kernel_optimize_test/arch/x86/kernel/pci-dma.c
Linus Torvalds 58bca4a8fa Merge branch 'for-linus' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping
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 d15bd7ee44
  "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
2012-04-04 17:13:43 -07:00

274 lines
6.6 KiB
C

#include <linux/dma-mapping.h>
#include <linux/dma-debug.h>
#include <linux/dmar.h>
#include <linux/export.h>
#include <linux/bootmem.h>
#include <linux/gfp.h>
#include <linux/pci.h>
#include <linux/kmemleak.h>
#include <asm/proto.h>
#include <asm/dma.h>
#include <asm/iommu.h>
#include <asm/gart.h>
#include <asm/calgary.h>
#include <asm/x86_init.h>
#include <asm/iommu_table.h>
static int forbid_dac __read_mostly;
struct dma_map_ops *dma_ops = &nommu_dma_ops;
EXPORT_SYMBOL(dma_ops);
static int iommu_sac_force __read_mostly;
#ifdef CONFIG_IOMMU_DEBUG
int panic_on_overflow __read_mostly = 1;
int force_iommu __read_mostly = 1;
#else
int panic_on_overflow __read_mostly = 0;
int force_iommu __read_mostly = 0;
#endif
int iommu_merge __read_mostly = 0;
int no_iommu __read_mostly;
/* Set this to 1 if there is a HW IOMMU in the system */
int iommu_detected __read_mostly = 0;
/*
* This variable becomes 1 if iommu=pt is passed on the kernel command line.
* If this variable is 1, IOMMU implementations do no DMA translation for
* devices and allow every device to access to whole physical memory. This is
* useful if a user wants to use an IOMMU only for KVM device assignment to
* guests and not for driver dma translation.
*/
int iommu_pass_through __read_mostly;
/*
* Group multi-function PCI devices into a single device-group for the
* iommu_device_group interface. This tells the iommu driver to pretend
* it cannot distinguish between functions of a device, exposing only one
* group for the device. Useful for disallowing use of individual PCI
* functions from userspace drivers.
*/
int iommu_group_mf __read_mostly;
extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
/* Dummy device used for NULL arguments (normally ISA). */
struct device x86_dma_fallback_dev = {
.init_name = "fallback device",
.coherent_dma_mask = ISA_DMA_BIT_MASK,
.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
};
EXPORT_SYMBOL(x86_dma_fallback_dev);
/* Number of entries preallocated for DMA-API debugging */
#define PREALLOC_DMA_DEBUG_ENTRIES 32768
int dma_set_mask(struct device *dev, u64 mask)
{
if (!dev->dma_mask || !dma_supported(dev, mask))
return -EIO;
*dev->dma_mask = mask;
return 0;
}
EXPORT_SYMBOL(dma_set_mask);
void __init pci_iommu_alloc(void)
{
struct iommu_table_entry *p;
sort_iommu_table(__iommu_table, __iommu_table_end);
check_iommu_entries(__iommu_table, __iommu_table_end);
for (p = __iommu_table; p < __iommu_table_end; p++) {
if (p && p->detect && p->detect() > 0) {
p->flags |= IOMMU_DETECTED;
if (p->early_init)
p->early_init();
if (p->flags & IOMMU_FINISH_IF_DETECTED)
break;
}
}
}
void *dma_generic_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_addr, gfp_t flag,
struct dma_attrs *attrs)
{
unsigned long dma_mask;
struct page *page;
dma_addr_t addr;
dma_mask = dma_alloc_coherent_mask(dev, flag);
flag |= __GFP_ZERO;
again:
page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
if (!page)
return NULL;
addr = page_to_phys(page);
if (addr + size > dma_mask) {
__free_pages(page, get_order(size));
if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) {
flag = (flag & ~GFP_DMA32) | GFP_DMA;
goto again;
}
return NULL;
}
*dma_addr = addr;
return page_address(page);
}
/*
* See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
* parameter documentation.
*/
static __init int iommu_setup(char *p)
{
iommu_merge = 1;
if (!p)
return -EINVAL;
while (*p) {
if (!strncmp(p, "off", 3))
no_iommu = 1;
/* gart_parse_options has more force support */
if (!strncmp(p, "force", 5))
force_iommu = 1;
if (!strncmp(p, "noforce", 7)) {
iommu_merge = 0;
force_iommu = 0;
}
if (!strncmp(p, "biomerge", 8)) {
iommu_merge = 1;
force_iommu = 1;
}
if (!strncmp(p, "panic", 5))
panic_on_overflow = 1;
if (!strncmp(p, "nopanic", 7))
panic_on_overflow = 0;
if (!strncmp(p, "merge", 5)) {
iommu_merge = 1;
force_iommu = 1;
}
if (!strncmp(p, "nomerge", 7))
iommu_merge = 0;
if (!strncmp(p, "forcesac", 8))
iommu_sac_force = 1;
if (!strncmp(p, "allowdac", 8))
forbid_dac = 0;
if (!strncmp(p, "nodac", 5))
forbid_dac = 1;
if (!strncmp(p, "usedac", 6)) {
forbid_dac = -1;
return 1;
}
#ifdef CONFIG_SWIOTLB
if (!strncmp(p, "soft", 4))
swiotlb = 1;
#endif
if (!strncmp(p, "pt", 2))
iommu_pass_through = 1;
if (!strncmp(p, "group_mf", 8))
iommu_group_mf = 1;
gart_parse_options(p);
#ifdef CONFIG_CALGARY_IOMMU
if (!strncmp(p, "calgary", 7))
use_calgary = 1;
#endif /* CONFIG_CALGARY_IOMMU */
p += strcspn(p, ",");
if (*p == ',')
++p;
}
return 0;
}
early_param("iommu", iommu_setup);
int dma_supported(struct device *dev, u64 mask)
{
struct dma_map_ops *ops = get_dma_ops(dev);
#ifdef CONFIG_PCI
if (mask > 0xffffffff && forbid_dac > 0) {
dev_info(dev, "PCI: Disallowing DAC for device\n");
return 0;
}
#endif
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.
The caller just has to use GFP_DMA in this case. */
if (mask < DMA_BIT_MASK(24))
return 0;
/* Tell the device to use SAC when IOMMU force is on. This
allows the driver to use cheaper accesses in some cases.
Problem with this is that if we overflow the IOMMU area and
return DAC as fallback address the device may not handle it
correctly.
As a special case some controllers have a 39bit address
mode that is as efficient as 32bit (aic79xx). Don't force
SAC for these. Assume all masks <= 40 bits are of this
type. Normally this doesn't make any difference, but gives
more gentle handling of IOMMU overflow. */
if (iommu_sac_force && (mask >= DMA_BIT_MASK(40))) {
dev_info(dev, "Force SAC with mask %Lx\n", mask);
return 0;
}
return 1;
}
EXPORT_SYMBOL(dma_supported);
static int __init pci_iommu_init(void)
{
struct iommu_table_entry *p;
dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
#ifdef CONFIG_PCI
dma_debug_add_bus(&pci_bus_type);
#endif
x86_init.iommu.iommu_init();
for (p = __iommu_table; p < __iommu_table_end; p++) {
if (p && (p->flags & IOMMU_DETECTED) && p->late_init)
p->late_init();
}
return 0;
}
/* Must execute after PCI subsystem */
rootfs_initcall(pci_iommu_init);
#ifdef CONFIG_PCI
/* Many VIA bridges seem to corrupt data for DAC. Disable it here */
static __devinit void via_no_dac(struct pci_dev *dev)
{
if (forbid_dac == 0) {
dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n");
forbid_dac = 1;
}
}
DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID,
PCI_CLASS_BRIDGE_PCI, 8, via_no_dac);
#endif