libbpf: fix USDT SIB argument handling causing unrecognized register error

On x86-64, USDT arguments can be specified using Scale-Index-Base (SIB)
addressing, e.g. "1@-96(%rbp,%rax,8)". The current USDT implementation
in libbpf cannot parse this format, causing `bpf_program__attach_usdt()`
to fail with -ENOENT (unrecognized register).

This patch fixes this by implementing the necessary changes:
- add correct handling for SIB-addressed arguments in `bpf_usdt_arg`.
- add adaptive support to `__bpf_usdt_arg_type` and
`__bpf_usdt_arg_spec` to represent SIB addressing parameters.

Change since v1(https://lore.kernel.org/lkml/[email protected]/):
- refactor the code to make it more readable
- modify the commit message to explain why and how

Change since v2:
- fix the `scale` uninitialized error

Signed-off-by: Jiawei Zhao <[email protected]>

Author: Phoenix500526

tools/lib/bpf/usdt.bpf.h

@@ -34,6 +34,7 @@ enum __bpf_usdt_arg_type {
 	BPF_USDT_ARG_CONST,
 	BPF_USDT_ARG_REG,
 	BPF_USDT_ARG_REG_DEREF,
+	BPF_USDT_ARG_SIB,
 };
 
 struct __bpf_usdt_arg_spec {
@@ -43,6 +44,10 @@ struct __bpf_usdt_arg_spec {
 	enum __bpf_usdt_arg_type arg_type;
 	/* offset of referenced register within struct pt_regs */
 	short reg_off;
+	/* offset of index register in pt_regs, only used in SIB mode */
+	short idx_reg_off;
+	/* scale factor for index register, only used in SIB mode */
+	short scale;
 	/* whether arg should be interpreted as signed value */
 	bool arg_signed;
 	/* number of bits that need to be cleared and, optionally,
@@ -149,7 +154,7 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res)
 {
 	struct __bpf_usdt_spec *spec;
 	struct __bpf_usdt_arg_spec *arg_spec;
-	unsigned long val;
+	unsigned long val, idx;
 	int err, spec_id;
 
 	*res = 0;
@@ -202,6 +207,32 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res)
 			return err;
 #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 		val >>= arg_spec->arg_bitshift;
+#endif
+		break;
+	case BPF_USDT_ARG_SIB:
+		/* Arg is in memory addressed by SIB (Scale-Index-Base) mode
+		 * (e.g., "-1@-96(%rbp,%rax,8)" in USDT arg spec). Register
+		 * is identified like with BPF_USDT_ARG_SIB case, the offset
+		 * is in arg_spec->val_off, the scale factor is in arg_spec->scale.
+		 * Firstly, we fetch the base register contents and the index
+		 * register contents from pt_regs. Secondly, we multiply the
+		 * index register contents by the scale factor, then add the
+		 * base address and the offset to get the final address. Finally,
+		 * we do another user-space probe read to fetch argument value
+		 * itself.
+		 */
+		err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off);
+		if (err)
+			return err;
+		err = bpf_probe_read_kernel(&idx, sizeof(idx), (void *)ctx + arg_spec->idx_reg_off);
+		if (err)
+			return err;
+		err = bpf_probe_read_user(&val, sizeof(val),
+				(void *)val + idx * arg_spec->scale + arg_spec->val_off);
+		if (err)
+			return err;
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+		val >>= arg_spec->arg_bitshift;
 #endif
 		break;
 	default:

tools/lib/bpf/usdt.c

@@ -200,13 +200,16 @@ enum usdt_arg_type {
 	USDT_ARG_CONST,
 	USDT_ARG_REG,
 	USDT_ARG_REG_DEREF,
+	USDT_ARG_SIB,
 };
 
 /* should match exactly struct __bpf_usdt_arg_spec from usdt.bpf.h */
 struct usdt_arg_spec {
 	__u64 val_off;
 	enum usdt_arg_type arg_type;
 	short reg_off;
+	short idx_reg_off;
+	short scale;
 	bool arg_signed;
 	char arg_bitshift;
 };
@@ -1283,11 +1286,28 @@ static int calc_pt_regs_off(const char *reg_name)
 
 static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
 {
-	char reg_name[16];
-	int len, reg_off;
+	char reg_name[16], idx_reg_off, idx_reg_name[16];
+	int len, reg_off, scale;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", arg_sz, &off, reg_name, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^,] , %d ) %n",
+				arg_sz, &off, reg_name, idx_reg_name, &scale, &len) == 5) {
+		/* Scale Index Base case, e.g., 1@-96(%rbp,%rax,8)*/
+		arg->arg_type = USDT_ARG_SIB;
+		arg->val_off = off;
+		arg->scale = scale;
+
+		reg_off = calc_pt_regs_off(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+
+		idx_reg_off = calc_pt_regs_off(idx_reg_name);
+		if (idx_reg_off < 0)
+			return idx_reg_off;
+		arg->idx_reg_off = idx_reg_off;
+	} else if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n",
+				arg_sz, &off, reg_name, &len) == 3) {
 		/* Memory dereference case, e.g., -4@-20(%rbp) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;