powerpc: Fix possible deadlock on page fault

 stack_grow_into/14082 is trying to acquire lock:
  (&mm->mmap_sem){++++++}, at: [<c000000000206d28>] .might_fault+0x78/0xe0

 but task is already holding lock:
  (&mm->mmap_sem){++++++}, at: [<c0000000007ffd8c>] .do_page_fault+0x24c/0x910

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock(&mm->mmap_sem);
   lock(&mm->mmap_sem);

  *** DEADLOCK ***

  May be due to missing lock nesting notation

 1 lock held by stack_grow_into/14082:
  #0:  (&mm->mmap_sem){++++++}, at: [<c0000000007ffd8c>] .do_page_fault+0x24c/0x910

 stack backtrace:
 CPU: 21 PID: 14082 Comm: stack_grow_into Not tainted 3.10.0-10.el7.ppc64.debug #1
 Call Trace:
 [c0000003d396b850] [c000000000016e7c] .show_stack+0x7c/0x1f0 (unreliable)
 [c0000003d396b920] [c000000000813fc8] .dump_stack+0x28/0x3c
 [c0000003d396b990] [c000000000124b90] .__lock_acquire+0x1640/0x1800
 [c0000003d396bab0] [c00000000012570c] .lock_acquire+0xac/0x250
 [c0000003d396bb80] [c000000000206d54] .might_fault+0xa4/0xe0
 [c0000003d396bbf0] [c0000000007ffe2c] .do_page_fault+0x2ec/0x910
 [c0000003d396be30] [c0000000000092e8] handle_page_fault+0x10/0x30

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 76d8e7c..2dd69bf 100644 (file)
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -206,7 +206,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
        int trap = TRAP(regs);
        int is_exec = trap == 0x400;
        int fault;
-       int rc = 0;
+       int rc = 0, store_update_sp = 0;
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
        /*
@@ -280,6 +280,14 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 
        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
+       /*
+        * We want to do this outside mmap_sem, because reading code around nip
+        * can result in fault, which will cause a deadlock when called with
+        * mmap_sem held
+        */
+       if (user_mode(regs))
+               store_update_sp = store_updates_sp(regs);
+
        /* When running in the kernel we expect faults to occur only to
         * addresses in user space.  All other faults represent errors in the
         * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -345,8 +353,7 @@ retry:
                 * between the last mapped region and the stack will
                 * expand the stack rather than segfaulting.
                 */
-               if (address + 2048 < uregs->gpr[1]
-                   && (!user_mode(regs) || !store_updates_sp(regs)))
+               if (address + 2048 < uregs->gpr[1] && !store_update_sp)
                        goto bad_area;
        }
        if (expand_stack(vma, address))