Merge branch 'libbpf: usdt arm arg parsing support'

Puranjay Mohan says:

====================

This series add the support of the ARM architecture to libbpf USDT. This
involves implementing the parse_usdt_arg() function for ARM.

It was seen that the last part of parse_usdt_arg() is repeated for all architectures,
so, the first patch in this series refactors these functions and moved the post
processing to parse_usdt_spec()

Changes in V2[1] to V3:

- Use a tabular approach to find register offsets.
- Add the patch for refactoring parse_usdt_arg()
====================
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

tools/lib/bpf/usdt.c

@@ -1141,12 +1141,13 @@ static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr,
 	return 0;
 }
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg);
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz);
 
 static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie)
 {
+	struct usdt_arg_spec *arg;
 	const char *s;
-	int len;
+	int arg_sz, len;
 
 	spec->usdt_cookie = usdt_cookie;
 	spec->arg_cnt = 0;
@@ -1159,10 +1160,25 @@ static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note,
 			return -E2BIG;
 		}
 
-		len = parse_usdt_arg(s, spec->arg_cnt, &spec->args[spec->arg_cnt]);
+		arg = &spec->args[spec->arg_cnt];
+		len = parse_usdt_arg(s, spec->arg_cnt, arg, &arg_sz);
 		if (len < 0)
 			return len;
 
+		arg->arg_signed = arg_sz < 0;
+		if (arg_sz < 0)
+			arg_sz = -arg_sz;
+
+		switch (arg_sz) {
+		case 1: case 2: case 4: case 8:
+			arg->arg_bitshift = 64 - arg_sz * 8;
+			break;
+		default:
+			pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
+				spec->arg_cnt, s, arg_sz);
+			return -EINVAL;
+		}
+
 		s += len;
 		spec->arg_cnt++;
 	}
@@ -1219,13 +1235,13 @@ static int calc_pt_regs_off(const char *reg_name)
 	return -ENOENT;
 }
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+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 arg_sz, len, reg_off;
+	int len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", &arg_sz, &off, reg_name, &len) == 3) {
+	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;
@@ -1233,7 +1249,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ ( %%%15[^)] ) %n", &arg_sz, reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ ( %%%15[^)] ) %n", arg_sz, reg_name, &len) == 2) {
 		/* Memory dereference case without offset, e.g., 8@(%rsp) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = 0;
@@ -1241,7 +1257,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ %%%15s %n", &arg_sz, reg_name, &len) == 2) {
+	} 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;
 		arg->val_off = 0;
@@ -1250,7 +1266,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ $%ld %n", &arg_sz, &off, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ $%ld %n", arg_sz, &off, &len) == 2) {
 		/* Constant value case, e.g., 4@$71 */
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
@@ -1260,20 +1276,6 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		return -EINVAL;
 	}
 
-	arg->arg_signed = arg_sz < 0;
-	if (arg_sz < 0)
-		arg_sz = -arg_sz;
-
-	switch (arg_sz) {
-	case 1: case 2: case 4: case 8:
-		arg->arg_bitshift = 64 - arg_sz * 8;
-		break;
-	default:
-		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
-			arg_num, arg_str, arg_sz);
-		return -EINVAL;
-	}
-
 	return len;
 }
 
@@ -1281,13 +1283,13 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 
 /* Do not support __s390__ for now, since user_pt_regs is broken with -m31. */
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
 {
 	unsigned int reg;
-	int arg_sz, len;
+	int len;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %%r%u ) %n", &arg_sz, &off, &reg, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %%r%u ) %n", arg_sz, &off, &reg, &len) == 3) {
 		/* Memory dereference case, e.g., -2@-28(%r15) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
@@ -1296,7 +1298,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 			return -EINVAL;
 		}
 		arg->reg_off = offsetof(user_pt_regs, gprs[reg]);
-	} else if (sscanf(arg_str, " %d @ %%r%u %n", &arg_sz, &reg, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %%r%u %n", arg_sz, &reg, &len) == 2) {
 		/* Register read case, e.g., -8@%r0 */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
@@ -1305,7 +1307,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 			return -EINVAL;
 		}
 		arg->reg_off = offsetof(user_pt_regs, gprs[reg]);
-	} else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %ld %n", arg_sz, &off, &len) == 2) {
 		/* Constant value case, e.g., 4@71 */
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
@@ -1315,20 +1317,6 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		return -EINVAL;
 	}
 
-	arg->arg_signed = arg_sz < 0;
-	if (arg_sz < 0)
-		arg_sz = -arg_sz;
-
-	switch (arg_sz) {
-	case 1: case 2: case 4: case 8:
-		arg->arg_bitshift = 64 - arg_sz * 8;
-		break;
-	default:
-		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
-			arg_num, arg_str, arg_sz);
-		return -EINVAL;
-	}
-
 	return len;
 }
 
@@ -1348,13 +1336,13 @@ static int calc_pt_regs_off(const char *reg_name)
 	return -ENOENT;
 }
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+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 arg_sz, len, reg_off;
+	int len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ \[ %15[a-z0-9], %ld ] %n", &arg_sz, reg_name, &off, &len) == 3) {
+	if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] , %ld ] %n", arg_sz, reg_name, &off, &len) == 3) {
 		/* Memory dereference case, e.g., -4@[sp, 96] */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
@@ -1362,7 +1350,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", &arg_sz, reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", arg_sz, reg_name, &len) == 2) {
 		/* Memory dereference case, e.g., -4@[sp] */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = 0;
@@ -1370,12 +1358,12 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %ld %n", arg_sz, &off, &len) == 2) {
 		/* Constant value case, e.g., 4@5 */
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
 		arg->reg_off = 0;
-	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -8@x4 */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
@@ -1388,20 +1376,6 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		return -EINVAL;
 	}
 
-	arg->arg_signed = arg_sz < 0;
-	if (arg_sz < 0)
-		arg_sz = -arg_sz;
-
-	switch (arg_sz) {
-	case 1: case 2: case 4: case 8:
-		arg->arg_bitshift = 64 - arg_sz * 8;
-		break;
-	default:
-		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
-			arg_num, arg_str, arg_sz);
-		return -EINVAL;
-	}
-
 	return len;
 }
 
@@ -1456,13 +1430,13 @@ static int calc_pt_regs_off(const char *reg_name)
 	return -ENOENT;
 }
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+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 arg_sz, len, reg_off;
+	int len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %15[a-z0-9] ) %n", &arg_sz, &off, reg_name, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %15[a-z0-9] ) %n", arg_sz, &off, reg_name, &len) == 3) {
 		/* Memory dereference case, e.g., -8@-88(s0) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
@@ -1470,12 +1444,12 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %ld %n", arg_sz, &off, &len) == 2) {
 		/* Constant value case, e.g., 4@5 */
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
 		arg->reg_off = 0;
-	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -8@a1 */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
@@ -1488,17 +1462,83 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		return -EINVAL;
 	}
 
-	arg->arg_signed = arg_sz < 0;
-	if (arg_sz < 0)
-		arg_sz = -arg_sz;
+	return len;
+}
 
-	switch (arg_sz) {
-	case 1: case 2: case 4: case 8:
-		arg->arg_bitshift = 64 - arg_sz * 8;
-		break;
-	default:
-		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
-			arg_num, arg_str, arg_sz);
+#elif defined(__arm__)
+
+static int calc_pt_regs_off(const char *reg_name)
+{
+	static struct {
+		const char *name;
+		size_t pt_regs_off;
+	} reg_map[] = {
+		{ "r0", offsetof(struct pt_regs, uregs[0]) },
+		{ "r1", offsetof(struct pt_regs, uregs[1]) },
+		{ "r2", offsetof(struct pt_regs, uregs[2]) },
+		{ "r3", offsetof(struct pt_regs, uregs[3]) },
+		{ "r4", offsetof(struct pt_regs, uregs[4]) },
+		{ "r5", offsetof(struct pt_regs, uregs[5]) },
+		{ "r6", offsetof(struct pt_regs, uregs[6]) },
+		{ "r7", offsetof(struct pt_regs, uregs[7]) },
+		{ "r8", offsetof(struct pt_regs, uregs[8]) },
+		{ "r9", offsetof(struct pt_regs, uregs[9]) },
+		{ "r10", offsetof(struct pt_regs, uregs[10]) },
+		{ "fp", offsetof(struct pt_regs, uregs[11]) },
+		{ "ip", offsetof(struct pt_regs, uregs[12]) },
+		{ "sp", offsetof(struct pt_regs, uregs[13]) },
+		{ "lr", offsetof(struct pt_regs, uregs[14]) },
+		{ "pc", offsetof(struct pt_regs, uregs[15]) },
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(reg_map); i++) {
+		if (strcmp(reg_name, reg_map[i].name) == 0)
+			return reg_map[i].pt_regs_off;
+	}
+
+	pr_warn("usdt: unrecognized register '%s'\n", reg_name);
+	return -ENOENT;
+}
+
+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;
+
+	if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] , #%ld ] %n",
+		   arg_sz, reg_name, &off, &len) == 3) {
+		/* Memory dereference case, e.g., -4@[fp, #96] */
+		arg->arg_type = USDT_ARG_REG_DEREF;
+		arg->val_off = off;
+		reg_off = calc_pt_regs_off(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", arg_sz, reg_name, &len) == 2) {
+		/* Memory dereference case, e.g., -4@[sp] */
+		arg->arg_type = USDT_ARG_REG_DEREF;
+		arg->val_off = 0;
+		reg_off = calc_pt_regs_off(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else if (sscanf(arg_str, " %d @ #%ld %n", arg_sz, &off, &len) == 2) {
+		/* Constant value case, e.g., 4@#5 */
+		arg->arg_type = USDT_ARG_CONST;
+		arg->val_off = off;
+		arg->reg_off = 0;
+	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", arg_sz, reg_name, &len) == 2) {
+		/* Register read case, e.g., -8@r4 */
+		arg->arg_type = USDT_ARG_REG;
+		arg->val_off = 0;
+		reg_off = calc_pt_regs_off(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else {
+		pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str);
 		return -EINVAL;
 	}
 
@@ -1507,7 +1547,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 
 #else
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
 {
 	pr_warn("usdt: libbpf doesn't support USDTs on current architecture\n");
 	return -ENOTSUP;