linux/tools/perf/trace, branch v5.4

perf trace beauty ioctl: Fix off-by-one error in cmd->string table

2019-08-26T14:58:29Z

While tracing a program that calls isatty(3), I noticed that strace reported TCGETS for the request argument of the underlying ioctl(2) syscall while perf trace reported TCSETS. strace is corrrect. The bug in perf was due to the tty ioctl beauty table starting at 0x5400 rather than 0x5401. Committer testing: Using augmented_raw_syscalls.o and settings to make 'perf trace' use strace formatting, i.e. with this in ~/.perfconfig # cat ~/.perfconfig [trace] add_events = /home/acme/git/linux/tools/perf/examples/bpf/augmented_raw_syscalls.c show_zeros = yes show_duration = no no_inherit = yes show_timestamp = no show_arg_names = no args_alignment = 40 show_prefix = yes # strace -e ioctl stty > /dev/null ioctl(0, TCGETS, {B38400 opost isig icanon echo ...}) = 0 ioctl(1, TIOCGWINSZ, 0x7fff8a9b0860) = -1 ENOTTY (Inappropriate ioctl for device) ioctl(1, TCGETS, 0x7fff8a9b0540) = -1 ENOTTY (Inappropriate ioctl for device) +++ exited with 0 +++ # Before: # perf trace -e ioctl stty > /dev/null ioctl(0, TCSETS, 0x7fff2cf79f20) = 0 ioctl(1, TIOCSWINSZ, 0x7fff2cf79f40) = -1 ENOTTY (Inappropriate ioctl for device) ioctl(1, TCSETS, 0x7fff2cf79c20) = -1 ENOTTY (Inappropriate ioctl for device) # After: # perf trace -e ioctl stty > /dev/null ioctl(0, TCGETS, 0x7ffed0763920) = 0 ioctl(1, TIOCGWINSZ, 0x7ffed0763940) = -1 ENOTTY (Inappropriate ioctl for device) ioctl(1, TCGETS, 0x7ffed0763620) = -1 ENOTTY (Inappropriate ioctl for device) # Signed-off-by: Benjamin Peterson Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Fixes: 1cc47f2d46206d67285aea0ca7e8450af571da13 ("perf trace beauty ioctl: Improve 'cmd' beautifier") Link: http://lkml.kernel.org/r/20190823033625.18814-1-benjamin@python.org Signed-off-by: Arnaldo Carvalho de Melo

tools perf beauty: Fix usbdevfs_ioctl table generator to handle _IOC()

2019-07-29T12:03:42Z

In addition to _IOW() and _IOR(), to handle this case: #define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len) That will happen in the next sync of this header file. Cc: Adrian Hunter Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-3br5e4t64e4lp0goo84che3s@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf trace: Beautify 'sync_file_range' arguments

2019-05-28T21:37:43Z

perf beauty: Add generator for sync_file_range's 'flags' arg values

2019-05-28T21:37:43Z

$ tools/perf/trace/beauty/sync_file_range.sh static const char *sync_file_range_flags[] = { [ilog2(1) + 1] = "WAIT_BEFORE", [ilog2(2) + 1] = "WRITE", [ilog2(4) + 1] = "WAIT_AFTER", }; $ When all are the above are present, then we have something called SYNC_FILE_RANGE_WRITE_AND_WAIT, that will be special cased in the upcoming scnprintf beautifier for this flags arg. Cc: Adrian Hunter Cc: Amir Goldstein Cc: Brendan Gregg Cc: Jiri Olsa Cc: Linus Torvalds Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-uf2vd7bc8fkz65j7yit8dh84@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf trace beauty clone: Handle CLONE_PIDFD

2019-05-28T21:37:43Z

In addition to the older flags. This will allow something like this to be implemented in 'perf trace" perf trace -e clone/PIDFD in flags/ I.e. ask for strace like tracing, system wide, looking for 'clone' syscalls that have the CLONE_PIDFD bit set in the 'flags' arg. For now we'll just see PIDFD if it is set in the 'flags' arg. Cc: Christian Brauner Cc: Adrian Hunter Cc: Brendan Gregg Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-drq9h7s8gcv8b87064fp6lb0@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf trace: Beautify 'fsmount' arguments

2019-05-28T21:37:43Z

Use existing beautifiers for the first arg, fd, assigned using the heuristic that looks for syscall arg names and associates SCA_FD with 'fd' named argumes, and wire up the recently introduced fsmount attr_flags table generator. Now it should be possible to just use: perf trace -e fsmount As root and see all fsmount syscalls with its args beautified. # cat sys_fsmount.c #define _GNU_SOURCE /* See feature_test_macros(7) */ #include #include /* For SYS_xxx definitions */ #define __NR_fsmount 432 #define MOUNT_ATTR_RDONLY 0x00000001 /* Mount read-only */ #define MOUNT_ATTR_NOSUID 0x00000002 /* Ignore suid and sgid bits */ #define MOUNT_ATTR_NODEV 0x00000004 /* Disallow access to device special files */ #define MOUNT_ATTR_NOEXEC 0x00000008 /* Disallow program execution */ #define MOUNT_ATTR__ATIME 0x00000070 /* Setting on how atime should be updated */ #define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */ #define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */ #define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ #define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ static inline int sys_fsmount(int fs_fd, int flags, int attr_flags) { syscall(__NR_fsmount, fs_fd, flags, attr_flags); } int main(int argc, char *argv[]) { int attr_flags = 0, fs_fd = 0; sys_fsmount(fs_fd++, 0, attr_flags); attr_flags |= MOUNT_ATTR_RDONLY; sys_fsmount(fs_fd++, 1, attr_flags); attr_flags |= MOUNT_ATTR_NOSUID; sys_fsmount(fs_fd++, 0, attr_flags); attr_flags |= MOUNT_ATTR_NODEV; sys_fsmount(fs_fd++, 1, attr_flags); attr_flags |= MOUNT_ATTR_NOEXEC; sys_fsmount(fs_fd++, 0, attr_flags); attr_flags |= MOUNT_ATTR_NOATIME; sys_fsmount(fs_fd++, 1, attr_flags); attr_flags |= MOUNT_ATTR_STRICTATIME; sys_fsmount(fs_fd++, 0, attr_flags); attr_flags |= MOUNT_ATTR_NODIRATIME; sys_fsmount(fs_fd++, 0, attr_flags); return 0; } # # perf trace -e fsmount ./sys_fsmount fsmount(0, 0, MOUNT_ATTR_RELATIME) = -1 EINVAL (Invalid argument) fsmount(1, FSMOUNT_CLOEXEC, MOUNT_ATTR_RDONLY|MOUNT_ATTR_RELATIME) = -1 EINVAL (Invalid argument) fsmount(2, 0, MOUNT_ATTR_RDONLY|MOUNT_ATTR_NOSUID|MOUNT_ATTR_RELATIME) = -1 EINVAL (Invalid argument) fsmount(3, FSMOUNT_CLOEXEC, MOUNT_ATTR_RDONLY|MOUNT_ATTR_NOSUID|MOUNT_ATTR_NODEV|MOUNT_ATTR_RELATIME) = -1 EBADF (Bad file descriptor) fsmount(4, 0, MOUNT_ATTR_RDONLY|MOUNT_ATTR_NOSUID|MOUNT_ATTR_NODEV|MOUNT_ATTR_NOEXEC|MOUNT_ATTR_RELATIME) = -1 EBADF (Bad file descriptor) fsmount(5, FSMOUNT_CLOEXEC, MOUNT_ATTR_RDONLY|MOUNT_ATTR_NOSUID|MOUNT_ATTR_NODEV|MOUNT_ATTR_NOEXEC|MOUNT_ATTR_NOATIME) = -1 EBADF (Bad file descriptor) fsmount(6, 0, MOUNT_ATTR_RDONLY|MOUNT_ATTR_NOSUID|MOUNT_ATTR_NODEV|MOUNT_ATTR_NOEXEC|MOUNT_ATTR_NOATIME|MOUNT_ATTR_STRICTATIME) = -1 EINVAL (Invalid argument) fsmount(7, 0, MOUNT_ATTR_RDONLY|MOUNT_ATTR_NOSUID|MOUNT_ATTR_NODEV|MOUNT_ATTR_NOEXEC|MOUNT_ATTR_NOATIME|MOUNT_ATTR_STRICTATIME|MOUNT_ATTR_NODIRATIME) = -1 EINVAL (Invalid argument) # Cc: Adrian Hunter Cc: Al Viro Cc: Brendan Gregg Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-w71uge0sfo6ns9uclhwtthca@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf trace: Introduce syscall_arg__scnprintf_strarray_flags

2019-05-28T21:37:43Z

So that one can just define a strarray and process it as a set of flags, similar to syscall_arg__scnprintf_strarray() with plain arrays. Cc: Adrian Hunter Cc: Brendan Gregg Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-nnt25wkpkow2w0yefhi6sb7q@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf beauty: Add generator for fsmount's 'attr_flags' arg values

2019-05-28T21:37:43Z

$ tools/perf/trace/beauty/fsmount.sh static const char *fsmount_attr_flags[] = { [ilog2(0x00000001) + 1] = "RDONLY", [ilog2(0x00000002) + 1] = "NOSUID", [ilog2(0x00000004) + 1] = "NODEV", [ilog2(0x00000008) + 1] = "NOEXEC", [ilog2(0x00000010) + 1] = "NOATIME", [ilog2(0x00000020) + 1] = "STRICTATIME", [ilog2(0x00000080) + 1] = "NODIRATIME", } MOUNT_ATTR__ATIME and MOUNT_ATTR_RELATIME will be special cased in the fsmount__scnprintf_flags() beautifier. Cc: Adrian Hunter Cc: Al Viro Cc: Brendan Gregg Cc: David Howells Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-sl24d7m2ge82mfmrbaf1mb0s@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf beauty: Add generator for fsconfig's 'cmd' arg values

2019-05-28T21:37:43Z

$ tools/perf/trace/beauty/fsconfig.sh static const char *fsconfig_cmds[] = { [0] = "SET_FLAG", [1] = "SET_STRING", [2] = "SET_BINARY", [3] = "SET_PATH", [4] = "SET_PATH_EMPTY", [5] = "SET_FD", [6] = "CMD_CREATE", [7] = "CMD_RECONFIGURE", }; $ Cc: Adrian Hunter Cc: Al Viro Cc: Brendan Gregg Cc: David Howells Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-u721396rkqmawmt91dwwsntu@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf trace: Beautify 'fspick' arguments

2019-05-28T21:37:42Z

Use existing beautifiers for the first 2 args (dfd, path) and wire up the recently introduced fspick flags table generator. Now it should be possible to just use: perf trace -e fspick As root and see all move_mount syscalls with its args beautified, either using the vfs_getname perf probe method or using the augmented_raw_syscalls.c eBPF helper to get the pathnames, the other args should work in all cases, i.e. all that is needed can be obtained directly from the raw_syscalls:sys_enter tracepoint args. # cat sys_fspick.c #define _GNU_SOURCE /* See feature_test_macros(7) */ #include #include /* For SYS_xxx definitions */ #include #define __NR_fspick 433 #define FSPICK_CLOEXEC 0x00000001 #define FSPICK_SYMLINK_NOFOLLOW 0x00000002 #define FSPICK_NO_AUTOMOUNT 0x00000004 #define FSPICK_EMPTY_PATH 0x00000008 static inline int sys_fspick(int fd, const char *path, int flags) { syscall(__NR_fspick, fd, path, flags); } int main(int argc, char *argv[]) { int flags = 0, fd = 0; open("/foo", 0); sys_fspick(fd++, "/foo1", flags); flags |= FSPICK_CLOEXEC; sys_fspick(fd++, "/foo2", flags); flags |= FSPICK_SYMLINK_NOFOLLOW; sys_fspick(fd++, "/foo3", flags); flags |= FSPICK_NO_AUTOMOUNT; sys_fspick(fd++, "/foo4", flags); flags |= FSPICK_EMPTY_PATH; return sys_fspick(fd++, "/foo5", flags); } # perf trace -e fspick ./sys_fspick LLVM: dumping /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o fspick(0, "/foo1", 0) = -1 ENOENT (No such file or directory) fspick(1, "/foo2", FSPICK_CLOEXEC) = -1 ENOENT (No such file or directory) fspick(2, "/foo3", FSPICK_CLOEXEC|FSPICK_SYMLINK_NOFOLLOW) = -1 ENOENT (No such file or directory) fspick(3, "/foo4", FSPICK_CLOEXEC|FSPICK_SYMLINK_NOFOLLOW|FSPICK_NO_AUTOMOUNT) = -1 ENOENT (No such file or directory) fspick(4, "/foo5", FSPICK_CLOEXEC|FSPICK_SYMLINK_NOFOLLOW|FSPICK_NO_AUTOMOUNT|FSPICK_EMPTY_PATH) = -1 ENOENT (No such file or directory) # Cc: Adrian Hunter Cc: Al Viro Cc: Brendan Gregg Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-erau5xjtt8wvgnhvdbchstuk@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo