This makes the hardware passthrough mode work a lot more like the
software version, so that the behaviour of a kernel with 'iommu=pt'
is the same whether the hardware supports passthrough or not.

In particular:
 - We use a single si_domain for the pass-through devices.
 - 32-bit devices can be taken out of the pass-through domain so that
   they don't have to use swiotlb.
 - Devices will work again after being removed from a KVM guest.
 - A potential oops on OOM (in init_context_pass_through()) is fixed.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

Yet another reason why trusting this stuff to the BIOS was a bad idea.
The HP DC7900 BIOS reports an iommu at an address which just returns all
ones, when VT-d is disabled in the BIOS.

Fix up the missing iounmap in the error paths while we're at it.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

This avoids a "Malformed early option 'iommu'" warning on boot when 
trying to use pass-through mode.
Signed-off-by: Alex Williamson <alex.williamson@hp.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

g_iommus is freed after we "goto error;".

Found by smatch (http://repo.or.cz/w/smatch.git).
Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

I see no reason why we did this _only_ in intel_unmap_page().
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

We only ever obtain this lock immediately before the iova_rbtree_lock,
and release it immediately after the iova_rbtree_lock. So ditch it and
just use iova_rbtree_lock.

[v2: Remove the lockdep bits this time too]
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

We did before, in the end -- but it was at the bottom of a long stack of
functions. Add an inline wrapper get_valid_domain_for_dev() which will
use the cached one _first_ and only make the out-of-line call if it's
not already set.

This takes the average time taken for a 1-page intel_map_sg() from 5961
cycles to 4812 cycles on my Lenovo x200s test box -- a modest 20%.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

* git://git.infradead.org/iommu-2.6:
  intel-iommu: Don't use identity mapping for PCI devices behind bridges
  intel-iommu: Use iommu_should_identity_map() at startup time too.
  intel-iommu: No mapping for non-PCI devices
  intel-iommu: Restore DMAR_BROKEN_GFX_WA option for broken graphics drivers
  intel-iommu: Add iommu_should_identity_map() function
  intel-iommu: Fix reattaching of devices to identity mapping domain
  intel-iommu: Don't set identity mapping for bypassed graphics devices
  intel-iommu: Fix dma vs. mm page confusion with aligned_nrpages()

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394-2.6:
  ieee1394: sbp2: add support for disks >2 TB (and 16 bytes long CDBs)
  firewire: sbp2: add support for disks >2 TB (and 16 bytes long CDBs)
  firewire: core: do not DMA-map stack addresses

This way they'll be properly initialized early enough for users that may
touch them before the framebuffer has been registered.

Drivers that allocate their fb_info structure some other way (like
matrocfb's broken static allocation) need to be fixed up appropriately.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

do_execve() and ptrace_attach() return -EINTR if
mutex_lock_interruptible(->cred_guard_mutex) fails.

This is not right, change the code to return ERESTARTNOINTR.

Perhaps we should also change proc_pid_attr_write().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Acked-by: Roland McGrath <roland@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

In include/linux/sysrq.h the constant EINVAL is being used but is undefined
if include/linux/errno.h is not included before.

Fix this by adding #include <linux/errno.h> at the beginning.
Signed-off-by: Tobias Doerffel <tobias.doerffel@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Correct the CLKVAL_F field value of VIDEO MAIN CONTROLLER 0 REGITSTER.

Frame Rate is 1 / [ { (VSPW+1) + (VBPD+1) + (LIINEVAL + 1) + (VFPD+1)
} x {(HSPW+1) + (HBPD +1)
+ (HFPD+1) + (HOZVAL + 1) } x { ( CLKVAL+1 ) / ( Frequency of Clock
source ) } ] and VCLK = Video Clock Source / (CLKVAL +1).

therefore CLKVAL_F should be "CLKVAL_F = Frequency of Clock source / pixel
clock * refresh".

for this, I added refresh value in platform data like below.

static struct s3c_fb_pd_win xxx_fb_win0 = {
	/* this is to ensure we use win0 */
	.win_mode = {
		.refresh	= 60,
		.pixclock	= (66+4+2+480)*(15+5+3+800),
		.left_margin	= 66,
		.right_margin	= 2,
		.upper_margin	= 15,
		.lower_margin	= 3,
		.hsync_len	= 4,
		.vsync_len	= 5,
		.xres		= 480,
		.yres		= 800,
	},
	.max_bpp	= 32,
	.default_bpp	= 24,
};

static struct s3c_fb_platdata xxx_lcd_pdata __initdata = {
	.win[0]		= &xxx_fb_win0,
	.vidcon0	= VIDCON0_VIDOUT_RGB | VIDCON0_PNRMODE_RGB,
	.vidcon1	= VIDCON1_INV_HSYNC | VIDCON1_INV_VSYNC
			| VIDCON1_INV_VCLK | VIDCON1_INV_VDEN,
	.setup_gpio	= s5pc1xx_fb_gpio_setup_24bpp,
};

xxx_machine_init()
{
                   .
                   .
                   .
               s3c_fb_set_platdata(&xxx_lcd_pdata);
}

platform data defined in machine code should be setting using
s3c_fb_set_platdata().
Signed-off-by: InKi Dae <inki.dae@samsung.com>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Krzysztof Helt <krzysztof.h1@poczta.fm>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

These warnings were observed on MIPS32 using 2.6.31-rc1 and gcc-4.2.0:

mm/page_alloc.c: In function 'alloc_pages_exact':
mm/page_alloc.c:1986: warning: passing argument 1 of 'virt_to_phys' makes pointer from integer without a cast

drivers/usb/mon/mon_bin.c: In function 'mon_alloc_buff':
drivers/usb/mon/mon_bin.c:1264: warning: passing argument 1 of 'virt_to_phys' makes pointer from integer without a cast

[akpm@linux-foundation.org: fix kernel/perf_counter.c too]
Signed-off-by: Kevin Cernekee <cernekee@gmail.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

In testing a backport of the write_begin/write_end AOPs, a 10% re-read
regression was noticed when running iozone.  This regression was
introduced because the old AOPs would always do a mark_page_accessed(page)
after the commit_write, but when the new AOPs where introduced, the only
place this was kept was in pagecache_write_end().

This patch does the same thing in the generic case as what is done in
pagecache_write_end(), which is just to mark the page accessed before we
do write_end().
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Acked-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Fix the multithread program core thread message error.

This issue affects arches with neither has CORE_DUMP_USE_REGSET nor
ELF_CORE_COPY_TASK_REGS, ARM is one of them.

The thread message of core file is generated in elf_dump_thread_status.
The register values is set by elf_core_copy_task_regs in this function.

If an arch doesn't define ELF_CORE_COPY_TASK_REGS,
elf_core_copy_task_regs() will do nothing.  Then the core file will not
have the register message of thread.

So add elf_core_copy_regs to set regiser values if ELF_CORE_COPY_TASK_REGS
doesn't define.

The following is how to reproduce this issue:

cat 1.c
#include <stdio.h>
#include <pthread.h>
#include <assert.h>

void td1(void * i)
{
       while (1)
       {
               printf ("1\n");
               sleep (1);
       }

       return;
}

void td2(void * i)
{
       while (1)
       {
               printf ("2\n");
               sleep (1);
       }

       return;
}

int
main(int argc,char *argv[],char *envp[])
{
       pthread_t       t1,t2;

       pthread_create(&t1, NULL, (void*)td1, NULL);
       pthread_create(&t2, NULL, (void*)td2, NULL);

       sleep (10);

       assert(0);

       return (0);
}
arm-xxx-gcc -g -lpthread 1.c -o 1
copy 1.c and 1 to a arm board.
Goto this board.
ulimit -c 1800000
./1
# ./1
1
2
1
...
...
1
1: 1.c:37: main: Assertion `0' failed.
Aborted (core dumped)
Then you can get a core file.
gdb 1 core.xxx
Without the patch:
(gdb) info threads
 3 process 909  0x00000000 in ?? ()
 2 process 908  0x00000000 in ?? ()
* 1 process 907  0x4a6e2238 in raise () from /lib/libc.so.6
You can found that the pc of 909 and 908 is 0x00000000.
With the patch:
(gdb) info threads
 3 process 885  0x4a749974 in nanosleep () from /lib/libc.so.6
 2 process 884  0x4a749974 in nanosleep () from /lib/libc.so.6
* 1 process 883  0x4a6e2238 in raise () from /lib/libc.so.6
The pc of 885 and 884 is right.
Signed-off-by: Hui Zhu <teawater@gmail.com>
Cc: Amerigo Wang <xiyou.wangcong@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: David Howells <dhowells@redhat.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Jakub Jelinek <jakub@redhat.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

I run many ffsb test cases on JBODs (typically 13/12 disks).  Comparing
with kernel 2.6.30, 2.6.31-rc1 has about 16% regression with
ffsb_create_4k.  The sub test case creates files continuously for 10
minitues and every file is 1MB.

Bisect located below patch.

5cee5815 is first bad commit
commit 5cee5815
Author: Jan Kara <jack@suse.cz>
Date:   Mon Apr 27 16:43:51 2009 +0200

    vfs: Make sys_sync() use fsync_super() (version 4)

    It is unnecessarily fragile to have two places (fsync_super() and do_sync())
    doing data integrity sync of the filesystem. Alter __fsync_super() to
    accommodate needs of both callers and use it. So after this patch
    __fsync_super() is the only place where we gather all the calls needed to
    properly send all data on a filesystem to disk.

As a matter of fact, ffsb calls sys_sync in the end to make sure all data
is flushed to disks and the flushing is counted into the result.  vmstat
shows ffsb is blocked when syncing for a long time.  With 2.6.30, ffsb is
blocked for a short time.

I checked the patch and did experiments to recover the original methods.
Eventually, the root cause is the patch deletes the calling to
wakeup_pdflush when syncing, so only ffsb is blocked on disk I/O.
wakeup_pdflush could ask pdflush to write back pages with ffsb at the
same time.

[akpm@linux-foundation.org: restore comment too]
Signed-off-by: Zhang Yanmin <yanmin_zhang@linux.intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Fix for this issue on x86_64:

rostedt@goodmis.org wrote:
> On bootup of the latest kernel my init segfaults. Debugging it,
> I found  that vread_tsc (a vsyscall) increments some strange
> kernel memory:
>
> 0000000000000000 <vread_tsc>:
>    0:   55                      push   %rbp
>    1:   48 ff 05 00 00 00 00    incq   0(%rip)
>                         # 8 <vread_tsc+0x8>
>                         4: R_X86_64_PC32        .bss+0x3c
>    8:   48 89 e5                mov    %rsp,%rbp
>    b:   66 66 90                xchg   %ax,%ax
>    e:   48 ff 05 00 00 00 00    incq   0(%rip)
>                         # 15 <vread_tsc+0x15>
>                         11: R_X86_64_PC32       .bss+0x44
>   15:   66 66 90                xchg   %ax,%ax
>   18:   48 ff 05 00 00 00 00    incq   0(%rip)
>                         # 1f <vread_tsc+0x1f>
>                         1b: R_X86_64_PC32       .bss+0x4c
>   1f:   0f 31                   rdtsc
>
>
> Those "incq" is very bad to happen in vsyscall memory, since
> userspace can not modify it. You need to make something prevent
> profiling of vsyscall  memory (like I do with ftrace).
Signed-off-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Tested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

When i2c_smbus_read_byte_data fails in ds1374_work, we forgot to unlock
the held lock.  Fix that.
Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
Cc: Alessandro Zummo <a.zummo@towertech.it>
Cc: Scott Wood <scottwood@freescale.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Fix a typo in the VLYNQ bus driver Kconfig which prevented to turn on
VLYNQ bus debugging.
Signed-off-by: Florian Fainelli <florian@openwrt.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Fix a typo in the vlynq bus driver which was missing the CONFIG_ prefix to
turn on debugging code.
Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca>
Signed-off-by: Florian Fainelli <florian@openwrt.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Remove redundant call to the sisfb_get_fix() before sis frambuffer is
registered.

This fixes a problem with uninitialized the fb_info->mm_lock mutex
introduced by the commit 537a1bf0 " fbdev: add mutex for fb_mmap
locking"
Signed-off-by: Krzysztof Helt <krzysztof.h1@wp.pl>
Tested-by: Wu Zhangjin <wuzhangjin@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Our current strategy for pass-through mode is to put all devices into
the 1:1 domain at startup (which is before we know what their dma_mask
will be), and only _later_ take them out of that domain, if it turns out
that they really can't address all of memory.

However, when there are a bunch of PCI devices behind a bridge, they all
end up with the same source-id on their DMA transactions, and hence in
the same IOMMU domain. This means that we _can't_ easily move them from
the 1:1 domain into their own domain at runtime, because there might be DMA
in-flight from their siblings.

So we have to adjust our pass-through strategy: For PCI devices not on
the root bus, and for the bridges which will take responsibility for
their transactions, we have to start up _out_ of the 1:1 domain, just in
case.

This fixes the BUG() we see when we have 32-bit-capable devices behind a
PCI-PCI bridge, and use the software identity mapping.

It does mean that we might end up using 'normal' mapping mode for some
devices which could actually live with the faster 1:1 mapping -- but
this is only for PCI devices behind bridges, which presumably aren't the
devices for which people are most concerned about performance.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

At boot time, the dma_mask won't have been set on any devices, so we
assume that all devices will be 64-bit capable (and thus get a 1:1 map).
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

Commit 537a1bf0 (fbdev: add mutex for
fb_mmap locking) introduces a ->mm_lock mutex for protecting smem
assignments. Unfortunately in the case of sm501fb these happen quite
early in the initialization code, well before the mutex_init() that takes
place in register_framebuffer(), leading to:

   Badness at kernel/mutex.c:207

   Pid : 1, Comm:          swapper
   CPU : 0                 Not tainted  (2.6.31-rc1-00284-g529ba0d9-dirty #2273)

   PC is at __mutex_lock_slowpath+0x72/0x1bc
   PR is at __mutex_lock_slowpath+0x66/0x1bc
   ...

matroxfb appears to have the same issue and has solved it with an early
mutex_init(), so we do the same for sm501fb.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Cc: Krzysztof Helt <krzysztof.h1@wp.pl>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/kyle/parisc-2.6: (27 commits)
  parisc: use generic atomic64 on 32-bit
  parisc: superio: fix build breakage
  parisc: Fix PCI resource allocation on non-PAT SBA machines
  parisc: perf: wire up sys_perf_counter_open
  parisc: add task_pt_regs macro
  parisc: wire sys_perf_counter_open to sys_ni_syscall
  parisc: inventory.c, fix bloated stack frame
  parisc: processor.c, fix bloated stack frame
  parisc: fix compile warning in mm/init.c
  parisc: remove dead code from sys_parisc32.c
  parisc: wire up rt_tgsigqueueinfo
  parisc: ensure broadcast tlb purge runs single threaded
  parisc: fix "delay!" timer handling
  parisc: fix mismatched parenthesis in memcpy.c
  parisc: Fix gcc 4.4 warning in lba_pci.c
  parisc: add parameter to read_cr16()
  parisc: decode_exc.c should include kernel.h
  parisc: remove obsolete hw_interrupt_type
  parisc: fix irq compile bugs in arch/parisc/kernel/irq.c
  parisc: advertise PCI devs after "assign_resources"
  ...

Manually fixed up trivial conflicts in tools/perf/perf.h due to addition
of SH vs HPPA perf-counter support.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sameo/mfd-2.6:
  mfd: fix pcap adc locking
  mfd: sm501, fix lock imbalance

* 'for-2.6.31' of git://linux-nfs.org/~bfields/linux:
  NFSD: Don't hold unrefcounted creds over call to nfsd_setuser()

* 'upstream' of git://ftp.linux-mips.org/pub/scm/upstream-linus:
  MIPS: Fix CONFIG_FLATMEM version of pfn_valid()
  MIPS: Reorganize Cavium OCTEON PCI support.
  Update Yoichi Yuasa's e-mail address
  MIPS: Allow suspend and hibernation again on uniprocessor kernels.
  MIPS: 64-bit: Fix o32 core dump
  MIPS: BC47xx: Fix SSB irq setup
  MIPS: CMP: Update sync-r4k for current kernel
  MIPS: CMP: Move gcmp_probe to before the SMP ops
  MIPS: CMP: activate CMP support
  MIPS: CMP: Extend IPI handling to CPU number
  MIPS: CMP: Extend the GIC IPI interrupts beyond 32
  MIPS: Define __arch_swab64 for all mips r2 cpus
  MIPS: Update VR41xx GPIO driver to use gpiolib
  MIPS: Hookup new syscalls sys_rt_tgsigqueueinfo and sys_perf_counter_open.
  MIPS: Malta: Remove unnecessary function prototypes
  MIPS: MT: Remove unnecessary semicolons
  MIPS: Add support for Texas Instruments AR7 System-on-a-Chip

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6:
  sound: do not set DEVNAME for OSS devices
  ALSA: hda - Add sanity check in PCM open callback
  ALSA: hda - Call snd_pcm_lib_hw_rates() again after codec open callback
  ALSA: hda - Avoid invalid formats and rates with shared SPDIF
  ALSA: hda - Improve ASUS eeePC 1000 mixer
  ALSA: hda - Add GPIO1 control at muting with HP laptops
  ALSA: usx2y - reparent sound device
  ALSA: snd_usb_caiaq: reparent sound device
  sound: virtuoso: fix Xonar D1/DX silence after resume
  ASoC: Only disable pxa2xx-i2s clocks if we enabled them
  ALSA: hda - Add quirk for HP 6930p
  ALSA: hda - Add missing static to patch_ca0110()
  ASoC: OMAP: fix OMAP1510 broken PCM pointer callback
  ASoC: remove BROKEN from Efika and pcm030 fabric drivers
  ASoC: Fix typo in MPC5200 PSC AC97 driver Kconfig

* git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild-fixes:
  kbuild: finally remove the obsolete variable $TOPDIR
  gitignore: ignore scripts/ihex2fw
  Kbuild: Disable the -Wformat-security gcc flag
  gitignore: ignore gcov output files
  kbuild: deb-pkg ship changelog
  Add new __init_task_data macro to be used in arch init_task.c files.
  asm-generic/vmlinux.lds.h: shuffle INIT_TASK* macro names in vmlinux.lds.h
  Add new macros for page-aligned data and bss sections.
  asm-generic/vmlinux.lds.h: Fix up RW_DATA_SECTION definition.

* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
  block: don't merge requests of different failfast settings
  cciss: Ignore stale commands after reboot

This should fix kernel.org bug #11821, where the dcdbas driver makes up
a platform device and then uses dma_alloc_coherent() on it, in an
attempt to get memory < 4GiB.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

We need to give people a little more time to fix the broken drivers.
Re-introduce this, but tied in properly with the 'iommu=pt' support this
time. Change the config option name and make it default to 'no' too.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

We do this twice, and it's about to get more complicated. This makes the
code slightly clearer about what it's doing, too.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

When we reattach a device to the si_domain (because it's been removed
from a VM), we weren't calling domain_context_mapping() to actually tell
the hardware about that.

We should really put the call to domain_context_mapping() into
domain_add_dev_info() -- we never call the latter without also doing the
former, and we can keep the error paths simple that way. But that's a
cleanup which can wait for 2.6.32 now.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

We should check iommu_dummy() _first_, because that means it's attached
to an iommu that we've just disabled completely. At the moment, we might
try to put the device into the identity mapping domain.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

The aligned_nrpages() function rounds up to the next VM page, but
returns its result as a number of DMA pages.

Purely theoretical except on IA64, which doesn't boot with VT-d right
now anyway.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>