vfio-pci: Invalidate mmaps and block MMIO access on disabled memory

Accessing the disabled memory space of a PCI device would typically
result in a master abort response on conventional PCI, or an
unsupported request on PCI express.  The user would generally see
these as a -1 response for the read return data and the write would be
silently discarded, possibly with an uncorrected, non-fatal AER error
triggered on the host.  Some systems however take it upon themselves
to bring down the entire system when they see something that might
indicate a loss of data, such as this discarded write to a disabled
memory space.

To avoid this, we want to try to block the user from accessing memory
spaces while they're disabled.  We start with a semaphore around the
memory enable bit, where writers modify the memory enable state and
must be serialized, while readers make use of the memory region and
can access in parallel.  Writers include both direct manipulation via
the command register, as well as any reset path where the internal
mechanics of the reset may both explicitly and implicitly disable
memory access, and manipulation of the MSI-X configuration, where the
MSI-X vector table resides in MMIO space of the device.  Readers
include the read and write file ops to access the vfio device fd
offsets as well as memory mapped access.  In the latter case, we make
use of our new vma list support to zap, or invalidate, those memory
mappings in order to force them to be faulted back in on access.

Our semaphore usage will stall user access to MMIO spaces across
internal operations like reset, but the user might experience new
behavior when trying to access the MMIO space while disabled via the
PCI command register.  Access via read or write while disabled will
return -EIO and access via memory maps will result in a SIGBUS.  This
is expected to be compatible with known use cases and potentially
provides better error handling capabilities than present in the
hardware, while avoiding the more readily accessible and severe
platform error responses that might otherwise occur.

Fixes: CVE-2020-12888
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

1 files changed, 30 insertions, 6 deletions

diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 90c0b80f8acf..3dcddbd572e6 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -395,6 +395,14 @@ static inline void p_setd(struct perm_bits *p, int off, u32 virt, u32 write)
 	*(__le32 *)(&p->write[off]) = cpu_to_le32(write);
 }
 
+/* Caller should hold memory_lock semaphore */
+bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev)
+{
+	u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);
+
+	return cmd & PCI_COMMAND_MEMORY;
+}
+
 /*
  * Restore the *real* BARs after we detect a FLR or backdoor reset.
  * (backdoor = some device specific technique that we didn't catch)
@@ -556,13 +564,18 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 
 		new_cmd = le32_to_cpu(val);
 
+		phys_io = !!(phys_cmd & PCI_COMMAND_IO);
+		virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
+		new_io = !!(new_cmd & PCI_COMMAND_IO);
+
 		phys_mem = !!(phys_cmd & PCI_COMMAND_MEMORY);
 		virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY);
 		new_mem = !!(new_cmd & PCI_COMMAND_MEMORY);
 
-		phys_io = !!(phys_cmd & PCI_COMMAND_IO);
-		virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
-		new_io = !!(new_cmd & PCI_COMMAND_IO);
+		if (!new_mem)
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
+		else
+			down_write(&vdev->memory_lock);
 
 		/*
 		 * If the user is writing mem/io enable (new_mem/io) and we
@@ -579,8 +592,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 	}
 
 	count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
-	if (count < 0)
+	if (count < 0) {
+		if (offset == PCI_COMMAND)
+			up_write(&vdev->memory_lock);
 		return count;
+	}
 
 	/*
 	 * Save current memory/io enable bits in vconfig to allow for
@@ -591,6 +607,8 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 
 		*virt_cmd &= cpu_to_le16(~mask);
 		*virt_cmd |= cpu_to_le16(new_cmd & mask);
+
+		up_write(&vdev->memory_lock);
 	}
 
 	/* Emulate INTx disable */
@@ -828,8 +846,11 @@ static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos,
 						 pos - offset + PCI_EXP_DEVCAP,
 						 &cap);
 
-		if (!ret && (cap & PCI_EXP_DEVCAP_FLR))
+		if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) {
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
 			pci_try_reset_function(vdev->pdev);
+			up_write(&vdev->memory_lock);
+		}
 	}
 
 	/*
@@ -907,8 +928,11 @@ static int vfio_af_config_write(struct vfio_pci_device *vdev, int pos,
 						pos - offset + PCI_AF_CAP,
 						&cap);
 
-		if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP))
+		if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) {
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
 			pci_try_reset_function(vdev->pdev);
+			up_write(&vdev->memory_lock);
+		}
 	}
 
 	return count;