Merge branch 'pci/virtualization'

  - probe for device reset support during enumeration instead of runtime
    (Bjorn Helgaas)

  - add ACS quirk for Ampere (née APM) root ports (Feng Kan)

  - add function 1 DMA alias quirk for Marvell 88SE9220 (Thomas
    Vincent-Cross)

  - protect device restore with device lock (Sinan Kaya)

  - handle failure of FLR gracefully (Sinan Kaya)

  - handle CRS (config retry status) after device resets (Sinan Kaya)

  - skip various config reads for SR-IOV VFs as an optimization (KarimAllah
    Ahmed)

* pci/virtualization:
  PCI/IOV: Add missing prototypes for powerpc pcibios interfaces
  PCI/IOV: Use VF0 cached config registers for other VFs
  PCI/IOV: Skip BAR sizing for VFs
  PCI/IOV: Skip INTx config reads for VFs
  PCI: Wait for device to become ready after secondary bus reset
  PCI: Add a return type for pci_reset_bridge_secondary_bus()
  PCI: Wait for device to become ready after a power management reset
  PCI: Rename pci_flr_wait() to pci_dev_wait() and make it generic
  PCI: Handle FLR failure and allow other reset types
  PCI: Protect restore with device lock to be consistent
  PCI: Add function 1 DMA alias quirk for Marvell 88SE9220
  PCI: Add ACS quirk for Ampere root ports
  PCI: Remove redundant probes for device reset support
  PCI: Probe for device reset support during enumeration

Conflicts:
	include/linux/pci.h

6 files changed, 159 insertions, 48 deletions

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 538de9057c23..8adf4a64f291 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -112,6 +112,29 @@ resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno)
 	return dev->sriov->barsz[resno - PCI_IOV_RESOURCES];
 }
 
+static void pci_read_vf_config_common(struct pci_dev *virtfn)
+{
+	struct pci_dev *physfn = virtfn->physfn;
+
+	/*
+	 * Some config registers are the same across all associated VFs.
+	 * Read them once from VF0 so we can skip reading them from the
+	 * other VFs.
+	 *
+	 * PCIe r4.0, sec 9.3.4.1, technically doesn't require all VFs to
+	 * have the same Revision ID and Subsystem ID, but we assume they
+	 * do.
+	 */
+	pci_read_config_dword(virtfn, PCI_CLASS_REVISION,
+			      &physfn->sriov->class);
+	pci_read_config_byte(virtfn, PCI_HEADER_TYPE,
+			     &physfn->sriov->hdr_type);
+	pci_read_config_word(virtfn, PCI_SUBSYSTEM_VENDOR_ID,
+			     &physfn->sriov->subsystem_vendor);
+	pci_read_config_word(virtfn, PCI_SUBSYSTEM_ID,
+			     &physfn->sriov->subsystem_device);
+}
+
 int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 {
 	int i;
@@ -134,13 +157,17 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 	virtfn->devfn = pci_iov_virtfn_devfn(dev, id);
 	virtfn->vendor = dev->vendor;
 	virtfn->device = iov->vf_device;
+	virtfn->is_virtfn = 1;
+	virtfn->physfn = pci_dev_get(dev);
+
+	if (id == 0)
+		pci_read_vf_config_common(virtfn);
+
 	rc = pci_setup_device(virtfn);
 	if (rc)
-		goto failed0;
+		goto failed1;
 
 	virtfn->dev.parent = dev->dev.parent;
-	virtfn->physfn = pci_dev_get(dev);
-	virtfn->is_virtfn = 1;
 	virtfn->multifunction = 0;
 
 	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
@@ -161,10 +188,10 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 	sprintf(buf, "virtfn%u", id);
 	rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf);
 	if (rc)
-		goto failed1;
+		goto failed2;
 	rc = sysfs_create_link(&virtfn->dev.kobj, &dev->dev.kobj, "physfn");
 	if (rc)
-		goto failed2;
+		goto failed3;
 
 	kobject_uevent(&virtfn->dev.kobj, KOBJ_CHANGE);
 
@@ -172,11 +199,12 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 
 	return 0;
 
-failed2:
+failed3:
 	sysfs_remove_link(&dev->dev.kobj, buf);
+failed2:
+	pci_stop_and_remove_bus_device(virtfn);
 failed1:
 	pci_dev_put(dev);
-	pci_stop_and_remove_bus_device(virtfn);
 failed0:
 	virtfn_remove_bus(dev->bus, bus);
 failed:
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 478dde8330c3..116e97dafda0 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1515,11 +1515,10 @@ static int pci_create_capabilities_sysfs(struct pci_dev *dev)
 	/* Active State Power Management */
 	pcie_aspm_create_sysfs_dev_files(dev);
 
-	if (!pci_probe_reset_function(dev)) {
+	if (dev->reset_fn) {
 		retval = device_create_file(&dev->dev, &reset_attr);
 		if (retval)
 			goto error;
-		dev->reset_fn = 1;
 	}
 	return 0;
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index bfac1d5ae842..43aeecc4b675 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -127,6 +127,9 @@ static int __init pcie_port_pm_setup(char *str)
 }
 __setup("pcie_port_pm=", pcie_port_pm_setup);
 
+/* Time to wait after a reset for device to become responsive */
+#define PCIE_RESET_READY_POLL_MS 60000
+
 /**
  * pci_bus_max_busnr - returns maximum PCI bus number of given bus' children
  * @bus: pointer to PCI bus structure to search
@@ -3969,20 +3972,13 @@ int pci_wait_for_pending_transaction(struct pci_dev *dev)
 }
 EXPORT_SYMBOL(pci_wait_for_pending_transaction);
 
-static void pci_flr_wait(struct pci_dev *dev)
+static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
 {
-	int delay = 1, timeout = 60000;
+	int delay = 1;
 	u32 id;
 
 	/*
-	 * 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
+	 * After reset, 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
@@ -3996,14 +3992,14 @@ static void pci_flr_wait(struct pci_dev *dev)
 	pci_read_config_dword(dev, PCI_COMMAND, &id);
 	while (id == ~0) {
 		if (delay > timeout) {
-			pci_warn(dev, "not ready %dms after FLR; giving up\n",
-				 100 + delay - 1);
-			return;
+			pci_warn(dev, "not ready %dms after %s; giving up\n",
+				 delay - 1, reset_type);
+			return -ENOTTY;
 		}
 
 		if (delay > 1000)
-			pci_info(dev, "not ready %dms after FLR; waiting\n",
-				 100 + delay - 1);
+			pci_info(dev, "not ready %dms after %s; waiting\n",
+				 delay - 1, reset_type);
 
 		msleep(delay);
 		delay *= 2;
@@ -4011,7 +4007,10 @@ static void pci_flr_wait(struct pci_dev *dev)
 	}
 
 	if (delay > 1000)
-		pci_info(dev, "ready %dms after FLR\n", 100 + delay - 1);
+		pci_info(dev, "ready %dms after %s\n", delay - 1,
+			 reset_type);
+
+	return 0;
 }
 
 /**
@@ -4040,13 +4039,21 @@ static bool pcie_has_flr(struct pci_dev *dev)
  * device supports FLR before calling this function, e.g. by using the
  * pcie_has_flr() helper.
  */
-void pcie_flr(struct pci_dev *dev)
+int pcie_flr(struct pci_dev *dev)
 {
 	if (!pci_wait_for_pending_transaction(dev))
 		pci_err(dev, "timed out waiting for pending transaction; performing function level reset anyway\n");
 
 	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR);
-	pci_flr_wait(dev);
+
+	/*
+	 * Per PCIe r4.0, 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);
+
+	return pci_dev_wait(dev, "FLR", PCIE_RESET_READY_POLL_MS);
 }
 EXPORT_SYMBOL_GPL(pcie_flr);
 
@@ -4079,8 +4086,16 @@ static int pci_af_flr(struct pci_dev *dev, int probe)
 		pci_err(dev, "timed out waiting for pending transaction; performing AF function level reset anyway\n");
 
 	pci_write_config_byte(dev, pos + PCI_AF_CTRL, PCI_AF_CTRL_FLR);
-	pci_flr_wait(dev);
-	return 0;
+
+	/*
+	 * Per Advanced Capabilities for Conventional PCI ECN, 13 April 2006,
+	 * updated 27 July 2006; 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);
+
+	return pci_dev_wait(dev, "AF_FLR", PCIE_RESET_READY_POLL_MS);
 }
 
 /**
@@ -4125,7 +4140,7 @@ static int pci_pm_reset(struct pci_dev *dev, int probe)
 	pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr);
 	pci_dev_d3_sleep(dev);
 
-	return 0;
+	return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS);
 }
 
 void pci_reset_secondary_bus(struct pci_dev *dev)
@@ -4167,9 +4182,11 @@ void __weak pcibios_reset_secondary_bus(struct pci_dev *dev)
  * Use the bridge control register to assert reset on the secondary bus.
  * Devices on the secondary bus are left in power-on state.
  */
-void pci_reset_bridge_secondary_bus(struct pci_dev *dev)
+int pci_reset_bridge_secondary_bus(struct pci_dev *dev)
 {
 	pcibios_reset_secondary_bus(dev);
+
+	return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS);
 }
 EXPORT_SYMBOL_GPL(pci_reset_bridge_secondary_bus);
 
@@ -4332,8 +4349,9 @@ int __pci_reset_function_locked(struct pci_dev *dev)
 	if (rc != -ENOTTY)
 		return rc;
 	if (pcie_has_flr(dev)) {
-		pcie_flr(dev);
-		return 0;
+		rc = pcie_flr(dev);
+		if (rc != -ENOTTY)
+			return rc;
 	}
 	rc = pci_af_flr(dev, 0);
 	if (rc != -ENOTTY)
@@ -4403,9 +4421,8 @@ int pci_reset_function(struct pci_dev *dev)
 {
 	int rc;
 
-	rc = pci_probe_reset_function(dev);
-	if (rc)
-		return rc;
+	if (!dev->reset_fn)
+		return -ENOTTY;
 
 	pci_dev_lock(dev);
 	pci_dev_save_and_disable(dev);
@@ -4440,9 +4457,8 @@ int pci_reset_function_locked(struct pci_dev *dev)
 {
 	int rc;
 
-	rc = pci_probe_reset_function(dev);
-	if (rc)
-		return rc;
+	if (!dev->reset_fn)
+		return -ENOTTY;
 
 	pci_dev_save_and_disable(dev);
 
@@ -4464,18 +4480,17 @@ int pci_try_reset_function(struct pci_dev *dev)
 {
 	int rc;
 
-	rc = pci_probe_reset_function(dev);
-	if (rc)
-		return rc;
+	if (!dev->reset_fn)
+		return -ENOTTY;
 
 	if (!pci_dev_trylock(dev))
 		return -EAGAIN;
 
 	pci_dev_save_and_disable(dev);
 	rc = __pci_reset_function_locked(dev);
+	pci_dev_restore(dev);
 	pci_dev_unlock(dev);
 
-	pci_dev_restore(dev);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(pci_try_reset_function);
@@ -4683,7 +4698,9 @@ static void pci_slot_restore(struct pci_slot *slot)
 	list_for_each_entry(dev, &slot->bus->devices, bus_list) {
 		if (!dev->slot || dev->slot != slot)
 			continue;
+		pci_dev_lock(dev);
 		pci_dev_restore(dev);
+		pci_dev_unlock(dev);
 		if (dev->subordinate)
 			pci_bus_restore(dev->subordinate);
 	}
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 38b2596df38a..6722302db194 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -293,6 +293,10 @@ struct pci_sriov {
 	u16		driver_max_VFs;	/* Max num VFs driver supports */
 	struct pci_dev	*dev;		/* Lowest numbered PF */
 	struct pci_dev	*self;		/* This PF */
+	u32		class;		/* VF device */
+	u8		hdr_type;	/* VF header type */
+	u16		subsystem_vendor; /* VF subsystem vendor */
+	u16		subsystem_device; /* VF subsystem device */
 	resource_size_t	barsz[PCI_SRIOV_NUM_BARS];	/* VF BAR size */
 	bool		drivers_autoprobe; /* Auto probing of VFs by driver */
 };
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index f26fcbf6942e..caa07109e5f5 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -329,6 +329,10 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 	if (dev->non_compliant_bars)
 		return;
 
+	/* Per PCIe r4.0, sec 9.3.4.1.11, the VF BARs are all RO Zero */
+	if (dev->is_virtfn)
+		return;
+
 	for (pos = 0; pos < howmany; pos++) {
 		struct resource *res = &dev->resource[pos];
 		reg = PCI_BASE_ADDRESS_0 + (pos << 2);
@@ -1240,6 +1244,13 @@ static void pci_read_irq(struct pci_dev *dev)
 {
 	unsigned char irq;
 
+	/* VFs are not allowed to use INTx, so skip the config reads */
+	if (dev->is_virtfn) {
+		dev->pin = 0;
+		dev->irq = 0;
+		return;
+	}
+
 	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &irq);
 	dev->pin = irq;
 	if (irq)
@@ -1399,6 +1410,43 @@ int pci_cfg_space_size(struct pci_dev *dev)
 	return PCI_CFG_SPACE_SIZE;
 }
 
+static u32 pci_class(struct pci_dev *dev)
+{
+	u32 class;
+
+#ifdef CONFIG_PCI_IOV
+	if (dev->is_virtfn)
+		return dev->physfn->sriov->class;
+#endif
+	pci_read_config_dword(dev, PCI_CLASS_REVISION, &class);
+	return class;
+}
+
+static void pci_subsystem_ids(struct pci_dev *dev, u16 *vendor, u16 *device)
+{
+#ifdef CONFIG_PCI_IOV
+	if (dev->is_virtfn) {
+		*vendor = dev->physfn->sriov->subsystem_vendor;
+		*device = dev->physfn->sriov->subsystem_device;
+		return;
+	}
+#endif
+	pci_read_config_word(dev, PCI_SUBSYSTEM_VENDOR_ID, vendor);
+	pci_read_config_word(dev, PCI_SUBSYSTEM_ID, device);
+}
+
+static u8 pci_hdr_type(struct pci_dev *dev)
+{
+	u8 hdr_type;
+
+#ifdef CONFIG_PCI_IOV
+	if (dev->is_virtfn)
+		return dev->physfn->sriov->hdr_type;
+#endif
+	pci_read_config_byte(dev, PCI_HEADER_TYPE, &hdr_type);
+	return hdr_type;
+}
+
 #define LEGACY_IO_RESOURCE	(IORESOURCE_IO | IORESOURCE_PCI_FIXED)
 
 static void pci_msi_setup_pci_dev(struct pci_dev *dev)
@@ -1464,8 +1512,7 @@ int pci_setup_device(struct pci_dev *dev)
 	struct pci_bus_region region;
 	struct resource *res;
 
-	if (pci_read_config_byte(dev, PCI_HEADER_TYPE, &hdr_type))
-		return -EIO;
+	hdr_type = pci_hdr_type(dev);
 
 	dev->sysdata = dev->bus->sysdata;
 	dev->dev.parent = dev->bus->bridge;
@@ -1487,7 +1534,8 @@ int pci_setup_device(struct pci_dev *dev)
 		     dev->bus->number, PCI_SLOT(dev->devfn),
 		     PCI_FUNC(dev->devfn));
 
-	pci_read_config_dword(dev, PCI_CLASS_REVISION, &class);
+	class = pci_class(dev);
+
 	dev->revision = class & 0xff;
 	dev->class = class >> 8;		    /* upper 3 bytes */
 
@@ -1527,8 +1575,8 @@ int pci_setup_device(struct pci_dev *dev)
 			goto bad;
 		pci_read_irq(dev);
 		pci_read_bases(dev, 6, PCI_ROM_ADDRESS);
-		pci_read_config_word(dev, PCI_SUBSYSTEM_VENDOR_ID, &dev->subsystem_vendor);
-		pci_read_config_word(dev, PCI_SUBSYSTEM_ID, &dev->subsystem_device);
+
+		pci_subsystem_ids(dev, &dev->subsystem_vendor, &dev->subsystem_device);
 
 		/*
 		 * Do the ugly legacy mode stuff here rather than broken chip
@@ -2131,6 +2179,9 @@ static void pci_init_capabilities(struct pci_dev *dev)
 
 	/* Advanced Error Reporting */
 	pci_aer_init(dev);
+
+	if (pci_probe_reset_function(dev) == 0)
+		dev->reset_fn = 1;
 }
 
 /*
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 8bf0ad91432a..df75bc8ed40d 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3888,6 +3888,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9182,
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c46 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0,
 			 quirk_dma_func1_alias);
+/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c127 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9220,
+			 quirk_dma_func1_alias);
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c49 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9230,
 			 quirk_dma_func1_alias);
@@ -4506,6 +4509,15 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_CAVIUM, PCI_ANY_ID, pci_quirk_cavium_acs },
 	/* APM X-Gene */
 	{ PCI_VENDOR_ID_AMCC, 0xE004, pci_quirk_xgene_acs },
+	/* Ampere Computing */
+	{ PCI_VENDOR_ID_AMPERE, 0xE005, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE006, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE007, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE008, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE009, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE00A, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE00B, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs },
 	{ 0 }
 };