Skip to contentSkip to conversation

vfio/nvgrace-gpu: Convey kvm to map device memory region as noncached

PATCH Applied [email protected] 3 participants 4 messages Feb 29, 2024 – Mar 6, 2024

Subsystems (5)
lore
Share & tools
lore

[email protected]

author maintainer
#0 lore raw

PATCH v2 1/1 vfio/nvgrace-gpu: Convey kvm to map device memory region as noncached

From: Ankit Agrawal <[email protected]>

The NVIDIA Grace Hopper GPUs have device memory that is supposed to be used as a regular RAM. It is accessible through CPU-GPU chip-to-chip cache coherent interconnect and is present in the system physical address space. The device memory is split into two regions - termed as usemem and resmem - in the system physical address space, with each region mapped and exposed to the VM as a separate fake device BAR [1].

Owing to a hardware defect for Multi-Instance GPU (MIG) feature [2], there is a requirement - as a workaround - for the resmem BAR to display uncached memory characteristics. Based on [3], on system with FWB enabled such as Grace Hopper, the requisite properties (uncached, unaligned access) can be achieved through a VM mapping (S1) of NORMAL_NC and host mapping (S2) of MT_S2_FWB_NORMAL_NC.

KVM currently maps the MMIO region in S2 as MT_S2_FWB_DEVICE_nGnRE by default. The fake device BARs thus displays DEVICE_nGnRE behavior in the VM.

The following table summarizes the behavior for the various S1 and S2 mapping combinations for systems with FWB enabled [3].

S1           |  S2           | Result
NORMAL_NC    |  NORMAL_NC    | NORMAL_NC
NORMAL_NC    |  DEVICE_nGnRE | DEVICE_nGnRE

Recently a change was added that modifies this default behavior and make KVM map MMIO as MT_S2_FWB_NORMAL_NC when a VMA flag VM_ALLOW_ANY_UNCACHED is set [4]. Setting S2 as MT_S2_FWB_NORMAL_NC provides the desired behavior (uncached, unaligned access) for resmem.

To use VM_ALLOW_ANY_UNCACHED flag, the platform must guarantee that no action taken on the MMIO mapping can trigger an uncontained failure. The Grace Hopper satisfies this requirement. So set the VM_ALLOW_ANY_UNCACHED flag in the VMA.

Applied over next-20240227.
base-commit: 22ba90670a51

Cc Alex Williamson <[email protected]>
Cc Kevin Tian <[email protected]>
Cc Jason Gunthorpe <[email protected]>
Cc Vikram Sethi <[email protected]>
Cc Zhi Wang <[email protected]>
---
 drivers/vfio/pci/nvgrace-gpu/main.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)
drivers/vfio/pci/nvgrace-gpu/main.c +10 -1
index 25814006352d..a7fd018aa548 100644
@@ -160,8 +160,17 @@ static int nvgrace_gpu_mmap(struct vfio_device *core_vdev,
 	 * The carved out region of the device memory needs the NORMAL_NC
 	 * property. Communicate as such to the hypervisor.
 	 */
-	if (index == RESMEM_REGION_INDEX)
+	if (index == RESMEM_REGION_INDEX) {
+		/*
+		 * The nvgrace-gpu module has no issues with uncontained
+		 * failures on NORMAL_NC accesses. VM_ALLOW_ANY_UNCACHED is
+		 * set to communicate to the KVM to S2 map as NORMAL_NC.
+		 * This opens up guest usage of NORMAL_NC for this mapping.
+		 */
+		vm_flags_set(vma, VM_ALLOW_ANY_UNCACHED);
+
 		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	}
 
 	/*
 	 * Perform a PFN map to the memory and back the device BAR by the
Signature · 1 line
2.34.1
reviewer Reviewed-by on v2 1/1
#1 lore raw
Quoted 51 lines · On Thu, Feb 29, 2024 at 07:39:34PM +0000, [email protected] wrote:

From: Ankit Agrawal <[email protected]>

The NVIDIA Grace Hopper GPUs have device memory that is supposed to be used as a regular RAM. It is accessible through CPU-GPU chip-to-chip cache coherent interconnect and is present in the system physical address space. The device memory is split into two regions - termed as usemem and resmem - in the system physical address space, with each region mapped and exposed to the VM as a separate fake device BAR [1].

Owing to a hardware defect for Multi-Instance GPU (MIG) feature [2], there is a requirement - as a workaround - for the resmem BAR to display uncached memory characteristics. Based on [3], on system with FWB enabled such as Grace Hopper, the requisite properties (uncached, unaligned access) can be achieved through a VM mapping (S1) of NORMAL_NC and host mapping (S2) of MT_S2_FWB_NORMAL_NC.

KVM currently maps the MMIO region in S2 as MT_S2_FWB_DEVICE_nGnRE by default. The fake device BARs thus displays DEVICE_nGnRE behavior in the VM.

The following table summarizes the behavior for the various S1 and S2 mapping combinations for systems with FWB enabled [3].

S1           |  S2           | Result
NORMAL_NC    |  NORMAL_NC    | NORMAL_NC
NORMAL_NC    |  DEVICE_nGnRE | DEVICE_nGnRE

Recently a change was added that modifies this default behavior and make KVM map MMIO as MT_S2_FWB_NORMAL_NC when a VMA flag VM_ALLOW_ANY_UNCACHED is set [4]. Setting S2 as MT_S2_FWB_NORMAL_NC provides the desired behavior (uncached, unaligned access) for resmem.

To use VM_ALLOW_ANY_UNCACHED flag, the platform must guarantee that no action taken on the MMIO mapping can trigger an uncontained failure. The Grace Hopper satisfies this requirement. So set the VM_ALLOW_ANY_UNCACHED flag in the VMA.

Applied over next-20240227.
base-commit: 22ba90670a51

Cc Alex Williamson <[email protected]>
Cc Kevin Tian <[email protected]>
Cc Jason Gunthorpe <[email protected]>
Cc Vikram Sethi <[email protected]>
Cc Zhi Wang <[email protected]>
Quoted 3 lines
---
 drivers/vfio/pci/nvgrace-gpu/main.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

Jason

#2 lore raw
In reply to [email protected]
Quoted 51 lines · On Thu, 29 Feb 2024 19:39:34 +0000 <[email protected]> wrote:

From: Ankit Agrawal <[email protected]>

The NVIDIA Grace Hopper GPUs have device memory that is supposed to be used as a regular RAM. It is accessible through CPU-GPU chip-to-chip cache coherent interconnect and is present in the system physical address space. The device memory is split into two regions - termed as usemem and resmem - in the system physical address space, with each region mapped and exposed to the VM as a separate fake device BAR [1].

Owing to a hardware defect for Multi-Instance GPU (MIG) feature [2], there is a requirement - as a workaround - for the resmem BAR to display uncached memory characteristics. Based on [3], on system with FWB enabled such as Grace Hopper, the requisite properties (uncached, unaligned access) can be achieved through a VM mapping (S1) of NORMAL_NC and host mapping (S2) of MT_S2_FWB_NORMAL_NC.

KVM currently maps the MMIO region in S2 as MT_S2_FWB_DEVICE_nGnRE by default. The fake device BARs thus displays DEVICE_nGnRE behavior in the VM.

The following table summarizes the behavior for the various S1 and S2 mapping combinations for systems with FWB enabled [3].

S1           |  S2           | Result
NORMAL_NC    |  NORMAL_NC    | NORMAL_NC
NORMAL_NC    |  DEVICE_nGnRE | DEVICE_nGnRE

Recently a change was added that modifies this default behavior and make KVM map MMIO as MT_S2_FWB_NORMAL_NC when a VMA flag VM_ALLOW_ANY_UNCACHED is set [4]. Setting S2 as MT_S2_FWB_NORMAL_NC provides the desired behavior (uncached, unaligned access) for resmem.

To use VM_ALLOW_ANY_UNCACHED flag, the platform must guarantee that no action taken on the MMIO mapping can trigger an uncontained failure. The Grace Hopper satisfies this requirement. So set the VM_ALLOW_ANY_UNCACHED flag in the VMA.

Applied over next-20240227.
base-commit: 22ba90670a51

Cc Alex Williamson <[email protected]>
Cc Kevin Tian <[email protected]>
Cc Jason Gunthorpe <[email protected]>
Cc Vikram Sethi <[email protected]>
Cc Zhi Wang <[email protected]>
Quoted 3 lines
---
 drivers/vfio/pci/nvgrace-gpu/main.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

Applied to vfio next branch for v6.9.

Oliver, FYI I did merge the branch you provided in [1] for this, thanks for the foresight in providing that.

Alex

[1]https://lore.kernel.org/all/[email protected]/

Quoted 24 lines
drivers/vfio/pci/nvgrace-gpu/main.c +10 -1
index 25814006352d..a7fd018aa548 100644
@@ -160,8 +160,17 @@ static int nvgrace_gpu_mmap(struct vfio_device *core_vdev,
 	 * The carved out region of the device memory needs the NORMAL_NC
 	 * property. Communicate as such to the hypervisor.
 	 */
-	if (index == RESMEM_REGION_INDEX)
+	if (index == RESMEM_REGION_INDEX) {
+		/*
+		 * The nvgrace-gpu module has no issues with uncontained
+		 * failures on NORMAL_NC accesses. VM_ALLOW_ANY_UNCACHED is
+		 * set to communicate to the KVM to S2 map as NORMAL_NC.
+		 * This opens up guest usage of NORMAL_NC for this mapping.
+		 */
+		vm_flags_set(vma, VM_ALLOW_ANY_UNCACHED);
+
 		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	}
 
 	/*
 	 * Perform a PFN map to the memory and back the device BAR by the
author maintainer
#3 lore raw
Quoted 23 lines
Quoted 19 lines

To use VM_ALLOW_ANY_UNCACHED flag, the platform must guarantee that no action taken on the MMIO mapping can trigger an uncontained failure. The Grace Hopper satisfies this requirement. So set the VM_ALLOW_ANY_UNCACHED flag in the VMA.

Applied over next-20240227.
base-commit: 22ba90670a51

Cc Alex Williamson <[email protected]>
Cc Kevin Tian <[email protected]>
Cc Jason Gunthorpe <[email protected]>
Cc Vikram Sethi <[email protected]>
Cc Zhi Wang <[email protected]>
Quoted 3 lines

---
  drivers/vfio/pci/nvgrace-gpu/main.c | 11 ++++++++++-

  1 file changed, 10 insertions(+), 1 deletion(-)
Quoted 8 lines

Applied to vfio next branch for v6.9.

Oliver, FYI I did merge the branch you provided in [1] for this, thanks for the foresight in providing that.

Alex

[1]https://lore.kernel.org/all/[email protected]/

Many thanks Alex, appreciate your help with this!