Skip to contentSkip to conversation

vfio/pci: Avoid mapping BARs for devices with non-mappable BARs

PATCH Applied Farhan Ali 5 participants 14 messages Jul 29 – Aug 10

Subsystems (3)
lore
Share & tools
lore

Farhan Ali

author
#0 lore raw

PATCH 1/1 vfio/pci: Avoid mapping BARs for devices with non-mappable BARs

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
 drivers/vfio/pci/vfio_pci_core.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +3 -0
index 3f11a9624b9c..6a184588ff23 100644
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
 		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+
 		if (!pci_resource_len(pdev, i))
 			continue;
 
Signature · 1 line
2.43.0
#1 lore raw
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 10 lines

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Quoted 7 lines

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")

Sashiko has reviewed this patch and found no issues. It looks great!

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
#2 lore raw
In reply to Farhan Ali
Quoted 26 lines · Farhan Ali

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
 drivers/vfio/pci/vfio_pci_core.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +0 -0
index 3f11a9624b9c..6a184588ff23 100644

drivers/vfio/pci/vfio_pci_core.c static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) · line 559

Quoted 6 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
 		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+

This would work for the ISM case at least, but I wonder: should we check vdev->bar_mmap_supported[bar] instead?

My question boils down to: do we still want messages for some of the cases where we set vdev->bar_mmap_supported[bar] = false in vfio_pci_probe_mmaps()?

Or should the messages only print when we probed, thought the bar could be mmap'd (vdev->bar_mmap_supported[bar] == true), and now hit a failure?

Thanks,
Matt

Quoted 3 lines
drivers/vfio/pci/vfio_pci_core.c +0 -0
 		if (!pci_resource_len(pdev, i))
 			continue;
 
author
#3 lore raw
Quoted 36 lines · Matthew Rosato
Quoted 26 lines · Farhan Ali

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
  drivers/vfio/pci/vfio_pci_core.c | 3 +++
  1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +0 -0
index 3f11a9624b9c..6a184588ff23 100644

drivers/vfio/pci/vfio_pci_core.c static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) · line 559

Quoted 6 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
  		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+

This would work for the ISM case at least, but I wonder: should we check vdev->bar_mmap_supported[bar] instead?

Quoted 3 lines

My question boils down to: do we still want messages for some of the cases where we set vdev->bar_mmap_supported[bar] = false in vfio_pci_probe_mmaps()?

AFAIU vfio_pci_probe_mmaps() is only called in vfio_pci_core_finish_enable(). Since vfio_pci_core_map_bars() is called in vfio_pci_core_enable(), and before vfio_pci_core_finish_enable(), bar_mmap_supported would be false here for all devices. So I don't think it would work here, unless I missed something?

Thanks

Farhan

Quoted 10 lines

Or should the messages only print when we probed, thought the bar could be mmap'd (vdev->bar_mmap_supported[bar] == true), and now hit a failure?

Thanks,
Matt

Quoted 3 lines
drivers/vfio/pci/vfio_pci_core.c +0 -0
  		if (!pci_resource_len(pdev, i))
  			continue;
 
maintainer
#4 lore raw
Quoted 41 lines · On Wed, 29 Jul 2026 13:28:46 -0700 Farhan Ali <[email protected]> wrote:
Quoted 36 lines · Matthew Rosato
Quoted 26 lines · Farhan Ali

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
  drivers/vfio/pci/vfio_pci_core.c | 3 +++
  1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +0 -0
index 3f11a9624b9c..6a184588ff23 100644

drivers/vfio/pci/vfio_pci_core.c static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) · line 559

Quoted 6 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
  		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+  

This would work for the ISM case at least, but I wonder: should we check vdev->bar_mmap_supported[bar] instead?

Quoted 3 lines

My question boils down to: do we still want messages for some of the cases where we set vdev->bar_mmap_supported[bar] = false in vfio_pci_probe_mmaps()?

Quoted 5 lines

AFAIU vfio_pci_probe_mmaps() is only called in vfio_pci_core_finish_enable(). Since vfio_pci_core_map_bars() is called in vfio_pci_core_enable(), and before vfio_pci_core_finish_enable(), bar_mmap_supported would be false here for all devices. So I don't think it would work here, unless I missed something?

Also IO Port and sub-page MMIO BARs are things that do exist. Thanks,

Alex

author
#5 lore raw
Quoted 43 lines · Alex Williamson
Quoted 40 lines · On Wed, 29 Jul 2026 13:28:46 -0700 Farhan Ali <[email protected]> wrote:
Quoted 39 lines · Matthew Rosato
Quoted 26 lines · Farhan Ali

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
   drivers/vfio/pci/vfio_pci_core.c | 3 +++
   1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +0 -0
index 3f11a9624b9c..6a184588ff23 100644

drivers/vfio/pci/vfio_pci_core.c static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) · line 559

Quoted 6 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
   		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+

This would work for the ISM case at least, but I wonder: should we check vdev->bar_mmap_supported[bar] instead?

My question boils down to: do we still want messages for some of the cases where we set vdev->bar_mmap_supported[bar] = false in vfio_pci_probe_mmaps()?

Quoted 8 lines
Quoted 5 lines

AFAIU vfio_pci_probe_mmaps() is only called in vfio_pci_core_finish_enable(). Since vfio_pci_core_map_bars() is called in vfio_pci_core_enable(), and before vfio_pci_core_finish_enable(), bar_mmap_supported would be false here for all devices. So I don't think it would work here, unless I missed something?

Also IO Port and sub-page MMIO BARs are things that do exist. Thanks,

Alex

Just to clarify, are you suggesting we expand this check to also avoid mapping IO port and sub-page MMIO BARs?

Thanks

Farhan

maintainer
#6 lore raw
Quoted 49 lines · On Wed, 29 Jul 2026 14:32:45 -0700 Farhan Ali <[email protected]> wrote:
Quoted 48 lines · Alex Williamson
Quoted 45 lines · On Wed, 29 Jul 2026 13:28:46 -0700 Farhan Ali <[email protected]> wrote:
Quoted 36 lines · Matthew Rosato
Quoted 26 lines · Farhan Ali

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
   drivers/vfio/pci/vfio_pci_core.c | 3 +++
   1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +0 -0
index 3f11a9624b9c..6a184588ff23 100644

drivers/vfio/pci/vfio_pci_core.c static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) · line 559

Quoted 6 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
   		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+  

This would work for the ISM case at least, but I wonder: should we check vdev->bar_mmap_supported[bar] instead?

Quoted 3 lines

My question boils down to: do we still want messages for some of the cases where we set vdev->bar_mmap_supported[bar] = false in vfio_pci_probe_mmaps()?

AFAIU vfio_pci_probe_mmaps() is only called in vfio_pci_core_finish_enable(). Since vfio_pci_core_map_bars() is called in vfio_pci_core_enable(), and before vfio_pci_core_finish_enable(), bar_mmap_supported would be false here for all devices. So I don't think it would work here, unless I missed something?

Quoted 4 lines
Quoted 1 line

Also IO Port and sub-page MMIO BARs are things that do exist. Thanks,

Just to clarify, are you suggesting we expand this check to also avoid mapping IO port and sub-page MMIO BARs?

Sorry, no, I'm not. I think we're conflating that the barmap is related to mmap access. The barmap itself is holding the iomap of the BAR, used for read/write. The only real relation to the mmap is that we request the resource via this path as well.

Therefore not only is the ordering of setting up bar_mmap_supported wrong, it's flagging entirely the wrong thing here and keying on it would entirely break IO port and sub-page MMIO BAR access. Thanks,

Alex

author
#7 lore raw
Quoted 60 lines · Alex Williamson
Quoted 44 lines · On Wed, 29 Jul 2026 14:32:45 -0700 Farhan Ali <[email protected]> wrote:
Quoted 43 lines · Alex Williamson
Quoted 40 lines · On Wed, 29 Jul 2026 13:28:46 -0700 Farhan Ali <[email protected]> wrote:
Quoted 39 lines · Matthew Rosato
Quoted 26 lines · Farhan Ali

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
    drivers/vfio/pci/vfio_pci_core.c | 3 +++
    1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +0 -0
index 3f11a9624b9c..6a184588ff23 100644

drivers/vfio/pci/vfio_pci_core.c static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) · line 559

Quoted 6 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
    		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+

This would work for the ISM case at least, but I wonder: should we check vdev->bar_mmap_supported[bar] instead?

My question boils down to: do we still want messages for some of the cases where we set vdev->bar_mmap_supported[bar] = false in vfio_pci_probe_mmaps()?

Quoted 8 lines
Quoted 6 lines
Quoted 5 lines

AFAIU vfio_pci_probe_mmaps() is only called in vfio_pci_core_finish_enable(). Since vfio_pci_core_map_bars() is called in vfio_pci_core_enable(), and before vfio_pci_core_finish_enable(), bar_mmap_supported would be false here for all devices. So I don't think it would work here, unless I missed something?

Also IO Port and sub-page MMIO BARs are things that do exist. Thanks,

Just to clarify, are you suggesting we expand this check to also avoid mapping IO port and sub-page MMIO BARs?

Sorry, no, I'm not. I think we're conflating that the barmap is related to mmap access. The barmap itself is holding the iomap of the BAR, used for read/write. The only real relation to the mmap is that we request the resource via this path as well.

Quoted 5 lines

Therefore not only is the ordering of setting up bar_mmap_supported wrong, it's flagging entirely the wrong thing here and keying on it would entirely break IO port and sub-page MMIO BAR access. Thanks,

Alex

Hi Alex,

I wanted some guidance on how we should proceed with this patch? The warning messages are a regression on s390 for ISM devices, so we would like to fix it.

Thanks

Farhan

maintainer
#8 lore raw
Quoted 65 lines · On Mon, 3 Aug 2026 09:39:19 -0700 Farhan Ali <[email protected]> wrote:
Quoted 64 lines · Alex Williamson
Quoted 44 lines · On Wed, 29 Jul 2026 14:32:45 -0700 Farhan Ali <[email protected]> wrote:
Quoted 43 lines · Alex Williamson
Quoted 40 lines · On Wed, 29 Jul 2026 13:28:46 -0700 Farhan Ali <[email protected]> wrote:
Quoted 39 lines · Matthew Rosato
Quoted 26 lines · Farhan Ali

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
    drivers/vfio/pci/vfio_pci_core.c | 3 +++
    1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +0 -0
index 3f11a9624b9c..6a184588ff23 100644

drivers/vfio/pci/vfio_pci_core.c static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) · line 559

Quoted 6 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
    		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+  

This would work for the ISM case at least, but I wonder: should we check vdev->bar_mmap_supported[bar] instead?

My question boils down to: do we still want messages for some of the cases where we set vdev->bar_mmap_supported[bar] = false in vfio_pci_probe_mmaps()?

Quoted 8 lines
Quoted 6 lines
Quoted 5 lines

AFAIU vfio_pci_probe_mmaps() is only called in vfio_pci_core_finish_enable(). Since vfio_pci_core_map_bars() is called in vfio_pci_core_enable(), and before vfio_pci_core_finish_enable(), bar_mmap_supported would be false here for all devices. So I don't think it would work here, unless I missed something?

Also IO Port and sub-page MMIO BARs are things that do exist. Thanks,

Just to clarify, are you suggesting we expand this check to also avoid mapping IO port and sub-page MMIO BARs?

Sorry, no, I'm not. I think we're conflating that the barmap is related to mmap access. The barmap itself is holding the iomap of the BAR, used for read/write. The only real relation to the mmap is that we request the resource via this path as well.

Therefore not only is the ordering of setting up bar_mmap_supported wrong, it's flagging entirely the wrong thing here and keying on it would entirely break IO port and sub-page MMIO BAR access. Thanks,

Quoted 7 lines
Quoted 1 line

Alex

Hi Alex,

I wanted some guidance on how we should proceed with this patch? The warning messages are a regression on s390 for ISM devices, so we would like to fix it.

I think the original proposal is probably the correct one. The non_mmapable_bars flag doesn't restrict its application to specific BAR types or access, at least not beyond "can't be mapped to CPU or peers."

If we can't map the BAR to the CPU, then we don't need to request the region or perform the pci_iomap(), which is what I understand explodes here. Therefore we really only need to establish the errno in the barmap here.

The bar_mmap_supported flag describes something else, whether the BAR can be mapped into the user address space. My intention was only to point out that there are BARs that cannot be mapped to the user address space because either they're not MMIO or we can't safely map the full page, therefore bar_mmap_supported is an invalid test for whether we should request the region or iomap the BAR.

Is there still a gap with the original proposal that I'm missing? Thanks,

Alex

author
#9 lore raw
Quoted 74 lines · Alex Williamson
Quoted 65 lines · On Mon, 3 Aug 2026 09:39:19 -0700 Farhan Ali <[email protected]> wrote:
Quoted 64 lines · Alex Williamson
Quoted 44 lines · On Wed, 29 Jul 2026 14:32:45 -0700 Farhan Ali <[email protected]> wrote:
Quoted 43 lines · Alex Williamson
Quoted 40 lines · On Wed, 29 Jul 2026 13:28:46 -0700 Farhan Ali <[email protected]> wrote:
Quoted 39 lines · Matthew Rosato
Quoted 26 lines · Farhan Ali

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
     drivers/vfio/pci/vfio_pci_core.c | 3 +++
     1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +0 -0
index 3f11a9624b9c..6a184588ff23 100644

drivers/vfio/pci/vfio_pci_core.c static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) · line 559

Quoted 6 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
     		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+

This would work for the ISM case at least, but I wonder: should we check vdev->bar_mmap_supported[bar] instead?

My question boils down to: do we still want messages for some of the cases where we set vdev->bar_mmap_supported[bar] = false in vfio_pci_probe_mmaps()?

Quoted 8 lines
Quoted 6 lines
Quoted 5 lines

AFAIU vfio_pci_probe_mmaps() is only called in vfio_pci_core_finish_enable(). Since vfio_pci_core_map_bars() is called in vfio_pci_core_enable(), and before vfio_pci_core_finish_enable(), bar_mmap_supported would be false here for all devices. So I don't think it would work here, unless I missed something?

Also IO Port and sub-page MMIO BARs are things that do exist. Thanks,

Just to clarify, are you suggesting we expand this check to also avoid mapping IO port and sub-page MMIO BARs?

Sorry, no, I'm not. I think we're conflating that the barmap is related to mmap access. The barmap itself is holding the iomap of the BAR, used for read/write. The only real relation to the mmap is that we request the resource via this path as well.

Therefore not only is the ordering of setting up bar_mmap_supported wrong, it's flagging entirely the wrong thing here and keying on it would entirely break IO port and sub-page MMIO BAR access. Thanks,

Quoted 6 lines
Quoted 1 line

Alex

Hi Alex,

I wanted some guidance on how we should proceed with this patch? The warning messages are a regression on s390 for ISM devices, so we would like to fix it.

Quoted 8 lines

I think the original proposal is probably the correct one. The non_mmapable_bars flag doesn't restrict its application to specific BAR types or access, at least not beyond "can't be mapped to CPU or peers."

If we can't map the BAR to the CPU, then we don't need to request the region or perform the pci_iomap(), which is what I understand explodes here. Therefore we really only need to establish the errno in the barmap here.

Yes, its the call to pci_iomap() that leads to the warning.

Quoted 9 lines

The bar_mmap_supported flag describes something else, whether the BAR can be mapped into the user address space. My intention was only to point out that there are BARs that cannot be mapped to the user address space because either they're not MMIO or we can't safely map the full page, therefore bar_mmap_supported is an invalid test for whether we should request the region or iomap the BAR.

Is there still a gap with the original proposal that I'm missing?

AFAICT this fix should be sufficient. I think Matt's question was to see if there were other cases for which bar_mmap_supported were set to false, that we need to consider here. But I will let him clarify to see if he has any concerns.

Thanks

Farhan

Reviewed-by
#10 lore raw
Quoted 8 lines
Quoted 8 lines

The bar_mmap_supported flag describes something else, whether the BAR can be mapped into the user address space.  My intention was only to point out that there are BARs that cannot be mapped to the user address space because either they're not MMIO or we can't safely map the full page, therefore bar_mmap_supported is an invalid test for whether we should request the region or iomap the BAR.

Quoted 6 lines
Quoted 1 line

Is there still a gap with the original proposal that I'm missing?

AFAICT this fix should be sufficient. I think Matt's question was to see if there were other cases for which bar_mmap_supported were set to false, that we need to consider here. But I will let him clarify to see if he has any concerns.

^ Yes exactly that. To be clear: I am happy from the s390 side with the fix as it is proposed.

My questions were basically trying to generate the conversation that was just had in an effort to avoid another fix later.

So, with the context provided (thanks!):

author
#11 lore raw
Quoted 15 lines · Matthew Rosato
Quoted 7 lines
Quoted 7 lines

The bar_mmap_supported flag describes something else, whether the BAR can be mapped into the user address space.  My intention was only to point out that there are BARs that cannot be mapped to the user address space because either they're not MMIO or we can't safely map the full page, therefore bar_mmap_supported is an invalid test for whether we should request the region or iomap the BAR.

Quoted 5 lines
Quoted 1 line

Is there still a gap with the original proposal that I'm missing?

AFAICT this fix should be sufficient. I think Matt's question was to see if there were other cases for which bar_mmap_supported were set to false, that we need to consider here. But I will let him clarify to see if he has any concerns.

^ Yes exactly that. To be clear: I am happy from the s390 side with the fix as it is proposed.

Quoted 6 lines

My questions were basically trying to generate the conversation that was just had in an effort to avoid another fix later.

So, with the context provided (thanks!):

Hi Alex,

Polite ping on this patch. Please let me know if there are any other concerns with this patch or if we could consider this for inclusion to fix the regression on s390.

Thanks

Farhan

Reviewed-by on v1 1/1
#12 lore raw
In reply to Farhan Ali
Quoted 26 lines · Farhan Ali

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
 drivers/vfio/pci/vfio_pci_core.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +0 -0
index 3f11a9624b9c..6a184588ff23 100644

drivers/vfio/pci/vfio_pci_core.c static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) · line 562

Quoted 9 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
 		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+
 		if (!pci_resource_len(pdev, i))
 			continue;
 

While I was following the discussion I forgot to reply. This looks good to me. Thank you for taking care of this.

Feel free to add:

maintainer Applied
#13 lore raw
In reply to Farhan Ali
Quoted 26 lines · On Wed, 29 Jul 2026 11:11:16 -0700 Farhan Ali <[email protected]> wrote:

vfio_pci_core_map_bars() calls pci_iomap() to set up BAR resources, but not all devices support having their BARs mapped by the CPU. The non_mappable_bars flag indicates that a PCI device's BARs cannot be accessed by the CPU. The ISM device on s390 is one such device. The BAR size for an ISM device is 256 TiB, and attempting to map the BAR will lead to warnings:

vmalloc_node_range for size 281474976714752 failed: Address range restricted to 0x2110bab00000 - 0x21903ab00000

Use pdev->non_mappable_bars to skip pci_iomap() for such devices. This flag is set by the PCI core at enumeration time and already serves the same purpose in vfio_pci_probe_mmaps().

Fixes 05f2a68b407a ("vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()")
---
 drivers/vfio/pci/vfio_pci_core.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +0 -0
index 3f11a9624b9c..6a184588ff23 100644

drivers/vfio/pci/vfio_pci_core.c static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) · line 562

Quoted 9 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
 		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+
 		if (!pci_resource_len(pdev, i))
 			continue;
 

Applied to vfio next branch for v7.3. Thanks,

Alex