linux/arch/x86/kernel/pci-dma.c

278 lines
6.7 KiB
C
Raw Normal View History

#include <linux/dma-mapping.h>
#include <linux/dma-debug.h>
#include <linux/dmar.h>
#include <linux/export.h>
#include <linux/bootmem.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#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;
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 65536
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;
unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
dma_addr_t addr;
dma_mask = dma_alloc_coherent_mask(dev, flag);
flag |= __GFP_ZERO;
again:
page = NULL;
if (!(flag & GFP_ATOMIC))
page = dma_alloc_from_contiguous(dev, count, get_order(size));
if (!page)
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);
}
void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_addr, struct dma_attrs *attrs)
{
unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
struct page *page = virt_to_page(vaddr);
if (!dma_release_from_contiguous(dev, page, count))
free_pages((unsigned long)vaddr, get_order(size));
}
/*
* 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;
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);
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 02:44:49 +00:00
#ifdef CONFIG_PCI
if (mask > 0xffffffff && forbid_dac > 0) {
dev_info(dev, "PCI: Disallowing DAC for device\n");
return 0;
}
#endif
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 02:44:49 +00:00
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();
}
x86: Handle HW IOMMU initialization failure gracefully If HW IOMMU initialization fails (Intel VT-d often does this, typically due to BIOS bugs), we fall back to nommu. It doesn't work for the majority since nowadays we have more than 4GB memory so we must use swiotlb instead of nommu. The problem is that it's too late to initialize swiotlb when HW IOMMU initialization fails. We need to allocate swiotlb memory earlier from bootmem allocator. Chris explained the issue in detail: http://marc.info/?l=linux-kernel&m=125657444317079&w=2 The current x86 IOMMU initialization sequence is too complicated and handling the above issue makes it more hacky. This patch changes x86 IOMMU initialization sequence to handle the above issue cleanly. The new x86 IOMMU initialization sequence are: 1. we initialize the swiotlb (and setting swiotlb to 1) in the case of (max_pfn > MAX_DMA32_PFN && !no_iommu). dma_ops is set to swiotlb_dma_ops or nommu_dma_ops. if swiotlb usage is forced by the boot option, we finish here. 2. we call the detection functions of all the IOMMUs 3. the detection function sets x86_init.iommu.iommu_init to the IOMMU initialization function (so we can avoid calling the initialization functions of all the IOMMUs needlessly). 4. if the IOMMU initialization function doesn't need to swiotlb then sets swiotlb to zero (e.g. the initialization is sucessful). 5. if we find that swiotlb is set to zero, we free swiotlb resource. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: chrisw@sous-sol.org Cc: dwmw2@infradead.org Cc: joerg.roedel@amd.com Cc: muli@il.ibm.com LKML-Reference: <1257849980-22640-10-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-10 10:46:20 +00:00
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 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