dma-mapping: provide a generic dma-noncoherent implementation

Add a new dma_map_ops implementation that uses dma-direct for the
address mapping of streaming mappings, and which requires arch-specific
implemenations of coherent allocate/free.

Architectures have to provide flushing helpers to ownership trasnfers
to the device and/or CPU, and can provide optional implementations of
the coherent mmap functionality, and the cache_flush routines for
non-coherent long term allocations.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Alexey Brodkin <abrodkin@synopsys.com>
Acked-by: Vineet Gupta <vgupta@synopsys.com>

4 files changed, 127 insertions, 4 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 6c4e9d0ce5d1..7a913937888b 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -441,10 +441,30 @@ config ARCH_DMA_ADDR_T_64BIT
 config IOMMU_HELPER
         bool
 
+config ARCH_HAS_SYNC_DMA_FOR_DEVICE
+        bool
+
+config ARCH_HAS_SYNC_DMA_FOR_CPU
+        bool
+        select NEED_DMA_MAP_STATE
+
 config DMA_DIRECT_OPS
         bool
         depends on HAS_DMA
 
+config DMA_NONCOHERENT_OPS
+        bool
+        depends on HAS_DMA
+        select DMA_DIRECT_OPS
+
+config DMA_NONCOHERENT_MMAP
+        bool
+        depends on DMA_NONCOHERENT_OPS
+
+config DMA_NONCOHERENT_CACHE_SYNC
+        bool
+        depends on DMA_NONCOHERENT_OPS
+
 config DMA_VIRT_OPS
         bool
         depends on HAS_DMA
diff --git a/lib/Makefile b/lib/Makefile
index 94203b5eecd4..9f18c8152281 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -30,6 +30,7 @@ lib-$(CONFIG_PRINTK) += dump_stack.o
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
 lib-$(CONFIG_DMA_DIRECT_OPS) += dma-direct.o
+lib-$(CONFIG_DMA_NONCOHERENT_OPS) += dma-noncoherent.o
 lib-$(CONFIG_DMA_VIRT_OPS) += dma-virt.o
 
 lib-y   += kobject.o klist.o
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index df9e726e0712..b824eb218782 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -128,7 +128,7 @@ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
                 free_pages((unsigned long)cpu_addr, page_order);
 }
 
-static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
+dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
                 unsigned long offset, size_t size, enum dma_data_direction dir,
                 unsigned long attrs)
 {
@@ -139,8 +139,8 @@ static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
         return dma_addr;
 }
 
-static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
-                int nents, enum dma_data_direction dir, unsigned long attrs)
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+                enum dma_data_direction dir, unsigned long attrs)
 {
         int i;
         struct scatterlist *sg;
@@ -175,7 +175,7 @@ int dma_direct_supported(struct device *dev, u64 mask)
         return 1;
 }
 
-static int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
+int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
         return dma_addr == DIRECT_MAPPING_ERROR;
 }
diff --git a/lib/dma-noncoherent.c b/lib/dma-noncoherent.c
new file mode 100644
index 000000000000..79e9a757387f
--- /dev/null
+++ b/lib/dma-noncoherent.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Christoph Hellwig.
+ *
+ * DMA operations that map physical memory directly without providing cache
+ * coherence.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/scatterlist.h>
+
+static void dma_noncoherent_sync_single_for_device(struct device *dev,
+                dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+        arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir);
+}
+
+static void dma_noncoherent_sync_sg_for_device(struct device *dev,
+                struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+        struct scatterlist *sg;
+        int i;
+
+        for_each_sg(sgl, sg, nents, i)
+                arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+}
+
+static dma_addr_t dma_noncoherent_map_page(struct device *dev, struct page *page,
+                unsigned long offset, size_t size, enum dma_data_direction dir,
+                unsigned long attrs)
+{
+        dma_addr_t addr;
+
+        addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+        if (!dma_mapping_error(dev, addr) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+                arch_sync_dma_for_device(dev, page_to_phys(page) + offset,
+                                size, dir);
+        return addr;
+}
+
+static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl,
+                int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+        nents = dma_direct_map_sg(dev, sgl, nents, dir, attrs);
+        if (nents > 0 && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+                dma_noncoherent_sync_sg_for_device(dev, sgl, nents, dir);
+        return nents;
+}
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+static void dma_noncoherent_sync_single_for_cpu(struct device *dev,
+                dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+        arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
+}
+
+static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
+                struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+        struct scatterlist *sg;
+        int i;
+
+        for_each_sg(sgl, sg, nents, i)
+                arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+}
+
+static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr,
+                size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+        if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+                dma_noncoherent_sync_single_for_cpu(dev, addr, size, dir);
+}
+
+static void dma_noncoherent_unmap_sg(struct device *dev, struct scatterlist *sgl,
+                int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+        if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+                dma_noncoherent_sync_sg_for_cpu(dev, sgl, nents, dir);
+}
+#endif
+
+const struct dma_map_ops dma_noncoherent_ops = {
+        .alloc                  = arch_dma_alloc,
+        .free                   = arch_dma_free,
+        .mmap                   = arch_dma_mmap,
+        .sync_single_for_device = dma_noncoherent_sync_single_for_device,
+        .sync_sg_for_device     = dma_noncoherent_sync_sg_for_device,
+        .map_page               = dma_noncoherent_map_page,
+        .map_sg                 = dma_noncoherent_map_sg,
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+        .sync_single_for_cpu    = dma_noncoherent_sync_single_for_cpu,
+        .sync_sg_for_cpu        = dma_noncoherent_sync_sg_for_cpu,
+        .unmap_page             = dma_noncoherent_unmap_page,
+        .unmap_sg               = dma_noncoherent_unmap_sg,
+#endif
+        .dma_supported          = dma_direct_supported,
+        .mapping_error          = dma_direct_mapping_error,
+        .cache_sync             = arch_dma_cache_sync,
+};
+EXPORT_SYMBOL(dma_noncoherent_ops);