On Wed, 2021-11-10 at 07:29 +0200, Dafna Hirschfeld wrote:
>
> On 10.11.21 04:20, Yong Wu wrote:
> > On Tue, 2021-11-09 at 14:21 +0200, Dafna Hirschfeld wrote:
> > > Hi
> > > This patch is needed in order to update the tlb when a device is
> > > powered on.
> > > Could you send this patch alone wi
Hi Alex,
On 2021/11/10 7:56, Alex Williamson wrote:
Hi Baolu,
Have you looked into this?
I am looking at this.
I'm able to reproduce by starting and
destroying an assigned device VM several times. It seems like it came
in with Joerg's pull request for the v5.15 merge window. Bisecting
la
On 10.11.21 04:20, Yong Wu wrote:
On Tue, 2021-11-09 at 14:21 +0200, Dafna Hirschfeld wrote:
Hi
This patch is needed in order to update the tlb when a device is
powered on.
Could you send this patch alone without the whole series so it get
accepted easier?
Which SoC are you testing on? In p
On Tue, 2021-11-09 at 14:21 +0200, Dafna Hirschfeld wrote:
> Hi
> This patch is needed in order to update the tlb when a device is
> powered on.
> Could you send this patch alone without the whole series so it get
> accepted easier?
Which SoC are you testing on? In previous SoC, the IOMMU HW don't
Hi Baolu,
Have you looked into this? I'm able to reproduce by starting and
destroying an assigned device VM several times. It seems like it came
in with Joerg's pull request for the v5.15 merge window. Bisecting
lands me on 3f34f1259776 where intel-iommu added map/unmap_pages
support, but I'm
Hi Paul,
> Thank you for your reply.
Thank you for getting back to us with a good insight.
[...]
> > I am curious - why is this a problem? Are you power-cycling your servers
> > so often to the point where the cumulative time spent in enumerating PCI
> > devices and adding them later to IOMMU g
From: Tvrtko Ursulin
[ Upstream commit 5240aed2cd2594fb392239f11b9681e5e1591619 ]
Handling of intel_iommu kernel command line option should return "true" to
indicate option is valid and so avoid logging it as unknown by the core
parsing code.
Also log unknown sub-options at the notice level to
From: Sven Peter
[ Upstream commit 5a009fc1364170b240a4d351b345e69bb3728b3e ]
DART has an additional global register to control which streams are
isolated. This register is a bit redundant since DART_TCR can already
be used to control isolation and is usually initialized to DART_STREAM_ALL
by th
From: Tvrtko Ursulin
[ Upstream commit 5240aed2cd2594fb392239f11b9681e5e1591619 ]
Handling of intel_iommu kernel command line option should return "true" to
indicate option is valid and so avoid logging it as unknown by the core
parsing code.
Also log unknown sub-options at the notice level to
Dear Robin,
Thank you for your reply.
Am 09.11.21 um 16:31 schrieb Robin Murphy:
On 2021-11-06 10:42, Paul Menzel wrote:
Am 05.11.21 um 19:53 schrieb Bjorn Helgaas:
On Fri, Nov 05, 2021 at 12:56:09PM +0100, Paul Menzel wrote:
On a PowerEdge T440/021KCD, BIOS 2.11.2 04/22/2021, Linux 5.1
Dear Krzysztof,
Thank you for your reply.
Am 08.11.21 um 18:18 schrieb Krzysztof Wilczyński:
On a PowerEdge T440/021KCD, BIOS 2.11.2 04/22/2021, Linux 5.10.70 takes
almost five seconds to initialize PCI. According to the timestamps, 1.5 s
are from assigning the PCI devices to the 142 IOMMU g
The pull request you sent on Tue, 9 Nov 2021 14:53:16 +0100:
> git://git.infradead.org/users/hch/dma-mapping.git tags/dma-mapping-5.16
has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/372594985c786b40108a5201ca3192223d6c0c40
Thank you!
--
Deet-doot-dot, I am a bot.
ht
On 2021-11-06 10:42, Paul Menzel wrote:
Dear Bjorn,
Thank you for your quick reply.
Am 05.11.21 um 19:53 schrieb Bjorn Helgaas:
On Fri, Nov 05, 2021 at 12:56:09PM +0100, Paul Menzel wrote:
On a PowerEdge T440/021KCD, BIOS 2.11.2 04/22/2021, Linux 5.10.70 takes
almost five seconds to initi
On 2021-11-09 14:25, Christoph Hellwig wrote:
On Thu, Nov 04, 2021 at 12:36:16PM +, Robin Murphy wrote:
- *dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
- /* return the page pointer as the opaque cookie */
- return page;
- }
+
On 2021-11-09 14:10, Christoph Hellwig wrote:
On Thu, Nov 04, 2021 at 12:35:41PM +, Robin Murphy wrote:
On 2021-10-21 10:06, Christoph Hellwig wrote:
When dma_set_decrypted fails for the remapping case in dma_direct_alloc
we also need to unmap the pages before freeing them.
Signed-off-by:
On Thu, Nov 04, 2021 at 12:36:08PM +, Robin Murphy wrote:
> How about:
> remap = IS_ENABLED(CONFIG_DMA_DIRECT_REMAP);
>
> if (remap && ...)
>
> for a bit less indentation? FWIW I reckon it's slightly more obvious that
> way round.
Done.
On Thu, Nov 04, 2021 at 12:36:16PM +, Robin Murphy wrote:
>> -*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
>> -/* return the page pointer as the opaque cookie */
>> -return page;
>> -}
>> +!force_dma_unencrypted(dev) && !is_swiotlb_f
On Thu, Nov 04, 2021 at 12:35:59PM +, Robin Murphy wrote:
>> @@ -166,6 +166,7 @@ static void *dma_direct_alloc_from_pool(struct device
>> *dev, size_t size,
>> void *dma_direct_alloc(struct device *dev, size_t size,
>> dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
>>
On Thu, Nov 04, 2021 at 12:35:49PM +, Robin Murphy wrote:
> Given that this is consistent for all uses of dma_set_encrypted(), seems
> like it should be factored into the helper itself.
Done.
___
iommu mailing list
iommu@lists.linux-foundation.org
h
On Thu, Nov 04, 2021 at 12:35:41PM +, Robin Murphy wrote:
> On 2021-10-21 10:06, Christoph Hellwig wrote:
>> When dma_set_decrypted fails for the remapping case in dma_direct_alloc
>> we also need to unmap the pages before freeing them.
>>
>> Signed-off-by: Christoph Hellwig
>> ---
>> kernel
Just a small set of changes this time. The request dma_direct_alloc
cleanups are still under review and haven't made the cut.
The following changes since commit 519d81956ee277b4419c723adfb154603c2565ba:
Linux 5.15-rc6 (2021-10-17 20:00:13 -1000)
are available in the Git repository at:
git:
Hi
This patch is needed in order to update the tlb when a device is powered on.
Could you send this patch alone without the whole series so it get
accepted easier?
I can resend the patch on your behalf if you want.
Thanks,
Dafna
On 23.09.21 14:58, Yong Wu wrote:
Prepare for 2 HWs that sharing p
22 matches
Mail list logo
