arch: mm: pass userspace fault flag to generic fault handler

Unlike global OOM handling, memory cgroup code will invoke the OOM killer
in any OOM situation because it has no way of telling faults occuring in
kernel context - which could be handled more gracefully - from
user-triggered faults.

Pass a flag that identifies faults originating in user space from the
architecture-specific fault handlers to generic code so that memcg OOM
handling can be improved.

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

2 files changed, 13 insertions, 5 deletions

diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index e98bfda205a2..59dbd4645725 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -177,8 +177,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
         unsigned long g2;
         int from_user = !(regs->psr & PSR_PS);
         int fault, code;
-        unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                              (write ? FAULT_FLAG_WRITE : 0));
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
         if (text_fault)
                 address = regs->pc;
@@ -235,6 +234,11 @@ good_area:
                         goto bad_area;
         }
 
+        if (from_user)
+                flags |= FAULT_FLAG_USER;
+        if (write)
+                flags |= FAULT_FLAG_WRITE;
+
         /*
          * If for any reason at all we couldn't handle the fault,
          * make sure we exit gracefully rather than endlessly redo
@@ -383,6 +387,7 @@ static void force_user_fault(unsigned long address, int write)
         struct vm_area_struct *vma;
         struct task_struct *tsk = current;
         struct mm_struct *mm = tsk->mm;
+        unsigned int flags = FAULT_FLAG_USER;
         int code;
 
         code = SEGV_MAPERR;
@@ -402,11 +407,12 @@ good_area:
         if (write) {
                 if (!(vma->vm_flags & VM_WRITE))
                         goto bad_area;
+                flags |= FAULT_FLAG_WRITE;
         } else {
                 if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
                         goto bad_area;
         }
-        switch (handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0)) {
+        switch (handle_mm_fault(mm, vma, address, flags)) {
         case VM_FAULT_SIGBUS:
         case VM_FAULT_OOM:
                 goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 5062ff389e83..2ebec263d685 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -315,7 +315,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
                         bad_kernel_pc(regs, address);
                         return;
                 }
-        }
+        } else
+                flags |= FAULT_FLAG_USER;
 
         /*
          * If we're in an interrupt or have no user
@@ -418,13 +419,14 @@ good_area:
                     vma->vm_file != NULL)
                         set_thread_fault_code(fault_code |
                                               FAULT_CODE_BLKCOMMIT);
+
+                flags |= FAULT_FLAG_WRITE;
         } else {
                 /* Allow reads even for write-only mappings */
                 if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
                         goto bad_area;
         }
 
-        flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
         fault = handle_mm_fault(mm, vma, address, flags);
 
         if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))