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.

Signed-off-by: Jiawei Zhao <[e-mail]>
Signed-off-by: Andrii Nakryiko <[e-mail]>
Link: https://lore.kernel.org/bpf/[e-mail]

tools/lib/bpf/usdt.bpf.h

···
 	BPF_USDT_ARG_CONST,
 	BPF_USDT_ARG_REG,
 	BPF_USDT_ARG_REG_DEREF,
+	BPF_USDT_ARG_SIB,
 };
 
+/*
+ * This struct layout is designed specifically to be backwards/forward
+ * compatible between libbpf versions for ARG_CONST, ARG_REG, and
+ * ARG_REG_DEREF modes. ARG_SIB requires libbpf v1.7+.
+ */
 struct __bpf_usdt_arg_spec {
 	/* u64 scalar interpreted depending on arg_type, see below */
 	__u64 val_off;
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	/* arg location case, see bpf_usdt_arg() for details */
-	enum __bpf_usdt_arg_type arg_type;
+	enum __bpf_usdt_arg_type arg_type: 8;
+	/* index register offset within struct pt_regs */
+	__u16 idx_reg_off: 12;
+	/* scale factor for index register (1, 2, 4, or 8) */
+	__u16 scale_bitshift: 4;
+	/* reserved for future use, keeps reg_off offset stable */
+	__u8 __reserved: 8;
+#else
+	__u8 __reserved: 8;
+	__u16 idx_reg_off: 12;
+	__u16 scale_bitshift: 4;
+	enum __bpf_usdt_arg_type arg_type: 8;
+#endif
 	/* offset of referenced register within struct pt_regs */
 	short reg_off;
 	/* whether arg should be interpreted as signed value */
···
 {
 	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;
···
 		if (err)
 			return err;
 		err = bpf_probe_read_user(&val, sizeof(val), (void *)val + arg_spec->val_off);
+		if (err)
+			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). We first
+		 * fetch the base register contents and the index register
+		 * contents from pt_regs. Then we calculate the final address
+		 * as base + (index * scale) + offset, and do a user-space
+		 * probe read to fetch the argument value.
+		 */
+		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_bitshift) + arg_spec->val_off));
 		if (err)
 			return err;
 #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__

tools/lib/bpf/usdt.c

···
 	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;
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	enum usdt_arg_type arg_type: 8;
+	__u16	idx_reg_off: 12;
+	__u16	scale_bitshift: 4;
+	__u8 __reserved: 8;     /* keep reg_off offset stable */
+#else
+	__u8 __reserved: 8;     /* keep reg_off offset stable */
+	__u16	idx_reg_off: 12;
+	__u16	scale_bitshift: 4;
+	enum usdt_arg_type arg_type: 8;
+#endif
 	short reg_off;
 	bool arg_signed;
 	char arg_bitshift;
···
 
 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;
-	long off;
+	char reg_name[16] = {0}, idx_reg_name[16] = {0};
+	int len, reg_off, idx_reg_off, scale = 1;
+	long off = 0;
 
-	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 ||
+		sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^,] , %d ) %n",
+		       arg_sz, reg_name, idx_reg_name, &scale, &len) == 4 ||
+		sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^)] ) %n",
+		       arg_sz, &off, reg_name, idx_reg_name, &len) == 4 ||
+		sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^)] ) %n",
+		       arg_sz, reg_name, idx_reg_name, &len) == 3
+		) {
+		/*
+		 * Scale Index Base case:
+		 * 1@-96(%rbp,%rax,8)
+		 * 1@(%rbp,%rax,8)
+		 * 1@-96(%rbp,%rax)
+		 * 1@(%rbp,%rax)
+		 */
+		arg->arg_type = USDT_ARG_SIB;
+		arg->val_off = off;
+
+		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;
+
+		/* validate scale factor and set fields directly */
+		switch (scale) {
+		case 1: arg->scale_bitshift = 0; break;
+		case 2: arg->scale_bitshift = 1; break;
+		case 4: arg->scale_bitshift = 2; break;
+		case 8: arg->scale_bitshift = 3; break;
+		default:
+			pr_warn("usdt: invalid SIB scale %d, expected 1, 2, 4, 8\n", scale);
+			return -EINVAL;
+		}
+	} 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;
···
 	} else if (sscanf(arg_str, " %d @ %%%15s %n", arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -4@%eax */
 		arg->arg_type = USDT_ARG_REG;
+		/* register read has no memory offset */
 		arg->val_off = 0;
 
 		reg_off = calc_pt_regs_off(reg_name);