diff options
-rw-r--r-- | arch/riscv/Kconfig | 13 | ||||
-rw-r--r-- | arch/riscv/include/asm/insn-def.h | 4 | ||||
-rw-r--r-- | arch/riscv/include/asm/page.h | 6 | ||||
-rw-r--r-- | arch/riscv/kernel/cpufeature.c | 11 | ||||
-rw-r--r-- | arch/riscv/lib/Makefile | 1 | ||||
-rw-r--r-- | arch/riscv/lib/clear_page.S | 74 |
6 files changed, 108 insertions, 1 deletions
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 69797e6eed6f..275be2ee87bf 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -457,6 +457,19 @@ config RISCV_ISA_ZICBOM If you don't know what to do here, say Y. +config RISCV_ISA_ZICBOZ + bool "Zicboz extension support for faster zeroing of memory" + depends on !XIP_KERNEL && MMU + select RISCV_ALTERNATIVE + default y + help + Enable the use of the ZICBOZ extension (cbo.zero instruction) + when available. + + The Zicboz extension is used for faster zeroing of memory. + + If you don't know what to do here, say Y. + config TOOLCHAIN_HAS_ZIHINTPAUSE bool default y diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h index e01ab51f50d2..6960beb75f32 100644 --- a/arch/riscv/include/asm/insn-def.h +++ b/arch/riscv/include/asm/insn-def.h @@ -192,4 +192,8 @@ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ RS1(base), SIMM12(2)) +#define CBO_zero(base) \ + INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ + RS1(base), SIMM12(4)) + #endif /* __ASM_INSN_DEF_H */ diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 7fed7c431928..21fdf9527ce8 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -49,10 +49,14 @@ #ifndef __ASSEMBLY__ +#ifdef CONFIG_RISCV_ISA_ZICBOZ +void clear_page(void *page); +#else #define clear_page(pgaddr) memset((pgaddr), 0, PAGE_SIZE) +#endif #define copy_page(to, from) memcpy((to), (from), PAGE_SIZE) -#define clear_user_page(pgaddr, vaddr, page) memset((pgaddr), 0, PAGE_SIZE) +#define clear_user_page(pgaddr, vaddr, page) clear_page(pgaddr) #define copy_user_page(vto, vfrom, vaddr, topg) \ memcpy((vto), (vfrom), PAGE_SIZE) diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index d424cd76beb1..8e7b0d703841 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -293,6 +293,17 @@ static bool riscv_cpufeature_patch_check(u16 id, u16 value) if (!value) return true; + switch (id) { + case RISCV_ISA_EXT_ZICBOZ: + /* + * Zicboz alternative applications provide the maximum + * supported block size order, or zero when it doesn't + * matter. If the current block size exceeds the maximum, + * then the alternative cannot be applied. + */ + return riscv_cboz_block_size <= (1U << value); + } + return false; } diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 6c74b0bedd60..26cb2502ecf8 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -8,5 +8,6 @@ lib-y += strlen.o lib-y += strncmp.o lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o +lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/riscv/lib/clear_page.S b/arch/riscv/lib/clear_page.S new file mode 100644 index 000000000000..d7a256eb53f4 --- /dev/null +++ b/arch/riscv/lib/clear_page.S @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2023 Ventana Micro Systems Inc. + */ + +#include <linux/linkage.h> +#include <asm/asm.h> +#include <asm/alternative-macros.h> +#include <asm-generic/export.h> +#include <asm/hwcap.h> +#include <asm/insn-def.h> +#include <asm/page.h> + +#define CBOZ_ALT(order, old, new) \ + ALTERNATIVE(old, new, 0, \ + ((order) << 16) | RISCV_ISA_EXT_ZICBOZ, \ + CONFIG_RISCV_ISA_ZICBOZ) + +/* void clear_page(void *page) */ +SYM_FUNC_START(clear_page) + li a2, PAGE_SIZE + + /* + * If Zicboz isn't present, or somehow has a block + * size larger than 4K, then fallback to memset. + */ + CBOZ_ALT(12, "j .Lno_zicboz", "nop") + + lw a1, riscv_cboz_block_size + add a2, a0, a2 +.Lzero_loop: + CBO_zero(a0) + add a0, a0, a1 + CBOZ_ALT(11, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_zero(a0) + add a0, a0, a1 + CBOZ_ALT(10, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBOZ_ALT(9, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBOZ_ALT(8, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + bltu a0, a2, .Lzero_loop + ret +.Lno_zicboz: + li a1, 0 + tail __memset +SYM_FUNC_END(clear_page) +EXPORT_SYMBOL(clear_page) |