1
0
Fork 0
alistair23-linux/arch/powerpc/kernel/mce_power.c

659 lines
21 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Machine check exception handling CPU-side for power7 and power8
*
* Copyright 2013 IBM Corporation
* Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
*/
#undef DEBUG
#define pr_fmt(fmt) "mce_power: " fmt
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/extable.h>
#include <asm/mmu.h>
#include <asm/mce.h>
#include <asm/machdep.h>
#include <asm/pgtable.h>
#include <asm/pte-walk.h>
#include <asm/sstep.h>
#include <asm/exception-64s.h>
#include <asm/extable.h>
/*
* Convert an address related to an mm to a PFN. NOTE: we are in real
* mode, we could potentially race with page table updates.
*/
unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
{
pte_t *ptep;
unsigned int shift;
unsigned long pfn, flags;
struct mm_struct *mm;
if (user_mode(regs))
mm = current->mm;
else
mm = &init_mm;
local_irq_save(flags);
ptep = __find_linux_pte(mm->pgd, addr, NULL, &shift);
if (!ptep || pte_special(*ptep)) {
pfn = ULONG_MAX;
goto out;
}
if (shift <= PAGE_SHIFT)
pfn = pte_pfn(*ptep);
else {
unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
pfn = pte_pfn(__pte(pte_val(*ptep) | (addr & rpnmask)));
}
out:
local_irq_restore(flags);
return pfn;
}
/* flush SLBs and reload */
#ifdef CONFIG_PPC_BOOK3S_64
void flush_and_reload_slb(void)
{
/* Invalidate all SLBs */
slb_flush_all_realmode();
#ifdef CONFIG_KVM_BOOK3S_HANDLER
/*
* If machine check is hit when in guest or in transition, we will
* only flush the SLBs and continue.
*/
if (get_paca()->kvm_hstate.in_guest)
return;
#endif
if (early_radix_enabled())
return;
/*
* This probably shouldn't happen, but it may be possible it's
* called in early boot before SLB shadows are allocated.
*/
if (!get_slb_shadow())
return;
slb_restore_bolted_realmode();
}
#endif
static void flush_erat(void)
{
#ifdef CONFIG_PPC_BOOK3S_64
if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) {
flush_and_reload_slb();
return;
}
#endif
asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
}
#define MCE_FLUSH_SLB 1
#define MCE_FLUSH_TLB 2
#define MCE_FLUSH_ERAT 3
static int mce_flush(int what)
{
#ifdef CONFIG_PPC_BOOK3S_64
if (what == MCE_FLUSH_SLB) {
flush_and_reload_slb();
return 1;
}
#endif
if (what == MCE_FLUSH_ERAT) {
flush_erat();
return 1;
}
if (what == MCE_FLUSH_TLB) {
powerpc/64s: Improve local TLB flush for boot and MCE on POWER9 There are several cases outside the normal address space management where a CPU's entire local TLB is to be flushed: 1. Booting the kernel, in case something has left stale entries in the TLB (e.g., kexec). 2. Machine check, to clean corrupted TLB entries. One other place where the TLB is flushed, is waking from deep idle states. The flush is a side-effect of calling ->cpu_restore with the intention of re-setting various SPRs. The flush itself is unnecessary because in the first case, the TLB should not acquire new corrupted TLB entries as part of sleep/wake (though they may be lost). This type of TLB flush is coded inflexibly, several times for each CPU type, and they have a number of problems with ISA v3.0B: - The current radix mode of the MMU is not taken into account, it is always done as a hash flushn For IS=2 (LPID-matching flush from host) and IS=3 with HV=0 (guest kernel flush), tlbie(l) is undefined if the R field does not match the current radix mode. - ISA v3.0B hash must flush the partition and process table caches as well. - ISA v3.0B radix must flush partition and process scoped translations, partition and process table caches, and also the page walk cache. So consolidate the flushing code and implement it in C and inline asm under the mm/ directory with the rest of the flush code. Add ISA v3.0B cases for radix and hash, and use the radix flush in radix environment. Provide a way for IS=2 (LPID flush) to specify the radix mode of the partition. Have KVM pass in the radix mode of the guest. Take out the flushes from early cputable/dt_cpu_ftrs detection hooks, and move it later in the boot process after, the MMU registers are set up and before relocation is first turned on. The TLB flush is no longer called when restoring from deep idle states. This was not be done as a separate step because booting secondaries uses the same cpu_restore as idle restore, which needs the TLB flush. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-12-23 08:15:50 -07:00
tlbiel_all();
return 1;
}
return 0;
}
#define SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42))
struct mce_ierror_table {
unsigned long srr1_mask;
unsigned long srr1_value;
bool nip_valid; /* nip is a valid indicator of faulting address */
unsigned int error_type;
unsigned int error_subtype;
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
unsigned int error_class;
unsigned int initiator;
unsigned int severity;
bool sync_error;
};
static const struct mce_ierror_table mce_p7_ierror_table[] = {
{ 0x00000000001c0000, 0x0000000000040000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000001c0000, 0x0000000000080000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000001c0000, 0x00000000000c0000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000000001c0000, 0x0000000000100000, true,
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000000001c0000, 0x0000000000140000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000000001c0000, 0x0000000000180000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000001c0000, 0x00000000001c0000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0, 0, 0, 0, 0, 0, 0 } };
static const struct mce_ierror_table mce_p8_ierror_table[] = {
{ 0x00000000081c0000, 0x0000000000040000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x0000000000080000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x00000000000c0000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000000081c0000, 0x0000000000100000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000000081c0000, 0x0000000000140000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000000081c0000, 0x0000000000180000, true,
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x00000000001c0000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x0000000008000000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_IFETCH_TIMEOUT, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x0000000008040000, true,
MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0, 0, 0, 0, 0, 0, 0 } };
static const struct mce_ierror_table mce_p9_ierror_table[] = {
{ 0x00000000081c0000, 0x0000000000040000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x0000000000080000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x00000000000c0000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000000081c0000, 0x0000000000100000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000000081c0000, 0x0000000000140000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000000081c0000, 0x0000000000180000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x00000000001c0000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH_FOREIGN, MCE_ECLASS_SOFTWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x0000000008000000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_IFETCH_TIMEOUT, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x0000000008040000, true,
MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x00000000080c0000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH, MCE_ECLASS_SOFTWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x0000000008100000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_SOFTWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000000081c0000, 0x0000000008140000, false,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_RA, MCE_RA_ERROR_STORE, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_FATAL, false }, /* ASYNC is fatal */
{ 0x00000000081c0000, 0x0000000008180000, false,
MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_STORE_TIMEOUT,
MCE_INITIATOR_CPU, MCE_SEV_FATAL, false }, /* ASYNC is fatal */
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
{ 0x00000000081c0000, 0x00000000081c0000, true, MCE_ECLASS_HARDWARE,
MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0, 0, 0, 0, 0, 0, 0 } };
struct mce_derror_table {
unsigned long dsisr_value;
bool dar_valid; /* dar is a valid indicator of faulting address */
unsigned int error_type;
unsigned int error_subtype;
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
unsigned int error_class;
unsigned int initiator;
unsigned int severity;
bool sync_error;
};
static const struct mce_derror_table mce_p7_derror_table[] = {
{ 0x00008000, false,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00004000, true,
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000800, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000400, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000080, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000100, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000040, true,
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARD_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0, false, 0, 0, 0, 0, 0 } };
static const struct mce_derror_table mce_p8_derror_table[] = {
{ 0x00008000, false,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00004000, true,
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00002000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00001000, true,
MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000800, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000400, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000200, true,
MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, /* SECONDARY ERAT */
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000080, true,
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000100, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0, false, 0, 0, 0, 0, 0 } };
static const struct mce_derror_table mce_p9_derror_table[] = {
{ 0x00008000, false,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00004000, true,
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00002000, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00001000, true,
MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000800, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000400, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000200, false,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE, MCE_ECLASS_SOFTWARE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000080, true,
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_SOFT_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
{ 0x00000100, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000040, true,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000020, false,
MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000010, false,
MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0x00000008, false,
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD_STORE_FOREIGN, MCE_ECLASS_HARDWARE,
MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
{ 0, false, 0, 0, 0, 0, 0 } };
static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr,
uint64_t *phys_addr)
{
/*
* Carefully look at the NIP to determine
* the instruction to analyse. Reading the NIP
* in real-mode is tricky and can lead to recursive
* faults
*/
int instr;
unsigned long pfn, instr_addr;
struct instruction_op op;
struct pt_regs tmp = *regs;
pfn = addr_to_pfn(regs, regs->nip);
if (pfn != ULONG_MAX) {
instr_addr = (pfn << PAGE_SHIFT) + (regs->nip & ~PAGE_MASK);
instr = *(unsigned int *)(instr_addr);
if (!analyse_instr(&op, &tmp, instr)) {
pfn = addr_to_pfn(regs, op.ea);
*addr = op.ea;
*phys_addr = (pfn << PAGE_SHIFT);
return 0;
}
/*
* analyse_instr() might fail if the instruction
* is not a load/store, although this is unexpected
* for load/store errors or if we got the NIP
* wrong
*/
}
*addr = 0;
return -1;
}
static int mce_handle_ierror(struct pt_regs *regs,
const struct mce_ierror_table table[],
struct mce_error_info *mce_err, uint64_t *addr,
uint64_t *phys_addr)
{
uint64_t srr1 = regs->msr;
int handled = 0;
int i;
*addr = 0;
for (i = 0; table[i].srr1_mask; i++) {
if ((srr1 & table[i].srr1_mask) != table[i].srr1_value)
continue;
/* attempt to correct the error */
switch (table[i].error_type) {
case MCE_ERROR_TYPE_SLB:
if (local_paca->in_mce == 1)
slb_save_contents(local_paca->mce_faulty_slbs);
handled = mce_flush(MCE_FLUSH_SLB);
break;
case MCE_ERROR_TYPE_ERAT:
handled = mce_flush(MCE_FLUSH_ERAT);
break;
case MCE_ERROR_TYPE_TLB:
handled = mce_flush(MCE_FLUSH_TLB);
break;
}
/* now fill in mce_error_info */
mce_err->error_type = table[i].error_type;
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
mce_err->error_class = table[i].error_class;
switch (table[i].error_type) {
case MCE_ERROR_TYPE_UE:
mce_err->u.ue_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_SLB:
mce_err->u.slb_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_ERAT:
mce_err->u.erat_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_TLB:
mce_err->u.tlb_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_USER:
mce_err->u.user_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_RA:
mce_err->u.ra_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_LINK:
mce_err->u.link_error_type = table[i].error_subtype;
break;
}
mce_err->sync_error = table[i].sync_error;
mce_err->severity = table[i].severity;
mce_err->initiator = table[i].initiator;
if (table[i].nip_valid) {
*addr = regs->nip;
if (mce_err->sync_error &&
table[i].error_type == MCE_ERROR_TYPE_UE) {
unsigned long pfn;
if (get_paca()->in_mce < MAX_MCE_DEPTH) {
pfn = addr_to_pfn(regs, regs->nip);
if (pfn != ULONG_MAX) {
*phys_addr =
(pfn << PAGE_SHIFT);
}
}
}
}
return handled;
}
mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
mce_err->error_class = MCE_ECLASS_UNKNOWN;
mce_err->severity = MCE_SEV_SEVERE;
mce_err->initiator = MCE_INITIATOR_CPU;
mce_err->sync_error = true;
return 0;
powerpc/book3s: Decode and save machine check event. Now that we handle machine check in linux, the MCE decoding should also take place in linux host. This info is crucial to log before we go down in case we can not handle the machine check errors. This patch decodes and populates a machine check event which contain high level meaning full MCE information. We do this in real mode C code with ME bit on. The MCE information is still available on emergency stack (in pt_regs structure format). Even if we take another exception at this point the MCE early handler will allocate a new stack frame on top of current one. So when we return back here we still have our MCE information safe on current stack. We use per cpu buffer to save high level MCE information. Each per cpu buffer is an array of machine check event structure indexed by per cpu counter mce_nest_count. The mce_nest_count is incremented every time we enter machine check early handler in real mode to get the current free slot (index = mce_nest_count - 1). The mce_nest_count is decremented once the MCE info is consumed by virtual mode machine exception handler. This patch provides save_mce_event(), get_mce_event() and release_mce_event() generic routines that can be used by machine check handlers to populate and retrieve the event. The routine release_mce_event() will free the event slot so that it can be reused. Caller can invoke get_mce_event() with a release flag either to release the event slot immediately OR keep it so that it can be fetched again. The event slot can be also released anytime by invoking release_mce_event(). This patch also updates kvm code to invoke get_mce_event to retrieve generic mce event rather than paca->opal_mce_evt. The KVM code always calls get_mce_event() with release flags set to false so that event is available for linus host machine If machine check occurs while we are in guest, KVM tries to handle the error. If KVM is able to handle MC error successfully, it enters the guest and delivers the machine check to guest. If KVM is not able to handle MC error, it exists the guest and passes the control to linux host machine check handler which then logs MC event and decides how to handle it in linux host. In failure case, KVM needs to make sure that the MC event is available for linux host to consume. Hence KVM always calls get_mce_event() with release flags set to false and later it invokes release_mce_event() only if it succeeds to handle error. Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-10-30 08:35:40 -06:00
}
static int mce_handle_derror(struct pt_regs *regs,
const struct mce_derror_table table[],
struct mce_error_info *mce_err, uint64_t *addr,
uint64_t *phys_addr)
powerpc/book3s: Decode and save machine check event. Now that we handle machine check in linux, the MCE decoding should also take place in linux host. This info is crucial to log before we go down in case we can not handle the machine check errors. This patch decodes and populates a machine check event which contain high level meaning full MCE information. We do this in real mode C code with ME bit on. The MCE information is still available on emergency stack (in pt_regs structure format). Even if we take another exception at this point the MCE early handler will allocate a new stack frame on top of current one. So when we return back here we still have our MCE information safe on current stack. We use per cpu buffer to save high level MCE information. Each per cpu buffer is an array of machine check event structure indexed by per cpu counter mce_nest_count. The mce_nest_count is incremented every time we enter machine check early handler in real mode to get the current free slot (index = mce_nest_count - 1). The mce_nest_count is decremented once the MCE info is consumed by virtual mode machine exception handler. This patch provides save_mce_event(), get_mce_event() and release_mce_event() generic routines that can be used by machine check handlers to populate and retrieve the event. The routine release_mce_event() will free the event slot so that it can be reused. Caller can invoke get_mce_event() with a release flag either to release the event slot immediately OR keep it so that it can be fetched again. The event slot can be also released anytime by invoking release_mce_event(). This patch also updates kvm code to invoke get_mce_event to retrieve generic mce event rather than paca->opal_mce_evt. The KVM code always calls get_mce_event() with release flags set to false so that event is available for linus host machine If machine check occurs while we are in guest, KVM tries to handle the error. If KVM is able to handle MC error successfully, it enters the guest and delivers the machine check to guest. If KVM is not able to handle MC error, it exists the guest and passes the control to linux host machine check handler which then logs MC event and decides how to handle it in linux host. In failure case, KVM needs to make sure that the MC event is available for linux host to consume. Hence KVM always calls get_mce_event() with release flags set to false and later it invokes release_mce_event() only if it succeeds to handle error. Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-10-30 08:35:40 -06:00
{
uint64_t dsisr = regs->dsisr;
int handled = 0;
int found = 0;
int i;
*addr = 0;
for (i = 0; table[i].dsisr_value; i++) {
if (!(dsisr & table[i].dsisr_value))
continue;
/* attempt to correct the error */
switch (table[i].error_type) {
case MCE_ERROR_TYPE_SLB:
if (local_paca->in_mce == 1)
slb_save_contents(local_paca->mce_faulty_slbs);
if (mce_flush(MCE_FLUSH_SLB))
handled = 1;
break;
case MCE_ERROR_TYPE_ERAT:
if (mce_flush(MCE_FLUSH_ERAT))
handled = 1;
break;
case MCE_ERROR_TYPE_TLB:
if (mce_flush(MCE_FLUSH_TLB))
handled = 1;
break;
}
/*
* Attempt to handle multiple conditions, but only return
* one. Ensure uncorrectable errors are first in the table
* to match.
*/
if (found)
continue;
/* now fill in mce_error_info */
mce_err->error_type = table[i].error_type;
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
mce_err->error_class = table[i].error_class;
switch (table[i].error_type) {
case MCE_ERROR_TYPE_UE:
mce_err->u.ue_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_SLB:
mce_err->u.slb_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_ERAT:
mce_err->u.erat_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_TLB:
mce_err->u.tlb_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_USER:
mce_err->u.user_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_RA:
mce_err->u.ra_error_type = table[i].error_subtype;
break;
case MCE_ERROR_TYPE_LINK:
mce_err->u.link_error_type = table[i].error_subtype;
break;
}
mce_err->sync_error = table[i].sync_error;
mce_err->severity = table[i].severity;
mce_err->initiator = table[i].initiator;
if (table[i].dar_valid)
*addr = regs->dar;
else if (mce_err->sync_error &&
table[i].error_type == MCE_ERROR_TYPE_UE) {
/*
* We do a maximum of 4 nested MCE calls, see
* kernel/exception-64s.h
*/
if (get_paca()->in_mce < MAX_MCE_DEPTH)
mce_find_instr_ea_and_phys(regs, addr,
phys_addr);
}
found = 1;
powerpc/book3s: Decode and save machine check event. Now that we handle machine check in linux, the MCE decoding should also take place in linux host. This info is crucial to log before we go down in case we can not handle the machine check errors. This patch decodes and populates a machine check event which contain high level meaning full MCE information. We do this in real mode C code with ME bit on. The MCE information is still available on emergency stack (in pt_regs structure format). Even if we take another exception at this point the MCE early handler will allocate a new stack frame on top of current one. So when we return back here we still have our MCE information safe on current stack. We use per cpu buffer to save high level MCE information. Each per cpu buffer is an array of machine check event structure indexed by per cpu counter mce_nest_count. The mce_nest_count is incremented every time we enter machine check early handler in real mode to get the current free slot (index = mce_nest_count - 1). The mce_nest_count is decremented once the MCE info is consumed by virtual mode machine exception handler. This patch provides save_mce_event(), get_mce_event() and release_mce_event() generic routines that can be used by machine check handlers to populate and retrieve the event. The routine release_mce_event() will free the event slot so that it can be reused. Caller can invoke get_mce_event() with a release flag either to release the event slot immediately OR keep it so that it can be fetched again. The event slot can be also released anytime by invoking release_mce_event(). This patch also updates kvm code to invoke get_mce_event to retrieve generic mce event rather than paca->opal_mce_evt. The KVM code always calls get_mce_event() with release flags set to false so that event is available for linus host machine If machine check occurs while we are in guest, KVM tries to handle the error. If KVM is able to handle MC error successfully, it enters the guest and delivers the machine check to guest. If KVM is not able to handle MC error, it exists the guest and passes the control to linux host machine check handler which then logs MC event and decides how to handle it in linux host. In failure case, KVM needs to make sure that the MC event is available for linux host to consume. Hence KVM always calls get_mce_event() with release flags set to false and later it invokes release_mce_event() only if it succeeds to handle error. Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-10-30 08:35:40 -06:00
}
if (found)
return handled;
mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
powerpc/powernv/mce: Print additional information about MCE error. Print more information about MCE error whether it is an hardware or software error. Some of the MCE errors can be easily categorized as hardware or software errors e.g. UEs are due to hardware error, where as error triggered due to invalid usage of tlbie is a pure software bug. But not all the MCE errors can be easily categorize into either software or hardware. There are errors like multihit errors which are usually result of a software bug, but in some rare cases a hardware failure can cause a multihit error. In past, we have seen case where after replacing faulty chip, multihit errors stopped occurring. Same with parity errors, which are usually due to faulty hardware but there are chances where multihit can also cause an parity error. Such errors are difficult to determine what really caused it. Hence this patch classifies MCE errors into following four categorize: 1. Hardware error: UE and Link timeout failure errors. 2. Probable hardware error (some chance of software cause) SLB/ERAT/TLB Parity errors. 3. Software error Invalid tlbie form. 4. Probable software error (some chance of hardware cause) SLB/ERAT/TLB Multihit errors. Sample output: MCE: CPU80: machine check (Warning) Guest SLB Multihit DAR: 000001001b6e0320 [Recovered] MCE: CPU80: PID: 24765 Comm: qemu-system-ppc Guest NIP: [00007fffa309dc60] MCE: CPU80: Probable Software error (some chance of hardware cause) Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-04-29 12:16:02 -06:00
mce_err->error_class = MCE_ECLASS_UNKNOWN;
mce_err->severity = MCE_SEV_SEVERE;
mce_err->initiator = MCE_INITIATOR_CPU;
mce_err->sync_error = true;
return 0;
powerpc/book3s: Decode and save machine check event. Now that we handle machine check in linux, the MCE decoding should also take place in linux host. This info is crucial to log before we go down in case we can not handle the machine check errors. This patch decodes and populates a machine check event which contain high level meaning full MCE information. We do this in real mode C code with ME bit on. The MCE information is still available on emergency stack (in pt_regs structure format). Even if we take another exception at this point the MCE early handler will allocate a new stack frame on top of current one. So when we return back here we still have our MCE information safe on current stack. We use per cpu buffer to save high level MCE information. Each per cpu buffer is an array of machine check event structure indexed by per cpu counter mce_nest_count. The mce_nest_count is incremented every time we enter machine check early handler in real mode to get the current free slot (index = mce_nest_count - 1). The mce_nest_count is decremented once the MCE info is consumed by virtual mode machine exception handler. This patch provides save_mce_event(), get_mce_event() and release_mce_event() generic routines that can be used by machine check handlers to populate and retrieve the event. The routine release_mce_event() will free the event slot so that it can be reused. Caller can invoke get_mce_event() with a release flag either to release the event slot immediately OR keep it so that it can be fetched again. The event slot can be also released anytime by invoking release_mce_event(). This patch also updates kvm code to invoke get_mce_event to retrieve generic mce event rather than paca->opal_mce_evt. The KVM code always calls get_mce_event() with release flags set to false so that event is available for linus host machine If machine check occurs while we are in guest, KVM tries to handle the error. If KVM is able to handle MC error successfully, it enters the guest and delivers the machine check to guest. If KVM is not able to handle MC error, it exists the guest and passes the control to linux host machine check handler which then logs MC event and decides how to handle it in linux host. In failure case, KVM needs to make sure that the MC event is available for linux host to consume. Hence KVM always calls get_mce_event() with release flags set to false and later it invokes release_mce_event() only if it succeeds to handle error. Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-10-30 08:35:40 -06:00
}
static long mce_handle_ue_error(struct pt_regs *regs,
struct mce_error_info *mce_err)
{
long handled = 0;
const struct exception_table_entry *entry;
entry = search_kernel_exception_table(regs->nip);
if (entry) {
mce_err->ignore_event = true;
regs->nip = extable_fixup(entry);
return 1;
}
/*
* On specific SCOM read via MMIO we may get a machine check
* exception with SRR0 pointing inside opal. If that is the
* case OPAL may have recovery address to re-read SCOM data in
* different way and hence we can recover from this MC.
*/
if (ppc_md.mce_check_early_recovery) {
if (ppc_md.mce_check_early_recovery(regs))
handled = 1;
}
return handled;
}
static long mce_handle_error(struct pt_regs *regs,
const struct mce_derror_table dtable[],
const struct mce_ierror_table itable[])
{
struct mce_error_info mce_err = { 0 };
powerpc/mce: Fix a bug where mce loops on memory UE. The current code extracts the physical address for UE errors and then hooks it up into memory failure infrastructure. On successful extraction of physical address it wrongly sets "handled = 1" which means this UE error has been recovered. Since MCE handler gets return value as handled = 1, it assumes that error has been recovered and goes back to same NIP. This causes MCE interrupt again and again in a loop leading to hard lockup. Also, initialize phys_addr to ULONG_MAX so that we don't end up queuing undesired page to hwpoison. Without this patch we see: Severe Machine check interrupt [Recovered] NIP: [000000001002588c] PID: 7109 Comm: find Initiator: CPU Error type: UE [Load/Store] Effective address: 00007fffd2755940 Physical address: 000020181a080000 ... Severe Machine check interrupt [Recovered] NIP: [000000001002588c] PID: 7109 Comm: find Initiator: CPU Error type: UE [Load/Store] Effective address: 00007fffd2755940 Physical address: 000020181a080000 Severe Machine check interrupt [Recovered] NIP: [000000001002588c] PID: 7109 Comm: find Initiator: CPU Error type: UE [Load/Store] Effective address: 00007fffd2755940 Physical address: 000020181a080000 Memory failure: 0x20181a08: recovery action for dirty LRU page: Recovered Memory failure: 0x20181a08: already hardware poisoned Memory failure: 0x20181a08: already hardware poisoned Memory failure: 0x20181a08: already hardware poisoned Memory failure: 0x20181a08: already hardware poisoned Memory failure: 0x20181a08: already hardware poisoned Memory failure: 0x20181a08: already hardware poisoned ... Watchdog CPU:38 Hard LOCKUP After this patch we see: Severe Machine check interrupt [Not recovered] NIP: [00007fffaae585f4] PID: 7168 Comm: find Initiator: CPU Error type: UE [Load/Store] Effective address: 00007fffaafe28ac Physical address: 00002017c0bd0000 find[7168]: unhandled signal 7 at 00007fffaae585f4 nip 00007fffaae585f4 lr 00007fffaae585e0 code 4 Memory failure: 0x2017c0bd: recovery action for dirty LRU page: Recovered Fixes: 01eaac2b0591 ("powerpc/mce: Hookup ierror (instruction) UE errors") Fixes: ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors") Cc: stable@vger.kernel.org # v4.15+ Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <bsingharora@gmail.com> Reviewed-by: Balbir Singh <bsingharora@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-04-22 22:59:27 -06:00
uint64_t addr, phys_addr = ULONG_MAX;
uint64_t srr1 = regs->msr;
long handled;
if (SRR1_MC_LOADSTORE(srr1))
handled = mce_handle_derror(regs, dtable, &mce_err, &addr,
&phys_addr);
else
handled = mce_handle_ierror(regs, itable, &mce_err, &addr,
&phys_addr);
if (!handled && mce_err.error_type == MCE_ERROR_TYPE_UE)
handled = mce_handle_ue_error(regs, &mce_err);
save_mce_event(regs, handled, &mce_err, regs->nip, addr, phys_addr);
return handled;
}
long __machine_check_early_realmode_p7(struct pt_regs *regs)
{
/* P7 DD1 leaves top bits of DSISR undefined */
regs->dsisr &= 0x0000ffff;
return mce_handle_error(regs, mce_p7_derror_table, mce_p7_ierror_table);
}
long __machine_check_early_realmode_p8(struct pt_regs *regs)
{
return mce_handle_error(regs, mce_p8_derror_table, mce_p8_ierror_table);
}
long __machine_check_early_realmode_p9(struct pt_regs *regs)
{
/*
* On POWER9 DD2.1 and below, it's possible to get a machine check
* caused by a paste instruction where only DSISR bit 25 is set. This
* will result in the MCE handler seeing an unknown event and the kernel
* crashing. An MCE that occurs like this is spurious, so we don't need
* to do anything in terms of servicing it. If there is something that
* needs to be serviced, the CPU will raise the MCE again with the
* correct DSISR so that it can be serviced properly. So detect this
* case and mark it as handled.
*/
if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x02000000)
return 1;
return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table);
}