x86: finish user fault error path with fatal signal

The x86 fault handler bails in the middle of error handling when the
task has a fatal signal pending.  For a subsequent patch this is a
problem in OOM situations because it relies on pagefault_out_of_memory()
being called even when the task has been killed, to perform proper
per-task OOM state unwinding.

Shortcutting the fault like this is a rather minor optimization that
saves a few instructions in rare cases.  Just remove it for
user-triggered faults.

Use the opportunity to split the fault retry handling from actual fault
errors and add locking documentation that reads suprisingly similar to
ARM's.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: azurIt <azurit@pobox.sk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 17 insertions, 18 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 6d77c3866faa..3aaeffcfd67a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -842,23 +842,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
         force_sig_info_fault(SIGBUS, code, address, tsk, fault);
 }
 
-static noinline int
+static noinline void
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
                unsigned long address, unsigned int fault)
 {
-        /*
-         * Pagefault was interrupted by SIGKILL. We have no reason to
-         * continue pagefault.
-         */
-        if (fatal_signal_pending(current)) {
-                if (!(fault & VM_FAULT_RETRY))
-                        up_read(&current->mm->mmap_sem);
-                if (!(error_code & PF_USER))
-                        no_context(regs, error_code, address, 0, 0);
-                return 1;
+        if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
+                up_read(&current->mm->mmap_sem);
+                no_context(regs, error_code, address, 0, 0);
+                return;
         }
-        if (!(fault & VM_FAULT_ERROR))
-                return 0;
 
         if (fault & VM_FAULT_OOM) {
                 /* Kernel mode? Handle exceptions or die: */
@@ -866,7 +858,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
                         up_read(&current->mm->mmap_sem);
                         no_context(regs, error_code, address,
                                    SIGSEGV, SEGV_MAPERR);
-                        return 1;
+                        return;
                 }
 
                 up_read(&current->mm->mmap_sem);
@@ -884,7 +876,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
                 else
                         BUG();
         }
-        return 1;
 }
 
 static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -1189,9 +1180,17 @@ good_area:
          */
         fault = handle_mm_fault(mm, vma, address, flags);
 
-        if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
-                if (mm_fault_error(regs, error_code, address, fault))
-                        return;
+        /*
+         * If we need to retry but a fatal signal is pending, handle the
+         * signal first. We do not need to release the mmap_sem because it
+         * would already be released in __lock_page_or_retry in mm/filemap.c.
+         */
+        if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)))
+                return;
+
+        if (unlikely(fault & VM_FAULT_ERROR)) {
+                mm_fault_error(regs, error_code, address, fault);
+                return;
         }
 
         /*