aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/ia64/include/asm/dma-mapping.h4
-rw-r--r--arch/x86/kernel/amd_iommu.c2
-rw-r--r--arch/x86/kernel/early-quirks.c18
-rw-r--r--arch/x86/kernel/k8.c5
-rw-r--r--arch/x86/kernel/pci-calgary_64.c14
-rw-r--r--arch/x86/kernel/pci-dma.c146
-rw-r--r--arch/x86/kernel/pci-gart_64.c89
-rw-r--r--arch/x86/kernel/pci-nommu.c47
-rw-r--r--drivers/pci/intel-iommu.c2
-rw-r--r--include/asm-x86/dma-mapping.h80
-rw-r--r--include/asm-x86/iommu.h1
-rw-r--r--include/linux/dma-mapping.h5
-rw-r--r--include/linux/pci_ids.h5
-rw-r--r--kernel/dma-coherent.c2
-rw-r--r--lib/swiotlb.c45
15 files changed, 241 insertions, 224 deletions
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 9f0df9bd46b..06ff1ba2146 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -8,7 +8,9 @@
#include <asm/machvec.h>
#include <linux/scatterlist.h>
-#define dma_alloc_coherent platform_dma_alloc_coherent
+#define dma_alloc_coherent(dev, size, handle, gfp) \
+ platform_dma_alloc_coherent(dev, size, handle, (gfp) | GFP_DMA)
+
/* coherent mem. is cheap */
static inline void *
dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 69b4d060b21..01c68c38840 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1038,8 +1038,6 @@ out:
/*
* The exported free_coherent function for dma_ops.
- * FIXME: fix the generic x86 DMA layer so that it actually calls that
- * function.
*/
static void free_coherent(struct device *dev, size_t size,
void *virt_addr, dma_addr_t dma_addr)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 4353cf5e6fa..24bb5faf5ef 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -95,6 +95,20 @@ static void __init nvidia_bugs(int num, int slot, int func)
}
+#ifdef CONFIG_DMAR
+static void __init intel_g33_dmar(int num, int slot, int func)
+{
+ struct acpi_table_header *dmar_tbl;
+ acpi_status status;
+
+ status = acpi_get_table(ACPI_SIG_DMAR, 0, &dmar_tbl);
+ if (ACPI_SUCCESS(status)) {
+ printk(KERN_INFO "BIOS BUG: DMAR advertised on Intel G31/G33 chipset -- ignoring\n");
+ dmar_disabled = 1;
+ }
+}
+#endif
+
#define QFLAG_APPLY_ONCE 0x1
#define QFLAG_APPLIED 0x2
#define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -114,6 +128,10 @@ static struct chipset early_qrk[] __initdata = {
PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, via_bugs },
{ PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, fix_hypertransport_config },
+#ifdef CONFIG_DMAR
+ { PCI_VENDOR_ID_INTEL, 0x29c0,
+ PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, intel_g33_dmar },
+#endif
{}
};
diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/k8.c
index 7377ccb2133..304d8bad655 100644
--- a/arch/x86/kernel/k8.c
+++ b/arch/x86/kernel/k8.c
@@ -16,8 +16,9 @@ EXPORT_SYMBOL(num_k8_northbridges);
static u32 *flush_words;
struct pci_device_id k8_nb_ids[] = {
- { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) },
- { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_11H_NB_MISC) },
{}
};
EXPORT_SYMBOL(k8_nb_ids);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index dcdac6c826e..8415d92853c 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -510,8 +510,22 @@ error:
return ret;
}
+static void calgary_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle)
+{
+ unsigned int npages;
+ struct iommu_table *tbl = find_iommu_table(dev);
+
+ size = PAGE_ALIGN(size);
+ npages = size >> PAGE_SHIFT;
+
+ iommu_free(tbl, dma_handle, npages);
+ free_pages((unsigned long)vaddr, get_order(size));
+}
+
static struct dma_mapping_ops calgary_dma_ops = {
.alloc_coherent = calgary_alloc_coherent,
+ .free_coherent = calgary_free_coherent,
.map_single = calgary_map_single,
.unmap_single = calgary_unmap_single,
.map_sg = calgary_map_sg,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 87d4d6964ec..0a1408abcc6 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -41,11 +41,12 @@ EXPORT_SYMBOL(bad_dma_address);
/* Dummy device used for NULL arguments (normally ISA). Better would
be probably a smaller DMA mask, but this is bug-to-bug compatible
to older i386. */
-struct device fallback_dev = {
+struct device x86_dma_fallback_dev = {
.bus_id = "fallback device",
.coherent_dma_mask = DMA_32BIT_MASK,
- .dma_mask = &fallback_dev.coherent_dma_mask,
+ .dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
};
+EXPORT_SYMBOL(x86_dma_fallback_dev);
int dma_set_mask(struct device *dev, u64 mask)
{
@@ -241,147 +242,6 @@ int dma_supported(struct device *dev, u64 mask)
}
EXPORT_SYMBOL(dma_supported);
-/* Allocate DMA memory on node near device */
-static noinline struct page *
-dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order)
-{
- int node;
-
- node = dev_to_node(dev);
-
- return alloc_pages_node(node, gfp, order);
-}
-
-/*
- * Allocate memory for a coherent mapping.
- */
-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;
- dma_addr_t bus;
- int noretry = 0;
-
- /* ignore region specifiers */
- gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-
- if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
- return memory;
-
- if (!dev) {
- dev = &fallback_dev;
- gfp |= GFP_DMA;
- }
- dma_mask = dev->coherent_dma_mask;
- if (dma_mask == 0)
- dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK;
-
- /* Device not DMA able */
- if (dev->dma_mask == NULL)
- return NULL;
-
- /* Don't invoke OOM killer or retry in lower 16MB DMA zone */
- if (gfp & __GFP_DMA)
- noretry = 1;
-
-#ifdef CONFIG_X86_64
- /* Why <=? Even when the mask is smaller than 4GB it is often
- larger than 16MB and in this case we have a chance of
- finding fitting memory in the next higher zone first. If
- not retry with true GFP_DMA. -AK */
- if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) {
- gfp |= GFP_DMA32;
- if (dma_mask < DMA_32BIT_MASK)
- noretry = 1;
- }
-#endif
-
- again:
- page = dma_alloc_pages(dev,
- noretry ? gfp | __GFP_NORETRY : gfp, get_order(size));
- if (page == NULL)
- return NULL;
-
- {
- int high, mmu;
- bus = page_to_phys(page);
- memory = page_address(page);
- high = (bus + size) >= dma_mask;
- mmu = high;
- if (force_iommu && !(gfp & GFP_DMA))
- mmu = 1;
- else if (high) {
- free_pages((unsigned long)memory,
- get_order(size));
-
- /* Don't use the 16MB ZONE_DMA unless absolutely
- needed. It's better to use remapping first. */
- if (dma_mask < DMA_32BIT_MASK && !(gfp & GFP_DMA)) {
- gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
- goto again;
- }
-
- /* Let low level make its own zone decisions */
- gfp &= ~(GFP_DMA32|GFP_DMA);
-
- if (ops->alloc_coherent)
- return ops->alloc_coherent(dev, size,
- dma_handle, gfp);
- return NULL;
- }
-
- memset(memory, 0, size);
- if (!mmu) {
- *dma_handle = bus;
- return memory;
- }
- }
-
- if (ops->alloc_coherent) {
- free_pages((unsigned long)memory, get_order(size));
- gfp &= ~(GFP_DMA|GFP_DMA32);
- return ops->alloc_coherent(dev, size, dma_handle, gfp);
- }
-
- if (ops->map_simple) {
- *dma_handle = ops->map_simple(dev, virt_to_phys(memory),
- size,
- PCI_DMA_BIDIRECTIONAL);
- if (*dma_handle != bad_dma_address)
- return memory;
- }
-
- if (panic_on_overflow)
- panic("dma_alloc_coherent: IOMMU overflow by %lu bytes\n",
- (unsigned long)size);
- free_pages((unsigned long)memory, get_order(size));
- return NULL;
-}
-EXPORT_SYMBOL(dma_alloc_coherent);
-
-/*
- * Unmap coherent memory.
- * The caller must ensure that the device has finished accessing the mapping.
- */
-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_from_coherent(dev, order, vaddr))
- return;
- if (ops->unmap_single)
- ops->unmap_single(dev, bus, size, 0);
- free_pages((unsigned long)vaddr, order);
-}
-EXPORT_SYMBOL(dma_free_coherent);
-
static int __init pci_iommu_init(void)
{
calgary_iommu_init();
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 49285f8fd4d..1b0c412566e 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;
@@ -90,16 +91,17 @@ static unsigned long alloc_iommu(struct device *dev, int size)
base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev),
PAGE_SIZE) >> PAGE_SHIFT;
- boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+ boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
PAGE_SIZE) >> PAGE_SHIFT;
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;
@@ -212,34 +214,24 @@ static void iommu_full(struct device *dev, size_t size, int dir)
static inline int
need_iommu(struct device *dev, unsigned long addr, size_t size)
{
- u64 mask = *dev->dma_mask;
- int high = addr + size > mask;
- int mmu = high;
-
- if (force_iommu)
- mmu = 1;
-
- return mmu;
+ return force_iommu ||
+ !is_buffer_dma_capable(*dev->dma_mask, addr, size);
}
static inline int
nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
{
- u64 mask = *dev->dma_mask;
- int high = addr + size > mask;
- int mmu = high;
-
- return mmu;
+ return !is_buffer_dma_capable(*dev->dma_mask, addr, size);
}
/* Map a single continuous physical area into the IOMMU.
* 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) {
@@ -259,16 +251,6 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
return iommu_bus_base + iommu_page*PAGE_SIZE + (phys_mem & ~PAGE_MASK);
}
-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);
-
- flush_gart();
-
- return map;
-}
-
/* Map a single area into the IOMMU */
static dma_addr_t
gart_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir)
@@ -276,12 +258,13 @@ gart_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir)
unsigned long bus;
if (!dev)
- dev = &fallback_dev;
+ dev = &x86_dma_fallback_dev;
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 +323,7 @@ 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 +345,7 @@ 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;
@@ -427,7 +410,7 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
return 0;
if (!dev)
- dev = &fallback_dev;
+ dev = &x86_dma_fallback_dev;
out = 0;
start = 0;
@@ -499,6 +482,41 @@ error:
return 0;
}
+/* allocate and map a coherent mapping */
+static void *
+gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
+ gfp_t flag)
+{
+ void *vaddr;
+ unsigned long align_mask;
+
+ vaddr = (void *)__get_free_pages(flag | __GFP_ZERO, get_order(size));
+ if (!vaddr)
+ return NULL;
+
+ align_mask = (1UL << get_order(size)) - 1;
+
+ *dma_addr = dma_map_area(dev, __pa(vaddr), size, DMA_BIDIRECTIONAL,
+ align_mask);
+ flush_gart();
+
+ if (*dma_addr != bad_dma_address)
+ return vaddr;
+
+ free_pages((unsigned long)vaddr, get_order(size));
+
+ return NULL;
+}
+
+/* free a coherent mapping */
+static void
+gart_free_coherent(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_addr)
+{
+ gart_unmap_single(dev, dma_addr, size, DMA_BIDIRECTIONAL);
+ free_pages((unsigned long)vaddr, get_order(size));
+}
+
static int no_agp;
static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size)
@@ -691,7 +709,6 @@ extern int agp_amd64_init(void);
static struct dma_mapping_ops gart_dma_ops = {
.map_single = gart_map_single,
- .map_simple = gart_map_simple,
.unmap_single = gart_unmap_single,
.sync_single_for_cpu = NULL,
.sync_single_for_device = NULL,
@@ -701,6 +718,8 @@ static struct dma_mapping_ops gart_dma_ops = {
.sync_sg_for_device = NULL,
.map_sg = gart_map_sg,
.unmap_sg = gart_unmap_sg,
+ .alloc_coherent = gart_alloc_coherent,
+ .free_coherent = gart_free_coherent,
};
void gart_iommu_shutdown(void)
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 3f91f71cdc3..1c1c98a31d5 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -14,7 +14,7 @@
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 && !is_buffer_dma_capable(*hwdev->dma_mask, bus, size)) {
if (*hwdev->dma_mask >= DMA_32BIT_MASK)
printk(KERN_ERR
"nommu_%s: overflow %Lx+%zu of device mask %Lx\n",
@@ -72,7 +72,52 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
return nents;
}
+static void *
+nommu_alloc_coherent(struct device *hwdev, size_t size,
+ dma_addr_t *dma_addr, gfp_t gfp)
+{
+ unsigned long dma_mask;
+ int node;
+ struct page *page;
+ dma_addr_t addr;
+
+ dma_mask = dma_alloc_coherent_mask(hwdev, gfp);
+
+ gfp |= __GFP_ZERO;
+
+ node = dev_to_node(hwdev);
+again:
+ page = alloc_pages_node(node, gfp, get_order(size));
+ if (!page)
+ return NULL;
+
+ addr = page_to_phys(page);
+ if (!is_buffer_dma_capable(dma_mask, addr, size) && !(gfp & GFP_DMA)) {
+ free_pages((unsigned long)page_address(page), get_order(size));
+ gfp |= GFP_DMA;
+ goto again;
+ }
+
+ if (check_addr("alloc_coherent", hwdev, addr, size)) {
+ *dma_addr = addr;
+ flush_write_buffers();
+ return page_address(page);
+ }
+
+ free_pages((unsigned long)page_address(page), get_order(size));
+
+ return NULL;
+}
+
+static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_addr)
+{
+ free_pages((unsigned long)vaddr, get_order(size));
+}
+
struct dma_mapping_ops nommu_dma_ops = {
+ .alloc_coherent = nommu_alloc_coherent,
+ .free_coherent = nommu_free_coherent,
.map_single = nommu_map_single,
.map_sg = nommu_map_sg,
.is_phys = 1,
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index c3edcdc08e7..6c4c1c3c50e 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -80,7 +80,7 @@ static long list_size;
static void domain_remove_dev_info(struct dmar_domain *domain);
-static int dmar_disabled;
+int dmar_disabled;
static int __initdata dmar_map_gfx = 1;
static int dmar_forcedac;
static int intel_iommu_strict;
diff --git a/include/asm-x86/dma-mapping.h b/include/asm-x86/dma-mapping.h
index ad9cd6d49bf..f408e6dd177 100644
--- a/include/asm-x86/dma-mapping.h
+++ b/include/asm-x86/dma-mapping.h
@@ -9,12 +9,12 @@
#include <linux/scatterlist.h>
#include <asm/io.h>
#include <asm/swiotlb.h>
+#include <asm-generic/dma-coherent.h>
extern dma_addr_t bad_dma_address;
extern int iommu_merge;
-extern struct device fallback_dev;
+extern struct device x86_dma_fallback_dev;
extern int panic_on_overflow;
-extern int force_iommu;
struct dma_mapping_ops {
int (*mapping_error)(struct device *dev,
@@ -25,9 +25,6 @@ struct dma_mapping_ops {
void *vaddr, dma_addr_t dma_handle);
dma_addr_t (*map_single)(struct device *hwdev, phys_addr_t ptr,
size_t size, int direction);
- /* like map_single, but doesn't check the device mask */
- dma_addr_t (*map_simple)(struct device *hwdev, phys_addr_t ptr,
- size_t size, int direction);
void (*unmap_single)(struct device *dev, dma_addr_t addr,
size_t size, int direction);
void (*sync_single_for_cpu)(struct device *hwdev,
@@ -87,13 +84,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag);
-
-void dma_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle);
-
+#define dma_is_consistent(d, h) (1)
extern int dma_supported(struct device *hwdev, u64 mask);
extern int dma_set_mask(struct device *dev, u64 mask);
@@ -247,7 +238,68 @@ static inline int dma_get_cache_alignment(void)
return boot_cpu_data.x86_clflush_size;
}
-#define dma_is_consistent(d, h) (1)
+static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
+ gfp_t gfp)
+{
+ unsigned long dma_mask = 0;
+
+ dma_mask = dev->coherent_dma_mask;
+ if (!dma_mask)
+ dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK;
+
+ return dma_mask;
+}
+
+static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
+{
+#ifdef CONFIG_X86_64
+ unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp);
+
+ if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
+ gfp |= GFP_DMA32;
+#endif
+ return gfp;
+}
+
+static inline 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;
+
+ gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+
+ if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
+ return memory;
+
+ if (!dev) {
+ dev = &x86_dma_fallback_dev;
+ gfp |= GFP_DMA;
+ }
+
+ if (!is_device_dma_capable(dev))
+ return NULL;
+
+ if (!ops->alloc_coherent)
+ return NULL;
+
+ return ops->alloc_coherent(dev, size, dma_handle,
+ dma_alloc_coherent_gfp_flags(dev, gfp));
+}
+
+static inline 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);
+
+ WARN_ON(irqs_disabled()); /* for portability */
+
+ if (dma_release_from_coherent(dev, get_order(size), vaddr))
+ return;
+
+ if (ops->free_coherent)
+ ops->free_coherent(dev, size, vaddr, bus);
+}
-#include <asm-generic/dma-coherent.h>
#endif
diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h
index 5f888cc5be4..621a1af94c4 100644
--- a/include/asm-x86/iommu.h
+++ b/include/asm-x86/iommu.h
@@ -6,6 +6,7 @@ extern void no_iommu_init(void);
extern struct dma_mapping_ops nommu_dma_ops;
extern int force_iommu, no_iommu;
extern int iommu_detected;
+extern int dmar_disabled;
extern unsigned long iommu_num_pages(unsigned long addr, unsigned long len);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 952e0f857ac..6ed50c1642f 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -48,6 +48,11 @@ static inline int is_device_dma_capable(struct device *dev)
return dev->dma_mask != NULL && *dev->dma_mask != DMA_MASK_NONE;
}
+static inline int is_buffer_dma_capable(u64 mask, dma_addr_t addr, size_t size)
+{
+ return addr + size <= mask;
+}
+
#ifdef CONFIG_HAS_DMA
#include <asm/dma-mapping.h>
#else
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index f1624b39675..2886b0eb53e 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -497,6 +497,11 @@
#define PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP 0x1101
#define PCI_DEVICE_ID_AMD_K8_NB_MEMCTL 0x1102
#define PCI_DEVICE_ID_AMD_K8_NB_MISC 0x1103
+#define PCI_DEVICE_ID_AMD_11H_NB_HT 0x1300
+#define PCI_DEVICE_ID_AMD_11H_NB_MAP 0x1301
+#define PCI_DEVICE_ID_AMD_11H_NB_DRAM 0x1302
+#define PCI_DEVICE_ID_AMD_11H_NB_MISC 0x1303
+#define PCI_DEVICE_ID_AMD_11H_NB_LINK 0x1304
#define PCI_DEVICE_ID_AMD_LANCE 0x2000
#define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001
#define PCI_DEVICE_ID_AMD_SCSI 0x2020
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
index c1d4d5b4c61..f013a0c2e11 100644
--- a/kernel/dma-coherent.c
+++ b/kernel/dma-coherent.c
@@ -124,6 +124,7 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
}
return (mem != NULL);
}
+EXPORT_SYMBOL(dma_alloc_from_coherent);
/**
* dma_release_from_coherent() - try to free the memory allocated from per-device coherent memory pool
@@ -151,3 +152,4 @@ int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
}
return 0;
}
+EXPORT_SYMBOL(dma_release_from_coherent);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 8826fdf0f18..240a67c2c97 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -274,13 +274,18 @@ cleanup1:
}
static int
-address_needs_mapping(struct device *hwdev, dma_addr_t addr)
+address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
{
dma_addr_t mask = 0xffffffff;
/* If the device has a mask, use it, otherwise default to 32 bits */
if (hwdev && hwdev->dma_mask)
mask = *hwdev->dma_mask;
- return (addr & ~mask) != 0;
+ return !is_buffer_dma_capable(mask, addr, size);
+}
+
+static int is_swiotlb_buffer(char *addr)
+{
+ return addr >= io_tlb_start && addr < io_tlb_end;
}
/*
@@ -467,15 +472,8 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
void *ret;
int order = get_order(size);
- /*
- * XXX fix me: the DMA API should pass us an explicit DMA mask
- * instead, or use ZONE_DMA32 (ia64 overloads ZONE_DMA to be a ~32
- * bit range instead of a 16MB one).
- */
- flags |= GFP_DMA;
-
ret = (void *)__get_free_pages(flags, order);
- if (ret && address_needs_mapping(hwdev, virt_to_bus(ret))) {
+ if (ret && address_needs_mapping(hwdev, virt_to_bus(ret), size)) {
/*
* The allocated memory isn't reachable by the device.
* Fall back on swiotlb_map_single().
@@ -490,19 +488,16 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
* swiotlb_map_single(), which will grab memory from
* the lowest available address range.
*/
- dma_addr_t handle;
- handle = swiotlb_map_single(hwdev, NULL, size, DMA_FROM_DEVICE);
- if (swiotlb_dma_mapping_error(hwdev, handle))
+ ret = map_single(hwdev, NULL, size, DMA_FROM_DEVICE);
+ if (!ret)
return NULL;
-
- ret = bus_to_virt(handle);
}
memset(ret, 0, size);
dev_addr = virt_to_bus(ret);
/* Confirm address can be DMA'd by device */
- if (address_needs_mapping(hwdev, dev_addr)) {
+ if (address_needs_mapping(hwdev, dev_addr, size)) {
printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
(unsigned long long)*hwdev->dma_mask,
(unsigned long long)dev_addr);
@@ -518,12 +513,11 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
dma_addr_t dma_handle)
{
WARN_ON(irqs_disabled());
- if (!(vaddr >= (void *)io_tlb_start
- && vaddr < (void *)io_tlb_end))
+ if (!is_swiotlb_buffer(vaddr))
free_pages((unsigned long) vaddr, get_order(size));
else
/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
- swiotlb_unmap_single (hwdev, dma_handle, size, DMA_TO_DEVICE);
+ unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
}
static void
@@ -567,7 +561,7 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
* we can safely return the device addr and not worry about bounce
* buffering it.
*/
- if (!address_needs_mapping(hwdev, dev_addr) && !swiotlb_force)
+ if (!address_needs_mapping(hwdev, dev_addr, size) && !swiotlb_force)
return dev_addr;
/*
@@ -584,7 +578,7 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
/*
* Ensure that the address returned is DMA'ble
*/
- if (address_needs_mapping(hwdev, dev_addr))
+ if (address_needs_mapping(hwdev, dev_addr, size))
panic("map_single: bounce buffer is not DMA'ble");
return dev_addr;
@@ -612,7 +606,7 @@ swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t dev_addr,
char *dma_addr = bus_to_virt(dev_addr);
BUG_ON(dir == DMA_NONE);
- if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
+ if (is_swiotlb_buffer(dma_addr))
unmap_single(hwdev, dma_addr, size, dir);
else if (dir == DMA_FROM_DEVICE)
dma_mark_clean(dma_addr, size);
@@ -642,7 +636,7 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
char *dma_addr = bus_to_virt(dev_addr);
BUG_ON(dir == DMA_NONE);
- if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
+ if (is_swiotlb_buffer(dma_addr))
sync_single(hwdev, dma_addr, size, dir, target);
else if (dir == DMA_FROM_DEVICE)
dma_mark_clean(dma_addr, size);
@@ -673,7 +667,7 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
char *dma_addr = bus_to_virt(dev_addr) + offset;
BUG_ON(dir == DMA_NONE);
- if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
+ if (is_swiotlb_buffer(dma_addr))
sync_single(hwdev, dma_addr, size, dir, target);
else if (dir == DMA_FROM_DEVICE)
dma_mark_clean(dma_addr, size);
@@ -727,7 +721,8 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
for_each_sg(sgl, sg, nelems, i) {
addr = SG_ENT_VIRT_ADDRESS(sg);
dev_addr = virt_to_bus(addr);
- if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) {
+ if (swiotlb_force ||
+ address_needs_mapping(hwdev, dev_addr, sg->length)) {
void *map = map_single(hwdev, addr, sg->length, dir);
if (!map) {
/* Don't panic here, we expect map_sg users
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-15 04:28:48 +0000