linux-kernel - [PATCH 4.14 52/88] PCI: Work around Huawei Intelligent NIC VF FLR erratum

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 28 Jun 2021 10:35:52 -0400
From:   Sasha Levin <sashal@...nel.org>
To:     linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc:     Chiqijun <chiqijun@...wei.com>,
        Bjorn Helgaas <bhelgaas@...gle.com>,
        Alex Williamson <alex.williamson@...hat.com>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>
Subject: [PATCH 4.14 52/88] PCI: Work around Huawei Intelligent NIC VF FLR erratum

From: Chiqijun <chiqijun@...wei.com>

commit ce00322c2365e1f7b0312f2f493539c833465d97 upstream.

pcie_flr() starts a Function Level Reset (FLR), waits 100ms (the maximum
time allowed for FLR completion by PCIe r5.0, sec 6.6.2), and waits for the
FLR to complete.  It assumes the FLR is complete when a config read returns
valid data.

When we do an FLR on several Huawei Intelligent NIC VFs at the same time,
firmware on the NIC processes them serially.  The VF may respond to config
reads before the firmware has completed its reset processing.  If we bind a
driver to the VF (e.g., by assigning the VF to a virtual machine) in the
interval between the successful config read and completion of the firmware
reset processing, the NIC VF driver may fail to load.

Prevent this driver failure by waiting for the NIC firmware to complete its
reset processing.  Not all NIC firmware supports this feature.

[bhelgaas: commit log]
Link: https://support.huawei.com/enterprise/en/doc/EDOC1100063073/87950645/vm-oss-occasionally-fail-to-load-the-in200-driver-when-the-vf-performs-flr
Link: https://lore.kernel.org/r/20210414132301.1793-1-chiqijun@huawei.com
Signed-off-by: Chiqijun <chiqijun@...wei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@...gle.com>
Reviewed-by: Alex Williamson <alex.williamson@...hat.com>
Cc: stable@...r.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
 drivers/pci/quirks.c | 65 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 3602e967e96a..db1ec8209b56 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3875,6 +3875,69 @@ 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
 
+#define PCI_DEVICE_ID_HINIC_VF      0x375E
+#define HINIC_VF_FLR_TYPE           0x1000
+#define HINIC_VF_FLR_CAP_BIT        (1UL << 30)
+#define HINIC_VF_OP                 0xE80
+#define HINIC_VF_FLR_PROC_BIT       (1UL << 18)
+#define HINIC_OPERATION_TIMEOUT     15000	/* 15 seconds */
+
+/* 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;
+	u32 val;
+
+	if (probe)
+		return 0;
+
+	bar = pci_iomap(pdev, 0, 0);
+	if (!bar)
+		return -ENOTTY;
+
+	/* Get and check firmware capabilities */
+	val = ioread32be(bar + HINIC_VF_FLR_TYPE);
+	if (!(val & HINIC_VF_FLR_CAP_BIT)) {
+		pci_iounmap(pdev, bar);
+		return -ENOTTY;
+	}
+
+	/* Set HINIC_VF_FLR_PROC_BIT for the start of FLR */
+	val = ioread32be(bar + HINIC_VF_OP);
+	val = val | HINIC_VF_FLR_PROC_BIT;
+	iowrite32be(val, bar + HINIC_VF_OP);
+
+	pcie_flr(pdev);
+
+	/*
+	 * The device must recapture its Bus and Device Numbers after FLR
+	 * in order generate Completions.  Issue a config write to let the
+	 * device capture this information.
+	 */
+	pci_write_config_word(pdev, PCI_VENDOR_ID, 0);
+
+	/* Firmware clears HINIC_VF_FLR_PROC_BIT when reset is complete */
+	timeout = jiffies + msecs_to_jiffies(HINIC_OPERATION_TIMEOUT);
+	do {
+		val = ioread32be(bar + HINIC_VF_OP);
+		if (!(val & HINIC_VF_FLR_PROC_BIT))
+			goto reset_complete;
+		msleep(20);
+	} while (time_before(jiffies, timeout));
+
+	val = ioread32be(bar + HINIC_VF_OP);
+	if (!(val & HINIC_VF_FLR_PROC_BIT))
+		goto reset_complete;
+
+	pci_warn(pdev, "Reset dev timeout, FLR ack reg: %#010x\n", 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 },
@@ -3884,6 +3947,8 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 		reset_ivb_igd },
 	{ 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 }
 };
 
-- 
2.30.2