RISC-V: Provide a fraemework for RISC-V ISA extensions

This series implements a generic framework to parse multi-letter ISA
extensions.

* palmer/riscv-isa:
  RISC-V: Improve /proc/cpuinfo output for ISA extensions
  RISC-V: Do no continue isa string parsing without correct XLEN
  RISC-V: Implement multi-letter ISA extension probing framework
  RISC-V: Extract multi-letter extension names from "riscv, isa"
  RISC-V: Minimal parser for "riscv, isa" strings
  RISC-V: Correctly print supported extensions

3 files changed, 195 insertions, 23 deletions

diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 5ce50468aff1..691fc9c8099b 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -34,7 +34,32 @@ extern unsigned long elf_hwcap;
 #define RISCV_ISA_EXT_s		('s' - 'a')
 #define RISCV_ISA_EXT_u		('u' - 'a')
 
+/*
+ * Increse this to higher value as kernel support more ISA extensions.
+ */
 #define RISCV_ISA_EXT_MAX	64
+#define RISCV_ISA_EXT_NAME_LEN_MAX 32
+
+/* The base ID for multi-letter ISA extensions */
+#define RISCV_ISA_EXT_BASE 26
+
+/*
+ * This enum represent the logical ID for each multi-letter RISC-V ISA extension.
+ * The logical ID should start from RISCV_ISA_EXT_BASE and must not exceed
+ * RISCV_ISA_EXT_MAX. 0-25 range is reserved for single letter
+ * extensions while all the multi-letter extensions should define the next
+ * available logical extension id.
+ */
+enum riscv_isa_ext_id {
+	RISCV_ISA_EXT_ID_MAX = RISCV_ISA_EXT_MAX,
+};
+
+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;
+};
 
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
 
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index 3e7e35d50e69..ecc2a09a66a9 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -6,6 +6,7 @@
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/of.h>
+#include <asm/hwcap.h>
 #include <asm/smp.h>
 #include <asm/pgtable.h>
 
@@ -63,12 +64,72 @@ int riscv_of_parent_hartid(struct device_node *node)
 }
 
 #ifdef CONFIG_PROC_FS
+#define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \
+	{							\
+		.uprop = #UPROP,				\
+		.isa_ext_id = EXTID,				\
+	}
+/**
+ * Here are the ordering rules of extension naming defined by RISC-V
+ * specification :
+ * 1. All extensions should be separated from other multi-letter extensions
+ *    from other multi-letter extensions by an underscore.
+ * 2. The first letter following the 'Z' conventionally indicates the most
+ *    closely related alphabetical extension category, IMAFDQLCBKJTPVH.
+ *    If multiple 'Z' extensions are named, they should be ordered first
+ *    by category, then alphabetically within a category.
+ * 3. Standard supervisor-level extensions (starts with 'S') should be
+ *    listed after standard unprivileged extensions.  If multiple
+ *    supervisor-level extensions are listed, they should be ordered
+ *    alphabetically.
+ * 4. Non-standard extensions (starts with 'X') must be listed after all
+ *    standard extensions. They must be separated from other multi-letter
+ *    extensions by an underscore.
+ */
+static struct riscv_isa_ext_data isa_ext_arr[] = {
+	__RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX),
+};
+
+static void print_isa_ext(struct seq_file *f)
+{
+	struct riscv_isa_ext_data *edata;
+	int i = 0, arr_sz;
+
+	arr_sz = ARRAY_SIZE(isa_ext_arr) - 1;
+
+	/* No extension support available */
+	if (arr_sz <= 0)
+		return;
+
+	for (i = 0; i <= arr_sz; i++) {
+		edata = &isa_ext_arr[i];
+		if (!__riscv_isa_extension_available(NULL, edata->isa_ext_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";
 
 static void print_isa(struct seq_file *f, const char *isa)
 {
-	/* Print the entire ISA as it is */
+	int i;
+
 	seq_puts(f, "isa\t\t: ");
-	seq_write(f, isa, strlen(isa));
+	/* 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);
+	}
+	print_isa_ext(f);
 	seq_puts(f, "\n");
 }
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index d959d207a40d..a43c08af5f4b 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -7,12 +7,15 @@
  */
 
 #include <linux/bitmap.h>
+#include <linux/ctype.h>
 #include <linux/of.h>
 #include <asm/processor.h>
 #include <asm/hwcap.h>
 #include <asm/smp.h>
 #include <asm/switch_to.h>
 
+#define NUM_ALPHA_EXTS ('z' - 'a' + 1)
+
 unsigned long elf_hwcap __read_mostly;
 
 /* Host ISA bitmap */
@@ -63,8 +66,8 @@ void __init riscv_fill_hwcap(void)
 {
 	struct device_node *node;
 	const char *isa;
-	char print_str[BITS_PER_LONG + 1];
-	size_t i, j, isa_len;
+	char print_str[NUM_ALPHA_EXTS + 1];
+	int i, j;
 	static unsigned long isa2hwcap[256] = {0};
 
 	isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I;
@@ -80,7 +83,8 @@ void __init riscv_fill_hwcap(void)
 
 	for_each_of_cpu_node(node) {
 		unsigned long this_hwcap = 0;
-		unsigned long this_isa = 0;
+		DECLARE_BITMAP(this_isa, RISCV_ISA_EXT_MAX);
+		const char *temp;
 
 		if (riscv_of_processor_hartid(node) < 0)
 			continue;
@@ -90,23 +94,104 @@ void __init riscv_fill_hwcap(void)
 			continue;
 		}
 
-		i = 0;
-		isa_len = strlen(isa);
+		temp = 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])];
-			/*
-			 * TODO: X, Y and Z extension parsing for Host ISA
-			 * bitmap will be added in-future.
-			 */
-			if ('a' <= isa[i] && isa[i] < 'x')
-				this_isa |= (1UL << (isa[i] - 'a'));
+		/* The riscv,isa DT property must start with rv64 or rv32 */
+		if (temp == isa)
+			continue;
+		bitmap_zero(this_isa, RISCV_ISA_EXT_MAX);
+		for (; *isa; ++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 'x':
+			case 'z':
+				ext_long = true;
+				/* Multi-letter extension must be delimited */
+				for (; *isa && *isa != '_'; ++isa)
+					if (unlikely(!islower(*isa)
+						     && !isdigit(*isa)))
+						ext_err = true;
+				/* Parse backwards */
+				ext_end = isa;
+				if (unlikely(ext_err))
+					break;
+				if (!isdigit(ext_end[-1]))
+					break;
+				/* Skip the minor version */
+				while (isdigit(*--ext_end))
+					;
+				if (ext_end[0] != 'p'
+				    || !isdigit(ext_end[-1])) {
+					/* Advance it to offset the pre-decrement */
+					++ext_end;
+					break;
+				}
+				/* Skip the major version */
+				while (isdigit(*--ext_end))
+					;
+				++ext_end;
+				break;
+			default:
+				if (unlikely(!islower(*ext))) {
+					ext_err = true;
+					break;
+				}
+				/* Find next extension */
+				if (!isdigit(*isa))
+					break;
+				/* Skip the minor version */
+				while (isdigit(*++isa))
+					;
+				if (*isa != 'p')
+					break;
+				if (!isdigit(*++isa)) {
+					--isa;
+					break;
+				}
+				/* Skip the major version */
+				while (isdigit(*++isa))
+					;
+				break;
+			}
+			if (*isa != '_')
+				--isa;
+
+#define SET_ISA_EXT_MAP(name, bit)						\
+			do {							\
+				if ((ext_end - ext == sizeof(name) - 1) &&	\
+				     !memcmp(ext, name, sizeof(name) - 1))	\
+					set_bit(bit, this_isa);			\
+			} while (false)						\
+
+			if (unlikely(ext_err))
+				continue;
+			if (!ext_long) {
+				this_hwcap |= isa2hwcap[(unsigned char)(*ext)];
+				set_bit(*ext - 'a', this_isa);
+			}
+#undef SET_ISA_EXT_MAP
 		}
 
 		/*
@@ -119,10 +204,11 @@ void __init riscv_fill_hwcap(void)
 		else
 			elf_hwcap = this_hwcap;
 
-		if (riscv_isa[0])
-			riscv_isa[0] &= this_isa;
+		if (bitmap_weight(riscv_isa, RISCV_ISA_EXT_MAX))
+			bitmap_and(riscv_isa, riscv_isa, this_isa, RISCV_ISA_EXT_MAX);
 		else
-			riscv_isa[0] = this_isa;
+			bitmap_copy(riscv_isa, this_isa, RISCV_ISA_EXT_MAX);
+
 	}
 
 	/* We don't support systems with F but without D, so mask those out
@@ -133,13 +219,13 @@ void __init riscv_fill_hwcap(void)
 	}
 
 	memset(print_str, 0, sizeof(print_str));
-	for (i = 0, j = 0; i < BITS_PER_LONG; i++)
+	for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++)
 		if (riscv_isa[0] & BIT_MASK(i))
 			print_str[j++] = (char)('a' + i);
-	pr_info("riscv: ISA extensions %s\n", print_str);
+	pr_info("riscv: base ISA extensions %s\n", print_str);
 
 	memset(print_str, 0, sizeof(print_str));
-	for (i = 0, j = 0; i < BITS_PER_LONG; i++)
+	for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++)
 		if (elf_hwcap & BIT_MASK(i))
 			print_str[j++] = (char)('a' + i);
 	pr_info("riscv: ELF capabilities %s\n", print_str);