Commit 515ecd53 authored by Matthew Rosato's avatar Matthew Rosato Committed by Alex Williamson
Browse files

vfio/pci: Decouple PCI_COMMAND_MEMORY bit checks from is_virtfn 



While it is true that devices with is_virtfn=1 will have a Memory Space
Enable bit that is hard-wired to 0, this is not the only case where we
see this behavior -- For example some bare-metal hypervisors lack
Memory Space Enable bit emulation for devices not setting is_virtfn
(s390). Fix this by instead checking for the newly-added
no_command_memory bit which directly denotes the need for
PCI_COMMAND_MEMORY emulation in vfio.

Fixes: abafbc55 ("vfio-pci: Invalidate mmaps and block MMIO access on disabled memory")
Signed-off-by: default avatarMatthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: default avatarNiklas Schnelle <schnelle@linux.ibm.com>
Reviewed-by: default avatarPierre Morel <pmorel@linux.ibm.com>
Signed-off-by: default avatarAlex Williamson <alex.williamson@redhat.com>
parent 08b6e22b

drivers/vfio/pci/vfio_pci_config.c

+14 −10
Original line number Diff line number Diff line
@@ -406,7 +406,7 @@ bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev) 
	 * PF SR-IOV capability, there's therefore no need to trigger

	 * faults based on the virtual value.

	 */

	return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY);

	return pdev->no_command_memory || (cmd & PCI_COMMAND_MEMORY);

}



/*
@@ -520,8 +520,8 @@ static int vfio_basic_config_read(struct vfio_pci_device *vdev, int pos, 


	count = vfio_default_config_read(vdev, pos, count, perm, offset, val);



	/* Mask in virtual memory enable for SR-IOV devices */

	if (offset == PCI_COMMAND && vdev->pdev->is_virtfn) {

	/* Mask in virtual memory enable */

	if (offset == PCI_COMMAND && vdev->pdev->no_command_memory) {

		u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);

		u32 tmp_val = le32_to_cpu(*val);
@@ -589,9 +589,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos, 
		 * shows it disabled (phys_mem/io, then the device has

		 * undergone some kind of backdoor reset and needs to be

		 * restored before we allow it to enable the bars.

		 * SR-IOV devices will trigger this, but we catch them later

		 * SR-IOV devices will trigger this - for mem enable let's

		 * catch this now and for io enable it will be caught later

		 */

		if ((new_mem && virt_mem && !phys_mem) ||

		if ((new_mem && virt_mem && !phys_mem &&

		     !pdev->no_command_memory) ||

		    (new_io && virt_io && !phys_io) ||

		    vfio_need_bar_restore(vdev))

			vfio_bar_restore(vdev);
@@ -1734,12 +1736,14 @@ int vfio_config_init(struct vfio_pci_device *vdev) 
				 vconfig[PCI_INTERRUPT_PIN]);



		vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */



	}

	if (pdev->no_command_memory) {

		/*

		 * VFs do no implement the memory enable bit of the COMMAND

		 * register therefore we'll not have it set in our initial

		 * copy of config space after pci_enable_device().  For

		 * consistency with PFs, set the virtual enable bit here.

		 * VFs and devices that set pdev->no_command_memory do not

		 * implement the memory enable bit of the COMMAND register

		 * therefore we'll not have it set in our initial copy of

		 * config space after pci_enable_device().  For consistency

		 * with PFs, set the virtual enable bit here.

		 */

		*(__le16 *)&vconfig[PCI_COMMAND] |=

					cpu_to_le16(PCI_COMMAND_MEMORY);

CRA Git | Maintained and supported by SUSTech CRA and CCSE