riscv: errata: thead: use riscv_nonstd_cache_ops for CMO

Previously, we use alternative mechanism to dynamically patch
the CMO operations for THEAD C906/C910 during boot for performance
reason. But as pointed out by Arnd, "there is already a significant
cost in accessing the invalidated cache lines afterwards, which is
likely going to be much higher than the cost of an indirect branch".
And indeed, there's no performance difference with GMAC and EMMC per
my test on Sipeed Lichee Pi 4A board.

Use riscv_nonstd_cache_ops for THEAD C906/C910 CMO to simplify
the alternative code, and to acchieve Arnd's goal -- "I think
moving the THEAD ops at the same level as all nonstandard operations
makes sense, but I'd still leave CMO as an explicit fast path that
avoids the indirect branch. This seems like the right thing to do both
for readability and for platforms on which the indirect branch has a
noticeable overhead."

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Tested-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231114143338.2406-2-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

1 files changed, 6 insertions, 44 deletions

diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 83ed25e43553..ea33288f8a25 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -24,9 +24,8 @@
 
 #ifdef CONFIG_ERRATA_THEAD
 #define	ERRATA_THEAD_PBMT 0
-#define	ERRATA_THEAD_CMO 1
-#define	ERRATA_THEAD_PMU 2
-#define	ERRATA_THEAD_NUMBER 3
+#define	ERRATA_THEAD_PMU 1
+#define	ERRATA_THEAD_NUMBER 2
 #endif
 
 #ifdef __ASSEMBLY__
@@ -94,54 +93,17 @@ asm volatile(ALTERNATIVE(						\
 #define ALT_THEAD_PMA(_val)
 #endif
 
-/*
- * th.dcache.ipa rs1 (invalidate, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000001    01010      rs1       000      00000  0001011
- * th.dache.iva rs1 (invalida, virtual address)
- *   0000001    00110      rs1       000      00000  0001011
- *
- * th.dcache.cpa rs1 (clean, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000001    01001      rs1       000      00000  0001011
- * th.dcache.cva rs1 (clean, virtual address)
- *   0000001    00101      rs1       000      00000  0001011
- *
- * th.dcache.cipa rs1 (clean then invalidate, physical address)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000001    01011      rs1       000      00000  0001011
- * th.dcache.civa rs1 (... virtual address)
- *   0000001    00111      rs1       000      00000  0001011
- *
- * th.sync.s (make sure all cache operations finished)
- * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
- *   0000000    11001     00000      000      00000  0001011
- */
-#define THEAD_INVAL_A0	".long 0x0265000b"
-#define THEAD_CLEAN_A0	".long 0x0255000b"
-#define THEAD_FLUSH_A0	".long 0x0275000b"
-#define THEAD_SYNC_S	".long 0x0190000b"
-
 #define ALT_CMO_OP(_op, _start, _size, _cachesize)			\
-asm volatile(ALTERNATIVE_2(						\
-	__nops(6),							\
+asm volatile(ALTERNATIVE(						\
+	__nops(5),							\
 	"mv a0, %1\n\t"							\
 	"j 2f\n\t"							\
 	"3:\n\t"							\
 	CBO_##_op(a0)							\
 	"add a0, a0, %0\n\t"						\
 	"2:\n\t"							\
-	"bltu a0, %2, 3b\n\t"						\
-	"nop", 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM,	\
-	"mv a0, %1\n\t"							\
-	"j 2f\n\t"							\
-	"3:\n\t"							\
-	THEAD_##_op##_A0 "\n\t"						\
-	"add a0, a0, %0\n\t"						\
-	"2:\n\t"							\
-	"bltu a0, %2, 3b\n\t"						\
-	THEAD_SYNC_S, THEAD_VENDOR_ID,					\
-			ERRATA_THEAD_CMO, CONFIG_ERRATA_THEAD_CMO)	\
+	"bltu a0, %2, 3b\n\t",						\
+	0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM)		\
 	: : "r"(_cachesize),						\
 	    "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)),	\
 	    "r"((unsigned long)(_start) + (_size))			\