mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-01 08:26:39 +07:00
c6b4832432
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 17 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. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
183 lines
4.7 KiB
C
183 lines
4.7 KiB
C
/* Various workarounds for chipset bugs.
|
|
This code runs very early and can't use the regular PCI subsystem
|
|
The entries are keyed to PCI bridges which usually identify chipsets
|
|
uniquely.
|
|
This is only for whole classes of chipsets with specific problems which
|
|
need early invasive action (e.g. before the timers are initialized).
|
|
Most PCI device specific workarounds can be done later and should be
|
|
in standard PCI quirks
|
|
Mainboard specific bugs should be handled by DMI entries.
|
|
CPU specific bugs in setup.c */
|
|
|
|
#include <linux/pci.h>
|
|
#include <linux/acpi.h>
|
|
#include <linux/pci_ids.h>
|
|
#include <asm/pci-direct.h>
|
|
#include <asm/dma.h>
|
|
#include <asm/io_apic.h>
|
|
#include <asm/apic.h>
|
|
|
|
#ifdef CONFIG_GART_IOMMU
|
|
#include <asm/gart.h>
|
|
#endif
|
|
|
|
static void __init fix_hypertransport_config(int num, int slot, int func)
|
|
{
|
|
u32 htcfg;
|
|
/*
|
|
* we found a hypertransport bus
|
|
* make sure that we 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)
|
|
{
|
|
#ifdef CONFIG_GART_IOMMU
|
|
if ((end_pfn > MAX_DMA32_PFN || force_iommu) &&
|
|
!gart_iommu_aperture_allowed) {
|
|
printk(KERN_INFO
|
|
"Looks like a VIA chipset. Disabling IOMMU."
|
|
" Override with iommu=allowed\n");
|
|
gart_iommu_aperture_disabled = 1;
|
|
}
|
|
#endif
|
|
}
|
|
|
|
#ifdef CONFIG_ACPI
|
|
#ifdef CONFIG_X86_IO_APIC
|
|
|
|
static int __init nvidia_hpet_check(struct acpi_table_header *header)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_X86_IO_APIC */
|
|
#endif /* CONFIG_ACPI */
|
|
|
|
static void __init nvidia_bugs(int num, int slot, int func)
|
|
{
|
|
#ifdef CONFIG_ACPI
|
|
#ifdef CONFIG_X86_IO_APIC
|
|
/*
|
|
* All timer overrides on Nvidia are
|
|
* wrong unless HPET is enabled.
|
|
* Unfortunately that's not true on many Asus boards.
|
|
* We don't know yet how to detect this automatically, but
|
|
* at least allow a command line override.
|
|
*/
|
|
if (acpi_use_timer_override)
|
|
return;
|
|
|
|
if (acpi_table_parse(ACPI_SIG_HPET, nvidia_hpet_check)) {
|
|
acpi_skip_timer_override = 1;
|
|
printk(KERN_INFO "Nvidia board "
|
|
"detected. Ignoring ACPI "
|
|
"timer override.\n");
|
|
printk(KERN_INFO "If you got timer trouble "
|
|
"try acpi_use_timer_override\n");
|
|
}
|
|
#endif
|
|
#endif
|
|
/* RED-PEN skip them on mptables too? */
|
|
|
|
}
|
|
|
|
static void __init ati_bugs(int num, int slot, int func)
|
|
{
|
|
#ifdef CONFIG_X86_IO_APIC
|
|
if (timer_over_8254 == 1) {
|
|
timer_over_8254 = 0;
|
|
printk(KERN_INFO
|
|
"ATI board detected. Disabling timer routing over 8254.\n");
|
|
}
|
|
#endif
|
|
}
|
|
|
|
#define QFLAG_APPLY_ONCE 0x1
|
|
#define QFLAG_APPLIED 0x2
|
|
#define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED)
|
|
struct chipset {
|
|
u32 vendor;
|
|
u32 device;
|
|
u32 class;
|
|
u32 class_mask;
|
|
u32 flags;
|
|
void (*f)(int num, int slot, int func);
|
|
};
|
|
|
|
static struct chipset early_qrk[] __initdata = {
|
|
{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
|
|
PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
|
|
{ PCI_VENDOR_ID_VIA, PCI_ANY_ID,
|
|
PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, via_bugs },
|
|
{ PCI_VENDOR_ID_ATI, PCI_ANY_ID,
|
|
PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, ati_bugs },
|
|
{ PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
|
|
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, fix_hypertransport_config },
|
|
{}
|
|
};
|
|
|
|
void __init early_quirks(void)
|
|
{
|
|
int num, slot, func;
|
|
|
|
if (!early_pci_allowed())
|
|
return;
|
|
|
|
/* Poor man's PCI discovery */
|
|
for (num = 0; num < 32; num++) {
|
|
for (slot = 0; slot < 32; slot++) {
|
|
for (func = 0; func < 8; func++) {
|
|
u16 class;
|
|
u16 vendor;
|
|
u16 device;
|
|
u8 type;
|
|
int i;
|
|
|
|
class = read_pci_config_16(num,slot,func,
|
|
PCI_CLASS_REVISION);
|
|
if (class == 0xffff)
|
|
break;
|
|
|
|
vendor = read_pci_config_16(num, slot, func,
|
|
PCI_VENDOR_ID);
|
|
|
|
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))) {
|
|
if ((early_qrk[i].flags & QFLAG_DONE) != QFLAG_DONE)
|
|
early_qrk[i].f(num, slot, func);
|
|
early_qrk[i].flags |= QFLAG_APPLIED;
|
|
|
|
}
|
|
}
|
|
|
|
type = read_pci_config_byte(num, slot, func,
|
|
PCI_HEADER_TYPE);
|
|
if (!(type & 0x80))
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
}
|