[PATCH v4 0/2] VMD MSI Remapping Bypass

6: https://patchwork.kernel.org/project/linux-pci/patch/20200728194945.14126-7-jonathan.derr...@intel.com/ Jon Derrick (2): iommu/vt-d: Use Real PCI DMA device for IRTE PCI: vmd: Disable MSI-X remapping when possible drivers/iommu/intel/irq_remapping.c | 3 +- drivers/pci/controller/vmd.c

[PATCH v4 2/2] PCI: vmd: Disable MSI-X remapping when possible

Wilczyński Signed-off-by: Jon Derrick --- drivers/pci/controller/vmd.c | 63 +--- 1 file changed, 51 insertions(+), 12 deletions(-) diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 5e80f28f0119..e3fcdfec58b3 100644 --- a/drivers/pci

[PATCH v4 1/2] iommu/vt-d: Use Real PCI DMA device for IRTE

-by: Jon Derrick --- drivers/iommu/intel/irq_remapping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 685200a5cff0..1939e070eec8 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers

[PATCH v3 2/2] PCI: vmd: Disable MSI-X remapping when possible

to properly set IRTE for child device interrupts to the VMD endpoint's context. Some VMD platforms have existing production BIOS which rely on MSI-X remapping and won't explicitly program the MSI-X remapping bit. This re-enables MSI-X remapping on unload. Acked-by: Joerg Roedel Signed-off-by: Jon Derrick

[PATCH v3 0/2] VMD MSI Remapping Bypass

.14126-7-jonathan.derr...@intel.com/ Jon Derrick (2): iommu/vt-d: Use Real PCI DMA device for IRTE PCI: vmd: Disable MSI-X remapping when possible drivers/iommu/intel/irq_remapping.c | 3 +- drivers/pci/controller/vmd.c| 61 +++-- 2 files changed, 51 inse

[PATCH v3 1/2] iommu/vt-d: Use Real PCI DMA device for IRTE

-by: Jon Derrick --- drivers/iommu/intel/irq_remapping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 685200a5cff0..1939e070eec8 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers

[PATCH v2 1/2] iommu/vt-d: Use Real PCI DMA device for IRTE

VMD retransmits child device MSI/X with the VMD endpoint's requester-id. In order to support direct interrupt remapping of VMD child devices, ensure that the IRTE is programmed with the VMD endpoint's requester-id using pci_real_dma_dev(). Signed-off-by: Jon Derrick --- drivers/iommu/intel

[PATCH v2 2/2] PCI: vmd: Disable MSI/X remapping when possible

to properly set IRTE for child device interrupts to the VMD endpoint's context. Some VMD platforms have existing production BIOS which rely on MSI/X remapping and won't explicitly program the MSI/X remapping bit. This re-enables MSI/X remapping on unload. Signed-off-by: Jon Derrick --- drivers/pci

[PATCH v2 0/2] VMD MSI Remapping Bypass

ble to a more logical location V1 patches 1-4 were already merged V1, 5/6: https://patchwork.kernel.org/project/linux-pci/patch/20200728194945.14126-6-jonathan.derr...@intel.com/ V1, 6/6: https://patchwork.kernel.org/project/linux-pci/patch/20200728194945.14126-7-jonathan.derr...@intel.com/ Jon Derr

[PATCH v1 0/3] iommu/vt-d: real DMA sub-device info allocation

_mapping() paths. [1] https://bugzilla.kernel.org/show_bug.cgi?id=207575 Jon Derrick (3): iommu/vt-d: Only clear real DMA device's context entries iommu/vt-d: Allocate domain info for real DMA sub-devices iommu/vt-d: Remove real DMA lookup in find_domain drivers/iommu/intel-iommu.c | 31

[PATCH v1 3/3] iommu/vt-d: Remove real DMA lookup in find_domain

a_dev() for mapping") Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=207575 Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 6d39b9b..5767882 100644 --- a/drivers/i

[PATCH v1 2/3] iommu/vt-d: Allocate domain info for real DMA sub-devices

device_domain_info and uses the sub-device's BDF so that these sub-devices won't alias to other devices. Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c | 19 +++ include/linux/intel-iommu.h | 1 + 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/intel

[PATCH v1 1/3] iommu/vt-d: Only clear real DMA device's context entries

a helper to determine if a struct device is a sub-device of a real DMA device. Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c | 9 - 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ff5a30a..1ff45b2 100644

[PATCH 0/1] Real DMA dev DMA domain patch

Sorry for the late patch here, but I hit the issue Baolu and Daniel pointed out could occur, and requires this fix (or iommu=nopt). Hoping to get it into an rc Jon Derrick (1): iommu/vt-d: use DMA domain for real DMA devices and subdevices drivers/iommu/intel-iommu.c | 56

[PATCH 1/1] iommu/vt-d: use DMA domain for real DMA devices and subdevices

0140c69637e ("iommu/vt-d: Use pci_real_dma_dev() for mapping") Signed-off-by: Jon Derrick Signed-off-by: Daniel Drake --- drivers/iommu/intel-iommu.c | 56 - 1 file changed, 43 insertions(+), 13 deletions(-) diff --git a/drivers/iommu/intel-iommu

[PATCH v5 7/7] x86/PCI: Remove X86_DEV_DMA_OPS

From: Christoph Hellwig There are no users of X86_DEV_DMA_OPS left, so remove the code. Reviewed-by: Jon Derrick Signed-off-by: Christoph Hellwig --- arch/x86/Kconfig | 3 --- arch/x86/include/asm/device.h | 10 -- arch/x86/pci/common.c | 38

[PATCH v5 0/7] Clean up VMD DMA Map Ops

x86/PCI: Remove X86_DEV_DMA_OPS Jon Derrick (5): x86/PCI: Expose VMD's PCI Device in pci_sysdata PCI: Introduce pci_real_dma_dev() iommu/vt-d: Use pci_real_dma_dev() for mapping iommu/vt-d: Remove VMD child device sanity check PCI: vmd: Stop overriding dma_map_ops arch/x86/Kco

[PATCH v5 5/7] iommu/vt-d: Remove VMD child device sanity check

from the hierarchy. Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c | 10 +- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 72f26e8..7e2c492f 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers

[PATCH v5 2/7] x86/PCI: Expose VMD's PCI Device in pci_sysdata

To be used by Intel-IOMMU code to find the correct domain. CC: Christoph Hellwig Signed-off-by: Jon Derrick --- arch/x86/include/asm/pci.h | 4 ++-- drivers/pci/controller/vmd.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/pci.h b/arch/x86

[PATCH v5 3/7] PCI: Introduce pci_real_dma_dev()

Signed-off-by: Jon Derrick --- arch/x86/pci/common.c | 10 ++ drivers/pci/pci.c | 19 ++- drivers/pci/search.c | 6 ++ include/linux/pci.h | 1 + 4 files changed, 35 insertions(+), 1 deletion(-) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index

[PATCH v5 6/7] PCI: vmd: Stop overriding dma_map_ops

endpoint when mapping and providing the correct child device's attributes during DMA operations. This patch removes the dma_map_ops redirect. Signed-off-by: Jon Derrick --- drivers/pci/controller/Kconfig | 1 - drivers/pci/controller/vmd.c | 150 - 2

[PATCH v5 4/7] iommu/vt-d: Use pci_real_dma_dev() for mapping

The PCI device may have a DMA requester on another bus, such as VMD subdevices needing to use the VMD endpoint. This case requires the real DMA device when mapping to IOMMU. Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c | 5 + 1 file changed, 5 insertions(+) diff --git

[PATCH v5 1/7] x86/PCI: Add a to_pci_sysdata helper

argument] Signed-off-by: Jon Derrick --- arch/x86/include/asm/pci.h | 29 + 1 file changed, 13 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 90d0731..a4e09db60 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86

[PATCH v4 5/7] iommu/vt-d: Remove VMD child device sanity check

from the hierarchy. Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c | 10 +- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 01a1b0f..c055699 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu

[PATCH v4 4/7] iommu/vt-d: Use pci_real_dma_dev() for mapping

The PCI device may have a DMA requester on another bus, such as VMD subdevices needing to use the VMD endpoint. This case requires the real DMA device when mapping to IOMMU. Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c | 9 + 1 file changed, 9 insertions(+) diff --git

[PATCH v4 2/7] x86/PCI: Expose VMD's PCI Device in pci_sysdata

To be used by Intel-IOMMU code to find the correct domain. CC: Christoph Hellwig Signed-off-by: Jon Derrick --- arch/x86/include/asm/pci.h | 4 ++-- drivers/pci/controller/vmd.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/pci.h b/arch/x86

[PATCH v4 1/7] x86/PCI: Add a to_pci_sysdata helper

argument] Signed-off-by: Jon Derrick --- arch/x86/include/asm/pci.h | 29 + 1 file changed, 13 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 90d0731..a4e09db60 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86

[PATCH v4 3/7] PCI: Introduce pci_real_dma_dev()

Signed-off-by: Jon Derrick --- arch/x86/pci/common.c | 10 ++ drivers/pci/pci.c | 19 ++- drivers/pci/search.c | 6 ++ include/linux/pci.h | 1 + 4 files changed, 35 insertions(+), 1 deletion(-) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index

[PATCH v4 7/7] x86/PCI: Remove X86_DEV_DMA_OPS

From: Christoph Hellwig There are no users of X86_DEV_DMA_OPS left, so remove the code. Reviewed-by: Jon Derrick Signed-off-by: Christoph Hellwig --- arch/x86/Kconfig | 3 --- arch/x86/include/asm/device.h | 10 -- arch/x86/pci/common.c | 38

[PATCH v4 0/7] Clean up VMD DMA Map Ops

ding pointer in struct device or pci_dev. Based on Bjorn's next: https://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git/log/?h=next Christoph Hellwig (2): x86/PCI: Add a to_pci_sysdata helper x86/PCI: Remove X86_DEV_DMA_OPS Jon Derrick (5): x86/PCI: Expose VMD's PCI De

[PATCH v4 6/7] PCI: vmd: Stop overriding dma_map_ops

endpoint when mapping and providing the correct child device's attributes during DMA operations. This patch removes the dma_map_ops redirect. Signed-off-by: Jon Derrick --- drivers/pci/controller/Kconfig | 1 - drivers/pci/controller/vmd.c | 150 - 2

[PATCH v3 3/5] PCI: Introduce pci_direct_dma_alias()

The current DMA alias implementation requires the aliased device be on the same PCI bus as the requester ID. This introduces an arch-specific mechanism to point to another PCI device when doing mapping and PCI DMA alias search. Signed-off-by: Jon Derrick --- arch/x86/pci/common.c | 7

[PATCH v3 1/5] x86/pci: Add a to_pci_sysdata helper

-off-by: Jon Derrick --- arch/x86/include/asm/pci.h | 28 +--- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 90d0731..cf680c5 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm

[PATCH v3 4/5] PCI: vmd: Stop overriding dma_map_ops

endpoint when mapping and providing the correct child device's attributes during DMA operations. This patch modifies Intel-IOMMU to check for a 'Direct DMA Alias' and refer to it for mapping. Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c| 18 +++-- drivers/pci/controller/Kconfig

[PATCH v3 0/5] Clean up VMD DMA Map Ops

' Changes from v1: Removed 1/5 & 2/5 misc fix patches that were merged Uses Christoph's staging/cleanup patches Introduce weak function rather than including pointer in struct device or pci_dev. Based on Joerg's next: https://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git/ Jon Derric

[PATCH v3 2/5] x86/PCI: Expose VMD's PCI Device in pci_sysdata

To be used by Intel-IOMMU code to find the correct domain. CC: Christoph Hellwig Signed-off-by: Jon Derrick --- arch/x86/include/asm/pci.h | 5 ++--- drivers/pci/controller/vmd.c | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/pci.h b/arch/x86

[PATCH v3 5/5] x86/pci: Remove X86_DEV_DMA_OPS

From: Christoph Hellwig There are no users of X86_DEV_DMA_OPS left, so remove the code. Reviewed-by: Jon Derrick Signed-off-by: Christoph Hellwig --- arch/x86/Kconfig | 3 --- arch/x86/include/asm/device.h | 10 -- arch/x86/pci/common.c | 38

[PATCH v2 1/5] x86/pci: Add a to_pci_sysdata helper

: added un-const cast] Signed-off-by: Jon Derrick --- arch/x86/include/asm/pci.h | 28 +--- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 90d0731..cf680c5 100644 --- a/arch/x86/include/asm/pci.h

[PATCH v2 4/5] PCI: vmd: Stop overriding dma_map_ops

endpoint when mapping and providing the correct child device's attributes during dma operations. This patch modifies intel-iommu to check for a 'direct dma alias' and refer to it for mapping. Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c| 17 +++-- drivers/pci/controller/Kconfig

[PATCH v2 0/5] Clean up VMD DMA Map Ops

Add a to_pci_sysdata helper x86/pci: Replace the vmd_domain field with a vmd_dev pointer Jon Derrick (3): PCI: Introduce direct dma alias PCI: vmd: Stop overriding dma_map_ops x86/pci: Remove X86_DEV_DMA_OPS arch/x86/Kconfig | 3 - arch/x86/include/asm/device.h | 10 ---

[PATCH v2 2/5] x86/pci: Replace the vmd_domain field with a vmd_dev pointer

From: Christoph Hellwig From: Christoph Hellwig Store the actual VMD device in struct pci_sysdata, so that we can later use it directly for DMA mappings. Reviewed-by: Jon Derrick Signed-off-by: Christoph Hellwig --- arch/x86/include/asm/pci.h | 5 ++--- drivers/pci/controller/vmd.c | 2

[PATCH v2 5/5] x86/pci: Remove X86_DEV_DMA_OPS

From: Christoph Hellwig There are no users of X86_DEV_DMA_OPS left, so remove the code. Reviewed-by: Jon Derrick Signed-off-by: Christoph Hellwig --- arch/x86/Kconfig | 3 --- arch/x86/include/asm/device.h | 10 -- arch/x86/pci/common.c | 38

[PATCH v2 3/5] PCI: Introduce direct dma alias

The current dma alias implementation requires the aliased device be on the same bus as the dma parent. This introduces an arch-specific mechanism to point to an arbitrary struct device when doing mapping and pci alias search. Signed-off-by: Jon Derrick --- arch/x86/pci/common.c | 7

[RFC 5/5] x86/PCI: Remove unused X86_DEV_DMA_OPS

VMD was the only user of device dma operations. Now that the IOMMU has been made aware of direct DMA aliases, VMD domain devices can reference the VMD endpoint directly and the VMD device dma operations has been made obsolete. Signed-off-by: Jon Derrick --- arch/x86/Kconfig | 3

[RFC 2/5] iommu/vt-d: Unlink device if failed to add to group

If the device fails to be added to the group, make sure to unlink the reference before returning. Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c | 13 ++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel

[RFC 3/5] x86/PCI: Expose VMD's device in pci_sysdata

To be used by intel-iommu code to find the correct domain. Signed-off-by: Jon Derrick --- arch/x86/include/asm/pci.h | 4 ++-- drivers/pci/controller/vmd.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index

[RFC 1/5] iommu: Remove device link to group on failure

This adds the missing teardown step that removes the device link from the group when the device addition fails. Signed-off-by: Jon Derrick --- drivers/iommu/iommu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index d5174f0..3e35284 100644

[RFC 0/5] Clean up VMD DMA Map Ops

far enough for proper teardown on addition failure. Jon Derrick (5): iommu: Remove device link to group on failure iommu/vt-d: Unlink device if failed to add to group x86/PCI: Expose VMD's device in pci_sysdata PCI: vmd: Stop overriding dma_map_ops x86/PCI: Remove unused X86_DEV_DMA_OPS

[RFC 4/5] PCI: vmd: Stop overriding dma_map_ops

of the changes required to support this mode. Signed-off-by: Jon Derrick --- arch/x86/pci/common.c | 6 +- drivers/iommu/intel-iommu.c| 13 ++-- drivers/pci/controller/Kconfig | 1 - drivers/pci/controller/vmd.c | 150 - drivers/pci/pci.c

[PATCH v3] iommu: Prevent VMD child devices from being remapping targets

an IOMMU, which prevents it from exposing an iommu_group sysfs directories and allowing subsequent binding by userspace-access drivers such as VFIO. Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- v2->3, wrapped in x86 ifdef to avoid ia64 compilation errors drivers/iommu/intel-io

[PATCH v2 4/4] iommu: Prevent VMD child devices from being remapping targets

an IOMMU, which prevents it from exposing an iommu_group sysfs directories and allowing subsequent binding by userspace-access drivers such as VFIO. Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- drivers/iommu/intel-iommu.c | 5 + 1 file changed, 5 insertions(+) diff --git a/d

[PATCH v2 0/4] VMD fixups

Mostly just cleanup in this revision, eg, trying to limit scope of vmd code to x86 Previous: https://patchwork.kernel.org/patch/9886095/ https://patchwork.kernel.org/patch/9886097/ https://patchwork.kernel.org/patch/9886101/ Jon Derrick (4): MAINTAINERS: Add Jonathan Derrick as VMD maintainer

[PATCH v2 3/4] x86/PCI: Use is_vmd rather than relying on the domain number

Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- arch/x86/pci/fixup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index ca4b02e5..1ed2fbf 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -628,7

[PATCH v2 2/4] pci/x86: Move VMD quirks to x86 fixups

VMD currently only exists for Intel x86 products Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- arch/x86/pci/fixup.c | 18 ++ drivers/pci/quirks.c | 17 - 2 files changed, 18 insertions(+), 17 deletions(-) diff --git a/arch/x86/pci/fixup.c b/ar

[PATCH v2 1/4] MAINTAINERS: Add Jonathan Derrick as VMD maintainer

Add myself as VMD maintainer Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> Acked-by: Keith Busch <keith.bu...@intel.com> --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index f66488d..3ec39df 100644 --- a/MAINTAINERS +++ b

Re: [PATCH 3/3] iommu: prevent VMD child devices from being remapping targets

Hi Robin, thanks for the reply. On 08/11/2017 12:25 PM, Robin Murphy wrote: > On 07/08/17 20:57, Jon Derrick wrote: >> VMD child devices must use the VMD endpoint's ID as the DMA source. >> Because of this, there needs to be a way to link the parent VMD >> endpoint's DMAR do

Re: [PATCH 2/3] pci: Generalize is_vmd behavior

On 08/11/2017 11:03 AM, Bjorn Helgaas wrote: > On Mon, Aug 07, 2017 at 01:57:12PM -0600, Jon Derrick wrote: >> Generalize is_vmd behavior to remove dependency on domain number >> checking in pci quirks. >> >> Signed-off-by: Jon Derrick <jonathan.derr...@intel.com>

[PATCH 3/3] iommu: prevent VMD child devices from being remapping targets

binding by userspace-access drivers such as VFIO. Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- drivers/iommu/intel-iommu.c | 5 + 1 file changed, 5 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 687f18f..651a6cd 100644 --- a/d

[PATCH 1/3] MAINTAINERS: Add Jonathan Derrick as VMD maintainer

Add myself as VMD maintainer Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index f66488d..3ec39df 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10090,6 +10090,7 @@ F: drivers/p

[PATCH 2/3] pci: Generalize is_vmd behavior

Generalize is_vmd behavior to remove dependency on domain number checking in pci quirks. Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- arch/x86/include/asm/pci.h | 8 +++- arch/x86/pci/common.c | 2 +- drivers/pci/quirks.c | 2 +- include/linux/pci.h