Merge patch series "RISC-V: Detect and report speed of unaligned vect…

…or accesses"

Charlie Jenkins <charlie@rivosinc.com> says:

Adds support for detecting and reporting the speed of unaligned vector
accesses on RISC-V CPUs. Adds vec_misaligned_speed key to the hwprobe
adds Zicclsm to cpufeature and fixes the check for scalar unaligned
emulated all CPUs. The vec_misaligned_speed key keeps the same format
as the scalar unaligned access speed key.

This set does not emulate unaligned vector accesses on CPUs that do not
support them. Only reports if userspace can run them and speed of
unaligned vector accesses if supported.

* b4-shazam-merge:
  RISC-V: hwprobe: Document unaligned vector perf key
  RISC-V: Report vector unaligned access speed hwprobe
  RISC-V: Detect unaligned vector accesses supported
  RISC-V: Replace RISCV_MISALIGNED with RISCV_SCALAR_MISALIGNED
  RISC-V: Scalar unaligned access emulated on hotplug CPUs
  RISC-V: Check scalar unaligned access on all CPUs

Link: https://lore.kernel.org/r/20241017-jesse_unaligned_vector-v10-0-5b33500160f8@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Documentation/arch/riscv/hwprobe.rst

@@ -274,3 +274,19 @@ The following keys are defined:
   represent the highest userspace virtual address usable.
 
 * :c:macro:`RISCV_HWPROBE_KEY_TIME_CSR_FREQ`: Frequency (in Hz) of `time CSR`.
+
+* :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF`: An enum value describing the
+     performance of misaligned vector accesses on the selected set of processors.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN`: The performance of misaligned
+    vector accesses is unknown.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW`: 32-bit misaligned accesses using vector
+    registers are slower than the equivalent quantity of byte accesses via vector registers.
+    Misaligned accesses may be supported directly in hardware, or trapped and emulated by software.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_FAST`: 32-bit misaligned accesses using vector
+    registers are faster than the equivalent quantity of byte accesses via vector registers.
+
+  * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED`: Misaligned vector accesses are
+    not supported at all and will generate a misaligned address fault.

arch/riscv/Kconfig

@@ -786,10 +786,24 @@ config THREAD_SIZE_ORDER
 
 config RISCV_MISALIGNED
 	bool
+	help
+	  Embed support for detecting and emulating misaligned
+	  scalar or vector loads and stores.
+
+config RISCV_SCALAR_MISALIGNED
+	bool
+	select RISCV_MISALIGNED
 	select SYSCTL_ARCH_UNALIGN_ALLOW
 	help
 	  Embed support for emulating misaligned loads and stores.
 
+config RISCV_VECTOR_MISALIGNED
+	bool
+	select RISCV_MISALIGNED
+	depends on RISCV_ISA_V
+	help
+	  Enable detecting support for vector misaligned loads and stores.
+
 choice
 	prompt "Unaligned Accesses Support"
 	default RISCV_PROBE_UNALIGNED_ACCESS
@@ -801,7 +815,7 @@ choice
 
 config RISCV_PROBE_UNALIGNED_ACCESS
 	bool "Probe for hardware unaligned access support"
-	select RISCV_MISALIGNED
+	select RISCV_SCALAR_MISALIGNED
 	help
 	  During boot, the kernel will run a series of tests to determine the
 	  speed of unaligned accesses. This probing will dynamically determine
@@ -812,7 +826,7 @@ config RISCV_PROBE_UNALIGNED_ACCESS
 
 config RISCV_EMULATED_UNALIGNED_ACCESS
 	bool "Emulate unaligned access where system support is missing"
-	select RISCV_MISALIGNED
+	select RISCV_SCALAR_MISALIGNED
 	help
 	  If unaligned memory accesses trap into the kernel as they are not
 	  supported by the system, the kernel will emulate the unaligned
@@ -841,6 +855,46 @@ config RISCV_EFFICIENT_UNALIGNED_ACCESS
 
 endchoice
 
+choice
+	prompt "Vector unaligned Accesses Support"
+	depends on RISCV_ISA_V
+	default RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+	help
+	  This determines the level of support for vector 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_VECTOR_UNALIGNED_ACCESS
+	bool "Probe speed of vector unaligned accesses"
+	select RISCV_VECTOR_MISALIGNED
+	depends on RISCV_ISA_V
+	help
+	  During boot, the kernel will run a series of tests to determine the
+	  speed of vector unaligned accesses if they are supported. This probing
+	  will dynamically determine the speed of vector unaligned accesses on
+	  the underlying system if they are supported.
+
+config RISCV_SLOW_VECTOR_UNALIGNED_ACCESS
+	bool "Assume the system supports slow vector unaligned memory accesses"
+	depends on NONPORTABLE
+	help
+	  Assume that the system supports slow vector 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_VECTOR_UNALIGNED_ACCESS
+	bool "Assume the system supports fast vector unaligned memory accesses"
+	depends on NONPORTABLE
+	help
+	  Assume that the system supports fast vector 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.
+
+endchoice
+
 source "arch/riscv/Kconfig.vendor"
 
 endmenu # "Platform type"

arch/riscv/include/asm/cpufeature.h

@@ -8,6 +8,7 @@
 
 #include <linux/bitmap.h>
 #include <linux/jump_label.h>
+#include <linux/workqueue.h>
 #include <asm/hwcap.h>
 #include <asm/alternative-macros.h>
 #include <asm/errno.h>
@@ -58,8 +59,9 @@ void __init riscv_user_isa_enable(void);
 #define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \
 	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate)
 
-#if defined(CONFIG_RISCV_MISALIGNED)
 bool check_unaligned_access_emulated_all_cpus(void);
+#if defined(CONFIG_RISCV_SCALAR_MISALIGNED)
+void check_unaligned_access_emulated(struct work_struct *work __always_unused);
 void unaligned_emulation_finish(void);
 bool unaligned_ctl_available(void);
 DECLARE_PER_CPU(long, misaligned_access_speed);
@@ -70,6 +72,12 @@ static inline bool unaligned_ctl_available(void)
 }
 #endif
 
+bool check_vector_unaligned_access_emulated_all_cpus(void);
+#if defined(CONFIG_RISCV_VECTOR_MISALIGNED)
+void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused);
+DECLARE_PER_CPU(long, vector_misaligned_access);
+#endif
+
 #if defined(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)
 DECLARE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key);
 

arch/riscv/include/asm/entry-common.h

@@ -25,18 +25,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 void handle_page_fault(struct pt_regs *regs);
 void handle_break(struct pt_regs *regs);
 
-#ifdef CONFIG_RISCV_MISALIGNED
 int handle_misaligned_load(struct pt_regs *regs);
 int handle_misaligned_store(struct pt_regs *regs);
-#else
-static inline int handle_misaligned_load(struct pt_regs *regs)
-{
-	return -1;
-}
-static inline int handle_misaligned_store(struct pt_regs *regs)
-{
-	return -1;
-}
-#endif
 
 #endif /* _ASM_RISCV_ENTRY_COMMON_H */

arch/riscv/include/asm/hwprobe.h

@@ -8,7 +8,7 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 9
+#define RISCV_HWPROBE_MAX_KEY 10
 
 static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 {

arch/riscv/include/asm/vector.h

@@ -21,6 +21,7 @@
 
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
+bool insn_is_vector(u32 insn_buf);
 bool riscv_v_first_use_handler(struct pt_regs *regs);
 void kernel_vector_begin(void);
 void kernel_vector_end(void);
@@ -268,6 +269,7 @@ struct pt_regs;
 
 static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; }
 static __always_inline bool has_vector(void) { return false; }
+static __always_inline bool insn_is_vector(u32 insn_buf) { return false; }
 static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }

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

@@ -88,6 +88,11 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW		2
 #define		RISCV_HWPROBE_MISALIGNED_SCALAR_FAST		3
 #define		RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED	4
+#define RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF	10
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN		0
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW		2
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_FAST		3
+#define		RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED	4
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 /* Flags */

arch/riscv/kernel/Makefile

@@ -70,7 +70,8 @@ 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_RISCV_PROBE_UNALIGNED_ACCESS)		+= copy-unaligned.o
+obj-$(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)	+= vec-copy-unaligned.o
 
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_FPU)		+= kernel_mode_fpu.o

arch/riscv/kernel/copy-unaligned.h

@@ -10,4 +10,9 @@
 void __riscv_copy_words_unaligned(void *dst, const void *src, size_t size);
 void __riscv_copy_bytes_unaligned(void *dst, const void *src, size_t size);
 
+#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+void __riscv_copy_vec_words_unaligned(void *dst, const void *src, size_t size);
+void __riscv_copy_vec_bytes_unaligned(void *dst, const void *src, size_t size);
+#endif
+
 #endif /* __RISCV_KERNEL_COPY_UNALIGNED_H */

arch/riscv/kernel/fpu.S

@@ -170,7 +170,7 @@ SYM_FUNC_END(__fstate_restore)
 	__access_func(f31)
 
 
-#ifdef CONFIG_RISCV_MISALIGNED
+#ifdef CONFIG_RISCV_SCALAR_MISALIGNED
 
 /*
  * Disable compressed instructions set to keep a constant offset between FP
@@ -224,4 +224,4 @@ SYM_FUNC_START(get_f64_reg)
 	fp_access_epilogue
 SYM_FUNC_END(get_f64_reg)
 
-#endif /* CONFIG_RISCV_MISALIGNED */
+#endif /* CONFIG_RISCV_SCALAR_MISALIGNED */

arch/riscv/kernel/sys_hwprobe.c

@@ -201,6 +201,43 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
 }
 #endif
 
+#ifdef CONFIG_RISCV_VECTOR_MISALIGNED
+static u64 hwprobe_vec_misaligned(const struct cpumask *cpus)
+{
+	int cpu;
+	u64 perf = -1ULL;
+
+	/* Return if supported or not even if speed wasn't probed */
+	for_each_cpu(cpu, cpus) {
+		int this_perf = per_cpu(vector_misaligned_access, cpu);
+
+		if (perf == -1ULL)
+			perf = this_perf;
+
+		if (perf != this_perf) {
+			perf = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+			break;
+		}
+	}
+
+	if (perf == -1ULL)
+		return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+
+	return perf;
+}
+#else
+static u64 hwprobe_vec_misaligned(const struct cpumask *cpus)
+{
+	if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS))
+		return RISCV_HWPROBE_MISALIGNED_VECTOR_FAST;
+
+	if (IS_ENABLED(CONFIG_RISCV_SLOW_VECTOR_UNALIGNED_ACCESS))
+		return RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW;
+
+	return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+}
+#endif
+
 static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 			     const struct cpumask *cpus)
 {
@@ -229,6 +266,10 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		pair->value = hwprobe_misaligned(cpus);
 		break;
 
+	case RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF:
+		pair->value = hwprobe_vec_misaligned(cpus);
+		break;
+
 	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
 		pair->value = 0;
 		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))