Pull DMA mapping branch from Marek Szyprowski:
"Short summary for the whole series:
A few limitations have been identified in the current dma-mapping
design and its implementations for various architectures. There exist
more than one function for allocating and freeing the buffers:
currently these 3 are used dma_{alloc, free}_coherent,
dma_{alloc,free}_writecombine, dma_{alloc,free}_noncoherent.
For most of the systems these calls are almost equivalent and can be
interchanged. For others, especially the truly non-coherent ones
(like ARM), the difference can be easily noticed in overall driver
performance. Sadly not all architectures provide implementations for
all of them, so the drivers might need to be adapted and cannot be
easily shared between different architectures. The provided patches
unify all these functions and hide the differences under the already
existing dma attributes concept. The thread with more references is
available here:
http://www.spinics.net/lists/linux-sh/msg09777.html
These patches are also a prerequisite for unifying DMA-mapping
implementation on ARM architecture with the common one provided by
dma_map_ops structure and extending it with IOMMU support. More
information is available in the following thread:
http://thread.gmane.org/gmane.linux.kernel.cross-arch/12819
More works on dma-mapping framework are planned, especially in the
area of buffer sharing and managing the shared mappings (together with
the recently introduced dma_buf interface: commit
d15bd7ee445d
"dma-buf: Introduce dma buffer sharing mechanism").
The patches in the current set introduce a new alloc/free methods
(with support for memory attributes) in dma_map_ops structure, which
will later replace dma_alloc_coherent and dma_alloc_writecombine
functions."
People finally started piping up with support for merging this, so I'm
merging it as the last of the pending stuff from the merge window.
Looks like pohmelfs is going to wait for 3.5 and more external support
for merging.
* 'for-linus' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping:
common: DMA-mapping: add NON-CONSISTENT attribute
common: DMA-mapping: add WRITE_COMBINE attribute
common: dma-mapping: introduce mmap method
common: dma-mapping: remove old alloc_coherent and free_coherent methods
Hexagon: adapt for dma_map_ops changes
Unicore32: adapt for dma_map_ops changes
Microblaze: adapt for dma_map_ops changes
SH: adapt for dma_map_ops changes
Alpha: adapt for dma_map_ops changes
SPARC: adapt for dma_map_ops changes
PowerPC: adapt for dma_map_ops changes
MIPS: adapt for dma_map_ops changes
X86 & IA64: adapt for dma_map_ops changes
common: dma-mapping: introduce generic alloc() and free() methods
#include <asm/io.h>
#include <asm/page.h> /* PAGE_OFFSET */
#include <asm/dma.h>
-#include <asm/system.h> /* wmb() */
#include <asm/acpi-ext.h>
* See Documentation/DMA-API-HOWTO.txt
*/
static void *
- sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags)
+ sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t flags, struct dma_attrs *attrs)
{
struct ioc *ioc;
void *addr;
*
* See Documentation/DMA-API-HOWTO.txt
*/
- static void sba_free_coherent (struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle)
+ static void sba_free_coherent(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_handle, struct dma_attrs *attrs)
{
sba_unmap_single_attrs(dev, dma_handle, size, 0, NULL);
free_pages((unsigned long) vaddr, get_order(size));
__setup("sbapagesize=",sba_page_override);
struct dma_map_ops sba_dma_ops = {
- .alloc_coherent = sba_alloc_coherent,
- .free_coherent = sba_free_coherent,
+ .alloc = sba_alloc_coherent,
+ .free = sba_free_coherent,
.map_page = sba_map_page,
.unmap_page = sba_unmap_page,
.map_sg = sba_map_sg_attrs,
static void *ibmebus_alloc_coherent(struct device *dev,
size_t size,
dma_addr_t *dma_handle,
- gfp_t flag)
+ gfp_t flag,
+ struct dma_attrs *attrs)
{
void *mem;
static void ibmebus_free_coherent(struct device *dev,
size_t size, void *vaddr,
- dma_addr_t dma_handle)
+ dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
{
kfree(vaddr);
}
}
static struct dma_map_ops ibmebus_dma_ops = {
- .alloc_coherent = ibmebus_alloc_coherent,
- .free_coherent = ibmebus_free_coherent,
+ .alloc = ibmebus_alloc_coherent,
+ .free = ibmebus_free_coherent,
.map_sg = ibmebus_map_sg,
.unmap_sg = ibmebus_unmap_sg,
.dma_supported = ibmebus_dma_supported,
struct bus_type ibmebus_bus_type = {
.name = "ibmebus",
- .uevent = of_device_uevent,
+ .uevent = of_device_uevent_modalias,
.bus_attrs = ibmebus_bus_attrs,
.match = ibmebus_bus_bus_match,
.probe = ibmebus_bus_device_probe,
#include <asm/abs_addr.h>
#include <asm/page.h>
#include <asm/hvcall.h>
-#include <asm/iseries/vio.h>
-#include <asm/iseries/hv_types.h>
-#include <asm/iseries/hv_lp_config.h>
-#include <asm/iseries/hv_call_xm.h>
-#include <asm/iseries/iommu.h>
static struct bus_type vio_bus_type;
}
static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag)
+ dma_addr_t *dma_handle, gfp_t flag,
+ struct dma_attrs *attrs)
{
struct vio_dev *viodev = to_vio_dev(dev);
void *ret;
return NULL;
}
- ret = dma_iommu_ops.alloc_coherent(dev, size, dma_handle, flag);
+ ret = dma_iommu_ops.alloc(dev, size, dma_handle, flag, attrs);
if (unlikely(ret == NULL)) {
vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
atomic_inc(&viodev->cmo.allocs_failed);
}
static void vio_dma_iommu_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle)
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
{
struct vio_dev *viodev = to_vio_dev(dev);
- dma_iommu_ops.free_coherent(dev, size, vaddr, dma_handle);
+ dma_iommu_ops.free(dev, size, vaddr, dma_handle, attrs);
vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
}
}
struct dma_map_ops vio_dma_mapping_ops = {
- .alloc_coherent = vio_dma_iommu_alloc_coherent,
- .free_coherent = vio_dma_iommu_free_coherent,
+ .alloc = vio_dma_iommu_alloc_coherent,
+ .free = vio_dma_iommu_free_coherent,
.map_sg = vio_dma_iommu_map_sg,
.unmap_sg = vio_dma_iommu_unmap_sg,
.map_page = vio_dma_iommu_map_page,
vio_bus_type.bus_attrs = vio_cmo_bus_attrs;
}
#else /* CONFIG_PPC_SMLPAR */
-/* Dummy functions for iSeries platform */
int vio_cmo_entitlement_update(size_t new_entitlement) { return 0; }
void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired) {}
static int vio_cmo_bus_probe(struct vio_dev *viodev) { return 0; }
struct iommu_table *tbl;
unsigned long offset, size;
- if (firmware_has_feature(FW_FEATURE_ISERIES))
- return vio_build_iommu_table_iseries(dev);
-
dma_window = of_get_property(dev->dev.of_node,
"ibm,my-dma-window", NULL);
if (!dma_window)
* vio_register_driver: - Register a new vio driver
* @drv: The vio_driver structure to be registered.
*/
-int vio_register_driver(struct vio_driver *viodrv)
+int __vio_register_driver(struct vio_driver *viodrv, struct module *owner,
+ const char *mod_name)
{
- printk(KERN_DEBUG "%s: driver %s registering\n", __func__,
- viodrv->driver.name);
+ pr_debug("%s: driver %s registering\n", __func__, viodrv->name);
/* fill in 'struct driver' fields */
+ viodrv->driver.name = viodrv->name;
+ viodrv->driver.pm = viodrv->pm;
viodrv->driver.bus = &vio_bus_type;
+ viodrv->driver.owner = owner;
+ viodrv->driver.mod_name = mod_name;
return driver_register(&viodrv->driver);
}
-EXPORT_SYMBOL(vio_register_driver);
+EXPORT_SYMBOL(__vio_register_driver);
/**
* vio_unregister_driver - Remove registration of vio driver.
{
struct iommu_table *tbl = get_iommu_table_base(dev);
- /* iSeries uses a common table for all vio devices */
- if (!firmware_has_feature(FW_FEATURE_ISERIES) && tbl)
+ if (tbl)
iommu_free_table(tbl, dev->of_node ?
dev->of_node->full_name : dev_name(dev));
of_node_put(dev->of_node);
viodev->name = of_node->name;
viodev->type = of_node->type;
viodev->unit_address = *unit_address;
- if (firmware_has_feature(FW_FEATURE_ISERIES)) {
- unit_address = of_get_property(of_node,
- "linux,unit_address", NULL);
- if (unit_address != NULL)
- viodev->unit_address = *unit_address;
- }
viodev->dev.of_node = of_node_get(of_node);
if (firmware_has_feature(FW_FEATURE_CMO))
#include <asm/calgary.h>
#include <asm/tce.h>
#include <asm/pci-direct.h>
-#include <asm/system.h>
#include <asm/dma.h>
#include <asm/rio.h>
#include <asm/bios_ebda.h>
}
static void* calgary_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag)
+ dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs)
{
void *ret = NULL;
dma_addr_t mapping;
}
static void calgary_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle)
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
{
unsigned int npages;
struct iommu_table *tbl = find_iommu_table(dev);
}
static struct dma_map_ops calgary_dma_ops = {
- .alloc_coherent = calgary_alloc_coherent,
- .free_coherent = calgary_free_coherent,
+ .alloc = calgary_alloc_coherent,
+ .free = calgary_free_coherent,
.map_sg = calgary_map_sg,
.unmap_sg = calgary_unmap_sg,
.map_page = calgary_map_page,
}
}
void *dma_generic_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_addr, gfp_t flag)
+ dma_addr_t *dma_addr, gfp_t flag,
+ struct dma_attrs *attrs)
{
unsigned long dma_mask;
struct page *page;
static __devinit void via_no_dac(struct pci_dev *dev)
{
- if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) {
+ if (forbid_dac == 0) {
dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n");
forbid_dac = 1;
}
}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac);
+DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID,
+ PCI_CLASS_BRIDGE_PCI, 8, via_no_dac);
#endif
* The exported alloc_coherent function for dma_ops.
*/
static void *alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_addr, gfp_t flag)
+ dma_addr_t *dma_addr, gfp_t flag,
+ struct dma_attrs *attrs)
{
unsigned long flags;
void *virt_addr;
* The exported free_coherent function for dma_ops.
*/
static void free_coherent(struct device *dev, size_t size,
- void *virt_addr, dma_addr_t dma_addr)
+ void *virt_addr, dma_addr_t dma_addr,
+ struct dma_attrs *attrs)
{
unsigned long flags;
struct protection_domain *domain;
* we don't need to preallocate the protection domains anymore.
* For now we have to.
*/
-static void prealloc_protection_domains(void)
+static void __init prealloc_protection_domains(void)
{
struct iommu_dev_data *dev_data;
struct dma_ops_domain *dma_dom;
}
static struct dma_map_ops amd_iommu_dma_ops = {
- .alloc_coherent = alloc_coherent,
- .free_coherent = free_coherent,
+ .alloc = alloc_coherent,
+ .free = free_coherent,
.map_page = map_page,
.unmap_page = unmap_page,
.map_sg = map_sg,
#define ROOT_SIZE VTD_PAGE_SIZE
#define CONTEXT_SIZE VTD_PAGE_SIZE
-#define IS_BRIDGE_HOST_DEVICE(pdev) \
- ((pdev->class >> 8) == PCI_CLASS_BRIDGE_HOST)
#define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
#define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
#define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e)
/* si_domain contains mulitple devices */
#define DOMAIN_FLAG_STATIC_IDENTITY (1 << 2)
+/* define the limit of IOMMUs supported in each domain */
+#ifdef CONFIG_X86
+# define IOMMU_UNITS_SUPPORTED MAX_IO_APICS
+#else
+# define IOMMU_UNITS_SUPPORTED 64
+#endif
+
struct dmar_domain {
int id; /* domain id */
int nid; /* node id */
- unsigned long iommu_bmp; /* bitmap of iommus this domain uses*/
+ DECLARE_BITMAP(iommu_bmp, IOMMU_UNITS_SUPPORTED);
+ /* bitmap of iommus this domain uses*/
struct list_head devices; /* all devices' list */
struct iova_domain iovad; /* iova's that belong to this domain */
BUG_ON(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE);
BUG_ON(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY);
- iommu_id = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
+ iommu_id = find_first_bit(domain->iommu_bmp, g_num_of_iommus);
if (iommu_id < 0 || iommu_id >= g_num_of_iommus)
return NULL;
domain->iommu_coherency = 1;
- for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
+ for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) {
if (!ecap_coherent(g_iommus[i]->ecap)) {
domain->iommu_coherency = 0;
break;
domain->iommu_snooping = 1;
- for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
+ for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) {
if (!ecap_sc_support(g_iommus[i]->ecap)) {
domain->iommu_snooping = 0;
break;
unsigned long nlongs;
ndomains = cap_ndoms(iommu->cap);
- pr_debug("IOMMU %d: Number of Domains supportd <%ld>\n", iommu->seq_id,
+ pr_debug("IOMMU %d: Number of Domains supported <%ld>\n", iommu->seq_id,
ndomains);
nlongs = BITS_TO_LONGS(ndomains);
return NULL;
domain->nid = -1;
- memset(&domain->iommu_bmp, 0, sizeof(unsigned long));
+ memset(domain->iommu_bmp, 0, sizeof(domain->iommu_bmp));
domain->flags = 0;
return domain;
domain->id = num;
set_bit(num, iommu->domain_ids);
- set_bit(iommu->seq_id, &domain->iommu_bmp);
+ set_bit(iommu->seq_id, domain->iommu_bmp);
iommu->domains[num] = domain;
spin_unlock_irqrestore(&iommu->lock, flags);
if (found) {
clear_bit(num, iommu->domain_ids);
- clear_bit(iommu->seq_id, &domain->iommu_bmp);
+ clear_bit(iommu->seq_id, domain->iommu_bmp);
iommu->domains[num] = NULL;
}
spin_unlock_irqrestore(&iommu->lock, flags);
dma_pte_free_pagetable(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
for_each_active_iommu(iommu, drhd)
- if (test_bit(iommu->seq_id, &domain->iommu_bmp))
+ if (test_bit(iommu->seq_id, domain->iommu_bmp))
iommu_detach_domain(domain, iommu);
free_domain_mem(domain);
spin_unlock_irqrestore(&iommu->lock, flags);
spin_lock_irqsave(&domain->iommu_lock, flags);
- if (!test_and_set_bit(iommu->seq_id, &domain->iommu_bmp)) {
+ if (!test_and_set_bit(iommu->seq_id, domain->iommu_bmp)) {
domain->iommu_count++;
if (domain->iommu_count == 1)
domain->nid = iommu->node;
return -EFAULT;
for_each_pci_dev(pdev) {
- /* Skip Host/PCI Bridge devices */
- if (IS_BRIDGE_HOST_DEVICE(pdev))
- continue;
if (iommu_should_identity_map(pdev, 1)) {
- printk(KERN_INFO "IOMMU: %s identity mapping for device %s\n",
- hw ? "hardware" : "software", pci_name(pdev));
-
ret = domain_add_dev_info(si_domain, pdev,
- hw ? CONTEXT_TT_PASS_THROUGH :
- CONTEXT_TT_MULTI_LEVEL);
- if (ret)
+ hw ? CONTEXT_TT_PASS_THROUGH :
+ CONTEXT_TT_MULTI_LEVEL);
+ if (ret) {
+ /* device not associated with an iommu */
+ if (ret == -ENODEV)
+ continue;
return ret;
+ }
+ pr_info("IOMMU: %s identity mapping for device %s\n",
+ hw ? "hardware" : "software", pci_name(pdev));
}
}
* endfor
*/
for_each_drhd_unit(drhd) {
- g_num_of_iommus++;
/*
* lock not needed as this is only incremented in the single
* threaded kernel __init code path all other access are read
* only
*/
+ if (g_num_of_iommus < IOMMU_UNITS_SUPPORTED) {
+ g_num_of_iommus++;
+ continue;
+ }
+ printk_once(KERN_ERR "intel-iommu: exceeded %d IOMMUs\n",
+ IOMMU_UNITS_SUPPORTED);
}
g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),
}
static void *intel_alloc_coherent(struct device *hwdev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags)
+ dma_addr_t *dma_handle, gfp_t flags,
+ struct dma_attrs *attrs)
{
void *vaddr;
int order;
}
static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
- dma_addr_t dma_handle)
+ dma_addr_t dma_handle, struct dma_attrs *attrs)
{
int order;
}
struct dma_map_ops intel_dma_ops = {
- .alloc_coherent = intel_alloc_coherent,
- .free_coherent = intel_free_coherent,
+ .alloc = intel_alloc_coherent,
+ .free = intel_free_coherent,
.map_sg = intel_map_sg,
.unmap_sg = intel_unmap_sg,
.map_page = intel_map_page,
if (found == 0) {
unsigned long tmp_flags;
spin_lock_irqsave(&domain->iommu_lock, tmp_flags);
- clear_bit(iommu->seq_id, &domain->iommu_bmp);
+ clear_bit(iommu->seq_id, domain->iommu_bmp);
domain->iommu_count--;
domain_update_iommu_cap(domain);
spin_unlock_irqrestore(&domain->iommu_lock, tmp_flags);
*/
spin_lock_irqsave(&domain->iommu_lock, flags2);
if (test_and_clear_bit(iommu->seq_id,
- &domain->iommu_bmp)) {
+ domain->iommu_bmp)) {
domain->iommu_count--;
domain_update_iommu_cap(domain);
}
domain->id = vm_domid++;
domain->nid = -1;
- memset(&domain->iommu_bmp, 0, sizeof(unsigned long));
+ memset(domain->iommu_bmp, 0, sizeof(domain->iommu_bmp));
domain->flags = DOMAIN_FLAG_VIRTUAL_MACHINE;
return domain;
#include <linux/scatterlist.h>
struct dma_map_ops {
- void* (*alloc_coherent)(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp);
- void (*free_coherent)(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle);
+ void* (*alloc)(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp,
+ struct dma_attrs *attrs);
+ void (*free)(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs);
+ int (*mmap)(struct device *, struct vm_area_struct *,
+ void *, dma_addr_t, size_t, struct dma_attrs *attrs);
+
dma_addr_t (*map_page)(struct device *dev, struct page *page,
unsigned long offset, size_t size,
enum dma_data_direction dir,
return DMA_BIT_MASK(32);
}
-#ifdef ARCH_HAS_DMA_SET_COHERENT_MASK
+#ifdef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK
int dma_set_coherent_mask(struct device *dev, u64 mask);
#else
static inline int dma_set_coherent_mask(struct device *dev, u64 mask)