On Fri, 2022-03-04 at 14:03 +, Robin Murphy wrote:
>
> OK, so either there's a mystery bug where IOVAs somehow get freed on
> offline CPUs, or the hotplug notifier isn't working correctly, or
> you've
> contrived a situation where alloc_iova_fast() is actually racing
> against
>
On 2022-03-04 9:22, John Garry wrote:
> On 04/03/2022 04:46, yf.wang--- via iommu wrote:
> > * MEDIATEK Confidentiality Notice
> > The
> > information contained in this e-mail message (including any
> > attachments) may be confidenti
On Fri, 2022-03-04 at 14:03 +, Robin Murphy wrote:
>
> OK, so either there's a mystery bug where IOVAs somehow get freed on
> offline CPUs, or the hotplug notifier isn't working correctly, or
> you've
> contrived a situation where alloc_iova_fast() is actually racing
> against
>
From: Yunfei Wang
In alloc_iova_fast function, if __alloc_and_insert_iova_range fail,
alloc_iova_fast will try flushing rcache and retry alloc iova, but
this has an issue:
Since __alloc_and_insert_iova_range fail will set the current alloc
iova size to max32_alloc_size (iovad->max32_alloc_size
From: Yunfei Wang
In alloc_iova_fast function, if __alloc_and_insert_iova_range fail,
alloc_iova_fast will try flushing rcache and retry alloc iova, but
this has an issue:
Since __alloc_and_insert_iova_range fail will set the current alloc
iova size to max32_alloc_size (iovad->max32_alloc_size
From: yf.w...@mediatek.com
On Thu, 2022-03-03 at 07:52 +0800, Miles Chen wrote:
> Thanks for your explanation.
>
> YF showed me some numbers yesterday and maybe we can have a further
> discussion in that test case. (It looks like that some iovas are
> freed but
> their pfn_lo(s) are less than
From: Yunfei Wang
In alloc_iova_fast function, if an iova alloc request fail,
it will free the iova ranges present in the percpu iova
rcaches and free global iova rcache and then retry, but
flushing CPU iova rcaches only for each online CPU, which
will cause incomplete rcache cleaning, and iova
On Fri, 2022-03-04 at 12:46 +0800, yf.w...@mediatek.com wrote:
> From: Yunfei Wang
>
> In alloc_iova_fast function, if an iova alloc request fail,
> it will free the iova ranges present in the percpu iova
> rcaches and free global iova rcache and then retry, but
> flushing CPU iova rcaches only
From: Yunfei Wang
The calling to kmem_cache_alloc for level 2 pgtable allocation may run
in atomic context, and it fails sometimes when DMA32 zone runs out of
memory.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to
From: Yunfei Wang
Add the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT support, so that allows
page table PA up to 35bit, not only in ZONE_DMA32.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 29 +
1 file changed, 25 insertions(+), 4
From: Yunfei Wang
When many devices share the same iova domain, iommu_dma_init_domain()
may be called at the same time. The checking of iovad->start_pfn will
all get false in iommu_dma_init_domain() and both enter init_iova_domain()
to do iovad initialization.
Fix this by protecting
From: Yunfei Wang
The calling to kmem_cache_alloc for level 2 pgtable allocation may run
in atomic context, and it fails sometimes when DMA32 zone runs out of
memory.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to
From: Yunfei Wang
Add the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT support, so that allows
page table PA up to 35bit, not only in ZONE_DMA32.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 29 +
1 file changed, 25 insertions(+), 4
From: Yunfei Wang
Add the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT support, so that allows
page table PA up to 35bit, not only in ZONE_DMA32.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 29 +
1 file changed, 25 insertions(+), 4
From: Yunfei Wang
The calling to kmem_cache_alloc for level 2 pgtable allocation may run
in atomic context, and it fails sometimes when DMA32 zone runs out of
memory.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to
On Thu, 2022-05-19 at 14:27 +0800, Miles Chen wrote:
> Hi Yunfei,
>
> > The calling to kmem_cache_alloc for level 2 pgtable allocation may
> > run
> > in atomic context, and it fails sometimes when DMA32 zone runs out
> > of
> > memory.
> >
> > Since Mediatek IOMMU hardware support at most 35bit
From: Yunfei Wang
The level 1 and level 2 pgtable are both allocated in ZONE_DMA32, and
may have two possible problem:
1.The level 2 pgtable is allocated in ZONE_DMA32 with atomic flag, and
it may fail if ZONE_DMA32 memory is used out.
2.Single memory feature will make ZONE_DMA32 empty, and
From: Yunfei Wang
The calling to kmem_cache_alloc for level 2 pgtable allocation may run
in atomic context, and it fails sometimes when DMA32 zone runs out of
memory.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to
On Thu, 2022-05-19 at 14:58 +0800, Yong Wu wrote:
> On Mon, 2022-05-16 at 22:16 +0800, yf.w...@mediatek.com wrote:
> > From: Yunfei Wang
> >
> > Add the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT support, so that
> > allows
> > page table PA up to 35bit, not only in ZONE_DMA32.
>
> Comment why
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA. So add
the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT to let level 1 and level 2
pgtable support at most 35bit PA.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 29
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA and
cause pgtable PA size larger than 32bit.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to bit35.
Signed-off-by: Ning Li
From: Yunfei Wang
The calling to kmem_cache_alloc for level 2 pgtable allocation may run
in atomic context, and it fails sometimes when DMA32 zone runs out of
memory.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to
From: Yunfei Wang
Add the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT support, so that allows
page table PA up to 35bit, not only in ZONE_DMA32.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 29 +
1 file changed, 25 insertions(+), 4
On Wed, 2022-06-22 at 09:28 +0800, Yong Wu wrote:
> On Thu, 2022-06-16 at 20:07 +0800, yf.w...@mediatek.com wrote:
> > From: Yunfei Wang
> >
> > Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA and
> > cause pgtable PA size larger than 32bit.
> >
> > Since Mediatek IOMMU hardware
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA and
cause pgtable PA size larger than 32bit.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to bit35.
Signed-off-by: Ning Li
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA. So add
the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT to let level 1 and level 2
pgtable support at most 35bit PA.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 13 +++--
This patchset adds MediaTek TTBR up to 35bit support for single normal zone.
Changes in v12:
- Update [PATCH 1/2]: remove GENMASK(31, 7)
- Update [PATCH 2/2]: remove MMU_PT_ADDR_MASK definition.
Changes in v11:
https://lore.kernel.org/linux-mediatek/20220630062508.23512-1-yf.w...@mediatek.com/
-
On Tue, 2022-06-14 at 13:56 +0100, Will Deacon wrote:
> Hi,
>
> For some reason, this series has landed in my spam folder so
> apologies
> for the delay :/
>
>
> > +static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
> > + struct io_pgtable_cfg *cfg)
>
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA and
cause pgtable PA size larger than 32bit.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to bit35.
Signed-off-by: Ning Li
From: Yunfei Wang
Rename MTK_IOMMU_TLB_ADDR to MTK_IOMMU_ADDR, and update MTK_IOMMU_ADDR
definition for better generality.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA. So add
the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT to let level 1 and level 2
pgtable support at most 35bit PA.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 14
On Wed, 2022-06-15 at 18:03 +0100, Robin Murphy wrote:
> On 2022-06-15 17:12, yf.w...@mediatek.com wrote:
> >
> > static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
> > struct io_pgtable_cfg *cfg)
> > {
> > @@ -240,10 +245,17 @@ static void
On Wed, 2022-06-15 at 18:14 +0100, Robin Murphy wrote:
> On 2022-06-15 17:12, yf.wang--- via iommu wrote:
> > From: Yunfei Wang
> >
> > Rename MTK_IOMMU_TLB_ADDR to MTK_IOMMU_ADDR, and update
> > MTK_IOMMU_ADDR
> > definition for better generality.
> >
>
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA and
cause pgtable PA size larger than 32bit.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to bit35.
Signed-off-by: Ning Li
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA. So add
the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT to let level 1 and level 2
pgtable support at most 35bit PA.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 17
On Wed, 2022-06-15 at 18:25 +0100, Robin Murphy wrote:
> On 2022-06-15 17:12, yf.wang--- via iommu wrote:
> > From: Yunfei Wang
> >
> > Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA. So
> > add
> > the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_E
From: Yunfei Wang
Rename MTK_IOMMU_TLB_ADDR to MTK_IOMMU_ADDR, and update MTK_IOMMU_ADDR
definition for better generality.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA and
cause pgtable PA size larger than 32bit.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to bit35.
Signed-off-by: Ning Li
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA. So add
the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT to let level 1 and level 2
pgtable support at most 35bit PA.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 14
On Thu, 2022-05-19 at 14:58 +0800, Yong Wu wrote:
> On Mon, 2022-05-16 at 22:16 +0800, yf.w...@mediatek.com wrote:
> > From: Yunfei Wang
> >
> > Add the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT support, so that
> > allows
> > page table PA up to 35bit, not only in ZONE_DMA32.
>
> Comment why
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA and
cause pgtable PA size larger than 32bit.
Since Mediatek IOMMU hardware support at most 35bit PA in pgtable,
so add a quirk to allow the PA of pgtables support up to bit35.
Signed-off-by: Ning Li
From: Yunfei Wang
Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA. So add
the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT to let level 1 and level 2
pgtable support at most 35bit PA.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
---
drivers/iommu/mtk_iommu.c | 12 +++-
From: Yunfei Wang
The data type of the return value of the iommu_map_sg_atomic
is ssize_t, but the data type of iova size is size_t,
e.g. one is int while the other is unsigned int.
When iommu_map_sg_atomic return value is compared with iova size,
it will force the signed int to be converted to
From: Yunfei Wang
The calling to kmem_cache_alloc for level 2 page table allocation may
run in atomic context, and it fails sometimes when DMA32 zone runs out
of memory.
Since Mediatek IOMMU hardware support at most 35bit PA in page table,
so add a quirk to allow the PA of level 2 pgtable
From: Yunfei Wang
Add the quirk IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT support, so that
level 2 page table can allocate in normal memory.
Signed-off-by: Ning Li
Signed-off-by: Yunfei Wang
Cc: # 5.10.*
---
drivers/iommu/mtk_iommu.c | 7 ++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff
45 matches
Mail list logo
