summaryrefslogtreecommitdiff
path: root/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c')
-rw-r--r--tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c252
1 files changed, 211 insertions, 41 deletions
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 2872f9bc0785..e4352881e3fa 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -7,9 +7,14 @@
*/
#include "vmlinux.h"
+#include "../trace_augment.h"
+
#include <bpf/bpf_helpers.h>
#include <linux/limits.h>
+#define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
+#define __PERF_ALIGN_MASK(x, mask) (((x)+(mask))&~(mask))
+
/**
* is_power_of_2() - check if a value is a power of two
* @n: the value to check
@@ -66,19 +71,6 @@ struct syscall_exit_args {
long ret;
};
-struct augmented_arg {
- unsigned int size;
- int err;
- char value[PATH_MAX];
-};
-
-struct pids_filtered {
- __uint(type, BPF_MAP_TYPE_HASH);
- __type(key, pid_t);
- __type(value, bool);
- __uint(max_entries, 64);
-} pids_filtered SEC(".maps");
-
/*
* Desired design of maximum size and alignment (see RFC2553)
*/
@@ -105,17 +97,27 @@ struct sockaddr_storage {
};
};
-struct augmented_args_payload {
- struct syscall_enter_args args;
- union {
- struct {
- struct augmented_arg arg, arg2;
- };
+struct augmented_arg {
+ unsigned int size;
+ int err;
+ union {
+ char value[PATH_MAX];
struct sockaddr_storage saddr;
- char __data[sizeof(struct augmented_arg)];
};
};
+struct pids_filtered {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, pid_t);
+ __type(value, bool);
+ __uint(max_entries, 64);
+} pids_filtered SEC(".maps");
+
+struct augmented_args_payload {
+ struct syscall_enter_args args;
+ struct augmented_arg arg, arg2; // We have to reserve space for two arguments (rename, etc)
+};
+
// We need more tmp space than the BPF stack can give us
struct augmented_args_tmp {
__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
@@ -124,6 +126,25 @@ struct augmented_args_tmp {
__uint(max_entries, 1);
} augmented_args_tmp SEC(".maps");
+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 {
+ 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;
@@ -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)
{
@@ -182,15 +208,17 @@ int sys_enter_connect(struct syscall_enter_args *args)
struct augmented_args_payload *augmented_args = augmented_args_payload();
const void *sockaddr_arg = (const void *)args->args[1];
unsigned int socklen = args->args[2];
- unsigned int len = sizeof(augmented_args->args);
+ unsigned int len = sizeof(u64) + sizeof(augmented_args->args); // the size + err in all 'augmented_arg' structs
if (augmented_args == NULL)
return 1; /* Failure: don't filter */
- _Static_assert(is_power_of_2(sizeof(augmented_args->saddr)), "sizeof(augmented_args->saddr) needs to be a power of two");
- socklen &= sizeof(augmented_args->saddr) - 1;
+ _Static_assert(is_power_of_2(sizeof(augmented_args->arg.saddr)), "sizeof(augmented_args->arg.saddr) needs to be a power of two");
+ socklen &= sizeof(augmented_args->arg.saddr) - 1;
- bpf_probe_read_user(&augmented_args->saddr, socklen, sockaddr_arg);
+ bpf_probe_read_user(&augmented_args->arg.saddr, socklen, sockaddr_arg);
+ augmented_args->arg.size = socklen;
+ augmented_args->arg.err = 0;
return augmented__output(args, augmented_args, len + socklen);
}
@@ -201,14 +229,14 @@ int sys_enter_sendto(struct syscall_enter_args *args)
struct augmented_args_payload *augmented_args = augmented_args_payload();
const void *sockaddr_arg = (const void *)args->args[4];
unsigned int socklen = args->args[5];
- unsigned int len = sizeof(augmented_args->args);
+ unsigned int len = sizeof(u64) + sizeof(augmented_args->args); // the size + err in all 'augmented_arg' structs
if (augmented_args == NULL)
return 1; /* Failure: don't filter */
- socklen &= sizeof(augmented_args->saddr) - 1;
+ socklen &= sizeof(augmented_args->arg.saddr) - 1;
- bpf_probe_read_user(&augmented_args->saddr, socklen, sockaddr_arg);
+ bpf_probe_read_user(&augmented_args->arg.saddr, socklen, sockaddr_arg);
return augmented__output(args, augmented_args, len + socklen);
}
@@ -249,30 +277,58 @@ int sys_enter_rename(struct syscall_enter_args *args)
struct augmented_args_payload *augmented_args = augmented_args_payload();
const void *oldpath_arg = (const void *)args->args[0],
*newpath_arg = (const void *)args->args[1];
- unsigned int len = sizeof(augmented_args->args), oldpath_len;
+ unsigned int len = sizeof(augmented_args->args), oldpath_len, newpath_len;
if (augmented_args == NULL)
return 1; /* Failure: don't filter */
+ len += 2 * sizeof(u64); // The overhead of size and err, just before the payload...
+
oldpath_len = augmented_arg__read_str(&augmented_args->arg, oldpath_arg, sizeof(augmented_args->arg.value));
- len += oldpath_len + augmented_arg__read_str((void *)(&augmented_args->arg) + oldpath_len, newpath_arg, sizeof(augmented_args->arg.value));
+ augmented_args->arg.size = PERF_ALIGN(oldpath_len + 1, sizeof(u64));
+ len += augmented_args->arg.size;
+
+ /* Every read from userspace is limited to value size */
+ if (augmented_args->arg.size > sizeof(augmented_args->arg.value))
+ return 1; /* Failure: don't filter */
+
+ struct augmented_arg *arg2 = (void *)&augmented_args->arg.value + augmented_args->arg.size;
+
+ newpath_len = augmented_arg__read_str(arg2, newpath_arg, sizeof(augmented_args->arg.value));
+ arg2->size = newpath_len;
+
+ len += newpath_len;
return augmented__output(args, augmented_args, len);
}
-SEC("tp/syscalls/sys_enter_renameat")
-int sys_enter_renameat(struct syscall_enter_args *args)
+SEC("tp/syscalls/sys_enter_renameat2")
+int sys_enter_renameat2(struct syscall_enter_args *args)
{
struct augmented_args_payload *augmented_args = augmented_args_payload();
const void *oldpath_arg = (const void *)args->args[1],
*newpath_arg = (const void *)args->args[3];
- unsigned int len = sizeof(augmented_args->args), oldpath_len;
+ unsigned int len = sizeof(augmented_args->args), oldpath_len, newpath_len;
if (augmented_args == NULL)
return 1; /* Failure: don't filter */
+ len += 2 * sizeof(u64); // The overhead of size and err, just before the payload...
+
oldpath_len = augmented_arg__read_str(&augmented_args->arg, oldpath_arg, sizeof(augmented_args->arg.value));
- len += oldpath_len + augmented_arg__read_str((void *)(&augmented_args->arg) + oldpath_len, newpath_arg, sizeof(augmented_args->arg.value));
+ augmented_args->arg.size = PERF_ALIGN(oldpath_len + 1, sizeof(u64));
+ len += augmented_args->arg.size;
+
+ /* Every read from userspace is limited to value size */
+ if (augmented_args->arg.size > sizeof(augmented_args->arg.value))
+ return 1; /* Failure: don't filter */
+
+ struct augmented_arg *arg2 = (void *)&augmented_args->arg.value + augmented_args->arg.size;
+
+ newpath_len = augmented_arg__read_str(arg2, newpath_arg, sizeof(augmented_args->arg.value));
+ arg2->size = newpath_len;
+
+ len += newpath_len;
return augmented__output(args, augmented_args, len);
}
@@ -293,26 +349,26 @@ int sys_enter_perf_event_open(struct syscall_enter_args *args)
{
struct augmented_args_payload *augmented_args = augmented_args_payload();
const struct perf_event_attr_size *attr = (const struct perf_event_attr_size *)args->args[0], *attr_read;
- unsigned int len = sizeof(augmented_args->args);
+ unsigned int len = sizeof(u64) + sizeof(augmented_args->args); // the size + err in all 'augmented_arg' structs
if (augmented_args == NULL)
goto failure;
- if (bpf_probe_read_user(&augmented_args->__data, sizeof(*attr), attr) < 0)
+ if (bpf_probe_read_user(&augmented_args->arg.value, sizeof(*attr), attr) < 0)
goto failure;
- attr_read = (const struct perf_event_attr_size *)augmented_args->__data;
+ attr_read = (const struct perf_event_attr_size *)augmented_args->arg.value;
__u32 size = attr_read->size;
if (!size)
size = PERF_ATTR_SIZE_VER0;
- if (size > sizeof(augmented_args->__data))
+ if (size > sizeof(augmented_args->arg.value))
goto failure;
// Now that we read attr->size and tested it against the size limits, read it completely
- if (bpf_probe_read_user(&augmented_args->__data, size, attr) < 0)
+ if (bpf_probe_read_user(&augmented_args->arg.value, size, attr) < 0)
goto failure;
return augmented__output(args, augmented_args, len + size);
@@ -325,16 +381,37 @@ int sys_enter_clock_nanosleep(struct syscall_enter_args *args)
{
struct augmented_args_payload *augmented_args = augmented_args_payload();
const void *rqtp_arg = (const void *)args->args[2];
+ unsigned int len = sizeof(u64) + sizeof(augmented_args->args); // the size + err in all 'augmented_arg' structs
+ __u32 size = sizeof(struct timespec64);
+
+ if (augmented_args == NULL)
+ goto failure;
+
+ if (size > sizeof(augmented_args->arg.value))
+ goto failure;
+
+ bpf_probe_read_user(&augmented_args->arg.value, size, rqtp_arg);
+
+ return augmented__output(args, augmented_args, len + size);
+failure:
+ return 1; /* Failure: don't filter */
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int sys_enter_nanosleep(struct syscall_enter_args *args)
+{
+ struct augmented_args_payload *augmented_args = augmented_args_payload();
+ const void *req_arg = (const void *)args->args[0];
unsigned int len = sizeof(augmented_args->args);
__u32 size = sizeof(struct timespec64);
if (augmented_args == NULL)
goto failure;
- if (size > sizeof(augmented_args->__data))
+ if (size > sizeof(augmented_args->arg.value))
goto failure;
- bpf_probe_read_user(&augmented_args->__data, size, rqtp_arg);
+ bpf_probe_read_user(&augmented_args->arg.value, size, req_arg);
return augmented__output(args, augmented_args, len + size);
failure:
@@ -351,6 +428,98 @@ 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, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value);
+ u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */
+ s64 aug_size, size;
+ 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 ((int)size < 0 && size >= -6) { /* buffer */
+ index = -(size + 1);
+ barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick.
+ index &= 7; // Satisfy the bounds checking with the verifier in some kernels.
+ aug_size = args->args[index] > TRACE_AUG_MAX_BUF ? TRACE_AUG_MAX_BUF : args->args[index];
+
+ if (aug_size > 0) {
+ if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, aug_size, arg))
+ augmented = true;
+ }
+ }
+
+ /* Augmented data size is limited to sizeof(augmented_arg->unnamed union with value field) */
+ if (aug_size > value_size)
+ aug_size = value_size;
+
+ /* write data to payload */
+ if (augmented) {
+ int written = offsetof(struct augmented_arg, value) + aug_size;
+
+ if (written < 0 || written > sizeof(struct augmented_arg))
+ return 1;
+
+ ((struct augmented_arg *)payload_offset)->size = aug_size;
+ output += written;
+ payload_offset += written;
+ do_output = true;
+ }
+ }
+
+ if (!do_output || (sizeof(struct syscall_enter_args) + output) > sizeof(struct beauty_payload_enter))
+ 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)
{
@@ -379,7 +548,8 @@ 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;
generated by cgit (git 2.34.1) at 2025-07-24 01:48:43 +0000