diff options
author | FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> | 2008-07-25 22:44:49 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-07-26 15:00:03 -0400 |
commit | 8d8bb39b9eba32dd70e87fd5ad5c5dd4ba118e06 (patch) | |
tree | 64090a84f4c4466f9f30ff46c993e0cede379052 /arch/x86/kernel/pci-dma.c | |
parent | c485b465a031b6f9b9a51300e0ee1f86efc6db87 (diff) |
dma-mapping: add the device argument to dma_mapping_error()
Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER
architecture does:
This enables us to cleanly fix the Calgary IOMMU issue that some devices
are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423).
I think that per-device dma_mapping_ops support would be also helpful for
KVM people to support PCI passthrough but Andi thinks that this makes it
difficult to support the PCI passthrough (see the above thread). So I
CC'ed this to KVM camp. Comments are appreciated.
A pointer to dma_mapping_ops to struct dev_archdata is added. If the
pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's
NULL, the system-wide dma_ops pointer is used as before.
If it's useful for KVM people, I plan to implement a mechanism to register
a hook called when a new pci (or dma capable) device is created (it works
with hot plugging). It enables IOMMUs to set up an appropriate
dma_mapping_ops per device.
The major obstacle is that dma_mapping_error doesn't take a pointer to the
device unlike other DMA operations. So x86 can't have dma_mapping_ops per
device. Note all the POWER IOMMUs use the same dma_mapping_error function
so this is not a problem for POWER but x86 IOMMUs use different
dma_mapping_error functions.
The first patch adds the device argument to dma_mapping_error. The patch
is trivial but large since it touches lots of drivers and dma-mapping.h in
all the architecture.
This patch:
dma_mapping_error() doesn't take a pointer to the device unlike other DMA
operations. So we can't have dma_mapping_ops per device.
Note that POWER already has dma_mapping_ops per device but all the POWER
IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device
argument.
[akpm@linux-foundation.org: fix sge]
[akpm@linux-foundation.org: fix svc_rdma]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix bnx2x]
[akpm@linux-foundation.org: fix s2io]
[akpm@linux-foundation.org: fix pasemi_mac]
[akpm@linux-foundation.org: fix sdhci]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix sparc]
[akpm@linux-foundation.org: fix ibmvscsi]
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Muli Ben-Yehuda <muli@il.ibm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Avi Kivity <avi@qumranet.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'arch/x86/kernel/pci-dma.c')
-rw-r--r-- | arch/x86/kernel/pci-dma.c | 27 |
1 files changed, 16 insertions, 11 deletions
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index cbecb05551bb..37544123896d 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c | |||
@@ -11,7 +11,7 @@ | |||
11 | 11 | ||
12 | static int forbid_dac __read_mostly; | 12 | static int forbid_dac __read_mostly; |
13 | 13 | ||
14 | const struct dma_mapping_ops *dma_ops; | 14 | struct dma_mapping_ops *dma_ops; |
15 | EXPORT_SYMBOL(dma_ops); | 15 | EXPORT_SYMBOL(dma_ops); |
16 | 16 | ||
17 | static int iommu_sac_force __read_mostly; | 17 | static int iommu_sac_force __read_mostly; |
@@ -312,6 +312,8 @@ static int dma_release_coherent(struct device *dev, int order, void *vaddr) | |||
312 | 312 | ||
313 | int dma_supported(struct device *dev, u64 mask) | 313 | int dma_supported(struct device *dev, u64 mask) |
314 | { | 314 | { |
315 | struct dma_mapping_ops *ops = get_dma_ops(dev); | ||
316 | |||
315 | #ifdef CONFIG_PCI | 317 | #ifdef CONFIG_PCI |
316 | if (mask > 0xffffffff && forbid_dac > 0) { | 318 | if (mask > 0xffffffff && forbid_dac > 0) { |
317 | dev_info(dev, "PCI: Disallowing DAC for device\n"); | 319 | dev_info(dev, "PCI: Disallowing DAC for device\n"); |
@@ -319,8 +321,8 @@ int dma_supported(struct device *dev, u64 mask) | |||
319 | } | 321 | } |
320 | #endif | 322 | #endif |
321 | 323 | ||
322 | if (dma_ops->dma_supported) | 324 | if (ops->dma_supported) |
323 | return dma_ops->dma_supported(dev, mask); | 325 | return ops->dma_supported(dev, mask); |
324 | 326 | ||
325 | /* Copied from i386. Doesn't make much sense, because it will | 327 | /* Copied from i386. Doesn't make much sense, because it will |
326 | only work for pci_alloc_coherent. | 328 | only work for pci_alloc_coherent. |
@@ -367,6 +369,7 @@ void * | |||
367 | dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, | 369 | dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, |
368 | gfp_t gfp) | 370 | gfp_t gfp) |
369 | { | 371 | { |
372 | struct dma_mapping_ops *ops = get_dma_ops(dev); | ||
370 | void *memory = NULL; | 373 | void *memory = NULL; |
371 | struct page *page; | 374 | struct page *page; |
372 | unsigned long dma_mask = 0; | 375 | unsigned long dma_mask = 0; |
@@ -435,8 +438,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, | |||
435 | /* Let low level make its own zone decisions */ | 438 | /* Let low level make its own zone decisions */ |
436 | gfp &= ~(GFP_DMA32|GFP_DMA); | 439 | gfp &= ~(GFP_DMA32|GFP_DMA); |
437 | 440 | ||
438 | if (dma_ops->alloc_coherent) | 441 | if (ops->alloc_coherent) |
439 | return dma_ops->alloc_coherent(dev, size, | 442 | return ops->alloc_coherent(dev, size, |
440 | dma_handle, gfp); | 443 | dma_handle, gfp); |
441 | return NULL; | 444 | return NULL; |
442 | } | 445 | } |
@@ -448,14 +451,14 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, | |||
448 | } | 451 | } |
449 | } | 452 | } |
450 | 453 | ||
451 | if (dma_ops->alloc_coherent) { | 454 | if (ops->alloc_coherent) { |
452 | free_pages((unsigned long)memory, get_order(size)); | 455 | free_pages((unsigned long)memory, get_order(size)); |
453 | gfp &= ~(GFP_DMA|GFP_DMA32); | 456 | gfp &= ~(GFP_DMA|GFP_DMA32); |
454 | return dma_ops->alloc_coherent(dev, size, dma_handle, gfp); | 457 | return ops->alloc_coherent(dev, size, dma_handle, gfp); |
455 | } | 458 | } |
456 | 459 | ||
457 | if (dma_ops->map_simple) { | 460 | if (ops->map_simple) { |
458 | *dma_handle = dma_ops->map_simple(dev, virt_to_phys(memory), | 461 | *dma_handle = ops->map_simple(dev, virt_to_phys(memory), |
459 | size, | 462 | size, |
460 | PCI_DMA_BIDIRECTIONAL); | 463 | PCI_DMA_BIDIRECTIONAL); |
461 | if (*dma_handle != bad_dma_address) | 464 | if (*dma_handle != bad_dma_address) |
@@ -477,12 +480,14 @@ EXPORT_SYMBOL(dma_alloc_coherent); | |||
477 | void dma_free_coherent(struct device *dev, size_t size, | 480 | void dma_free_coherent(struct device *dev, size_t size, |
478 | void *vaddr, dma_addr_t bus) | 481 | void *vaddr, dma_addr_t bus) |
479 | { | 482 | { |
483 | struct dma_mapping_ops *ops = get_dma_ops(dev); | ||
484 | |||
480 | int order = get_order(size); | 485 | int order = get_order(size); |
481 | WARN_ON(irqs_disabled()); /* for portability */ | 486 | WARN_ON(irqs_disabled()); /* for portability */ |
482 | if (dma_release_coherent(dev, order, vaddr)) | 487 | if (dma_release_coherent(dev, order, vaddr)) |
483 | return; | 488 | return; |
484 | if (dma_ops->unmap_single) | 489 | if (ops->unmap_single) |
485 | dma_ops->unmap_single(dev, bus, size, 0); | 490 | ops->unmap_single(dev, bus, size, 0); |
486 | free_pages((unsigned long)vaddr, order); | 491 | free_pages((unsigned long)vaddr, order); |
487 | } | 492 | } |
488 | EXPORT_SYMBOL(dma_free_coherent); | 493 | EXPORT_SYMBOL(dma_free_coherent); |