[PATCH] powerpc: IOMMU support for honoring dma_mask

Some devices don't support full 32-bit DMA address space, which we currently
assume. Add the required mask-passing to the IOMMU allocators.

Signed-off-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Paul Mackerras <paulus@samba.org>

3 files changed, 65 insertions, 17 deletions

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index d9a7fdef59b9..4eba60a32890 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -61,6 +61,7 @@ __setup("iommu=", setup_iommu);
 static unsigned long iommu_range_alloc(struct iommu_table *tbl,
                                        unsigned long npages,
                                        unsigned long *handle,
+                                       unsigned long mask,
                                        unsigned int align_order)
 { 
         unsigned long n, end, i, start;
@@ -97,9 +98,21 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl,
          */
         if (start >= limit)
                 start = largealloc ? tbl->it_largehint : tbl->it_hint;
-        
+
  again:
 
+        if (limit + tbl->it_offset > mask) {
+                limit = mask - tbl->it_offset + 1;
+                /* If we're constrained on address range, first try
+                 * at the masked hint to avoid O(n) search complexity,
+                 * but on second pass, start at 0.
+                 */
+                if ((start & mask) >= limit || pass > 0)
+                        start = 0;
+                else
+                        start &= mask;
+        }
+
         n = find_next_zero_bit(tbl->it_map, limit, start);
 
         /* Align allocation */
@@ -150,14 +163,14 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl,
 
 static dma_addr_t iommu_alloc(struct iommu_table *tbl, void *page,
                        unsigned int npages, enum dma_data_direction direction,
-                       unsigned int align_order)
+                       unsigned long mask, unsigned int align_order)
 {
         unsigned long entry, flags;
         dma_addr_t ret = DMA_ERROR_CODE;
-        
+
         spin_lock_irqsave(&(tbl->it_lock), flags);
 
-        entry = iommu_range_alloc(tbl, npages, NULL, align_order);
+        entry = iommu_range_alloc(tbl, npages, NULL, mask, align_order);
 
         if (unlikely(entry == DMA_ERROR_CODE)) {
                 spin_unlock_irqrestore(&(tbl->it_lock), flags);
@@ -236,7 +249,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 
 int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
                 struct scatterlist *sglist, int nelems,
-                enum dma_data_direction direction)
+                unsigned long mask, enum dma_data_direction direction)
 {
         dma_addr_t dma_next = 0, dma_addr;
         unsigned long flags;
@@ -274,7 +287,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
                 vaddr = (unsigned long)page_address(s->page) + s->offset;
                 npages = PAGE_ALIGN(vaddr + slen) - (vaddr & PAGE_MASK);
                 npages >>= PAGE_SHIFT;
-                entry = iommu_range_alloc(tbl, npages, &handle, 0);
+                entry = iommu_range_alloc(tbl, npages, &handle, mask >> PAGE_SHIFT, 0);
 
                 DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);
 
@@ -479,7 +492,8 @@ void iommu_free_table(struct device_node *dn)
  * byte within the page as vaddr.
  */
 dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr,
-                size_t size, enum dma_data_direction direction)
+                size_t size, unsigned long mask,
+                enum dma_data_direction direction)
 {
         dma_addr_t dma_handle = DMA_ERROR_CODE;
         unsigned long uaddr;
@@ -492,7 +506,8 @@ dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr,
         npages >>= PAGE_SHIFT;
 
         if (tbl) {
-                dma_handle = iommu_alloc(tbl, vaddr, npages, direction, 0);
+                dma_handle = iommu_alloc(tbl, vaddr, npages, direction,
+                                         mask >> PAGE_SHIFT, 0);
                 if (dma_handle == DMA_ERROR_CODE) {
                         if (printk_ratelimit())  {
                                 printk(KERN_INFO "iommu_alloc failed, "
@@ -521,7 +536,7 @@ void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle,
  * to the dma address (mapping) of the first page.
  */
 void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size,
-                dma_addr_t *dma_handle, gfp_t flag)
+                dma_addr_t *dma_handle, unsigned long mask, gfp_t flag)
 {
         void *ret = NULL;
         dma_addr_t mapping;
@@ -551,7 +566,8 @@ void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size,
         memset(ret, 0, size);
 
         /* Set up tces to cover the allocated range */
-        mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL, order);
+        mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL,
+                              mask >> PAGE_SHIFT, order);
         if (mapping == DMA_ERROR_CODE) {
                 free_pages((unsigned long)ret, order);
                 ret = NULL;
diff --git a/arch/powerpc/kernel/pci_iommu.c b/arch/powerpc/kernel/pci_iommu.c
index c336f3e31cff..c1d95e14bbed 100644
--- a/arch/powerpc/kernel/pci_iommu.c
+++ b/arch/powerpc/kernel/pci_iommu.c
@@ -59,6 +59,25 @@ static inline struct iommu_table *devnode_table(struct device *dev)
 }
 
 
+static inline unsigned long device_to_mask(struct device *hwdev)
+{
+        struct pci_dev *pdev;
+
+        if (!hwdev) {
+                pdev = ppc64_isabridge_dev;
+                if (!pdev) /* This is the best guess we can do */
+                        return 0xfffffffful;
+        } else
+                pdev = to_pci_dev(hwdev);
+
+        if (pdev->dma_mask)
+                return pdev->dma_mask;
+
+        /* Assume devices without mask can take 32 bit addresses */
+        return 0xfffffffful;
+}
+
+
 /* Allocates a contiguous real buffer and creates mappings over it.
  * Returns the virtual address of the buffer and sets dma_handle
  * to the dma address (mapping) of the first page.
@@ -67,7 +86,7 @@ static void *pci_iommu_alloc_coherent(struct device *hwdev, size_t size,
                            dma_addr_t *dma_handle, gfp_t flag)
 {
         return iommu_alloc_coherent(devnode_table(hwdev), size, dma_handle,
-                        flag);
+                        device_to_mask(hwdev), flag);
 }
 
 static void pci_iommu_free_coherent(struct device *hwdev, size_t size,
@@ -85,7 +104,8 @@ static void pci_iommu_free_coherent(struct device *hwdev, size_t size,
 static dma_addr_t pci_iommu_map_single(struct device *hwdev, void *vaddr,
                 size_t size, enum dma_data_direction direction)
 {
-        return iommu_map_single(devnode_table(hwdev), vaddr, size, direction);
+        return iommu_map_single(devnode_table(hwdev), vaddr, size,
+                                device_to_mask(hwdev), direction);
 }
 
 
@@ -100,7 +120,7 @@ static int pci_iommu_map_sg(struct device *pdev, struct scatterlist *sglist,
                 int nelems, enum dma_data_direction direction)
 {
         return iommu_map_sg(pdev, devnode_table(pdev), sglist,
-                        nelems, direction);
+                        nelems, device_to_mask(pdev), direction);
 }
 
 static void pci_iommu_unmap_sg(struct device *pdev, struct scatterlist *sglist,
@@ -112,7 +132,19 @@ static void pci_iommu_unmap_sg(struct device *pdev, struct scatterlist *sglist,
 /* We support DMA to/from any memory page via the iommu */
 static int pci_iommu_dma_supported(struct device *dev, u64 mask)
 {
-        return 1;
+        struct iommu_table *tbl = devnode_table(dev);
+
+        if (!tbl || tbl->it_offset > mask) {
+                printk(KERN_INFO "Warning: IOMMU table offset too big for device mask\n");
+                if (tbl)
+                        printk(KERN_INFO "mask: 0x%08lx, table offset: 0x%08lx\n",
+                                mask, tbl->it_offset);
+                else
+                        printk(KERN_INFO "mask: 0x%08lx, table unavailable\n",
+                                mask);
+                return 0;
+        } else
+                return 1;
 }
 
 void pci_iommu_init(void)
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 13c655ba2841..971020cf3f7d 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -202,7 +202,7 @@ static dma_addr_t vio_map_single(struct device *dev, void *vaddr,
                           size_t size, enum dma_data_direction direction)
 {
         return iommu_map_single(to_vio_dev(dev)->iommu_table, vaddr, size,
-                        direction);
+                        ~0ul, direction);
 }
 
 static void vio_unmap_single(struct device *dev, dma_addr_t dma_handle,
@@ -216,7 +216,7 @@ static int vio_map_sg(struct device *dev, struct scatterlist *sglist,
                 int nelems, enum dma_data_direction direction)
 {
         return iommu_map_sg(dev, to_vio_dev(dev)->iommu_table, sglist,
-                        nelems, direction);
+                        nelems, ~0ul, direction);
 }
 
 static void vio_unmap_sg(struct device *dev, struct scatterlist *sglist,
@@ -229,7 +229,7 @@ static void *vio_alloc_coherent(struct device *dev, size_t size,
                            dma_addr_t *dma_handle, gfp_t flag)
 {
         return iommu_alloc_coherent(to_vio_dev(dev)->iommu_table, size,
-                        dma_handle, flag);
+                        dma_handle, ~0ul, flag);
 }
 
 static void vio_free_coherent(struct device *dev, size_t size,