On Thu, Jan 21, 2021 at 07:12:36PM +, Jonathan Cameron wrote:
> > @@ -2502,6 +2647,7 @@ static void arm_smmu_release_device(struct device
> > *dev)
> >
> > master = dev_iommu_priv_get(dev);
> > WARN_ON(arm_smmu_master_sva_enabled(master));
> > +
If a group with non-pinned-page dirty scope is detached with dirty
logging enabled, we should fully populate the dirty bitmaps at the
time it's removed since we don't know the extent of its previous DMA,
nor will the group be present to trigger the full bitmap when the user
retrieves the dirty
v3:
- Populate bitmap unconditionally.
- Sanity check notifier when remove all domains.
v2:
- Address suggestions from Alex.
- Remove unnecessary patches.
Keqian Zhu (2):
vfio/iommu_type1: Populate full dirty when detach non-pinned group
vfio/iommu_type1: Fix some sanity checks in
vfio_sanity_check_pfn_list() is used to check whether pfn_list and
notifier are empty when remove the external domain, so it makes a
wrong assumption that only external domain will use the pinning
interface.
Now we apply the pfn_list check when a vfio_dma is removed and apply
the notifier check
On Fri, 22 Jan 2021 09:51:20 +0100
Jean-Philippe Brucker wrote:
> On Thu, Jan 21, 2021 at 07:12:36PM +, Jonathan Cameron wrote:
> > > @@ -2502,6 +2647,7 @@ static void arm_smmu_release_device(struct device
> > > *dev)
> > >
> > > master = dev_iommu_priv_get(dev);
> > >
On 2021/1/21 4:47, Dave Jiang wrote:
>
> On 1/8/2021 7:52 AM, Jean-Philippe Brucker wrote:
>> The IOPF (I/O Page Fault) feature is now enabled independently from the
>> SVA feature, because some IOPF implementations are device-specific and
>> do not require IOMMU support for PCIe PRI or Arm SMMU
On Thu, Nov 26, 2020 at 11:42:30AM +0800, Zhen Lei wrote:
> When changing from a set of pages/smaller blocks to a larger block for an
> address, the software should follow the sequence of BBML processing.
>
> When changing from a block to a set of pages/smaller blocks for an
> address, there's no
On 2021-01-22 12:51, Will Deacon wrote:
On Thu, Nov 26, 2020 at 11:42:30AM +0800, Zhen Lei wrote:
When changing from a set of pages/smaller blocks to a larger block for an
address, the software should follow the sequence of BBML processing.
When changing from a block to a set of pages/smaller
Hi Jean,
On 1/21/21 1:36 PM, Jean-Philippe Brucker wrote:
> When handling faults from the event or PRI queue, we need to find the
> struct device associated with a SID. Add a rb_tree to keep track of
> SIDs.
>
> Acked-by: Jonathan Cameron
> Signed-off-by: Jean-Philippe Brucker
Reviewed-by:
To support sharing page tables with the CPU, the SMMU can participate in
Broadcast TLB Maintenance (BTM), where TLB invalidate instructions from
the CPU are received by the SMMU. For platforms that do no implement BTM
[1], it is still possible to use SVA, by sending all TLB invalidations
through
Extract some of the cmd initialization and the ATC invalidation from
arm_smmu_tlb_inv_range(), to allow an MMU notifier to invalidate a VA
range by ASID.
Signed-off-by: Jean-Philippe Brucker
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 62 -
1 file changed, 35
When BTM isn't supported by the SMMU, send invalidations on the
command queue.
Signed-off-by: Jean-Philippe Brucker
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 3 +++
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 14 +++---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
ARMv8.1 extensions added Virtualization Host Extensions (VHE), which allow
to run a host kernel at EL2. When using normal DMA, Device and CPU address
spaces are dissociated, and do not need to implement the same
capabilities, so VHE hasn't been used in the SMMU until now.
With shared address
On 2021-01-22 12:41, Will Deacon wrote:
On Tue, Nov 24, 2020 at 12:15:58PM -0700, Jordan Crouse wrote:
Call report_iommu_fault() to allow upper-level drivers to register their
own fault handlers.
Signed-off-by: Jordan Crouse
---
drivers/iommu/arm/arm-smmu/arm-smmu.c | 16 +---
On Tue, Nov 24, 2020 at 12:15:58PM -0700, Jordan Crouse wrote:
> Call report_iommu_fault() to allow upper-level drivers to register their
> own fault handlers.
>
> Signed-off-by: Jordan Crouse
> ---
>
> drivers/iommu/arm/arm-smmu/arm-smmu.c | 16 +---
> 1 file changed, 13
No functional change.
Signed-off-by: Zhen Lei
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 6 +-
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index
On Fri, 22 Jan 2021 12:52:55 +0100
Jean-Philippe Brucker wrote:
> To support sharing page tables with the CPU, the SMMU can participate in
> Broadcast TLB Maintenance (BTM), where TLB invalidate instructions from
> the CPU are received by the SMMU. For platforms that do no implement BTM
> [1],
On Thu, Jan 21, 2021 at 02:09:42PM +, Robin Murphy wrote:
> Since we now keep track of page 1 via a separate pointer that already
> encapsulates aliasing to page 0 as necessary, we can remove the clunky
> fixup routine and simply use the relevant bases directly. The current
> architecture spec
On Wed, 20 Jan 2021 17:40:04 -0800, Bjorn Andersson wrote:
> Add compatible for the ARM SMMU found in the Qualcomm SC8180x platform.
Applied to will (for-joerg/arm-smmu/updates), thanks!
[1/2] dt-bindings: arm-smmu-qcom: Add Qualcomm SC8180X compatible
On Thu, 21 Jan 2021 14:09:42 +, Robin Murphy wrote:
> Since we now keep track of page 1 via a separate pointer that already
> encapsulates aliasing to page 0 as necessary, we can remove the clunky
> fixup routine and simply use the relevant bases directly. The current
> architecture spec
On Fri, 22 Jan 2021 21:14:48 +0800, Zhen Lei wrote:
> No functional change.
Applied to will (for-joerg/arm-smmu/updates), thanks!
[1/1] iommu/arm-smmu-v3: Use DEFINE_RES_MEM() to simplify code
https://git.kernel.org/will/c/932bc8c7d742
Cheers,
--
Will
https://fixes.arm64.dev
On Fri, 15 Jan 2021 14:33:21 +0530, Vinod Koul wrote:
> Add compatible string for sm8350 iommu to documentation.
Applied to will (for-joerg/arm-smmu/updates), thanks!
[1/2] dt-bindings: arm-smmu: Add sm8350 compatible string
https://git.kernel.org/will/c/70b5b6a6daea
[2/2] iommu:
On Fri, Jan 22, 2021 at 12:52:56PM +0100, Jean-Philippe Brucker wrote:
> Extract some of the cmd initialization and the ATC invalidation from
> arm_smmu_tlb_inv_range(), to allow an MMU notifier to invalidate a VA
> range by ASID.
>
> Signed-off-by: Jean-Philippe Brucker
> ---
>
On 2021-01-22 11:52, Jean-Philippe Brucker wrote:
Extract some of the cmd initialization and the ATC invalidation from
arm_smmu_tlb_inv_range(), to allow an MMU notifier to invalidate a VA
range by ASID.
Signed-off-by: Jean-Philippe Brucker
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c |
On 2021/1/22 21:00, Robin Murphy wrote:
> On 2021-01-22 12:51, Will Deacon wrote:
>> On Thu, Nov 26, 2020 at 11:42:30AM +0800, Zhen Lei wrote:
>>> When changing from a set of pages/smaller blocks to a larger block for an
>>> address, the software should follow the sequence of BBML processing.
On Fri, Jan 22, 2021 at 09:21:20PM +0800, Leizhen (ThunderTown) wrote:
> On 2021/1/22 21:00, Robin Murphy wrote:
> > On 2021-01-22 12:51, Will Deacon wrote:
> >> On Thu, Nov 26, 2020 at 11:42:30AM +0800, Zhen Lei wrote:
> >>> - tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data);
> >>> -
On Tue, Jan 12, 2021 at 09:22:23PM -0600, Rob Herring wrote:
> On Thu, 07 Jan 2021 20:01:18 +0530, Manivannan Sadhasivam wrote:
> > Add devicetree binding for Qualcomm SDX55 SMMU.
> >
> > Cc: Will Deacon
> > Cc: Robin Murphy
> > Cc: Joerg Roedel
> > Cc: iommu@lists.linux-foundation.org
> >
On Fri, Jan 22, 2021 at 01:14:49PM +, Will Deacon wrote:
> On Tue, Jan 12, 2021 at 09:22:23PM -0600, Rob Herring wrote:
> > On Thu, 07 Jan 2021 20:01:18 +0530, Manivannan Sadhasivam wrote:
> > > Add devicetree binding for Qualcomm SDX55 SMMU.
> > >
> > > Cc: Will Deacon
> > > Cc: Robin
On 1/22/2021 4:53 AM, Zhou Wang wrote:
On 2021/1/21 4:47, Dave Jiang wrote:
On 1/8/2021 7:52 AM, Jean-Philippe Brucker wrote:
The IOPF (I/O Page Fault) feature is now enabled independently from the
SVA feature, because some IOPF implementations are device-specific and
do not require IOMMU
Hi Vivek,
> -Original Message-
> From: Vivek Kumar Gautam [mailto:vivek.gau...@arm.com]
> Sent: 21 January 2021 17:34
> To: Auger Eric ; linux-ker...@vger.kernel.org;
> linux-arm-ker...@lists.infradead.org; iommu@lists.linux-foundation.org;
> virtualizat...@lists.linux-foundation.org
>
On 2021-01-21 21:30, isa...@codeaurora.org wrote:
On 2021-01-12 08:00, Robin Murphy wrote:
On 2021-01-11 14:54, Isaac J. Manjarres wrote:
The iommu_map_sg() code currently iterates through the given
scatter-gather list, and in the worst case, invokes iommu_map()
for each element in the
On 2021-01-22 11:52, Jean-Philippe Brucker wrote:
When BTM isn't supported by the SMMU, send invalidations on the
command queue.
Signed-off-by: Jean-Philippe Brucker
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 3 +++
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 14
On Fri, Jan 22, 2021 at 02:04:55PM +, Robin Murphy wrote:
> > @@ -182,9 +183,13 @@ static void arm_smmu_mm_invalidate_range(struct
> > mmu_notifier *mn,
> > unsigned long start, unsigned long end)
> > {
> > struct arm_smmu_mmu_notifier *smmu_mn =
ARMv8.1 extensions added Virtualization Host Extensions (VHE), which allow
to run a host kernel at EL2. When using normal DMA, Device and CPU address
spaces are dissociated, and do not need to implement the same
capabilities, so VHE hasn't been used in the SMMU until now.
With shared address
When BTM isn't supported by the SMMU, send invalidations on the
command queue.
Reviewed-by: Jonathan Cameron
Signed-off-by: Jean-Philippe Brucker
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 3 +++
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 10 +++---
Since v1 [1]
* Renamed arm_smmu_tlb_inv_range()
* Removed unnecessary tlb_inv_command variable
* Rebased onto for-joerg/arm-smmu/updates (oddly I didn't get any
conflict, I hope it will apply this time)
[1]
https://lore.kernel.org/linux-iommu/20210122115257.2502526-1-jean-phili...@linaro.org/
Extract some of the cmd initialization and the ATC invalidation from
arm_smmu_tlb_inv_range(), to allow an MMU notifier to invalidate a VA
range by ASID.
Reviewed-by: Jonathan Cameron
Signed-off-by: Jean-Philippe Brucker
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 63
On 2021-01-22 16:18, Chuck Lever wrote:
On Jan 21, 2021, at 10:00 PM, Lu Baolu wrote:
+Isaac
On 1/22/21 3:09 AM, Chuck Lever wrote:
On Jan 18, 2021, at 1:00 PM, Robin Murphy wrote:
On 2021-01-18 16:18, Chuck Lever wrote:
On Jan 12, 2021, at 9:38 AM, Will Deacon wrote:
[Expanding cc
> On Jan 21, 2021, at 10:00 PM, Lu Baolu wrote:
>
> +Isaac
>
> On 1/22/21 3:09 AM, Chuck Lever wrote:
>>> On Jan 18, 2021, at 1:00 PM, Robin Murphy wrote:
>>>
>>> On 2021-01-18 16:18, Chuck Lever wrote:
> On Jan 12, 2021, at 9:38 AM, Will Deacon wrote:
>
> [Expanding cc list
> On Jan 22, 2021, at 12:38 PM, Robin Murphy wrote:
>
> On 2021-01-22 16:18, Chuck Lever wrote:
>>> On Jan 21, 2021, at 10:00 PM, Lu Baolu wrote:
>>>
>>> +Isaac
>>>
>>> On 1/22/21 3:09 AM, Chuck Lever wrote:
> On Jan 18, 2021, at 1:00 PM, Robin Murphy wrote:
>
> On 2021-01-18
On Fri, 22 Jan 2021 16:10:53 +0100, Jean-Philippe Brucker wrote:
> Since v1 [1]
> * Renamed arm_smmu_tlb_inv_range()
> * Removed unnecessary tlb_inv_command variable
> * Rebased onto for-joerg/arm-smmu/updates (oddly I didn't get any
> conflict, I hope it will apply this time)
>
> [1]
>
On Thu, Jan 07, 2021 at 08:29:02PM +0800, Yong Wu wrote:
> This patchset is to improve tlb flushing performance in iommu_map/unmap
> for MediaTek IOMMU.
>
> For iommu_map, currently MediaTek IOMMU use IO_PGTABLE_QUIRK_TLBI_ON_MAP
> to do tlb_flush for each a memory chunk. this is so unnecessary.
On Thu, Jan 21, 2021 at 02:24:27PM +0800, Yong Wu wrote:
> In this file, we have 2 drivers, smi-common and smi-larb.
> Use platform_register_drivers.
>
> Signed-off-by: Yong Wu
> ---
> drivers/memory/mtk-smi.c | 25 ++---
> 1 file changed, 6 insertions(+), 19 deletions(-)
On Thu, Jan 21, 2021 at 02:24:28PM +0800, Yong Wu wrote:
> The config MTK_SMI always depends on MTK_IOMMU which is built-in
> currently. Thus we don't have module_exit before. This patch adds
> module_exit and module_license. It is a preparing patch for supporting
> MTK_SMI could been built as a
On Thu, Jan 21, 2021 at 02:24:29PM +0800, Yong Wu wrote:
> This patch switches MTK_SMI to tristate. Support it could be 'm'.
>
> Meanwhile, Fix a build issue while MTK_SMI is built as module.
s/Fix/fix.
What error is being fixed here? How can I reproduce it? Aren't you just
adjusting it to
45 matches
Mail list logo
