RISC-V: Add a syscall for HW probing

We don't have enough space for these all in ELF_HWCAP{,2} and there's no
system call that quite does this, so let's just provide an arch-specific
one to probe for hardware capabilities.  This currently just provides
m{arch,imp,vendor}id, but with the key-value pairs we can pass more in
the future.

Co-developed-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Evan Green <evan@rivosinc.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Tested-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Reviewed-by: Paul Walmsley <paul.walmsley@sifive.com>
Link: https://lore.kernel.org/r/20230407231103.2622178-3-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Documentation/riscv/hwprobe.rst

@@ -0,0 +1,41 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+RISC-V Hardware Probing Interface
+---------------------------------
+
+The RISC-V hardware probing interface is based around a single syscall, which
+is defined in <asm/hwprobe.h>::
+
+    struct riscv_hwprobe {
+        __s64 key;
+        __u64 value;
+    };
+
+    long sys_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+                           size_t cpu_count, cpu_set_t *cpus,
+                           unsigned int flags);
+
+The arguments are split into three groups: an array of key-value pairs, a CPU
+set, and some flags. The key-value pairs are supplied with a count. Userspace
+must prepopulate the key field for each element, and the kernel will fill in the
+value if the key is recognized. If a key is unknown to the kernel, its key field
+will be cleared to -1, and its value set to 0. The CPU set is defined by
+CPU_SET(3). For value-like keys (eg. vendor/arch/impl), the returned value will
+be only be valid if all CPUs in the given set have the same value. Otherwise -1
+will be returned. For boolean-like keys, the value returned will be a logical
+AND of the values for the specified CPUs. Usermode can supply NULL for cpus and
+0 for cpu_count as a shortcut for all online CPUs. There are currently no flags,
+this value must be zero for future compatibility.
+
+On success 0 is returned, on failure a negative error code is returned.
+
+The following keys are defined:
+
+* :c:macro:`RISCV_HWPROBE_KEY_MVENDORID`: Contains the value of ``mvendorid``,
+  as defined by the RISC-V privileged architecture specification.
+
+* :c:macro:`RISCV_HWPROBE_KEY_MARCHID`: Contains the value of ``marchid``, as
+  defined by the RISC-V privileged architecture specification.
+
+* :c:macro:`RISCV_HWPROBE_KEY_MIMPLID`: Contains the value of ``mimplid``, as
+  defined by the RISC-V privileged architecture specification.

Documentation/riscv/index.rst

@@ -7,6 +7,7 @@ RISC-V architecture
 
     boot-image-header
     vm-layout
+    hwprobe
     patch-acceptance
     uabi
 

arch/riscv/include/asm/hwprobe.h

@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright 2023 Rivos, Inc
+ */
+
+#ifndef _ASM_HWPROBE_H
+#define _ASM_HWPROBE_H
+
+#include <uapi/asm/hwprobe.h>
+
+#define RISCV_HWPROBE_MAX_KEY 2
+
+#endif

arch/riscv/include/asm/syscall.h

@@ -10,6 +10,7 @@
 #ifndef _ASM_RISCV_SYSCALL_H
 #define _ASM_RISCV_SYSCALL_H
 
+#include <asm/hwprobe.h>
 #include <uapi/linux/audit.h>
 #include <linux/sched.h>
 #include <linux/err.h>
@@ -75,4 +76,7 @@ static inline int syscall_get_arch(struct task_struct *task)
 }
 
 asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
+
+asmlinkage long sys_riscv_hwprobe(struct riscv_hwprobe *, size_t, size_t,
+				  unsigned long *, unsigned int);
 #endif	/* _ASM_RISCV_SYSCALL_H */

arch/riscv/include/uapi/asm/hwprobe.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright 2023 Rivos, Inc
+ */
+
+#ifndef _UAPI_ASM_HWPROBE_H
+#define _UAPI_ASM_HWPROBE_H
+
+#include <linux/types.h>
+
+/*
+ * Interface for probing hardware capabilities from userspace, see
+ * Documentation/riscv/hwprobe.rst for more information.
+ */
+struct riscv_hwprobe {
+	__s64 key;
+	__u64 value;
+};
+
+#define RISCV_HWPROBE_KEY_MVENDORID	0
+#define RISCV_HWPROBE_KEY_MARCHID	1
+#define RISCV_HWPROBE_KEY_MIMPID	2
+/* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
+
+#endif

arch/riscv/include/uapi/asm/unistd.h

@@ -43,3 +43,12 @@
 #define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
 #endif
 __SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
+
+/*
+ * Allows userspace to query the kernel for CPU architecture and
+ * microarchitecture details across a given set of CPUs.
+ */
+#ifndef __NR_riscv_hwprobe
+#define __NR_riscv_hwprobe (__NR_arch_specific_syscall + 14)
+#endif
+__SYSCALL(__NR_riscv_hwprobe, sys_riscv_hwprobe)

arch/riscv/kernel/sys_riscv.c

@@ -6,8 +6,11 @@
  */
 
 #include <linux/syscalls.h>
-#include <asm/unistd.h>
 #include <asm/cacheflush.h>
+#include <asm/hwprobe.h>
+#include <asm/sbi.h>
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
 #include <asm-generic/mman-common.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
@@ -69,3 +72,133 @@ SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
 
 	return 0;
 }
+
+/*
+ * The hwprobe interface, for allowing userspace to probe to see which features
+ * are supported by the hardware.  See Documentation/riscv/hwprobe.rst for more
+ * details.
+ */
+static void hwprobe_arch_id(struct riscv_hwprobe *pair,
+			    const struct cpumask *cpus)
+{
+	u64 id = -1ULL;
+	bool first = true;
+	int cpu;
+
+	for_each_cpu(cpu, cpus) {
+		u64 cpu_id;
+
+		switch (pair->key) {
+		case RISCV_HWPROBE_KEY_MVENDORID:
+			cpu_id = riscv_cached_mvendorid(cpu);
+			break;
+		case RISCV_HWPROBE_KEY_MIMPID:
+			cpu_id = riscv_cached_mimpid(cpu);
+			break;
+		case RISCV_HWPROBE_KEY_MARCHID:
+			cpu_id = riscv_cached_marchid(cpu);
+			break;
+		}
+
+		if (first)
+			id = cpu_id;
+
+		/*
+		 * If there's a mismatch for the given set, return -1 in the
+		 * value.
+		 */
+		if (id != cpu_id) {
+			id = -1ULL;
+			break;
+		}
+	}
+
+	pair->value = id;
+}
+
+static void hwprobe_one_pair(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	switch (pair->key) {
+	case RISCV_HWPROBE_KEY_MVENDORID:
+	case RISCV_HWPROBE_KEY_MARCHID:
+	case RISCV_HWPROBE_KEY_MIMPID:
+		hwprobe_arch_id(pair, cpus);
+		break;
+
+	/*
+	 * For forward compatibility, unknown keys don't fail the whole
+	 * call, but get their element key set to -1 and value set to 0
+	 * indicating they're unrecognized.
+	 */
+	default:
+		pair->key = -1;
+		pair->value = 0;
+		break;
+	}
+}
+
+static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpu_count,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	size_t out;
+	int ret;
+	cpumask_t cpus;
+
+	/* Check the reserved flags. */
+	if (flags != 0)
+		return -EINVAL;
+
+	/*
+	 * The interface supports taking in a CPU mask, and returns values that
+	 * are consistent across that mask. Allow userspace to specify NULL and
+	 * 0 as a shortcut to all online CPUs.
+	 */
+	cpumask_clear(&cpus);
+	if (!cpu_count && !cpus_user) {
+		cpumask_copy(&cpus, cpu_online_mask);
+	} else {
+		if (cpu_count > cpumask_size())
+			cpu_count = cpumask_size();
+
+		ret = copy_from_user(&cpus, cpus_user, cpu_count);
+		if (ret)
+			return -EFAULT;
+
+		/*
+		 * Userspace must provide at least one online CPU, without that
+		 * there's no way to define what is supported.
+		 */
+		cpumask_and(&cpus, &cpus, cpu_online_mask);
+		if (cpumask_empty(&cpus))
+			return -EINVAL;
+	}
+
+	for (out = 0; out < pair_count; out++, pairs++) {
+		struct riscv_hwprobe pair;
+
+		if (get_user(pair.key, &pairs->key))
+			return -EFAULT;
+
+		pair.value = 0;
+		hwprobe_one_pair(&pair, &cpus);
+		ret = put_user(pair.key, &pairs->key);
+		if (ret == 0)
+			ret = put_user(pair.value, &pairs->value);
+
+		if (ret)
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
+		size_t, pair_count, size_t, cpu_count, unsigned long __user *,
+		cpus, unsigned int, flags)
+{
+	return do_riscv_hwprobe(pairs, pair_count, cpu_count,
+				cpus, flags);
+}