1
linux/arch/x86/kernel/pci-nommu.c
FUJITA Tomonori 8d8bb39b9e 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>
2008-07-26 12:00:03 -07:00

89 lines
2.3 KiB
C

/* Fallback functions when the main IOMMU code is not compiled in. This
code is roughly equivalent to i386. */
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/pci.h>
#include <linux/string.h>
#include <linux/dma-mapping.h>
#include <linux/scatterlist.h>
#include <asm/iommu.h>
#include <asm/processor.h>
#include <asm/dma.h>
static int
check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
{
if (hwdev && bus + size > *hwdev->dma_mask) {
if (*hwdev->dma_mask >= DMA_32BIT_MASK)
printk(KERN_ERR
"nommu_%s: overflow %Lx+%zu of device mask %Lx\n",
name, (long long)bus, size,
(long long)*hwdev->dma_mask);
return 0;
}
return 1;
}
static dma_addr_t
nommu_map_single(struct device *hwdev, phys_addr_t paddr, size_t size,
int direction)
{
dma_addr_t bus = paddr;
WARN_ON(size == 0);
if (!check_addr("map_single", hwdev, bus, size))
return bad_dma_address;
flush_write_buffers();
return bus;
}
/* Map a set of buffers described by scatterlist in streaming
* mode for DMA. This is the scatter-gather version of the
* above pci_map_single interface. Here the scatter gather list
* elements are each tagged with the appropriate dma address
* and length. They are obtained via sg_dma_{address,length}(SG).
*
* NOTE: An implementation may be able to use a smaller number of
* DMA address/length pairs than there are SG table elements.
* (for example via virtual mapping capabilities)
* The routine returns the number of addr/length pairs actually
* used, at most nents.
*
* Device ownership issues as mentioned above for pci_map_single are
* the same here.
*/
static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
int nents, int direction)
{
struct scatterlist *s;
int i;
WARN_ON(nents == 0 || sg[0].length == 0);
for_each_sg(sg, s, nents, i) {
BUG_ON(!sg_page(s));
s->dma_address = sg_phys(s);
if (!check_addr("map_sg", hwdev, s->dma_address, s->length))
return 0;
s->dma_length = s->length;
}
flush_write_buffers();
return nents;
}
struct dma_mapping_ops nommu_dma_ops = {
.map_single = nommu_map_single,
.map_sg = nommu_map_sg,
.is_phys = 1,
};
void __init no_iommu_init(void)
{
if (dma_ops)
return;
force_iommu = 0; /* no HW IOMMU */
dma_ops = &nommu_dma_ops;
}