[v3] PCI: Add pci reset quirk for Huawei Intelligent NIC virtual function

From: Chiqijun
Date: Fri Dec 25 2020 - 04:24:16 EST


When multiple VFs do FLR at the same time, the firmware is
processed serially, resulting in some VF FLRs being delayed more
than 100ms, when the virtual machine restarts and the device
driver is loaded, the firmware is doing the corresponding VF
FLR, causing the driver to fail to load.

To solve this problem, add host and firmware status synchronization
during FLR.

Signed-off-by: Chiqijun <chiqijun@xxxxxxxxxx>
---
v3:
- The MSE bit in the VF configuration space is hardwired to zero,
remove the setting of PCI_COMMAND_MEMORY bit. Add comment for
set PCI_COMMAND register.

v2:
- Update comments
- Use the HINIC_VF_FLR_CAP_BIT_SHIFT and HINIC_VF_FLR_PROC_BIT_SHIFT
macro instead of the magic number
---
drivers/pci/quirks.c | 77 ++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 77 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f70692ac79c5..9c310012ef19 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3912,6 +3912,81 @@ static int delay_250ms_after_flr(struct pci_dev *dev, int probe)
return 0;
}

+#define PCI_DEVICE_ID_HINIC_VF 0x375E
+#define HINIC_VF_FLR_TYPE 0x1000
+#define HINIC_VF_FLR_CAP_BIT_SHIFT 6
+#define HINIC_VF_OP 0xE80
+#define HINIC_VF_FLR_PROC_BIT_SHIFT 10
+#define HINIC_OPERATION_TIMEOUT 15000
+
+/* Device-specific reset method for Huawei Intelligent NIC virtual functions */
+static int reset_hinic_vf_dev(struct pci_dev *pdev, int probe)
+{
+ unsigned long timeout;
+ void __iomem *bar;
+ u16 command;
+ u32 val;
+
+ if (probe)
+ return 0;
+
+ bar = pci_iomap(pdev, 0, 0);
+ if (!bar)
+ return -ENOTTY;
+
+ /*
+ * FLR cap bit bit30, FLR processing bit: bit18, to avoid big-endian
+ * conversion the big-endian bit6, bit10 is directly operated here.
+ *
+ * Get and check firmware capabilities.
+ */
+ val = readl(bar + HINIC_VF_FLR_TYPE);
+ if (!(val & (1UL << HINIC_VF_FLR_CAP_BIT_SHIFT))) {
+ pci_iounmap(pdev, bar);
+ return -ENOTTY;
+ }
+
+ /*
+ * Set the processing bit for the start of FLR, which will be cleared
+ * by the firmware after FLR is completed.
+ */
+ val = readl(bar + HINIC_VF_OP);
+ val = val | (1UL << HINIC_VF_FLR_PROC_BIT_SHIFT);
+ writel(val, bar + HINIC_VF_OP);
+
+ /* Perform the actual device function reset */
+ pcie_flr(pdev);
+
+ /*
+ * The device must learn BDF after FLR in order to respond to BAR's
+ * read request, therefore, we issue a configure write request to let
+ * the device capture BDF.
+ */
+ pci_read_config_word(pdev, PCI_COMMAND, &command);
+ pci_write_config_word(pdev, PCI_COMMAND, command);
+
+ /* Waiting for device reset complete */
+ timeout = jiffies + msecs_to_jiffies(HINIC_OPERATION_TIMEOUT);
+ do {
+ val = readl(bar + HINIC_VF_OP);
+ if (!(val & (1UL << HINIC_VF_FLR_PROC_BIT_SHIFT)))
+ goto reset_complete;
+ msleep(20);
+ } while (time_before(jiffies, timeout));
+
+ val = readl(bar + HINIC_VF_OP);
+ if (!(val & (1UL << HINIC_VF_FLR_PROC_BIT_SHIFT)))
+ goto reset_complete;
+
+ pci_warn(pdev, "Reset dev timeout, flr ack reg: %x\n",
+ be32_to_cpu(val));
+
+reset_complete:
+ pci_iounmap(pdev, bar);
+
+ 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 },
@@ -3923,6 +3998,8 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
{ PCI_VENDOR_ID_INTEL, 0x0953, delay_250ms_after_flr },
{ PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID,
reset_chelsio_generic_dev },
+ { PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HINIC_VF,
+ reset_hinic_vf_dev },
{ 0 }
};

--
2.17.1