[PATCH] PCI: vmd: Enable interrupt ordering quirk for Arrow Lake

[PATCH] PCI: vmd: Enable interrupt ordering quirk for Arrow Lake

[Vladimir Nedoshivin]

Intel Arrow Lake VMD device 0xad0b is affected by ARL004. The VMD may
signal an MSI before preceding posted writes from the child device have
reached memory, which can cause the demuxed handler to observe stale
completion data.

The existing VMD_FEAT_INTERRUPT_QUIRK implements Intel's documented
workaround by issuing a configuration-space read to the MSI initiator
before dispatching the interrupt.

Enable the existing quirk for 0xad0b as well as 0x7d0b and make the
comments describe both MTL016 and ARL004.

Tested on an MSI Vector 17 HX AI with Intel VMD 8086:ad0b and an NVMe
device behind VMD. With the quirk enabled, the NVMe completion stalls
observed without the workaround are no longer reproduced.

Link: https://bugs.launchpad.net/bugs/2166325
Signed-off-by: Vladimir Nedoshivin <gvozd188@mail.ru>
---
 drivers/pci/controller/vmd.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index e45ef8cb16e..9d97a832785 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -94,7 +94,8 @@ enum vmd_features {
 	VMD_FEAT_USE_BIOS_INFO		= (1 << 6),
 
 	/*
-	 * Meteor Lake VMD (device ID 0x7d0b) is affected by erratum MTL016:
+	 * Some Intel VMD devices are affected by interrupt ordering errata,
+	 * including MTL016 (0x7d0b) and ARL004 (0xad0b):
 	 * the VMD may signal its MSI before the posted writes that carry the
 	 * child device's DMA data have landed in memory.  The demuxed handler
 	 * then runs against a not-yet-coherent completion queue and misses the
@@ -131,7 +132,7 @@ static DEFINE_RAW_SPINLOCK(list_lock);
  * @enabled:	true if driver enabled IRQ
  * @virq:	the virtual IRQ value provided to the requesting driver.
  * @flush_addr:	config space address of the initiating device, read before
- *		demuxing to flush its posted writes (MTL016); NULL if the
+ *		demuxing to flush its posted writes; NULL if the
  *		VMD is not affected.
  *
  * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to
@@ -1300,7 +1301,7 @@ static const struct pci_device_id vmd_ids[] = {
 	{PCI_VDEVICE(INTEL, 0x7d0b),
 		.driver_data = VMD_FEATS_CLIENT | VMD_FEAT_INTERRUPT_QUIRK,},
 	{PCI_VDEVICE(INTEL, 0xad0b),
-		.driver_data = VMD_FEATS_CLIENT,},
+		.driver_data = VMD_FEATS_CLIENT | VMD_FEAT_INTERRUPT_QUIRK,},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B),
 		.driver_data = VMD_FEATS_CLIENT,},
 	{PCI_VDEVICE(INTEL, 0xb60b),

base-commit: 95ac22dd4bf13373f90bb6d51bcd1fd1d8f5db54
-- 
2.53.0

Re: [PATCH] PCI: vmd: Enable interrupt ordering quirk for Arrow Lake

[Bjorn Helgaas]

On Fri, Sep 11, 2026 at 12:05:39AM +0400, Vladimir Nedoshivin wrote:
> Intel Arrow Lake VMD device 0xad0b is affected by ARL004. The VMD may
> signal an MSI before preceding posted writes from the child device have
> reached memory, which can cause the demuxed handler to observe stale
> completion data.
> 
> The existing VMD_FEAT_INTERRUPT_QUIRK implements Intel's documented
> workaround by issuing a configuration-space read to the MSI initiator
> before dispatching the interrupt.
> 
> Enable the existing quirk for 0xad0b as well as 0x7d0b and make the
> comments describe both MTL016 and ARL004.
> 
> Tested on an MSI Vector 17 HX AI with Intel VMD 8086:ad0b and an NVMe
> device behind VMD. With the quirk enabled, the NVMe completion stalls
> observed without the workaround are no longer reproduced.
> 
> Link: https://bugs.launchpad.net/bugs/2166325
> Signed-off-by: Vladimir Nedoshivin <gvozd188@mail.ru>

Applied on pci/controller/vmd, thanks!

I added the erratum source and text to the commit logs of both the
Meteor Lake quirk and this one:

  PCI: vmd: Flush DMA writes before handling MSI on Arrow Lake

  Per the Intel Core Ultra Processors (Series 2) Specification Update
  (ID 834774 of 9/1/2026), the Arrow Lake VMD device 0xad0b is affected by an
  MSI erratum:

    ARL004: MSI from VMD-Owned Device May Pass Memory Write

    Problem      When the storage subsystem is configured to operate in RAID
		 0 or 1 mode, a Message Signaled Interrupt (MSI) from an
		 Intel® Volume Management Device (Intel® VMD) owned device
		 may interrupt a core before a previous write from the device
		 is completed.

    Workaround   None identified. The VMD MSI interrupt-handler should
		 initially perform a dummy register read to the MSI initiator
		 device prior to any writes to ensure proper PCIe ordering.

  ...

> ---
>  drivers/pci/controller/vmd.c | 7 ++++---
>  1 file changed, 4 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
> index e45ef8cb16e..9d97a832785 100644
> --- a/drivers/pci/controller/vmd.c
> +++ b/drivers/pci/controller/vmd.c
> @@ -94,7 +94,8 @@ enum vmd_features {
>  	VMD_FEAT_USE_BIOS_INFO		= (1 << 6),
>  
>  	/*
> -	 * Meteor Lake VMD (device ID 0x7d0b) is affected by erratum MTL016:
> +	 * Some Intel VMD devices are affected by interrupt ordering errata,
> +	 * including MTL016 (0x7d0b) and ARL004 (0xad0b):
>  	 * the VMD may signal its MSI before the posted writes that carry the
>  	 * child device's DMA data have landed in memory.  The demuxed handler
>  	 * then runs against a not-yet-coherent completion queue and misses the
> @@ -131,7 +132,7 @@ static DEFINE_RAW_SPINLOCK(list_lock);
>   * @enabled:	true if driver enabled IRQ
>   * @virq:	the virtual IRQ value provided to the requesting driver.
>   * @flush_addr:	config space address of the initiating device, read before
> - *		demuxing to flush its posted writes (MTL016); NULL if the
> + *		demuxing to flush its posted writes; NULL if the
>   *		VMD is not affected.
>   *
>   * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to
> @@ -1300,7 +1301,7 @@ static const struct pci_device_id vmd_ids[] = {
>  	{PCI_VDEVICE(INTEL, 0x7d0b),
>  		.driver_data = VMD_FEATS_CLIENT | VMD_FEAT_INTERRUPT_QUIRK,},
>  	{PCI_VDEVICE(INTEL, 0xad0b),
> -		.driver_data = VMD_FEATS_CLIENT,},
> +		.driver_data = VMD_FEATS_CLIENT | VMD_FEAT_INTERRUPT_QUIRK,},
>  	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B),
>  		.driver_data = VMD_FEATS_CLIENT,},
>  	{PCI_VDEVICE(INTEL, 0xb60b),
> 
> base-commit: 95ac22dd4bf13373f90bb6d51bcd1fd1d8f5db54
> -- 
> 2.53.0
>