lkml.org 
[lkml]   [2008]   [Aug]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    Patch in this message
    /
    Date
    SubjectRe: [PATCH]: PCI: GART iommu alignment fixes [v2]
    From
    On Thu, 07 Aug 2008 13:41:40 -0400
    Prarit Bhargava <prarit@redhat.com> wrote:

    > In that case, I hit the BUG() check warning in iommu_is_span_boundary()
    > because boundary_size was calculated as (unsigned long) 0xffffffff + 1 = 0.
    >
    > That's why we must cast to "unsigned long long".
    >
    > ie) it is possible to hit this BUG() right now.

    Wrong, it doesn't happen, as I said again and again.


    > >>>> Maybe I'm missing something -- what implies size has to be a power of
    > >>>> two?
    > >>>>
    > >>> Yes, see iommu_area_alloc().
    > >>>
    > >> /me looks and still doesn't see where the size passed into
    > >> gart_map_simple() must be a power of two. ... and if that was the case,
    > >> shouldn't we be failing all the time? I mean, I've seen values passed
    > >> into pci_alloc_consistent like 0x3820 -- clearly not a multiple of 2.
    > >>
    > >> iommu_area_alloc() deals with pages, not actual sizes as
    > >> gart_map_simple() does.
    > >>
    >
    > Tomonori-san, I think I understand where your confusion may lie. The
    > size argument in the iommu-helper.c code is NOT the same size in
    > dma_alloc_coherent() and gart_map_simple(). In iommu-helper.c the size
    > is the # of pages, and the in the exported function calls it is an
    > actual size. Is that what is confusing you?

    I understand it. FYI, I wrote iommu-helper.c.

    Again, you don't understand the code. Here's a patch to fix the GART
    to allocate a size-aligned address for alloc_coherent.

    But as I told you again and again, I doubt that this fixes something.

    =
    From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
    Subject: [PATCH] x86 gart: allocate size-aligned address for alloc_coherent

    This fixes GART to return a properly aligned address as
    DMA-mapping.txt defines.

    Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
    ---
    arch/x86/kernel/pci-gart_64.c | 25 ++++++++++++++++---------
    1 files changed, 16 insertions(+), 9 deletions(-)

    diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
    index 49285f8..8e64b49 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;
    @@ -95,11 +96,12 @@ static unsigned long alloc_iommu(struct device *dev, int size)

    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 = (roundup_pow_of_two(size) >> PAGE_SHIFT) - 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;
    --
    1.5.5.GIT


    \
     
     \ /
      Last update: 2008-08-09 05:53    [W:2.747 / U:0.140 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site