Merge patch series "RISC-V: Enable cbo.zero in usermode"

Andrew Jones <ajones@ventanamicro.com> says:

In order for usermode to issue cbo.zero, it needs privilege granted to
issue the extension instruction (patch 2) and to know that the extension
is available and its block size (patch 3). Patch 1 could be separate from
this series (it just fixes up some error messages), patches 4-5 convert
the hwprobe selftest to a statically-linked, TAP test and patch 6 adds a
new hwprobe test for the new information as well as testing CBO
instructions can or cannot be issued as appropriate.

* b4-shazam-merge:
  RISC-V: selftests: Add CBO tests
  RISC-V: selftests: Convert hwprobe test to kselftest API
  RISC-V: selftests: Statically link hwprobe test
  RISC-V: hwprobe: Expose Zicboz extension and its block size
  RISC-V: Enable cbo.zero in usermode
  RISC-V: Make zicbom/zicboz errors consistent

Link: https://lore.kernel.org/r/20230918131518.56803-8-ajones@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

9 files changed, 69 insertions, 17 deletions

diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index d0345bd659c9..13b7d35648a9 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -31,5 +31,6 @@ DECLARE_PER_CPU(long, misaligned_access_speed);
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
 void check_unaligned_access(int cpu);
+void riscv_user_isa_enable(void);
 
 #endif
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 777cb8299551..5fba25db82d2 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -275,6 +275,7 @@
 #define CSR_SIE			0x104
 #define CSR_STVEC		0x105
 #define CSR_SCOUNTEREN		0x106
+#define CSR_SENVCFG		0x10a
 #define CSR_SSCRATCH		0x140
 #define CSR_SEPC		0x141
 #define CSR_SCAUSE		0x142
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index b7b58258f6c7..31774bcdf1c6 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -70,6 +70,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/jump_label.h>
+#include <asm/cpufeature.h>
 
 unsigned long riscv_get_elf_hwcap(void);
 
@@ -137,6 +138,21 @@ l_yes:
 	return true;
 }
 
+static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext))
+		return true;
+
+	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
+
+static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext))
+		return true;
+
+	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
 #endif
 
 #endif /* _ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index 78936f4ff513..39df8604fea1 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -8,6 +8,6 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 5
+#define RISCV_HWPROBE_MAX_KEY 6
 
 #endif
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 006bfb48343d..86d08a0e617b 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -29,6 +29,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZBA		(1 << 3)
 #define		RISCV_HWPROBE_EXT_ZBB		(1 << 4)
 #define		RISCV_HWPROBE_EXT_ZBS		(1 << 5)
+#define		RISCV_HWPROBE_EXT_ZICBOZ	(1 << 6)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
@@ -36,6 +37,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_MISALIGNED_FAST		(3 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_UNSUPPORTED	(4 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_MASK		(7 << 0)
+#define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE	6
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 #endif
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 1cfbba65d11a..8ad6da03ee34 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -93,10 +93,10 @@ static bool riscv_isa_extension_check(int id)
 		return true;
 	case RISCV_ISA_EXT_ZICBOZ:
 		if (!riscv_cboz_block_size) {
-			pr_err("Zicboz detected in ISA string, but no cboz-block-size found\n");
+			pr_err("Zicboz detected in ISA string, disabling as no cboz-block-size found\n");
 			return false;
 		} else if (!is_power_of_2(riscv_cboz_block_size)) {
-			pr_err("cboz-block-size present, but is not a power-of-2\n");
+			pr_err("Zicboz disabled as cboz-block-size present, but is not a power-of-2\n");
 			return false;
 		}
 		return true;
@@ -653,6 +653,12 @@ static int check_unaligned_access_boot_cpu(void)
 
 arch_initcall(check_unaligned_access_boot_cpu);
 
+void riscv_user_isa_enable(void)
+{
+	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ))
+		csr_set(CSR_SENVCFG, ENVCFG_CBZE);
+}
+
 #ifdef CONFIG_RISCV_ALTERNATIVE
 /*
  * Alternative patch sites consider 48 bits when determining when to patch
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index e600aab116a4..8fd6c02353d4 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -26,6 +26,7 @@
 #include <asm/acpi.h>
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/early_ioremap.h>
 #include <asm/pgtable.h>
@@ -314,10 +315,13 @@ void __init setup_arch(char **cmdline_p)
 	riscv_fill_hwcap();
 	init_rt_signal_env();
 	apply_boot_alternatives();
+
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) &&
 	    riscv_isa_extension_available(NULL, ZICBOM))
 		riscv_noncoherent_supported();
 	riscv_set_dma_cache_alignment();
+
+	riscv_user_isa_enable();
 }
 
 static int __init topology_init(void)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 1b8da4e40a4d..d1b0a6fc3adf 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -25,6 +25,8 @@
 #include <linux/of.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/mm.h>
+
+#include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/cpufeature.h>
 #include <asm/irq.h>
@@ -253,6 +255,8 @@ asmlinkage __visible void smp_callin(void)
 			elf_hwcap &= ~COMPAT_HWCAP_ISA_V;
 	}
 
+	riscv_user_isa_enable();
+
 	/*
 	 * Remote TLB flushes are ignored while the CPU is offline, so emit
 	 * a local TLB flush right now just in case.
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 473159b5f303..d7266a9abc66 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -145,26 +145,38 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 	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;
+#define EXT_KEY(ext)									\
+	do {										\
+		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
+			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
+		else									\
+			missing |= RISCV_HWPROBE_EXT_##ext;				\
+	} while (false)
+
+		/*
+		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
+		 * regardless of the kernel's configuration, as no other checks, besides
+		 * presence in the hart_isa bitmap, are made.
+		 */
+		EXT_KEY(ZBA);
+		EXT_KEY(ZBB);
+		EXT_KEY(ZBS);
+		EXT_KEY(ZICBOZ);
+#undef EXT_KEY
 	}
 
 	/* Now turn off reporting features if any CPU is missing it. */
 	pair->value &= ~missing;
 }
 
+static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
+{
+	struct riscv_hwprobe pair;
+
+	hwprobe_isa_ext0(&pair, cpus);
+	return (pair.value & ext);
+}
+
 static u64 hwprobe_misaligned(const struct cpumask *cpus)
 {
 	int cpu;
@@ -215,6 +227,12 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		pair->value = hwprobe_misaligned(cpus);
 		break;
 
+	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
+		pair->value = 0;
+		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
+			pair->value = riscv_cboz_block_size;
+		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