Skip to content

Commit

Permalink
Merge branch 'iommu-for-linus' of git://git.kernel.org/pub/scm/linux/…
Browse files Browse the repository at this point in the history 
…kernel/git/tip/linux-2.6-tip

* 'iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (60 commits)
  dma-debug: make memory range checks more consistent
  dma-debug: warn of unmapping an invalid dma address
  dma-debug: fix dma_debug_add_bus() definition for !CONFIG_DMA_API_DEBUG
  dma-debug/x86: register pci bus for dma-debug leak detection
  dma-debug: add a check dma memory leaks
  dma-debug: add checks for kernel text and rodata
  dma-debug: print stacktrace of mapping path on unmap error
  dma-debug: Documentation update
  dma-debug: x86 architecture bindings
  dma-debug: add function to dump dma mappings
  dma-debug: add checks for sync_single_sg_*
  dma-debug: add checks for sync_single_range_*
  dma-debug: add checks for sync_single_*
  dma-debug: add checking for [alloc|free]_coherent
  dma-debug: add add checking for map/unmap_sg
  dma-debug: add checking for map/unmap_page/single
  dma-debug: add core checking functions
  dma-debug: add debugfs interface
  dma-debug: add kernel command line parameters
  dma-debug: add initialization code
  ...

Fix trivial conflicts due to whitespace changes in arch/x86/kernel/pci-nommu.c
  • Loading branch information
@torvalds
torvalds committed Mar 30, 2009
2 parents e1c5024 + b0d44c0 commit 712b000
Show file tree
Hide file tree
Showing 40 changed files with 1,899 additions and 844 deletions.
106 changes: 106 additions & 0 deletions Documentation/DMA-API.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -609,3 +609,109 @@ size is the size (and should be a page-sized multiple).
The return value will be either a pointer to the processor virtual
address of the memory, or an error (via PTR_ERR()) if any part of the
region is occupied.

Part III - Debug drivers use of the DMA-API
-------------------------------------------

The DMA-API as described above as some constraints. DMA addresses must be
released with the corresponding function with the same size for example. With
the advent of hardware IOMMUs it becomes more and more important that drivers
do not violate those constraints. In the worst case such a violation can
result in data corruption up to destroyed filesystems.

To debug drivers and find bugs in the usage of the DMA-API checking code can
be compiled into the kernel which will tell the developer about those
violations. If your architecture supports it you can select the "Enable
debugging of DMA-API usage" option in your kernel configuration. Enabling this
option has a performance impact. Do not enable it in production kernels.

If you boot the resulting kernel will contain code which does some bookkeeping
about what DMA memory was allocated for which device. If this code detects an
error it prints a warning message with some details into your kernel log. An
example warning message may look like this:

------------[ cut here ]------------
WARNING: at /data2/repos/linux-2.6-iommu/lib/dma-debug.c:448
check_unmap+0x203/0x490()
Hardware name:
forcedeth 0000:00:08.0: DMA-API: device driver frees DMA memory with wrong
function [device address=0x00000000640444be] [size=66 bytes] [mapped as
single] [unmapped as page]
Modules linked in: nfsd exportfs bridge stp llc r8169
Pid: 0, comm: swapper Tainted: G W 2.6.28-dmatest-09289-g8bb99c0 #1
Call Trace:
<IRQ> [<ffffffff80240b22>] warn_slowpath+0xf2/0x130
[<ffffffff80647b70>] _spin_unlock+0x10/0x30
[<ffffffff80537e75>] usb_hcd_link_urb_to_ep+0x75/0xc0
[<ffffffff80647c22>] _spin_unlock_irqrestore+0x12/0x40
[<ffffffff8055347f>] ohci_urb_enqueue+0x19f/0x7c0
[<ffffffff80252f96>] queue_work+0x56/0x60
[<ffffffff80237e10>] enqueue_task_fair+0x20/0x50
[<ffffffff80539279>] usb_hcd_submit_urb+0x379/0xbc0
[<ffffffff803b78c3>] cpumask_next_and+0x23/0x40
[<ffffffff80235177>] find_busiest_group+0x207/0x8a0
[<ffffffff8064784f>] _spin_lock_irqsave+0x1f/0x50
[<ffffffff803c7ea3>] check_unmap+0x203/0x490
[<ffffffff803c8259>] debug_dma_unmap_page+0x49/0x50
[<ffffffff80485f26>] nv_tx_done_optimized+0xc6/0x2c0
[<ffffffff80486c13>] nv_nic_irq_optimized+0x73/0x2b0
[<ffffffff8026df84>] handle_IRQ_event+0x34/0x70
[<ffffffff8026ffe9>] handle_edge_irq+0xc9/0x150
[<ffffffff8020e3ab>] do_IRQ+0xcb/0x1c0
[<ffffffff8020c093>] ret_from_intr+0x0/0xa
<EOI> <4>---[ end trace f6435a98e2a38c0e ]---

The driver developer can find the driver and the device including a stacktrace
of the DMA-API call which caused this warning.

Per default only the first error will result in a warning message. All other
errors will only silently counted. This limitation exist to prevent the code
from flooding your kernel log. To support debugging a device driver this can
be disabled via debugfs. See the debugfs interface documentation below for
details.

The debugfs directory for the DMA-API debugging code is called dma-api/. In
this directory the following files can currently be found:

dma-api/all_errors This file contains a numeric value. If this
value is not equal to zero the debugging code
will print a warning for every error it finds
into the kernel log. Be carefull with this
option. It can easily flood your logs.

dma-api/disabled This read-only file contains the character 'Y'
if the debugging code is disabled. This can
happen when it runs out of memory or if it was
disabled at boot time

dma-api/error_count This file is read-only and shows the total
numbers of errors found.

dma-api/num_errors The number in this file shows how many
warnings will be printed to the kernel log
before it stops. This number is initialized to
one at system boot and be set by writing into
this file

dma-api/min_free_entries
This read-only file can be read to get the
minimum number of free dma_debug_entries the
allocator has ever seen. If this value goes
down to zero the code will disable itself
because it is not longer reliable.

dma-api/num_free_entries
The current number of free dma_debug_entries
in the allocator.

If you have this code compiled into your kernel it will be enabled by default.
If you want to boot without the bookkeeping anyway you can provide
'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
Notice that you can not enable it again at runtime. You have to reboot to do
so.

When the code disables itself at runtime this is most likely because it ran
out of dma_debug_entries. These entries are preallocated at boot. The number
of preallocated entries is defined per architecture. If it is too low for you
boot with 'dma_debug_entries=<your_desired_number>' to overwrite the
architectural default.
10 changes: 10 additions & 0 deletions Documentation/kernel-parameters.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -492,6 +492,16 @@ and is between 256 and 4096 characters. It is defined in the file
Range: 0 - 8192
Default: 64

dma_debug=off If the kernel is compiled with DMA_API_DEBUG support
this option disables the debugging code at boot.

dma_debug_entries=<number>
This option allows to tune the number of preallocated
entries for DMA-API debugging code. One entry is
required per DMA-API allocation. Use this if the
DMA-API debugging code disables itself because the
architectural default is too low.

hpet= [X86-32,HPET] option to control HPET usage
Format: { enable (default) | disable | force |
verbose }
Expand Down
2 changes: 2 additions & 0 deletions arch/Kconfig
View file
Original file line number Diff line number Diff line change
Expand Up @@ -106,3 +106,5 @@ config HAVE_CLK
The <linux/clk.h> calls support software clock gating and
thus are a key power management tool on many systems.

config HAVE_DMA_API_DEBUG
bool
4 changes: 2 additions & 2 deletions arch/ia64/dig/Makefile
View file
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,8 @@

obj-y := setup.o
ifeq ($(CONFIG_DMAR), y)
obj-$(CONFIG_IA64_GENERIC) += machvec.o machvec_vtd.o dig_vtd_iommu.o
obj-$(CONFIG_IA64_GENERIC) += machvec.o machvec_vtd.o
else
obj-$(CONFIG_IA64_GENERIC) += machvec.o
endif
obj-$(CONFIG_IA64_DIG_VTD) += dig_vtd_iommu.o

59 changes: 0 additions & 59 deletions arch/ia64/dig/dig_vtd_iommu.c
View file

This file was deleted.

165 changes: 14 additions & 151 deletions arch/ia64/hp/common/hwsw_iommu.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -13,49 +13,34 @@
*/

#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/swiotlb.h>

#include <asm/machvec.h>

extern struct dma_map_ops sba_dma_ops, swiotlb_dma_ops;

/* swiotlb declarations & definitions: */
extern int swiotlb_late_init_with_default_size (size_t size);

/* hwiommu declarations & definitions: */

extern ia64_mv_dma_alloc_coherent sba_alloc_coherent;
extern ia64_mv_dma_free_coherent sba_free_coherent;
extern ia64_mv_dma_map_single_attrs sba_map_single_attrs;
extern ia64_mv_dma_unmap_single_attrs sba_unmap_single_attrs;
extern ia64_mv_dma_map_sg_attrs sba_map_sg_attrs;
extern ia64_mv_dma_unmap_sg_attrs sba_unmap_sg_attrs;
extern ia64_mv_dma_supported sba_dma_supported;
extern ia64_mv_dma_mapping_error sba_dma_mapping_error;

#define hwiommu_alloc_coherent sba_alloc_coherent
#define hwiommu_free_coherent sba_free_coherent
#define hwiommu_map_single_attrs sba_map_single_attrs
#define hwiommu_unmap_single_attrs sba_unmap_single_attrs
#define hwiommu_map_sg_attrs sba_map_sg_attrs
#define hwiommu_unmap_sg_attrs sba_unmap_sg_attrs
#define hwiommu_dma_supported sba_dma_supported
#define hwiommu_dma_mapping_error sba_dma_mapping_error
#define hwiommu_sync_single_for_cpu machvec_dma_sync_single
#define hwiommu_sync_sg_for_cpu machvec_dma_sync_sg
#define hwiommu_sync_single_for_device machvec_dma_sync_single
#define hwiommu_sync_sg_for_device machvec_dma_sync_sg


/*
* Note: we need to make the determination of whether or not to use
* the sw I/O TLB based purely on the device structure. Anything else
* would be unreliable or would be too intrusive.
*/
static inline int
use_swiotlb (struct device *dev)
static inline int use_swiotlb(struct device *dev)
{
return dev && dev->dma_mask && !hwiommu_dma_supported(dev, *dev->dma_mask);
return dev && dev->dma_mask &&
!sba_dma_ops.dma_supported(dev, *dev->dma_mask);
}

struct dma_map_ops *hwsw_dma_get_ops(struct device *dev)
{
if (use_swiotlb(dev))
return &swiotlb_dma_ops;
return &sba_dma_ops;
}
EXPORT_SYMBOL(hwsw_dma_get_ops);

void __init
hwsw_init (void)
{
Expand All @@ -71,125 +56,3 @@ hwsw_init (void)
#endif
}
}

void *
hwsw_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags)
{
if (use_swiotlb(dev))
return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
else
return hwiommu_alloc_coherent(dev, size, dma_handle, flags);
}

void
hwsw_free_coherent (struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle)
{
if (use_swiotlb(dev))
swiotlb_free_coherent(dev, size, vaddr, dma_handle);
else
hwiommu_free_coherent(dev, size, vaddr, dma_handle);
}

dma_addr_t
hwsw_map_single_attrs(struct device *dev, void *addr, size_t size, int dir,
struct dma_attrs *attrs)
{
if (use_swiotlb(dev))
return swiotlb_map_single_attrs(dev, addr, size, dir, attrs);
else
return hwiommu_map_single_attrs(dev, addr, size, dir, attrs);
}
EXPORT_SYMBOL(hwsw_map_single_attrs);

void
hwsw_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
int dir, struct dma_attrs *attrs)
{
if (use_swiotlb(dev))
return swiotlb_unmap_single_attrs(dev, iova, size, dir, attrs);
else
return hwiommu_unmap_single_attrs(dev, iova, size, dir, attrs);
}
EXPORT_SYMBOL(hwsw_unmap_single_attrs);

int
hwsw_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents,
int dir, struct dma_attrs *attrs)
{
if (use_swiotlb(dev))
return swiotlb_map_sg_attrs(dev, sglist, nents, dir, attrs);
else
return hwiommu_map_sg_attrs(dev, sglist, nents, dir, attrs);
}
EXPORT_SYMBOL(hwsw_map_sg_attrs);

void
hwsw_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents,
int dir, struct dma_attrs *attrs)
{
if (use_swiotlb(dev))
return swiotlb_unmap_sg_attrs(dev, sglist, nents, dir, attrs);
else
return hwiommu_unmap_sg_attrs(dev, sglist, nents, dir, attrs);
}
EXPORT_SYMBOL(hwsw_unmap_sg_attrs);

void
hwsw_sync_single_for_cpu (struct device *dev, dma_addr_t addr, size_t size, int dir)
{
if (use_swiotlb(dev))
swiotlb_sync_single_for_cpu(dev, addr, size, dir);
else
hwiommu_sync_single_for_cpu(dev, addr, size, dir);
}

void
hwsw_sync_sg_for_cpu (struct device *dev, struct scatterlist *sg, int nelems, int dir)
{
if (use_swiotlb(dev))
swiotlb_sync_sg_for_cpu(dev, sg, nelems, dir);
else
hwiommu_sync_sg_for_cpu(dev, sg, nelems, dir);
}

void
hwsw_sync_single_for_device (struct device *dev, dma_addr_t addr, size_t size, int dir)
{
if (use_swiotlb(dev))
swiotlb_sync_single_for_device(dev, addr, size, dir);
else
hwiommu_sync_single_for_device(dev, addr, size, dir);
}

void
hwsw_sync_sg_for_device (struct device *dev, struct scatterlist *sg, int nelems, int dir)
{
if (use_swiotlb(dev))
swiotlb_sync_sg_for_device(dev, sg, nelems, dir);
else
hwiommu_sync_sg_for_device(dev, sg, nelems, dir);
}

int
hwsw_dma_supported (struct device *dev, u64 mask)
{
if (hwiommu_dma_supported(dev, mask))
return 1;
return swiotlb_dma_supported(dev, mask);
}

int
hwsw_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return hwiommu_dma_mapping_error(dev, dma_addr) ||
swiotlb_dma_mapping_error(dev, dma_addr);
}

EXPORT_SYMBOL(hwsw_dma_mapping_error);
EXPORT_SYMBOL(hwsw_dma_supported);
EXPORT_SYMBOL(hwsw_alloc_coherent);
EXPORT_SYMBOL(hwsw_free_coherent);
EXPORT_SYMBOL(hwsw_sync_single_for_cpu);
EXPORT_SYMBOL(hwsw_sync_single_for_device);
EXPORT_SYMBOL(hwsw_sync_sg_for_cpu);
EXPORT_SYMBOL(hwsw_sync_sg_for_device);
Loading

0 comments on commit 712b000

Please sign in to comment.