summaryrefslogtreecommitdiffstats
path: root/mm/memory-failure.c
diff options
context:
space:
mode:
authorHuang Ying <ying.huang@intel.com>2010-05-31 14:28:19 +0800
committerAvi Kivity <avi@redhat.com>2010-08-01 10:35:26 +0300
commitbf998156d24bcb127318ad5bf531ac3bdfcd6449 (patch)
tree616c19474d7cb626ff9eebc54f6753563a4322cd /mm/memory-failure.c
parent540ad6b62b3a188a53b51cac81d8a60d40e29fbd (diff)
downloadop-kernel-dev-bf998156d24bcb127318ad5bf531ac3bdfcd6449.zip
op-kernel-dev-bf998156d24bcb127318ad5bf531ac3bdfcd6449.tar.gz
KVM: Avoid killing userspace through guest SRAO MCE on unmapped pages
In common cases, guest SRAO MCE will cause corresponding poisoned page be un-mapped and SIGBUS be sent to QEMU-KVM, then QEMU-KVM will relay the MCE to guest OS. But it is reported that if the poisoned page is accessed in guest after unmapping and before MCE is relayed to guest OS, userspace will be killed. The reason is as follows. Because poisoned page has been un-mapped, guest access will cause guest exit and kvm_mmu_page_fault will be called. kvm_mmu_page_fault can not get the poisoned page for fault address, so kernel and user space MMIO processing is tried in turn. In user MMIO processing, poisoned page is accessed again, then userspace is killed by force_sig_info. To fix the bug, kvm_mmu_page_fault send HWPOISON signal to QEMU-KVM and do not try kernel and user space MMIO processing for poisoned page. [xiao: fix warning introduced by avi] Reported-by: Max Asbock <masbock@linux.vnet.ibm.com> Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Diffstat (limited to 'mm/memory-failure.c')
-rw-r--r--mm/memory-failure.c30
1 files changed, 30 insertions, 0 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 620b0b4..378b0f6 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -45,6 +45,7 @@
#include <linux/page-isolation.h>
#include <linux/suspend.h>
#include <linux/slab.h>
+#include <linux/swapops.h>
#include "internal.h"
int sysctl_memory_failure_early_kill __read_mostly = 0;
@@ -1296,3 +1297,32 @@ done:
/* keep elevated page count for bad page */
return ret;
}
+
+int is_hwpoison_address(unsigned long addr)
+{
+ pgd_t *pgdp;
+ pud_t pud, *pudp;
+ pmd_t pmd, *pmdp;
+ pte_t pte, *ptep;
+ swp_entry_t entry;
+
+ pgdp = pgd_offset(current->mm, addr);
+ if (!pgd_present(*pgdp))
+ return 0;
+ pudp = pud_offset(pgdp, addr);
+ pud = *pudp;
+ if (!pud_present(pud) || pud_large(pud))
+ return 0;
+ pmdp = pmd_offset(pudp, addr);
+ pmd = *pmdp;
+ if (!pmd_present(pmd) || pmd_large(pmd))
+ return 0;
+ ptep = pte_offset_map(pmdp, addr);
+ pte = *ptep;
+ pte_unmap(ptep);
+ if (!is_swap_pte(pte))
+ return 0;
+ entry = pte_to_swp_entry(pte);
+ return is_hwpoison_entry(entry);
+}
+EXPORT_SYMBOL_GPL(is_hwpoison_address);
OpenPOWER on IntegriCloud