[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240824163322.60796-7-howardchu95@gmail.com>
Date: Sun, 25 Aug 2024 00:33:20 +0800
From: Howard Chu <howardchu95@...il.com>
To: acme@...nel.org
Cc: adrian.hunter@...el.com,
irogers@...gle.com,
jolsa@...nel.org,
kan.liang@...ux.intel.com,
namhyung@...nel.org,
linux-perf-users@...r.kernel.org,
linux-kernel@...r.kernel.org,
Arnaldo Carvalho de Melo <acme@...hat.com>
Subject: [PATCH v3 6/8] perf trace: Collect augmented data using BPF
Include trace_augment.h for TRACE_AUG_MAX_BUF, so that BPF reads
TRACE_AUG_MAX_BUF bytes of buffer maximum.
Determine what type of argument and how many bytes to read from user space, us ing the
value in the beauty_map. This is the relation of parameter type and its corres ponding
value in the beauty map, and how many bytes we read eventually:
string: 1 -> size of string (till null)
struct: size of struct -> size of struct
buffer: -1 * (index of paired len) -> value of paired len (maximum: TRACE_AUG_ MAX_BUF)
After reading from user space, we output the augmented data using
bpf_perf_event_output().
If the struct augmenter, augment_sys_enter() failed, we fall back to
using bpf_tail_call().
I have to make the payload 6 times the size of augmented_arg, to pass the
BPF verifier.
Committer notes:
It works, but we need to wire it up to the userspace specialized pretty
printer, otherwise we get things like:
root@...ber:~# perf trace -e connect ssh localhost
0.000 ( 0.010 ms): :784442/784442 connect(fd: 3, uservaddr: {2,}, addrlen: 16) = 0
0.016 ( 0.006 ms): :784442/784442 connect(fd: 3, uservaddr: {10,}, addrlen: 28) = 0
0.033 ( 0.096 ms): :784442/784442 connect(fd: 3, uservaddr: {10,}, addrlen: 28) = 0
root@...alhost's password: 71.292 ( 0.037 ms): ssh/784442 connect(fd: 4, uservaddr: {1,{['/','v','a','r','/','r','u','n','/','.','h','e','i','m',],},}, addrlen: 110) = 0
72.087 ( 0.013 ms): ssh/784442 connect(fd: 4, uservaddr: {1,{['/','v','a','r','/','r','u','n','/','.','h','e','i','m',],},}, addrlen: 110) = 0
root@...ber:~#
When we used to have:
root@...ber:~# perf trace -e connect ssh localhost
0.000 ( 0.011 ms): ssh/786564 connect(fd: 3, uservaddr: { .family: INET, port: 22, addr: 127.0.0.1 }, addrlen: 16) = 0
0.017 ( 0.006 ms): ssh/786564 connect(fd: 3, uservaddr: { .family: INET6, port: 22, addr: ::1 }, addrlen: 28) = 0
0.263 ( 0.043 ms): ssh/786564 connect(fd: 3, uservaddr: { .family: INET6, port: 22, addr: ::1 }, addrlen: 28) = 0
63.770 ( 0.044 ms): ssh/786564 connect(fd: 4, uservaddr: { .family: LOCAL, path: /var/run/.heim_org.h5l.kcm-socket }, addrlen: 110) = 0
65.467 ( 0.042 ms): ssh/786564 connect(fd: 4, uservaddr: { .family: LOCAL, path: /var/run/.heim_org.h5l.kcm-socket }, addrlen: 110) = 0
root@...alhost's password:
That is closer to what strace produces:
root@...ber:~# strace -e connect ssh localhost
connect(3, {sa_family=AF_INET, sin_port=htons(22), sin_addr=inet_addr("127.0.0.1")}, 16) = 0
connect(3, {sa_family=AF_INET6, sin6_port=htons(22), sin6_flowinfo=htonl(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_scope_id=0}, 28) = 0
connect(3, {sa_family=AF_INET6, sin6_port=htons(22), sin6_flowinfo=htonl(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_scope_id=0}, 28) = 0
connect(4, {sa_family=AF_UNIX, sun_path="/var/run/.heim_org.h5l.kcm-socket"}, 110) = 0
connect(4, {sa_family=AF_UNIX, sun_path="/var/run/.heim_org.h5l.kcm-socket"}, 110) = 0
root@...alhost's password:
Signed-off-by: Howard Chu <howardchu95@...il.com>
Tested-by: Arnaldo Carvalho de Melo <acme@...hat.com>
Cc: Adrian Hunter <adrian.hunter@...el.com>
Cc: Ian Rogers <irogers@...gle.com>
Cc: Jiri Olsa <jolsa@...nel.org>
Cc: Kan Liang <kan.liang@...ux.intel.com>
Cc: Namhyung Kim <namhyung@...nel.org>
Link: https://lore.kernel.org/r/20240815013626.935097-10-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>
---
.../bpf_skel/augmented_raw_syscalls.bpf.c | 114 +++++++++++++++++-
1 file changed, 113 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 0acbd74e8c76..f29a8dfca044 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -7,6 +7,8 @@
*/
#include "vmlinux.h"
+#include "../trace_augment.h"
+
#include <bpf/bpf_helpers.h>
#include <linux/limits.h>
@@ -124,6 +126,25 @@ struct augmented_args_tmp {
__uint(max_entries, 1);
} augmented_args_tmp SEC(".maps");
+struct beauty_payload_enter {
+ struct syscall_enter_args args;
+ struct augmented_arg aug_args[6];
+};
+
+struct beauty_map_enter {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, int);
+ __type(value, __u32[6]);
+ __uint(max_entries, 512);
+} beauty_map_enter SEC(".maps");
+
+struct beauty_payload_enter_map {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __type(key, int);
+ __type(value, struct beauty_payload_enter);
+ __uint(max_entries, 1);
+} beauty_payload_enter_map SEC(".maps");
+
static inline struct augmented_args_payload *augmented_args_payload(void)
{
int key = 0;
@@ -136,6 +157,11 @@ static inline int augmented__output(void *ctx, struct augmented_args_payload *ar
return bpf_perf_event_output(ctx, &__augmented_syscalls__, BPF_F_CURRENT_CPU, args, len);
}
+static inline int augmented__beauty_output(void *ctx, void *data, int len)
+{
+ return bpf_perf_event_output(ctx, &__augmented_syscalls__, BPF_F_CURRENT_CPU, data, len);
+}
+
static inline
unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const void *arg, unsigned int arg_len)
{
@@ -372,6 +398,91 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid)
return bpf_map_lookup_elem(pids, &pid) != NULL;
}
+static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
+{
+ bool augmented, do_output = false;
+ int zero = 0, size, aug_size, index, output = 0,
+ value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value);
+ unsigned int nr, *beauty_map;
+ struct beauty_payload_enter *payload;
+ void *arg, *payload_offset;
+
+ /* fall back to do predefined tail call */
+ if (args == NULL)
+ return 1;
+
+ /* use syscall number to get beauty_map entry */
+ nr = (__u32)args->syscall_nr;
+ beauty_map = bpf_map_lookup_elem(&beauty_map_enter, &nr);
+
+ /* set up payload for output */
+ payload = bpf_map_lookup_elem(&beauty_payload_enter_map, &zero);
+ payload_offset = (void *)&payload->aug_args;
+
+ if (beauty_map == NULL || payload == NULL)
+ return 1;
+
+ /* copy the sys_enter header, which has the syscall_nr */
+ __builtin_memcpy(&payload->args, args, sizeof(struct syscall_enter_args));
+
+ /*
+ * Determine what type of argument and how many bytes to read from user space, using the
+ * value in the beauty_map. This is the relation of parameter type and its corresponding
+ * value in the beauty map, and how many bytes we read eventually:
+ *
+ * string: 1 -> size of string
+ * struct: size of struct -> size of struct
+ * buffer: -1 * (index of paired len) -> value of paired len (maximum: TRACE_AUG_MAX_BUF)
+ */
+ for (int i = 0; i < 6; i++) {
+ arg = (void *)args->args[i];
+ augmented = false;
+ size = beauty_map[i];
+ aug_size = size; /* size of the augmented data read from user space */
+
+ if (size == 0 || arg == NULL)
+ continue;
+
+ if (size == 1) { /* string */
+ aug_size = bpf_probe_read_user_str(((struct augmented_arg *)payload_offset)->value, value_size, arg);
+ /* minimum of 0 to pass the verifier */
+ if (aug_size < 0)
+ aug_size = 0;
+
+ augmented = true;
+ } else if (size > 0 && size <= value_size) { /* struct */
+ if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, size, arg))
+ augmented = true;
+ } else if (size < 0 && size >= -6) { /* buffer */
+ index = -(size + 1);
+ aug_size = args->args[index];
+
+ if (aug_size > TRACE_AUG_MAX_BUF)
+ aug_size = TRACE_AUG_MAX_BUF;
+
+ if (aug_size > 0) {
+ if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, aug_size, arg))
+ augmented = true;
+ }
+ }
+
+ /* write data to payload */
+ if (augmented) {
+ int written = offsetof(struct augmented_arg, value) + aug_size;
+
+ ((struct augmented_arg *)payload_offset)->size = aug_size;
+ output += written;
+ payload_offset += written;
+ do_output = true;
+ }
+ }
+
+ if (!do_output)
+ return 1;
+
+ return augmented__beauty_output(ctx, payload, sizeof(struct syscall_enter_args) + output);
+}
+
SEC("tp/raw_syscalls/sys_enter")
int sys_enter(struct syscall_enter_args *args)
{
@@ -400,7 +511,8 @@ int sys_enter(struct syscall_enter_args *args)
* "!raw_syscalls:unaugmented" that will just return 1 to return the
* unaugmented tracepoint payload.
*/
- bpf_tail_call(args, &syscalls_sys_enter, augmented_args->args.syscall_nr);
+ if (augment_sys_enter(args, &augmented_args->args))
+ bpf_tail_call(args, &syscalls_sys_enter, augmented_args->args.syscall_nr);
// If not found on the PROG_ARRAY syscalls map, then we're filtering it:
return 0;
--
2.45.2
Powered by blists - more mailing lists