PCI-E Link training bug

[Jeff Roberson]

Hello Folks,

At least one intel chipset will occasionally negotiate a 4x link for an 8x 
device in an 8x port.  It is a known errata in the 5400 mch.  Simply 
disabling and re-enabling the link is all that is required to restore full 
throughput.  Toggling the retrain bit in the pci-e link control register 
alone is insufficient.

I have added a small bit of code to the pcie port device which checks for 
this condition and attempts to retrain the link.  It is possible that it 
will give a false positive if the port is capable of accepting lesser 
width devices.  This should be harmless although I would not rule out poor 
implementations having issues with gratuitous retraining.

Thanks,
Jeffdiff -r d021d01742ae drivers/pci/pcie/portdrv_pci.c
--- a/drivers/pci/pcie/portdrv_pci.c	Tue Mar 09 15:13:58 2010 -0800
+++ b/drivers/pci/pcie/portdrv_pci.c	Tue Aug 03 03:25:51 2010 -0700
@@ -70,6 +70,47 @@
 #endif
 
 /*
+ * pcie_portdrv_check_link - Check for link width mismatch
+ * @dev: PCI-Express port device to conditionally retrain
+ *
+ * Verify that the negotiated link matches the links capability and
+ * attempt to retrain if it does not.  This may be a perfectly valid
+ * configuration, however, on some intel chipsets (i5400) an errata
+ * may cause the link to negotiate down erroneously.
+ */
+static inline void
+pcie_portdrv_check_link(struct pci_dev *dev)
+{
+	u32 linkcap;
+	u16 linkstat;
+	u16 linkctrl;
+	int capwidth;
+	int width;
+	int pos;
+	int i;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	for (i = 0; i < 3; i++) {
+		pci_read_config_dword(dev, pos + PCI_EXP_LNKCAP, &linkcap);
+		pci_read_config_word(dev, pos + PCI_EXP_LNKSTA, &linkstat);
+		capwidth = (linkcap >> 4) & 0x3f;
+		width = (linkstat >> 4) & 0x3f;
+		if (width == capwidth || width == 0)
+			return;
+		dev_printk(KERN_INFO, &dev->dev,
+		    "Link width mismatch: %d != %d, retraining\n",
+		    capwidth, width);
+		pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, &linkctrl);
+		pci_write_config_word(dev, pos + PCI_EXP_LNKCTL,
+		    linkctrl | PCI_EXP_LNKCTL_DIS);
+		msleep(125);
+		pci_write_config_word(dev, pos + PCI_EXP_LNKCTL,
+		    linkctrl | PCI_EXP_LNKCTL_RL);
+		msleep(125);
+	}
+}
+
+/*
  * pcie_portdrv_probe - Probe PCI-Express port devices
  * @dev: PCI-Express port device being probed
  *
@@ -99,6 +140,7 @@
 		pci_disable_device(dev);
 		return -ENOMEM;
 	}
+	pcie_portdrv_check_link(dev);
 
 	pcie_portdrv_save_config(dev);
 
diff -r d021d01742ae include/linux/pci_regs.h
--- a/include/linux/pci_regs.h	Tue Mar 09 15:13:58 2010 -0800
+++ b/include/linux/pci_regs.h	Tue Aug 03 03:25:51 2010 -0700
@@ -400,6 +400,7 @@
 #define  PCI_EXP_LNKCAP_L1EL	0x38000	/* L1 Exit Latency */
 #define  PCI_EXP_LNKCAP_CLKPM	0x40000	/* L1 Clock Power Management */
 #define PCI_EXP_LNKCTL		16	/* Link Control */
+#define  PCI_EXP_LNKCTL_DIS	0x10	/* Disable Link */
 #define  PCI_EXP_LNKCTL_RL	0x20	/* Retrain Link */
 #define  PCI_EXP_LNKCTL_CCC	0x40	/* Common Clock COnfiguration */
 #define  PCI_EXP_LNKCTL_CLKREQ_EN 0x100	/* Enable clkreq */