aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorJeremy Fitzhardinge <jeremy@goop.org>2008-01-30 13:34:11 +0100
committerIngo Molnar <mingo@elte.hu>2008-01-30 13:34:11 +0100
commit5b727a3b0158a129827c21ce3bfb0ba997e8ddd0 (patch)
treee0d43e258fa46e22ac6c4daf82c5005dc0e762c6 /arch
parentb406ac61e94875723540bd56e26f634afdeef489 (diff)
x86: ignore spurious faults
When changing a kernel page from RO->RW, it's OK to leave stale TLB entries around, since doing a global flush is expensive and they pose no security problem. They can, however, generate a spurious fault, which we should catch and simply return from (which will have the side-effect of reloading the TLB to the current PTE). This can occur when running under Xen, because it frequently changes kernel pages from RW->RO->RW to implement Xen's pagetable semantics. It could also occur when using CONFIG_DEBUG_PAGEALLOC, since it avoids doing a global TLB flush after changing page permissions. Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Harvey Harrison <harvey.harrison@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/mm/fault.c55
1 files changed, 55 insertions, 0 deletions
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 99d273dbc75..1c836527dde 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -435,6 +435,51 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
#endif
/*
+ * Handle a spurious fault caused by a stale TLB entry. This allows
+ * us to lazily refresh the TLB when increasing the permissions of a
+ * kernel page (RO -> RW or NX -> X). Doing it eagerly is very
+ * expensive since that implies doing a full cross-processor TLB
+ * flush, even if no stale TLB entries exist on other processors.
+ * There are no security implications to leaving a stale TLB when
+ * increasing the permissions on a page.
+ */
+static int spurious_fault(unsigned long address,
+ unsigned long error_code)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ /* Reserved-bit violation or user access to kernel space? */
+ if (error_code & (PF_USER | PF_RSVD))
+ return 0;
+
+ pgd = init_mm.pgd + pgd_index(address);
+ if (!pgd_present(*pgd))
+ return 0;
+
+ pud = pud_offset(pgd, address);
+ if (!pud_present(*pud))
+ return 0;
+
+ pmd = pmd_offset(pud, address);
+ if (!pmd_present(*pmd))
+ return 0;
+
+ pte = pte_offset_kernel(pmd, address);
+ if (!pte_present(*pte))
+ return 0;
+
+ if ((error_code & PF_WRITE) && !pte_write(*pte))
+ return 0;
+ if ((error_code & PF_INSTR) && !pte_exec(*pte))
+ return 0;
+
+ return 1;
+}
+
+/*
* X86_32
* Handle a fault on the vmalloc or module mapping area
*
@@ -568,6 +613,11 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
if (!(error_code & (PF_RSVD|PF_USER|PF_PROT)) &&
vmalloc_fault(address) >= 0)
return;
+
+ /* Can handle a stale RO->RW TLB */
+ if (spurious_fault(address, error_code))
+ return;
+
/*
* Don't take the mm semaphore here. If we fixup a prefetch
* fault we could otherwise deadlock.
@@ -598,6 +648,11 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
if (vmalloc_fault(address) >= 0)
return;
}
+
+ /* Can handle a stale RO->RW TLB */
+ if (spurious_fault(address, error_code))
+ return;
+
/*
* Don't take the mm semaphore here. If we fixup a prefetch
* fault we could otherwise deadlock.