lkml.org 
[lkml]   [2008]   [Aug]   [15]   [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 Fri, 15 Aug 2008 20:00:48 +0200
Ingo Molnar <mingo@elte.hu> wrote:

>
> * Ingo Molnar <mingo@elte.hu> wrote:
>
> >
> > * FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> wrote:
> >
> > > 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.
> >
> > applied to tip/x86/gart, thanks! Any v2.6.27-urgency of this patch?
>
> hm, -tip testing has found that this patch causes a hard hang during
> bootup:
>
> initcall ali_init+0x0/0x1b returned 0 after 3 msecs
> calling amd_init+0x0/0x1b
> bus: 'pci': add driver pata_amd
> bus: 'pci': driver_probe_device: matched device 0000:00:06.0 with driver pata_amd
> bus: 'pci': really_probe: probing driver pata_amd with device 0000:00:06.0
> pata_amd 0000:00:06.0: version 0.3.10
> pata_amd 0000:00:06.0: setting latency timer to 64
> [hard hang]
>
> should have continued with:
>
> scsi0 : pata_amd
> device: 'host0': device_add
> device: 'host0': device_add
> scsi1 : pata_amd
> [... etc. ... ]
>
> on an AMD X2 testsystem. (Asus board) Can send more info on request.
> Config is:
>
> http://redhat.com/~mingo/misc/config-Fri_Aug_15_18_30_56_CEST_2008.bad
>
> Any idea why that is so? Apparently the alignment change wasnt as benign
> as assumed.

Ah, sorry,

@@ -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);

This code doesn't work with the case size < PAGE_SIZE.

I think that dmam_alloc_consistent in libata-core fails due to this
bug.

Can you try this?

BTW, I think that this is not urgent stuff at all.


diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 49285f8..045ae6f 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 = (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;

\
 
 \ /
  Last update: 2008-08-16 03:19    [W:0.114 / U:0.144 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site