Merge branch 'pci/enumeration' into next

* pci/enumeration:
  PCI: Warn periodically while waiting for non-CRS ("device ready") status
  PCI: Wait up to 60 seconds for device to become ready after FLR
  PCI: Factor out pci_bus_wait_crs()
  PCI: Add pci_bus_crs_vendor_id() to detect CRS response data
  PCI: Always check for non-CRS response before timeout
  PCI: Avoid race while enabling upstream bridges
  PCI: Mark Broadcom HT2100 Root Port Extended Tags as broken

drivers/pci/pci.c

@@ -52,6 +52,7 @@ static void pci_pme_list_scan(struct work_struct *work);
 static LIST_HEAD(pci_pme_list);
 static DEFINE_MUTEX(pci_pme_list_mutex);
 static DECLARE_DELAYED_WORK(pci_pme_work, pci_pme_list_scan);
+static DEFINE_MUTEX(pci_bridge_mutex);
 
 struct pci_pme_device {
 	struct list_head list;
@@ -1348,10 +1349,16 @@ static void pci_enable_bridge(struct pci_dev *dev)
 	if (bridge)
 		pci_enable_bridge(bridge);
 
+	/*
+	 * Hold pci_bridge_mutex to prevent a race when enabling two
+	 * devices below the bridge simultaneously.  The race may cause a
+	 * PCI_COMMAND_MEMORY update to be lost (see changelog).
+	 */
+	mutex_lock(&pci_bridge_mutex);
 	if (pci_is_enabled(dev)) {
 		if (!dev->is_busmaster)
 			pci_set_master(dev);
-		return;
+		goto end;
 	}
 
 	retval = pci_enable_device(dev);
@@ -1359,6 +1366,8 @@ static void pci_enable_bridge(struct pci_dev *dev)
 		dev_err(&dev->dev, "Error enabling bridge (%d), continuing\n",
 			retval);
 	pci_set_master(dev);
+end:
+	mutex_unlock(&pci_bridge_mutex);
 }
 
 static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
@@ -1383,7 +1392,7 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
 		return 0;		/* already enabled */
 
 	bridge = pci_upstream_bridge(dev);
-	if (bridge)
+	if (bridge && !pci_is_enabled(bridge))
 		pci_enable_bridge(bridge);
 
 	/* only skip sriov related */
@@ -3811,27 +3820,49 @@ int pci_wait_for_pending_transaction(struct pci_dev *dev)
 }
 EXPORT_SYMBOL(pci_wait_for_pending_transaction);
 
-/*
- * We should only need to wait 100ms after FLR, but some devices take longer.
- * Wait for up to 1000ms for config space to return something other than -1.
- * Intel IGD requires this when an LCD panel is attached.  We read the 2nd
- * dword because VFs don't implement the 1st dword.
- */
 static void pci_flr_wait(struct pci_dev *dev)
 {
-	int i = 0;
+	int delay = 1, timeout = 60000;
 	u32 id;
 
-	do {
-		msleep(100);
+	/*
+	 * Per PCIe r3.1, sec 6.6.2, a device must complete an FLR within
+	 * 100ms, but may silently discard requests while the FLR is in
+	 * progress.  Wait 100ms before trying to access the device.
+	 */
+	msleep(100);
+
+	/*
+	 * After 100ms, the device should not silently discard config
+	 * requests, but it may still indicate that it needs more time by
+	 * responding to them with CRS completions.  The Root Port will
+	 * generally synthesize ~0 data to complete the read (except when
+	 * CRS SV is enabled and the read was for the Vendor ID; in that
+	 * case it synthesizes 0x0001 data).
+	 *
+	 * Wait for the device to return a non-CRS completion.  Read the
+	 * Command register instead of Vendor ID so we don't have to
+	 * contend with the CRS SV value.
+	 */
+	pci_read_config_dword(dev, PCI_COMMAND, &id);
+	while (id == ~0) {
+		if (delay > timeout) {
+			dev_warn(&dev->dev, "not ready %dms after FLR; giving up\n",
+				 100 + delay - 1);
+			return;
+		}
+
+		if (delay > 1000)
+			dev_info(&dev->dev, "not ready %dms after FLR; waiting\n",
+				 100 + delay - 1);
+
+		msleep(delay);
+		delay *= 2;
 		pci_read_config_dword(dev, PCI_COMMAND, &id);
-	} while (i++ < 10 && id == ~0);
+	}
 
-	if (id == ~0)
-		dev_warn(&dev->dev, "Failed to return from FLR\n");
-	else if (i > 1)
-		dev_info(&dev->dev, "Required additional %dms to return from FLR\n",
-			 (i - 1) * 100);
+	if (delay > 1000)
+		dev_info(&dev->dev, "ready %dms after FLR\n", 100 + delay - 1);
 }
 
 /**

drivers/pci/pci.h

@@ -235,6 +235,7 @@ enum pci_bar_type {
 	pci_bar_mem64,		/* A 64-bit memory BAR */
 };
 
+int pci_configure_extended_tags(struct pci_dev *dev, void *ign);
 bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl,
 				int crs_timeout);
 int pci_setup_device(struct pci_dev *dev);

drivers/pci/probe.c

@@ -1745,21 +1745,50 @@ static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp)
 	 */
 }
 
-static void pci_configure_extended_tags(struct pci_dev *dev)
+int pci_configure_extended_tags(struct pci_dev *dev, void *ign)
 {
-	u32 dev_cap;
+	struct pci_host_bridge *host;
+	u32 cap;
+	u16 ctl;
 	int ret;
 
 	if (!pci_is_pcie(dev))
-		return;
+		return 0;
 
-	ret = pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &dev_cap);
+	ret = pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap);
 	if (ret)
-		return;
+		return 0;
 
-	if (dev_cap & PCI_EXP_DEVCAP_EXT_TAG)
+	if (!(cap & PCI_EXP_DEVCAP_EXT_TAG))
+		return 0;
+
+	ret = pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &ctl);
+	if (ret)
+		return 0;
+
+	host = pci_find_host_bridge(dev->bus);
+	if (!host)
+		return 0;
+
+	/*
+	 * If some device in the hierarchy doesn't handle Extended Tags
+	 * correctly, make sure they're disabled.
+	 */
+	if (host->no_ext_tags) {
+		if (ctl & PCI_EXP_DEVCTL_EXT_TAG) {
+			dev_info(&dev->dev, "disabling Extended Tags\n");
+			pcie_capability_clear_word(dev, PCI_EXP_DEVCTL,
+						   PCI_EXP_DEVCTL_EXT_TAG);
+		}
+		return 0;
+	}
+
+	if (!(ctl & PCI_EXP_DEVCTL_EXT_TAG)) {
+		dev_info(&dev->dev, "enabling Extended Tags\n");
 		pcie_capability_set_word(dev, PCI_EXP_DEVCTL,
 					 PCI_EXP_DEVCTL_EXT_TAG);
+	}
+	return 0;
 }
 
 static void pci_configure_device(struct pci_dev *dev)
@@ -1768,7 +1797,7 @@ static void pci_configure_device(struct pci_dev *dev)
 	int ret;
 
 	pci_configure_mps(dev);
-	pci_configure_extended_tags(dev);
+	pci_configure_extended_tags(dev, NULL);
 
 	memset(&hpp, 0, sizeof(hpp));
 	ret = pci_get_hp_params(dev, &hpp);
@@ -1824,42 +1853,69 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pci_alloc_dev);
 
-bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
-				int crs_timeout)
+static bool pci_bus_crs_vendor_id(u32 l)
+{
+	return (l & 0xffff) == 0x0001;
+}
+
+static bool pci_bus_wait_crs(struct pci_bus *bus, int devfn, u32 *l,
+			     int timeout)
 {
 	int delay = 1;
 
-	if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, l))
-		return false;
+	if (!pci_bus_crs_vendor_id(*l))
+		return true;	/* not a CRS completion */
 
-	/* some broken boards return 0 or ~0 if a slot is empty: */
-	if (*l == 0xffffffff || *l == 0x00000000 ||
-	    *l == 0x0000ffff || *l == 0xffff0000)
-		return false;
+	if (!timeout)
+		return false;	/* CRS, but caller doesn't want to wait */
 
 	/*
-	 * Configuration Request Retry Status.  Some root ports return the
-	 * actual device ID instead of the synthetic ID (0xFFFF) required
-	 * by the PCIe spec.  Ignore the device ID and only check for
-	 * (vendor id == 1).
+	 * We got the reserved Vendor ID that indicates a completion with
+	 * Configuration Request Retry Status (CRS).  Retry until we get a
+	 * valid Vendor ID or we time out.
 	 */
-	while ((*l & 0xffff) == 0x0001) {
-		if (!crs_timeout)
+	while (pci_bus_crs_vendor_id(*l)) {
+		if (delay > timeout) {
+			pr_warn("pci %04x:%02x:%02x.%d: not ready after %dms; giving up\n",
+				pci_domain_nr(bus), bus->number,
+				PCI_SLOT(devfn), PCI_FUNC(devfn), delay - 1);
+
 			return false;
+		}
+		if (delay >= 1000)
+			pr_info("pci %04x:%02x:%02x.%d: not ready after %dms; waiting\n",
+				pci_domain_nr(bus), bus->number,
+				PCI_SLOT(devfn), PCI_FUNC(devfn), delay - 1);
 
 		msleep(delay);
 		delay *= 2;
+
 		if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, l))
 			return false;
-		/* Card hasn't responded in 60 seconds?  Must be stuck. */
-		if (delay > crs_timeout) {
-			printk(KERN_WARNING "pci %04x:%02x:%02x.%d: not responding\n",
-			       pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
-			       PCI_FUNC(devfn));
-			return false;
-		}
 	}
 
+	if (delay >= 1000)
+		pr_info("pci %04x:%02x:%02x.%d: ready after %dms\n",
+			pci_domain_nr(bus), bus->number,
+			PCI_SLOT(devfn), PCI_FUNC(devfn), delay - 1);
+
+	return true;
+}
+
+bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
+				int timeout)
+{
+	if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, l))
+		return false;
+
+	/* some broken boards return 0 or ~0 if a slot is empty: */
+	if (*l == 0xffffffff || *l == 0x00000000 ||
+	    *l == 0x0000ffff || *l == 0xffff0000)
+		return false;
+
+	if (pci_bus_crs_vendor_id(*l))
+		return pci_bus_wait_crs(bus, devfn, l, timeout);
+
 	return true;
 }
 EXPORT_SYMBOL(pci_bus_read_dev_vendor_id);

drivers/pci/quirks.c

@@ -4664,3 +4664,19 @@ static void quirk_intel_no_flr(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_intel_no_flr);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_intel_no_flr);
+
+static void quirk_no_ext_tags(struct pci_dev *pdev)
+{
+	struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus);
+
+	if (!bridge)
+		return;
+
+	bridge->no_ext_tags = 1;
+	dev_info(&pdev->dev, "disabling Extended Tags (this device can't handle them)\n");
+
+	pci_walk_bus(bridge->bus, pci_configure_extended_tags, NULL);
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0140, quirk_no_ext_tags);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0142, quirk_no_ext_tags);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0144, quirk_no_ext_tags);

include/linux/pci.h

@@ -473,6 +473,7 @@ struct pci_host_bridge {
 	void *release_data;
 	struct msi_controller *msi;
 	unsigned int ignore_reset_delay:1;	/* for entire hierarchy */
+	unsigned int no_ext_tags:1;		/* no Extended Tags */
 	/* Resource alignment requirements */
 	resource_size_t (*align_resource)(struct pci_dev *dev,
 			const struct resource *res,