Merge patch series "RISC-V: Probe DT extension support using riscv,isa-extensions & riscv,isa-base"

Conor Dooley <conor.dooley@microchip.com> says:

Based on my latest iteration of deprecating riscv,isa [1], here's an
implementation of the new properties for Linux. The first few patches,
up to "RISC-V: split riscv_fill_hwcap() in 3", are all prep work that
further tames some of the extension related code, on top of my already
applied series that cleans up the ISA string parser.
Perhaps "RISC-V: shunt isa_ext_arr to cpufeature.c" is a bit gratuitous,
but I figured a bit of coalescing of extension related data structures
would be a good idea. Note that riscv,isa will still be used in the
absence of the new properties. Palmer suggested adding a Kconfig option
to turn off the fallback for DT, which I have gone and done. It's locked
behind the NONPORTABLE option for good reason.

* b4-shazam-merge:
  RISC-V: provide Kconfig & commandline options to control parsing "riscv,isa"
  RISC-V: try new extension properties in of_early_processor_hartid()
  RISC-V: enable extension detection from dedicated properties
  RISC-V: split riscv_fill_hwcap() in 3
  RISC-V: add single letter extensions to riscv_isa_ext
  RISC-V: add missing single letter extension definitions
  RISC-V: repurpose riscv_isa_ext array in riscv_fill_hwcap()
  RISC-V: shunt isa_ext_arr to cpufeature.c
  RISC-V: drop a needless check in print_isa_ext()
  RISC-V: don't parse dt/acpi isa string to get rv32/rv64
  RISC-V: Provide a more helpful error message on invalid ISA strings

Link: https://lore.kernel.org/r/20230713-target-much-8ac624e90df8@wendy
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

4 files changed, 427 insertions, 298 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 4c07b9189c86..f52dd125ac5e 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -848,6 +848,24 @@ config XIP_PHYS_ADDR
 	  be linked for and stored to.  This address is dependent on your
 	  own flash usage.
 
+config RISCV_ISA_FALLBACK
+	bool "Permit falling back to parsing riscv,isa for extension support by default"
+	default y
+	help
+	  Parsing the "riscv,isa" devicetree property has been deprecated and
+	  replaced by a list of explicitly defined strings. For compatibility
+	  with existing platforms, the kernel will fall back to parsing the
+	  "riscv,isa" property if the replacements are not found.
+
+	  Selecting N here will result in a kernel that does not use the
+	  fallback, unless the commandline "riscv_isa_fallback" parameter is
+	  present.
+
+	  Please see the dt-binding, located at
+	  Documentation/devicetree/bindings/riscv/extensions.yaml for details
+	  on the replacement properties, "riscv,isa-base" and
+	  "riscv,isa-extensions".
+
 endmenu # "Boot options"
 
 config BUILTIN_DTB
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index f041bfa7f6a0..b7b58258f6c7 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -14,12 +14,17 @@
 #include <uapi/asm/hwcap.h>
 
 #define RISCV_ISA_EXT_a		('a' - 'a')
+#define RISCV_ISA_EXT_b		('b' - 'a')
 #define RISCV_ISA_EXT_c		('c' - 'a')
 #define RISCV_ISA_EXT_d		('d' - 'a')
 #define RISCV_ISA_EXT_f		('f' - 'a')
 #define RISCV_ISA_EXT_h		('h' - 'a')
 #define RISCV_ISA_EXT_i		('i' - 'a')
+#define RISCV_ISA_EXT_j		('j' - 'a')
+#define RISCV_ISA_EXT_k		('k' - 'a')
 #define RISCV_ISA_EXT_m		('m' - 'a')
+#define RISCV_ISA_EXT_p		('p' - 'a')
+#define RISCV_ISA_EXT_q		('q' - 'a')
 #define RISCV_ISA_EXT_s		('s' - 'a')
 #define RISCV_ISA_EXT_u		('u' - 'a')
 #define RISCV_ISA_EXT_v		('v' - 'a')
@@ -55,7 +60,6 @@
 #define RISCV_ISA_EXT_ZIHPM		42
 
 #define RISCV_ISA_EXT_MAX		64
-#define RISCV_ISA_EXT_NAME_LEN_MAX	32
 
 #ifdef CONFIG_RISCV_M_MODE
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SMAIA
@@ -70,12 +74,15 @@
 unsigned long riscv_get_elf_hwcap(void);
 
 struct riscv_isa_ext_data {
-	/* Name of the extension displayed to userspace via /proc/cpuinfo */
-	char uprop[RISCV_ISA_EXT_NAME_LEN_MAX];
-	/* The logical ISA extension ID */
-	unsigned int isa_ext_id;
+	const unsigned int id;
+	const char *name;
+	const char *property;
 };
 
+extern const struct riscv_isa_ext_data riscv_isa_ext[];
+extern const size_t riscv_isa_ext_count;
+extern bool riscv_isa_fallback;
+
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
 
 #define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext)
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index a2fc952318e9..208f1a700121 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -41,7 +41,7 @@ int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart)
 	return 0;
 }
 
-int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart)
+int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart)
 {
 	const char *isa;
 
@@ -61,16 +61,53 @@ int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *har
 		return -ENODEV;
 	}
 
+	if (of_property_read_string(node, "riscv,isa-base", &isa))
+		goto old_interface;
+
+	if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32i", 5)) {
+		pr_warn("CPU with hartid=%lu does not support rv32i", *hart);
+		return -ENODEV;
+	}
+
+	if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64i", 5)) {
+		pr_warn("CPU with hartid=%lu does not support rv64i", *hart);
+		return -ENODEV;
+	}
+
+	if (!of_property_present(node, "riscv,isa-extensions"))
+		return -ENODEV;
+
+	if (of_property_match_string(node, "riscv,isa-extensions", "i") < 0 ||
+	    of_property_match_string(node, "riscv,isa-extensions", "m") < 0 ||
+	    of_property_match_string(node, "riscv,isa-extensions", "a") < 0) {
+		pr_warn("CPU with hartid=%lu does not support ima", *hart);
+		return -ENODEV;
+	}
+
+	return 0;
+
+old_interface:
+	if (!riscv_isa_fallback) {
+		pr_warn("CPU with hartid=%lu is invalid: this kernel does not parse \"riscv,isa\"",
+			*hart);
+		return -ENODEV;
+	}
+
 	if (of_property_read_string(node, "riscv,isa", &isa)) {
-		pr_warn("CPU with hartid=%lu has no \"riscv,isa\" property\n", *hart);
+		pr_warn("CPU with hartid=%lu has no \"riscv,isa-base\" or \"riscv,isa\" property\n",
+			*hart);
 		return -ENODEV;
 	}
 
-	if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7))
+	if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7)) {
+		pr_warn("CPU with hartid=%lu does not support rv32ima", *hart);
 		return -ENODEV;
+	}
 
-	if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7))
+	if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) {
+		pr_warn("CPU with hartid=%lu does not support rv64ima", *hart);
 		return -ENODEV;
+	}
 
 	return 0;
 }
@@ -160,112 +197,26 @@ arch_initcall(riscv_cpuinfo_init);
 
 #ifdef CONFIG_PROC_FS
 
-#define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \
-	{							\
-		.uprop = #UPROP,				\
-		.isa_ext_id = EXTID,				\
-	}
-
-/*
- * The canonical order of ISA extension names in the ISA string is defined in
- * chapter 27 of the unprivileged specification.
- *
- * Ordinarily, for in-kernel data structures, this order is unimportant but
- * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo.
- *
- * The specification uses vague wording, such as should, when it comes to
- * ordering, so for our purposes the following rules apply:
- *
- * 1. All multi-letter extensions must be separated from other extensions by an
- *    underscore.
- *
- * 2. Additional standard extensions (starting with 'Z') must be sorted after
- *    single-letter extensions and before any higher-privileged extensions.
-
- * 3. The first letter following the 'Z' conventionally indicates the most
- *    closely related alphabetical extension category, IMAFDQLCBKJTPVH.
- *    If multiple 'Z' extensions are named, they must be ordered first by
- *    category, then alphabetically within a category.
- *
- * 3. Standard supervisor-level extensions (starting with 'S') must be listed
- *    after standard unprivileged extensions.  If multiple supervisor-level
- *    extensions are listed, they must be ordered alphabetically.
- *
- * 4. Standard machine-level extensions (starting with 'Zxm') must be listed
- *    after any lower-privileged, standard extensions.  If multiple
- *    machine-level extensions are listed, they must be ordered
- *    alphabetically.
- *
- * 5. Non-standard extensions (starting with 'X') must be listed after all
- *    standard extensions. If multiple non-standard extensions are listed, they
- *    must be ordered alphabetically.
- *
- * An example string following the order is:
- *    rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux
- *
- * New entries to this struct should follow the ordering rules described above.
- */
-static struct riscv_isa_ext_data isa_ext_arr[] = {
-	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
-	__RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ),
-	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
-	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
-	__RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI),
-	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
-	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
-	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
-	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
-	__RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS),
-	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
-	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
-	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
-	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
-	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
-	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
-	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
-	__RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX),
-};
-
-static void print_isa_ext(struct seq_file *f)
+static void print_isa(struct seq_file *f)
 {
-	struct riscv_isa_ext_data *edata;
-	int i = 0, arr_sz;
-
-	arr_sz = ARRAY_SIZE(isa_ext_arr) - 1;
+	seq_puts(f, "isa\t\t: ");
 
-	/* No extension support available */
-	if (arr_sz <= 0)
-		return;
+	if (IS_ENABLED(CONFIG_32BIT))
+		seq_write(f, "rv32", 4);
+	else
+		seq_write(f, "rv64", 4);
 
-	for (i = 0; i <= arr_sz; i++) {
-		edata = &isa_ext_arr[i];
-		if (!__riscv_isa_extension_available(NULL, edata->isa_ext_id))
+	for (int i = 0; i < riscv_isa_ext_count; i++) {
+		if (!__riscv_isa_extension_available(NULL, riscv_isa_ext[i].id))
 			continue;
-		seq_printf(f, "_%s", edata->uprop);
-	}
-}
 
-/*
- * These are the only valid base (single letter) ISA extensions as per the spec.
- * It also specifies the canonical order in which it appears in the spec.
- * Some of the extension may just be a place holder for now (B, K, P, J).
- * This should be updated once corresponding extensions are ratified.
- */
-static const char base_riscv_exts[13] = "imafdqcbkjpvh";
+		/* Only multi-letter extensions are split by underscores */
+		if (strnlen(riscv_isa_ext[i].name, 2) != 1)
+			seq_puts(f, "_");
 
-static void print_isa(struct seq_file *f, const char *isa)
-{
-	int i;
-
-	seq_puts(f, "isa\t\t: ");
-	/* Print the rv[64/32] part */
-	seq_write(f, isa, 4);
-	for (i = 0; i < sizeof(base_riscv_exts); i++) {
-		if (__riscv_isa_extension_available(NULL, base_riscv_exts[i] - 'a'))
-			/* Print only enabled the base ISA extensions */
-			seq_write(f, &base_riscv_exts[i], 1);
+		seq_printf(f, "%s", riscv_isa_ext[i].name);
 	}
-	print_isa_ext(f);
+
 	seq_puts(f, "\n");
 }
 
@@ -316,27 +267,21 @@ static int c_show(struct seq_file *m, void *v)
 	unsigned long cpu_id = (unsigned long)v - 1;
 	struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id);
 	struct device_node *node;
-	const char *compat, *isa;
+	const char *compat;
 
 	seq_printf(m, "processor\t: %lu\n", cpu_id);
 	seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id));
+	print_isa(m);
+	print_mmu(m);
 
 	if (acpi_disabled) {
 		node = of_get_cpu_node(cpu_id, NULL);
-		if (!of_property_read_string(node, "riscv,isa", &isa))
-			print_isa(m, isa);
 
-		print_mmu(m);
 		if (!of_property_read_string(node, "compatible", &compat) &&
 		    strcmp(compat, "riscv"))
 			seq_printf(m, "uarch\t\t: %s\n", compat);
 
 		of_node_put(node);
-	} else {
-		if (!acpi_get_riscv_isa(NULL, cpu_id, &isa))
-			print_isa(m, isa);
-
-		print_mmu(m);
 	}
 
 	seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid);
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index bdcf460ea53d..71fb840ee246 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -99,29 +99,252 @@ static bool riscv_isa_extension_check(int id)
 	return true;
 }
 
-void __init riscv_fill_hwcap(void)
+#define __RISCV_ISA_EXT_DATA(_name, _id) {	\
+	.name = #_name,				\
+	.property = #_name,			\
+	.id = _id,				\
+}
+
+/*
+ * The canonical order of ISA extension names in the ISA string is defined in
+ * chapter 27 of the unprivileged specification.
+ *
+ * Ordinarily, for in-kernel data structures, this order is unimportant but
+ * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo.
+ *
+ * The specification uses vague wording, such as should, when it comes to
+ * ordering, so for our purposes the following rules apply:
+ *
+ * 1. All multi-letter extensions must be separated from other extensions by an
+ *    underscore.
+ *
+ * 2. Additional standard extensions (starting with 'Z') must be sorted after
+ *    single-letter extensions and before any higher-privileged extensions.
+ *
+ * 3. The first letter following the 'Z' conventionally indicates the most
+ *    closely related alphabetical extension category, IMAFDQLCBKJTPVH.
+ *    If multiple 'Z' extensions are named, they must be ordered first by
+ *    category, then alphabetically within a category.
+ *
+ * 3. Standard supervisor-level extensions (starting with 'S') must be listed
+ *    after standard unprivileged extensions.  If multiple supervisor-level
+ *    extensions are listed, they must be ordered alphabetically.
+ *
+ * 4. Standard machine-level extensions (starting with 'Zxm') must be listed
+ *    after any lower-privileged, standard extensions.  If multiple
+ *    machine-level extensions are listed, they must be ordered
+ *    alphabetically.
+ *
+ * 5. Non-standard extensions (starting with 'X') must be listed after all
+ *    standard extensions. If multiple non-standard extensions are listed, they
+ *    must be ordered alphabetically.
+ *
+ * An example string following the order is:
+ *    rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux
+ *
+ * New entries to this struct should follow the ordering rules described above.
+ */
+const struct riscv_isa_ext_data riscv_isa_ext[] = {
+	__RISCV_ISA_EXT_DATA(i, RISCV_ISA_EXT_i),
+	__RISCV_ISA_EXT_DATA(m, RISCV_ISA_EXT_m),
+	__RISCV_ISA_EXT_DATA(a, RISCV_ISA_EXT_a),
+	__RISCV_ISA_EXT_DATA(f, RISCV_ISA_EXT_f),
+	__RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d),
+	__RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q),
+	__RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c),
+	__RISCV_ISA_EXT_DATA(b, RISCV_ISA_EXT_b),
+	__RISCV_ISA_EXT_DATA(k, RISCV_ISA_EXT_k),
+	__RISCV_ISA_EXT_DATA(j, RISCV_ISA_EXT_j),
+	__RISCV_ISA_EXT_DATA(p, RISCV_ISA_EXT_p),
+	__RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v),
+	__RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h),
+	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
+	__RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ),
+	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
+	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
+	__RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI),
+	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
+	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
+	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
+	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
+	__RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS),
+	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
+	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
+	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
+	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
+	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
+	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
+	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+};
+
+const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
+
+static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct riscv_isainfo *isainfo,
+					  unsigned long *isa2hwcap, const char *isa)
+{
+	/*
+	 * For all possible cpus, we have already validated in
+	 * the boot process that they at least contain "rv" and
+	 * whichever of "32"/"64" this kernel supports, and so this
+	 * section can be skipped.
+	 */
+	isa += 4;
+
+	while (*isa) {
+		const char *ext = isa++;
+		const char *ext_end = isa;
+		bool ext_long = false, ext_err = false;
+
+		switch (*ext) {
+		case 's':
+			/*
+			 * Workaround for invalid single-letter 's' & 'u'(QEMU).
+			 * No need to set the bit in riscv_isa as 's' & 'u' are
+			 * not valid ISA extensions. It works until multi-letter
+			 * extension starting with "Su" appears.
+			 */
+			if (ext[-1] != '_' && ext[1] == 'u') {
+				++isa;
+				ext_err = true;
+				break;
+			}
+			fallthrough;
+		case 'S':
+		case 'x':
+		case 'X':
+		case 'z':
+		case 'Z':
+			/*
+			 * Before attempting to parse the extension itself, we find its end.
+			 * As multi-letter extensions must be split from other multi-letter
+			 * extensions with an "_", the end of a multi-letter extension will
+			 * either be the null character or the "_" at the start of the next
+			 * multi-letter extension.
+			 *
+			 * Next, as the extensions version is currently ignored, we
+			 * eliminate that portion. This is done by parsing backwards from
+			 * the end of the extension, removing any numbers. This may be a
+			 * major or minor number however, so the process is repeated if a
+			 * minor number was found.
+			 *
+			 * ext_end is intended to represent the first character *after* the
+			 * name portion of an extension, but will be decremented to the last
+			 * character itself while eliminating the extensions version number.
+			 * A simple re-increment solves this problem.
+			 */
+			ext_long = true;
+			for (; *isa && *isa != '_'; ++isa)
+				if (unlikely(!isalnum(*isa)))
+					ext_err = true;
+
+			ext_end = isa;
+			if (unlikely(ext_err))
+				break;
+
+			if (!isdigit(ext_end[-1]))
+				break;
+
+			while (isdigit(*--ext_end))
+				;
+
+			if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) {
+				++ext_end;
+				break;
+			}
+
+			while (isdigit(*--ext_end))
+				;
+
+			++ext_end;
+			break;
+		default:
+			/*
+			 * Things are a little easier for single-letter extensions, as they
+			 * are parsed forwards.
+			 *
+			 * After checking that our starting position is valid, we need to
+			 * ensure that, when isa was incremented at the start of the loop,
+			 * that it arrived at the start of the next extension.
+			 *
+			 * If we are already on a non-digit, there is nothing to do. Either
+			 * we have a multi-letter extension's _, or the start of an
+			 * extension.
+			 *
+			 * Otherwise we have found the current extension's major version
+			 * number. Parse past it, and a subsequent p/minor version number
+			 * if present. The `p` extension must not appear immediately after
+			 * a number, so there is no fear of missing it.
+			 *
+			 */
+			if (unlikely(!isalpha(*ext))) {
+				ext_err = true;
+				break;
+			}
+
+			if (!isdigit(*isa))
+				break;
+
+			while (isdigit(*++isa))
+				;
+
+			if (tolower(*isa) != 'p')
+				break;
+
+			if (!isdigit(*++isa)) {
+				--isa;
+				break;
+			}
+
+			while (isdigit(*++isa))
+				;
+
+			break;
+		}
+
+		/*
+		 * The parser expects that at the start of an iteration isa points to the
+		 * first character of the next extension. As we stop parsing an extension
+		 * on meeting a non-alphanumeric character, an extra increment is needed
+		 * where the succeeding extension is a multi-letter prefixed with an "_".
+		 */
+		if (*isa == '_')
+			++isa;
+
+#define SET_ISA_EXT_MAP(name, bit)						\
+		do {								\
+			if ((ext_end - ext == strlen(name)) &&			\
+			     !strncasecmp(ext, name, strlen(name)) &&		\
+			     riscv_isa_extension_check(bit))			\
+				set_bit(bit, isainfo->isa);			\
+		} while (false)							\
+
+		if (unlikely(ext_err))
+			continue;
+		if (!ext_long) {
+			int nr = tolower(*ext) - 'a';
+
+			if (riscv_isa_extension_check(nr)) {
+				*this_hwcap |= isa2hwcap[nr];
+				set_bit(nr, isainfo->isa);
+			}
+		} else {
+			for (int i = 0; i < riscv_isa_ext_count; i++)
+				SET_ISA_EXT_MAP(riscv_isa_ext[i].name,
+						riscv_isa_ext[i].id);
+		}
+#undef SET_ISA_EXT_MAP
+	}
+}
+
+static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
 {
 	struct device_node *node;
 	const char *isa;
-	char print_str[NUM_ALPHA_EXTS + 1];
-	int i, j, rc;
-	unsigned long isa2hwcap[26] = {0};
+	int rc;
 	struct acpi_table_header *rhct;
 	acpi_status status;
 	unsigned int cpu;
 
-	isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I;
-	isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M;
-	isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A;
-	isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F;
-	isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D;
-	isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C;
-	isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V;
-
-	elf_hwcap = 0;
-
-	bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX);
-
 	if (!acpi_disabled) {
 		status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct);
 		if (ACPI_FAILURE(status))
@@ -153,169 +376,7 @@ void __init riscv_fill_hwcap(void)
 			}
 		}
 
-		/*
-		 * For all possible cpus, we have already validated in
-		 * the boot process that they at least contain "rv" and
-		 * whichever of "32"/"64" this kernel supports, and so this
-		 * section can be skipped.
-		 */
-		isa += 4;
-
-		while (*isa) {
-			const char *ext = isa++;
-			const char *ext_end = isa;
-			bool ext_long = false, ext_err = false;
-
-			switch (*ext) {
-			case 's':
-				/*
-				 * Workaround for invalid single-letter 's' & 'u'(QEMU).
-				 * No need to set the bit in riscv_isa as 's' & 'u' are
-				 * not valid ISA extensions. It works until multi-letter
-				 * extension starting with "Su" appears.
-				 */
-				if (ext[-1] != '_' && ext[1] == 'u') {
-					++isa;
-					ext_err = true;
-					break;
-				}
-				fallthrough;
-			case 'S':
-			case 'x':
-			case 'X':
-			case 'z':
-			case 'Z':
-				/*
-				 * Before attempting to parse the extension itself, we find its end.
-				 * As multi-letter extensions must be split from other multi-letter
-				 * extensions with an "_", the end of a multi-letter extension will
-				 * either be the null character or the "_" at the start of the next
-				 * multi-letter extension.
-				 *
-				 * Next, as the extensions version is currently ignored, we
-				 * eliminate that portion. This is done by parsing backwards from
-				 * the end of the extension, removing any numbers. This may be a
-				 * major or minor number however, so the process is repeated if a
-				 * minor number was found.
-				 *
-				 * ext_end is intended to represent the first character *after* the
-				 * name portion of an extension, but will be decremented to the last
-				 * character itself while eliminating the extensions version number.
-				 * A simple re-increment solves this problem.
-				 */
-				ext_long = true;
-				for (; *isa && *isa != '_'; ++isa)
-					if (unlikely(!isalnum(*isa)))
-						ext_err = true;
-
-				ext_end = isa;
-				if (unlikely(ext_err))
-					break;
-
-				if (!isdigit(ext_end[-1]))
-					break;
-
-				while (isdigit(*--ext_end))
-					;
-
-				if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) {
-					++ext_end;
-					break;
-				}
-
-				while (isdigit(*--ext_end))
-					;
-
-				++ext_end;
-				break;
-			default:
-				/*
-				 * Things are a little easier for single-letter extensions, as they
-				 * are parsed forwards.
-				 *
-				 * After checking that our starting position is valid, we need to
-				 * ensure that, when isa was incremented at the start of the loop,
-				 * that it arrived at the start of the next extension.
-				 *
-				 * If we are already on a non-digit, there is nothing to do. Either
-				 * we have a multi-letter extension's _, or the start of an
-				 * extension.
-				 *
-				 * Otherwise we have found the current extension's major version
-				 * number. Parse past it, and a subsequent p/minor version number
-				 * if present. The `p` extension must not appear immediately after
-				 * a number, so there is no fear of missing it.
-				 *
-				 */
-				if (unlikely(!isalpha(*ext))) {
-					ext_err = true;
-					break;
-				}
-
-				if (!isdigit(*isa))
-					break;
-
-				while (isdigit(*++isa))
-					;
-
-				if (tolower(*isa) != 'p')
-					break;
-
-				if (!isdigit(*++isa)) {
-					--isa;
-					break;
-				}
-
-				while (isdigit(*++isa))
-					;
-
-				break;
-			}
-
-			/*
-			 * The parser expects that at the start of an iteration isa points to the
-			 * first character of the next extension. As we stop parsing an extension
-			 * on meeting a non-alphanumeric character, an extra increment is needed
-			 * where the succeeding extension is a multi-letter prefixed with an "_".
-			 */
-			if (*isa == '_')
-				++isa;
-
-#define SET_ISA_EXT_MAP(name, bit)							\
-			do {								\
-				if ((ext_end - ext == sizeof(name) - 1) &&		\
-				     !strncasecmp(ext, name, sizeof(name) - 1) &&	\
-				     riscv_isa_extension_check(bit))			\
-					set_bit(bit, isainfo->isa);			\
-			} while (false)							\
-
-			if (unlikely(ext_err))
-				continue;
-			if (!ext_long) {
-				int nr = tolower(*ext) - 'a';
-
-				if (riscv_isa_extension_check(nr)) {
-					this_hwcap |= isa2hwcap[nr];
-					set_bit(nr, isainfo->isa);
-				}
-			} else {
-				/* sorted alphabetically */
-				SET_ISA_EXT_MAP("smaia", RISCV_ISA_EXT_SMAIA);
-				SET_ISA_EXT_MAP("ssaia", RISCV_ISA_EXT_SSAIA);
-				SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF);
-				SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC);
-				SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL);
-				SET_ISA_EXT_MAP("svnapot", RISCV_ISA_EXT_SVNAPOT);
-				SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT);
-				SET_ISA_EXT_MAP("zba", RISCV_ISA_EXT_ZBA);
-				SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB);
-				SET_ISA_EXT_MAP("zbs", RISCV_ISA_EXT_ZBS);
-				SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM);
-				SET_ISA_EXT_MAP("zicboz", RISCV_ISA_EXT_ZICBOZ);
-				SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE);
-			}
-#undef SET_ISA_EXT_MAP
-		}
+		riscv_parse_isa_string(&this_hwcap, isainfo, isa2hwcap, isa);
 
 		/*
 		 * Linux requires the following extensions, so we may as well
@@ -352,9 +413,107 @@ void __init riscv_fill_hwcap(void)
 
 	if (!acpi_disabled && rhct)
 		acpi_put_table((struct acpi_table_header *)rhct);
+}
+
+static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		unsigned long this_hwcap = 0;
+		struct device_node *cpu_node;
+		struct riscv_isainfo *isainfo = &hart_isa[cpu];
+
+		cpu_node = of_cpu_device_node_get(cpu);
+		if (!cpu_node) {
+			pr_warn("Unable to find cpu node\n");
+			continue;
+		}
+
+		if (!of_property_present(cpu_node, "riscv,isa-extensions")) {
+			of_node_put(cpu_node);
+			continue;
+		}
+
+		for (int i = 0; i < riscv_isa_ext_count; i++) {
+			if (of_property_match_string(cpu_node, "riscv,isa-extensions",
+						     riscv_isa_ext[i].property) < 0)
+				continue;
+
+			if (!riscv_isa_extension_check(riscv_isa_ext[i].id))
+				continue;
+
+			/* Only single letter extensions get set in hwcap */
+			if (strnlen(riscv_isa_ext[i].name, 2) == 1)
+				this_hwcap |= isa2hwcap[riscv_isa_ext[i].id];
+
+			set_bit(riscv_isa_ext[i].id, isainfo->isa);
+		}
+
+		of_node_put(cpu_node);
+
+		/*
+		 * All "okay" harts should have same isa. Set HWCAP based on
+		 * common capabilities of every "okay" hart, in case they don't.
+		 */
+		if (elf_hwcap)
+			elf_hwcap &= this_hwcap;
+		else
+			elf_hwcap = this_hwcap;
+
+		if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
+			bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX);
+		else
+			bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX);
+	}
+
+	if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
+		return -ENOENT;
+
+	return 0;
+}
+
+#ifdef CONFIG_RISCV_ISA_FALLBACK
+bool __initdata riscv_isa_fallback = true;
+#else
+bool __initdata riscv_isa_fallback;
+static int __init riscv_isa_fallback_setup(char *__unused)
+{
+	riscv_isa_fallback = true;
+	return 1;
+}
+early_param("riscv_isa_fallback", riscv_isa_fallback_setup);
+#endif
+
+void __init riscv_fill_hwcap(void)
+{
+	char print_str[NUM_ALPHA_EXTS + 1];
+	unsigned long isa2hwcap[26] = {0};
+	int i, j;
+
+	isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I;
+	isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M;
+	isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A;
+	isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F;
+	isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D;
+	isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C;
+	isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V;
+
+	if (!acpi_disabled) {
+		riscv_fill_hwcap_from_isa_string(isa2hwcap);
+	} else {
+		int ret = riscv_fill_hwcap_from_ext_list(isa2hwcap);
+
+		if (ret && riscv_isa_fallback) {
+			pr_info("Falling back to deprecated \"riscv,isa\"\n");
+			riscv_fill_hwcap_from_isa_string(isa2hwcap);
+		}
+	}
 
-	/* We don't support systems with F but without D, so mask those out
-	 * here. */
+	/*
+	 * We don't support systems with F but without D, so mask those out
+	 * here.
+	 */
 	if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) {
 		pr_info("This kernel does not support systems with F but not D\n");
 		elf_hwcap &= ~COMPAT_HWCAP_ISA_F;