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.

Signed-off-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240815013626.935097-10-howardchu95@gmail.com
Link: https://lore.kernel.org/r/20240824163322.60796-7-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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 4ebce67637435192b2d364d91cdd336cc77046b7..b2f17cca014bcff47fb84e15aaacb80ffec011d9 100644 (file)
--- 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>
 
@@ -131,6 +133,18 @@ struct beauty_map_enter {
        __uint(max_entries, 512);
 } beauty_map_enter SEC(".maps");
 
+struct beauty_payload_enter {
+       struct syscall_enter_args args;
+       struct augmented_arg aug_args[6];
+};
+
+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;
@@ -143,6 +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)
 {
@@ -401,6 +420,91 @@ 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)
 {
@@ -429,7 +533,8 @@ 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;