kernel_optimize_test/tools/perf/examples/bpf/augmented_syscalls.c

56 lines
1.8 KiB
C
Raw Normal View History

perf trace: Handle "bpf-output" events associated with "__augmented_syscalls__" BPF map Add an example BPF script that writes syscalls:sys_enter_openat raw tracepoint payloads augmented with the first 64 bytes of the "filename" syscall pointer arg. Then catch it and print it just like with things written to the "__bpf_stdout__" map associated with a PERF_COUNT_SW_BPF_OUTPUT software event, by just letting the default tracepoint handler in 'perf trace', trace__event_handler(), to use bpf_output__fprintf(trace, sample), just like it does with all other PERF_COUNT_SW_BPF_OUTPUT events, i.e. just do a dump on the payload, so that we can check if what is being printed has at least the first 64 bytes of the "filename" arg: The augmented_syscalls.c eBPF script: # cat tools/perf/examples/bpf/augmented_syscalls.c // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> struct bpf_map SEC("maps") __augmented_syscalls__ = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, .key_size = sizeof(int), .value_size = sizeof(u32), .max_entries = __NR_CPUS__, }; struct syscall_enter_openat_args { unsigned long long common_tp_fields; long syscall_nr; long dfd; char *filename_ptr; long flags; long mode; }; struct augmented_enter_openat_args { struct syscall_enter_openat_args args; char filename[64]; }; int syscall_enter(openat)(struct syscall_enter_openat_args *args) { struct augmented_enter_openat_args augmented_args; probe_read(&augmented_args.args, sizeof(augmented_args.args), args); probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr); perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, sizeof(augmented_args)); return 1; } license(GPL); # So it will just prepare a raw_syscalls:sys_enter payload for the "openat" syscall. This will eventually be done for all syscalls with pointer args, globally or just when the user asks, using some spec, which args of which syscalls it wants "expanded" this way, we'll probably start with just all the syscalls that have char * pointers with familiar names, the ones we already handle with the probe:vfs_getname kprobe if it is in place hooking the kernel getname_flags() function used to copy from user the paths. Running it we get: # perf trace -e perf/tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null 0.000 ( ): __augmented_syscalls__:X?.C......................`\..................../etc/ld.so.cache..#......,....ao.k...............k......1."......... 0.006 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: 0x5c600da8, flags: CLOEXEC 0.008 ( 0.005 ms): cat/31292 openat(dfd: CWD, filename: 0x5c600da8, flags: CLOEXEC ) = 3 0.036 ( ): __augmented_syscalls__:X?.C.......................\..................../lib64/libc.so.6......... .\....#........?.......=.C..../."......... 0.037 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: 0x5c808ce0, flags: CLOEXEC 0.039 ( 0.007 ms): cat/31292 openat(dfd: CWD, filename: 0x5c808ce0, flags: CLOEXEC ) = 3 0.323 ( ): __augmented_syscalls__:X?.C.....................P....................../etc/passwd......>.C....@................>.C.....,....ao.>.C........ 0.325 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: 0xe8be50d6 0.327 ( 0.004 ms): cat/31292 openat(dfd: CWD, filename: 0xe8be50d6 ) = 3 # We need to go on optimizing this to avoid seding trash or zeroes in the pointer content payload, using the return from bpf_probe_read_str(), but to keep things simple at this stage and make incremental progress, lets leave it at that for now. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-g360n1zbj6bkbk6q0qo11c28@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08 02:40:13 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* Augment the openat syscall with the contents of the filename pointer argument.
*
* Test it with:
*
* perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
*
* It'll catch some openat syscalls related to the dynamic linked and
* the last one should be the one for '/etc/passwd'.
*
* This matches what is marshalled into the raw_syscall:sys_enter payload
* expected by the 'perf trace' beautifiers, and can be used by them unmodified,
* which will be done as that feature is implemented in the next csets, for now
* it will appear in a dump done by the default tracepoint handler in 'perf trace',
* that uses bpf_output__fprintf() to just dump those contents, as done with
* the bpf-output event associated with the __bpf_output__ map declared in
* tools/perf/include/bpf/stdio.h.
*/
#include <stdio.h>
struct bpf_map SEC("maps") __augmented_syscalls__ = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(u32),
.max_entries = __NR_CPUS__,
};
struct syscall_enter_openat_args {
unsigned long long common_tp_fields;
long syscall_nr;
long dfd;
char *filename_ptr;
long flags;
long mode;
};
struct augmented_enter_openat_args {
struct syscall_enter_openat_args args;
char filename[64];
};
int syscall_enter(openat)(struct syscall_enter_openat_args *args)
{
struct augmented_enter_openat_args augmented_args;
probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr);
perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
&augmented_args, sizeof(augmented_args));
perf trace: Make the augmented_syscalls filter out the tracepoint event When we attach a eBPF object to a tracepoint, if we return 1, then that tracepoint will be stored in the perf's ring buffer. In the augmented_syscalls.c case we want to just attach and _override_ the tracepoint payload with an augmented, extended one. In this example, tools/perf/examples/bpf/augmented_syscalls.c, we are attaching to the 'openat' syscall, and adding, after the syscalls:sys_enter_openat usual payload as defined by /sys/kernel/debug/tracing/events/syscalls/sys_enter_openat/format, a snapshot of its sole pointer arg: # grep 'field:.*\*' /sys/kernel/debug/tracing/events/syscalls/sys_enter_openat/format field:const char * filename; offset:24; size:8; signed:0; # For now this is not being considered, the next csets will make use of it, but as this is overriding the syscall tracepoint enter, we don't want that event appearing on the ring buffer, just our synthesized one. Before: # perf trace -e ~acme/git/perf/tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null 0.000 ( ): __augmented_syscalls__:dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC 0.006 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: , flags: CLOEXEC 0.007 ( 0.004 ms): cat/24044 openat(dfd: CWD, filename: 0x216dda8, flags: CLOEXEC ) = 3 0.028 ( ): __augmented_syscalls__:dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC 0.030 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: , flags: CLOEXEC 0.031 ( 0.006 ms): cat/24044 openat(dfd: CWD, filename: 0x2375ce0, flags: CLOEXEC ) = 3 0.291 ( ): __augmented_syscalls__:dfd: CWD, filename: /etc/passwd 0.293 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: 0.294 ( 0.004 ms): cat/24044 openat(dfd: CWD, filename: 0x637db06b ) = 3 # After: # perf trace -e ~acme/git/perf/tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null 0.000 ( ): __augmented_syscalls__:dfd: CWD, filename: 0x9c6a1da8, flags: CLOEXEC 0.005 ( 0.015 ms): cat/27341 openat(dfd: CWD, filename: 0x9c6a1da8, flags: CLOEXEC ) = 3 0.040 ( ): __augmented_syscalls__:dfd: CWD, filename: 0x9c8a9ce0, flags: CLOEXEC 0.041 ( 0.006 ms): cat/27341 openat(dfd: CWD, filename: 0x9c8a9ce0, flags: CLOEXEC ) = 3 0.294 ( ): __augmented_syscalls__:dfd: CWD, filename: 0x482a706b 0.296 ( 0.067 ms): cat/27341 openat(dfd: CWD, filename: 0x482a706b ) = 3 # Now lets replace that __augmented_syscalls__ name with the syscall name, using: # grep 'field:.*syscall_nr' /sys/kernel/debug/tracing/events/syscalls/sys_enter_openat/format field:int __syscall_nr; offset:8; size:4; signed:1; # That the synthesized payload has exactly where the syscall enter tracepoint puts it. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-og4r9k87mzp9hv7el046idmd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-21 22:14:15 +08:00
return 0;
perf trace: Handle "bpf-output" events associated with "__augmented_syscalls__" BPF map Add an example BPF script that writes syscalls:sys_enter_openat raw tracepoint payloads augmented with the first 64 bytes of the "filename" syscall pointer arg. Then catch it and print it just like with things written to the "__bpf_stdout__" map associated with a PERF_COUNT_SW_BPF_OUTPUT software event, by just letting the default tracepoint handler in 'perf trace', trace__event_handler(), to use bpf_output__fprintf(trace, sample), just like it does with all other PERF_COUNT_SW_BPF_OUTPUT events, i.e. just do a dump on the payload, so that we can check if what is being printed has at least the first 64 bytes of the "filename" arg: The augmented_syscalls.c eBPF script: # cat tools/perf/examples/bpf/augmented_syscalls.c // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> struct bpf_map SEC("maps") __augmented_syscalls__ = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, .key_size = sizeof(int), .value_size = sizeof(u32), .max_entries = __NR_CPUS__, }; struct syscall_enter_openat_args { unsigned long long common_tp_fields; long syscall_nr; long dfd; char *filename_ptr; long flags; long mode; }; struct augmented_enter_openat_args { struct syscall_enter_openat_args args; char filename[64]; }; int syscall_enter(openat)(struct syscall_enter_openat_args *args) { struct augmented_enter_openat_args augmented_args; probe_read(&augmented_args.args, sizeof(augmented_args.args), args); probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr); perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, sizeof(augmented_args)); return 1; } license(GPL); # So it will just prepare a raw_syscalls:sys_enter payload for the "openat" syscall. This will eventually be done for all syscalls with pointer args, globally or just when the user asks, using some spec, which args of which syscalls it wants "expanded" this way, we'll probably start with just all the syscalls that have char * pointers with familiar names, the ones we already handle with the probe:vfs_getname kprobe if it is in place hooking the kernel getname_flags() function used to copy from user the paths. Running it we get: # perf trace -e perf/tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null 0.000 ( ): __augmented_syscalls__:X?.C......................`\..................../etc/ld.so.cache..#......,....ao.k...............k......1."......... 0.006 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: 0x5c600da8, flags: CLOEXEC 0.008 ( 0.005 ms): cat/31292 openat(dfd: CWD, filename: 0x5c600da8, flags: CLOEXEC ) = 3 0.036 ( ): __augmented_syscalls__:X?.C.......................\..................../lib64/libc.so.6......... .\....#........?.......=.C..../."......... 0.037 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: 0x5c808ce0, flags: CLOEXEC 0.039 ( 0.007 ms): cat/31292 openat(dfd: CWD, filename: 0x5c808ce0, flags: CLOEXEC ) = 3 0.323 ( ): __augmented_syscalls__:X?.C.....................P....................../etc/passwd......>.C....@................>.C.....,....ao.>.C........ 0.325 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: 0xe8be50d6 0.327 ( 0.004 ms): cat/31292 openat(dfd: CWD, filename: 0xe8be50d6 ) = 3 # We need to go on optimizing this to avoid seding trash or zeroes in the pointer content payload, using the return from bpf_probe_read_str(), but to keep things simple at this stage and make incremental progress, lets leave it at that for now. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-g360n1zbj6bkbk6q0qo11c28@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08 02:40:13 +08:00
}
license(GPL);