PCI: Enable PASID only if entire path supports End-End TLP prefixes

A PCIe endpoint carries the process address space identifier (PASID) in
the TLP prefix as part of the memory read/write transaction. The address
information in the TLP is relevant only for a given PASID context.

An IOMMU takes PASID value and the address information from the
TLP to look up the physical address in the system.

PASID is an End-End TLP Prefix (PCIe r4.0, sec 6.20).  Sec 2.2.10.2 says

  It is an error to receive a TLP with an End-End TLP Prefix by a
  Receiver that does not support End-End TLP Prefixes. A TLP in
  violation of this rule is handled as a Malformed TLP. This is a
  reported error associated with the Receiving Port (see Section 6.2).

Prevent error condition by proactively requiring End-End TLP prefix to be
supported on the entire data path between the endpoint and the root port
before enabling PASID.

Signed-off-by: Sinan Kaya <[email protected]>
Signed-off-by: Bjorn Helgaas <[email protected]>

Author: Sinan Kaya

drivers/pci/ats.c

@@ -273,6 +273,9 @@ int pci_enable_pasid(struct pci_dev *pdev, int features)
 	if (WARN_ON(pdev->pasid_enabled))
 		return -EBUSY;
 
+	if (!pdev->eetlp_prefix_path)
+		return -EINVAL;
+
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID);
 	if (!pos)
 		return -EINVAL;

drivers/pci/probe.c

@@ -2042,6 +2042,29 @@ static void pci_configure_ltr(struct pci_dev *dev)
 #endif
 }
 
+static void pci_configure_eetlp_prefix(struct pci_dev *dev)
+{
+#ifdef CONFIG_PCI_PASID
+	struct pci_dev *bridge;
+	u32 cap;
+
+	if (!pci_is_pcie(dev))
+		return;
+
+	pcie_capability_read_dword(dev, PCI_EXP_DEVCAP2, &cap);
+	if (!(cap & PCI_EXP_DEVCAP2_EE_PREFIX))
+		return;
+
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+		dev->eetlp_prefix_path = 1;
+	else {
+		bridge = pci_upstream_bridge(dev);
+		if (bridge && bridge->eetlp_prefix_path)
+			dev->eetlp_prefix_path = 1;
+	}
+#endif
+}
+
 static void pci_configure_device(struct pci_dev *dev)
 {
 	struct hotplug_params hpp;
@@ -2051,6 +2074,7 @@ static void pci_configure_device(struct pci_dev *dev)
 	pci_configure_extended_tags(dev, NULL);
 	pci_configure_relaxed_ordering(dev);
 	pci_configure_ltr(dev);
+	pci_configure_eetlp_prefix(dev);
 
 	memset(&hpp, 0, sizeof(hpp));
 	ret = pci_get_hp_params(dev, &hpp);

include/linux/pci.h

@@ -350,6 +350,7 @@ struct pci_dev {
 	unsigned int	ltr_path:1;	/* Latency Tolerance Reporting
 					   supported from root to here */
 #endif
+	unsigned int	eetlp_prefix_path:1;	/* End-to-End TLP Prefix */
 
 	pci_channel_state_t error_state;	/* Current connectivity state */
 	struct device	dev;			/* Generic device interface */

include/uapi/linux/pci_regs.h

@@ -636,6 +636,7 @@
 #define  PCI_EXP_DEVCAP2_OBFF_MASK	0x000c0000 /* OBFF support mechanism */
 #define  PCI_EXP_DEVCAP2_OBFF_MSG	0x00040000 /* New message signaling */
 #define  PCI_EXP_DEVCAP2_OBFF_WAKE	0x00080000 /* Re-use WAKE# for OBFF */
+#define PCI_EXP_DEVCAP2_EE_PREFIX	0x00200000 /* End-End TLP Prefix */
 #define PCI_EXP_DEVCTL2		40	/* Device Control 2 */
 #define  PCI_EXP_DEVCTL2_COMP_TIMEOUT	0x000f	/* Completion Timeout Value */
 #define  PCI_EXP_DEVCTL2_COMP_TMOUT_DIS	0x0010	/* Completion Timeout Disable */