[PATCH] Disable SW irqbalance/irqaffinity for E7520/E7320/E7525 v2

As part of the workaround for the "Interrupt message re-ordering across hub
interface" errata (page #16 in
http://developer.intel.com/design/chipsets/specupdt/30288402.pdf), BIOS may
enable hardware IRQ balancing for E7520/E7320/E7525(revision ID 0x9 and
below) based platforms.

Add pci quirks to disable SW irqbalance/affinity on those platforms.  Move
balanced_irq_init() to late_initcall so that kirqd will be started after
pci quirks.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/kernel/io_apic.c

@@ -636,7 +636,7 @@ static int __init balanced_irq_init(void)
 	return 0;
 }
 
-static int __init irqbalance_disable(char *str)
+int __init irqbalance_disable(char *str)
 {
 	irqbalance_disabled = 1;
 	return 0;
@@ -653,7 +653,7 @@ static inline void move_irq(int irq)
 	}
 }
 
-__initcall(balanced_irq_init);
+late_initcall(balanced_irq_init);
 
 #else /* !CONFIG_IRQBALANCE */
 static inline void move_irq(int irq) { }

drivers/pci/quirks.c

@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/delay.h>
+#include <linux/irq.h>
 
 #undef DEBUG
 
@@ -978,11 +979,58 @@ static void __init quirk_intel_ide_combined(struct pci_dev *pdev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,    PCI_ANY_ID,	  quirk_intel_ide_combined );
 #endif /* CONFIG_SCSI_SATA */
 
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP)
+
+void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
+{
+	u8 config, rev;
+	u32 word;
+	extern struct pci_raw_ops *raw_pci_ops;
+
+	/* BIOS may enable hardware IRQ balancing for
+	 * E7520/E7320/E7525(revision ID 0x9 and below)
+	 * based platforms.
+	 * Disable SW irqbalance/affinity on those platforms.
+	 */
+	pci_read_config_byte(dev, PCI_CLASS_REVISION, &rev);
+	if (rev > 0x9)
+		return;
+
+	printk(KERN_INFO "Intel E7520/7320/7525 detected.");
+
+	/* enable access to config space*/
+	pci_read_config_byte(dev, 0xf4, &config);
+	config |= 0x2;
+	pci_write_config_byte(dev, 0xf4, config);
+
+	/* read xTPR register */
+	raw_pci_ops->read(0, 0, 0x40, 0x4c, 2, &word);
+
+	if (!(word & (1 << 13))) {
+		printk(KERN_INFO "Disabling irq balancing and affinity\n");
+#ifdef CONFIG_IRQBALANCE
+		irqbalance_disable("");
+#endif
+		noirqdebug_setup("");
+		no_irq_affinity = 1;
+	}
+
+	config &= ~0x2;
+	/* disable access to config space*/
+	pci_write_config_byte(dev, 0xf4, config);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7320_MCH,	quirk_intel_irqbalance);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7525_MCH,	quirk_intel_irqbalance);
+#endif
+
 int pciehp_msi_quirk;
 
 static void __devinit quirk_pciehp_msi(struct pci_dev *pdev)
 {
 	pciehp_msi_quirk = 1;
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP)
+	quirk_intel_irqbalance(pdev);
+#endif
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_SMCH,	quirk_pciehp_msi );
 

include/asm-i386/irq.h

@@ -34,4 +34,8 @@ extern void release_vm86_irqs(struct task_struct *);
 # define irq_ctx_init(cpu) do { } while (0)
 #endif
 
+#ifdef CONFIG_IRQBALANCE
+extern int irqbalance_disable(char *str);
+#endif
+
 #endif /* _ASM_IRQ_H */

include/linux/irq.h

@@ -76,6 +76,8 @@ extern int setup_irq(unsigned int irq, struct irqaction * new);
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 extern cpumask_t irq_affinity[NR_IRQS];
+extern int no_irq_affinity;
+extern int noirqdebug_setup(char *str);
 
 extern asmlinkage int handle_IRQ_event(unsigned int irq, struct pt_regs *regs,
 				       struct irqaction *action);

include/linux/pci_ids.h

@@ -2205,6 +2205,8 @@
 #define PCI_DEVICE_ID_INTEL_82855GM_HB	0x3580
 #define PCI_DEVICE_ID_INTEL_82855GM_IG	0x3582
 #define PCI_DEVICE_ID_INTEL_SMCH	0x3590
+#define PCI_DEVICE_ID_INTEL_E7320_MCH	0x3592
+#define PCI_DEVICE_ID_INTEL_E7525_MCH	0x359e
 #define PCI_DEVICE_ID_INTEL_80310	0x530d
 #define PCI_DEVICE_ID_INTEL_82371SB_0	0x7000
 #define PCI_DEVICE_ID_INTEL_82371SB_1	0x7010

kernel/irq/proc.c

@@ -32,13 +32,14 @@ static int irq_affinity_read_proc(char *page, char **start, off_t off,
 	return len;
 }
 
+int no_irq_affinity;
 static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
 				   unsigned long count, void *data)
 {
 	unsigned int irq = (int)(long)data, full_count = count, err;
 	cpumask_t new_value, tmp;
 
-	if (!irq_desc[irq].handler->set_affinity)
+	if (!irq_desc[irq].handler->set_affinity || no_irq_affinity)
 		return -EIO;
 
 	err = cpumask_parse(buffer, count, new_value);

kernel/irq/spurious.c

@@ -85,7 +85,7 @@ void note_interrupt(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret)
 
 int noirqdebug;
 
-static int __init noirqdebug_setup(char *str)
+int __init noirqdebug_setup(char *str)
 {
 	noirqdebug = 1;
 	printk(KERN_INFO "IRQ lockup detection disabled\n");