linux/include/asm-m68k
FUJITA Tomonori 8d8bb39b9e 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 12:00:03 -07:00
..
a.out-core.h aout: suppress A.OUT library support if !CONFIG_ARCH_SUPPORTS_AOUT 2008-02-08 09:22:30 -08:00
a.out.h aout: move STACK_TOP[_MAX] to asm/processor.h 2008-02-08 09:22:29 -08:00
adb_iop.h
amigahw.h m68k/amiga/: possible cleanups 2008-07-20 17:24:39 -07:00
amigaints.h m68k/amiga/: possible cleanups 2008-07-20 17:24:39 -07:00
amigayle.h
amipcmcia.h
apollodma.h m68k: remove CVS keywords 2008-07-20 17:24:38 -07:00
apollohw.h
atafd.h
atafdreg.h
atari_joystick.h
atari_stdma.h
atari_stram.h
atarihw.h
atariints.h
atarikb.h
atomic.h
auxvec.h
bitops.h m68k: Add ext2_find_{first,next}_bit() for ext4 2008-06-12 18:05:39 -07:00
blinken.h
bootinfo.h
bug.h m68k: Make gcc aware that BUG() does not return 2008-05-18 13:28:48 -07:00
bugs.h
bvme6000hw.h
byteorder.h
cache.h
cachectl.h
cacheflush.h
checksum.h
contregs.h
cputime.h
current.h
delay.h
device.h
div64.h rename div64_64 to div64_u64 2008-05-01 08:03:58 -07:00
dma-mapping.h dma-mapping: add the device argument to dma_mapping_error() 2008-07-26 12:00:03 -07:00
dma.h
dsp56k.h
dvma.h PAGE_ALIGN(): correctly handle 64-bit values on 32-bit architectures 2008-07-24 10:47:21 -07:00
elf.h Cleanup asm/{elf,page,user}.h: #ifdef __KERNEL__ is no longer needed 2008-02-07 08:42:30 -08:00
emergency-restart.h
entry.h
errno.h
fb.h
fbio.h
fcntl.h
floppy.h
fpu.h m68k: Allow no CPU/platform type for allnoconfig 2008-07-20 17:24:38 -07:00
futex.h
hardirq.h
hp300hw.h
hw_irq.h
hwtest.h
ide.h ide: define MAX_HWIFS in <linux/ide.h> 2008-07-24 22:53:30 +02:00
idprom.h
intersil.h
io.h m68k: Prefix ISA type with ISA_TYPE_ 2008-05-18 13:28:50 -07:00
ioctl.h
ioctls.h
ipcbuf.h
irq_regs.h
irq.h m68k: Allow no CPU/platform type for allnoconfig 2008-07-20 17:24:38 -07:00
Kbuild
kdebug.h
kmap_types.h
linkage.h
local.h
mac_asc.h
mac_baboon.h m68k/mac/: possible cleanups 2008-07-20 17:24:39 -07:00
mac_iop.h
mac_mouse.h
mac_oss.h
mac_psc.h
mac_via.h m68k/mac/: possible cleanups 2008-07-20 17:24:39 -07:00
machdep.h
machines.h m68k/sun3/: possible cleanups 2008-07-20 17:24:39 -07:00
machw.h m68k: remove old mac_esp cruft 2008-05-05 12:38:50 -07:00
macintosh.h m68k/mac/: possible cleanups 2008-07-20 17:24:39 -07:00
macints.h
math-emu.h
mc146818rtc.h
md.h m68k: remove CVS keywords 2008-07-20 17:24:38 -07:00
mman.h
mmu_context.h
mmu.h
mmzone.h
module.h
motorola_pgalloc.h CONFIG_HIGHPTE vs. sub-page page tables. 2008-02-08 09:22:42 -08:00
motorola_pgtable.h mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
movs.h
msgbuf.h
mutex.h
mvme16xhw.h
mvme147hw.h
namei.h
nubus.h
openprom.h m68k: remove CVS keywords 2008-07-20 17:24:38 -07:00
oplib.h m68k: remove AP1000 code 2008-07-20 17:24:38 -07:00
page_offset.h
page.h PAGE_ALIGN(): correctly handle 64-bit values on 32-bit architectures 2008-07-24 10:47:21 -07:00
param.h avoid overflows in kernel/time.c 2008-02-08 09:22:39 -08:00
parport.h
pci.h
percpu.h
pgalloc.h
pgtable.h cleanup after APUS removal 2008-02-06 10:41:01 -08:00
poll.h
posix_types.h asm-*/posix_types.h: scrub __GLIBC__ 2008-02-08 09:22:34 -08:00
processor.h aout: move STACK_TOP[_MAX] to asm/processor.h 2008-02-08 09:22:29 -08:00
ptrace.h
q40_master.h
q40ints.h
raw_io.h
resource.h
rtc.h
sbus.h m68k: remove stale ARCH_SUN4 #define 2008-07-20 17:24:39 -07:00
scatterlist.h Add CONFIG_DEBUG_SG sg validation 2007-10-22 21:20:03 +02:00
sections.h
segment.h
sembuf.h
serial.h
setup.h m68k: export m68k_mmutype 2008-05-18 13:28:50 -07:00
shm.h
shmbuf.h
shmparam.h
sigcontext.h
siginfo.h
signal.h
socket.h [NET]: Introducing socket mark socket option. 2008-01-31 19:27:19 -08:00
sockios.h
spinlock.h
stat.h
statfs.h
string.h
sun3_pgalloc.h CONFIG_HIGHPTE vs. sub-page page tables. 2008-02-08 09:22:42 -08:00
sun3_pgtable.h mm: introduce pte_special pte bit 2008-04-28 08:58:23 -07:00
sun3-head.h m68k: remove CVS keywords 2008-07-20 17:24:38 -07:00
sun3ints.h
sun3mmu.h
sun3x.h
sun3xflop.h
sun3xprom.h
suspend.h
system.h Add cmpxchg_local to m86k 2008-02-07 08:42:32 -08:00
termbits.h
termios.h
thread_info.h clean up duplicated alloc/free_thread_info 2008-07-25 10:53:28 -07:00
timex.h
tlb.h
tlbflush.h m68k: Allow no CPU/platform type for allnoconfig 2008-07-20 17:24:38 -07:00
topology.h
traps.h
types.h m68k: types: use <asm-generic/int-*.h> for the m68k architecture 2008-05-02 16:18:28 -07:00
uaccess.h m68k: Convert access_ok() to an inline function 2008-05-18 13:28:48 -07:00
ucontext.h
unaligned.h kernel: Move arches to use common unaligned access 2008-04-29 08:06:27 -07:00
unistd.h m68k{,nommu}: Wire up new timerfd syscalls 2008-03-04 08:04:11 -08:00
user.h Sanitize the type of struct user.u_ar0 2008-02-07 08:42:30 -08:00
virtconvert.h
xor.h
zorro.h