diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-11-12 10:06:34 +0900 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-11-12 10:06:34 +0900 |
commit | ad5d69899e52792671c1aa6c7360464c7edfe09c (patch) | |
tree | 21833c1fdab4b3cf791d4fdc86dd578e4a620514 /tools/perf/builtin-trace.c | |
parent | ef1417a5a6a400dbc1a2f44da716ab146a29ddc4 (diff) | |
parent | caea6cf52139116e43e615d87fcbf9823e197fdf (diff) |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar:
"As a first remark I'd like to note that the way to build perf tooling
has been simplified and sped up, in the future it should be enough for
you to build perf via:
cd tools/perf/
make install
(ie without the -j option.) The build system will figure out the
number of CPUs and will do a parallel build+install.
The various build system inefficiencies and breakages Linus reported
against the v3.12 pull request should now be resolved - please
(re-)report any remaining annoyances or bugs.
Main changes on the perf kernel side:
* Performance optimizations:
. perf ring-buffer code optimizations, by Peter Zijlstra
. perf ring-buffer code optimizations, by Oleg Nesterov
. x86 NMI call-stack processing optimizations, by Peter Zijlstra
. perf context-switch optimizations, by Peter Zijlstra
. perf sampling speedups, by Peter Zijlstra
. x86 Intel PEBS processing speedups, by Peter Zijlstra
* Enhanced hardware support:
. for Intel Ivy Bridge-EP uncore PMUs, by Zheng Yan
. for Haswell transactions, by Andi Kleen, Peter Zijlstra
* Core perf events code enhancements and fixes by Oleg Nesterov:
. for uprobes, if fork() is called with pending ret-probes
. for uprobes platform support code
* New ABI details by Andi Kleen:
. Report x86 Haswell TSX transaction abort cost as weight
Main changes on the perf tooling side (some of these tooling changes
utilize the above kernel side changes):
* 'perf report/top' enhancements:
. Convert callchain children list to rbtree, greatly reducing the
time taken for callchain processing, from Namhyung Kim.
. Add new COMM infrastructure, further improving histogram
processing, from Frédéric Weisbecker, one fix from Namhyung Kim.
. Add /proc/kcore based live-annotation improvements, including
build-id cache support, multi map 'call' instruction navigation
fixes, kcore address validation, objdump workarounds. From
Adrian Hunter.
. Show progress on histogram collapsing, that can take a long
time, from Namhyung Kim.
. Add --max-stack option to limit callchain stack scan in 'top'
and 'report', improving callchain processing when reducing the
stack depth is an option, from Waiman Long.
. Add new option --ignore-vmlinux for perf top, from Willy
Tarreau.
* 'perf trace' enhancements:
. 'perf trace' now can can use a 'perf probe' dynamic tracepoints
to hook into the userspace -> kernel pathname copy so that it
can map fds to pathnames without reading /proc/pid/fd/ symlinks.
From Arnaldo Carvalho de Melo.
. Show VFS path associated with fd in live sessions, using a
'vfs_getname' 'perf probe' created dynamic tracepoint or by
looking at /proc/pid/fd, from Arnaldo Carvalho de Melo.
. Add 'trace' beautifiers for lots of syscall arguments, from
Arnaldo Carvalho de Melo.
. Implement more compact 'trace' output by suppressing zeroed
args, from Arnaldo Carvalho de Melo.
. Show thread COMM by default in 'trace', from Arnaldo Carvalho de
Melo.
. Add option to show full timestamp in 'trace', from David Ahern.
. Add 'record' command in 'trace', to record raw_syscalls:*, from
David Ahern.
. Add summary option to dump syscall statistics in 'trace', from
David Ahern.
. Improve error messages in 'trace', providing hints about system
configuration steps needed for using it, from Ramkumar
Ramachandra.
. 'perf trace' now emits hints as to why tracing is not possible,
helping the user to setup the system to allow tracing in the
desired permission granularity, telling if the problem is due to
debugfs not being mounted or with not enough permission for
!root, /proc/sys/kernel/perf_event_paranoit value, etc. From
Arnaldo Carvalho de Melo.
* 'perf record' enhancements:
. Check maximum frequency rate for record/top, emitting better
error messages, from Jiri Olsa.
. 'perf record' code cleanups, from David Ahern.
. Improve write_output error message in 'perf record', from Adrian
Hunter.
. Allow specifying B/K/M/G unit to the --mmap-pages arguments,
from Jiri Olsa.
. Fix command line callchain attribute tests to handle the new
-g/--call-chain semantics, from Arnaldo Carvalho de Melo.
* 'perf kvm' enhancements:
. Disable live kvm command if timerfd is not supported, from David
Ahern.
. Fix detection of non-core features, from David Ahern.
* 'perf list' enhancements:
. Add usage to 'perf list', from David Ahern.
. Show error in 'perf list' if tracepoints not available, from
Pekka Enberg.
* 'perf probe' enhancements:
. Support "$vars" meta argument syntax for local variables,
allowing asking for all possible variables at a given probe
point to be collected when it hits, from Masami Hiramatsu.
* 'perf sched' enhancements:
. Address the root cause of that 'perf sched' stack initialization
build slowdown, by programmatically setting a big array after
moving the global variable back to the stack. Fix from Adrian
Hunter.
* 'perf script' enhancements:
. Set up output options for in-stream attributes, from Adrian
Hunter.
. Print addr by default for BTS in 'perf script', from Adrian
Juntmer
* 'perf stat' enhancements:
. Improved messages when doing profiling in all or a subset of
CPUs using a workload as the session delimitator, as in:
'perf stat --cpu 0,2 sleep 10s'
from Arnaldo Carvalho de Melo.
. Add units to nanosec-based counters in 'perf stat', from David
Ahern.
. Remove bogus info when using 'perf stat' -e cycles/instructions,
from Ramkumar Ramachandra.
* 'perf lock' enhancements:
. 'perf lock' fixes and cleanups, from Davidlohr Bueso.
* 'perf test' enhancements:
. Fixup PERF_SAMPLE_TRANSACTION handling in sample synthesizing
and 'perf test', from Adrian Hunter.
. Clarify the "sample parsing" test entry, from Arnaldo Carvalho
de Melo.
. Consider PERF_SAMPLE_TRANSACTION in the "sample parsing" test,
from Arnaldo Carvalho de Melo.
. Memory leak fixes in 'perf test', from Felipe Pena.
* 'perf bench' enhancements:
. Change the procps visible command-name of invididual benchmark
tests plus cleanups, from Ingo Molnar.
* Generic perf tooling infrastructure/plumbing changes:
. Separating data file properties from session, code
reorganization from Jiri Olsa.
. Fix version when building out of tree, as when using one of
these:
$ make help | grep perf
perf-tar-src-pkg - Build perf-3.12.0.tar source tarball
perf-targz-src-pkg - Build perf-3.12.0.tar.gz source tarball
perf-tarbz2-src-pkg - Build perf-3.12.0.tar.bz2 source tarball
perf-tarxz-src-pkg - Build perf-3.12.0.tar.xz source tarball
$
from David Ahern.
. Enhance option parse error message, showing just the help lines
of the options affected, from Namhyung Kim.
. libtraceevent updates from upstream trace-cmd repo, from Steven
Rostedt.
. Always use perf_evsel__set_sample_bit to set sample_type, from
Adrian Hunter.
. Memory and mmap leak fixes from Chenggang Qin.
. Assorted build fixes for from David Ahern and Jiri Olsa.
. Speed up and prettify the build system, from Ingo Molnar.
. Implement addr2line directly using libbfd, from Roberto Vitillo.
. Separate the GTK support in a separate libperf-gtk.so DSO, that
is only loaded when --gtk is specified, from Namhyung Kim.
. perf bash completion fixes and improvements from Ramkumar
Ramachandra.
. Support for Openembedded/Yocto -dbg packages, from Ricardo
Ribalda Delgado.
And lots and lots of other fixes and code reorganizations that did not
make it into the list, see the shortlog, diffstat and the Git log for
details!"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (300 commits)
uprobes: Fix the memory out of bound overwrite in copy_insn()
uprobes: Fix the wrong usage of current->utask in uprobe_copy_process()
perf tools: Remove unneeded include
perf record: Remove post_processing_offset variable
perf record: Remove advance_output function
perf record: Refactor feature handling into a separate function
perf trace: Don't relookup fields by name in each sample
perf tools: Fix version when building out of tree
perf evsel: Ditch evsel->handler.data field
uprobes: Export write_opcode() as uprobe_write_opcode()
uprobes: Introduce arch_uprobe->ixol
uprobes: Kill module_init() and module_exit()
uprobes: Move function declarations out of arch
perf/x86/intel: Add Ivy Bridge-EP uncore IRP box support
perf/x86/intel/uncore: Add filter support for IvyBridge-EP QPI boxes
perf: Factor out strncpy() in perf_event_mmap_event()
tools/perf: Add required memory barriers
perf: Fix arch_perf_out_copy_user default
perf: Update a stale comment
perf: Optimize perf_output_begin() -- address calculation
...
Diffstat (limited to 'tools/perf/builtin-trace.c')
-rw-r--r-- | tools/perf/builtin-trace.c | 1403 |
1 files changed, 1225 insertions, 178 deletions
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 99c8d9ad672..329b7832b5d 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -10,9 +10,11 @@ #include "util/strlist.h" #include "util/intlist.h" #include "util/thread_map.h" +#include "util/stat.h" #include <libaudit.h> #include <stdlib.h> +#include <sys/eventfd.h> #include <sys/mman.h> #include <linux/futex.h> @@ -33,49 +35,279 @@ # define MADV_UNMERGEABLE 13 #endif -static size_t syscall_arg__scnprintf_hex(char *bf, size_t size, - unsigned long arg, - u8 arg_idx __maybe_unused, - u8 *arg_mask __maybe_unused) +struct tp_field { + int offset; + union { + u64 (*integer)(struct tp_field *field, struct perf_sample *sample); + void *(*pointer)(struct tp_field *field, struct perf_sample *sample); + }; +}; + +#define TP_UINT_FIELD(bits) \ +static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \ +{ \ + return *(u##bits *)(sample->raw_data + field->offset); \ +} + +TP_UINT_FIELD(8); +TP_UINT_FIELD(16); +TP_UINT_FIELD(32); +TP_UINT_FIELD(64); + +#define TP_UINT_FIELD__SWAPPED(bits) \ +static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \ +{ \ + u##bits value = *(u##bits *)(sample->raw_data + field->offset); \ + return bswap_##bits(value);\ +} + +TP_UINT_FIELD__SWAPPED(16); +TP_UINT_FIELD__SWAPPED(32); +TP_UINT_FIELD__SWAPPED(64); + +static int tp_field__init_uint(struct tp_field *field, + struct format_field *format_field, + bool needs_swap) { - return scnprintf(bf, size, "%#lx", arg); + field->offset = format_field->offset; + + switch (format_field->size) { + case 1: + field->integer = tp_field__u8; + break; + case 2: + field->integer = needs_swap ? tp_field__swapped_u16 : tp_field__u16; + break; + case 4: + field->integer = needs_swap ? tp_field__swapped_u32 : tp_field__u32; + break; + case 8: + field->integer = needs_swap ? tp_field__swapped_u64 : tp_field__u64; + break; + default: + return -1; + } + + return 0; } -#define SCA_HEX syscall_arg__scnprintf_hex +static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample) +{ + return sample->raw_data + field->offset; +} -static size_t syscall_arg__scnprintf_whence(char *bf, size_t size, - unsigned long arg, - u8 arg_idx __maybe_unused, - u8 *arg_mask __maybe_unused) +static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field) { - int whence = arg; + field->offset = format_field->offset; + field->pointer = tp_field__ptr; + return 0; +} - switch (whence) { -#define P_WHENCE(n) case SEEK_##n: return scnprintf(bf, size, #n) - P_WHENCE(SET); - P_WHENCE(CUR); - P_WHENCE(END); -#ifdef SEEK_DATA - P_WHENCE(DATA); -#endif -#ifdef SEEK_HOLE - P_WHENCE(HOLE); -#endif -#undef P_WHENCE - default: break; +struct syscall_tp { + struct tp_field id; + union { + struct tp_field args, ret; + }; +}; + +static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel, + struct tp_field *field, + const char *name) +{ + struct format_field *format_field = perf_evsel__field(evsel, name); + + if (format_field == NULL) + return -1; + + return tp_field__init_uint(field, format_field, evsel->needs_swap); +} + +#define perf_evsel__init_sc_tp_uint_field(evsel, name) \ + ({ struct syscall_tp *sc = evsel->priv;\ + perf_evsel__init_tp_uint_field(evsel, &sc->name, #name); }) + +static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel, + struct tp_field *field, + const char *name) +{ + struct format_field *format_field = perf_evsel__field(evsel, name); + + if (format_field == NULL) + return -1; + + return tp_field__init_ptr(field, format_field); +} + +#define perf_evsel__init_sc_tp_ptr_field(evsel, name) \ + ({ struct syscall_tp *sc = evsel->priv;\ + perf_evsel__init_tp_ptr_field(evsel, &sc->name, #name); }) + +static void perf_evsel__delete_priv(struct perf_evsel *evsel) +{ + free(evsel->priv); + evsel->priv = NULL; + perf_evsel__delete(evsel); +} + +static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, + void *handler, int idx) +{ + struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction, idx); + + if (evsel) { + evsel->priv = malloc(sizeof(struct syscall_tp)); + + if (evsel->priv == NULL) + goto out_delete; + + if (perf_evsel__init_sc_tp_uint_field(evsel, id)) + goto out_delete; + + evsel->handler = handler; } - return scnprintf(bf, size, "%#x", whence); + return evsel; + +out_delete: + perf_evsel__delete_priv(evsel); + return NULL; } -#define SCA_WHENCE syscall_arg__scnprintf_whence +#define perf_evsel__sc_tp_uint(evsel, name, sample) \ + ({ struct syscall_tp *fields = evsel->priv; \ + fields->name.integer(&fields->name, sample); }) + +#define perf_evsel__sc_tp_ptr(evsel, name, sample) \ + ({ struct syscall_tp *fields = evsel->priv; \ + fields->name.pointer(&fields->name, sample); }) + +static int perf_evlist__add_syscall_newtp(struct perf_evlist *evlist, + void *sys_enter_handler, + void *sys_exit_handler) +{ + int ret = -1; + int idx = evlist->nr_entries; + struct perf_evsel *sys_enter, *sys_exit; + + sys_enter = perf_evsel__syscall_newtp("sys_enter", sys_enter_handler, idx++); + if (sys_enter == NULL) + goto out; + + if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args)) + goto out_delete_sys_enter; + + sys_exit = perf_evsel__syscall_newtp("sys_exit", sys_exit_handler, idx++); + if (sys_exit == NULL) + goto out_delete_sys_enter; + + if (perf_evsel__init_sc_tp_uint_field(sys_exit, ret)) + goto out_delete_sys_exit; + + perf_evlist__add(evlist, sys_enter); + perf_evlist__add(evlist, sys_exit); + + ret = 0; +out: + return ret; + +out_delete_sys_exit: + perf_evsel__delete_priv(sys_exit); +out_delete_sys_enter: + perf_evsel__delete_priv(sys_enter); + goto out; +} + + +struct syscall_arg { + unsigned long val; + struct thread *thread; + struct trace *trace; + void *parm; + u8 idx; + u8 mask; +}; + +struct strarray { + int offset; + int nr_entries; + const char **entries; +}; + +#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \ + .nr_entries = ARRAY_SIZE(array), \ + .entries = array, \ +} + +#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \ + .offset = off, \ + .nr_entries = ARRAY_SIZE(array), \ + .entries = array, \ +} + +static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size, + const char *intfmt, + struct syscall_arg *arg) +{ + struct strarray *sa = arg->parm; + int idx = arg->val - sa->offset; + + if (idx < 0 || idx >= sa->nr_entries) + return scnprintf(bf, size, intfmt, arg->val); + + return scnprintf(bf, size, "%s", sa->entries[idx]); +} + +static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size, + struct syscall_arg *arg) +{ + return __syscall_arg__scnprintf_strarray(bf, size, "%d", arg); +} + +#define SCA_STRARRAY syscall_arg__scnprintf_strarray + +static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size, + struct syscall_arg *arg) +{ + return __syscall_arg__scnprintf_strarray(bf, size, "%#x", arg); +} + +#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray + +static size_t syscall_arg__scnprintf_fd(char *bf, size_t size, + struct syscall_arg *arg); + +#define SCA_FD syscall_arg__scnprintf_fd + +static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size, + struct syscall_arg *arg) +{ + int fd = arg->val; + + if (fd == AT_FDCWD) + return scnprintf(bf, size, "CWD"); + + return syscall_arg__scnprintf_fd(bf, size, arg); +} + +#define SCA_FDAT syscall_arg__scnprintf_fd_at + +static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size, + struct syscall_arg *arg); + +#define SCA_CLOSE_FD syscall_arg__scnprintf_close_fd + +static size_t syscall_arg__scnprintf_hex(char *bf, size_t size, + struct syscall_arg *arg) +{ + return scnprintf(bf, size, "%#lx", arg->val); +} + +#define SCA_HEX syscall_arg__scnprintf_hex static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size, - unsigned long arg, - u8 arg_idx __maybe_unused, - u8 *arg_mask __maybe_unused) + struct syscall_arg *arg) { - int printed = 0, prot = arg; + int printed = 0, prot = arg->val; if (prot == PROT_NONE) return scnprintf(bf, size, "NONE"); @@ -104,10 +336,9 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size, #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, - unsigned long arg, u8 arg_idx __maybe_unused, - u8 *arg_mask __maybe_unused) + struct syscall_arg *arg) { - int printed = 0, flags = arg; + int printed = 0, flags = arg->val; #define P_MMAP_FLAG(n) \ if (flags & MAP_##n) { \ @@ -148,10 +379,9 @@ 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_madvise_behavior(char *bf, size_t size, - unsigned long arg, u8 arg_idx __maybe_unused, - u8 *arg_mask __maybe_unused) + struct syscall_arg *arg) { - int behavior = arg; + int behavior = arg->val; switch (behavior) { #define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n) @@ -190,8 +420,38 @@ static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size, #define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior -static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, unsigned long arg, - u8 arg_idx __maybe_unused, u8 *arg_mask) +static size_t syscall_arg__scnprintf_flock(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, op = arg->val; + + if (op == 0) + return scnprintf(bf, size, "NONE"); +#define P_CMD(cmd) \ + if ((op & LOCK_##cmd) == LOCK_##cmd) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #cmd); \ + op &= ~LOCK_##cmd; \ + } + + P_CMD(SH); + P_CMD(EX); + P_CMD(NB); + P_CMD(UN); + P_CMD(MAND); + P_CMD(RW); + P_CMD(READ); + P_CMD(WRITE); +#undef P_OP + + if (op) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", op); + + return printed; +} + +#define SCA_FLOCK syscall_arg__scnprintf_flock + +static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg) { enum syscall_futex_args { SCF_UADDR = (1 << 0), @@ -201,24 +461,24 @@ static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, unsigned lo SCF_UADDR2 = (1 << 4), SCF_VAL3 = (1 << 5), }; - int op = arg; + int op = arg->val; int cmd = op & FUTEX_CMD_MASK; size_t printed = 0; switch (cmd) { #define P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n); - P_FUTEX_OP(WAIT); *arg_mask |= SCF_VAL3|SCF_UADDR2; break; - P_FUTEX_OP(WAKE); *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; - P_FUTEX_OP(FD); *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; - P_FUTEX_OP(REQUEUE); *arg_mask |= SCF_VAL3|SCF_TIMEOUT; break; - P_FUTEX_OP(CMP_REQUEUE); *arg_mask |= SCF_TIMEOUT; break; - P_FUTEX_OP(CMP_REQUEUE_PI); *arg_mask |= SCF_TIMEOUT; break; + P_FUTEX_OP(WAIT); arg->mask |= SCF_VAL3|SCF_UADDR2; break; + P_FUTEX_OP(WAKE); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(FD); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(REQUEUE); arg->mask |= SCF_VAL3|SCF_TIMEOUT; break; + P_FUTEX_OP(CMP_REQUEUE); arg->mask |= SCF_TIMEOUT; break; + P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT; break; P_FUTEX_OP(WAKE_OP); break; - P_FUTEX_OP(LOCK_PI); *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; - P_FUTEX_OP(UNLOCK_PI); *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; - P_FUTEX_OP(TRYLOCK_PI); *arg_mask |= SCF_VAL3|SCF_UADDR2; break; - P_FUTEX_OP(WAIT_BITSET); *arg_mask |= SCF_UADDR2; break; - P_FUTEX_OP(WAKE_BITSET); *arg_mask |= SCF_UADDR2; break; + P_FUTEX_OP(LOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(UNLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(TRYLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2; break; + P_FUTEX_OP(WAIT_BITSET); arg->mask |= SCF_UADDR2; break; + P_FUTEX_OP(WAKE_BITSET); arg->mask |= SCF_UADDR2; break; P_FUTEX_OP(WAIT_REQUEUE_PI); break; default: printed = scnprintf(bf, size, "%#x", cmd); break; } @@ -234,14 +494,194 @@ static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, unsigned lo #define SCA_FUTEX_OP syscall_arg__scnprintf_futex_op +static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", }; +static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, 1); + +static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", }; +static DEFINE_STRARRAY(itimers); + +static const char *whences[] = { "SET", "CUR", "END", +#ifdef SEEK_DATA +"DATA", +#endif +#ifdef SEEK_HOLE +"HOLE", +#endif +}; +static DEFINE_STRARRAY(whences); + +static const char *fcntl_cmds[] = { + "DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK", + "SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "F_GETLK64", + "F_SETLK64", "F_SETLKW64", "F_SETOWN_EX", "F_GETOWN_EX", + "F_GETOWNER_UIDS", +}; +static DEFINE_STRARRAY(fcntl_cmds); + +static const char *rlimit_resources[] = { + "CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE", + "MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO", + "RTTIME", +}; +static DEFINE_STRARRAY(rlimit_resources); + +static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", }; +static DEFINE_STRARRAY(sighow); + +static const char *clockid[] = { + "REALTIME", "MONOTONIC", "PROCESS_CPUTIME_ID", "THREAD_CPUTIME_ID", + "MONOTONIC_RAW", "REALTIME_COARSE", "MONOTONIC_COARSE", +}; +static DEFINE_STRARRAY(clockid); + +static const char *socket_families[] = { + "UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM", + "BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI", + "SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC", + "RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC", + "BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF", + "ALG", "NFC", "VSOCK", +}; +static DEFINE_STRARRAY(socket_families); + +#ifndef SOCK_TYPE_MASK +#define SOCK_TYPE_MASK 0xf +#endif + +static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size, + struct syscall_arg *arg) +{ + size_t printed; + int type = arg->val, + flags = type & ~SOCK_TYPE_MASK; + + type &= SOCK_TYPE_MASK; + /* + * Can't use a strarray, MIPS may override for ABI reasons. + */ + switch (type) { +#define P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break; + P_SK_TYPE(STREAM); + P_SK_TYPE(DGRAM); + P_SK_TYPE(RAW); + P_SK_TYPE(RDM); + P_SK_TYPE(SEQPACKET); + P_SK_TYPE(DCCP); + P_SK_TYPE(PACKET); +#undef P_SK_TYPE + default: + printed = scnprintf(bf, size, "%#x", type); + } + +#define P_SK_FLAG(n) \ + if (flags & SOCK_##n) { \ + printed += scnprintf(bf + printed, size - printed, "|%s", #n); \ + flags &= ~SOCK_##n; \ + } + + P_SK_FLAG(CLOEXEC); + P_SK_FLAG(NONBLOCK); +#undef P_SK_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "|%#x", flags); + + return printed; +} + +#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type + +#ifndef MSG_PROBE +#define MSG_PROBE 0x10 +#endif +#ifndef MSG_WAITFORONE +#define MSG_WAITFORONE 0x10000 +#endif +#ifndef MSG_SENDPAGE_NOTLAST +#define MSG_SENDPAGE_NOTLAST 0x20000 +#endif +#ifndef MSG_FASTOPEN +#define MSG_FASTOPEN 0x20000000 +#endif + +static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (flags == 0) + return scnprintf(bf, size, "NONE"); +#define P_MSG_FLAG(n) \ + if (flags & MSG_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~MSG_##n; \ + } + + P_MSG_FLAG(OOB); + P_MSG_FLAG(PEEK); + P_MSG_FLAG(DONTROUTE); + P_MSG_FLAG(TRYHARD); + P_MSG_FLAG(CTRUNC); + P_MSG_FLAG(PROBE); + P_MSG_FLAG(TRUNC); + P_MSG_FLAG(DONTWAIT); + P_MSG_FLAG(EOR); + P_MSG_FLAG(WAITALL); + P_MSG_FLAG(FIN); + P_MSG_FLAG(SYN); + P_MSG_FLAG(CONFIRM); + P_MSG_FLAG(RST); + P_MSG_FLAG(ERRQUEUE); + P_MSG_FLAG(NOSIGNAL); + P_MSG_FLAG(MORE); + P_MSG_FLAG(WAITFORONE); + P_MSG_FLAG(SENDPAGE_NOTLAST); + P_MSG_FLAG(FASTOPEN); + P_MSG_FLAG(CMSG_CLOEXEC); +#undef P_MSG_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags + +static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size, + struct syscall_arg *arg) +{ + size_t printed = 0; + int mode = arg->val; + + if (mode == F_OK) /* 0 */ + return scnprintf(bf, size, "F"); +#define P_MODE(n) \ + if (mode & n##_OK) { \ + printed += scnprintf(bf + printed, size - printed, "%s", #n); \ + mode &= ~n##_OK; \ + } + + P_MODE(R); + P_MODE(W); + P_MODE(X); +#undef P_MODE + + if (mode) + printed += scnprintf(bf + printed, size - printed, "|%#x", mode); + + return printed; +} + +#define SCA_ACCMODE syscall_arg__scnprintf_access_mode + static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, - unsigned long arg, - u8 arg_idx, u8 *arg_mask) + struct syscall_arg *arg) { - int printed = 0, flags = arg; + int printed = 0, flags = arg->val; if (!(flags & O_CREAT)) - *arg_mask |= 1 << (arg_idx + 1); /* Mask the mode parm */ + arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */ if (flags == 0) return scnprintf(bf, size, "RDONLY"); @@ -291,32 +731,225 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, #define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags +static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (flags == 0) + return scnprintf(bf, size, "NONE"); +#define P_FLAG(n) \ + if (flags & EFD_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~EFD_##n; \ + } + + P_FLAG(SEMAPHORE); + P_FLAG(CLOEXEC); + P_FLAG(NONBLOCK); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags + +static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_FLAG(n) \ + if (flags & O_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~O_##n; \ + } + + P_FLAG(CLOEXEC); + P_FLAG(NONBLOCK); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags + +static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg) +{ + int sig = arg->val; + + switch (sig) { +#define P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n) + P_SIGNUM(HUP); + P_SIGNUM(INT); + P_SIGNUM(QUIT); + P_SIGNUM(ILL); + P_SIGNUM(TRAP); + P_SIGNUM(ABRT); + P_SIGNUM(BUS); + P_SIGNUM(FPE); + P_SIGNUM(KILL); + P_SIGNUM(USR1); + P_SIGNUM(SEGV); + P_SIGNUM(USR2); + P_SIGNUM(PIPE); + P_SIGNUM(ALRM); + P_SIGNUM(TERM); + P_SIGNUM(STKFLT); + P_SIGNUM(CHLD); + P_SIGNUM(CONT); + P_SIGNUM(STOP); + P_SIGNUM(TSTP); + P_SIGNUM(TTIN); + P_SIGNUM(TTOU); + P_SIGNUM(URG); + P_SIGNUM(XCPU); + P_SIGNUM(XFSZ); + P_SIGNUM(VTALRM); + P_SIGNUM(PROF); + P_SIGNUM(WINCH); + P_SIGNUM(IO); + P_SIGNUM(PWR); + P_SIGNUM(SYS); + default: break; + } + + return scnprintf(bf, size, "%#x", sig); +} + +#define SCA_SIGNUM syscall_arg__scnprintf_signum + +#define TCGETS 0x5401 + +static const char *tioctls[] = { + "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW", + "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL", + "TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI", + "TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC", + "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX", + "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO", + "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK", + "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2", + "TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK", + "TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", + "TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL", + [0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG", + "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS", + "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI", + "TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE", +}; + +static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401); + +#define STRARRAY(arg, name, array) \ + .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \ + .arg_parm = { [arg] = &strarray__##array, } + static struct syscall_fmt { const char *name; const char *alias; - size_t (*arg_scnprintf[6])(char *bf, size_t size, unsigned long arg, u8 arg_idx, u8 *arg_mask); + size_t (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg); + void *arg_parm[6]; bool errmsg; bool timeout; bool hexret; } syscall_fmts[] = { - { .name = "access", .errmsg = true, }, + { .name = "access", .errmsg = true, + .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, }, { .name = "arch_prctl", .errmsg = true, .alias = "prctl", }, { .name = "brk", .hexret = true, .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, }, - { .name = "mmap", .hexret = true, }, + { .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), }, + { .name = "close", .errmsg = true, + .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, { .name = "connect", .errmsg = true, }, - { .name = "fstat", .errmsg = true, .alias = "newfstat", }, - { .name = "fstatat", .errmsg = true, .alias = "newfstatat", }, + { .name = "dup", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "dup2", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "dup3", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), }, + { .name = "eventfd2", .errmsg = true, + .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, }, + { .name = "faccessat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "fadvise64", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fallocate", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fchdir", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fchmod", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fchmodat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "fchown", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fchownat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "fcntl", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ + [1] = SCA_STRARRAY, /* cmd */ }, + .arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, }, + { .name = "fdatasync", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "flock", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ + [1] = SCA_FLOCK, /* cmd */ }, }, + { .name = "fsetxattr", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fstat", .errmsg = true, .alias = "newfstat", + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fstatat", .errmsg = true, .alias = "newfstatat", + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "fstatfs", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fsync", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "ftruncate", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "futex", .errmsg = true, .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, }, + { .name = "futimesat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "getdents", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "getdents64", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), }, + { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "ioctl", .errmsg = true, - .arg_scnprintf = { [2] = SCA_HEX, /* arg */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ + [1] = SCA_STRHEXARRAY, /* cmd */ + [2] = SCA_HEX, /* arg */ }, + .arg_parm = { [1] = &strarray__tioctls, /* cmd */ }, }, + { .name = "kill", .errmsg = true, + .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, + { .name = "linkat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "lseek", .errmsg = true, - .arg_scnprintf = { [2] = SCA_WHENCE, /* whence */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ + [2] = SCA_STRARRAY, /* whence */ }, + .arg_parm = { [2] = &strarray__whences, /* whence */ }, }, { .name = "lstat", .errmsg = true, .alias = "newlstat", }, { .name = "madvise", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* start */ [2] = SCA_MADV_BHV, /* behavior */ }, }, + { .name = "mkdirat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "mknodat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "mlock", .errmsg = true, + .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, + { .name = "mlockall", .errmsg = true, + .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, { .name = "mmap", .hexret = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ [2] = SCA_MMAP_PROT, /* prot */ @@ -327,24 +960,91 @@ static struct syscall_fmt { { .name = "mremap", .hexret = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ [4] = SCA_HEX, /* new_addr */ }, }, + { .name = "munlock", .errmsg = true, + .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, { .name = "munmap", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, + { .name = "name_to_handle_at", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "newfstatat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "open", .errmsg = true, .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, }, { .name = "open_by_handle_at", .errmsg = true, - .arg_scnprintf = { [2] = SCA_OPEN_FLAGS, /* flags */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ + [2] = SCA_OPEN_FLAGS, /* flags */ }, }, { .name = "openat", .errmsg = true, - .arg_scnprintf = { [2] = SCA_OPEN_FLAGS, /* flags */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ + [2] = SCA_OPEN_FLAGS, /* flags */ }, }, + { .name = "pipe2", .errmsg = true, + .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, }, { .name = "poll", .errmsg = true, .timeout = true, }, { .name = "ppoll", .errmsg = true, .timeout = true, }, - { .name = "pread", .errmsg = true, .alias = "pread64", }, - { .name = "pwrite", .errmsg = true, .alias = "pwrite64", }, - { .name = "read", .errmsg = true, }, - { .name = "recvfrom", .errmsg = true, }, + { .name = "pread", .errmsg = true, .alias = "pread64", + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "preadv", .errmsg = true, .alias = "pread", + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resour |