aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorIngo Molnar <mingo@elte.hu>2008-02-04 16:48:07 +0100
committerIngo Molnar <mingo@elte.hu>2008-02-04 16:48:07 +0100
commit34508f66b69ff1708192654f631eb8f1d4c52005 (patch)
treef4197d445541c1a04e1bc351b4209136593c20d0
parent65e074dffa198978ab0c9976a19b954fbe1183e2 (diff)
x86: AMD Athlon X2 hard hang fix
An Athlon 64 X2 test system showed hard hangs shortly after marking the kernel text read-only, if we tried to preserve largepages and changed the PSE entry from RW to RO. The pagetable code itself is correct, it's the CPU that locked up hard (and not even the NMI watchdog could punch through that hard hang). So be conservative and always do splitups - like we did in the past. Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--arch/x86/mm/pageattr.c11
1 files changed, 11 insertions, 0 deletions
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 40b7ac58e67..3810f7a83b1 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -243,6 +243,17 @@ static int try_preserve_large_page(pte_t *kpte, unsigned long address,
pgprot_t old_prot, new_prot;
int level, res = CPA_SPLIT;
+ /*
+ * An Athlon 64 X2 showed hard hangs if we tried to preserve
+ * largepages and changed the PSE entry from RW to RO.
+ *
+ * As AMD CPUs have a long series of erratas in this area,
+ * (and none of the known ones seem to explain this hang),
+ * disable this code until the hang can be debugged:
+ */
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ return res;
+
spin_lock_irqsave(&pgd_lock, flags);
/*
* Check for races, another CPU might have split this page