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

1 files changed, 108 insertions, 0 deletions

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);