Merge patch series "riscv: Use Kconfig to set unaligned access speed"

Charlie Jenkins <charlie@rivosinc.com> says:

If the hardware unaligned access speed is known at compile time, it is
possible to avoid running the unaligned access speed probe to speedup
boot-time.

* b4-shazam-merge:
  riscv: Set unaligned access speed at compile time
  riscv: Decouple emulated unaligned accesses from access speed
  riscv: Only check online cpus for emulated accesses
  riscv: lib: Introduce has_fast_unaligned_access()

Link: https://lore.kernel.org/r/20240308-disable_misaligned_probe_config-v9-0-a388770ba0ce@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Author: palmer-dabbelt

arch/riscv/Kconfig

@@ -704,27 +704,61 @@ config THREAD_SIZE_ORDER
 	  affects irq stack size, which is equal to thread stack size.
 
 config RISCV_MISALIGNED
-	bool "Support misaligned load/store traps for kernel and userspace"
+	bool
 	select SYSCTL_ARCH_UNALIGN_ALLOW
-	default y
 	help
-	  Say Y here if you want the kernel to embed support for misaligned
-	  load/store for both kernel and userspace. When disable, misaligned
-	  accesses will generate SIGBUS in userspace and panic in kernel.
+	  Embed support for emulating misaligned loads and stores.
+
+choice
+	prompt "Unaligned Accesses Support"
+	default RISCV_PROBE_UNALIGNED_ACCESS
+	help
+	  This determines the level of support for unaligned accesses. This
+	  information is used by the kernel to perform optimizations. It is also
+	  exposed to user space via the hwprobe syscall. The hardware will be
+	  probed at boot by default.
+
+config RISCV_PROBE_UNALIGNED_ACCESS
+	bool "Probe for hardware unaligned access support"
+	select RISCV_MISALIGNED
+	help
+	  During boot, the kernel will run a series of tests to determine the
+	  speed of unaligned accesses. This probing will dynamically determine
+	  the speed of unaligned accesses on the underlying system. If unaligned
+	  memory accesses trap into the kernel as they are not supported by the
+	  system, the kernel will emulate the unaligned accesses to preserve the
+	  UABI.
+
+config RISCV_EMULATED_UNALIGNED_ACCESS
+	bool "Emulate unaligned access where system support is missing"
+	select RISCV_MISALIGNED
+	help
+	  If unaligned memory accesses trap into the kernel as they are not
+	  supported by the system, the kernel will emulate the unaligned
+	  accesses to preserve the UABI. When the underlying system does support
+	  unaligned accesses, the unaligned accesses are assumed to be slow.
+
+config RISCV_SLOW_UNALIGNED_ACCESS
+	bool "Assume the system supports slow unaligned memory accesses"
+	depends on NONPORTABLE
+	help
+	  Assume that the system supports slow unaligned memory accesses. The
+	  kernel and userspace programs may not be able to run at all on systems
+	  that do not support unaligned memory accesses.
 
 config RISCV_EFFICIENT_UNALIGNED_ACCESS
-	bool "Assume the CPU supports fast unaligned memory accesses"
+	bool "Assume the system supports fast unaligned memory accesses"
 	depends on NONPORTABLE
 	select DCACHE_WORD_ACCESS if MMU
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	help
-	  Say Y here if you want the kernel to assume that the CPU supports
-	  efficient unaligned memory accesses.  When enabled, this option
-	  improves the performance of the kernel on such CPUs.  However, the
-	  kernel will run much more slowly, or will not be able to run at all,
-	  on CPUs that do not support efficient unaligned memory accesses.
+	  Assume that the system supports fast unaligned memory accesses. When
+	  enabled, this option improves the performance of the kernel on such
+	  systems. However, the kernel and userspace programs will run much more
+	  slowly, or will not be able to run at all, on systems that do not
+	  support efficient unaligned memory accesses.
 
-	  If unsure what to do here, say N.
+endchoice
 
 endmenu # "Platform type"
 

arch/riscv/include/asm/cpufeature.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright 2022-2023 Rivos, Inc
+ * Copyright 2022-2024 Rivos, Inc
  */
 
 #ifndef _ASM_CPUFEATURE_H
@@ -28,29 +28,38 @@ struct riscv_isainfo {
 
 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];
 
 void riscv_user_isa_enable(void);
 
-#ifdef CONFIG_RISCV_MISALIGNED
-bool unaligned_ctl_available(void);
-bool check_unaligned_access_emulated(int cpu);
+#if defined(CONFIG_RISCV_MISALIGNED)
+bool check_unaligned_access_emulated_all_cpus(void);
 void unaligned_emulation_finish(void);
+bool unaligned_ctl_available(void);
+DECLARE_PER_CPU(long, misaligned_access_speed);
 #else
 static inline bool unaligned_ctl_available(void)
 {
 	return false;
 }
+#endif
+
+#if defined(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)
+DECLARE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key);
 
-static inline bool check_unaligned_access_emulated(int cpu)
+static __always_inline bool has_fast_unaligned_accesses(void)
 {
-	return false;
+	return static_branch_likely(&fast_unaligned_access_speed_key);
+}
+#else
+static __always_inline bool has_fast_unaligned_accesses(void)
+{
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+		return true;
+	else
+		return false;
 }
-
-static inline void unaligned_emulation_finish(void) {}
 #endif
 
 unsigned long riscv_get_elf_hwcap(void);
@@ -135,6 +144,4 @@ static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsi
 	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
 }
 
-DECLARE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
-
 #endif

arch/riscv/kernel/Makefile

@@ -38,7 +38,6 @@ extra-y += vmlinux.lds
 obj-y	+= head.o
 obj-y	+= soc.o
 obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o
-obj-y	+= copy-unaligned.o
 obj-y	+= cpu.o
 obj-y	+= cpufeature.o
 obj-y	+= entry.o
@@ -62,6 +61,9 @@ obj-y	+= tests/
 obj-$(CONFIG_MMU) += vdso.o vdso/
 
 obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
+obj-$(CONFIG_RISCV_MISALIGNED)	+= unaligned_access_speed.o
+obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)	+= copy-unaligned.o
+
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
 obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o