On Wed, Feb 04, 2015 at 05:34:50PM +0100, Peter Zijlstra wrote:
You just lost your atomic_dec.
So this should be the correct version then.
From 2a52250e542d8964c8285a37b71fe838a44c05c4 Mon Sep 17 00:00:00 2001
From: Joerg Roedel jroe...@suse.de
Date: Wed, 4 Feb 2015 15:50:38 +0100
Subject
Hi Jiang,
On Thu, Feb 05, 2015 at 01:51:26PM +0800, Jiang Liu wrote:
Reviewed-by: Jiang Liu jiang@linux.intel.com
Thanks for your review.
Actually there's another racing pattern.
for (irq = 0; irq nr_irqs; irq++) {
desc = irq_to_desc(irq);
access desc-xxx
}
When
Hi Linus,
On Tue, Feb 03, 2015 at 11:23:44AM -0800, Linus Torvalds wrote:
The linux wakeup model has always been that there can be multiple
sources of wakeup events, and the proper way to wait for something is
generally a variation of
prepare_to_wait(..);
for (;;) {
On Mon, Jan 19, 2015 at 03:04:00PM +0100, Joerg Roedel wrote:
Instead of adding another variable I think it is better to just move the
trace_unmap call before the unmap loop. It can actually replace the
pr_debug there.
Okay, forget this. I just noticed that your follow-on patch requires
On Fri, Jan 16, 2015 at 04:47:19PM -0700, Shuah Khan wrote:
iommu_unmap() calls trace_unmap() with changed iova and original
size. trace_unmap() should report original iova instead. Change
iommu_unmap() to call trace_unmap() with original iova.
Signed-off-by: Shuah Khan
On Thu, Jan 15, 2015 at 10:25:11AM +, Will Deacon wrote:
If you get an Ack from any of Arnd/Joerg/akpm then I'm happy to take it via
the arm-smmu pull (along with the patch making use of it).
Joerg, would you be ok with that?
I am ok with that, but like to have another Ack for it.
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/rockchip-iommu.c | 40
1 file changed, 24 insertions(+), 16
From: Joerg Roedel jroe...@suse.de
Hi,
here is patch-set to replace the existing domain_init and
domain_destroy iommu-ops with the new domain_alloc and
domain_free callbacks
The new callbacks move the allocation of iommu domains into
the iommu driver, allowing them to put a generic
iommu_domain
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/fsl_pamu_domain.c | 60 ++---
drivers/iommu/fsl_pamu_domain.h
From: Joerg Roedel jroe...@suse.de
When regulator is not selected during kconfig, linking of
the exynos iommu driver fails due to missing symbols.
Fix it!
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/tegra-smmu.c | 41 +++--
1 file changed, 23 insertions(+), 18
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/exynos-iommu.c | 87
1 file changed, 47 insertions
From: Joerg Roedel jroe...@suse.de
Implement the new domain_alloc and domain_free call-backs
and remove the old domain_init/destroy ones.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/omap-iommu.c | 49 +++---
1 file changed, 29 insertions
From: Joerg Roedel jroe...@suse.de
The default domain will be used (if supported by the iommu
driver) when the devices in the iommu group are not attached
to any other domain.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/iommu.c | 26 +++---
1 file changed
From: Joerg Roedel jroe...@suse.de
This function can be used to request the current domain a
device is attached to.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/iommu.c | 18 ++
include/linux/iommu.h | 6 ++
2 files changed, 24 insertions(+)
diff --git
From: Joerg Roedel jroe...@suse.de
Make use of the default domain and re-attach a device to it
when it is detached from another domain. Also enforce that a
device has to be in the default domain before it can be
attached to a different domain.
Signed-off-by: Joerg Roedel jroe...@suse.de
From: Joerg Roedel jroe...@suse.de
When assigning devices to large memory guests (=128GB guest
memory in the failure case) the functions to create the
IOMMU page-tables for the whole guest might run for a very
long time. On non-preemptible kernels this might cause
Soft-Lockup warnings. Fix
On Fri, Jan 23, 2015 at 06:04:25PM +0100, Borislav Petkov wrote:
On Tue, Jan 06, 2015 at 03:51:12PM +0100, Joerg Roedel wrote:
+
+err_warn:
+ pr_warn(swiotlb: coherent allocation failed for device %s size=%zu\n,
+ dev_name(hwdev), size);
+ dump_stack();
Are we really
On Mon, Jan 26, 2015 at 11:22:36AM +0800, Baoquan He wrote:
Ok, so this practically does all allocations __GFP_NOWARN now. Shouldn't
you be doing this before swiotlb_alloc_coherent() and not before
dma_generic_alloc_coherent()?
I think this patch mainly suppress warning from buddy
Hi Baoquan,
thanks for your reply.
On Fri, Jan 23, 2015 at 04:44:53PM +0800, Baoquan He wrote:
2) increase low-mem when crashkernel=high. But we have to be careful to
do this. We implement crashkernel=high not only for the unhappiness
crashkernel reservation is limited below 4G, but dma/dma32
On Fri, Jan 23, 2015 at 06:02:43PM +0100, Borislav Petkov wrote:
On Tue, Jan 06, 2015 at 03:51:14PM +0100, Joerg Roedel wrote:
From: Joerg Roedel jroe...@suse.de
When the crashkernel is loaded above 4GiB in memory the
first kernel only allocates 72MiB of low-memory for the DMA
On Thu, Jan 15, 2015 at 07:29:43PM -0700, Shuah Khan wrote:
iommu_map() calls trace_map() with iova and size. trace_map()
should report original iova and original size as opposed to
iova and size after they get changed during mapping. size is
always zero at the end of mapping which is useless
From: Joerg Roedel jroe...@suse.de
For easier compile testing of these iommu drivers.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/Kconfig | 9 ++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 325188e
Hi,
here are a couple of iommu fixes and cleanups to fix compile
errors and some warnings on ARM and PPC.
Regards,
Joerg
Joerg Roedel (4):
iommu: Make more drivers depend on COMPILE_TEST
iommu/exynos: Make driver depend on REGULATOR
iommu/omap: Print phys_addr_t using %pa
iommu
From: Joerg Roedel jroe...@suse.de
Fixes this compile warning:
drivers/iommu/omap-iommu.c: In function 'omap_iommu_map':
drivers/iommu/omap-iommu.c:1139:2: warning: format '%x' expects argument of
type 'unsigned int', but argument 5 has type 'phys_addr_t' [-Wformat=]
dev_dbg(dev, mapping da
From: Joerg Roedel jroe...@suse.de
These new call-backs defer the allocation and destruction of
'struct iommu_domain' to the iommu driver. This allows
drivers to embed this struct into their private domain
structures and to get rid of the domain_init and
domain_destroy call-backs when all drivers
From: Joerg Roedel jroe...@suse.de
Implement the new iommu-ops function pointers and remove the
obsolete domain_init and domain_destroy functions.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/amd_iommu.c | 84 ++---
drivers/iommu
From: Joerg Roedel jroe...@suse.de
This allows to handle domains differently based on their
type in the future. An IOMMU driver can implement certain
optimizations for DMA-API domains for example.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/iommu.c | 5 +++--
include/linux
From: Joerg Roedel jroe...@suse.de
Fix two compile warnings.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/fsl_pamu.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c
index 80ac68d..e63904b 100644
From: Joerg Roedel jroe...@suse.de
All drivers have been converted to the new domain_alloc and
domain_free iommu-ops. So remove the old ones and get rid of
iommu_domain-priv too, as this is no longer needed when the
struct iommu_domain is embedded in the private structures of
the iommu drivers
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/ipmmu-vmsa.c | 43 ---
1 file changed, 24 insertions(+), 19
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/shmobile-iommu.c | 40
1 file changed, 24 insertions(+), 16
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/arm-smmu.c | 46 +++---
1 file changed, 27 insertions(+), 19
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/msm_iommu.c | 73 +++
1 file changed, 36 insertions
From: Joerg Roedel jroe...@suse.de
Get rid of domain_init and domain_destroy and implement
domain_alloc/domain_free instead.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/intel-iommu.c | 48 ++---
1 file changed, 28 insertions(+), 20
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/tegra-gart.c | 67 +++---
1 file changed, 46 insertions
From: Joerg Roedel jroe...@suse.de
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/iommu.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index e66cc08..34636eb 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
more explict.
With patch 3 applied, attach/detach_device will only succeed
when the device is the only one in its group. This probably
requires changes in the callers, which are not included
here.
Any useful comments and feedback appreciated.
Thanks,
Joerg
Joerg Roedel (5):
iommu: Add
From: Joerg Roedel jroe...@suse.de
This patch changes the behavior of the iommu_attach_device
and iommu_detach_device functions. With this change these
functions only work on devices that have their own group.
For all other devices the iommu_group_attach/detach
functions must be used.
Signed-off
Hi Linus,
The following changes since commit 26bc420b59a38e4e6685a73345a0def461136dce:
Linux 3.19-rc6 (2015-01-25 20:04:41 -0800)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
tags/iommu-fixes-v3.19-rc6
for you to fetch changes up to
Hi Jerry,
On Wed, Dec 17, 2014 at 02:37:47PM -0700, Jerry Hoemann wrote:
Before applying this change on a 3.18-rc7 kernel layered on a
RHEL 7.0 root disk, I was able to reproduce the memory
leak that Alex reported when powering on/off a VM w/ a PCI
device assigned to it.
After applying
On Fri, Dec 05, 2014 at 02:47:37PM +0100, Krzysztof Kozlowski wrote:
drivers/iommu/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Applied to iommu/fixes, thanks.
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to
On Sun, Dec 21, 2014 at 10:14:30PM +0100, Wolfram Sang wrote:
This platform_driver does not need to set an owner, it will be populated by
the
driver core.
Signed-off-by: Wolfram Sang w...@the-dreams.de
---
Generated with coccinelle. SmPL file is in the introductory msg. The big
cleanup
On Mon, Jan 05, 2015 at 12:09:03PM +0100, Krzysztof Kozlowski wrote:
Thanks, but... Few days after my patch Mark Brown posted something
similar:
http://lists.infradead.org/pipermail/linux-arm-kernel/2014-December/310743.html
It was merged by Arnd Bergman and sent to Linus around 3.19-rc1. It
Hello Raimonds,
On Mon, Jan 05, 2015 at 05:25:25PM +0200, Raimonds Cicans wrote:
After kernel upgrade (3.13 = 3.17) I started to receive following
string in my logs:
AMD-Vi: Event logged [IO_PAGE_FAULT device=08:00.0 domain=0x001c
address=0x01355000 flags=0x]
I would like to
From: Joerg Roedel jroe...@suse.de
When the crashkernel is loaded above 4GiB in memory the
first kernel only allocates 72MiB of low-memory for the DMA
requirements of the second kernel. On systems with many
devices this is not enough and causes device driver
initialization errors and failed crash
From: Joerg Roedel jroe...@suse.de
When we boot a kdump kernel in high memory, there is by
default only 72MB of low memory available. The swiotlb code
takes 64MB of it (by default) so that there are only 8MB
left to allocate from. On systems with many devices this
causes page allocator warnings
From: Joerg Roedel jroe...@suse.de
Print a warning when all allocation tries have been failed
and the function is about to return NULL. This prepares for
calling the function with __GFP_NOWARN to suppress
allocation failure warnings before all fall-backs have
failed.
Signed-off-by: Joerg Roedel
on the affected systems,
128MiB low-memory was still not enough there, thus I set the
value to 256MiB to fix the issues.
Any feedback appreciated.
Thanks,
Joerg
Joerg Roedel (3):
swiotlb: Warn on allocation failure in swiotlb_alloc_coherent
x86, swiotlb: Try coherent allocations
On Mon, Jan 12, 2015 at 03:06:19PM +0800, Li, Zhen-Hua wrote:
Allow specification of the domain-id for the new domain.
This patch only adds the 'did' parameter to iommu_attach_domain()
and modifies all of its callers to specify the default value of -1
which says no did specified, allocate a
On Mon, Jan 12, 2015 at 10:29:19AM -0500, Vivek Goyal wrote:
Kdump has the notion of backup region. Where certain parts of old kernels
memory can be moved to a different location (first 640K on x86 as of now)
and new kernel can make use of this memory now.
So we will have to just make sure
Hi Oded,
On Mon, Dec 22, 2014 at 12:23:44PM +0200, Oded Gabbay wrote:
The drm guys suggested we move iommu/ subsystem before gpu/
subsystem in drivers/Makefile instead of the above patch (and the
complementing patch-set in amdkfd).
I did that and it works, so please see this patch as
On Mon, Jan 12, 2015 at 03:06:20PM +0800, Li, Zhen-Hua wrote:
+
+#ifdef CONFIG_CRASH_DUMP
+
+/*
+ * Fix Crashdump failure caused by leftover DMA through a hardware IOMMU
+ *
+ * Fixes the crashdump kernel to deal with an active iommu and legacy
+ * DMA from the (old) panicked kernel in a
On Tue, Jan 13, 2015 at 04:12:29PM +0800, Li, ZhenHua wrote:
Current status:
1. Use old root entry table,
2. Copy old context entry tables.
3. Copy old page tables.
4. Allocate new page table when device driver is loading.
I remember the progress we discussed was this. Checking the old
my
Tested-by: Joerg Roedel jroe...@suse.de
Regards,
Joerg
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http
Ping.
On Tue, Jan 06, 2015 at 03:51:11PM +0100, Joerg Roedel wrote:
v1-v2:
* Updated comments based on feedback from Konrad
* Added Acked-bys
* Rebased to v3.19-rc3
Hi,
here is a patch-set to fix failed kdump kernel boots when
the systems was booted with crashkernel=X,high. On those
On Mon, Jan 12, 2015 at 11:15:38AM -0500, Vivek Goyal wrote:
On Mon, Jan 12, 2015 at 05:06:46PM +0100, Joerg Roedel wrote:
On Mon, Jan 12, 2015 at 10:29:19AM -0500, Vivek Goyal wrote:
Kdump has the notion of backup region. Where certain parts of old kernels
memory can be moved
On Thu, Feb 12, 2015 at 06:08:45PM -0800, Linus Torvalds wrote:
Any ideas? The Pixel Chromebook does have an odd and often broken
BIOS/firmware thing, but it *used* to suspend and resume very reliably
once we got around its insane TPM thing.
Hmm, looking at the patch and the surrounding code
Hi Baoquan,
On Sat, Feb 14, 2015 at 06:58:34PM +0800, Baoquan He wrote:
This patch is very helpful and necessary since several users complained
about the failure caused by not enough low mem. And the default value
256M is suitable since the testing data showed it's sufficient
now and should
Hi Baoquan,
On Wed, Feb 04, 2015 at 03:10:20PM +0100, Joerg Roedel wrote:
That makes sense. I also asked the customer to test intermediate values,
we already know that it works with 256MB but also that 128MB are not
enough. I will report back when I have the results of the intermediate
values
iommu/arm-smmu: Avoid build warning
Emil Medve (3):
iommu/fsl: Fix section mismatch
iommu/fsl: Remove unused fsl_of_pamu_ids[]
iommu/fsl: Various cleanups
Joerg Roedel (9):
Merge branch 'iommu/next' of git://linuxtv.org/pinchartl/fbdev into
arm/renesas
Merge branch
Hi Baoquan,
On Fri, Feb 13, 2015 at 11:34:38PM +0800, Baoquan He wrote:
Conclusively, I like 256M since the testing data showed it's sufficient
now and should be save for a long time.
Thanks, I am fine with 256MB too, so can I have your Acked-by on this
series? I will rebase and resend it then
-d driver
* Compile error fix for the VMSA IPMMU driver because of the
IOMMU_EXEC - IOMMU_NOEXEC conversion
* Two small cleanups as an aftermath of the merge window and the
domain-leak fix
Joerg
Hi Linus,
The following changes since commit c517d838eb7d07bbe9507871fab3931deccff539:
Linux 4.0-rc1 (2015-02-22 18:21:14 -0800)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
tags/iommu-fixes-v4.0-rc3
for you to fetch changes up to
On Mon, Mar 23, 2015 at 07:50:21PM -0600, Alex Williamson wrote:
Unused after commit 71684406905f (iommu/vt-d: Detach domain *only*
from attached iommus). Reported by 0-day builder.
Signed-off-by: Alex Williamson alex.william...@redhat.com
---
drivers/iommu/intel-iommu.c |1 -
1 file
On Tue, Mar 24, 2015 at 07:57:49AM -0400, Mark Hounschell wrote:
I'll be happy to test it.
Okay, here you go:
git://git.kernel.org/pub/scm/linux/kernel/git/joro/linux.git amd-iommu
This branch has two patches on-top of v4.0-rc5 which should fix the
issue you described here. Please let
Hi again,
On Wed, Mar 25, 2015 at 02:59:37PM +0100, Joerg Roedel wrote:
On Tue, Mar 24, 2015 at 07:57:49AM -0400, Mark Hounschell wrote:
I'll be happy to test it.
Okay, here you go:
git://git.kernel.org/pub/scm/linux/kernel/git/joro/linux.git amd-iommu
I just added more patches
From: Joerg Roedel jroe...@suse.de
Check for the new __IOMMU_DOMAIN_PAGING flag before calling
into the iommu drivers -map and -unmap call-backs.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/iommu.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/iommu/iommu.c
From: Joerg Roedel jroe...@suse.de
These new call-backs defer the allocation and destruction of
'struct iommu_domain' to the iommu driver. This allows
drivers to embed this struct into their private domain
structures and to get rid of the domain_init and
domain_destroy call-backs when all drivers
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/fsl_pamu_domain.c | 60 ++---
drivers/iommu/fsl_pamu_domain.h
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/shmobile-iommu.c | 39 +++
1 file changed, 23 insertions(+), 16
From: Joerg Roedel jroe...@suse.de
Get rid of domain_init and domain_destroy and implement
domain_alloc/domain_free instead.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/intel-iommu.c | 48 ++---
1 file changed, 28 insertions(+), 20
From: Joerg Roedel jroe...@suse.de
Implement the new iommu-ops function pointers and remove the
obsolete domain_init and domain_destroy functions.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/amd_iommu.c | 84 ++---
drivers/iommu
for x86, ARM and PPC
and runtime tested on x86 (Intel VT-d and AMD IOMMU).
Please review.
Thanks,
Joerg
Joerg Roedel (15):
iommu: Introduce domain_alloc and domain_free iommu_ops
iommu: Introduce iommu domain types
iommu/amd: Make use of domain_alloc and domain_free
iommu/vt-d
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/ipmmu-vmsa.c | 41 +++--
1 file changed, 23 insertions(+), 18
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/tegra-gart.c | 67 +++---
1 file changed, 46 insertions
From: Joerg Roedel jroe...@suse.de
All drivers have been converted to the new domain_alloc and
domain_free iommu-ops. So remove the old ones and get rid of
iommu_domain-priv too, as this is no longer needed when the
struct iommu_domain is embedded in the private structures of
the iommu drivers
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/msm_iommu.c | 73 +++
1 file changed, 36 insertions
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/rockchip-iommu.c | 40
1 file changed, 24 insertions(+), 16
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/exynos-iommu.c | 87
1 file changed, 47 insertions
From: Joerg Roedel jroe...@suse.de
This allows to handle domains differently based on their
type in the future. An IOMMU driver can implement certain
optimizations for DMA-API domains for example.
The domain types can be extended later and some of the
existing domain attributes can be migrated
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/arm-smmu.c | 46 +++---
1 file changed, 27 insertions(+), 19
From: Joerg Roedel jroe...@suse.de
Implement domain_alloc and domain_free iommu-ops as a
replacement for domain_init/domain_destroy.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/tegra-smmu.c | 41 +++--
1 file changed, 23 insertions(+), 18
On Wed, Mar 25, 2015 at 12:36:34PM -0400, Mark Hounschell wrote:
BTW, so far the first 2 patches are working well. I was going to
wait until the end of the day to report but so far I have been
unable to produce the problems I was seeing. And I am in the middle
of some driver work so lots of
From: Joerg Roedel jroe...@suse.de
Implement the new domain_alloc and domain_free call-backs
and remove the old domain_init/destroy ones.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/omap-iommu.c | 49 +++---
1 file changed, 29 insertions
On Tue, Mar 24, 2015 at 02:32:01AM +, Wu, Feng wrote:
I think it is better to put this as a union into struct irte. It saves
memory and unnecessary casting in later patches.
Thanks for the comments!
Thinking more about this, I think its probably fine to keep the two
versions of the
Hi,
here are a few fixes and enhancements for the AMD IOMMU
driver for the next merge window. They are tested on
different versions of AMD IOMMUs. Please review.
Thanks,
Joerg
Joerg Roedel (9):
iommu/amd: Use BUS_NOTIFY_REMOVED_DEVICE
iommu/amd: Ignore BUS_NOTIFY_UNBOUND_DRIVER
From: Joerg Roedel jroe...@suse.de
Now that fetch_pte returns the page-size of the pte, the
call in this function can also be optimized a little bit.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/amd_iommu.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff
From: Joerg Roedel jroe...@suse.de
Use the new device-notifier event instead of the old
BUS_NOTIFY_DEL_DEVICE to make sure the device driver had a
chance to uninit the device before all its mappings are
teared down.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/amd_iommu.c | 2
From: Joerg Roedel jroe...@suse.de
Now that fetch_pte returns the page-size of the pte, this
function can be optimized too.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/amd_iommu.c | 12 +++-
1 file changed, 3 insertions(+), 9 deletions(-)
diff --git a/drivers/iommu
From: Joerg Roedel jroe...@suse.de
Detaching a device from its domain at this event is
problematic for several reasons:
* The device might me in an alias group and
detaching it will also detach all other devices in
the group. This removes valid DMA mappings from
From: Joerg Roedel jroe...@suse.de
Now that fetch_pte returns the page-size of the pte, this
function can be optimized a lot.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/amd_iommu.c | 32
1 file changed, 8 insertions(+), 24 deletions(-)
diff
From: Joerg Roedel jroe...@suse.de
Don't explicitly add __GFP_ZERO to the allocator flags.
Leave this up to the caller.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/amd_iommu.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu
From: Joerg Roedel jroe...@suse.de
When a default page-size for given level should be mapped,
the level encoding must be 0 rather than 7. This fixes an
issue seen on IOMMUv2 hardware, where this encoding is
enforced.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/amd_iommu.c | 11
From: Joerg Roedel jroe...@suse.de
Add code to allocate memory from the contiguous memory
allocator to support coherent allocations larger than 8MB.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/amd_iommu.c | 44
1 file changed, 28
From: Joerg Roedel jroe...@suse.de
Extend the fetch_pte function to also return the page-size
that is mapped by the returned pte.
Signed-off-by: Joerg Roedel jroe...@suse.de
---
drivers/iommu/amd_iommu.c | 52 -
drivers/iommu/amd_iommu_types.h | 6
Hi Linus,
The following changes since commit bc465aa9d045feb0e13b4a8f32cc33c1943f62d6:
Linux 4.0-rc5 (2015-03-22 16:50:21 -0700)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
tags/iommu-fixes-v4.0-rc6
for you to fetch changes up to
Hi Alex,
On Fri, Mar 27, 2015 at 10:24:22PM -0600, Alex Williamson wrote:
For 1-5,16
Reviewed-by: Alex Williamson alex.william...@redhat.com
Thanks a lot for your review.
My only comment/question is whether you'd want to consider using
ERR_PTR() return values from domain_alloc(). It's an
Hi Will,
On Mon, Mar 30, 2015 at 06:43:15PM +0100, Will Deacon wrote:
Whilst I'm still a bit worried about the ability of the IOMMU driver to do
very much in the -domain_alloc callback (since we don't know which IOMMU
instance the domain is for), it doesn't leave us any worse off than we
On Thu, Mar 26, 2015 at 01:43:03PM +0100, Joerg Roedel wrote:
Changes v1-v2:
* Rebased to v4.0-rc5
* Converted domain-types to a bit-field
Applied this series to the core branch.
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message
901 - 1000 of 6605 matches
Mail list logo