Merge branch 'pci/virtualization'

  - To avoid bus errors, enable PASID only if entire path supports End-End
    TLP prefixes (Sinan Kaya)

  - Unify slot and bus reset functions and remove hotplug knowledge from
    callers (Sinan Kaya)

  - Add Function-Level Reset quirks for Intel and Samsung NVMe devices to
    fix guest reboot issues (Alex Williamson)

  - Add function 1 DMA alias quirk for Marvell 88SS9183 PCIe SSD Controller
    (Bjorn Helgaas)

* pci/virtualization:
  PCI: Add function 1 DMA alias quirk for Marvell 88SS9183
  PCI: Delay after FLR of Intel DC P3700 NVMe
  PCI: Disable Samsung SM961/PM961 NVMe before FLR
  PCI: Export pcie_has_flr()
  PCI: Rename pci_try_reset_bus() to pci_reset_bus()
  PCI: Deprecate pci_reset_bus() and pci_reset_slot() functions
  PCI: Unify try slot and bus reset API
  PCI: Hide pci_reset_bridge_secondary_bus() from drivers
  IB/hfi1: Use pci_try_reset_bus() for initiating PCI Secondary Bus Reset
  PCI: Handle error return from pci_reset_bridge_secondary_bus()
  PCI/IOV: Tidy pci_sriov_set_totalvfs()
  PCI: Enable PASID only if entire path supports End-End TLP prefixes

# Conflicts:
#	drivers/pci/hotplug/pciehp_hpc.c

11 files changed, 177 insertions, 81 deletions

diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 4d4371bf2c7c..baf7c324f7b8 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -905,9 +905,7 @@ static int trigger_sbr(struct hfi1_devdata *dd)
 	 * delay after a reset is required.  Per spec requirements,
 	 * the link is either working or not after that point.
 	 */
-	pci_reset_bridge_secondary_bus(dev->bus->self);
-
-	return 0;
+	return pci_reset_bus(dev);
 }
 
 /*
diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
index 4923a2a8e14b..5b78f3b1b918 100644
--- a/drivers/pci/ats.c
+++ b/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;
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 5b15e76f3564..7136e3430925 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -761,6 +761,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	struct controller *ctrl = slot->ctrl;
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 	u16 stat_mask = 0, ctrl_mask = 0;
+	int rc;
 
 	if (probe)
 		return 0;
@@ -778,7 +779,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0);
 
-	pci_reset_bridge_secondary_bus(ctrl->pcie->port);
+	rc = pci_bridge_secondary_bus_reset(ctrl->pcie->port);
 
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask);
 	pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask);
@@ -786,7 +787,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask);
 
 	up_write(&ctrl->reset_lock);
-	return 0;
+	return rc;
 }
 
 int pcie_init_notification(struct controller *ctrl)
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 0f04ae648cf1..c5f3cd4ed766 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -818,15 +818,15 @@ int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs)
 {
 	if (!dev->is_physfn)
 		return -ENOSYS;
+
 	if (numvfs > dev->sriov->total_VFs)
 		return -EINVAL;
 
 	/* Shouldn't change if VFs already enabled */
 	if (dev->sriov->ctrl & PCI_SRIOV_CTRL_VFE)
 		return -EBUSY;
-	else
-		dev->sriov->driver_max_VFs = numvfs;
 
+	dev->sriov->driver_max_VFs = numvfs;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pci_sriov_set_totalvfs);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 77960fe9d9f3..80da4841c7d2 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4349,7 +4349,7 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
  * Returns true if the device advertises support for PCIe function level
  * resets.
  */
-static bool pcie_has_flr(struct pci_dev *dev)
+bool pcie_has_flr(struct pci_dev *dev)
 {
 	u32 cap;
 
@@ -4359,6 +4359,7 @@ static bool pcie_has_flr(struct pci_dev *dev)
 	pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap);
 	return cap & PCI_EXP_DEVCAP_FLR;
 }
+EXPORT_SYMBOL_GPL(pcie_has_flr);
 
 /**
  * pcie_flr - initiate a PCIe function level reset
@@ -4534,19 +4535,18 @@ void __weak pcibios_reset_secondary_bus(struct pci_dev *dev)
 }
 
 /**
- * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge.
+ * pci_bridge_secondary_bus_reset - Reset the secondary bus on a PCI bridge.
  * @dev: Bridge device
  *
  * Use the bridge control register to assert reset on the secondary bus.
  * Devices on the secondary bus are left in power-on state.
  */
-int pci_reset_bridge_secondary_bus(struct pci_dev *dev)
+int pci_bridge_secondary_bus_reset(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);
 
 static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
 {
@@ -4563,9 +4563,7 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
 	if (probe)
 		return 0;
 
-	pci_reset_bridge_secondary_bus(dev->bus->self);
-
-	return 0;
+	return pci_bridge_secondary_bus_reset(dev->bus->self);
 }
 
 static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, int probe)
@@ -5097,7 +5095,7 @@ int pci_probe_reset_slot(struct pci_slot *slot)
 EXPORT_SYMBOL_GPL(pci_probe_reset_slot);
 
 /**
- * pci_reset_slot - reset a PCI slot
+ * __pci_reset_slot - Try to reset a PCI slot
  * @slot: PCI slot to reset
  *
  * A PCI bus may host multiple slots, each slot may support a reset mechanism
@@ -5109,33 +5107,9 @@ EXPORT_SYMBOL_GPL(pci_probe_reset_slot);
  * through this function.  PCI config space of all devices in the slot and
  * behind the slot is saved before and restored after reset.
  *
- * Return 0 on success, non-zero on error.
- */
-int pci_reset_slot(struct pci_slot *slot)
-{
-	int rc;
-
-	rc = pci_slot_reset(slot, 1);
-	if (rc)
-		return rc;
-
-	pci_slot_save_and_disable(slot);
-
-	rc = pci_slot_reset(slot, 0);
-
-	pci_slot_restore(slot);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(pci_reset_slot);
-
-/**
- * pci_try_reset_slot - Try to reset a PCI slot
- * @slot: PCI slot to reset
- *
  * Same as above except return -EAGAIN if the slot cannot be locked
  */
-int pci_try_reset_slot(struct pci_slot *slot)
+static int __pci_reset_slot(struct pci_slot *slot)
 {
 	int rc;
 
@@ -5156,10 +5130,11 @@ int pci_try_reset_slot(struct pci_slot *slot)
 
 	return rc;
 }
-EXPORT_SYMBOL_GPL(pci_try_reset_slot);
 
 static int pci_bus_reset(struct pci_bus *bus, int probe)
 {
+	int ret;
+
 	if (!bus->self || !pci_bus_resetable(bus))
 		return -ENOTTY;
 
@@ -5170,11 +5145,11 @@ static int pci_bus_reset(struct pci_bus *bus, int probe)
 
 	might_sleep();
 
-	pci_reset_bridge_secondary_bus(bus->self);
+	ret = pci_bridge_secondary_bus_reset(bus->self);
 
 	pci_bus_unlock(bus);
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -5190,15 +5165,12 @@ int pci_probe_reset_bus(struct pci_bus *bus)
 EXPORT_SYMBOL_GPL(pci_probe_reset_bus);
 
 /**
- * pci_reset_bus - reset a PCI bus
+ * __pci_reset_bus - Try to reset a PCI bus
  * @bus: top level PCI bus to reset
  *
- * Do a bus reset on the given bus and any subordinate buses, saving
- * and restoring state of all devices.
- *
- * Return 0 on success, non-zero on error.
+ * Same as above except return -EAGAIN if the bus cannot be locked
  */
-int pci_reset_bus(struct pci_bus *bus)
+static int __pci_reset_bus(struct pci_bus *bus)
 {
 	int rc;
 
@@ -5208,42 +5180,30 @@ int pci_reset_bus(struct pci_bus *bus)
 
 	pci_bus_save_and_disable(bus);
 
-	rc = pci_bus_reset(bus, 0);
+	if (pci_bus_trylock(bus)) {
+		might_sleep();
+		rc = pci_bridge_secondary_bus_reset(bus->self);
+		pci_bus_unlock(bus);
+	} else
+		rc = -EAGAIN;
 
 	pci_bus_restore(bus);
 
 	return rc;
 }
-EXPORT_SYMBOL_GPL(pci_reset_bus);
 
 /**
- * pci_try_reset_bus - Try to reset a PCI bus
- * @bus: top level PCI bus to reset
+ * pci_reset_bus - Try to reset a PCI bus
+ * @pdev: top level PCI device to reset via slot/bus
  *
  * Same as above except return -EAGAIN if the bus cannot be locked
  */
-int pci_try_reset_bus(struct pci_bus *bus)
+int pci_reset_bus(struct pci_dev *pdev)
 {
-	int rc;
-
-	rc = pci_bus_reset(bus, 1);
-	if (rc)
-		return rc;
-
-	pci_bus_save_and_disable(bus);
-
-	if (pci_bus_trylock(bus)) {
-		might_sleep();
-		pci_reset_bridge_secondary_bus(bus->self);
-		pci_bus_unlock(bus);
-	} else
-		rc = -EAGAIN;
-
-	pci_bus_restore(bus);
-
-	return rc;
+	return pci_probe_reset_slot(pdev->slot) ?
+	    __pci_reset_slot(pdev->slot) : __pci_reset_bus(pdev->bus);
 }
-EXPORT_SYMBOL_GPL(pci_try_reset_bus);
+EXPORT_SYMBOL_GPL(pci_reset_bus);
 
 /**
  * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 61960411bd3b..6e0d1528d471 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -34,6 +34,7 @@ int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vmai,
 		  enum pci_mmap_api mmap_api);
 
 int pci_probe_reset_function(struct pci_dev *dev);
+int pci_bridge_secondary_bus_reset(struct pci_dev *dev);
 
 /**
  * struct pci_platform_pm_ops - Firmware PM callbacks
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 4e823ae051a7..83180edd6ed4 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1517,6 +1517,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 {
 	u32 reg32;
 	int pos;
+	int rc;
 
 	pos = dev->aer_cap;
 
@@ -1525,7 +1526,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
 	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
 
-	pci_reset_bridge_secondary_bus(dev);
+	rc = pci_bridge_secondary_bus_reset(dev);
 	pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n");
 
 	/* Clear Root Error Status */
@@ -1537,7 +1538,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
 	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
 
-	return PCI_ERS_RESULT_RECOVERED;
+	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
 
 /**
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 674984a9277a..708fd3a0d646 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -175,9 +175,11 @@ out:
  */
 static pci_ers_result_t default_reset_link(struct pci_dev *dev)
 {
-	pci_reset_bridge_secondary_bus(dev);
+	int rc;
+
+	rc = pci_bridge_secondary_bus_reset(dev);
 	pci_printk(KERN_DEBUG, dev, "downstream link has been reset\n");
-	return PCI_ERS_RESULT_RECOVERED;
+	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
 
 static pci_ers_result_t reset_link(struct pci_dev *dev, u32 service)
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 8fa78f0ae4d9..ec784009a36b 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2070,6 +2070,29 @@ 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;
@@ -2079,6 +2102,7 @@ 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);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 6b635022f2fe..b2e6c02385e5 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -25,6 +25,7 @@
 #include <linux/sched.h>
 #include <linux/ktime.h>
 #include <linux/mm.h>
+#include <linux/nvme.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/pm_runtime.h>
 #include <linux/switchtec.h>
@@ -3667,6 +3668,108 @@ static int reset_chelsio_generic_dev(struct pci_dev *dev, int probe)
 #define PCI_DEVICE_ID_INTEL_IVB_M_VGA      0x0156
 #define PCI_DEVICE_ID_INTEL_IVB_M2_VGA     0x0166
 
+/*
+ * The Samsung SM961/PM961 controller can sometimes enter a fatal state after
+ * FLR where config space reads from the device return -1.  We seem to be
+ * able to avoid this condition if we disable the NVMe controller prior to
+ * FLR.  This quirk is generic for any NVMe class device requiring similar
+ * assistance to quiesce the device prior to FLR.
+ *
+ * NVMe specification: https://nvmexpress.org/resources/specifications/
+ * Revision 1.0e:
+ *    Chapter 2: Required and optional PCI config registers
+ *    Chapter 3: NVMe control registers
+ *    Chapter 7.3: Reset behavior
+ */
+static int nvme_disable_and_flr(struct pci_dev *dev, int probe)
+{
+	void __iomem *bar;
+	u16 cmd;
+	u32 cfg;
+
+	if (dev->class != PCI_CLASS_STORAGE_EXPRESS ||
+	    !pcie_has_flr(dev) || !pci_resource_start(dev, 0))
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	bar = pci_iomap(dev, 0, NVME_REG_CC + sizeof(cfg));
+	if (!bar)
+		return -ENOTTY;
+
+	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	pci_write_config_word(dev, PCI_COMMAND, cmd | PCI_COMMAND_MEMORY);
+
+	cfg = readl(bar + NVME_REG_CC);
+
+	/* Disable controller if enabled */
+	if (cfg & NVME_CC_ENABLE) {
+		u32 cap = readl(bar + NVME_REG_CAP);
+		unsigned long timeout;
+
+		/*
+		 * Per nvme_disable_ctrl() skip shutdown notification as it
+		 * could complete commands to the admin queue.  We only intend
+		 * to quiesce the device before reset.
+		 */
+		cfg &= ~(NVME_CC_SHN_MASK | NVME_CC_ENABLE);
+
+		writel(cfg, bar + NVME_REG_CC);
+
+		/*
+		 * Some controllers require an additional delay here, see
+		 * NVME_QUIRK_DELAY_BEFORE_CHK_RDY.  None of those are yet
+		 * supported by this quirk.
+		 */
+
+		/* Cap register provides max timeout in 500ms increments */
+		timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
+
+		for (;;) {
+			u32 status = readl(bar + NVME_REG_CSTS);
+
+			/* Ready status becomes zero on disable complete */
+			if (!(status & NVME_CSTS_RDY))
+				break;
+
+			msleep(100);
+
+			if (time_after(jiffies, timeout)) {
+				pci_warn(dev, "Timeout waiting for NVMe ready status to clear after disable\n");
+				break;
+			}
+		}
+	}
+
+	pci_iounmap(dev, bar);
+
+	pcie_flr(dev);
+
+	return 0;
+}
+
+/*
+ * Intel DC P3700 NVMe controller will timeout waiting for ready status
+ * to change after NVMe enable if the driver starts interacting with the
+ * device too soon after FLR.  A 250ms delay after FLR has heuristically
+ * proven to produce reliably working results for device assignment cases.
+ */
+static int delay_250ms_after_flr(struct pci_dev *dev, int probe)
+{
+	if (!pcie_has_flr(dev))
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	pcie_flr(dev);
+
+	msleep(250);
+
+	return 0;
+}
+
 static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF,
 		 reset_intel_82599_sfp_virtfn },
@@ -3674,6 +3777,8 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 		reset_ivb_igd },
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_M2_VGA,
 		reset_ivb_igd },
+	{ PCI_VENDOR_ID_SAMSUNG, 0xa804, nvme_disable_and_flr },
+	{ PCI_VENDOR_ID_INTEL, 0x0953, delay_250ms_after_flr },
 	{ PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID,
 		reset_chelsio_generic_dev },
 	{ 0 }
@@ -3743,6 +3848,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x917a,
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c78 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9182,
 			 quirk_dma_func1_alias);
+/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c134 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9183,
+			 quirk_dma_func1_alias);
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c46 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0,
 			 quirk_dma_func1_alias);
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index b423a309a6e0..345c0dc8a6dc 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1010,8 +1010,7 @@ reset_info_exit:
 						    &info, slot);
 		if (!ret)
 			/* User has access, do the reset */
-			ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
-				     pci_try_reset_bus(vdev->pdev->bus);
+			ret = pci_reset_bus(vdev->pdev);
 
 hot_reset_release:
 		for (i--; i >= 0; i--)
@@ -1373,8 +1372,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
 	}
 
 	if (needs_reset)
-		ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
-			     pci_try_reset_bus(vdev->pdev->bus);
+		ret = pci_reset_bus(vdev->pdev);
 
 put_devs:
 	for (i = 0; i < devs.cur_index; i++) {