Merge branch 'pci/virtualization' into next

* pci/virtualization:
  PCI: Document reset method return values
  PCI: Detach driver before procfs & sysfs teardown on device remove
  PCI: Apply Cavium ThunderX ACS quirk to more Root Ports
  PCI: Set Cavium ACS capability quirk flags to assert RR/CR/SV/UF
  PCI: Restore ARI Capable Hierarchy before setting numVFs
  PCI: Create SR-IOV virtfn/physfn links before attaching driver
  PCI: Expose SR-IOV offset, stride, and VF device ID via sysfs
  PCI: Cache the VF device ID in the SR-IOV structure
  PCI: Add Kconfig PCI_IOV dependency for PCI_REALLOC_ENABLE_AUTO
  PCI: Remove unused function __pci_reset_function()
  PCI: Remove reset argument from pci_iov_{add,remove}_virtfn()

arch/powerpc/kernel/eeh_driver.c

@@ -441,7 +441,7 @@ static void *eeh_add_virt_device(void *data, void *userdata)
 	}
 
 #ifdef CONFIG_PPC_POWERNV
-	pci_iov_add_virtfn(edev->physfn, pdn->vf_index, 0);
+	pci_iov_add_virtfn(edev->physfn, pdn->vf_index);
 #endif
 	return NULL;
 }
@@ -499,7 +499,7 @@ static void *eeh_rmv_device(void *data, void *userdata)
 #ifdef CONFIG_PPC_POWERNV
 		struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
-		pci_iov_remove_virtfn(edev->physfn, pdn->vf_index, 0);
+		pci_iov_remove_virtfn(edev->physfn, pdn->vf_index);
 		edev->pdev = NULL;
 
 		/*

drivers/pci/Kconfig

@@ -51,13 +51,13 @@ config PCI_DEBUG
 config PCI_REALLOC_ENABLE_AUTO
 	bool "Enable PCI resource re-allocation detection"
 	depends on PCI
+	depends on PCI_IOV
 	help
 	  Say Y here if you want the PCI core to detect if PCI resource
 	  re-allocation needs to be enabled. You can always use pci=realloc=on
-          or pci=realloc=off to override it.  Note this feature is a no-op
-          unless PCI_IOV support is also enabled; in that case it will
-          automatically re-allocate PCI resources if SR-IOV BARs have not
-          been allocated by the BIOS.
+	  or pci=realloc=off to override it.  It will automatically
+	  re-allocate PCI resources if SR-IOV BARs have not been allocated by
+	  the BIOS.
 
 	  When in doubt, say N.
 

drivers/pci/iov.c

@@ -113,7 +113,7 @@ resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno)
 	return dev->sriov->barsz[resno - PCI_IOV_RESOURCES];
 }
 
-int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset)
+int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 {
 	int i;
 	int rc = -ENOMEM;
@@ -134,7 +134,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset)
 
 	virtfn->devfn = pci_iov_virtfn_devfn(dev, id);
 	virtfn->vendor = dev->vendor;
-	pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_DID, &virtfn->device);
+	virtfn->device = iov->vf_device;
 	rc = pci_setup_device(virtfn);
 	if (rc)
 		goto failed0;
@@ -157,12 +157,8 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset)
 		BUG_ON(rc);
 	}
 
-	if (reset)
-		__pci_reset_function(virtfn);
-
 	pci_device_add(virtfn, virtfn->bus);
 
-	pci_bus_add_device(virtfn);
 	sprintf(buf, "virtfn%u", id);
 	rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf);
 	if (rc)
@@ -173,6 +169,8 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset)
 
 	kobject_uevent(&virtfn->dev.kobj, KOBJ_CHANGE);
 
+	pci_bus_add_device(virtfn);
+
 	return 0;
 
 failed2:
@@ -187,7 +185,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset)
 	return rc;
 }
 
-void pci_iov_remove_virtfn(struct pci_dev *dev, int id, int reset)
+void pci_iov_remove_virtfn(struct pci_dev *dev, int id)
 {
 	char buf[VIRTFN_ID_LEN];
 	struct pci_dev *virtfn;
@@ -198,11 +196,6 @@ void pci_iov_remove_virtfn(struct pci_dev *dev, int id, int reset)
 	if (!virtfn)
 		return;
 
-	if (reset) {
-		device_release_driver(&virtfn->dev);
-		__pci_reset_function(virtfn);
-	}
-
 	sprintf(buf, "virtfn%u", id);
 	sysfs_remove_link(&dev->dev.kobj, buf);
 	/*
@@ -317,7 +310,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 	pci_cfg_access_unlock(dev);
 
 	for (i = 0; i < initial; i++) {
-		rc = pci_iov_add_virtfn(dev, i, 0);
+		rc = pci_iov_add_virtfn(dev, i);
 		if (rc)
 			goto failed;
 	}
@@ -329,7 +322,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 
 failed:
 	while (i--)
-		pci_iov_remove_virtfn(dev, i, 0);
+		pci_iov_remove_virtfn(dev, i);
 
 err_pcibios:
 	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE);
@@ -356,7 +349,7 @@ static void sriov_disable(struct pci_dev *dev)
 		return;
 
 	for (i = 0; i < iov->num_VFs; i++)
-		pci_iov_remove_virtfn(dev, i, 0);
+		pci_iov_remove_virtfn(dev, i);
 
 	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE);
 	pci_cfg_access_lock(dev);
@@ -449,6 +442,7 @@ static int sriov_init(struct pci_dev *dev, int pos)
 	iov->nres = nres;
 	iov->ctrl = ctrl;
 	iov->total_VFs = total;
+	pci_read_config_word(dev, pos + PCI_SRIOV_VF_DID, &iov->vf_device);
 	iov->pgsz = pgsz;
 	iov->self = dev;
 	iov->drivers_autoprobe = true;
@@ -504,6 +498,14 @@ static void sriov_restore_state(struct pci_dev *dev)
 	if (ctrl & PCI_SRIOV_CTRL_VFE)
 		return;
 
+	/*
+	 * Restore PCI_SRIOV_CTRL_ARI before pci_iov_set_numvfs() because
+	 * it reads offset & stride, which depend on PCI_SRIOV_CTRL_ARI.
+	 */
+	ctrl &= ~PCI_SRIOV_CTRL_ARI;
+	ctrl |= iov->ctrl & PCI_SRIOV_CTRL_ARI;
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, ctrl);
+
 	for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++)
 		pci_update_resource(dev, i);
 
@@ -724,7 +726,7 @@ int pci_vfs_assigned(struct pci_dev *dev)
 	 * determine the device ID for the VFs, the vendor ID will be the
 	 * same as the PF so there is no need to check for that one
 	 */
-	pci_read_config_word(dev, dev->sriov->pos + PCI_SRIOV_VF_DID, &dev_id);
+	dev_id = dev->sriov->vf_device;
 
 	/* loop through all the VFs to see if we own any that are assigned */
 	vfdev = pci_get_device(dev->vendor, dev_id, NULL);

drivers/pci/pci-sysfs.c

@@ -648,6 +648,33 @@ static ssize_t sriov_numvfs_store(struct device *dev,
 	return count;
 }
 
+static ssize_t sriov_offset_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return sprintf(buf, "%u\n", pdev->sriov->offset);
+}
+
+static ssize_t sriov_stride_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return sprintf(buf, "%u\n", pdev->sriov->stride);
+}
+
+static ssize_t sriov_vf_device_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return sprintf(buf, "%x\n", pdev->sriov->vf_device);
+}
+
 static ssize_t sriov_drivers_autoprobe_show(struct device *dev,
 					    struct device_attribute *attr,
 					    char *buf)
@@ -676,6 +703,9 @@ static struct device_attribute sriov_totalvfs_attr = __ATTR_RO(sriov_totalvfs);
 static struct device_attribute sriov_numvfs_attr =
 		__ATTR(sriov_numvfs, (S_IRUGO|S_IWUSR|S_IWGRP),
 		       sriov_numvfs_show, sriov_numvfs_store);
+static struct device_attribute sriov_offset_attr = __ATTR_RO(sriov_offset);
+static struct device_attribute sriov_stride_attr = __ATTR_RO(sriov_stride);
+static struct device_attribute sriov_vf_device_attr = __ATTR_RO(sriov_vf_device);
 static struct device_attribute sriov_drivers_autoprobe_attr =
 		__ATTR(sriov_drivers_autoprobe, (S_IRUGO|S_IWUSR|S_IWGRP),
 		       sriov_drivers_autoprobe_show, sriov_drivers_autoprobe_store);
@@ -1748,6 +1778,9 @@ static const struct attribute_group pci_dev_hp_attr_group = {
 static struct attribute *sriov_dev_attrs[] = {
 	&sriov_totalvfs_attr.attr,
 	&sriov_numvfs_attr.attr,
+	&sriov_offset_attr.attr,
+	&sriov_stride_attr.attr,
+	&sriov_vf_device_attr.attr,
 	&sriov_drivers_autoprobe_attr.attr,
 	NULL,
 };

drivers/pci/pci.c

@@ -4246,35 +4246,6 @@ static void pci_dev_restore(struct pci_dev *dev)
 		err_handler->reset_done(dev);
 }
 
-/**
- * __pci_reset_function - reset a PCI device function
- * @dev: PCI device to reset
- *
- * Some devices allow an individual function to be reset without affecting
- * other functions in the same device.  The PCI device must be responsive
- * to PCI config space in order to use this function.
- *
- * The device function is presumed to be unused when this function is called.
- * Resetting the device will make the contents of PCI configuration space
- * random, so any caller of this must be prepared to reinitialise the
- * device including MSI, bus mastering, BARs, decoding IO and memory spaces,
- * etc.
- *
- * Returns 0 if the device function was successfully reset or negative if the
- * device doesn't support resetting a single function.
- */
-int __pci_reset_function(struct pci_dev *dev)
-{
-	int ret;
-
-	pci_dev_lock(dev);
-	ret = __pci_reset_function_locked(dev);
-	pci_dev_unlock(dev);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(__pci_reset_function);
-
 /**
  * __pci_reset_function_locked - reset a PCI device function while holding
  * the @dev mutex lock.
@@ -4300,6 +4271,14 @@ int __pci_reset_function_locked(struct pci_dev *dev)
 
 	might_sleep();
 
+	/*
+	 * A reset method returns -ENOTTY if it doesn't support this device
+	 * and we should try the next method.
+	 *
+	 * If it returns 0 (success), we're finished.  If it returns any
+	 * other error, we're also finished: this indicates that further
+	 * reset mechanisms might be broken on the device.
+	 */
 	rc = pci_dev_specific_reset(dev, 0);
 	if (rc != -ENOTTY)
 		return rc;
@@ -4365,8 +4344,8 @@ int pci_probe_reset_function(struct pci_dev *dev)
  *
  * This function does not just reset the PCI portion of a device, but
  * clears all the state associated with the device.  This function differs
- * from __pci_reset_function in that it saves and restores device state
- * over the reset.
+ * from __pci_reset_function_locked() in that it saves and restores device state
+ * over the reset and takes the PCI device lock.
  *
  * Returns 0 if the device function was successfully reset or negative if the
  * device doesn't support resetting a single function.
@@ -4401,7 +4380,7 @@ EXPORT_SYMBOL_GPL(pci_reset_function);
  *
  * This function does not just reset the PCI portion of a device, but
  * clears all the state associated with the device.  This function differs
- * from __pci_reset_function() in that it saves and restores device state
+ * from __pci_reset_function_locked() in that it saves and restores device state
  * over the reset.  It also differs from pci_reset_function() in that it
  * requires the PCI device lock to be held.
  *

drivers/pci/pci.h

@@ -263,6 +263,7 @@ struct pci_sriov {
 	u16 num_VFs;		/* number of VFs available */
 	u16 offset;		/* first VF Routing ID offset */
 	u16 stride;		/* following VF stride */
+	u16 vf_device;		/* VF device ID */
 	u32 pgsz;		/* page size for BAR alignment */
 	u8 link;		/* Function Dependency Link */
 	u8 max_VF_buses;	/* max buses consumed by VFs */

drivers/pci/quirks.c

@@ -4211,17 +4211,32 @@ static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags)
 #endif
 }
 
+static bool pci_quirk_cavium_acs_match(struct pci_dev *dev)
+{
+	/*
+	 * Effectively selects all downstream ports for whole ThunderX 1
+	 * family by 0xf800 mask (which represents 8 SoCs), while the lower
+	 * bits of device ID are used to indicate which subdevice is used
+	 * within the SoC.
+	 */
+	return (pci_is_pcie(dev) &&
+		(pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) &&
+		((dev->device & 0xf800) == 0xa000));
+}
+
 static int pci_quirk_cavium_acs(struct pci_dev *dev, u16 acs_flags)
 {
 	/*
-	 * Cavium devices matching this quirk do not perform peer-to-peer
-	 * with other functions, allowing masking out these bits as if they
-	 * were unimplemented in the ACS capability.
+	 * Cavium root ports don't advertise an ACS capability.  However,
+	 * the RTL internally implements similar protection as if ACS had
+	 * Request Redirection, Completion Redirection, Source Validation,
+	 * and Upstream Forwarding features enabled.  Assert that the
+	 * hardware implements and enables equivalent ACS functionality for
+	 * these flags.
 	 */
-	acs_flags &= ~(PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR |
-		       PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_DT);
+	acs_flags &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_SV | PCI_ACS_UF);
 
-	if (!((dev->device >= 0xa000) && (dev->device <= 0xa0ff)))
+	if (!pci_quirk_cavium_acs_match(dev))
 		return -ENOTTY;
 
 	return acs_flags ? 0 : 1;

drivers/pci/remove.c

@@ -19,9 +19,9 @@ static void pci_stop_dev(struct pci_dev *dev)
 	pci_pme_active(dev, false);
 
 	if (dev->is_added) {
+		device_release_driver(&dev->dev);
 		pci_proc_detach_device(dev);
 		pci_remove_sysfs_dev_files(dev);
-		device_release_driver(&dev->dev);
 		dev->is_added = 0;
 	}
 

include/linux/pci.h

@@ -1093,7 +1093,6 @@ int pcie_set_mps(struct pci_dev *dev, int mps);
 int pcie_get_minimum_link(struct pci_dev *dev, enum pci_bus_speed *speed,
 			  enum pcie_link_width *width);
 void pcie_flr(struct pci_dev *dev);
-int __pci_reset_function(struct pci_dev *dev);
 int __pci_reset_function_locked(struct pci_dev *dev);
 int pci_reset_function(struct pci_dev *dev);
 int pci_reset_function_locked(struct pci_dev *dev);
@@ -1965,8 +1964,8 @@ int pci_iov_virtfn_devfn(struct pci_dev *dev, int id);
 
 int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn);
 void pci_disable_sriov(struct pci_dev *dev);
-int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset);
-void pci_iov_remove_virtfn(struct pci_dev *dev, int id, int reset);
+int pci_iov_add_virtfn(struct pci_dev *dev, int id);
+void pci_iov_remove_virtfn(struct pci_dev *dev, int id);
 int pci_num_vf(struct pci_dev *dev);
 int pci_vfs_assigned(struct pci_dev *dev);
 int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs);
@@ -1983,12 +1982,12 @@ static inline int pci_iov_virtfn_devfn(struct pci_dev *dev, int id)
 }
 static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn)
 { return -ENODEV; }
-static inline int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset)
+static inline int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 {
 	return -ENOSYS;
 }
 static inline void pci_iov_remove_virtfn(struct pci_dev *dev,
-					 int id, int reset) { }
+					 int id) { }
 static inline void pci_disable_sriov(struct pci_dev *dev) { }
 static inline int pci_num_vf(struct pci_dev *dev) { return 0; }
 static inline int pci_vfs_assigned(struct pci_dev *dev)