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@wendySigned-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Documentation/admin-guide/kernel-parameters.txt

@@ -5468,6 +5468,13 @@
 			[KNL] Disable ring 3 MONITOR/MWAIT feature on supported
 			CPUs.
 
+	riscv_isa_fallback [RISCV]
+			When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit
+			falling back to detecting extension support by parsing
+			"riscv,isa" property on devicetree systems when the
+			replacement properties are not found. See the Kconfig
+			entry for RISCV_ISA_FALLBACK.
+
 	ro		[KNL] Mount root device read-only on boot
 
 	rodata=		[KNL]

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

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)

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";
 
-static void print_isa(struct seq_file *f, const char *isa)
-{
-	int i;
+		/* Only multi-letter extensions are split by underscores */
+		if (strnlen(riscv_isa_ext[i].name, 2) != 1)
+			seq_puts(f, "_");
 
-	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);