riscv: implement cache-management errata for T-Head SoCs

The T-Head C906 and C910 implement a scheme for handling
cache operations different from the generic Zicbom extension.

Add an errata for it next to the generic dma coherency ops.
Reviewed-by: Samuel Holland <samuel@sholland.org>
Tested-by: Samuel Holland <samuel@sholland.org>
Reviewed-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20220706231536.2041855-5-heiko@sntech.deSigned-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/Kconfig.erratas

@@ -55,4 +55,15 @@ config ERRATA_THEAD_PBMT
 
 	  If you don't know what to do here, say "Y".
 
+config ERRATA_THEAD_CMO
+	bool "Apply T-Head cache management errata"
+	depends on ERRATA_THEAD
+	select RISCV_DMA_NONCOHERENT
+	default y
+	help
+	  This will apply the cache management errata to handle the
+	  non-standard handling on non-coherent operations on T-Head SoCs.
+
+	  If you don't know what to do here, say "Y".
+
 endmenu

arch/riscv/errata/thead/errata.c

@@ -27,6 +27,23 @@ static bool errata_probe_pbmt(unsigned int stage,
 	return false;
 }
 
+static bool errata_probe_cmo(unsigned int stage,
+			     unsigned long arch_id, unsigned long impid)
+{
+#ifdef CONFIG_ERRATA_THEAD_CMO
+	if (arch_id != 0 || impid != 0)
+		return false;
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		return false;
+
+	riscv_noncoherent_supported();
+	return true;
+#else
+	return false;
+#endif
+}
+
 static u32 thead_errata_probe(unsigned int stage,
 			      unsigned long archid, unsigned long impid)
 {
@@ -35,6 +52,9 @@ static u32 thead_errata_probe(unsigned int stage,
 	if (errata_probe_pbmt(stage, archid, impid))
 		cpu_req_errata |= (1U << ERRATA_THEAD_PBMT);
 
+	if (errata_probe_cmo(stage, archid, impid))
+		cpu_req_errata |= (1U << ERRATA_THEAD_CMO);
+
 	return cpu_req_errata;
 }
 

arch/riscv/include/asm/errata_list.h

@@ -16,7 +16,8 @@
 
 #ifdef CONFIG_ERRATA_THEAD
 #define	ERRATA_THEAD_PBMT 0
-#define	ERRATA_THEAD_NUMBER 1
+#define	ERRATA_THEAD_CMO 1
+#define	ERRATA_THEAD_NUMBER 2
 #endif
 
 #define	CPUFEATURE_SVPBMT 0
@@ -94,17 +95,54 @@ asm volatile(ALTERNATIVE(						\
 #define ALT_THEAD_PMA(_val)
 #endif
 
+/*
+ * dcache.ipa rs1 (invalidate, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01010      rs1       000      00000  0001011
+ * dache.iva rs1 (invalida, virtual address)
+ *   0000001    00110      rs1       000      00000  0001011
+ *
+ * dcache.cpa rs1 (clean, physical address)
+ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
+ *   0000001    01001      rs1       000      00000  0001011
+ * dcache.cva rs1 (clean, virtual address)
+ *   0000001    00100      rs1       000      00000  0001011
+ *
+ * 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
+ * dcache.civa rs1 (... virtual address)
+ *   0000001    00111      rs1       000      00000  0001011
+ *
+ * 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 0x0245000b"
+#define THEAD_flush_A0	".long 0x0275000b"
+#define THEAD_SYNC_S	".long 0x0190000b"
+
 #define ALT_CMO_OP(_op, _start, _size, _cachesize)			\
-asm volatile(ALTERNATIVE(						\
-	__nops(5),							\
+asm volatile(ALTERNATIVE_2(						\
+	__nops(6),							\
 	"mv a0, %1\n\t"							\
 	"j 2f\n\t"							\
 	"3:\n\t"							\
 	"cbo." __stringify(_op) " (a0)\n\t"				\
 	"add a0, a0, %0\n\t"						\
 	"2:\n\t"							\
-	"bltu a0, %2, 3b\n\t", 0,					\
-		CPUFEATURE_ZICBOM, CONFIG_RISCV_ISA_ZICBOM)		\
+	"bltu a0, %2, 3b\n\t"						\
+	"nop", 0, CPUFEATURE_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)	\
 	: : "r"(_cachesize),						\
 	    "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)),	\
 	    "r"((unsigned long)(_start) + (_size))			\