Re: [PATCH 5.4 v3 1/1] iommu/vt-d: Fix agaw for a supported 48 bit guest address width
Hi Greg, I don’t have any commit ID since the fix is not in mainline or any Linus’ tree yet. The driver has completely changed for newer stable versions (and also mainline) and the fix only applies for 5.4, 4.19, and 4.14 stable kernels. Thanks, Saeed > On Apr 13, 2021, at 12:32 AM, Greg KH wrote: > > > On Mon, Apr 12, 2021 at 01:27:35PM -0700, Saeed Mirzamohammadi wrote: >> The IOMMU driver calculates the guest addressability for a DMA request >> based on the value of the mgaw reported from the IOMMU. However, this >> is a fused value and as mentioned in the spec, the guest width >> should be calculated based on the minimum of supported adjusted guest >> address width (SAGAW) and MGAW. >> >> This is from specification: >> "Guest addressability for a given DMA request is limited to the >> minimum of the value reported through this field and the adjusted >> guest address width of the corresponding page-table structure. >> (Adjusted guest address widths supported by hardware are reported >> through the SAGAW field)." >> >> This causes domain initialization to fail and following >> errors appear for EHCI PCI driver: >> >> [2.486393] ehci-pci :01:00.4: EHCI Host Controller >> [2.486624] ehci-pci :01:00.4: new USB bus registered, assigned bus >> number 1 >> [2.489127] ehci-pci :01:00.4: DMAR: Allocating domain failed >> [2.489350] ehci-pci :01:00.4: DMAR: 32bit DMA uses non-identity >> mapping >> [2.489359] ehci-pci :01:00.4: can't setup: -12 >> [2.489531] ehci-pci :01:00.4: USB bus 1 deregistered >> [2.490023] ehci-pci :01:00.4: init :01:00.4 fail, -12 >> [2.490358] ehci-pci: probe of :01:00.4 failed with error -12 >> >> This issue happens when the value of the sagaw corresponds to a >> 48-bit agaw. This fix updates the calculation of the agaw based on >> the minimum of IOMMU's sagaw value and MGAW. >> >> Cc: sta...@vger.kernel.org >> Signed-off-by: Saeed Mirzamohammadi >> Tested-by: Camille Lu >> Reviewed-by: Lu Baolu > > What is the git commit id of this patch in Linus's tree? > > thanks, > > greg k-h ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Re: [PATCH 5.4 v3 1/1] iommu/vt-d: Fix agaw for a supported 48 bit guest address width
Hi Greg, I don’t have any commit ID since the fix is not in mainline or any Linus’ tree yet. The driver has completely changed for newer stable versions (and also mainline) and the fix only applies for 5.4, 4.19, and 4.14 stable kernels. Thanks, Saeed > On Apr 13, 2021, at 12:32 AM, Greg KH wrote: > > To: line so that we can correctly respond to patches...> > > On Mon, Apr 12, 2021 at 01:27:35PM -0700, Saeed Mirzamohammadi wrote: >> The IOMMU driver calculates the guest addressability for a DMA request >> based on the value of the mgaw reported from the IOMMU. However, this >> is a fused value and as mentioned in the spec, the guest width >> should be calculated based on the minimum of supported adjusted guest >> address width (SAGAW) and MGAW. >> >> This is from specification: >> "Guest addressability for a given DMA request is limited to the >> minimum of the value reported through this field and the adjusted >> guest address width of the corresponding page-table structure. >> (Adjusted guest address widths supported by hardware are reported >> through the SAGAW field)." >> >> This causes domain initialization to fail and following >> errors appear for EHCI PCI driver: >> >> [2.486393] ehci-pci :01:00.4: EHCI Host Controller >> [2.486624] ehci-pci :01:00.4: new USB bus registered, assigned bus >> number 1 >> [2.489127] ehci-pci :01:00.4: DMAR: Allocating domain failed >> [2.489350] ehci-pci :01:00.4: DMAR: 32bit DMA uses non-identity >> mapping >> [2.489359] ehci-pci :01:00.4: can't setup: -12 >> [2.489531] ehci-pci :01:00.4: USB bus 1 deregistered >> [2.490023] ehci-pci :01:00.4: init :01:00.4 fail, -12 >> [2.490358] ehci-pci: probe of :01:00.4 failed with error -12 >> >> This issue happens when the value of the sagaw corresponds to a >> 48-bit agaw. This fix updates the calculation of the agaw based on >> the minimum of IOMMU's sagaw value and MGAW. >> >> Cc: sta...@vger.kernel.org >> Signed-off-by: Saeed Mirzamohammadi >> Tested-by: Camille Lu >> Reviewed-by: Lu Baolu > > What is the git commit id of this patch in Linus's tree? > > thanks, > > greg k-h ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH 5.4 v3 1/1] iommu/vt-d: Fix agaw for a supported 48 bit guest address width
The IOMMU driver calculates the guest addressability for a DMA request based on the value of the mgaw reported from the IOMMU. However, this is a fused value and as mentioned in the spec, the guest width should be calculated based on the minimum of supported adjusted guest address width (SAGAW) and MGAW. This is from specification: "Guest addressability for a given DMA request is limited to the minimum of the value reported through this field and the adjusted guest address width of the corresponding page-table structure. (Adjusted guest address widths supported by hardware are reported through the SAGAW field)." This causes domain initialization to fail and following errors appear for EHCI PCI driver: [2.486393] ehci-pci :01:00.4: EHCI Host Controller [2.486624] ehci-pci :01:00.4: new USB bus registered, assigned bus number 1 [2.489127] ehci-pci :01:00.4: DMAR: Allocating domain failed [2.489350] ehci-pci :01:00.4: DMAR: 32bit DMA uses non-identity mapping [2.489359] ehci-pci :01:00.4: can't setup: -12 [2.489531] ehci-pci :01:00.4: USB bus 1 deregistered [2.490023] ehci-pci :01:00.4: init :01:00.4 fail, -12 [2.490358] ehci-pci: probe of :01:00.4 failed with error -12 This issue happens when the value of the sagaw corresponds to a 48-bit agaw. This fix updates the calculation of the agaw based on the minimum of IOMMU's sagaw value and MGAW. Cc: sta...@vger.kernel.org Signed-off-by: Saeed Mirzamohammadi Tested-by: Camille Lu Reviewed-by: Lu Baolu --- Change in v2: - Added cap_width to calculate AGAW based on the minimum value of MGAW and AGAW. Changes in v3: - Added Lu's Reviewed-by. - Added stable list. --- drivers/iommu/intel-iommu.c | 7 --- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 953d86ca6d2b..a2a03df97704 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1853,7 +1853,7 @@ static inline int guestwidth_to_adjustwidth(int gaw) static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, int guest_width) { - int adjust_width, agaw; + int adjust_width, agaw, cap_width; unsigned long sagaw; int err; @@ -1867,8 +1867,9 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, domain_reserve_special_ranges(domain); /* calculate AGAW */ - if (guest_width > cap_mgaw(iommu->cap)) - guest_width = cap_mgaw(iommu->cap); + cap_width = min_t(int, cap_mgaw(iommu->cap), agaw_to_width(iommu->agaw)); + if (guest_width > cap_width) + guest_width = cap_width; domain->gaw = guest_width; adjust_width = guestwidth_to_adjustwidth(guest_width); agaw = width_to_agaw(adjust_width); -- 2.27.0 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Re: [PATCH 5.4 v2 1/1] iommu/vt-d: Fix agaw for a supported 48 bit guest address width
Hi Greg, This patch fixes an issue with the IOMMU driver and it only applies to 5.4, 4.19, and 4.14 stable kernels. May I know when this patch would be available in the stable kernels? Subject: iommu/vt-d: Fix agaw for a supported 48 bit guest address width Thanks, Saeed > On Apr 11, 2021, at 4:49 PM, Lu Baolu wrote: > > I guess you need to ask Greg KH with this > Cc-ing to sta...@vger.kernel.org. > > Best regards, > baolu > > On 2021/4/12 3:36, Saeed Mirzamohammadi wrote: >> Hi Lu, >> Thanks for the review. May I know when do we expect this to be applied to >> 5.4? >> Thanks, >> Saeed >>> On Apr 7, 2021, at 5:25 PM, Lu Baolu >> <mailto:baolu...@linux.intel.com>> wrote: >>> >>> On 4/8/21 2:40 AM, Saeed Mirzamohammadi wrote: >>>> The IOMMU driver calculates the guest addressability for a DMA request >>>> based on the value of the mgaw reported from the IOMMU. However, this >>>> is a fused value and as mentioned in the spec, the guest width >>>> should be calculated based on the minimum of supported adjusted guest >>>> address width (SAGAW) and MGAW. >>>> This is from specification: >>>> "Guest addressability for a given DMA request is limited to the >>>> minimum of the value reported through this field and the adjusted >>>> guest address width of the corresponding page-table structure. >>>> (Adjusted guest address widths supported by hardware are reported >>>> through the SAGAW field)." >>>> This causes domain initialization to fail and following >>>> errors appear for EHCI PCI driver: >>>> [2.486393] ehci-pci :01:00.4: EHCI Host Controller >>>> [2.486624] ehci-pci :01:00.4: new USB bus registered, assigned bus >>>> number 1 >>>> [2.489127] ehci-pci :01:00.4: DMAR: Allocating domain failed >>>> [2.489350] ehci-pci :01:00.4: DMAR: 32bit DMA uses non-identity >>>> mapping >>>> [2.489359] ehci-pci :01:00.4: can't setup: -12 >>>> [2.489531] ehci-pci :01:00.4: USB bus 1 deregistered >>>> [2.490023] ehci-pci :01:00.4: init :01:00.4 fail, -12 >>>> [2.490358] ehci-pci: probe of :01:00.4 failed with error -12 >>>> This issue happens when the value of the sagaw corresponds to a >>>> 48-bit agaw. This fix updates the calculation of the agaw based on >>>> the minimum of IOMMU's sagaw value and MGAW. >>>> Signed-off-by: Saeed Mirzamohammadi >>> <mailto:saeed.mirzamohamm...@oracle.com>> >>>> Tested-by: Camille Lu mailto:camille...@hpe.com>> >>>> --- >>>> Change in v2: >>>> - Added cap_width to calculate AGAW based on the minimum value of MGAW and >>>> AGAW. >>>> --- >>>> drivers/iommu/intel-iommu.c | 7 --- >>>> 1 file changed, 4 insertions(+), 3 deletions(-) >>>> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c >>>> index 953d86ca6d2b..a2a03df97704 100644 >>>> --- a/drivers/iommu/intel-iommu.c >>>> +++ b/drivers/iommu/intel-iommu.c >>>> @@ -1853,7 +1853,7 @@ static inline int guestwidth_to_adjustwidth(int gaw) >>>> static int domain_init(struct dmar_domain *domain, struct intel_iommu >>>> *iommu, >>>> int guest_width) >>>> { >>>> -int adjust_width, agaw; >>>> +int adjust_width, agaw, cap_width; >>>> unsigned long sagaw; >>>> int err; >>>> @@ -1867,8 +1867,9 @@ static int domain_init(struct dmar_domain *domain, >>>> struct intel_iommu *iommu, >>>> domain_reserve_special_ranges(domain); >>>> /* calculate AGAW */ >>>> -if (guest_width > cap_mgaw(iommu->cap)) >>>> -guest_width = cap_mgaw(iommu->cap); >>>> +cap_width = min_t(int, cap_mgaw(iommu->cap), agaw_to_width(iommu->agaw)); >>>> +if (guest_width > cap_width) >>>> +guest_width = cap_width; >>>> domain->gaw = guest_width; >>>> adjust_width = guestwidth_to_adjustwidth(guest_width); >>>> agaw = width_to_agaw(adjust_width); >>> >>> Reviewed-by: Lu Baolu >> <mailto:baolu...@linux.intel.com>> >>> >>> Best regards, >>> baolu ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Re: [PATCH 5.4 v2 1/1] iommu/vt-d: Fix agaw for a supported 48 bit guest address width
Hi Lu, Thanks for the review. May I know when do we expect this to be applied to 5.4? Thanks, Saeed On Apr 7, 2021, at 5:25 PM, Lu Baolu mailto:baolu...@linux.intel.com>> wrote: On 4/8/21 2:40 AM, Saeed Mirzamohammadi wrote: The IOMMU driver calculates the guest addressability for a DMA request based on the value of the mgaw reported from the IOMMU. However, this is a fused value and as mentioned in the spec, the guest width should be calculated based on the minimum of supported adjusted guest address width (SAGAW) and MGAW. This is from specification: "Guest addressability for a given DMA request is limited to the minimum of the value reported through this field and the adjusted guest address width of the corresponding page-table structure. (Adjusted guest address widths supported by hardware are reported through the SAGAW field)." This causes domain initialization to fail and following errors appear for EHCI PCI driver: [2.486393] ehci-pci :01:00.4: EHCI Host Controller [2.486624] ehci-pci :01:00.4: new USB bus registered, assigned bus number 1 [2.489127] ehci-pci :01:00.4: DMAR: Allocating domain failed [2.489350] ehci-pci :01:00.4: DMAR: 32bit DMA uses non-identity mapping [2.489359] ehci-pci :01:00.4: can't setup: -12 [2.489531] ehci-pci :01:00.4: USB bus 1 deregistered [2.490023] ehci-pci :01:00.4: init :01:00.4 fail, -12 [2.490358] ehci-pci: probe of :01:00.4 failed with error -12 This issue happens when the value of the sagaw corresponds to a 48-bit agaw. This fix updates the calculation of the agaw based on the minimum of IOMMU's sagaw value and MGAW. Signed-off-by: Saeed Mirzamohammadi mailto:saeed.mirzamohamm...@oracle.com>> Tested-by: Camille Lu mailto:camille...@hpe.com>> --- Change in v2: - Added cap_width to calculate AGAW based on the minimum value of MGAW and AGAW. --- drivers/iommu/intel-iommu.c | 7 --- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 953d86ca6d2b..a2a03df97704 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1853,7 +1853,7 @@ static inline int guestwidth_to_adjustwidth(int gaw) static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, int guest_width) { - int adjust_width, agaw; + int adjust_width, agaw, cap_width; unsigned long sagaw; int err; @@ -1867,8 +1867,9 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, domain_reserve_special_ranges(domain); /* calculate AGAW */ - if (guest_width > cap_mgaw(iommu->cap)) - guest_width = cap_mgaw(iommu->cap); + cap_width = min_t(int, cap_mgaw(iommu->cap), agaw_to_width(iommu->agaw)); + if (guest_width > cap_width) + guest_width = cap_width; domain->gaw = guest_width; adjust_width = guestwidth_to_adjustwidth(guest_width); agaw = width_to_agaw(adjust_width); Reviewed-by: Lu Baolu mailto:baolu...@linux.intel.com>> Best regards, baolu ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Re: [PATCH v5.4 1/1] iommu/vt-d: Fix agaw for a supported 48 bit guest address width
Hi Lu, On Apr 6, 2021, at 6:43 PM, Lu Baolu mailto:baolu...@linux.intel.com>> wrote: Hi Saeed, On 4/7/21 12:35 AM, Saeed Mirzamohammadi wrote: The IOMMU driver calculates the guest addressability for a DMA request based on the value of the mgaw reported from the IOMMU. However, this is a fused value and as mentioned in the spec, the guest width should be calculated based on the supported adjusted guest address width (SAGAW). This is from specification: "Guest addressability for a given DMA request is limited to the minimum of the value reported through this field and the adjusted guest address width of the corresponding page-table structure. (Adjusted guest address widths supported by hardware are reported through the SAGAW field)." This causes domain initialization to fail and following errors appear for EHCI PCI driver: [2.486393] ehci-pci :01:00.4: EHCI Host Controller [2.486624] ehci-pci :01:00.4: new USB bus registered, assigned bus number 1 [2.489127] ehci-pci :01:00.4: DMAR: Allocating domain failed [2.489350] ehci-pci :01:00.4: DMAR: 32bit DMA uses non-identity mapping [2.489359] ehci-pci :01:00.4: can't setup: -12 [2.489531] ehci-pci :01:00.4: USB bus 1 deregistered [2.490023] ehci-pci :01:00.4: init :01:00.4 fail, -12 [2.490358] ehci-pci: probe of :01:00.4 failed with error -12 This issue happens when the value of the sagaw corresponds to a 48-bit agaw. This fix updates the calculation of the agaw based on the IOMMU's sagaw value. Signed-off-by: Saeed Mirzamohammadi mailto:saeed.mirzamohamm...@oracle.com>> Tested-by: Camille Lu mailto:camille...@hpe.com>> --- drivers/iommu/intel-iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 953d86ca6d2b..396e14fad54b 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1867,8 +1867,8 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, domain_reserve_special_ranges(domain); /* calculate AGAW */ - if (guest_width > cap_mgaw(iommu->cap)) - guest_width = cap_mgaw(iommu->cap); + if (guest_width > agaw_to_width(iommu->agaw)) + guest_width = agaw_to_width(iommu->agaw); The spec requires to use a minimum of MGAW and AGAW, so why not, cap_width = min_t(int, cap_mgaw(iommu->cap), agaw_to_width(iommu->agaw)); if (guest_width > cap_width) guest_width = cap_width; Yes, this works better. I just sent the v2. Thanks, Saeed Best regards, baolu domain->gaw = guest_width; adjust_width = guestwidth_to_adjustwidth(guest_width); agaw = width_to_agaw(adjust_width); ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH 5.4 v2 1/1] iommu/vt-d: Fix agaw for a supported 48 bit guest address width
The IOMMU driver calculates the guest addressability for a DMA request based on the value of the mgaw reported from the IOMMU. However, this is a fused value and as mentioned in the spec, the guest width should be calculated based on the minimum of supported adjusted guest address width (SAGAW) and MGAW. This is from specification: "Guest addressability for a given DMA request is limited to the minimum of the value reported through this field and the adjusted guest address width of the corresponding page-table structure. (Adjusted guest address widths supported by hardware are reported through the SAGAW field)." This causes domain initialization to fail and following errors appear for EHCI PCI driver: [2.486393] ehci-pci :01:00.4: EHCI Host Controller [2.486624] ehci-pci :01:00.4: new USB bus registered, assigned bus number 1 [2.489127] ehci-pci :01:00.4: DMAR: Allocating domain failed [2.489350] ehci-pci :01:00.4: DMAR: 32bit DMA uses non-identity mapping [2.489359] ehci-pci :01:00.4: can't setup: -12 [2.489531] ehci-pci :01:00.4: USB bus 1 deregistered [2.490023] ehci-pci :01:00.4: init :01:00.4 fail, -12 [2.490358] ehci-pci: probe of :01:00.4 failed with error -12 This issue happens when the value of the sagaw corresponds to a 48-bit agaw. This fix updates the calculation of the agaw based on the minimum of IOMMU's sagaw value and MGAW. Signed-off-by: Saeed Mirzamohammadi Tested-by: Camille Lu --- Change in v2: - Added cap_width to calculate AGAW based on the minimum value of MGAW and AGAW. --- drivers/iommu/intel-iommu.c | 7 --- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 953d86ca6d2b..a2a03df97704 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1853,7 +1853,7 @@ static inline int guestwidth_to_adjustwidth(int gaw) static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, int guest_width) { - int adjust_width, agaw; + int adjust_width, agaw, cap_width; unsigned long sagaw; int err; @@ -1867,8 +1867,9 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, domain_reserve_special_ranges(domain); /* calculate AGAW */ - if (guest_width > cap_mgaw(iommu->cap)) - guest_width = cap_mgaw(iommu->cap); + cap_width = min_t(int, cap_mgaw(iommu->cap), agaw_to_width(iommu->agaw)); + if (guest_width > cap_width) + guest_width = cap_width; domain->gaw = guest_width; adjust_width = guestwidth_to_adjustwidth(guest_width); agaw = width_to_agaw(adjust_width); -- 2.27.0 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5.4 1/1] iommu/vt-d: Fix agaw for a supported 48 bit guest address width
The IOMMU driver calculates the guest addressability for a DMA request based on the value of the mgaw reported from the IOMMU. However, this is a fused value and as mentioned in the spec, the guest width should be calculated based on the supported adjusted guest address width (SAGAW). This is from specification: "Guest addressability for a given DMA request is limited to the minimum of the value reported through this field and the adjusted guest address width of the corresponding page-table structure. (Adjusted guest address widths supported by hardware are reported through the SAGAW field)." This causes domain initialization to fail and following errors appear for EHCI PCI driver: [2.486393] ehci-pci :01:00.4: EHCI Host Controller [2.486624] ehci-pci :01:00.4: new USB bus registered, assigned bus number 1 [2.489127] ehci-pci :01:00.4: DMAR: Allocating domain failed [2.489350] ehci-pci :01:00.4: DMAR: 32bit DMA uses non-identity mapping [2.489359] ehci-pci :01:00.4: can't setup: -12 [2.489531] ehci-pci :01:00.4: USB bus 1 deregistered [2.490023] ehci-pci :01:00.4: init :01:00.4 fail, -12 [2.490358] ehci-pci: probe of :01:00.4 failed with error -12 This issue happens when the value of the sagaw corresponds to a 48-bit agaw. This fix updates the calculation of the agaw based on the IOMMU's sagaw value. Signed-off-by: Saeed Mirzamohammadi Tested-by: Camille Lu --- drivers/iommu/intel-iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 953d86ca6d2b..396e14fad54b 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1867,8 +1867,8 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, domain_reserve_special_ranges(domain); /* calculate AGAW */ - if (guest_width > cap_mgaw(iommu->cap)) - guest_width = cap_mgaw(iommu->cap); + if (guest_width > agaw_to_width(iommu->agaw)) + guest_width = agaw_to_width(iommu->agaw); domain->gaw = guest_width; adjust_width = guestwidth_to_adjustwidth(guest_width); agaw = width_to_agaw(adjust_width); -- 2.27.0 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu