dma-mapping: treat dev->bus_dma_mask as a DMA limit

Using a mask to represent bus DMA constraints has a set of limitations.
The biggest one being it can only hold a power of two (minus one). The
DMA mapping code is already aware of this and treats dev->bus_dma_mask
as a limit. This quirk is already used by some architectures although
still rare.

With the introduction of the Raspberry Pi 4 we've found a new contender
for the use of bus DMA limits, as its PCIe bus can only address the
lower 3GB of memory (of a total of 4GB). This is impossible to represent
with a mask. To make things worse the device-tree code rounds non power
of two bus DMA limits to the next power of two, which is unacceptable in
this case.

In the light of this, rename dev->bus_dma_mask to dev->bus_dma_limit all
over the tree and treat it as such. Note that dev->bus_dma_limit should
contain the higher accessible DMA address.

Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

4 files changed, 14 insertions, 20 deletions

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 5a7551d060f2..33f71983e001 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -1057,8 +1057,8 @@ static int rc_dma_get_range(struct device *dev, u64 *size)
  */
 void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 {
-	u64 mask, dmaaddr = 0, size = 0, offset = 0;
-	int ret, msb;
+	u64 end, mask, dmaaddr = 0, size = 0, offset = 0;
+	int ret;
 
 	/*
 	 * If @dev is expected to be DMA-capable then the bus code that created
@@ -1085,19 +1085,13 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	}
 
 	if (!ret) {
-		msb = fls64(dmaaddr + size - 1);
 		/*
-		 * Round-up to the power-of-two mask or set
-		 * the mask to the whole 64-bit address space
-		 * in case the DMA region covers the full
-		 * memory window.
+		 * Limit coherent and dma mask based on size retrieved from
+		 * firmware.
 		 */
-		mask = msb == 64 ? U64_MAX : (1ULL << msb) - 1;
-		/*
-		 * Limit coherent and dma mask based on size
-		 * retrieved from firmware.
-		 */
-		dev->bus_dma_mask = mask;
+		end = dmaaddr + size - 1;
+		mask = DMA_BIT_MASK(ilog2(end) + 1);
+		dev->bus_dma_limit = end;
 		dev->coherent_dma_mask = mask;
 		*dev->dma_mask = mask;
 	}
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 05c2b32dcc4d..7c6d06ffb586 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -897,7 +897,7 @@ static int ahci_configure_dma_masks(struct pci_dev *pdev, int using_dac)
 	 * value, don't extend it here. This happens on STA2X11, for example.
 	 *
 	 * XXX: manipulating the DMA mask from platform code is completely
-	 * bogus, platform code should use dev->bus_dma_mask instead..
+	 * bogus, platform code should use dev->bus_dma_limit instead..
 	 */
 	if (pdev->dma_mask && pdev->dma_mask < DMA_BIT_MASK(32))
 		return 0;
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 0fa8c1d818b7..646332fbf3d7 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -405,8 +405,7 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
 		iova_len = roundup_pow_of_two(iova_len);
 
-	if (dev->bus_dma_mask)
-		dma_limit &= dev->bus_dma_mask;
+	dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit);
 
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, domain->geometry.aperture_end);
diff --git a/drivers/of/device.c b/drivers/of/device.c
index da8158392010..e9127db7b067 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -93,7 +93,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	bool coherent;
 	unsigned long offset;
 	const struct iommu_ops *iommu;
-	u64 mask;
+	u64 mask, end;
 
 	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
 	if (ret < 0) {
@@ -148,12 +148,13 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	 * Limit coherent and dma mask based on size and default mask
 	 * set by the driver.
 	 */
-	mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1);
+	end = dma_addr + size - 1;
+	mask = DMA_BIT_MASK(ilog2(end) + 1);
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
-	/* ...but only set bus mask if we found valid dma-ranges earlier */
+	/* ...but only set bus limit if we found valid dma-ranges earlier */
 	if (!ret)
-		dev->bus_dma_mask = mask;
+		dev->bus_dma_limit = end;
 
 	coherent = of_dma_is_coherent(np);
 	dev_dbg(dev, "device is%sdma coherent\n",