[PATCH] kexec: force x86_64 arches to boot kdump kernels on boot cpu

Neil Horman nhorman at tuxdriver.com
Tue Dec 11 14:24:34 EST 2007


On Tue, Dec 11, 2007 at 11:46:34AM -0700, Eric W. Biederman wrote:
> Neil Horman <nhorman at tuxdriver.com> writes:
> 
> Ok. My only remaining nit to pick is that fix_hypertransport_config
> is right in the middle of the nvidia quirks, which can be a bit
> confusing when reading through the code.  Otherwise I think this
> is a version that we can merge.
> 
Sure, I'll move it to the top of the file

> Let's get a clean description on this thing and send it to the
> current x86 maintainers. Thomas, Ingo, and HPA
> 

Clean Summary:

Recently a kdump bug was discovered in which a system would hang inside 
calibrate_delay during the booting of the kdump kernel.  This was caused by the 
fact that the jiffies counter was not being incremented during timer 
calibration.  The root cause of this problem was found to be a bios 
misconfiguration of the hypertransport bus.  On system affected by this hang, 
the bios had assigned APIC ids which used extended apic bits (more than the 
nominal 4 bit ids's), but failed to configure bit 18 of the hypertransport 
transaction config register, which indicated that the mask for the destination 
field of interrupt packets accross the ht bus (see section 3.3.9 of 
http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/26094.PDF).  
If a crash occurs on a cpu with an APIC id that extends beyond 4 bits, it will 
not recieve interrupts during the kdump kernel boot, and this hang will be the 
result.  The fix is to add this patch, whcih add an early pci quirk check, to 
forcibly enable this bit in the httcfg register.  This enables all cpus on a 
system to receive interrupts, and allows kdump kernel bootup to procede 
normally.  

> 
> > Thanks & Regards
> > Neil
> >
> > Signed-off-by: Neil Horman <nhorman at tuxdriver.com>
> Acked-by: "Eric W. Biederman" <ebiederm at xmission.com>
> 

Signed-off-by: Neil Horman <nhorman at tuxdriver.com>


 early-quirks.c |   90 +++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 69 insertions(+), 21 deletions(-)



diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 88bb83e..c0d0c69 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -21,8 +21,36 @@
 #include <asm/gart.h>
 #endif
 
-static void __init via_bugs(void)
+static void __init fix_hypertransport_config(int num, int slot, int func)
 {
+	u32 htcfg;
+	/*
+	 *we found a hypertransport bus
+	 *make sure that are broadcasting
+	 *interrupts to all cpus on the ht bus
+	 *if we're using extended apic ids
+	 */
+	htcfg = read_pci_config(num, slot, func, 0x68);
+	if (htcfg & (1 << 18)) {	
+		printk(KERN_INFO "Detected use of extended apic ids on hypertransport bus\n");
+		if ((htcfg & (1 << 17)) == 0) {
+			printk(KERN_INFO "Enabling hypertransport extended apic interrupt broadcast\n");
+			printk(KERN_INFO "Note this is a bios bug, please contact your hw vendor\n");
+			htcfg |= (1 << 17);
+			write_pci_config(num, slot, func, 0x68, htcfg);
+		}
+	}
+
+	
+}
+
+static void __init via_bugs(int  num, int slot, int func)
+{
+	static int fix_applied = 0;
+
+	if (fix_applied++)
+		return;
+
 #ifdef CONFIG_GART_IOMMU
 	if ((end_pfn > MAX_DMA32_PFN ||  force_iommu) &&
 	    !gart_iommu_aperture_allowed) {
@@ -44,8 +72,13 @@ static int __init nvidia_hpet_check(struct acpi_table_header *header)
 #endif /* CONFIG_X86_IO_APIC */
 #endif /* CONFIG_ACPI */
 
-static void __init nvidia_bugs(void)
+static void __init nvidia_bugs(int num, int slot, int func)
 {
+	static int fix_applied = 0;
+
+	if (fix_applied++)
+		return;
+
 #ifdef CONFIG_ACPI
 #ifdef CONFIG_X86_IO_APIC
 	/*
@@ -72,8 +105,13 @@ static void __init nvidia_bugs(void)
 
 }
 
-static void __init ati_bugs(void)
+static void __init ati_bugs(int num, int slot, int func)
 {
+	static int fix_applied = 0;
+
+	if (fix_applied++)
+		return;
+
 #ifdef CONFIG_X86_IO_APIC
 	if (timer_over_8254 == 1) {
 		timer_over_8254 = 0;
@@ -84,14 +122,18 @@ static void __init ati_bugs(void)
 }
 
 struct chipset {
-	u16 vendor;
-	void (*f)(void);
+	u32 vendor;
+	u32 device;
+	u32 class;
+	u32 class_mask;
+	void (*f)(int num, int slot, int func);
 };
 
 static struct chipset early_qrk[] __initdata = {
-	{ PCI_VENDOR_ID_NVIDIA, nvidia_bugs },
-	{ PCI_VENDOR_ID_VIA, via_bugs },
-	{ PCI_VENDOR_ID_ATI, ati_bugs },
+	{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, nvidia_bugs },
+	{ PCI_VENDOR_ID_VIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, via_bugs },
+	{ PCI_VENDOR_ID_ATI, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, ati_bugs },
+	{ PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, fix_hypertransport_config },
 	{}
 };
 
@@ -106,27 +148,33 @@ void __init early_quirks(void)
 	for (num = 0; num < 32; num++) {
 		for (slot = 0; slot < 32; slot++) {
 			for (func = 0; func < 8; func++) {
-				u32 class;
-				u32 vendor;
+				u16 class;
+				u16 vendor;
+				u16 device;
 				u8 type;
 				int i;
-				class = read_pci_config(num,slot,func,
+
+				class = read_pci_config_16(num,slot,func,
 							PCI_CLASS_REVISION);
-				if (class == 0xffffffff)
+				if (class == 0xffff)
 					break;
 
-				if ((class >> 16) != PCI_CLASS_BRIDGE_PCI)
-					continue;
-
-				vendor = read_pci_config(num, slot, func,
+				vendor = read_pci_config_16(num, slot, func,
 							 PCI_VENDOR_ID);
-				vendor &= 0xffff;
 
-				for (i = 0; early_qrk[i].f; i++)
-					if (early_qrk[i].vendor == vendor) {
-						early_qrk[i].f();
-						return;
+				device = read_pci_config_16(num, slot, func,
+							PCI_DEVICE_ID);
+
+				for(i=0;early_qrk[i].f != NULL;i++) {
+					if (((early_qrk[i].vendor == PCI_ANY_ID) ||
+					    (early_qrk[i].vendor == vendor)) &&
+					   ((early_qrk[i].device == PCI_ANY_ID) ||
+					    (early_qrk[i].device == device)) &&
+					   (!((early_qrk[i].class ^ class) & 
+					     early_qrk[i].class_mask))) {
+						early_qrk[i].f(num, slot, func);
 					}
+				}
 
 				type = read_pci_config_byte(num, slot, func,
 							    PCI_HEADER_TYPE);



More information about the kexec mailing list