Merge phase #1 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

This merges phase 1 of the x86 tree, which is a collection of branches:

  x86/alternatives, x86/cleanups, x86/commandline, x86/crashdump,
  x86/debug, x86/defconfig, x86/doc, x86/exports, x86/fpu, x86/gart,
  x86/idle, x86/mm, x86/mtrr, x86/nmi-watchdog, x86/oprofile,
  x86/paravirt, x86/reboot, x86/sparse-fixes, x86/tsc, x86/urgent and
  x86/vmalloc

and as Ingo says: "these are the easiest, purely independent x86 topics
with no conflicts, in one nice Octopus merge".

* 'x86-v28-for-linus-phase1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (147 commits)
  x86: mtrr_cleanup: treat WRPROT as UNCACHEABLE
  x86: mtrr_cleanup: first 1M may be covered in var mtrrs
  x86: mtrr_cleanup: print out correct type v2
  x86: trivial printk fix in efi.c
  x86, debug: mtrr_cleanup print out var mtrr before change it
  x86: mtrr_cleanup try gran_size to less than 1M, v3
  x86: mtrr_cleanup try gran_size to less than 1M, cleanup
  x86: change MTRR_SANITIZER to def_bool y
  x86, debug printouts: IOMMU setup failures should not be KERN_ERR
  x86: export set_memory_ro and set_memory_rw
  x86: mtrr_cleanup try gran_size to less than 1M
  x86: mtrr_cleanup prepare to make gran_size to less 1M
  x86: mtrr_cleanup safe to get more spare regs now
  x86_64: be less annoying on boot, v2
  x86: mtrr_cleanup hole size should be less than half of chunk_size, v2
  x86: add mtrr_cleanup_debug command line
  x86: mtrr_cleanup optimization, v2
  x86: don't need to go to chunksize to 4G
  x86_64: be less annoying on boot
  x86, olpc: fix endian bug in openfirmware workaround
  ...

1 files changed, 17 insertions, 10 deletions

diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index be33a5442d82..1a895a582534 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -82,7 +82,8 @@ AGPEXTERN __u32 *agp_gatt_table;
 static unsigned long next_bit;  /* protected by iommu_bitmap_lock */
 static int need_flush;          /* global flush state. set for each gart wrap */
 
-static unsigned long alloc_iommu(struct device *dev, int size)
+static unsigned long alloc_iommu(struct device *dev, int size,
+                                 unsigned long align_mask)
 {
         unsigned long offset, flags;
         unsigned long boundary_size;
@@ -90,16 +91,17 @@ static unsigned long alloc_iommu(struct device *dev, int size)
 
         base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev),
                            PAGE_SIZE) >> PAGE_SHIFT;
-        boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+        boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
                               PAGE_SIZE) >> PAGE_SHIFT;
 
         spin_lock_irqsave(&iommu_bitmap_lock, flags);
         offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit,
-                                  size, base_index, boundary_size, 0);
+                                  size, base_index, boundary_size, align_mask);
         if (offset == -1) {
                 need_flush = 1;
                 offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, 0,
-                                          size, base_index, boundary_size, 0);
+                                          size, base_index, boundary_size,
+                                          align_mask);
         }
         if (offset != -1) {
                 next_bit = offset+size;
@@ -236,10 +238,10 @@ nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
  * Caller needs to check if the iommu is needed and flush.
  */
 static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
-                                size_t size, int dir)
+                                size_t size, int dir, unsigned long align_mask)
 {
         unsigned long npages = iommu_num_pages(phys_mem, size);
-        unsigned long iommu_page = alloc_iommu(dev, npages);
+        unsigned long iommu_page = alloc_iommu(dev, npages, align_mask);
         int i;
 
         if (iommu_page == -1) {
@@ -262,7 +264,11 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 static dma_addr_t
 gart_map_simple(struct device *dev, phys_addr_t paddr, size_t size, int dir)
 {
-        dma_addr_t map = dma_map_area(dev, paddr, size, dir);
+        dma_addr_t map;
+        unsigned long align_mask;
+
+        align_mask = (1UL << get_order(size)) - 1;
+        map = dma_map_area(dev, paddr, size, dir, align_mask);
 
         flush_gart();
 
@@ -281,7 +287,8 @@ gart_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir)
         if (!need_iommu(dev, paddr, size))
                 return paddr;
 
-        bus = gart_map_simple(dev, paddr, size, dir);
+        bus = dma_map_area(dev, paddr, size, dir, 0);
+        flush_gart();
 
         return bus;
 }
@@ -340,7 +347,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
                 unsigned long addr = sg_phys(s);
 
                 if (nonforced_iommu(dev, addr, s->length)) {
-                        addr = dma_map_area(dev, addr, s->length, dir);
+                        addr = dma_map_area(dev, addr, s->length, dir, 0);
                         if (addr == bad_dma_address) {
                                 if (i > 0)
                                         gart_unmap_sg(dev, sg, i, dir);
@@ -362,7 +369,7 @@ static int __dma_map_cont(struct device *dev, struct scatterlist *start,
                           int nelems, struct scatterlist *sout,
                           unsigned long pages)
 {
-        unsigned long iommu_start = alloc_iommu(dev, pages);
+        unsigned long iommu_start = alloc_iommu(dev, pages, 0);
         unsigned long iommu_page = iommu_start;
         struct scatterlist *s;
         int i;