Merge patch series "RISC-V: Apply Zicboz to clear_page"

Andrew Jones <ajones@ventanamicro.com> says:

When the Zicboz extension is available we can more rapidly zero naturally
aligned Zicboz block sized chunks of memory. As pages are always page
aligned and are larger than any Zicboz block size will be, then
clear_page() appears to be a good candidate for the extension. While cycle
count and energy consumption should also be considered, we can be pretty
certain that implementing clear_page() with the Zicboz extension is a win
by comparing the new dynamic instruction count with its current count[1].
Doing so we see that the new count is just over a quarter of the old count
(see patch6's commit message for more details).

For those of you who reviewed v1[2], you may be looking for the memset()
patches. As pointed out in v1, and a couple follow-up emails, it's not
clear that patching memset() is a win yet. When I get a chance to test
on real hardware with a comprehensive benchmark collection then I can
post the memset() patches separately (assuming the benchmarks show it's
worthwhile).

* b4-shazam-merge:
  RISC-V: KVM: Expose Zicboz to the guest
  RISC-V: KVM: Provide UAPI for Zicboz block size
  RISC-V: Use Zicboz in clear_page when available
  RISC-V: cpufeatures: Put the upper 16 bits of patch ID to work
  RISC-V: Add Zicboz detection and block size parsing
  dt-bindings: riscv: Document cboz-block-size
  RISC-V: Factor out body of riscv_init_cbom_blocksize loop
  RISC-V: alternatives: Support patching multiple insns in assembly

Link: https://lore.kernel.org/r/20230224162631.405473-1-ajones@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

6 files changed, 19 insertions, 5 deletions

diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h
index 993a44a8fdac..b8c55fb3ab2c 100644
--- a/arch/riscv/include/asm/alternative-macros.h
+++ b/arch/riscv/include/asm/alternative-macros.h
@@ -14,7 +14,7 @@
 	.4byte \patch_id
 .endm
 
-.macro ALT_NEW_CONTENT vendor_id, patch_id, enable = 1, new_c : vararg
+.macro ALT_NEW_CONTENT vendor_id, patch_id, enable = 1, new_c
 	.if \enable
 	.pushsection .alternative, "a"
 	ALT_ENTRY 886b, 888f, \vendor_id, \patch_id, 889f - 888f
@@ -41,13 +41,13 @@
 	\old_c
 	.option pop
 887 :
-	ALT_NEW_CONTENT \vendor_id, \patch_id, \enable, \new_c
+	ALT_NEW_CONTENT \vendor_id, \patch_id, \enable, "\new_c"
 .endm
 
 .macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, patch_id_1, enable_1,	\
 				new_c_2, vendor_id_2, patch_id_2, enable_2
 	ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \patch_id_1, \enable_1
-	ALT_NEW_CONTENT \vendor_id_2, \patch_id_2, \enable_2, \new_c_2
+	ALT_NEW_CONTENT \vendor_id_2, \patch_id_2, \enable_2, "\new_c_2"
 .endm
 
 #define __ALTERNATIVE_CFG(...)		ALTERNATIVE_CFG __VA_ARGS__
diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h
index c8dea9e94310..58ccd2f8cab7 100644
--- a/arch/riscv/include/asm/alternative.h
+++ b/arch/riscv/include/asm/alternative.h
@@ -13,10 +13,14 @@
 #ifdef CONFIG_RISCV_ALTERNATIVE
 
 #include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <asm/hwcap.h>
 
+#define PATCH_ID_CPUFEATURE_ID(p)		lower_16_bits(p)
+#define PATCH_ID_CPUFEATURE_VALUE(p)		upper_16_bits(p)
+
 #define RISCV_ALTERNATIVES_BOOT		0 /* alternatives applied during regular boot */
 #define RISCV_ALTERNATIVES_MODULE	1 /* alternatives applied during module-init */
 #define RISCV_ALTERNATIVES_EARLY_BOOT	2 /* alternatives applied before mmu start */
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 03e3b95ae6da..8091b8bf4883 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -50,7 +50,8 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
 #endif /* CONFIG_SMP */
 
 extern unsigned int riscv_cbom_block_size;
-void riscv_init_cbom_blocksize(void);
+extern unsigned int riscv_cboz_block_size;
+void riscv_init_cbo_blocksizes(void);
 
 #ifdef CONFIG_RISCV_DMA_NONCOHERENT
 void riscv_noncoherent_supported(void);
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 0ed15c2a2816..bbde5aafa957 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -43,6 +43,7 @@
 #define RISCV_ISA_EXT_ZICBOM		31
 #define RISCV_ISA_EXT_ZIHINTPAUSE	32
 #define RISCV_ISA_EXT_SVNAPOT		33
+#define RISCV_ISA_EXT_ZICBOZ		34
 
 #define RISCV_ISA_EXT_MAX		64
 #define RISCV_ISA_EXT_NAME_LEN_MAX	32
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 0f3220e253bc..8666960d0113 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -44,10 +44,14 @@
 
 #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)