Hi all,
Today's linux-next merge of the nvdimm tree got a conflict in:
arch/x86/kernel/cpu/mcheck/mce.c
between commit:
d3d6923cd1ae ("x86/mce: Carve out the crashing_cpu check")
from the tip tree and commit:
f6785eac562b ("x86/memory_failure: Introduce {set,clear}_mce_nospec()")
from the nvdimm tree.
I fixed it up (see below) and can carry the fix as necessary. This
is now fixed as far as linux-next is concerned, but any non trivial
conflicts should be mentioned to your upstream maintainer when your tree
is submitted for merging. You may also want to consider cooperating
with the maintainer of the conflicting tree to minimise any particularly
complex conflicts.
--
Cheers,
Stephen Rothwell
diff --cc arch/x86/kernel/cpu/mcheck/mce.c
index 9a16f15f79eb,a0fbf0a8b7e6..000000000000
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@@ -1076,129 -1070,6 +1072,100 @@@ static int do_memory_failure(struct mc
return ret;
}
- #ifndef mce_unmap_kpfn
- static void mce_unmap_kpfn(unsigned long pfn)
- {
- unsigned long decoy_addr;
-
- /*
- * Unmap this page from the kernel 1:1 mappings to make sure
- * we don't log more errors because of speculative access to
- * the page.
- * We would like to just call:
- * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1);
- * but doing that would radically increase the odds of a
- * speculative access to the poison page because we'd have
- * the virtual address of the kernel 1:1 mapping sitting
- * around in registers.
- * Instead we get tricky. We create a non-canonical address
- * that looks just like the one we want, but has bit 63 flipped.
- * This relies on set_memory_np() not checking whether we passed
- * a legal address.
- */
-
- decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
-
- if (set_memory_np(decoy_addr, 1))
- pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
- }
- #endif
-
-
+/*
+ * Cases where we avoid rendezvous handler timeout:
+ * 1) If this CPU is offline.
+ *
+ * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
+ * skip those CPUs which remain looping in the 1st kernel - see
+ * crash_nmi_callback().
+ *
+ * Note: there still is a small window between kexec-ing and the new,
+ * kdump kernel establishing a new #MC handler where a broadcasted MCE
+ * might not get handled properly.
+ */
+static bool __mc_check_crashing_cpu(int cpu)
+{
+ if (cpu_is_offline(cpu) ||
+ (crashing_cpu != -1 && crashing_cpu != cpu)) {
+ u64 mcgstatus;
+
+ mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+ if (mcgstatus & MCG_STATUS_RIPV) {
+ mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+ return true;
+ }
+ }
+ return false;
+}
+
+static void __mc_scan_banks(struct mce *m, struct mce *final,
+ unsigned long *toclear, unsigned long *valid_banks,
+ int no_way_out, int *worst)
+{
+ struct mca_config *cfg = &mca_cfg;
+ int severity, i;
+
+ for (i = 0; i < cfg->banks; i++) {
+ __clear_bit(i, toclear);
+ if (!test_bit(i, valid_banks))
+ continue;
+
+ if (!mce_banks[i].ctl)
+ continue;
+
+ m->misc = 0;
+ m->addr = 0;
+ m->bank = i;
+
+ m->status = mce_rdmsrl(msr_ops.status(i));
+ if (!(m->status & MCI_STATUS_VAL))
+ continue;
+
+ /*
+ * Corrected or non-signaled errors are handled by
+ * machine_check_poll(). Leave them alone, unless this panics.
+ */
+ if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
+ !no_way_out)
+ continue;
+
+ /* Set taint even when machine check was not enabled. */
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
+ severity = mce_severity(m, cfg->tolerant, NULL, true);
+
+ /*
+ * When machine check was for corrected/deferred handler don't
+ * touch, unless we're panicking.
+ */
+ if ((severity == MCE_KEEP_SEVERITY ||
+ severity == MCE_UCNA_SEVERITY) && !no_way_out)
+ continue;
+
+ __set_bit(i, toclear);
+
+ /* Machine check event was not enabled. Clear, but ignore. */
+ if (severity == MCE_NO_SEVERITY)
+ continue;
+
+ mce_read_aux(m, i);
+
+ /* assuming valid severity level != 0 */
+ m->severity = severity;
+
+ mce_log(m);
+
+ if (severity > *worst) {
+ *final = *m;
+ *worst = severity;
+ }
+ }
+
+ /* mce_clear_state will clear *final, save locally for use later */
+ *m = *final;
+}
+
/*
* The actual machine check handler. This only handles real
* exceptions when something got corrupted coming in through int 18.
Attachment:
pgpHsIwo3evvw.pgp
Description: OpenPGP digital signature
