[RFC PATCH v3 2/4] riscv: cpufeature: Minimal parser for "riscv, isa" strings

[Tsukasa OI]

Current hart ISA ("riscv,isa") parser don't correctly parse:

1. Multi-letter extensions
2. Version numbers

If we don't have those in "riscv,isa", that's fine.  However, many of
standardized multi-letter extensions are being frozen and ratified.
The current "riscv,isa" parser that is easily confused by multi-letter
extensions and "p" in version numbers can be a huge problem for adding
new extensions through the device tree.

Leaving it would create incompatible hacks and would make "riscv,isa"
value unreliable.

This commit implements minimal parser for "riscv,isa" strings.  With this,
we can safely ignore multi-letter extensions and version numbers.

Important Note:
  This commit does handle "H" as a single-letter extension.  This
  handling is not compliant with current version of RISC-V ISA Manual
  but will going to be in a few months.

Signed-off-by: Tsukasa OI <research_trasio at irq.a4lg.com>
---
 arch/riscv/kernel/cpufeature.c | 59 +++++++++++++++++++++++++++-------
 1 file changed, 48 insertions(+), 11 deletions(-)

diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index dd3d57eb4eea..d4ff704db53b 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/bitmap.h>
+#include <linux/ctype.h>
 #include <linux/of.h>
 #include <asm/processor.h>
 #include <asm/hwcap.h>
@@ -66,7 +67,7 @@ void __init riscv_fill_hwcap(void)
 	struct device_node *node;
 	const char *isa;
 	char print_str[NUM_ALPHA_EXTS + 1];
-	size_t i, j, isa_len;
+	int i, j;
 	static unsigned long isa2hwcap[256] = {0};
 
 	isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I;
@@ -92,23 +93,59 @@ void __init riscv_fill_hwcap(void)
 			continue;
 		}
 
-		i = 0;
-		isa_len = strlen(isa);
 #if IS_ENABLED(CONFIG_32BIT)
 		if (!strncmp(isa, "rv32", 4))
-			i += 4;
+			isa += 4;
 #elif IS_ENABLED(CONFIG_64BIT)
 		if (!strncmp(isa, "rv64", 4))
-			i += 4;
+			isa += 4;
 #endif
-		for (; i < isa_len; ++i) {
-			this_hwcap |= isa2hwcap[(unsigned char)(isa[i])];
+		for (; *isa; ++isa) {
+			const char *ext = isa++;
+			bool ext_long, ext_err = false;
+
+			switch (*ext) {
+			case 's':
+			case 'x':
+			case 'z':
+				ext_long = true;
+				/* Multi-letter extension must be delimited */
+				for (; *isa && *isa != '_'; ++isa)
+					if (!islower(*isa) && !isdigit(*isa))
+						ext_err = true;
+				/* ... but must be ignored. */
+				break;
+			default:
+				ext_long = false;
+				if (!islower(*ext)) {
+					ext_err = true;
+					break;
+				}
+				/* Find next extension */
+				if (!isdigit(*isa))
+					break;
+				while (isdigit(*++isa))
+					;
+				if (*isa != 'p')
+					break;
+				if (!isdigit(*++isa)) {
+					--isa;
+					break;
+				}
+				while (isdigit(*++isa))
+					;
+				break;
+			}
+			if (*isa != '_')
+				--isa;
 			/*
-			 * TODO: X, Y and Z extension parsing for Host ISA
-			 * bitmap will be added in-future.
+			 * TODO: Full version-aware handling including
+			 * multi-letter extensions will be added in-future.
 			 */
-			if ('a' <= isa[i] && isa[i] < 'x')
-				this_isa |= (1UL << (isa[i] - 'a'));
+			if (ext_err || ext_long)
+				continue;
+			this_hwcap |= isa2hwcap[(unsigned char)(*ext)];
+			this_isa |= (1UL << (*ext - 'a'));
 		}
 
 		/*
-- 
2.32.0