* [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU
@ 2022-04-04 16:47 Mario Limonciello via iommu
2022-04-04 16:47 ` [PATCH 1/2] swiotlb: Check that slabs have been allocated when requested Mario Limonciello via iommu
` (2 more replies)
0 siblings, 3 replies; 6+ messages in thread
From: Mario Limonciello via iommu @ 2022-04-04 16:47 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon
Cc: Hegde Vasant, open list, Christoph Hellwig,
open list:IOMMU DRIVERS, Mario Limonciello, Robin Murphy
It's been observed that plugging in a TBT3 NVME device to a port marked
with ExternalFacingPort that some DMA transactions occur that are not a
full page and so the DMA API attempts to use software bounce buffers
instead of relying upon the IOMMU translation.
This doesn't work and leads to messaging like:
swiotlb buffer is full (sz: 4096 bytes), total 0 (slots), used 0 (slots)
The bounce buffers were originally set up, but torn down during
the boot process.
* This happens because as part of IOMMU initialization
`amd_iommu_init_dma_ops` gets called and resets the global swiotlb to 0.
* When late_init gets called `pci_swiotlb_late_init` `swiotlb_exit` is
called and the buffers are torn down.
This can be observed in the logs:
```
[ 0.407286] AMD-Vi: Extended features (0x246577efa2254afa): PPR NX GT [5] IA GA PC GA_vAPIC
[ 0.407291] AMD-Vi: Interrupt remapping enabled
[ 0.407292] AMD-Vi: Virtual APIC enabled
[ 0.407872] software IO TLB: tearing down default memory pool
```
This series adds some better messaging in case something like this comes
up again and also adds checks that swiotlb really is active before
trying to use it.
Mario Limonciello (2):
swiotlb: Check that slabs have been allocated when requested
iommu: Don't use swiotlb unless it's active
drivers/iommu/dma-iommu.c | 3 ++-
kernel/dma/swiotlb.c | 5 +++++
2 files changed, 7 insertions(+), 1 deletion(-)
--
2.34.1
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH 1/2] swiotlb: Check that slabs have been allocated when requested
2022-04-04 16:47 [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU Mario Limonciello via iommu
@ 2022-04-04 16:47 ` Mario Limonciello via iommu
2022-04-04 16:47 ` [PATCH 2/2] iommu: Don't use swiotlb unless it's active Mario Limonciello via iommu
2022-04-04 16:54 ` [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU Christoph Hellwig
2 siblings, 0 replies; 6+ messages in thread
From: Mario Limonciello via iommu @ 2022-04-04 16:47 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon
Cc: Hegde Vasant, open list, Christoph Hellwig,
open list:IOMMU DRIVERS, Mario Limonciello, Robin Murphy
If the IOMMU is in use and an untrusted device is connected to an external
facing port but the address requested isn't page aligned will cause the
kernel to attempt to use bounce buffers.
If the bounce buffers have not been allocated however, this leads
to messages like this:
swiotlb buffer is full (sz: 4096 bytes), total 0 (slots), used 0 (slots)
Clarify the error message because the buffer isn't full, it doesn't
exist!
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
kernel/dma/swiotlb.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 73a41cec9e38..d2a20cedf0d2 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -591,6 +591,11 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
if (!mem)
panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+ if (!mem->nslabs) {
+ dev_warn_once(dev, "No slabs have been configured, unable to use SWIOTLB buffer");
+ return (phys_addr_t)DMA_MAPPING_ERROR;
+ }
+
if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
--
2.34.1
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH 2/2] iommu: Don't use swiotlb unless it's active
2022-04-04 16:47 [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU Mario Limonciello via iommu
2022-04-04 16:47 ` [PATCH 1/2] swiotlb: Check that slabs have been allocated when requested Mario Limonciello via iommu
@ 2022-04-04 16:47 ` Mario Limonciello via iommu
2022-04-04 16:54 ` [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU Christoph Hellwig
2 siblings, 0 replies; 6+ messages in thread
From: Mario Limonciello via iommu @ 2022-04-04 16:47 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon
Cc: Hegde Vasant, open list, Christoph Hellwig,
open list:IOMMU DRIVERS, Mario Limonciello, Robin Murphy
The helper function `dev_use_swiotlb` is used for various decision
making points for how to handle DMA mapping requests.
If the kernel doesn't have any memory allocated for swiotlb to use, then
an untrusted device being connected to the system may fail to initialize
when a request is made.
To avoid this situation, don't mark the use of swiotlb when it has not
been set up.
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
drivers/iommu/dma-iommu.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 09f6e1c0f9c0..92ca136c8a12 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -504,7 +504,8 @@ static bool dev_is_untrusted(struct device *dev)
static bool dev_use_swiotlb(struct device *dev)
{
- return IS_ENABLED(CONFIG_SWIOTLB) && dev_is_untrusted(dev);
+ return IS_ENABLED(CONFIG_SWIOTLB) && dev_is_untrusted(dev) \
+ && is_swiotlb_active(dev);
}
/**
--
2.34.1
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
^ permalink raw reply related [flat|nested] 6+ messages in thread* Re: [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU
2022-04-04 16:47 [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU Mario Limonciello via iommu
2022-04-04 16:47 ` [PATCH 1/2] swiotlb: Check that slabs have been allocated when requested Mario Limonciello via iommu
2022-04-04 16:47 ` [PATCH 2/2] iommu: Don't use swiotlb unless it's active Mario Limonciello via iommu
@ 2022-04-04 16:54 ` Christoph Hellwig
2022-04-04 17:05 ` Limonciello, Mario via iommu
2 siblings, 1 reply; 6+ messages in thread
From: Christoph Hellwig @ 2022-04-04 16:54 UTC (permalink / raw)
To: Mario Limonciello
Cc: Will Deacon, Hegde Vasant, open list, Christoph Hellwig,
open list:IOMMU DRIVERS, Robin Murphy
On Mon, Apr 04, 2022 at 11:47:05AM -0500, Mario Limonciello wrote:
> The bounce buffers were originally set up, but torn down during
> the boot process.
> * This happens because as part of IOMMU initialization
> `amd_iommu_init_dma_ops` gets called and resets the global swiotlb to 0.
> * When late_init gets called `pci_swiotlb_late_init` `swiotlb_exit` is
> called and the buffers are torn down.
I think the proper thing is to do this:
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index a1ada7bff44e6..079694f894b85 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1838,17 +1838,10 @@ void amd_iommu_domain_update(struct protection_domain *domain)
amd_iommu_domain_flush_complete(domain);
}
-static void __init amd_iommu_init_dma_ops(void)
-{
- swiotlb = (iommu_default_passthrough() || sme_me_mask) ? 1 : 0;
-}
-
int __init amd_iommu_init_api(void)
{
int err;
- amd_iommu_init_dma_ops();
-
err = bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
if (err)
return err;
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
^ permalink raw reply related [flat|nested] 6+ messages in thread* RE: [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU
2022-04-04 16:54 ` [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU Christoph Hellwig
@ 2022-04-04 17:05 ` Limonciello, Mario via iommu
2022-04-04 17:24 ` Christoph Hellwig
0 siblings, 1 reply; 6+ messages in thread
From: Limonciello, Mario via iommu @ 2022-04-04 17:05 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Will Deacon, Hegde, Vasant, open list, open list:IOMMU DRIVERS,
Robin Murphy
[AMD Official Use Only]
> On Mon, Apr 04, 2022 at 11:47:05AM -0500, Mario Limonciello wrote:
> > The bounce buffers were originally set up, but torn down during
> > the boot process.
> > * This happens because as part of IOMMU initialization
> > `amd_iommu_init_dma_ops` gets called and resets the global swiotlb to 0.
> > * When late_init gets called `pci_swiotlb_late_init` `swiotlb_exit` is
> > called and the buffers are torn down.
>
> I think the proper thing is to do this:
>
> diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
> index a1ada7bff44e6..079694f894b85 100644
> --- a/drivers/iommu/amd/iommu.c
> +++ b/drivers/iommu/amd/iommu.c
> @@ -1838,17 +1838,10 @@ void amd_iommu_domain_update(struct
> protection_domain *domain)
> amd_iommu_domain_flush_complete(domain);
> }
>
> -static void __init amd_iommu_init_dma_ops(void)
> -{
> - swiotlb = (iommu_default_passthrough() || sme_me_mask) ? 1 : 0;
> -}
> -
> int __init amd_iommu_init_api(void)
> {
> int err;
>
> - amd_iommu_init_dma_ops();
> -
> err = bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
> if (err)
> return err;
I do expect that solves it as well. The reason I submitted the way I did is
that there seemed to be a strong affinity for having swiotlb disabled when IOMMU
is enabled on AMD IOMMU. The original code that disabled SWIOTLB in AMD IOMMU
dates all the way back to 2.6.33 (commit 75f1cdf1dda92cae037ec848ae63690d91913eac)
and it has ping ponged around since then to add more criteria that it would be or wouldn't
be disabled, but was never actually dropped until your suggestion.
If the consensus is that it should be dropped, I'll validate it does help and then send that out
as a v2. I do think that my messaging patch (1/2) may still be useful for debugging in the
future if for another reason SWIOTLB is disabled.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU
2022-04-04 17:05 ` Limonciello, Mario via iommu
@ 2022-04-04 17:24 ` Christoph Hellwig
0 siblings, 0 replies; 6+ messages in thread
From: Christoph Hellwig @ 2022-04-04 17:24 UTC (permalink / raw)
To: Limonciello, Mario
Cc: Will Deacon, Hegde, Vasant, open list, Christoph Hellwig,
open list:IOMMU DRIVERS, Robin Murphy
On Mon, Apr 04, 2022 at 05:05:00PM +0000, Limonciello, Mario wrote:
> I do expect that solves it as well. The reason I submitted the way I
> did is that there seemed to be a strong affinity for having swiotlb
> disabled when IOMMU is enabled on AMD IOMMU. The original code that
> disabled SWIOTLB in AMD IOMMU dates all the way back to 2.6.33 (commit
> 75f1cdf1dda92cae037ec848ae63690d91913eac) and it has ping ponged around
> since then to add more criteria that it would be or wouldn't be
> disabled, but was never actually dropped until your suggestion.
Well, that was before we started bounce buffering for untrusted devices.
We can't just have a less secure path for them because some conditions
are not met. Especially given that most AMD systems right now probably
don't have that swiotlb buffer if the IOMMU is enabled. So not freeing
the buffer in this case is a bug fix that is needed to properly
support the bounce buffering for unaligned I/O to untrusted devices.
> I do think that my messaging patch (1/2) may still be useful for
> debugging in the future if for another reason SWIOTLB is disabled.
I think the warning is useful. For dma-direct we have it in the caller
so I'd be tempted todo the same for dma-iommu.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2022-04-04 17:24 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2022-04-04 16:47 [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU Mario Limonciello via iommu
2022-04-04 16:47 ` [PATCH 1/2] swiotlb: Check that slabs have been allocated when requested Mario Limonciello via iommu
2022-04-04 16:47 ` [PATCH 2/2] iommu: Don't use swiotlb unless it's active Mario Limonciello via iommu
2022-04-04 16:54 ` [PATCH 0/2] Fix issues with untrusted devices and AMD IOMMU Christoph Hellwig
2022-04-04 17:05 ` Limonciello, Mario via iommu
2022-04-04 17:24 ` Christoph Hellwig
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox