Skip to contentSkip to conversation

Documentation: x86: rework IOMMU documentation

PATCH In review Alex Deucher 5 participants 6 messages Apr 22, 2022 – Apr 28, 2022 Documentation

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 Documentation: x86: rework IOMMU documentation

Add preliminary documentation for AMD IOMMU and combine with the existing Intel IOMMU documentation and clean up and modernize some of the existing documentation to align with the current state of the kernel.

---

V2: Incorporate feedback from Robin to clarify IOMMU vs DMA engine (e.g.,
a device) and document proper DMA API. Also correct the fact that the AMD IOMMU is not limited to managing PCI devices.
v3: Fix spelling and rework text as suggested by Vasant
v4: Combine Intel and AMD documents into a single document as suggested
by Dave Hansen
v5: Clarify that keywords are related to ACPI, grammatical fixes
v6: Make more stuff common based on feedback from Robin

 Documentation/x86/index.rst       |   2 +-
 Documentation/x86/intel-iommu.rst | 115 ------------------------
 Documentation/x86/iommu.rst       | 143 ++++++++++++++++++++++++++++++
 3 files changed, 144 insertions(+), 116 deletions(-)
 delete mode 100644 Documentation/x86/intel-iommu.rst
 create mode 100644 Documentation/x86/iommu.rst
Documentation/x86/index.rst +1 -1
index f498f1d36cd3..6f8409fe0674 100644
@@ -21,7 +21,7 @@ x86-specific Documentation
    tlb
    mtrr
    pat
-   intel-iommu
+   iommu
    intel_txt
    amd-memory-encryption
    pti
Documentation/x86/intel-iommu.rst deleted +0 -115

115 lines not on this page · raw message

Documentation/x86/iommu.rst new file +143 -0

143 lines not on this page · raw message

Signature · 6 lines
2.35.1

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu
Reviewed-by on v1 1/1
#1 lore raw
Quoted 4 lines · Alex Deucher

Add preliminary documentation for AMD IOMMU and combine with the existing Intel IOMMU documentation and clean up and modernize some of the existing documentation to align with the current state of the kernel.

FWIW,

Quoted 292 lines

---

V2: Incorporate feedback from Robin to clarify IOMMU vs DMA engine (e.g.,
a device) and document proper DMA API. Also correct the fact that the AMD IOMMU is not limited to managing PCI devices.
v3: Fix spelling and rework text as suggested by Vasant
v4: Combine Intel and AMD documents into a single document as suggested
by Dave Hansen
v5: Clarify that keywords are related to ACPI, grammatical fixes
v6: Make more stuff common based on feedback from Robin

  Documentation/x86/index.rst       |   2 +-
  Documentation/x86/intel-iommu.rst | 115 ------------------------
  Documentation/x86/iommu.rst       | 143 ++++++++++++++++++++++++++++++
  3 files changed, 144 insertions(+), 116 deletions(-)

delete mode 100644 Documentation/x86/intel-iommu.rst create mode 100644 Documentation/x86/iommu.rst

Documentation/x86/index.rst +1 -1
index f498f1d36cd3..6f8409fe0674 100644
@@ -21,7 +21,7 @@ x86-specific Documentation
     tlb
     mtrr
     pat
-   intel-iommu
+   iommu
     intel_txt
     amd-memory-encryption
     pti
Documentation/x86/intel-iommu.rst deleted +0 -115
deleted file mode 100644
index 099f13d51d5f..000000000000
@@ -1,115 +0,0 @@
-===================
-Linux IOMMU Support
-===================
-
-The architecture spec can be obtained from the below location.
-
-http://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/vt-directed-io-spec.pdf
-
-This guide gives a quick cheat sheet for some basic understanding.
-
-Some Keywords
-
-- DMAR - DMA remapping
-- DRHD - DMA Remapping Hardware Unit Definition
-- RMRR - Reserved memory Region Reporting Structure
-- ZLR  - Zero length reads from PCI devices
-- IOVA - IO Virtual address.
-
-Basic stuff
------------
-
-ACPI enumerates and lists the different DMA engines in the platform, and
-device scope relationships between PCI devices and which DMA engine  controls
-them.
-
-What is RMRR?
--------------
-
-There are some devices the BIOS controls, for e.g USB devices to perform
-PS2 emulation. The regions of memory used for these devices are marked
-reserved in the e820 map. When we turn on DMA translation, DMA to those
-regions will fail. Hence BIOS uses RMRR to specify these regions along with
-devices that need to access these regions. OS is expected to setup
-unity mappings for these regions for these devices to access these regions.
-
-How is IOVA generated?
-----------------------
-
-Well behaved drivers call pci_map_*() calls before sending command to device
-that needs to perform DMA. Once DMA is completed and mapping is no longer
-required, device performs a pci_unmap_*() calls to unmap the region.
-
-The Intel IOMMU driver allocates a virtual address per domain. Each PCIE
-device has its own domain (hence protection). Devices under p2p bridges
-share the virtual address with all devices under the p2p bridge due to
-transaction id aliasing for p2p bridges.
-
-IOVA generation is pretty generic. We used the same technique as vmalloc()
-but these are not global address spaces, but separate for each domain.
-Different DMA engines may support different number of domains.
-
-We also allocate guard pages with each mapping, so we can attempt to catch
-any overflow that might happen.
-
-
-Graphics Problems?
-------------------
-If you encounter issues with graphics devices, you can try adding
-option intel_iommu=igfx_off to turn off the integrated graphics engine.
-If this fixes anything, please ensure you file a bug reporting the problem.
-
-Some exceptions to IOVA
------------------------
-Interrupt ranges are not address translated, (0xfee00000 - 0xfeefffff).
-The same is true for peer to peer transactions. Hence we reserve the
-address from PCI MMIO ranges so they are not allocated for IOVA addresses.
-
-
-Fault reporting
----------------
-When errors are reported, the DMA engine signals via an interrupt. The fault
-reason and device that caused it with fault reason is printed on console.
-
-See below for sample.
-
-
-Boot Message Sample
--------------------
-
-Something like this gets printed indicating presence of DMAR tables
-in ACPI.
-
-ACPI: DMAR (v001 A M I  OEMDMAR  0x00000001 MSFT 0x00000097) @ 0x000000007f5b5ef0
-
-When DMAR is being processed and initialized by ACPI, prints DMAR locations
-and any RMRR's processed::
-
-	ACPI DMAR:Host address width 36
-	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed90000
-	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed91000
-	ACPI DMAR:DRHD (flags: 0x00000001)base: 0x00000000fed93000
-	ACPI DMAR:RMRR base: 0x00000000000ed000 end: 0x00000000000effff
-	ACPI DMAR:RMRR base: 0x000000007f600000 end: 0x000000007fffffff
-
-When DMAR is enabled for use, you will notice..
-
-PCI-DMA: Using DMAR IOMMU
--------------------------
-
-Fault reporting
-^^^^^^^^^^^^^^^
-
-::
-
-	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
-	DMAR:[fault reason 05] PTE Write access is not set
-	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
-	DMAR:[fault reason 05] PTE Write access is not set
-
-TBD
-----
-
-- For compatibility testing, could use unity map domain for all devices, just
-  provide a 1-1 for all useful memory under a single domain for all devices.
-- API for paravirt ops for abstracting functionality for VMM folks.
Documentation/x86/iommu.rst new file +133 -0
new file mode 100644
index 000000000000..ed87d76a38d5
@@ -0,0 +1,143 @@
+=================
+x86 IOMMU Support
+=================
+
+The architecture specs can be obtained from the below locations.
+
+- Intel: http://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/vt-directed-io-spec.pdf
+- AMD: https://www.amd.com/system/files/TechDocs/48882_IOMMU.pdf
+
+This guide gives a quick cheat sheet for some basic understanding.
+
+Basic stuff
+-----------
+
+ACPI enumerates and lists the different IOMMUs on the platform, and
+device scope relationships between devices and which IOMMU controls
+them.
+
+Some ACPI Keywords:
+
+- DMAR - Intel DMA Remapping table
+- DRHD - Intel DMA Remapping Hardware Unit Definition
+- RMRR - Intel Reserved Memory Region Reporting Structure
+- IVRS - AMD I/O Virtualization Reporting Structure
+- IVDB - AMD I/O Virtualization Definition Block
+- IVHD - AMD I/O Virtualization Hardware Definition
+
+What is Intel RMRR?
+^^^^^^^^^^^^^^^^^^^
+
+There are some devices the BIOS controls, for e.g USB devices to perform
+PS2 emulation. The regions of memory used for these devices are marked
+reserved in the e820 map. When we turn on DMA translation, DMA to those
+regions will fail. Hence BIOS uses RMRR to specify these regions along with
+devices that need to access these regions. OS is expected to setup
+unity mappings for these regions for these devices to access these regions.
+
+What is AMD IVRS?
+^^^^^^^^^^^^^^^^^
+
+The architecture defines an ACPI-compatible data structure called an I/O
+Virtualization Reporting Structure (IVRS) that is used to convey information
+related to I/O virtualization to system software.  The IVRS describes the
+configuration and capabilities of the IOMMUs contained in the platform as
+well as information about the devices that each IOMMU virtualizes.
+
+The IVRS provides information about the following:
+
+- IOMMUs present in the platform including their capabilities and proper configuration
+- System I/O topology relevant to each IOMMU
+- Peripheral devices that cannot be otherwise enumerated
+- Memory regions used by SMI/SMM, platform firmware, and platform hardware. These are generally exclusion ranges to be configured by system software.
+
+How is an I/O Virtual Address (IOVA) generated?
+-----------------------------------------------
+
+Well behaved drivers call dma_map_*() calls before sending command to device
+that needs to perform DMA. Once DMA is completed and mapping is no longer
+required, driver performs dma_unmap_*() calls to unmap the region.
+
+Some exceptions to IOVAs
+------------------------
+
+Interrupt ranges are not address translated, (0xfee00000 - 0xfeefffff).
+The same is true for peer to peer transactions. Hence we reserve the
+address from PCI MMIO ranges so they are not allocated for IOVA addresses.
+
+Graphics Problems?
+------------------
+
+If you encounter issues with integrated graphics devices, you can try
+adding the option "iommu.passthrough=1", or the equivalent "iommu=pt",
+to the kernel command line to use a 1:1 mapping for the IOMMU in
+general.  On Intel you can also try "intel_iommu=igfx_off" to turn off
+translation specifically for the integrated graphics engine only.  If
+this fixes anything, please ensure you file a bug reporting the problem.
+
+Fault reporting
+---------------
+When errors are reported, the IOMMU signals via an interrupt. The fault
+reason and device that caused it is printed on the console.
+
+
+Kernel Log Samples
+------------------
+
+Intel Boot Messages
+^^^^^^^^^^^^^^^^^^^
+
+Something like this gets printed indicating presence of DMAR tables
+in ACPI:
+
+::
+
+	ACPI: DMAR (v001 A M I  OEMDMAR  0x00000001 MSFT 0x00000097) @ 0x000000007f5b5ef0
+
+When DMAR is being processed and initialized by ACPI, prints DMAR locations
+and any RMRR's processed:
+
+::
+
+	ACPI DMAR:Host address width 36
+	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed90000
+	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed91000
+	ACPI DMAR:DRHD (flags: 0x00000001)base: 0x00000000fed93000
+	ACPI DMAR:RMRR base: 0x00000000000ed000 end: 0x00000000000effff
+	ACPI DMAR:RMRR base: 0x000000007f600000 end: 0x000000007fffffff
+
+When DMAR is enabled for use, you will notice:
+
+::
+
+	PCI-DMA: Using DMAR IOMMU
+
+Intel Fault reporting
+^^^^^^^^^^^^^^^^^^^^^
+
+::
+
+	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
+	DMAR:[fault reason 05] PTE Write access is not set
+	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
+	DMAR:[fault reason 05] PTE Write access is not set
+
+AMD Boot Messages
+^^^^^^^^^^^^^^^^^
+
+Something like this gets printed indicating presence of the IOMMU:
+
+::
+
+	AMD-Vi: Found IOMMU cap 0x40
+	AMD-Vi: Extended features (0x4f77ef22294ada): PPR NX GT IA GA PC GA_vAPIC

Documentation/x86/iommu.rst line 143

Quoted 10 lines
Documentation/x86/iommu.rst new file +10 -0
+	AMD-Vi: Interrupt remapping enabled
+	AMD-Vi: Virtual APIC enabled
+
+AMD Fault reporting
+^^^^^^^^^^^^^^^^^^^
+
+::
+
+	AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0007 address=0xffffc02000 flags=0x0000]
+	AMD-Vi: Event logged [IO_PAGE_FAULT device=07:00.0 domain=0x0007 address=0xffffc02000 flags=0x0000]

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

#2 lore raw
In reply to Alex Deucher

Hi Alex,

Thanks for doing this, really helps to catch up the current state. Please see my comments inline.

Quoted 51 lines · Alex Deucher

Add preliminary documentation for AMD IOMMU and combine with the existing Intel IOMMU documentation and clean up and modernize some of the existing documentation to align with the current state of the kernel.

---

V2: Incorporate feedback from Robin to clarify IOMMU vs DMA engine (e.g.,
a device) and document proper DMA API. Also correct the fact that the AMD IOMMU is not limited to managing PCI devices.
v3: Fix spelling and rework text as suggested by Vasant
v4: Combine Intel and AMD documents into a single document as suggested
by Dave Hansen
v5: Clarify that keywords are related to ACPI, grammatical fixes
v6: Make more stuff common based on feedback from Robin

 Documentation/x86/index.rst       |   2 +-
 Documentation/x86/intel-iommu.rst | 115 ------------------------
 Documentation/x86/iommu.rst       | 143 ++++++++++++++++++++++++++++++
 3 files changed, 144 insertions(+), 116 deletions(-)
 delete mode 100644 Documentation/x86/intel-iommu.rst
 create mode 100644 Documentation/x86/iommu.rst
Documentation/x86/index.rst +1 -1
index f498f1d36cd3..6f8409fe0674 100644
@@ -21,7 +21,7 @@ x86-specific Documentation
    tlb
    mtrr
    pat
-   intel-iommu
+   iommu
    intel_txt
    amd-memory-encryption
    pti
(quoted diff) +0 -0

b/Documentation/x86/intel-iommu.rst deleted file mode 100644 index 099f13d51d5f..000000000000

Documentation/x86/intel-iommu.rst deleted +0 -8
@@ -1,115 +0,0 @@
-===================
-Linux IOMMU Support
-===================
-
-The architecture spec can be obtained from the below location.
-
-http://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/vt-directed-io-spec.pdf
-

Documentation/x86/intel-iommu.rst line 18

Quoted 10 lines
Documentation/x86/intel-iommu.rst deleted +0 -10
-This guide gives a quick cheat sheet for some basic understanding.
-
-Some Keywords
-
-- DMAR - DMA remapping
-- DRHD - DMA Remapping Hardware Unit Definition
-- RMRR - Reserved memory Region Reporting Structure
-- ZLR  - Zero length reads from PCI devices
-- IOVA - IO Virtual address.
-

I feel this combined document only focus on IOVA and DMA APIs, it is considered as legacy DMA after scalable mode is introduced by Intel to support DMA with PASID, shared virtual addressing (SVA). Perhaps, we can also combine ./Documentation/x86/sva.rst

With scalable mode, it affects boot messages, fault reporting, etc. I am not saying no to this document, just suggesting. I don't know where AMD is at in terms of PASID support but there are lots of things in common between VT-d and ARM's SMMU in terms of PASID/SVA. Should we broaden the purpose of this document even further?

Quoted 249 lines
Documentation/x86/intel-iommu.rst deleted +0 -5
-Basic stuff
------------
-
-ACPI enumerates and lists the different DMA engines in the platform, and
-device scope relationships between PCI devices and which DMA engine

controls -them.

Documentation/x86/intel-iommu.rst deleted +0 -8
-
-What is RMRR?
--------------
-
-There are some devices the BIOS controls, for e.g USB devices to perform
-PS2 emulation. The regions of memory used for these devices are marked
-reserved in the e820 map. When we turn on DMA translation, DMA to those
-regions will fail. Hence BIOS uses RMRR to specify these regions along

with -devices that need to access these regions. OS is expected to setup -unity mappings for these regions for these devices to access these regions. -

Documentation/x86/intel-iommu.rst deleted +0 -4
-How is IOVA generated?
-----------------------
-
-Well behaved drivers call pci_map_*() calls before sending command to

device -that needs to perform DMA. Once DMA is completed and mapping is no longer -required, device performs a pci_unmap_*() calls to unmap the region. -

Documentation/x86/intel-iommu.rst deleted +0 -6
-The Intel IOMMU driver allocates a virtual address per domain. Each PCIE
-device has its own domain (hence protection). Devices under p2p bridges
-share the virtual address with all devices under the p2p bridge due to
-transaction id aliasing for p2p bridges.
-
-IOVA generation is pretty generic. We used the same technique as

vmalloc() -but these are not global address spaces, but separate for each domain. -Different DMA engines may support different number of domains.

Documentation/x86/intel-iommu.rst deleted +0 -2
-
-We also allocate guard pages with each mapping, so we can attempt to

catch -any overflow that might happen.

Documentation/x86/intel-iommu.rst deleted +0 -7
-
-
-Graphics Problems?
-------------------
-If you encounter issues with graphics devices, you can try adding
-option intel_iommu=igfx_off to turn off the integrated graphics engine.
-If this fixes anything, please ensure you file a bug reporting the

problem. -

Documentation/x86/intel-iommu.rst deleted +0 -5
-Some exceptions to IOVA
------------------------
-Interrupt ranges are not address translated, (0xfee00000 - 0xfeefffff).
-The same is true for peer to peer transactions. Hence we reserve the
-address from PCI MMIO ranges so they are not allocated for IOVA

addresses. -

Documentation/x86/intel-iommu.rst deleted +0 -4
-
-Fault reporting
----------------
-When errors are reported, the DMA engine signals via an interrupt. The

fault -reason and device that caused it with fault reason is printed on console. -

Documentation/x86/intel-iommu.rst deleted +0 -10
-See below for sample.
-
-
-Boot Message Sample
--------------------
-
-Something like this gets printed indicating presence of DMAR tables
-in ACPI.
-
-ACPI: DMAR (v001 A M I  OEMDMAR  0x00000001 MSFT 0x00000097) @

0x000000007f5b5ef0 -
-When DMAR is being processed and initialized by ACPI, prints DMAR locations -and any RMRR's processed::

Documentation/x86/intel-iommu.rst deleted +0 -27
-
-	ACPI DMAR:Host address width 36
-	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed90000
-	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed91000
-	ACPI DMAR:DRHD (flags: 0x00000001)base: 0x00000000fed93000
-	ACPI DMAR:RMRR base: 0x00000000000ed000 end: 0x00000000000effff
-	ACPI DMAR:RMRR base: 0x000000007f600000 end: 0x000000007fffffff
-
-When DMAR is enabled for use, you will notice..
-
-PCI-DMA: Using DMAR IOMMU
--------------------------
-
-Fault reporting
-^^^^^^^^^^^^^^^
-
-::
-
-	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
-	DMAR:[fault reason 05] PTE Write access is not set
-	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
-	DMAR:[fault reason 05] PTE Write access is not set
-
-TBD
-----
-
-- For compatibility testing, could use unity map domain for all devices,

just
- provide a 1-1 for all useful memory under a single domain for all devices. -- API for paravirt ops for abstracting functionality for VMM folks. diff --git a/Documentation/x86/iommu.rst b/Documentation/x86/iommu.rst new file mode 100644
index 000000000000..ed87d76a38d5

Documentation/x86/iommu.rst new file +7 -0
@@ -0,0 +1,143 @@
+=================
+x86 IOMMU Support
+=================
+
+The architecture specs can be obtained from the below locations.
+
+- Intel:

http://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/vt-directed-io-spec.pdf
+- AMD: https://www.amd.com/system/files/TechDocs/48882_IOMMU.pdf +

Documentation/x86/iommu.rst new file +25 -0
+This guide gives a quick cheat sheet for some basic understanding.
+
+Basic stuff
+-----------
+
+ACPI enumerates and lists the different IOMMUs on the platform, and
+device scope relationships between devices and which IOMMU controls
+them.
+
+Some ACPI Keywords:
+
+- DMAR - Intel DMA Remapping table
+- DRHD - Intel DMA Remapping Hardware Unit Definition
+- RMRR - Intel Reserved Memory Region Reporting Structure
+- IVRS - AMD I/O Virtualization Reporting Structure
+- IVDB - AMD I/O Virtualization Definition Block
+- IVHD - AMD I/O Virtualization Hardware Definition
+
+What is Intel RMRR?
+^^^^^^^^^^^^^^^^^^^
+
+There are some devices the BIOS controls, for e.g USB devices to perform
+PS2 emulation. The regions of memory used for these devices are marked
+reserved in the e820 map. When we turn on DMA translation, DMA to those
+regions will fail. Hence BIOS uses RMRR to specify these regions along

with +devices that need to access these regions. OS is expected to setup +unity mappings for these regions for these devices to access these regions. +

Documentation/x86/iommu.rst new file +5 -0
+What is AMD IVRS?
+^^^^^^^^^^^^^^^^^
+
+The architecture defines an ACPI-compatible data structure called an I/O
+Virtualization Reporting Structure (IVRS) that is used to convey

information +related to I/O virtualization to system software. The IVRS describes the +configuration and capabilities of the IOMMUs contained in the platform as +well as information about the devices that each IOMMU virtualizes. +

Documentation/x86/iommu.rst new file +3 -0
+The IVRS provides information about the following:
+
+- IOMMUs present in the platform including their capabilities and proper

configuration +- System I/O topology relevant to each IOMMU

+- Peripheral devices that cannot be otherwise enumerated
+- Memory regions used by SMI/SMM, platform firmware, and platform

hardware. These are generally exclusion ranges to be configured by system software. + +How is an I/O Virtual Address (IOVA) generated?
+-----------------------------------------------

Documentation/x86/iommu.rst new file +2 -0
+
+Well behaved drivers call dma_map_*() calls before sending command to

device +that needs to perform DMA. Once DMA is completed and mapping is no longer +required, driver performs dma_unmap_*() calls to unmap the region. +

Documentation/x86/iommu.rst new file +6 -0
+Some exceptions to IOVAs
+------------------------
+
+Interrupt ranges are not address translated, (0xfee00000 - 0xfeefffff).
+The same is true for peer to peer transactions. Hence we reserve the
+address from PCI MMIO ranges so they are not allocated for IOVA

addresses. +

Documentation/x86/iommu.rst new file +28 -0
+Graphics Problems?
+------------------
+
+If you encounter issues with integrated graphics devices, you can try
+adding the option "iommu.passthrough=1", or the equivalent "iommu=pt",
+to the kernel command line to use a 1:1 mapping for the IOMMU in
+general.  On Intel you can also try "intel_iommu=igfx_off" to turn off
+translation specifically for the integrated graphics engine only.  If
+this fixes anything, please ensure you file a bug reporting the problem.
+
+Fault reporting
+---------------
+When errors are reported, the IOMMU signals via an interrupt. The fault
+reason and device that caused it is printed on the console.
+
+
+Kernel Log Samples
+------------------
+
+Intel Boot Messages
+^^^^^^^^^^^^^^^^^^^
+
+Something like this gets printed indicating presence of DMAR tables
+in ACPI:
+
+::
+
+	ACPI: DMAR (v001 A M I  OEMDMAR  0x00000001 MSFT 0x00000097) @

0x000000007f5b5ef0 +
+When DMAR is being processed and initialized by ACPI, prints DMAR locations +and any RMRR's processed:

Documentation/x86/iommu.rst new file +35 -0
+
+::
+
+	ACPI DMAR:Host address width 36
+	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed90000
+	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed91000
+	ACPI DMAR:DRHD (flags: 0x00000001)base: 0x00000000fed93000
+	ACPI DMAR:RMRR base: 0x00000000000ed000 end: 0x00000000000effff
+	ACPI DMAR:RMRR base: 0x000000007f600000 end: 0x000000007fffffff
+
+When DMAR is enabled for use, you will notice:
+
+::
+
+	PCI-DMA: Using DMAR IOMMU
+
+Intel Fault reporting
+^^^^^^^^^^^^^^^^^^^^^
+
+::
+
+	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
+	DMAR:[fault reason 05] PTE Write access is not set
+	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
+	DMAR:[fault reason 05] PTE Write access is not set
+
+AMD Boot Messages
+^^^^^^^^^^^^^^^^^
+
+Something like this gets printed indicating presence of the IOMMU:
+
+::
+
+	AMD-Vi: Found IOMMU cap 0x40
+	AMD-Vi: Extended features (0x4f77ef22294ada): PPR NX GT IA GA PC

GA_vAPIC

Documentation/x86/iommu.rst new file +9 -0
+	AMD-Vi: Interrupt remapping enabled
+	AMD-Vi: Virtual APIC enabled
+
+AMD Fault reporting
+^^^^^^^^^^^^^^^^^^^
+
+::
+
+	AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0007

address=0xffffc02000 flags=0x0000]

Documentation/x86/iommu.rst new file +1 -0
+	AMD-Vi: Event logged [IO_PAGE_FAULT device=07:00.0 domain=0x0007
Quoted 1 line

address=0xffffc02000 flags=0x0000]

Thanks,

Jacob
_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

#3 lore raw

[Public]

Quoted 91 lines

-----Original Message-----
From: Jacob Pan <[email protected]>
Sent: Tuesday, April 26, 2022 12:45 PM
To: Deucher, Alexander <[email protected]>
Cc: [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Suthikulpanit, Suravee <[email protected]>; [email protected]; [email protected] foundation.org; [email protected]; Hegde, Vasant <[email protected]>; [email protected]; Lu, Baolu <[email protected]>
Subject: Re: [PATCH] Documentation: x86: rework IOMMU documentation

Hi Alex,

Thanks for doing this, really helps to catch up the current state. Please see my comments inline.

Quoted 17 lines · Alex Deucher

Add preliminary documentation for AMD IOMMU and combine with the existing Intel IOMMU documentation and clean up and modernize some of the existing documentation to align with the current state of the kernel.

---

V2: Incorporate feedback from Robin to clarify IOMMU vs DMA engine (e.g.,
a device) and document proper DMA API. Also correct the fact that the AMD IOMMU is not limited to managing PCI devices.
v3: Fix spelling and rework text as suggested by Vasant
v4: Combine Intel and AMD documents into a single document as suggested
by Dave Hansen
v5: Clarify that keywords are related to ACPI, grammatical fixes
v6: Make more stuff common based on feedback from Robin

Quoted 3 lines
 Documentation/x86/index.rst       |   2 +-
 Documentation/x86/intel-iommu.rst | 115 ------------------------
 Documentation/x86/iommu.rst       | 143

++++++++++++++++++++++++++++++

Quoted 23 lines
 3 files changed, 144 insertions(+), 116 deletions(-)  delete mode

100644 Documentation/x86/intel-iommu.rst create mode 100644 Documentation/x86/iommu.rst

Documentation/x86/index.rst +1 -1
index f498f1d36cd3..6f8409fe0674 100644
@@ -21,7 +21,7 @@ x86-specific Documentation
    tlb
    mtrr
    pat
-   intel-iommu
+   iommu
    intel_txt
    amd-memory-encryption
    pti
(quoted diff) +0 -0

b/Documentation/x86/intel-iommu.rst deleted file mode 100644 index 099f13d51d5f..000000000000

Documentation/x86/intel-iommu.rst line 7

Quoted 7 lines
Documentation/x86/intel-iommu.rst deleted +0 -7
@@ -1,115 +0,0 @@
-===================
-Linux IOMMU Support
-===================
-
-The architecture spec can be obtained from the below location.
-
-

https://nam11.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.

Quoted 1 line

intel.com%2Fcontent%2Fdam%2Fwww%2Fpublic%2Fus%2Fen%2Fdocuments %2Fprodu

Quoted 1 line

ct-specifications%2Fvt-directed-io-

spec.pdf&amp;data=05%7C01%7Calexand

Quoted 1 line

er.deucher%40amd.com%7C929847a4b2524432d1a608da27a3c9b0%7C3dd 8961fe488

Quoted 1 line

4e608e11a82d994e183d%7C0%7C0%7C637865881851295857%7CUnknow n%7CTWFpbGZs

Quoted 1 line

b3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0 %3D

Quoted 1 line

%7C3000%7C%7C%7C&amp;sdata=KaPkvBSHWbn1cKBRzyk9H%2BuNDll%2Bq 3wPfR3SFVA

Quoted 16 lines

Documentation/x86/intel-iommu.rst line 18

Quoted 12 lines

LwkU%3D&amp;reserved=0

Documentation/x86/intel-iommu.rst deleted +0 -11
-
-This guide gives a quick cheat sheet for some basic understanding.
-
-Some Keywords
-
-- DMAR - DMA remapping
-- DRHD - DMA Remapping Hardware Unit Definition
-- RMRR - Reserved memory Region Reporting Structure
-- ZLR  - Zero length reads from PCI devices
-- IOVA - IO Virtual address.
-

I feel this combined document only focus on IOVA and DMA APIs, it is considered as legacy DMA after scalable mode is introduced by Intel to support DMA with PASID, shared virtual addressing (SVA). Perhaps, we can also combine ./Documentation/x86/sva.rst

I think it would make sense to take that up in a separate patch set.

Quoted 6 lines

With scalable mode, it affects boot messages, fault reporting, etc. I am not saying no to this document, just suggesting. I don't know where AMD is at in terms of PASID support but there are lots of things in common between VT-d and ARM's SMMU in terms of PASID/SVA. Should we broaden the purpose of this document even further?

I think that would make sense for a future clean up. I'd like to land the current clean up first.

AMD's IOMMU driver has supported PASID for probably 8-10 years. When we originally added it no other vendors were interested in supporting it so we made it a private API which was used by other AMD drivers that needed it at the time. Suravee can probably comment on the status of our support for the cross vendor API.

Alex

Quoted 289 lines
Quoted 12 lines
Documentation/x86/intel-iommu.rst deleted +0 -4
-Basic stuff
------------
-
-ACPI enumerates and lists the different DMA engines in the platform,

and -device scope relationships between PCI devices and which DMA engine controls -them.

Documentation/x86/intel-iommu.rst deleted +0 -5
-
-What is RMRR?
--------------
-
-There are some devices the BIOS controls, for e.g USB devices to
Quoted 3 lines

perform
-PS2 emulation. The regions of memory used for these devices are marked -reserved in the e820 map. When we turn on DMA translation,

DMA

Quoted 15 lines

to those -regions will fail. Hence BIOS uses RMRR to specify these regions along with -devices that need to access these regions. OS is expected to setup -unity mappings for these regions for these devices to access these regions. - -How is IOVA generated?
-----------------------

Documentation/x86/intel-iommu.rst deleted +0 -2
-
-Well behaved drivers call pci_map_*() calls before sending command to

device -that needs to perform DMA. Once DMA is completed and mapping is no longer -required, device performs a pci_unmap_*() calls to unmap the region. - -The Intel IOMMU driver allocates a virtual address per domain. Each PCIE -device has its own domain (hence protection). Devices under p2p bridges -share the virtual address with all devices under the p2p bridge due to -transaction id aliasing for p2p bridges.

Documentation/x86/intel-iommu.rst deleted +0 -2
-
-IOVA generation is pretty generic. We used the same technique as
Quoted 2 lines

vmalloc() -but these are not global address spaces, but separate for each domain. -Different DMA engines may support different number of

domains.

Quoted 34 lines
Documentation/x86/intel-iommu.rst deleted +0 -2
-
-We also allocate guard pages with each mapping, so we can attempt to

catch -any overflow that might happen.

Documentation/x86/intel-iommu.rst deleted +0 -7
-
-
-Graphics Problems?
-------------------
-If you encounter issues with graphics devices, you can try adding
-option intel_iommu=igfx_off to turn off the integrated graphics engine.
-If this fixes anything, please ensure you file a bug reporting the

problem. - -Some exceptions to IOVA
------------------------

Documentation/x86/intel-iommu.rst deleted +0 -3
-Interrupt ranges are not address translated, (0xfee00000 - 0xfeefffff).
-The same is true for peer to peer transactions. Hence we reserve the
-address from PCI MMIO ranges so they are not allocated for IOVA

addresses. -

Documentation/x86/intel-iommu.rst deleted +0 -4
-
-Fault reporting
----------------
-When errors are reported, the DMA engine signals via an interrupt.

The fault -reason and device that caused it with fault reason is printed on console. - -See below for sample.

Documentation/x86/intel-iommu.rst deleted +0 -9
-
-
-Boot Message Sample
--------------------
-
-Something like this gets printed indicating presence of DMAR tables
-in ACPI.
-
-ACPI: DMAR (v001 A M I  OEMDMAR  0x00000001 MSFT 0x00000097) @

0x000000007f5b5ef0 -
-When DMAR is being processed and initialized by ACPI, prints DMAR locations -and any RMRR's processed::

Documentation/x86/intel-iommu.rst

Quoted 6 lines
Documentation/x86/intel-iommu.rst deleted +0 -6
-
-	ACPI DMAR:Host address width 36
-	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed90000
-	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed91000
-	ACPI DMAR:DRHD (flags: 0x00000001)base: 0x00000000fed93000
-	ACPI DMAR:RMRR base: 0x00000000000ed000 end:

0x00000000000effff

Documentation/x86/intel-iommu.rst

Quoted 1 line
Documentation/x86/intel-iommu.rst deleted +0 -1
-	ACPI DMAR:RMRR base: 0x000000007f600000 end:

0x000000007fffffff

Quoted 30 lines
Documentation/x86/intel-iommu.rst deleted +0 -20
-
-When DMAR is enabled for use, you will notice..
-
-PCI-DMA: Using DMAR IOMMU
--------------------------
-
-Fault reporting
-^^^^^^^^^^^^^^^
-
-::
-
-	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
-	DMAR:[fault reason 05] PTE Write access is not set
-	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
-	DMAR:[fault reason 05] PTE Write access is not set
-
-TBD
-----
-
-- For compatibility testing, could use unity map domain for all

devices, just
- provide a 1-1 for all useful memory under a single domain for all devices. -- API for paravirt ops for abstracting functionality for VMM folks. diff --git a/Documentation/x86/iommu.rst b/Documentation/x86/iommu.rst new file mode 100644 index 000000000000..ed87d76a38d5

Documentation/x86/iommu.rst line 7

Quoted 7 lines
Documentation/x86/iommu.rst new file +7 -0
@@ -0,0 +1,143 @@
+=================
+x86 IOMMU Support
+=================
+
+The architecture specs can be obtained from the below locations.
+
+- Intel:

https://nam11.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.i

Quoted 1 line

ntel.com%2Fcontent%2Fdam%2Fwww%2Fpublic%2Fus%2Fen%2Fdocuments% 2Fproduc

Quoted 1 line

t-specifications%2Fvt-directed-io-

spec.pdf&amp;data=05%7C01%7Calexande

Quoted 1 line

r.deucher%40amd.com%7C929847a4b2524432d1a608da27a3c9b0%7C3dd8 961fe4884

Quoted 1 line

e608e11a82d994e183d%7C0%7C0%7C637865881851295857%7CUnknown %7CTWFpbGZsb

Quoted 1 line

3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0 %3D%

Quoted 1 line

7C3000%7C%7C%7C&amp;sdata=KaPkvBSHWbn1cKBRzyk9H%2BuNDll%2Bq3 wPfR3SFVAL

Quoted 3 lines

wkU%3D&amp;reserved=0
+- AMD:

+https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww .amd.com%2Fsystem%2Ffiles%2FTechDocs%2F48882_IOMMU.pdf&amp;data =05%7C01%7Calexander.deucher%40amd.com%7C929847a4b2524432d1a6 08da27a3c9b0%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C63 7865881851295857%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMD AiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C& amp;sdata=QFq8HBY6cm2XaZ50u5LQA3RX3NX%2BwVsMqfJFDH9bFDs%3D&a mp;reserved=0 + This guide gives a quick cheat sheet for some basic understanding.

Quoted 14 lines
Documentation/x86/iommu.rst new file +14 -0
+
+Basic stuff
+-----------
+
+ACPI enumerates and lists the different IOMMUs on the platform, and
+device scope relationships between devices and which IOMMU controls
+them.
+
+Some ACPI Keywords:
+
+- DMAR - Intel DMA Remapping table
+- DRHD - Intel DMA Remapping Hardware Unit Definition
+- RMRR - Intel Reserved Memory Region Reporting Structure
+- IVRS - AMD I/O Virtualization Reporting Structure

Documentation/x86/iommu.rst

Quoted 10 lines
Documentation/x86/iommu.rst new file +10 -0
+- IVDB - AMD I/O Virtualization Definition Block
+- IVHD - AMD I/O Virtualization Hardware Definition
+
+What is Intel RMRR?
+^^^^^^^^^^^^^^^^^^^
+
+There are some devices the BIOS controls, for e.g USB devices to
+perform
+PS2 emulation. The regions of memory used for these devices are
+marked reserved in the e820 map. When we turn on DMA translation,

DMA

Quoted 37 lines
Documentation/x86/iommu.rst new file +2 -0
+to those regions will fail. Hence BIOS uses RMRR to specify these
+regions along

with +devices that need to access these regions. OS is expected to setup
+unity mappings for these regions for these devices to access these regions. +

Documentation/x86/iommu.rst new file +5 -0
+What is AMD IVRS?
+^^^^^^^^^^^^^^^^^
+
+The architecture defines an ACPI-compatible data structure called an
+I/O Virtualization Reporting Structure (IVRS) that is used to convey

information +related to I/O virtualization to system software. The IVRS describes the +configuration and capabilities of the IOMMUs contained in the platform as +well as information about the devices that each IOMMU virtualizes. +

Documentation/x86/iommu.rst new file +4 -0
+The IVRS provides information about the following:
+
+- IOMMUs present in the platform including their capabilities and
+proper

configuration +- System I/O topology relevant to each IOMMU

+- Peripheral devices that cannot be otherwise enumerated
+- Memory regions used by SMI/SMM, platform firmware, and platform

hardware. These are generally exclusion ranges to be configured by system software. + +How is an I/O Virtual Address (IOVA) generated?
+-----------------------------------------------

Documentation/x86/iommu.rst new file +2 -0
+
+Well behaved drivers call dma_map_*() calls before sending command to

device +that needs to perform DMA. Once DMA is completed and mapping is no longer +required, driver performs dma_unmap_*() calls to unmap the region. +

Documentation/x86/iommu.rst new file +6 -0
+Some exceptions to IOVAs
+------------------------
+
+Interrupt ranges are not address translated, (0xfee00000 - 0xfeefffff).
+The same is true for peer to peer transactions. Hence we reserve the
+address from PCI MMIO ranges so they are not allocated for IOVA

addresses. +

Documentation/x86/iommu.rst

Quoted 9 lines
Documentation/x86/iommu.rst new file +9 -0
+Graphics Problems?
+------------------
+
+If you encounter issues with integrated graphics devices, you can try
+adding the option "iommu.passthrough=1", or the equivalent
+"iommu=pt", to the kernel command line to use a 1:1 mapping for the
+IOMMU in general.  On Intel you can also try "intel_iommu=igfx_off"
+to turn off translation specifically for the integrated graphics
+engine only.  If this fixes anything, please ensure you file a bug reporting

the problem.

Quoted 9 lines
Documentation/x86/iommu.rst new file +9 -0
+
+Fault reporting
+---------------
+When errors are reported, the IOMMU signals via an interrupt. The
+fault reason and device that caused it is printed on the console.
+
+
+Kernel Log Samples
+------------------

Documentation/x86/iommu.rst

Quoted 10 lines
Documentation/x86/iommu.rst new file +10 -0
+
+Intel Boot Messages
+^^^^^^^^^^^^^^^^^^^
+
+Something like this gets printed indicating presence of DMAR tables
+in ACPI:
+
+::
+
+	ACPI: DMAR (v001 A M I  OEMDMAR  0x00000001 MSFT

0x00000097) @

Documentation/x86/iommu.rst

Quoted 11 lines

0x000000007f5b5ef0 +
+When DMAR is being processed and initialized by ACPI, prints DMAR locations +and any RMRR's processed:

Documentation/x86/iommu.rst new file +8 -0
+
+::
+
+	ACPI DMAR:Host address width 36
+	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed90000
+	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed91000
+	ACPI DMAR:DRHD (flags: 0x00000001)base: 0x00000000fed93000
+	ACPI DMAR:RMRR base: 0x00000000000ed000 end:

0x00000000000effff

Documentation/x86/iommu.rst

Quoted 1 line
Documentation/x86/iommu.rst new file +1 -0
+	ACPI DMAR:RMRR base: 0x000000007f600000 end:

0x000000007fffffff

Quoted 37 lines
Documentation/x86/iommu.rst new file +26 -0
+
+When DMAR is enabled for use, you will notice:
+
+::
+
+	PCI-DMA: Using DMAR IOMMU
+
+Intel Fault reporting
+^^^^^^^^^^^^^^^^^^^^^
+
+::
+
+	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
+	DMAR:[fault reason 05] PTE Write access is not set
+	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
+	DMAR:[fault reason 05] PTE Write access is not set
+
+AMD Boot Messages
+^^^^^^^^^^^^^^^^^
+
+Something like this gets printed indicating presence of the IOMMU:
+
+::
+
+	AMD-Vi: Found IOMMU cap 0x40
+	AMD-Vi: Extended features (0x4f77ef22294ada): PPR NX GT IA GA PC

GA_vAPIC

Documentation/x86/iommu.rst new file +9 -0
+	AMD-Vi: Interrupt remapping enabled
+	AMD-Vi: Virtual APIC enabled
+
+AMD Fault reporting
+^^^^^^^^^^^^^^^^^^^
+
+::
+
+	AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0007

address=0xffffc02000 flags=0x0000]

Documentation/x86/iommu.rst

Quoted 1 line
Documentation/x86/iommu.rst new file +1 -0
+	AMD-Vi: Event logged [IO_PAGE_FAULT device=07:00.0

domain=0x0007

Quoted 6 lines
Quoted 1 line

address=0xffffc02000 flags=0x0000]

Thanks,

Jacob

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Acked-by on v1 1/1
#4 lore raw
In reply to Alex Deucher
Quoted 17 lines · Alex Deucher

Add preliminary documentation for AMD IOMMU and combine with the existing Intel IOMMU documentation and clean up and modernize some of the existing documentation to align with the current state of the kernel.

---

V2: Incorporate feedback from Robin to clarify IOMMU vs DMA engine (e.g.,
a device) and document proper DMA API. Also correct the fact that the AMD IOMMU is not limited to managing PCI devices.
v3: Fix spelling and rework text as suggested by Vasant
v4: Combine Intel and AMD documents into a single document as suggested
by Dave Hansen
v5: Clarify that keywords are related to ACPI, grammatical fixes
v6: Make more stuff common based on feedback from Robin

Quoted 6 lines
 Documentation/x86/index.rst       |   2 +-
 Documentation/x86/intel-iommu.rst | 115 ------------------------
 Documentation/x86/iommu.rst       | 143 ++++++++++++++++++++++++++++++
 3 files changed, 144 insertions(+), 116 deletions(-)
 delete mode 100644 Documentation/x86/intel-iommu.rst
 create mode 100644 Documentation/x86/iommu.rst

Jonathan, will you merge that through the documentation tree?