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()

2 files changed, 117 insertions, 0 deletions

diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index ac7a25298a04..d76aabf4b94d 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -30,3 +30,4 @@ endif
 endif
 
 obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
+obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
new file mode 100644
index 000000000000..cd2225304c82
--- /dev/null
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -0,0 +1,116 @@
+// 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;
+}