +static int hist_browser__show_callchain(struct hist_browser *browser, + struct rb_root *root, int level, + unsigned short row, u64 total, + print_callchain_entry_fn print, + struct callchain_print_arg *arg, + check_output_full_fn is_output_full) { struct rb_node *node; - int first_row = row, width, offset = level * LEVEL_OFFSET_STEP; - u64 new_total, remaining; + int first_row = row, offset = level * LEVEL_OFFSET_STEP; + u64 new_total; + bool need_percent; - if (callchain_param.mode == CHAIN_GRAPH_REL) - new_total = chain_node->children_hit; - else - new_total = total; + node = rb_first(root); + need_percent = !!rb_next(node); - remaining = new_total; - node = rb_first(&chain_node->rb_root); while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); struct rb_node *next = rb_next(node); @@ -469,30 +561,28 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse int first = true; int extra_offset = 0; - remaining -= cumul; - list_for_each_entry(chain, &child->val, list) { char bf[1024], *alloc_str; const char *str; - int color; bool was_first = first; if (first) first = false; - else + else if (need_percent) extra_offset = LEVEL_OFFSET_STEP; folded_sign = callchain_list__folded(chain); - if (*row_offset != 0) { - --*row_offset; + if (arg->row_offset != 0) { + arg->row_offset--; goto do_next; } alloc_str = NULL; str = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso); - if (was_first) { - double percent = cumul * 100.0 / new_total; + + if (was_first && need_percent) { + double percent = cumul * 100.0 / total; if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0) str = "Not enough memory!"; @@ -500,22 +590,11 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse str = alloc_str; } - color = HE_COLORSET_NORMAL; - width = browser->b.width - (offset + extra_offset + 2); - if (ui_browser__is_current_entry(&browser->b, row)) { - browser->selection = &chain->ms; - color = HE_COLORSET_SELECTED; - *is_current_entry = true; - } + print(browser, chain, str, offset + extra_offset, row, arg); - ui_browser__set_color(&browser->b, color); - ui_browser__gotorc(&browser->b, row, 0); - slsmg_write_nstring(" ", offset + extra_offset); - slsmg_printf("%c ", folded_sign); - slsmg_write_nstring(str, width); free(alloc_str); - if (++row == browser->b.height) + if (is_output_full(browser, ++row)) goto out; do_next: if (folded_sign == '+') @@ -524,89 +603,21 @@ do_next: if (folded_sign == '-') { const int new_level = level + (extra_offset ? 2 : 1); - row += hist_browser__show_callchain_node_rb_tree(browser, child, new_total, - new_level, row, row_offset, - is_current_entry); - } - if (row == browser->b.height) - goto out; - node = next; - } -out: - return row - first_row; -} - -static int hist_browser__show_callchain_node(struct hist_browser *browser, - struct callchain_node *node, - int level, unsigned short row, - off_t *row_offset, - bool *is_current_entry) -{ - struct callchain_list *chain; - int first_row = row, - offset = level * LEVEL_OFFSET_STEP, - width = browser->b.width - offset; - char folded_sign = ' '; - - list_for_each_entry(chain, &node->val, list) { - char bf[1024], *s; - int color; - folded_sign = callchain_list__folded(chain); - - if (*row_offset != 0) { - --*row_offset; - continue; - } + if (callchain_param.mode == CHAIN_GRAPH_REL) + new_total = child->children_hit; + else + new_total = total; - color = HE_COLORSET_NORMAL; - if (ui_browser__is_current_entry(&browser->b, row)) { - browser->selection = &chain->ms; - color = HE_COLORSET_SELECTED; - *is_current_entry = true; + row += hist_browser__show_callchain(browser, &child->rb_root, + new_level, row, new_total, + print, arg, is_output_full); } - - s = callchain_list__sym_name(chain, bf, sizeof(bf), - browser->show_dso); - ui_browser__gotorc(&browser->b, row, 0); - ui_browser__set_color(&browser->b, color); - slsmg_write_nstring(" ", offset); - slsmg_printf("%c ", folded_sign); - slsmg_write_nstring(s, width - 2); - - if (++row == browser->b.height) - goto out; - } - - if (folded_sign == '-') - row += hist_browser__show_callchain_node_rb_tree(browser, node, - browser->hists->stats.total_period, - level + 1, row, - row_offset, - is_current_entry); -out: - return row - first_row; -} - -static int hist_browser__show_callchain(struct hist_browser *browser, - struct rb_root *chain, - int level, unsigned short row, - off_t *row_offset, - bool *is_current_entry) -{ - struct rb_node *nd; - int first_row = row; - - for (nd = rb_first(chain); nd; nd = rb_next(nd)) { - struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); - - row += hist_browser__show_callchain_node(browser, node, level, - row, row_offset, - is_current_entry); - if (row == browser->b.height) + if (is_output_full(browser, row)) break; + node = next; } - +out: return row - first_row; } @@ -619,17 +630,18 @@ struct hpp_arg { static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...) { struct hpp_arg *arg = hpp->ptr; - int ret; + int ret, len; va_list args; double percent; va_start(args, fmt); + len = va_arg(args, int); percent = va_arg(args, double); va_end(args); ui_browser__set_percent_color(arg->b, percent, arg->current_entry); - ret = scnprintf(hpp->buf, hpp->size, fmt, percent); + ret = scnprintf(hpp->buf, hpp->size, fmt, len, percent); slsmg_printf("%s", hpp->buf); advance_hpp(hpp, ret); @@ -643,12 +655,12 @@ static u64 __hpp_get_##_field(struct hist_entry *he) \ } \ \ static int \ -hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\ +hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ - return __hpp__fmt(hpp, he, __hpp_get_##_field, " %6.2f%%", \ - __hpp__slsmg_color_printf, true); \ + return hpp__fmt(fmt, hpp, he, __hpp_get_##_field, " %*.2f%%", \ + __hpp__slsmg_color_printf, true); \ } #define __HPP_COLOR_ACC_PERCENT_FN(_type, _field) \ @@ -658,18 +670,20 @@ static u64 __hpp_get_acc_##_field(struct hist_entry *he) \ } \ \ static int \ -hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\ +hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ if (!symbol_conf.cumulate_callchain) { \ - int ret = scnprintf(hpp->buf, hpp->size, "%8s", "N/A"); \ + int len = fmt->user_len ?: fmt->len; \ + int ret = scnprintf(hpp->buf, hpp->size, \ + "%*s", len, "N/A"); \ slsmg_printf("%s", hpp->buf); \ \ return ret; \ } \ - return __hpp__fmt(hpp, he, __hpp_get_acc_##_field, " %6.2f%%", \ - __hpp__slsmg_color_printf, true); \ + return hpp__fmt(fmt, hpp, he, __hpp_get_acc_##_field, \ + " %*.2f%%", __hpp__slsmg_color_printf, true); \ } __HPP_COLOR_PERCENT_FN(overhead, period) @@ -733,7 +747,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, .ptr = &arg, }; - ui_browser__gotorc(&browser->b, row, 0); + hist_browser__gotorc(browser, row, 0); perf_hpp__for_each_format(fmt) { if (perf_hpp__should_skip(fmt)) @@ -777,17 +791,79 @@ static int hist_browser__show_entry(struct hist_browser *browser, } else --row_offset; - if (folded_sign == '-' && row != browser->b.height) { - printed += hist_browser__show_callchain(browser, &entry->sorted_chain, - 1, row, &row_offset, - ¤t_entry); - if (current_entry) + if (folded_sign == '-' && row != browser->b.rows) { + u64 total = hists__total_period(entry->hists); + struct callchain_print_arg arg = { + .row_offset = row_offset, + .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, + hist_browser__check_output_full); + + if (arg.is_current_entry) browser->he_selection = entry; } return printed; } +static int advance_hpp_check(struct perf_hpp *hpp, int inc) +{ + advance_hpp(hpp, inc); + return hpp->size <= 0; +} + +static int hists__scnprintf_headers(char *buf, size_t size, struct hists *hists) +{ + struct perf_hpp dummy_hpp = { + .buf = buf, + .size = size, + }; + struct perf_hpp_fmt *fmt; + size_t ret = 0; + + if (symbol_conf.use_callchain) { + ret = scnprintf(buf, size, " "); + if (advance_hpp_check(&dummy_hpp, ret)) + return ret; + } + + perf_hpp__for_each_format(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; + + ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists)); + if (advance_hpp_check(&dummy_hpp, ret)) + break; + + ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " "); + if (advance_hpp_check(&dummy_hpp, ret)) + break; + } + + return ret; +} + +static void hist_browser__show_headers(struct hist_browser *browser) +{ + char headers[1024]; + + hists__scnprintf_headers(headers, sizeof(headers), browser->hists); + ui_browser__gotorc(&browser->b, 0, 0); + ui_browser__set_color(&browser->b, HE_COLORSET_ROOT); + slsmg_write_nstring(headers, browser->b.width + 1); +} + static void ui_browser__hists_init_top(struct ui_browser *browser) { if (browser->top == NULL) { @@ -801,9 +877,15 @@ static void ui_browser__hists_init_top(struct ui_browser *browser) static unsigned int hist_browser__refresh(struct ui_browser *browser) { unsigned row = 0; + u16 header_offset = 0; struct rb_node *nd; struct hist_browser *hb = container_of(browser, struct hist_browser, b); + if (hb->show_headers) { + hist_browser__show_headers(hb); + header_offset = 1; + } + ui_browser__hists_init_top(browser); for (nd = browser->top; nd; nd = rb_next(nd)) { @@ -818,11 +900,11 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser) continue; row += hist_browser__show_entry(hb, h, row); - if (row == browser->height) + if (row == browser->rows) break; } - return row; + return row + header_offset; } static struct rb_node *hists__filter_entries(struct rb_node *nd, @@ -984,113 +1066,21 @@ do_offset: } } -static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *browser, - struct callchain_node *chain_node, - u64 total, int level, - FILE *fp) -{ - struct rb_node *node; - int offset = level * LEVEL_OFFSET_STEP; - u64 new_total, remaining; - int printed = 0; - - if (callchain_param.mode == CHAIN_GRAPH_REL) - new_total = chain_node->children_hit; - else - new_total = total; - - remaining = new_total; - node = rb_first(&chain_node->rb_root); - while (node) { - struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); - struct rb_node *next = rb_next(node); - u64 cumul = callchain_cumul_hits(child); - struct callchain_list *chain; - char folded_sign = ' '; - int first = true; - int extra_offset = 0; - - remaining -= cumul; - - list_for_each_entry(chain, &child->val, list) { - char bf[1024], *alloc_str; - const char *str; - bool was_first = first; - - if (first) - first = false; - else - extra_offset = LEVEL_OFFSET_STEP; - - folded_sign = callchain_list__folded(chain); - - alloc_str = NULL; - str = callchain_list__sym_name(chain, bf, sizeof(bf), - browser->show_dso); - if (was_first) { - double percent = cumul * 100.0 / new_total; - - if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0) - str = "Not enough memory!"; - else - str = alloc_str; - } - - printed += fprintf(fp, "%*s%c %s\n", offset + extra_offset, " ", folded_sign, str); - free(alloc_str); - if (folded_sign == '+') - break; - } - - if (folded_sign == '-') { - const int new_level = level + (extra_offset ? 2 : 1); - printed += hist_browser__fprintf_callchain_node_rb_tree(browser, child, new_total, - new_level, fp); - } - - node = next; - } - - return printed; -} - -static int hist_browser__fprintf_callchain_node(struct hist_browser *browser, - struct callchain_node *node, - int level, FILE *fp) -{ - struct callchain_list *chain; - int offset = level * LEVEL_OFFSET_STEP; - char folded_sign = ' '; - int printed = 0; - - list_for_each_entry(chain, &node->val, list) { - char bf[1024], *s; - - folded_sign = callchain_list__folded(chain); - s = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso); - printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s); - } - - if (folded_sign == '-') - printed += hist_browser__fprintf_callchain_node_rb_tree(browser, node, - browser->hists->stats.total_period, - level + 1, fp); - return printed; -} - static int hist_browser__fprintf_callchain(struct hist_browser *browser, - struct rb_root *chain, int level, FILE *fp) + struct hist_entry *he, FILE *fp) { - struct rb_node *nd; - int printed = 0; - - for (nd = rb_first(chain); nd; nd = rb_next(nd)) { - struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); + u64 total = hists__total_period(he->hists); + struct callchain_print_arg arg = { + .fp = fp, + }; - printed += hist_browser__fprintf_callchain_node(browser, node, level, fp); - } + if (symbol_conf.cumulate_callchain) + total = he->stat_acc->period; - return printed; + hist_browser__show_callchain(browser, &he->sorted_chain, 1, 0, total, + hist_browser__fprintf_callchain_entry, &arg, + hist_browser__check_dump_full); + return arg.printed; } static int hist_browser__fprintf_entry(struct hist_browser *browser, @@ -1129,7 +1119,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, printed += fprintf(fp, "%s\n", rtrim(s)); if (folded_sign == '-') - printed += hist_browser__fprintf_callchain(browser, &he->sorted_chain, 1, fp); + printed += hist_browser__fprintf_callchain(browser, he, fp); return printed; } @@ -1191,8 +1181,10 @@ static struct hist_browser *hist_browser__new(struct hists *hists) if (browser) { browser->hists = hists; browser->b.refresh = hist_browser__refresh; + browser->b.refresh_dimensions = hist_browser__refresh_dimensions; browser->b.seek = ui_browser__hists_seek; browser->b.use_navkeypressed = true; + browser->show_headers = symbol_conf.show_hist_headers; } return browser; @@ -1213,8 +1205,15 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser return browser->he_selection->thread; } -static int hists__browser_title(struct hists *hists, char *bf, size_t size, - const char *ev_name) +/* Check whether the browser is for 'top' or 'report' */ +static inline bool is_report_browser(void *timer) +{ + return timer == NULL; +} + +static int hists__browser_title(struct hists *hists, + struct hist_browser_timer *hbt, + char *bf, size_t size) { char unit; int printed; @@ -1223,6 +1222,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size, unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; u64 nr_events = hists->stats.total_period; struct perf_evsel *evsel = hists_to_evsel(hists); + const char *ev_name = perf_evsel__name(evsel); char buf[512]; size_t buflen = sizeof(buf); @@ -1238,19 +1238,21 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size, ev_name = buf; for_each_group_member(pos, evsel) { + struct hists *pos_hists = evsel__hists(pos); + if (symbol_conf.filter_relative) { - nr_samples += pos->hists.stats.nr_non_filtered_samples; - nr_events += pos->hists.stats.total_non_filtered_period; + nr_samples += pos_hists->stats.nr_non_filtered_samples; + nr_events += pos_hists->stats.total_non_filtered_period; } else { - nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; - nr_events += pos->hists.stats.total_period; + nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE]; + nr_events += pos_hists->stats.total_period; } } } 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); @@ -1265,6 +1267,13 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size, if (dso) printed += scnprintf(bf + printed, size - printed, ", DSO: %s", dso->short_name); + if (!is_report_browser(hbt)) { + struct perf_top *top = hbt->arg; + + if (top->zero) + printed += scnprintf(bf + printed, size - printed, " [z]"); + } + return printed; } @@ -1276,12 +1285,6 @@ static inline void free_popup_options(char **options, int n) zfree(&options[i]); } -/* Check whether the browser is for 'top' or 'report' */ -static inline bool is_report_browser(void *timer) -{ - return timer == NULL; -} - /* * Only runtime switching of perf data file will make "input_name" point * to a malloced buffer. So add "is_input_name_malloced" flag to decide @@ -1390,13 +1393,13 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb) } static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, - const char *helpline, const char *ev_name, + const char *helpline, bool left_exits, struct hist_browser_timer *hbt, float min_pcnt, struct perf_session_env *env) { - struct hists *hists = &evsel->hists; + struct hists *hists = evsel__hists(evsel); struct hist_browser *browser = hist_browser__new(hists); struct branch_info *bi; struct pstack *fstack; @@ -1406,6 +1409,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, char buf[64]; char script_opt[64]; int delay_secs = hbt ? hbt->refresh : 0; + struct perf_hpp_fmt *fmt; #define HIST_BROWSER_HELP_COMMON \ "h/?/F1 Show this window\n" \ @@ -1422,6 +1426,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "d Zoom into current DSO\n" \ "E Expand all callchains\n" \ "F Toggle percentage of filtered entries\n" \ + "H Display column headers\n" \ /* help messages are sorted by lexical order of the hotkey */ const char report_help[] = HIST_BROWSER_HELP_COMMON @@ -1436,6 +1441,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "P Print histograms to perf.hist.N\n" "t Zoom into current Thread\n" "V Verbose (DSO names in callchains, etc)\n" + "z Toggle zeroing of samples\n" "/ Filter symbol by name"; if (browser == NULL) @@ -1454,6 +1460,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, memset(options, 0, sizeof(options)); + perf_hpp__for_each_format(fmt) + perf_hpp__reset_width(fmt, hists); + + if (symbol_conf.col_width_list_str) + perf_hpp__set_user_width(symbol_conf.col_width_list_str); + while (1) { const struct thread *thread = NULL; const struct dso *dso = NULL; @@ -1465,7 +1477,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, nr_options = 0; - key = hist_browser__run(browser, ev_name, hbt); + key = hist_browser__run(browser, hbt); if (browser->he_selection != NULL) { thread = hist_browser__selected_thread(browser); @@ -1530,6 +1542,13 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, case 'F': symbol_conf.filter_relative ^= 1; continue; + case 'z': + if (!is_report_browser(hbt)) { + struct perf_top *top = hbt->arg; + + top->zero = !top->zero; + } + continue; case K_F1: case 'h': case '?': @@ -1795,8 +1814,9 @@ static void perf_evsel_menu__write(struct ui_browser *browser, struct perf_evsel_menu *menu = container_of(browser, struct perf_evsel_menu, b); struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node); + struct hists *hists = evsel__hists(evsel); bool current_entry = ui_browser__is_current_entry(browser, row); - unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + unsigned long nr_events = hists->stats.nr_events[PERF_RECORD_SAMPLE]; const char *ev_name = perf_evsel__name(evsel); char bf[256], unit; const char *warn = " "; @@ -1811,7 +1831,8 @@ static void perf_evsel_menu__write(struct ui_browser *browser, ev_name = perf_evsel__group_name(evsel); for_each_group_member(pos, evsel) { - nr_events += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + struct hists *pos_hists = evsel__hists(pos); + nr_events += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE]; } } @@ -1820,7 +1841,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser, unit, unit == ' ' ? "" : " ", ev_name); slsmg_printf("%s", bf); - nr_events = evsel->hists.stats.nr_events[PERF_RECORD_LOST]; + nr_events = hists->stats.nr_events[PERF_RECORD_LOST]; if (nr_events != 0) { menu->lost_events = true; if (!current_entry) @@ -1843,7 +1864,7 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu, { struct perf_evlist *evlist = menu->b.priv; struct perf_evsel *pos; - const char *ev_name, *title = "Available samples"; + const char *title = "Available samples"; int delay_secs = hbt ? hbt->refresh : 0; int key; @@ -1876,9 +1897,8 @@ browse_hists: */ if (hbt) hbt->timer(hbt->arg); - ev_name = perf_evsel__name(pos); key = perf_evsel__hists_browse(pos, nr_events, help, - ev_name, true, hbt, + true, hbt, menu->min_pcnt, menu->env); ui_browser__show_title(&menu->b, title); @@ -1982,10 +2002,9 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, single_entry: if (nr_entries == 1) { struct perf_evsel *first = perf_evlist__first(evlist); - const char *ev_name = perf_evsel__name(first); return perf_evsel__hists_browse(first, nr_entries, help, - ev_name, false, hbt, min_pcnt, + false, hbt, min_pcnt, env); } diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 6ca60e4..4b3585e 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -11,6 +11,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...) { int ret = 0; + int len; va_list args; double percent; const char *markup; @@ -18,6 +19,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...) size_t size = hpp->size; va_start(args, fmt); + len = va_arg(args, int); percent = va_arg(args, double); va_end(args); @@ -25,7 +27,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...) if (markup) ret += scnprintf(buf, size, markup); - ret += scnprintf(buf + ret, size - ret, fmt, percent); + ret += scnprintf(buf + ret, size - ret, fmt, len, percent); if (markup) ret += scnprintf(buf + ret, size - ret, "</span>"); @@ -39,12 +41,12 @@ static u64 he_get_##_field(struct hist_entry *he) \ return he->stat._field; \ } \ \ -static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ +static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ - return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \ - __percent_color_snprintf, true); \ + return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%", \ + __percent_color_snprintf, true); \ } #define __HPP_COLOR_ACC_PERCENT_FN(_type, _field) \ @@ -57,8 +59,8 @@ static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ - return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%", \ - __percent_color_snprintf, true); \ + return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", \ + __percent_color_snprintf, true); \ } __HPP_COLOR_PERCENT_FN(overhead, period) @@ -87,15 +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) { @@ -126,7 +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) { @@ -205,10 +198,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, if (perf_hpp__is_sort_entry(fmt)) sym_col = col_idx; - fmt->header(fmt, &hpp, hists_to_evsel(hists)); - gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), - -1, ltrim(s), + -1, fmt->name, renderer, "markup", col_idx++, NULL); } @@ -319,7 +310,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, gtk_container_add(GTK_CONTAINER(window), vbox); evlist__for_each(evlist, pos) { - struct hists *hists = &pos->hists; + struct hists *hists = evsel__hists(pos); const char *evname = perf_evsel__name(pos); GtkWidget *scrolled_window; GtkWidget *tab_label; diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 498adb2..dc0d095 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -15,9 +15,9 @@ __ret; \ }) -int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, - hpp_field_fn get_field, const char *fmt, - hpp_snprint_fn print_fn, bool fmt_percent) +static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, + hpp_field_fn get_field, const char *fmt, int len, + hpp_snprint_fn print_fn, bool fmt_percent) { int ret; struct hists *hists = he->hists; @@ -32,9 +32,9 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, if (total) percent = 100.0 * get_field(he) / total; - ret = hpp__call_print_fn(hpp, print_fn, fmt, percent); + ret = hpp__call_print_fn(hpp, print_fn, fmt, len, percent); } else - ret = hpp__call_print_fn(hpp, print_fn, fmt, get_field(he)); + ret = hpp__call_print_fn(hpp, print_fn, fmt, len, get_field(he)); if (perf_evsel__is_group_event(evsel)) { int prev_idx, idx_delta; @@ -60,19 +60,19 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, */ if (fmt_percent) { ret += hpp__call_print_fn(hpp, print_fn, - fmt, 0.0); + fmt, len, 0.0); } else { ret += hpp__call_print_fn(hpp, print_fn, - fmt, 0ULL); + fmt, len, 0ULL); } } if (fmt_percent) { - ret += hpp__call_print_fn(hpp, print_fn, fmt, + ret += hpp__call_print_fn(hpp, print_fn, fmt, len, 100.0 * period / total); } else { ret += hpp__call_print_fn(hpp, print_fn, fmt, - period); + len, period); } prev_idx = perf_evsel__group_idx(evsel); @@ -86,10 +86,10 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, */ if (fmt_percent) { ret += hpp__call_print_fn(hpp, print_fn, - fmt, 0.0); + fmt, len, 0.0); } else { ret += hpp__call_print_fn(hpp, print_fn, - fmt, 0ULL); + fmt, len, 0ULL); } } } @@ -104,16 +104,35 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, return ret; } -int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he, - hpp_field_fn get_field, const char *fmt, - hpp_snprint_fn print_fn, bool fmt_percent) +int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he, hpp_field_fn get_field, + const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent) +{ + int len = fmt->user_len ?: fmt->len; + + if (symbol_conf.field_sep) { + return __hpp__fmt(hpp, he, get_field, fmtstr, 1, + print_fn, fmt_percent); + } + + if (fmt_percent) + len -= 2; /* 2 for a space and a % sign */ + else + len -= 1; + + return __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent); +} + +int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he, hpp_field_fn get_field, + const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent) { if (!symbol_conf.cumulate_callchain) { - return snprintf(hpp->buf, hpp->size, "%*s", - fmt_percent ? 8 : 12, "N/A"); + int len = fmt->user_len ?: fmt->len; + return snprintf(hpp->buf, hpp->size, " %*s", len - 1, "N/A"); } - return __hpp__fmt(hpp, he, get_field, fmt, print_fn, fmt_percent); + return hpp__fmt(fmt, hpp, he, get_field, fmtstr, print_fn, fmt_percent); } static int field_cmp(u64 field_a, u64 field_b) @@ -143,8 +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; @@ -190,30 +209,26 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b, return ret; } -#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ -static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ - struct perf_hpp *hpp, \ - struct perf_evsel *evsel) \ -{ \ - int len = _min_width; \ - \ - if (symbol_conf.event_group) \ - len = max(len, evsel->nr_members * _unit_width); \ - \ - return scnprintf(hpp->buf, hpp->size, "%*s", len, _str); \ -} - -#define __HPP_WIDTH_FN(_type, _min_width, _unit_width) \ -static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ - struct perf_hpp *hpp __maybe_unused, \ - struct perf_evsel *evsel) \ -{ \ - int len = _min_width; \ - \ - if (symbol_conf.event_group) \ - len = max(len, evsel->nr_members * _unit_width); \ - \ - return len; \ +static int hpp__width_fn(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused, + struct perf_evsel *evsel) +{ + int len = fmt->user_len ?: fmt->len; + + if (symbol_conf.event_group) + len = max(len, evsel->nr_members * fmt->len); + + if (len < (int)strlen(fmt->name)) + len = strlen(fmt->name); + + return len; +} + +static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel) +{ + int len = hpp__width_fn(fmt, hpp, evsel); + return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name); } static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...) @@ -221,11 +236,12 @@ static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...) va_list args; ssize_t ssize = hpp->size; double percent; - int ret; + int ret, len; va_start(args, fmt); + len = va_arg(args, int); percent = va_arg(args, double); - ret = value_color_snprintf(hpp->buf, hpp->size, fmt, percent); + ret = percent_color_len_snprintf(hpp->buf, hpp->size, fmt, len, percent); va_end(args); return (ret >= ssize) ? (ssize - 1) : ret; @@ -250,20 +266,19 @@ static u64 he_get_##_field(struct hist_entry *he) \ return he->stat._field; \ } \ \ -static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ +static int hpp__color_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ - return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \ - hpp_color_scnprintf, true); \ + return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%", \ + hpp_color_scnprintf, true); \ } #define __HPP_ENTRY_PERCENT_FN(_type, _field) \ -static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \ +static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ - const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \ - return __hpp__fmt(hpp, he, he_get_##_field, fmt, \ - hpp_entry_scnprintf, true); \ + return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%", \ + hpp_entry_scnprintf, true); \ } #define __HPP_SORT_FN(_type, _field) \ @@ -278,20 +293,19 @@ static u64 he_get_acc_##_field(struct hist_entry *he) \ return he->stat_acc->_field; \ } \ \ -static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ +static int hpp__color_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ - return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%", \ - hpp_color_scnprintf, true); \ + return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", \ + hpp_color_scnprintf, true); \ } #define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field) \ -static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \ +static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ - const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \ - return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, fmt, \ - hpp_entry_scnprintf, true); \ + return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", \ + hpp_entry_scnprintf, true); \ } #define __HPP_SORT_ACC_FN(_type, _field) \ @@ -306,12 +320,11 @@ static u64 he_get_raw_##_field(struct hist_entry *he) \ return he->stat._field; \ } \ \ -static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \ +static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ - const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64; \ - return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, \ - hpp_entry_scnprintf, false); \ + return hpp__fmt(fmt, hpp, he, he_get_raw_##_field, " %*"PRIu64, \ + hpp_entry_scnprintf, false); \ } #define __HPP_SORT_RAW_FN(_type, _field) \ @@ -321,37 +334,29 @@ static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ } -#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width) \ -__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ -__HPP_WIDTH_FN(_type, _min_width, _unit_width) \ +#define HPP_PERCENT_FNS(_type, _field) \ __HPP_COLOR_PERCENT_FN(_type, _field) \ __HPP_ENTRY_PERCENT_FN(_type, _field) \ __HPP_SORT_FN(_type, _field) -#define HPP_PERCENT_ACC_FNS(_type, _str, _field, _min_width, _unit_width)\ -__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ -__HPP_WIDTH_FN(_type, _min_width, _unit_width) \ +#define HPP_PERCENT_ACC_FNS(_type, _field) \ __HPP_COLOR_ACC_PERCENT_FN(_type, _field) \ __HPP_ENTRY_ACC_PERCENT_FN(_type, _field) \ __HPP_SORT_ACC_FN(_type, _field) -#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width) \ -__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ -__HPP_WIDTH_FN(_type, _min_width, _unit_width) \ +#define HPP_RAW_FNS(_type, _field) \ __HPP_ENTRY_RAW_FN(_type, _field) \ __HPP_SORT_RAW_FN(_type, _field) -__HPP_HEADER_FN(overhead_self, "Self", 8, 8) - -HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8) -HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8) -HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8) -HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8) -HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8) -HPP_PERCENT_ACC_FNS(overhead_acc, "Children", period, 8, 8) +HPP_PERCENT_FNS(overhead, period) +HPP_PERCENT_FNS(overhead_sys, period_sys) +HPP_PERCENT_FNS(overhead_us, period_us) +HPP_PERCENT_FNS(overhead_guest_sys, period_guest_sys) +HPP_PERCENT_FNS(overhead_guest_us, period_guest_us) +HPP_PERCENT_ACC_FNS(overhead_acc, period) -HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12) -HPP_RAW_FNS(period, "Period", period, 12, 12) +HPP_RAW_FNS(samples, nr_events) +HPP_RAW_FNS(period, period) static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused, struct hist_entry *b __maybe_unused) @@ -359,47 +364,50 @@ static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused, return 0; } -#define HPP__COLOR_PRINT_FNS(_name) \ +#define HPP__COLOR_PRINT_FNS(_name, _fn) \ { \ - .header = hpp__header_ ## _name, \ - .width = hpp__width_ ## _name, \ - .color = hpp__color_ ## _name, \ - .entry = hpp__entry_ ## _name, \ + .name = _name, \ + .header = hpp__header_fn, \ + .width = hpp__width_fn, \ + .color = hpp__color_ ## _fn, \ + .entry = hpp__entry_ ## _fn, \ .cmp = hpp__nop_cmp, \ .collapse = hpp__nop_cmp, \ - .sort = hpp__sort_ ## _name, \ + .sort = hpp__sort_ ## _fn, \ } -#define HPP__COLOR_ACC_PRINT_FNS(_name) \ +#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn) \ { \ - .header = hpp__header_ ## _name, \ - .width = hpp__width_ ## _name, \ - .color = hpp__color_ ## _name, \ - .entry = hpp__entry_ ## _name, \ + .name = _name, \ + .header = hpp__header_fn, \ + .width = hpp__width_fn, \ + .color = hpp__color_ ## _fn, \ + .entry = hpp__entry_ ## _fn, \ .cmp = hpp__nop_cmp, \ .collapse = hpp__nop_cmp, \ - .sort = hpp__sort_ ## _name, \ + .sort = hpp__sort_ ## _fn, \ } -#define HPP__PRINT_FNS(_name) \ +#define HPP__PRINT_FNS(_name, _fn) \ { \ - .header = hpp__header_ ## _name, \ - .width = hpp__width_ ## _name, \ - .entry = hpp__entry_ ## _name, \ + .name = _name, \ + .header = hpp__header_fn, \ + .width = hpp__width_fn, \ + .entry = hpp__entry_ ## _fn, \ .cmp = hpp__nop_cmp, \ .collapse = hpp__nop_cmp, \ - .sort = hpp__sort_ ## _name, \ + .sort = hpp__sort_ ## _fn, \ } struct perf_hpp_fmt perf_hpp__format[] = { - HPP__COLOR_PRINT_FNS(overhead), - HPP__COLOR_PRINT_FNS(overhead_sys), - HPP__COLOR_PRINT_FNS(overhead_us), - HPP__COLOR_PRINT_FNS(overhead_guest_sys), - HPP__COLOR_PRINT_FNS(overhead_guest_us), - HPP__COLOR_ACC_PRINT_FNS(overhead_acc), - HPP__PRINT_FNS(samples), - HPP__PRINT_FNS(period) + HPP__COLOR_PRINT_FNS("Overhead", overhead), + HPP__COLOR_PRINT_FNS("sys", overhead_sys), + HPP__COLOR_PRINT_FNS("usr", overhead_us), + HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys), + HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us), + HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc), + HPP__PRINT_FNS("Samples", samples), + HPP__PRINT_FNS("Period", period) }; LIST_HEAD(perf_hpp__list); @@ -444,14 +452,12 @@ void perf_hpp__init(void) /* * If user specified field order, no need to setup default fields. */ - if (field_order) + if (is_strict_order(field_order)) return; if (symbol_conf.cumulate_callchain) { perf_hpp__column_enable(PERF_HPP__OVERHEAD_ACC); - - perf_hpp__format[PERF_HPP__OVERHEAD].header = - hpp__header_overhead_self; + perf_hpp__format[PERF_HPP__OVERHEAD].name = "Self"; } perf_hpp__column_enable(PERF_HPP__OVERHEAD); @@ -513,11 +519,11 @@ void perf_hpp__column_disable(unsigned col) void perf_hpp__cancel_cumulate(void) { - if (field_order) + if (is_strict_order(field_order)) return; perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC); - perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead; + perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead"; } void perf_hpp__setup_output_field(void) @@ -622,3 +628,59 @@ unsigned int hists__sort_list_width(struct hists *hists) return ret; } + +void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) +{ + int idx; + + if (perf_hpp__is_sort_entry(fmt)) + return perf_hpp__reset_sort_width(fmt, hists); + + for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) { + if (fmt == &perf_hpp__format[idx]) + break; + } + + if (idx == PERF_HPP__MAX_INDEX) + return; + + switch (idx) { + case PERF_HPP__OVERHEAD: + case PERF_HPP__OVERHEAD_SYS: + case PERF_HPP__OVERHEAD_US: + case PERF_HPP__OVERHEAD_ACC: + fmt->len = 8; + break; + + case PERF_HPP__OVERHEAD_GUEST_SYS: + case PERF_HPP__OVERHEAD_GUEST_US: + fmt->len = 9; + break; + + case PERF_HPP__SAMPLES: + case PERF_HPP__PERIOD: + fmt->len = 12; + break; + + default: + break; + } +} + +void perf_hpp__set_user_width(const char *width_list_str) +{ + struct perf_hpp_fmt *fmt; + const char *ptr = width_list_str; + + perf_hpp__for_each_format(fmt) { + char *p; + + int len = strtol(ptr, &p, 10); + fmt->user_len = len; + + if (*p == ',') + ptr = p + 1; + else + break; + } +} diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 90122ab..dfcbc90 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; @@ -395,10 +390,12 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, init_rem_hits(); - perf_hpp__for_each_format(fmt) perf_hpp__reset_width(fmt, hists); + if (symbol_conf.col_width_list_str) + perf_hpp__set_user_width(symbol_conf.col_width_list_str); + if (!show_header) goto print_entries; @@ -479,7 +476,7 @@ print_entries: if (h->ms.map == NULL && verbose > 1) { __map_groups__fprintf_maps(h->thread->mg, - MAP__FUNCTION, verbose, fp); + MAP__FUNCTION, fp); fprintf(fp, "%.10s end\n", graph_dotted_line); } } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 809b4c5..79999ce 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -17,11 +17,13 @@ #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); @@ -232,9 +234,16 @@ static int mov__parse(struct ins_operands *ops) return -1; target = ++s; + comment = strchr(s, '#'); - while (s[0] != '\0' && !isspace(s[0])) - ++s; + if (comment != NULL) + s = comment - 1; + else + s = strchr(s, '\0') - 1; + + while (s > target && isspace(s[0])) + --s; + s++; prev = *s; *s = '\0'; @@ -244,7 +253,6 @@ static int mov__parse(struct ins_operands *ops) if (ops->target.raw == NULL) goto out_free_source; - comment = strchr(s, '#'); if (comment == NULL) return 0; @@ -472,7 +480,7 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr)); - if (addr < sym->start || addr > sym->end) + if (addr < sym->start || addr >= sym->end) return -ERANGE; offset = addr - sym->start; @@ -564,13 +572,15 @@ 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; @@ -782,13 +792,15 @@ 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; @@ -806,6 +818,12 @@ 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: */ @@ -830,14 +848,15 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, end = map__rip_2objdump(map, sym->end); offset = line_ip - start; - if ((u64)line_ip < start || (u64)line_ip > end) + if ((u64)line_ip < start || (u64)line_ip >= end) offset = -1; else 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; @@ -863,6 +882,11 @@ 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); @@ -898,11 +922,10 @@ 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) { - snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", - symbol_conf.symfs, filename); - } + if (filename) + symbol__join_symfs(symfs_filename, filename); if (filename == NULL) { if (dso->has_build_id) { @@ -911,6 +934,8 @@ 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)) { @@ -922,8 +947,7 @@ fallback: * DSO is the same as when 'perf record' ran. */ filename = (char *)dso->long_name; - snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", - symbol_conf.symfs, filename); + symbol__join_symfs(symfs_filename, filename); free_filename = false; } @@ -963,7 +987,7 @@ fallback: kce.kcore_filename = symfs_filename; kce.addr = map__rip_2objdump(map, sym->start); kce.offs = sym->start; - kce.len = sym->end + 1 - sym->start; + kce.len = sym->end - sym->start; if (!kcore_extract__create(&kce)) { delete_extract = true; strlcpy(symfs_filename, kce.extract_filename, @@ -979,12 +1003,12 @@ 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 : "", map__rip_2objdump(map, sym->start), - map__rip_2objdump(map, sym->end+1), + map__rip_2objdump(map, sym->end), symbol_conf.annotate_asm_raw ? "" : "--no-show-raw", symbol_conf.annotate_src ? "-S" : "", symfs_filename, filename); @@ -996,7 +1020,8 @@ 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; /* @@ -1167,7 +1192,7 @@ 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 112d6e2..0784a94 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; }; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index a904a4c..0c72680 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 ae39256..8236319 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 7b176dd..5cf9e1b 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -22,6 +22,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *); extern int perf_default_config(const char *, const char *, void *); extern int perf_config(config_fn_t fn, void *); extern int perf_config_int(const char *, const char *); +extern u64 perf_config_u64(const char *, const char *); extern int perf_config_bool(const char *, const char *); extern int config_error_nonbool(const char *); extern const char *perf_config_dirname(const char *, const char *); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 48b6d3f..64b377e 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -25,77 +25,176 @@ __thread struct callchain_cursor callchain_cursor; -int -parse_callchain_report_opt(const char *arg) +#ifdef HAVE_DWARF_UNWIND_SUPPORT +static int get_stack_size(const char *str, unsigned long *_size) { - char *tok, *tok2; char *endptr; + unsigned long size; + unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); - symbol_conf.use_callchain = true; + size = strtoul(str, &endptr, 0); - if (!arg) + do { + if (*endptr) + break; + + size = round_up(size, sizeof(u64)); + if (!size || size > max_size) + break; + + *_size = size; return 0; - tok = strtok((char *)arg, ","); - if (!tok) - return -1; + } while (0); - /* get the output mode */ - if (!strncmp(tok, "graph", strlen(arg))) { - callchain_param.mode = CHAIN_GRAPH_ABS; + pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", + max_size, str); + return -1; +} +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ - } else if (!strncmp(tok, "flat", strlen(arg))) { - callchain_param.mode = CHAIN_FLAT; - } else if (!strncmp(tok, "fractal", strlen(arg))) { - callchain_param.mode = CHAIN_GRAPH_REL; - } else if (!strncmp(tok, "none", strlen(arg))) { - callchain_param.mode = CHAIN_NONE; - symbol_conf.use_callchain = false; - return 0; - } else { - return -1; - } +int parse_callchain_record_opt(const char *arg) +{ + char *tok, *name, *saveptr = NULL; + char *buf; + int ret = -1; + + /* We need buffer that we know we can write to. */ + buf = malloc(strlen(arg) + 1); + if (!buf) + return -ENOMEM; + + strcpy(buf, arg); + + tok = strtok_r((char *)buf, ",", &saveptr); + name = tok ? : (char *)buf; + + do { + /* Framepointer style */ + if (!strncmp(name, "fp", sizeof("fp"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + callchain_param.record_mode = CALLCHAIN_FP; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph fp\n"); + break; - /* get the min percentage */ - tok = strtok(NULL, ","); - if (!tok) - goto setup; +#ifdef HAVE_DWARF_UNWIND_SUPPORT + /* Dwarf style */ + } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { + const unsigned long default_stack_dump_size = 8192; - callchain_param.min_percent = strtod(tok, &endptr); - if (tok == endptr) - return -1; + ret = 0; + callchain_param.record_mode = CALLCHAIN_DWARF; + callchain_param.dump_size = default_stack_dump_size; + + tok = strtok_r(NULL, ",", &saveptr); + if (tok) { + unsigned long size = 0; - /* get the print limit */ - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; + ret = get_stack_size(tok, &size); + callchain_param.dump_size = size; + } +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ + } else { + pr_err("callchain: Unknown --call-graph option " + "value: %s\n", arg); + break; + } - if (tok2[0] != 'c') { - callchain_param.print_limit = strtoul(tok2, &endptr, 0); - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; + } while (0); + + free(buf); + return ret; +} + +static int parse_callchain_mode(const char *value) +{ + if (!strncmp(value, "graph", strlen(value))) { + callchain_param.mode = CHAIN_GRAPH_ABS; + return 0; + } + if (!strncmp(value, "flat", strlen(value))) { + callchain_param.mode = CHAIN_FLAT; + return 0; + } + if (!strncmp(value, "fractal", strlen(value))) { + callchain_param.mode = CHAIN_GRAPH_REL; + return 0; } + return -1; +} - /* get the call chain order */ - if (!strncmp(tok2, "caller", strlen("caller"))) +static int parse_callchain_order(const char *value) +{ + if (!strncmp(value, "caller", strlen(value))) { callchain_param.order = ORDER_CALLER; - else if (!strncmp(tok2, "callee", strlen("callee"))) + return 0; + } + if (!strncmp(value, "callee", strlen(value))) { callchain_param.order = ORDER_CALLEE; - else - return -1; + return 0; + } + return -1; +} - /* Get the sort key */ - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; - if (!strncmp(tok2, "function", strlen("function"))) +static int parse_callchain_sort_key(const char *value) +{ + if (!strncmp(value, "function", strlen(value))) { callchain_param.key = CCKEY_FUNCTION; - else if (!strncmp(tok2, "address", strlen("address"))) + return 0; + } + if (!strncmp(value, "address", strlen(value))) { callchain_param.key = CCKEY_ADDRESS; - else - return -1; -setup: + return 0; + } + if (!strncmp(value, "branch", strlen(value))) { + callchain_param.branch_callstack = 1; + return 0; + } + return -1; +} + +int +parse_callchain_report_opt(const char *arg) +{ + char *tok; + char *endptr; + bool minpcnt_set = false; + + symbol_conf.use_callchain = true; + + if (!arg) + return 0; + + while ((tok = strtok((char *)arg, ",")) != NULL) { + if (!strncmp(tok, "none", strlen(tok))) { + callchain_param.mode = CHAIN_NONE; + symbol_conf.use_callchain = false; + return 0; + } + + if (!parse_callchain_mode(tok) || + !parse_callchain_order(tok) || + !parse_callchain_sort_key(tok)) { + /* parsing ok - move on to the next */ + } else if (!minpcnt_set) { + /* try to get the min percent */ + callchain_param.min_percent = strtod(tok, &endptr); + if (tok == endptr) + return -1; + minpcnt_set = true; + } else { + /* try print limit at last */ + callchain_param.print_limit = strtoul(tok, &endptr, 0); + if (tok == endptr) + return -1; + } + + arg = NULL; + } + if (callchain_register_param(&callchain_param) < 0) { pr_err("Can't register callchain params\n"); return -1; @@ -103,6 +202,47 @@ setup: return 0; } +int perf_callchain_config(const char *var, const char *value) +{ + char *endptr; + + if (prefixcmp(var, "call-graph.")) + return 0; + var += sizeof("call-graph.") - 1; + + if (!strcmp(var, "record-mode")) + return parse_callchain_record_opt(value); +#ifdef HAVE_DWARF_UNWIND_SUPPORT + if (!strcmp(var, "dump-size")) { + unsigned long size = 0; + int ret; + + ret = get_stack_size(value, &size); + callchain_param.dump_size = size; + + return ret; + } +#endif + if (!strcmp(var, "print-type")) + return parse_callchain_mode(value); + if (!strcmp(var, "order")) + return parse_callchain_order(value); + if (!strcmp(var, "sort-key")) + return parse_callchain_sort_key(value); + if (!strcmp(var, "threshold")) { + callchain_param.min_percent = strtod(value, &endptr); + if (value == endptr) + return -1; + } + if (!strcmp(var, "print-limit")) { + callchain_param.print_limit = strtod(value, &endptr); + if (value == endptr) + return -1; + } + + return 0; +} + static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, enum chain_mode mode) @@ -618,15 +758,15 @@ 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; } int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample) { - if (!symbol_conf.use_callchain) + if (!symbol_conf.use_callchain || sample->callchain == NULL) return 0; return callchain_append(he->callchain, &callchain_cursor, sample->period); } @@ -672,3 +812,32 @@ 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; +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 8f84423..dbc08cf 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -54,17 +54,24 @@ enum chain_key { }; struct callchain_param { + bool enabled; + enum perf_call_graph_mode record_mode; + u32 dump_size; enum chain_mode mode; u32 print_limit; double min_percent; sort_chain_func_t sort; enum chain_order order; enum chain_key key; + bool branch_callstack; }; +extern struct callchain_param callchain_param; + struct callchain_list { u64 ip; struct map_symbol ms; + char *srcline; struct list_head list; }; @@ -154,7 +161,6 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) struct option; struct hist_entry; -int record_parse_callchain(const char *arg, struct record_opts *opts); int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); int record_callchain_opt(const struct option *opt, const char *arg, int unset); @@ -166,7 +172,9 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * bool hide_unresolved); extern const char record_callchain_help[]; +int parse_callchain_record_opt(const char *arg); int parse_callchain_report_opt(const char *arg); +int perf_callchain_config(const char *var, const char *value); static inline void callchain_cursor_snapshot(struct callchain_cursor *dest, struct callchain_cursor *src) @@ -176,4 +184,18 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest, dest->first = src->curr; dest->nr -= src->pos; } + +#ifdef HAVE_SKIP_CALLCHAIN_IDX +extern int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain); +#else +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); + #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c new file mode 100644 index 0000000..47b78b3 --- /dev/null +++ b/tools/perf/util/cloexec.c @@ -0,0 +1,74 @@ +#include <sched.h> +#include "util.h" +#include "../perf.h" +#include "cloexec.h" +#include "asm/bug.h" +#include "debug.h" + +static unsigned long flag = PERF_FLAG_FD_CLOEXEC; + +static int perf_flag_probe(void) +{ + /* use 'safest' configuration as used in perf_evsel__fallback() */ + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + .exclude_kernel = 1, + }; + int fd; + int err; + int cpu; + pid_t pid = -1; + char sbuf[STRERR_BUFSIZE]; + + cpu = sched_getcpu(); + if (cpu < 0) + cpu = 0; + + while (1) { + /* check cloexec flag */ + fd = sys_perf_event_open(&attr, pid, cpu, -1, + PERF_FLAG_FD_CLOEXEC); + if (fd < 0 && pid == -1 && errno == EACCES) { + pid = 0; + continue; + } + break; + } + err = errno; + + if (fd >= 0) { + close(fd); + return 1; + } + + WARN_ONCE(err != EINVAL && err != EBUSY, + "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n", + 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); + err = errno; + + 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; +} + +unsigned long perf_event_open_cloexec_flag(void) +{ + static bool probed; + + if (!probed) { + if (perf_flag_probe() <= 0) + flag = 0; + probed = true; + } + + return flag; +} diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h new file mode 100644 index 0000000..94a5a7d --- /dev/null +++ b/tools/perf/util/cloexec.h @@ -0,0 +1,6 @@ +#ifndef __PERF_CLOEXEC_H +#define __PERF_CLOEXEC_H + +unsigned long perf_event_open_cloexec_flag(void); + +#endif /* __PERF_CLOEXEC_H */ diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 87b8672..f465418 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -335,3 +335,19 @@ int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...) va_end(args); return value_color_snprintf(bf, size, fmt, percent); } + +int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...) +{ + va_list args; + int len; + double percent; + const char *color; + + va_start(args, fmt); + len = va_arg(args, int); + percent = va_arg(args, double); + va_end(args); + + color = get_percent_color(percent); + return color_snprintf(bf, size, color, fmt, len, percent); +} diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 7ff30a6..0a594b8 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -41,6 +41,7 @@ int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...); int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf); int value_color_snprintf(char *bf, size_t size, const char *fmt, double value); int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...); +int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...); int percent_color_fprintf(FILE *fp, const char *fmt, double percent); const char *get_percent_color(double percent); diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index f9e7776..b2bb59d 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -74,7 +74,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) return new; } -struct comm *comm__new(const char *str, u64 timestamp) +struct comm *comm__new(const char *str, u64 timestamp, bool exec) { struct comm *comm = zalloc(sizeof(*comm)); @@ -82,6 +82,7 @@ struct comm *comm__new(const char *str, u64 timestamp) return NULL; comm->start = timestamp; + comm->exec = exec; comm->comm_str = comm_str__findnew(str, &comm_str_root); if (!comm->comm_str) { @@ -94,7 +95,7 @@ struct comm *comm__new(const char *str, u64 timestamp) return comm; } -int comm__override(struct comm *comm, const char *str, u64 timestamp) +int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec) { struct comm_str *new, *old = comm->comm_str; @@ -106,6 +107,8 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp) comm_str__put(old); comm->comm_str = new; comm->start = timestamp; + if (exec) + comm->exec = true; return 0; } diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h index fac5bd5..71c9c39 100644 --- a/tools/perf/util/comm.h +++ b/tools/perf/util/comm.h @@ -11,11 +11,17 @@ struct comm { struct comm_str *comm_str; u64 start; struct list_head list; + bool exec; + union { /* Tool specific area */ + void *priv; + u64 db_id; + }; }; void comm__free(struct comm *comm); -struct comm *comm__new(const char *str, u64 timestamp); +struct comm *comm__new(const char *str, u64 timestamp, bool exec); const char *comm__str(const struct comm *comm); -int comm__override(struct comm *comm, const char *str, u64 timestamp); +int comm__override(struct comm *comm, const char *str, u64 timestamp, + bool exec); #endif /* __PERF_COMM_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 24519e1..e18f653 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -222,7 +222,8 @@ static int perf_parse_file(config_fn_t fn, void *data) const unsigned char *bomptr = utf8_bom; for (;;) { - int c = get_next_char(); + int line, c = get_next_char(); + if (bomptr && *bomptr) { /* We are at the file beginning; skip UTF8-encoded BOM * if present. Sane editors won't put this in on their @@ -261,8 +262,16 @@ static int perf_parse_file(config_fn_t fn, void *data) if (!isalpha(c)) break; var[baselen] = tolower(c); - if (get_value(fn, data, var, baselen+1) < 0) + + /* + * The get_value function might or might not reach the '\n', + * so saving the current line number for error reporting. + */ + line = config_linenr; + if (get_value(fn, data, var, baselen+1) < 0) { + config_linenr = line; break; + } } die("bad config file line %d in %s", config_linenr, config_file_name); } @@ -286,6 +295,21 @@ static int parse_unit_factor(const char *end, unsigned long *val) return 0; } +static int perf_parse_llong(const char *value, long long *ret) +{ + if (value && *value) { + char *end; + long long val = strtoll(value, &end, 0); + unsigned long factor = 1; + + if (!parse_unit_factor(end, &factor)) + return 0; + *ret = val * factor; + return 1; + } + return 0; +} + static int perf_parse_long(const char *value, long *ret) { if (value && *value) { @@ -307,6 +331,15 @@ static void die_bad_config(const char *name) die("bad config value for '%s'", name); } +u64 perf_config_u64(const char *name, const char *value) +{ + long long ret = 0; + + if (!perf_parse_llong(value, &ret)) + die_bad_config(name); + return (u64) ret; +} + int perf_config_int(const char *name, const char *value) { long ret = 0; @@ -350,6 +383,16 @@ static int perf_default_core_config(const char *var __maybe_unused, return 0; } +static int perf_ui_config(const char *var, const char *value) +{ + /* Add other config variables here. */ + if (!strcmp(var, "ui.show-headers")) { + symbol_conf.show_hist_headers = perf_config_bool(var, value); + return 0; + } + return 0; +} + int perf_default_config(const char *var, const char *value, void *dummy __maybe_unused) { @@ -359,6 +402,12 @@ int perf_default_config(const char *var, const char *value, if (!prefixcmp(var, "hist.")) return perf_hist_config(var, value); + if (!prefixcmp(var, "ui.")) + return perf_ui_config(var, value); + + if (!prefixcmp(var, "call-graph.")) + return perf_callchain_config(var, value); + /* Add other config variables here. */ return 0; } @@ -473,7 +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; @@ -490,12 +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/data.c b/tools/perf/util/data.c index 55de44e..1921942 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -7,6 +7,7 @@ #include "data.h" #include "util.h" +#include "debug.h" static bool check_pipe(struct perf_data_file *file) { @@ -49,12 +50,14 @@ static int open_file_read(struct perf_data_file *file) { struct stat st; int fd; + char sbuf[STRERR_BUFSIZE]; fd = open(file->path, O_RDONLY); if (fd < 0) { int err = errno; - pr_err("failed to open %s: %s", file->path, strerror(err)); + pr_err("failed to open %s: %s", file->path, + strerror_r(err, sbuf, sizeof(sbuf))); if (err == ENOENT && !strcmp(file->path, "perf.data")) pr_err(" (try 'perf record' first)"); pr_err("\n"); @@ -65,7 +68,7 @@ static int open_file_read(struct perf_data_file *file) goto out_close; if (!file->force && st.st_uid && (st.st_uid != geteuid())) { - pr_err("file %s not owned by current user or root\n", + pr_err("File %s not owned by current user or root (use -f to override)\n", file->path); goto out_close; } @@ -87,6 +90,7 @@ static int open_file_read(struct perf_data_file *file) static int open_file_write(struct perf_data_file *file) { int fd; + char sbuf[STRERR_BUFSIZE]; if (check_backup(file)) return -1; @@ -94,7 +98,8 @@ static int open_file_write(struct perf_data_file *file) fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); if (fd < 0) - pr_err("failed to open %s : %s\n", file->path, strerror(errno)); + pr_err("failed to open %s : %s\n", file->path, + strerror_r(errno, sbuf, sizeof(sbuf))); return fd; } diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c new file mode 100644 index 0000000..c81dae3 --- /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 0000000..adbd22d --- /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 299b555..ad60b2f 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -13,15 +13,20 @@ #include "util.h" #include "target.h" +#define NSECS_PER_SEC 1000000000ULL +#define NSECS_PER_USEC 1000ULL + int verbose; bool dump_trace = false, quiet = false; +int debug_ordered_events; +static int redirect_to_stderr; -static int _eprintf(int level, const char *fmt, va_list args) +static int _eprintf(int level, int var, const char *fmt, va_list args) { int ret = 0; - if (verbose >= level) { - if (use_browser >= 1) + if (var >= level) { + if (use_browser >= 1 && !redirect_to_stderr) ui_helpline__vshow(fmt, args); else ret = vfprintf(stderr, fmt, args); @@ -30,18 +35,47 @@ static int _eprintf(int level, const char *fmt, va_list args) return ret; } -int eprintf(int level, const char *fmt, ...) +int eprintf(int level, int var, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); - ret = _eprintf(level, fmt, args); + ret = _eprintf(level, var, fmt, args); va_end(args); return ret; } +static int __eprintf_time(u64 t, const char *fmt, va_list args) +{ + int ret = 0; + u64 secs, usecs, nsecs = t; + + secs = nsecs / NSECS_PER_SEC; + nsecs -= secs * NSECS_PER_SEC; + usecs = nsecs / NSECS_PER_USEC; + + ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ", + secs, usecs); + ret += vfprintf(stderr, fmt, args); + return ret; +} + +int eprintf_time(int level, int var, u64 t, const char *fmt, ...) +{ + int ret = 0; + va_list args; + + if (var >= level) { + va_start(args, fmt); + ret = __eprintf_time(t, fmt, args); + va_end(args); + } + + return ret; +} + /* * Overloading libtraceevent standard info print * function, display with -v in perf. @@ -51,9 +85,9 @@ void pr_stat(const char *fmt, ...) va_list args; va_start(args, fmt); - _eprintf(1, fmt, args); + _eprintf(1, verbose, fmt, args); va_end(args); - eprintf(1, "\n"); + eprintf(1, verbose, "\n"); } int dump_printf(const char *fmt, ...) @@ -105,3 +139,49 @@ void trace_event(union perf_event *event) } printf(".\n"); } + +static struct debug_variable { + const char *name; + int *ptr; +} debug_variables[] = { + { .name = "verbose", .ptr = &verbose }, + { .name = "ordered-events", .ptr = &debug_ordered_events}, + { .name = "stderr", .ptr = &redirect_to_stderr}, + { .name = NULL, } +}; + +int perf_debug_option(const char *str) +{ + struct debug_variable *var = &debug_variables[0]; + char *vstr, *s = strdup(str); + int v = 1; + + vstr = strchr(s, '='); + if (vstr) + *vstr++ = 0; + + while (var->name) { + if (!strcmp(s, var->name)) + break; + var++; + } + + if (!var->name) { + pr_err("Unknown debug variable name '%s'\n", s); + free(s); + return -1; + } + + if (vstr) { + v = atoi(vstr); + /* + * Allow only values in range (0, 10), + * otherwise set 0. + */ + v = (v < 0) || (v > 10) ? 0 : v; + } + + *var->ptr = v; + free(s); + return 0; +} diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 443694c..be264d6 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -3,6 +3,7 @@ #define __PERF_DEBUG_H #include <stdbool.h> +#include <string.h> #include "event.h" #include "../ui/helpline.h" #include "../ui/progress.h" @@ -10,6 +11,33 @@ extern int verbose; extern bool quiet, dump_trace; +extern int debug_ordered_events; + +#ifndef pr_fmt +#define pr_fmt(fmt) fmt +#endif + +#define pr_err(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warning(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info(fmt, ...) \ + eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug(fmt, ...) \ + eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debugN(n, fmt, ...) \ + eprintf(n, verbose, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) + +#define pr_time_N(n, var, t, fmt, ...) \ + eprintf_time(n, var, t, fmt, ##__VA_ARGS__) + +#define pr_oe_time(t, fmt, ...) pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__) + +#define STRERR_BUFSIZE 128 /* For the buffer size of strerror_r */ int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(union perf_event *event); @@ -19,4 +47,9 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); void pr_stat(const char *fmt, ...); +int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4))); +int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5))); + +int perf_debug_option(const char *str); + #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 819f104..45be944 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', }; @@ -37,6 +39,7 @@ int dso__read_binary_type_filename(const struct dso *dso, { char build_id_hex[BUILD_ID_SIZE * 2 + 1]; int ret = 0; + size_t len; switch (type) { case DSO_BINARY_TYPE__DEBUGLINK: { @@ -60,26 +63,25 @@ int dso__read_binary_type_filename(const struct dso *dso, break; case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: - snprintf(filename, size, "%s/usr/lib/debug%s.debug", - symbol_conf.symfs, dso->long_name); + len = __symbol__join_symfs(filename, size, "/usr/lib/debug"); + snprintf(filename + len, size - len, "%s.debug", dso->long_name); break; case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: - snprintf(filename, size, "%s/usr/lib/debug%s", - symbol_conf.symfs, dso->long_name); + len = __symbol__join_symfs(filename, size, "/usr/lib/debug"); + snprintf(filename + len, size - len, "%s", dso->long_name); break; case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: { const char *last_slash; - size_t len; size_t dir_size; last_slash = dso->long_name + dso->long_name_len; while (last_slash != dso->long_name && *last_slash != '/') last_slash--; - len = scnprintf(filename, size, "%s", symbol_conf.symfs); + len = __symbol__join_symfs(filename, size, ""); dir_size = last_slash - dso->long_name + 2; if (dir_size > (size - len)) { ret = -1; @@ -100,26 +102,26 @@ int dso__read_binary_type_filename(const struct dso *dso, build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex); - snprintf(filename, size, - "%s/usr/lib/debug/.build-id/%.2s/%s.debug", - symbol_conf.symfs, build_id_hex, build_id_hex + 2); + len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/"); + snprintf(filename + len, size - len, "%.2s/%s.debug", + build_id_hex, build_id_hex + 2); break; case DSO_BINARY_TYPE__VMLINUX: case DSO_BINARY_TYPE__GUEST_VMLINUX: case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: - snprintf(filename, size, "%s%s", - symbol_conf.symfs, dso->long_name); + __symbol__join_symfs(filename, size, dso->long_name); break; case DSO_BINARY_TYPE__GUEST_KMODULE: - snprintf(filename, size, "%s%s%s", symbol_conf.symfs, - root_dir, dso->long_name); + 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: - snprintf(filename, size, "%s%s", symbol_conf.symfs, - dso->long_name); + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: + __symbol__join_symfs(filename, size, dso->long_name); break; case DSO_BINARY_TYPE__KCORE: @@ -139,6 +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. */ @@ -164,13 +233,15 @@ static void close_first_dso(void); static int do_open(char *name) { int fd; + char sbuf[STRERR_BUFSIZE]; do { fd = open(name, O_RDONLY); if (fd >= 0) return fd; - pr_debug("dso open failed, mmap: %s\n", strerror(errno)); + pr_debug("dso open failed, mmap: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); if (!dso__data_open_cnt || errno != EMFILE) break; @@ -216,7 +287,7 @@ static int open_dso(struct dso *dso, struct machine *machine) { int fd = __open_dso(dso, machine); - if (fd > 0) { + if (fd >= 0) { dso__list_add(dso); /* * Check if we crossed the allowed number @@ -331,26 +402,44 @@ int dso__data_fd(struct dso *dso, struct machine *machine) }; int i = 0; + if (dso->data.status == DSO_DATA_STATUS_ERROR) + return -1; + if (dso->data.fd >= 0) - return dso->data.fd; + goto out; if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) { dso->data.fd = open_dso(dso, machine); - return dso->data.fd; + goto out; } do { - int fd; - dso->binary_type = binary_type_data[i++]; - fd = open_dso(dso, machine); - if (fd >= 0) - return dso->data.fd = fd; + dso->data.fd = open_dso(dso, machine); + if (dso->data.fd >= 0) + goto out; } while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND); +out: + if (dso->data.fd >= 0) + dso->data.status = DSO_DATA_STATUS_OK; + else + dso->data.status = DSO_DATA_STATUS_ERROR; + + return dso->data.fd; +} + +bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by) +{ + u32 flag = 1 << by; - return -EINVAL; + if (dso->data.status_seen & flag) + return true; + + dso->data.status_seen |= flag; + + return false; } static void @@ -514,10 +603,12 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size) static int data_file_size(struct dso *dso) { struct stat st; + char sbuf[STRERR_BUFSIZE]; if (!dso->data.file_size) { if (fstat(dso->data.fd, &st)) { - pr_err("dso mmap failed, fstat: %s\n", strerror(errno)); + pr_err("dso mmap failed, fstat: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); return -1; } dso->data.file_size = st.st_size; @@ -526,6 +617,28 @@ static int data_file_size(struct dso *dso) return 0; } +/** + * dso__data_size - Return dso data size + * @dso: dso object + * @machine: machine object + * + * Return: dso data size + */ +off_t dso__data_size(struct dso *dso, struct machine *machine) +{ + int fd; + + fd = dso__data_fd(dso, machine); + if (fd < 0) + return fd; + + if (data_file_size(dso)) + return -1; + + /* For now just estimate dso data size is close to file size */ + return dso->data.file_size; +} + static ssize_t data_read_offset(struct dso *dso, u64 offset, u8 *data, ssize_t size) { @@ -611,6 +724,65 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name, return dso; } +/* + * Find a matching entry and/or link current entry to RB tree. + * Either one of the dso or name parameter must be non-NULL or the + * function will not work. + */ +static struct dso *dso__findlink_by_longname(struct rb_root *root, + struct dso *dso, const char *name) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + + if (!name) + name = dso->long_name; + /* + * Find node with the matching name + */ + while (*p) { + struct dso *this = rb_entry(*p, struct dso, rb_node); + int rc = strcmp(name, this->long_name); + + parent = *p; + if (rc == 0) { + /* + * In case the new DSO is a duplicate of an existing + * one, print an one-time warning & put the new entry + * at the end of the list of duplicates. + */ + if (!dso || (dso == this)) + return this; /* Find matching dso */ + /* + * The core kernel DSOs may have duplicated long name. + * In this case, the short name should be different. + * Comparing the short names to differentiate the DSOs. + */ + rc = strcmp(dso->short_name, this->short_name); + if (rc == 0) { + pr_err("Duplicated dso name: %s\n", name); + return NULL; + } + } + if (rc < 0) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + if (dso) { + /* Add new node and rebalance tree */ + rb_link_node(&dso->rb_node, parent, p); + rb_insert_color(&dso->rb_node, root); + } + return NULL; +} + +static inline struct dso * +dso__find_by_longname(const struct rb_root *root, const char *name) +{ + return dso__findlink_by_longname((struct rb_root *)root, NULL, name); +} + void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) { if (name == NULL) @@ -701,8 +873,10 @@ struct dso *dso__new(const char *name) dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; dso->data.cache = RB_ROOT; dso->data.fd = -1; + dso->data.status = DSO_DATA_STATUS_UNKNOWN; dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND; + dso->is_64_bit = (sizeof(void *) == 8); dso->loaded = 0; dso->rel = 0; dso->sorted_by_name = 0; @@ -711,6 +885,7 @@ struct dso *dso__new(const char *name) dso->a2l_fails = 1; dso->kernel = DSO_TYPE_USER; dso->needs_swap = DSO_SWAP__UNSET; + RB_CLEAR_NODE(&dso->rb_node); INIT_LIST_HEAD(&dso->node); INIT_LIST_HEAD(&dso->data.open_entry); } @@ -721,6 +896,10 @@ struct dso *dso__new(const char *name) void dso__delete(struct dso *dso) { int i; + + if (!RB_EMPTY_NODE(&dso->rb_node)) + pr_err("DSO %s is still in rbtree when being deleted!\n", + dso->long_name); for (i = 0; i < MAP__NR_TYPES; ++i) symbols__delete(&dso->symbols[i]); @@ -807,35 +986,34 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) return have_build_id; } -void dsos__add(struct list_head *head, struct dso *dso) +void dsos__add(struct dsos *dsos, struct dso *dso) { - list_add_tail(&dso->node, head); + list_add_tail(&dso->node, &dsos->head); + dso__findlink_by_longname(&dsos->root, dso, NULL); } -struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short) +struct dso *dsos__find(const struct dsos *dsos, const char *name, + bool cmp_short) { struct dso *pos; if (cmp_short) { - list_for_each_entry(pos, head, node) + list_for_each_entry(pos, &dsos->head, node) if (strcmp(pos->short_name, name) == 0) return pos; return NULL; } - list_for_each_entry(pos, head, node) - if (strcmp(pos->long_name, name) == 0) - return pos; - return NULL; + return dso__find_by_longname(&dsos->root, name); } -struct dso *__dsos__findnew(struct list_head *head, const char *name) +struct dso *__dsos__findnew(struct dsos *dsos, const char *name) { - struct dso *dso = dsos__find(head, name, false); + struct dso *dso = dsos__find(dsos, name, false); if (!dso) { dso = dso__new(name); if (dso != NULL) { - dsos__add(head, dso); + dsos__add(dsos, dso); dso__set_basename(dso); } } @@ -898,3 +1076,14 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp) return ret; } + +enum dso_type dso__type(struct dso *dso, struct machine *machine) +{ + int fd; + + fd = dso__data_fd(dso, machine); + if (fd < 0) + return DSO__TYPE_UNKNOWN; + + return dso__type_fd(fd); +} diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index ad553ba..3782c82 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -5,6 +5,7 @@ #include <linux/rbtree.h> #include <stdbool.h> #include <linux/types.h> +#include <linux/bitops.h> #include "map.h" #include "build-id.h" @@ -21,7 +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, @@ -40,6 +43,23 @@ enum dso_swap_type { DSO_SWAP__YES, }; +enum dso_data_status { + DSO_DATA_STATUS_ERROR = -1, + DSO_DATA_STATUS_UNKNOWN = 0, + DSO_DATA_STATUS_OK = 1, +}; + +enum dso_data_status_seen { + DSO_DATA_STATUS_SEEN_ITRACE, +}; + +enum dso_type { + DSO__TYPE_UNKNOWN, + DSO__TYPE_64BIT, + DSO__TYPE_32BIT, + DSO__TYPE_X32BIT, +}; + #define DSO__SWAP(dso, type, val) \ ({ \ type ____r = val; \ @@ -72,8 +92,18 @@ struct dso_cache { char data[0]; }; +/* + * DSOs are put into both a list for fast iteration and rbtree for fast + * long name lookup. + */ +struct dsos { + struct list_head head; + struct rb_root root; /* rbtree root sorted by long name */ +}; + struct dso { struct list_head node; + struct rb_node rb_node; /* rbtree node sorted by long name */ struct rb_root symbols[MAP__NR_TYPES]; struct rb_root symbol_names[MAP__NR_TYPES]; void *a2l; @@ -90,6 +120,7 @@ struct dso { u8 annotate_warned:1; u8 short_name_allocated:1; u8 long_name_allocated:1; + u8 is_64_bit:1; u8 sorted_by_name; u8 loaded; u8 rel; @@ -98,15 +129,23 @@ struct dso { const char *long_name; u16 long_name_len; u16 short_name_len; + void *dwfl; /* DWARF debug info */ /* dso data file */ struct { struct rb_root cache; int fd; + int status; + u32 status_seen; size_t file_size; struct list_head open_entry; } data; + union { /* Tool specific area */ + void *priv; + u64 db_id; + }; + char name[0]; }; @@ -148,11 +187,17 @@ 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: * dso__data_fd * dso__data_close + * dso__data_size * dso__data_read_offset * dso__data_read_addr * @@ -190,20 +235,22 @@ int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type t int dso__data_fd(struct dso *dso, struct machine *machine); void dso__data_close(struct dso *dso); +off_t dso__data_size(struct dso *dso, struct machine *machine); ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, u64 offset, u8 *data, ssize_t size); ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size); +bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by); struct map *dso__new_map(const char *name); struct dso *dso__kernel_findnew(struct machine *machine, const char *name, const char *short_name, int dso_type); -void dsos__add(struct list_head *head, struct dso *dso); -struct dso *dsos__find(const struct list_head *head, const char *name, +void dsos__add(struct dsos *dsos, struct dso *dso); +struct dso *dsos__find(const struct dsos *dsos, const char *name, bool cmp_short); -struct dso *__dsos__findnew(struct list_head *head, const char *name); +struct dso *__dsos__findnew(struct dsos *dsos, const char *name); bool __dsos__read_build_ids(struct list_head *head, bool with_hits); size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, @@ -229,4 +276,6 @@ static inline bool dso__is_kcore(struct dso *dso) void dso__free_a2l(struct dso *dso); +enum dso_type dso__type(struct dso *dso, struct machine *machine); + #endif /* __PERF_DSO */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index d0281bd..6c6d044 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) @@ -558,13 +559,17 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, struct map *map; struct kmap *kmap; int err; + union perf_event *event; + + if (machine->vmlinux_maps[0] == NULL) + return -1; + /* * We should get this from /sys/kernel/sections/.text, but till that is * available use this, and after it is use this as a fallback for older * kernels. */ - union perf_event *event = zalloc((sizeof(event->mmap) + - machine->id_hdr_size)); + event = zalloc((sizeof(event->mmap) + machine->id_hdr_size)); if (event == NULL) { pr_debug("Not enough memory synthesizing mmap event " "for kernel modules\n"); @@ -603,7 +608,14 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) { - return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid); + const char *s; + + if (event->header.misc & PERF_RECORD_MISC_COMM_EXEC) + s = " exec"; + else + s = ""; + + return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid); } int perf_event__process_comm(struct perf_tool *tool __maybe_unused, @@ -719,12 +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; @@ -777,10 +789,11 @@ try_again: * "[vdso]" dso, but for now lets use the old trick of looking * in the whole kernel symbol list. */ - if ((long long)al->addr < 0 && - cpumode == PERF_RECORD_MISC_USER && - machine && mg != &machine->kmaps) { + if (cpumode == PERF_RECORD_MISC_USER && machine && + mg != &machine->kmaps && + machine__kernel_ip(machine, al->addr)) { mg = &machine->kmaps; + load_map = true; goto try_again; } } else { @@ -794,14 +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; } @@ -830,8 +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>"); @@ -866,3 +878,43 @@ int perf_event__preprocess_sample(const union perf_event *event, return 0; } + +bool is_bts_event(struct perf_event_attr *attr) +{ + return attr->type == PERF_TYPE_HARDWARE && + (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) && + attr->sample_period == 1; +} + +bool sample_addr_correlates_sym(struct perf_event_attr *attr) +{ + if (attr->type == PERF_TYPE_SOFTWARE && + (attr->config == PERF_COUNT_SW_PAGE_FAULTS || + attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN || + attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)) + return true; + + if (is_bts_event(attr)) + return true; + + return false; +} + +void perf_event__preprocess_sample_addr(union perf_event *event, + struct perf_sample *sample, + struct thread *thread, + struct addr_location *al) +{ + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->addr, al); + if (!al->map) + thread__find_addr_map(thread, cpumode, MAP__VARIABLE, + sample->addr, al); + + al->cpu = sample->cpu; + al->sym = NULL; + + if (al->map) + al->sym = map__find_symbol(al->map, al->addr, NULL); +} diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index e5dd40a..c4ffe2b 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; @@ -156,10 +182,13 @@ struct perf_sample { u32 cpu; u32 raw_size; u64 data_src; + u32 flags; + u16 insn_len; void *raw_data; 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; }; @@ -185,9 +214,37 @@ 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 }; +/* + * The kernel collects the number of events it couldn't send in a stretch and + * when possible sends this number in a PERF_RECORD_LOST event. The number of + * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while + * total_lost tells exactly how many events the kernel in fact lost, i.e. it is + * the sum of all struct lost_event.lost fields reported. + * + * The total_period is needed because by default auto-freq is used, so + * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get + * the total number of low level events, it is necessary to to sum all struct + * sample_event.period and stash the result in total_period. + */ +struct events_stats { + u64 total_period; + u64 total_non_filtered_period; + u64 total_lost; + u64 total_invalid_chains; + u32 nr_events[PERF_RECORD_HEADER_MAX]; + u32 nr_non_filtered_samples; + u32 nr_lost_warned; + u32 nr_unknown_events; + u32 nr_invalid_chains; + u32 nr_unknown_id; + u32 nr_unprocessable_samples; + u32 nr_unordered_events; +}; + struct attr_event { struct perf_event_header header; struct perf_event_attr attr; @@ -211,6 +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; @@ -225,6 +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); @@ -288,6 +359,15 @@ int perf_event__preprocess_sample(const union perf_event *event, struct addr_location *al, struct perf_sample *sample); +struct thread; + +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 thread *thread, + struct addr_location *al); + const char *perf_event__name(unsigned int id); size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 59ef280..cbab1fb 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 +25,10 @@ #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); #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) #define SID(e, x, y) xyarray__entry(e->sample_id, x, y) @@ -37,6 +42,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, INIT_HLIST_HEAD(&evlist->heads[i]); INIT_LIST_HEAD(&evlist->entries); perf_evlist__set_maps(evlist, cpus, threads); + fdarray__init(&evlist->pollfd, 64); evlist->workload.pid = -1; } @@ -102,7 +108,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist) void perf_evlist__exit(struct perf_evlist *evlist) { zfree(&evlist->mmap); - zfree(&evlist->pollfd); + fdarray__exit(&evlist->pollfd); } void perf_evlist__delete(struct perf_evlist *evlist) @@ -122,6 +128,7 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) { list_add_tail(&entry->node, &evlist->entries); entry->idx = evlist->nr_entries; + entry->tracking = !entry->idx; if (!evlist->nr_entries++) perf_evlist__set_id_pos(evlist); @@ -265,17 +272,27 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist, return 0; } +static int perf_evlist__nr_threads(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + if (evsel->system_wide) + return 1; + else + return thread_map__nr(evlist->threads); +} + void perf_evlist__disable(struct perf_evlist *evlist) { int cpu, thread; struct perf_evsel *pos; int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = thread_map__nr(evlist->threads); + int nr_threads; for (cpu = 0; cpu < nr_cpus; cpu++) { evlist__for_each(evlist, pos) { if (!perf_evsel__is_group_leader(pos) || !pos->fd) continue; + nr_threads = perf_evlist__nr_threads(evlist, pos); for (thread = 0; thread < nr_threads; thread++) ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE, 0); @@ -288,12 +305,13 @@ void perf_evlist__enable(struct perf_evlist *evlist) int cpu, thread; struct perf_evsel *pos; int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = thread_map__nr(evlist->threads); + int nr_threads; for (cpu = 0; cpu < nr_cpus; cpu++) { evlist__for_each(evlist, pos) { if (!perf_evsel__is_group_leader(pos) || !pos->fd) continue; + nr_threads = perf_evlist__nr_threads(evlist, pos); for (thread = 0; thread < nr_threads; thread++) ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); @@ -305,12 +323,14 @@ int perf_evlist__disable_event(struct perf_evlist *evlist, struct perf_evsel *evsel) { int cpu, thread, err; + int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_threads = perf_evlist__nr_threads(evlist, evsel); if (!evsel->fd) return 0; - for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { - for (thread = 0; thread < evlist->threads->nr; thread++) { + for (cpu = 0; cpu < nr_cpus; cpu++) { + for (thread = 0; thread < nr_threads; thread++) { err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_DISABLE, 0); if (err) @@ -324,12 +344,14 @@ int perf_evlist__enable_event(struct perf_evlist *evlist, struct perf_evsel *evsel) { int cpu, thread, err; + int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_threads = perf_evlist__nr_threads(evlist, evsel); if (!evsel->fd) return -EINVAL; - for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { - for (thread = 0; thread < evlist->threads->nr; thread++) { + for (cpu = 0; cpu < nr_cpus; cpu++) { + for (thread = 0; thread < nr_threads; thread++) { err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); if (err) @@ -339,21 +361,111 @@ int perf_evlist__enable_event(struct perf_evlist *evlist, return 0; } -static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) +static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist, + struct perf_evsel *evsel, int cpu) +{ + int thread, err; + int nr_threads = perf_evlist__nr_threads(evlist, evsel); + + if (!evsel->fd) + return -EINVAL; + + for (thread = 0; thread < nr_threads; thread++) { + err = ioctl(FD(evsel, cpu, thread), + PERF_EVENT_IOC_ENABLE, 0); + if (err) + return err; + } + return 0; +} + +static int perf_evlist__enable_event_thread(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int thread) +{ + int cpu, err; + int nr_cpus = cpu_map__nr(evlist->cpus); + + if (!evsel->fd) + return -EINVAL; + + for (cpu = 0; cpu < nr_cpus; cpu++) { + err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); + if (err) + return err; + } + return 0; +} + +int perf_evlist__enable_event_idx(struct perf_evlist *evlist, + struct perf_evsel *evsel, int idx) +{ + bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus); + + if (per_cpu_mmaps) + return perf_evlist__enable_event_cpu(evlist, evsel, idx); + else + return perf_evlist__enable_event_thread(evlist, evsel, idx); +} + +int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { int nr_cpus = cpu_map__nr(evlist->cpus); int nr_threads = thread_map__nr(evlist->threads); - int nfds = nr_cpus * nr_threads * evlist->nr_entries; - evlist->pollfd = malloc(sizeof(struct pollfd) * nfds); - return evlist->pollfd != NULL ? 0 : -ENOMEM; + int nfds = 0; + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + if (evsel->system_wide) + nfds += nr_cpus; + else + nfds += nr_cpus * nr_threads; + } + + if (fdarray__available_entries(&evlist->pollfd) < nfds && + fdarray__grow(&evlist->pollfd, nfds) < 0) + return -ENOMEM; + + return 0; } -void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd) +static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx) { - fcntl(fd, F_SETFL, O_NONBLOCK); - evlist->pollfd[evlist->nr_fds].fd = fd; - evlist->pollfd[evlist->nr_fds].events = POLLIN; - evlist->nr_fds++; + int pos = fdarray__add(&evlist->pollfd, fd, POLLIN | POLLERR | POLLHUP); + /* + * Save the idx so that when we filter out fds POLLHUP'ed we can + * close the associated evlist->mmap[] entry. + */ + if (pos >= 0) { + evlist->pollfd.priv[pos].idx = idx; + + fcntl(fd, F_SETFL, O_NONBLOCK); + } + + return pos; +} + +int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd) +{ + return __perf_evlist__add_pollfd(evlist, fd, -1); +} + +static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd) +{ + struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd); + + perf_evlist__mmap_put(evlist, fda->priv[fd].idx); +} + +int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask) +{ + return fdarray__filter(&evlist->pollfd, revents_and_mask, + perf_evlist__munmap_filtered); +} + +int perf_evlist__poll(struct perf_evlist *evlist, int timeout) +{ + return fdarray__poll(&evlist->pollfd, timeout); } static void perf_evlist__id_hash(struct perf_evlist *evlist, @@ -417,6 +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; @@ -566,14 +694,36 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) return event; } +static bool perf_mmap__empty(struct perf_mmap *md) +{ + return perf_mmap__read_head(md) != md->prev; +} + +static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx) +{ + ++evlist->mmap[idx].refcnt; +} + +static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx) +{ + BUG_ON(evlist->mmap[idx].refcnt == 0); + + if (--evlist->mmap[idx].refcnt == 0) + __perf_evlist__munmap(evlist, idx); +} + void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) { + struct perf_mmap *md = &evlist->mmap[idx]; + if (!evlist->overwrite) { - struct perf_mmap *md = &evlist->mmap[idx]; unsigned int old = md->prev; perf_mmap__write_tail(md, old); } + + if (md->refcnt == 1 && perf_mmap__empty(md)) + perf_evlist__mmap_put(evlist, idx); } static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) @@ -581,6 +731,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) if (evlist->mmap[idx].base != NULL) { munmap(evlist->mmap[idx].base, evlist->mmap_len); evlist->mmap[idx].base = NULL; + evlist->mmap[idx].refcnt = 0; } } @@ -606,12 +757,31 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) return evlist->mmap != NULL ? 0 : -ENOMEM; } -static int __perf_evlist__mmap(struct perf_evlist *evlist, - int idx, int prot, int mask, int fd) +struct mmap_params { + int prot; + int mask; +}; + +static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx, + struct mmap_params *mp, int fd) { + /* + * The last one will be done at perf_evlist__mmap_consume(), so that we + * make sure we don't prevent tools from consuming every last event in + * the ring buffer. + * + * I.e. we can get the POLLHUP meaning that the fd doesn't exist + * anymore, but the last events for it are still in the ring buffer, + * waiting to be consumed. + * + * Tools can chose to ignore this at their own discretion, but the + * evlist layer can't just drop it when filtering events in + * perf_evlist__filter_pollfd(). + */ + evlist->mmap[idx].refcnt = 2; evlist->mmap[idx].prev = 0; - evlist->mmap[idx].mask = mask; - evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot, + evlist->mmap[idx].mask = mp->mask; + evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot, MAP_SHARED, fd, 0); if (evlist->mmap[idx].base == MAP_FAILED) { pr_debug2("failed to mmap perf event ring buffer, error %d\n", @@ -620,39 +790,61 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, return -1; } - perf_evlist__add_pollfd(evlist, fd); return 0; } static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, - int prot, int mask, int cpu, int thread, - int *output) + struct mmap_params *mp, int cpu, + int thread, int *output) { struct perf_evsel *evsel; evlist__for_each(evlist, evsel) { - int fd = FD(evsel, cpu, thread); + int fd; + + if (evsel->system_wide && thread) + continue; + + fd = FD(evsel, cpu, thread); if (*output == -1) { *output = fd; - if (__perf_evlist__mmap(evlist, idx, prot, mask, - *output) < 0) + if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0) return -1; } else { if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) return -1; + + perf_evlist__mmap_get(evlist, idx); } - if ((evsel->attr.read_format & PERF_FORMAT_ID) && - perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 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) { + 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; } -static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, - int mask) +static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, + struct mmap_params *mp) { int cpu, thread; int nr_cpus = cpu_map__nr(evlist->cpus); @@ -663,8 +855,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int output = -1; for (thread = 0; thread < nr_threads; thread++) { - if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask, - cpu, thread, &output)) + if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu, + thread, &output)) goto out_unmap; } } @@ -677,8 +869,8 @@ out_unmap: return -1; } -static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, - int mask) +static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, + struct mmap_params *mp) { int thread; int nr_threads = thread_map__nr(evlist->threads); @@ -687,8 +879,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, for (thread = 0; thread < nr_threads; thread++) { int output = -1; - if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0, - thread, &output)) + if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread, + &output)) goto out_unmap; } @@ -702,10 +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; @@ -742,7 +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", @@ -793,18 +999,20 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, struct perf_evsel *evsel; const struct cpu_map *cpus = evlist->cpus; const struct thread_map *threads = evlist->threads; - int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask; + struct mmap_params mp = { + .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), + }; if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) return -ENOMEM; - if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0) + if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0) return -ENOMEM; evlist->overwrite = overwrite; evlist->mmap_len = perf_evlist__mmap_size(pages); pr_debug("mmap size %zuB\n", evlist->mmap_len); - mask = evlist->mmap_len - page_size - 1; + mp.mask = evlist->mmap_len - page_size - 1; evlist__for_each(evlist, evsel) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && @@ -814,9 +1022,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, } if (cpu_map__empty(cpus)) - return perf_evlist__mmap_per_thread(evlist, prot, mask); + return perf_evlist__mmap_per_thread(evlist, &mp); - return perf_evlist__mmap_per_cpu(evlist, prot, mask); + return perf_evlist__mmap_per_cpu(evlist, &mp); } int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) @@ -839,6 +1047,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) out_delete_threads: thread_map__delete(evlist->threads); + evlist->threads = NULL; return -1; } @@ -1011,11 +1220,51 @@ void perf_evlist__close(struct perf_evlist *evlist) } } +static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) +{ + int err = -ENOMEM; + + /* + * Try reading /sys/devices/system/cpu/online to get + * an all cpus map. + * + * FIXME: -ENOMEM is the best we can do here, the cpu_map + * code needs an overhaul to properly forward the + * error, and we may not want to do that fallback to a + * default cpu identity map :-\ + */ + evlist->cpus = cpu_map__new(NULL); + if (evlist->cpus == NULL) + goto out; + + evlist->threads = thread_map__new_dummy(); + if (evlist->threads == NULL) + goto out_free_cpus; + + err = 0; +out: + return err; +out_free_cpus: + cpu_map__delete(evlist->cpus); + evlist->cpus = NULL; + goto out; +} + int perf_evlist__open(struct perf_evlist *evlist) { struct perf_evsel *evsel; int err; + /* + * Default: one fd per CPU, all threads, aka systemwide + * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL + */ + if (evlist->threads == NULL && evlist->cpus == NULL) { + err = perf_evlist__create_syswide_maps(evlist); + if (err < 0) + goto out_err; + } + perf_evlist__update_id_pos(evlist); evlist__for_each(evlist, evsel) { @@ -1055,6 +1304,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar } if (!evlist->workload.pid) { + int ret; + if (pipe_output) dup2(2, 1); @@ -1072,8 +1323,22 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar /* * Wait until the parent tells us to go. */ - if (read(go_pipe[0], &bf, 1) == -1) - perror("unable to read pipe"); + ret = read(go_pipe[0], &bf, 1); + /* + * The parent will ask for the execvp() to be performed by + * writing exactly one byte, in workload.cork_fd, usually via + * perf_evlist__start_workload(). + * + * For cancelling the workload without actuallin running it, + * the parent will just close workload.cork_fd, without writing + * anything, i.e. read will return zero and we just exit() + * here. + */ + if (ret != 1) { + if (ret == -1) + perror("unable to read pipe"); + exit(ret); + } execvp(argv[0], (char **)argv); @@ -1096,8 +1361,14 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar sigaction(SIGUSR1, &act, NULL); } - if (target__none(target)) + if (target__none(target)) { + if (evlist->threads == NULL) { + fprintf(stderr, "FATAL: evlist->threads need to be set at this point (%s:%d).\n", + __func__, __LINE__); + goto out_close_pipes; + } evlist->threads->map[0] = evlist->workload.pid; + } close(child_ready_pipe[1]); close(go_pipe[0]); @@ -1196,7 +1467,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, int err, char *buf, size_t size) { int printed, value; - char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf)); + char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf)); switch (err) { case EACCES: @@ -1214,10 +1485,42 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, "For your workloads it needs to be <= 1\nHint:\t"); } printed += scnprintf(buf + printed, size - printed, - "For system wide tracing it needs to be set to -1"); + "For system wide tracing it needs to be set to -1.\n"); printed += scnprintf(buf + printed, size - printed, - ".\nHint:\tThe current value is %d.", value); + "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n" + "Hint:\tThe current value is %d.", value); + break; + default: + scnprintf(buf, size, "%s", emsg); + break; + } + + 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); @@ -1243,3 +1546,19 @@ void perf_evlist__to_front(struct perf_evlist *evlist, list_splice(&move, &evlist->entries); } + +void perf_evlist__set_tracking_event(struct perf_evlist *evlist, + struct perf_evsel *tracking_evsel) +{ + struct perf_evsel *evsel; + + if (tracking_evsel->tracking) + return; + + evlist__for_each(evlist, evsel) { + if (evsel != tracking_evsel) + evsel->tracking = false; + } + + tracking_evsel->tracking = true; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index f5173cd..0ba93f6 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -2,6 +2,7 @@ #define __PERF_EVLIST_H 1 #include <linux/list.h> +#include <api/fd/array.h> #include <stdio.h> #include "../perf.h" #include "event.h" @@ -17,9 +18,15 @@ struct record_opts; #define PERF_EVLIST__HLIST_BITS 8 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) +/** + * struct perf_mmap - perf's ring buffer mmap details + * + * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this + */ struct perf_mmap { void *base; int mask; + int refcnt; unsigned int prev; char event_copy[PERF_SAMPLE_MAX_SIZE]; }; @@ -29,7 +36,6 @@ struct perf_evlist { struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; int nr_entries; int nr_groups; - int nr_fds; int nr_mmaps; size_t mmap_len; int id_pos; @@ -40,8 +46,8 @@ struct perf_evlist { pid_t pid; } workload; bool overwrite; + struct fdarray pollfd; struct perf_mmap *mmap; - struct pollfd *pollfd; struct thread_map *threads; struct cpu_map *cpus; struct perf_evsel *selected; @@ -82,7 +88,11 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu, int thread, u64 id); -void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); +int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); +int perf_evlist__alloc_pollfd(struct perf_evlist *evlist); +int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask); + +int perf_evlist__poll(struct perf_evlist *evlist, int timeout); struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); @@ -107,6 +117,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, void *ucontext)); int perf_evlist__start_workload(struct perf_evlist *evlist); +struct option; + int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset); @@ -122,6 +134,8 @@ int perf_evlist__disable_event(struct perf_evlist *evlist, struct perf_evsel *evsel); int perf_evlist__enable_event(struct perf_evlist *evlist, struct perf_evsel *evsel); +int perf_evlist__enable_event_idx(struct perf_evlist *evlist, + struct perf_evsel *evsel, int idx); void perf_evlist__set_selected(struct perf_evlist *evlist, struct perf_evsel *evsel); @@ -171,6 +185,7 @@ 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) { @@ -262,4 +277,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, #define evlist__for_each_safe(evlist, tmp, evsel) \ __evlist__for_each_safe(&(evlist)->entries, tmp, evsel) +void perf_evlist__set_tracking_event(struct perf_evlist *evlist, + struct perf_evsel *tracking_evsel); + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 8606175..1e90c85 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -15,6 +15,8 @@ #include <linux/perf_event.h> #include <sys/resource.h> #include "asm/bug.h" +#include "callchain.h" +#include "cgroup.h" #include "evsel.h" #include "evlist.h" #include "util.h" @@ -29,8 +31,51 @@ static struct { bool sample_id_all; bool exclude_guest; bool mmap2; + bool cloexec; } perf_missing_features; +static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused) +{ + return 0; +} + +static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused) +{ +} + +static struct { + size_t size; + int (*init)(struct perf_evsel *evsel); + void (*fini)(struct perf_evsel *evsel); +} perf_evsel__object = { + .size = sizeof(struct perf_evsel), + .init = perf_evsel__no_extra_init, + .fini = perf_evsel__no_extra_fini, +}; + +int perf_evsel__object_config(size_t object_size, + int (*init)(struct perf_evsel *evsel), + void (*fini)(struct perf_evsel *evsel)) +{ + + if (object_size == 0) + goto set_methods; + + if (perf_evsel__object.size > object_size) + return -EINVAL; + + perf_evsel__object.size = object_size; + +set_methods: + if (init != NULL) + perf_evsel__object.init = init; + + if (fini != NULL) + perf_evsel__object.fini = fini; + + return 0; +} + #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) int __perf_evsel__sample_size(u64 sample_type) @@ -115,16 +160,6 @@ void perf_evsel__calc_id_pos(struct perf_evsel *evsel) evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type); } -void hists__init(struct hists *hists) -{ - memset(hists, 0, sizeof(*hists)); - hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; - hists->entries_in = &hists->entries_in_array[0]; - hists->entries_collapsed = RB_ROOT; - hists->entries = RB_ROOT; - pthread_mutex_init(&hists->lock, NULL); -} - void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, enum perf_event_sample_format bit) { @@ -161,19 +196,20 @@ void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx) { evsel->idx = idx; + evsel->tracking = !idx; evsel->attr = *attr; evsel->leader = evsel; evsel->unit = ""; evsel->scale = 1.0; INIT_LIST_HEAD(&evsel->node); - hists__init(&evsel->hists); + perf_evsel__object.init(evsel); evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); perf_evsel__calc_id_pos(evsel); } struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { - struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + struct perf_evsel *evsel = zalloc(perf_evsel__object.size); if (evsel != NULL) perf_evsel__init(evsel, attr, idx); @@ -183,7 +219,7 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx) { - struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + struct perf_evsel *evsel = zalloc(perf_evsel__object.size); if (evsel != NULL) { struct perf_event_attr attr = { @@ -501,20 +537,19 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) } static void -perf_evsel__config_callgraph(struct perf_evsel *evsel, - struct record_opts *opts) +perf_evsel__config_callgraph(struct perf_evsel *evsel) { bool function = perf_evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->attr; perf_evsel__set_sample_bit(evsel, CALLCHAIN); - if (opts->call_graph == CALLCHAIN_DWARF) { + if (callchain_param.record_mode == CALLCHAIN_DWARF) { if (!function) { perf_evsel__set_sample_bit(evsel, REGS_USER); perf_evsel__set_sample_bit(evsel, STACK_USER); attr->sample_regs_user = PERF_REGS_MASK; - attr->sample_stack_user = opts->stack_dump_size; + attr->sample_stack_user = callchain_param.dump_size; attr->exclude_callchain_user = 1; } else { pr_info("Cannot use DWARF unwind for function trace event," @@ -560,7 +595,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) { struct perf_evsel *leader = evsel->leader; struct perf_event_attr *attr = &evsel->attr; - int track = !evsel->idx; /* only the first counter needs these */ + int track = evsel->tracking; bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread; attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1; @@ -623,8 +658,21 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->mmap_data = track; } - if (opts->call_graph_enabled) - perf_evsel__config_callgraph(evsel, opts); + /* + * 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); @@ -632,12 +680,15 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (opts->period) perf_evsel__set_sample_bit(evsel, PERIOD); - if (!perf_missing_features.sample_id_all && - (opts->sample_time || !opts->no_inherit || - target__has_cpu(&opts->target) || per_cpu)) + /* + * When the user explicitely disabled time don't force it here. + */ + if (opts->sample_time && + (!perf_missing_features.sample_id_all && + (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu))) perf_evsel__set_sample_bit(evsel, TIME); - if (opts->raw_samples) { + if (opts->raw_samples && !evsel->no_aux_samples) { perf_evsel__set_sample_bit(evsel, TIME); perf_evsel__set_sample_bit(evsel, RAW); perf_evsel__set_sample_bit(evsel, CPU); @@ -650,7 +701,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->watermark = 0; attr->wakeup_events = 1; } - if (opts->branch_stack) { + if (opts->branch_stack && !evsel->no_aux_samples) { perf_evsel__set_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type = opts->branch_stack; } @@ -681,11 +732,20 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) && !opts->initial_delay) attr->enable_on_exec = 1; + + if (evsel->immediate) { + attr->disabled = 0; + attr->enable_on_exec = 0; + } } -int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { int cpu, thread; + + if (evsel->system_wide) + nthreads = 1; + evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); if (evsel->fd) { @@ -704,6 +764,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea { int cpu, thread; + if (evsel->system_wide) + nthreads = 1; + for (cpu = 0; cpu < ncpus; cpu++) { for (thread = 0; thread < nthreads; thread++) { int fd = FD(evsel, cpu, thread), @@ -734,6 +797,9 @@ 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 (evsel->system_wide) + nthreads = 1; + evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); if (evsel->sample_id == NULL) return -ENOMEM; @@ -761,13 +827,13 @@ int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus) return evsel->counts != NULL ? 0 : -ENOMEM; } -void perf_evsel__free_fd(struct perf_evsel *evsel) +static void perf_evsel__free_fd(struct perf_evsel *evsel) { xyarray__delete(evsel->fd); evsel->fd = NULL; } -void perf_evsel__free_id(struct perf_evsel *evsel) +static void perf_evsel__free_id(struct perf_evsel *evsel) { xyarray__delete(evsel->sample_id); evsel->sample_id = NULL; @@ -778,6 +844,9 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { int cpu, thread; + if (evsel->system_wide) + nthreads = 1; + for (cpu = 0; cpu < ncpus; cpu++) for (thread = 0; thread < nthreads; ++thread) { close(FD(evsel, cpu, thread)); @@ -795,22 +864,20 @@ void perf_evsel__exit(struct perf_evsel *evsel) assert(list_empty(&evsel->node)); perf_evsel__free_fd(evsel); perf_evsel__free_id(evsel); + close_cgroup(evsel->cgrp); + zfree(&evsel->group_name); + zfree(&evsel->name); + perf_evsel__object.fini(evsel); } void perf_evsel__delete(struct perf_evsel *evsel) { perf_evsel__exit(evsel); - close_cgroup(evsel->cgrp); - zfree(&evsel->group_name); - if (evsel->tp_format) - pevent_free_format(evsel->tp_format); - zfree(&evsel->name); 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; @@ -830,78 +897,60 @@ 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; - aggr->val = aggr->ena = aggr->run = 0; + memset(&count, 0, sizeof(count)); - for (cpu = 0; cpu < ncpus; cpu++) { - for (thread = 0; thread < nthreads; thread++) { - if (FD(evsel, cpu, thread) < 0) - continue; + if (FD(evsel, cpu, thread) < 0) + return -EINVAL; - if (readn(FD(evsel, cpu, thread), - &count, nv * sizeof(u64)) < 0) - return -errno; + if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0) + return -errno; - aggr->val += count.val; - if (scale) { - aggr->ena += count.ena; - aggr->run += count.run; - } - } - } + return cb(evsel, cpu, thread, &count); +} - compute_deltas(evsel, -1, aggr); +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; - evsel->counts->scaled = 0; - if (scale) { - if (aggr->run == 0) { - evsel->counts->scaled = -1; - aggr->val = 0; - return 0; - } + if (FD(evsel, cpu, thread) < 0) + return -EINVAL; - 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 (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; + + perf_evsel__compute_deltas(evsel, cpu, &count); + perf_counts_values__scale(&count, scale, NULL); + evsel->counts->cpu[cpu] = count; return 0; } @@ -960,6 +1009,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) ret += PRINT_ATTR2(exclude_user, exclude_kernel); ret += PRINT_ATTR2(exclude_hv, exclude_idle); ret += PRINT_ATTR2(mmap, comm); + ret += PRINT_ATTR2(mmap2, comm_exec); ret += PRINT_ATTR2(freq, inherit_stat); ret += PRINT_ATTR2(enable_on_exec, task); ret += PRINT_ATTR2(watermark, precise_ip); @@ -967,7 +1017,6 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) ret += PRINT_ATTR2(exclude_host, exclude_guest); ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel, "excl.callchain_user", exclude_callchain_user); - ret += PRINT_ATTR_U32(mmap2); ret += PRINT_ATTR_U32(wakeup_events); ret += PRINT_ATTR_U32(wakeup_watermark); @@ -979,6 +1028,7 @@ 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); @@ -988,21 +1038,28 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { - int cpu, thread; - unsigned long flags = 0; + int cpu, thread, nthreads; + unsigned long flags = PERF_FLAG_FD_CLOEXEC; int pid = -1, err; enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; + if (evsel->system_wide) + nthreads = 1; + else + nthreads = threads->nr; + if (evsel->fd == NULL && - perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) + perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0) return -ENOMEM; if (evsel->cgrp) { - flags = PERF_FLAG_PID_CGROUP; + flags |= PERF_FLAG_PID_CGROUP; pid = evsel->cgrp->fd; } fallback_missing_features: + if (perf_missing_features.cloexec) + flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC; if (perf_missing_features.mmap2) evsel->attr.mmap2 = 0; if (perf_missing_features.exclude_guest) @@ -1016,10 +1073,10 @@ retry_sample_id: for (cpu = 0; cpu < cpus->nr; cpu++) { - for (thread = 0; thread < threads->nr; thread++) { + for (thread = 0; thread < nthreads; thread++) { int group_fd; - if (!evsel->cgrp) + if (!evsel->cgrp && !evsel->system_wide) pid = threads->map[thread]; group_fd = get_group_fd(evsel, cpu, thread); @@ -1071,7 +1128,10 @@ try_fallback: if (err != -EINVAL || cpu > 0 || thread > 0) goto out_close; - if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { + if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) { + perf_missing_features.cloexec = true; + goto fallback_missing_features; + } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { perf_missing_features.mmap2 = true; goto fallback_missing_features; } else if (!perf_missing_features.exclude_guest && @@ -1089,7 +1149,7 @@ out_close: close(FD(evsel, cpu, thread)); FD(evsel, cpu, thread) = -1; } - thread = threads->nr; + thread = nthreads; } while (--cpu >= 0); return err; } @@ -1468,6 +1528,23 @@ 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; } @@ -1563,6 +1640,16 @@ 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; } @@ -1741,6 +1828,17 @@ 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; } @@ -1870,7 +1968,7 @@ 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 @@ -1940,6 +2038,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, if_print(mmap); if_print(mmap2); if_print(comm); + if_print(comm_exec); if_print(freq); if_print(inherit_stat); if_print(enable_on_exec); @@ -1990,6 +2089,8 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, int err, char *msg, size_t size) { + char sbuf[STRERR_BUFSIZE]; + switch (err) { case EPERM: case EACCES: @@ -2024,13 +2125,20 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it."); #endif break; + case EBUSY: + if (find_process("oprofiled")) + return scnprintf(msg, size, + "The PMU counters are busy/taken by another profiler.\n" + "We found oprofile daemon running, please stop it and try again."); + break; default: break; } return scnprintf(msg, size, - "The sys_perf_event_open() syscall returned with %d (%s) for event (%s). \n" + "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n" "/bin/dmesg may provide additional information.\n" "No CONFIG_PERF_EVENTS=y kernel support configured?\n", - err, strerror(err), perf_evsel__name(evsel)); + err, strerror_r(err, sbuf, sizeof(sbuf)), + perf_evsel__name(evsel)); } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index a52e9a5..3862274 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -7,8 +7,6 @@ #include <linux/perf_event.h> #include <linux/types.h> #include "xyarray.h" -#include "cgroup.h" -#include "hist.h" #include "symbol.h" struct perf_counts_values { @@ -38,11 +36,16 @@ 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; }; +struct cgroup_sel; + /** struct perf_evsel - event selector * * @name - Can be set to retain the original event name passed by the user, @@ -54,6 +57,7 @@ struct perf_sample_id { * @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; @@ -66,14 +70,15 @@ struct perf_evsel { struct perf_counts *prev_raw_counts; int idx; u32 ids; - struct hists hists; 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; @@ -83,6 +88,12 @@ struct perf_evsel { int is_pos; bool supported; bool needs_swap; + bool no_aux_samples; + bool immediate; + bool system_wide; + bool tracking; + bool per_pkg; + unsigned long *per_pkg_mask; /* parse modifier helper */ int exclude_GH; int nr_members; @@ -96,13 +107,22 @@ union u64_swap { u32 val32[2]; }; -#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists) - struct cpu_map; +struct target; 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)); + struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx); static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr) @@ -149,12 +169,9 @@ const char *perf_evsel__name(struct perf_evsel *evsel); const char *perf_evsel__group_name(struct perf_evsel *evsel); int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size); -int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus); -void perf_evsel__free_fd(struct perf_evsel *evsel); -void perf_evsel__free_id(struct perf_evsel *evsel); void perf_evsel__free_counts(struct perf_evsel *evsel); void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); @@ -219,6 +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); @@ -248,37 +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); -} - -void hists__init(struct hists *hists); - 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 0000000..95ef1cf --- /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 893f8e2..b20e40c 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); @@ -171,295 +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__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 (is_vdso_map(pos->short_name)) { - name = (char *) VDSO__MAP_NAME; - name_len = sizeof(VDSO__MAP_NAME) + 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, machine, - machine->pid, kmisc, fd); - if (err == 0) - err = __dsos__write_buildid_table(&machine->user_dsos, 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 ? VDSO__MAP_NAME : 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 = is_vdso_map(dso->short_name); - 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, machine, - debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos, 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 = __dsos__read_build_ids(&machine->kernel_dsos, with_hits); - ret |= __dsos__read_build_ids(&machine->user_dsos, 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) { @@ -478,13 +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; } @@ -534,16 +239,12 @@ static int write_version(int fd, struct perf_header *h __maybe_unused, return do_write_string(fd, perf_version_string); } -static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int __write_cpudesc(int fd, const char *cpuinfo_proc) { -#ifndef CPUINFO_PROC -#define CPUINFO_PROC NULL -#endif FILE *file; char *buf = NULL; char *s, *p; - const char *search = CPUINFO_PROC; + const char *search = cpuinfo_proc; size_t len = 0; int ret = -1; @@ -560,8 +261,10 @@ static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, break; } - if (ret) + if (ret) { + ret = -1; goto done; + } s = buf; @@ -593,6 +296,25 @@ done: return ret; } +static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ +#ifndef CPUINFO_PROC +#define CPUINFO_PROC {"model name", } +#endif + const char *cpuinfo_procs[] = CPUINFO_PROC; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) { + int ret; + ret = __write_cpudesc(fd, cpuinfo_procs[i]); + if (ret >= 0) + return ret; + } + return -1; +} + + static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, struct perf_evlist *evlist __maybe_unused) { @@ -905,7 +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; @@ -1507,7 +1230,7 @@ static int __event_process_build_id(struct build_id_event *bev, struct perf_session *session) { int err = -1; - struct list_head *head; + struct dsos *dsos; struct machine *machine; u16 misc; struct dso *dso; @@ -1522,28 +1245,28 @@ static int __event_process_build_id(struct build_id_event *bev, switch (misc) { case PERF_RECORD_MISC_KERNEL: dso_type = DSO_TYPE_KERNEL; - head = &machine->kernel_dsos; + dsos = &machine->kernel_dsos; break; case PERF_RECORD_MISC_GUEST_KERNEL: dso_type = DSO_TYPE_GUEST_KERNEL; - head = &machine->kernel_dsos; + dsos = &machine->kernel_dsos; break; case PERF_RECORD_MISC_USER: case PERF_RECORD_MISC_GUEST_USER: dso_type = DSO_TYPE_USER; - head = &machine->user_dsos; + dsos = &machine->user_dsos; break; default: goto out; } - dso = __dsos__findnew(head, filename); + dso = __dsos__findnew(dsos, filename); if (dso != NULL) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; 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), @@ -2417,6 +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, }; @@ -3064,8 +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 d08cfe4..3bb90ac 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); @@ -151,6 +147,10 @@ int perf_event__process_build_id(struct perf_tool *tool, struct perf_session *session); bool is_perf_magic(u64 magic); +#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 30df618..6e88b9e 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -3,6 +3,7 @@ #include "hist.h" #include "session.h" #include "sort.h" +#include "evlist.h" #include "evsel.h" #include "annotate.h" #include <math.h> @@ -14,13 +15,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists, static bool hists__filter_entry_by_symbol(struct hists *hists, struct hist_entry *he); -struct callchain_param callchain_param = { - .mode = CHAIN_GRAPH_REL, - .min_percent = 0.5, - .order = ORDER_CALLEE, - .key = CCKEY_FUNCTION -}; - u16 hists__col_len(struct hists *hists, enum hist_column col) { return hists->col_len[col]; @@ -277,6 +271,28 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) } } +void hists__delete_entries(struct hists *hists) +{ + struct rb_node *next = rb_first(&hists->entries); + struct hist_entry *n; + + while (next) { + 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); + } +} + /* * histogram, sorted on item, collects periods */ @@ -494,6 +510,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al { u64 cost; struct mem_info *mi = iter->priv; + struct hists *hists = evsel__hists(iter->evsel); struct hist_entry *he; if (mi == NULL) @@ -510,7 +527,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al * and this is indirectly achieved by passing period=weight here * and the he_stat__add_period() function. */ - he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi, + he = __hists__add_entry(hists, al, iter->parent, NULL, mi, cost, cost, 0, true); if (!he) return -ENOMEM; @@ -524,13 +541,14 @@ iter_finish_mem_entry(struct hist_entry_iter *iter, struct addr_location *al __maybe_unused) { struct perf_evsel *evsel = iter->evsel; + struct hists *hists = evsel__hists(evsel); struct hist_entry *he = iter->he; int err = -EINVAL; if (he == NULL) goto out; - hists__inc_nr_samples(&evsel->hists, he->filtered); + hists__inc_nr_samples(hists, he->filtered); err = hist_entry__append_callchain(he, iter->sample); @@ -596,6 +614,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a { struct branch_info *bi; struct perf_evsel *evsel = iter->evsel; + struct hists *hists = evsel__hists(evsel); struct hist_entry *he = NULL; int i = iter->curr; int err = 0; @@ -609,12 +628,12 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a * The report shows the percentage of total branches captured * and not events sampled. Thus we use a pseudo period of 1. */ - he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL, + he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL, 1, 1, 0, true); if (he == NULL) return -ENOMEM; - hists__inc_nr_samples(&evsel->hists, he->filtered); + hists__inc_nr_samples(hists, he->filtered); out: iter->he = he; @@ -646,7 +665,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location struct perf_sample *sample = iter->sample; struct hist_entry *he; - he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, sample->period, sample->weight, sample->transaction, true); if (he == NULL) @@ -669,7 +688,7 @@ iter_finish_normal_entry(struct hist_entry_iter *iter, iter->he = NULL; - hists__inc_nr_samples(&evsel->hists, he->filtered); + hists__inc_nr_samples(evsel__hists(evsel), he->filtered); return hist_entry__append_callchain(he, sample); } @@ -702,12 +721,13 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, struct addr_location *al) { struct perf_evsel *evsel = iter->evsel; + struct hists *hists = evsel__hists(evsel); struct perf_sample *sample = iter->sample; struct hist_entry **he_cache = iter->priv; struct hist_entry *he; int err = 0; - he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + he = __hists__add_entry(hists, al, iter->parent, NULL, NULL, sample->period, sample->weight, sample->transaction, true); if (he == NULL) @@ -724,7 +744,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, */ callchain_cursor_commit(&callchain_cursor); - hists__inc_nr_samples(&evsel->hists, he->filtered); + hists__inc_nr_samples(hists, he->filtered); return err; } @@ -780,7 +800,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, } } - he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, sample->period, sample->weight, sample->transaction, false); if (he == NULL) @@ -1386,6 +1406,21 @@ int hists__link(struct hists *leader, struct hists *other) return 0; } + +size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp) +{ + struct perf_evsel *pos; + size_t ret = 0; + + evlist__for_each(evlist, pos) { + ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); + ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp); + } + + return ret; +} + + u64 hists__total_period(struct hists *hists) { return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period : @@ -1412,3 +1447,31 @@ int perf_hist_config(const char *var, const char *value) return 0; } + +static int hists_evsel__init(struct perf_evsel *evsel) +{ + struct hists *hists = evsel__hists(evsel); + + memset(hists, 0, sizeof(*hists)); + hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; + hists->entries_in = &hists->entries_in_array[0]; + hists->entries_collapsed = RB_ROOT; + hists->entries = RB_ROOT; + pthread_mutex_init(&hists->lock, NULL); + return 0; +} + +/* + * XXX We probably need a hists_evsel__exit() to free the hist_entries + * stored in the rbtree... + */ + +int hists__init(void) +{ + int err = perf_evsel__object_config(sizeof(struct hists_evsel), + hists_evsel__init, NULL); + if (err) + fputs("FATAL ERROR: Couldn't setup hists class\n", stderr); + + return err; +} diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 742f49a..d0ef9a1 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -4,12 +4,11 @@ #include <linux/types.h> #include <pthread.h> #include "callchain.h" +#include "evsel.h" #include "header.h" #include "color.h" #include "ui/progress.h" -extern struct callchain_param callchain_param; - struct hist_entry; struct addr_location; struct symbol; @@ -23,32 +22,6 @@ enum hist_filter { HIST_FILTER__HOST, }; -/* - * The kernel collects the number of events it couldn't send in a stretch and - * when possible sends this number in a PERF_RECORD_LOST event. The number of - * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while - * total_lost tells exactly how many events the kernel in fact lost, i.e. it is - * the sum of all struct lost_event.lost fields reported. - * - * The total_period is needed because by default auto-freq is used, so - * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get - * the total number of low level events, it is necessary to to sum all struct - * sample_event.period and stash the result in total_period. - */ -struct events_stats { - u64 total_period; - u64 total_non_filtered_period; - u64 total_lost; - u64 total_invalid_chains; - u32 nr_events[PERF_RECORD_HEADER_MAX]; - u32 nr_non_filtered_samples; - u32 nr_lost_warned; - u32 nr_unknown_events; - u32 nr_invalid_chains; - u32 nr_unknown_id; - u32 nr_unprocessable_samples; -}; - enum hist_column { HISTC_SYMBOL, HISTC_DSO, @@ -152,6 +125,7 @@ void hists__output_resort(struct hists *hists); void hists__collapse_resort(struct hists *hists, struct ui_progress *prog); void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); +void hists__delete_entries(struct hists *hists); void hists__output_recalc_col_len(struct hists *hists, int max_rows); u64 hists__total_period(struct hists *hists); @@ -164,6 +138,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp); +size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); @@ -184,6 +159,25 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *he); void hists__match(struct hists *leader, struct hists *other); int hists__link(struct hists *leader, struct hists *other); +struct hists_evsel { + struct perf_evsel evsel; + struct hists hists; +}; + +static inline struct perf_evsel *hists_to_evsel(struct hists *hists) +{ + struct hists_evsel *hevsel = container_of(hists, struct hists_evsel, hists); + return &hevsel->evsel; +} + +static inline struct hists *evsel__hists(struct perf_evsel *evsel) +{ + struct hists_evsel *hevsel = (struct hists_evsel *)evsel; + return &hevsel->hists; +} + +int hists__init(void); + struct perf_hpp { char *buf; size_t size; @@ -192,6 +186,7 @@ struct perf_hpp { }; struct perf_hpp_fmt { + const char *name; int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct perf_evsel *evsel); int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, @@ -207,6 +202,8 @@ struct perf_hpp_fmt { struct list_head list; struct list_head sort_list; bool elide; + int len; + int user_len; }; extern struct list_head perf_hpp__list; @@ -261,17 +258,19 @@ static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format) } void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists); +void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists); +void perf_hpp__set_user_width(const char *width_list_str); typedef u64 (*hpp_field_fn)(struct hist_entry *he); typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front); typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...); -int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, - hpp_field_fn get_field, const char *fmt, - hpp_snprint_fn print_fn, bool fmt_percent); -int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he, - hpp_field_fn get_field, const char *fmt, - hpp_snprint_fn print_fn, bool fmt_percent); +int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he, hpp_field_fn get_field, + const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent); +int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he, hpp_field_fn get_field, + const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent); static inline void advance_hpp(struct perf_hpp *hpp, int inc) { diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h deleted file mode 100644 index d82b170b..0000000 --- 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/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h index 01ffd12..40bd214 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 dadfa7e..0000000 --- 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/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index 9844c31..09e8e7a 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -94,27 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...) return (i >= ssize) ? (ssize - 1) : i; } -int eprintf(int level, - const char *fmt, ...) __attribute__((format(printf, 2, 3))); - -#ifndef pr_fmt -#define pr_fmt(fmt) fmt -#endif - -#define pr_err(fmt, ...) \ - eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warning(fmt, ...) \ - eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) \ - eprintf(0, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug(fmt, ...) \ - eprintf(1, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debugN(n, fmt, ...) \ - eprintf(n, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) -#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) - /* * This looks more complex than it should be. But we need to * get the type for the ~ right in round_down (it needs to be diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h index 97a8007..6f19c54 100644 --- a/tools/perf/util/include/linux/string.h +++ b/tools/perf/util/include/linux/string.h @@ -1,4 +1,3 @@ #include <string.h> void *memdup(const void *src, size_t len); -int str_append(char **s, int *len, const char *a); diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h new file mode 100644 index 0000000..cf1d7913 --- /dev/null +++ b/tools/perf/util/kvm-stat.h @@ -0,0 +1,139 @@ +#ifndef __PERF_KVM_STAT_H +#define __PERF_KVM_STAT_H + +#include "../perf.h" +#include "evsel.h" +#include "evlist.h" +#include "session.h" +#include "tool.h" +#include "stat.h" + +struct event_key { + #define INVALID_KEY (~0ULL) + u64 key; + int info; + struct exit_reasons_table *exit_reasons; +}; + +struct kvm_event_stats { + u64 time; + struct stats stats; +}; + +struct kvm_event { + struct list_head hash_entry; + struct rb_node rb; + + struct event_key key; + + struct kvm_event_stats total; + + #define DEFAULT_VCPU_NUM 8 + int max_vcpu; + struct kvm_event_stats *vcpu; +}; + +typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); + +struct kvm_event_key { + const char *name; + key_cmp_fun key; +}; + +struct perf_kvm_stat; + +struct child_event_ops { + void (*get_key)(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); + const char *name; +}; + +struct kvm_events_ops { + bool (*is_begin_event)(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); + bool (*is_end_event)(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key); + struct child_event_ops *child_ops; + void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key, + char *decode); + const char *name; +}; + +struct exit_reasons_table { + unsigned long exit_code; + const char *reason; +}; + +#define EVENTS_BITS 12 +#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) + +struct perf_kvm_stat { + struct perf_tool tool; + struct record_opts opts; + struct perf_evlist *evlist; + struct perf_session *session; + + const char *file_name; + const char *report_event; + const char *sort_key; + int trace_vcpu; + + struct exit_reasons_table *exit_reasons; + const char *exit_reasons_isa; + + struct kvm_events_ops *events_ops; + key_cmp_fun compare; + struct list_head kvm_events_cache[EVENTS_CACHE_SIZE]; + + u64 total_time; + u64 total_count; + u64 lost_events; + u64 duration; + + struct intlist *pid_list; + + struct rb_root result; + + int timerfd; + unsigned int display_time; + bool live; +}; + +struct kvm_reg_events_ops { + const char *name; + struct kvm_events_ops *ops; +}; + +void exit_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); +bool exit_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); +bool exit_event_end(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); +void exit_event_decode_key(struct perf_kvm_stat *kvm, + struct event_key *key, + char *decode); + +bool kvm_exit_event(struct perf_evsel *evsel); +bool kvm_entry_event(struct perf_evsel *evsel); + +#define define_exit_reasons_table(name, symbols) \ + static struct exit_reasons_table name[] = { \ + symbols, { -1, NULL } \ + } + +/* + * arch specific callbacks and data structures + */ +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid); + +extern const char * const kvm_events_tp[]; +extern struct kvm_reg_events_ops kvm_reg_events_ops[]; +extern const char * const kvm_skip_events[]; + +#endif /* __PERF_KVM_STAT_H */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index c73e1fc..94de3e4 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -8,33 +8,44 @@ #include "sort.h" #include "strlist.h" #include "thread.h" +#include "vdso.h" #include <stdbool.h> #include <symbol/kallsyms.h> #include "unwind.h" +#include "linux/hash.h" + +static void dsos__init(struct dsos *dsos) +{ + INIT_LIST_HEAD(&dsos->head); + dsos->root = RB_ROOT; +} 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); - INIT_LIST_HEAD(&machine->user_dsos); - INIT_LIST_HEAD(&machine->kernel_dsos); + dsos__init(&machine->user_dsos); + dsos__init(&machine->kernel_dsos); machine->threads = RB_ROOT; INIT_LIST_HEAD(&machine->dead_threads); machine->last_match = NULL; - machine->kmaps.machine = machine; + machine->vdso_info = NULL; + machine->pid = pid; machine->symbol_filter = NULL; machine->id_hdr_size = 0; + machine->comm_exec = false; + machine->kernel_start = 0; machine->root_dir = strdup(root_dir); if (machine->root_dir == NULL) return -ENOMEM; if (pid != HOST_KERNEL_ID) { - struct thread *thread = machine__findnew_thread(machine, 0, + struct thread *thread = machine__findnew_thread(machine, -1, pid); char comm[64]; @@ -45,6 +56,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) thread__set_comm(thread, comm, 0); } + machine->current_tid = NULL; + return 0; } @@ -65,11 +78,12 @@ out_delete: return NULL; } -static void dsos__delete(struct list_head *dsos) +static void dsos__delete(struct dsos *dsos) { struct dso *pos, *n; - list_for_each_entry_safe(pos, n, dsos, node) { + list_for_each_entry_safe(pos, n, &dsos->head, node) { + RB_CLEAR_NODE(&pos->rb_node); list_del(&pos->node); dso__delete(pos); } @@ -103,7 +117,9 @@ void machine__exit(struct machine *machine) map_groups__exit(&machine->kmaps); dsos__delete(&machine->user_dsos); dsos__delete(&machine->kernel_dsos); + vdso__exit(machine); zfree(&machine->root_dir); + zfree(&machine->current_tid); } void machine__delete(struct machine *machine) @@ -172,6 +188,19 @@ void machines__set_symbol_filter(struct machines *machines, } } +void machines__set_comm_exec(struct machines *machines, bool comm_exec) +{ + struct rb_node *nd; + + machines->host.comm_exec = comm_exec; + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *machine = rb_entry(nd, struct machine, rb_node); + + machine->comm_exec = comm_exec; + } +} + struct machine *machines__find(struct machines *machines, pid_t pid) { struct rb_node **p = &machines->guests.rb_node; @@ -272,6 +301,52 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size) return; } +static void machine__update_thread_pid(struct machine *machine, + struct thread *th, pid_t pid) +{ + struct thread *leader; + + if (pid == th->pid_ || pid == -1 || th->pid_ != -1) + return; + + th->pid_ = pid; + + if (th->pid_ == th->tid) + return; + + leader = machine__findnew_thread(machine, th->pid_, th->pid_); + if (!leader) + goto out_err; + + if (!leader->mg) + leader->mg = map_groups__new(machine); + + if (!leader->mg) + goto out_err; + + if (th->mg == leader->mg) + return; + + if (th->mg) { + /* + * Maps are created from MMAP events which provide the pid and + * tid. Consequently there never should be any maps on a thread + * with an unknown pid. Just print an error if there are. + */ + if (!map_groups__empty(th->mg)) + pr_err("Discarding thread maps for %d:%d\n", + th->pid_, th->tid); + map_groups__delete(th->mg); + } + + th->mg = map_groups__get(leader->mg); + + return; + +out_err: + pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid); +} + static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid, bool create) @@ -285,10 +360,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * so most of the time we dont have to look up * the full rbtree: */ - if (machine->last_match && machine->last_match->tid == tid) { - if (pid && pid != machine->last_match->pid_) - machine->last_match->pid_ = pid; - return machine->last_match; + th = machine->last_match; + if (th && th->tid == tid) { + machine__update_thread_pid(machine, th, pid); + return th; } while (*p != NULL) { @@ -297,8 +372,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, if (th->tid == tid) { machine->last_match = th; - if (pid && pid != th->pid_) - th->pid_ = pid; + machine__update_thread_pid(machine, th, pid); return th; } @@ -325,8 +399,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * within thread__init_map_groups to find the thread * leader and that would screwed the rb tree. */ - if (thread__init_map_groups(th, machine)) + if (thread__init_map_groups(th, machine)) { + thread__delete(th); return NULL; + } } return th; @@ -344,17 +420,31 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid, return __machine__findnew_thread(machine, pid, tid, false); } +struct comm *machine__thread_exec_comm(struct machine *machine, + struct thread *thread) +{ + if (machine->comm_exec) + return thread__exec_comm(thread); + else + return thread__comm(thread); +} + int machine__process_comm_event(struct machine *machine, union perf_event *event, struct perf_sample *sample) { struct thread *thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid); + bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC; + + if (exec) + machine->comm_exec = true; if (dump_trace) perf_event__fprintf_comm(event, stdout); - if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) { + if (thread == NULL || + __thread__set_comm(thread, event->comm.comm, sample->time, exec)) { dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); return -1; } @@ -375,6 +465,7 @@ 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; @@ -387,6 +478,11 @@ 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; } @@ -394,23 +490,23 @@ struct map *machine__new_module(struct machine *machine, u64 start, size_t machines__fprintf_dsos(struct machines *machines, FILE *fp) { struct rb_node *nd; - size_t ret = __dsos__fprintf(&machines->host.kernel_dsos, fp) + - __dsos__fprintf(&machines->host.user_dsos, fp); + size_t ret = __dsos__fprintf(&machines->host.kernel_dsos.head, fp) + + __dsos__fprintf(&machines->host.user_dsos.head, fp); for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret += __dsos__fprintf(&pos->kernel_dsos, fp); - ret += __dsos__fprintf(&pos->user_dsos, fp); + ret += __dsos__fprintf(&pos->kernel_dsos.head, fp); + ret += __dsos__fprintf(&pos->user_dsos.head, fp); } return ret; } -size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, +size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm) { - return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) + - __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm); + return __dsos__fprintf_buildid(&m->kernel_dsos.head, fp, skip, parm) + + __dsos__fprintf_buildid(&m->user_dsos.head, fp, skip, parm); } size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, @@ -511,8 +607,8 @@ const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; * Returns the name of the start symbol in *symbol_name. Pass in NULL as * symbol_name if it's not that important. */ -static u64 machine__get_kernel_start_addr(struct machine *machine, - const char **symbol_name) +static u64 machine__get_running_kernel_start(struct machine *machine, + const char **symbol_name) { char filename[PATH_MAX]; int i; @@ -539,7 +635,7 @@ static u64 machine__get_kernel_start_addr(struct machine *machine, int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { enum map_type type; - u64 start = machine__get_kernel_start_addr(machine, NULL); + u64 start = machine__get_running_kernel_start(machine, NULL); for (type = 0; type < MAP__NR_TYPES; ++type) { struct kmap *kmap; @@ -772,8 +868,14 @@ 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); @@ -858,7 +960,7 @@ int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); const char *name; - u64 addr = machine__get_kernel_start_addr(machine, &name); + u64 addr = machine__get_running_kernel_start(machine, &name); if (!addr) return -1; @@ -911,7 +1013,7 @@ static bool machine__uses_kcore(struct machine *machine) { struct dso *dso; - list_for_each_entry(dso, &machine->kernel_dsos, node) { + list_for_each_entry(dso, &machine->kernel_dsos.head, node) { if (dso__is_kcore(dso)) return true; } @@ -955,6 +1057,11 @@ 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, '-', '_'); @@ -979,8 +1086,20 @@ 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; @@ -988,6 +1107,9 @@ 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); /* @@ -1045,14 +1167,14 @@ int machine__process_mmap2_event(struct machine *machine, else type = MAP__FUNCTION; - map = map__new(&machine->user_dsos, event->mmap2.start, + map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, event->mmap2.pid, event->mmap2.maj, event->mmap2.min, event->mmap2.ino, event->mmap2.ino_generation, event->mmap2.prot, event->mmap2.flags, - event->mmap2.filename, type); + event->mmap2.filename, type, thread); if (map == NULL) goto out_problem; @@ -1095,11 +1217,11 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event else type = MAP__FUNCTION; - map = map__new(&machine->user_dsos, event->mmap.start, + map = map__new(machine, event->mmap.start, event->mmap.len, event->mmap.pgoff, event->mmap.pid, 0, 0, 0, 0, 0, 0, event->mmap.filename, - type); + type, thread); if (map == NULL) goto out_problem; @@ -1200,7 +1322,7 @@ 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) { @@ -1214,7 +1336,7 @@ 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; @@ -1222,15 +1344,23 @@ 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, m, MAP__FUNCTION, addr, &al); + } + ams->addr = addr; ams->al_addr = al.addr; ams->sym = al.sym; @@ -1245,14 +1375,72 @@ 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) { @@ -1264,85 +1452,156 @@ 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 err; + 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; } - 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) - ip = chain->ips[i]; + j = i; else - ip = chain->ips[chain->nr - i - 1]; + j = chain->nr - i - 1; - 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; - } +#ifdef HAVE_SKIP_CALLCHAIN_IDX + if (j == skip_idx) continue; - } +#endif + ip = chain->ips[j]; - 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 = add_callchain_ip(thread, parent, root_al, false, ip); - err = callchain_cursor_append(&callchain_cursor, - ip, al.map, al.sym); if (err) - return err; + return (err < 0) ? err : 0; } return 0; @@ -1355,19 +1614,16 @@ 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; @@ -1381,7 +1637,7 @@ 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); } @@ -1420,3 +1676,68 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too /* command specified */ return 0; } + +pid_t machine__get_current_tid(struct machine *machine, int cpu) +{ + if (cpu < 0 || cpu >= MAX_NR_CPUS || !machine->current_tid) + return -1; + + return machine->current_tid[cpu]; +} + +int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, + pid_t tid) +{ + struct thread *thread; + + if (cpu < 0) + return -EINVAL; + + if (!machine->current_tid) { + int i; + + machine->current_tid = calloc(MAX_NR_CPUS, sizeof(pid_t)); + if (!machine->current_tid) + return -ENOMEM; + for (i = 0; i < MAX_NR_CPUS; i++) + machine->current_tid[i] = -1; + } + + if (cpu >= MAX_NR_CPUS) { + pr_err("Requested CPU %d too large. ", cpu); + pr_err("Consider raising MAX_NR_CPUS\n"); + return -EINVAL; + } + + machine->current_tid[cpu] = tid; + + thread = machine__findnew_thread(machine, pid, tid); + if (!thread) + return -ENOMEM; + + thread->cpu = cpu; + + return 0; +} + +int machine__get_kernel_start(struct machine *machine) +{ + struct map *map = machine__kernel_map(machine, MAP__FUNCTION); + int err = 0; + + /* + * The only addresses above 2^63 are kernel addresses of a 64-bit + * kernel. Note that addresses are unsigned so that on a 32-bit system + * all addresses including kernel addresses are less than 2^32. In + * that case (32-bit system), if the kernel mapping is unknown, all + * addresses will be assumed to be in user space - see + * machine__kernel_ip(). + */ + machine->kernel_start = 1ULL << 63; + if (map) { + err = map__load(map, machine->symbol_filter); + if (map->start) + machine->kernel_start = map->start; + } + return err; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index c8c74a1..e8b7779 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -4,6 +4,7 @@ #include <sys/types.h> #include <linux/rbtree.h> #include "map.h" +#include "dso.h" #include "event.h" struct addr_location; @@ -20,19 +21,29 @@ union perf_event; extern const char *ref_reloc_sym_names[]; +struct vdso_info; + struct machine { struct rb_node rb_node; pid_t pid; u16 id_hdr_size; + bool comm_exec; char *root_dir; struct rb_root threads; struct list_head dead_threads; struct thread *last_match; - struct list_head user_dsos; - struct list_head kernel_dsos; + struct vdso_info *vdso_info; + struct dsos user_dsos; + struct dsos kernel_dsos; struct map_groups kmaps; struct map *vmlinux_maps[MAP__NR_TYPES]; + u64 kernel_start; symbol_filter_t symbol_filter; + pid_t *current_tid; + union { /* Tool specific area */ + void *priv; + u64 db_id; + }; }; static inline @@ -41,8 +52,26 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type) return machine->vmlinux_maps[type]; } +int machine__get_kernel_start(struct machine *machine); + +static inline u64 machine__kernel_start(struct machine *machine) +{ + if (!machine->kernel_start) + machine__get_kernel_start(machine); + return machine->kernel_start; +} + +static inline bool machine__kernel_ip(struct machine *machine, u64 ip) +{ + u64 kernel_start = machine__kernel_start(machine); + + return ip >= kernel_start; +} + struct thread *machine__find_thread(struct machine *machine, pid_t pid, pid_t tid); +struct comm *machine__thread_exec_comm(struct machine *machine, + struct thread *thread); int machine__process_comm_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); @@ -84,6 +113,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size); void machines__set_symbol_filter(struct machines *machines, symbol_filter_t symbol_filter); +void machines__set_comm_exec(struct machines *machines, bool comm_exec); struct machine *machine__new_host(void); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); @@ -96,13 +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 @@ -191,4 +220,8 @@ int machine__synthesize_threads(struct machine *machine, struct target *target, perf_event__process, data_mmap); } +pid_t machine__get_current_tid(struct machine *machine, int cpu); +int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, + pid_t tid); + #endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 25c571f..62ca9f2 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -12,6 +12,8 @@ #include "vdso.h" #include "build-id.h" #include "util.h" +#include "debug.h" +#include "machine.h" #include <linux/string.h> const char *map_type__name[MAP__NR_TYPES] = { @@ -29,6 +31,7 @@ static inline int is_anon_memory(const char *filename) static inline int is_no_dso_memory(const char *filename) { return !strncmp(filename, "[stack", 6) || + !strncmp(filename, "/SYSV",5) || !strcmp(filename, "[heap]"); } @@ -136,10 +139,10 @@ void map__init(struct map *map, enum map_type type, map->erange_warned = false; } -struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, +struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, char *filename, - enum map_type type) + enum map_type type, struct thread *thread) { struct map *map = malloc(sizeof(*map)); @@ -172,9 +175,9 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, if (vdso) { pgoff = 0; - dso = vdso__dso_findnew(dsos__list); + dso = vdso__dso_findnew(machine, thread); } else - dso = __dsos__findnew(dsos__list, filename); + dso = __dsos__findnew(&machine->user_dsos, filename); if (dso == NULL) goto out_delete; @@ -357,7 +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); @@ -410,14 +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; } @@ -454,12 +457,26 @@ void map_groups__exit(struct map_groups *mg) } } -struct map_groups *map_groups__new(void) +bool map_groups__empty(struct map_groups *mg) +{ + int i; + + for (i = 0; i < MAP__NR_TYPES; ++i) { + if (maps__first(&mg->maps[i])) + return false; + if (!list_empty(&mg->removed_maps[i])) + return false; + } + + return true; +} + +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; } @@ -539,7 +556,7 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter) { - if (ams->addr < ams->map->start || ams->addr > ams->map->end) { + if (ams->addr < ams->map->start || ams->addr >= ams->map->end) { if (ams->map->groups == NULL) return -1; ams->map = map_groups__find(ams->map->groups, ams->map->type, @@ -554,8 +571,8 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter) return ams->sym ? 0 : -1; } -size_t __map_groups__fprintf_maps(struct map_groups *mg, - enum map_type type, int verbose, FILE *fp) +size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, + FILE *fp) { size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); struct rb_node *nd; @@ -573,17 +590,16 @@ size_t __map_groups__fprintf_maps(struct map_groups *mg, return printed; } -size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp) +static size_t map_groups__fprintf_maps(struct map_groups *mg, FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_maps(mg, i, verbose, fp); + printed += __map_groups__fprintf_maps(mg, i, fp); return printed; } static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg, - enum map_type type, - int verbose, FILE *fp) + enum map_type type, FILE *fp) { struct map *pos; size_t printed = 0; @@ -600,23 +616,23 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg, } static size_t map_groups__fprintf_removed_maps(struct map_groups *mg, - int verbose, FILE *fp) + FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp); + printed += __map_groups__fprintf_removed_maps(mg, i, fp); return printed; } -size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp) +size_t map_groups__fprintf(struct map_groups *mg, FILE *fp) { - size_t printed = map_groups__fprintf_maps(mg, verbose, fp); + size_t printed = map_groups__fprintf_maps(mg, fp); printed += fprintf(fp, "Removed maps:\n"); - return printed + map_groups__fprintf_removed_maps(mg, verbose, fp); + return printed + map_groups__fprintf_removed_maps(mg, fp); } int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, - int verbose, FILE *fp) + FILE *fp) { struct rb_root *root = &mg->maps[map->type]; struct rb_node *next = rb_first(root); @@ -648,7 +664,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, goto move_map; } - before->end = map->start - 1; + before->end = map->start; map_groups__insert(mg, before); if (verbose >= 2) map__fprintf(before, fp); @@ -662,7 +678,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, goto move_map; } - after->start = map->end + 1; + after->start = map->end; map_groups__insert(mg, after); if (verbose >= 2) map__fprintf(after, fp); @@ -736,7 +752,7 @@ struct map *maps__find(struct rb_root *maps, u64 ip) m = rb_entry(parent, struct map, rb_node); if (ip < m->start) p = &(*p)->rb_left; - else if (ip > m->end) + else if (ip >= m->end) p = &(*p)->rb_right; else return m; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 7758c72..6951a9d 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -64,8 +64,9 @@ 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); static inline struct map_groups *map_groups__get(struct map_groups *mg) { @@ -103,6 +104,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip); u64 map__objdump_2mem(struct map *map, u64 ip); struct symbol; +struct thread; /* map__for_each_symbol - iterate over the symbols in the given map * @@ -118,10 +120,10 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); -struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, +struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, - char *filename, enum map_type type); + char *filename, enum map_type type, struct thread *thread); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); void map__delete(struct map *map); struct map *map__clone(struct map *map); @@ -141,19 +143,18 @@ void map__fixup_end(struct map *map); void map__reloc_vmlinux(struct map *map); -size_t __map_groups__fprintf_maps(struct map_groups *mg, - enum map_type type, int verbose, FILE *fp); +size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, + FILE *fp); void maps__insert(struct rb_root *maps, struct map *map); 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); -size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp); -size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp); +size_t map_groups__fprintf(struct map_groups *mg, FILE *fp); int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr); @@ -210,7 +211,7 @@ struct symbol *map_groups__find_function_by_name(struct map_groups *mg, } int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, - int verbose, FILE *fp); + FILE *fp); struct map *map_groups__find_by_name(struct map_groups *mg, enum map_type type, const char *name); diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c new file mode 100644 index 0000000..fd4be94 --- /dev/null +++ b/tools/perf/util/ordered-events.c @@ -0,0 +1,286 @@ +#include <linux/list.h> +#include <linux/compiler.h> +#include <linux/string.h> +#include "ordered-events.h" +#include "evlist.h" +#include "session.h" +#include "asm/bug.h" +#include "debug.h" + +#define pr_N(n, fmt, ...) \ + eprintf(n, debug_ordered_events, fmt, ##__VA_ARGS__) + +#define pr(fmt, ...) pr_N(1, pr_fmt(fmt), ##__VA_ARGS__) + +static void queue_event(struct ordered_events *oe, struct ordered_event *new) +{ + struct ordered_event *last = oe->last; + u64 timestamp = new->timestamp; + struct list_head *p; + + ++oe->nr_events; + oe->last = new; + + pr_oe_time2(timestamp, "queue_event nr_events %u\n", oe->nr_events); + + if (!last) { + list_add(&new->list, &oe->events); + oe->max_timestamp = timestamp; + return; + } + + /* + * last event might point to some random place in the list as it's + * the last queued event. We expect that the new event is close to + * this. + */ + if (last->timestamp <= timestamp) { + while (last->timestamp <= timestamp) { + p = last->list.next; + if (p == &oe->events) { + list_add_tail(&new->list, &oe->events); + oe->max_timestamp = timestamp; + return; + } + last = list_entry(p, struct ordered_event, list); + } + list_add_tail(&new->list, &last->list); + } else { + while (last->timestamp > timestamp) { + p = last->list.prev; + if (p == &oe->events) { + list_add(&new->list, &oe->events); + return; + } + last = list_entry(p, struct ordered_event, list); + } + list_add(&new->list, &last->list); + } +} + +static union perf_event *__dup_event(struct ordered_events *oe, + union perf_event *event) +{ + union perf_event *new_event = NULL; + + if (oe->cur_alloc_size < oe->max_alloc_size) { + new_event = memdup(event, event->header.size); + if (new_event) + oe->cur_alloc_size += event->header.size; + } + + return new_event; +} + +static union perf_event *dup_event(struct ordered_events *oe, + union perf_event *event) +{ + return oe->copy_on_queue ? __dup_event(oe, event) : event; +} + +static void free_dup_event(struct ordered_events *oe, union perf_event *event) +{ + if (oe->copy_on_queue) { + oe->cur_alloc_size -= event->header.size; + free(event); + } +} + +#define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct ordered_event)) +static struct ordered_event *alloc_event(struct ordered_events *oe, + union perf_event *event) +{ + struct list_head *cache = &oe->cache; + struct ordered_event *new = NULL; + union perf_event *new_event; + + new_event = dup_event(oe, event); + if (!new_event) + return NULL; + + if (!list_empty(cache)) { + new = list_entry(cache->next, struct ordered_event, list); + list_del(&new->list); + } else if (oe->buffer) { + new = oe->buffer + oe->buffer_idx; + if (++oe->buffer_idx == MAX_SAMPLE_BUFFER) + oe->buffer = NULL; + } else if (oe->cur_alloc_size < oe->max_alloc_size) { + size_t size = MAX_SAMPLE_BUFFER * sizeof(*new); + + oe->buffer = malloc(size); + if (!oe->buffer) { + free_dup_event(oe, new_event); + return NULL; + } + + pr("alloc size %" PRIu64 "B (+%zu), max %" PRIu64 "B\n", + oe->cur_alloc_size, size, oe->max_alloc_size); + + oe->cur_alloc_size += size; + list_add(&oe->buffer->list, &oe->to_free); + + /* First entry is abused to maintain the to_free list. */ + oe->buffer_idx = 2; + new = oe->buffer + 1; + } else { + pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size); + } + + new->event = new_event; + return new; +} + +struct ordered_event * +ordered_events__new(struct ordered_events *oe, u64 timestamp, + union perf_event *event) +{ + struct ordered_event *new; + + new = alloc_event(oe, event); + if (new) { + new->timestamp = timestamp; + queue_event(oe, new); + } + + return new; +} + +void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event) +{ + list_move(&event->list, &oe->cache); + oe->nr_events--; + free_dup_event(oe, event->event); +} + +static int __ordered_events__flush(struct perf_session *s, + struct perf_tool *tool) +{ + struct ordered_events *oe = &s->ordered_events; + struct list_head *head = &oe->events; + struct ordered_event *tmp, *iter; + struct perf_sample sample; + u64 limit = oe->next_flush; + u64 last_ts = oe->last ? oe->last->timestamp : 0ULL; + bool show_progress = limit == ULLONG_MAX; + struct ui_progress prog; + int ret; + + if (!tool->ordered_events || !limit) + return 0; + + if (show_progress) + ui_progress__init(&prog, oe->nr_events, "Processing time ordered events..."); + + list_for_each_entry_safe(iter, tmp, head, list) { + if (session_done()) + return 0; + + if (iter->timestamp > limit) + break; + + ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample); + if (ret) + pr_err("Can't parse sample, err = %d\n", ret); + else { + ret = perf_session__deliver_event(s, iter->event, &sample, tool, + iter->file_offset); + if (ret) + return ret; + } + + ordered_events__delete(oe, iter); + oe->last_flush = iter->timestamp; + + if (show_progress) + ui_progress__update(&prog, 1); + } + + if (list_empty(head)) + oe->last = NULL; + else if (last_ts <= limit) + oe->last = list_entry(head->prev, struct ordered_event, list); + + return 0; +} + +int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, + enum oe_flush how) +{ + struct ordered_events *oe = &s->ordered_events; + static const char * const str[] = { + "NONE", + "FINAL", + "ROUND", + "HALF ", + }; + int err; + + switch (how) { + case OE_FLUSH__FINAL: + oe->next_flush = ULLONG_MAX; + break; + + case OE_FLUSH__HALF: + { + struct ordered_event *first, *last; + struct list_head *head = &oe->events; + + first = list_entry(head->next, struct ordered_event, list); + last = oe->last; + + /* Warn if we are called before any event got allocated. */ + if (WARN_ONCE(!last || list_empty(head), "empty queue")) + return 0; + + oe->next_flush = first->timestamp; + oe->next_flush += (last->timestamp - first->timestamp) / 2; + break; + } + + case OE_FLUSH__ROUND: + case OE_FLUSH__NONE: + default: + break; + }; + + pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush PRE %s, nr_events %u\n", + str[how], oe->nr_events); + pr_oe_time(oe->max_timestamp, "max_timestamp\n"); + + err = __ordered_events__flush(s, tool); + + if (!err) { + if (how == OE_FLUSH__ROUND) + oe->next_flush = oe->max_timestamp; + + oe->last_flush_type = how; + } + + pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush POST %s, nr_events %u\n", + str[how], oe->nr_events); + pr_oe_time(oe->last_flush, "last_flush\n"); + + return err; +} + +void ordered_events__init(struct ordered_events *oe) +{ + INIT_LIST_HEAD(&oe->events); + INIT_LIST_HEAD(&oe->cache); + INIT_LIST_HEAD(&oe->to_free); + oe->max_alloc_size = (u64) -1; + oe->cur_alloc_size = 0; +} + +void ordered_events__free(struct ordered_events *oe) +{ + while (!list_empty(&oe->to_free)) { + struct ordered_event *event; + + event = list_entry(oe->to_free.next, struct ordered_event, list); + list_del(&event->list); + free_dup_event(oe, event->event); + free(event); + } +} diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h new file mode 100644 index 0000000..7b8f9b0 --- /dev/null +++ b/tools/perf/util/ordered-events.h @@ -0,0 +1,59 @@ +#ifndef __ORDERED_EVENTS_H +#define __ORDERED_EVENTS_H + +#include <linux/types.h> +#include "tool.h" + +struct perf_session; + +struct ordered_event { + u64 timestamp; + u64 file_offset; + union perf_event *event; + struct list_head list; +}; + +enum oe_flush { + OE_FLUSH__NONE, + OE_FLUSH__FINAL, + OE_FLUSH__ROUND, + OE_FLUSH__HALF, +}; + +struct ordered_events { + u64 last_flush; + u64 next_flush; + u64 max_timestamp; + u64 max_alloc_size; + u64 cur_alloc_size; + struct list_head events; + struct list_head cache; + struct list_head to_free; + struct ordered_event *buffer; + struct ordered_event *last; + int buffer_idx; + unsigned int nr_events; + enum oe_flush last_flush_type; + bool copy_on_queue; +}; + +struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp, + union perf_event *event); +void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event); +int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, + enum oe_flush how); +void ordered_events__init(struct ordered_events *oe); +void ordered_events__free(struct ordered_events *oe); + +static inline +void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size) +{ + oe->max_alloc_size = size; +} + +static inline +void ordered_events__set_copy_on_queue(struct ordered_events *oe, bool copy) +{ + oe->copy_on_queue = copy; +} +#endif /* __ORDERED_EVENTS_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 1e15df1..77b43fe 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -6,10 +6,11 @@ #include "parse-options.h" #include "parse-events.h" #include "exec_cmd.h" -#include "linux/string.h" +#include "string.h" #include "symbol.h" #include "cache.h" #include "header.h" +#include "debug.h" #include <api/fs/debugfs.h> #include "parse-events-bison.h" #define YY_EXTRA_TYPE int @@ -29,6 +30,15 @@ extern int parse_events_debug; #endif int parse_events_parse(void *data, void *scanner); +static struct perf_pmu_event_symbol *perf_pmu_events_list; +/* + * The variable indicates the number of supported pmu event symbols. + * 0 means not initialized and ready to init + * -1 means failed to init, don't try anymore + * >0 is the number of supported pmu event symbols + */ +static int perf_pmu_events_list_num; + static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = { .symbol = "cpu-cycles", @@ -633,18 +643,28 @@ int parse_events_add_pmu(struct list_head *list, int *idx, char *name, struct list_head *head_config) { struct perf_event_attr attr; + struct perf_pmu_info info; struct perf_pmu *pmu; struct perf_evsel *evsel; - const char *unit; - double scale; pmu = perf_pmu__find(name); if (!pmu) return -EINVAL; - memset(&attr, 0, sizeof(attr)); + if (pmu->default_config) { + memcpy(&attr, pmu->default_config, + sizeof(struct perf_event_attr)); + } else { + memset(&attr, 0, sizeof(attr)); + } - if (perf_pmu__check_alias(pmu, head_config, &unit, &scale)) + if (!head_config) { + attr.type = pmu->type; + evsel = __add_event(list, idx, &attr, NULL, pmu->cpus); + return evsel ? 0 : -ENOMEM; + } + + if (perf_pmu__check_alias(pmu, head_config, &info)) return -EINVAL; /* @@ -659,8 +679,10 @@ int parse_events_add_pmu(struct list_head *list, int *idx, evsel = __add_event(list, idx, &attr, pmu_event_name(head_config), pmu->cpus); if (evsel) { - evsel->unit = unit; - evsel->scale = scale; + evsel->unit = info.unit; + evsel->scale = info.scale; + evsel->per_pkg = info.per_pkg; + evsel->snapshot = info.snapshot; } return evsel ? 0 : -ENOMEM; @@ -852,30 +874,111 @@ int parse_events_name(struct list_head *list, char *name) return 0; } -static int parse_events__scanner(const char *str, void *data, int start_token); +static int +comp_pmu(const void *p1, const void *p2) +{ + struct perf_pmu_event_symbol *pmu1 = (struct perf_pmu_event_symbol *) p1; + struct perf_pmu_event_symbol *pmu2 = (struct perf_pmu_event_symbol *) p2; -static int parse_events_fixup(int ret, const char *str, void *data, - int start_token) + return strcmp(pmu1->symbol, pmu2->symbol); +} + +static void perf_pmu__parse_cleanup(void) { - char *o = strdup(str); - char *s = NULL; - char *t = o; - char *p; + if (perf_pmu_events_list_num > 0) { + struct perf_pmu_event_symbol *p; + int i; + + for (i = 0; i < perf_pmu_events_list_num; i++) { + p = perf_pmu_events_list + i; + free(p->symbol); + } + free(perf_pmu_events_list); + perf_pmu_events_list = NULL; + perf_pmu_events_list_num = 0; + } +} + +#define SET_SYMBOL(str, stype) \ +do { \ + p->symbol = str; \ + if (!p->symbol) \ + goto err; \ + p->type = stype; \ +} while (0) + +/* + * Read the pmu events list from sysfs + * Save it into perf_pmu_events_list + */ +static void perf_pmu__parse_init(void) +{ + + struct perf_pmu *pmu = NULL; + struct perf_pmu_alias *alias; int len = 0; - if (!o) - return ret; - while ((p = strsep(&t, ",")) != NULL) { - if (s) - str_append(&s, &len, ","); - str_append(&s, &len, "cpu/"); - str_append(&s, &len, p); - str_append(&s, &len, "/"); + pmu = perf_pmu__find("cpu"); + if ((pmu == NULL) || list_empty(&pmu->aliases)) { + perf_pmu_events_list_num = -1; + return; } - free(o); - if (!s) - return -ENOMEM; - return parse_events__scanner(s, data, start_token); + list_for_each_entry(alias, &pmu->aliases, list) { + if (strchr(alias->name, '-')) + len++; + len++; + } + perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len); + if (!perf_pmu_events_list) + return; + perf_pmu_events_list_num = len; + + len = 0; + list_for_each_entry(alias, &pmu->aliases, list) { + struct perf_pmu_event_symbol *p = perf_pmu_events_list + len; + char *tmp = strchr(alias->name, '-'); + + if (tmp != NULL) { + SET_SYMBOL(strndup(alias->name, tmp - alias->name), + PMU_EVENT_SYMBOL_PREFIX); + p++; + SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX); + len += 2; + } else { + SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL); + len++; + } + } + qsort(perf_pmu_events_list, len, + sizeof(struct perf_pmu_event_symbol), comp_pmu); + + return; +err: + perf_pmu__parse_cleanup(); +} + +enum perf_pmu_event_symbol_type +perf_pmu__parse_check(const char *name) +{ + struct perf_pmu_event_symbol p, *r; + + /* scan kernel pmu events from sysfs if needed */ + if (perf_pmu_events_list_num == 0) + perf_pmu__parse_init(); + /* + * name "cpu" could be prefix of cpu-cycles or cpu// events. + * cpu-cycles has been handled by hardcode. + * So it must be cpu// events, not kernel pmu event. + */ + if ((perf_pmu_events_list_num <= 0) || !strcmp(name, "cpu")) + return PMU_EVENT_SYMBOL_ERR; + + p.symbol = strdup(name); + r = bsearch(&p, perf_pmu_events_list, + (size_t) perf_pmu_events_list_num, + sizeof(struct perf_pmu_event_symbol), comp_pmu); + free(p.symbol); + return r ? r->type : PMU_EVENT_SYMBOL_ERR; } static int parse_events__scanner(const char *str, void *data, int start_token) @@ -898,8 +1001,6 @@ static int parse_events__scanner(const char *str, void *data, int start_token) parse_events__flush_buffer(buffer, scanner); parse_events__delete_buffer(buffer, scanner); parse_events_lex_destroy(scanner); - if (ret && !strchr(str, '/')) - ret = parse_events_fixup(ret, str, data, start_token); return ret; } @@ -934,6 +1035,7 @@ int parse_events(struct perf_evlist *evlist, const char *str) int ret; ret = parse_events__scanner(str, &data, PE_START_EVENTS); + perf_pmu__parse_cleanup(); if (!ret) { int entries = data.idx - evlist->nr_entries; perf_evlist__splice_list_tail(evlist, &data.list, entries); @@ -973,7 +1075,7 @@ int parse_filter(const struct option *opt, const char *str, if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) { fprintf(stderr, - "-F option should follow a -e tracepoint option\n"); + "--filter option should follow a -e tracepoint option\n"); return -1; } @@ -1006,9 +1108,11 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; + char sbuf[STRERR_BUFSIZE]; if (debugfs_valid_mountpoint(tracing_events_path)) { - printf(" [ Tracepoints not available: %s ]\n", strerror(errno)); + printf(" [ Tracepoints not available: %s ]\n", + strerror_r(errno, sbuf, sizeof(sbuf))); return; } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index df094b4..db2cf78 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -35,6 +35,18 @@ extern int parse_filter(const struct option *opt, const char *str, int unset); #define EVENTS_HELP_MAX (128*1024) +enum perf_pmu_event_symbol_type { + PMU_EVENT_SYMBOL_ERR, /* not a PMU EVENT */ + PMU_EVENT_SYMBOL, /* normal style PMU event */ + PMU_EVENT_SYMBOL_PREFIX, /* prefix of pre-suf style event */ + PMU_EVENT_SYMBOL_SUFFIX, /* suffix of pre-suf style event */ +}; + +struct perf_pmu_event_symbol { + char *symbol; + enum perf_pmu_event_symbol_type type; +}; + enum { PARSE_EVENTS__TERM_TYPE_NUM, PARSE_EVENTS__TERM_TYPE_STR, @@ -95,6 +107,8 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type); int parse_events_add_pmu(struct list_head *list, int *idx, char *pmu , struct list_head *head_config); +enum perf_pmu_event_symbol_type +perf_pmu__parse_check(const char *name); void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 3432995..906630b 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -51,6 +51,24 @@ static int str(yyscan_t scanner, int token) return token; } +static int pmu_str_check(yyscan_t scanner) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + yylval->str = strdup(text); + switch (perf_pmu__parse_check(text)) { + case PMU_EVENT_SYMBOL_PREFIX: + return PE_PMU_EVENT_PRE; + case PMU_EVENT_SYMBOL_SUFFIX: + return PE_PMU_EVENT_SUF; + case PMU_EVENT_SYMBOL: + return PE_KERNEL_PMU_EVENT; + default: + return PE_NAME; + } +} + static int sym(yyscan_t scanner, int type, int config) { YYSTYPE *yylval = parse_events_get_lval(scanner); @@ -178,6 +196,16 @@ alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_AL emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } + /* + * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately. + * Because the prefix cycles is mixed up with cpu-cycles. + * loads and stores are mixed up with cache event + */ +cycles-ct { return str(yyscanner, PE_KERNEL_PMU_EVENT); } +cycles-t { return str(yyscanner, PE_KERNEL_PMU_EVENT); } +mem-loads { return str(yyscanner, PE_KERNEL_PMU_EVENT); } +mem-stores { return str(yyscanner, PE_KERNEL_PMU_EVENT); } + L1-dcache|l1-d|l1d|L1-data | L1-icache|l1-i|l1i|L1-instruction | LLC|L2 | @@ -199,7 +227,7 @@ r{num_raw_hex} { return raw(yyscanner); } {num_hex} { return value(yyscanner, 16); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } -{name} { return str(yyscanner, PE_NAME); } +{name} { return pmu_str_check(yyscanner); } "/" { BEGIN(config); return '/'; } - { return '-'; } , { BEGIN(event); return ','; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 0bc87ba..93c4c9f 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -47,6 +47,7 @@ static inc_group_count(struct list_head *list, %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP %token PE_ERROR +%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT %type <num> PE_VALUE %type <num> PE_VALUE_SYM_HW %type <num> PE_VALUE_SYM_SW @@ -58,6 +59,7 @@ static inc_group_count(struct list_head *list, %type <str> PE_MODIFIER_EVENT %type <str> PE_MODIFIER_BP %type <str> PE_EVENT_NAME +%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT %type <num> value_sym %type <head> event_config %type <term> event_term @@ -210,6 +212,54 @@ PE_NAME '/' event_config '/' parse_events__free_terms($3); $$ = list; } +| +PE_NAME '/' '/' +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL)); + $$ = list; +} +| +PE_KERNEL_PMU_EVENT sep_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *head; + struct parse_events_term *term; + struct list_head *list; + + ALLOC_LIST(head); + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, 1)); + list_add_tail(&term->list, head); + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head)); + parse_events__free_terms(head); + $$ = list; +} +| +PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *head; + struct parse_events_term *term; + struct list_head *list; + char pmu_name[128]; + snprintf(&pmu_name, 128, "%s-%s", $1, $3); + + ALLOC_LIST(head); + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + &pmu_name, 1)); + list_add_tail(&term->list, head); + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head)); + parse_events__free_terms(head); + $$ = list; +} value_sym: PE_VALUE_SYM_HW diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index bf48092..f62dee7b 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) { + 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 d8dac8a..97b153f 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; @@ -98,6 +100,7 @@ struct option { parse_opt_cb *callback; intptr_t defval; bool *set; + void *data; }; #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v ) @@ -131,6 +134,10 @@ struct option { { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\ .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\ .flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG} +#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \ + .value = (v), (a), .help = (h), .callback = (f), \ + .flags = PARSE_OPT_OPTARG, .data = (d) } /* parse_options() will filter out the processed options and leave the * non-option argments in argv[]. @@ -168,6 +175,7 @@ struct parse_opt_ctx_t { const char **out; int argc, cpidx; const char *opt; + const struct option *excl_opt; int flags; }; @@ -206,4 +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 7a811eb..5c9c494 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -2,6 +2,8 @@ #include <sys/types.h> #include <unistd.h> #include <stdio.h> +#include <stdbool.h> +#include <stdarg.h> #include <dirent.h> #include <api/fs/fs.h> #include <locale.h> @@ -10,16 +12,6 @@ #include "parse-events.h" #include "cpumap.h" -#define UNIT_MAX_LEN 31 /* max length for event unit name */ - -struct perf_pmu_alias { - char *name; - struct list_head terms; - struct list_head list; - char unit[UNIT_MAX_LEN+1]; - double scale; -}; - struct perf_pmu_format { char *name; int value; @@ -171,6 +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; @@ -189,6 +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) { @@ -202,12 +230,31 @@ 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); return 0; } +static inline bool pmu_alias_info_file(char *name) +{ + size_t len; + + len = strlen(name); + if (len > 5 && !strcmp(name + len - 5, ".unit")) + 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; +} + /* * Process all the sysfs attributes located under the directory * specified in 'dir' parameter. @@ -216,7 +263,6 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) { struct dirent *evt_ent; DIR *event_dir; - size_t len; int ret = 0; event_dir = opendir(dir); @@ -232,13 +278,9 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) continue; /* - * skip .unit and .scale info files - * parsed in perf_pmu__new_alias() + * skip info files parsed in perf_pmu__new_alias() */ - len = strlen(name); - if (len > 5 && !strcmp(name + len - 5, ".unit")) - continue; - if (len > 6 && !strcmp(name + len - 6, ".scale")) + if (pmu_alias_info_file(name)) continue; snprintf(path, PATH_MAX, "%s/%s", dir, name); @@ -387,6 +429,12 @@ static struct cpu_map *pmu_cpumask(const char *name) return cpus; } +struct perf_event_attr *__attribute__((weak)) +perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) +{ + return NULL; +} + static struct perf_pmu *pmu_lookup(const char *name) { struct perf_pmu *pmu; @@ -421,6 +469,9 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->name = strdup(name); pmu->type = type; list_add_tail(&pmu->list, &pmus); + + pmu->default_config = perf_pmu__get_default_config(pmu); + return pmu; } @@ -479,28 +530,24 @@ pmu_find_format(struct list_head *formats, char *name) } /* - * Returns value based on the format definition (format parameter) + * Sets value based on the format definition (format parameter) * and unformated value (value parameter). - * - * TODO maybe optimize a little ;) */ -static __u64 pmu_format_value(unsigned long *format, __u64 value) +static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, + bool zero) { unsigned long fbit, vbit; - __u64 v = 0; for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) { if (!test_bit(fbit, format)) continue; - if (!(value & (1llu << vbit++))) - continue; - - v |= (1llu << fbit); + if (value & (1llu << vbit++)) + *v |= (1llu << fbit); + else if (zero) + *v &= ~(1llu << fbit); } - - return v; } /* @@ -509,7 +556,8 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value) */ static int pmu_config_term(struct list_head *formats, struct perf_event_attr *attr, - struct parse_events_term *term) + struct parse_events_term *term, + bool zero) { struct perf_pmu_format *format; __u64 *vp; @@ -548,18 +596,19 @@ static int pmu_config_term(struct list_head *formats, * non-hardcoded terms, here's the place to translate * them into value. */ - *vp |= pmu_format_value(format->bits, term->val.num); + pmu_format_value(format->bits, term->val.num, vp, zero); return 0; } int perf_pmu__config_terms(struct list_head *formats, struct perf_event_attr *attr, - struct list_head *head_terms) + struct list_head *head_terms, + bool zero) { struct parse_events_term *term; list_for_each_entry(term, head_terms, list) - if (pmu_config_term(formats, attr, term)) + if (pmu_config_term(formats, attr, term, zero)) return -EINVAL; return 0; @@ -573,8 +622,10 @@ int perf_pmu__config_terms(struct list_head *formats, int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms) { + bool zero = !!pmu->default_config; + attr->type = pmu->type; - return perf_pmu__config_terms(&pmu->format, attr, head_terms); + return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero); } static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu, @@ -608,23 +659,27 @@ 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; } @@ -634,18 +689,21 @@ static int check_unit_scale(struct perf_pmu_alias *alias, * defined for the alias */ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, - const char **unit, double *scale) + struct perf_pmu_info *info) { struct parse_events_term *term, *h; struct perf_pmu_alias *alias; int ret; + info->per_pkg = false; + /* * Mark unit and scale as not set * (different from default values, see below) */ - *unit = NULL; - *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); @@ -655,10 +713,13 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, if (ret) return ret; - ret = check_unit_scale(alias, unit, 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); } @@ -668,11 +729,11 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, * set defaults as for evsel * unit cannot left to NULL */ - if (*unit == NULL) - *unit = ""; + if (info->unit == NULL) + info->unit = ""; - if (*scale == 0.0) - *scale = 1.0; + if (info->scale == 0.0) + info->scale = 1.0; return 0; } @@ -738,15 +799,18 @@ 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"); @@ -756,13 +820,23 @@ 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++) { @@ -771,12 +845,20 @@ 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) @@ -794,3 +876,39 @@ bool pmu_have_event(const char *pname, const char *name) } return false; } + +static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) +{ + struct stat st; + char path[PATH_MAX]; + const char *sysfs; + + sysfs = sysfs__mountpoint(); + if (!sysfs) + return NULL; + + snprintf(path, PATH_MAX, + "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name); + + if (stat(path, &st) < 0) + return NULL; + + return fopen(path, "r"); +} + +int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, + ...) +{ + va_list args; + FILE *file; + int ret = EOF; + + va_start(args, fmt); + file = perf_pmu__open_file(pmu, name); + if (file) { + ret = vfscanf(file, fmt, args); + fclose(file); + } + va_end(args); + return ret; +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index c14a543..6b1249f 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -13,13 +13,36 @@ enum { #define PERF_PMU_FORMAT_BITS 64 +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; - struct list_head aliases; - struct list_head list; + struct list_head format; /* HEAD struct perf_pmu_format -> list */ + struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */ + struct list_head list; /* ELEM */ +}; + +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 */ + +struct perf_pmu_alias { + char *name; + struct list_head terms; /* HEAD struct parse_events_term -> list */ + 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); @@ -27,9 +50,10 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms); int perf_pmu__config_terms(struct list_head *formats, struct perf_event_attr *attr, - struct list_head *head_terms); + struct list_head *head_terms, + bool zero); int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, - const char **unit, double *scale); + struct perf_pmu_info *info); struct list_head *perf_pmu__alias(struct perf_pmu *pmu, struct list_head *head_terms); int perf_pmu_wrap(void); @@ -45,5 +69,11 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); void print_pmu_events(const char *event_glob, bool name_only); bool pmu_have_event(const char *pname, const char *name); +int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, + ...) __attribute__((format(scanf, 3, 4))); + int perf_pmu__test(void); + +struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu); + #endif /* __PMU_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 9a0a183..28eb141 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -79,7 +79,7 @@ static int init_symbol_maps(bool user_only) int ret; symbol_conf.sort_by_name = true; - ret = symbol__init(); + ret = symbol__init(NULL); if (ret < 0) { pr_debug("Failed to init symbol map.\n"); goto out; @@ -184,7 +184,8 @@ static struct dso *kernel_get_module_dso(const char *module) const char *vmlinux_name; if (module) { - list_for_each_entry(dso, &host_machine->kernel_dsos, node) { + list_for_each_entry(dso, &host_machine->kernel_dsos.head, + node) { if (strncmp(dso->short_name + 1, module, dso->short_name_len - 2) == 0) goto found; @@ -258,21 +259,33 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) #ifdef HAVE_DWARF_SUPPORT /* Open new debuginfo of given module */ -static struct debuginfo *open_debuginfo(const char *module) +static struct debuginfo *open_debuginfo(const char *module, bool silent) { const char *path = module; + struct debuginfo *ret; if (!module || !strchr(module, '/')) { path = kernel_get_module_path(module); if (!path) { - pr_err("Failed to find path of %s module.\n", - module ?: "kernel"); + if (!silent) + pr_err("Failed to find path of %s module.\n", + module ?: "kernel"); return NULL; } } - return debuginfo__new(path); + ret = debuginfo__new(path); + if (!ret && !silent) { + pr_warning("The %s file has no debug information.\n", path); + if (!module || !strtailcmp(path, ".ko")) + pr_warning("Rebuild with CONFIG_DEBUG_INFO=y, "); + else + pr_warning("Rebuild with -g, "); + pr_warning("or install an appropriate debuginfo package.\n"); + } + return ret; } + static int get_text_start_address(const char *exec, unsigned long *address) { Elf *elf; @@ -333,15 +346,13 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, pr_debug("try to find information at %" PRIx64 " in %s\n", addr, tp->module ? : "kernel"); - dinfo = open_debuginfo(tp->module); + dinfo = open_debuginfo(tp->module, verbose == 0); if (dinfo) { ret = debuginfo__find_probe_point(dinfo, (unsigned long)addr, pp); debuginfo__delete(dinfo); - } else { - pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr); + } else ret = -ENOENT; - } if (ret > 0) { pp->retprobe = tp->retprobe; @@ -457,13 +468,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, struct debuginfo *dinfo; int ntevs, ret = 0; - dinfo = open_debuginfo(target); + dinfo = open_debuginfo(target, !need_dwarf); if (!dinfo) { - if (need_dwarf) { - pr_warning("Failed to open debuginfo file.\n"); + if (need_dwarf) return -ENOENT; - } pr_debug("Could not open debuginfo. Try to use symbols.\n"); return 0; } @@ -565,7 +574,7 @@ static int get_real_path(const char *raw_path, const char *comp_dir, static int __show_one_line(FILE *fp, int l, bool skip, bool show_num) { - char buf[LINEBUF_SIZE]; + char buf[LINEBUF_SIZE], sbuf[STRERR_BUFSIZE]; const char *color = show_num ? "" : PERF_COLOR_BLUE; const char *prefix = NULL; @@ -585,7 +594,8 @@ static int __show_one_line(FILE *fp, int l, bool skip, bool show_num) return 1; error: if (ferror(fp)) { - pr_warning("File read error: %s\n", strerror(errno)); + pr_warning("File read error: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); return -1; } return 0; @@ -618,13 +628,12 @@ static int __show_line_range(struct line_range *lr, const char *module) FILE *fp; int ret; char *tmp; + char sbuf[STRERR_BUFSIZE]; /* Search a line range */ - dinfo = open_debuginfo(module); - if (!dinfo) { - pr_warning("Failed to open debuginfo file.\n"); + dinfo = open_debuginfo(module, false); + if (!dinfo) return -ENOENT; - } ret = debuginfo__find_line_range(dinfo, lr); debuginfo__delete(dinfo); @@ -656,7 +665,7 @@ static int __show_line_range(struct line_range *lr, const char *module) fp = fopen(lr->path, "r"); if (fp == NULL) { pr_warning("Failed to open %s: %s\n", lr->path, - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); return -errno; } /* Skip to starting line number */ @@ -689,11 +698,11 @@ end: return ret; } -int show_line_range(struct line_range *lr, const char *module) +int show_line_range(struct line_range *lr, const char *module, bool user) { int ret; - ret = init_symbol_maps(false); + ret = init_symbol_maps(user); if (ret < 0) return ret; ret = __show_line_range(lr, module); @@ -768,13 +777,12 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, int i, ret = 0; struct debuginfo *dinfo; - ret = init_symbol_maps(false); + ret = init_symbol_maps(pevs->uprobes); if (ret < 0) return ret; - dinfo = open_debuginfo(module); + dinfo = open_debuginfo(module, false); if (!dinfo) { - pr_warning("Failed to open debuginfo file.\n"); ret = -ENOENT; goto out; } @@ -815,7 +823,8 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, } int show_line_range(struct line_range *lr __maybe_unused, - const char *module __maybe_unused) + const char *module __maybe_unused, + bool user __maybe_unused) { pr_warning("Debuginfo-analysis is not supported.\n"); return -ENOSYS; @@ -1405,8 +1414,7 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len) return tmp - buf; error: - pr_debug("Failed to synthesize perf probe argument: %s\n", - strerror(-ret)); + pr_debug("Failed to synthesize perf probe argument: %d\n", ret); return ret; } @@ -1455,8 +1463,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp) return buf; error: - pr_debug("Failed to synthesize perf probe point: %s\n", - strerror(-ret)); + pr_debug("Failed to synthesize perf probe point: %d\n", ret); free(buf); return NULL; } @@ -1780,10 +1787,11 @@ static void clear_probe_trace_event(struct probe_trace_event *tev) memset(tev, 0, sizeof(*tev)); } -static void print_warn_msg(const char *file, bool is_kprobe) +static void print_open_warning(int err, bool is_kprobe) { + char sbuf[STRERR_BUFSIZE]; - if (errno == ENOENT) { + if (err == -ENOENT) { const char *config; if (!is_kprobe) @@ -1791,25 +1799,43 @@ static void print_warn_msg(const char *file, bool is_kprobe) else config = "CONFIG_KPROBE_EVENTS"; - pr_warning("%s file does not exist - please rebuild kernel" - " with %s.\n", file, config); - } else - pr_warning("Failed to open %s file: %s\n", file, - strerror(errno)); + pr_warning("%cprobe_events file does not exist" + " - please rebuild kernel with %s.\n", + is_kprobe ? 'k' : 'u', config); + } else if (err == -ENOTSUP) + pr_warning("Debugfs is not mounted.\n"); + else + pr_warning("Failed to open %cprobe_events: %s\n", + is_kprobe ? 'k' : 'u', + strerror_r(-err, sbuf, sizeof(sbuf))); +} + +static void print_both_open_warning(int kerr, int uerr) +{ + /* Both kprobes and uprobes are disabled, warn it. */ + if (kerr == -ENOTSUP && uerr == -ENOTSUP) + pr_warning("Debugfs is not mounted.\n"); + else if (kerr == -ENOENT && uerr == -ENOENT) + pr_warning("Please rebuild kernel with CONFIG_KPROBE_EVENTS " + "or/and CONFIG_UPROBE_EVENTS.\n"); + else { + char sbuf[STRERR_BUFSIZE]; + pr_warning("Failed to open kprobe events: %s.\n", + strerror_r(-kerr, sbuf, sizeof(sbuf))); + pr_warning("Failed to open uprobe events: %s.\n", + strerror_r(-uerr, sbuf, sizeof(sbuf))); + } } -static int open_probe_events(const char *trace_file, bool readwrite, - bool is_kprobe) +static int open_probe_events(const char *trace_file, bool readwrite) { char buf[PATH_MAX]; const char *__debugfs; int ret; __debugfs = debugfs_find_mountpoint(); - if (__debugfs == NULL) { - pr_warning("Debugfs is not mounted.\n"); - return -ENOENT; - } + if (__debugfs == NULL) + return -ENOTSUP; ret = e_snprintf(buf, PATH_MAX, "%s/%s", __debugfs, trace_file); if (ret >= 0) { @@ -1820,19 +1846,19 @@ static int open_probe_events(const char *trace_file, bool readwrite, ret = open(buf, O_RDONLY, 0); if (ret < 0) - print_warn_msg(buf, is_kprobe); + ret = -errno; } return ret; } static int open_kprobe_events(bool readwrite) { - return open_probe_events("tracing/kprobe_events", readwrite, true); + return open_probe_events("tracing/kprobe_events", readwrite); } static int open_uprobe_events(bool readwrite) { - return open_probe_events("tracing/uprobe_events", readwrite, false); + return open_probe_events("tracing/uprobe_events", readwrite); } /* Get raw string list of current kprobe_events or uprobe_events */ @@ -1857,7 +1883,7 @@ static struct strlist *get_probe_trace_command_rawlist(int fd) p[idx] = '\0'; ret = strlist__add(sl, buf); if (ret < 0) { - pr_debug("strlist__add failed: %s\n", strerror(-ret)); + pr_debug("strlist__add failed (%d)\n", ret); strlist__delete(sl); return NULL; } @@ -1884,21 +1910,21 @@ 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; } @@ -1916,7 +1942,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe) rawlist = get_probe_trace_command_rawlist(fd); if (!rawlist) - return -ENOENT; + return -ENOMEM; strlist__for_each(ent, rawlist) { ret = parse_probe_trace_command(ent->s, &tev); @@ -1940,27 +1966,34 @@ static int __show_perf_probe_events(int fd, bool is_kprobe) /* List up current perf-probe events */ int show_perf_probe_events(void) { - int fd, ret; + int kp_fd, up_fd, ret; setup_pager(); - fd = open_kprobe_events(false); - - if (fd < 0) - return fd; ret = init_symbol_maps(false); if (ret < 0) return ret; - ret = __show_perf_probe_events(fd, true); - close(fd); + kp_fd = open_kprobe_events(false); + if (kp_fd >= 0) { + ret = __show_perf_probe_events(kp_fd, true); + close(kp_fd); + if (ret < 0) + goto out; + } - fd = open_uprobe_events(false); - if (fd >= 0) { - ret = __show_perf_probe_events(fd, false); - close(fd); + up_fd = open_uprobe_events(false); + if (kp_fd < 0 && up_fd < 0) { + print_both_open_warning(kp_fd, up_fd); + ret = kp_fd; + goto out; } + if (up_fd >= 0) { + ret = __show_perf_probe_events(up_fd, false); + close(up_fd); + } +out: exit_symbol_maps(); return ret; } @@ -1976,6 +2009,8 @@ static struct strlist *get_probe_trace_event_names(int fd, bool include_group) memset(&tev, 0, sizeof(tev)); rawlist = get_probe_trace_command_rawlist(fd); + if (!rawlist) + return NULL; sl = strlist__new(true, NULL); strlist__for_each(ent, rawlist) { ret = parse_probe_trace_command(ent->s, &tev); @@ -2005,6 +2040,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev) { int ret = 0; char *buf = synthesize_probe_trace_command(tev); + char sbuf[STRERR_BUFSIZE]; if (!buf) { pr_debug("Failed to synthesize probe trace event.\n"); @@ -2016,7 +2052,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev) ret = write(fd, buf, strlen(buf)); if (ret <= 0) pr_warning("Failed to write event: %s\n", - strerror(errno)); + strerror_r(errno, sbuf, sizeof(sbuf))); } free(buf); return ret; @@ -2030,7 +2066,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base, /* Try no suffix */ ret = e_snprintf(buf, len, "%s", base); if (ret < 0) { - pr_debug("snprintf() failed: %s\n", strerror(-ret)); + pr_debug("snprintf() failed: %d\n", ret); return ret; } if (!strlist__has_entry(namelist, buf)) @@ -2046,7 +2082,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base, for (i = 1; i < MAX_EVENT_INDEX; i++) { ret = e_snprintf(buf, len, "%s_%d", base, i); if (ret < 0) { - pr_debug("snprintf() failed: %s\n", strerror(-ret)); + pr_debug("snprintf() failed: %d\n", ret); return ret; } if (!strlist__has_entry(namelist, buf)) @@ -2075,8 +2111,11 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, else fd = open_kprobe_events(true); - if (fd < 0) + if (fd < 0) { + print_open_warning(fd, !pev->uprobes); return fd; + } + /* Get current event names */ namelist = get_probe_trace_event_names(fd, false); if (!namelist) { @@ -2085,7 +2124,7 @@ 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) @@ -2140,8 +2179,8 @@ 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); } @@ -2405,10 +2444,11 @@ 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", strerror(-ret)); + pr_warning("Failed to delete event: %s\n", + strerror_r(-ret, buf, sizeof(buf))); return ret; } @@ -2449,15 +2489,18 @@ int del_perf_probe_events(struct strlist *dellist) /* Get current event names */ kfd = open_kprobe_events(true); - if (kfd < 0) - return kfd; + if (kfd >= 0) + namelist = get_probe_trace_event_names(kfd, true); - namelist = get_probe_trace_event_names(kfd, true); ufd = open_uprobe_events(true); - if (ufd >= 0) unamelist = get_probe_trace_event_names(ufd, true); + if (kfd < 0 && ufd < 0) { + print_both_open_warning(kfd, ufd); + goto error; + } + if (namelist == NULL && unamelist == NULL) goto error; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 776c934..e01e994 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -128,7 +128,8 @@ extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, bool force_add); extern int del_perf_probe_events(struct strlist *dellist); extern int show_perf_probe_events(void); -extern int show_line_range(struct line_range *lr, const char *module); +extern int show_line_range(struct line_range *lr, const char *module, + bool user); extern int show_available_vars(struct perf_probe_event *pevs, int npevs, int max_probe_points, const char *module, struct strfilter *filter, bool externs); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 98e3047..c7918f8 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -26,7 +26,6 @@ #include <errno.h> #include <stdio.h> #include <unistd.h> -#include <getopt.h> #include <stdlib.h> #include <string.h> #include <stdarg.h> @@ -282,6 +281,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, struct probe_trace_arg_ref **ref_ptr = &tvar->ref; Dwarf_Die type; char buf[16]; + char sbuf[STRERR_BUFSIZE]; int bsize, boffs, total; int ret; @@ -368,7 +368,7 @@ formatted: if (ret >= 16) ret = -E2BIG; pr_warning("Failed to convert variable type: %s\n", - strerror(-ret)); + strerror_r(-ret, sbuf, sizeof(sbuf))); return ret; } tvar->type = strdup(buf); @@ -609,14 +609,18 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, return -EINVAL; } - /* Get an appropriate symbol from symtab */ - symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); + symbol = dwarf_diename(sp_die); if (!symbol) { - pr_warning("Failed to find symbol at 0x%lx\n", - (unsigned long)paddr); - return -ENOENT; + /* Try to get the symbol name from symtab */ + symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); + if (!symbol) { + pr_warning("Failed to find symbol at 0x%lx\n", + (unsigned long)paddr); + return -ENOENT; + } + eaddr = sym.st_value; } - tp->offset = (unsigned long)(paddr - sym.st_value); + tp->offset = (unsigned long)(paddr - eaddr); tp->address = (unsigned long)paddr; tp->symbol = strdup(symbol); if (!tp->symbol) @@ -780,10 +784,12 @@ static int find_lazy_match_lines(struct intlist *list, size_t line_len; ssize_t len; int count = 0, linenum = 1; + char sbuf[STRERR_BUFSIZE]; fp = fopen(fname, "r"); if (!fp) { - pr_warning("Failed to open %s: %s\n", fname, strerror(errno)); + pr_warning("Failed to open %s: %s\n", fname, + strerror_r(errno, sbuf, sizeof(sbuf))); return -errno; } diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c index daa17ae..a126e6c 100644 --- a/tools/perf/util/pstack.c +++ b/tools/perf/util/pstack.c @@ -6,6 +6,7 @@ #include "util.h" #include "pstack.h" +#include "debug.h" #include <linux/kernel.h> #include <stdlib.h> diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 122669c..3dda85c 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -14,12 +14,12 @@ */ int verbose; -int eprintf(int level, const char *fmt, ...) +int eprintf(int level, int var, const char *fmt, ...) { va_list args; int ret = 0; - if (verbose >= level) { + if (var >= level) { va_start(args, fmt); ret = vfprintf(stderr, fmt, args); va_end(args); @@ -736,7 +736,7 @@ static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist, if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout)) return NULL; - n = poll(evlist->pollfd, evlist->nr_fds, timeout); + n = perf_evlist__poll(evlist, timeout); if (n < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; @@ -753,9 +753,9 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, PyObject *list = PyList_New(0); int i; - for (i = 0; i < evlist->nr_fds; ++i) { + for (i = 0; i < evlist->pollfd.nr; ++i) { PyObject *file; - FILE *fp = fdopen(evlist->pollfd[i].fd, "r"); + FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r"); if (fp == NULL) goto free_list; diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 049e0a0..8acd0df 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -4,6 +4,7 @@ #include "parse-events.h" #include <api/fs/fs.h> #include "util.h" +#include "cloexec.h" typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel); @@ -11,7 +12,9 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) { struct perf_evlist *evlist; struct perf_evsel *evsel; + unsigned long flags = perf_event_open_cloexec_flag(); int err = -EAGAIN, fd; + static pid_t pid = -1; evlist = perf_evlist__new(); if (!evlist) @@ -22,14 +25,22 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) evsel = perf_evlist__first(evlist); - fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); - if (fd < 0) - goto out_delete; + while (1) { + fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags); + if (fd < 0) { + if (pid == -1 && errno == EACCES) { + pid = 0; + continue; + } + goto out_delete; + } + break; + } close(fd); fn(evsel); - fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags); if (fd < 0) { if (errno == EINVAL) err = -EINVAL; @@ -45,7 +56,7 @@ out_delete: static bool perf_probe_api(setup_probe_fn_t fn) { - const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL}; + const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL}; struct cpu_map *cpus; int cpu, ret, i = 0; @@ -69,15 +80,26 @@ static void perf_probe_sample_identifier(struct perf_evsel *evsel) evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER; } +static void perf_probe_comm_exec(struct perf_evsel *evsel) +{ + evsel->attr.comm_exec = 1; +} + bool perf_can_sample_identifier(void) { return perf_probe_api(perf_probe_sample_identifier); } +static bool perf_can_comm_exec(void) +{ + return perf_probe_api(perf_probe_comm_exec); +} + void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) { struct perf_evsel *evsel; bool use_sample_identifier = false; + bool use_comm_exec; /* * Set the evsel leader links before we configure attributes, @@ -89,8 +111,13 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) if (evlist->cpus->map[0] < 0) opts->no_inherit = true; - evlist__for_each(evlist, evsel) + use_comm_exec = perf_can_comm_exec(); + + evlist__for_each(evlist, evsel) { perf_evsel__config(evsel, opts); + if (evsel->tracking && use_comm_exec) + evsel->attr.comm_exec = 1; + } if (evlist->nr_entries > 1) { struct perf_evsel *first = perf_evlist__first(evlist); @@ -110,16 +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) @@ -183,6 +201,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) struct perf_evsel *evsel; int err, fd, cpu; bool ret = false; + pid_t pid = -1; temp_evlist = perf_evlist__new(); if (!temp_evlist) @@ -203,11 +222,20 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) cpu = evlist->cpus->map[0]; } - fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); - if (fd >= 0) { - close(fd); - ret = true; + while (1) { + fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, + perf_event_open_cloexec_flag()); + if (fd < 0) { + if (pid == -1 && errno == EACCES) { + pid = 0; + continue; + } + goto out_delete; + } + break; } + close(fd); + ret = true; out_delete: perf_evlist__delete(temp_evlist); diff --git a/tools/perf/util/run-command.c b/tools/perf/util/run-command.c index da8e9b2..34622b5 100644 --- a/tools/perf/util/run-command.c +++ b/tools/perf/util/run-command.c @@ -1,6 +1,7 @@ #include "cache.h" #include "run-command.h" #include "exec_cmd.h" +#include "debug.h" static inline void close_pair(int fd[2]) { @@ -19,6 +20,7 @@ int start_command(struct child_process *cmd) { int need_in, need_out, need_err; int fdin[2], fdout[2], fderr[2]; + char sbuf[STRERR_BUFSIZE]; /* * In case of errors we must keep the promise to close FDs @@ -99,7 +101,7 @@ int start_command(struct child_process *cmd) if (cmd->dir && chdir(cmd->dir)) die("exec %s: cd to %s failed (%s)", cmd->argv[0], - cmd->dir, strerror(errno)); + cmd->dir, strerror_r(errno, sbuf, sizeof(sbuf))); if (cmd->env) { for (; *cmd->env; cmd->env++) { if (strchr(*cmd->env, '=')) @@ -153,6 +155,8 @@ int start_command(struct child_process *cmd) static int wait_or_whine(pid_t pid) { + char sbuf[STRERR_BUFSIZE]; + for (;;) { int status, code; pid_t waiting = waitpid(pid, &status, 0); @@ -160,7 +164,8 @@ static int wait_or_whine(pid_t pid) if (waiting < 0) { if (errno == EINTR) continue; - error("waitpid failed (%s)", strerror(errno)); + error("waitpid failed (%s)", + strerror_r(errno, sbuf, sizeof(sbuf))); return -ERR_RUN_COMMAND_WAITPID; } if (waiting != pid) diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index af7da56..22ebc46 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> @@ -34,6 +35,7 @@ #include "../event.h" #include "../trace-event.h" #include "../evsel.h" +#include "../debug.h" void boot_Perf__Trace__Context(pTHX_ CV *cv); void boot_DynaLoader(pTHX_ CV *cv); @@ -56,7 +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; @@ -237,35 +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; @@ -277,7 +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); @@ -285,6 +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; @@ -431,6 +415,11 @@ error: return err; } +static int perl_flush_script(void) +{ + return 0; +} + /* * Stop trace script */ @@ -632,6 +621,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) struct scripting_ops perl_scripting_ops = { .name = "Perl", .start_script = perl_start_script, + .flush_script = perl_flush_script, .stop_script = perl_stop_script, .process_event = perl_process_event, .generate_script = perl_generate_script, diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 1c41932..d808a32 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -24,21 +24,30 @@ #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" +#include "../callchain.h" #include "../evsel.h" #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" 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 @@ -50,10 +59,32 @@ 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) { PyErr_Print(); Py_FatalError("problem in Python trace event handler"); + // Py_FatalError does not return + // but we have to make the compiler happy + abort(); } /* @@ -67,6 +98,35 @@ static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObj Py_DECREF(val); } +static PyObject *get_handler(const char *handler_name) +{ + PyObject *handler; + + handler = PyDict_GetItemString(main_dict, handler_name); + if (handler && !PyCallable_Check(handler)) + return NULL; + return handler; +} + +static void call_object(PyObject *handler, PyObject *args, const char *die_msg) +{ + PyObject *retval; + + retval = PyObject_CallObject(handler, args); + if (retval == NULL) + handler_call_die(die_msg); + Py_DECREF(retval); +} + +static void try_call_object(const char *handler_name, PyObject *args) +{ + PyObject *handler; + + handler = get_handler(handler_name); + if (handler) + call_object(handler, args, handler_name); +} + static void define_value(enum print_arg_type field_type, const char *ev_name, const char *field_name, @@ -74,7 +134,7 @@ static void define_value(enum print_arg_type field_type, const char *field_str) { const char *handler_name = "define_flag_value"; - PyObject *handler, *t, *retval; + PyObject *t; unsigned long long value; unsigned n = 0; @@ -92,12 +152,7 @@ static void define_value(enum print_arg_type field_type, PyTuple_SetItem(t, n++, PyInt_FromLong(value)); PyTuple_SetItem(t, n++, PyString_FromString(field_str)); - handler = PyDict_GetItemString(main_dict, handler_name); - if (handler && PyCallable_Check(handler)) { - retval = PyObject_CallObject(handler, t); - if (retval == NULL) - handler_call_die(handler_name); - } + try_call_object(handler_name, t); Py_DECREF(t); } @@ -120,7 +175,7 @@ static void define_field(enum print_arg_type field_type, const char *delim) { const char *handler_name = "define_flag_field"; - PyObject *handler, *t, *retval; + PyObject *t; unsigned n = 0; if (field_type == PRINT_SYMBOL) @@ -138,12 +193,7 @@ static void define_field(enum print_arg_type field_type, if (field_type == PRINT_FLAGS) PyTuple_SetItem(t, n++, PyString_FromString(delim)); - handler = PyDict_GetItemString(main_dict, handler_name); - if (handler && PyCallable_Check(handler)) { - retval = PyObject_CallObject(handler, t); - if (retval == NULL) - handler_call_die(handler_name); - } + try_call_object(handler_name, t); Py_DECREF(t); } @@ -206,42 +256,135 @@ 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 PyObject *get_field_numeric_entry(struct event_format *event, + struct format_field *field, void *data) { - static char ev_name[256]; - struct event_format *event; - int type = evsel->attr.config; + bool is_array = field->flags & FIELD_IS_ARRAY; + PyObject *obj, *list = NULL; + unsigned long long val; + unsigned int item_size, n_items, i; - /* - * 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; + if (is_array) { + list = PyList_New(field->arraylen); + item_size = field->size / field->arraylen; + n_items = field->arraylen; + } else { + item_size = field->size; + n_items = 1; + } - sprintf(ev_name, "%s__%s", event->system, event->name); + for (i = 0; i < n_items; i++) { + + val = read_size(event, data + field->offset + i * item_size, + item_size); + if (field->flags & FIELD_IS_SIGNED) { + if ((long long)val >= LONG_MIN && + (long long)val <= LONG_MAX) + obj = PyInt_FromLong(val); + else + obj = PyLong_FromLongLong(val); + } else { + if (val <= LONG_MAX) + obj = PyInt_FromLong(val); + else + obj = PyLong_FromUnsignedLongLong(val); + } + if (is_array) + PyList_SET_ITEM(list, i, obj); + } + if (is_array) + obj = list; + return obj; +} - define_event_symbols(event, ev_name, event->print_fmt.args); - return event; +static PyObject *python_process_callchain(struct perf_sample *sample, + struct perf_evsel *evsel, + struct addr_location *al) +{ + PyObject *pylist; + + pylist = PyList_New(0); + if (!pylist) + Py_FatalError("couldn't create Python list"); + + if (!symbol_conf.use_callchain || !sample->callchain) + goto exit; + + 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; + } + callchain_cursor_commit(&callchain_cursor); + + + while (1) { + PyObject *pyelem; + struct callchain_cursor_node *node; + node = callchain_cursor_current(&callchain_cursor); + if (!node) + break; + + pyelem = PyDict_New(); + if (!pyelem) + Py_FatalError("couldn't create Python dictionary"); + + + pydict_set_item_string_decref(pyelem, "ip", + PyLong_FromUnsignedLongLong(node->ip)); + + if (node->sym) { + PyObject *pysym = PyDict_New(); + if (!pysym) + Py_FatalError("couldn't create Python dictionary"); + pydict_set_item_string_decref(pysym, "start", + PyLong_FromUnsignedLongLong(node->sym->start)); + pydict_set_item_string_decref(pysym, "end", + PyLong_FromUnsignedLongLong(node->sym->end)); + pydict_set_item_string_decref(pysym, "binding", + PyInt_FromLong(node->sym->binding)); + pydict_set_item_string_decref(pysym, "name", + PyString_FromStringAndSize(node->sym->name, + node->sym->namelen)); + pydict_set_item_string_decref(pyelem, "sym", pysym); + } + + if (node->map) { + struct map *map = node->map; + const char *dsoname = "[unknown]"; + if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else if (map->dso->name) + dsoname = map->dso->name; + } + pydict_set_item_string_decref(pyelem, "dso", + PyString_FromString(dsoname)); + } + + callchain_cursor_advance(&callchain_cursor); + PyList_Append(pylist, pyelem); + Py_DECREF(pyelem); + } + +exit: + return pylist; } + static void python_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, struct addr_location *al) { - PyObject *handler, *retval, *context, *t, *obj, *dict = NULL; + 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 long val; unsigned long s, ns; - struct event_format *event; unsigned n = 0; int pid; int cpu = sample->cpu; @@ -253,7 +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); @@ -261,9 +403,10 @@ static void python_process_tracepoint(struct perf_sample *sample, sprintf(handler_name, "%s__%s", event->system, event->name); - handler = PyDict_GetItemString(main_dict, handler_name); - if (handler && !PyCallable_Check(handler)) - handler = NULL; + 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(); if (!dict) @@ -280,18 +423,23 @@ static void python_process_tracepoint(struct perf_sample *sample, PyTuple_SetItem(t, n++, PyString_FromString(handler_name)); PyTuple_SetItem(t, n++, context); + /* ip unwinding */ + callchain = python_process_callchain(sample, evsel, al); + if (handler) { PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); PyTuple_SetItem(t, n++, PyInt_FromLong(s)); PyTuple_SetItem(t, n++, PyInt_FromLong(ns)); PyTuple_SetItem(t, n++, PyInt_FromLong(pid)); PyTuple_SetItem(t, n++, PyString_FromString(comm)); + PyTuple_SetItem(t, n++, callchain); } else { pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu)); pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s)); pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns)); pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid)); pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm)); + pydict_set_item_string_decref(dict, "common_callchain", callchain); } for (field = event->format.fields; field; field = field->next) { if (field->flags & FIELD_IS_STRING) { @@ -303,20 +451,7 @@ static void python_process_tracepoint(struct perf_sample *sample, offset = field->offset; obj = PyString_FromString((char *)data + offset); } else { /* FIELD_IS_NUMERIC */ - val = read_size(event, data + field->offset, - field->size); - if (field->flags & FIELD_IS_SIGNED) { - if ((long long)val >= LONG_MIN && - (long long)val <= LONG_MAX) - obj = PyInt_FromLong(val); - else - obj = PyLong_FromLongLong(val); - } else { - if (val <= LONG_MAX) - obj = PyInt_FromLong(val); - else - obj = PyLong_FromUnsignedLongLong(val); - } + obj = get_field_numeric_entry(event, field, data); } if (handler) PyTuple_SetItem(t, n++, obj); @@ -324,6 +459,7 @@ static void python_process_tracepoint(struct perf_sample *sample, pydict_set_item_string_decref(dict, field->name, obj); } + if (!handler) PyTuple_SetItem(t, n++, dict); @@ -331,29 +467,304 @@ static void python_process_tracepoint(struct perf_sample *sample, Py_FatalError("error resizing Python tuple"); if (handler) { - retval = PyObject_CallObject(handler, t); - if (retval == NULL) - handler_call_die(handler_name); + call_object(handler, t, handler_name); } else { - handler = PyDict_GetItemString(main_dict, "trace_unhandled"); - if (handler && PyCallable_Check(handler)) { - - retval = PyObject_CallObject(handler, t); - if (retval == NULL) - handler_call_die("trace_unhandled"); - } + try_call_object("trace_unhandled", t); Py_DECREF(dict); } 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, struct addr_location *al) { - PyObject *handler, *retval, *t, *dict; + PyObject *handler, *t, *dict, *callchain, *dict_sample; static char handler_name[64]; unsigned n = 0; @@ -369,17 +780,34 @@ static void python_process_general_event(struct perf_sample *sample, if (!dict) Py_FatalError("couldn't create Python dictionary"); + dict_sample = PyDict_New(); + if (!dict_sample) + Py_FatalError("couldn't create Python dictionary"); + snprintf(handler_name, sizeof(handler_name), "%s", "process_event"); - handler = PyDict_GetItemString(main_dict, handler_name); - if (!handler || !PyCallable_Check(handler)) + handler = get_handler(handler_name); + if (!handler) goto exit; pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( (const char *)&evsel->attr, sizeof(evsel->attr))); - pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize( - (const char *)sample, sizeof(*sample))); + + pydict_set_item_string_decref(dict_sample, "pid", + PyInt_FromLong(sample->pid)); + pydict_set_item_string_decref(dict_sample, "tid", + PyInt_FromLong(sample->tid)); + pydict_set_item_string_decref(dict_sample, "cpu", + PyInt_FromLong(sample->cpu)); + pydict_set_item_string_decref(dict_sample, "ip", + PyLong_FromUnsignedLongLong(sample->ip)); + pydict_set_item_string_decref(dict_sample, "time", + PyLong_FromUnsignedLongLong(sample->time)); + pydict_set_item_string_decref(dict_sample, "period", + PyLong_FromUnsignedLongLong(sample->period)); + pydict_set_item_string_decref(dict, "sample", dict_sample); + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( (const char *)sample->raw_data, sample->raw_size)); pydict_set_item_string_decref(dict, "comm", @@ -393,66 +821,129 @@ static void python_process_general_event(struct perf_sample *sample, PyString_FromString(al->sym->name)); } + /* ip unwinding */ + callchain = python_process_callchain(sample, evsel, al); + pydict_set_item_string_decref(dict, "callchain", callchain); + PyTuple_SetItem(t, n++, dict); if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); - retval = PyObject_CallObject(handler, t); - if (retval == NULL) - handler_call_die(handler_name); + call_object(handler, t, handler_name); exit: Py_DECREF(dict); 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); } } static int run_start_sub(void) { - PyObject *handler, *retval; - int err = 0; - main_module = PyImport_AddModule("__main__"); if (main_module == NULL) return -1; Py_INCREF(main_module); main_dict = PyModule_GetDict(main_module); - if (main_dict == NULL) { - err = -1; + if (main_dict == NULL) goto error; - } Py_INCREF(main_dict); - handler = PyDict_GetItemString(main_dict, "trace_begin"); - if (handler == NULL || !PyCallable_Check(handler)) - goto out; + try_call_object("trace_begin", NULL); - retval = PyObject_CallObject(handler, NULL); - if (retval == NULL) - handler_call_die("trace_begin"); + return 0; - Py_DECREF(retval); - return err; error: Py_XDECREF(main_dict); Py_XDECREF(main_module); -out: - return err; + 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); } /* @@ -460,6 +951,7 @@ out: */ 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; @@ -498,6 +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(); @@ -506,29 +1006,29 @@ error: return err; } +static int python_flush_script(void) +{ + struct tables *tables = &tables_global; + + return db_export__flush(&tables->dbe); +} + /* * Stop trace script */ static int python_stop_script(void) { - PyObject *handler, *retval; - int err = 0; + struct tables *tables = &tables_global; - handler = PyDict_GetItemString(main_dict, "trace_end"); - if (handler == NULL || !PyCallable_Check(handler)) - goto out; + try_call_object("trace_end", NULL); + + db_export__exit(&tables->dbe); - retval = PyObject_CallObject(handler, NULL); - if (retval == NULL) - handler_call_die("trace_end"); - else - Py_DECREF(retval); -out: Py_XDECREF(main_dict); Py_XDECREF(main_module); Py_Finalize(); - return err; + return 0; } static int python_generate_script(struct pevent *pevent, const char *outfile) @@ -589,6 +1089,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "common_nsecs, "); fprintf(ofp, "common_pid, "); fprintf(ofp, "common_comm,\n\t"); + fprintf(ofp, "common_callchain, "); not_first = 0; count = 0; @@ -632,7 +1133,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%%u"); } - fprintf(ofp, "\\n\" %% \\\n\t\t("); + fprintf(ofp, "\" %% \\\n\t\t("); not_first = 0; count = 0; @@ -668,7 +1169,15 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s", f->name); } - fprintf(ofp, "),\n\n"); + fprintf(ofp, ")\n\n"); + + fprintf(ofp, "\t\tfor node in common_callchain:"); + fprintf(ofp, "\n\t\t\tif 'sym' in node:"); + fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])"); + fprintf(ofp, "\n\t\t\telse:"); + fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n"); + fprintf(ofp, "\t\tprint \"\\n\"\n\n"); + } fprintf(ofp, "def trace_unhandled(event_name, context, " @@ -692,6 +1201,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) struct scripting_ops python_scripting_ops = { .name = "Python", .start_script = python_start_script, + .flush_script = python_flush_script, .stop_script = python_stop_script, .process_event = python_process_event, .generate_script = python_generate_script, diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 64a186e..5f0e05a 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -14,7 +14,7 @@ #include "util.h" #include "cpumap.h" #include "perf_regs.h" -#include "vdso.h" +#include "asm/bug.h" static int perf_session__open(struct perf_session *session) { @@ -67,6 +67,25 @@ static void perf_session__destroy_kernel_maps(struct perf_session *session) machines__destroy_kernel_maps(&session->machines); } +static bool perf_session__has_comm_exec(struct perf_session *session) +{ + struct perf_evsel *evsel; + + evlist__for_each(session->evlist, evsel) { + if (evsel->attr.comm_exec) + return true; + } + + return false; +} + +static void perf_session__set_comm_exec(struct perf_session *session) +{ + bool comm_exec = perf_session__has_comm_exec(session); + + machines__set_comm_exec(&session->machines, comm_exec); +} + struct perf_session *perf_session__new(struct perf_data_file *file, bool repipe, struct perf_tool *tool) { @@ -76,9 +95,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file, goto out; session->repipe = repipe; - INIT_LIST_HEAD(&session->ordered_samples.samples); - INIT_LIST_HEAD(&session->ordered_samples.sample_cache); - INIT_LIST_HEAD(&session->ordered_samples.to_free); + ordered_events__init(&session->ordered_events); machines__init(&session->machines); if (file) { @@ -92,6 +109,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file, goto out_close; perf_session__set_id_hdr_size(session); + perf_session__set_comm_exec(session); } } @@ -101,13 +119,13 @@ struct perf_session *perf_session__new(struct perf_data_file *file, * kernel MMAP event, in perf_event__process_mmap(). */ if (perf_session__create_kernel_maps(session) < 0) - goto out_delete; + pr_warning("Cannot read kernel map\n"); } if (tool && tool->ordering_requires_timestamps && - tool->ordered_samples && !perf_evlist__sample_id_all(session->evlist)) { + tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); - tool->ordered_samples = false; + tool->ordered_events = false; } return session; @@ -156,7 +174,6 @@ void perf_session__delete(struct perf_session *session) if (session->file) perf_data_file__close(session->file); free(session); - vdso__exit(); } static int process_event_synth_tracing_data_stub(struct perf_tool *tool @@ -211,6 +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) @@ -240,11 +266,13 @@ void perf_tool__fill_defaults(struct perf_tool *tool) if (tool->build_id == NULL) tool->build_id = process_finished_round_stub; if (tool->finished_round == NULL) { - if (tool->ordered_samples) + if (tool->ordered_events) tool->finished_round = process_finished_round; 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) @@ -443,91 +471,10 @@ 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, }; -struct sample_queue { - u64 timestamp; - u64 file_offset; - union perf_event *event; - struct list_head list; -}; - -static void perf_session_free_sample_buffers(struct perf_session *session) -{ - struct ordered_samples *os = &session->ordered_samples; - - while (!list_empty(&os->to_free)) { - struct sample_queue *sq; - - sq = list_entry(os->to_free.next, struct sample_queue, list); - list_del(&sq->list); - free(sq); - } -} - -static int perf_session_deliver_event(struct perf_session *session, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool, - u64 file_offset); - -static int flush_sample_queue(struct perf_session *s, - struct perf_tool *tool) -{ - struct ordered_samples *os = &s->ordered_samples; - struct list_head *head = &os->samples; - struct sample_queue *tmp, *iter; - struct perf_sample sample; - u64 limit = os->next_flush; - u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL; - bool show_progress = limit == ULLONG_MAX; - struct ui_progress prog; - int ret; - - if (!tool->ordered_samples || !limit) - return 0; - - if (show_progress) - ui_progress__init(&prog, os->nr_samples, "Processing time ordered events..."); - - list_for_each_entry_safe(iter, tmp, head, list) { - if (session_done()) - return 0; - - if (iter->timestamp > limit) - break; - - ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample); - if (ret) - pr_err("Can't parse sample, err = %d\n", ret); - else { - ret = perf_session_deliver_event(s, iter->event, &sample, tool, - iter->file_offset); - if (ret) - return ret; - } - - os->last_flush = iter->timestamp; - list_del(&iter->list); - list_add(&iter->list, &os->sample_cache); - - if (show_progress) - ui_progress__update(&prog, 1); - } - - if (list_empty(head)) { - os->last_sample = NULL; - } else if (last_ts <= limit) { - os->last_sample = - list_entry(head->prev, struct sample_queue, list); - } - - os->nr_samples = 0; - - return 0; -} - /* * When perf record finishes a pass on every buffers, it records this pseudo * event. @@ -571,99 +518,38 @@ static int process_finished_round(struct perf_tool *tool, union perf_event *event __maybe_unused, struct perf_session *session) { - int ret = flush_sample_queue(session, tool); - if (!ret) - session->ordered_samples.next_flush = session->ordered_samples.max_timestamp; - - return ret; + return ordered_events__flush(session, tool, OE_FLUSH__ROUND); } -/* The queue is ordered by time */ -static void __queue_event(struct sample_queue *new, struct perf_session *s) -{ - struct ordered_samples *os = &s->ordered_samples; - struct sample_queue *sample = os->last_sample; - u64 timestamp = new->timestamp; - struct list_head *p; - - ++os->nr_samples; - os->last_sample = new; - - if (!sample) { - list_add(&new->list, &os->samples); - os->max_timestamp = timestamp; - return; - } - - /* - * last_sample might point to some random place in the list as it's - * the last queued event. We expect that the new event is close to - * this. - */ - if (sample->timestamp <= timestamp) { - while (sample->timestamp <= timestamp) { - p = sample->list.next; - if (p == &os->samples) { - list_add_tail(&new->list, &os->samples); - os->max_timestamp = timestamp; - return; - } - sample = list_entry(p, struct sample_queue, list); - } - list_add_tail(&new->list, &sample->list); - } else { - while (sample->timestamp > timestamp) { - p = sample->list.prev; - if (p == &os->samples) { - list_add(&new->list, &os->samples); - return; - } - sample = list_entry(p, struct sample_queue, list); - } - list_add(&new->list, &sample->list); - } -} - -#define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct sample_queue)) - int perf_session_queue_event(struct perf_session *s, union perf_event *event, - struct perf_sample *sample, u64 file_offset) + struct perf_tool *tool, struct perf_sample *sample, + u64 file_offset) { - struct ordered_samples *os = &s->ordered_samples; - struct list_head *sc = &os->sample_cache; + struct ordered_events *oe = &s->ordered_events; u64 timestamp = sample->time; - struct sample_queue *new; + struct ordered_event *new; if (!timestamp || timestamp == ~0ULL) return -ETIME; - if (timestamp < s->ordered_samples.last_flush) { - printf("Warning: Timestamp below last timeslice flush\n"); - return -EINVAL; - } + if (timestamp < oe->last_flush) { + 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); - if (!list_empty(sc)) { - new = list_entry(sc->next, struct sample_queue, list); - list_del(&new->list); - } else if (os->sample_buffer) { - new = os->sample_buffer + os->sample_buffer_idx; - if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER) - os->sample_buffer = NULL; - } else { - os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new)); - if (!os->sample_buffer) - return -ENOMEM; - list_add(&os->sample_buffer->list, &os->to_free); - os->sample_buffer_idx = 2; - new = os->sample_buffer + 1; + s->stats.nr_unordered_events++; } - new->timestamp = timestamp; - new->file_offset = file_offset; - new->event = event; + new = ordered_events__new(oe, timestamp, event); + if (!new) { + ordered_events__flush(s, tool, OE_FLUSH__HALF); + new = ordered_events__new(oe, timestamp, event); + } - __queue_event(new, s); + if (!new) + return -ENOMEM; + new->file_offset = file_offset; return 0; } @@ -702,15 +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) @@ -809,6 +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); @@ -923,11 +843,10 @@ perf_session__deliver_sample(struct perf_session *session, &sample->read.one, machine); } -static int perf_session_deliver_event(struct perf_session *session, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool, - u64 file_offset) +int perf_session__deliver_event(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, u64 file_offset) { struct perf_evsel *evsel; struct machine *machine; @@ -935,22 +854,6 @@ static int perf_session_deliver_event(struct perf_session *session, dump_event(session, event, file_offset, sample); evsel = perf_evlist__id2evsel(session->evlist, sample->id); - if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) { - /* - * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here - * because the tools right now may apply filters, discarding - * some of the samples. For consistency, in the future we - * should have something like nr_filtered_samples and remove - * the sample->period from total_sample_period, etc, KISS for - * now tho. - * - * Also testing against NULL allows us to handle files without - * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the - * future probably it'll be a good idea to restrict event - * processing via perf_session to files with both set. - */ - hists__inc_nr_events(&evsel->hists, event->header.type); - } machine = perf_session__find_machine_for_cpumode(session, event, sample); @@ -994,8 +897,10 @@ static int perf_session_deliver_event(struct perf_session *session, } } -static int perf_session__process_user_event(struct perf_session *session, union perf_event *event, - struct perf_tool *tool, u64 file_offset) +static s64 perf_session__process_user_event(struct perf_session *session, + union perf_event *event, + struct perf_tool *tool, + u64 file_offset) { int fd = perf_data_file__fd(session->file); int err; @@ -1006,8 +911,10 @@ static int perf_session__process_user_event(struct perf_session *session, union switch (event->header.type) { case PERF_RECORD_HEADER_ATTR: err = tool->attr(tool, event, &session->evlist); - if (err == 0) + if (err == 0) { perf_session__set_id_hdr_size(session); + perf_session__set_comm_exec(session); + } return err; case PERF_RECORD_HEADER_EVENT_TYPE: /* @@ -1023,11 +930,26 @@ static int perf_session__process_user_event(struct perf_session *session, union 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; @@ -1037,7 +959,62 @@ static void event_swap(union perf_event *event, bool sample_id_all) swap(event, sample_id_all); } -static int perf_session__process_event(struct perf_session *session, +int perf_session__peek_event(struct perf_session *session, off_t file_offset, + void *buf, size_t buf_sz, + union perf_event **event_ptr, + struct perf_sample *sample) +{ + union perf_event *event; + size_t hdr_sz, rest; + int fd; + + if (session->one_mmap && !session->header.needs_swap) { + event = file_offset - session->one_mmap_offset + + session->one_mmap_addr; + goto out_parse_sample; + } + + if (perf_data_file__is_pipe(session->file)) + return -1; + + fd = perf_data_file__fd(session->file); + hdr_sz = sizeof(struct perf_event_header); + + if (buf_sz < hdr_sz) + return -1; + + if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 || + readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz) + return -1; + + event = (union perf_event *)buf; + + if (session->header.needs_swap) + perf_event_header__bswap(&event->header); + + if (event->header.size < hdr_sz) + return -1; + + rest = event->header.size - hdr_sz; + + if (readn(fd, &buf, rest) != (ssize_t)rest) + return -1; + + if (session->header.needs_swap) + event_swap(event, perf_evlist__sample_id_all(session->evlist)); + +out_parse_sample: + + if (sample && event->header.type < PERF_RECORD_USER_TYPE_START && + perf_evlist__parse_sample(session->evlist, event, sample)) + return -1; + + *event_ptr = event; + + return 0; +} + +static s64 perf_session__process_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool, u64 file_offset) @@ -1063,15 +1040,15 @@ static int perf_session__process_event(struct perf_session *session, if (ret) return ret; - if (tool->ordered_samples) { - ret = perf_session_queue_event(session, event, &sample, + if (tool->ordered_events) { + ret = perf_session_queue_event(session, event, tool, &sample, file_offset); if (ret != -ETIME) return ret; } - return perf_session_deliver_event(session, event, &sample, tool, - file_offset); + return perf_session__deliver_event(session, event, &sample, tool, + file_offset); } void perf_event_header__bswap(struct perf_event_header *hdr) @@ -1083,13 +1060,14 @@ void perf_event_header__bswap(struct perf_event_header *hdr) struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) { - return machine__findnew_thread(&session->machines.host, 0, pid); + return machine__findnew_thread(&session->machines.host, -1, pid); } static struct thread *perf_session__register_idle_thread(struct perf_session *session) { - struct thread *thread = perf_session__findnew(session, 0); + struct thread *thread; + thread = machine__findnew_thread(&session->machines.host, 0, 0); if (thread == NULL || thread__set_comm(thread, "swapper", 0)) { pr_err("problem inserting idle task.\n"); thread = NULL; @@ -1136,6 +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; @@ -1147,7 +1128,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session, union perf_event *event; uint32_t size, cur_size = 0; void *buf = NULL; - int skip = 0; + s64 skip = 0; u64 head; ssize_t err; void *p; @@ -1222,12 +1203,11 @@ more: goto more; done: /* do the final flush for ordered samples */ - session->ordered_samples.next_flush = ULLONG_MAX; - err = flush_sample_queue(session, tool); + err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); out_err: free(buf); perf_session__warn_about_errors(session, tool); - perf_session_free_sample_buffers(session); + ordered_events__free(&session->ordered_events); return err; } @@ -1276,13 +1256,13 @@ int __perf_session__process_events(struct perf_session *session, u64 file_size, struct perf_tool *tool) { int fd = perf_data_file__fd(session->file); - u64 head, page_offset, file_offset, file_pos; + u64 head, page_offset, file_offset, file_pos, size; int err, mmap_prot, mmap_flags, map_idx = 0; size_t mmap_size; char *buf, *mmaps[NUM_MMAPS]; union perf_event *event; - uint32_t size; struct ui_progress prog; + s64 skip; perf_tool__fill_defaults(tool); @@ -1296,8 +1276,10 @@ int __perf_session__process_events(struct perf_session *session, ui_progress__init(&prog, file_size, "Processing events..."); mmap_size = MMAP_SIZE; - if (mmap_size > file_size) + if (mmap_size > file_size) { mmap_size = file_size; + session->one_mmap = true; + } memset(mmaps, 0, sizeof(mmaps)); @@ -1319,6 +1301,10 @@ remap: mmaps[map_idx] = buf; map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1); file_pos = file_offset + head; + if (session->one_mmap) { + session->one_mmap_addr = buf; + session->one_mmap_offset = file_offset; + } more: event = fetch_mmaped_event(session, head, mmap_size, buf); @@ -1337,7 +1323,8 @@ more: size = event->header.size; if (size < sizeof(struct perf_event_header) || - perf_session__process_event(session, event, tool, file_pos) < 0) { + (skip = perf_session__process_event(session, event, tool, file_pos)) + < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", file_offset + head, event->header.size, event->header.type); @@ -1345,6 +1332,9 @@ more: goto out_err; } + if (skip) + size += skip; + head += size; file_pos += size; @@ -1358,12 +1348,12 @@ more: out: /* do the final flush for ordered samples */ - session->ordered_samples.next_flush = ULLONG_MAX; - err = flush_sample_queue(session, tool); + err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); out_err: ui_progress__finish(); perf_session__warn_about_errors(session, tool); - perf_session_free_sample_buffers(session); + ordered_events__free(&session->ordered_events); + session->one_mmap = false; return err; } @@ -1444,16 +1434,9 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) { - struct perf_evsel *pos; size_t ret = fprintf(fp, "Aggregated stats:\n"); ret += events_stats__fprintf(&session->stats, fp); - - evlist__for_each(session->evlist, pos) { - ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); - ret += events_stats__fprintf(&pos->hists.stats, fp); - } - return ret; } @@ -1494,9 +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; @@ -1671,3 +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 3140f8a..dc26ebf 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -2,33 +2,19 @@ #define __PERF_SESSION_H #include "trace-event.h" -#include "hist.h" #include "event.h" #include "header.h" #include "machine.h" #include "symbol.h" #include "thread.h" #include "data.h" +#include "ordered-events.h" #include <linux/rbtree.h> #include <linux/perf_event.h> -struct sample_queue; struct ip_callchain; struct thread; -struct ordered_samples { - u64 last_flush; - u64 next_flush; - u64 max_timestamp; - struct list_head samples; - struct list_head sample_cache; - struct list_head to_free; - struct sample_queue *sample_buffer; - struct sample_queue *last_sample; - int sample_buffer_idx; - unsigned int nr_samples; -}; - struct perf_session { struct perf_header header; struct machines machines; @@ -36,7 +22,10 @@ struct perf_session { struct trace_event tevent; struct events_stats stats; bool repipe; - struct ordered_samples ordered_samples; + bool one_mmap; + void *one_mmap_addr; + u64 one_mmap_offset; + struct ordered_events ordered_events; struct perf_data_file *file; }; @@ -55,6 +44,11 @@ void perf_session__delete(struct perf_session *session); void perf_event_header__bswap(struct perf_event_header *hdr); +int perf_session__peek_event(struct perf_session *session, off_t file_offset, + void *buf, size_t buf_sz, + 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); @@ -62,10 +56,16 @@ int perf_session__process_events(struct perf_session *session, struct perf_tool *tool); int perf_session_queue_event(struct perf_session *s, union perf_event *event, - struct perf_sample *sample, u64 file_offset); + struct perf_tool *tool, struct perf_sample *sample, + u64 file_offset); void perf_tool__fill_defaults(struct perf_tool *tool); +int perf_session__deliver_event(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, u64 file_offset); + int perf_session__resolve_callchain(struct perf_session *session, struct perf_evsel *evsel, struct thread *thread, @@ -125,5 +125,20 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, extern volatile int session_done; -#define session_done() (*(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 1ec57dd..9139dda 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -70,12 +70,14 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { const char *comm = thread__comm_str(he->thread); - return repsep_snprintf(bf, size, "%*s:%5d", width - 6, - comm ?: "", he->thread->tid); + + width = max(7U, width) - 6; + return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid, + width, width, comm ?: ""); } struct sort_entry sort_thread = { - .se_header = "Command: Pid", + .se_header = " Pid:Command", .se_cmp = sort__thread_cmp, .se_snprintf = hist_entry__thread_snprintf, .se_width_idx = HISTC_THREAD, @@ -106,7 +108,7 @@ sort__comm_sort(struct hist_entry *left, struct hist_entry *right) static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm)); + return repsep_snprintf(bf, size, "%-*.*s", width, width, comm__str(he->comm)); } struct sort_entry sort_comm = { @@ -152,10 +154,10 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf, if (map && map->dso) { const char *dso_name = !verbose ? map->dso->short_name : map->dso->long_name; - return repsep_snprintf(bf, size, "%-*s", width, dso_name); + return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name); } - return repsep_snprintf(bf, size, "%-*s", width, "[unknown]"); + return repsep_snprintf(bf, size, "%-*.*s", width, width, "[unknown]"); } static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf, @@ -257,7 +259,10 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, width - ret, ""); } - return ret; + if (ret > width) + bf[width] = '\0'; + + return width; } static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, @@ -286,7 +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) { @@ -295,17 +301,17 @@ 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); } static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, - size_t size, - unsigned int width __maybe_unused) + size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%s", he->srcline); + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline); } struct sort_entry sort_srcline = { @@ -332,7 +338,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*s", width, + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->parent ? he->parent->name : "[other]"); } @@ -354,7 +360,7 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*d", width, he->cpu); + return repsep_snprintf(bf, size, "%*.*d", width, width, he->cpu); } struct sort_entry sort_cpu = { @@ -369,6 +375,9 @@ struct sort_entry sort_cpu = { static int64_t sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return _sort__dso_cmp(left->branch_info->from.map, right->branch_info->from.map); } @@ -376,13 +385,19 @@ sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__dso_snprintf(he->branch_info->from.map, - bf, size, width); + if (he->branch_info) + return _hist_entry__dso_snprintf(he->branch_info->from.map, + bf, size, width); + else + return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } static int64_t sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return _sort__dso_cmp(left->branch_info->to.map, right->branch_info->to.map); } @@ -390,8 +405,11 @@ sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__dso_snprintf(he->branch_info->to.map, - bf, size, width); + if (he->branch_info) + return _hist_entry__dso_snprintf(he->branch_info->to.map, + bf, size, width); + else + return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } static int64_t @@ -400,6 +418,12 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) struct addr_map_symbol *from_l = &left->branch_info->from; struct addr_map_symbol *from_r = &right->branch_info->from; + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + + from_l = &left->branch_info->from; + from_r = &right->branch_info->from; + if (!from_l->sym && !from_r->sym) return _sort__addr_cmp(from_l->addr, from_r->addr); @@ -409,8 +433,13 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) static int64_t sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) { - struct addr_map_symbol *to_l = &left->branch_info->to; - struct addr_map_symbol *to_r = &right->branch_info->to; + struct addr_map_symbol *to_l, *to_r; + + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + + to_l = &left->branch_info->to; + to_r = &right->branch_info->to; if (!to_l->sym && !to_r->sym) return _sort__addr_cmp(to_l->addr, to_r->addr); @@ -421,19 +450,27 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - struct addr_map_symbol *from = &he->branch_info->from; - return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, - he->level, bf, size, width); + if (he->branch_info) { + struct addr_map_symbol *from = &he->branch_info->from; + return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, + he->level, bf, size, width); + } + + return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - struct addr_map_symbol *to = &he->branch_info->to; - return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, - he->level, bf, size, width); + if (he->branch_info) { + struct addr_map_symbol *to = &he->branch_info->to; + return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, + he->level, bf, size, width); + } + + return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } struct sort_entry sort_dso_from = { @@ -467,11 +504,13 @@ struct sort_entry sort_sym_to = { static int64_t sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right) { - const unsigned char mp = left->branch_info->flags.mispred != - right->branch_info->flags.mispred; - const unsigned char p = left->branch_info->flags.predicted != - right->branch_info->flags.predicted; + unsigned char mp, p; + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + + mp = left->branch_info->flags.mispred != right->branch_info->flags.mispred; + p = left->branch_info->flags.predicted != right->branch_info->flags.predicted; return mp || p; } @@ -479,12 +518,14 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width){ static const char *out = "N/A"; - if (he->branch_info->flags.predicted) - out = "N"; - else if (he->branch_info->flags.mispred) - out = "Y"; + if (he->branch_info) { + if (he->branch_info->flags.predicted) + out = "N"; + else if (he->branch_info->flags.mispred) + out = "Y"; + } - return repsep_snprintf(bf, size, "%-*s", width, out); + return repsep_snprintf(bf, size, "%-*.*s", width, width, out); } /* --sort daddr_sym */ @@ -985,6 +1026,9 @@ struct sort_entry sort_mem_dcacheline = { static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return left->branch_info->flags.abort != right->branch_info->flags.abort; } @@ -992,10 +1036,15 @@ sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - static const char *out = "."; + static const char *out = "N/A"; + + if (he->branch_info) { + if (he->branch_info->flags.abort) + out = "A"; + else + out = "."; + } - if (he->branch_info->flags.abort) - out = "A"; return repsep_snprintf(bf, size, "%-*s", width, out); } @@ -1009,6 +1058,9 @@ struct sort_entry sort_abort = { static int64_t sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return left->branch_info->flags.in_tx != right->branch_info->flags.in_tx; } @@ -1016,10 +1068,14 @@ sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - static const char *out = "."; + static const char *out = "N/A"; - if (he->branch_info->flags.in_tx) - out = "T"; + if (he->branch_info) { + if (he->branch_info->flags.in_tx) + out = "T"; + else + out = "."; + } return repsep_snprintf(bf, size, "%-*s", width, out); } @@ -1194,7 +1250,7 @@ bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) return hse_a->se == hse_b->se; } -void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) +void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists) { struct hpp_sort_entry *hse; @@ -1202,20 +1258,21 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) return; hse = container_of(fmt, struct hpp_sort_entry, hpp); - hists__new_col_len(hists, hse->se->se_width_idx, - strlen(hse->se->se_header)); + hists__new_col_len(hists, hse->se->se_width_idx, strlen(fmt->name)); } static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct perf_evsel *evsel) { struct hpp_sort_entry *hse; - size_t len; + size_t len = fmt->user_len; hse = container_of(fmt, struct hpp_sort_entry, hpp); - len = hists__col_len(&evsel->hists, hse->se->se_width_idx); - return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header); + if (!len) + len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx); + + return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name); } static int __sort__hpp_width(struct perf_hpp_fmt *fmt, @@ -1223,20 +1280,26 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt, struct perf_evsel *evsel) { struct hpp_sort_entry *hse; + size_t len = fmt->user_len; hse = container_of(fmt, struct hpp_sort_entry, hpp); - return hists__col_len(&evsel->hists, hse->se->se_width_idx); + if (!len) + len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx); + + return len; } static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he) { struct hpp_sort_entry *hse; - size_t len; + size_t len = fmt->user_len; hse = container_of(fmt, struct hpp_sort_entry, hpp); - len = hists__col_len(he->hists, hse->se->se_width_idx); + + if (!len) + len = hists__col_len(he->hists, hse->se->se_width_idx); return hse->se->se_snprintf(he, hpp->buf, hpp->size, len); } @@ -1253,6 +1316,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) } hse->se = sd->entry; + hse->hpp.name = sd->entry->se_header; hse->hpp.header = __sort__hpp_header; hse->hpp.width = __sort__hpp_width; hse->hpp.entry = __sort__hpp_entry; @@ -1265,6 +1329,8 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) INIT_LIST_HEAD(&hse->hpp.list); INIT_LIST_HEAD(&hse->hpp.sort_list); hse->hpp.elide = false; + hse->hpp.len = 0; + hse->hpp.user_len = 0; return hse; } @@ -1432,14 +1498,49 @@ static const char *get_default_sort_order(void) return default_sort_orders[sort__mode]; } +static int setup_sort_order(void) +{ + char *new_sort_order; + + /* + * Append '+'-prefixed sort order to the default sort + * order string. + */ + if (!sort_order || is_strict_order(sort_order)) + return 0; + + if (sort_order[1] == '\0') { + error("Invalid --sort key: `+'"); + return -EINVAL; + } + + /* + * We allocate new sort_order string, but we never free it, + * because it's checked over the rest of the code. + */ + if (asprintf(&new_sort_order, "%s,%s", + get_default_sort_order(), sort_order + 1) < 0) { + error("Not enough memory to set up --sort"); + return -ENOMEM; + } + + sort_order = new_sort_order; + return 0; +} + static int __setup_sorting(void) { char *tmp, *tok, *str; - const char *sort_keys = sort_order; + const char *sort_keys; int ret = 0; + ret = setup_sort_order(); + if (ret) + return ret; + + sort_keys = sort_order; if (sort_keys == NULL) { - if (field_order) { + if (is_strict_order(field_order)) { /* * If user specified field order but no sort order, * we'll honor it and not add default sort orders. @@ -1625,23 +1726,36 @@ static void reset_dimensions(void) memory_sort_dimensions[i].taken = 0; } +bool is_strict_order(const char *order) +{ + return order && (*order != '+'); +} + static int __setup_output_field(void) { - char *tmp, *tok, *str; - int ret = 0; + char *tmp, *tok, *str, *strp; + int ret = -EINVAL; if (field_order == NULL) return 0; reset_dimensions(); - str = strdup(field_order); + strp = str = strdup(field_order); if (str == NULL) { error("Not enough memory to setup output fields"); return -ENOMEM; } - for (tok = strtok_r(str, ", ", &tmp); + if (!is_strict_order(field_order)) + strp++; + + if (!strlen(strp)) { + error("Invalid --fields key: `+'"); + goto out; + } + + for (tok = strtok_r(strp, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { ret = output_field_add(tok); if (ret == -EINVAL) { @@ -1653,6 +1767,7 @@ static int __setup_output_field(void) } } +out: free(str); return ret; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 041f0c9..c03e4ff 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -218,4 +218,5 @@ void perf_hpp__set_elide(int idx, bool elide); int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); +bool is_strict_order(const char *order); #endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index f3e4bc5..c93fb0c 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/string.c b/tools/perf/util/string.c index 2553e5b..6afd610 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -9,78 +9,48 @@ */ s64 perf_atoll(const char *str) { - unsigned int i; - s64 length = -1, unit = 1; + s64 length; + char *p; + char c; if (!isdigit(str[0])) goto out_err; - for (i = 1; i < strlen(str); i++) { - switch (str[i]) { - case 'B': - case 'b': - break; - case 'K': - if (str[i + 1] != 'B') - goto out_err; - else - goto kilo; - case 'k': - if (str[i + 1] != 'b') - goto out_err; -kilo: - unit = K; - break; - case 'M': - if (str[i + 1] != 'B') - goto out_err; - else - goto mega; - case 'm': - if (str[i + 1] != 'b') - goto out_err; -mega: - unit = K * K; - break; - case 'G': - if (str[i + 1] != 'B') + length = strtoll(str, &p, 10); + switch (c = *p++) { + case 'b': case 'B': + if (*p) goto out_err; - else - goto giga; - case 'g': - if (str[i + 1] != 'b') - goto out_err; -giga: - unit = K * K * K; + case '\0': + return length; + default: + goto out_err; + /* two-letter suffices */ + case 'k': case 'K': + length <<= 10; break; - case 'T': - if (str[i + 1] != 'B') - goto out_err; - else - goto tera; - case 't': - if (str[i + 1] != 'b') - goto out_err; -tera: - unit = K * K * K * K; + case 'm': case 'M': + length <<= 20; break; - case '\0': /* only specified figures */ - unit = 1; + case 'g': case 'G': + length <<= 30; break; - default: - if (!isdigit(str[i])) - goto out_err; + case 't': case 'T': + length <<= 40; break; - } } - - length = atoll(str) * unit; - goto out; + /* we want the cases to match */ + if (islower(c)) { + if (strcmp(p, "b") != 0) + goto out_err; + } else { + if (strcmp(p, "B") != 0) + goto out_err; + } + return length; out_err: - length = -1; -out: - return length; + return -1; } /* @@ -387,27 +357,3 @@ void *memdup(const void *src, size_t len) return p; } - -/** - * str_append - reallocate string and append another - * @s: pointer to string pointer - * @len: pointer to len (initialized) - * @a: string to append. - */ -int str_append(char **s, int *len, const char *a) -{ - int olen = *s ? strlen(*s) : 0; - int nlen = olen + strlen(a) + 1; - if (*len < nlen) { - *len = *len * 2; - if (*len < nlen) - *len = nlen; - *s = realloc(*s, *len); - if (!*s) - return -ENOMEM; - if (olen == 0) - **s = 0; - } - strcat(*s, a); - return 0; -} diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 6a0a13d..283d3e7 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -30,6 +30,7 @@ static u64 turbo_frequency, max_freq; #define SLOT_MULT 30.0 #define SLOT_HEIGHT 25.0 +#define SLOT_HALF (SLOT_HEIGHT / 2) int svg_page_width = 1000; u64 svg_highlight; @@ -114,8 +115,14 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end) fprintf(svgfile, " rect { stroke-width: 1; }\n"); fprintf(svgfile, " rect.process { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.process3 { fill:rgb(180,180,180); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.sample { fill:rgb( 0, 0,255); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.sample_hi{ fill:rgb(255,128, 0); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.error { fill:rgb(255, 0, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.net { fill:rgb( 0,128, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.disk { fill:rgb( 0, 0,255); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.sync { fill:rgb(128,128, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.poll { fill:rgb( 0,128,128); fill-opacity:0.2; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.blocked { fill:rgb(255, 0, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.waiting { fill:rgb(224,214, 0); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.WAITING { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); @@ -132,12 +139,81 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end) fprintf(svgfile, " ]]>\n </style>\n</defs>\n"); } +static double normalize_height(double height) +{ + if (height < 0.25) + return 0.25; + else if (height < 0.50) + return 0.50; + else if (height < 0.75) + return 0.75; + else + return 0.100; +} + +void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges) +{ + double w = time2pixels(end) - time2pixels(start); + height = normalize_height(height); + + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges); + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", + time2pixels(start), + w, + Yslot * SLOT_MULT, + SLOT_HALF * height, + type); + fprintf(svgfile, "</g>\n"); +} + +void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges) +{ + double w = time2pixels(end) - time2pixels(start); + height = normalize_height(height); + + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges); + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", + time2pixels(start), + w, + Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HALF * height, + SLOT_HALF * height, + type); + fprintf(svgfile, "</g>\n"); +} + +void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges) +{ + double w = time2pixels(end) - time2pixels(start); + height = normalize_height(height); + + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges); + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", + time2pixels(start), + w, + Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HEIGHT * height, + SLOT_HEIGHT * height, + type); + fprintf(svgfile, "</g>\n"); +} + void svg_box(int Yslot, u64 start, u64 end, const char *type) { if (!svgfile) return; - fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type); } @@ -174,7 +250,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) cpu, time_to_string(end - start)); if (backtrace) fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace); - fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type); @@ -186,7 +262,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) text_size = round_text_size(text_size); if (text_size > MIN_TEXT_SIZE) - fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">%i</text>\n", time2pixels(start), Yslot * SLOT_MULT + SLOT_HEIGHT - 1, text_size, cpu + 1); fprintf(svgfile, "</g>\n"); @@ -202,10 +278,10 @@ static char *time_to_string(u64 duration) return text; if (duration < 1000 * 1000) { /* less than 1 msec */ - sprintf(text, "%4.1f us", duration / 1000.0); + sprintf(text, "%.1f us", duration / 1000.0); return text; } - sprintf(text, "%4.1f ms", duration / 1000.0 / 1000); + sprintf(text, "%.1f ms", duration / 1000.0 / 1000); return text; } @@ -233,14 +309,14 @@ void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) font_size = round_text_size(font_size); - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT); + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT); fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start)); if (backtrace) fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace); - fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style); if (font_size > MIN_TEXT_SIZE) - fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%1.8fpt\"> %s</text>\n", + fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\"> %s</text>\n", font_size, text); fprintf(svgfile, "</g>\n"); } @@ -289,16 +365,16 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq) fprintf(svgfile, "<g>\n"); - fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n", + fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"cpu\"/>\n", time2pixels(first_time), time2pixels(last_time)-time2pixels(first_time), cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT); sprintf(cpu_string, "CPU %i", (int)cpu); - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n", 10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string); - fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n", + fprintf(svgfile, "<text transform=\"translate(%.8f,%.8f)\" font-size=\"1.25pt\">%s</text>\n", 10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model()); fprintf(svgfile, "</g>\n"); @@ -319,11 +395,11 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c else type = "sample"; - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu)); + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), cpu2y(cpu)); fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start)); if (backtrace) fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace); - fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n", time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type); width = time2pixels(end)-time2pixels(start); if (width > 6) @@ -332,7 +408,7 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c width = round_text_size(width); if (width > MIN_TEXT_SIZE) - fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%3.8fpt\">%s</text>\n", + fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\">%s</text>\n", width, name); fprintf(svgfile, "</g>\n"); @@ -353,7 +429,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type) type = 6; sprintf(style, "c%i", type); - fprintf(svgfile, "<rect class=\"%s\" x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\"/>\n", + fprintf(svgfile, "<rect class=\"%s\" x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\"/>\n", style, time2pixels(start), time2pixels(end)-time2pixels(start), cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT); @@ -365,7 +441,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type) width = round_text_size(width); if (width > MIN_TEXT_SIZE) - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">C%i</text>\n", time2pixels(start), cpu2y(cpu)+width, width, type); fprintf(svgfile, "</g>\n"); @@ -407,9 +483,9 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq) if (max_freq) height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT); height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height; - fprintf(svgfile, "<line x1=\"%4.8f\" x2=\"%4.8f\" y1=\"%4.1f\" y2=\"%4.1f\" class=\"pstate\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" x2=\"%.8f\" y1=\"%.1f\" y2=\"%.1f\" class=\"pstate\"/>\n", time2pixels(start), time2pixels(end), height, height); - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"0.25pt\">%s</text>\n", time2pixels(start), height+0.9, HzToHuman(freq)); fprintf(svgfile, "</g>\n"); @@ -435,32 +511,32 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc if (row1 < row2) { if (row1) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32); if (desc2) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_HEIGHT/48, desc2); } if (row2) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32, time2pixels(start), row2 * SLOT_MULT); if (desc1) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s ></text></g>\n", time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32, desc1); } } else { if (row2) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32); if (desc1) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/48, desc1); } if (row1) { - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row1 * SLOT_MULT - SLOT_MULT/32, time2pixels(start), row1 * SLOT_MULT); if (desc2) - fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", + fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s <</text></g>\n", time2pixels(start), row1 * SLOT_MULT - SLOT_HEIGHT/32, desc2); } } @@ -468,7 +544,7 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc if (row2 > row1) height += SLOT_HEIGHT; if (row1) - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", time2pixels(start), height); fprintf(svgfile, "</g>\n"); @@ -488,16 +564,16 @@ void svg_wakeline(u64 start, int row1, int row2, const char *backtrace) fprintf(svgfile, "<desc>%s</desc>\n", backtrace); if (row1 < row2) - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row2 * SLOT_MULT); else - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row1 * SLOT_MULT); height = row1 * SLOT_MULT; if (row2 > row1) height += SLOT_HEIGHT; - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", time2pixels(start), height); fprintf(svgfile, "</g>\n"); @@ -515,9 +591,9 @@ void svg_interrupt(u64 start, int row, const char *backtrace) if (backtrace) fprintf(svgfile, "<desc>%s</desc>\n", backtrace); - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", time2pixels(start), row * SLOT_MULT); - fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", + fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT); fprintf(svgfile, "</g>\n"); @@ -528,7 +604,7 @@ void svg_text(int Yslot, u64 start, const char *text) if (!svgfile) return; - fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n", + fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n", time2pixels(start), Yslot * SLOT_MULT+SLOT_HEIGHT/2, text); } @@ -537,12 +613,26 @@ static void svg_legenda_box(int X, const char *text, const char *style) double boxsize; boxsize = SLOT_HEIGHT / 2; - fprintf(svgfile, "<rect x=\"%i\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", + fprintf(svgfile, "<rect x=\"%i\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n", X, boxsize, boxsize, style); - fprintf(svgfile, "<text transform=\"translate(%4.8f, %4.8f)\" font-size=\"%4.8fpt\">%s</text>\n", + fprintf(svgfile, "<text transform=\"translate(%.8f, %.8f)\" font-size=\"%.8fpt\">%s</text>\n", X + boxsize + 5, boxsize, 0.8 * boxsize, text); } +void svg_io_legenda(void) +{ + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + svg_legenda_box(0, "Disk", "disk"); + svg_legenda_box(100, "Network", "net"); + svg_legenda_box(200, "Sync", "sync"); + svg_legenda_box(300, "Poll", "poll"); + svg_legenda_box(400, "Error", "error"); + fprintf(svgfile, "</g>\n"); +} + void svg_legenda(void) { if (!svgfile) @@ -559,7 +649,7 @@ void svg_legenda(void) fprintf(svgfile, "</g>\n"); } -void svg_time_grid(void) +void svg_time_grid(double min_thickness) { u64 i; @@ -579,8 +669,10 @@ void svg_time_grid(void) color = 128; } - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n", - time2pixels(i), SLOT_MULT/2, time2pixels(i), total_height, color, color, color, thickness); + if (thickness >= min_thickness) + fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%.3f\"/>\n", + time2pixels(i), SLOT_MULT/2, time2pixels(i), + total_height, color, color, color, thickness); i += 10000000; } diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h index e3aff53..9292a52 100644 --- a/tools/perf/util/svghelper.h +++ b/tools/perf/util/svghelper.h @@ -4,6 +4,9 @@ #include <linux/types.h> extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end); +extern void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); +extern void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); +extern void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges); extern void svg_box(int Yslot, u64 start, u64 end, const char *type); extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace); extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace); @@ -16,7 +19,8 @@ extern void svg_cstate(int cpu, u64 start, u64 end, int type); extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq); -extern void svg_time_grid(void); +extern void svg_time_grid(double min_thickness); +extern void svg_io_legenda(void); extern void svg_legenda(void); extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace); extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 6864661..06fcd1b 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -6,10 +6,32 @@ #include <inttypes.h> #include "symbol.h" +#include "machine.h" #include "vdso.h" #include <symbol/kallsyms.h> #include "debug.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 + #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT static int elf_getphdrnum(Elf *elf, size_t *dst) { @@ -49,7 +71,8 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) static inline int elf_sym__is_function(const GElf_Sym *sym) { - return elf_sym__type(sym) == STT_FUNC && + return (elf_sym__type(sym) == STT_FUNC || + elf_sym__type(sym) == STT_GNU_IFUNC) && sym->st_name != 0 && sym->st_shndx != SHN_UNDEF; } @@ -544,6 +567,35 @@ 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->symtab_type) + return -1; + + 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; @@ -569,7 +621,11 @@ 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; @@ -598,6 +654,8 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, goto out_elf_end; } + ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64); + ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab", NULL); if (ss->symshdr.sh_type != SHT_SYMTAB) @@ -619,7 +677,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, GElf_Shdr shdr; ss->adjust_symbols = (ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL || - is_vdso_map(dso->short_name) || + dso__is_vdso(dso) || elf_section_by_name(elf, &ehdr, &shdr, ".gnu.prelink_undo", NULL) != NULL); @@ -677,6 +735,11 @@ static u64 ref_reloc(struct kmap *kmap) return 0; } +static bool want_demangle(bool is_kernel_sym) +{ + return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; +} + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, symbol_filter_t filter, int kmodule) @@ -698,6 +761,7 @@ int dso__load_sym(struct dso *dso, struct map *map, bool remap_kernel = false, adjust_kernel_syms = false; dso->symtab_type = syms_ss->type; + dso->is_64_bit = syms_ss->is_64_bit; dso->rel = syms_ss->ehdr.e_type == ET_REL; /* @@ -708,6 +772,14 @@ int dso__load_sym(struct dso *dso, struct map *map, symbols__delete(&dso->symbols[map->type]); if (!syms_ss->symtab) { + /* + * If the vmlinux is stripped, fail so we will fall back + * to using kallsyms. The vmlinux runtime symbols aren't + * of much use. + */ + if (dso->kernel) + goto out_elf_end; + syms_ss->symtab = syms_ss->dynsym; syms_ss->symshdr = syms_ss->dynshdr; } @@ -732,7 +804,7 @@ int dso__load_sym(struct dso *dso, struct map *map, if (symstrs == NULL) goto out_elf_end; - sec_strndx = elf_getscn(elf, ehdr.e_shstrndx); + sec_strndx = elf_getscn(runtime_ss->elf, runtime_ss->ehdr.e_shstrndx); if (sec_strndx == NULL) goto out_elf_end; @@ -912,7 +984,11 @@ int dso__load_sym(struct dso *dso, struct map *map, } curr_dso->symtab_type = dso->symtab_type; map_groups__insert(kmap->kmaps, curr_map); - dsos__add(&dso->node, curr_dso); + /* + * The new DSO should go to the kernel DSOS + */ + dsos__add(&map->groups->machine->kernel_dsos, + curr_dso); dso__set_loaded(curr_dso, map->type); } else curr_dso = curr_map->dso; @@ -934,9 +1010,12 @@ new_symbol: * DWARF DW_compile_unit has this, but we don't always have access * to it... */ - if (symbol_conf.demangle) { - demangled = bfd_demangle(NULL, elf_name, - DMGL_PARAMS | DMGL_ANSI); + if (want_demangle(dso->kernel || kmodule)) { + int demangle_flags = DMGL_NO_OPTS; + if (verbose) + demangle_flags = DMGL_PARAMS | DMGL_ANSI; + + demangled = bfd_demangle(NULL, elf_name, demangle_flags); if (demangled != NULL) elf_name = demangled; } @@ -1024,6 +1103,39 @@ int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, return err; } +enum dso_type dso__type_fd(int fd) +{ + enum dso_type dso_type = DSO__TYPE_UNKNOWN; + GElf_Ehdr ehdr; + Elf_Kind ek; + Elf *elf; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + goto out; + + ek = elf_kind(elf); + if (ek != ELF_K_ELF) + goto out_end; + + if (gelf_getclass(elf) == ELFCLASS64) { + dso_type = DSO__TYPE_64BIT; + goto out_end; + } + + if (gelf_getehdr(elf, &ehdr) == NULL) + goto out_end; + + if (ehdr.e_machine == EM_X86_64) + dso_type = DSO__TYPE_X32BIT; + else + dso_type = DSO__TYPE_32BIT; +out_end: + elf_end(elf); +out: + return dso_type; +} + static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len) { ssize_t r; diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index bd15f49..d7efb03 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; @@ -288,6 +292,44 @@ int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused, return 0; } +static int fd__is_64_bit(int fd) +{ + u8 e_ident[EI_NIDENT]; + + if (lseek(fd, 0, SEEK_SET)) + return -1; + + if (readn(fd, e_ident, sizeof(e_ident)) != sizeof(e_ident)) + return -1; + + if (memcmp(e_ident, ELFMAG, SELFMAG) || + e_ident[EI_VERSION] != EV_CURRENT) + return -1; + + return e_ident[EI_CLASS] == ELFCLASS64; +} + +enum dso_type dso__type_fd(int fd) +{ + Elf64_Ehdr ehdr; + int ret; + + ret = fd__is_64_bit(fd); + if (ret < 0) + return DSO__TYPE_UNKNOWN; + + if (ret) + return DSO__TYPE_64BIT; + + if (readn(fd, &ehdr, sizeof(ehdr)) != sizeof(ehdr)) + return DSO__TYPE_UNKNOWN; + + if (ehdr.e_machine == EM_X86_64) + return DSO__TYPE_X32BIT; + + return DSO__TYPE_32BIT; +} + int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, struct symsrc *ss, struct symsrc *runtime_ss __maybe_unused, @@ -295,10 +337,14 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, int kmodule __maybe_unused) { unsigned char *build_id[BUILD_ID_SIZE]; + int ret; + + ret = fd__is_64_bit(ss->fd); + if (ret >= 0) + dso->is_64_bit = ret; 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 7b9096f..c24c5b8 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -15,6 +15,7 @@ #include "machine.h" #include "symbol.h" #include "strlist.h" +#include "header.h" #include <elf.h> #include <limits.h> @@ -33,7 +34,9 @@ struct symbol_conf symbol_conf = { .try_vmlinux_path = true, .annotate_src = true, .demangle = true, + .demangle_kernel = false, .cumulate_callchain = true, + .show_hist_headers = true, .symfs = "", }; @@ -48,7 +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, }; @@ -183,7 +188,7 @@ void symbols__fixup_end(struct rb_root *symbols) curr = rb_entry(nd, struct symbol, rb_node); if (prev->end == prev->start && prev->end != curr->start) - prev->end = curr->start - 1; + prev->end = curr->start; } /* Last entry */ @@ -204,7 +209,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) { prev = curr; curr = rb_entry(nd, struct map, rb_node); - prev->end = curr->start - 1; + prev->end = curr->start; } /* @@ -226,7 +231,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) sym = ((void *)sym) + symbol_conf.priv_size; sym->start = start; - sym->end = len ? start + len - 1 : start; + sym->end = len ? start + len : start; sym->binding = binding; sym->namelen = namelen - 1; @@ -322,7 +327,7 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip) if (ip < s->start) n = n->rb_left; - else if (ip > s->end) + else if (ip >= s->end) n = n->rb_right; else return s; @@ -341,6 +346,16 @@ static struct symbol *symbols__first(struct rb_root *symbols) return NULL; } +static struct symbol *symbols__next(struct symbol *sym) +{ + struct rb_node *n = rb_next(&sym->rb_node); + + if (n) + return rb_entry(n, struct symbol, rb_node); + + return NULL; +} + struct symbol_name_rb_node { struct rb_node rb_node; struct symbol sym; @@ -411,11 +426,16 @@ struct symbol *dso__find_symbol(struct dso *dso, return symbols__find(&dso->symbols[type], addr); } -static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) +struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) { return symbols__first(&dso->symbols[type]); } +struct symbol *dso__next_symbol(struct symbol *sym) +{ + return symbols__next(sym); +} + struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name) { @@ -507,10 +527,15 @@ struct process_kallsyms_args { struct dso *dso; }; +/* + * These are symbols in the kernel image, so make sure that + * sym is from a kernel DSO. + */ bool symbol__is_idle(struct symbol *sym) { const char * const idle_symbols[] = { "cpu_idle", + "cpu_startup_entry", "intel_idle", "default_idle", "native_safe_halt", @@ -1064,6 +1089,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, &is_64_bit); if (err) goto out_err; + dso->is_64_bit = is_64_bit; if (list_empty(&md.maps)) { err = -EINVAL; @@ -1276,7 +1302,9 @@ 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(). @@ -1344,7 +1372,9 @@ 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. @@ -1451,8 +1481,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, if (vmlinux[0] == '/') snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux); else - snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s", - symbol_conf.symfs, vmlinux); + symbol__join_symfs(symfs_vmlinux, vmlinux); if (dso->kernel == DSO_TYPE_GUEST_KERNEL) symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX; @@ -1482,12 +1511,10 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, symbol_filter_t filter) { int i, err = 0; - char *filename; + char *filename = NULL; - pr_debug("Looking at the vmlinux_path (%d entries long)\n", - vmlinux_path__nr_entries + 1); - - 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) @@ -1495,6 +1522,9 @@ 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) @@ -1662,6 +1692,7 @@ do_kallsyms: free(kallsyms_allocated_filename); if (err > 0 && !dso__is_kcore(dso)) { + dso->binary_type = DSO_BINARY_TYPE__KALLSYMS; dso__set_long_name(dso, "[kernel.kallsyms]", false); map__fixup_start(map); map__fixup_end(map); @@ -1709,6 +1740,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, if (err > 0) pr_debug("Using %s for symbols\n", kallsyms_filename); if (err > 0 && !dso__is_kcore(dso)) { + dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS; machine__mmap_name(machine, path, sizeof(path)); dso__set_long_name(dso, strdup(path), true); map__fixup_start(map); @@ -1726,12 +1758,13 @@ static void vmlinux_path__exit(void) zfree(&vmlinux_path); } -static int vmlinux_path__init(void) +static int vmlinux_path__init(struct perf_session_env *env) { struct utsname uts; char bf[PATH_MAX]; + char *kernel_version; - vmlinux_path = malloc(sizeof(char *) * 5); + vmlinux_path = malloc(sizeof(char *) * 6); if (vmlinux_path == NULL) return -1; @@ -1744,25 +1777,37 @@ static int vmlinux_path__init(void) goto out_fail; ++vmlinux_path__nr_entries; - /* only try running kernel version if no symfs was given */ + /* only try kernel version if no symfs was given */ if (symbol_conf.symfs[0] != 0) return 0; - if (uname(&uts) < 0) - return -1; + if (env) { + kernel_version = env->os_release; + } else { + if (uname(&uts) < 0) + goto out_fail; + + kernel_version = uts.release; + } - snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release); + snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version); vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); if (vmlinux_path[vmlinux_path__nr_entries] == NULL) goto out_fail; ++vmlinux_path__nr_entries; - snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", uts.release); + snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s", + kernel_version); + vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); + if (vmlinux_path[vmlinux_path__nr_entries] == NULL) + goto out_fail; + ++vmlinux_path__nr_entries; + snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version); vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); if (vmlinux_path[vmlinux_path__nr_entries] == NULL) goto out_fail; ++vmlinux_path__nr_entries; snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux", - uts.release); + kernel_version); vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); if (vmlinux_path[vmlinux_path__nr_entries] == NULL) goto out_fail; @@ -1808,7 +1853,7 @@ static bool symbol__read_kptr_restrict(void) return value; } -int symbol__init(void) +int symbol__init(struct perf_session_env *env) { const char *symfs; @@ -1823,7 +1868,7 @@ int symbol__init(void) symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) - sizeof(struct symbol)); - if (symbol_conf.try_vmlinux_path && vmlinux_path__init() < 0) + if (symbol_conf.try_vmlinux_path && vmlinux_path__init(env) < 0) return -1; if (symbol_conf.field_sep && *symbol_conf.field_sep == '.') { diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 615c752..9d602e9 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -13,6 +13,7 @@ #include <libgen.h> #include "build-id.h" #include "event.h" +#include "util.h" #ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> @@ -22,27 +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: @@ -59,6 +39,7 @@ extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, #endif #ifndef DMGL_PARAMS +#define DMGL_NO_OPTS 0 /* For readability... */ #define DMGL_PARAMS (1 << 0) /* Include function args */ #define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ #endif @@ -93,7 +74,7 @@ void symbols__delete(struct rb_root *symbols); static inline size_t symbol__size(const struct symbol *sym) { - return sym->end - sym->start + 1; + return sym->end - sym->start; } struct strlist; @@ -103,6 +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, @@ -118,7 +100,10 @@ struct symbol_conf { annotate_src, event_group, demangle, - filter_relative; + demangle_kernel, + filter_relative, + show_hist_headers, + branch_callstack; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -142,6 +127,14 @@ struct symbol_conf { }; extern struct symbol_conf symbol_conf; + +static inline int __symbol__join_symfs(char *bf, size_t size, const char *path) +{ + return path__join(bf, size, symbol_conf.symfs, path); +} + +#define symbol__join_symfs(bf, path) __symbol__join_symfs(bf, sizeof(bf), path) + extern int vmlinux_path__nr_entries; extern char **vmlinux_path; @@ -215,6 +208,7 @@ struct symsrc { GElf_Shdr dynshdr; bool adjust_symbols; + bool is_64_bit; #endif }; @@ -238,6 +232,11 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name); +struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); +struct symbol *dso__next_symbol(struct symbol *sym); + +enum dso_type dso__type_fd(int fd); + int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); int modules__parse(const char *filename, void *arg, @@ -246,7 +245,8 @@ int modules__parse(const char *filename, void *arg, int filename__read_debuglink(const char *filename, char *debuglink, size_t size); -int symbol__init(void); +struct perf_session_env; +int symbol__init(struct perf_session_env *env); void symbol__exit(void); void symbol__elf_init(void); struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name); diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c new file mode 100644 index 0000000..9ed59a4 --- /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 0000000..b843bbe --- /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 2fde0d5..9ebc8b1 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -4,17 +4,19 @@ #include <string.h> #include "session.h" #include "thread.h" +#include "thread-stack.h" #include "util.h" #include "debug.h" #include "comm.h" +#include "unwind.h" int thread__init_map_groups(struct thread *thread, struct machine *machine) { struct thread *leader; pid_t pid = thread->pid_; - if (pid == thread->tid) { - thread->mg = map_groups__new(); + if (pid == thread->tid || pid == -1) { + thread->mg = map_groups__new(machine); } else { leader = machine__findnew_thread(machine, pid, pid); if (leader) @@ -34,19 +36,24 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread->pid_ = pid; thread->tid = tid; thread->ppid = -1; + thread->cpu = -1; INIT_LIST_HEAD(&thread->comm_list); + if (unwind__prepare_access(thread) < 0) + goto err_thread; + comm_str = malloc(32); if (!comm_str) goto err_thread; snprintf(comm_str, 32, ":%d", tid); - comm = comm__new(comm_str, 0); + comm = comm__new(comm_str, 0, false); free(comm_str); if (!comm) goto err_thread; list_add(&comm->list, &thread->comm_list); + } return thread; @@ -60,12 +67,17 @@ void thread__delete(struct thread *thread) { struct comm *comm, *tmp; - map_groups__put(thread->mg); - thread->mg = NULL; + thread_stack__free(thread); + + if (thread->mg) { + map_groups__put(thread->mg); + thread->mg = NULL; + } list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) { list_del(&comm->list); comm__free(comm); } + unwind__finish_access(thread); free(thread); } @@ -78,22 +90,38 @@ struct comm *thread__comm(const struct thread *thread) return list_first_entry(&thread->comm_list, struct comm, list); } -/* CHECKME: time should always be 0 if event aren't ordered */ -int thread__set_comm(struct thread *thread, const char *str, u64 timestamp) +struct comm *thread__exec_comm(const struct thread *thread) +{ + struct comm *comm, *last = NULL; + + list_for_each_entry(comm, &thread->comm_list, list) { + if (comm->exec) + return comm; + last = comm; + } + + return last; +} + +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) { - err = comm__override(curr, str, timestamp); + /* Override the default :tid entry */ + if (!thread->comm_set) { + err = comm__override(curr, str, timestamp, exec); if (err) return err; } else { - new = comm__new(str, timestamp); + new = comm__new(str, timestamp, exec); if (!new) return -ENOMEM; list_add(&new->list, &thread->comm_list); + + if (exec) + unwind__flush_access(thread); } thread->comm_set = true; @@ -127,12 +155,12 @@ int thread__comm_len(struct thread *thread) size_t thread__fprintf(struct thread *thread, FILE *fp) { return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) + - map_groups__fprintf(thread->mg, verbose, fp); + map_groups__fprintf(thread->mg, fp); } void thread__insert_map(struct thread *thread, struct map *map) { - map_groups__fixup_overlappings(thread->mg, map, verbose, stderr); + map_groups__fixup_overlappings(thread->mg, map, stderr); map_groups__insert(thread->mg, map); } @@ -172,7 +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) { @@ -185,8 +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 3c0c272..160fd06 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; @@ -17,13 +19,16 @@ struct thread { pid_t pid_; /* Not all tools update this */ pid_t tid; pid_t ppid; + int cpu; char shortname[3]; bool comm_set; 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; @@ -37,24 +42,31 @@ static inline void thread__exited(struct thread *thread) thread->dead = true; } -int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp); +int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp, + bool exec); +static inline int thread__set_comm(struct thread *thread, const char *comm, + u64 timestamp) +{ + return __thread__set_comm(thread, comm, timestamp, false); +} + int thread__comm_len(struct thread *thread); struct comm *thread__comm(const struct thread *thread); +struct comm *thread__exec_comm(const struct thread *thread); const char *thread__comm_str(const struct thread *thread); 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/thread_map.c b/tools/perf/util/thread_map.c index 5d32159..f93b973 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -214,6 +214,17 @@ out_free_threads: goto out; } +struct thread_map *thread_map__new_dummy(void) +{ + struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t)); + + if (threads != NULL) { + threads->map[0] = -1; + threads->nr = 1; + } + return threads; +} + static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) { struct thread_map *threads = NULL, *nt; @@ -224,14 +235,8 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) struct strlist *slist; /* perf-stat expects threads to be generated even if tid not given */ - if (!tid_str) { - threads = malloc(sizeof(*threads) + sizeof(pid_t)); - if (threads != NULL) { - threads->map[0] = -1; - threads->nr = 1; - } - return threads; - } + if (!tid_str) + return thread_map__new_dummy(); slist = strlist__new(false, tid_str); if (!slist) diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 0cd8b31..95313f4 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -9,6 +9,7 @@ struct thread_map { pid_t map[]; }; +struct thread_map *thread_map__new_dummy(void); struct thread_map *thread_map__new_by_pid(pid_t pid); struct thread_map *thread_map__new_by_tid(pid_t tid); struct thread_map *thread_map__new_by_uid(uid_t uid); diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 4385816..bb2708b 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -39,8 +39,9 @@ struct perf_tool { event_attr_op attr; event_op2 tracing_data; event_op2 finished_round, - build_id; - bool ordered_samples; + build_id, + id_index; + bool ordered_events; bool ordering_requires_timestamps; }; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 7e6fcfe..eb72716 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -40,6 +40,7 @@ #include "trace-event.h" #include <api/fs/debugfs.h> #include "evsel.h" +#include "debug.h" #define VERSION "0.5" @@ -191,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) strcmp(dent->d_name, "..") == 0 || !name_in_tp_list(dent->d_name, tps)) continue; - format = malloc(strlen(sys) + strlen(dent->d_name) + 10); - if (!format) { + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; } - sprintf(format, "%s/%s/format", sys, dent->d_name); ret = stat(format, &st); free(format); if (ret < 0) @@ -217,12 +216,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) strcmp(dent->d_name, "..") == 0 || !name_in_tp_list(dent->d_name, tps)) continue; - format = malloc(strlen(sys) + strlen(dent->d_name) + 10); - if (!format) { + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; } - sprintf(format, "%s/%s/format", sys, dent->d_name); ret = stat(format, &st); if (ret >= 0) { @@ -317,12 +314,10 @@ static int record_event_files(struct tracepoint_path *tps) strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; - sys = malloc(strlen(path) + strlen(dent->d_name) + 2); - if (!sys) { + if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) { err = -ENOMEM; goto out; } - sprintf(sys, "%s/%s", path, dent->d_name); ret = stat(sys, &st); if (ret >= 0) { ssize_t size = strlen(dent->d_name) + 1; diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index e113e18..54d9e9b 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -22,7 +22,6 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <getopt.h> #include <stdarg.h> #include <sys/types.h> #include <sys/stat.h> @@ -36,6 +35,7 @@ #include "../perf.h" #include "util.h" #include "trace-event.h" +#include "debug.h" static int input_fd; diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 57aaccc..5c9bdd1 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -30,6 +30,11 @@ struct scripting_context *scripting_context; +static int flush_script_unsupported(void) +{ + return 0; +} + static int stop_script_unsupported(void) { return 0; @@ -74,6 +79,7 @@ static int python_generate_script_unsupported(struct pevent *pevent struct scripting_ops python_scripting_unsupported_ops = { .name = "Python", .start_script = python_start_script_unsupported, + .flush_script = flush_script_unsupported, .stop_script = stop_script_unsupported, .process_event = process_event_unsupported, .generate_script = python_generate_script_unsupported, @@ -137,6 +143,7 @@ static int perl_generate_script_unsupported(struct pevent *pevent struct scripting_ops perl_scripting_unsupported_ops = { .name = "Perl", .start_script = perl_start_script_unsupported, + .flush_script = flush_script_unsupported, .stop_script = stop_script_unsupported, .process_event = process_event_unsupported, .generate_script = perl_generate_script_unsupported, diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 7b6d686..52aaa19 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -64,6 +64,7 @@ struct perf_session; struct scripting_ops { const char *name; int (*start_script) (const char *script, int argc, const char **argv); + int (*flush_script) (void); int (*stop_script) (void); void (*process_event) (union perf_event *event, struct perf_sample *sample, diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c new file mode 100644 index 0000000..4d4210d --- /dev/null +++ b/tools/perf/util/tsc.c @@ -0,0 +1,30 @@ +#include <linux/compiler.h> +#include <linux/types.h> + +#include "tsc.h" + +u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc) +{ + u64 t, quot, rem; + + t = ns - tc->time_zero; + quot = t / tc->time_mult; + rem = t % tc->time_mult; + return (quot << tc->time_shift) + + (rem << tc->time_shift) / tc->time_mult; +} + +u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) +{ + u64 quot, rem; + + quot = cyc >> tc->time_shift; + rem = cyc & ((1 << tc->time_shift) - 1); + return tc->time_zero + quot * tc->time_mult + + ((rem * tc->time_mult) >> tc->time_shift); +} + +u64 __weak rdtsc(void) +{ + return 0; +} diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h new file mode 100644 index 0000000..a8b78f1 --- /dev/null +++ b/tools/perf/util/tsc.h @@ -0,0 +1,12 @@ +#ifndef __PERF_TSC_H +#define __PERF_TSC_H + +#include <linux/types.h> + +#include "../arch/x86/util/tsc.h" + +u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); +u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); +u64 rdtsc(void); + +#endif diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 5ec80a5..2dcfe9a 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -3,6 +3,7 @@ #include <elfutils/libdwfl.h> #include <inttypes.h> #include <errno.h> +#include "debug.h" #include "unwind.h" #include "unwind-libdw.h" #include "machine.h" @@ -25,7 +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); @@ -88,7 +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); @@ -163,14 +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 25578b9..371219a 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -24,12 +24,14 @@ #include <linux/list.h> #include <libunwind.h> #include <libunwind-ptrace.h> +#include "callchain.h" #include "thread.h" #include "session.h" #include "perf_regs.h" #include "unwind.h" #include "symbol.h" #include "util.h" +#include "debug.h" extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, @@ -282,7 +284,7 @@ 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; } @@ -372,7 +374,7 @@ 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); @@ -474,14 +476,13 @@ 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; @@ -524,12 +525,12 @@ static unw_accessors_t accessors = { .get_proc_name = get_proc_name, }; -static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, - void *arg, int max_stack) +int unwind__prepare_access(struct thread *thread) { unw_addr_space_t addr_space; - unw_cursor_t c; - int ret; + + if (callchain_param.record_mode != CALLCHAIN_DWARF) + return 0; addr_space = unw_create_addr_space(&accessors, 0); if (!addr_space) { @@ -537,6 +538,45 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, return -ENOMEM; } + unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL); + thread__set_priv(thread, addr_space); + + return 0; +} + +void unwind__flush_access(struct thread *thread) +{ + unw_addr_space_t addr_space; + + if (callchain_param.record_mode != CALLCHAIN_DWARF) + return; + + addr_space = thread__priv(thread); + unw_flush_cache(addr_space, 0, 0); +} + +void unwind__finish_access(struct thread *thread) +{ + unw_addr_space_t addr_space; + + if (callchain_param.record_mode != CALLCHAIN_DWARF) + return; + + addr_space = thread__priv(thread); + unw_destroy_addr_space(addr_space); +} + +static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, + void *arg, int max_stack) +{ + unw_addr_space_t addr_space; + unw_cursor_t c; + int ret; + + addr_space = thread__priv(ui->thread); + if (addr_space == NULL) + return -1; + ret = unw_init_remote(&c, addr_space, ui); if (ret) display_error(ret); @@ -545,22 +585,21 @@ 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; } - unw_destroy_addr_space(addr_space); 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; @@ -571,7 +610,7 @@ 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 f030612..12790cf 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include "event.h" #include "symbol.h" +#include "thread.h" struct unwind_entry { struct map *map; @@ -15,23 +16,40 @@ 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 */ #ifdef HAVE_LIBUNWIND_SUPPORT int libunwind__arch_reg_id(int regnum); +int unwind__prepare_access(struct thread *thread); +void unwind__flush_access(struct thread *thread); +void unwind__finish_access(struct thread *thread); +#else +static inline int unwind__prepare_access(struct thread *thread __maybe_unused) +{ + return 0; +} + +static inline void unwind__flush_access(struct thread *thread __maybe_unused) {} +static inline void unwind__finish_access(struct thread *thread __maybe_unused) {} #endif #else 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) { return 0; } + +static inline int unwind__prepare_access(struct thread *thread __maybe_unused) +{ + return 0; +} + +static inline void unwind__flush_access(struct thread *thread __maybe_unused) {} +static inline void unwind__finish_access(struct thread *thread __maybe_unused) {} #endif /* HAVE_DWARF_UNWIND_SUPPORT */ #endif /* __UNWIND_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 95aefa7..b86744f 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,5 +1,6 @@ #include "../perf.h" #include "util.h" +#include "debug.h" #include <api/fs/fs.h> #include <sys/mman.h> #ifdef HAVE_BACKTRACE_SUPPORT @@ -12,6 +13,15 @@ #include <limits.h> #include <byteswap.h> #include <linux/kernel.h> +#include <unistd.h> +#include "callchain.h" + +struct callchain_param callchain_param = { + .mode = CHAIN_GRAPH_REL, + .min_percent = 0.5, + .order = ORDER_CALLEE, + .key = CCKEY_FUNCTION +}; /* * XXX We need to find a better place for these things... @@ -281,6 +291,18 @@ void get_term_dimensions(struct winsize *ws) ws->ws_col = 80; } +void set_term_quiet_input(struct termios *old) +{ + struct termios tc; + + tcgetattr(0, old); + tc = *old; + tc.c_lflag &= ~(ICANON | ECHO); + tc.c_cc[VMIN] = 0; + tc.c_cc[VTIME] = 0; + tcsetattr(0, TCSANOW, &tc); +} + static void set_tracing_events_path(const char *mountpoint) { snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s", @@ -333,12 +355,9 @@ const char *find_tracing_dir(void) if (!debugfs) return NULL; - tracing = malloc(strlen(debugfs) + 9); - if (!tracing) + if (asprintf(&tracing, "%s/tracing", debugfs) < 0) return NULL; - sprintf(tracing, "%s/tracing", debugfs); - tracing_found = 1; return tracing; } @@ -352,11 +371,9 @@ char *get_tracing_file(const char *name) if (!tracing) return NULL; - file = malloc(strlen(tracing) + strlen(name) + 2); - if (!file) + if (asprintf(&file, "%s/%s", tracing, name) < 0) return NULL; - sprintf(file, "%s/%s", tracing, name); return file; } @@ -425,28 +442,12 @@ 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; void *bf = NULL, *nbf; int fd, n, err = 0; + char sbuf[STRERR_BUFSIZE]; fd = open(filename, O_RDONLY); if (fd < 0) @@ -467,8 +468,8 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep) n = read(fd, bf + size, alloc_size - size); if (n < 0) { if (size) { - pr_warning("read failed %d: %s\n", - errno, strerror(errno)); + pr_warning("read failed %d: %s\n", errno, + strerror_r(errno, sbuf, sizeof(sbuf))); err = 0; } else err = -errno; @@ -505,16 +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; @@ -540,3 +534,39 @@ void mem_bswap_64(void *src, int byte_size) ++m; } } + +bool find_process(const char *name) +{ + size_t len = strlen(name); + DIR *dir; + struct dirent *d; + int ret = -1; + + dir = opendir(procfs__mountpoint()); + if (!dir) + return -1; + + /* Walk through the directory. */ + while (ret && (d = readdir(dir)) != NULL) { + char path[PATH_MAX]; + char *data; + size_t size; + + if ((d->d_type != DT_DIR) || + !strcmp(".", d->d_name) || + !strcmp("..", d->d_name)) + continue; + + scnprintf(path, sizeof(path), "%s/%s/comm", + procfs__mountpoint(), d->d_name); + + if (filename__read_str(path, &data, &size)) + continue; + + ret = strncmp(name, data, len); + free(data); + } + + closedir(dir); + return ret ? false : true; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 6686436..027a515 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -39,6 +39,8 @@ #define _ALL_SOURCE 1 #define _BSD_SOURCE 1 +/* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */ +#define _DEFAULT_SOURCE 1 #define HAS_BOOL #include <unistd.h> @@ -64,16 +66,18 @@ #include <regex.h> #include <utime.h> #include <sys/wait.h> -#include <sys/poll.h> +#include <poll.h> #include <sys/socket.h> #include <sys/ioctl.h> #include <inttypes.h> +#include <linux/kernel.h> #include <linux/magic.h> #include <linux/types.h> #include <sys/ttydefaults.h> #include <api/fs/debugfs.h> #include <termios.h> #include <linux/bitops.h> +#include <termios.h> extern const char *graph_line; extern const char *graph_dotted_line; @@ -149,8 +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) { @@ -266,35 +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); @@ -307,6 +281,7 @@ extern unsigned int page_size; extern int cacheline_size; void get_term_dimensions(struct winsize *ws); +void set_term_quiet_input(struct termios *old); struct parse_tag { char tag; @@ -317,12 +292,28 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags); #define SRCLINE_UNKNOWN ((char *) "??:0") +static inline int path__join(char *bf, size_t size, + const char *path1, const char *path2) +{ + return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2); +} + +static inline int path__join3(char *bf, size_t size, + const char *path1, const char *path2, + const char *path3) +{ + return scnprintf(bf, size, "%s%s%s%s%s", + path1, path1[0] ? "/" : "", + path2, path2[0] ? "/" : "", path3); +} + 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); @@ -330,4 +321,10 @@ void mem_bswap_64(void *src, int byte_size); 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 0ddb3b8..5c7dd79 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -11,43 +11,60 @@ #include "vdso.h" #include "util.h" #include "symbol.h" +#include "machine.h" +#include "thread.h" #include "linux/string.h" +#include "debug.h" -static bool vdso_found; -static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX"; +/* + * 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" -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; - } +#define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX" - while (!found && fgets(line, sizeof(line), maps)) { - int m = -1; +struct vdso_file { + bool found; + bool error; + char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)]; + const char *dso_name; + const char *read_prog; +}; - /* 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; +struct vdso_info { + struct vdso_file vdso; +#if BITS_PER_LONG == 64 + struct vdso_file vdso32; + struct vdso_file vdsox32; +#endif +}; - if (!strncmp(&line[m], VDSO__MAP_NAME, - sizeof(VDSO__MAP_NAME) - 1)) - found = 1; - } +static struct vdso_info *vdso_info__new(void) +{ + static const struct vdso_info vdso_info_init = { + .vdso = { + .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 + }; - fclose(maps); - return !found; + return memdup(&vdso_info_init, sizeof(vdso_info_init)); } -static char *get_file(void) +static char *get_file(struct vdso_file *vdso_file) { char *vdso = NULL; char *buf = NULL; @@ -55,10 +72,10 @@ static char *get_file(void) size_t size; int fd; - if (vdso_found) - return vdso_file; + if (vdso_file->found) + return vdso_file->temp_file_name; - if (find_vdso_map(&start, &end)) + if (vdso_file->error || find_vdso_map(&start, &end)) return NULL; size = end - start; @@ -67,45 +84,238 @@ static char *get_file(void) if (!buf) return NULL; - fd = mkstemp(vdso_file); + fd = mkstemp(vdso_file->temp_file_name); if (fd < 0) goto out; if (size == (size_t) write(fd, buf, size)) - vdso = vdso_file; + vdso = vdso_file->temp_file_name; close(fd); out: free(buf); - vdso_found = (vdso != NULL); + vdso_file->found = (vdso != NULL); + vdso_file->error = !vdso_file->found; return vdso; } -void vdso__exit(void) +void vdso__exit(struct machine *machine) +{ + struct vdso_info *vdso_info = machine->vdso_info; + + if (!vdso_info) + return; + + 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); +} + +static struct dso *vdso__new(struct machine *machine, const char *short_name, + const char *long_name) +{ + struct dso *dso; + + dso = dso__new(short_name); + if (dso != NULL) { + dsos__add(&machine->user_dsos, dso); + dso__set_long_name(dso, long_name, false); + } + + 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) { - if (vdso_found) - unlink(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; } -struct dso *vdso__dso_findnew(struct list_head *head) +static struct dso *vdso__findnew_compat(struct machine *machine, + struct vdso_file *vdso_file) { - struct dso *dso = dsos__find(head, VDSO__MAP_NAME, true); + 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) +{ + struct vdso_info *vdso_info; + struct dso *dso; + + if (!machine->vdso_info) + machine->vdso_info = vdso_info__new(); + + vdso_info = machine->vdso_info; + 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; - file = get_file(); + file = get_file(&vdso_info->vdso); if (!file) return NULL; - dso = dso__new(VDSO__MAP_NAME); - if (dso != NULL) { - dsos__add(head, dso); - dso__set_long_name(dso, file, false); - } + dso = vdso__new(machine, DSO__NAME_VDSO, file); } return dso; } + +bool dso__is_vdso(struct dso *dso) +{ + 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 0f76e7c..d97da16 100644 --- a/tools/perf/util/vdso.h +++ b/tools/perf/util/vdso.h @@ -7,12 +7,23 @@ #define VDSO__MAP_NAME "[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) { return !strcmp(filename, VDSO__MAP_NAME); } -struct dso *vdso__dso_findnew(struct list_head *head); -void vdso__exit(void); +struct dso; + +bool dso__is_vdso(struct dso *dso); + +struct machine; +struct thread; + +struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread); +void vdso__exit(struct machine *machine); #endif /* __PERF_VDSO__ */ diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c new file mode 100644 index 0000000..495a449 --- /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/Makefile b/tools/power/acpi/Makefile index e5a3c4b..3d1537b 100644 --- a/tools/power/acpi/Makefile +++ b/tools/power/acpi/Makefile @@ -108,13 +108,18 @@ DUMP_OBJS = \ apmain.o\ osunixdir.o\ osunixmap.o\ + osunixxf.o\ tbprint.o\ tbxfroot.o\ utbuffer.o\ + utdebug.o\ utexcep.o\ + utglobal.o\ utmath.o\ + utprint.o\ utstring.o\ utxferror.o\ + oslibcfs.o\ oslinuxtbl.o\ cmfsize.o\ getopt.o diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c index 5140e5e..f4b9533 100644 --- a/tools/power/acpi/common/cmfsize.c +++ b/tools/power/acpi/common/cmfsize.c @@ -58,44 +58,46 @@ ACPI_MODULE_NAME("cmfsize") * RETURN: File Size. On error, -1 (ACPI_UINT32_MAX) * * DESCRIPTION: Get the size of a file. Uses seek-to-EOF. File must be open. - * Does not disturb the current file pointer. Uses perror for - * error messages. + * Does not disturb the current file pointer. * ******************************************************************************/ -u32 cm_get_file_size(FILE * file) +u32 cm_get_file_size(ACPI_FILE file) { long file_size; long current_offset; + acpi_status status; /* Save the current file pointer, seek to EOF to obtain file size */ - current_offset = ftell(file); + current_offset = acpi_os_get_file_offset(file); if (current_offset < 0) { goto offset_error; } - if (fseek(file, 0, SEEK_END)) { + status = acpi_os_set_file_offset(file, 0, ACPI_FILE_END); + if (ACPI_FAILURE(status)) { goto seek_error; } - file_size = ftell(file); + file_size = acpi_os_get_file_offset(file); if (file_size < 0) { goto offset_error; } /* Restore original file pointer */ - if (fseek(file, current_offset, SEEK_SET)) { + status = acpi_os_set_file_offset(file, current_offset, ACPI_FILE_BEGIN); + if (ACPI_FAILURE(status)) { goto seek_error; } return ((u32)file_size); offset_error: - perror("Could not get file offset"); + acpi_log_error("Could not get file offset"); return (ACPI_UINT32_MAX); seek_error: - perror("Could not seek file"); + acpi_log_error("Could not set file offset"); return (ACPI_UINT32_MAX); } diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c index a302f52..2f0f34a 100644 --- a/tools/power/acpi/common/getopt.c +++ b/tools/power/acpi/common/getopt.c @@ -51,14 +51,12 @@ * "f|" - Option has required single-char sub-options */ -#include <stdio.h> -#include <string.h> #include <acpi/acpi.h> #include "accommon.h" #include "acapps.h" #define ACPI_OPTION_ERROR(msg, badchar) \ - if (acpi_gbl_opterr) {fprintf (stderr, "%s%c\n", msg, badchar);} + if (acpi_gbl_opterr) {acpi_log_error ("%s%c\n", msg, badchar);} int acpi_gbl_opterr = 1; int acpi_gbl_optind = 1; @@ -113,7 +111,7 @@ int acpi_getopt_argument(int argc, char **argv) * PARAMETERS: argc, argv - from main * opts - options info list * - * RETURN: Option character or EOF + * RETURN: Option character or ACPI_OPT_END * * DESCRIPTION: Get the next option * @@ -128,10 +126,10 @@ int acpi_getopt(int argc, char **argv, char *opts) if (acpi_gbl_optind >= argc || argv[acpi_gbl_optind][0] != '-' || argv[acpi_gbl_optind][1] == '\0') { - return (EOF); - } else if (strcmp(argv[acpi_gbl_optind], "--") == 0) { + return (ACPI_OPT_END); + } else if (ACPI_STRCMP(argv[acpi_gbl_optind], "--") == 0) { acpi_gbl_optind++; - return (EOF); + return (ACPI_OPT_END); } } @@ -142,7 +140,7 @@ int acpi_getopt(int argc, char **argv, char *opts) /* Make sure that the option is legal */ if (current_char == ':' || - (opts_ptr = strchr(opts, current_char)) == NULL) { + (opts_ptr = ACPI_STRCHR(opts, current_char)) == NULL) { ACPI_OPTION_ERROR("Illegal option: -", current_char); if (argv[acpi_gbl_optind][++current_char_ptr] == '\0') { diff --git a/tools/power/acpi/os_specific/service_layers/oslibcfs.c b/tools/power/acpi/os_specific/service_layers/oslibcfs.c new file mode 100644 index 0000000..c13ff9c --- /dev/null +++ b/tools/power/acpi/os_specific/service_layers/oslibcfs.c @@ -0,0 +1,214 @@ +/****************************************************************************** + * + * Module Name: oslibcfs - C library OSL for file I/O + * + *****************************************************************************/ + +/* + * Copyright (C) 2000 - 2014, Intel Corp. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions, and the following disclaimer, + * without modification. + * 2. Redistributions in binary form must reproduce at minimum a disclaimer + * substantially similar to the "NO WARRANTY" disclaimer below + * ("Disclaimer") and any redistribution must be conditioned upon + * including a substantially similar Disclaimer requirement for further + * binary redistribution. + * 3. Neither the names of the above-listed copyright holders nor the names + * of any contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * NO WARRANTY + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, + * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING + * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGES. + */ + +#include <acpi/acpi.h> +#include <stdio.h> +#include <stdarg.h> + +#define _COMPONENT ACPI_OS_SERVICES +ACPI_MODULE_NAME("oslibcfs") + +/******************************************************************************* + * + * FUNCTION: acpi_os_open_file + * + * PARAMETERS: path - File path + * modes - File operation type + * + * RETURN: File descriptor. + * + * DESCRIPTION: Open a file for reading (ACPI_FILE_READING) or/and writing + * (ACPI_FILE_WRITING). + * + ******************************************************************************/ +ACPI_FILE acpi_os_open_file(const char *path, u8 modes) +{ + ACPI_FILE file; + u32 i = 0; + char modes_str[4]; + + if (modes & ACPI_FILE_READING) { + modes_str[i++] = 'r'; + } + if (modes & ACPI_FILE_WRITING) { + modes_str[i++] = 'w'; + } + if (modes & ACPI_FILE_BINARY) { + modes_str[i++] = 'b'; + } + + modes_str[i++] = '\0'; + + file = fopen(path, modes_str); + if (!file) { + perror("Could not open file"); + } + + return (file); +} + +/******************************************************************************* + * + * FUNCTION: acpi_os_close_file + * + * PARAMETERS: file - An open file descriptor + * + * RETURN: None. + * + * DESCRIPTION: Close a file opened via acpi_os_open_file. + * + ******************************************************************************/ + +void acpi_os_close_file(ACPI_FILE file) +{ + fclose(file); +} + +/******************************************************************************* + * + * FUNCTION: acpi_os_read_file + * + * PARAMETERS: file - An open file descriptor + * buffer - Data buffer + * size - Data block size + * count - Number of data blocks + * + * RETURN: Number of bytes actually read. + * + * DESCRIPTION: Read from a file. + * + ******************************************************************************/ + +int +acpi_os_read_file(ACPI_FILE file, void *buffer, acpi_size size, acpi_size count) +{ + int length; + + length = fread(buffer, size, count, file); + if (length < 0) { + perror("Error reading file"); + } + + return (length); +} + +/******************************************************************************* + * + * FUNCTION: acpi_os_write_file + * + * PARAMETERS: file - An open file descriptor + * buffer - Data buffer + * size - Data block size + * count - Number of data blocks + * + * RETURN: Number of bytes actually written. + * + * DESCRIPTION: Write to a file. + * + ******************************************************************************/ + +int +acpi_os_write_file(ACPI_FILE file, + void *buffer, acpi_size size, acpi_size count) +{ + int length; + + length = fwrite(buffer, size, count, file); + if (length < 0) { + perror("Error writing file"); + } + + return (length); +} + +/******************************************************************************* + * + * FUNCTION: acpi_os_get_file_offset + * + * PARAMETERS: file - An open file descriptor + * + * RETURN: Current file pointer position. + * + * DESCRIPTION: Get current file offset. + * + ******************************************************************************/ + +long acpi_os_get_file_offset(ACPI_FILE file) +{ + long offset; + + offset = ftell(file); + return (offset); +} + +/******************************************************************************* + * + * FUNCTION: acpi_os_set_file_offset + * + * PARAMETERS: file - An open file descriptor + * offset - New file offset + * from - From begin/end of file + * + * RETURN: Status + * + * DESCRIPTION: Set current file offset. + * + ******************************************************************************/ + +acpi_status acpi_os_set_file_offset(ACPI_FILE file, long offset, u8 from) +{ + int ret = 0; + + if (from == ACPI_FILE_BEGIN) { + ret = fseek(file, offset, SEEK_SET); + } + if (from == ACPI_FILE_END) { + ret = fseek(file, offset, SEEK_END); + } + + if (ret < 0) { + return (AE_ERROR); + } else { + return (AE_OK); + } +} diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c index 28c5200..0dc2485 100644 --- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c +++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c @@ -77,6 +77,9 @@ osl_map_table(acpi_size address, static void osl_unmap_table(struct acpi_table_header *table); +static acpi_physical_address +osl_find_rsdp_via_efi_by_keyword(FILE * file, const char *keyword); + static acpi_physical_address osl_find_rsdp_via_efi(void); static acpi_status osl_load_rsdp(void); @@ -417,6 +420,38 @@ acpi_os_get_table_by_index(u32 index, /****************************************************************************** * + * FUNCTION: osl_find_rsdp_via_efi_by_keyword + * + * PARAMETERS: keyword - Character string indicating ACPI GUID version + * in the EFI table + * + * RETURN: RSDP address if found + * + * DESCRIPTION: Find RSDP address via EFI using keyword indicating the ACPI + * GUID version. + * + *****************************************************************************/ + +static acpi_physical_address +osl_find_rsdp_via_efi_by_keyword(FILE * file, const char *keyword) +{ + char buffer[80]; + unsigned long long address = 0; + char format[32]; + + snprintf(format, 32, "%s=%s", keyword, "%llx"); + fseek(file, 0, SEEK_SET); + while (fgets(buffer, 80, file)) { + if (sscanf(buffer, format, &address) == 1) { + break; + } + } + + return ((acpi_physical_address) (address)); +} + +/****************************************************************************** + * * FUNCTION: osl_find_rsdp_via_efi * * PARAMETERS: None @@ -430,20 +465,19 @@ acpi_os_get_table_by_index(u32 index, static acpi_physical_address osl_find_rsdp_via_efi(void) { FILE *file; - char buffer[80]; - unsigned long address = 0; + acpi_physical_address address = 0; file = fopen(EFI_SYSTAB, "r"); if (file) { - while (fgets(buffer, 80, file)) { - if (sscanf(buffer, "ACPI20=0x%lx", &address) == 1) { - break; - } + address = osl_find_rsdp_via_efi_by_keyword(file, "ACPI20"); + if (!address) { + address = + osl_find_rsdp_via_efi_by_keyword(file, "ACPI"); } fclose(file); } - return ((acpi_physical_address) (address)); + return (address); } /****************************************************************************** diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c new file mode 100644 index 0000000..7ccb073 --- /dev/null +++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c @@ -0,0 +1,1319 @@ +/****************************************************************************** + * + * Module Name: osunixxf - UNIX OSL interfaces + * + *****************************************************************************/ + +/* + * Copyright (C) 2000 - 2014, Intel Corp. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions, and the following disclaimer, + * without modification. + * 2. Redistributions in binary form must reproduce at minimum a disclaimer + * substantially similar to the "NO WARRANTY" disclaimer below + * ("Disclaimer") and any redistribution must be conditioned upon + * including a substantially similar Disclaimer requirement for further + * binary redistribution. + * 3. Neither the names of the above-listed copyright holders nor the names + * of any contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * NO WARRANTY + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, + * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING + * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGES. + */ + +/* + * These interfaces are required in order to compile the ASL compiler and the + * various ACPICA tools under Linux or other Unix-like system. + */ +#include <acpi/acpi.h> +#include "accommon.h" +#include "amlcode.h" +#include "acparser.h" +#include "acdebug.h" + +#include <stdio.h> +#include <stdlib.h> +#include <stdarg.h> +#include <unistd.h> +#include <sys/time.h> +#include <semaphore.h> +#include <pthread.h> +#include <errno.h> + +#define _COMPONENT ACPI_OS_SERVICES +ACPI_MODULE_NAME("osunixxf") + +u8 acpi_gbl_debug_timeout = FALSE; + +/* Upcalls to acpi_exec */ + +void +ae_table_override(struct acpi_table_header *existing_table, + struct acpi_table_header **new_table); + +typedef void *(*PTHREAD_CALLBACK) (void *); + +/* Buffer used by acpi_os_vprintf */ + +#define ACPI_VPRINTF_BUFFER_SIZE 512 +#define _ASCII_NEWLINE '\n' + +/* Terminal support for acpi_exec only */ + +#ifdef ACPI_EXEC_APP +#include <termios.h> + +struct termios original_term_attributes; +int term_attributes_were_set = 0; + +acpi_status acpi_ut_read_line(char *buffer, u32 buffer_length, u32 *bytes_read); + +static void os_enter_line_edit_mode(void); + +static void os_exit_line_edit_mode(void); + +/****************************************************************************** + * + * FUNCTION: os_enter_line_edit_mode, os_exit_line_edit_mode + * + * PARAMETERS: None + * + * RETURN: None + * + * DESCRIPTION: Enter/Exit the raw character input mode for the terminal. + * + * Interactive line-editing support for the AML debugger. Used with the + * common/acgetline module. + * + * readline() is not used because of non-portability. It is not available + * on all systems, and if it is, often the package must be manually installed. + * + * Therefore, we use the POSIX tcgetattr/tcsetattr and do the minimal line + * editing that we need in acpi_os_get_line. + * + * If the POSIX tcgetattr/tcsetattr interfaces are unavailable, these + * calls will also work: + * For os_enter_line_edit_mode: system ("stty cbreak -echo") + * For os_exit_line_edit_mode: system ("stty cooked echo") + * + *****************************************************************************/ + +static void os_enter_line_edit_mode(void) +{ + struct termios local_term_attributes; + + term_attributes_were_set = 0; + + /* STDIN must be a terminal */ + + if (!isatty(STDIN_FILENO)) { + return; + } + + /* Get and keep the original attributes */ + + if (tcgetattr(STDIN_FILENO, &original_term_attributes)) { + fprintf(stderr, "Could not get terminal attributes!\n"); + return; + } + + /* Set the new attributes to enable raw character input */ + + memcpy(&local_term_attributes, &original_term_attributes, + sizeof(struct termios)); + + local_term_attributes.c_lflag &= ~(ICANON | ECHO); + local_term_attributes.c_cc[VMIN] = 1; + local_term_attributes.c_cc[VTIME] = 0; + + if (tcsetattr(STDIN_FILENO, TCSANOW, &local_term_attributes)) { + fprintf(stderr, "Could not set terminal attributes!\n"); + return; + } + + term_attributes_were_set = 1; +} + +static void os_exit_line_edit_mode(void) +{ + + if (!term_attributes_were_set) { + return; + } + + /* Set terminal attributes back to the original values */ + + if (tcsetattr(STDIN_FILENO, TCSANOW, &original_term_attributes)) { + fprintf(stderr, "Could not restore terminal attributes!\n"); + } +} + +#else + +/* These functions are not needed for other ACPICA utilities */ + +#define os_enter_line_edit_mode() +#define os_exit_line_edit_mode() +#endif + +/****************************************************************************** + * + * FUNCTION: acpi_os_initialize, acpi_os_terminate + * + * PARAMETERS: None + * + * RETURN: Status + * + * DESCRIPTION: Initialize and terminate this module. + * + *****************************************************************************/ + +acpi_status acpi_os_initialize(void) +{ + acpi_status status; + + acpi_gbl_output_file = stdout; + + os_enter_line_edit_mode(); + + status = acpi_os_create_lock(&acpi_gbl_print_lock); + if (ACPI_FAILURE(status)) { + return (status); + } + + return (AE_OK); +} + +acpi_status acpi_os_terminate(void) +{ + + os_exit_line_edit_mode(); + return (AE_OK); +} + +#ifndef ACPI_USE_NATIVE_RSDP_POINTER +/****************************************************************************** + * + * FUNCTION: acpi_os_get_root_pointer + * + * PARAMETERS: None + * + * RETURN: RSDP physical address + * + * DESCRIPTION: Gets the ACPI root pointer (RSDP) + * + *****************************************************************************/ + +acpi_physical_address acpi_os_get_root_pointer(void) +{ + + return (0); +} +#endif + +/****************************************************************************** + * + * FUNCTION: acpi_os_predefined_override + * + * PARAMETERS: init_val - Initial value of the predefined object + * new_val - The new value for the object + * + * RETURN: Status, pointer to value. Null pointer returned if not + * overriding. + * + * DESCRIPTION: Allow the OS to override predefined names + * + *****************************************************************************/ + +acpi_status +acpi_os_predefined_override(const struct acpi_predefined_names * init_val, + acpi_string * new_val) +{ + + if (!init_val || !new_val) { + return (AE_BAD_PARAMETER); + } + + *new_val = NULL; + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_table_override + * + * PARAMETERS: existing_table - Header of current table (probably + * firmware) + * new_table - Where an entire new table is returned. + * + * RETURN: Status, pointer to new table. Null pointer returned if no + * table is available to override + * + * DESCRIPTION: Return a different version of a table if one is available + * + *****************************************************************************/ + +acpi_status +acpi_os_table_override(struct acpi_table_header * existing_table, + struct acpi_table_header ** new_table) +{ + + if (!existing_table || !new_table) { + return (AE_BAD_PARAMETER); + } + + *new_table = NULL; + +#ifdef ACPI_EXEC_APP + + ae_table_override(existing_table, new_table); + return (AE_OK); +#else + + return (AE_NO_ACPI_TABLES); +#endif +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_physical_table_override + * + * PARAMETERS: existing_table - Header of current table (probably firmware) + * new_address - Where new table address is returned + * (Physical address) + * new_table_length - Where new table length is returned + * + * RETURN: Status, address/length of new table. Null pointer returned + * if no table is available to override. + * + * DESCRIPTION: Returns AE_SUPPORT, function not used in user space. + * + *****************************************************************************/ + +acpi_status +acpi_os_physical_table_override(struct acpi_table_header * existing_table, + acpi_physical_address * new_address, + u32 *new_table_length) +{ + + return (AE_SUPPORT); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_redirect_output + * + * PARAMETERS: destination - An open file handle/pointer + * + * RETURN: None + * + * DESCRIPTION: Causes redirect of acpi_os_printf and acpi_os_vprintf + * + *****************************************************************************/ + +void acpi_os_redirect_output(void *destination) +{ + + acpi_gbl_output_file = destination; +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_printf + * + * PARAMETERS: fmt, ... - Standard printf format + * + * RETURN: None + * + * DESCRIPTION: Formatted output. Note: very similar to acpi_os_vprintf + * (performance), changes should be tracked in both functions. + * + *****************************************************************************/ + +void ACPI_INTERNAL_VAR_XFACE acpi_os_printf(const char *fmt, ...) +{ + va_list args; + u8 flags; + + flags = acpi_gbl_db_output_flags; + if (flags & ACPI_DB_REDIRECTABLE_OUTPUT) { + + /* Output is directable to either a file (if open) or the console */ + + if (acpi_gbl_debug_file) { + + /* Output file is open, send the output there */ + + va_start(args, fmt); + vfprintf(acpi_gbl_debug_file, fmt, args); + va_end(args); + } else { + /* No redirection, send output to console (once only!) */ + + flags |= ACPI_DB_CONSOLE_OUTPUT; + } + } + + if (flags & ACPI_DB_CONSOLE_OUTPUT) { + va_start(args, fmt); + vfprintf(acpi_gbl_output_file, fmt, args); + va_end(args); + } +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_vprintf + * + * PARAMETERS: fmt - Standard printf format + * args - Argument list + * + * RETURN: None + * + * DESCRIPTION: Formatted output with argument list pointer. Note: very + * similar to acpi_os_printf, changes should be tracked in both + * functions. + * + *****************************************************************************/ + +void acpi_os_vprintf(const char *fmt, va_list args) +{ + u8 flags; + char buffer[ACPI_VPRINTF_BUFFER_SIZE]; + + /* + * We build the output string in a local buffer because we may be + * outputting the buffer twice. Using vfprintf is problematic because + * some implementations modify the args pointer/structure during + * execution. Thus, we use the local buffer for portability. + * + * Note: Since this module is intended for use by the various ACPICA + * utilities/applications, we can safely declare the buffer on the stack. + * Also, This function is used for relatively small error messages only. + */ + vsnprintf(buffer, ACPI_VPRINTF_BUFFER_SIZE, fmt, args); + + flags = acpi_gbl_db_output_flags; + if (flags & ACPI_DB_REDIRECTABLE_OUTPUT) { + + /* Output is directable to either a file (if open) or the console */ + + if (acpi_gbl_debug_file) { + + /* Output file is open, send the output there */ + + fputs(buffer, acpi_gbl_debug_file); + } else { + /* No redirection, send output to console (once only!) */ + + flags |= ACPI_DB_CONSOLE_OUTPUT; + } + } + + if (flags & ACPI_DB_CONSOLE_OUTPUT) { + fputs(buffer, acpi_gbl_output_file); + } +} + +#ifndef ACPI_EXEC_APP +/****************************************************************************** + * + * FUNCTION: acpi_os_get_line + * + * PARAMETERS: buffer - Where to return the command line + * buffer_length - Maximum length of Buffer + * bytes_read - Where the actual byte count is returned + * + * RETURN: Status and actual bytes read + * + * DESCRIPTION: Get the next input line from the terminal. NOTE: For the + * acpi_exec utility, we use the acgetline module instead to + * provide line-editing and history support. + * + *****************************************************************************/ + +acpi_status acpi_os_get_line(char *buffer, u32 buffer_length, u32 *bytes_read) +{ + int input_char; + u32 end_of_line; + + /* Standard acpi_os_get_line for all utilities except acpi_exec */ + + for (end_of_line = 0;; end_of_line++) { + if (end_of_line >= buffer_length) { + return (AE_BUFFER_OVERFLOW); + } + + if ((input_char = getchar()) == EOF) { + return (AE_ERROR); + } + + if (!input_char || input_char == _ASCII_NEWLINE) { + break; + } + + buffer[end_of_line] = (char)input_char; + } + + /* Null terminate the buffer */ + + buffer[end_of_line] = 0; + + /* Return the number of bytes in the string */ + + if (bytes_read) { + *bytes_read = end_of_line; + } + + return (AE_OK); +} +#endif + +#ifndef ACPI_USE_NATIVE_MEMORY_MAPPING +/****************************************************************************** + * + * FUNCTION: acpi_os_map_memory + * + * PARAMETERS: where - Physical address of memory to be mapped + * length - How much memory to map + * + * RETURN: Pointer to mapped memory. Null on error. + * + * DESCRIPTION: Map physical memory into caller's address space + * + *****************************************************************************/ + +void *acpi_os_map_memory(acpi_physical_address where, acpi_size length) +{ + + return (ACPI_TO_POINTER((acpi_size) where)); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_unmap_memory + * + * PARAMETERS: where - Logical address of memory to be unmapped + * length - How much memory to unmap + * + * RETURN: None. + * + * DESCRIPTION: Delete a previously created mapping. Where and Length must + * correspond to a previous mapping exactly. + * + *****************************************************************************/ + +void acpi_os_unmap_memory(void *where, acpi_size length) +{ + + return; +} +#endif + +/****************************************************************************** + * + * FUNCTION: acpi_os_allocate + * + * PARAMETERS: size - Amount to allocate, in bytes + * + * RETURN: Pointer to the new allocation. Null on error. + * + * DESCRIPTION: Allocate memory. Algorithm is dependent on the OS. + * + *****************************************************************************/ + +void *acpi_os_allocate(acpi_size size) +{ + void *mem; + + mem = (void *)malloc((size_t) size); + return (mem); +} + +#ifdef USE_NATIVE_ALLOCATE_ZEROED +/****************************************************************************** + * + * FUNCTION: acpi_os_allocate_zeroed + * + * PARAMETERS: size - Amount to allocate, in bytes + * + * RETURN: Pointer to the new allocation. Null on error. + * + * DESCRIPTION: Allocate and zero memory. Algorithm is dependent on the OS. + * + *****************************************************************************/ + +void *acpi_os_allocate_zeroed(acpi_size size) +{ + void *mem; + + mem = (void *)calloc(1, (size_t) size); + return (mem); +} +#endif + +/****************************************************************************** + * + * FUNCTION: acpi_os_free + * + * PARAMETERS: mem - Pointer to previously allocated memory + * + * RETURN: None. + * + * DESCRIPTION: Free memory allocated via acpi_os_allocate + * + *****************************************************************************/ + +void acpi_os_free(void *mem) +{ + + free(mem); +} + +#ifdef ACPI_SINGLE_THREADED +/****************************************************************************** + * + * FUNCTION: Semaphore stub functions + * + * DESCRIPTION: Stub functions used for single-thread applications that do + * not require semaphore synchronization. Full implementations + * of these functions appear after the stubs. + * + *****************************************************************************/ + +acpi_status +acpi_os_create_semaphore(u32 max_units, + u32 initial_units, acpi_handle * out_handle) +{ + *out_handle = (acpi_handle) 1; + return (AE_OK); +} + +acpi_status acpi_os_delete_semaphore(acpi_handle handle) +{ + return (AE_OK); +} + +acpi_status acpi_os_wait_semaphore(acpi_handle handle, u32 units, u16 timeout) +{ + return (AE_OK); +} + +acpi_status acpi_os_signal_semaphore(acpi_handle handle, u32 units) +{ + return (AE_OK); +} + +#else +/****************************************************************************** + * + * FUNCTION: acpi_os_create_semaphore + * + * PARAMETERS: initial_units - Units to be assigned to the new semaphore + * out_handle - Where a handle will be returned + * + * RETURN: Status + * + * DESCRIPTION: Create an OS semaphore + * + *****************************************************************************/ + +acpi_status +acpi_os_create_semaphore(u32 max_units, + u32 initial_units, acpi_handle * out_handle) +{ + sem_t *sem; + + if (!out_handle) { + return (AE_BAD_PARAMETER); + } +#ifdef __APPLE__ + { + char *semaphore_name = tmpnam(NULL); + + sem = + sem_open(semaphore_name, O_EXCL | O_CREAT, 0755, + initial_units); + if (!sem) { + return (AE_NO_MEMORY); + } + sem_unlink(semaphore_name); /* This just deletes the name */ + } + +#else + sem = acpi_os_allocate(sizeof(sem_t)); + if (!sem) { + return (AE_NO_MEMORY); + } + + if (sem_init(sem, 0, initial_units) == -1) { + acpi_os_free(sem); + return (AE_BAD_PARAMETER); + } +#endif + + *out_handle = (acpi_handle) sem; + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_delete_semaphore + * + * PARAMETERS: handle - Handle returned by acpi_os_create_semaphore + * + * RETURN: Status + * + * DESCRIPTION: Delete an OS semaphore + * + *****************************************************************************/ + +acpi_status acpi_os_delete_semaphore(acpi_handle handle) +{ + sem_t *sem = (sem_t *) handle; + + if (!sem) { + return (AE_BAD_PARAMETER); + } + + if (sem_destroy(sem) == -1) { + return (AE_BAD_PARAMETER); + } + + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_wait_semaphore + * + * PARAMETERS: handle - Handle returned by acpi_os_create_semaphore + * units - How many units to wait for + * msec_timeout - How long to wait (milliseconds) + * + * RETURN: Status + * + * DESCRIPTION: Wait for units + * + *****************************************************************************/ + +acpi_status +acpi_os_wait_semaphore(acpi_handle handle, u32 units, u16 msec_timeout) +{ + acpi_status status = AE_OK; + sem_t *sem = (sem_t *) handle; +#ifndef ACPI_USE_ALTERNATE_TIMEOUT + struct timespec time; + int ret_val; +#endif + + if (!sem) { + return (AE_BAD_PARAMETER); + } + + switch (msec_timeout) { + /* + * No Wait: + * -------- + * A zero timeout value indicates that we shouldn't wait - just + * acquire the semaphore if available otherwise return AE_TIME + * (a.k.a. 'would block'). + */ + case 0: + + if (sem_trywait(sem) == -1) { + status = (AE_TIME); + } + break; + + /* Wait Indefinitely */ + + case ACPI_WAIT_FOREVER: + + if (sem_wait(sem)) { + status = (AE_TIME); + } + break; + + /* Wait with msec_timeout */ + + default: + +#ifdef ACPI_USE_ALTERNATE_TIMEOUT + /* + * Alternate timeout mechanism for environments where + * sem_timedwait is not available or does not work properly. + */ + while (msec_timeout) { + if (sem_trywait(sem) == 0) { + + /* Got the semaphore */ + return (AE_OK); + } + + if (msec_timeout >= 10) { + msec_timeout -= 10; + usleep(10 * ACPI_USEC_PER_MSEC); /* ten milliseconds */ + } else { + msec_timeout--; + usleep(ACPI_USEC_PER_MSEC); /* one millisecond */ + } + } + status = (AE_TIME); +#else + /* + * The interface to sem_timedwait is an absolute time, so we need to + * get the current time, then add in the millisecond Timeout value. + */ + if (clock_gettime(CLOCK_REALTIME, &time) == -1) { + perror("clock_gettime"); + return (AE_TIME); + } + + time.tv_sec += (msec_timeout / ACPI_MSEC_PER_SEC); + time.tv_nsec += + ((msec_timeout % ACPI_MSEC_PER_SEC) * ACPI_NSEC_PER_MSEC); + + /* Handle nanosecond overflow (field must be less than one second) */ + + if (time.tv_nsec >= ACPI_NSEC_PER_SEC) { + time.tv_sec += (time.tv_nsec / ACPI_NSEC_PER_SEC); + time.tv_nsec = (time.tv_nsec % ACPI_NSEC_PER_SEC); + } + + while (((ret_val = sem_timedwait(sem, &time)) == -1) + && (errno == EINTR)) { + continue; + } + + if (ret_val != 0) { + if (errno != ETIMEDOUT) { + perror("sem_timedwait"); + } + status = (AE_TIME); + } +#endif + break; + } + + return (status); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_signal_semaphore + * + * PARAMETERS: handle - Handle returned by acpi_os_create_semaphore + * units - Number of units to send + * + * RETURN: Status + * + * DESCRIPTION: Send units + * + *****************************************************************************/ + +acpi_status acpi_os_signal_semaphore(acpi_handle handle, u32 units) +{ + sem_t *sem = (sem_t *) handle; + + if (!sem) { + return (AE_BAD_PARAMETER); + } + + if (sem_post(sem) == -1) { + return (AE_LIMIT); + } + + return (AE_OK); +} + +#endif /* ACPI_SINGLE_THREADED */ + +/****************************************************************************** + * + * FUNCTION: Spinlock interfaces + * + * DESCRIPTION: Map these interfaces to semaphore interfaces + * + *****************************************************************************/ + +acpi_status acpi_os_create_lock(acpi_spinlock * out_handle) +{ + + return (acpi_os_create_semaphore(1, 1, out_handle)); +} + +void acpi_os_delete_lock(acpi_spinlock handle) +{ + acpi_os_delete_semaphore(handle); +} + +acpi_cpu_flags acpi_os_acquire_lock(acpi_handle handle) +{ + acpi_os_wait_semaphore(handle, 1, 0xFFFF); + return (0); +} + +void acpi_os_release_lock(acpi_spinlock handle, acpi_cpu_flags flags) +{ + acpi_os_signal_semaphore(handle, 1); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_install_interrupt_handler + * + * PARAMETERS: interrupt_number - Level handler should respond to. + * isr - Address of the ACPI interrupt handler + * except_ptr - Where status is returned + * + * RETURN: Handle to the newly installed handler. + * + * DESCRIPTION: Install an interrupt handler. Used to install the ACPI + * OS-independent handler. + * + *****************************************************************************/ + +u32 +acpi_os_install_interrupt_handler(u32 interrupt_number, + acpi_osd_handler service_routine, + void *context) +{ + + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_remove_interrupt_handler + * + * PARAMETERS: handle - Returned when handler was installed + * + * RETURN: Status + * + * DESCRIPTION: Uninstalls an interrupt handler. + * + *****************************************************************************/ + +acpi_status +acpi_os_remove_interrupt_handler(u32 interrupt_number, + acpi_osd_handler service_routine) +{ + + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_stall + * + * PARAMETERS: microseconds - Time to sleep + * + * RETURN: Blocks until sleep is completed. + * + * DESCRIPTION: Sleep at microsecond granularity + * + *****************************************************************************/ + +void acpi_os_stall(u32 microseconds) +{ + + if (microseconds) { + usleep(microseconds); + } +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_sleep + * + * PARAMETERS: milliseconds - Time to sleep + * + * RETURN: Blocks until sleep is completed. + * + * DESCRIPTION: Sleep at millisecond granularity + * + *****************************************************************************/ + +void acpi_os_sleep(u64 milliseconds) +{ + + /* Sleep for whole seconds */ + + sleep(milliseconds / ACPI_MSEC_PER_SEC); + + /* + * Sleep for remaining microseconds. + * Arg to usleep() is in usecs and must be less than 1,000,000 (1 second). + */ + usleep((milliseconds % ACPI_MSEC_PER_SEC) * ACPI_USEC_PER_MSEC); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_get_timer + * + * PARAMETERS: None + * + * RETURN: Current time in 100 nanosecond units + * + * DESCRIPTION: Get the current system time + * + *****************************************************************************/ + +u64 acpi_os_get_timer(void) +{ + struct timeval time; + + /* This timer has sufficient resolution for user-space application code */ + + gettimeofday(&time, NULL); + + /* (Seconds * 10^7 = 100ns(10^-7)) + (Microseconds(10^-6) * 10^1 = 100ns) */ + + return (((u64)time.tv_sec * ACPI_100NSEC_PER_SEC) + + ((u64)time.tv_usec * ACPI_100NSEC_PER_USEC)); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_read_pci_configuration + * + * PARAMETERS: pci_id - Seg/Bus/Dev + * pci_register - Device Register + * value - Buffer where value is placed + * width - Number of bits + * + * RETURN: Status + * + * DESCRIPTION: Read data from PCI configuration space + * + *****************************************************************************/ + +acpi_status +acpi_os_read_pci_configuration(struct acpi_pci_id *pci_id, + u32 pci_register, u64 *value, u32 width) +{ + + *value = 0; + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_write_pci_configuration + * + * PARAMETERS: pci_id - Seg/Bus/Dev + * pci_register - Device Register + * value - Value to be written + * width - Number of bits + * + * RETURN: Status. + * + * DESCRIPTION: Write data to PCI configuration space + * + *****************************************************************************/ + +acpi_status +acpi_os_write_pci_configuration(struct acpi_pci_id * pci_id, + u32 pci_register, u64 value, u32 width) +{ + + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_read_port + * + * PARAMETERS: address - Address of I/O port/register to read + * value - Where value is placed + * width - Number of bits + * + * RETURN: Value read from port + * + * DESCRIPTION: Read data from an I/O port or register + * + *****************************************************************************/ + +acpi_status acpi_os_read_port(acpi_io_address address, u32 *value, u32 width) +{ + + switch (width) { + case 8: + + *value = 0xFF; + break; + + case 16: + + *value = 0xFFFF; + break; + + case 32: + + *value = 0xFFFFFFFF; + break; + + default: + + return (AE_BAD_PARAMETER); + } + + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_write_port + * + * PARAMETERS: address - Address of I/O port/register to write + * value - Value to write + * width - Number of bits + * + * RETURN: None + * + * DESCRIPTION: Write data to an I/O port or register + * + *****************************************************************************/ + +acpi_status acpi_os_write_port(acpi_io_address address, u32 value, u32 width) +{ + + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_read_memory + * + * PARAMETERS: address - Physical Memory Address to read + * value - Where value is placed + * width - Number of bits (8,16,32, or 64) + * + * RETURN: Value read from physical memory address. Always returned + * as a 64-bit integer, regardless of the read width. + * + * DESCRIPTION: Read data from a physical memory address + * + *****************************************************************************/ + +acpi_status +acpi_os_read_memory(acpi_physical_address address, u64 *value, u32 width) +{ + + switch (width) { + case 8: + case 16: + case 32: + case 64: + + *value = 0; + break; + + default: + + return (AE_BAD_PARAMETER); + } + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_write_memory + * + * PARAMETERS: address - Physical Memory Address to write + * value - Value to write + * width - Number of bits (8,16,32, or 64) + * + * RETURN: None + * + * DESCRIPTION: Write data to a physical memory address + * + *****************************************************************************/ + +acpi_status +acpi_os_write_memory(acpi_physical_address address, u64 value, u32 width) +{ + + return (AE_OK); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_readable + * + * PARAMETERS: pointer - Area to be verified + * length - Size of area + * + * RETURN: TRUE if readable for entire length + * + * DESCRIPTION: Verify that a pointer is valid for reading + * + *****************************************************************************/ + +u8 acpi_os_readable(void *pointer, acpi_size length) +{ + + return (TRUE); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_writable + * + * PARAMETERS: pointer - Area to be verified + * length - Size of area + * + * RETURN: TRUE if writable for entire length + * + * DESCRIPTION: Verify that a pointer is valid for writing + * + *****************************************************************************/ + +u8 acpi_os_writable(void *pointer, acpi_size length) +{ + + return (TRUE); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_signal + * + * PARAMETERS: function - ACPI A signal function code + * info - Pointer to function-dependent structure + * + * RETURN: Status + * + * DESCRIPTION: Miscellaneous functions. Example implementation only. + * + *****************************************************************************/ + +acpi_status acpi_os_signal(u32 function, void *info) +{ + + switch (function) { + case ACPI_SIGNAL_FATAL: + + break; + + case ACPI_SIGNAL_BREAKPOINT: + + break; + + default: + + break; + } + + return (AE_OK); +} + +/* Optional multi-thread support */ + +#ifndef ACPI_SINGLE_THREADED +/****************************************************************************** + * + * FUNCTION: acpi_os_get_thread_id + * + * PARAMETERS: None + * + * RETURN: Id of the running thread + * + * DESCRIPTION: Get the ID of the current (running) thread + * + *****************************************************************************/ + +acpi_thread_id acpi_os_get_thread_id(void) +{ + pthread_t thread; + + thread = pthread_self(); + return (ACPI_CAST_PTHREAD_T(thread)); +} + +/****************************************************************************** + * + * FUNCTION: acpi_os_execute + * + * PARAMETERS: type - Type of execution + * function - Address of the function to execute + * context - Passed as a parameter to the function + * + * RETURN: Status. + * + * DESCRIPTION: Execute a new thread + * + *****************************************************************************/ + +acpi_status +acpi_os_execute(acpi_execute_type type, + acpi_osd_exec_callback function, void *context) +{ + pthread_t thread; + int ret; + + ret = + pthread_create(&thread, NULL, (PTHREAD_CALLBACK) function, context); + if (ret) { + acpi_os_printf("Create thread failed"); + } + return (0); +} + +#else /* ACPI_SINGLE_THREADED */ +acpi_thread_id acpi_os_get_thread_id(void) +{ + return (1); +} + +acpi_status +acpi_os_execute(acpi_execute_type type, + acpi_osd_exec_callback function, void *context) +{ + + function(context); + + return (AE_OK); +} + +#endif /* ACPI_SINGLE_THREADED */ + +/****************************************************************************** + * + * FUNCTION: acpi_os_wait_events_complete + * + * PARAMETERS: None + * + * RETURN: None + * + * DESCRIPTION: Wait for all asynchronous events to complete. This + * implementation does nothing. + * + *****************************************************************************/ + +void acpi_os_wait_events_complete(void) +{ + return; +} diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h index 46f5195..a2d37d6 100644 --- a/tools/power/acpi/tools/acpidump/acpidump.h +++ b/tools/power/acpi/tools/acpidump/acpidump.h @@ -47,7 +47,6 @@ #ifdef _DECLARE_GLOBALS #define EXTERN #define INIT_GLOBAL(a,b) a=b -#define DEFINE_ACPI_GLOBALS 1 #else #define EXTERN extern #define INIT_GLOBAL(a,b) a @@ -69,7 +68,7 @@ EXTERN u8 INIT_GLOBAL(gbl_verbose_mode, FALSE); EXTERN u8 INIT_GLOBAL(gbl_binary_mode, FALSE); EXTERN u8 INIT_GLOBAL(gbl_dump_customized_tables, FALSE); EXTERN u8 INIT_GLOBAL(gbl_do_not_dump_xsdt, FALSE); -EXTERN FILE INIT_GLOBAL(*gbl_output_file, NULL); +EXTERN ACPI_FILE INIT_GLOBAL(gbl_output_file, NULL); EXTERN char INIT_GLOBAL(*gbl_output_filename, NULL); EXTERN u64 INIT_GLOBAL(gbl_rsdp_base, 0); diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c index 3cac123..24d32968 100644 --- a/tools/power/acpi/tools/acpidump/apdump.c +++ b/tools/power/acpi/tools/acpidump/apdump.c @@ -69,17 +69,16 @@ u8 ap_is_valid_header(struct acpi_table_header *table) /* Make sure signature is all ASCII and a valid ACPI name */ if (!acpi_ut_valid_acpi_name(table->signature)) { - fprintf(stderr, - "Table signature (0x%8.8X) is invalid\n", - *(u32 *)table->signature); + acpi_log_error("Table signature (0x%8.8X) is invalid\n", + *(u32 *)table->signature); return (FALSE); } /* Check for minimum table length */ if (table->length < sizeof(struct acpi_table_header)) { - fprintf(stderr, "Table length (0x%8.8X) is invalid\n", - table->length); + acpi_log_error("Table length (0x%8.8X) is invalid\n", + table->length); return (FALSE); } } @@ -116,8 +115,8 @@ u8 ap_is_valid_checksum(struct acpi_table_header *table) } if (ACPI_FAILURE(status)) { - fprintf(stderr, "%4.4s: Warning: wrong checksum in table\n", - table->signature); + acpi_log_error("%4.4s: Warning: wrong checksum in table\n", + table->signature); } return (AE_OK); @@ -147,7 +146,7 @@ u32 ap_get_table_length(struct acpi_table_header *table) if (ACPI_VALIDATE_RSDP_SIG(table->signature)) { rsdp = ACPI_CAST_PTR(struct acpi_table_rsdp, table); - return (rsdp->length); + return (acpi_tb_get_rsdp_length(rsdp)); } /* Normal ACPI table */ @@ -196,12 +195,13 @@ ap_dump_table_buffer(struct acpi_table_header *table, * Note: simplest to just always emit a 64-bit address. acpi_xtract * utility can handle this. */ - printf("%4.4s @ 0x%8.8X%8.8X\n", table->signature, - ACPI_FORMAT_UINT64(address)); + acpi_ut_file_printf(gbl_output_file, "%4.4s @ 0x%8.8X%8.8X\n", + table->signature, ACPI_FORMAT_UINT64(address)); - acpi_ut_dump_buffer(ACPI_CAST_PTR(u8, table), table_length, - DB_BYTE_DISPLAY, 0); - printf("\n"); + acpi_ut_dump_buffer_to_file(gbl_output_file, + ACPI_CAST_PTR(u8, table), table_length, + DB_BYTE_DISPLAY, 0); + acpi_ut_file_printf(gbl_output_file, "\n"); return (0); } @@ -239,20 +239,20 @@ int ap_dump_all_tables(void) if (status == AE_LIMIT) { return (0); } else if (i == 0) { - fprintf(stderr, - "Could not get ACPI tables, %s\n", - acpi_format_exception(status)); + acpi_log_error + ("Could not get ACPI tables, %s\n", + acpi_format_exception(status)); return (-1); } else { - fprintf(stderr, - "Could not get ACPI table at index %u, %s\n", - i, acpi_format_exception(status)); + acpi_log_error + ("Could not get ACPI table at index %u, %s\n", + i, acpi_format_exception(status)); continue; } } table_status = ap_dump_table_buffer(table, instance, address); - free(table); + ACPI_FREE(table); if (table_status) { break; @@ -288,22 +288,22 @@ int ap_dump_table_by_address(char *ascii_address) status = acpi_ut_strtoul64(ascii_address, 0, &long_address); if (ACPI_FAILURE(status)) { - fprintf(stderr, "%s: Could not convert to a physical address\n", - ascii_address); + acpi_log_error("%s: Could not convert to a physical address\n", + ascii_address); return (-1); } address = (acpi_physical_address) long_address; status = acpi_os_get_table_by_address(address, &table); if (ACPI_FAILURE(status)) { - fprintf(stderr, "Could not get table at 0x%8.8X%8.8X, %s\n", - ACPI_FORMAT_UINT64(address), - acpi_format_exception(status)); + acpi_log_error("Could not get table at 0x%8.8X%8.8X, %s\n", + ACPI_FORMAT_UINT64(address), + acpi_format_exception(status)); return (-1); } table_status = ap_dump_table_buffer(table, 0, address); - free(table); + ACPI_FREE(table); return (table_status); } @@ -329,24 +329,24 @@ int ap_dump_table_by_name(char *signature) acpi_status status; int table_status; - if (strlen(signature) != ACPI_NAME_SIZE) { - fprintf(stderr, - "Invalid table signature [%s]: must be exactly 4 characters\n", - signature); + if (ACPI_STRLEN(signature) != ACPI_NAME_SIZE) { + acpi_log_error + ("Invalid table signature [%s]: must be exactly 4 characters\n", + signature); return (-1); } /* Table signatures are expected to be uppercase */ - strcpy(local_signature, signature); + ACPI_STRCPY(local_signature, signature); acpi_ut_strupr(local_signature); /* To be friendly, handle tables whose signatures do not match the name */ if (ACPI_COMPARE_NAME(local_signature, "FADT")) { - strcpy(local_signature, ACPI_SIG_FADT); + ACPI_STRCPY(local_signature, ACPI_SIG_FADT); } else if (ACPI_COMPARE_NAME(local_signature, "MADT")) { - strcpy(local_signature, ACPI_SIG_MADT); + ACPI_STRCPY(local_signature, ACPI_SIG_MADT); } /* Dump all instances of this signature (to handle multiple SSDTs) */ @@ -362,14 +362,14 @@ int ap_dump_table_by_name(char *signature) return (0); } - fprintf(stderr, - "Could not get ACPI table with signature [%s], %s\n", - local_signature, acpi_format_exception(status)); + acpi_log_error + ("Could not get ACPI table with signature [%s], %s\n", + local_signature, acpi_format_exception(status)); return (-1); } table_status = ap_dump_table_buffer(table, instance, address); - free(table); + ACPI_FREE(table); if (table_status) { break; @@ -409,43 +409,21 @@ int ap_dump_table_from_file(char *pathname) /* File must be at least as long as the table length */ if (table->length > file_size) { - fprintf(stderr, - "Table length (0x%X) is too large for input file (0x%X) %s\n", - table->length, file_size, pathname); + acpi_log_error + ("Table length (0x%X) is too large for input file (0x%X) %s\n", + table->length, file_size, pathname); goto exit; } if (gbl_verbose_mode) { - fprintf(stderr, - "Input file: %s contains table [%4.4s], 0x%X (%u) bytes\n", - pathname, table->signature, file_size, file_size); + acpi_log_error + ("Input file: %s contains table [%4.4s], 0x%X (%u) bytes\n", + pathname, table->signature, file_size, file_size); } table_status = ap_dump_table_buffer(table, 0, 0); exit: - free(table); + ACPI_FREE(table); return (table_status); } - -/****************************************************************************** - * - * FUNCTION: acpi_os* print functions - * - * DESCRIPTION: Used for linkage with ACPICA modules - * - ******************************************************************************/ - -void ACPI_INTERNAL_VAR_XFACE acpi_os_printf(const char *fmt, ...) -{ - va_list args; - - va_start(args, fmt); - vfprintf(stdout, fmt, args); - va_end(args); -} - -void acpi_os_vprintf(const char *fmt, va_list args) -{ - vfprintf(stdout, fmt, args); -} diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c index 4488acc..d470046 100644 --- a/tools/power/acpi/tools/acpidump/apfiles.c +++ b/tools/power/acpi/tools/acpidump/apfiles.c @@ -44,6 +44,27 @@ #include "acpidump.h" #include "acapps.h" +/* Local prototypes */ + +static int ap_is_existing_file(char *pathname); + +static int ap_is_existing_file(char *pathname) +{ +#ifndef _GNU_EFI + struct stat stat_info; + + if (!stat(pathname, &stat_info)) { + acpi_log_error("Target path already exists, overwrite? [y|n] "); + + if (getchar() != 'y') { + return (-1); + } + } +#endif + + return 0; +} + /****************************************************************************** * * FUNCTION: ap_open_output_file @@ -59,25 +80,19 @@ int ap_open_output_file(char *pathname) { - struct stat stat_info; - FILE *file; + ACPI_FILE file; /* If file exists, prompt for overwrite */ - if (!stat(pathname, &stat_info)) { - fprintf(stderr, - "Target path already exists, overwrite? [y|n] "); - - if (getchar() != 'y') { - return (-1); - } + if (ap_is_existing_file(pathname) != 0) { + return (-1); } /* Point stdout to the file */ - file = freopen(pathname, "w", stdout); + file = acpi_os_open_file(pathname, ACPI_FILE_WRITING); if (!file) { - perror("Could not open output file"); + acpi_log_error("Could not open output file: %s\n", pathname); return (-1); } @@ -106,7 +121,7 @@ int ap_write_to_binary_file(struct acpi_table_header *table, u32 instance) { char filename[ACPI_NAME_SIZE + 16]; char instance_str[16]; - FILE *file; + ACPI_FILE file; size_t actual; u32 table_length; @@ -130,35 +145,37 @@ int ap_write_to_binary_file(struct acpi_table_header *table, u32 instance) /* Handle multiple SSDts - create different filenames for each */ if (instance > 0) { - sprintf(instance_str, "%u", instance); - strcat(filename, instance_str); + acpi_ut_snprintf(instance_str, sizeof(instance_str), "%u", + instance); + ACPI_STRCAT(filename, instance_str); } - strcat(filename, ACPI_TABLE_FILE_SUFFIX); + ACPI_STRCAT(filename, ACPI_TABLE_FILE_SUFFIX); if (gbl_verbose_mode) { - fprintf(stderr, - "Writing [%4.4s] to binary file: %s 0x%X (%u) bytes\n", - table->signature, filename, table->length, - table->length); + acpi_log_error + ("Writing [%4.4s] to binary file: %s 0x%X (%u) bytes\n", + table->signature, filename, table->length, table->length); } /* Open the file and dump the entire table in binary mode */ - file = fopen(filename, "wb"); + file = acpi_os_open_file(filename, + ACPI_FILE_WRITING | ACPI_FILE_BINARY); if (!file) { - perror("Could not open output file"); + acpi_log_error("Could not open output file: %s\n", filename); return (-1); } - actual = fwrite(table, 1, table_length, file); + actual = acpi_os_write_file(file, table, 1, table_length); if (actual != table_length) { - perror("Error writing binary output file"); - fclose(file); + acpi_log_error("Error writing binary output file: %s\n", + filename); + acpi_os_close_file(file); return (-1); } - fclose(file); + acpi_os_close_file(file); return (0); } @@ -179,15 +196,16 @@ struct acpi_table_header *ap_get_table_from_file(char *pathname, u32 *out_file_size) { struct acpi_table_header *buffer = NULL; - FILE *file; + ACPI_FILE file; u32 file_size; size_t actual; /* Must use binary mode */ - file = fopen(pathname, "rb"); + file = + acpi_os_open_file(pathname, ACPI_FILE_READING | ACPI_FILE_BINARY); if (!file) { - perror("Could not open input file"); + acpi_log_error("Could not open input file: %s\n", pathname); return (NULL); } @@ -195,27 +213,25 @@ struct acpi_table_header *ap_get_table_from_file(char *pathname, file_size = cm_get_file_size(file); if (file_size == ACPI_UINT32_MAX) { - fprintf(stderr, - "Could not get input file size: %s\n", pathname); + acpi_log_error("Could not get input file size: %s\n", pathname); goto cleanup; } /* Allocate a buffer for the entire file */ - buffer = calloc(1, file_size); + buffer = ACPI_ALLOCATE_ZEROED(file_size); if (!buffer) { - fprintf(stderr, - "Could not allocate file buffer of size: %u\n", - file_size); + acpi_log_error("Could not allocate file buffer of size: %u\n", + file_size); goto cleanup; } /* Read the entire file */ - actual = fread(buffer, 1, file_size, file); + actual = acpi_os_read_file(file, buffer, 1, file_size); if (actual != file_size) { - fprintf(stderr, "Could not read input file: %s\n", pathname); - free(buffer); + acpi_log_error("Could not read input file: %s\n", pathname); + ACPI_FREE(buffer); buffer = NULL; goto cleanup; } @@ -223,6 +239,6 @@ struct acpi_table_header *ap_get_table_from_file(char *pathname, *out_file_size = file_size; cleanup: - fclose(file); + acpi_os_close_file(file); return (buffer); } diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index 51e8d63..853b4da 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -72,7 +72,7 @@ static void ap_display_usage(void); static int ap_do_options(int argc, char **argv); -static void ap_insert_action(char *argument, u32 to_be_done); +static int ap_insert_action(char *argument, u32 to_be_done); /* Table for deferred actions from command line options */ @@ -104,7 +104,7 @@ static void ap_display_usage(void) ACPI_OPTION("-v", "Display version information"); ACPI_OPTION("-z", "Verbose mode"); - printf("\nTable Options:\n"); + ACPI_USAGE_TEXT("\nTable Options:\n"); ACPI_OPTION("-a <Address>", "Get table via a physical address"); ACPI_OPTION("-f <BinaryFile>", "Get table via a binary file"); @@ -112,9 +112,9 @@ static void ap_display_usage(void) ACPI_OPTION("-x", "Do not use but dump XSDT"); ACPI_OPTION("-x -x", "Do not use or dump XSDT"); - printf("\n" - "Invocation without parameters dumps all available tables\n" - "Multiple mixed instances of -a, -f, and -n are supported\n\n"); + ACPI_USAGE_TEXT("\n" + "Invocation without parameters dumps all available tables\n" + "Multiple mixed instances of -a, -f, and -n are supported\n\n"); } /****************************************************************************** @@ -124,13 +124,13 @@ static void ap_display_usage(void) * PARAMETERS: argument - Pointer to the argument for this action * to_be_done - What to do to process this action * - * RETURN: None. Exits program if action table becomes full. + * RETURN: Status * * DESCRIPTION: Add an action item to the action table * ******************************************************************************/ -static void ap_insert_action(char *argument, u32 to_be_done) +static int ap_insert_action(char *argument, u32 to_be_done) { /* Insert action and check for table overflow */ @@ -140,10 +140,12 @@ static void ap_insert_action(char *argument, u32 to_be_done) current_action++; if (current_action > AP_MAX_ACTIONS) { - fprintf(stderr, "Too many table options (max %u)\n", - AP_MAX_ACTIONS); - exit(-1); + acpi_log_error("Too many table options (max %u)\n", + AP_MAX_ACTIONS); + return (-1); } + + return (0); } /****************************************************************************** @@ -166,7 +168,8 @@ static int ap_do_options(int argc, char **argv) /* Command line options */ - while ((j = acpi_getopt(argc, argv, AP_SUPPORTED_OPTIONS)) != EOF) + while ((j = + acpi_getopt(argc, argv, AP_SUPPORTED_OPTIONS)) != ACPI_OPT_END) switch (j) { /* * Global options @@ -185,12 +188,12 @@ static int ap_do_options(int argc, char **argv) case '?': ap_display_usage(); - exit(0); + return (1); case 'o': /* Redirect output to a single file */ if (ap_open_output_file(acpi_gbl_optarg)) { - exit(-1); + return (-1); } continue; @@ -200,10 +203,10 @@ static int ap_do_options(int argc, char **argv) acpi_ut_strtoul64(acpi_gbl_optarg, 0, &gbl_rsdp_base); if (ACPI_FAILURE(status)) { - fprintf(stderr, - "%s: Could not convert to a physical address\n", - acpi_gbl_optarg); - exit(-1); + acpi_log_error + ("%s: Could not convert to a physical address\n", + acpi_gbl_optarg); + return (-1); } continue; @@ -223,13 +226,13 @@ static int ap_do_options(int argc, char **argv) case 'v': /* Revision/version */ - printf(ACPI_COMMON_SIGNON(AP_UTILITY_NAME)); - exit(0); + acpi_os_printf(ACPI_COMMON_SIGNON(AP_UTILITY_NAME)); + return (1); case 'z': /* Verbose mode */ gbl_verbose_mode = TRUE; - fprintf(stderr, ACPI_COMMON_SIGNON(AP_UTILITY_NAME)); + acpi_log_error(ACPI_COMMON_SIGNON(AP_UTILITY_NAME)); continue; /* @@ -237,32 +240,40 @@ static int ap_do_options(int argc, char **argv) */ case 'a': /* Get table by physical address */ - ap_insert_action(acpi_gbl_optarg, - AP_DUMP_TABLE_BY_ADDRESS); + if (ap_insert_action + (acpi_gbl_optarg, AP_DUMP_TABLE_BY_ADDRESS)) { + return (-1); + } break; case 'f': /* Get table from a file */ - ap_insert_action(acpi_gbl_optarg, - AP_DUMP_TABLE_BY_FILE); + if (ap_insert_action + (acpi_gbl_optarg, AP_DUMP_TABLE_BY_FILE)) { + return (-1); + } break; case 'n': /* Get table by input name (signature) */ - ap_insert_action(acpi_gbl_optarg, - AP_DUMP_TABLE_BY_NAME); + if (ap_insert_action + (acpi_gbl_optarg, AP_DUMP_TABLE_BY_NAME)) { + return (-1); + } break; default: ap_display_usage(); - exit(-1); + return (-1); } /* If there are no actions, this means "get/dump all tables" */ if (current_action == 0) { - ap_insert_action(NULL, AP_DUMP_ALL_TABLES); + if (ap_insert_action(NULL, AP_DUMP_ALL_TABLES)) { + return (-1); + } } return (0); @@ -280,7 +291,11 @@ static int ap_do_options(int argc, char **argv) * ******************************************************************************/ +#ifndef _GNU_EFI int ACPI_SYSTEM_XFACE main(int argc, char *argv[]) +#else +int ACPI_SYSTEM_XFACE acpi_main(int argc, char *argv[]) +#endif { int status = 0; struct ap_dump_action *action; @@ -288,11 +303,17 @@ int ACPI_SYSTEM_XFACE main(int argc, char *argv[]) u32 i; ACPI_DEBUG_INITIALIZE(); /* For debug version only */ + acpi_os_initialize(); + gbl_output_file = ACPI_FILE_OUT; /* Process command line options */ - if (ap_do_options(argc, argv)) { - return (-1); + status = ap_do_options(argc, argv); + if (status > 0) { + return (0); + } + if (status < 0) { + return (status); } /* Get/dump ACPI table(s) as requested */ @@ -322,9 +343,8 @@ int ACPI_SYSTEM_XFACE main(int argc, char *argv[]) default: - fprintf(stderr, - "Internal error, invalid action: 0x%X\n", - action->to_be_done); + acpi_log_error("Internal error, invalid action: 0x%X\n", + action->to_be_done); return (-1); } @@ -333,18 +353,18 @@ int ACPI_SYSTEM_XFACE main(int argc, char *argv[]) } } - if (gbl_output_file) { + if (gbl_output_filename) { if (gbl_verbose_mode) { /* Summary for the output file */ file_size = cm_get_file_size(gbl_output_file); - fprintf(stderr, - "Output file %s contains 0x%X (%u) bytes\n\n", - gbl_output_filename, file_size, file_size); + acpi_log_error + ("Output file %s contains 0x%X (%u) bytes\n\n", + gbl_output_filename, file_size, file_size); } - fclose(gbl_output_file); + acpi_os_close_file(gbl_output_file); } return (status); diff --git a/tools/power/cpupower/bench/parse.c b/tools/power/cpupower/bench/parse.c index 543bba1..f503fb5 100644 --- a/tools/power/cpupower/bench/parse.c +++ b/tools/power/cpupower/bench/parse.c @@ -158,14 +158,15 @@ struct config *prepare_default_config() int prepare_config(const char *path, struct config *config) { size_t len = 0; - char *opt, *val, *line = NULL; - FILE *configfile = fopen(path, "r"); + char opt[16], val[32], *line = NULL; + FILE *configfile; if (config == NULL) { fprintf(stderr, "error: config is NULL\n"); return 1; } + configfile = fopen(path, "r"); if (configfile == NULL) { perror("fopen"); fprintf(stderr, "error: unable to read configfile\n"); @@ -174,52 +175,54 @@ int prepare_config(const char *path, struct config *config) } while (getline(&line, &len, configfile) != -1) { - if (line[0] == '#' || line[0] == ' ') + if (line[0] == '#' || line[0] == ' ' || line[0] == '\n') continue; - sscanf(line, "%as = %as", &opt, &val); + if (sscanf(line, "%14s = %30s", opt, val) < 2) + continue; dprintf("parsing: %s -> %s\n", opt, val); - if (strncmp("sleep", opt, strlen(opt)) == 0) + if (strcmp("sleep", opt) == 0) sscanf(val, "%li", &config->sleep); - else if (strncmp("load", opt, strlen(opt)) == 0) + else if (strcmp("load", opt) == 0) sscanf(val, "%li", &config->load); - else if (strncmp("load_step", opt, strlen(opt)) == 0) + else if (strcmp("load_step", opt) == 0) sscanf(val, "%li", &config->load_step); - else if (strncmp("sleep_step", opt, strlen(opt)) == 0) + else if (strcmp("sleep_step", opt) == 0) sscanf(val, "%li", &config->sleep_step); - else if (strncmp("cycles", opt, strlen(opt)) == 0) + else if (strcmp("cycles", opt) == 0) sscanf(val, "%u", &config->cycles); - else if (strncmp("rounds", opt, strlen(opt)) == 0) + else if (strcmp("rounds", opt) == 0) sscanf(val, "%u", &config->rounds); - else if (strncmp("verbose", opt, strlen(opt)) == 0) + else if (strcmp("verbose", opt) == 0) sscanf(val, "%u", &config->verbose); - else if (strncmp("output", opt, strlen(opt)) == 0) + else if (strcmp("output", opt) == 0) config->output = prepare_output(val); - else if (strncmp("cpu", opt, strlen(opt)) == 0) + else if (strcmp("cpu", opt) == 0) sscanf(val, "%u", &config->cpu); - else if (strncmp("governor", opt, 14) == 0) - strncpy(config->governor, val, 14); + else if (strcmp("governor", opt) == 0) { + strncpy(config->governor, val, + sizeof(config->governor)); + config->governor[sizeof(config->governor) - 1] = '\0'; + } - else if (strncmp("priority", opt, strlen(opt)) == 0) { + else if (strcmp("priority", opt) == 0) { if (string_to_prio(val) != SCHED_ERR) config->prio = string_to_prio(val); } } free(line); - free(opt); - free(val); return 0; } diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c index a416de8..f656e58 100644 --- a/tools/power/cpupower/utils/cpufreq-set.c +++ b/tools/power/cpupower/utils/cpufreq-set.c @@ -320,12 +320,11 @@ int cmd_freq_set(int argc, char **argv) printf(_("Setting cpu: %d\n"), cpu); ret = do_one_cpu(cpu, &new_pol, freq, policychange); - if (ret) - break; + if (ret) { + print_error(); + return ret; + } } - if (ret) - print_error(); - - return ret; + return 0; } diff --git a/tools/power/cpupower/utils/cpupower.c b/tools/power/cpupower/utils/cpupower.c index 7cdcf88..9ea9143 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 851c7a1..4e8fe2c 100644 --- a/tools/power/cpupower/utils/helpers/sysfs.c +++ b/tools/power/cpupower/utils/helpers/sysfs.c @@ -81,7 +81,7 @@ int sysfs_is_cpu_online(unsigned int cpu) close(fd); value = strtoull(linebuf, &endp, 0); - if (value > 1 || value < 0) + if (value > 1) return -EINVAL; return value; @@ -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/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index 5650ab5..90a8c4f 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -237,7 +237,7 @@ static int init_maxfreq_mode(void) unsigned long long hwcr; unsigned long min; - if (!cpupower_cpu_info.caps & CPUPOWER_CAP_INV_TSC) + if (!(cpupower_cpu_info.caps & CPUPOWER_CAP_INV_TSC)) goto use_sysfs; if (cpupower_cpu_info.vendor == X86_VENDOR_AMD) { diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index d0396af..5b1b807 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -267,90 +267,90 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) /* * Example Format w/ field column widths: * - * Package Core CPU Avg_MHz Bzy_MHz TSC_MHz SMI %Busy CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt - * 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 + * Package Core CPU Avg_MHz Bzy_MHz TSC_MHz SMI %Busy CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt + * 123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678 */ void print_header(void) { if (show_pkg) - outp += sprintf(outp, "Package "); + outp += sprintf(outp, " Package"); if (show_core) - outp += sprintf(outp, " Core "); + outp += sprintf(outp, " Core"); if (show_cpu) - outp += sprintf(outp, " CPU "); + outp += sprintf(outp, " CPU"); if (has_aperf) - outp += sprintf(outp, "Avg_MHz "); + outp += sprintf(outp, " Avg_MHz"); if (do_nhm_cstates) - outp += sprintf(outp, " %%Busy "); + outp += sprintf(outp, " %%Busy"); if (has_aperf) - outp += sprintf(outp, "Bzy_MHz "); - outp += sprintf(outp, "TSC_MHz "); + outp += sprintf(outp, " Bzy_MHz"); + outp += sprintf(outp, " TSC_MHz"); if (do_smi) - outp += sprintf(outp, " SMI "); + outp += sprintf(outp, " SMI"); if (extra_delta_offset32) - outp += sprintf(outp, " count 0x%03X ", extra_delta_offset32); + outp += sprintf(outp, " count 0x%03X", extra_delta_offset32); if (extra_delta_offset64) - outp += sprintf(outp, " COUNT 0x%03X ", extra_delta_offset64); + outp += sprintf(outp, " COUNT 0x%03X", extra_delta_offset64); if (extra_msr_offset32) - outp += sprintf(outp, " MSR 0x%03X ", extra_msr_offset32); + outp += sprintf(outp, " MSR 0x%03X", extra_msr_offset32); if (extra_msr_offset64) - outp += sprintf(outp, " MSR 0x%03X ", extra_msr_offset64); + outp += sprintf(outp, " MSR 0x%03X", extra_msr_offset64); if (do_nhm_cstates) - outp += sprintf(outp, " CPU%%c1 "); + outp += sprintf(outp, " CPU%%c1"); if (do_nhm_cstates && !do_slm_cstates) - outp += sprintf(outp, " CPU%%c3 "); + outp += sprintf(outp, " CPU%%c3"); if (do_nhm_cstates) - outp += sprintf(outp, " CPU%%c6 "); + outp += sprintf(outp, " CPU%%c6"); if (do_snb_cstates) - outp += sprintf(outp, " CPU%%c7 "); + outp += sprintf(outp, " CPU%%c7"); if (do_dts) - outp += sprintf(outp, "CoreTmp "); + outp += sprintf(outp, " CoreTmp"); if (do_ptm) - outp += sprintf(outp, " PkgTmp "); + outp += sprintf(outp, " PkgTmp"); if (do_snb_cstates) - outp += sprintf(outp, "Pkg%%pc2 "); + outp += sprintf(outp, " Pkg%%pc2"); if (do_nhm_cstates && !do_slm_cstates) - outp += sprintf(outp, "Pkg%%pc3 "); + outp += sprintf(outp, " Pkg%%pc3"); if (do_nhm_cstates && !do_slm_cstates) - outp += sprintf(outp, "Pkg%%pc6 "); + outp += sprintf(outp, " Pkg%%pc6"); if (do_snb_cstates) - outp += sprintf(outp, "Pkg%%pc7 "); + outp += sprintf(outp, " Pkg%%pc7"); if (do_c8_c9_c10) { - outp += sprintf(outp, "Pkg%%pc8 "); - outp += sprintf(outp, "Pkg%%pc9 "); - outp += sprintf(outp, "Pk%%pc10 "); + outp += sprintf(outp, " Pkg%%pc8"); + outp += sprintf(outp, " Pkg%%pc9"); + outp += sprintf(outp, " Pk%%pc10"); } if (do_rapl && !rapl_joules) { if (do_rapl & RAPL_PKG) - outp += sprintf(outp, "PkgWatt "); + outp += sprintf(outp, " PkgWatt"); if (do_rapl & RAPL_CORES) - outp += sprintf(outp, "CorWatt "); + outp += sprintf(outp, " CorWatt"); if (do_rapl & RAPL_GFX) - outp += sprintf(outp, "GFXWatt "); + outp += sprintf(outp, " GFXWatt"); if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, "RAMWatt "); + outp += sprintf(outp, " RAMWatt"); if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, " PKG_%% "); + outp += sprintf(outp, " PKG_%%"); if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, " RAM_%% "); + outp += sprintf(outp, " RAM_%%"); } else { if (do_rapl & RAPL_PKG) - outp += sprintf(outp, " Pkg_J "); + outp += sprintf(outp, " Pkg_J"); if (do_rapl & RAPL_CORES) - outp += sprintf(outp, " Cor_J "); + outp += sprintf(outp, " Cor_J"); if (do_rapl & RAPL_GFX) - outp += sprintf(outp, " GFX_J "); + outp += sprintf(outp, " GFX_J"); if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, " RAM_W "); + outp += sprintf(outp, " RAM_W"); if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, " PKG_%% "); + outp += sprintf(outp, " PKG_%%"); if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, " RAM_%% "); - outp += sprintf(outp, " time "); + outp += sprintf(outp, " RAM_%%"); + outp += sprintf(outp, " time"); } outp += sprintf(outp, "\n"); diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 4063156..b9cd036 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -72,7 +72,7 @@ my %default = ( "IGNORE_UNUSED" => 0, ); -my $ktest_config; +my $ktest_config = "ktest.conf"; my $version; my $have_version = 0; my $machine; @@ -149,7 +149,6 @@ my $bisect_ret_abort; my $bisect_ret_default; my $in_patchcheck = 0; my $run_test; -my $redirect; my $buildlog; my $testlog; my $dmesg; @@ -195,6 +194,7 @@ my $config_bisect_check; my $patchcheck_type; my $patchcheck_start; +my $patchcheck_cherry; my $patchcheck_end; # set when a test is something other that just building or install @@ -321,6 +321,7 @@ my %option_map = ( "PATCHCHECK_TYPE" => \$patchcheck_type, "PATCHCHECK_START" => \$patchcheck_start, + "PATCHCHECK_CHERRY" => \$patchcheck_cherry, "PATCHCHECK_END" => \$patchcheck_end, ); @@ -522,7 +523,7 @@ sub read_ync { return read_prompt 1, $prompt; } -sub get_ktest_config { +sub get_mandatory_config { my ($config) = @_; my $ans; @@ -553,29 +554,29 @@ sub get_ktest_config { } } -sub get_ktest_configs { - get_ktest_config("MACHINE"); - get_ktest_config("BUILD_DIR"); - get_ktest_config("OUTPUT_DIR"); +sub get_mandatory_configs { + get_mandatory_config("MACHINE"); + get_mandatory_config("BUILD_DIR"); + get_mandatory_config("OUTPUT_DIR"); if ($newconfig) { - get_ktest_config("BUILD_OPTIONS"); + get_mandatory_config("BUILD_OPTIONS"); } # options required for other than just building a kernel if (!$buildonly) { - get_ktest_config("POWER_CYCLE"); - get_ktest_config("CONSOLE"); + get_mandatory_config("POWER_CYCLE"); + get_mandatory_config("CONSOLE"); } # options required for install and more if ($buildonly != 1) { - get_ktest_config("SSH_USER"); - get_ktest_config("BUILD_TARGET"); - get_ktest_config("TARGET_IMAGE"); + get_mandatory_config("SSH_USER"); + get_mandatory_config("BUILD_TARGET"); + get_mandatory_config("TARGET_IMAGE"); } - get_ktest_config("LOCALVERSION"); + get_mandatory_config("LOCALVERSION"); return if ($buildonly); @@ -583,7 +584,7 @@ sub get_ktest_configs { if (!defined($rtype)) { if (!defined($opt{"GRUB_MENU"})) { - get_ktest_config("REBOOT_TYPE"); + get_mandatory_config("REBOOT_TYPE"); $rtype = $entered_configs{"REBOOT_TYPE"}; } else { $rtype = "grub"; @@ -591,16 +592,16 @@ sub get_ktest_configs { } if ($rtype eq "grub") { - get_ktest_config("GRUB_MENU"); + get_mandatory_config("GRUB_MENU"); } if ($rtype eq "grub2") { - get_ktest_config("GRUB_MENU"); - get_ktest_config("GRUB_FILE"); + get_mandatory_config("GRUB_MENU"); + get_mandatory_config("GRUB_FILE"); } if ($rtype eq "syslinux") { - get_ktest_config("SYSLINUX_LABEL"); + get_mandatory_config("SYSLINUX_LABEL"); } } @@ -683,11 +684,8 @@ sub set_value { } ${$overrides}{$lvalue} = $prvalue; } - if ($rvalue =~ /^\s*$/) { - delete $opt{$lvalue}; - } else { - $opt{$lvalue} = $prvalue; - } + + $opt{$lvalue} = $prvalue; } sub set_eval { @@ -1090,7 +1088,7 @@ sub read_config { $test_case = __read_config $config, \$test_num; # make sure we have all mandatory configs - get_ktest_configs; + get_mandatory_configs; # was a test specified? if (!$test_case) { @@ -1449,6 +1447,12 @@ sub wait_for_monitor { } } print "** Monitor flushed **\n"; + + # if stop is defined but wasn't hit, return error + # used by reboot (which wants to see a reboot) + if (defined($stop) && !$booted) { + $bug = 1; + } return $bug; } @@ -1529,7 +1533,7 @@ sub fail { } sub run_command { - my ($command) = @_; + my ($command, $redirect) = @_; my $dolog = 0; my $dord = 0; my $pid; @@ -1998,7 +2002,7 @@ sub get_version { # get the release name return if ($have_version); doprint "$make kernelrelease ... "; - $version = `$make kernelrelease | tail -1`; + $version = `$make -s kernelrelease | tail -1`; chomp($version); doprint "$version\n"; $have_version = 1; @@ -2265,9 +2269,7 @@ sub build { # Run old config regardless, to enforce min configurations make_oldconfig; - $redirect = "$buildlog"; - my $build_ret = run_command "$make $build_options"; - undef $redirect; + my $build_ret = run_command "$make $build_options", $buildlog; if (defined($post_build)) { # Because a post build may change the kernel version @@ -2339,15 +2341,17 @@ sub success { sub answer_bisect { for (;;) { - doprint "Pass or fail? [p/f]"; + doprint "Pass, fail, or skip? [p/f/s]"; my $ans = <STDIN>; chomp $ans; if ($ans eq "p" || $ans eq "P") { return 1; } elsif ($ans eq "f" || $ans eq "F") { return 0; + } elsif ($ans eq "s" || $ans eq "S") { + return -1; } else { - print "Please answer 'P' or 'F'\n"; + print "Please answer 'p', 'f', or 's'\n"; } } } @@ -2360,9 +2364,7 @@ sub child_run_test { $poweroff_on_error = 0; $die_on_failure = 1; - $redirect = "$testlog"; - run_command $run_test or $failed = 1; - undef $redirect; + run_command $run_test, $testlog or $failed = 1; exit $failed; } @@ -2731,15 +2733,17 @@ sub bisect { run_command "git bisect start$start_files" or dodie "could not start bisect"; - run_command "git bisect good $good" or - dodie "could not set bisect good to $good"; - - run_git_bisect "git bisect bad $bad" or - dodie "could not set bisect bad to $bad"; - if (defined($replay)) { run_command "git bisect replay $replay" or dodie "failed to run replay"; + } else { + + run_command "git bisect good $good" or + dodie "could not set bisect good to $good"; + + run_git_bisect "git bisect bad $bad" or + dodie "could not set bisect bad to $bad"; + } if (defined($start)) { @@ -2789,12 +2793,17 @@ my %dependency; sub assign_configs { my ($hash, $config) = @_; + doprint "Reading configs from $config\n"; + open (IN, $config) or dodie "Failed to read $config"; while (<IN>) { + chomp; if (/^((CONFIG\S*)=.*)/) { ${$hash}{$2} = $1; + } elsif (/^(# (CONFIG\S*) is not set)/) { + ${$hash}{$2} = $1; } } @@ -2807,27 +2816,6 @@ sub process_config_ignore { assign_configs \%config_ignore, $config; } -sub read_current_config { - my ($config_ref) = @_; - - %{$config_ref} = (); - undef %{$config_ref}; - - my @key = keys %{$config_ref}; - if ($#key >= 0) { - print "did not delete!\n"; - exit; - } - open (IN, "$output_config"); - - while (<IN>) { - if (/^(CONFIG\S+)=(.*)/) { - ${$config_ref}{$1} = $2; - } - } - close(IN); -} - sub get_dependencies { my ($config) = @_; @@ -2846,53 +2834,97 @@ sub get_dependencies { return @deps; } +sub save_config { + my ($pc, $file) = @_; + + my %configs = %{$pc}; + + doprint "Saving configs into $file\n"; + + open(OUT, ">$file") or dodie "Can not write to $file"; + + foreach my $config (keys %configs) { + print OUT "$configs{$config}\n"; + } + close(OUT); +} + sub create_config { - my @configs = @_; + my ($name, $pc) = @_; - open(OUT, ">$output_config") or dodie "Can not write to $output_config"; + doprint "Creating old config from $name configs\n"; - foreach my $config (@configs) { - print OUT "$config_set{$config}\n"; - my @deps = get_dependencies $config; - foreach my $dep (@deps) { - print OUT "$config_set{$dep}\n"; + save_config $pc, $output_config; + + make_oldconfig; +} + +# compare two config hashes, and return configs with different vals. +# It returns B's config values, but you can use A to see what A was. +sub diff_config_vals { + my ($pa, $pb) = @_; + + # crappy Perl way to pass in hashes. + my %a = %{$pa}; + my %b = %{$pb}; + + my %ret; + + foreach my $item (keys %a) { + if (defined($b{$item}) && $b{$item} ne $a{$item}) { + $ret{$item} = $b{$item}; } } - # turn off configs to keep off - foreach my $config (keys %config_off) { - print OUT "# $config is not set\n"; - } + return %ret; +} - # turn off configs that should be off for now - foreach my $config (@config_off_tmp) { - print OUT "# $config is not set\n"; - } +# compare two config hashes and return the configs in B but not A +sub diff_configs { + my ($pa, $pb) = @_; - foreach my $config (keys %config_ignore) { - print OUT "$config_ignore{$config}\n"; + my %ret; + + # crappy Perl way to pass in hashes. + my %a = %{$pa}; + my %b = %{$pb}; + + foreach my $item (keys %b) { + if (!defined($a{$item})) { + $ret{$item} = $b{$item}; + } } - close(OUT); - make_oldconfig; + return %ret; } +# return if two configs are equal or not +# 0 is equal +1 b has something a does not +# +1 if a and b have a different item. +# -1 if a has something b does not sub compare_configs { - my (%a, %b) = @_; + my ($pa, $pb) = @_; - foreach my $item (keys %a) { - if (!defined($b{$item})) { - print "diff $item\n"; + my %ret; + + # crappy Perl way to pass in hashes. + my %a = %{$pa}; + my %b = %{$pb}; + + foreach my $item (keys %b) { + if (!defined($a{$item})) { + return 1; + } + if ($a{$item} ne $b{$item}) { return 1; } - delete $b{$item}; } - my @keys = keys %b; - if ($#keys) { - print "diff2 $keys[0]\n"; + foreach my $item (keys %a) { + if (!defined($b{$item})) { + return -1; + } } - return -1 if ($#keys >= 0); return 0; } @@ -2900,24 +2932,13 @@ sub compare_configs { sub run_config_bisect_test { my ($type) = @_; - return run_bisect_test $type, "oldconfig"; -} - -sub process_passed { - my (%configs) = @_; + my $ret = run_bisect_test $type, "oldconfig"; - doprint "These configs had no failure: (Enabling them for further compiles)\n"; - # Passed! All these configs are part of a good compile. - # Add them to the min options. - foreach my $config (keys %configs) { - if (defined($config_list{$config})) { - doprint " removing $config\n"; - $config_ignore{$config} = $config_list{$config}; - delete $config_list{$config}; - } + if ($bisect_manual) { + $ret = answer_bisect; } - doprint "config copied to $outputdir/config_good\n"; - run_command "cp -f $output_config $outputdir/config_good"; + + return $ret; } sub process_failed { @@ -2928,253 +2949,225 @@ sub process_failed { doprint "***************************************\n\n"; } -sub run_config_bisect { +# used for config bisecting +my $good_config; +my $bad_config; - my @start_list = keys %config_list; +sub process_new_config { + my ($tc, $nc, $gc, $bc) = @_; - if ($#start_list < 0) { - doprint "No more configs to test!!!\n"; - return -1; + my %tmp_config = %{$tc}; + my %good_configs = %{$gc}; + my %bad_configs = %{$bc}; + + my %new_configs; + + my $runtest = 1; + my $ret; + + create_config "tmp_configs", \%tmp_config; + assign_configs \%new_configs, $output_config; + + $ret = compare_configs \%new_configs, \%bad_configs; + if (!$ret) { + doprint "New config equals bad config, try next test\n"; + $runtest = 0; + } + + if ($runtest) { + $ret = compare_configs \%new_configs, \%good_configs; + if (!$ret) { + doprint "New config equals good config, try next test\n"; + $runtest = 0; + } } - doprint "***** RUN TEST ***\n"; + %{$nc} = %new_configs; + + return $runtest; +} + +sub run_config_bisect { + my ($pgood, $pbad) = @_; + my $type = $config_bisect_type; + + my %good_configs = %{$pgood}; + my %bad_configs = %{$pbad}; + + my %diff_configs = diff_config_vals \%good_configs, \%bad_configs; + my %b_configs = diff_configs \%good_configs, \%bad_configs; + my %g_configs = diff_configs \%bad_configs, \%good_configs; + + my @diff_arr = keys %diff_configs; + my $len_diff = $#diff_arr + 1; + + my @b_arr = keys %b_configs; + my $len_b = $#b_arr + 1; + + my @g_arr = keys %g_configs; + my $len_g = $#g_arr + 1; + + my $runtest = 1; + my %new_configs; my $ret; - my %current_config; - my $count = $#start_list + 1; - doprint " $count configs to test\n"; + # First, lets get it down to a single subset. + # Is the problem with a difference in values? + # Is the problem with a missing config? + # Is the problem with a config that breaks things? - my $half = int($#start_list / 2); + # Enable all of one set and see if we get a new bad + # or good config. - do { - my @tophalf = @start_list[0 .. $half]; + # first set the good config to the bad values. - # keep the bottom half off - if ($half < $#start_list) { - @config_off_tmp = @start_list[$half + 1 .. $#start_list]; - } else { - @config_off_tmp = (); - } + doprint "d=$len_diff g=$len_g b=$len_b\n"; - create_config @tophalf; - read_current_config \%current_config; - - $count = $#tophalf + 1; - doprint "Testing $count configs\n"; - my $found = 0; - # make sure we test something - foreach my $config (@tophalf) { - if (defined($current_config{$config})) { - logit " $config\n"; - $found = 1; - } - } - if (!$found) { - # try the other half - doprint "Top half produced no set configs, trying bottom half\n"; - - # keep the top half off - @config_off_tmp = @tophalf; - @tophalf = @start_list[$half + 1 .. $#start_list]; - - create_config @tophalf; - read_current_config \%current_config; - foreach my $config (@tophalf) { - if (defined($current_config{$config})) { - logit " $config\n"; - $found = 1; - } - } - if (!$found) { - doprint "Failed: Can't make new config with current configs\n"; - foreach my $config (@start_list) { - doprint " CONFIG: $config\n"; - } - return -1; + # first lets enable things in bad config that are enabled in good config + + if ($len_diff > 0) { + if ($len_b > 0 || $len_g > 0) { + my %tmp_config = %bad_configs; + + doprint "Set tmp config to be bad config with good config values\n"; + foreach my $item (@diff_arr) { + $tmp_config{$item} = $good_configs{$item}; } - $count = $#tophalf + 1; - doprint "Testing $count configs\n"; - } - $ret = run_config_bisect_test $type; - if ($bisect_manual) { - $ret = answer_bisect; - } - if ($ret) { - process_passed %current_config; - return 0; + $runtest = process_new_config \%tmp_config, \%new_configs, + \%good_configs, \%bad_configs; } + } - doprint "This config had a failure.\n"; - doprint "Removing these configs that were not set in this config:\n"; - doprint "config copied to $outputdir/config_bad\n"; - run_command "cp -f $output_config $outputdir/config_bad"; + if (!$runtest && $len_diff > 0) { - # A config exists in this group that was bad. - foreach my $config (keys %config_list) { - if (!defined($current_config{$config})) { - doprint " removing $config\n"; - delete $config_list{$config}; - } + if ($len_diff == 1) { + process_failed $diff_arr[0]; + return 1; } + my %tmp_config = %bad_configs; - @start_list = @tophalf; + my $half = int($#diff_arr / 2); + my @tophalf = @diff_arr[0 .. $half]; - if ($#start_list == 0) { - process_failed $start_list[0]; - return 1; + doprint "Settings bisect with top half:\n"; + doprint "Set tmp config to be bad config with some good config values\n"; + foreach my $item (@tophalf) { + $tmp_config{$item} = $good_configs{$item}; } - # remove half the configs we are looking at and see if - # they are good. - $half = int($#start_list / 2); - } while ($#start_list > 0); + $runtest = process_new_config \%tmp_config, \%new_configs, + \%good_configs, \%bad_configs; - # we found a single config, try it again unless we are running manually + if (!$runtest) { + my %tmp_config = %bad_configs; - if ($bisect_manual) { - process_failed $start_list[0]; - return 1; - } + doprint "Try bottom half\n"; - my @tophalf = @start_list[0 .. 0]; + my @bottomhalf = @diff_arr[$half+1 .. $#diff_arr]; - $ret = run_config_bisect_test $type; - if ($ret) { - process_passed %current_config; + foreach my $item (@bottomhalf) { + $tmp_config{$item} = $good_configs{$item}; + } + + $runtest = process_new_config \%tmp_config, \%new_configs, + \%good_configs, \%bad_configs; + } + } + + if ($runtest) { + $ret = run_config_bisect_test $type; + if ($ret) { + doprint "NEW GOOD CONFIG\n"; + %good_configs = %new_configs; + run_command "mv $good_config ${good_config}.last"; + save_config \%good_configs, $good_config; + %{$pgood} = %good_configs; + } else { + doprint "NEW BAD CONFIG\n"; + %bad_configs = %new_configs; + run_command "mv $bad_config ${bad_config}.last"; + save_config \%bad_configs, $bad_config; + %{$pbad} = %bad_configs; + } return 0; } - process_failed $start_list[0]; - return 1; + fail "Hmm, need to do a mix match?\n"; + return -1; } sub config_bisect { my ($i) = @_; - my $start_config = $config_bisect; + my $type = $config_bisect_type; + my $ret; - my $tmpconfig = "$tmpdir/use_config"; + $bad_config = $config_bisect; if (defined($config_bisect_good)) { - process_config_ignore $config_bisect_good; - } - - # Make the file with the bad config and the min config - if (defined($minconfig)) { - # read the min config for things to ignore - run_command "cp $minconfig $tmpconfig" or - dodie "failed to copy $minconfig to $tmpconfig"; + $good_config = $config_bisect_good; + } elsif (defined($minconfig)) { + $good_config = $minconfig; } else { - unlink $tmpconfig; - } - - if (-f $tmpconfig) { - load_force_config($tmpconfig); - process_config_ignore $tmpconfig; - } - - # now process the start config - run_command "cp $start_config $output_config" or - dodie "failed to copy $start_config to $output_config"; - - # read directly what we want to check - my %config_check; - open (IN, $output_config) - or dodie "failed to open $output_config"; - - while (<IN>) { - if (/^((CONFIG\S*)=.*)/) { - $config_check{$2} = $1; + doprint "No config specified, checking if defconfig works"; + $ret = run_bisect_test $type, "defconfig"; + if (!$ret) { + fail "Have no good config to compare with, please set CONFIG_BISECT_GOOD"; + return 1; } + $good_config = $output_config; } - close(IN); - # Now run oldconfig with the minconfig - make_oldconfig; + # we don't want min configs to cause issues here. + doprint "Disabling 'MIN_CONFIG' for this test\n"; + undef $minconfig; - # check to see what we lost (or gained) - open (IN, $output_config) - or dodie "Failed to read $start_config"; + my %good_configs; + my %bad_configs; + my %tmp_configs; - my %removed_configs; - my %added_configs; + doprint "Run good configs through make oldconfig\n"; + assign_configs \%tmp_configs, $good_config; + create_config "$good_config", \%tmp_configs; + assign_configs \%good_configs, $output_config; - while (<IN>) { - if (/^((CONFIG\S*)=.*)/) { - # save off all options - $config_set{$2} = $1; - if (defined($config_check{$2})) { - if (defined($config_ignore{$2})) { - $removed_configs{$2} = $1; - } else { - $config_list{$2} = $1; - } - } elsif (!defined($config_ignore{$2})) { - $added_configs{$2} = $1; - $config_list{$2} = $1; - } - } elsif (/^# ((CONFIG\S*).*)/) { - # Keep these configs disabled - $config_set{$2} = $1; - $config_off{$2} = $1; - } - } - close(IN); + doprint "Run bad configs through make oldconfig\n"; + assign_configs \%tmp_configs, $bad_config; + create_config "$bad_config", \%tmp_configs; + assign_configs \%bad_configs, $output_config; - my @confs = keys %removed_configs; - if ($#confs >= 0) { - doprint "Configs overridden by default configs and removed from check:\n"; - foreach my $config (@confs) { - doprint " $config\n"; - } - } - @confs = keys %added_configs; - if ($#confs >= 0) { - doprint "Configs appearing in make oldconfig and added:\n"; - foreach my $config (@confs) { - doprint " $config\n"; - } - } + $good_config = "$tmpdir/good_config"; + $bad_config = "$tmpdir/bad_config"; + + save_config \%good_configs, $good_config; + save_config \%bad_configs, $bad_config; - my %config_test; - my $once = 0; - @config_off_tmp = (); + if (defined($config_bisect_check) && $config_bisect_check ne "0") { + if ($config_bisect_check ne "good") { + doprint "Testing bad config\n"; - # Sometimes kconfig does weird things. We must make sure - # that the config we autocreate has everything we need - # to test, otherwise we may miss testing configs, or - # may not be able to create a new config. - # Here we create a config with everything set. - create_config (keys %config_list); - read_current_config \%config_test; - foreach my $config (keys %config_list) { - if (!defined($config_test{$config})) { - if (!$once) { - $once = 1; - doprint "Configs not produced by kconfig (will not be checked):\n"; + $ret = run_bisect_test $type, "useconfig:$bad_config"; + if ($ret) { + fail "Bad config succeeded when expected to fail!"; + return 0; } - doprint " $config\n"; - delete $config_list{$config}; } - } - my $ret; + if ($config_bisect_check ne "bad") { + doprint "Testing good config\n"; - if (defined($config_bisect_check) && $config_bisect_check) { - doprint " Checking to make sure bad config with min config fails\n"; - create_config keys %config_list; - $ret = run_config_bisect_test $config_bisect_type; - if ($ret) { - doprint " FAILED! Bad config with min config boots fine\n"; - return -1; + $ret = run_bisect_test $type, "useconfig:$good_config"; + if (!$ret) { + fail "Good config failed when expected to succeed!"; + return 0; + } } - doprint " Bad config with min config fails as expected\n"; } do { - $ret = run_config_bisect; + $ret = run_config_bisect \%good_configs, \%bad_configs; } while (!$ret); return $ret if ($ret < 0); @@ -3197,9 +3190,16 @@ sub patchcheck { my $start = $patchcheck_start; + my $cherry = $patchcheck_cherry; + if (!defined($cherry)) { + $cherry = 0; + } + my $end = "HEAD"; if (defined($patchcheck_end)) { $end = $patchcheck_end; + } elsif ($cherry) { + die "PATCHCHECK_END must be defined with PATCHCHECK_CHERRY\n"; } # Get the true sha1's since we can use things like HEAD~3 @@ -3213,24 +3213,38 @@ sub patchcheck { $type = "boot"; } - open (IN, "git log --pretty=oneline $end|") or - dodie "could not get git list"; + if ($cherry) { + open (IN, "git cherry -v $start $end|") or + dodie "could not get git list"; + } else { + open (IN, "git log --pretty=oneline $end|") or + dodie "could not get git list"; + } my @list; while (<IN>) { chomp; + # git cherry adds a '+' we want to remove + s/^\+ //; $list[$#list+1] = $_; last if (/^$start/); } close(IN); - if ($list[$#list] !~ /^$start/) { - fail "SHA1 $start not found"; + if (!$cherry) { + if ($list[$#list] !~ /^$start/) { + fail "SHA1 $start not found"; + } + + # go backwards in the list + @list = reverse @list; } - # go backwards in the list - @list = reverse @list; + doprint("Going to test the following commits:\n"); + foreach my $l (@list) { + doprint "$l\n"; + } my $save_clean = $noclean; my %ignored_warnings; @@ -3455,29 +3469,6 @@ sub read_depends { read_kconfig($kconfig); } -sub read_config_list { - my ($config) = @_; - - open (IN, $config) - or dodie "Failed to read $config"; - - while (<IN>) { - if (/^((CONFIG\S*)=.*)/) { - if (!defined($config_ignore{$2})) { - $config_list{$2} = $1; - } - } - } - - close(IN); -} - -sub read_output_config { - my ($config) = @_; - - assign_configs \%config_ignore, $config; -} - sub make_new_config { my @configs = @_; @@ -3577,7 +3568,9 @@ 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"; @@ -3863,7 +3856,7 @@ sub make_warnings_file { success $i; } -$#ARGV < 1 or die "ktest.pl version: $VERSION\n usage: ktest.pl config-file\n"; +$#ARGV < 1 or die "ktest.pl version: $VERSION\n usage: ktest.pl [config-file]\n"; if ($#ARGV == 0) { $ktest_config = $ARGV[0]; @@ -3873,8 +3866,6 @@ if ($#ARGV == 0) { exit 0; } } -} else { - $ktest_config = "ktest.conf"; } if (! -f $ktest_config) { @@ -3953,12 +3944,22 @@ 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}; } @@ -3966,13 +3967,13 @@ 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}; } @@ -4085,8 +4086,14 @@ 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; diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf index 172eec4..6c58cd8 100644 --- a/tools/testing/ktest/sample.conf +++ b/tools/testing/ktest/sample.conf @@ -906,6 +906,16 @@ # # PATCHCHECK_END is the last patch to check (default HEAD) # +# PATCHCHECK_CHERRY if set to non zero, then git cherry will be +# performed against PATCHCHECK_START and PATCHCHECK_END. That is +# +# git cherry ${PATCHCHECK_START} ${PATCHCHECK_END} +# +# Then the changes found will be tested. +# +# Note, PATCHCHECK_CHERRY requires PATCHCHECK_END to be defined. +# (default 0) +# # PATCHCHECK_TYPE is required and is the type of test to run: # build, boot, test. # @@ -1098,49 +1108,35 @@ # # The way it works is this: # -# First it finds a config to work with. Since a different version, or -# MIN_CONFIG may cause different dependecies, it must run through this -# preparation. -# -# Overwrites any config set in the bad config with a config set in -# either the MIN_CONFIG or ADD_CONFIG. Thus, make sure these configs -# are minimal and do not disable configs you want to test: -# (ie. # CONFIG_FOO is not set). -# -# An oldconfig is run on the bad config and any new config that -# appears will be added to the configs to test. -# -# Finally, it generates a config with the above result and runs it -# again through make oldconfig to produce a config that should be -# satisfied by kconfig. -# -# Then it starts the bisect. +# You can specify a good config with CONFIG_BISECT_GOOD, otherwise it +# will use the MIN_CONFIG, and if that's not specified, it will use +# the config that comes with "make defconfig". # -# The configs to test are cut in half. If all the configs in this -# half depend on a config in the other half, then the other half -# is tested instead. If no configs are enabled by either half, then -# this means a circular dependency exists and the test fails. +# It runs both the good and bad configs through a make oldconfig to +# make sure that they are set up for the kernel that is checked out. # -# A config is created with the test half, and the bisect test is run. +# It then reads the configs that are set, as well as the ones that are +# not set for both the good and bad configs, and then compares them. +# It will set half of the good configs within the bad config (note, +# "set" means to make the bad config match the good config, a config +# in the good config that is off, will be turned off in the bad +# config. That is considered a "set"). # -# If the bisect succeeds, then all configs in the generated config -# are removed from the configs to test and added to the configs that -# will be enabled for all builds (they will be enabled, but not be part -# of the configs to examine). +# It tests this new config and if it works, it becomes the new good +# config, otherwise it becomes the new bad config. It continues this +# process until there's only one config left and it will report that +# config. # -# If the bisect fails, then all test configs that were not enabled by -# the config file are removed from the test. These configs will not -# be enabled in future tests. Since current config failed, we consider -# this to be a subset of the config that we started with. +# The "bad config" can also be a config that is needed to boot but was +# disabled because it depended on something that wasn't set. # -# When we are down to one config, it is considered the bad config. +# During this process, it saves the current good and bad configs in +# ${TMP_DIR}/good_config and ${TMP_DIR}/bad_config respectively. +# If you stop the test, you can copy them to a new location to +# reuse them again. # -# Note, the config chosen may not be the true bad config. Due to -# dependencies and selections of the kbuild system, mulitple -# configs may be needed to cause a failure. If you disable the -# config that was found and restart the test, if the test fails -# again, it is recommended to rerun the config_bisect with a new -# bad config without the found config enabled. +# Although the MIN_CONFIG may be the config it starts with, the +# MIN_CONFIG is ignored. # # The option BUILD_TYPE will be ignored. # @@ -1160,13 +1156,16 @@ # CONFIG_BISECT_GOOD (optional) # If you have a good config to start with, then you # can specify it with CONFIG_BISECT_GOOD. Otherwise -# the MIN_CONFIG is the base. +# the MIN_CONFIG is the base, if MIN_CONFIG is not set +# It will build a config with "make defconfig" # # CONFIG_BISECT_CHECK (optional) # Set this to 1 if you want to confirm that the config ktest # generates (the bad config with the min config) is still bad. # It may be that the min config fixes what broke the bad config # and the test will not return a result. +# Set it to "good" to test only the good config and set it +# to "bad" to only test the bad config. # # Example: # TEST_START diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index e66e710..4e51122 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,16 +1,26 @@ TARGETS = breakpoints TARGETS += cpu-hotplug TARGETS += efivarfs +TARGETS += exec +TARGETS += firmware +TARGETS += ftrace TARGETS += kcmp +TARGETS += memfd TARGETS += memory-hotplug +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 += vm +#Please keep the TARGETS list alphabetically sorted + +TARGETS_HOTPLUG = cpu-hotplug +TARGETS_HOTPLUG += memory-hotplug all: for TARGET in $(TARGETS); do \ @@ -22,6 +32,21 @@ run_tests: all make -C $$TARGET run_tests; \ done; +hotplug: + for TARGET in $(TARGETS_HOTPLUG); do \ + make -C $$TARGET; \ + done; + +run_hotplug: hotplug + for TARGET in $(TARGETS_HOTPLUG); do \ + make -C $$TARGET run_full_test; \ + done; + +clean_hotplug: + for TARGET in $(TARGETS_HOTPLUG); do \ + make -C $$TARGET clean; \ + done; + clean: for TARGET in $(TARGETS); do \ make -C $$TARGET clean; \ diff --git a/tools/testing/selftests/README.txt b/tools/testing/selftests/README.txt deleted file mode 100644 index 5e2faf9..0000000 --- a/tools/testing/selftests/README.txt +++ /dev/null @@ -1,42 +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. - -Running the selftests -===================== - -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 targetted for a single subsystem: - - $ 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. - - -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/breakpoint_test.c b/tools/testing/selftests/breakpoints/breakpoint_test.c index a0743f3..120895a 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 790c23a..e9c28d8 100644 --- a/tools/testing/selftests/cpu-hotplug/Makefile +++ b/tools/testing/selftests/cpu-hotplug/Makefile @@ -3,4 +3,7 @@ all: run_tests: @/bin/bash ./on-off-test.sh || echo "cpu-hotplug selftests: [FAIL]" +run_full_test: + @/bin/bash ./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/on-off-test.sh index bdde7cf..98b1d65 100644 --- a/tools/testing/selftests/cpu-hotplug/on-off-test.sh +++ b/tools/testing/selftests/cpu-hotplug/on-off-test.sh @@ -11,6 +11,8 @@ prerequisite() exit 0 fi + taskset -p 01 $$ + SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'` if [ ! -d "$SYSFS" ]; then @@ -22,6 +24,19 @@ prerequisite() echo $msg cpu hotplug is not supported >&2 exit 0 fi + + echo "CPU online/offline summary:" + online_cpus=`cat $SYSFS/devices/system/cpu/online` + online_max=${online_cpus##*-} + echo -e "\t Cpus in online state: $online_cpus" + + offline_cpus=`cat $SYSFS/devices/system/cpu/offline` + if [[ "a$offline_cpus" = "a" ]]; then + offline_cpus=0 + else + offline_max=${offline_cpus##*-} + fi + echo -e "\t Cpus in offline state: $offline_cpus" } # @@ -113,15 +128,25 @@ offline_cpu_expect_fail() } error=-12 +allcpus=0 priority=0 +online_cpus=0 +online_max=0 +offline_cpus=0 +offline_max=0 -while getopts e:hp: opt; do +while getopts e:ahp: opt; do case $opt in e) error=$OPTARG ;; + a) + allcpus=1 + ;; h) - echo "Usage $0 [ -e errno ] [ -p notifier-priority ]" + echo "Usage $0 [ -a ] [ -e errno ] [ -p notifier-priority ]" + echo -e "\t default offline one cpu" + echo -e "\t run with -a option to offline all cpus" exit ;; p) @@ -138,6 +163,29 @@ fi prerequisite # +# Safe test (default) - offline and online one cpu +# +if [ $allcpus -eq 0 ]; then + echo "Limited scope test: one hotplug cpu" + echo -e "\t (leaves cpu in the original state):" + echo -e "\t online to offline to online: cpu $online_max" + offline_cpu_expect_success $online_max + online_cpu_expect_success $online_max + + if [[ $offline_cpus -gt 0 ]]; then + echo -e "\t offline to online to offline: cpu $offline_max" + online_cpu_expect_success $offline_max + offline_cpu_expect_success $offline_max + fi + exit 0 +else + echo "Full scope test: all hotplug cpus" + echo -e "\t online all offline cpus" + echo -e "\t offline all online cpus" + echo -e "\t online all offline cpus" +fi + +# # Online all hot-pluggable CPUs # for cpu in `hotplaggable_offline_cpus`; do diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore new file mode 100644 index 0000000..64073e0 --- /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 0000000..66dfc2c --- /dev/null +++ b/tools/testing/selftests/exec/Makefile @@ -0,0 +1,25 @@ +CC = $(CROSS_COMPILE)gcc +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 $@ $^ + +run_tests: all + ./execveat + +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 0000000..d273624 --- /dev/null +++ b/tools/testing/selftests/exec/execveat.c @@ -0,0 +1,397 @@ +/* + * 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 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) { + printf("[FAIL] (child %d exited with %d not %d)\n", + child, WEXITSTATUS(status), expected_rc); + 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); +} + +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. + */ + if (is_script) + fail += check_execveat_invoked_rc(dot_dfd, longpath, 0, 127); + 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); + + /* 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 new file mode 100644 index 0000000..e23cce0 --- /dev/null +++ b/tools/testing/selftests/firmware/Makefile @@ -0,0 +1,27 @@ +# Makefile for firmware loading selftests + +# 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 + +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 + +# 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 new file mode 100644 index 0000000..3fc6c10 --- /dev/null +++ b/tools/testing/selftests/firmware/fw_filesystem.sh @@ -0,0 +1,62 @@ +#!/bin/sh +# This validates that the kernel will load firmware out of its list of +# firmware locations on disk. Since the user helper does similar work, +# we reset the custom load directory to a location the user helper doesn't +# know so we can be sure we're not accidentally testing the user helper. +set -e + +modprobe test_firmware + +DIR=/sys/devices/virtual/misc/test_firmware + +OLD_TIMEOUT=$(cat /sys/class/firmware/timeout) +OLD_FWPATH=$(cat /sys/module/firmware_class/parameters/path) + +FWPATH=$(mktemp -d) +FW="$FWPATH/test-firmware.bin" + +test_finish() +{ + echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout + echo -n "$OLD_PATH" >/sys/module/firmware_class/parameters/path + rm -f "$FW" + rmdir "$FWPATH" +} + +trap "test_finish" EXIT + +# Turn down the timeout so failures don't take so long. +echo 1 >/sys/class/firmware/timeout +# Set the kernel search path. +echo -n "$FWPATH" >/sys/module/firmware_class/parameters/path + +# This is an unlikely real-world firmware content. :) +echo "ABCD0123" >"$FW" + +NAME=$(basename "$FW") + +# Request a firmware that doesn't exist, it should fail. +echo -n "nope-$NAME" >"$DIR"/trigger_request +if diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was not expected to match" >&2 + exit 1 +else + echo "$0: timeout works" +fi + +# This should succeed via kernel load or will fail after 1 second after +# being handed over to the user helper, which won't find the fw either. +if ! echo -n "$NAME" >"$DIR"/trigger_request ; then + echo "$0: could not trigger request" >&2 + exit 1 +fi + +# Verify the contents are what we expect. +if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was not loaded" >&2 + exit 1 +else + echo "$0: filesystem loading works" +fi + +exit 0 diff --git a/tools/testing/selftests/firmware/fw_userhelper.sh b/tools/testing/selftests/firmware/fw_userhelper.sh new file mode 100644 index 0000000..6efbade --- /dev/null +++ b/tools/testing/selftests/firmware/fw_userhelper.sh @@ -0,0 +1,89 @@ +#!/bin/sh +# This validates that the kernel will fall back to using the user helper +# to load firmware it can't find on disk itself. We must request a firmware +# that the kernel won't find, and any installed helper (e.g. udev) also +# won't find so that we can do the load ourself manually. +set -e + +modprobe test_firmware + +DIR=/sys/devices/virtual/misc/test_firmware + +OLD_TIMEOUT=$(cat /sys/class/firmware/timeout) + +FWPATH=$(mktemp -d) +FW="$FWPATH/test-firmware.bin" + +test_finish() +{ + echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout + rm -f "$FW" + rmdir "$FWPATH" +} + +load_fw() +{ + local name="$1" + local file="$2" + + # This will block until our load (below) has finished. + echo -n "$name" >"$DIR"/trigger_request & + + # Give kernel a chance to react. + local timeout=10 + while [ ! -e "$DIR"/"$name"/loading ]; do + sleep 0.1 + timeout=$(( $timeout - 1 )) + if [ "$timeout" -eq 0 ]; then + echo "$0: firmware interface never appeared" >&2 + exit 1 + fi + done + + echo 1 >"$DIR"/"$name"/loading + cat "$file" >"$DIR"/"$name"/data + echo 0 >"$DIR"/"$name"/loading + + # Wait for request to finish. + wait +} + +trap "test_finish" EXIT + +# This is an unlikely real-world firmware content. :) +echo "ABCD0123" >"$FW" +NAME=$(basename "$FW") + +# Test failure when doing nothing (timeout works). +echo 1 >/sys/class/firmware/timeout +echo -n "$NAME" >"$DIR"/trigger_request +if diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was not expected to match" >&2 + exit 1 +else + echo "$0: timeout works" +fi + +# Put timeout high enough for us to do work but not so long that failures +# slow down this test too much. +echo 4 >/sys/class/firmware/timeout + +# Load this script instead of the desired firmware. +load_fw "$NAME" "$0" +if diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was not expected to match" >&2 + exit 1 +else + echo "$0: firmware comparison works" +fi + +# Do a proper load, which should work correctly. +load_fw "$NAME" "$FW" +if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was not loaded" >&2 + exit 1 +else + echo "$0: user helper firmware loading works" +fi + +exit 0 diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile new file mode 100644 index 0000000..76cc9f1 --- /dev/null +++ b/tools/testing/selftests/ftrace/Makefile @@ -0,0 +1,7 @@ +all: + +run_tests: + @/bin/sh ./ftracetest || echo "ftrace selftests: [FAIL]" + +clean: + rm -rf logs/* diff --git a/tools/testing/selftests/ftrace/README b/tools/testing/selftests/ftrace/README new file mode 100644 index 0000000..182e76f --- /dev/null +++ b/tools/testing/selftests/ftrace/README @@ -0,0 +1,82 @@ +Linux Ftrace Testcases + +This is a collection of testcases for ftrace tracing feature in the Linux +kernel. Since ftrace exports interfaces via the debugfs, we just need +shell scripts for testing. Feel free to add new test cases. + +Running the ftrace testcases +============================ + +At first, you need to be the root user to run this script. +To run all testcases: + + $ sudo ./ftracetest + +To run specific testcases: + + # ./ftracetest test.d/basic3.tc + +Or you can also run testcases under given directory: + + # ./ftracetest test.d/kprobe/ + +Contributing new testcases +========================== + +Copy test.d/template to your testcase (whose filename must have *.tc +extension) and rewrite the test description line. + + * The working directory of the script is <debugfs>/tracing/. + + * Take care with side effects as the tests are run with root privilege. + + * The tests should not run for a long period of time (more than 1 min.) + These are to be unit tests. + + * You can add a directory for your testcases under test.d/ if needed. + + * The test cases should run on dash (busybox shell) for testing on + minimal cross-build environments. + + * Note that the tests are run with "set -e" (errexit) option. If any + command fails, the test will be terminated immediately. + + * The tests can return some result codes instead of pass or fail by + using exit_unresolved, exit_untested, exit_unsupported and exit_xfail. + +Result code +=========== + +Ftracetest supports following result codes. + + * PASS: The test succeeded as expected. The test which exits with 0 is + counted as passed test. + + * FAIL: The test failed, but was expected to succeed. The test which exits + with !0 is counted as failed test. + + * UNRESOLVED: The test produced unclear or intermidiate results. + for example, the test was interrupted + or the test depends on a previous test, which failed. + or the test was set up incorrectly + The test which is in above situation, must call exit_unresolved. + + * UNTESTED: The test was not run, currently just a placeholder. + In this case, the test must call exit_untested. + + * UNSUPPORTED: The test failed because of lack of feature. + In this case, the test must call exit_unsupported. + + * XFAIL: The test failed, and was expected to fail. + To return XFAIL, call exit_xfail from the test. + +There are some sample test scripts for result code under samples/. +You can also run samples as below: + + # ./ftracetest samples/ + +TODO +==== + + * Fancy colored output :) + diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest new file mode 100755 index 0000000..da48812 --- /dev/null +++ b/tools/testing/selftests/ftrace/ftracetest @@ -0,0 +1,270 @@ +#!/bin/sh + +# ftracetest - Ftrace test shell scripts +# +# Copyright (C) Hitachi Ltd., 2014 +# Written by Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> +# +# Released under the terms of the GPL v2. + +usage() { # errno [message] +[ "$2" ] && echo $2 +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 +} + +errexit() { # message + echo "Error: $1" 1>&2 + exit 1 +} + +# Ensuring user privilege +if [ `id -u` -ne 0 ]; then + errexit "this must be run by root user" +fi + +# Utilities +absdir() { # file_path + (cd `dirname $1`; pwd) +} + +abspath() { + echo `absdir $1`/`basename $1` +} + +find_testcases() { #directory + echo `find $1 -name \*.tc | sort` +} + +parse_opts() { # opts + local OPT_TEST_CASES= + local OPT_TEST_DIR= + + while [ "$1" ]; do + case "$1" in + --help|-h) + usage 0 + ;; + --keep|-k) + KEEP_LOG=1 + shift 1 + ;; + --verbose|-v) + VERBOSE=1 + shift 1 + ;; + --debug|-d) + DEBUG=1 + shift 1 + ;; + *.tc) + if [ -f "$1" ]; then + OPT_TEST_CASES="$OPT_TEST_CASES `abspath $1`" + shift 1 + else + usage 1 "$1 is not a testcase" + fi + ;; + *) + if [ -d "$1" ]; then + OPT_TEST_DIR=`abspath $1` + OPT_TEST_CASES="$OPT_TEST_CASES `find_testcases $OPT_TEST_DIR`" + shift 1 + else + usage 1 "Invalid option ($1)" + fi + ;; + esac + done + if [ "$OPT_TEST_CASES" ]; then + TEST_CASES=$OPT_TEST_CASES + fi +} + +# Parameters +DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' ' | head -1` +TRACING_DIR=$DEBUGFS_DIR/tracing +TOP_DIR=`absdir $0` +TEST_DIR=$TOP_DIR/test.d +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 $* + +[ $DEBUG -ne 0 ] && set -x + +# Verify parameters +if [ -z "$DEBUGFS_DIR" -o ! -d "$TRACING_DIR" ]; then + errexit "No ftrace directory found" +fi + +# Preparing logs +LOG_FILE=$LOG_DIR/ftracetest.log +mkdir -p $LOG_DIR || errexit "Failed to make a log directory: $LOG_DIR" +date > $LOG_FILE +prlog() { # messages + echo "$@" | tee -a $LOG_FILE +} +catlog() { #file + cat $1 | tee -a $LOG_FILE +} +prlog "=== Ftrace unit tests ===" + + +# Testcase management +# Test result codes - Dejagnu extended code +PASS=0 # The test succeeded. +FAIL=1 # The test failed, but was expected to succeed. +UNRESOLVED=2 # The test produced indeterminate results. (e.g. interrupted) +UNTESTED=3 # The test was not run, currently just a placeholder. +UNSUPPORTED=4 # The test failed because of lack of feature. +XFAIL=5 # The test failed, and was expected to fail. + +# Accumulations +PASSED_CASES= +FAILED_CASES= +UNRESOLVED_CASES= +UNTESTED_CASES= +UNSUPPORTED_CASES= +XFAILED_CASES= +UNDEFINED_CASES= +TOTAL_RESULT=0 + +CASENO=0 +testcase() { # testfile + CASENO=$((CASENO+1)) + desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:` + prlog -n "[$CASENO]$desc" +} + +eval_result() { # sigval + case $1 in + $PASS) + prlog " [PASS]" + PASSED_CASES="$PASSED_CASES $CASENO" + return 0 + ;; + $FAIL) + prlog " [FAIL]" + FAILED_CASES="$FAILED_CASES $CASENO" + return 1 # this is a bug. + ;; + $UNRESOLVED) + prlog " [UNRESOLVED]" + UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" + return 1 # this is a kind of bug.. something happened. + ;; + $UNTESTED) + prlog " [UNTESTED]" + UNTESTED_CASES="$UNTESTED_CASES $CASENO" + return 0 + ;; + $UNSUPPORTED) + prlog " [UNSUPPORTED]" + UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" + return 1 # this is not a bug, but the result should be reported. + ;; + $XFAIL) + prlog " [XFAIL]" + XFAILED_CASES="$XFAILED_CASES $CASENO" + return 0 + ;; + *) + prlog " [UNDEFINED]" + UNDEFINED_CASES="$UNDEFINED_CASES $CASENO" + return 1 # this must be a test bug + ;; + esac +} + +# Signal handling for result codes +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 $SIG_PID + exit 0 +} +trap 'SIG_RESULT=$UNRESOLVED' $SIG_UNRESOLVED + +SIG_UNTESTED=$((SIG_BASE + UNTESTED)) +exit_untested () { + kill -s $SIG_UNTESTED $SIG_PID + exit 0 +} +trap 'SIG_RESULT=$UNTESTED' $SIG_UNTESTED + +SIG_UNSUPPORTED=$((SIG_BASE + UNSUPPORTED)) +exit_unsupported () { + kill -s $SIG_UNSUPPORTED $SIG_PID + exit 0 +} +trap 'SIG_RESULT=$UNSUPPORTED' $SIG_UNSUPPORTED + +SIG_XFAIL=$((SIG_BASE + XFAIL)) +exit_xfail () { + kill -s $SIG_XFAIL $SIG_PID + exit 0 +} +trap 'SIG_RESULT=$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 $LOG_DIR/${testname}-log.XXXXXX` + testcase $1 + echo "execute: "$1 > $testlog + SIG_RESULT=0 + 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 + else + catlog $testlog + TOTAL_RESULT=1 + fi +} + +# load in the helper functions +. $TEST_DIR/functions + +# Main loop +for t in $TEST_CASES; do + run_test $t +done + +prlog "" +prlog "# of passed: " `echo $PASSED_CASES | wc -w` +prlog "# of failed: " `echo $FAILED_CASES | wc -w` +prlog "# of unresolved: " `echo $UNRESOLVED_CASES | wc -w` +prlog "# of untested: " `echo $UNTESTED_CASES | wc -w` +prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` +prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` +prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` + +# if no error, return 0 +exit $TOTAL_RESULT diff --git a/tools/testing/selftests/ftrace/samples/fail.tc b/tools/testing/selftests/ftrace/samples/fail.tc new file mode 100644 index 0000000..15e35b9 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/fail.tc @@ -0,0 +1,4 @@ +#!/bin/sh +# description: failure-case example +cat non-exist-file +echo "this is not executed" diff --git a/tools/testing/selftests/ftrace/samples/pass.tc b/tools/testing/selftests/ftrace/samples/pass.tc new file mode 100644 index 0000000..d015493 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/pass.tc @@ -0,0 +1,3 @@ +#!/bin/sh +# description: pass-case example +return 0 diff --git a/tools/testing/selftests/ftrace/samples/unresolved.tc b/tools/testing/selftests/ftrace/samples/unresolved.tc new file mode 100644 index 0000000..41e99d3 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/unresolved.tc @@ -0,0 +1,4 @@ +#!/bin/sh +# description: unresolved-case example +trap exit_unresolved INT +kill -INT $PID diff --git a/tools/testing/selftests/ftrace/samples/unsupported.tc b/tools/testing/selftests/ftrace/samples/unsupported.tc new file mode 100644 index 0000000..45910ff --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/unsupported.tc @@ -0,0 +1,3 @@ +#!/bin/sh +# description: unsupported-case example +exit_unsupported diff --git a/tools/testing/selftests/ftrace/samples/untested.tc b/tools/testing/selftests/ftrace/samples/untested.tc new file mode 100644 index 0000000..35a4594 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/untested.tc @@ -0,0 +1,3 @@ +#!/bin/sh +# description: untested-case example +exit_untested diff --git a/tools/testing/selftests/ftrace/samples/xfail.tc b/tools/testing/selftests/ftrace/samples/xfail.tc new file mode 100644 index 0000000..9dd3953 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/xfail.tc @@ -0,0 +1,3 @@ +#!/bin/sh +# description: xfail-case example +cat non-exist-file || exit_xfail diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc new file mode 100644 index 0000000..9980ff1 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc @@ -0,0 +1,3 @@ +#!/bin/sh +# description: Basic trace file check +test -f README -a -f trace -a -f tracing_on -a -f trace_pipe diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc new file mode 100644 index 0000000..bf9a7b0 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc @@ -0,0 +1,7 @@ +#!/bin/sh +# description: Basic test for tracers +test -f available_tracers +for t in `cat available_tracers`; do + echo $t > current_tracer +done +echo nop > current_tracer diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc new file mode 100644 index 0000000..bde6625 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc @@ -0,0 +1,8 @@ +#!/bin/sh +# description: Basic trace clock test +test -f trace_clock +for c in `cat trace_clock | tr -d \[\]`; do + echo $c > trace_clock + grep '\['$c'\]' trace_clock +done +echo local > trace_clock 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 0000000..fd9c49a --- /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 -1
\ No newline at end of file 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 0000000..668616d --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc @@ -0,0 +1,53 @@ +#!/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 -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 +usleep 1 + +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 +usleep 1 + +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 +usleep 1 + +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 0000000..655c415 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -0,0 +1,53 @@ +#!/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 -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 +usleep 1 + +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 +usleep 1 + +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 +usleep 1 + +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 0000000..4808457 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc @@ -0,0 +1,47 @@ +#!/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 -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 +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 +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 +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 0000000..c15e018 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc @@ -0,0 +1,89 @@ +#!/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 + echo 0 > /proc/sys/kernel/stack_tracer_enabled + enable_tracing + clear_trace + echo > set_ftrace_filter +} + +fail() { # msg + do_reset + echo $1 + exit -1 +} + +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 0000000..6af5f63 --- /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 -1 +} + +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 0000000..2e719cb --- /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 -1 +} + +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 0000000..5d8cd06 --- /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 new file mode 100644 index 0000000..a5a4262 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc @@ -0,0 +1,12 @@ +#!/bin/sh +# description: Kprobe dynamic event - adding and removing + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +echo 0 > events/enable +echo > kprobe_events +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 new file mode 100644 index 0000000..d8c7bb6 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc @@ -0,0 +1,14 @@ +#!/bin/sh +# description: Kprobe dynamic event - busy event check + +[ -f kprobe_events ] || exit_unsupported + +echo 0 > events/enable +echo > kprobe_events +echo p:myevent do_fork > kprobe_events +test -d events/kprobes/myevent +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 new file mode 100644 index 0000000..c45ee27 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc @@ -0,0 +1,17 @@ +#!/bin/sh +# description: Kprobe dynamic event with arguments + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +echo 0 > events/enable +echo > kprobe_events +echo 'p:testprobe do_fork $stack $stack0 +0($stack)' > kprobe_events +grep testprobe kprobe_events +test -d events/kprobes/testprobe +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 0000000..ab41d2b --- /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 new file mode 100644 index 0000000..3171798 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc @@ -0,0 +1,16 @@ +#!/bin/sh +# description: Kretprobe dynamic event with arguments + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +echo 0 > events/enable +echo > kprobe_events +echo 'r:testprobe2 do_fork $retval' > kprobe_events +grep testprobe2 kprobe_events +test -d events/kprobes/testprobe2 +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/ftrace/test.d/template b/tools/testing/selftests/ftrace/test.d/template new file mode 100644 index 0000000..5448f7a --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/template @@ -0,0 +1,9 @@ +#!/bin/sh +# description: %HERE DESCRIBE WHAT THIS DOES% +# you have to add ".tc" extention for your testcase file +# Note that all tests are run with "errexit" option. + +exit 0 # Return 0 if the test is passed, otherwise return !0 +# If the test could not run because of lack of feature, call exit_unsupported +# If the test returned unclear results, call exit_unresolved +# If the test is a dummy, or a placeholder, call exit_untested diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile index 5386fd7..74bbefd 100644 --- a/tools/testing/selftests/ipc/Makefile +++ b/tools/testing/selftests/ipc/Makefile @@ -1,18 +1,18 @@ 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 + ARCH := x86 CFLAGS := -DCONFIG_X86_32 -D__i386__ endif ifeq ($(ARCH),x86_64) - ARCH := X86 + ARCH := x86 CFLAGS := -DCONFIG_X86_64 -D__x86_64__ endif CFLAGS += -I../../../../usr/include/ all: -ifeq ($(ARCH),X86) +ifeq ($(ARCH),x86) gcc $(CFLAGS) msgque.c -o msgque_test else echo "Not an x86 target, can't build msgque selftest" diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c index 552f081..1b2ce33 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 d7d6bbe..ff0eefd 100644 --- a/tools/testing/selftests/kcmp/Makefile +++ b/tools/testing/selftests/kcmp/Makefile @@ -1,25 +1,7 @@ -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/ +CC := $(CROSS_COMPILE)$(CC) 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 run_tests: all @./kcmp_test || echo "kcmp_test: [FAIL]" diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c index fa4f1b3..a5a4da8 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 %li returned (%s)\n", + 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 0000000..572c888 --- /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/memfd/.gitignore b/tools/testing/selftests/memfd/.gitignore new file mode 100644 index 0000000..afe87c4 --- /dev/null +++ b/tools/testing/selftests/memfd/.gitignore @@ -0,0 +1,4 @@ +fuse_mnt +fuse_test +memfd_test +memfd-test-file diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile new file mode 100644 index 0000000..b80cd10 --- /dev/null +++ b/tools/testing/selftests/memfd/Makefile @@ -0,0 +1,20 @@ +CFLAGS += -D_FILE_OFFSET_BITS=64 +CFLAGS += -I../../../../include/uapi/ +CFLAGS += -I../../../../include/ + +all: + gcc $(CFLAGS) memfd_test.c -o memfd_test + +run_tests: all + gcc $(CFLAGS) memfd_test.c -o memfd_test + @./memfd_test || echo "memfd_test: [FAIL]" + +build_fuse: + gcc $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt + gcc $(CFLAGS) fuse_test.c -o fuse_test + +run_fuse: build_fuse + @./run_fuse_test.sh || echo "fuse_test: [FAIL]" + +clean: + $(RM) memfd_test fuse_test diff --git a/tools/testing/selftests/memfd/fuse_mnt.c b/tools/testing/selftests/memfd/fuse_mnt.c new file mode 100644 index 0000000..feacf12 --- /dev/null +++ b/tools/testing/selftests/memfd/fuse_mnt.c @@ -0,0 +1,110 @@ +/* + * memfd test file-system + * This file uses FUSE to create a dummy file-system with only one file /memfd. + * This file is read-only and takes 1s per read. + * + * This file-system is used by the memfd test-cases to force the kernel to pin + * pages during reads(). Due to the 1s delay of this file-system, this is a + * nice way to test race-conditions against get_user_pages() in the kernel. + * + * We use direct_io==1 to force the kernel to use direct-IO for this + * file-system. + */ + +#define FUSE_USE_VERSION 26 + +#include <fuse.h> +#include <stdio.h> +#include <string.h> +#include <errno.h> +#include <fcntl.h> +#include <unistd.h> + +static const char memfd_content[] = "memfd-example-content"; +static const char memfd_path[] = "/memfd"; + +static int memfd_getattr(const char *path, struct stat *st) +{ + memset(st, 0, sizeof(*st)); + + if (!strcmp(path, "/")) { + st->st_mode = S_IFDIR | 0755; + st->st_nlink = 2; + } else if (!strcmp(path, memfd_path)) { + st->st_mode = S_IFREG | 0444; + st->st_nlink = 1; + st->st_size = strlen(memfd_content); + } else { + return -ENOENT; + } + + return 0; +} + +static int memfd_readdir(const char *path, + void *buf, + fuse_fill_dir_t filler, + off_t offset, + struct fuse_file_info *fi) +{ + if (strcmp(path, "/")) + return -ENOENT; + + filler(buf, ".", NULL, 0); + filler(buf, "..", NULL, 0); + filler(buf, memfd_path + 1, NULL, 0); + + return 0; +} + +static int memfd_open(const char *path, struct fuse_file_info *fi) +{ + if (strcmp(path, memfd_path)) + return -ENOENT; + + if ((fi->flags & 3) != O_RDONLY) + return -EACCES; + + /* force direct-IO */ + fi->direct_io = 1; + + return 0; +} + +static int memfd_read(const char *path, + char *buf, + size_t size, + off_t offset, + struct fuse_file_info *fi) +{ + size_t len; + + if (strcmp(path, memfd_path) != 0) + return -ENOENT; + + sleep(1); + + len = strlen(memfd_content); + if (offset < len) { + if (offset + size > len) + size = len - offset; + + memcpy(buf, memfd_content + offset, size); + } else { + size = 0; + } + + return size; +} + +static struct fuse_operations memfd_ops = { + .getattr = memfd_getattr, + .readdir = memfd_readdir, + .open = memfd_open, + .read = memfd_read, +}; + +int main(int argc, char *argv[]) +{ + return fuse_main(argc, argv, &memfd_ops, NULL); +} diff --git a/tools/testing/selftests/memfd/fuse_test.c b/tools/testing/selftests/memfd/fuse_test.c new file mode 100644 index 0000000..67908b1 --- /dev/null +++ b/tools/testing/selftests/memfd/fuse_test.c @@ -0,0 +1,311 @@ +/* + * memfd GUP test-case + * This tests memfd interactions with get_user_pages(). We require the + * fuse_mnt.c program to provide a fake direct-IO FUSE mount-point for us. This + * file-system delays _all_ reads by 1s and forces direct-IO. This means, any + * read() on files in that file-system will pin the receive-buffer pages for at + * least 1s via get_user_pages(). + * + * We use this trick to race ADD_SEALS against a write on a memfd object. The + * ADD_SEALS must fail if the memfd pages are still pinned. Note that we use + * the read() syscall with our memory-mapped memfd object as receive buffer to + * force the kernel to write into our memfd object. + */ + +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + +#include <errno.h> +#include <inttypes.h> +#include <limits.h> +#include <linux/falloc.h> +#include <linux/fcntl.h> +#include <linux/memfd.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/wait.h> +#include <unistd.h> + +#define MFD_DEF_SIZE 8192 +#define STACK_SIZE 65535 + +static int sys_memfd_create(const char *name, + unsigned int flags) +{ + return syscall(__NR_memfd_create, name, flags); +} + +static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags) +{ + int r, fd; + + fd = sys_memfd_create(name, flags); + if (fd < 0) { + printf("memfd_create(\"%s\", %u) failed: %m\n", + name, flags); + abort(); + } + + r = ftruncate(fd, sz); + if (r < 0) { + printf("ftruncate(%llu) failed: %m\n", (unsigned long long)sz); + abort(); + } + + return fd; +} + +static __u64 mfd_assert_get_seals(int fd) +{ + long r; + + r = fcntl(fd, F_GET_SEALS); + if (r < 0) { + printf("GET_SEALS(%d) failed: %m\n", fd); + abort(); + } + + return r; +} + +static void mfd_assert_has_seals(int fd, __u64 seals) +{ + __u64 s; + + s = mfd_assert_get_seals(fd); + if (s != seals) { + printf("%llu != %llu = GET_SEALS(%d)\n", + (unsigned long long)seals, (unsigned long long)s, fd); + abort(); + } +} + +static void mfd_assert_add_seals(int fd, __u64 seals) +{ + long r; + __u64 s; + + s = mfd_assert_get_seals(fd); + r = fcntl(fd, F_ADD_SEALS, seals); + if (r < 0) { + printf("ADD_SEALS(%d, %llu -> %llu) failed: %m\n", + fd, (unsigned long long)s, (unsigned long long)seals); + abort(); + } +} + +static int mfd_busy_add_seals(int fd, __u64 seals) +{ + long r; + __u64 s; + + r = fcntl(fd, F_GET_SEALS); + if (r < 0) + s = 0; + else + s = r; + + r = fcntl(fd, F_ADD_SEALS, seals); + if (r < 0 && errno != EBUSY) { + printf("ADD_SEALS(%d, %llu -> %llu) didn't fail as expected with EBUSY: %m\n", + fd, (unsigned long long)s, (unsigned long long)seals); + abort(); + } + + return r; +} + +static void *mfd_assert_mmap_shared(int fd) +{ + void *p; + + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + +static void *mfd_assert_mmap_private(int fd) +{ + void *p; + + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + +static int global_mfd = -1; +static void *global_p = NULL; + +static int sealing_thread_fn(void *arg) +{ + int sig, r; + + /* + * This thread first waits 200ms so any pending operation in the parent + * is correctly started. After that, it tries to seal @global_mfd as + * SEAL_WRITE. This _must_ fail as the parent thread has a read() into + * that memory mapped object still ongoing. + * We then wait one more second and try sealing again. This time it + * must succeed as there shouldn't be anyone else pinning the pages. + */ + + /* wait 200ms for FUSE-request to be active */ + usleep(200000); + + /* unmount mapping before sealing to avoid i_mmap_writable failures */ + munmap(global_p, MFD_DEF_SIZE); + + /* Try sealing the global file; expect EBUSY or success. Current + * kernels will never succeed, but in the future, kernels might + * implement page-replacements or other fancy ways to avoid racing + * writes. */ + r = mfd_busy_add_seals(global_mfd, F_SEAL_WRITE); + if (r >= 0) { + printf("HURRAY! This kernel fixed GUP races!\n"); + } else { + /* wait 1s more so the FUSE-request is done */ + sleep(1); + + /* try sealing the global file again */ + mfd_assert_add_seals(global_mfd, F_SEAL_WRITE); + } + + return 0; +} + +static pid_t spawn_sealing_thread(void) +{ + uint8_t *stack; + pid_t pid; + + stack = malloc(STACK_SIZE); + if (!stack) { + printf("malloc(STACK_SIZE) failed: %m\n"); + abort(); + } + + pid = clone(sealing_thread_fn, + stack + STACK_SIZE, + SIGCHLD | CLONE_FILES | CLONE_FS | CLONE_VM, + NULL); + if (pid < 0) { + printf("clone() failed: %m\n"); + abort(); + } + + return pid; +} + +static void join_sealing_thread(pid_t pid) +{ + waitpid(pid, NULL, 0); +} + +int main(int argc, char **argv) +{ + static const char zero[MFD_DEF_SIZE]; + int fd, mfd, r; + void *p; + int was_sealed; + pid_t pid; + + if (argc < 2) { + printf("error: please pass path to file in fuse_mnt mount-point\n"); + abort(); + } + + /* open FUSE memfd file for GUP testing */ + printf("opening: %s\n", argv[1]); + fd = open(argv[1], O_RDONLY | O_CLOEXEC); + if (fd < 0) { + printf("cannot open(\"%s\"): %m\n", argv[1]); + abort(); + } + + /* create new memfd-object */ + mfd = mfd_assert_new("kern_memfd_fuse", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + /* mmap memfd-object for writing */ + p = mfd_assert_mmap_shared(mfd); + + /* pass mfd+mapping to a separate sealing-thread which tries to seal + * the memfd objects with SEAL_WRITE while we write into it */ + global_mfd = mfd; + global_p = p; + pid = spawn_sealing_thread(); + + /* Use read() on the FUSE file to read into our memory-mapped memfd + * object. This races the other thread which tries to seal the + * memfd-object. + * If @fd is on the memfd-fake-FUSE-FS, the read() is delayed by 1s. + * This guarantees that the receive-buffer is pinned for 1s until the + * data is written into it. The racing ADD_SEALS should thus fail as + * the pages are still pinned. */ + r = read(fd, p, MFD_DEF_SIZE); + if (r < 0) { + printf("read() failed: %m\n"); + abort(); + } else if (!r) { + printf("unexpected EOF on read()\n"); + abort(); + } + + was_sealed = mfd_assert_get_seals(mfd) & F_SEAL_WRITE; + + /* Wait for sealing-thread to finish and verify that it + * successfully sealed the file after the second try. */ + join_sealing_thread(pid); + mfd_assert_has_seals(mfd, F_SEAL_WRITE); + + /* *IF* the memfd-object was sealed at the time our read() returned, + * then the kernel did a page-replacement or canceled the read() (or + * whatever magic it did..). In that case, the memfd object is still + * all zero. + * In case the memfd-object was *not* sealed, the read() was successfull + * and the memfd object must *not* be all zero. + * Note that in real scenarios, there might be a mixture of both, but + * in this test-cases, we have explicit 200ms delays which should be + * enough to avoid any in-flight writes. */ + + p = mfd_assert_mmap_private(mfd); + if (was_sealed && memcmp(p, zero, MFD_DEF_SIZE)) { + printf("memfd sealed during read() but data not discarded\n"); + abort(); + } else if (!was_sealed && !memcmp(p, zero, MFD_DEF_SIZE)) { + printf("memfd sealed after read() but data discarded\n"); + abort(); + } + + close(mfd); + close(fd); + + printf("fuse: DONE\n"); + + return 0; +} diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c new file mode 100644 index 0000000..0b9eafb --- /dev/null +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -0,0 +1,911 @@ +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + +#include <errno.h> +#include <inttypes.h> +#include <limits.h> +#include <linux/falloc.h> +#include <linux/fcntl.h> +#include <linux/memfd.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <unistd.h> + +#define MFD_DEF_SIZE 8192 +#define STACK_SIZE 65535 + +static int sys_memfd_create(const char *name, + unsigned int flags) +{ + return syscall(__NR_memfd_create, name, flags); +} + +static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags) +{ + int r, fd; + + fd = sys_memfd_create(name, flags); + if (fd < 0) { + printf("memfd_create(\"%s\", %u) failed: %m\n", + name, flags); + abort(); + } + + r = ftruncate(fd, sz); + if (r < 0) { + printf("ftruncate(%llu) failed: %m\n", (unsigned long long)sz); + abort(); + } + + return fd; +} + +static void mfd_fail_new(const char *name, unsigned int flags) +{ + int r; + + r = sys_memfd_create(name, flags); + if (r >= 0) { + printf("memfd_create(\"%s\", %u) succeeded, but failure expected\n", + name, flags); + close(r); + abort(); + } +} + +static unsigned int mfd_assert_get_seals(int fd) +{ + int r; + + r = fcntl(fd, F_GET_SEALS); + if (r < 0) { + printf("GET_SEALS(%d) failed: %m\n", fd); + abort(); + } + + return (unsigned int)r; +} + +static void mfd_assert_has_seals(int fd, unsigned int seals) +{ + unsigned int s; + + s = mfd_assert_get_seals(fd); + if (s != seals) { + printf("%u != %u = GET_SEALS(%d)\n", seals, s, fd); + abort(); + } +} + +static void mfd_assert_add_seals(int fd, unsigned int seals) +{ + int r; + unsigned int s; + + s = mfd_assert_get_seals(fd); + r = fcntl(fd, F_ADD_SEALS, seals); + if (r < 0) { + printf("ADD_SEALS(%d, %u -> %u) failed: %m\n", fd, s, seals); + abort(); + } +} + +static void mfd_fail_add_seals(int fd, unsigned int seals) +{ + int r; + unsigned int s; + + r = fcntl(fd, F_GET_SEALS); + if (r < 0) + s = 0; + else + s = (unsigned int)r; + + r = fcntl(fd, F_ADD_SEALS, seals); + if (r >= 0) { + printf("ADD_SEALS(%d, %u -> %u) didn't fail as expected\n", + fd, s, seals); + abort(); + } +} + +static void mfd_assert_size(int fd, size_t size) +{ + struct stat st; + int r; + + r = fstat(fd, &st); + if (r < 0) { + printf("fstat(%d) failed: %m\n", fd); + abort(); + } else if (st.st_size != size) { + printf("wrong file size %lld, but expected %lld\n", + (long long)st.st_size, (long long)size); + abort(); + } +} + +static int mfd_assert_dup(int fd) +{ + int r; + + r = dup(fd); + if (r < 0) { + printf("dup(%d) failed: %m\n", fd); + abort(); + } + + return r; +} + +static void *mfd_assert_mmap_shared(int fd) +{ + void *p; + + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + +static void *mfd_assert_mmap_private(int fd) +{ + void *p; + + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ, + MAP_PRIVATE, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + +static int mfd_assert_open(int fd, int flags, mode_t mode) +{ + char buf[512]; + int r; + + sprintf(buf, "/proc/self/fd/%d", fd); + r = open(buf, flags, mode); + if (r < 0) { + printf("open(%s) failed: %m\n", buf); + abort(); + } + + return r; +} + +static void mfd_fail_open(int fd, int flags, mode_t mode) +{ + char buf[512]; + int r; + + sprintf(buf, "/proc/self/fd/%d", fd); + r = open(buf, flags, mode); + if (r >= 0) { + printf("open(%s) didn't fail as expected\n", buf); + abort(); + } +} + +static void mfd_assert_read(int fd) +{ + char buf[16]; + void *p; + ssize_t l; + + l = read(fd, buf, sizeof(buf)); + if (l != sizeof(buf)) { + printf("read() failed: %m\n"); + abort(); + } + + /* verify PROT_READ *is* allowed */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ, + MAP_PRIVATE, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + munmap(p, MFD_DEF_SIZE); + + /* verify MAP_PRIVATE is *always* allowed (even writable) */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + munmap(p, MFD_DEF_SIZE); +} + +static void mfd_assert_write(int fd) +{ + ssize_t l; + void *p; + int r; + + /* verify write() succeeds */ + l = write(fd, "\0\0\0\0", 4); + if (l != 4) { + printf("write() failed: %m\n"); + abort(); + } + + /* verify PROT_READ | PROT_WRITE is allowed */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + *(char *)p = 0; + munmap(p, MFD_DEF_SIZE); + + /* verify PROT_WRITE is allowed */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + *(char *)p = 0; + munmap(p, MFD_DEF_SIZE); + + /* verify PROT_READ with MAP_SHARED is allowed and a following + * mprotect(PROT_WRITE) allows writing */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE); + if (r < 0) { + printf("mprotect() failed: %m\n"); + abort(); + } + + *(char *)p = 0; + munmap(p, MFD_DEF_SIZE); + + /* verify PUNCH_HOLE works */ + r = fallocate(fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + 0, + MFD_DEF_SIZE); + if (r < 0) { + printf("fallocate(PUNCH_HOLE) failed: %m\n"); + abort(); + } +} + +static void mfd_fail_write(int fd) +{ + ssize_t l; + void *p; + int r; + + /* verify write() fails */ + l = write(fd, "data", 4); + if (l != -EPERM) { + printf("expected EPERM on write(), but got %d: %m\n", (int)l); + abort(); + } + + /* verify PROT_READ | PROT_WRITE is not allowed */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p != MAP_FAILED) { + printf("mmap() didn't fail as expected\n"); + abort(); + } + + /* verify PROT_WRITE is not allowed */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p != MAP_FAILED) { + printf("mmap() didn't fail as expected\n"); + abort(); + } + + /* Verify PROT_READ with MAP_SHARED with a following mprotect is not + * allowed. Note that for r/w the kernel already prevents the mmap. */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ, + MAP_SHARED, + fd, + 0); + if (p != MAP_FAILED) { + r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE); + if (r >= 0) { + printf("mmap()+mprotect() didn't fail as expected\n"); + abort(); + } + } + + /* verify PUNCH_HOLE fails */ + r = fallocate(fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + 0, + MFD_DEF_SIZE); + if (r >= 0) { + printf("fallocate(PUNCH_HOLE) didn't fail as expected\n"); + abort(); + } +} + +static void mfd_assert_shrink(int fd) +{ + int r, fd2; + + r = ftruncate(fd, MFD_DEF_SIZE / 2); + if (r < 0) { + printf("ftruncate(SHRINK) failed: %m\n"); + abort(); + } + + mfd_assert_size(fd, MFD_DEF_SIZE / 2); + + fd2 = mfd_assert_open(fd, + O_RDWR | O_CREAT | O_TRUNC, + S_IRUSR | S_IWUSR); + close(fd2); + + mfd_assert_size(fd, 0); +} + +static void mfd_fail_shrink(int fd) +{ + int r; + + r = ftruncate(fd, MFD_DEF_SIZE / 2); + if (r >= 0) { + printf("ftruncate(SHRINK) didn't fail as expected\n"); + abort(); + } + + mfd_fail_open(fd, + O_RDWR | O_CREAT | O_TRUNC, + S_IRUSR | S_IWUSR); +} + +static void mfd_assert_grow(int fd) +{ + int r; + + r = ftruncate(fd, MFD_DEF_SIZE * 2); + if (r < 0) { + printf("ftruncate(GROW) failed: %m\n"); + abort(); + } + + mfd_assert_size(fd, MFD_DEF_SIZE * 2); + + r = fallocate(fd, + 0, + 0, + MFD_DEF_SIZE * 4); + if (r < 0) { + printf("fallocate(ALLOC) failed: %m\n"); + abort(); + } + + mfd_assert_size(fd, MFD_DEF_SIZE * 4); +} + +static void mfd_fail_grow(int fd) +{ + int r; + + r = ftruncate(fd, MFD_DEF_SIZE * 2); + if (r >= 0) { + printf("ftruncate(GROW) didn't fail as expected\n"); + abort(); + } + + r = fallocate(fd, + 0, + 0, + MFD_DEF_SIZE * 4); + if (r >= 0) { + printf("fallocate(ALLOC) didn't fail as expected\n"); + abort(); + } +} + +static void mfd_assert_grow_write(int fd) +{ + static char buf[MFD_DEF_SIZE * 8]; + ssize_t l; + + l = pwrite(fd, buf, sizeof(buf), 0); + if (l != sizeof(buf)) { + printf("pwrite() failed: %m\n"); + abort(); + } + + mfd_assert_size(fd, MFD_DEF_SIZE * 8); +} + +static void mfd_fail_grow_write(int fd) +{ + static char buf[MFD_DEF_SIZE * 8]; + ssize_t l; + + l = pwrite(fd, buf, sizeof(buf), 0); + if (l == sizeof(buf)) { + printf("pwrite() didn't fail as expected\n"); + abort(); + } +} + +static int idle_thread_fn(void *arg) +{ + sigset_t set; + int sig; + + /* dummy waiter; SIGTERM terminates us anyway */ + sigemptyset(&set); + sigaddset(&set, SIGTERM); + sigwait(&set, &sig); + + return 0; +} + +static pid_t spawn_idle_thread(unsigned int flags) +{ + uint8_t *stack; + pid_t pid; + + stack = malloc(STACK_SIZE); + if (!stack) { + printf("malloc(STACK_SIZE) failed: %m\n"); + abort(); + } + + pid = clone(idle_thread_fn, + stack + STACK_SIZE, + SIGCHLD | flags, + NULL); + if (pid < 0) { + printf("clone() failed: %m\n"); + abort(); + } + + return pid; +} + +static void join_idle_thread(pid_t pid) +{ + kill(pid, SIGTERM); + waitpid(pid, NULL, 0); +} + +/* + * Test memfd_create() syscall + * Verify syscall-argument validation, including name checks, flag validation + * and more. + */ +static void test_create(void) +{ + char buf[2048]; + int fd; + + /* test NULL name */ + mfd_fail_new(NULL, 0); + + /* test over-long name (not zero-terminated) */ + memset(buf, 0xff, sizeof(buf)); + mfd_fail_new(buf, 0); + + /* test over-long zero-terminated name */ + memset(buf, 0xff, sizeof(buf)); + buf[sizeof(buf) - 1] = 0; + mfd_fail_new(buf, 0); + + /* verify "" is a valid name */ + fd = mfd_assert_new("", 0, 0); + close(fd); + + /* verify invalid O_* open flags */ + mfd_fail_new("", 0x0100); + mfd_fail_new("", ~MFD_CLOEXEC); + mfd_fail_new("", ~MFD_ALLOW_SEALING); + mfd_fail_new("", ~0); + mfd_fail_new("", 0x80000000U); + + /* verify MFD_CLOEXEC is allowed */ + fd = mfd_assert_new("", 0, MFD_CLOEXEC); + close(fd); + + /* verify MFD_ALLOW_SEALING is allowed */ + fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING); + close(fd); + + /* verify MFD_ALLOW_SEALING | MFD_CLOEXEC is allowed */ + fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING | MFD_CLOEXEC); + close(fd); +} + +/* + * Test basic sealing + * A very basic sealing test to see whether setting/retrieving seals works. + */ +static void test_basic(void) +{ + int fd; + + fd = mfd_assert_new("kern_memfd_basic", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + /* add basic seals */ + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_SHRINK | + F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_SHRINK | + F_SEAL_WRITE); + + /* add them again */ + mfd_assert_add_seals(fd, F_SEAL_SHRINK | + F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_SHRINK | + F_SEAL_WRITE); + + /* add more seals and seal against sealing */ + mfd_assert_add_seals(fd, F_SEAL_GROW | F_SEAL_SEAL); + mfd_assert_has_seals(fd, F_SEAL_SHRINK | + F_SEAL_GROW | + F_SEAL_WRITE | + F_SEAL_SEAL); + + /* verify that sealing no longer works */ + mfd_fail_add_seals(fd, F_SEAL_GROW); + mfd_fail_add_seals(fd, 0); + + close(fd); + + /* verify sealing does not work without MFD_ALLOW_SEALING */ + fd = mfd_assert_new("kern_memfd_basic", + MFD_DEF_SIZE, + MFD_CLOEXEC); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + mfd_fail_add_seals(fd, F_SEAL_SHRINK | + F_SEAL_GROW | + F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + close(fd); +} + +/* + * Test SEAL_WRITE + * Test whether SEAL_WRITE actually prevents modifications. + */ +static void test_seal_write(void) +{ + int fd; + + fd = mfd_assert_new("kern_memfd_seal_write", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + + mfd_assert_read(fd); + mfd_fail_write(fd); + mfd_assert_shrink(fd); + mfd_assert_grow(fd); + mfd_fail_grow_write(fd); + + close(fd); +} + +/* + * Test SEAL_SHRINK + * Test whether SEAL_SHRINK actually prevents shrinking + */ +static void test_seal_shrink(void) +{ + int fd; + + fd = mfd_assert_new("kern_memfd_seal_shrink", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_SHRINK); + mfd_assert_has_seals(fd, F_SEAL_SHRINK); + + mfd_assert_read(fd); + mfd_assert_write(fd); + mfd_fail_shrink(fd); + mfd_assert_grow(fd); + mfd_assert_grow_write(fd); + + close(fd); +} + +/* + * Test SEAL_GROW + * Test whether SEAL_GROW actually prevents growing + */ +static void test_seal_grow(void) +{ + int fd; + + fd = mfd_assert_new("kern_memfd_seal_grow", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_GROW); + mfd_assert_has_seals(fd, F_SEAL_GROW); + + mfd_assert_read(fd); + mfd_assert_write(fd); + mfd_assert_shrink(fd); + mfd_fail_grow(fd); + mfd_fail_grow_write(fd); + + close(fd); +} + +/* + * Test SEAL_SHRINK | SEAL_GROW + * Test whether SEAL_SHRINK | SEAL_GROW actually prevents resizing + */ +static void test_seal_resize(void) +{ + int fd; + + fd = mfd_assert_new("kern_memfd_seal_resize", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_SHRINK | F_SEAL_GROW); + mfd_assert_has_seals(fd, F_SEAL_SHRINK | F_SEAL_GROW); + + mfd_assert_read(fd); + mfd_assert_write(fd); + mfd_fail_shrink(fd); + mfd_fail_grow(fd); + mfd_fail_grow_write(fd); + + close(fd); +} + +/* + * Test sharing via dup() + * Test that seals are shared between dupped FDs and they're all equal. + */ +static void test_share_dup(void) +{ + int fd, fd2; + + fd = mfd_assert_new("kern_memfd_share_dup", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + + fd2 = mfd_assert_dup(fd); + mfd_assert_has_seals(fd2, 0); + + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd2, F_SEAL_WRITE); + + mfd_assert_add_seals(fd2, F_SEAL_SHRINK); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK); + mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK); + + mfd_assert_add_seals(fd, F_SEAL_SEAL); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL); + mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL); + + mfd_fail_add_seals(fd, F_SEAL_GROW); + mfd_fail_add_seals(fd2, F_SEAL_GROW); + mfd_fail_add_seals(fd, F_SEAL_SEAL); + mfd_fail_add_seals(fd2, F_SEAL_SEAL); + + close(fd2); + + mfd_fail_add_seals(fd, F_SEAL_GROW); + close(fd); +} + +/* + * Test sealing with active mmap()s + * Modifying seals is only allowed if no other mmap() refs exist. + */ +static void test_share_mmap(void) +{ + int fd; + void *p; + + fd = mfd_assert_new("kern_memfd_share_mmap", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + + /* shared/writable ref prevents sealing WRITE, but allows others */ + p = mfd_assert_mmap_shared(fd); + mfd_fail_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_SHRINK); + mfd_assert_has_seals(fd, F_SEAL_SHRINK); + munmap(p, MFD_DEF_SIZE); + + /* readable ref allows sealing */ + p = mfd_assert_mmap_private(fd); + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK); + munmap(p, MFD_DEF_SIZE); + + close(fd); +} + +/* + * Test sealing with open(/proc/self/fd/%d) + * Via /proc we can get access to a separate file-context for the same memfd. + * This is *not* like dup(), but like a real separate open(). Make sure the + * semantics are as expected and we correctly check for RDONLY / WRONLY / RDWR. + */ +static void test_share_open(void) +{ + int fd, fd2; + + fd = mfd_assert_new("kern_memfd_share_open", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + + fd2 = mfd_assert_open(fd, O_RDWR, 0); + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd2, F_SEAL_WRITE); + + mfd_assert_add_seals(fd2, F_SEAL_SHRINK); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK); + mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK); + + close(fd); + fd = mfd_assert_open(fd2, O_RDONLY, 0); + + mfd_fail_add_seals(fd, F_SEAL_SEAL); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK); + mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK); + + close(fd2); + fd2 = mfd_assert_open(fd, O_RDWR, 0); + + mfd_assert_add_seals(fd2, F_SEAL_SEAL); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL); + mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL); + + close(fd2); + close(fd); +} + +/* + * Test sharing via fork() + * Test whether seal-modifications work as expected with forked childs. + */ +static void test_share_fork(void) +{ + int fd; + pid_t pid; + + fd = mfd_assert_new("kern_memfd_share_fork", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + + pid = spawn_idle_thread(0); + mfd_assert_add_seals(fd, F_SEAL_SEAL); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + + mfd_fail_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + + join_idle_thread(pid); + + mfd_fail_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + + close(fd); +} + +int main(int argc, char **argv) +{ + pid_t pid; + + printf("memfd: CREATE\n"); + test_create(); + printf("memfd: BASIC\n"); + test_basic(); + + printf("memfd: SEAL-WRITE\n"); + test_seal_write(); + printf("memfd: SEAL-SHRINK\n"); + test_seal_shrink(); + printf("memfd: SEAL-GROW\n"); + test_seal_grow(); + printf("memfd: SEAL-RESIZE\n"); + test_seal_resize(); + + printf("memfd: SHARE-DUP\n"); + test_share_dup(); + printf("memfd: SHARE-MMAP\n"); + test_share_mmap(); + printf("memfd: SHARE-OPEN\n"); + test_share_open(); + printf("memfd: SHARE-FORK\n"); + test_share_fork(); + + /* Run test-suite in a multi-threaded environment with a shared + * file-table. */ + pid = spawn_idle_thread(CLONE_FILES | CLONE_FS | CLONE_VM); + printf("memfd: SHARE-DUP (shared file-table)\n"); + test_share_dup(); + printf("memfd: SHARE-MMAP (shared file-table)\n"); + test_share_mmap(); + printf("memfd: SHARE-OPEN (shared file-table)\n"); + test_share_open(); + printf("memfd: SHARE-FORK (shared file-table)\n"); + test_share_fork(); + join_idle_thread(pid); + + printf("memfd: DONE\n"); + + return 0; +} diff --git a/tools/testing/selftests/memfd/run_fuse_test.sh b/tools/testing/selftests/memfd/run_fuse_test.sh new file mode 100644 index 0000000..69b930e --- /dev/null +++ b/tools/testing/selftests/memfd/run_fuse_test.sh @@ -0,0 +1,14 @@ +#!/bin/sh + +if test -d "./mnt" ; then + fusermount -u ./mnt + rmdir ./mnt +fi + +set -e + +mkdir mnt +./fuse_mnt ./mnt +./fuse_test ./mnt/memfd +fusermount -u ./mnt +rmdir ./mnt diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile index 058c76f..d46b8d4 100644 --- a/tools/testing/selftests/memory-hotplug/Makefile +++ b/tools/testing/selftests/memory-hotplug/Makefile @@ -1,6 +1,9 @@ all: run_tests: + @/bin/bash ./on-off-test.sh -r 2 || echo "memory-hotplug selftests: [FAIL]" + +run_full_test: @/bin/bash ./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/on-off-test.sh index a2816f6..6cddde0 100644 --- a/tools/testing/selftests/memory-hotplug/on-off-test.sh +++ b/tools/testing/selftests/memory-hotplug/on-off-test.sh @@ -142,10 +142,16 @@ fi prerequisite +echo "Test scope: $ratio% hotplug memory" +echo -e "\t online all hotplug memory in offline state" +echo -e "\t offline $ratio% hotplug memory in online state" +echo -e "\t online all hotplug memory in offline state" + # # Online all hot-pluggable memory # for memory in `hotplaggable_offline_memory`; do + echo offline-online $memory online_memory_expect_success $memory done @@ -154,6 +160,7 @@ done # for memory in `hotpluggable_online_memory`; do if [ $((RANDOM % 100)) -lt $ratio ]; then + echo online-offline $memory offline_memory_expect_success $memory fi done @@ -162,6 +169,7 @@ done # Online all hot-pluggable memory again # for memory in `hotplaggable_offline_memory`; do + echo offline-online $memory online_memory_expect_success $memory done diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile new file mode 100644 index 0000000..337d853 --- /dev/null +++ b/tools/testing/selftests/mount/Makefile @@ -0,0 +1,17 @@ +# Makefile for mount selftests. + +all: unprivileged-remount-test + +unprivileged-remount-test: unprivileged-remount-test.c + gcc -Wall -O2 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 + +run_tests: all test_unprivileged_remount + +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 new file mode 100644 index 0000000..5177850 --- /dev/null +++ b/tools/testing/selftests/mount/unprivileged-remount-test.c @@ -0,0 +1,370 @@ +#define _GNU_SOURCE +#include <sched.h> +#include <stdio.h> +#include <errno.h> +#include <string.h> +#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> +#include <grp.h> +#include <stdbool.h> +#include <stdarg.h> + +#ifndef CLONE_NEWNS +# define CLONE_NEWNS 0x00020000 +#endif +#ifndef CLONE_NEWUTS +# define CLONE_NEWUTS 0x04000000 +#endif +#ifndef CLONE_NEWIPC +# define CLONE_NEWIPC 0x08000000 +#endif +#ifndef CLONE_NEWNET +# define CLONE_NEWNET 0x40000000 +#endif +#ifndef CLONE_NEWUSER +# define CLONE_NEWUSER 0x10000000 +#endif +#ifndef CLONE_NEWPID +# define CLONE_NEWPID 0x20000000 +#endif + +#ifndef MS_REC +# define MS_REC 16384 +#endif +#ifndef MS_RELATIME +# define MS_RELATIME (1 << 21) +#endif +#ifndef MS_STRICTATIME +# define MS_STRICTATIME (1 << 24) +#endif + +static void die(char *fmt, ...) +{ + va_list ap; + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + exit(EXIT_FAILURE); +} + +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; + + buf_len = vsnprintf(buf, sizeof(buf), fmt, ap); + if (buf_len < 0) { + die("vsnprintf failed: %s\n", + strerror(errno)); + } + if (buf_len >= sizeof(buf)) { + die("vsnprintf output truncated\n"); + } + + fd = open(filename, O_WRONLY); + if (fd < 0) { + if ((errno == ENOENT) && enoent_ok) + return; + die("open of %s failed: %s\n", + filename, strerror(errno)); + } + written = write(fd, buf, buf_len); + if (written != buf_len) { + if (written >= 0) { + die("short write to %s\n", filename); + } else { + die("write to %s failed: %s\n", + filename, strerror(errno)); + } + } + if (close(fd) != 0) { + die("close of %s failed: %s\n", + filename, strerror(errno)); + } +} + +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; + gid_t gid; + + uid = getuid(); + gid = getgid(); + + if (unshare(CLONE_NEWUSER) !=0) { + die("unshare(CLONE_NEWUSER) failed: %s\n", + 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 (setgid(0) != 0) { + die ("setgid(0) failed %s\n", + strerror(errno)); + } + if (setuid(0) != 0) { + die("setuid(0) failed %s\n", + strerror(errno)); + } +} + +static +bool test_unpriv_remount(const char *fstype, const char *mount_options, + int mount_flags, int remount_flags, int invalid_flags) +{ + pid_t child; + + 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; + } + + create_and_enter_userns(); + if (unshare(CLONE_NEWNS) != 0) { + die("unshare(CLONE_NEWNS) 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(); + + if (unshare(CLONE_NEWNS) != 0) { + die("unshare(CLONE_NEWNS) failed: %s\n", + strerror(errno)); + } + + if (mount("/tmp", "/tmp", "none", + MS_REMOUNT | MS_BIND | remount_flags, NULL) != 0) { + /* system("cat /proc/self/mounts"); */ + die("remount of /tmp failed: %s\n", + strerror(errno)); + } + + if (mount("/tmp", "/tmp", "none", + MS_REMOUNT | MS_BIND | invalid_flags, NULL) == 0) { + /* system("cat /proc/self/mounts"); */ + die("remount of /tmp with invalid flags " + "succeeded unexpectedly\n"); + } + exit(EXIT_SUCCESS); +} + +static bool test_unpriv_remount_simple(int mount_flags) +{ + 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("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)) { + die("MS_RDONLY malfunctions\n"); + } + if (!test_unpriv_remount("devpts", "newinstance", MS_NODEV, MS_NODEV, 0)) { + die("MS_NODEV malfunctions\n"); + } + if (!test_unpriv_remount_simple(MS_NOSUID)) { + die("MS_NOSUID malfunctions\n"); + } + if (!test_unpriv_remount_simple(MS_NOEXEC)) { + die("MS_NOEXEC malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_RELATIME, + MS_NOATIME)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_STRICTATIME, + MS_NOATIME)) + { + die("MS_STRICTATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_NOATIME, + MS_STRICTATIME)) + { + die("MS_NOATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME, + MS_NOATIME)) + { + die("MS_RELATIME|MS_NODIRATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME, + MS_NOATIME)) + { + die("MS_STRICTATIME|MS_NODIRATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME, + MS_STRICTATIME)) + { + die("MS_NOATIME|MS_DIRATIME malfunctions\n"); + } + 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 218a122..8056e2e 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -1,6 +1,6 @@ all: - gcc -O2 -lrt mq_open_tests.c -o mq_open_tests - gcc -O2 -lrt -lpthread -lpopt -o mq_perf_tests mq_perf_tests.c + gcc -O2 mq_open_tests.c -o mq_open_tests -lrt + gcc -O2 -o mq_perf_tests mq_perf_tests.c -lrt -lpthread -lpopt run_tests: @./mq_open_tests /test1 || echo "mq_open_tests: [FAIL]" diff --git a/tools/testing/selftests/mqueue/mq_open_tests.c b/tools/testing/selftests/mqueue/mq_open_tests.c index 711cc29..9c1a5d35 100644 --- a/tools/testing/selftests/mqueue/mq_open_tests.c +++ b/tools/testing/selftests/mqueue/mq_open_tests.c @@ -80,7 +80,8 @@ void shutdown(int exit_val, char *err_cause, int line_no) if (in_shutdown++) return; - seteuid(0); + if (seteuid(0) == -1) + perror("seteuid() failed"); if (queue != -1) if (mq_close(queue)) @@ -292,8 +293,10 @@ int main(int argc, char *argv[]) /* Tell the user our initial state */ printf("\nInitial system state:\n"); printf("\tUsing queue path:\t\t%s\n", queue_path); - printf("\tRLIMIT_MSGQUEUE(soft):\t\t%d\n", saved_limits.rlim_cur); - printf("\tRLIMIT_MSGQUEUE(hard):\t\t%d\n", saved_limits.rlim_max); + printf("\tRLIMIT_MSGQUEUE(soft):\t\t%ld\n", + (long) saved_limits.rlim_cur); + printf("\tRLIMIT_MSGQUEUE(hard):\t\t%ld\n", + (long) saved_limits.rlim_max); printf("\tMaximum Message Size:\t\t%d\n", saved_max_msgsize); printf("\tMaximum Queue Size:\t\t%d\n", saved_max_msgs); if (default_settings) { @@ -308,8 +311,8 @@ int main(int argc, char *argv[]) validate_current_settings(); printf("Adjusted system state for testing:\n"); - printf("\tRLIMIT_MSGQUEUE(soft):\t\t%d\n", cur_limits.rlim_cur); - printf("\tRLIMIT_MSGQUEUE(hard):\t\t%d\n", cur_limits.rlim_max); + printf("\tRLIMIT_MSGQUEUE(soft):\t\t%ld\n", (long) cur_limits.rlim_cur); + printf("\tRLIMIT_MSGQUEUE(hard):\t\t%ld\n", (long) cur_limits.rlim_max); printf("\tMaximum Message Size:\t\t%d\n", cur_max_msgsize); printf("\tMaximum Queue Size:\t\t%d\n", cur_max_msgs); if (default_settings) { @@ -454,7 +457,12 @@ int main(int argc, char *argv[]) else printf("Queue open with total size > 2GB when euid = 0 " "failed:\t\t\tPASS\n"); - seteuid(99); + + if (seteuid(99) == -1) { + perror("seteuid() failed"); + exit(1); + } + attr.mq_maxmsg = cur_max_msgs; attr.mq_msgsize = cur_max_msgsize; if (test_queue_fail(&attr, &result)) diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c index 2fadd4b..94dae65 100644 --- a/tools/testing/selftests/mqueue/mq_perf_tests.c +++ b/tools/testing/selftests/mqueue/mq_perf_tests.c @@ -296,9 +296,9 @@ static inline void open_queue(struct mq_attr *attr) printf("\n\tQueue %s created:\n", queue_path); printf("\t\tmq_flags:\t\t\t%s\n", result.mq_flags & O_NONBLOCK ? "O_NONBLOCK" : "(null)"); - printf("\t\tmq_maxmsg:\t\t\t%d\n", result.mq_maxmsg); - printf("\t\tmq_msgsize:\t\t\t%d\n", result.mq_msgsize); - printf("\t\tmq_curmsgs:\t\t\t%d\n", result.mq_curmsgs); + printf("\t\tmq_maxmsg:\t\t\t%lu\n", result.mq_maxmsg); + printf("\t\tmq_msgsize:\t\t\t%lu\n", result.mq_msgsize); + printf("\t\tmq_curmsgs:\t\t\t%lu\n", result.mq_curmsgs); } void *fake_cont_thread(void *arg) @@ -440,7 +440,7 @@ void *perf_test_thread(void *arg) shutdown(2, "clock_getres()", __LINE__); printf("\t\tMax priorities:\t\t\t%d\n", mq_prio_max); - printf("\t\tClock resolution:\t\t%d nsec%s\n", res.tv_nsec, + printf("\t\tClock resolution:\t\t%lu nsec%s\n", res.tv_nsec, res.tv_nsec > 1 ? "s" : ""); @@ -454,20 +454,20 @@ void *perf_test_thread(void *arg) recv_total.tv_nsec = 0; for (i = 0; i < TEST1_LOOPS; i++) do_send_recv(); - printf("\t\tSend msg:\t\t\t%d.%ds total time\n", + printf("\t\tSend msg:\t\t\t%ld.%lus total time\n", send_total.tv_sec, send_total.tv_nsec); nsec = ((unsigned long long)send_total.tv_sec * 1000000000 + send_total.tv_nsec) / TEST1_LOOPS; - printf("\t\t\t\t\t\t%d nsec/msg\n", nsec); - printf("\t\tRecv msg:\t\t\t%d.%ds total time\n", + printf("\t\t\t\t\t\t%lld nsec/msg\n", nsec); + printf("\t\tRecv msg:\t\t\t%ld.%lus total time\n", recv_total.tv_sec, recv_total.tv_nsec); nsec = ((unsigned long long)recv_total.tv_sec * 1000000000 + recv_total.tv_nsec) / TEST1_LOOPS; - printf("\t\t\t\t\t\t%d nsec/msg\n", nsec); + printf("\t\t\t\t\t\t%lld nsec/msg\n", nsec); for (cur_test = test2; cur_test->desc != NULL; cur_test++) { - printf(cur_test->desc); + printf("%s:\n", cur_test->desc); printf("\t\t(%d iterations)\n", TEST2_LOOPS); prio_out = 0; send_total.tv_sec = 0; @@ -493,16 +493,16 @@ void *perf_test_thread(void *arg) cur_test->func(&prio_out); } printf("done.\n"); - printf("\t\tSend msg:\t\t\t%d.%ds total time\n", + printf("\t\tSend msg:\t\t\t%ld.%lus total time\n", send_total.tv_sec, send_total.tv_nsec); nsec = ((unsigned long long)send_total.tv_sec * 1000000000 + send_total.tv_nsec) / TEST2_LOOPS; - printf("\t\t\t\t\t\t%d nsec/msg\n", nsec); - printf("\t\tRecv msg:\t\t\t%d.%ds total time\n", + printf("\t\t\t\t\t\t%lld nsec/msg\n", nsec); + printf("\t\tRecv msg:\t\t\t%ld.%lus total time\n", recv_total.tv_sec, recv_total.tv_nsec); nsec = ((unsigned long long)recv_total.tv_sec * 1000000000 + recv_total.tv_nsec) / TEST2_LOOPS; - printf("\t\t\t\t\t\t%d nsec/msg\n", nsec); + printf("\t\t\t\t\t\t%lld nsec/msg\n", nsec); printf("\t\tDraining queue..."); fflush(stdout); clock_gettime(clock, &start); @@ -653,8 +653,10 @@ int main(int argc, char *argv[]) /* Tell the user our initial state */ printf("\nInitial system state:\n"); printf("\tUsing queue path:\t\t\t%s\n", queue_path); - printf("\tRLIMIT_MSGQUEUE(soft):\t\t\t%d\n", saved_limits.rlim_cur); - printf("\tRLIMIT_MSGQUEUE(hard):\t\t\t%d\n", saved_limits.rlim_max); + printf("\tRLIMIT_MSGQUEUE(soft):\t\t\t%ld\n", + (long) saved_limits.rlim_cur); + printf("\tRLIMIT_MSGQUEUE(hard):\t\t\t%ld\n", + (long) saved_limits.rlim_max); printf("\tMaximum Message Size:\t\t\t%d\n", saved_max_msgsize); printf("\tMaximum Queue Size:\t\t\t%d\n", saved_max_msgs); printf("\tNice value:\t\t\t\t%d\n", cur_nice); @@ -667,10 +669,10 @@ int main(int argc, char *argv[]) printf("\tRLIMIT_MSGQUEUE(soft):\t\t\t(unlimited)\n"); printf("\tRLIMIT_MSGQUEUE(hard):\t\t\t(unlimited)\n"); } else { - printf("\tRLIMIT_MSGQUEUE(soft):\t\t\t%d\n", - cur_limits.rlim_cur); - printf("\tRLIMIT_MSGQUEUE(hard):\t\t\t%d\n", - cur_limits.rlim_max); + printf("\tRLIMIT_MSGQUEUE(soft):\t\t\t%ld\n", + (long) cur_limits.rlim_cur); + printf("\tRLIMIT_MSGQUEUE(hard):\t\t\t%ld\n", + (long) cur_limits.rlim_max); } printf("\tMaximum Message Size:\t\t\t%d\n", cur_max_msgsize); printf("\tMaximum Queue Size:\t\t\t%d\n", cur_max_msgs); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index c7493b8..62f22cc 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -14,12 +14,6 @@ all: $(NET_PROGS) 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_bpf.sh clean: $(RM) $(NET_PROGS) diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 57b9c2b..6f67333 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -128,7 +128,7 @@ static int sock_fanout_read_ring(int fd, void *ring) struct tpacket2_hdr *header = ring; int count = 0; - while (header->tp_status & TP_STATUS_USER && count < RING_NUM_FRAMES) { + while (count < RING_NUM_FRAMES && header->tp_status & TP_STATUS_USER) { count++; header = ring + (count * getpagesize()); } diff --git a/tools/testing/selftests/net/test_bpf.sh b/tools/testing/selftests/net/test_bpf.sh new file mode 100755 index 0000000..8b29796 --- /dev/null +++ b/tools/testing/selftests/net/test_bpf.sh @@ -0,0 +1,10 @@ +#!/bin/sh +# Runs bpf test using test_bpf kernel module + +if /sbin/modprobe -q test_bpf ; then + /sbin/modprobe -q -r test_bpf; + echo "test_bpf: ok"; +else + echo "test_bpf: [FAIL]"; + exit 1; +fi diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 54833a7..f6ff90a 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -13,14 +13,14 @@ CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CUR export CC CFLAGS -TARGETS = pmu copyloops mm tm +TARGETS = pmu copyloops mm tm primitives endif -all: - @for TARGET in $(TARGETS); do \ - $(MAKE) -C $$TARGET all; \ - done; +all: $(TARGETS) + +$(TARGETS): + $(MAKE) -k -C $@ all run_tests: all @for TARGET in $(TARGETS); do \ @@ -36,4 +36,4 @@ clean: tags: find . -name '*.c' -o -name '*.h' | xargs ctags -.PHONY: all run_tests clean tags +.PHONY: all run_tests clean tags $(TARGETS) diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index b9ff0db..c9f4263 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -1,10 +1,12 @@ noarg: $(MAKE) -C ../ -PROGS := count_instructions -EXTRA_SOURCES := ../harness.c event.c +PROGS := count_instructions l3_bank_test per_event_excludes +EXTRA_SOURCES := ../harness.c event.c lib.c -all: $(PROGS) sub_all +SUB_TARGETS = ebb + +all: $(PROGS) $(SUB_TARGETS) $(PROGS): $(EXTRA_SOURCES) @@ -20,13 +22,8 @@ run_tests: all sub_run_tests clean: sub_clean rm -f $(PROGS) loop.o - -SUB_TARGETS = ebb - -sub_all: - @for TARGET in $(SUB_TARGETS); do \ - $(MAKE) -C $$TARGET all; \ - done; +$(SUB_TARGETS): + $(MAKE) -k -C $@ all sub_run_tests: all @for TARGET in $(SUB_TARGETS); do \ @@ -38,4 +35,4 @@ sub_clean: $(MAKE) -C $$TARGET clean; \ done; -.PHONY: all run_tests clean sub_all sub_run_tests sub_clean +.PHONY: all run_tests clean sub_run_tests sub_clean $(SUB_TARGETS) diff --git a/tools/testing/selftests/powerpc/pmu/count_instructions.c b/tools/testing/selftests/powerpc/pmu/count_instructions.c index 312b4f0..4622117 100644 --- a/tools/testing/selftests/powerpc/pmu/count_instructions.c +++ b/tools/testing/selftests/powerpc/pmu/count_instructions.c @@ -12,6 +12,7 @@ #include "event.h" #include "utils.h" +#include "lib.h" extern void thirty_two_instruction_loop(u64 loops); @@ -90,7 +91,7 @@ static u64 determine_overhead(struct event *events) return overhead; } -static int count_instructions(void) +static int test_body(void) { struct event events[2]; u64 overhead; @@ -111,17 +112,23 @@ static int count_instructions(void) overhead = determine_overhead(events); printf("Overhead of null loop: %llu instructions\n", overhead); - /* Run for 1M instructions */ - FAIL_IF(do_count_loop(events, 0x100000, overhead, true)); + /* Run for 1Mi instructions */ + FAIL_IF(do_count_loop(events, 1000000, overhead, true)); + + /* Run for 10Mi instructions */ + FAIL_IF(do_count_loop(events, 10000000, overhead, true)); + + /* Run for 100Mi instructions */ + FAIL_IF(do_count_loop(events, 100000000, overhead, true)); - /* Run for 10M instructions */ - FAIL_IF(do_count_loop(events, 0xa00000, overhead, true)); + /* Run for 1Bi instructions */ + FAIL_IF(do_count_loop(events, 1000000000, overhead, true)); - /* Run for 100M instructions */ - FAIL_IF(do_count_loop(events, 0x6400000, overhead, true)); + /* Run for 16Bi instructions */ + FAIL_IF(do_count_loop(events, 16000000000, overhead, true)); - /* Run for 1G instructions */ - FAIL_IF(do_count_loop(events, 0x40000000, overhead, true)); + /* Run for 64Bi instructions */ + FAIL_IF(do_count_loop(events, 64000000000, overhead, true)); event_close(&events[0]); event_close(&events[1]); @@ -129,6 +136,11 @@ static int count_instructions(void) return 0; } +static int count_instructions(void) +{ + return eat_cpu(test_body); +} + int main(void) { return test_harness(count_instructions, "count_instructions"); diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index edbba2a..3dc4332 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -13,11 +13,12 @@ PROGS := reg_access_test event_attributes_test cycles_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 + lost_exception_test no_handler_test \ + cycles_with_mmcr2_test all: $(PROGS) -$(PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c +$(PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c busy_loop.S instruction_count_test: ../loop.S diff --git a/tools/testing/selftests/powerpc/pmu/ebb/busy_loop.S b/tools/testing/selftests/powerpc/pmu/ebb/busy_loop.S new file mode 100644 index 0000000..c7e4093 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/busy_loop.S @@ -0,0 +1,271 @@ +/* + * Copyright 2014, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#include <ppc-asm.h> + + .text + +FUNC_START(core_busy_loop) + stdu %r1, -168(%r1) + std r14, 160(%r1) + std r15, 152(%r1) + std r16, 144(%r1) + std r17, 136(%r1) + std r18, 128(%r1) + std r19, 120(%r1) + std r20, 112(%r1) + std r21, 104(%r1) + std r22, 96(%r1) + std r23, 88(%r1) + std r24, 80(%r1) + std r25, 72(%r1) + std r26, 64(%r1) + std r27, 56(%r1) + std r28, 48(%r1) + std r29, 40(%r1) + std r30, 32(%r1) + std r31, 24(%r1) + + li r3, 0x3030 + std r3, -96(%r1) + li r4, 0x4040 + std r4, -104(%r1) + li r5, 0x5050 + std r5, -112(%r1) + li r6, 0x6060 + std r6, -120(%r1) + li r7, 0x7070 + std r7, -128(%r1) + li r8, 0x0808 + std r8, -136(%r1) + li r9, 0x0909 + std r9, -144(%r1) + li r10, 0x1010 + std r10, -152(%r1) + li r11, 0x1111 + std r11, -160(%r1) + li r14, 0x1414 + std r14, -168(%r1) + li r15, 0x1515 + std r15, -176(%r1) + li r16, 0x1616 + std r16, -184(%r1) + li r17, 0x1717 + std r17, -192(%r1) + li r18, 0x1818 + std r18, -200(%r1) + li r19, 0x1919 + std r19, -208(%r1) + li r20, 0x2020 + std r20, -216(%r1) + li r21, 0x2121 + std r21, -224(%r1) + li r22, 0x2222 + std r22, -232(%r1) + li r23, 0x2323 + std r23, -240(%r1) + li r24, 0x2424 + std r24, -248(%r1) + li r25, 0x2525 + std r25, -256(%r1) + li r26, 0x2626 + std r26, -264(%r1) + li r27, 0x2727 + std r27, -272(%r1) + li r28, 0x2828 + std r28, -280(%r1) + li r29, 0x2929 + std r29, -288(%r1) + li r30, 0x3030 + li r31, 0x3131 + + li r3, 0 +0: addi r3, r3, 1 + cmpwi r3, 100 + blt 0b + + /* Return 1 (fail) unless we get through all the checks */ + li r3, 1 + + /* Check none of our registers have been corrupted */ + cmpwi r4, 0x4040 + bne 1f + cmpwi r5, 0x5050 + bne 1f + cmpwi r6, 0x6060 + bne 1f + cmpwi r7, 0x7070 + bne 1f + cmpwi r8, 0x0808 + bne 1f + cmpwi r9, 0x0909 + bne 1f + cmpwi r10, 0x1010 + bne 1f + cmpwi r11, 0x1111 + bne 1f + cmpwi r14, 0x1414 + bne 1f + cmpwi r15, 0x1515 + bne 1f + cmpwi r16, 0x1616 + bne 1f + cmpwi r17, 0x1717 + bne 1f + cmpwi r18, 0x1818 + bne 1f + cmpwi r19, 0x1919 + bne 1f + cmpwi r20, 0x2020 + bne 1f + cmpwi r21, 0x2121 + bne 1f + cmpwi r22, 0x2222 + bne 1f + cmpwi r23, 0x2323 + bne 1f + cmpwi r24, 0x2424 + bne 1f + cmpwi r25, 0x2525 + bne 1f + cmpwi r26, 0x2626 + bne 1f + cmpwi r27, 0x2727 + bne 1f + cmpwi r28, 0x2828 + bne 1f + cmpwi r29, 0x2929 + bne 1f + cmpwi r30, 0x3030 + bne 1f + cmpwi r31, 0x3131 + bne 1f + + /* Load junk into all our registers before we reload them from the stack. */ + li r3, 0xde + li r4, 0xad + li r5, 0xbe + li r6, 0xef + li r7, 0xde + li r8, 0xad + li r9, 0xbe + li r10, 0xef + li r11, 0xde + li r14, 0xad + li r15, 0xbe + li r16, 0xef + li r17, 0xde + li r18, 0xad + li r19, 0xbe + li r20, 0xef + li r21, 0xde + li r22, 0xad + li r23, 0xbe + li r24, 0xef + li r25, 0xde + li r26, 0xad + li r27, 0xbe + li r28, 0xef + li r29, 0xdd + + ld r3, -96(%r1) + cmpwi r3, 0x3030 + bne 1f + ld r4, -104(%r1) + cmpwi r4, 0x4040 + bne 1f + ld r5, -112(%r1) + cmpwi r5, 0x5050 + bne 1f + ld r6, -120(%r1) + cmpwi r6, 0x6060 + bne 1f + ld r7, -128(%r1) + cmpwi r7, 0x7070 + bne 1f + ld r8, -136(%r1) + cmpwi r8, 0x0808 + bne 1f + ld r9, -144(%r1) + cmpwi r9, 0x0909 + bne 1f + ld r10, -152(%r1) + cmpwi r10, 0x1010 + bne 1f + ld r11, -160(%r1) + cmpwi r11, 0x1111 + bne 1f + ld r14, -168(%r1) + cmpwi r14, 0x1414 + bne 1f + ld r15, -176(%r1) + cmpwi r15, 0x1515 + bne 1f + ld r16, -184(%r1) + cmpwi r16, 0x1616 + bne 1f + ld r17, -192(%r1) + cmpwi r17, 0x1717 + bne 1f + ld r18, -200(%r1) + cmpwi r18, 0x1818 + bne 1f + ld r19, -208(%r1) + cmpwi r19, 0x1919 + bne 1f + ld r20, -216(%r1) + cmpwi r20, 0x2020 + bne 1f + ld r21, -224(%r1) + cmpwi r21, 0x2121 + bne 1f + ld r22, -232(%r1) + cmpwi r22, 0x2222 + bne 1f + ld r23, -240(%r1) + cmpwi r23, 0x2323 + bne 1f + ld r24, -248(%r1) + cmpwi r24, 0x2424 + bne 1f + ld r25, -256(%r1) + cmpwi r25, 0x2525 + bne 1f + ld r26, -264(%r1) + cmpwi r26, 0x2626 + bne 1f + ld r27, -272(%r1) + cmpwi r27, 0x2727 + bne 1f + ld r28, -280(%r1) + cmpwi r28, 0x2828 + bne 1f + ld r29, -288(%r1) + cmpwi r29, 0x2929 + bne 1f + + /* Load 0 (success) to return */ + li r3, 0 + +1: ld r14, 160(%r1) + ld r15, 152(%r1) + ld r16, 144(%r1) + ld r17, 136(%r1) + ld r18, 128(%r1) + ld r19, 120(%r1) + ld r20, 112(%r1) + ld r21, 104(%r1) + ld r22, 96(%r1) + ld r23, 88(%r1) + ld r24, 80(%r1) + ld r25, 72(%r1) + ld r26, 64(%r1) + ld r27, 56(%r1) + ld r28, 48(%r1) + ld r29, 40(%r1) + ld r30, 32(%r1) + ld r31, 24(%r1) + addi %r1, %r1, 168 + blr diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c new file mode 100644 index 0000000..d43029b --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c @@ -0,0 +1,91 @@ +/* + * Copyright 2014, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> + +#include "ebb.h" + + +/* + * Test of counting cycles while manipulating the user accessible bits in MMCR2. + */ + +/* We use two values because the first freezes PMC1 and so we would get no EBBs */ +#define MMCR2_EXPECTED_1 0x4020100804020000UL /* (FC1P|FC2P|FC3P|FC4P|FC5P|FC6P) */ +#define MMCR2_EXPECTED_2 0x0020100804020000UL /* ( FC2P|FC3P|FC4P|FC5P|FC6P) */ + + +int cycles_with_mmcr2(void) +{ + struct event event; + uint64_t val, expected[2], actual; + int i; + bool bad_mmcr2; + + event_init_named(&event, 0x1001e, "cycles"); + event_leader_ebb_init(&event); + + event.attr.exclude_kernel = 1; + event.attr.exclude_hv = 1; + event.attr.exclude_idle = 1; + + FAIL_IF(event_open(&event)); + + ebb_enable_pmc_counting(1); + setup_ebb_handler(standard_ebb_callee); + ebb_global_enable(); + + FAIL_IF(ebb_event_enable(&event)); + + mtspr(SPRN_PMC1, pmc_sample_period(sample_period)); + + /* XXX Set of MMCR2 must be after enable */ + expected[0] = MMCR2_EXPECTED_1; + expected[1] = MMCR2_EXPECTED_2; + i = 0; + bad_mmcr2 = false; + + /* Make sure we loop until we take at least one EBB */ + while ((ebb_state.stats.ebb_count < 20 && !bad_mmcr2) || + ebb_state.stats.ebb_count < 1) + { + mtspr(SPRN_MMCR2, expected[i % 2]); + + FAIL_IF(core_busy_loop()); + + val = mfspr(SPRN_MMCR2); + if (val != expected[i % 2]) { + bad_mmcr2 = true; + actual = val; + } + + i++; + } + + ebb_global_disable(); + ebb_freeze_pmcs(); + + count_pmc(1, sample_period); + + dump_ebb_state(); + + event_close(&event); + + FAIL_IF(ebb_state.stats.ebb_count == 0); + + if (bad_mmcr2) + printf("Bad MMCR2 value seen is 0x%lx\n", actual); + + FAIL_IF(bad_mmcr2); + + return 0; +} + +int main(void) +{ + return test_harness(cycles_with_mmcr2, "cycles_with_mmcr2"); +} diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c index 1b46be9..d7a72ce 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c @@ -224,6 +224,7 @@ void dump_ebb_hw_state(void) printf("HW state:\n" \ "MMCR0 0x%016x %s\n" \ + "MMCR2 0x%016lx\n" \ "EBBHR 0x%016lx\n" \ "BESCR 0x%016llx %s\n" \ "PMC1 0x%016lx\n" \ @@ -233,10 +234,11 @@ void dump_ebb_hw_state(void) "PMC5 0x%016lx\n" \ "PMC6 0x%016lx\n" \ "SIAR 0x%016lx\n", - mmcr0, decode_mmcr0(mmcr0), mfspr(SPRN_EBBHR), bescr, - decode_bescr(bescr), mfspr(SPRN_PMC1), mfspr(SPRN_PMC2), - mfspr(SPRN_PMC3), mfspr(SPRN_PMC4), mfspr(SPRN_PMC5), - mfspr(SPRN_PMC6), mfspr(SPRN_SIAR)); + mmcr0, decode_mmcr0(mmcr0), mfspr(SPRN_MMCR2), + mfspr(SPRN_EBBHR), bescr, decode_bescr(bescr), + mfspr(SPRN_PMC1), mfspr(SPRN_PMC2), mfspr(SPRN_PMC3), + mfspr(SPRN_PMC4), mfspr(SPRN_PMC5), mfspr(SPRN_PMC6), + mfspr(SPRN_SIAR)); } void dump_ebb_state(void) @@ -335,257 +337,6 @@ void event_leader_ebb_init(struct event *e) e->attr.pinned = 1; } -int core_busy_loop(void) -{ - int rc; - - asm volatile ( - "li 3, 0x3030\n" - "std 3, -96(1)\n" - "li 4, 0x4040\n" - "std 4, -104(1)\n" - "li 5, 0x5050\n" - "std 5, -112(1)\n" - "li 6, 0x6060\n" - "std 6, -120(1)\n" - "li 7, 0x7070\n" - "std 7, -128(1)\n" - "li 8, 0x0808\n" - "std 8, -136(1)\n" - "li 9, 0x0909\n" - "std 9, -144(1)\n" - "li 10, 0x1010\n" - "std 10, -152(1)\n" - "li 11, 0x1111\n" - "std 11, -160(1)\n" - "li 14, 0x1414\n" - "std 14, -168(1)\n" - "li 15, 0x1515\n" - "std 15, -176(1)\n" - "li 16, 0x1616\n" - "std 16, -184(1)\n" - "li 17, 0x1717\n" - "std 17, -192(1)\n" - "li 18, 0x1818\n" - "std 18, -200(1)\n" - "li 19, 0x1919\n" - "std 19, -208(1)\n" - "li 20, 0x2020\n" - "std 20, -216(1)\n" - "li 21, 0x2121\n" - "std 21, -224(1)\n" - "li 22, 0x2222\n" - "std 22, -232(1)\n" - "li 23, 0x2323\n" - "std 23, -240(1)\n" - "li 24, 0x2424\n" - "std 24, -248(1)\n" - "li 25, 0x2525\n" - "std 25, -256(1)\n" - "li 26, 0x2626\n" - "std 26, -264(1)\n" - "li 27, 0x2727\n" - "std 27, -272(1)\n" - "li 28, 0x2828\n" - "std 28, -280(1)\n" - "li 29, 0x2929\n" - "std 29, -288(1)\n" - "li 30, 0x3030\n" - "li 31, 0x3131\n" - - "li 3, 0\n" - "0: " - "addi 3, 3, 1\n" - "cmpwi 3, 100\n" - "blt 0b\n" - - /* Return 1 (fail) unless we get through all the checks */ - "li 0, 1\n" - - /* Check none of our registers have been corrupted */ - "cmpwi 4, 0x4040\n" - "bne 1f\n" - "cmpwi 5, 0x5050\n" - "bne 1f\n" - "cmpwi 6, 0x6060\n" - "bne 1f\n" - "cmpwi 7, 0x7070\n" - "bne 1f\n" - "cmpwi 8, 0x0808\n" - "bne 1f\n" - "cmpwi 9, 0x0909\n" - "bne 1f\n" - "cmpwi 10, 0x1010\n" - "bne 1f\n" - "cmpwi 11, 0x1111\n" - "bne 1f\n" - "cmpwi 14, 0x1414\n" - "bne 1f\n" - "cmpwi 15, 0x1515\n" - "bne 1f\n" - "cmpwi 16, 0x1616\n" - "bne 1f\n" - "cmpwi 17, 0x1717\n" - "bne 1f\n" - "cmpwi 18, 0x1818\n" - "bne 1f\n" - "cmpwi 19, 0x1919\n" - "bne 1f\n" - "cmpwi 20, 0x2020\n" - "bne 1f\n" - "cmpwi 21, 0x2121\n" - "bne 1f\n" - "cmpwi 22, 0x2222\n" - "bne 1f\n" - "cmpwi 23, 0x2323\n" - "bne 1f\n" - "cmpwi 24, 0x2424\n" - "bne 1f\n" - "cmpwi 25, 0x2525\n" - "bne 1f\n" - "cmpwi 26, 0x2626\n" - "bne 1f\n" - "cmpwi 27, 0x2727\n" - "bne 1f\n" - "cmpwi 28, 0x2828\n" - "bne 1f\n" - "cmpwi 29, 0x2929\n" - "bne 1f\n" - "cmpwi 30, 0x3030\n" - "bne 1f\n" - "cmpwi 31, 0x3131\n" - "bne 1f\n" - - /* Load junk into all our registers before we reload them from the stack. */ - "li 3, 0xde\n" - "li 4, 0xad\n" - "li 5, 0xbe\n" - "li 6, 0xef\n" - "li 7, 0xde\n" - "li 8, 0xad\n" - "li 9, 0xbe\n" - "li 10, 0xef\n" - "li 11, 0xde\n" - "li 14, 0xad\n" - "li 15, 0xbe\n" - "li 16, 0xef\n" - "li 17, 0xde\n" - "li 18, 0xad\n" - "li 19, 0xbe\n" - "li 20, 0xef\n" - "li 21, 0xde\n" - "li 22, 0xad\n" - "li 23, 0xbe\n" - "li 24, 0xef\n" - "li 25, 0xde\n" - "li 26, 0xad\n" - "li 27, 0xbe\n" - "li 28, 0xef\n" - "li 29, 0xdd\n" - - "ld 3, -96(1)\n" - "cmpwi 3, 0x3030\n" - "bne 1f\n" - "ld 4, -104(1)\n" - "cmpwi 4, 0x4040\n" - "bne 1f\n" - "ld 5, -112(1)\n" - "cmpwi 5, 0x5050\n" - "bne 1f\n" - "ld 6, -120(1)\n" - "cmpwi 6, 0x6060\n" - "bne 1f\n" - "ld 7, -128(1)\n" - "cmpwi 7, 0x7070\n" - "bne 1f\n" - "ld 8, -136(1)\n" - "cmpwi 8, 0x0808\n" - "bne 1f\n" - "ld 9, -144(1)\n" - "cmpwi 9, 0x0909\n" - "bne 1f\n" - "ld 10, -152(1)\n" - "cmpwi 10, 0x1010\n" - "bne 1f\n" - "ld 11, -160(1)\n" - "cmpwi 11, 0x1111\n" - "bne 1f\n" - "ld 14, -168(1)\n" - "cmpwi 14, 0x1414\n" - "bne 1f\n" - "ld 15, -176(1)\n" - "cmpwi 15, 0x1515\n" - "bne 1f\n" - "ld 16, -184(1)\n" - "cmpwi 16, 0x1616\n" - "bne 1f\n" - "ld 17, -192(1)\n" - "cmpwi 17, 0x1717\n" - "bne 1f\n" - "ld 18, -200(1)\n" - "cmpwi 18, 0x1818\n" - "bne 1f\n" - "ld 19, -208(1)\n" - "cmpwi 19, 0x1919\n" - "bne 1f\n" - "ld 20, -216(1)\n" - "cmpwi 20, 0x2020\n" - "bne 1f\n" - "ld 21, -224(1)\n" - "cmpwi 21, 0x2121\n" - "bne 1f\n" - "ld 22, -232(1)\n" - "cmpwi 22, 0x2222\n" - "bne 1f\n" - "ld 23, -240(1)\n" - "cmpwi 23, 0x2323\n" - "bne 1f\n" - "ld 24, -248(1)\n" - "cmpwi 24, 0x2424\n" - "bne 1f\n" - "ld 25, -256(1)\n" - "cmpwi 25, 0x2525\n" - "bne 1f\n" - "ld 26, -264(1)\n" - "cmpwi 26, 0x2626\n" - "bne 1f\n" - "ld 27, -272(1)\n" - "cmpwi 27, 0x2727\n" - "bne 1f\n" - "ld 28, -280(1)\n" - "cmpwi 28, 0x2828\n" - "bne 1f\n" - "ld 29, -288(1)\n" - "cmpwi 29, 0x2929\n" - "bne 1f\n" - - /* Load 0 (success) to return */ - "li 0, 0\n" - - "1: mr %0, 0\n" - - : "=r" (rc) - : /* no inputs */ - : "3", "4", "5", "6", "7", "8", "9", "10", "11", "14", - "15", "16", "17", "18", "19", "20", "21", "22", "23", - "24", "25", "26", "27", "28", "29", "30", "31", - "memory" - ); - - return rc; -} - -int core_busy_loop_with_freeze(void) -{ - int rc; - - mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC); - rc = core_busy_loop(); - mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) | MMCR0_FC); - - return rc; -} - int ebb_child(union pipe read_pipe, union pipe write_pipe) { struct event event; diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.h b/tools/testing/selftests/powerpc/pmu/ebb/ebb.h index e62bde0..e44eee5 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.h +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.h @@ -70,7 +70,6 @@ int ebb_check_mmcr0(void); extern u64 sample_period; int core_busy_loop(void); -int core_busy_loop_with_freeze(void); int ebb_child(union pipe read_pipe, union pipe write_pipe); int catch_sigill(void (*func)(void)); void write_pmc1(void); diff --git a/tools/testing/selftests/powerpc/pmu/l3_bank_test.c b/tools/testing/selftests/powerpc/pmu/l3_bank_test.c new file mode 100644 index 0000000..77472f3 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/l3_bank_test.c @@ -0,0 +1,48 @@ +/* + * Copyright 2014, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "event.h" +#include "utils.h" + +#define MALLOC_SIZE (0x10000 * 10) /* Ought to be enough .. */ + +/* + * Tests that the L3 bank handling is correct. We fixed it in commit e9aaac1. + */ +static int l3_bank_test(void) +{ + struct event event; + char *p; + int i; + + p = malloc(MALLOC_SIZE); + FAIL_IF(!p); + + event_init(&event, 0x84918F); + + FAIL_IF(event_open(&event)); + + for (i = 0; i < MALLOC_SIZE; i += 0x10000) + p[i] = i; + + event_read(&event); + event_report(&event); + + FAIL_IF(event.result.running == 0); + FAIL_IF(event.result.enabled == 0); + + event_close(&event); + free(p); + + return 0; +} + +int main(void) +{ + return test_harness(l3_bank_test, "l3_bank_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c index 0f6a473..9768dea 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.c +++ b/tools/testing/selftests/powerpc/pmu/lib.c @@ -5,10 +5,15 @@ #define _GNU_SOURCE /* For CPU_ZERO etc. */ +#include <elf.h> #include <errno.h> +#include <fcntl.h> +#include <link.h> #include <sched.h> #include <setjmp.h> #include <stdlib.h> +#include <sys/stat.h> +#include <sys/types.h> #include <sys/wait.h> #include "utils.h" @@ -177,8 +182,8 @@ struct addr_range libc, vdso; int parse_proc_maps(void) { + unsigned long start, end; char execute, name[128]; - uint64_t start, end; FILE *f; int rc; @@ -250,3 +255,46 @@ out_close: out: return rc; } + +static char auxv[4096]; + +void *get_auxv_entry(int type) +{ + ElfW(auxv_t) *p; + void *result; + ssize_t num; + int fd; + + fd = open("/proc/self/auxv", O_RDONLY); + if (fd == -1) { + perror("open"); + return NULL; + } + + result = NULL; + + num = read(fd, auxv, sizeof(auxv)); + if (num < 0) { + perror("read"); + goto out; + } + + if (num > sizeof(auxv)) { + printf("Overflowed auxv buffer\n"); + goto out; + } + + p = (ElfW(auxv_t) *)auxv; + + while (p->a_type != AT_NULL) { + if (p->a_type == type) { + result = (void *)p->a_un.a_val; + break; + } + + p++; + } +out: + close(fd); + return result; +} diff --git a/tools/testing/selftests/powerpc/pmu/lib.h b/tools/testing/selftests/powerpc/pmu/lib.h index ca5d72a..0f0339c 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.h +++ b/tools/testing/selftests/powerpc/pmu/lib.h @@ -29,6 +29,7 @@ extern int notify_parent(union pipe write_pipe); extern int notify_parent_of_error(union pipe write_pipe); extern pid_t eat_cpu(int (test_function)(void)); extern bool require_paranoia_below(int level); +extern void *get_auxv_entry(int type); struct addr_range { uint64_t first, last; diff --git a/tools/testing/selftests/powerpc/pmu/per_event_excludes.c b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c new file mode 100644 index 0000000..fddbbc9 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c @@ -0,0 +1,114 @@ +/* + * Copyright 2014, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#define _GNU_SOURCE + +#include <elf.h> +#include <limits.h> +#include <stdio.h> +#include <stdbool.h> +#include <string.h> +#include <sys/prctl.h> + +#include "event.h" +#include "lib.h" +#include "utils.h" + +/* + * Test that per-event excludes work. + */ + +static int per_event_excludes(void) +{ + struct event *e, events[4]; + char *platform; + int i; + + platform = (char *)get_auxv_entry(AT_BASE_PLATFORM); + FAIL_IF(!platform); + SKIP_IF(strcmp(platform, "power8") != 0); + + /* + * We need to create the events disabled, otherwise the running/enabled + * counts don't match up. + */ + e = &events[0]; + event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "instructions"); + e->attr.disabled = 1; + + e = &events[1]; + event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "instructions(k)"); + e->attr.disabled = 1; + e->attr.exclude_user = 1; + e->attr.exclude_hv = 1; + + e = &events[2]; + event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "instructions(h)"); + e->attr.disabled = 1; + e->attr.exclude_user = 1; + e->attr.exclude_kernel = 1; + + e = &events[3]; + event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "instructions(u)"); + e->attr.disabled = 1; + e->attr.exclude_hv = 1; + e->attr.exclude_kernel = 1; + + FAIL_IF(event_open(&events[0])); + + /* + * The open here will fail if we don't have per event exclude support, + * because the second event has an incompatible set of exclude settings + * and we're asking for the events to be in a group. + */ + for (i = 1; i < 4; i++) + FAIL_IF(event_open_with_group(&events[i], events[0].fd)); + + /* + * Even though the above will fail without per-event excludes we keep + * testing in order to be thorough. + */ + prctl(PR_TASK_PERF_EVENTS_ENABLE); + + /* Spin for a while */ + for (i = 0; i < INT_MAX; i++) + asm volatile("" : : : "memory"); + + prctl(PR_TASK_PERF_EVENTS_DISABLE); + + for (i = 0; i < 4; i++) { + FAIL_IF(event_read(&events[i])); + event_report(&events[i]); + } + + /* + * We should see that all events have enabled == running. That + * shows that they were all on the PMU at once. + */ + for (i = 0; i < 4; i++) + FAIL_IF(events[i].result.running != events[i].result.enabled); + + /* + * We can also check that the result for instructions is >= all the + * other counts. That's because it is counting all instructions while + * the others are counting a subset. + */ + for (i = 1; i < 4; i++) + FAIL_IF(events[0].result.value < events[i].result.value); + + for (i = 0; i < 4; i++) + event_close(&events[i]); + + return 0; +} + +int main(void) +{ + return test_harness(per_event_excludes, "per_event_excludes"); +} diff --git a/tools/testing/selftests/powerpc/primitives/Makefile b/tools/testing/selftests/powerpc/primitives/Makefile new file mode 100644 index 0000000..ea737ca --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/Makefile @@ -0,0 +1,17 @@ +CFLAGS += -I$(CURDIR) + +PROGS := load_unaligned_zeropad + +all: $(PROGS) + +$(PROGS): ../harness.c + +run_tests: all + @-for PROG in $(PROGS); do \ + ./$$PROG; \ + done; + +clean: + rm -f $(PROGS) *.o + +.PHONY: all run_tests clean diff --git a/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h b/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h new file mode 120000 index 0000000..b14255e --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h @@ -0,0 +1 @@ +../.././../../../../arch/powerpc/include/asm/asm-compat.h
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h b/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h diff --git a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c new file mode 100644 index 0000000..d1b6475 --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c @@ -0,0 +1,147 @@ +/* + * Userspace test harness for load_unaligned_zeropad. Creates two + * pages and uses mprotect to prevent access to the second page and + * a SEGV handler that walks the exception tables and runs the fixup + * routine. + * + * The results are compared against a normal load that is that is + * performed while access to the second page is enabled via mprotect. + * + * Copyright (C) 2014 Anton Blanchard <anton@au.ibm.com>, IBM + * + * 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 <stdlib.h> +#include <string.h> +#include <stdio.h> +#include <stdbool.h> +#include <signal.h> +#include <unistd.h> +#include <sys/mman.h> + +#define FIXUP_SECTION ".ex_fixup" + +#include "word-at-a-time.h" + +#include "utils.h" + + +static int page_size; +static char *mem_region; + +static int protect_region(void) +{ + if (mprotect(mem_region + page_size, page_size, PROT_NONE)) { + perror("mprotect"); + return 1; + } + + return 0; +} + +static int unprotect_region(void) +{ + if (mprotect(mem_region + page_size, page_size, PROT_READ|PROT_WRITE)) { + perror("mprotect"); + return 1; + } + + return 0; +} + +extern char __start___ex_table[]; +extern char __stop___ex_table[]; + +#if defined(__powerpc64__) +#define UCONTEXT_NIA(UC) (UC)->uc_mcontext.gp_regs[PT_NIP] +#elif defined(__powerpc__) +#define UCONTEXT_NIA(UC) (UC)->uc_mcontext.uc_regs->gregs[PT_NIP] +#else +#error implement UCONTEXT_NIA +#endif + +static int segv_error; + +static void segv_handler(int signr, siginfo_t *info, void *ptr) +{ + ucontext_t *uc = (ucontext_t *)ptr; + unsigned long addr = (unsigned long)info->si_addr; + unsigned long *ip = &UCONTEXT_NIA(uc); + unsigned long *ex_p = (unsigned long *)__start___ex_table; + + while (ex_p < (unsigned long *)__stop___ex_table) { + unsigned long insn, fixup; + + insn = *ex_p++; + fixup = *ex_p++; + + if (insn == *ip) { + *ip = fixup; + return; + } + } + + printf("No exception table match for NIA %lx ADDR %lx\n", *ip, addr); + segv_error++; +} + +static void setup_segv_handler(void) +{ + struct sigaction action; + + memset(&action, 0, sizeof(action)); + action.sa_sigaction = segv_handler; + action.sa_flags = SA_SIGINFO; + sigaction(SIGSEGV, &action, NULL); +} + +static int do_one_test(char *p, int page_offset) +{ + unsigned long should; + unsigned long got; + + FAIL_IF(unprotect_region()); + should = *(unsigned long *)p; + FAIL_IF(protect_region()); + + got = load_unaligned_zeropad(p); + + if (should != got) + printf("offset %u load_unaligned_zeropad returned 0x%lx, should be 0x%lx\n", page_offset, got, should); + + return 0; +} + +static int test_body(void) +{ + unsigned long i; + + page_size = getpagesize(); + mem_region = mmap(NULL, page_size * 2, PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANONYMOUS, -1, 0); + + FAIL_IF(mem_region == MAP_FAILED); + + for (i = 0; i < page_size; i++) + mem_region[i] = i; + + memset(mem_region+page_size, 0, page_size); + + setup_segv_handler(); + + for (i = 0; i < page_size; i++) + FAIL_IF(do_one_test(mem_region+i, i)); + + FAIL_IF(segv_error); + + return 0; +} + +int main(void) +{ + return test_harness(test_body, "load_unaligned_zeropad"); +} diff --git a/tools/testing/selftests/powerpc/primitives/word-at-a-time.h b/tools/testing/selftests/powerpc/primitives/word-at-a-time.h new file mode 120000 index 0000000..eb74401 --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/word-at-a-time.h @@ -0,0 +1 @@ +../../../../../arch/powerpc/include/asm/word-at-a-time.h
\ No newline at end of file diff --git a/tools/testing/selftests/ptrace/peeksiginfo.c b/tools/testing/selftests/ptrace/peeksiginfo.c index d46558b..c34cd8a 100644 --- a/tools/testing/selftests/ptrace/peeksiginfo.c +++ b/tools/testing/selftests/ptrace/peeksiginfo.c @@ -31,6 +31,10 @@ static int sys_ptrace(int request, pid_t pid, void *addr, void *data) #define TEST_SICODE_PRIV -1 #define TEST_SICODE_SHARE -2 +#ifndef PAGE_SIZE +#define PAGE_SIZE sysconf(_SC_PAGESIZE) +#endif + #define err(fmt, ...) \ fprintf(stderr, \ "Error (%s:%d): " fmt, \ diff --git a/tools/testing/selftests/rcutorture/bin/config2frag.sh b/tools/testing/selftests/rcutorture/bin/config2frag.sh index 9f9ffcd..56f51ae 100644..100755 --- a/tools/testing/selftests/rcutorture/bin/config2frag.sh +++ b/tools/testing/selftests/rcutorture/bin/config2frag.sh @@ -1,5 +1,5 @@ -#!/bin/sh -# Usage: sh config2frag.sh < .config > configfrag +#!/bin/bash +# Usage: config2frag.sh < .config > configfrag # # Converts the "# CONFIG_XXX is not set" to "CONFIG_XXX=n" so that the # resulting file becomes a legitimate Kconfig fragment. diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh index d686537..eee31e2 100755 --- a/tools/testing/selftests/rcutorture/bin/configcheck.sh +++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh @@ -1,5 +1,5 @@ -#!/bin/sh -# Usage: sh configcheck.sh .config .config-template +#!/bin/bash +# Usage: configcheck.sh .config .config-template # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index 9c3f3d3..15f1a17 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -1,6 +1,6 @@ -#!/bin/sh +#!/bin/bash # -# sh configinit.sh config-spec-file [ build output dir ] +# Usage: configinit.sh config-spec-file [ build output dir ] # # Create a .config file from the spec file. Run from the kernel source tree. # Exits with 0 if all went well, with 1 if all went well but the config diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index d01b865..b325470 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -64,6 +64,26 @@ configfrag_boot_params () { fi } +# configfrag_boot_cpus bootparam-string config-fragment-file config-cpus +# +# Decreases number of CPUs based on any maxcpus= boot parameters specified. +configfrag_boot_cpus () { + local bootargs="`configfrag_boot_params "$1" "$2"`" + local maxcpus + if echo "${bootargs}" | grep -q 'maxcpus=[0-9]' + then + maxcpus="`echo "${bootargs}" | sed -e 's/^.*maxcpus=\([0-9]*\).*$/\1/'`" + if test "$3" -gt "$maxcpus" + then + echo $maxcpus + else + echo $3 + fi + else + echo $3 + fi +} + # configfrag_hotplug_cpu config-fragment-file # # Returns 1 if the config fragment specifies hotplug CPU. diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 7c1e56b..00cb0db 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -2,7 +2,7 @@ # # Build a kvm-ready Linux kernel from the tree in the current directory. # -# Usage: sh kvm-build.sh config-template build-dir more-configs +# Usage: kvm-build.sh config-template build-dir more-configs # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh index 7f1ff1a..43f7640 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh @@ -2,7 +2,7 @@ # # Analyze a given results directory for locktorture progress. # -# Usage: sh kvm-recheck-lock.sh resdir +# Usage: kvm-recheck-lock.sh resdir # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index 307c4b9..d6cc07f 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -2,7 +2,7 @@ # # Analyze a given results directory for rcutorture progress. # -# Usage: sh kvm-recheck-rcu.sh resdir +# Usage: kvm-recheck-rcu.sh resdir # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index ee1f6ca..4f5b20f 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -4,7 +4,7 @@ # check the build and console output for errors. Given a directory # containing results directories, this recursively checks them all. # -# Usage: sh kvm-recheck.sh resdir ... +# Usage: kvm-recheck.sh resdir ... # # 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 @@ -54,10 +54,16 @@ do if test -f "$i/qemu-cmd" then print_bug qemu failed + echo " $i" + elif test -f "$i/buildonly" + then + echo Build-only run, no boot/test + configcheck.sh $i/.config $i/ConfigFragment + parse-build.sh $i/Make.out $configfile else print_bug Build failed + echo " $i" fi - echo " $i" fi done done 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 27e544e..8ca9f21 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -6,7 +6,7 @@ # Execute this in the source tree. Do not run it as a background task # because qemu does not seem to like that much. # -# Usage: sh kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args +# 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 @@ -42,9 +42,10 @@ grace=120 T=/tmp/kvm-test-1-run.sh.$$ 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 $config_template | sed -e 's,/[^/]*$,,'` @@ -131,11 +132,15 @@ boot_args=$6 cd $KVM kstarttime=`awk 'BEGIN { print systime() }' < /dev/null` -echo ' ---' `date`: Starting kernel +if test -z "$TORTURE_BUILDONLY" +then + echo ' ---' `date`: Starting kernel +fi # Generate -smp qemu argument. qemu_args="-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` if test $cpu_count -gt $vcpus then @@ -157,13 +162,14 @@ boot_args="`configfrag_boot_params "$boot_args" "$config_template"`" # Generate kernel-version-specific boot parameters boot_args="`per_version_boot_params "$boot_args" $builddir/.config $seconds`" -echo $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd if test -n "$TORTURE_BUILDONLY" then echo Build-only run specified, boot/test omitted. + touch $resdir/buildonly exit 0 fi -( $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) & +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 @@ -209,7 +215,7 @@ then fi if test $kruntime -ge $((seconds + grace)) then - echo "!!! Hang at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1 + echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1 kill -KILL $qemu_pid break fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 40285c5..368d64a 100644..100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -7,7 +7,7 @@ # Edit the definitions below to set the locations of the various directories, # as well as the test duration. # -# Usage: sh kvm.sh [ options ] +# Usage: kvm.sh [ options ] # # 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 @@ -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" @@ -186,9 +178,11 @@ fi touch $T/cfgcpu for CF in $configs do - if test -f "$CONFIGFRAG/$kversion/$CF" + if test -f "$CONFIGFRAG/$CF" then - echo $CF `configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF` >> $T/cfgcpu + 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." exit 1 @@ -250,7 +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 @@ -283,7 +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/ \ @@ -340,12 +333,18 @@ function dump(first, pastlast) for (j = 1; j < jn; j++) { builddir=KVM "/b" j print "rm -f " builddir ".ready" - print "echo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`"; - print "echo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log"; + print "if test -z \"$TORTURE_BUILDONLY\"" + print "then" + print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`"; + print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log"; + print "fi" } print "wait" - print "echo ---- All kernel runs complete. `date`"; - print "echo ---- All kernel runs complete. `date` >> " rd "/log"; + print "if test -z \"$TORTURE_BUILDONLY\"" + print "then" + print "\techo ---- All kernel runs complete. `date`"; + print "\techo ---- All kernel runs complete. `date` >> " rd "/log"; + print "fi" for (j = 1; j < jn; j++) { builddir=KVM "/b" j print "echo ----", cfr[j], cpusr[j] ovf ": Build/run results:"; @@ -385,10 +384,7 @@ echo echo echo " --- `date` Test summary:" echo Results directory: $resdir/$ds -if test -z "$TORTURE_BUILDONLY" -then - kvm-recheck.sh $resdir/$ds -fi +kvm-recheck.sh $resdir/$ds ___EOF___ if test "$dryrun" = script @@ -403,7 +399,7 @@ then sed -e 's/:.*$//' -e 's/^echo //' exit 0 else - # Not a dryru, so run the script. + # Not a dryrun, so run the script. sh $T/script fi diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh index 5432309..499d1e5 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-build.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # # Check the build output from an rcutorture run for goodness. # The "file" is a pathname on the local system, and "title" is @@ -6,8 +6,7 @@ # # The file must contain kernel build output. # -# Usage: -# sh parse-build.sh file title +# Usage: parse-build.sh file title # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 4185d4c..f962ba4 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -1,11 +1,10 @@ -#!/bin/sh +#!/bin/bash # # Check the console output from an rcutorture run for oopses. # The "file" is a pathname on the local system, and "title" is # a text string for error-message purposes. # -# Usage: -# sh parse-console.sh file title +# Usage: parse-console.sh file title # # 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 @@ -33,6 +32,10 @@ title="$2" . functions.sh +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 if test -s $T then diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh index 3455560..e3c5f07 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-torture.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # # Check the console output from a torture run for goodness. # The "file" is a pathname on the local system, and "title" is @@ -7,8 +7,7 @@ # The file must contain torture output, but can be interspersed # with other dmesg text, as in console-log output. # -# Usage: -# sh parse-torture.sh file title +# Usage: parse-torture.sh file title # # 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 diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST index a061b22..6910b73 100644 --- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST @@ -1 +1,4 @@ LOCK01 +LOCK02 +LOCK03 +LOCK04
\ No newline at end of file diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK02 b/tools/testing/selftests/rcutorture/configs/lock/LOCK02 new file mode 100644 index 0000000..1d1da14 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK02 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot new file mode 100644 index 0000000..5aa44b4 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot @@ -0,0 +1 @@ +locktorture.torture_type=mutex_lock diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK03 b/tools/testing/selftests/rcutorture/configs/lock/LOCK03 new file mode 100644 index 0000000..1d1da14 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK03 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot new file mode 100644 index 0000000..a67bbe0 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot @@ -0,0 +1 @@ +locktorture.torture_type=rwsem_lock diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK04 b/tools/testing/selftests/rcutorture/configs/lock/LOCK04 new file mode 100644 index 0000000..1d1da14 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK04 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot new file mode 100644 index 0000000..48c04fe --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot @@ -0,0 +1 @@ +locktorture.torture_type=rw_lock diff --git a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh index 9746ea1..252aae6 100644 --- a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh @@ -38,6 +38,6 @@ per_version_boot_params () { echo $1 `locktorture_param_onoff "$1" "$2"` \ locktorture.stat_interval=15 \ locktorture.shutdown_secs=$3 \ - locktorture.locktorture_runnable=1 \ + locktorture.torture_runnable=1 \ locktorture.verbose=1 } diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST index cd3d29c..a3a1a05 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST @@ -11,3 +11,6 @@ SRCU-N SRCU-P TINY01 TINY02 +TASKS01 +TASKS02 +TASKS03 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 new file mode 100644 index 0000000..97f0a0b --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 @@ -0,0 +1,9 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=2 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_RCU=y +CONFIG_TASKS_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot new file mode 100644 index 0000000..cd2a188 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot @@ -0,0 +1 @@ +rcutorture.torture_type=tasks diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 new file mode 100644 index 0000000..696d2ea7 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 @@ -0,0 +1,5 @@ +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +CONFIG_TASKS_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot new file mode 100644 index 0000000..cd2a188 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot @@ -0,0 +1 @@ +rcutorture.torture_type=tasks diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 new file mode 100644 index 0000000..9c60da5 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 @@ -0,0 +1,13 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=2 +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +CONFIG_TASKS_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=n +CONFIG_NO_HZ_FULL=y +CONFIG_NO_HZ_FULL_ALL=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot new file mode 100644 index 0000000..cd2a188 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot @@ -0,0 +1 @@ +rcutorture.torture_type=tasks diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 index f4feaee..36e41df 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 0000000..0f08027 --- /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 9c827ec..f8a10a7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -1,22 +1,18 @@ CONFIG_SMP=y -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 CONFIG_RCU_FAST_NO_HZ=y CONFIG_RCU_TRACE=y CONFIG_HOTPLUG_CPU=y -CONFIG_RCU_FANOUT=8 -CONFIG_RCU_FANOUT_EXACT=n +CONFIG_MAXSMP=y CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ZERO=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=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/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot index 0fc8a34..adc3abc 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot @@ -1 +1 @@ -rcutorture.torture_type=rcu_bh +rcutorture.torture_type=rcu_bh maxcpus=8 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 index 1a777b5..629122f 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 @@ -18,8 +18,6 @@ CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n -CONFIG_PROVE_RCU_DELAY=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 61c8d9c..a25de47 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 @@ -18,8 +18,6 @@ CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n -CONFIG_PROVE_RCU_DELAY=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 c1f111c..53f24e0 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 @@ -14,9 +14,7 @@ CONFIG_RCU_FANOUT_LEAF=4 CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=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 7dbd27c..0f84db3 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -18,7 +18,5 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=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 d0f32e5..212e3bf 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -18,7 +18,5 @@ CONFIG_RCU_NOCB_CPU_NONE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y CONFIG_PROVE_RCU=y -CONFIG_PROVE_RCU_DELAY=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 3b42b8b..15b3e1a 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 2e477df..7eee63b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -19,7 +19,5 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y CONFIG_PROVE_RCU=y -CONFIG_PROVE_RCU_DELAY=n 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 0000000..da9a03a --- /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 042f86e..92a97fa 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -1,5 +1,6 @@ CONFIG_SMP=y CONFIG_NR_CPUS=16 +CONFIG_CPUMASK_OFFSTACK=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n @@ -7,7 +8,7 @@ CONFIG_PREEMPT=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y -CONFIG_NO_HZ_FULL_ALL=y +CONFIG_NO_HZ_FULL_ALL=n CONFIG_NO_HZ_FULL_SYSIDLE=y CONFIG_RCU_FAST_NO_HZ=n CONFIG_RCU_TRACE=y @@ -17,7 +18,5 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_FANOUT_EXACT=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=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/TREE07.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot new file mode 100644 index 0000000..d446099 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot @@ -0,0 +1 @@ +nohz_full=2-9 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 index 3438cee..5812027 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 @@ -18,8 +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_RCU_DELAY=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 bf4523d..3eaecca 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 @@ -18,8 +18,6 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=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 3b42b8b..2561daf 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 81e4f7c..6076b36 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 @@ -13,8 +13,6 @@ CONFIG_SUSPEND=n CONFIG_HIBERNATION=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_RCU_DELAY=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 1822394..0000000 --- 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 d3ef873..0000000 --- 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 02e4185..0000000 --- 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 b3100f6..0000000 --- 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 c56b445..0000000 --- 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 90d924f..0000000 --- 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 023f312..0000000 --- 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 6fd0235..0000000 --- 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 f72402d..0000000 --- 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 0f3b667..0000000 --- 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 b035e14..0000000 --- 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 3ccf6a9..0000000 --- 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 ef624ce..0000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,28 +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_PROVE_RCU_DELAY=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 e3361c3..0000000 --- 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 64abfc3..0000000 --- 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 5ace37a..0000000 --- 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 da4cbc66..0000000 --- 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 d81e11d..0000000 --- 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 02e4185..0000000 --- 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 b3100f6..0000000 --- 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 c56b445..0000000 --- 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 90d924f..0000000 --- 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 0ccc36d..0000000 --- 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 3f640cf..0000000 --- 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 285da2d..0000000 --- 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 023f312..0000000 --- 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 6fd0235..0000000 --- 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 9647c44..0000000 --- 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 0f3b667..0000000 --- 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 b035e14..0000000 --- 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 3ccf6a9..0000000 --- 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 ef624ce..0000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,28 +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_PROVE_RCU_DELAY=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 f4c9175..0000000 --- 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 77a8c5b..0000000 --- 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 0eecebc..0000000 --- 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 0eecebc..0000000 --- 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 588bc70..0000000 --- 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 e3361c3..0000000 --- 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 64abfc3..0000000 --- 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 1822394..0000000 --- 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 d81e11d..0000000 --- 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 02e4185..0000000 --- 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 b3100f6..0000000 --- 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 c56b445..0000000 --- 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 90d924f..0000000 --- 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 023f312..0000000 --- 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 6fd0235..0000000 --- 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 9647c44..0000000 --- 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 0f3b667..0000000 --- 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 b035e14..0000000 --- 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 3ccf6a9..0000000 --- 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 ef624ce..0000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,28 +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_PROVE_RCU_DELAY=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 e3361c3..0000000 --- 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 64abfc3..0000000 --- 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 bae5569..0000000 --- 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 1822394..0000000 --- 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 d81e11d..0000000 --- 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 02e4185..0000000 --- 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 b3100f6..0000000 --- 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 c56b445..0000000 --- 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 90d924f..0000000 --- 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 023f312..0000000 --- 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 6fd0235..0000000 --- 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 9647c44..0000000 --- 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 0f3b667..0000000 --- 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 b035e14..0000000 --- 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 3ccf6a9..0000000 --- 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 ef624ce..0000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp +++ /dev/null @@ -1,28 +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_PROVE_RCU_DELAY=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 e3361c3..0000000 --- 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 64abfc3..0000000 --- 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 8977d8d..0000000 --- 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/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh index 8977d8d..ffb85ed 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh @@ -51,7 +51,7 @@ per_version_boot_params () { `rcutorture_param_n_barrier_cbs "$1"` \ rcutorture.stat_interval=15 \ rcutorture.shutdown_secs=$3 \ - rcutorture.rcutorture_runnable=1 \ + rcutorture.torture_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 28db67b..9ef33a7 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 adbb76c..ec03c88 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: @@ -14,11 +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_PROVE_RCU_DELAY -- Do one. -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. @@ -28,7 +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. @@ -78,7 +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 @@ -89,7 +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/rcutorture/doc/initrd.txt b/tools/testing/selftests/rcutorture/doc/initrd.txt index 49d134c..4170e71 100644 --- a/tools/testing/selftests/rcutorture/doc/initrd.txt +++ b/tools/testing/selftests/rcutorture/doc/initrd.txt @@ -6,6 +6,7 @@ this case. There are probably much better ways of doing this. That said, here are the commands: ------------------------------------------------------------------------ +cd tools/testing/selftests/rcutorture zcat /initrd.img > /tmp/initrd.img.zcat mkdir initrd cd initrd diff --git a/tools/testing/selftests/size/.gitignore b/tools/testing/selftests/size/.gitignore new file mode 100644 index 0000000..189b781 --- /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 0000000..04dc25e --- /dev/null +++ b/tools/testing/selftests/size/Makefile @@ -0,0 +1,12 @@ +CC = $(CROSS_COMPILE)gcc + +all: get_size + +get_size: get_size.c + $(CC) -static -ffreestanding -nostartfiles -s $< -o $@ + +run_tests: all + ./get_size + +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 0000000..2d1af7c --- /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/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 41bd855..f87d970 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 @@ -194,16 +196,16 @@ int main(int argc, char **argv) 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 +217,7 @@ 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/user/Makefile b/tools/testing/selftests/user/Makefile index 396255b..12c9d15 100644 --- a/tools/testing/selftests/user/Makefile +++ b/tools/testing/selftests/user/Makefile @@ -4,10 +4,4 @@ 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_user_copy.sh 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 0000000..350107f --- /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 3f94e1a..4c4b1f6 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -3,6 +3,7 @@ CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall BINARIES = hugepage-mmap hugepage-shm map_hugetlb thuge-gen hugetlbfstest +BINARIES += transhuge-stress all: $(BINARIES) %: %.c diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c new file mode 100644 index 0000000..fd7f1b4 --- /dev/null +++ b/tools/testing/selftests/vm/transhuge-stress.c @@ -0,0 +1,144 @@ +/* + * Stress test for transparent huge pages, memory compaction and migration. + * + * Authors: Konstantin Khlebnikov <koct9i@gmail.com> + * + * This is free and unencumbered software released into the public domain. + */ + +#include <stdlib.h> +#include <stdio.h> +#include <stdint.h> +#include <err.h> +#include <time.h> +#include <unistd.h> +#include <fcntl.h> +#include <string.h> +#include <sys/mman.h> + +#define PAGE_SHIFT 12 +#define HPAGE_SHIFT 21 + +#define PAGE_SIZE (1 << PAGE_SHIFT) +#define HPAGE_SIZE (1 << HPAGE_SHIFT) + +#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) +#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) + +int pagemap_fd; + +int64_t allocate_transhuge(void *ptr) +{ + uint64_t ent[2]; + + /* drop pmd */ + if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANONYMOUS | + MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) + errx(2, "mmap transhuge"); + + if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) + err(2, "MADV_HUGEPAGE"); + + /* allocate transparent huge page */ + *(volatile void **)ptr = ptr; + + if (pread(pagemap_fd, ent, sizeof(ent), + (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) + err(2, "read pagemap"); + + if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && + PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && + !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) + return PAGEMAP_PFN(ent[0]); + + return -1; +} + +int main(int argc, char **argv) +{ + size_t ram, len; + void *ptr, *p; + struct timespec a, b; + double s; + uint8_t *map; + size_t map_len; + + ram = sysconf(_SC_PHYS_PAGES); + if (ram > SIZE_MAX / sysconf(_SC_PAGESIZE) / 4) + ram = SIZE_MAX / 4; + else + ram *= sysconf(_SC_PAGESIZE); + + if (argc == 1) + len = ram; + else if (!strcmp(argv[1], "-h")) + errx(1, "usage: %s [size in MiB]", argv[0]); + else + len = atoll(argv[1]) << 20; + + warnx("allocate %zd transhuge pages, using %zd MiB virtual memory" + " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20, + len >> (20 + HPAGE_SHIFT - PAGE_SHIFT - 1)); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + err(2, "open pagemap"); + + len -= len % HPAGE_SIZE; + ptr = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0); + if (ptr == MAP_FAILED) + err(2, "initial mmap"); + ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE; + + if (madvise(ptr, len, MADV_HUGEPAGE)) + err(2, "MADV_HUGEPAGE"); + + map_len = ram >> (HPAGE_SHIFT - 1); + map = malloc(map_len); + if (!map) + errx(2, "map malloc"); + + while (1) { + int nr_succeed = 0, nr_failed = 0, nr_pages = 0; + + memset(map, 0, map_len); + + clock_gettime(CLOCK_MONOTONIC, &a); + for (p = ptr; p < ptr + len; p += HPAGE_SIZE) { + int64_t pfn; + + pfn = allocate_transhuge(p); + + if (pfn < 0) { + nr_failed++; + } else { + size_t idx = pfn >> (HPAGE_SHIFT - PAGE_SHIFT); + + nr_succeed++; + if (idx >= map_len) { + map = realloc(map, idx + 1); + if (!map) + errx(2, "map realloc"); + memset(map + map_len, 0, idx + 1 - map_len); + map_len = idx + 1; + } + if (!map[idx]) + nr_pages++; + map[idx] = 1; + } + + /* split transhuge page, keep last page */ + if (madvise(p, HPAGE_SIZE - PAGE_SIZE, MADV_DONTNEED)) + err(2, "MADV_DONTNEED"); + } + clock_gettime(CLOCK_MONOTONIC, &b); + s = b.tv_sec - a.tv_sec + (b.tv_nsec - a.tv_nsec) / 1000000000.; + + warnx("%.3f s/loop, %.3f ms/page, %10.3f MiB/s\t" + "%4d succeed, %4d failed, %4d different pages", + s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 << 20), + nr_succeed, nr_failed, nr_pages); + } +} diff --git a/tools/thermal/tmon/sysfs.c b/tools/thermal/tmon/sysfs.c index dfe4548..1c12536 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/time/udelay_test.sh b/tools/time/udelay_test.sh new file mode 100755 index 0000000..12d46b9 --- /dev/null +++ b/tools/time/udelay_test.sh @@ -0,0 +1,66 @@ +#!/bin/bash + +# udelay() test script +# +# Test is executed by writing and reading to /sys/kernel/debug/udelay_test +# and exercises a variety of delays to ensure that udelay() is delaying +# at least as long as requested (as compared to ktime). +# +# Copyright (C) 2014 Google, Inc. +# +# This software is licensed under the terms of the GNU General Public +# License version 2, as published by the Free Software Foundation, and +# may be copied, distributed, and modified under those terms. +# +# 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. + +MODULE_NAME=udelay_test +UDELAY_PATH=/sys/kernel/debug/udelay_test + +setup() +{ + /sbin/modprobe -q $MODULE_NAME + tmp_file=`mktemp` +} + +test_one() +{ + delay=$1 + echo $delay > $UDELAY_PATH + tee -a $tmp_file < $UDELAY_PATH +} + +cleanup() +{ + if [ -f $tmp_file ]; then + rm $tmp_file + fi + /sbin/modprobe -q -r $MODULE_NAME +} + +trap cleanup EXIT +setup + +# Delay for a variety of times. +# 1..200, 200..500 (by 10), 500..2000 (by 100) +for (( delay = 1; delay < 200; delay += 1 )); do + test_one $delay +done +for (( delay = 200; delay < 500; delay += 10 )); do + test_one $delay +done +for (( delay = 500; delay <= 2000; delay += 100 )); do + test_one $delay +done + +# Search for failures +count=`grep -c FAIL $tmp_file` +if [ $? -eq "0" ]; then + echo "ERROR: $count delays failed to delay long enough" + retcode=1 +fi + +exit $retcode diff --git a/tools/usb/ffs-aio-example/multibuff/device_app/aio_multibuff.c b/tools/usb/ffs-aio-example/multibuff/device_app/aio_multibuff.c index 87216a0..aaca1f4 100644 --- a/tools/usb/ffs-aio-example/multibuff/device_app/aio_multibuff.c +++ b/tools/usb/ffs-aio-example/multibuff/device_app/aio_multibuff.c @@ -1,3 +1,30 @@ +/* + * This is free and unencumbered software released into the public domain. + * + * Anyone is free to copy, modify, publish, use, compile, sell, or + * distribute this software, either in source code form or as a compiled + * binary, for any purpose, commercial or non-commercial, and by any + * means. + * + * In jurisdictions that recognize copyright laws, the author or authors + * of this software dedicate any and all copyright interest in the + * software to the public domain. We make this dedication for the benefit + * of the public at large and to the detriment of our heirs and + * successors. We intend this dedication to be an overt act of + * relinquishment in perpetuity of all present and future rights to this + * software under copyright law. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * For more information, please refer to <http://unlicense.org/> + */ + #define _BSD_SOURCE /* for endian.h */ #include <endian.h> @@ -27,7 +54,9 @@ /******************** Descriptors and Strings *******************************/ static const struct { - struct usb_functionfs_descs_head header; + struct usb_functionfs_descs_head_v2 header; + __le32 fs_count; + __le32 hs_count; struct { struct usb_interface_descriptor intf; struct usb_endpoint_descriptor_no_audio bulk_sink; @@ -35,11 +64,12 @@ static const struct { } __attribute__ ((__packed__)) fs_descs, hs_descs; } __attribute__ ((__packed__)) descriptors = { .header = { - .magic = htole32(FUNCTIONFS_DESCRIPTORS_MAGIC), + .magic = htole32(FUNCTIONFS_DESCRIPTORS_MAGIC_V2), + .flags = htole32(FUNCTIONFS_HAS_FS_DESC | + FUNCTIONFS_HAS_HS_DESC), .length = htole32(sizeof(descriptors)), - .fs_count = 3, - .hs_count = 3, }, + .fs_count = htole32(3), .fs_descs = { .intf = { .bLength = sizeof(descriptors.fs_descs.intf), @@ -61,6 +91,7 @@ static const struct { .bmAttributes = USB_ENDPOINT_XFER_BULK, }, }, + .hs_count = htole32(3), .hs_descs = { .intf = { .bLength = sizeof(descriptors.hs_descs.intf), @@ -311,7 +342,7 @@ int main(int argc, char *argv[]) iobuf[i].requested = ret; printf("submit: %d requests buf: %d\n", ret, i); } else - perror("unable to submit reqests"); + perror("unable to submit requests"); } /* if event is ready to read */ 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 b0ad874..daa3abe 100644 --- a/tools/usb/ffs-aio-example/multibuff/host_app/test.c +++ b/tools/usb/ffs-aio-example/multibuff/host_app/test.c @@ -1,3 +1,30 @@ +/* + * This is free and unencumbered software released into the public domain. + * + * Anyone is free to copy, modify, publish, use, compile, sell, or + * distribute this software, either in source code form or as a compiled + * binary, for any purpose, commercial or non-commercial, and by any + * means. + * + * In jurisdictions that recognize copyright laws, the author or authors + * of this software dedicate any and all copyright interest in the + * software to the public domain. We make this dedication for the benefit + * of the public at large and to the detriment of our heirs and + * successors. We intend this dedication to be an overt act of + * relinquishment in perpetuity of all present and future rights to this + * software under copyright law. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * For more information, please refer to <http://unlicense.org/> + */ + #include <libusb.h> #include <stdio.h> #include <string.h> 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 f558664..adc310a 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 @@ -1,3 +1,30 @@ +/* + * This is free and unencumbered software released into the public domain. + * + * Anyone is free to copy, modify, publish, use, compile, sell, or + * distribute this software, either in source code form or as a compiled + * binary, for any purpose, commercial or non-commercial, and by any + * means. + * + * In jurisdictions that recognize copyright laws, the author or authors + * of this software dedicate any and all copyright interest in the + * software to the public domain. We make this dedication for the benefit + * of the public at large and to the detriment of our heirs and + * successors. We intend this dedication to be an overt act of + * relinquishment in perpetuity of all present and future rights to this + * software under copyright law. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * For more information, please refer to <http://unlicense.org/> + */ + #define _BSD_SOURCE /* for endian.h */ #include <endian.h> @@ -25,7 +52,9 @@ /******************** Descriptors and Strings *******************************/ static const struct { - struct usb_functionfs_descs_head header; + struct usb_functionfs_descs_head_v2 header; + __le32 fs_count; + __le32 hs_count; struct { struct usb_interface_descriptor intf; struct usb_endpoint_descriptor_no_audio bulk_sink; @@ -33,11 +62,12 @@ static const struct { } __attribute__ ((__packed__)) fs_descs, hs_descs; } __attribute__ ((__packed__)) descriptors = { .header = { - .magic = htole32(FUNCTIONFS_DESCRIPTORS_MAGIC), + .magic = htole32(FUNCTIONFS_DESCRIPTORS_MAGIC_V2), + .flags = htole32(FUNCTIONFS_HAS_FS_DESC | + FUNCTIONFS_HAS_HS_DESC), .length = htole32(sizeof(descriptors)), - .fs_count = 3, - .hs_count = 3, }, + .fs_count = htole32(3), .fs_descs = { .intf = { .bLength = sizeof(descriptors.fs_descs.intf), @@ -59,6 +89,7 @@ static const struct { .bmAttributes = USB_ENDPOINT_XFER_BULK, }, }, + .hs_count = htole32(3), .hs_descs = { .intf = { .bLength = sizeof(descriptors.hs_descs.intf), 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 64b6a57..acd6332 100644 --- a/tools/usb/ffs-aio-example/simple/host_app/test.c +++ b/tools/usb/ffs-aio-example/simple/host_app/test.c @@ -1,3 +1,30 @@ +/* + * This is free and unencumbered software released into the public domain. + * + * Anyone is free to copy, modify, publish, use, compile, sell, or + * distribute this software, either in source code form or as a compiled + * binary, for any purpose, commercial or non-commercial, and by any + * means. + * + * In jurisdictions that recognize copyright laws, the author or authors + * of this software dedicate any and all copyright interest in the + * software to the public domain. We make this dedication for the benefit + * of the public at large and to the detriment of our heirs and + * successors. We intend this dedication to be an overt act of + * relinquishment in perpetuity of all present and future rights to this + * software under copyright law. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * For more information, please refer to <http://unlicense.org/> + */ + #include <libusb.h> #include <stdio.h> #include <string.h> diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c index a87e99f..88d5e71 100644 --- a/tools/usb/ffs-test.c +++ b/tools/usb/ffs-test.c @@ -1,5 +1,5 @@ /* - * ffs-test.c.c -- user mode filesystem api for usb composite function + * ffs-test.c -- user mode filesystem api for usb composite function * * Copyright (C) 2010 Samsung Electronics * Author: Michal Nazarewicz <mina86@mina86.com> @@ -29,6 +29,7 @@ #include <fcntl.h> #include <pthread.h> #include <stdarg.h> +#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -106,7 +107,9 @@ static void _msg(unsigned level, const char *fmt, ...) /******************** Descriptors and Strings *******************************/ static const struct { - struct usb_functionfs_descs_head header; + struct usb_functionfs_descs_head_v2 header; + __le32 fs_count; + __le32 hs_count; struct { struct usb_interface_descriptor intf; struct usb_endpoint_descriptor_no_audio sink; @@ -114,11 +117,12 @@ static const struct { } __attribute__((packed)) fs_descs, hs_descs; } __attribute__((packed)) descriptors = { .header = { - .magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC), + .magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC_V2), + .flags = cpu_to_le32(FUNCTIONFS_HAS_FS_DESC | + FUNCTIONFS_HAS_HS_DESC), .length = cpu_to_le32(sizeof descriptors), - .fs_count = cpu_to_le32(3), - .hs_count = cpu_to_le32(3), }, + .fs_count = cpu_to_le32(3), .fs_descs = { .intf = { .bLength = sizeof descriptors.fs_descs.intf, @@ -142,6 +146,7 @@ static const struct { /* .wMaxPacketSize = autoconfiguration (kernel) */ }, }, + .hs_count = cpu_to_le32(3), .hs_descs = { .intf = { .bLength = sizeof descriptors.fs_descs.intf, @@ -168,6 +173,89 @@ static const struct { }, }; +static size_t descs_to_legacy(void **legacy, const void *descriptors_v2) +{ + const unsigned char *descs_end, *descs_start; + __u32 length, fs_count = 0, hs_count = 0, count; + + /* Read v2 header */ + { + const struct { + const struct usb_functionfs_descs_head_v2 header; + const __le32 counts[]; + } __attribute__((packed)) *const in = descriptors_v2; + const __le32 *counts = in->counts; + __u32 flags; + + if (le32_to_cpu(in->header.magic) != + FUNCTIONFS_DESCRIPTORS_MAGIC_V2) + return 0; + length = le32_to_cpu(in->header.length); + if (length <= sizeof in->header) + return 0; + length -= sizeof in->header; + flags = le32_to_cpu(in->header.flags); + if (flags & ~(FUNCTIONFS_HAS_FS_DESC | FUNCTIONFS_HAS_HS_DESC | + FUNCTIONFS_HAS_SS_DESC)) + return 0; + +#define GET_NEXT_COUNT_IF_FLAG(ret, flg) do { \ + if (!(flags & (flg))) \ + break; \ + if (length < 4) \ + return 0; \ + ret = le32_to_cpu(*counts); \ + length -= 4; \ + ++counts; \ + } while (0) + + GET_NEXT_COUNT_IF_FLAG(fs_count, FUNCTIONFS_HAS_FS_DESC); + GET_NEXT_COUNT_IF_FLAG(hs_count, FUNCTIONFS_HAS_HS_DESC); + GET_NEXT_COUNT_IF_FLAG(count, FUNCTIONFS_HAS_SS_DESC); + + count = fs_count + hs_count; + if (!count) + return 0; + descs_start = (const void *)counts; + +#undef GET_NEXT_COUNT_IF_FLAG + } + + /* + * Find the end of FS and HS USB descriptors. SS descriptors + * are ignored since legacy format does not support them. + */ + descs_end = descs_start; + do { + if (length < *descs_end) + return 0; + length -= *descs_end; + descs_end += *descs_end; + } while (--count); + + /* Allocate legacy descriptors and copy the data. */ + { +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + struct { + struct usb_functionfs_descs_head header; + __u8 descriptors[]; + } __attribute__((packed)) *out; +#pragma GCC diagnostic pop + + length = sizeof out->header + (descs_end - descs_start); + out = malloc(length); + out->header.magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC); + out->header.length = cpu_to_le32(length); + out->header.fs_count = cpu_to_le32(fs_count); + out->header.hs_count = cpu_to_le32(hs_count); + memcpy(out->descriptors, descs_start, descs_end - descs_start); + *legacy = out; + } + + return length; +} + #define STR_INTERFACE_ "Source/Sink" @@ -487,12 +575,29 @@ ep0_consume(struct thread *ignore, const void *buf, size_t nbytes) return nbytes; } -static void ep0_init(struct thread *t) +static void ep0_init(struct thread *t, bool legacy_descriptors) { + void *legacy; ssize_t ret; + size_t len; + + if (legacy_descriptors) { + info("%s: writing descriptors\n", t->filename); + goto legacy; + } - info("%s: writing descriptors\n", t->filename); + info("%s: writing descriptors (in v2 format)\n", t->filename); ret = write(t->fd, &descriptors, sizeof descriptors); + + if (ret < 0 && errno == EINVAL) { + warn("%s: new format rejected, trying legacy\n", t->filename); +legacy: + len = descs_to_legacy(&legacy, &descriptors); + if (len) { + ret = write(t->fd, legacy, len); + free(legacy); + } + } die_on(ret < 0, "%s: write: descriptors", t->filename); info("%s: writing strings\n", t->filename); @@ -503,14 +608,15 @@ static void ep0_init(struct thread *t) /******************** Main **************************************************/ -int main(void) +int main(int argc, char **argv) { + bool legacy_descriptors; unsigned i; - /* XXX TODO: Argument parsing missing */ + legacy_descriptors = argc > 2 && !strcmp(argv[1], "-l"); init_thread(threads); - ep0_init(threads); + ep0_init(threads, legacy_descriptors); for (i = 1; i < sizeof threads / sizeof *threads; ++i) init_thread(threads + i); diff --git a/tools/usb/usbip/.gitignore b/tools/usb/usbip/.gitignore new file mode 100644 index 0000000..9aad9e3 --- /dev/null +++ b/tools/usb/usbip/.gitignore @@ -0,0 +1,28 @@ +Makefile +Makefile.in +aclocal.m4 +autom4te.cache/ +config.guess +config.h +config.h.in +config.log +config.status +config.sub +configure +depcomp +install-sh +libsrc/Makefile +libsrc/Makefile.in +libtool +ltmain.sh +missing +src/Makefile +src/Makefile.in +stamp-h1 +libsrc/libusbip.la +libsrc/libusbip_la-names.lo +libsrc/libusbip_la-usbip_common.lo +libsrc/libusbip_la-usbip_host_driver.lo +libsrc/libusbip_la-vhci_driver.lo +src/usbip +src/usbipd diff --git a/tools/usb/usbip/AUTHORS b/tools/usb/usbip/AUTHORS new file mode 100644 index 0000000..a27ea8d --- /dev/null +++ b/tools/usb/usbip/AUTHORS @@ -0,0 +1,3 @@ +Takahiro Hirofuchi +Robert Leibl +matt mooney <mfm@muteddisk.com> diff --git a/tools/usb/usbip/COPYING b/tools/usb/usbip/COPYING new file mode 100644 index 0000000..c5611e4 --- /dev/null +++ b/tools/usb/usbip/COPYING @@ -0,0 +1,340 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc. + 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +License is intended to guarantee your freedom to share and change free +software--to make sure the software is free for all its users. This +General Public License applies to most of the Free Software +Foundation's software and to any other program whose authors commit to +using it. (Some other Free Software Foundation software is covered by +the GNU Library General Public License instead.) You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +this service if you wish), that you receive source code or can get it +if you want it, that you can change the software or use pieces of it +in new free programs; and that you know you can do these things. + + To protect your rights, we need to make restrictions that forbid +anyone to deny you these rights or to ask you to surrender the rights. +These restrictions translate to certain responsibilities for you if you +distribute copies of the software, or if you modify it. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must give the recipients all the rights that +you have. You must make sure that they, too, receive or can get the +source code. And you must show them these terms so they know their +rights. + + We protect your rights with two steps: (1) copyright the software, and +(2) offer you this license which gives you legal permission to copy, +distribute and/or modify the software. + + Also, for each author's protection and ours, we want to make certain +that everyone understands that there is no warranty for this free +software. If the software is modified by someone else and passed on, we +want its recipients to know that what they have is not the original, so +that any problems introduced by others will not reflect on the original +authors' reputations. + + Finally, any free program is threatened constantly by software +patents. We wish to avoid the danger that redistributors of a free +program will individually obtain patent licenses, in effect making the +program proprietary. To prevent this, we have made it clear that any +patent must be licensed for everyone's free use or not licensed at all. + + The precise terms and conditions for copying, distribution and +modification follow. + + GNU GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License applies to any program or other work which contains +a notice placed by the copyright holder saying it may be distributed +under the terms of this General Public License. The "Program", below, +refers to any such program or work, and a "work based on the Program" +means either the Program or any derivative work under copyright law: +that is to say, a work containing the Program or a portion of it, +either verbatim or with modifications and/or translated into another +language. (Hereinafter, translation is included without limitation in +the term "modification".) Each licensee is addressed as "you". + +Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running the Program is not restricted, and the output from the Program +is covered only if its contents constitute a work based on the +Program (independent of having been made by running the Program). +Whether that is true depends on what the Program does. + + 1. You may copy and distribute verbatim copies of the Program's +source code as you receive it, in any medium, provided that you +conspicuously and appropriately publish on each copy an appropriate +copyright notice and disclaimer of warranty; keep intact all the +notices that refer to this License and to the absence of any warranty; +and give any other recipients of the Program a copy of this License +along with the Program. + +You may charge a fee for the physical act of transferring a copy, and +you may at your option offer warranty protection in exchange for a fee. + + 2. You may modify your copy or copies of the Program or any portion +of it, thus forming a work based on the Program, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) You must cause the modified files to carry prominent notices + stating that you changed the files and the date of any change. + + b) You must cause any work that you distribute or publish, that in + whole or in part contains or is derived from the Program or any + part thereof, to be licensed as a whole at no charge to all third + parties under the terms of this License. + + c) If the modified program normally reads commands interactively + when run, you must cause it, when started running for such + interactive use in the most ordinary way, to print or display an + announcement including an appropriate copyright notice and a + notice that there is no warranty (or else, saying that you provide + a warranty) and that users may redistribute the program under + these conditions, and telling the user how to view a copy of this + License. (Exception: if the Program itself is interactive but + does not normally print such an announcement, your work based on + the Program is not required to print an announcement.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Program, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Program, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Program. + +In addition, mere aggregation of another work not based on the Program +with the Program (or with a work based on the Program) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may copy and distribute the Program (or a work based on it, +under Section 2) in object code or executable form under the terms of +Sections 1 and 2 above provided that you also do one of the following: + + a) Accompany it with the complete corresponding machine-readable + source code, which must be distributed under the terms of Sections + 1 and 2 above on a medium customarily used for software interchange; or, + + b) Accompany it with a written offer, valid for at least three + years, to give any third party, for a charge no more than your + cost of physically performing source distribution, a complete + machine-readable copy of the corresponding source code, to be + distributed under the terms of Sections 1 and 2 above on a medium + customarily used for software interchange; or, + + c) Accompany it with the information you received as to the offer + to distribute corresponding source code. (This alternative is + allowed only for noncommercial distribution and only if you + received the program in object code or executable form with such + an offer, in accord with Subsection b above.) + +The source code for a work means the preferred form of the work for +making modifications to it. For an executable work, complete source +code means all the source code for all modules it contains, plus any +associated interface definition files, plus the scripts used to +control compilation and installation of the executable. However, as a +special exception, the source code distributed need not include +anything that is normally distributed (in either source or binary +form) with the major components (compiler, kernel, and so on) of the +operating system on which the executable runs, unless that component +itself accompanies the executable. + +If distribution of executable or object code is made by offering +access to copy from a designated place, then offering equivalent +access to copy the source code from the same place counts as +distribution of the source code, even though third parties are not +compelled to copy the source along with the object code. + + 4. You may not copy, modify, sublicense, or distribute the Program +except as expressly provided under this License. Any attempt +otherwise to copy, modify, sublicense or distribute the Program is +void, and will automatically terminate your rights under this License. +However, parties who have received copies, or rights, from you under +this License will not have their licenses terminated so long as such +parties remain in full compliance. + + 5. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Program or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Program (or any work based on the +Program), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Program or works based on it. + + 6. Each time you redistribute the Program (or any work based on the +Program), the recipient automatically receives a license from the +original licensor to copy, distribute or modify the Program subject to +these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties to +this License. + + 7. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Program at all. For example, if a patent +license would not permit royalty-free redistribution of the Program by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Program. + +If any portion of this section is held invalid or unenforceable under +any particular circumstance, the balance of the section is intended to +apply and the section as a whole is intended to apply in other +circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system, which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 8. If the distribution and/or use of the Program is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Program under this License +may add an explicit geographical distribution limitation excluding +those countries, so that distribution is permitted only in or among +countries not thus excluded. In such case, this License incorporates +the limitation as if written in the body of this License. + + 9. The Free Software Foundation may publish revised and/or new versions +of the General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + +Each version is given a distinguishing version number. If the Program +specifies a version number of this License which applies to it and "any +later version", you have the option of following the terms and conditions +either of that version or of any later version published by the Free +Software Foundation. If the Program does not specify a version number of +this License, you may choose any version ever published by the Free Software +Foundation. + + 10. If you wish to incorporate parts of the Program into other free +programs whose distribution conditions are different, write to the author +to ask for permission. For software which is copyrighted by the Free +Software Foundation, write to the Free Software Foundation; we sometimes +make exceptions for this. Our decision will be guided by the two goals +of preserving the free status of all derivatives of our free software and +of promoting the sharing and reuse of software generally. + + NO WARRANTY + + 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY +FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN +OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES +PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED +OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS +TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE +PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, +REPAIR OR CORRECTION. + + 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR +REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, +INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING +OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED +TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY +YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER +PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE +POSSIBILITY OF SUCH DAMAGES. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +convey the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + <one line to give the program's name and a brief idea of what it does.> + Copyright (C) <year> <name of author> + + 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, write to the Free Software + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + + +Also add information on how to contact you by electronic and paper mail. + +If the program is interactive, make it output a short notice like this +when it starts in an interactive mode: + + Gnomovision version 69, Copyright (C) year name of author + Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, the commands you use may +be called something other than `show w' and `show c'; they could even be +mouse-clicks or menu items--whatever suits your program. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the program, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the program + `Gnomovision' (which makes passes at compilers) written by James Hacker. + + <signature of Ty Coon>, 1 April 1989 + Ty Coon, President of Vice + +This General Public License does not permit incorporating your program into +proprietary programs. If your program is a subroutine library, you may +consider it more useful to permit linking proprietary applications with the +library. If this is what you want to do, use the GNU Library General +Public License instead of this License. diff --git a/tools/usb/usbip/INSTALL b/tools/usb/usbip/INSTALL new file mode 100644 index 0000000..d3c5b40 --- /dev/null +++ b/tools/usb/usbip/INSTALL @@ -0,0 +1,237 @@ +Installation Instructions +************************* + +Copyright (C) 1994, 1995, 1996, 1999, 2000, 2001, 2002, 2004, 2005, +2006, 2007 Free Software Foundation, Inc. + +This file is free documentation; the Free Software Foundation gives +unlimited permission to copy, distribute and modify it. + +Basic Installation +================== + +Briefly, the shell commands `./configure; make; make install' should +configure, build, and install this package. The following +more-detailed instructions are generic; see the `README' file for +instructions specific to this package. + + The `configure' shell script attempts to guess correct values for +various system-dependent variables used during compilation. It uses +those values to create a `Makefile' in each directory of the package. +It may also create one or more `.h' files containing system-dependent +definitions. Finally, it creates a shell script `config.status' that +you can run in the future to recreate the current configuration, and a +file `config.log' containing compiler output (useful mainly for +debugging `configure'). + + It can also use an optional file (typically called `config.cache' +and enabled with `--cache-file=config.cache' or simply `-C') that saves +the results of its tests to speed up reconfiguring. Caching is +disabled by default to prevent problems with accidental use of stale +cache files. + + If you need to do unusual things to compile the package, please try +to figure out how `configure' could check whether to do them, and mail +diffs or instructions to the address given in the `README' so they can +be considered for the next release. If you are using the cache, and at +some point `config.cache' contains results you don't want to keep, you +may remove or edit it. + + The file `configure.ac' (or `configure.in') is used to create +`configure' by a program called `autoconf'. You need `configure.ac' if +you want to change it or regenerate `configure' using a newer version +of `autoconf'. + +The simplest way to compile this package is: + + 1. `cd' to the directory containing the package's source code and type + `./configure' to configure the package for your system. + + Running `configure' might take a while. While running, it prints + some messages telling which features it is checking for. + + 2. Type `make' to compile the package. + + 3. Optionally, type `make check' to run any self-tests that come with + the package. + + 4. Type `make install' to install the programs and any data files and + documentation. + + 5. You can remove the program binaries and object files from the + source code directory by typing `make clean'. To also remove the + files that `configure' created (so you can compile the package for + a different kind of computer), type `make distclean'. There is + also a `make maintainer-clean' target, but that is intended mainly + for the package's developers. If you use it, you may have to get + all sorts of other programs in order to regenerate files that came + with the distribution. + + 6. Often, you can also type `make uninstall' to remove the installed + files again. + +Compilers and Options +===================== + +Some systems require unusual options for compilation or linking that the +`configure' script does not know about. Run `./configure --help' for +details on some of the pertinent environment variables. + + You can give `configure' initial values for configuration parameters +by setting variables in the command line or in the environment. Here +is an example: + + ./configure CC=c99 CFLAGS=-g LIBS=-lposix + + *Note Defining Variables::, for more details. + +Compiling For Multiple Architectures +==================================== + +You can compile the package for more than one kind of computer at the +same time, by placing the object files for each architecture in their +own directory. To do this, you can use GNU `make'. `cd' to the +directory where you want the object files and executables to go and run +the `configure' script. `configure' automatically checks for the +source code in the directory that `configure' is in and in `..'. + + With a non-GNU `make', it is safer to compile the package for one +architecture at a time in the source code directory. After you have +installed the package for one architecture, use `make distclean' before +reconfiguring for another architecture. + +Installation Names +================== + +By default, `make install' installs the package's commands under +`/usr/local/bin', include files under `/usr/local/include', etc. You +can specify an installation prefix other than `/usr/local' by giving +`configure' the option `--prefix=PREFIX'. + + You can specify separate installation prefixes for +architecture-specific files and architecture-independent files. If you +pass the option `--exec-prefix=PREFIX' to `configure', the package uses +PREFIX as the prefix for installing programs and libraries. +Documentation and other data files still use the regular prefix. + + In addition, if you use an unusual directory layout you can give +options like `--bindir=DIR' to specify different values for particular +kinds of files. Run `configure --help' for a list of the directories +you can set and what kinds of files go in them. + + If the package supports it, you can cause programs to be installed +with an extra prefix or suffix on their names by giving `configure' the +option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'. + +Optional Features +================= + +Some packages pay attention to `--enable-FEATURE' options to +`configure', where FEATURE indicates an optional part of the package. +They may also pay attention to `--with-PACKAGE' options, where PACKAGE +is something like `gnu-as' or `x' (for the X Window System). The +`README' should mention any `--enable-' and `--with-' options that the +package recognizes. + + For packages that use the X Window System, `configure' can usually +find the X include and library files automatically, but if it doesn't, +you can use the `configure' options `--x-includes=DIR' and +`--x-libraries=DIR' to specify their locations. + +Specifying the System Type +========================== + +There may be some features `configure' cannot figure out automatically, +but needs to determine by the type of machine the package will run on. +Usually, assuming the package is built to be run on the _same_ +architectures, `configure' can figure that out, but if it prints a +message saying it cannot guess the machine type, give it the +`--build=TYPE' option. TYPE can either be a short name for the system +type, such as `sun4', or a canonical name which has the form: + + CPU-COMPANY-SYSTEM + +where SYSTEM can have one of these forms: + + OS KERNEL-OS + + See the file `config.sub' for the possible values of each field. If +`config.sub' isn't included in this package, then this package doesn't +need to know the machine type. + + If you are _building_ compiler tools for cross-compiling, you should +use the option `--target=TYPE' to select the type of system they will +produce code for. + + If you want to _use_ a cross compiler, that generates code for a +platform different from the build platform, you should specify the +"host" platform (i.e., that on which the generated programs will +eventually be run) with `--host=TYPE'. + +Sharing Defaults +================ + +If you want to set default values for `configure' scripts to share, you +can create a site shell script called `config.site' that gives default +values for variables like `CC', `cache_file', and `prefix'. +`configure' looks for `PREFIX/share/config.site' if it exists, then +`PREFIX/etc/config.site' if it exists. Or, you can set the +`CONFIG_SITE' environment variable to the location of the site script. +A warning: not all `configure' scripts look for a site script. + +Defining Variables +================== + +Variables not defined in a site shell script can be set in the +environment passed to `configure'. However, some packages may run +configure again during the build, and the customized values of these +variables may be lost. In order to avoid this problem, you should set +them in the `configure' command line, using `VAR=value'. For example: + + ./configure CC=/usr/local2/bin/gcc + +causes the specified `gcc' to be used as the C compiler (unless it is +overridden in the site shell script). + +Unfortunately, this technique does not work for `CONFIG_SHELL' due to +an Autoconf bug. Until the bug is fixed you can use this workaround: + + CONFIG_SHELL=/bin/bash /bin/bash ./configure CONFIG_SHELL=/bin/bash + +`configure' Invocation +====================== + +`configure' recognizes the following options to control how it operates. + +`--help' +`-h' + Print a summary of the options to `configure', and exit. + +`--version' +`-V' + Print the version of Autoconf used to generate the `configure' + script, and exit. + +`--cache-file=FILE' + Enable the cache: use and save the results of the tests in FILE, + traditionally `config.cache'. FILE defaults to `/dev/null' to + disable caching. + +`--config-cache' +`-C' + Alias for `--cache-file=config.cache'. + +`--quiet' +`--silent' +`-q' + Do not print messages saying which checks are being made. To + suppress all normal output, redirect it to `/dev/null' (any error + messages will still be shown). + +`--srcdir=DIR' + Look for the package's source code in directory DIR. Usually + `configure' can determine that directory automatically. + +`configure' also accepts some other, not widely useful, options. Run +`configure --help' for more details. + diff --git a/tools/usb/usbip/Makefile.am b/tools/usb/usbip/Makefile.am new file mode 100644 index 0000000..66f8bf0 --- /dev/null +++ b/tools/usb/usbip/Makefile.am @@ -0,0 +1,6 @@ +SUBDIRS := libsrc src +includedir = @includedir@/usbip +include_HEADERS := $(addprefix libsrc/, \ + usbip_common.h vhci_driver.h usbip_host_driver.h) + +dist_man_MANS := $(addprefix doc/, usbip.8 usbipd.8) diff --git a/tools/usb/usbip/README b/tools/usb/usbip/README new file mode 100644 index 0000000..831f49f --- /dev/null +++ b/tools/usb/usbip/README @@ -0,0 +1,202 @@ +# +# README for usbip-utils +# +# Copyright (C) 2011 matt mooney <mfm@muteddisk.com> +# 2005-2008 Takahiro Hirofuchi + + +[Requirements] + - USB/IP device drivers + Found in the staging directory of the Linux kernel. + + - libudev >= 2.0 + libudev library + + - libwrap0-dev + tcp wrapper library + + - gcc >= 4.0 + + - libtool, automake >= 1.9, autoconf >= 2.5.0, pkg-config + +[Optional] + - hwdata + Contains USB device identification data. + + +[Install] + 0. Generate configuration scripts. + $ ./autogen.sh + + 1. Compile & install the userspace utilities. + $ ./configure [--with-tcp-wrappers=no] [--with-usbids-dir=<dir>] + $ make install + + 2. Compile & install USB/IP drivers. + + +[Usage] + server:# (Physically attach your USB device.) + + server:# insmod usbip-core.ko + server:# insmod usbip-host.ko + + server:# usbipd -D + - Start usbip daemon. + + server:# usbip list -l + - List driver assignments for USB devices. + + server:# usbip bind --busid 1-2 + - Bind usbip-host.ko to the device with busid 1-2. + - The USB device 1-2 is now exportable to other hosts! + - Use `usbip unbind --busid 1-2' to stop exporting the device. + + client:# insmod usbip-core.ko + client:# insmod vhci-hcd.ko + + client:# usbip list --remote <host> + - List exported USB devices on the <host>. + + client:# usbip attach --remote <host> --busid 1-2 + - Connect the remote USB device. + + client:# usbip port + - Show virtual port status. + + client:# usbip detach --port <port> + - Detach the USB device. + + +[Example] +--------------------------- + SERVER SIDE +--------------------------- +Physically attach your USB devices to this host. + + trois:# insmod path/to/usbip-core.ko + trois:# insmod path/to/usbip-host.ko + trois:# usbipd -D + +In another terminal, let's look up what USB devices are physically +attached to this host. + + trois:# usbip list -l + Local USB devices + ================= + - busid 1-1 (05a9:a511) + 1-1:1.0 -> ov511 + + - busid 3-2 (0711:0902) + 3-2:1.0 -> none + + - busid 3-3.1 (08bb:2702) + 3-3.1:1.0 -> snd-usb-audio + 3-3.1:1.1 -> snd-usb-audio + + - busid 3-3.2 (04bb:0206) + 3-3.2:1.0 -> usb-storage + + - busid 3-3 (0409:0058) + 3-3:1.0 -> hub + + - busid 4-1 (046d:08b2) + 4-1:1.0 -> none + 4-1:1.1 -> none + 4-1:1.2 -> none + + - busid 5-2 (058f:9254) + 5-2:1.0 -> hub + +A USB storage device of busid 3-3.2 is now bound to the usb-storage +driver. To export this device, we first mark the device as +"exportable"; the device is bound to the usbip-host driver. Please +remember you can not export a USB hub. + +Mark the device of busid 3-3.2 as exportable: + + trois:# usbip --debug bind --busid 3-3.2 + ... + usbip debug: usbip_bind.c:162:[unbind_other] 3-3.2:1.0 -> usb-storage + ... + bind device on busid 3-3.2: complete + + trois:# usbip list -l + Local USB devices + ================= + ... + + - busid 3-3.2 (04bb:0206) + 3-3.2:1.0 -> usbip-host + ... + +--------------------------- + CLIENT SIDE +--------------------------- +First, let's list available remote devices that are marked as +exportable on the host. + + deux:# insmod path/to/usbip-core.ko + deux:# insmod path/to/vhci-hcd.ko + + deux:# usbip list --remote 10.0.0.3 + Exportable USB devices + ====================== + - 10.0.0.3 + 1-1: Prolific Technology, Inc. : unknown product (067b:3507) + : /sys/devices/pci0000:00/0000:00:1f.2/usb1/1-1 + : (Defined at Interface level) / unknown subclass / unknown protocol (00/00/00) + : 0 - Mass Storage / SCSI / Bulk (Zip) (08/06/50) + + 1-2.2.1: Apple Computer, Inc. : unknown product (05ac:0203) + : /sys/devices/pci0000:00/0000:00:1f.2/usb1/1-2/1-2.2/1-2.2.1 + : (Defined at Interface level) / unknown subclass / unknown protocol (00/00/00) + : 0 - Human Interface Devices / Boot Interface Subclass / Keyboard (03/01/01) + + 1-2.2.3: OmniVision Technologies, Inc. : OV511+ WebCam (05a9:a511) + : /sys/devices/pci0000:00/0000:00:1f.2/usb1/1-2/1-2.2/1-2.2.3 + : (Defined at Interface level) / unknown subclass / unknown protocol (00/00/00) + : 0 - Vendor Specific Class / unknown subclass / unknown protocol (ff/00/00) + + 3-1: Logitech, Inc. : QuickCam Pro 4000 (046d:08b2) + : /sys/devices/pci0000:00/0000:00:1e.0/0000:02:0a.0/usb3/3-1 + : (Defined at Interface level) / unknown subclass / unknown protocol (00/00/00) + : 0 - Data / unknown subclass / unknown protocol (0a/ff/00) + : 1 - Audio / Control Device / unknown protocol (01/01/00) + : 2 - Audio / Streaming / unknown protocol (01/02/00) + +Attach a remote USB device: + + deux:# usbip attach --remote 10.0.0.3 --busid 1-1 + port 0 attached + +Show the devices attached to this client: + + deux:# usbip port + Port 00: <Port in Use> at Full Speed(12Mbps) + Prolific Technology, Inc. : unknown product (067b:3507) + 6-1 -> usbip://10.0.0.3:3240/1-1 (remote bus/dev 001/004) + 6-1:1.0 used by usb-storage + /sys/class/scsi_device/0:0:0:0/device + /sys/class/scsi_host/host0/device + /sys/block/sda/device + +Detach the imported device: + + deux:# usbip detach --port 0 + port 0 detached + + +[Checklist] + - See 'Debug Tips' on the project wiki. + - http://usbip.wiki.sourceforge.net/how-to-debug-usbip + - usbip-host.ko must be bound to the target device. + - See /proc/bus/usb/devices and find "Driver=..." lines of the device. + - Shutdown firewall. + - usbip now uses TCP port 3240. + - Disable SELinux. + - Check the kernel and daemon messages. + + +[Contact] + Mailing List: linux-usb@vger.kernel.org diff --git a/tools/usb/usbip/autogen.sh b/tools/usb/usbip/autogen.sh new file mode 100755 index 0000000..e1112d3 --- /dev/null +++ b/tools/usb/usbip/autogen.sh @@ -0,0 +1,9 @@ +#!/bin/sh -x + +#aclocal +#autoheader +#libtoolize --copy --force +#automake-1.9 -acf +#autoconf + +autoreconf -i -f -v diff --git a/tools/usb/usbip/cleanup.sh b/tools/usb/usbip/cleanup.sh new file mode 100755 index 0000000..955c3cc --- /dev/null +++ b/tools/usb/usbip/cleanup.sh @@ -0,0 +1,12 @@ +#!/bin/sh + +if [ -r Makefile ]; then + make distclean +fi + +FILES="aclocal.m4 autom4te.cache compile config.guess config.h.in config.log \ + config.status config.sub configure cscope.out depcomp install-sh \ + libsrc/Makefile libsrc/Makefile.in libtool ltmain.sh Makefile \ + Makefile.in missing src/Makefile src/Makefile.in" + +rm -vRf $FILES diff --git a/tools/usb/usbip/configure.ac b/tools/usb/usbip/configure.ac new file mode 100644 index 0000000..607d05c --- /dev/null +++ b/tools/usb/usbip/configure.ac @@ -0,0 +1,111 @@ +dnl Process this file with autoconf to produce a configure script. + +AC_PREREQ(2.59) +AC_INIT([usbip-utils], [2.0], [linux-usb@vger.kernel.org]) +AC_DEFINE([USBIP_VERSION], [0x00000111], [binary-coded decimal version number]) + +CURRENT=0 +REVISION=1 +AGE=0 +AC_SUBST([LIBUSBIP_VERSION], [$CURRENT:$REVISION:$AGE], [library version]) + +AC_CONFIG_SRCDIR([src/usbipd.c]) +AC_CONFIG_HEADERS([config.h]) + +AM_INIT_AUTOMAKE([foreign]) +LT_INIT + +# Silent build for automake >= 1.11 +m4_ifdef([AM_SILENT_RULES], [AM_SILENT_RULES([yes])]) + +AC_SUBST([EXTRA_CFLAGS], ["-Wall -Werror -Wextra -std=gnu99"]) + +# Checks for programs. +AC_PROG_CC +AC_PROG_INSTALL +AC_PROG_MAKE_SET + +# Checks for header files. +AC_HEADER_DIRENT +AC_HEADER_STDC +AC_CHECK_HEADERS([arpa/inet.h fcntl.h netdb.h netinet/in.h stdint.h stdlib.h dnl + string.h sys/socket.h syslog.h unistd.h]) + +# Checks for typedefs, structures, and compiler characteristics. +AC_TYPE_INT32_T +AC_TYPE_SIZE_T +AC_TYPE_SSIZE_T +AC_TYPE_UINT16_T +AC_TYPE_UINT32_T +AC_TYPE_UINT8_T + +# Checks for library functions. +AC_FUNC_REALLOC +AC_CHECK_FUNCS([memset mkdir regcomp socket strchr strerror strstr dnl + strtoul]) + +AC_CHECK_HEADER([libudev.h], + [AC_CHECK_LIB([udev], [udev_new], + [LIBS="$LIBS -ludev"], + [AC_MSG_ERROR([Missing udev library!])])], + [AC_MSG_ERROR([Missing /usr/include/libudev.h])]) + +# Checks for libwrap library. +AC_MSG_CHECKING([whether to use the libwrap (TCP wrappers) library]) +AC_ARG_WITH([tcp-wrappers], + [AS_HELP_STRING([--with-tcp-wrappers], + [use the libwrap (TCP wrappers) library])], + dnl [ACTION-IF-GIVEN] + [if test "$withval" = "yes"; then + AC_MSG_RESULT([yes]) + AC_MSG_CHECKING([for hosts_access in -lwrap]) + saved_LIBS="$LIBS" + LIBS="-lwrap $saved_LIBS" + AC_TRY_LINK( + [int hosts_access(); int allow_severity, deny_severity;], + [hosts_access()], + [AC_MSG_RESULT([yes]); + AC_DEFINE([HAVE_LIBWRAP], [1], + [use tcp wrapper]) wrap_LIB="-lwrap"], + [AC_MSG_RESULT([not found]); exit 1]) + else + AC_MSG_RESULT([no]); + fi], + dnl [ACTION-IF-NOT-GIVEN] + [AC_MSG_RESULT([(default)]) + AC_MSG_CHECKING([for hosts_access in -lwrap]) + saved_LIBS="$LIBS" + LIBS="-lwrap $saved_LIBS" + AC_TRY_LINK( + [int hosts_access(); int allow_severity, deny_severity;], + [hosts_access()], + [AC_MSG_RESULT([yes]); + AC_DEFINE([HAVE_LIBWRAP], [1], [use tcp wrapper])], + [AC_MSG_RESULT([no]); LIBS="$saved_LIBS"])]) + +# Sets directory containing usb.ids. +AC_ARG_WITH([usbids-dir], + [AS_HELP_STRING([--with-usbids-dir=DIR], + [where usb.ids is found (default /usr/share/hwdata/)])], + [USBIDS_DIR=$withval], [USBIDS_DIR="/usr/share/hwdata/"]) +AC_SUBST([USBIDS_DIR]) + +# use _FORTIFY_SOURCE +AC_MSG_CHECKING([whether to use fortify]) +AC_ARG_WITH([fortify], + [AS_HELP_STRING([--with-fortify], + [use _FORTIFY_SROUCE option when compiling)])], + dnl [ACTION-IF-GIVEN] + [if test "$withval" = "yes"; then + AC_MSG_RESULT([yes]) + CFLAGS="$CFLAGS -D_FORTIFY_SOURCE -O" + else + AC_MSG_RESULT([no]) + CFLAGS="$CFLAGS -U_FORTIFY_SOURCE" + fi + ], + dnl [ACTION-IF-NOT-GIVEN] + [AC_MSG_RESULT([default])]) + +AC_CONFIG_FILES([Makefile libsrc/Makefile src/Makefile]) +AC_OUTPUT diff --git a/tools/usb/usbip/doc/usbip.8 b/tools/usb/usbip/doc/usbip.8 new file mode 100644 index 0000000..a6097be --- /dev/null +++ b/tools/usb/usbip/doc/usbip.8 @@ -0,0 +1,95 @@ +.TH USBIP "8" "February 2009" "usbip" "System Administration Utilities" +.SH NAME +usbip \- manage USB/IP devices +.SH SYNOPSIS +.B usbip +[\fIoptions\fR] <\fIcommand\fR> <\fIargs\fR> + +.SH DESCRIPTION +On a USB/IP server, devices can be listed, bound, and unbound using +this program. On a USB/IP client, devices exported by USB/IP servers +can be listed, attached and detached. + +.SH OPTIONS +.HP +\fB\-\-debug\fR +.IP +Print debugging information. +.PP + +.HP +\fB\-\-log\fR +.IP +Log to syslog. +.PP + +.HP +\fB\-\-tcp-port PORT\fR +.IP +Connect to PORT on remote host (used for attach and list --remote). +.PP + +.SH COMMANDS +.HP +\fBversion\fR +.IP +Show version and exit. +.PP + +.HP +\fBhelp\fR [\fIcommand\fR] +.IP +Print the program help message, or help on a specific command, and +then exit. +.PP + +.HP +\fBattach\fR \-\-remote=<\fIhost\fR> \-\-busid=<\fIbus_id\fR> +.IP +Attach a remote USB device. +.PP + +.HP +\fBdetach\fR \-\-port=<\fIport\fR> +.IP +Detach an imported USB device. +.PP + +.HP +\fBbind\fR \-\-busid=<\fIbusid\fR> +.IP +Make a device exportable. +.PP + +.HP +\fBunbind\fR \-\-busid=<\fIbusid\fR> +.IP +Stop exporting a device so it can be used by a local driver. +.PP + +.HP +\fBlist\fR \-\-remote=<\fIhost\fR> +.IP +List USB devices exported by a remote host. +.PP + +.HP +\fBlist\fR \-\-local +.IP +List local USB devices. +.PP + + +.SH EXAMPLES + + client:# usbip list --remote=server + - List exportable usb devices on the server. + + client:# usbip attach --remote=server --busid=1-2 + - Connect the remote USB device. + + client:# usbip detach --port=0 + - Detach the usb device. + +.SH "SEE ALSO" +\fBusbipd\fP\fB(8)\fB\fP diff --git a/tools/usb/usbip/doc/usbipd.8 b/tools/usb/usbip/doc/usbipd.8 new file mode 100644 index 0000000..ac4635d --- /dev/null +++ b/tools/usb/usbip/doc/usbipd.8 @@ -0,0 +1,91 @@ +.TH USBIP "8" "February 2009" "usbip" "System Administration Utilities" +.SH NAME +usbipd \- USB/IP server daemon +.SH SYNOPSIS +.B usbipd +[\fIoptions\fR] + +.SH DESCRIPTION +.B usbipd +provides USB/IP clients access to exported USB devices. + +Devices have to explicitly be exported using +.B usbip bind +before usbipd makes them available to other hosts. + +The daemon accepts connections from USB/IP clients +on TCP port 3240 by default. + +.SH OPTIONS +.HP +\fB\-4\fR, \fB\-\-ipv4\fR +.IP +Bind to IPv4. Default is both. +.PP + +.HP +\fB\-6\fR, \fB\-\-ipv6\fR +.IP +Bind to IPv6. Default is both. +.PP + +.HP +\fB\-D\fR, \fB\-\-daemon\fR +.IP +Run as a daemon process. +.PP + +.HP +\fB\-d\fR, \fB\-\-debug\fR +.IP +Print debugging information. +.PP + +.HP +\fB\-PFILE\fR, \fB\-\-pid FILE\fR +.IP +Write process id to FILE. +.br +If no FILE specified, use /var/run/usbipd.pid +.PP + +\fB\-tPORT\fR, \fB\-\-tcp\-port PORT\fR +.IP +Listen on TCP/IP port PORT. +.PP + +\fB\-h\fR, \fB\-\-help\fR +.IP +Print the program help message and exit. +.PP + +.HP +\fB\-v\fR, \fB\-\-version\fR +.IP +Show version. +.PP + +.SH LIMITATIONS + +.B usbipd +offers no authentication or authorization for USB/IP. Any +USB/IP client can connect and use exported devices. + +.SH EXAMPLES + + server:# modprobe usbip + + server:# usbipd -D + - Start usbip daemon. + + server:# usbip list --local + - List driver assignments for usb devices. + + server:# usbip bind --busid=1-2 + - Bind usbip-host.ko to the device of busid 1-2. + - A usb device 1-2 is now exportable to other hosts! + - Use 'usbip unbind --busid=1-2' when you want to shutdown exporting and use the device locally. + +.SH "SEE ALSO" +\fBusbip\fP\fB(8)\fB\fP + diff --git a/tools/usb/usbip/libsrc/Makefile.am b/tools/usb/usbip/libsrc/Makefile.am new file mode 100644 index 0000000..7c8f8a4 --- /dev/null +++ b/tools/usb/usbip/libsrc/Makefile.am @@ -0,0 +1,8 @@ +libusbip_la_CPPFLAGS = -DUSBIDS_FILE='"@USBIDS_DIR@/usb.ids"' +libusbip_la_CFLAGS = @EXTRA_CFLAGS@ +libusbip_la_LDFLAGS = -version-info @LIBUSBIP_VERSION@ + +lib_LTLIBRARIES := libusbip.la +libusbip_la_SOURCES := names.c names.h usbip_host_driver.c usbip_host_driver.h \ + usbip_common.c usbip_common.h vhci_driver.c vhci_driver.h \ + sysfs_utils.c sysfs_utils.h diff --git a/tools/usb/usbip/libsrc/list.h b/tools/usb/usbip/libsrc/list.h new file mode 100644 index 0000000..5eaaa78 --- /dev/null +++ b/tools/usb/usbip/libsrc/list.h @@ -0,0 +1,136 @@ +#ifndef _LIST_H +#define _LIST_H + +/* Stripped down implementation of linked list taken + * from the Linux Kernel. + */ + +/* + * Simple doubly linked list implementation. + * + * Some of the internal functions ("__xxx") are useful when + * manipulating whole lists rather than single entries, as + * sometimes we already know the next/prev entries and we can + * generate better code by using them directly rather than + * using the generic single-entry routines. + */ + +struct list_head { + struct list_head *next, *prev; +}; + +#define LIST_HEAD_INIT(name) { &(name), &(name) } + +#define LIST_HEAD(name) \ + struct list_head name = LIST_HEAD_INIT(name) + +static inline void INIT_LIST_HEAD(struct list_head *list) +{ + list->next = list; + list->prev = list; +} + +/* + * Insert a new entry between two known consecutive entries. + * + * This is only for internal list manipulation where we know + * the prev/next entries already! + */ +static inline void __list_add(struct list_head *new, + struct list_head *prev, + struct list_head *next) +{ + next->prev = new; + new->next = next; + new->prev = prev; + prev->next = new; +} + +/** + * list_add - add a new entry + * @new: new entry to be added + * @head: list head to add it after + * + * Insert a new entry after the specified head. + * This is good for implementing stacks. + */ +static inline void list_add(struct list_head *new, struct list_head *head) +{ + __list_add(new, head, head->next); +} + +/* + * Delete a list entry by making the prev/next entries + * point to each other. + * + * This is only for internal list manipulation where we know + * the prev/next entries already! + */ +static inline void __list_del(struct list_head * prev, struct list_head * next) +{ + next->prev = prev; + prev->next = next; +} + +#define POISON_POINTER_DELTA 0 +#define LIST_POISON1 ((void *) 0x00100100 + POISON_POINTER_DELTA) +#define LIST_POISON2 ((void *) 0x00200200 + POISON_POINTER_DELTA) + +/** + * list_del - deletes entry from list. + * @entry: the element to delete from the list. + * Note: list_empty() on entry does not return true after this, the entry is + * in an undefined state. + */ +static inline void __list_del_entry(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); +} + +static inline void list_del(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + entry->next = LIST_POISON1; + entry->prev = LIST_POISON2; +} + +/** + * list_entry - get the struct for this entry + * @ptr: the &struct list_head pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + */ +#define list_entry(ptr, type, member) \ + container_of(ptr, type, member) +/** + * list_for_each - iterate over a list + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each(pos, head) \ + for (pos = (head)->next; pos != (head); pos = pos->next) + +/** + * list_for_each_safe - iterate over a list safe against removal of list entry + * @pos: the &struct list_head to use as a loop cursor. + * @n: another &struct list_head to use as temporary storage + * @head: the head for your list. + */ +#define list_for_each_safe(pos, n, head) \ + for (pos = (head)->next, n = pos->next; pos != (head); \ + pos = n, n = pos->next) + +#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) + +/** + * container_of - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + */ +#define container_of(ptr, type, member) ({ \ + const typeof( ((type *)0)->member ) *__mptr = (ptr); \ + (type *)( (char *)__mptr - offsetof(type,member) );}) + +#endif diff --git a/tools/usb/usbip/libsrc/names.c b/tools/usb/usbip/libsrc/names.c new file mode 100644 index 0000000..81ff852 --- /dev/null +++ b/tools/usb/usbip/libsrc/names.c @@ -0,0 +1,504 @@ +/* + * names.c -- USB name database manipulation routines + * + * Copyright (C) 1999, 2000 Thomas Sailer (sailer@ife.ee.ethz.ch) + * + * 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, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * + * + * + * + * Copyright (C) 2005 Takahiro Hirofuchi + * - names_deinit() is added. + * + */ + +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <dirent.h> +#include <string.h> +#include <errno.h> +#include <stdlib.h> +#include <unistd.h> +#include <stdio.h> +#include <ctype.h> + +#include "names.h" +#include "usbip_common.h" + +struct vendor { + struct vendor *next; + u_int16_t vendorid; + char name[1]; +}; + +struct product { + struct product *next; + u_int16_t vendorid, productid; + char name[1]; +}; + +struct class { + struct class *next; + u_int8_t classid; + char name[1]; +}; + +struct subclass { + struct subclass *next; + u_int8_t classid, subclassid; + char name[1]; +}; + +struct protocol { + struct protocol *next; + u_int8_t classid, subclassid, protocolid; + char name[1]; +}; + +struct genericstrtable { + struct genericstrtable *next; + unsigned int num; + char name[1]; +}; + + +#define HASH1 0x10 +#define HASH2 0x02 +#define HASHSZ 16 + +static unsigned int hashnum(unsigned int num) +{ + unsigned int mask1 = HASH1 << 27, mask2 = HASH2 << 27; + + for (; mask1 >= HASH1; mask1 >>= 1, mask2 >>= 1) + if (num & mask1) + num ^= mask2; + return num & (HASHSZ-1); +} + + +static struct vendor *vendors[HASHSZ] = { NULL, }; +static struct product *products[HASHSZ] = { NULL, }; +static struct class *classes[HASHSZ] = { NULL, }; +static struct subclass *subclasses[HASHSZ] = { NULL, }; +static struct protocol *protocols[HASHSZ] = { NULL, }; + +const char *names_vendor(u_int16_t vendorid) +{ + struct vendor *v; + + v = vendors[hashnum(vendorid)]; + for (; v; v = v->next) + if (v->vendorid == vendorid) + return v->name; + return NULL; +} + +const char *names_product(u_int16_t vendorid, u_int16_t productid) +{ + struct product *p; + + p = products[hashnum((vendorid << 16) | productid)]; + for (; p; p = p->next) + if (p->vendorid == vendorid && p->productid == productid) + return p->name; + return NULL; +} + +const char *names_class(u_int8_t classid) +{ + struct class *c; + + c = classes[hashnum(classid)]; + for (; c; c = c->next) + if (c->classid == classid) + return c->name; + return NULL; +} + +const char *names_subclass(u_int8_t classid, u_int8_t subclassid) +{ + struct subclass *s; + + s = subclasses[hashnum((classid << 8) | subclassid)]; + for (; s; s = s->next) + if (s->classid == classid && s->subclassid == subclassid) + return s->name; + return NULL; +} + +const char *names_protocol(u_int8_t classid, u_int8_t subclassid, + u_int8_t protocolid) +{ + struct protocol *p; + + p = protocols[hashnum((classid << 16) | (subclassid << 8) + | protocolid)]; + for (; p; p = p->next) + if (p->classid == classid && p->subclassid == subclassid && + p->protocolid == protocolid) + return p->name; + return NULL; +} + +/* add a cleanup function by takahiro */ +struct pool { + struct pool *next; + void *mem; +}; + +static struct pool *pool_head; + +static void *my_malloc(size_t size) +{ + struct pool *p; + + p = calloc(1, sizeof(struct pool)); + if (!p) + return NULL; + + p->mem = calloc(1, size); + if (!p->mem) { + free(p); + return NULL; + } + + p->next = pool_head; + pool_head = p; + + return p->mem; +} + +void names_free(void) +{ + struct pool *pool; + + if (!pool_head) + return; + + for (pool = pool_head; pool != NULL; ) { + struct pool *tmp; + + if (pool->mem) + free(pool->mem); + + tmp = pool; + pool = pool->next; + free(tmp); + } +} + +static int new_vendor(const char *name, u_int16_t vendorid) +{ + struct vendor *v; + unsigned int h = hashnum(vendorid); + + v = vendors[h]; + for (; v; v = v->next) + if (v->vendorid == vendorid) + return -1; + v = my_malloc(sizeof(struct vendor) + strlen(name)); + if (!v) + return -1; + strcpy(v->name, name); + v->vendorid = vendorid; + v->next = vendors[h]; + vendors[h] = v; + return 0; +} + +static int new_product(const char *name, u_int16_t vendorid, + u_int16_t productid) +{ + struct product *p; + unsigned int h = hashnum((vendorid << 16) | productid); + + p = products[h]; + for (; p; p = p->next) + if (p->vendorid == vendorid && p->productid == productid) + return -1; + p = my_malloc(sizeof(struct product) + strlen(name)); + if (!p) + return -1; + strcpy(p->name, name); + p->vendorid = vendorid; + p->productid = productid; + p->next = products[h]; + products[h] = p; + return 0; +} + +static int new_class(const char *name, u_int8_t classid) +{ + struct class *c; + unsigned int h = hashnum(classid); + + c = classes[h]; + for (; c; c = c->next) + if (c->classid == classid) + return -1; + c = my_malloc(sizeof(struct class) + strlen(name)); + if (!c) + return -1; + strcpy(c->name, name); + c->classid = classid; + c->next = classes[h]; + classes[h] = c; + return 0; +} + +static int new_subclass(const char *name, u_int8_t classid, u_int8_t subclassid) +{ + struct subclass *s; + unsigned int h = hashnum((classid << 8) | subclassid); + + s = subclasses[h]; + for (; s; s = s->next) + if (s->classid == classid && s->subclassid == subclassid) + return -1; + s = my_malloc(sizeof(struct subclass) + strlen(name)); + if (!s) + return -1; + strcpy(s->name, name); + s->classid = classid; + s->subclassid = subclassid; + s->next = subclasses[h]; + subclasses[h] = s; + return 0; +} + +static int new_protocol(const char *name, u_int8_t classid, u_int8_t subclassid, + u_int8_t protocolid) +{ + struct protocol *p; + unsigned int h = hashnum((classid << 16) | (subclassid << 8) + | protocolid); + + p = protocols[h]; + for (; p; p = p->next) + if (p->classid == classid && p->subclassid == subclassid + && p->protocolid == protocolid) + return -1; + p = my_malloc(sizeof(struct protocol) + strlen(name)); + if (!p) + return -1; + strcpy(p->name, name); + p->classid = classid; + p->subclassid = subclassid; + p->protocolid = protocolid; + p->next = protocols[h]; + protocols[h] = p; + return 0; +} + +static void parse(FILE *f) +{ + char buf[512], *cp; + unsigned int linectr = 0; + int lastvendor = -1; + int lastclass = -1; + int lastsubclass = -1; + int lasthut = -1; + int lastlang = -1; + unsigned int u; + + while (fgets(buf, sizeof(buf), f)) { + linectr++; + /* remove line ends */ + cp = strchr(buf, '\r'); + if (cp) + *cp = 0; + cp = strchr(buf, '\n'); + if (cp) + *cp = 0; + if (buf[0] == '#' || !buf[0]) + continue; + cp = buf; + if (buf[0] == 'P' && buf[1] == 'H' && buf[2] == 'Y' && + buf[3] == 'S' && buf[4] == 'D' && + buf[5] == 'E' && buf[6] == 'S' && /*isspace(buf[7])*/ + buf[7] == ' ') { + continue; + } + if (buf[0] == 'P' && buf[1] == 'H' && + buf[2] == 'Y' && /*isspace(buf[3])*/ buf[3] == ' ') { + continue; + } + if (buf[0] == 'B' && buf[1] == 'I' && buf[2] == 'A' && + buf[3] == 'S' && /*isspace(buf[4])*/ buf[4] == ' ') { + continue; + } + if (buf[0] == 'L' && /*isspace(buf[1])*/ buf[1] == ' ') { + lasthut = lastclass = lastvendor = lastsubclass = -1; + /* + * set 1 as pseudo-id to indicate that the parser is + * in a `L' section. + */ + lastlang = 1; + continue; + } + if (buf[0] == 'C' && /*isspace(buf[1])*/ buf[1] == ' ') { + /* class spec */ + cp = buf+2; + while (isspace(*cp)) + cp++; + if (!isxdigit(*cp)) { + err("Invalid class spec at line %u", linectr); + continue; + } + u = strtoul(cp, &cp, 16); + while (isspace(*cp)) + cp++; + if (!*cp) { + err("Invalid class spec at line %u", linectr); + continue; + } + if (new_class(cp, u)) + err("Duplicate class spec at line %u class %04x %s", + linectr, u, cp); + dbg("line %5u class %02x %s", linectr, u, cp); + lasthut = lastlang = lastvendor = lastsubclass = -1; + lastclass = u; + continue; + } + if (buf[0] == 'A' && buf[1] == 'T' && isspace(buf[2])) { + /* audio terminal type spec */ + continue; + } + if (buf[0] == 'H' && buf[1] == 'C' && buf[2] == 'C' + && isspace(buf[3])) { + /* HID Descriptor bCountryCode */ + continue; + } + if (isxdigit(*cp)) { + /* vendor */ + u = strtoul(cp, &cp, 16); + while (isspace(*cp)) + cp++; + if (!*cp) { + err("Invalid vendor spec at line %u", linectr); + continue; + } + if (new_vendor(cp, u)) + err("Duplicate vendor spec at line %u vendor %04x %s", + linectr, u, cp); + dbg("line %5u vendor %04x %s", linectr, u, cp); + lastvendor = u; + lasthut = lastlang = lastclass = lastsubclass = -1; + continue; + } + if (buf[0] == '\t' && isxdigit(buf[1])) { + /* product or subclass spec */ + u = strtoul(buf+1, &cp, 16); + while (isspace(*cp)) + cp++; + if (!*cp) { + err("Invalid product/subclass spec at line %u", + linectr); + continue; + } + if (lastvendor != -1) { + if (new_product(cp, lastvendor, u)) + err("Duplicate product spec at line %u product %04x:%04x %s", + linectr, lastvendor, u, cp); + dbg("line %5u product %04x:%04x %s", linectr, + lastvendor, u, cp); + continue; + } + if (lastclass != -1) { + if (new_subclass(cp, lastclass, u)) + err("Duplicate subclass spec at line %u class %02x:%02x %s", + linectr, lastclass, u, cp); + dbg("line %5u subclass %02x:%02x %s", linectr, + lastclass, u, cp); + lastsubclass = u; + continue; + } + if (lasthut != -1) { + /* do not store hut */ + continue; + } + if (lastlang != -1) { + /* do not store langid */ + continue; + } + err("Product/Subclass spec without prior Vendor/Class spec at line %u", + linectr); + continue; + } + if (buf[0] == '\t' && buf[1] == '\t' && isxdigit(buf[2])) { + /* protocol spec */ + u = strtoul(buf+2, &cp, 16); + while (isspace(*cp)) + cp++; + if (!*cp) { + err("Invalid protocol spec at line %u", + linectr); + continue; + } + if (lastclass != -1 && lastsubclass != -1) { + if (new_protocol(cp, lastclass, lastsubclass, + u)) + err("Duplicate protocol spec at line %u class %02x:%02x:%02x %s", + linectr, lastclass, lastsubclass, + u, cp); + dbg("line %5u protocol %02x:%02x:%02x %s", + linectr, lastclass, lastsubclass, u, cp); + continue; + } + err("Protocol spec without prior Class and Subclass spec at line %u", + linectr); + continue; + } + if (buf[0] == 'H' && buf[1] == 'I' && + buf[2] == 'D' && /*isspace(buf[3])*/ buf[3] == ' ') { + continue; + } + if (buf[0] == 'H' && buf[1] == 'U' && + buf[2] == 'T' && /*isspace(buf[3])*/ buf[3] == ' ') { + lastlang = lastclass = lastvendor = lastsubclass = -1; + /* + * set 1 as pseudo-id to indicate that the parser is + * in a `HUT' section. + */ + lasthut = 1; + continue; + } + if (buf[0] == 'R' && buf[1] == ' ') + continue; + + if (buf[0] == 'V' && buf[1] == 'T') + continue; + + err("Unknown line at line %u", linectr); + } +} + + +int names_init(char *n) +{ + FILE *f; + + f = fopen(n, "r"); + if (!f) + return errno; + + parse(f); + fclose(f); + return 0; +} diff --git a/tools/usb/usbip/libsrc/names.h b/tools/usb/usbip/libsrc/names.h new file mode 100644 index 0000000..6809265 --- /dev/null +++ b/tools/usb/usbip/libsrc/names.h @@ -0,0 +1,41 @@ +/* + * names.h -- USB name database manipulation routines + * + * Copyright (C) 1999, 2000 Thomas Sailer (sailer@ife.ee.ethz.ch) + * + * 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, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * + * + * Copyright (C) 2005 Takahiro Hirofuchi + * - names_free() is added. + */ + +#ifndef _NAMES_H +#define _NAMES_H + +#include <sys/types.h> + +/* used by usbip_common.c */ +extern const char *names_vendor(u_int16_t vendorid); +extern const char *names_product(u_int16_t vendorid, u_int16_t productid); +extern const char *names_class(u_int8_t classid); +extern const char *names_subclass(u_int8_t classid, u_int8_t subclassid); +extern const char *names_protocol(u_int8_t classid, u_int8_t subclassid, + u_int8_t protocolid); +extern int names_init(char *n); +extern void names_free(void); + +#endif /* _NAMES_H */ diff --git a/tools/usb/usbip/libsrc/sysfs_utils.c b/tools/usb/usbip/libsrc/sysfs_utils.c new file mode 100644 index 0000000..36ac88e --- /dev/null +++ b/tools/usb/usbip/libsrc/sysfs_utils.c @@ -0,0 +1,31 @@ +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <errno.h> + +#include "sysfs_utils.h" +#include "usbip_common.h" + +int write_sysfs_attribute(const char *attr_path, const char *new_value, + size_t len) +{ + int fd; + int length; + + fd = open(attr_path, O_WRONLY); + if (fd < 0) { + dbg("error opening attribute %s", attr_path); + return -1; + } + + length = write(fd, new_value, len); + if (length < 0) { + dbg("error writing to attribute %s", attr_path); + close(fd); + return -1; + } + + close(fd); + + return 0; +} diff --git a/tools/usb/usbip/libsrc/sysfs_utils.h b/tools/usb/usbip/libsrc/sysfs_utils.h new file mode 100644 index 0000000..32ac1d1 --- /dev/null +++ b/tools/usb/usbip/libsrc/sysfs_utils.h @@ -0,0 +1,8 @@ + +#ifndef __SYSFS_UTILS_H +#define __SYSFS_UTILS_H + +int write_sysfs_attribute(const char *attr_path, const char *new_value, + size_t len); + +#endif diff --git a/tools/usb/usbip/libsrc/usbip_common.c b/tools/usb/usbip/libsrc/usbip_common.c new file mode 100644 index 0000000..ac73710 --- /dev/null +++ b/tools/usb/usbip/libsrc/usbip_common.c @@ -0,0 +1,285 @@ +/* + * Copyright (C) 2005-2007 Takahiro Hirofuchi + */ + +#include <libudev.h> +#include "usbip_common.h" +#include "names.h" + +#undef PROGNAME +#define PROGNAME "libusbip" + +int usbip_use_syslog; +int usbip_use_stderr; +int usbip_use_debug; + +extern struct udev *udev_context; + +struct speed_string { + int num; + char *speed; + char *desc; +}; + +static const struct speed_string speed_strings[] = { + { USB_SPEED_UNKNOWN, "unknown", "Unknown Speed"}, + { USB_SPEED_LOW, "1.5", "Low Speed(1.5Mbps)" }, + { USB_SPEED_FULL, "12", "Full Speed(12Mbps)" }, + { USB_SPEED_HIGH, "480", "High Speed(480Mbps)" }, + { USB_SPEED_WIRELESS, "53.3-480", "Wireless"}, + { USB_SPEED_SUPER, "5000", "Super Speed(5000Mbps)" }, + { 0, NULL, NULL } +}; + +struct portst_string { + int num; + char *desc; +}; + +static struct portst_string portst_strings[] = { + { SDEV_ST_AVAILABLE, "Device Available" }, + { SDEV_ST_USED, "Device in Use" }, + { SDEV_ST_ERROR, "Device Error"}, + { VDEV_ST_NULL, "Port Available"}, + { VDEV_ST_NOTASSIGNED, "Port Initializing"}, + { VDEV_ST_USED, "Port in Use"}, + { VDEV_ST_ERROR, "Port Error"}, + { 0, NULL} +}; + +const char *usbip_status_string(int32_t status) +{ + for (int i = 0; portst_strings[i].desc != NULL; i++) + if (portst_strings[i].num == status) + return portst_strings[i].desc; + + return "Unknown Status"; +} + +const char *usbip_speed_string(int num) +{ + for (int i = 0; speed_strings[i].speed != NULL; i++) + if (speed_strings[i].num == num) + return speed_strings[i].desc; + + return "Unknown Speed"; +} + + +#define DBG_UDEV_INTEGER(name)\ + dbg("%-20s = %x", to_string(name), (int) udev->name) + +#define DBG_UINF_INTEGER(name)\ + dbg("%-20s = %x", to_string(name), (int) uinf->name) + +void dump_usb_interface(struct usbip_usb_interface *uinf) +{ + char buff[100]; + + usbip_names_get_class(buff, sizeof(buff), + uinf->bInterfaceClass, + uinf->bInterfaceSubClass, + uinf->bInterfaceProtocol); + dbg("%-20s = %s", "Interface(C/SC/P)", buff); +} + +void dump_usb_device(struct usbip_usb_device *udev) +{ + char buff[100]; + + dbg("%-20s = %s", "path", udev->path); + dbg("%-20s = %s", "busid", udev->busid); + + usbip_names_get_class(buff, sizeof(buff), + udev->bDeviceClass, + udev->bDeviceSubClass, + udev->bDeviceProtocol); + dbg("%-20s = %s", "Device(C/SC/P)", buff); + + DBG_UDEV_INTEGER(bcdDevice); + + usbip_names_get_product(buff, sizeof(buff), + udev->idVendor, + udev->idProduct); + dbg("%-20s = %s", "Vendor/Product", buff); + + DBG_UDEV_INTEGER(bNumConfigurations); + DBG_UDEV_INTEGER(bNumInterfaces); + + dbg("%-20s = %s", "speed", + usbip_speed_string(udev->speed)); + + DBG_UDEV_INTEGER(busnum); + DBG_UDEV_INTEGER(devnum); +} + + +int read_attr_value(struct udev_device *dev, const char *name, + const char *format) +{ + const char *attr; + int num = 0; + int ret; + + attr = udev_device_get_sysattr_value(dev, name); + if (!attr) { + err("udev_device_get_sysattr_value failed"); + goto err; + } + + /* The client chooses the device configuration + * when attaching it so right after being bound + * to usbip-host on the server the device will + * have no configuration. + * Therefore, attributes such as bConfigurationValue + * and bNumInterfaces will not exist and sscanf will + * fail. Check for these cases and don't treat them + * as errors. + */ + + ret = sscanf(attr, format, &num); + if (ret < 1) { + if (strcmp(name, "bConfigurationValue") && + strcmp(name, "bNumInterfaces")) { + err("sscanf failed for attribute %s", name); + goto err; + } + } + +err: + + return num; +} + + +int read_attr_speed(struct udev_device *dev) +{ + const char *speed; + + speed = udev_device_get_sysattr_value(dev, "speed"); + if (!speed) { + err("udev_device_get_sysattr_value failed"); + goto err; + } + + for (int i = 0; speed_strings[i].speed != NULL; i++) { + if (!strcmp(speed, speed_strings[i].speed)) + return speed_strings[i].num; + } + +err: + + return USB_SPEED_UNKNOWN; +} + +#define READ_ATTR(object, type, dev, name, format) \ + do { \ + (object)->name = (type) read_attr_value(dev, to_string(name), \ + format); \ + } while (0) + + +int read_usb_device(struct udev_device *sdev, struct usbip_usb_device *udev) +{ + uint32_t busnum, devnum; + const char *path, *name; + + READ_ATTR(udev, uint8_t, sdev, bDeviceClass, "%02x\n"); + READ_ATTR(udev, uint8_t, sdev, bDeviceSubClass, "%02x\n"); + READ_ATTR(udev, uint8_t, sdev, bDeviceProtocol, "%02x\n"); + + READ_ATTR(udev, uint16_t, sdev, idVendor, "%04x\n"); + READ_ATTR(udev, uint16_t, sdev, idProduct, "%04x\n"); + READ_ATTR(udev, uint16_t, sdev, bcdDevice, "%04x\n"); + + READ_ATTR(udev, uint8_t, sdev, bConfigurationValue, "%02x\n"); + READ_ATTR(udev, uint8_t, sdev, bNumConfigurations, "%02x\n"); + READ_ATTR(udev, uint8_t, sdev, bNumInterfaces, "%02x\n"); + + READ_ATTR(udev, uint8_t, sdev, devnum, "%d\n"); + udev->speed = read_attr_speed(sdev); + + path = udev_device_get_syspath(sdev); + name = udev_device_get_sysname(sdev); + + strncpy(udev->path, path, SYSFS_PATH_MAX); + strncpy(udev->busid, name, SYSFS_BUS_ID_SIZE); + + sscanf(name, "%u-%u", &busnum, &devnum); + udev->busnum = busnum; + + return 0; +} + +int read_usb_interface(struct usbip_usb_device *udev, int i, + struct usbip_usb_interface *uinf) +{ + char busid[SYSFS_BUS_ID_SIZE]; + struct udev_device *sif; + + sprintf(busid, "%s:%d.%d", udev->busid, udev->bConfigurationValue, i); + + sif = udev_device_new_from_subsystem_sysname(udev_context, "usb", busid); + if (!sif) { + err("udev_device_new_from_subsystem_sysname %s failed", busid); + return -1; + } + + READ_ATTR(uinf, uint8_t, sif, bInterfaceClass, "%02x\n"); + READ_ATTR(uinf, uint8_t, sif, bInterfaceSubClass, "%02x\n"); + READ_ATTR(uinf, uint8_t, sif, bInterfaceProtocol, "%02x\n"); + + return 0; +} + +int usbip_names_init(char *f) +{ + return names_init(f); +} + +void usbip_names_free(void) +{ + names_free(); +} + +void usbip_names_get_product(char *buff, size_t size, uint16_t vendor, + uint16_t product) +{ + const char *prod, *vend; + + prod = names_product(vendor, product); + if (!prod) + prod = "unknown product"; + + + vend = names_vendor(vendor); + if (!vend) + vend = "unknown vendor"; + + snprintf(buff, size, "%s : %s (%04x:%04x)", vend, prod, vendor, product); +} + +void usbip_names_get_class(char *buff, size_t size, uint8_t class, + uint8_t subclass, uint8_t protocol) +{ + const char *c, *s, *p; + + if (class == 0 && subclass == 0 && protocol == 0) { + snprintf(buff, size, "(Defined at Interface level) (%02x/%02x/%02x)", class, subclass, protocol); + return; + } + + p = names_protocol(class, subclass, protocol); + if (!p) + p = "unknown protocol"; + + s = names_subclass(class, subclass); + if (!s) + s = "unknown subclass"; + + c = names_class(class); + if (!c) + c = "unknown class"; + + snprintf(buff, size, "%s / %s / %s (%02x/%02x/%02x)", c, s, p, class, subclass, protocol); +} diff --git a/tools/usb/usbip/libsrc/usbip_common.h b/tools/usb/usbip/libsrc/usbip_common.h new file mode 100644 index 0000000..15fe792 --- /dev/null +++ b/tools/usb/usbip/libsrc/usbip_common.h @@ -0,0 +1,137 @@ +/* + * Copyright (C) 2005-2007 Takahiro Hirofuchi + */ + +#ifndef __USBIP_COMMON_H +#define __USBIP_COMMON_H + +#include <libudev.h> + +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <syslog.h> +#include <unistd.h> +#include <linux/usb/ch9.h> +#include <linux/usbip.h> + +#ifndef USBIDS_FILE +#define USBIDS_FILE "/usr/share/hwdata/usb.ids" +#endif + +#ifndef VHCI_STATE_PATH +#define VHCI_STATE_PATH "/var/run/vhci_hcd" +#endif + +/* kernel module names */ +#define USBIP_CORE_MOD_NAME "usbip-core" +#define USBIP_HOST_DRV_NAME "usbip-host" +#define USBIP_VHCI_DRV_NAME "vhci_hcd" + +/* sysfs constants */ +#define SYSFS_MNT_PATH "/sys" +#define SYSFS_BUS_NAME "bus" +#define SYSFS_BUS_TYPE "usb" +#define SYSFS_DRIVERS_NAME "drivers" + +#define SYSFS_PATH_MAX 256 +#define SYSFS_BUS_ID_SIZE 32 + +extern int usbip_use_syslog; +extern int usbip_use_stderr; +extern int usbip_use_debug ; + +#define PROGNAME "usbip" + +#define pr_fmt(fmt) "%s: %s: " fmt "\n", PROGNAME +#define dbg_fmt(fmt) pr_fmt("%s:%d:[%s] " fmt), "debug", \ + __FILE__, __LINE__, __func__ + +#define err(fmt, args...) \ + do { \ + if (usbip_use_syslog) { \ + syslog(LOG_ERR, pr_fmt(fmt), "error", ##args); \ + } \ + if (usbip_use_stderr) { \ + fprintf(stderr, pr_fmt(fmt), "error", ##args); \ + } \ + } while (0) + +#define info(fmt, args...) \ + do { \ + if (usbip_use_syslog) { \ + syslog(LOG_INFO, pr_fmt(fmt), "info", ##args); \ + } \ + if (usbip_use_stderr) { \ + fprintf(stderr, pr_fmt(fmt), "info", ##args); \ + } \ + } while (0) + +#define dbg(fmt, args...) \ + do { \ + if (usbip_use_debug) { \ + if (usbip_use_syslog) { \ + syslog(LOG_DEBUG, dbg_fmt(fmt), ##args); \ + } \ + if (usbip_use_stderr) { \ + fprintf(stderr, dbg_fmt(fmt), ##args); \ + } \ + } \ + } while (0) + +#define BUG() \ + do { \ + err("sorry, it's a bug!"); \ + abort(); \ + } while (0) + +struct usbip_usb_interface { + uint8_t bInterfaceClass; + uint8_t bInterfaceSubClass; + uint8_t bInterfaceProtocol; + uint8_t padding; /* alignment */ +} __attribute__((packed)); + +struct usbip_usb_device { + char path[SYSFS_PATH_MAX]; + char busid[SYSFS_BUS_ID_SIZE]; + + uint32_t busnum; + uint32_t devnum; + uint32_t speed; + + uint16_t idVendor; + uint16_t idProduct; + uint16_t bcdDevice; + + uint8_t bDeviceClass; + uint8_t bDeviceSubClass; + uint8_t bDeviceProtocol; + uint8_t bConfigurationValue; + uint8_t bNumConfigurations; + uint8_t bNumInterfaces; +} __attribute__((packed)); + +#define to_string(s) #s + +void dump_usb_interface(struct usbip_usb_interface *); +void dump_usb_device(struct usbip_usb_device *); +int read_usb_device(struct udev_device *sdev, struct usbip_usb_device *udev); +int read_attr_value(struct udev_device *dev, const char *name, + const char *format); +int read_usb_interface(struct usbip_usb_device *udev, int i, + struct usbip_usb_interface *uinf); + +const char *usbip_speed_string(int num); +const char *usbip_status_string(int32_t status); + +int usbip_names_init(char *); +void usbip_names_free(void); +void usbip_names_get_product(char *buff, size_t size, uint16_t vendor, + uint16_t product); +void usbip_names_get_class(char *buff, size_t size, uint8_t class, + uint8_t subclass, uint8_t protocol); + +#endif /* __USBIP_COMMON_H */ diff --git a/tools/usb/usbip/libsrc/usbip_host_driver.c b/tools/usb/usbip/libsrc/usbip_host_driver.c new file mode 100644 index 0000000..bef08d5 --- /dev/null +++ b/tools/usb/usbip/libsrc/usbip_host_driver.c @@ -0,0 +1,280 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> + +#include <errno.h> +#include <unistd.h> + +#include <libudev.h> + +#include "usbip_common.h" +#include "usbip_host_driver.h" +#include "list.h" +#include "sysfs_utils.h" + +#undef PROGNAME +#define PROGNAME "libusbip" + +struct usbip_host_driver *host_driver; +struct udev *udev_context; + +static int32_t read_attr_usbip_status(struct usbip_usb_device *udev) +{ + char status_attr_path[SYSFS_PATH_MAX]; + int fd; + int length; + char status; + int value = 0; + + snprintf(status_attr_path, SYSFS_PATH_MAX, "%s/usbip_status", + udev->path); + + fd = open(status_attr_path, O_RDONLY); + if (fd < 0) { + err("error opening attribute %s", status_attr_path); + return -1; + } + + length = read(fd, &status, 1); + if (length < 0) { + err("error reading attribute %s", status_attr_path); + close(fd); + return -1; + } + + value = atoi(&status); + + return value; +} + +static +struct usbip_exported_device *usbip_exported_device_new(const char *sdevpath) +{ + struct usbip_exported_device *edev = NULL; + struct usbip_exported_device *edev_old; + size_t size; + int i; + + edev = calloc(1, sizeof(struct usbip_exported_device)); + + edev->sudev = udev_device_new_from_syspath(udev_context, sdevpath); + if (!edev->sudev) { + err("udev_device_new_from_syspath: %s", sdevpath); + goto err; + } + + read_usb_device(edev->sudev, &edev->udev); + + edev->status = read_attr_usbip_status(&edev->udev); + if (edev->status < 0) + goto err; + + /* reallocate buffer to include usb interface data */ + size = sizeof(struct usbip_exported_device) + + edev->udev.bNumInterfaces * sizeof(struct usbip_usb_interface); + + edev_old = edev; + edev = realloc(edev, size); + if (!edev) { + edev = edev_old; + dbg("realloc failed"); + goto err; + } + + for (i = 0; i < edev->udev.bNumInterfaces; i++) + read_usb_interface(&edev->udev, i, &edev->uinf[i]); + + return edev; +err: + if (edev->sudev) + udev_device_unref(edev->sudev); + if (edev) + free(edev); + + return NULL; +} + +static int refresh_exported_devices(void) +{ + struct usbip_exported_device *edev; + struct udev_enumerate *enumerate; + struct udev_list_entry *devices, *dev_list_entry; + struct udev_device *dev; + const char *path; + const char *driver; + + enumerate = udev_enumerate_new(udev_context); + udev_enumerate_add_match_subsystem(enumerate, "usb"); + udev_enumerate_scan_devices(enumerate); + + devices = udev_enumerate_get_list_entry(enumerate); + + udev_list_entry_foreach(dev_list_entry, devices) { + path = udev_list_entry_get_name(dev_list_entry); + dev = udev_device_new_from_syspath(udev_context, path); + if (dev == NULL) + continue; + + /* Check whether device uses usbip-host driver. */ + driver = udev_device_get_driver(dev); + if (driver != NULL && !strcmp(driver, USBIP_HOST_DRV_NAME)) { + edev = usbip_exported_device_new(path); + if (!edev) { + dbg("usbip_exported_device_new failed"); + continue; + } + + list_add(&edev->node, &host_driver->edev_list); + host_driver->ndevs++; + } + } + + return 0; +} + +static void usbip_exported_device_destroy(void) +{ + struct list_head *i, *tmp; + struct usbip_exported_device *edev; + + list_for_each_safe(i, tmp, &host_driver->edev_list) { + edev = list_entry(i, struct usbip_exported_device, node); + list_del(i); + free(edev); + } +} + +int usbip_host_driver_open(void) +{ + int rc; + + udev_context = udev_new(); + if (!udev_context) { + err("udev_new failed"); + return -1; + } + + host_driver = calloc(1, sizeof(*host_driver)); + + host_driver->ndevs = 0; + INIT_LIST_HEAD(&host_driver->edev_list); + + rc = refresh_exported_devices(); + if (rc < 0) + goto err_free_host_driver; + + return 0; + +err_free_host_driver: + free(host_driver); + host_driver = NULL; + + udev_unref(udev_context); + + return -1; +} + +void usbip_host_driver_close(void) +{ + if (!host_driver) + return; + + usbip_exported_device_destroy(); + + free(host_driver); + host_driver = NULL; + + udev_unref(udev_context); +} + +int usbip_host_refresh_device_list(void) +{ + int rc; + + usbip_exported_device_destroy(); + + host_driver->ndevs = 0; + INIT_LIST_HEAD(&host_driver->edev_list); + + rc = refresh_exported_devices(); + if (rc < 0) + return -1; + + return 0; +} + +int usbip_host_export_device(struct usbip_exported_device *edev, int sockfd) +{ + char attr_name[] = "usbip_sockfd"; + char sockfd_attr_path[SYSFS_PATH_MAX]; + char sockfd_buff[30]; + int ret; + + if (edev->status != SDEV_ST_AVAILABLE) { + dbg("device not available: %s", edev->udev.busid); + switch (edev->status) { + case SDEV_ST_ERROR: + dbg("status SDEV_ST_ERROR"); + break; + case SDEV_ST_USED: + dbg("status SDEV_ST_USED"); + break; + default: + dbg("status unknown: 0x%x", edev->status); + } + return -1; + } + + /* only the first interface is true */ + snprintf(sockfd_attr_path, sizeof(sockfd_attr_path), "%s/%s", + edev->udev.path, attr_name); + + snprintf(sockfd_buff, sizeof(sockfd_buff), "%d\n", sockfd); + + ret = write_sysfs_attribute(sockfd_attr_path, sockfd_buff, + strlen(sockfd_buff)); + if (ret < 0) { + err("write_sysfs_attribute failed: sockfd %s to %s", + sockfd_buff, sockfd_attr_path); + return ret; + } + + info("connect: %s", edev->udev.busid); + + return ret; +} + +struct usbip_exported_device *usbip_host_get_device(int num) +{ + struct list_head *i; + struct usbip_exported_device *edev; + int cnt = 0; + + list_for_each(i, &host_driver->edev_list) { + edev = list_entry(i, struct usbip_exported_device, node); + if (num == cnt) + return edev; + else + cnt++; + } + + return NULL; +} diff --git a/tools/usb/usbip/libsrc/usbip_host_driver.h b/tools/usb/usbip/libsrc/usbip_host_driver.h new file mode 100644 index 0000000..2a31f85 --- /dev/null +++ b/tools/usb/usbip/libsrc/usbip_host_driver.h @@ -0,0 +1,49 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __USBIP_HOST_DRIVER_H +#define __USBIP_HOST_DRIVER_H + +#include <stdint.h> +#include "usbip_common.h" +#include "list.h" + +struct usbip_host_driver { + int ndevs; + /* list of exported device */ + struct list_head edev_list; +}; + +struct usbip_exported_device { + struct udev_device *sudev; + int32_t status; + struct usbip_usb_device udev; + struct list_head node; + struct usbip_usb_interface uinf[]; +}; + +extern struct usbip_host_driver *host_driver; + +int usbip_host_driver_open(void); +void usbip_host_driver_close(void); + +int usbip_host_refresh_device_list(void); +int usbip_host_export_device(struct usbip_exported_device *edev, int sockfd); +struct usbip_exported_device *usbip_host_get_device(int num); + +#endif /* __USBIP_HOST_DRIVER_H */ diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c new file mode 100644 index 0000000..ad92047 --- /dev/null +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -0,0 +1,411 @@ +/* + * Copyright (C) 2005-2007 Takahiro Hirofuchi + */ + +#include "usbip_common.h" +#include "vhci_driver.h" +#include <limits.h> +#include <netdb.h> +#include <libudev.h> +#include "sysfs_utils.h" + +#undef PROGNAME +#define PROGNAME "libusbip" + +struct usbip_vhci_driver *vhci_driver; +struct udev *udev_context; + +static struct usbip_imported_device * +imported_device_init(struct usbip_imported_device *idev, char *busid) +{ + struct udev_device *sudev; + + sudev = udev_device_new_from_subsystem_sysname(udev_context, + "usb", busid); + if (!sudev) { + dbg("udev_device_new_from_subsystem_sysname failed: %s", busid); + goto err; + } + read_usb_device(sudev, &idev->udev); + udev_device_unref(sudev); + + return idev; + +err: + return NULL; +} + + + +static int parse_status(const char *value) +{ + int ret = 0; + char *c; + + + for (int i = 0; i < vhci_driver->nports; i++) + memset(&vhci_driver->idev[i], 0, sizeof(vhci_driver->idev[i])); + + + /* skip a header line */ + c = strchr(value, '\n'); + if (!c) + return -1; + c++; + + while (*c != '\0') { + int port, status, speed, devid; + unsigned long socket; + char lbusid[SYSFS_BUS_ID_SIZE]; + + ret = sscanf(c, "%d %d %d %x %lx %31s\n", + &port, &status, &speed, + &devid, &socket, lbusid); + + if (ret < 5) { + dbg("sscanf failed: %d", ret); + BUG(); + } + + dbg("port %d status %d speed %d devid %x", + port, status, speed, devid); + dbg("socket %lx lbusid %s", socket, lbusid); + + + /* if a device is connected, look at it */ + { + struct usbip_imported_device *idev = &vhci_driver->idev[port]; + + idev->port = port; + idev->status = status; + + idev->devid = devid; + + idev->busnum = (devid >> 16); + idev->devnum = (devid & 0x0000ffff); + + if (idev->status != VDEV_ST_NULL + && idev->status != VDEV_ST_NOTASSIGNED) { + idev = imported_device_init(idev, lbusid); + if (!idev) { + dbg("imported_device_init failed"); + return -1; + } + } + } + + + /* go to the next line */ + c = strchr(c, '\n'); + if (!c) + break; + c++; + } + + dbg("exit"); + + return 0; +} + +static int refresh_imported_device_list(void) +{ + const char *attr_status; + + attr_status = udev_device_get_sysattr_value(vhci_driver->hc_device, + "status"); + if (!attr_status) { + err("udev_device_get_sysattr_value failed"); + return -1; + } + + return parse_status(attr_status); +} + +static int get_nports(void) +{ + char *c; + int nports = 0; + const char *attr_status; + + attr_status = udev_device_get_sysattr_value(vhci_driver->hc_device, + "status"); + if (!attr_status) { + err("udev_device_get_sysattr_value failed"); + return -1; + } + + /* skip a header line */ + c = strchr(attr_status, '\n'); + if (!c) + return 0; + c++; + + while (*c != '\0') { + /* go to the next line */ + c = strchr(c, '\n'); + if (!c) + return nports; + c++; + nports += 1; + } + + return nports; +} + +/* + * Read the given port's record. + * + * To avoid buffer overflow we will read the entire line and + * validate each part's size. The initial buffer is padded by 4 to + * accommodate the 2 spaces, 1 newline and an additional character + * which is needed to properly validate the 3rd part without it being + * truncated to an acceptable length. + */ +static int read_record(int rhport, char *host, unsigned long host_len, + char *port, unsigned long port_len, char *busid) +{ + int part; + FILE *file; + char path[PATH_MAX+1]; + char *buffer, *start, *end; + char delim[] = {' ', ' ', '\n'}; + int max_len[] = {(int)host_len, (int)port_len, SYSFS_BUS_ID_SIZE}; + size_t buffer_len = host_len + port_len + SYSFS_BUS_ID_SIZE + 4; + + buffer = malloc(buffer_len); + if (!buffer) + return -1; + + snprintf(path, PATH_MAX, VHCI_STATE_PATH"/port%d", rhport); + + file = fopen(path, "r"); + if (!file) { + err("fopen"); + free(buffer); + return -1; + } + + if (fgets(buffer, buffer_len, file) == NULL) { + err("fgets"); + free(buffer); + fclose(file); + return -1; + } + fclose(file); + + /* validate the length of each of the 3 parts */ + start = buffer; + for (part = 0; part < 3; part++) { + end = strchr(start, delim[part]); + if (end == NULL || (end - start) > max_len[part]) { + free(buffer); + return -1; + } + start = end + 1; + } + + if (sscanf(buffer, "%s %s %s\n", host, port, busid) != 3) { + err("sscanf"); + free(buffer); + return -1; + } + + free(buffer); + + return 0; +} + +/* ---------------------------------------------------------------------- */ + +int usbip_vhci_driver_open(void) +{ + udev_context = udev_new(); + if (!udev_context) { + err("udev_new failed"); + return -1; + } + + vhci_driver = calloc(1, sizeof(struct usbip_vhci_driver)); + + /* will be freed in usbip_driver_close() */ + vhci_driver->hc_device = + udev_device_new_from_subsystem_sysname(udev_context, + USBIP_VHCI_BUS_TYPE, + USBIP_VHCI_DRV_NAME); + if (!vhci_driver->hc_device) { + err("udev_device_new_from_subsystem_sysname failed"); + goto err; + } + + vhci_driver->nports = get_nports(); + + dbg("available ports: %d", vhci_driver->nports); + + if (refresh_imported_device_list()) + goto err; + + return 0; + +err: + udev_device_unref(vhci_driver->hc_device); + + if (vhci_driver) + free(vhci_driver); + + vhci_driver = NULL; + + udev_unref(udev_context); + + return -1; +} + + +void usbip_vhci_driver_close(void) +{ + if (!vhci_driver) + return; + + udev_device_unref(vhci_driver->hc_device); + + free(vhci_driver); + + vhci_driver = NULL; + + udev_unref(udev_context); +} + + +int usbip_vhci_refresh_device_list(void) +{ + + if (refresh_imported_device_list()) + goto err; + + return 0; +err: + dbg("failed to refresh device list"); + return -1; +} + + +int usbip_vhci_get_free_port(void) +{ + for (int i = 0; i < vhci_driver->nports; i++) { + if (vhci_driver->idev[i].status == VDEV_ST_NULL) + return i; + } + + return -1; +} + +int usbip_vhci_attach_device2(uint8_t port, int sockfd, uint32_t devid, + uint32_t speed) { + char buff[200]; /* what size should be ? */ + char attach_attr_path[SYSFS_PATH_MAX]; + char attr_attach[] = "attach"; + const char *path; + int ret; + + snprintf(buff, sizeof(buff), "%u %d %u %u", + port, sockfd, devid, speed); + dbg("writing: %s", buff); + + path = udev_device_get_syspath(vhci_driver->hc_device); + snprintf(attach_attr_path, sizeof(attach_attr_path), "%s/%s", + path, attr_attach); + dbg("attach attribute path: %s", attach_attr_path); + + ret = write_sysfs_attribute(attach_attr_path, buff, strlen(buff)); + if (ret < 0) { + dbg("write_sysfs_attribute failed"); + return -1; + } + + dbg("attached port: %d", port); + + return 0; +} + +static unsigned long get_devid(uint8_t busnum, uint8_t devnum) +{ + return (busnum << 16) | devnum; +} + +/* will be removed */ +int usbip_vhci_attach_device(uint8_t port, int sockfd, uint8_t busnum, + uint8_t devnum, uint32_t speed) +{ + int devid = get_devid(busnum, devnum); + + return usbip_vhci_attach_device2(port, sockfd, devid, speed); +} + +int usbip_vhci_detach_device(uint8_t port) +{ + char detach_attr_path[SYSFS_PATH_MAX]; + char attr_detach[] = "detach"; + char buff[200]; /* what size should be ? */ + const char *path; + int ret; + + snprintf(buff, sizeof(buff), "%u", port); + dbg("writing: %s", buff); + + path = udev_device_get_syspath(vhci_driver->hc_device); + snprintf(detach_attr_path, sizeof(detach_attr_path), "%s/%s", + path, attr_detach); + dbg("detach attribute path: %s", detach_attr_path); + + ret = write_sysfs_attribute(detach_attr_path, buff, strlen(buff)); + if (ret < 0) { + dbg("write_sysfs_attribute failed"); + return -1; + } + + dbg("detached port: %d", port); + + return 0; +} + +int usbip_vhci_imported_device_dump(struct usbip_imported_device *idev) +{ + char product_name[100]; + char host[NI_MAXHOST] = "unknown host"; + char serv[NI_MAXSERV] = "unknown port"; + char remote_busid[SYSFS_BUS_ID_SIZE]; + int ret; + int read_record_error = 0; + + if (idev->status == VDEV_ST_NULL || idev->status == VDEV_ST_NOTASSIGNED) + return 0; + + ret = read_record(idev->port, host, sizeof(host), serv, sizeof(serv), + remote_busid); + if (ret) { + err("read_record"); + read_record_error = 1; + } + + printf("Port %02d: <%s> at %s\n", idev->port, + usbip_status_string(idev->status), + usbip_speed_string(idev->udev.speed)); + + usbip_names_get_product(product_name, sizeof(product_name), + idev->udev.idVendor, idev->udev.idProduct); + + printf(" %s\n", product_name); + + if (!read_record_error) { + printf("%10s -> usbip://%s:%s/%s\n", idev->udev.busid, + host, serv, remote_busid); + printf("%10s -> remote bus/dev %03d/%03d\n", " ", + idev->busnum, idev->devnum); + } else { + printf("%10s -> unknown host, remote port and remote busid\n", + idev->udev.busid); + printf("%10s -> remote bus/dev %03d/%03d\n", " ", + idev->busnum, idev->devnum); + } + + return 0; +} diff --git a/tools/usb/usbip/libsrc/vhci_driver.h b/tools/usb/usbip/libsrc/vhci_driver.h new file mode 100644 index 0000000..fa2316c --- /dev/null +++ b/tools/usb/usbip/libsrc/vhci_driver.h @@ -0,0 +1,59 @@ +/* + * Copyright (C) 2005-2007 Takahiro Hirofuchi + */ + +#ifndef __VHCI_DRIVER_H +#define __VHCI_DRIVER_H + +#include <libudev.h> +#include <stdint.h> + +#include "usbip_common.h" + +#define USBIP_VHCI_BUS_TYPE "platform" +#define MAXNPORT 128 + +struct usbip_imported_device { + uint8_t port; + uint32_t status; + + uint32_t devid; + + uint8_t busnum; + uint8_t devnum; + + /* usbip_class_device list */ + struct usbip_usb_device udev; +}; + +struct usbip_vhci_driver { + + /* /sys/devices/platform/vhci_hcd */ + struct udev_device *hc_device; + + int nports; + struct usbip_imported_device idev[MAXNPORT]; +}; + + +extern struct usbip_vhci_driver *vhci_driver; + +int usbip_vhci_driver_open(void); +void usbip_vhci_driver_close(void); + +int usbip_vhci_refresh_device_list(void); + + +int usbip_vhci_get_free_port(void); +int usbip_vhci_attach_device2(uint8_t port, int sockfd, uint32_t devid, + uint32_t speed); + +/* will be removed */ +int usbip_vhci_attach_device(uint8_t port, int sockfd, uint8_t busnum, + uint8_t devnum, uint32_t speed); + +int usbip_vhci_detach_device(uint8_t port); + +int usbip_vhci_imported_device_dump(struct usbip_imported_device *idev); + +#endif /* __VHCI_DRIVER_H */ diff --git a/tools/usb/usbip/src/Makefile.am b/tools/usb/usbip/src/Makefile.am new file mode 100644 index 0000000..e81a4eb --- /dev/null +++ b/tools/usb/usbip/src/Makefile.am @@ -0,0 +1,11 @@ +AM_CPPFLAGS = -I$(top_srcdir)/libsrc -DUSBIDS_FILE='"@USBIDS_DIR@/usb.ids"' +AM_CFLAGS = @EXTRA_CFLAGS@ +LDADD = $(top_builddir)/libsrc/libusbip.la + +sbin_PROGRAMS := usbip usbipd + +usbip_SOURCES := usbip.h utils.h usbip.c utils.c usbip_network.c \ + usbip_attach.c usbip_detach.c usbip_list.c \ + usbip_bind.c usbip_unbind.c usbip_port.c + +usbipd_SOURCES := usbip_network.h usbipd.c usbip_network.c diff --git a/tools/usb/usbip/src/usbip.c b/tools/usb/usbip/src/usbip.c new file mode 100644 index 0000000..d7599d9 --- /dev/null +++ b/tools/usb/usbip/src/usbip.c @@ -0,0 +1,201 @@ +/* + * command structure borrowed from udev + * (git://git.kernel.org/pub/scm/linux/hotplug/udev.git) + * + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include <getopt.h> +#include <syslog.h> + +#include "usbip_common.h" +#include "usbip_network.h" +#include "usbip.h" + +static int usbip_help(int argc, char *argv[]); +static int usbip_version(int argc, char *argv[]); + +static const char usbip_version_string[] = PACKAGE_STRING; + +static const char usbip_usage_string[] = + "usbip [--debug] [--log] [--tcp-port PORT] [version]\n" + " [help] <command> <args>\n"; + +static void usbip_usage(void) +{ + printf("usage: %s", usbip_usage_string); +} + +struct command { + const char *name; + int (*fn)(int argc, char *argv[]); + const char *help; + void (*usage)(void); +}; + +static const struct command cmds[] = { + { + .name = "help", + .fn = usbip_help, + .help = NULL, + .usage = NULL + }, + { + .name = "version", + .fn = usbip_version, + .help = NULL, + .usage = NULL + }, + { + .name = "attach", + .fn = usbip_attach, + .help = "Attach a remote USB device", + .usage = usbip_attach_usage + }, + { + .name = "detach", + .fn = usbip_detach, + .help = "Detach a remote USB device", + .usage = usbip_detach_usage + }, + { + .name = "list", + .fn = usbip_list, + .help = "List exportable or local USB devices", + .usage = usbip_list_usage + }, + { + .name = "bind", + .fn = usbip_bind, + .help = "Bind device to " USBIP_HOST_DRV_NAME ".ko", + .usage = usbip_bind_usage + }, + { + .name = "unbind", + .fn = usbip_unbind, + .help = "Unbind device from " USBIP_HOST_DRV_NAME ".ko", + .usage = usbip_unbind_usage + }, + { + .name = "port", + .fn = usbip_port_show, + .help = "Show imported USB devices", + .usage = NULL + }, + { NULL, NULL, NULL, NULL } +}; + +static int usbip_help(int argc, char *argv[]) +{ + const struct command *cmd; + int i; + int ret = 0; + + if (argc > 1 && argv++) { + for (i = 0; cmds[i].name != NULL; i++) + if (!strcmp(cmds[i].name, argv[0]) && cmds[i].usage) { + cmds[i].usage(); + goto done; + } + ret = -1; + } + + usbip_usage(); + printf("\n"); + for (cmd = cmds; cmd->name != NULL; cmd++) + if (cmd->help != NULL) + printf(" %-10s %s\n", cmd->name, cmd->help); + printf("\n"); +done: + return ret; +} + +static int usbip_version(int argc, char *argv[]) +{ + (void) argc; + (void) argv; + + printf(PROGNAME " (%s)\n", usbip_version_string); + return 0; +} + +static int run_command(const struct command *cmd, int argc, char *argv[]) +{ + dbg("running command: `%s'", cmd->name); + return cmd->fn(argc, argv); +} + +int main(int argc, char *argv[]) +{ + static const struct option opts[] = { + { "debug", no_argument, NULL, 'd' }, + { "log", no_argument, NULL, 'l' }, + { "tcp-port", required_argument, NULL, 't' }, + { NULL, 0, NULL, 0 } + }; + + char *cmd; + int opt; + int i, rc = -1; + + usbip_use_stderr = 1; + opterr = 0; + for (;;) { + opt = getopt_long(argc, argv, "+dlt:", opts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'd': + usbip_use_debug = 1; + break; + case 'l': + usbip_use_syslog = 1; + openlog("", LOG_PID, LOG_USER); + break; + case 't': + usbip_setup_port_number(optarg); + break; + case '?': + printf("usbip: invalid option\n"); + default: + usbip_usage(); + goto out; + } + } + + cmd = argv[optind]; + if (cmd) { + for (i = 0; cmds[i].name != NULL; i++) + if (!strcmp(cmds[i].name, cmd)) { + argc -= optind; + argv += optind; + optind = 0; + rc = run_command(&cmds[i], argc, argv); + goto out; + } + } + + /* invalid command */ + usbip_help(0, NULL); +out: + return (rc > -1 ? EXIT_SUCCESS : EXIT_FAILURE); +} diff --git a/tools/usb/usbip/src/usbip.h b/tools/usb/usbip/src/usbip.h new file mode 100644 index 0000000..84fe66a --- /dev/null +++ b/tools/usb/usbip/src/usbip.h @@ -0,0 +1,40 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __USBIP_H +#define __USBIP_H + +#ifdef HAVE_CONFIG_H +#include "../config.h" +#endif + +/* usbip commands */ +int usbip_attach(int argc, char *argv[]); +int usbip_detach(int argc, char *argv[]); +int usbip_list(int argc, char *argv[]); +int usbip_bind(int argc, char *argv[]); +int usbip_unbind(int argc, char *argv[]); +int usbip_port_show(int argc, char *argv[]); + +void usbip_attach_usage(void); +void usbip_detach_usage(void); +void usbip_list_usage(void); +void usbip_bind_usage(void); +void usbip_unbind_usage(void); + +#endif /* __USBIP_H */ diff --git a/tools/usb/usbip/src/usbip_attach.c b/tools/usb/usbip/src/usbip_attach.c new file mode 100644 index 0000000..d58a14d --- /dev/null +++ b/tools/usb/usbip/src/usbip_attach.c @@ -0,0 +1,241 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#include <sys/stat.h> + +#include <limits.h> +#include <stdint.h> +#include <stdio.h> +#include <string.h> + +#include <fcntl.h> +#include <getopt.h> +#include <unistd.h> +#include <errno.h> + +#include "vhci_driver.h" +#include "usbip_common.h" +#include "usbip_network.h" +#include "usbip.h" + +static const char usbip_attach_usage_string[] = + "usbip attach <args>\n" + " -r, --remote=<host> The machine with exported USB devices\n" + " -b, --busid=<busid> Busid of the device on <host>\n"; + +void usbip_attach_usage(void) +{ + printf("usage: %s", usbip_attach_usage_string); +} + +#define MAX_BUFF 100 +static int record_connection(char *host, char *port, char *busid, int rhport) +{ + int fd; + char path[PATH_MAX+1]; + char buff[MAX_BUFF+1]; + int ret; + + ret = mkdir(VHCI_STATE_PATH, 0700); + if (ret < 0) { + /* if VHCI_STATE_PATH exists, then it better be a directory */ + if (errno == EEXIST) { + struct stat s; + + ret = stat(VHCI_STATE_PATH, &s); + if (ret < 0) + return -1; + if (!(s.st_mode & S_IFDIR)) + return -1; + } else + return -1; + } + + snprintf(path, PATH_MAX, VHCI_STATE_PATH"/port%d", rhport); + + fd = open(path, O_WRONLY|O_CREAT|O_TRUNC, S_IRWXU); + if (fd < 0) + return -1; + + snprintf(buff, MAX_BUFF, "%s %s %s\n", + host, port, busid); + + ret = write(fd, buff, strlen(buff)); + if (ret != (ssize_t) strlen(buff)) { + close(fd); + return -1; + } + + close(fd); + + return 0; +} + +static int import_device(int sockfd, struct usbip_usb_device *udev) +{ + int rc; + int port; + + rc = usbip_vhci_driver_open(); + if (rc < 0) { + err("open vhci_driver"); + return -1; + } + + port = usbip_vhci_get_free_port(); + if (port < 0) { + err("no free port"); + usbip_vhci_driver_close(); + return -1; + } + + rc = usbip_vhci_attach_device(port, sockfd, udev->busnum, + udev->devnum, udev->speed); + if (rc < 0) { + err("import device"); + usbip_vhci_driver_close(); + return -1; + } + + usbip_vhci_driver_close(); + + return port; +} + +static int query_import_device(int sockfd, char *busid) +{ + int rc; + struct op_import_request request; + struct op_import_reply reply; + uint16_t code = OP_REP_IMPORT; + + memset(&request, 0, sizeof(request)); + memset(&reply, 0, sizeof(reply)); + + /* send a request */ + rc = usbip_net_send_op_common(sockfd, OP_REQ_IMPORT, 0); + if (rc < 0) { + err("send op_common"); + return -1; + } + + strncpy(request.busid, busid, SYSFS_BUS_ID_SIZE-1); + + PACK_OP_IMPORT_REQUEST(0, &request); + + rc = usbip_net_send(sockfd, (void *) &request, sizeof(request)); + if (rc < 0) { + err("send op_import_request"); + return -1; + } + + /* receive a reply */ + rc = usbip_net_recv_op_common(sockfd, &code); + if (rc < 0) { + err("recv op_common"); + return -1; + } + + rc = usbip_net_recv(sockfd, (void *) &reply, sizeof(reply)); + if (rc < 0) { + err("recv op_import_reply"); + return -1; + } + + PACK_OP_IMPORT_REPLY(0, &reply); + + /* check the reply */ + if (strncmp(reply.udev.busid, busid, SYSFS_BUS_ID_SIZE)) { + err("recv different busid %s", reply.udev.busid); + return -1; + } + + /* import a device */ + return import_device(sockfd, &reply.udev); +} + +static int attach_device(char *host, char *busid) +{ + int sockfd; + int rc; + int rhport; + + sockfd = usbip_net_tcp_connect(host, usbip_port_string); + if (sockfd < 0) { + err("tcp connect"); + return -1; + } + + rhport = query_import_device(sockfd, busid); + if (rhport < 0) { + err("query"); + return -1; + } + + close(sockfd); + + rc = record_connection(host, usbip_port_string, busid, rhport); + if (rc < 0) { + err("record connection"); + return -1; + } + + return 0; +} + +int usbip_attach(int argc, char *argv[]) +{ + static const struct option opts[] = { + { "remote", required_argument, NULL, 'r' }, + { "busid", required_argument, NULL, 'b' }, + { NULL, 0, NULL, 0 } + }; + char *host = NULL; + char *busid = NULL; + int opt; + int ret = -1; + + for (;;) { + opt = getopt_long(argc, argv, "r:b:", opts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'r': + host = optarg; + break; + case 'b': + busid = optarg; + break; + default: + goto err_out; + } + } + + if (!host || !busid) + goto err_out; + + ret = attach_device(host, busid); + goto out; + +err_out: + usbip_attach_usage(); +out: + return ret; +} diff --git a/tools/usb/usbip/src/usbip_bind.c b/tools/usb/usbip/src/usbip_bind.c new file mode 100644 index 0000000..fa46141 --- /dev/null +++ b/tools/usb/usbip/src/usbip_bind.c @@ -0,0 +1,214 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#include <libudev.h> + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <getopt.h> + +#include "usbip_common.h" +#include "utils.h" +#include "usbip.h" +#include "sysfs_utils.h" + +enum unbind_status { + UNBIND_ST_OK, + UNBIND_ST_USBIP_HOST, + UNBIND_ST_FAILED +}; + +static const char usbip_bind_usage_string[] = + "usbip bind <args>\n" + " -b, --busid=<busid> Bind " USBIP_HOST_DRV_NAME ".ko to device " + "on <busid>\n"; + +void usbip_bind_usage(void) +{ + printf("usage: %s", usbip_bind_usage_string); +} + +/* call at unbound state */ +static int bind_usbip(char *busid) +{ + char attr_name[] = "bind"; + char bind_attr_path[SYSFS_PATH_MAX]; + int rc = -1; + + snprintf(bind_attr_path, sizeof(bind_attr_path), "%s/%s/%s/%s/%s/%s", + SYSFS_MNT_PATH, SYSFS_BUS_NAME, SYSFS_BUS_TYPE, + SYSFS_DRIVERS_NAME, USBIP_HOST_DRV_NAME, attr_name); + + rc = write_sysfs_attribute(bind_attr_path, busid, strlen(busid)); + if (rc < 0) { + err("error binding device %s to driver: %s", busid, + strerror(errno)); + return -1; + } + + return 0; +} + +/* buggy driver may cause dead lock */ +static int unbind_other(char *busid) +{ + enum unbind_status status = UNBIND_ST_OK; + + char attr_name[] = "unbind"; + char unbind_attr_path[SYSFS_PATH_MAX]; + int rc = -1; + + struct udev *udev; + struct udev_device *dev; + const char *driver; + const char *bDevClass; + + /* Create libudev context. */ + udev = udev_new(); + + /* Get the device. */ + dev = udev_device_new_from_subsystem_sysname(udev, "usb", busid); + if (!dev) { + dbg("unable to find device with bus ID %s", busid); + goto err_close_busid_dev; + } + + /* Check what kind of device it is. */ + bDevClass = udev_device_get_sysattr_value(dev, "bDeviceClass"); + if (!bDevClass) { + dbg("unable to get bDevClass device attribute"); + goto err_close_busid_dev; + } + + if (!strncmp(bDevClass, "09", strlen(bDevClass))) { + dbg("skip unbinding of hub"); + goto err_close_busid_dev; + } + + /* Get the device driver. */ + driver = udev_device_get_driver(dev); + if (!driver) { + /* No driver bound to this device. */ + goto out; + } + + if (!strncmp(USBIP_HOST_DRV_NAME, driver, + strlen(USBIP_HOST_DRV_NAME))) { + /* Already bound to usbip-host. */ + status = UNBIND_ST_USBIP_HOST; + goto out; + } + + /* Unbind device from driver. */ + snprintf(unbind_attr_path, sizeof(unbind_attr_path), "%s/%s/%s/%s/%s/%s", + SYSFS_MNT_PATH, SYSFS_BUS_NAME, SYSFS_BUS_TYPE, + SYSFS_DRIVERS_NAME, driver, attr_name); + + rc = write_sysfs_attribute(unbind_attr_path, busid, strlen(busid)); + if (rc < 0) { + err("error unbinding device %s from driver", busid); + goto err_close_busid_dev; + } + + goto out; + +err_close_busid_dev: + status = UNBIND_ST_FAILED; +out: + udev_device_unref(dev); + udev_unref(udev); + + return status; +} + +static int bind_device(char *busid) +{ + int rc; + struct udev *udev; + struct udev_device *dev; + + /* Check whether the device with this bus ID exists. */ + udev = udev_new(); + dev = udev_device_new_from_subsystem_sysname(udev, "usb", busid); + if (!dev) { + err("device with the specified bus ID does not exist"); + return -1; + } + udev_unref(udev); + + rc = unbind_other(busid); + if (rc == UNBIND_ST_FAILED) { + err("could not unbind driver from device on busid %s", busid); + return -1; + } else if (rc == UNBIND_ST_USBIP_HOST) { + err("device on busid %s is already bound to %s", busid, + USBIP_HOST_DRV_NAME); + return -1; + } + + rc = modify_match_busid(busid, 1); + if (rc < 0) { + err("unable to bind device on %s", busid); + return -1; + } + + rc = bind_usbip(busid); + if (rc < 0) { + err("could not bind device to %s", USBIP_HOST_DRV_NAME); + modify_match_busid(busid, 0); + return -1; + } + + info("bind device on busid %s: complete", busid); + + return 0; +} + +int usbip_bind(int argc, char *argv[]) +{ + static const struct option opts[] = { + { "busid", required_argument, NULL, 'b' }, + { NULL, 0, NULL, 0 } + }; + + int opt; + int ret = -1; + + for (;;) { + opt = getopt_long(argc, argv, "b:", opts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'b': + ret = bind_device(optarg); + goto out; + default: + goto err_out; + } + } + +err_out: + usbip_bind_usage(); +out: + return ret; +} diff --git a/tools/usb/usbip/src/usbip_detach.c b/tools/usb/usbip/src/usbip_detach.c new file mode 100644 index 0000000..05c6d15 --- /dev/null +++ b/tools/usb/usbip/src/usbip_detach.c @@ -0,0 +1,110 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#include <ctype.h> +#include <limits.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <getopt.h> +#include <unistd.h> + +#include "vhci_driver.h" +#include "usbip_common.h" +#include "usbip_network.h" +#include "usbip.h" + +static const char usbip_detach_usage_string[] = + "usbip detach <args>\n" + " -p, --port=<port> " USBIP_VHCI_DRV_NAME + " port the device is on\n"; + +void usbip_detach_usage(void) +{ + printf("usage: %s", usbip_detach_usage_string); +} + +static int detach_port(char *port) +{ + int ret; + uint8_t portnum; + char path[PATH_MAX+1]; + + for (unsigned int i = 0; i < strlen(port); i++) + if (!isdigit(port[i])) { + err("invalid port %s", port); + return -1; + } + + /* check max port */ + + portnum = atoi(port); + + /* remove the port state file */ + + snprintf(path, PATH_MAX, VHCI_STATE_PATH"/port%d", portnum); + + remove(path); + rmdir(VHCI_STATE_PATH); + + ret = usbip_vhci_driver_open(); + if (ret < 0) { + err("open vhci_driver"); + return -1; + } + + ret = usbip_vhci_detach_device(portnum); + if (ret < 0) + return -1; + + usbip_vhci_driver_close(); + + return ret; +} + +int usbip_detach(int argc, char *argv[]) +{ + static const struct option opts[] = { + { "port", required_argument, NULL, 'p' }, + { NULL, 0, NULL, 0 } + }; + int opt; + int ret = -1; + + for (;;) { + opt = getopt_long(argc, argv, "p:", opts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'p': + ret = detach_port(optarg); + goto out; + default: + goto err_out; + } + } + +err_out: + usbip_detach_usage(); +out: + return ret; +} diff --git a/tools/usb/usbip/src/usbip_list.c b/tools/usb/usbip/src/usbip_list.c new file mode 100644 index 0000000..d5ce34a --- /dev/null +++ b/tools/usb/usbip/src/usbip_list.c @@ -0,0 +1,283 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#include <sys/types.h> +#include <libudev.h> + +#include <errno.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <getopt.h> +#include <netdb.h> +#include <unistd.h> + +#include "usbip_common.h" +#include "usbip_network.h" +#include "usbip.h" + +static const char usbip_list_usage_string[] = + "usbip list [-p|--parsable] <args>\n" + " -p, --parsable Parsable list format\n" + " -r, --remote=<host> List the exportable USB devices on <host>\n" + " -l, --local List the local USB devices\n"; + +void usbip_list_usage(void) +{ + printf("usage: %s", usbip_list_usage_string); +} + +static int get_exported_devices(char *host, int sockfd) +{ + char product_name[100]; + char class_name[100]; + struct op_devlist_reply reply; + uint16_t code = OP_REP_DEVLIST; + struct usbip_usb_device udev; + struct usbip_usb_interface uintf; + unsigned int i; + int rc, j; + + rc = usbip_net_send_op_common(sockfd, OP_REQ_DEVLIST, 0); + if (rc < 0) { + dbg("usbip_net_send_op_common failed"); + return -1; + } + + rc = usbip_net_recv_op_common(sockfd, &code); + if (rc < 0) { + dbg("usbip_net_recv_op_common failed"); + return -1; + } + + memset(&reply, 0, sizeof(reply)); + rc = usbip_net_recv(sockfd, &reply, sizeof(reply)); + if (rc < 0) { + dbg("usbip_net_recv_op_devlist failed"); + return -1; + } + PACK_OP_DEVLIST_REPLY(0, &reply); + dbg("exportable devices: %d\n", reply.ndev); + + if (reply.ndev == 0) { + info("no exportable devices found on %s", host); + return 0; + } + + printf("Exportable USB devices\n"); + printf("======================\n"); + printf(" - %s\n", host); + + for (i = 0; i < reply.ndev; i++) { + memset(&udev, 0, sizeof(udev)); + rc = usbip_net_recv(sockfd, &udev, sizeof(udev)); + if (rc < 0) { + dbg("usbip_net_recv failed: usbip_usb_device[%d]", i); + return -1; + } + usbip_net_pack_usb_device(0, &udev); + + usbip_names_get_product(product_name, sizeof(product_name), + udev.idVendor, udev.idProduct); + usbip_names_get_class(class_name, sizeof(class_name), + udev.bDeviceClass, udev.bDeviceSubClass, + udev.bDeviceProtocol); + printf("%11s: %s\n", udev.busid, product_name); + printf("%11s: %s\n", "", udev.path); + printf("%11s: %s\n", "", class_name); + + for (j = 0; j < udev.bNumInterfaces; j++) { + rc = usbip_net_recv(sockfd, &uintf, sizeof(uintf)); + if (rc < 0) { + err("usbip_net_recv failed: usbip_usb_intf[%d]", + j); + + return -1; + } + usbip_net_pack_usb_interface(0, &uintf); + + usbip_names_get_class(class_name, sizeof(class_name), + uintf.bInterfaceClass, + uintf.bInterfaceSubClass, + uintf.bInterfaceProtocol); + printf("%11s: %2d - %s\n", "", j, class_name); + } + + printf("\n"); + } + + return 0; +} + +static int list_exported_devices(char *host) +{ + int rc; + int sockfd; + + sockfd = usbip_net_tcp_connect(host, usbip_port_string); + if (sockfd < 0) { + err("could not connect to %s:%s: %s", host, + usbip_port_string, gai_strerror(sockfd)); + return -1; + } + dbg("connected to %s:%s", host, usbip_port_string); + + rc = get_exported_devices(host, sockfd); + if (rc < 0) { + err("failed to get device list from %s", host); + return -1; + } + + close(sockfd); + + return 0; +} + +static void print_device(const char *busid, const char *vendor, + const char *product, bool parsable) +{ + if (parsable) + printf("busid=%s#usbid=%.4s:%.4s#", busid, vendor, product); + else + printf(" - busid %s (%.4s:%.4s)\n", busid, vendor, product); +} + +static void print_product_name(char *product_name, bool parsable) +{ + if (!parsable) + printf(" %s\n", product_name); +} + +static int list_devices(bool parsable) +{ + struct udev *udev; + struct udev_enumerate *enumerate; + struct udev_list_entry *devices, *dev_list_entry; + struct udev_device *dev; + const char *path; + const char *idVendor; + const char *idProduct; + const char *bConfValue; + const char *bNumIntfs; + const char *busid; + char product_name[128]; + int ret = -1; + + /* Create libudev context. */ + udev = udev_new(); + + /* Create libudev device enumeration. */ + enumerate = udev_enumerate_new(udev); + + /* Take only USB devices that are not hubs and do not have + * the bInterfaceNumber attribute, i.e. are not interfaces. + */ + udev_enumerate_add_match_subsystem(enumerate, "usb"); + udev_enumerate_add_nomatch_sysattr(enumerate, "bDeviceClass", "09"); + udev_enumerate_add_nomatch_sysattr(enumerate, "bInterfaceNumber", NULL); + udev_enumerate_scan_devices(enumerate); + + devices = udev_enumerate_get_list_entry(enumerate); + + /* Show information about each device. */ + udev_list_entry_foreach(dev_list_entry, devices) { + path = udev_list_entry_get_name(dev_list_entry); + dev = udev_device_new_from_syspath(udev, path); + + /* Get device information. */ + idVendor = udev_device_get_sysattr_value(dev, "idVendor"); + idProduct = udev_device_get_sysattr_value(dev, "idProduct"); + bConfValue = udev_device_get_sysattr_value(dev, "bConfigurationValue"); + bNumIntfs = udev_device_get_sysattr_value(dev, "bNumInterfaces"); + busid = udev_device_get_sysname(dev); + if (!idVendor || !idProduct || !bConfValue || !bNumIntfs) { + err("problem getting device attributes: %s", + strerror(errno)); + goto err_out; + } + + /* Get product name. */ + usbip_names_get_product(product_name, sizeof(product_name), + strtol(idVendor, NULL, 16), + strtol(idProduct, NULL, 16)); + + /* Print information. */ + print_device(busid, idVendor, idProduct, parsable); + print_product_name(product_name, parsable); + + printf("\n"); + + udev_device_unref(dev); + } + + ret = 0; + +err_out: + udev_enumerate_unref(enumerate); + udev_unref(udev); + + return ret; +} + +int usbip_list(int argc, char *argv[]) +{ + static const struct option opts[] = { + { "parsable", no_argument, NULL, 'p' }, + { "remote", required_argument, NULL, 'r' }, + { "local", no_argument, NULL, 'l' }, + { NULL, 0, NULL, 0 } + }; + + bool parsable = false; + int opt; + int ret = -1; + + if (usbip_names_init(USBIDS_FILE)) + err("failed to open %s", USBIDS_FILE); + + for (;;) { + opt = getopt_long(argc, argv, "pr:l", opts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'p': + parsable = true; + break; + case 'r': + ret = list_exported_devices(optarg); + goto out; + case 'l': + ret = list_devices(parsable); + goto out; + default: + goto err_out; + } + } + +err_out: + usbip_list_usage(); +out: + usbip_names_free(); + + return ret; +} diff --git a/tools/usb/usbip/src/usbip_network.c b/tools/usb/usbip/src/usbip_network.c new file mode 100644 index 0000000..b4c37e7 --- /dev/null +++ b/tools/usb/usbip/src/usbip_network.c @@ -0,0 +1,303 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#include <sys/socket.h> + +#include <string.h> + +#include <arpa/inet.h> +#include <netdb.h> +#include <netinet/tcp.h> +#include <unistd.h> + +#ifdef HAVE_LIBWRAP +#include <tcpd.h> +#endif + +#include "usbip_common.h" +#include "usbip_network.h" + +int usbip_port = 3240; +char *usbip_port_string = "3240"; + +void usbip_setup_port_number(char *arg) +{ + dbg("parsing port arg '%s'", arg); + char *end; + unsigned long int port = strtoul(arg, &end, 10); + + if (end == arg) { + err("port: could not parse '%s' as a decimal integer", arg); + return; + } + + if (*end != '\0') { + err("port: garbage at end of '%s'", arg); + return; + } + + if (port > UINT16_MAX) { + err("port: %s too high (max=%d)", + arg, UINT16_MAX); + return; + } + + usbip_port = port; + usbip_port_string = arg; + info("using port %d (\"%s\")", usbip_port, usbip_port_string); +} + +void usbip_net_pack_uint32_t(int pack, uint32_t *num) +{ + uint32_t i; + + if (pack) + i = htonl(*num); + else + i = ntohl(*num); + + *num = i; +} + +void usbip_net_pack_uint16_t(int pack, uint16_t *num) +{ + uint16_t i; + + if (pack) + i = htons(*num); + else + i = ntohs(*num); + + *num = i; +} + +void usbip_net_pack_usb_device(int pack, struct usbip_usb_device *udev) +{ + usbip_net_pack_uint32_t(pack, &udev->busnum); + usbip_net_pack_uint32_t(pack, &udev->devnum); + usbip_net_pack_uint32_t(pack, &udev->speed); + + usbip_net_pack_uint16_t(pack, &udev->idVendor); + usbip_net_pack_uint16_t(pack, &udev->idProduct); + usbip_net_pack_uint16_t(pack, &udev->bcdDevice); +} + +void usbip_net_pack_usb_interface(int pack __attribute__((unused)), + struct usbip_usb_interface *udev + __attribute__((unused))) +{ + /* uint8_t members need nothing */ +} + +static ssize_t usbip_net_xmit(int sockfd, void *buff, size_t bufflen, + int sending) +{ + ssize_t nbytes; + ssize_t total = 0; + + if (!bufflen) + return 0; + + do { + if (sending) + nbytes = send(sockfd, buff, bufflen, 0); + else + nbytes = recv(sockfd, buff, bufflen, MSG_WAITALL); + + if (nbytes <= 0) + return -1; + + buff = (void *)((intptr_t) buff + nbytes); + bufflen -= nbytes; + total += nbytes; + + } while (bufflen > 0); + + return total; +} + +ssize_t usbip_net_recv(int sockfd, void *buff, size_t bufflen) +{ + return usbip_net_xmit(sockfd, buff, bufflen, 0); +} + +ssize_t usbip_net_send(int sockfd, void *buff, size_t bufflen) +{ + return usbip_net_xmit(sockfd, buff, bufflen, 1); +} + +int usbip_net_send_op_common(int sockfd, uint32_t code, uint32_t status) +{ + struct op_common op_common; + int rc; + + memset(&op_common, 0, sizeof(op_common)); + + op_common.version = USBIP_VERSION; + op_common.code = code; + op_common.status = status; + + PACK_OP_COMMON(1, &op_common); + + rc = usbip_net_send(sockfd, &op_common, sizeof(op_common)); + if (rc < 0) { + dbg("usbip_net_send failed: %d", rc); + return -1; + } + + return 0; +} + +int usbip_net_recv_op_common(int sockfd, uint16_t *code) +{ + struct op_common op_common; + int rc; + + memset(&op_common, 0, sizeof(op_common)); + + rc = usbip_net_recv(sockfd, &op_common, sizeof(op_common)); + if (rc < 0) { + dbg("usbip_net_recv failed: %d", rc); + goto err; + } + + PACK_OP_COMMON(0, &op_common); + + if (op_common.version != USBIP_VERSION) { + dbg("version mismatch: %d %d", op_common.version, + USBIP_VERSION); + goto err; + } + + switch (*code) { + case OP_UNSPEC: + break; + default: + if (op_common.code != *code) { + dbg("unexpected pdu %#0x for %#0x", op_common.code, + *code); + goto err; + } + } + + if (op_common.status != ST_OK) { + dbg("request failed at peer: %d", op_common.status); + goto err; + } + + *code = op_common.code; + + return 0; +err: + return -1; +} + +int usbip_net_set_reuseaddr(int sockfd) +{ + const int val = 1; + int ret; + + ret = setsockopt(sockfd, SOL_SOCKET, SO_REUSEADDR, &val, sizeof(val)); + if (ret < 0) + dbg("setsockopt: SO_REUSEADDR"); + + return ret; +} + +int usbip_net_set_nodelay(int sockfd) +{ + const int val = 1; + int ret; + + ret = setsockopt(sockfd, IPPROTO_TCP, TCP_NODELAY, &val, sizeof(val)); + if (ret < 0) + dbg("setsockopt: TCP_NODELAY"); + + return ret; +} + +int usbip_net_set_keepalive(int sockfd) +{ + const int val = 1; + int ret; + + ret = setsockopt(sockfd, SOL_SOCKET, SO_KEEPALIVE, &val, sizeof(val)); + if (ret < 0) + dbg("setsockopt: SO_KEEPALIVE"); + + return ret; +} + +int usbip_net_set_v6only(int sockfd) +{ + const int val = 1; + int ret; + + ret = setsockopt(sockfd, IPPROTO_IPV6, IPV6_V6ONLY, &val, sizeof(val)); + if (ret < 0) + dbg("setsockopt: IPV6_V6ONLY"); + + return ret; +} + +/* + * IPv6 Ready + */ +int usbip_net_tcp_connect(char *hostname, char *service) +{ + struct addrinfo hints, *res, *rp; + int sockfd; + int ret; + + memset(&hints, 0, sizeof(hints)); + hints.ai_family = AF_UNSPEC; + hints.ai_socktype = SOCK_STREAM; + + /* get all possible addresses */ + ret = getaddrinfo(hostname, service, &hints, &res); + if (ret < 0) { + dbg("getaddrinfo: %s service %s: %s", hostname, service, + gai_strerror(ret)); + return ret; + } + + /* try the addresses */ + for (rp = res; rp; rp = rp->ai_next) { + sockfd = socket(rp->ai_family, rp->ai_socktype, + rp->ai_protocol); + if (sockfd < 0) + continue; + + /* should set TCP_NODELAY for usbip */ + usbip_net_set_nodelay(sockfd); + /* TODO: write code for heartbeat */ + usbip_net_set_keepalive(sockfd); + + if (connect(sockfd, rp->ai_addr, rp->ai_addrlen) == 0) + break; + + close(sockfd); + } + + freeaddrinfo(res); + + if (!rp) + return EAI_SYSTEM; + + return sockfd; +} diff --git a/tools/usb/usbip/src/usbip_network.h b/tools/usb/usbip/src/usbip_network.h new file mode 100644 index 0000000..c1e875c --- /dev/null +++ b/tools/usb/usbip/src/usbip_network.h @@ -0,0 +1,185 @@ +/* + * Copyright (C) 2005-2007 Takahiro Hirofuchi + */ + +#ifndef __USBIP_NETWORK_H +#define __USBIP_NETWORK_H + +#ifdef HAVE_CONFIG_H +#include "../config.h" +#endif + +#include <sys/types.h> + +#include <stdint.h> + +extern int usbip_port; +extern char *usbip_port_string; +void usbip_setup_port_number(char *arg); + +/* ---------------------------------------------------------------------- */ +/* Common header for all the kinds of PDUs. */ +struct op_common { + uint16_t version; + +#define OP_REQUEST (0x80 << 8) +#define OP_REPLY (0x00 << 8) + uint16_t code; + + /* add more error code */ +#define ST_OK 0x00 +#define ST_NA 0x01 + uint32_t status; /* op_code status (for reply) */ + +} __attribute__((packed)); + +#define PACK_OP_COMMON(pack, op_common) do {\ + usbip_net_pack_uint16_t(pack, &(op_common)->version);\ + usbip_net_pack_uint16_t(pack, &(op_common)->code);\ + usbip_net_pack_uint32_t(pack, &(op_common)->status);\ +} while (0) + +/* ---------------------------------------------------------------------- */ +/* Dummy Code */ +#define OP_UNSPEC 0x00 +#define OP_REQ_UNSPEC OP_UNSPEC +#define OP_REP_UNSPEC OP_UNSPEC + +/* ---------------------------------------------------------------------- */ +/* Retrieve USB device information. (still not used) */ +#define OP_DEVINFO 0x02 +#define OP_REQ_DEVINFO (OP_REQUEST | OP_DEVINFO) +#define OP_REP_DEVINFO (OP_REPLY | OP_DEVINFO) + +struct op_devinfo_request { + char busid[SYSFS_BUS_ID_SIZE]; +} __attribute__((packed)); + +struct op_devinfo_reply { + struct usbip_usb_device udev; + struct usbip_usb_interface uinf[]; +} __attribute__((packed)); + +/* ---------------------------------------------------------------------- */ +/* Import a remote USB device. */ +#define OP_IMPORT 0x03 +#define OP_REQ_IMPORT (OP_REQUEST | OP_IMPORT) +#define OP_REP_IMPORT (OP_REPLY | OP_IMPORT) + +struct op_import_request { + char busid[SYSFS_BUS_ID_SIZE]; +} __attribute__((packed)); + +struct op_import_reply { + struct usbip_usb_device udev; +// struct usbip_usb_interface uinf[]; +} __attribute__((packed)); + +#define PACK_OP_IMPORT_REQUEST(pack, request) do {\ +} while (0) + +#define PACK_OP_IMPORT_REPLY(pack, reply) do {\ + usbip_net_pack_usb_device(pack, &(reply)->udev);\ +} while (0) + +/* ---------------------------------------------------------------------- */ +/* Export a USB device to a remote host. */ +#define OP_EXPORT 0x06 +#define OP_REQ_EXPORT (OP_REQUEST | OP_EXPORT) +#define OP_REP_EXPORT (OP_REPLY | OP_EXPORT) + +struct op_export_request { + struct usbip_usb_device udev; +} __attribute__((packed)); + +struct op_export_reply { + int returncode; +} __attribute__((packed)); + + +#define PACK_OP_EXPORT_REQUEST(pack, request) do {\ + usbip_net_pack_usb_device(pack, &(request)->udev);\ +} while (0) + +#define PACK_OP_EXPORT_REPLY(pack, reply) do {\ +} while (0) + +/* ---------------------------------------------------------------------- */ +/* un-Export a USB device from a remote host. */ +#define OP_UNEXPORT 0x07 +#define OP_REQ_UNEXPORT (OP_REQUEST | OP_UNEXPORT) +#define OP_REP_UNEXPORT (OP_REPLY | OP_UNEXPORT) + +struct op_unexport_request { + struct usbip_usb_device udev; +} __attribute__((packed)); + +struct op_unexport_reply { + int returncode; +} __attribute__((packed)); + +#define PACK_OP_UNEXPORT_REQUEST(pack, request) do {\ + usbip_net_pack_usb_device(pack, &(request)->udev);\ +} while (0) + +#define PACK_OP_UNEXPORT_REPLY(pack, reply) do {\ +} while (0) + +/* ---------------------------------------------------------------------- */ +/* Negotiate IPSec encryption key. (still not used) */ +#define OP_CRYPKEY 0x04 +#define OP_REQ_CRYPKEY (OP_REQUEST | OP_CRYPKEY) +#define OP_REP_CRYPKEY (OP_REPLY | OP_CRYPKEY) + +struct op_crypkey_request { + /* 128bit key */ + uint32_t key[4]; +} __attribute__((packed)); + +struct op_crypkey_reply { + uint32_t __reserved; +} __attribute__((packed)); + + +/* ---------------------------------------------------------------------- */ +/* Retrieve the list of exported USB devices. */ +#define OP_DEVLIST 0x05 +#define OP_REQ_DEVLIST (OP_REQUEST | OP_DEVLIST) +#define OP_REP_DEVLIST (OP_REPLY | OP_DEVLIST) + +struct op_devlist_request { +} __attribute__((packed)); + +struct op_devlist_reply { + uint32_t ndev; + /* followed by reply_extra[] */ +} __attribute__((packed)); + +struct op_devlist_reply_extra { + struct usbip_usb_device udev; + struct usbip_usb_interface uinf[]; +} __attribute__((packed)); + +#define PACK_OP_DEVLIST_REQUEST(pack, request) do {\ +} while (0) + +#define PACK_OP_DEVLIST_REPLY(pack, reply) do {\ + usbip_net_pack_uint32_t(pack, &(reply)->ndev);\ +} while (0) + +void usbip_net_pack_uint32_t(int pack, uint32_t *num); +void usbip_net_pack_uint16_t(int pack, uint16_t *num); +void usbip_net_pack_usb_device(int pack, struct usbip_usb_device *udev); +void usbip_net_pack_usb_interface(int pack, struct usbip_usb_interface *uinf); + +ssize_t usbip_net_recv(int sockfd, void *buff, size_t bufflen); +ssize_t usbip_net_send(int sockfd, void *buff, size_t bufflen); +int usbip_net_send_op_common(int sockfd, uint32_t code, uint32_t status); +int usbip_net_recv_op_common(int sockfd, uint16_t *code); +int usbip_net_set_reuseaddr(int sockfd); +int usbip_net_set_nodelay(int sockfd); +int usbip_net_set_keepalive(int sockfd); +int usbip_net_set_v6only(int sockfd); +int usbip_net_tcp_connect(char *hostname, char *port); + +#endif /* __USBIP_NETWORK_H */ diff --git a/tools/usb/usbip/src/usbip_port.c b/tools/usb/usbip/src/usbip_port.c new file mode 100644 index 0000000..a2e884fd --- /dev/null +++ b/tools/usb/usbip/src/usbip_port.c @@ -0,0 +1,57 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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 "vhci_driver.h" +#include "usbip_common.h" + +static int list_imported_devices(void) +{ + int i; + struct usbip_imported_device *idev; + int ret; + + ret = usbip_vhci_driver_open(); + if (ret < 0) { + err("open vhci_driver"); + return -1; + } + + printf("Imported USB devices\n"); + printf("====================\n"); + + for (i = 0; i < vhci_driver->nports; i++) { + idev = &vhci_driver->idev[i]; + + if (usbip_vhci_imported_device_dump(idev) < 0) + ret = -1; + } + + usbip_vhci_driver_close(); + + return ret; + +} + +int usbip_port_show(__attribute__((unused)) int argc, + __attribute__((unused)) char *argv[]) +{ + int ret; + + ret = list_imported_devices(); + if (ret < 0) + err("list imported devices"); + + return ret; +} diff --git a/tools/usb/usbip/src/usbip_unbind.c b/tools/usb/usbip/src/usbip_unbind.c new file mode 100644 index 0000000..a4a496c --- /dev/null +++ b/tools/usb/usbip/src/usbip_unbind.c @@ -0,0 +1,141 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#include <libudev.h> + +#include <errno.h> +#include <stdio.h> +#include <string.h> + +#include <getopt.h> + +#include "usbip_common.h" +#include "utils.h" +#include "usbip.h" +#include "sysfs_utils.h" + +static const char usbip_unbind_usage_string[] = + "usbip unbind <args>\n" + " -b, --busid=<busid> Unbind " USBIP_HOST_DRV_NAME ".ko from " + "device on <busid>\n"; + +void usbip_unbind_usage(void) +{ + printf("usage: %s", usbip_unbind_usage_string); +} + +static int unbind_device(char *busid) +{ + char bus_type[] = "usb"; + int rc, ret = -1; + + char unbind_attr_name[] = "unbind"; + char unbind_attr_path[SYSFS_PATH_MAX]; + char rebind_attr_name[] = "rebind"; + char rebind_attr_path[SYSFS_PATH_MAX]; + + struct udev *udev; + struct udev_device *dev; + const char *driver; + + /* Create libudev context. */ + udev = udev_new(); + + /* Check whether the device with this bus ID exists. */ + dev = udev_device_new_from_subsystem_sysname(udev, "usb", busid); + if (!dev) { + err("device with the specified bus ID does not exist"); + goto err_close_udev; + } + + /* Check whether the device is using usbip-host driver. */ + driver = udev_device_get_driver(dev); + if (!driver || strcmp(driver, "usbip-host")) { + err("device is not bound to usbip-host driver"); + goto err_close_udev; + } + + /* Unbind device from driver. */ + snprintf(unbind_attr_path, sizeof(unbind_attr_path), "%s/%s/%s/%s/%s/%s", + SYSFS_MNT_PATH, SYSFS_BUS_NAME, bus_type, SYSFS_DRIVERS_NAME, + USBIP_HOST_DRV_NAME, unbind_attr_name); + + rc = write_sysfs_attribute(unbind_attr_path, busid, strlen(busid)); + if (rc < 0) { + err("error unbinding device %s from driver", busid); + goto err_close_udev; + } + + /* Notify driver of unbind. */ + rc = modify_match_busid(busid, 0); + if (rc < 0) { + err("unable to unbind device on %s", busid); + goto err_close_udev; + } + + /* Trigger new probing. */ + snprintf(rebind_attr_path, sizeof(unbind_attr_path), "%s/%s/%s/%s/%s/%s", + SYSFS_MNT_PATH, SYSFS_BUS_NAME, bus_type, SYSFS_DRIVERS_NAME, + USBIP_HOST_DRV_NAME, rebind_attr_name); + + rc = write_sysfs_attribute(rebind_attr_path, busid, strlen(busid)); + if (rc < 0) { + err("error rebinding"); + goto err_close_udev; + } + + ret = 0; + info("unbind device on busid %s: complete", busid); + +err_close_udev: + udev_device_unref(dev); + udev_unref(udev); + + return ret; +} + +int usbip_unbind(int argc, char *argv[]) +{ + static const struct option opts[] = { + { "busid", required_argument, NULL, 'b' }, + { NULL, 0, NULL, 0 } + }; + + int opt; + int ret = -1; + + for (;;) { + opt = getopt_long(argc, argv, "b:", opts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'b': + ret = unbind_device(optarg); + goto out; + default: + goto err_out; + } + } + +err_out: + usbip_unbind_usage(); +out: + return ret; +} diff --git a/tools/usb/usbip/src/usbipd.c b/tools/usb/usbip/src/usbipd.c new file mode 100644 index 0000000..2a7cd2b --- /dev/null +++ b/tools/usb/usbip/src/usbipd.c @@ -0,0 +1,677 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#ifdef HAVE_CONFIG_H +#include "../config.h" +#endif + +#define _GNU_SOURCE +#include <errno.h> +#include <unistd.h> +#include <netdb.h> +#include <string.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <arpa/inet.h> +#include <sys/socket.h> +#include <netinet/in.h> + +#ifdef HAVE_LIBWRAP +#include <tcpd.h> +#endif + +#include <getopt.h> +#include <signal.h> +#include <poll.h> + +#include "usbip_host_driver.h" +#include "usbip_common.h" +#include "usbip_network.h" +#include "list.h" + +#undef PROGNAME +#define PROGNAME "usbipd" +#define MAXSOCKFD 20 + +#define MAIN_LOOP_TIMEOUT 10 + +#define DEFAULT_PID_FILE "/var/run/" PROGNAME ".pid" + +static const char usbip_version_string[] = PACKAGE_STRING; + +static const char usbipd_help_string[] = + "usage: usbipd [options]\n" + "\n" + " -4, --ipv4\n" + " Bind to IPv4. Default is both.\n" + "\n" + " -6, --ipv6\n" + " Bind to IPv6. Default is both.\n" + "\n" + " -D, --daemon\n" + " Run as a daemon process.\n" + "\n" + " -d, --debug\n" + " Print debugging information.\n" + "\n" + " -PFILE, --pid FILE\n" + " Write process id to FILE.\n" + " If no FILE specified, use " DEFAULT_PID_FILE "\n" + "\n" + " -tPORT, --tcp-port PORT\n" + " Listen on TCP/IP port PORT.\n" + "\n" + " -h, --help\n" + " Print this help.\n" + "\n" + " -v, --version\n" + " Show version.\n"; + +static void usbipd_help(void) +{ + printf("%s\n", usbipd_help_string); +} + +static int recv_request_import(int sockfd) +{ + struct op_import_request req; + struct usbip_exported_device *edev; + struct usbip_usb_device pdu_udev; + struct list_head *i; + int found = 0; + int error = 0; + int rc; + + memset(&req, 0, sizeof(req)); + + rc = usbip_net_recv(sockfd, &req, sizeof(req)); + if (rc < 0) { + dbg("usbip_net_recv failed: import request"); + return -1; + } + PACK_OP_IMPORT_REQUEST(0, &req); + + list_for_each(i, &host_driver->edev_list) { + edev = list_entry(i, struct usbip_exported_device, node); + if (!strncmp(req.busid, edev->udev.busid, SYSFS_BUS_ID_SIZE)) { + info("found requested device: %s", req.busid); + found = 1; + break; + } + } + + if (found) { + /* should set TCP_NODELAY for usbip */ + usbip_net_set_nodelay(sockfd); + + /* export device needs a TCP/IP socket descriptor */ + rc = usbip_host_export_device(edev, sockfd); + if (rc < 0) + error = 1; + } else { + info("requested device not found: %s", req.busid); + error = 1; + } + + rc = usbip_net_send_op_common(sockfd, OP_REP_IMPORT, + (!error ? ST_OK : ST_NA)); + if (rc < 0) { + dbg("usbip_net_send_op_common failed: %#0x", OP_REP_IMPORT); + return -1; + } + + if (error) { + dbg("import request busid %s: failed", req.busid); + return -1; + } + + memcpy(&pdu_udev, &edev->udev, sizeof(pdu_udev)); + usbip_net_pack_usb_device(1, &pdu_udev); + + rc = usbip_net_send(sockfd, &pdu_udev, sizeof(pdu_udev)); + if (rc < 0) { + dbg("usbip_net_send failed: devinfo"); + return -1; + } + + dbg("import request busid %s: complete", req.busid); + + return 0; +} + +static int send_reply_devlist(int connfd) +{ + struct usbip_exported_device *edev; + struct usbip_usb_device pdu_udev; + struct usbip_usb_interface pdu_uinf; + struct op_devlist_reply reply; + struct list_head *j; + int rc, i; + + reply.ndev = 0; + /* number of exported devices */ + list_for_each(j, &host_driver->edev_list) { + reply.ndev += 1; + } + info("exportable devices: %d", reply.ndev); + + rc = usbip_net_send_op_common(connfd, OP_REP_DEVLIST, ST_OK); + if (rc < 0) { + dbg("usbip_net_send_op_common failed: %#0x", OP_REP_DEVLIST); + return -1; + } + PACK_OP_DEVLIST_REPLY(1, &reply); + + rc = usbip_net_send(connfd, &reply, sizeof(reply)); + if (rc < 0) { + dbg("usbip_net_send failed: %#0x", OP_REP_DEVLIST); + return -1; + } + + list_for_each(j, &host_driver->edev_list) { + edev = list_entry(j, struct usbip_exported_device, node); + dump_usb_device(&edev->udev); + memcpy(&pdu_udev, &edev->udev, sizeof(pdu_udev)); + usbip_net_pack_usb_device(1, &pdu_udev); + + rc = usbip_net_send(connfd, &pdu_udev, sizeof(pdu_udev)); + if (rc < 0) { + dbg("usbip_net_send failed: pdu_udev"); + return -1; + } + + for (i = 0; i < edev->udev.bNumInterfaces; i++) { + dump_usb_interface(&edev->uinf[i]); + memcpy(&pdu_uinf, &edev->uinf[i], sizeof(pdu_uinf)); + usbip_net_pack_usb_interface(1, &pdu_uinf); + + rc = usbip_net_send(connfd, &pdu_uinf, + sizeof(pdu_uinf)); + if (rc < 0) { + err("usbip_net_send failed: pdu_uinf"); + return -1; + } + } + } + + return 0; +} + +static int recv_request_devlist(int connfd) +{ + struct op_devlist_request req; + int rc; + + memset(&req, 0, sizeof(req)); + + rc = usbip_net_recv(connfd, &req, sizeof(req)); + if (rc < 0) { + dbg("usbip_net_recv failed: devlist request"); + return -1; + } + + rc = send_reply_devlist(connfd); + if (rc < 0) { + dbg("send_reply_devlist failed"); + return -1; + } + + return 0; +} + +static int recv_pdu(int connfd) +{ + uint16_t code = OP_UNSPEC; + int ret; + + ret = usbip_net_recv_op_common(connfd, &code); + if (ret < 0) { + dbg("could not receive opcode: %#0x", code); + return -1; + } + + ret = usbip_host_refresh_device_list(); + if (ret < 0) { + dbg("could not refresh device list: %d", ret); + return -1; + } + + info("received request: %#0x(%d)", code, connfd); + switch (code) { + case OP_REQ_DEVLIST: + ret = recv_request_devlist(connfd); + break; + case OP_REQ_IMPORT: + ret = recv_request_import(connfd); + break; + case OP_REQ_DEVINFO: + case OP_REQ_CRYPKEY: + default: + err("received an unknown opcode: %#0x", code); + ret = -1; + } + + if (ret == 0) + info("request %#0x(%d): complete", code, connfd); + else + info("request %#0x(%d): failed", code, connfd); + + return ret; +} + +#ifdef HAVE_LIBWRAP +static int tcpd_auth(int connfd) +{ + struct request_info request; + int rc; + + request_init(&request, RQ_DAEMON, PROGNAME, RQ_FILE, connfd, 0); + fromhost(&request); + rc = hosts_access(&request); + if (rc == 0) + return -1; + + return 0; +} +#endif + +static int do_accept(int listenfd) +{ + int connfd; + struct sockaddr_storage ss; + socklen_t len = sizeof(ss); + char host[NI_MAXHOST], port[NI_MAXSERV]; + int rc; + + memset(&ss, 0, sizeof(ss)); + + connfd = accept(listenfd, (struct sockaddr *)&ss, &len); + if (connfd < 0) { + err("failed to accept connection"); + return -1; + } + + rc = getnameinfo((struct sockaddr *)&ss, len, host, sizeof(host), + port, sizeof(port), NI_NUMERICHOST | NI_NUMERICSERV); + if (rc) + err("getnameinfo: %s", gai_strerror(rc)); + +#ifdef HAVE_LIBWRAP + rc = tcpd_auth(connfd); + if (rc < 0) { + info("denied access from %s", host); + close(connfd); + return -1; + } +#endif + info("connection from %s:%s", host, port); + + return connfd; +} + +int process_request(int listenfd) +{ + pid_t childpid; + int connfd; + + connfd = do_accept(listenfd); + if (connfd < 0) + return -1; + childpid = fork(); + if (childpid == 0) { + close(listenfd); + recv_pdu(connfd); + exit(0); + } + close(connfd); + return 0; +} + +static void addrinfo_to_text(struct addrinfo *ai, char buf[], + const size_t buf_size) +{ + char hbuf[NI_MAXHOST]; + char sbuf[NI_MAXSERV]; + int rc; + + buf[0] = '\0'; + + rc = getnameinfo(ai->ai_addr, ai->ai_addrlen, hbuf, sizeof(hbuf), + sbuf, sizeof(sbuf), NI_NUMERICHOST | NI_NUMERICSERV); + if (rc) + err("getnameinfo: %s", gai_strerror(rc)); + + snprintf(buf, buf_size, "%s:%s", hbuf, sbuf); +} + +static int listen_all_addrinfo(struct addrinfo *ai_head, int sockfdlist[], + int maxsockfd) +{ + struct addrinfo *ai; + int ret, nsockfd = 0; + const size_t ai_buf_size = NI_MAXHOST + NI_MAXSERV + 2; + char ai_buf[ai_buf_size]; + + for (ai = ai_head; ai && nsockfd < maxsockfd; ai = ai->ai_next) { + int sock; + + addrinfo_to_text(ai, ai_buf, ai_buf_size); + dbg("opening %s", ai_buf); + sock = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol); + if (sock < 0) { + err("socket: %s: %d (%s)", + ai_buf, errno, strerror(errno)); + continue; + } + + usbip_net_set_reuseaddr(sock); + usbip_net_set_nodelay(sock); + /* We use seperate sockets for IPv4 and IPv6 + * (see do_standalone_mode()) */ + usbip_net_set_v6only(sock); + + if (sock >= FD_SETSIZE) { + err("FD_SETSIZE: %s: sock=%d, max=%d", + ai_buf, sock, FD_SETSIZE); + close(sock); + continue; + } + + ret = bind(sock, ai->ai_addr, ai->ai_addrlen); + if (ret < 0) { + err("bind: %s: %d (%s)", + ai_buf, errno, strerror(errno)); + close(sock); + continue; + } + + ret = listen(sock, SOMAXCONN); + if (ret < 0) { + err("listen: %s: %d (%s)", + ai_buf, errno, strerror(errno)); + close(sock); + continue; + } + + info("listening on %s", ai_buf); + sockfdlist[nsockfd++] = sock; + } + + return nsockfd; +} + +static struct addrinfo *do_getaddrinfo(char *host, int ai_family) +{ + struct addrinfo hints, *ai_head; + int rc; + + memset(&hints, 0, sizeof(hints)); + hints.ai_family = ai_family; + hints.ai_socktype = SOCK_STREAM; + hints.ai_flags = AI_PASSIVE; + + rc = getaddrinfo(host, usbip_port_string, &hints, &ai_head); + if (rc) { + err("failed to get a network address %s: %s", usbip_port_string, + gai_strerror(rc)); + return NULL; + } + + return ai_head; +} + +static void signal_handler(int i) +{ + dbg("received '%s' signal", strsignal(i)); +} + +static void set_signal(void) +{ + struct sigaction act; + + memset(&act, 0, sizeof(act)); + act.sa_handler = signal_handler; + sigemptyset(&act.sa_mask); + sigaction(SIGTERM, &act, NULL); + sigaction(SIGINT, &act, NULL); + act.sa_handler = SIG_IGN; + sigaction(SIGCLD, &act, NULL); +} + +static const char *pid_file; + +static void write_pid_file(void) +{ + if (pid_file) { + dbg("creating pid file %s", pid_file); + FILE *fp; + + fp = fopen(pid_file, "w"); + if (!fp) { + err("pid_file: %s: %d (%s)", + pid_file, errno, strerror(errno)); + return; + } + fprintf(fp, "%d\n", getpid()); + fclose(fp); + } +} + +static void remove_pid_file(void) +{ + if (pid_file) { + dbg("removing pid file %s", pid_file); + unlink(pid_file); + } +} + +static int do_standalone_mode(int daemonize, int ipv4, int ipv6) +{ + struct addrinfo *ai_head; + int sockfdlist[MAXSOCKFD]; + int nsockfd, family; + int i, terminate; + struct pollfd *fds; + struct timespec timeout; + sigset_t sigmask; + + if (usbip_host_driver_open()) { + err("please load " USBIP_CORE_MOD_NAME ".ko and " + USBIP_HOST_DRV_NAME ".ko!"); + return -1; + } + + if (daemonize) { + if (daemon(0, 0) < 0) { + err("daemonizing failed: %s", strerror(errno)); + usbip_host_driver_close(); + return -1; + } + umask(0); + usbip_use_syslog = 1; + } + set_signal(); + write_pid_file(); + + info("starting " PROGNAME " (%s)", usbip_version_string); + + /* + * To suppress warnings on systems with bindv6only disabled + * (default), we use seperate sockets for IPv6 and IPv4 and set + * IPV6_V6ONLY on the IPv6 sockets. + */ + if (ipv4 && ipv6) + family = AF_UNSPEC; + else if (ipv4) + family = AF_INET; + else + family = AF_INET6; + + ai_head = do_getaddrinfo(NULL, family); + if (!ai_head) { + usbip_host_driver_close(); + return -1; + } + nsockfd = listen_all_addrinfo(ai_head, sockfdlist, + sizeof(sockfdlist) / sizeof(*sockfdlist)); + freeaddrinfo(ai_head); + if (nsockfd <= 0) { + err("failed to open a listening socket"); + usbip_host_driver_close(); + return -1; + } + + dbg("listening on %d address%s", nsockfd, (nsockfd == 1) ? "" : "es"); + + fds = calloc(nsockfd, sizeof(struct pollfd)); + for (i = 0; i < nsockfd; i++) { + fds[i].fd = sockfdlist[i]; + fds[i].events = POLLIN; + } + timeout.tv_sec = MAIN_LOOP_TIMEOUT; + timeout.tv_nsec = 0; + + sigfillset(&sigmask); + sigdelset(&sigmask, SIGTERM); + sigdelset(&sigmask, SIGINT); + + terminate = 0; + while (!terminate) { + int r; + + r = ppoll(fds, nsockfd, &timeout, &sigmask); + if (r < 0) { + dbg("%s", strerror(errno)); + terminate = 1; + } else if (r) { + for (i = 0; i < nsockfd; i++) { + if (fds[i].revents & POLLIN) { + dbg("read event on fd[%d]=%d", + i, sockfdlist[i]); + process_request(sockfdlist[i]); + } + } + } else { + dbg("heartbeat timeout on ppoll()"); + } + } + + info("shutting down " PROGNAME); + free(fds); + usbip_host_driver_close(); + + return 0; +} + +int main(int argc, char *argv[]) +{ + static const struct option longopts[] = { + { "ipv4", no_argument, NULL, '4' }, + { "ipv6", no_argument, NULL, '6' }, + { "daemon", no_argument, NULL, 'D' }, + { "daemon", no_argument, NULL, 'D' }, + { "debug", no_argument, NULL, 'd' }, + { "pid", optional_argument, NULL, 'P' }, + { "tcp-port", required_argument, NULL, 't' }, + { "help", no_argument, NULL, 'h' }, + { "version", no_argument, NULL, 'v' }, + { NULL, 0, NULL, 0 } + }; + + enum { + cmd_standalone_mode = 1, + cmd_help, + cmd_version + } cmd; + + int daemonize = 0; + int ipv4 = 0, ipv6 = 0; + int opt, rc = -1; + + pid_file = NULL; + + usbip_use_stderr = 1; + usbip_use_syslog = 0; + + if (geteuid() != 0) + err("not running as root?"); + + cmd = cmd_standalone_mode; + for (;;) { + opt = getopt_long(argc, argv, "46DdP::t:hv", longopts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case '4': + ipv4 = 1; + break; + case '6': + ipv6 = 1; + break; + case 'D': + daemonize = 1; + break; + case 'd': + usbip_use_debug = 1; + break; + case 'h': + cmd = cmd_help; + break; + case 'P': + pid_file = optarg ? optarg : DEFAULT_PID_FILE; + break; + case 't': + usbip_setup_port_number(optarg); + break; + case 'v': + cmd = cmd_version; + break; + case '?': + usbipd_help(); + default: + goto err_out; + } + } + + if (!ipv4 && !ipv6) + ipv4 = ipv6 = 1; + + switch (cmd) { + case cmd_standalone_mode: + rc = do_standalone_mode(daemonize, ipv4, ipv6); + remove_pid_file(); + break; + case cmd_version: + printf(PROGNAME " (%s)\n", usbip_version_string); + rc = 0; + break; + case cmd_help: + usbipd_help(); + rc = 0; + break; + default: + usbipd_help(); + goto err_out; + } + +err_out: + return (rc > -1 ? EXIT_SUCCESS : EXIT_FAILURE); +} diff --git a/tools/usb/usbip/src/utils.c b/tools/usb/usbip/src/utils.c new file mode 100644 index 0000000..2b3d6d2 --- /dev/null +++ b/tools/usb/usbip/src/utils.c @@ -0,0 +1,52 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#include <errno.h> +#include <stdio.h> +#include <string.h> + +#include "usbip_common.h" +#include "utils.h" +#include "sysfs_utils.h" + +int modify_match_busid(char *busid, int add) +{ + char attr_name[] = "match_busid"; + char command[SYSFS_BUS_ID_SIZE + 4]; + char match_busid_attr_path[SYSFS_PATH_MAX]; + int rc; + + snprintf(match_busid_attr_path, sizeof(match_busid_attr_path), + "%s/%s/%s/%s/%s/%s", SYSFS_MNT_PATH, SYSFS_BUS_NAME, + SYSFS_BUS_TYPE, SYSFS_DRIVERS_NAME, USBIP_HOST_DRV_NAME, + attr_name); + + if (add) + snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", busid); + else + snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", busid); + + rc = write_sysfs_attribute(match_busid_attr_path, command, + sizeof(command)); + if (rc < 0) { + dbg("failed to write match_busid: %s", strerror(errno)); + return -1; + } + + return 0; +} diff --git a/tools/usb/usbip/src/utils.h b/tools/usb/usbip/src/utils.h new file mode 100644 index 0000000..5916fd3 --- /dev/null +++ b/tools/usb/usbip/src/utils.h @@ -0,0 +1,25 @@ +/* + * Copyright (C) 2011 matt mooney <mfm@muteddisk.com> + * 2005-2007 Takahiro Hirofuchi + * + * 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, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __UTILS_H +#define __UTILS_H + +int modify_match_busid(char *busid, int add); + +#endif /* __UTILS_H */ + diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile index 9325f46..505ad51 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 5a2d1f0..a3e0701 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 0000000..9de9e6a --- /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 5049967..806d683 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 0000000..e7a1096 --- /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 00ea679..e044589 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 14a4f4c..5f94f51 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 3d907da..ac884b6 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 c4d6d2e..264fbc2 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -132,6 +132,7 @@ static const char * const page_flag_names[] = { [KPF_NOPAGE] = "n:nopage", [KPF_KSM] = "x:ksm", [KPF_THP] = "t:thp", + [KPF_BALLOON] = "o:balloon", [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 0000000..77147b4 --- /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; +} |
