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

[Neil Horman]

On Fri, Dec 07, 2007 at 09:21:44AM -0500, Neil Horman wrote:
> On Fri, Dec 07, 2007 at 01:22:04AM -0800, Yinghai Lu wrote:
> > On Dec 7, 2007 12:50 AM, Yinghai Lu <yhlu.kernel at gmail.com> wrote:
> > >
> > > On Dec 6, 2007 4:33 PM, Eric W. Biederman <ebiederm at xmission.com> wrote:
> > ...
> > > >
> > > > My feel is that if it is for legacy interrupts only it should not be a problem.
> > > > Let's investigate and see if we can unconditionally enable this quirk
> > > > for all opteron systems.
> > >
> > > i checked that bit
> > >
> > > http://www.openbios.org/viewvc/trunk/LinuxBIOSv2/src/northbridge/amd/amdk8/coherent_ht.c?revision=2596&view=markup
<snip>
> > 
> > it should be bit 18 (HTTC_APIC_EXT_ID)
> > 
> > 
> > YH
> 
> this seems reasonable, I can reroll the patch for this.  As I think about it I'm
> also going to update the patch to make this check occur for any pci class 0600
> device from vendor AMD, since its possible that more than just nvidia chipsets
> can be affected.
> 
> I'll repost as soon as I've tested, thanks!
> Neil


Ok, New patch attached.  It preforms the same function as previously described,
but is more restricted in its application.  As Yinghai pointed out, the
broadcast mask bit (bit 17 in the htcfg register) should only be enabled, if the
extened apic id bit (bit 18 in the same register) is also set.  So this patch
now check for that bit to be turned on first.  Also, this patch now adds an
independent quirk check for all AMD hypertransport host controllers, since its
possible for this misconfiguration to be present in systems other than nvidias.
The net effect of these changes is, that its now applicable to all AMD systems
containing hypertransport busses, and is only activated if extended apic ids are
in use, meaning that this quirk guarantees that all processors in a system are
elligible to receive interrupts from the ioapic, even if their apicid extends
beyond the nominal 4 bit limitation.  Tested successfully by me.

Thanks & Regards
Neil

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


 early-quirks.c |   83 ++++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 76 insertions(+), 7 deletions(-)



diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 88bb83e..d5a7b30 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -44,6 +44,50 @@ static int __init nvidia_hpet_check(struct acpi_table_header *header)
 #endif /* CONFIG_X86_IO_APIC */
 #endif /* CONFIG_ACPI */
 
+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)) == 1) {	
+		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");
+			htcfg |= (1 << 17);
+			write_pci_config(num, slot, func, 0x68, htcfg);
+		}
+	}
+	
+}
+
+static void __init check_hypertransport_config()
+{
+	int num, slot, func;
+	u32 device, vendor;
+	func = 0;
+	for (num = 0; num < 32; num++) {
+		for (slot = 0; slot < 32; slot++) {
+			vendor = read_pci_config(num,slot,func,
+						PCI_VENDOR_ID); 
+			device = read_pci_config(num,slot,func,
+						PCI_DEVICE_ID);
+			vendor &= 0x0000ffff;
+			device >>= 16;
+			if ((vendor == PCI_VENDOR_ID_AMD) &&
+			    (device == PCI_DEVICE_ID_AMD_K8_NB))
+				fix_hypertransport_config(num,slot,func);
+		}
+	}
+
+	return;
+
+}
+
 static void __init nvidia_bugs(void)
 {
 #ifdef CONFIG_ACPI
@@ -83,6 +127,12 @@ static void __init ati_bugs(void)
 #endif
 }
 
+static void __init amd_host_bugs(void)
+{
+	printk(KERN_CRIT "IN AMD_HOST_BUGS\n");
+	check_hypertransport_config();
+}
+
 struct chipset {
 	u16 vendor;
 	void (*f)(void);
@@ -95,9 +145,16 @@ static struct chipset early_qrk[] __initdata = {
 	{}
 };
 
+static struct chipset early_host_qrk[] __initdata = {
+	{ PCI_VENDOR_ID_AMD, amd_host_bugs},
+	{}
+};
+
 void __init early_quirks(void)
 {
 	int num, slot, func;
+	u8 found_bridge = 0;
+	u8 found_host = 0;
 
 	if (!early_pci_allowed())
 		return;
@@ -115,18 +172,30 @@ void __init early_quirks(void)
 				if (class == 0xffffffff)
 					break;
 
-				if ((class >> 16) != PCI_CLASS_BRIDGE_PCI)
+				class >>= 16;
+				if ((class != PCI_CLASS_BRIDGE_PCI) &&
+				    (class != PCI_CLASS_BRIDGE_HOST))
 					continue;
 
 				vendor = read_pci_config(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;
-					}
+				if ((class == PCI_CLASS_BRIDGE_PCI) && (!found_bridge)) {
+					for (i = 0; early_qrk[i].f; i++)
+						if (early_qrk[i].vendor == vendor) {
+							early_qrk[i].f();
+							found_bridge = 1;;
+						}
+				} else if (!found_host) {
+					for (i = 0; early_host_qrk[i].f; i++)
+						if (early_host_qrk[i].vendor == vendor) {
+							early_host_qrk[i].f();
+							found_host = 1;
+						}
+				}
+
+				if (found_bridge && found_host)
+					return;
 
 				type = read_pci_config_byte(num, slot, func,
 							    PCI_HEADER_TYPE);