+#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)