1 files changed, 45 insertions, 11 deletions

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4bc43e535d3b..82a093cee09a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/highmem.h>
 
 #include <asm/memory.h>
 #include <asm/highmem.h>
@@ -148,6 +149,7 @@ static int __init consistent_init(void)
 {
         int ret = 0;
         pgd_t *pgd;
+        pud_t *pud;
         pmd_t *pmd;
         pte_t *pte;
         int i = 0;
@@ -155,7 +157,15 @@ static int __init consistent_init(void)
 
         do {
                 pgd = pgd_offset(&init_mm, base);
-                pmd = pmd_alloc(&init_mm, pgd, base);
+
+                pud = pud_alloc(&init_mm, pgd, base);
+                if (!pud) {
+                        printk(KERN_ERR "%s: no pud tables\n", __func__);
+                        ret = -ENOMEM;
+                        break;
+                }
+
+                pmd = pmd_alloc(&init_mm, pud, base);
                 if (!pmd) {
                         printk(KERN_ERR "%s: no pmd tables\n", __func__);
                         ret = -ENOMEM;
@@ -198,7 +208,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
          * fragmentation of the DMA space, and also prevents allocations
          * smaller than a section from crossing a section boundary.
          */
-        bit = fls(size - 1) + 1;
+        bit = fls(size - 1);
         if (bit > SECTION_SHIFT)
                 bit = SECTION_SHIFT;
         align = 1 << bit;
@@ -311,7 +321,7 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
                 addr = page_address(page);
 
         if (addr)
-                *handle = page_to_dma(dev, page);
+                *handle = pfn_to_dma(dev, page_to_pfn(page));
 
         return addr;
 }
@@ -406,7 +416,7 @@ void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr
         if (!arch_is_coherent())
                 __dma_free_remap(cpu_addr, size);
 
-        __dma_free_buffer(dma_to_page(dev, handle), size);
+        __dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size);
 }
 EXPORT_SYMBOL(dma_free_coherent);
 
@@ -480,10 +490,10 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
                                 op(vaddr, len, dir);
                                 kunmap_high(page);
                         } else if (cache_is_vipt()) {
-                                pte_t saved_pte;
-                                vaddr = kmap_high_l1_vipt(page, &saved_pte);
+                                /* unmapped pages might still be cached */
+                                vaddr = kmap_atomic(page);
                                 op(vaddr + offset, len, dir);
-                                kunmap_high_l1_vipt(page, saved_pte);
+                                kunmap_atomic(vaddr);
                         }
                 } else {
                         vaddr = page_address(page) + offset;
@@ -523,6 +533,12 @@ void ___dma_page_dev_to_cpu(struct page *page, unsigned long off,
                 outer_inv_range(paddr, paddr + size);
 
         dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
+
+        /*
+         * Mark the D-cache clean for this page to avoid extra flushing.
+         */
+        if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
+                set_bit(PG_dcache_clean, &page->flags);
 }
 EXPORT_SYMBOL(___dma_page_dev_to_cpu);
 
@@ -548,17 +564,20 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
         struct scatterlist *s;
         int i, j;
 
+        BUG_ON(!valid_dma_direction(dir));
+
         for_each_sg(sg, s, nents, i) {
-                s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
+                s->dma_address = __dma_map_page(dev, sg_page(s), s->offset,
                                                 s->length, dir);
                 if (dma_mapping_error(dev, s->dma_address))
                         goto bad_mapping;
         }
+        debug_dma_map_sg(dev, sg, nents, nents, dir);
         return nents;
 
  bad_mapping:
         for_each_sg(sg, s, i, j)
-                dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+                __dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
         return 0;
 }
 EXPORT_SYMBOL(dma_map_sg);
@@ -567,7 +586,7 @@ EXPORT_SYMBOL(dma_map_sg);
  * dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @sg: list of buffers
- * @nents: number of buffers to unmap (returned from dma_map_sg)
+ * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
  * @dir: DMA transfer direction (same as was passed to dma_map_sg)
  *
  * Unmap a set of streaming mode DMA translations.  Again, CPU access
@@ -579,8 +598,10 @@ void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
         struct scatterlist *s;
         int i;
 
+        debug_dma_unmap_sg(dev, sg, nents, dir);
+
         for_each_sg(sg, s, nents, i)
-                dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+                __dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
 }
 EXPORT_SYMBOL(dma_unmap_sg);
 
@@ -605,6 +626,8 @@ void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
                 __dma_page_dev_to_cpu(sg_page(s), s->offset,
                                       s->length, dir);
         }
+
+        debug_dma_sync_sg_for_cpu(dev, sg, nents, dir);
 }
 EXPORT_SYMBOL(dma_sync_sg_for_cpu);
 
@@ -629,5 +652,16 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
                 __dma_page_cpu_to_dev(sg_page(s), s->offset,
                                       s->length, dir);
         }
+
+        debug_dma_sync_sg_for_device(dev, sg, nents, dir);
 }
 EXPORT_SYMBOL(dma_sync_sg_for_device);
+
+#define PREALLOC_DMA_DEBUG_ENTRIES      4096
+
+static int __init dma_debug_do_init(void)
+{
+        dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+        return 0;
+}
+fs_initcall(dma_debug_do_init);