RISC-V: Enable cbo.zero in usermode

When Zicboz is present, enable its instruction (cbo.zero) in
usermode by setting its respective senvcfg bit. We don't bother
trying to set this bit per-task, which would also require an
interface for tasks to request enabling and/or disabling. Instead,
permanently set the bit for each hart which has the extension when
bringing it online.

This patch also introduces riscv_cpu_has_extension_[un]likely()
functions to check a specific hart's ISA bitmap for extensions.
Prior to checking the specific hart's bitmap in these functions
we try the bitmap which represents the LCD of extensions, but only
when we know it will use its optimized, alternatives path by gating
its call on CONFIG_RISCV_ALTERNATIVE. When alternatives are used, the
compiler ensures that the invocation of the LCD search becomes a
constant true or false. When it's true, even the new functions will
completely vanish from their callsites. OTOH, when the LCD check is
false, we need to do a search of the hart's ISA bitmap. Had we also
checked the LCD bitmap without the use of alternatives, then we would
have ended up with two bitmap searches instead of one.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230918131518.56803-10-ajones@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Author: Andrew Jones

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

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

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 @@ riscv_has_extension_unlikely(const unsigned long ext)
 	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 */

arch/riscv/kernel/cpufeature.c

@@ -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

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)

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.