riscv: implement Zicbom-based CMO instructions + the t-head variant

This series is based on the alternatives changes done in my svpbmt
series and thus also depends on Atish's isa-extension parsing series.

It implements using the cache-management instructions from the  Zicbom-
extension to handle cache flush, etc actions on platforms needing them.

SoCs using cpu cores from T-Head like the Allwinne D1 implement a
different set of cache instructions. But while they are different,
instructions they provide the same functionality, so a variant can easly
hook into the existing alternatives mechanism on those.

[Palmer:  Some minor fixups, including a RISCV_ISA_ZICBOM dependency on
MMU that's probably not strictly necessary.  The Zicbom support will
trip up sparse for users that have new toolchains, I just sent a patch.]

Link: https://lore.kernel.org/all/20220706231536.2041855-1-heiko@sntech.de/
Link: https://lore.kernel.org/linux-sparse/20220811033138.20676-1-palmer@rivosinc.com/T/#u

* palmer/riscv-zicbom:
  riscv: implement cache-management errata for T-Head SoCs
  riscv: Add support for non-coherent devices using zicbom extension
  dt-bindings: riscv: document cbom-block-size
  of: also handle dma-noncoherent in of_dma_is_coherent()

4 files changed, 72 insertions, 2 deletions

diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
index 9b58b104559e..d3036df23ccb 100644
--- a/arch/riscv/include/asm/cache.h
+++ b/arch/riscv/include/asm/cache.h
@@ -11,6 +11,10 @@
 
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
+#define ARCH_DMA_MINALIGN L1_CACHE_BYTES
+#endif
+
 /*
  * RISC-V requires the stack pointer to be 16-byte aligned, so ensure that
  * the flat loader aligns it accordingly.
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 23ff70350992..a60acaecfeda 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -42,6 +42,16 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
 
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_RISCV_ISA_ZICBOM
+void riscv_init_cbom_blocksize(void);
+#else
+static inline void riscv_init_cbom_blocksize(void) { }
+#endif
+
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
+void riscv_noncoherent_supported(void);
+#endif
+
 /*
  * Bits in sys_riscv_flush_icache()'s flags argument.
  */
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 398e351e7002..19a771085781 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -16,11 +16,13 @@
 
 #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
-#define	CPUFEATURE_NUMBER 1
+#define	CPUFEATURE_ZICBOM 1
+#define	CPUFEATURE_NUMBER 2
 
 #ifdef __ASSEMBLY__
 
@@ -87,6 +89,59 @@ 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_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"						\
+	"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))			\
+	: "a0")
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index e48eebdd2631..ed4045e70f7a 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -54,6 +54,7 @@ extern unsigned long elf_hwcap;
 enum riscv_isa_ext_id {
 	RISCV_ISA_EXT_SSCOFPMF = RISCV_ISA_EXT_BASE,
 	RISCV_ISA_EXT_SVPBMT,
+	RISCV_ISA_EXT_ZICBOM,
 	RISCV_ISA_EXT_ID_MAX = RISCV_ISA_EXT_MAX,
 };