RISC-V: Use Zicboz in clear_page when available

Using memset() to zero a 4K page takes 563 total instructions, where
20 are branches. clear_page(), with Zicboz and a 64 byte block size,
takes 169 total instructions, where 4 are branches and 33 are nops.
Even though the block size is a variable, thanks to alternatives, we
can still implement a Duff device without having to do any preliminary
calculations. This is achieved by using the alternatives' cpufeature
value (the upper 16 bits of patch_id). The value used is the maximum
zicboz block size order accepted at the patch site. This enables us
to stop patching / unrolling when 4K bytes have been zeroed (we would
loop and continue after 4K if the page size would be larger)

For 4K pages, unrolling 16 times allows block sizes of 64 and 128 to
only loop a few times and larger block sizes to not loop at all. Since
cbo.zero doesn't take an offset, we also need an 'add' after each
instruction, making the loop body 112 to 160 bytes. Hopefully this
is small enough to not cause icache misses.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230224162631.405473-7-ajones@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Author: Andrew Jones

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

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 */

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)
 

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;
 }
 

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

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)