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()

Documentation/devicetree/bindings/riscv/cpus.yaml

@@ -63,6 +63,11 @@ properties:
       - riscv,sv48
       - riscv,none
 
+  riscv,cbom-block-size:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      The blocksize in bytes for the Zicbom cache operations.
+
   riscv,isa:
     description:
       Identifies the specific RISC-V instruction set architecture

arch/riscv/Kconfig

@@ -113,6 +113,7 @@ config RISCV
 	select MODULES_USE_ELF_RELA if MODULES
 	select MODULE_SECTIONS if MODULES
 	select OF
+	select OF_DMA_DEFAULT_COHERENT
 	select OF_EARLY_FLATTREE
 	select OF_IRQ
 	select PCI_DOMAINS_GENERIC if PCI
@@ -218,6 +219,14 @@ config PGTABLE_LEVELS
 config LOCKDEP_SUPPORT
 	def_bool y
 
+config RISCV_DMA_NONCOHERENT
+	bool
+	select ARCH_HAS_DMA_PREP_COHERENT
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SETUP_DMA_OPS
+	select DMA_DIRECT_REMAP
+
 source "arch/riscv/Kconfig.socs"
 source "arch/riscv/Kconfig.erratas"
 
@@ -392,6 +401,28 @@ config RISCV_ISA_SVPBMT
 
 	   If you don't know what to do here, say Y.
 
+config CC_HAS_ZICBOM
+	bool
+	default y if 64BIT && $(cc-option,-mabi=lp64 -march=rv64ima_zicbom)
+	default y if 32BIT && $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom)
+
+config RISCV_ISA_ZICBOM
+	bool "Zicbom extension support for non-coherent DMA operation"
+	depends on CC_HAS_ZICBOM
+	depends on !XIP_KERNEL && MMU
+	select RISCV_DMA_NONCOHERENT
+	select RISCV_ALTERNATIVE
+	default y
+	help
+	   Adds support to dynamically detect the presence of the ZICBOM
+	   extension (Cache Block Management Operations) and enable its
+	   usage.
+
+	   The Zicbom extension can be used to handle for example
+	   non-coherent DMA support on devices that need it.
+
+	   If you don't know what to do here, say Y.
+
 config FPU
 	bool "FPU support"
 	default y

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 # "CPU errata selection"

arch/riscv/Makefile

@@ -56,6 +56,10 @@ riscv-march-$(CONFIG_RISCV_ISA_C)	:= $(riscv-march-y)c
 toolchain-need-zicsr-zifencei := $(call cc-option-yn, -march=$(riscv-march-y)_zicsr_zifencei)
 riscv-march-$(toolchain-need-zicsr-zifencei) := $(riscv-march-y)_zicsr_zifencei
 
+# Check if the toolchain supports Zicbom extension
+toolchain-supports-zicbom := $(call cc-option-yn, -march=$(riscv-march-y)_zicbom)
+riscv-march-$(toolchain-supports-zicbom) := $(riscv-march-y)_zicbom
+
 KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y))
 KBUILD_AFLAGS += -march=$(riscv-march-y)
 

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/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.

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.
  */

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

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,
 };
 

arch/riscv/kernel/cpu.c

@@ -93,6 +93,7 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid)
 static struct riscv_isa_ext_data isa_ext_arr[] = {
 	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
 	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
 	__RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX),
 };
 

arch/riscv/kernel/cpufeature.c

@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <asm/alternative.h>
+#include <asm/cacheflush.h>
 #include <asm/errata_list.h>
 #include <asm/hwcap.h>
 #include <asm/patch.h>
@@ -200,6 +201,7 @@ void __init riscv_fill_hwcap(void)
 			} else {
 				SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF);
 				SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT);
+				SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM);
 			}
 #undef SET_ISA_EXT_MAP
 		}
@@ -261,6 +263,25 @@ static bool __init_or_module cpufeature_probe_svpbmt(unsigned int stage)
 	return false;
 }
 
+static bool __init_or_module cpufeature_probe_zicbom(unsigned int stage)
+{
+#ifdef CONFIG_RISCV_ISA_ZICBOM
+	switch (stage) {
+	case RISCV_ALTERNATIVES_EARLY_BOOT:
+		return false;
+	default:
+		if (riscv_isa_extension_available(NULL, ZICBOM)) {
+			riscv_noncoherent_supported();
+			return true;
+		} else {
+			return false;
+		}
+	}
+#endif
+
+	return false;
+}
+
 /*
  * Probe presence of individual extensions.
  *
@@ -275,6 +296,9 @@ static u32 __init_or_module cpufeature_probe(unsigned int stage)
 	if (cpufeature_probe_svpbmt(stage))
 		cpu_req_feature |= (1U << CPUFEATURE_SVPBMT);
 
+	if (cpufeature_probe_zicbom(stage))
+		cpu_req_feature |= (1U << CPUFEATURE_ZICBOM);
+
 	return cpu_req_feature;
 }
 

arch/riscv/kernel/setup.c

@@ -22,6 +22,7 @@
 #include <linux/crash_dump.h>
 
 #include <asm/alternative.h>
+#include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
 #include <asm/early_ioremap.h>
 #include <asm/pgtable.h>
@@ -296,6 +297,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	riscv_fill_hwcap();
+	riscv_init_cbom_blocksize();
 	apply_boot_alternatives();
 }
 

arch/riscv/mm/Makefile

@@ -30,3 +30,4 @@ endif
 endif
 
 obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
+obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o

arch/riscv/mm/dma-noncoherent.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * RISC-V specific functions to support DMA for non-coherent devices
+ *
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <asm/cacheflush.h>
+
+static unsigned int riscv_cbom_block_size = L1_CACHE_BYTES;
+static bool noncoherent_supported;
+
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+			      enum dma_data_direction dir)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+		break;
+	case DMA_FROM_DEVICE:
+		ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+		break;
+	case DMA_BIDIRECTIONAL:
+		ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+		break;
+	default:
+		break;
+	}
+}
+
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+			   enum dma_data_direction dir)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+		break;
+	default:
+		break;
+	}
+}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+	void *flush_addr = page_address(page);
+
+	ALT_CMO_OP(flush, flush_addr, size, riscv_cbom_block_size);
+}
+
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+		const struct iommu_ops *iommu, bool coherent)
+{
+	WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
+		   TAINT_CPU_OUT_OF_SPEC,
+		   "%s %s: ARCH_DMA_MINALIGN smaller than riscv,cbom-block-size (%d < %d)",
+		   dev_driver_string(dev), dev_name(dev),
+		   ARCH_DMA_MINALIGN, riscv_cbom_block_size);
+
+	WARN_TAINT(!coherent && !noncoherent_supported, TAINT_CPU_OUT_OF_SPEC,
+		   "%s %s: device non-coherent but no non-coherent operations supported",
+		   dev_driver_string(dev), dev_name(dev));
+
+	dev->dma_coherent = coherent;
+}
+
+#ifdef CONFIG_RISCV_ISA_ZICBOM
+void riscv_init_cbom_blocksize(void)
+{
+	struct device_node *node;
+	int ret;
+	u32 val;
+
+	for_each_of_cpu_node(node) {
+		unsigned long hartid;
+		int cbom_hartid;
+
+		ret = riscv_of_processor_hartid(node, &hartid);
+		if (ret)
+			continue;
+
+		if (hartid < 0)
+			continue;
+
+		/* set block-size for cbom extension if available */
+		ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
+		if (ret)
+			continue;
+
+		if (!riscv_cbom_block_size) {
+			riscv_cbom_block_size = val;
+			cbom_hartid = hartid;
+		} else {
+			if (riscv_cbom_block_size != val)
+				pr_warn("cbom-block-size mismatched between harts %d and %lu\n",
+					cbom_hartid, hartid);
+		}
+	}
+}
+#endif
+
+void riscv_noncoherent_supported(void)
+{
+	noncoherent_supported = true;
+}

drivers/of/address.c

@@ -1045,26 +1045,29 @@ phys_addr_t __init of_dma_get_max_cpu_address(struct device_node *np)
  *
  * It returns true if "dma-coherent" property was found
  * for this device in the DT, or if DMA is coherent by
- * default for OF devices on the current platform.
+ * default for OF devices on the current platform and no
+ * "dma-noncoherent" property was found for this device.
  */
 bool of_dma_is_coherent(struct device_node *np)
 {
 	struct device_node *node;
-
-	if (IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT))
-		return true;
+	bool is_coherent = IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT);
 
 	node = of_node_get(np);
 
 	while (node) {
 		if (of_property_read_bool(node, "dma-coherent")) {
-			of_node_put(node);
-			return true;
+			is_coherent = true;
+			break;
+		}
+		if (of_property_read_bool(node, "dma-noncoherent")) {
+			is_coherent = false;
+			break;
 		}
 		node = of_get_next_dma_parent(node);
 	}
 	of_node_put(node);
-	return false;
+	return is_coherent;
 }
 EXPORT_SYMBOL_GPL(of_dma_is_coherent);