Commit 8d8bb39b authored by FUJITA Tomonori's avatar FUJITA Tomonori Committed by Linus Torvalds
Browse files

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: default avatarFUJITA 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: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent c485b465
......@@ -298,10 +298,10 @@ recommended that you never use these unless you really know what the
cache width is.
int
dma_mapping_error(dma_addr_t dma_addr)
dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
int
pci_dma_mapping_error(dma_addr_t dma_addr)
pci_dma_mapping_error(struct pci_dev *hwdev, dma_addr_t dma_addr)
In some circumstances dma_map_single and dma_map_page will fail to create
a mapping. A driver can check for these errors by testing the returned
......
......@@ -280,7 +280,7 @@ unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
/*
* Trying to unmap an invalid mapping
*/
if (dma_mapping_error(dma_addr)) {
if (dma_mapping_error(dev, dma_addr)) {
dev_err(dev, "Trying to unmap invalid mapping\n");
return;
}
......
......@@ -186,9 +186,10 @@ hwsw_dma_supported (struct device *dev, u64 mask)
}
int
hwsw_dma_mapping_error (dma_addr_t dma_addr)
hwsw_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return hwiommu_dma_mapping_error (dma_addr) || swiotlb_dma_mapping_error(dma_addr);
return hwiommu_dma_mapping_error(dev, dma_addr) ||
swiotlb_dma_mapping_error(dev, dma_addr);
}
EXPORT_SYMBOL(hwsw_dma_mapping_error);
......
......@@ -2147,7 +2147,7 @@ sba_dma_supported (struct device *dev, u64 mask)
}
int
sba_dma_mapping_error (dma_addr_t dma_addr)
sba_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return 0;
}
......
......@@ -350,7 +350,7 @@ void sn_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
}
EXPORT_SYMBOL(sn_dma_sync_sg_for_device);
int sn_dma_mapping_error(dma_addr_t dma_addr)
int sn_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return 0;
}
......
......@@ -348,7 +348,7 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nele
EXPORT_SYMBOL(dma_sync_sg_for_device);
int dma_mapping_error(dma_addr_t dma_addr)
int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return 0;
}
......
......@@ -281,7 +281,7 @@ static int __init scc_pciex_iowa_init(struct iowa_bus *bus, void *data)
dummy_page_da = dma_map_single(bus->phb->parent, dummy_page_va,
PAGE_SIZE, DMA_FROM_DEVICE);
if (dma_mapping_error(dummy_page_da)) {
if (dma_mapping_error(bus->phb->parent, dummy_page_da)) {
pr_err("PCIEX:Map dummy page failed.\n");
kfree(dummy_page_va);
return -1;
......
......@@ -111,7 +111,7 @@ static int __init spiderpci_pci_setup_chip(struct pci_controller *phb,
dummy_page_da = dma_map_single(phb->parent, dummy_page_va,
PAGE_SIZE, DMA_FROM_DEVICE);
if (dma_mapping_error(dummy_page_da)) {
if (dma_mapping_error(phb->parent, dummy_page_da)) {
pr_err("SPIDER-IOWA:Map dummy page filed.\n");
kfree(dummy_page_va);
return -1;
......
......@@ -871,7 +871,7 @@ static int proc_mf_dump_cmdline(char *page, char **start, off_t off,
count = 256 - off;
dma_addr = iseries_hv_map(page, off + count, DMA_FROM_DEVICE);
if (dma_mapping_error(dma_addr))
if (dma_mapping_error(NULL, dma_addr))
return -ENOMEM;
memset(page, 0, off + count);
memset(&vsp_cmd, 0, sizeof(vsp_cmd));
......
......@@ -544,7 +544,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
return ret;
}
static const struct dma_mapping_ops calgary_dma_ops = {
static struct dma_mapping_ops calgary_dma_ops = {
.alloc_coherent = calgary_alloc_coherent,
.map_single = calgary_map_single,
.unmap_single = calgary_unmap_single,
......
......@@ -11,7 +11,7 @@
static int forbid_dac __read_mostly;
const struct dma_mapping_ops *dma_ops;
struct dma_mapping_ops *dma_ops;
EXPORT_SYMBOL(dma_ops);
static int iommu_sac_force __read_mostly;
......@@ -312,6 +312,8 @@ static int dma_release_coherent(struct device *dev, int order, void *vaddr)
int dma_supported(struct device *dev, u64 mask)
{
struct dma_mapping_ops *ops = get_dma_ops(dev);
#ifdef CONFIG_PCI
if (mask > 0xffffffff && forbid_dac > 0) {
dev_info(dev, "PCI: Disallowing DAC for device\n");
......@@ -319,8 +321,8 @@ int dma_supported(struct device *dev, u64 mask)
}
#endif
if (dma_ops->dma_supported)
return dma_ops->dma_supported(dev, mask);
if (ops->dma_supported)
return ops->dma_supported(dev, mask);
/* Copied from i386. Doesn't make much sense, because it will
only work for pci_alloc_coherent.
......@@ -367,6 +369,7 @@ void *
dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
gfp_t gfp)
{
struct dma_mapping_ops *ops = get_dma_ops(dev);
void *memory = NULL;
struct page *page;
unsigned long dma_mask = 0;
......@@ -435,8 +438,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
/* Let low level make its own zone decisions */
gfp &= ~(GFP_DMA32|GFP_DMA);
if (dma_ops->alloc_coherent)
return dma_ops->alloc_coherent(dev, size,
if (ops->alloc_coherent)
return ops->alloc_coherent(dev, size,
dma_handle, gfp);
return NULL;
}
......@@ -448,14 +451,14 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
}
}
if (dma_ops->alloc_coherent) {
if (ops->alloc_coherent) {
free_pages((unsigned long)memory, get_order(size));
gfp &= ~(GFP_DMA|GFP_DMA32);
return dma_ops->alloc_coherent(dev, size, dma_handle, gfp);
return ops->alloc_coherent(dev, size, dma_handle, gfp);
}
if (dma_ops->map_simple) {
*dma_handle = dma_ops->map_simple(dev, virt_to_phys(memory),
if (ops->map_simple) {
*dma_handle = ops->map_simple(dev, virt_to_phys(memory),
size,
PCI_DMA_BIDIRECTIONAL);
if (*dma_handle != bad_dma_address)
......@@ -477,12 +480,14 @@ EXPORT_SYMBOL(dma_alloc_coherent);
void dma_free_coherent(struct device *dev, size_t size,
void *vaddr, dma_addr_t bus)
{
struct dma_mapping_ops *ops = get_dma_ops(dev);
int order = get_order(size);
WARN_ON(irqs_disabled()); /* for portability */
if (dma_release_coherent(dev, order, vaddr))
return;
if (dma_ops->unmap_single)
dma_ops->unmap_single(dev, bus, size, 0);
if (ops->unmap_single)
ops->unmap_single(dev, bus, size, 0);
free_pages((unsigned long)vaddr, order);
}
EXPORT_SYMBOL(dma_free_coherent);
......
......@@ -692,8 +692,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
extern int agp_amd64_init(void);
static const struct dma_mapping_ops gart_dma_ops = {
.mapping_error = NULL,
static struct dma_mapping_ops gart_dma_ops = {
.map_single = gart_map_single,
.map_simple = gart_map_simple,
.unmap_single = gart_unmap_single,
......
......@@ -72,21 +72,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
return nents;
}
/* Make sure we keep the same behaviour */
static int nommu_mapping_error(dma_addr_t dma_addr)
{
#ifdef CONFIG_X86_32
return 0;
#else
return (dma_addr == bad_dma_address);
#endif
}
const struct dma_mapping_ops nommu_dma_ops = {
struct dma_mapping_ops nommu_dma_ops = {
.map_single = nommu_map_single,
.map_sg = nommu_map_sg,
.mapping_error = nommu_mapping_error,
.is_phys = 1,
};
......
......@@ -18,7 +18,7 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size,
return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction);
}
const struct dma_mapping_ops swiotlb_dma_ops = {
struct dma_mapping_ops swiotlb_dma_ops = {
.mapping_error = swiotlb_dma_mapping_error,
.alloc_coherent = swiotlb_alloc_coherent,
.free_coherent = swiotlb_free_coherent,
......
......@@ -50,7 +50,7 @@ fw_iso_buffer_init(struct fw_iso_buffer *buffer, struct fw_card *card,
address = dma_map_page(card->device, buffer->pages[i],
0, PAGE_SIZE, direction);
if (dma_mapping_error(address)) {
if (dma_mapping_error(card->device, address)) {
__free_page(buffer->pages[i]);
goto out_pages;
}
......
......@@ -953,7 +953,7 @@ at_context_queue_packet(struct context *ctx, struct fw_packet *packet)
payload_bus =
dma_map_single(ohci->card.device, packet->payload,
packet->payload_length, DMA_TO_DEVICE);
if (dma_mapping_error(payload_bus)) {
if (dma_mapping_error(ohci->card.device, payload_bus)) {
packet->ack = RCODE_SEND_ERROR;
return -1;
}
......
......@@ -543,7 +543,7 @@ sbp2_send_management_orb(struct sbp2_logical_unit *lu, int node_id,
orb->response_bus =
dma_map_single(device->card->device, &orb->response,
sizeof(orb->response), DMA_FROM_DEVICE);
if (dma_mapping_error(orb->response_bus))
if (dma_mapping_error(device->card->device, orb->response_bus))
goto fail_mapping_response;
orb->request.response.high = 0;
......@@ -577,7 +577,7 @@ sbp2_send_management_orb(struct sbp2_logical_unit *lu, int node_id,
orb->base.request_bus =
dma_map_single(device->card->device, &orb->request,
sizeof(orb->request), DMA_TO_DEVICE);
if (dma_mapping_error(orb->base.request_bus))
if (dma_mapping_error(device->card->device, orb->base.request_bus))
goto fail_mapping_request;
sbp2_send_orb(&orb->base, lu, node_id, generation,
......@@ -1424,7 +1424,7 @@ sbp2_map_scatterlist(struct sbp2_command_orb *orb, struct fw_device *device,
orb->page_table_bus =
dma_map_single(device->card->device, orb->page_table,
sizeof(orb->page_table), DMA_TO_DEVICE);
if (dma_mapping_error(orb->page_table_bus))
if (dma_mapping_error(device->card->device, orb->page_table_bus))
goto fail_page_table;
/*
......@@ -1509,7 +1509,7 @@ static int sbp2_scsi_queuecommand(struct scsi_cmnd *cmd, scsi_done_fn_t done)
orb->base.request_bus =
dma_map_single(device->card->device, &orb->request,
sizeof(orb->request), DMA_TO_DEVICE);
if (dma_mapping_error(orb->base.request_bus))
if (dma_mapping_error(device->card->device, orb->base.request_bus))
goto out;
sbp2_send_orb(&orb->base, lu, lu->tgt->node_id, lu->generation,
......
......@@ -698,7 +698,7 @@ int ipath_sdma_verbs_send(struct ipath_devdata *dd,
addr = dma_map_single(&dd->pcidev->dev, tx->txreq.map_addr,
tx->map_len, DMA_TO_DEVICE);
if (dma_mapping_error(addr)) {
if (dma_mapping_error(&dd->pcidev->dev, addr)) {
ret = -EIO;
goto unlock;
}
......
......@@ -206,7 +206,7 @@ static int ipath_user_sdma_coalesce(const struct ipath_devdata *dd,
dma_addr = dma_map_page(&dd->pcidev->dev, page, 0, len,
DMA_TO_DEVICE);
if (dma_mapping_error(dma_addr)) {
if (dma_mapping_error(&dd->pcidev->dev, dma_addr)) {
ret = -ENOMEM;
goto free_unmap;
}
......@@ -301,7 +301,7 @@ static int ipath_user_sdma_pin_pages(const struct ipath_devdata *dd,
pages[j], 0, flen, DMA_TO_DEVICE);
unsigned long fofs = addr & ~PAGE_MASK;
if (dma_mapping_error(dma_addr)) {
if (dma_mapping_error(&dd->pcidev->dev, dma_addr)) {
ret = -ENOMEM;
goto done;
}
......@@ -508,7 +508,7 @@ static int ipath_user_sdma_queue_pkts(const struct ipath_devdata *dd,
if (page) {
dma_addr = dma_map_page(&dd->pcidev->dev,
page, 0, len, DMA_TO_DEVICE);
if (dma_mapping_error(dma_addr)) {
if (dma_mapping_error(&dd->pcidev->dev, dma_addr)) {
ret = -ENOMEM;
goto free_pbc;
}
......
......@@ -780,7 +780,7 @@ int mthca_map_eq_icm(struct mthca_dev *dev, u64 icm_virt)
return -ENOMEM;
dev->eq_table.icm_dma = pci_map_page(dev->pdev, dev->eq_table.icm_page, 0,
PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
if (pci_dma_mapping_error(dev->eq_table.icm_dma)) {
if (pci_dma_mapping_error(dev->pdev, dev->eq_table.icm_dma)) {
__free_page(dev->eq_table.icm_page);
return -ENOMEM;
}
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment