Commit graph

64,840 commits

Author SHA1 Message Date
Joerg Roedel
47bccd6bb2 amd-iommu: don't free dma adresses below 512MB with CONFIG_IOMMU_STRESS
This will test the automatic aperture enlargement code. This is
important because only very few devices will ever trigger this code
path. So force it under CONFIG_IOMMU_STRESS.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:18:33 +02:00
Joerg Roedel
f5e9705c64 amd-iommu: don't preallocate page tables with CONFIG_IOMMU_STRESS
This forces testing of on-demand page table allocation code.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:18:08 +02:00
Joerg Roedel
fe16f088a8 amd-iommu: disable round-robin allocator for CONFIG_IOMMU_STRESS
Disabling the round-robin allocator results in reusing the same
dma-addresses again very fast. This is a good test if the iotlb flushing
is working correctly.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:17:13 +02:00
Joerg Roedel
d9cfed9254 amd-iommu: remove amd_iommu_size kernel parameter
This parameter is not longer necessary when aperture increases
dynamically.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:16:49 +02:00
Joerg Roedel
11b83888ae amd-iommu: enlarge the aperture dynamically
By dynamically increasing the aperture the extended allocator is now
ready for use.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:15:57 +02:00
Joerg Roedel
00cd122ae5 amd-iommu: handle exlusion ranges and unity mappings in alloc_new_range
This patch makes sure no reserved addresses are allocated in an dma_ops
domain when the aperture is increased dynamically.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:15:19 +02:00
Joerg Roedel
9cabe89b99 amd-iommu: move aperture_range allocation code to seperate function
This patch prepares the dynamic increasement of dma_ops domain
apertures.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:14:35 +02:00
Joerg Roedel
803b8cb4d9 amd-iommu: change dma_dom->next_bit to dma_dom->next_address
Simplify the code a little bit by using the same unit for all address
space related state in the dma_ops domain structure.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:14:26 +02:00
Joerg Roedel
384de72910 amd-iommu: make address allocator aware of multiple aperture ranges
This patch changes the AMD IOMMU address allocator to allow up to 32
aperture ranges per dma_ops domain.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:14:15 +02:00
Joerg Roedel
53812c115c amd-iommu: handle page table allocation failures in dma_ops code
The code will be required when the aperture size increases dynamically
in the extended address allocator.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:13:43 +02:00
Joerg Roedel
8bda3092bc amd-iommu: move page table allocation code to seperate function
This patch makes page table allocation usable for dma_ops code.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:13:20 +02:00
Joerg Roedel
c3239567a2 amd-iommu: introduce aperture_range structure
This is a preperation for extended address allocator.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:12:52 +02:00
Joerg Roedel
736501ee00 amd-iommu: implement suspend/resume
This patch puts everything together and enables suspend/resume support
in the AMD IOMMU driver.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:11:39 +02:00
Joerg Roedel
05f92db9f4 amd_iommu: un __init functions required for suspend/resume
This patch makes sure that no function required for suspend/resume of
AMD IOMMU driver is thrown away after boot.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:10:56 +02:00
Joerg Roedel
7d7a110c61 amd-iommu: add function to flush tlb for all devices
This function is required for suspend/resume support with AMD IOMMU
enabled.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:10:43 +02:00
Joerg Roedel
bfd1be1857 amd-iommu: add function to flush tlb for all domains
This function is required for suspend/resume support with AMD IOMMU
enabled.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:10:12 +02:00
Joerg Roedel
92ac4320af amd-iommu: add function to disable all iommus
This function is required for suspend/resume support with AMD IOMMU
enabled.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:09:26 +02:00
Joerg Roedel
d91cecdd79 amd-iommu: remove support for msi-x
Current hardware uses msi instead of msi-x so this code it not necessary
and can not be tested. The best thing is to drop this code.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:09:18 +02:00
Joerg Roedel
fab6afa309 amd-iommu: drop pointless iommu-loop in msi setup code
It is not necessary to loop again over all IOMMUs in this code. So drop
the loop.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:09:08 +02:00
Joerg Roedel
58492e1288 amd-iommu: consolidate hardware initialization to one function
This patch restructures the AMD IOMMU initialization code to initialize
all hardware registers with one single function call.
This is helpful for suspend/resume support.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:08:58 +02:00
Joerg Roedel
3bd221724a amd-iommu: introduce for_each_iommu* macros
This patch introduces the for_each_iommu and for_each_iommu_safe macros
to simplify the developers life when having to iterate over all AMD
IOMMUs in the system.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:08:50 +02:00
Chris Wright
c1eee67b2d amd iommu: properly detach from protection domain on ->remove
Some drivers may use the dma api during ->remove which will
cause a protection domain to get reattached to a device.  Delay the
detach until after the driver is completely unbound.

[ joro: added a little merge helper ]

[ Impact: fix too early device<->domain removal ]

Signed-off-by: Chris Wright <chrisw@redhat.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:06:54 +02:00
Joerg Roedel
0bc252f430 amd-iommu: make sure only ivmd entries are parsed
The bug never triggered. But it should be fixed to protect against
broken ACPI tables in the future.

[ Impact: protect against broken ivrs acpi table ]

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:06:47 +02:00
Neil Turton
7455aab1f9 amd-iommu: fix the handling of device aliases in the AMD IOMMU driver.
The devid parameter to set_dev_entry_from_acpi is the requester ID
rather than the device ID since it is used to index the IOMMU device
table.  The handling of IVHD_DEV_ALIAS used to pass the device ID.
This patch fixes it to pass the requester ID.

[ Impact: fix setting the wrong req-id in acpi-table parsing ]

Signed-off-by: Neil Turton <nturton@solarflare.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:06:38 +02:00
Neil Turton
421f909c80 amd-iommu: fix an off-by-one error in the AMD IOMMU driver.
The variable amd_iommu_last_bdf holds the maximum bdf of any device
controlled by an IOMMU, so the number of device entries needed is
amd_iommu_last_bdf+1.  The function tbl_size used amd_iommu_last_bdf
instead.  This would be a problem if the last device were a large
enough power of 2.

[ Impact: fix amd_iommu_last_bdf off-by-one error ]

Signed-off-by: Neil Turton <nturton@solarflare.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 18:06:27 +02:00
Joerg Roedel
2e8b569614 amd-iommu: disable device isolation with CONFIG_IOMMU_STRESS
With device isolation disabled we can test better for race conditions in
dma_ops related code.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 17:56:57 +02:00
Joerg Roedel
2be69c79e9 x86/iommu: add IOMMU_STRESS Kconfig entry
This Kconfig option is intended to enable various code paths or
parameters in IOMMU implementations to stress test the code and/or the
hardware. This can also be done by disabling optimizations in the code
when this option is switched on.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
2009-05-28 17:55:33 +02:00
Joerg Roedel
b3b99ef8b4 amd-iommu: move protection domain printk to dump code
This information is only helpful for debugging. Don't print it anymore
unless explicitly requested.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 17:55:08 +02:00
Joerg Roedel
02acc43a29 amd-iommu: print ivmd information to dmesg when requested
Add information about device memory mapping requirements for the IOMMU
as described in the IVRS ACPI table to the kernel log if amd_iommu_dump
was specified on the kernel command line.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 17:53:30 +02:00
Joerg Roedel
42a698f40a amd-iommu: print ivhd information to dmesg when requested
Add information about devices belonging to an IOMMU as described in the
IVRS ACPI table to the kernel log if amd_iommu_dump was specified on the
kernel command line.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 17:52:04 +02:00
Joerg Roedel
9c72041f71 amd-iommu: add dump for iommus described in ivrs table
Add information about IOMMU devices described in the IVRS ACPI table to
the kernel log if amd_iommu_dump was specified on the kernel command
line.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 17:50:56 +02:00
Joerg Roedel
fefda117dd amd-iommu: add amd_iommu_dump parameter
This kernel parameter will be useful to get some AMD IOMMU related
information in dmesg that is not necessary for the default user but may
be helpful in debug situations.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
2009-05-28 17:49:56 +02:00
Valentin Longchamp
0573cb5f45 mx31: correct csi_clk parent (v2)
changes since v1: we now check if the parent configuration bit was
changed since reset and change the parent when needed.

csi_clk parent was defined with ahb_clk. However, according to the
m31 reference manual, it should be serial_pll_clk.

Guennadi always used a 20 MHz clock that was by chance changed to
a 45 MHz that fits in the mt9t031 spec. Now the clocks are computed
and output correctly (measured on oscillo).

Signed-off-by: Valentin Longchamp <valentin.longchamp@epfl.ch>
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
2009-05-28 17:20:53 +02:00
Fabio Estevam
0b0ef44295 MX3: Add missing entry in devices.h
Add missing mxc_rnga_device entry in devices.h (mxc-master tree).

Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
2009-05-28 17:19:23 +02:00
Paulius Zaleckas
67a433ce27 Gemini: Fix SRAM/ROM location after memory swap
Signed-off-by: Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
2009-05-28 16:42:25 +03:00
Russell King
e03cdade0c [ARM] smp: use new cpumask functions
Convert cpu_*_mask bit twiddling to the new set_cpu_*() API.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2009-05-28 14:16:52 +01:00
Catalin Marinas
af73110d23 [ARM] 5516/1: Flush the D-cache after initialising the SCU
On MP systems, the data loaded by CPU0 before the SCU was initialised
may not be visible to the other CPUs.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

This also includes the following compile fix:

This patch includes 'asm/cacheflush.h' which is needed to use
'flush_cache_all()' function.

Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2009-05-28 13:52:05 +01:00
Petr Tesarik
7d96fd41ca x86: move rdtsc_barrier() into the TSC vread method
The *fence instructions were moved to vsyscall_64.c by commit
cb9e35dce9.  But this breaks the
vDSO, because vread methods are also called from there.

Besides, the synchronization might be unnecessary for other
time sources than TSC.

[ Impact: fix potential time warp in VDSO ]

Signed-off-by: Petr Tesarik <ptesarik@suse.cz>
LKML-Reference: <9d0ea9ea0f866bdc1f4d76831221ae117f11ea67.1243241859.git.ptesarik@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@kernel.org>
2009-05-28 14:15:54 +02:00
Pallipadi, Venkatesh
ee1ca48fae ACPI: Disable ARB_DISABLE on platforms where it is not needed
ARB_DISABLE is a NOP on all of the recent Intel platforms.

For such platforms, reduce contention on c3_lock
by skipping the fake ARB_DISABLE.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
2009-05-27 21:57:30 -04:00
Yinghai Lu
abfe0af981 x86: enable_update_mptable should be a macro
instead of declaring one variant as an inline function...
because other case is a variable

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4A13B344.7030307@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-05-28 01:59:05 +02:00
Linus Torvalds
b5c42bc8db Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/vapier/blackfin
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/vapier/blackfin:
  Blackfin: fix strncmp.o build error
  Blackfin: drop unneeded asm/.gitignore
  Blackfin: ignore generated vmlinux.lds
  MAINTAINERS: drop (subscribers-only) markings on Blackfin lists
  MAINTAINERS: update Blackfin items
  Blackfin: hook up preadv/pwritev syscalls
2009-05-27 10:58:49 -07:00
Benjamin Herrenschmidt
8b31e49d1d powerpc: Fix up dma_alloc_coherent() on platforms without cache coherency.
The implementation we just revived has issues, such as using a
Kconfig-defined virtual address area in kernel space that nothing
actually carves out (and thus will overlap whatever is there),
or having some dependencies on being self contained in a single
PTE page which adds unnecessary constraints on the kernel virtual
address space.

This fixes it by using more classic PTE accessors and automatically
locating the area for consistent memory, carving an appropriate hole
in the kernel virtual address space, leaving only the size of that
area as a Kconfig option. It also brings some dma-mask related fixes
from the ARM implementation which was almost identical initially but
grew its own fixes.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-05-27 16:33:59 +10:00
Benjamin Herrenschmidt
f637a49e50 powerpc: Minor cleanups of kernel virt address space definitions
Make FIXADDR_TOP a compile time constant and cleanup a
couple of definitions relative to the layout of the kernel
address space on ppc32. We also print out that layout at
boot time for debugging purposes.

This is a pre-requisite for properly fixing non-coherent
DMA allocactions.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-05-27 16:32:50 +10:00
Benjamin Herrenschmidt
b16e7766d6 powerpc: Move dma-noncoherent.c from arch/powerpc/lib to arch/powerpc/mm
(pre-requisite to make the next patches more palatable)

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-05-27 16:32:05 +10:00
Mike Frysinger
add8a5050a Blackfin: fix strncmp.o build error
Fix some more fallout of the string changes:

  CC      arch/blackfin/lib/strncmp.o
In file included from include/linux/bitmap.h:9,
                 from include/linux/nodemask.h:90,
                 from include/linux/mmzone.h:17,
                 from include/linux/gfp.h:5,
                 from include/linux/kmod.h:23,
                 from include/linux/module.h:14,
                 from arch/blackfin/lib/strncmp.c:14:
include/linux/string.h: In function ‘strstarts’:
include/linux/string.h:132: error: implicit declaration of function ‘strncmp’
make[1]: *** [arch/blackfin/lib/strncmp.o] Error 1

Signed-off-by: Mike Frysinger <vapier@gentoo.org>
CC: Rusty Russell <rusty@rustcorp.com.au>
2009-05-27 00:27:05 -04:00
Mike Frysinger
2ec10ea91b Blackfin: drop unneeded asm/.gitignore
We don't create a include/asm/mach/ symlink anymore, so we don't need the
.gitignore for it.

Signed-off-by: Mike Frysinger <vapier@gentoo.org>
2009-05-27 00:27:04 -04:00
Mike Frysinger
6b50520b2f Blackfin: ignore generated vmlinux.lds
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
2009-05-27 00:27:03 -04:00
Mike Frysinger
7a1450fdf4 Blackfin: hook up preadv/pwritev syscalls
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
2009-05-27 00:27:00 -04:00
Benjamin Herrenschmidt
84532a0fc3 Revert "powerpc: Rework dma-noncoherent to use generic vmalloc layer"
This reverts commit 33f00dcedb.

    While it was a good idea to try to use the mm/vmalloc.c allocator instead
    of our own (in fact, ours is itself a dup on an old variant of the vmalloc
    one), unfortunately, the approach is terminally busted since
    dma_alloc_coherent() can be called at interrupt time or in atomic contexts
    and there's little chances we'll make the code in mm/vmalloc.c cope with\       that :-(

    Until we can get the generic code to forbid that idiocy and fix all
    drivers abusing it, we pretty much have no choice but revert to
    our custom virtual space allocator.

    There's also a problem with SMP safety since freeing such mapping
    would require an IPI which cannot be done at interrupt time.

    However, right now, I don't think we support any platform that is
    both SMP and has non-coherent DMA (don't laugh, I know such things
    do exist !) so we can sort that out later.

    Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-05-27 13:33:14 +10:00
Kevin Hilman
a330bd4750 Revert "ARM: OMAP: Mask interrupts when disabling interrupts, v2"
This reverts commit 5461af5af5.

Adding a disable hook to the irq_chip is not the way to fix the
problem being addressed by this patch.  Instead, we need to fix
support for [enable|disable]_irq_wake().

Signed-off-by: Kevin Hilman <khilman@deeprootsystems.com>
2009-05-26 15:56:55 -07:00