On 11/01/2019 18:17, Christoph Hellwig wrote:
Just returning the physical address when not map_resource method is
present is highly dangerous as it doesn't take any offset in the
direct mapping into account and does the completely wrong thing for
IOMMUs. Instead provide a proper implementation in the direct mapping
code, and also wire it up for arm and powerpc.
Ignoring the offset was kind of intentional there, because at the time I
was primarily thinking about it in terms of the Keystone 2 platform
where the peripherals are all in the same place (0-2GB) in both the bus
and CPU physical address maps, and only the view of RAM differs between
the two (2-4GB vs. 32-34GB). However, on something like BCM283x, the
peripherals region is also offset from its bus address in the CPU view,
but at a *different* offset relative to that of RAM.
Fortunately, I'm not aware of any platform which has a DMA engine behind
an IOMMU (and thus *needs* to use dma_map_resource() to avoid said IOMMU
blocking the slave device register reads/writes) and also has any
nonzero offsets, and AFAIK the IOMMU-less platforms above aren't using
dma_map_resource() at all, so this change shouldn't actually break
anything, but I guess we have a bit of a problem making it truly generic
and robust :(
Is this perhaps another shove in the direction of overhauling
dma_pfn_offset into an arbitrary "DMA ranges" lookup table?
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
arch/arm/mm/dma-mapping.c | 2 ++
arch/powerpc/kernel/dma-swiotlb.c | 1 +
arch/powerpc/kernel/dma.c | 1 +
include/linux/dma-mapping.h | 12 +++++++-----
kernel/dma/direct.c | 14 ++++++++++++++
5 files changed, 25 insertions(+), 5 deletions(-)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index f1e2922e447c..3c8534904209 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -188,6 +188,7 @@ const struct dma_map_ops arm_dma_ops = {
.unmap_page = arm_dma_unmap_page,
.map_sg = arm_dma_map_sg,
.unmap_sg = arm_dma_unmap_sg,
+ .map_resource = dma_direct_map_resource,
.sync_single_for_cpu = arm_dma_sync_single_for_cpu,
.sync_single_for_device = arm_dma_sync_single_for_device,
.sync_sg_for_cpu = arm_dma_sync_sg_for_cpu,
@@ -211,6 +212,7 @@ const struct dma_map_ops arm_coherent_dma_ops = {
.get_sgtable = arm_dma_get_sgtable,
.map_page = arm_coherent_dma_map_page,
.map_sg = arm_dma_map_sg,
+ .map_resource = dma_direct_map_resource,
.dma_supported = arm_dma_supported,
};
EXPORT_SYMBOL(arm_coherent_dma_ops);
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 7d5fc9751622..fbb2506a414e 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -55,6 +55,7 @@ const struct dma_map_ops powerpc_swiotlb_dma_ops = {
.dma_supported = swiotlb_dma_supported,
.map_page = dma_direct_map_page,
.unmap_page = dma_direct_unmap_page,
+ .map_resource = dma_direct_map_resource,
.sync_single_for_cpu = dma_direct_sync_single_for_cpu,
.sync_single_for_device = dma_direct_sync_single_for_device,
.sync_sg_for_cpu = dma_direct_sync_sg_for_cpu,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index b1903ebb2e9c..258b9e8ebb99 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -273,6 +273,7 @@ const struct dma_map_ops dma_nommu_ops = {
.dma_supported = dma_nommu_dma_supported,
.map_page = dma_nommu_map_page,
.unmap_page = dma_nommu_unmap_page,
+ .map_resource = dma_direct_map_resource,
.get_required_mask = dma_nommu_get_required_mask,
#ifdef CONFIG_NOT_COHERENT_CACHE
.sync_single_for_cpu = dma_nommu_sync_single,
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index cef2127e1d70..d3087829a6df 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -208,6 +208,8 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
unsigned long attrs);
int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
enum dma_data_direction dir, unsigned long attrs);
+dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir, unsigned long attrs);
#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
defined(CONFIG_SWIOTLB)
@@ -346,19 +348,19 @@ static inline dma_addr_t dma_map_resource(struct device *dev,
unsigned long attrs)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
- dma_addr_t addr;
+ dma_addr_t addr = DMA_MAPPING_ERROR;
BUG_ON(!valid_dma_direction(dir));
/* Don't allow RAM to be mapped */
BUG_ON(pfn_valid(PHYS_PFN(phys_addr)));
- addr = phys_addr;
- if (ops && ops->map_resource)
+ if (dma_is_direct(ops))
+ addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
+ else if (ops->map_resource)
addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
Might it be reasonable to do:
if (!dma_is_direct(ops) && ops->map_resource)
addr = ops->map_resource(...);
else
addr = dma_direct_map_resource(...);
and avoid having to explicitly wire up the dma_direct callback elsewhere?
Robin.
debug_dma_map_resource(dev, phys_addr, size, dir, addr);
-
return addr;
}
@@ -369,7 +371,7 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr,
const struct dma_map_ops *ops = get_dma_ops(dev);
BUG_ON(!valid_dma_direction(dir));
- if (ops && ops->unmap_resource)
+ if (!dma_is_direct(ops) && ops->unmap_resource)
ops->unmap_resource(dev, addr, size, dir, attrs);
debug_dma_unmap_resource(dev, addr, size, dir);
}
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 355d16acee6d..8e0359b04957 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -356,6 +356,20 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
}
EXPORT_SYMBOL(dma_direct_map_sg);
+dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ dma_addr_t dma_addr = phys_to_dma(dev, paddr);
+
+ if (unlikely(!dma_direct_possible(dev, dma_addr, size))) {
+ report_addr(dev, dma_addr, size);
+ return DMA_MAPPING_ERROR;
+ }
+
+ return dma_addr;
+}
+EXPORT_SYMBOL(dma_direct_map_resource);
+
/*
* Because 32-bit DMA masks are so common we expect every architecture to be
* able to satisfy them - either by not supporting more physical memory, or by
