summaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel/mce.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-05-10 05:29:27 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-05-10 05:29:27 -0700
commitb970afcfcabd63cd3832e95db096439c177c3592 (patch)
treeb63e662c780e02617916f4c0269e2adddc67f5a0 /arch/powerpc/kernel/mce.c
parent8ea5b2abd07e2280a332bd9c1a7f4dd15b9b6c13 (diff)
parent8150a153c013aa2dd1ffae43370b89ac1347a7fb (diff)
Merge tag 'powerpc-5.2-1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman: "Slightly delayed due to the issue with printk() calling probe_kernel_read() interacting with our new user access prevention stuff, but all fixed now. The only out-of-area changes are the addition of a cpuhp_state, small additions to Documentation and MAINTAINERS updates. Highlights: - Support for Kernel Userspace Access/Execution Prevention (like SMAP/SMEP/PAN/PXN) on some 64-bit and 32-bit CPUs. This prevents the kernel from accidentally accessing userspace outside copy_to/from_user(), or ever executing userspace. - KASAN support on 32-bit. - Rework of where we map the kernel, vmalloc, etc. on 64-bit hash to use the same address ranges we use with the Radix MMU. - A rewrite into C of large parts of our idle handling code for 64-bit Book3S (ie. power8 & power9). - A fast path entry for syscalls on 32-bit CPUs, for a 12-17% speedup in the null_syscall benchmark. - On 64-bit bare metal we have support for recovering from errors with the time base (our clocksource), however if that fails currently we hang in __delay() and never crash. We now have support for detecting that case and short circuiting __delay() so we at least panic() and reboot. - Add support for optionally enabling the DAWR on Power9, which had to be disabled by default due to a hardware erratum. This has the effect of enabling hardware breakpoints for GDB, the downside is a badly behaved program could crash the machine by pointing the DAWR at cache inhibited memory. This is opt-in obviously. - xmon, our crash handler, gets support for a read only mode where operations that could change memory or otherwise disturb the system are disabled. Plus many clean-ups, reworks and minor fixes etc. Thanks to: Christophe Leroy, Akshay Adiga, Alastair D'Silva, Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Anton Blanchard, Ben Hutchings, Bo YU, Breno Leitao, Cédric Le Goater, Christopher M. Riedl, Christoph Hellwig, Colin Ian King, David Gibson, Ganesh Goudar, Gautham R. Shenoy, George Spelvin, Greg Kroah-Hartman, Greg Kurz, Horia Geantă, Jagadeesh Pagadala, Joel Stanley, Joe Perches, Julia Lawall, Laurentiu Tudor, Laurent Vivier, Lukas Bulwahn, Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Malaterre, Michael Neuling, Mukesh Ojha, Nathan Fontenot, Nathan Lynch, Nicholas Piggin, Nick Desaulniers, Oliver O'Halloran, Peng Hao, Qian Cai, Ravi Bangoria, Rick Lindsley, Russell Currey, Sachin Sant, Stewart Smith, Sukadev Bhattiprolu, Thomas Huth, Tobin C. Harding, Tyrel Datwyler, Valentin Schneider, Wei Yongjun, Wen Yang, YueHaibing" * tag 'powerpc-5.2-1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (205 commits) powerpc/64s: Use early_mmu_has_feature() in set_kuap() powerpc/book3s/64: check for NULL pointer in pgd_alloc() powerpc/mm: Fix hugetlb page initialization ocxl: Fix return value check in afu_ioctl() powerpc/mm: fix section mismatch for setup_kup() powerpc/mm: fix redundant inclusion of pgtable-frag.o in Makefile powerpc/mm: Fix makefile for KASAN powerpc/kasan: add missing/lost Makefile selftests/powerpc: Add a signal fuzzer selftest powerpc/booke64: set RI in default MSR ocxl: Provide global MMIO accessors for external drivers ocxl: move event_fd handling to frontend ocxl: afu_irq only deals with IRQ IDs, not offsets ocxl: Allow external drivers to use OpenCAPI contexts ocxl: Create a clear delineation between ocxl backend & frontend ocxl: Don't pass pci_dev around ocxl: Split pci.c ocxl: Remove some unused exported symbols ocxl: Remove superfluous 'extern' from headers ocxl: read_pasid never returns an error, so make it void ...
Diffstat (limited to 'arch/powerpc/kernel/mce.c')
-rw-r--r--arch/powerpc/kernel/mce.c106
1 files changed, 63 insertions, 43 deletions
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index b5fec1f9751a..4581377cfc98 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -112,6 +112,7 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->srr1 = regs->msr;
mce->gpr3 = regs->gpr[3];
mce->in_use = 1;
+ mce->cpu = get_paca()->paca_index;
/* Mark it recovered if we have handled it and MSR(RI=1). */
if (handled && (regs->msr & MSR_RI))
@@ -121,6 +122,8 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->initiator = mce_err->initiator;
mce->severity = mce_err->severity;
+ mce->sync_error = mce_err->sync_error;
+ mce->error_class = mce_err->error_class;
/*
* Populate the mce error_type and type-specific error_type.
@@ -310,7 +313,11 @@ static void machine_check_process_queued_event(struct irq_work *work)
void machine_check_print_event_info(struct machine_check_event *evt,
bool user_mode, bool in_guest)
{
- const char *level, *sevstr, *subtype;
+ const char *level, *sevstr, *subtype, *err_type;
+ uint64_t ea = 0, pa = 0;
+ int n = 0;
+ char dar_str[50];
+ char pa_str[50];
static const char *mc_ue_types[] = {
"Indeterminate",
"Instruction fetch",
@@ -357,6 +364,13 @@ void machine_check_print_event_info(struct machine_check_event *evt,
"Store (timeout)",
"Page table walk Load/Store (timeout)",
};
+ static const char *mc_error_class[] = {
+ "Unknown",
+ "Hardware error",
+ "Probable Hardware error (some chance of software cause)",
+ "Software error",
+ "Probable Software error (some chance of hardware cause)",
+ };
/* Print things out */
if (evt->version != MCE_V1) {
@@ -371,9 +385,9 @@ void machine_check_print_event_info(struct machine_check_event *evt,
break;
case MCE_SEV_WARNING:
level = KERN_WARNING;
- sevstr = "";
+ sevstr = "Warning";
break;
- case MCE_SEV_ERROR_SYNC:
+ case MCE_SEV_SEVERE:
level = KERN_ERR;
sevstr = "Severe";
break;
@@ -384,101 +398,107 @@ void machine_check_print_event_info(struct machine_check_event *evt,
break;
}
- printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
- evt->disposition == MCE_DISPOSITION_RECOVERED ?
- "Recovered" : "Not recovered");
-
- if (in_guest) {
- printk("%s Guest NIP: %016llx\n", level, evt->srr0);
- } else if (user_mode) {
- printk("%s NIP: [%016llx] PID: %d Comm: %s\n", level,
- evt->srr0, current->pid, current->comm);
- } else {
- printk("%s NIP [%016llx]: %pS\n", level, evt->srr0,
- (void *)evt->srr0);
- }
-
- printk("%s Initiator: %s\n", level,
- evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
switch (evt->error_type) {
case MCE_ERROR_TYPE_UE:
+ err_type = "UE";
subtype = evt->u.ue_error.ue_error_type <
ARRAY_SIZE(mc_ue_types) ?
mc_ue_types[evt->u.ue_error.ue_error_type]
: "Unknown";
- printk("%s Error type: UE [%s]\n", level, subtype);
if (evt->u.ue_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt->u.ue_error.effective_address);
+ ea = evt->u.ue_error.effective_address;
if (evt->u.ue_error.physical_address_provided)
- printk("%s Physical address: %016llx\n",
- level, evt->u.ue_error.physical_address);
+ pa = evt->u.ue_error.physical_address;
break;
case MCE_ERROR_TYPE_SLB:
+ err_type = "SLB";
subtype = evt->u.slb_error.slb_error_type <
ARRAY_SIZE(mc_slb_types) ?
mc_slb_types[evt->u.slb_error.slb_error_type]
: "Unknown";
- printk("%s Error type: SLB [%s]\n", level, subtype);
if (evt->u.slb_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt->u.slb_error.effective_address);
+ ea = evt->u.slb_error.effective_address;
break;
case MCE_ERROR_TYPE_ERAT:
+ err_type = "ERAT";
subtype = evt->u.erat_error.erat_error_type <
ARRAY_SIZE(mc_erat_types) ?
mc_erat_types[evt->u.erat_error.erat_error_type]
: "Unknown";
- printk("%s Error type: ERAT [%s]\n", level, subtype);
if (evt->u.erat_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt->u.erat_error.effective_address);
+ ea = evt->u.erat_error.effective_address;
break;
case MCE_ERROR_TYPE_TLB:
+ err_type = "TLB";
subtype = evt->u.tlb_error.tlb_error_type <
ARRAY_SIZE(mc_tlb_types) ?
mc_tlb_types[evt->u.tlb_error.tlb_error_type]
: "Unknown";
- printk("%s Error type: TLB [%s]\n", level, subtype);
if (evt->u.tlb_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt->u.tlb_error.effective_address);
+ ea = evt->u.tlb_error.effective_address;
break;
case MCE_ERROR_TYPE_USER:
+ err_type = "User";
subtype = evt->u.user_error.user_error_type <
ARRAY_SIZE(mc_user_types) ?
mc_user_types[evt->u.user_error.user_error_type]
: "Unknown";
- printk("%s Error type: User [%s]\n", level, subtype);
if (evt->u.user_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt->u.user_error.effective_address);
+ ea = evt->u.user_error.effective_address;
break;
case MCE_ERROR_TYPE_RA:
+ err_type = "Real address";
subtype = evt->u.ra_error.ra_error_type <
ARRAY_SIZE(mc_ra_types) ?
mc_ra_types[evt->u.ra_error.ra_error_type]
: "Unknown";
- printk("%s Error type: Real address [%s]\n", level, subtype);
if (evt->u.ra_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt->u.ra_error.effective_address);
+ ea = evt->u.ra_error.effective_address;
break;
case MCE_ERROR_TYPE_LINK:
+ err_type = "Link";
subtype = evt->u.link_error.link_error_type <
ARRAY_SIZE(mc_link_types) ?
mc_link_types[evt->u.link_error.link_error_type]
: "Unknown";
- printk("%s Error type: Link [%s]\n", level, subtype);
if (evt->u.link_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt->u.link_error.effective_address);
+ ea = evt->u.link_error.effective_address;
break;
default:
case MCE_ERROR_TYPE_UNKNOWN:
- printk("%s Error type: Unknown\n", level);
+ err_type = "Unknown";
+ subtype = "";
break;
}
+
+ dar_str[0] = pa_str[0] = '\0';
+ if (ea && evt->srr0 != ea) {
+ /* Load/Store address */
+ n = sprintf(dar_str, "DAR: %016llx ", ea);
+ if (pa)
+ sprintf(dar_str + n, "paddr: %016llx ", pa);
+ } else if (pa) {
+ sprintf(pa_str, " paddr: %016llx", pa);
+ }
+
+ printk("%sMCE: CPU%d: machine check (%s) %s %s %s %s[%s]\n",
+ level, evt->cpu, sevstr, in_guest ? "Guest" : "Host",
+ err_type, subtype, dar_str,
+ evt->disposition == MCE_DISPOSITION_RECOVERED ?
+ "Recovered" : "Not recovered");
+
+ if (in_guest || user_mode) {
+ printk("%sMCE: CPU%d: PID: %d Comm: %s %sNIP: [%016llx]%s\n",
+ level, evt->cpu, current->pid, current->comm,
+ in_guest ? "Guest " : "", evt->srr0, pa_str);
+ } else {
+ printk("%sMCE: CPU%d: NIP: [%016llx] %pS%s\n",
+ level, evt->cpu, evt->srr0, (void *)evt->srr0, pa_str);
+ }
+
+ subtype = evt->error_class < ARRAY_SIZE(mc_error_class) ?
+ mc_error_class[evt->error_class] : "Unknown";
+ printk("%sMCE: CPU%d: %s\n", level, evt->cpu, subtype);
}
EXPORT_SYMBOL_GPL(machine_check_print_event_info);