diff options
| author | Evan Green <evan@rivosinc.com> | 2023-04-07 16:11:01 -0700 |
|---|---|---|
| committer | Palmer Dabbelt <palmer@rivosinc.com> | 2023-04-18 15:48:16 -0700 |
| commit | 62a31d6e38bd0faef7c956b358d651f7bdc4ae0c (patch) | |
| tree | 87f6468aa566a9d30fe225fa1e444e64cb387dff /arch/riscv/include | |
| parent | 00e76e2c6a2bd3976d44d4a1fdd0b7a3c2566607 (diff) | |
RISC-V: hwprobe: Support probing of misaligned access performance
This allows userspace to select various routines to use based on the
performance of misaligned access on the target hardware.
Rather than adding DT bindings, this change taps into the alternatives
mechanism used to probe CPU errata. Add a new function pointer alongside
the vendor-specific errata_patch_func() that probes for desirable errata
(otherwise known as "features"). Unlike the errata_patch_func(), this
function is called on each CPU as it comes up, so it can save
feature information per-CPU.
The T-head C906 has fast unaligned access, both as defined by GCC [1],
and in performing a basic benchmark, which determined that byte copies
are >50% slower than a misaligned word copy of the same data size (source
for this test at [2]):
bytecopy size f000 count 50000 offset 0 took 31664899 us
wordcopy size f000 count 50000 offset 0 took 5180919 us
wordcopy size f000 count 50000 offset 1 took 13416949 us
[1] https://github.com/gcc-mirror/gcc/blob/master/gcc/config/riscv/riscv.cc#L353
[2] https://pastebin.com/EPXvDHSW
Co-developed-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Evan Green <evan@rivosinc.com>
Reviewed-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Tested-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Paul Walmsley <paul.walmsley@sifive.com>
Link: https://lore.kernel.org/r/20230407231103.2622178-5-evan@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Diffstat (limited to 'arch/riscv/include')
| -rw-r--r-- | arch/riscv/include/asm/alternative.h | 5 | ||||
| -rw-r--r-- | arch/riscv/include/asm/cpufeature.h | 2 | ||||
| -rw-r--r-- | arch/riscv/include/asm/hwprobe.h | 2 | ||||
| -rw-r--r-- | arch/riscv/include/uapi/asm/hwprobe.h | 7 |
4 files changed, 15 insertions, 1 deletions
diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h index b8648d4f2ac1..b5774e24d4a3 100644 --- a/arch/riscv/include/asm/alternative.h +++ b/arch/riscv/include/asm/alternative.h @@ -28,6 +28,7 @@ #define ALT_OLD_PTR(a) __ALT_PTR(a, old_offset) #define ALT_ALT_PTR(a) __ALT_PTR(a, alt_offset) +void __init probe_vendor_features(unsigned int cpu); void __init apply_boot_alternatives(void); void __init apply_early_boot_alternatives(void); void apply_module_alternatives(void *start, size_t length); @@ -55,11 +56,15 @@ void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned long archid, unsigned long impid, unsigned int stage); +void thead_feature_probe_func(unsigned int cpu, unsigned long archid, + unsigned long impid); + void riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned int stage); #else /* CONFIG_RISCV_ALTERNATIVE */ +static inline void probe_vendor_features(unsigned int cpu) { } static inline void apply_boot_alternatives(void) { } static inline void apply_early_boot_alternatives(void) { } static inline void apply_module_alternatives(void *start, size_t length) { } diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 66ebaae449c8..808d5403f2ac 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -18,4 +18,6 @@ struct riscv_cpuinfo { DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); +DECLARE_PER_CPU(long, misaligned_access_speed); + #endif diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index d717c80a64ff..78936f4ff513 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 4 +#define RISCV_HWPROBE_MAX_KEY 5 #endif diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index 398e08f7e083..8d745a4ad8a2 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -25,6 +25,13 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_KEY_IMA_EXT_0 4 #define RISCV_HWPROBE_IMA_FD (1 << 0) #define RISCV_HWPROBE_IMA_C (1 << 1) +#define RISCV_HWPROBE_KEY_CPUPERF_0 5 +#define RISCV_HWPROBE_MISALIGNED_UNKNOWN (0 << 0) +#define RISCV_HWPROBE_MISALIGNED_EMULATED (1 << 0) +#define RISCV_HWPROBE_MISALIGNED_SLOW (2 << 0) +#define RISCV_HWPROBE_MISALIGNED_FAST (3 << 0) +#define RISCV_HWPROBE_MISALIGNED_UNSUPPORTED (4 << 0) +#define RISCV_HWPROBE_MISALIGNED_MASK (7 << 0) /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ #endif |