Merge patch series "RISC-V: Export Zba, Zbb to usermode via hwprobe"

Evan Green <evan@rivosinc.com> says:

This change detects the presence of Zba, Zbb, and Zbs extensions and exports
them per-hart to userspace via the hwprobe mechanism. Glibc can then use
these in setting up hwcaps-based library search paths.

There's a little bit of extra housekeeping here: the first change adds
Zba and Zbs to the set of extensions the kernel recognizes, and the second
change starts tracking ISA features per-hart (in addition to the ANDed
mask of features across all harts which the kernel uses to make
decisions). Now that we track the ISA information per-hart, we could
even fix up /proc/cpuinfo to accurately report extension per-hart,
though I've left that out of this series for now.

* b4-shazam-merge:
  RISC-V: hwprobe: Expose Zba, Zbb, and Zbs
  RISC-V: Track ISA extensions per hart
  RISC-V: Add Zba, Zbs extension probing

Link: https://lore.kernel.org/r/20230509182504.2997252-1-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

7 files changed, 81 insertions, 16 deletions

diff --git a/Documentation/riscv/hwprobe.rst b/Documentation/riscv/hwprobe.rst
index 7431d9d01c73..19165ebd82ba 100644
--- a/Documentation/riscv/hwprobe.rst
+++ b/Documentation/riscv/hwprobe.rst
@@ -67,6 +67,16 @@ The following keys are defined:
   * :c:macro:`RISCV_HWPROBE_IMA_V`: The V extension is supported, as defined by
     version 1.0 of the RISC-V Vector extension manual.
 
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBA`: The Zba address generation extension is
+       supported, as defined in version 1.0 of the Bit-Manipulation ISA
+       extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBB`: The Zbb extension is supported, as defined
+       in version 1.0 of the Bit-Manipulation ISA extensions.
+
+  * :c:macro:`RISCV_HWPROBE_EXT_ZBS`: The Zbs extension is supported, as defined
+       in version 1.0 of the Bit-Manipulation ISA extensions.
+
 * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
   information about the selected set of processors.
 
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 808d5403f2ac..23fed53b8815 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -6,6 +6,9 @@
 #ifndef _ASM_CPUFEATURE_H
 #define _ASM_CPUFEATURE_H
 
+#include <linux/bitmap.h>
+#include <asm/hwcap.h>
+
 /*
  * These are probed via a device_initcall(), via either the SBI or directly
  * from the corresponding CSRs.
@@ -16,8 +19,15 @@ struct riscv_cpuinfo {
 	unsigned long mimpid;
 };
 
+struct riscv_isainfo {
+	DECLARE_BITMAP(isa, RISCV_ISA_EXT_MAX);
+};
+
 DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
 
 DECLARE_PER_CPU(long, misaligned_access_speed);
 
+/* Per-cpu ISA extensions. */
+extern struct riscv_isainfo hart_isa[NR_CPUS];
+
 #endif
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index e6c288ac4581..bdd614dee8a0 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -47,6 +47,8 @@
 #define RISCV_ISA_EXT_ZICBOZ		34
 #define RISCV_ISA_EXT_SMAIA		35
 #define RISCV_ISA_EXT_SSAIA		36
+#define RISCV_ISA_EXT_ZBA		37
+#define RISCV_ISA_EXT_ZBS		38
 
 #define RISCV_ISA_EXT_MAX		64
 #define RISCV_ISA_EXT_NAME_LEN_MAX	32
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 7c6fdcf7ced5..006bfb48343d 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -26,6 +26,9 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_IMA_FD		(1 << 0)
 #define		RISCV_HWPROBE_IMA_C		(1 << 1)
 #define		RISCV_HWPROBE_IMA_V		(1 << 2)
+#define		RISCV_HWPROBE_EXT_ZBA		(1 << 3)
+#define		RISCV_HWPROBE_EXT_ZBB		(1 << 4)
+#define		RISCV_HWPROBE_EXT_ZBS		(1 << 5)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index 637263f9a7b9..e58e93dec889 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -187,7 +187,9 @@ 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(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
+	__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),
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index d1e9e879f577..f8dc577fc912 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -30,6 +30,9 @@ unsigned long elf_hwcap __read_mostly;
 /* Host ISA bitmap */
 static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
 
+/* Per-cpu ISA extensions. */
+struct riscv_isainfo hart_isa[NR_CPUS];
+
 /* Performance information */
 DEFINE_PER_CPU(long, misaligned_access_speed);
 
@@ -126,8 +129,8 @@ void __init riscv_fill_hwcap(void)
 	}
 
 	for_each_possible_cpu(cpu) {
+		struct riscv_isainfo *isainfo = &hart_isa[cpu];
 		unsigned long this_hwcap = 0;
-		DECLARE_BITMAP(this_isa, RISCV_ISA_EXT_MAX);
 		const char *temp;
 
 		if (acpi_disabled) {
@@ -159,7 +162,6 @@ void __init riscv_fill_hwcap(void)
 		/* 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;
@@ -239,7 +241,7 @@ void __init riscv_fill_hwcap(void)
 				if ((ext_end - ext == sizeof(name) - 1) &&		\
 				     !strncasecmp(ext, name, sizeof(name) - 1) &&	\
 				     riscv_isa_extension_check(bit))			\
-					set_bit(bit, this_isa);				\
+					set_bit(bit, isainfo->isa);			\
 			} while (false)							\
 
 			if (unlikely(ext_err))
@@ -249,7 +251,7 @@ void __init riscv_fill_hwcap(void)
 
 				if (riscv_isa_extension_check(nr)) {
 					this_hwcap |= isa2hwcap[nr];
-					set_bit(nr, this_isa);
+					set_bit(nr, isainfo->isa);
 				}
 			} else {
 				/* sorted alphabetically */
@@ -260,7 +262,9 @@ void __init riscv_fill_hwcap(void)
 				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);
@@ -279,9 +283,9 @@ void __init riscv_fill_hwcap(void)
 			elf_hwcap = this_hwcap;
 
 		if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
-			bitmap_copy(riscv_isa, this_isa, RISCV_ISA_EXT_MAX);
+			bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX);
 		else
-			bitmap_and(riscv_isa, riscv_isa, this_isa, RISCV_ISA_EXT_MAX);
+			bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX);
 	}
 
 	if (!acpi_disabled && rhct)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 88357a848797..26ef5526bfb4 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -122,6 +122,49 @@ static void hwprobe_arch_id(struct riscv_hwprobe *pair,
 	pair->value = id;
 }
 
+static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	int cpu;
+	u64 missing = 0;
+
+	pair->value = 0;
+	if (has_fpu())
+		pair->value |= RISCV_HWPROBE_IMA_FD;
+
+	if (riscv_isa_extension_available(NULL, c))
+		pair->value |= RISCV_HWPROBE_IMA_C;
+
+	if (has_vector())
+		pair->value |= RISCV_HWPROBE_IMA_V;
+
+	/*
+	 * Loop through and record extensions that 1) anyone has, and 2) anyone
+	 * doesn't have.
+	 */
+	for_each_cpu(cpu, cpus) {
+		struct riscv_isainfo *isainfo = &hart_isa[cpu];
+
+		if (riscv_isa_extension_available(isainfo->isa, ZBA))
+			pair->value |= RISCV_HWPROBE_EXT_ZBA;
+		else
+			missing |= RISCV_HWPROBE_EXT_ZBA;
+
+		if (riscv_isa_extension_available(isainfo->isa, ZBB))
+			pair->value |= RISCV_HWPROBE_EXT_ZBB;
+		else
+			missing |= RISCV_HWPROBE_EXT_ZBB;
+
+		if (riscv_isa_extension_available(isainfo->isa, ZBS))
+			pair->value |= RISCV_HWPROBE_EXT_ZBS;
+		else
+			missing |= RISCV_HWPROBE_EXT_ZBS;
+	}
+
+	/* Now turn off reporting features if any CPU is missing it. */
+	pair->value &= ~missing;
+}
+
 static u64 hwprobe_misaligned(const struct cpumask *cpus)
 {
 	int cpu;
@@ -165,16 +208,7 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		break;
 
 	case RISCV_HWPROBE_KEY_IMA_EXT_0:
-		pair->value = 0;
-		if (has_fpu())
-			pair->value |= RISCV_HWPROBE_IMA_FD;
-
-		if (riscv_isa_extension_available(NULL, c))
-			pair->value |= RISCV_HWPROBE_IMA_C;
-
-		if (has_vector())
-			pair->value |= RISCV_HWPROBE_IMA_V;
-
+		hwprobe_isa_ext0(pair, cpus);
 		break;
 
 	case RISCV_HWPROBE_KEY_CPUPERF_0: