powerpc/64: Initialise thread_info for emergency stacks

Emergency stacks have their thread_info mostly uninitialised, which in
particular means garbage preempt_count values.

Emergency stack code runs with interrupts disabled entirely, and is
used very rarely, so this has been unnoticed so far. It was found by a
proposed new powerpc watchdog that takes a soft-NMI directly from the
masked_interrupt handler and using the emergency stack. That crashed
at BUG_ON(in_nmi()) in nmi_enter(). preempt_count()s were found to be
garbage.

To fix this, zero the entire THREAD_SIZE allocation, and initialize
the thread_info.

Cc: stable@vger.kernel.org
Reported-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Move it all into setup_64.c, use a function not a macro. Fix
      crashes on Cell by setting preempt_count to 0 not HARDIRQ_OFFSET]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index a8c1f99e96072530cb1f2d9ed702dffd78665720..4640f6d64f8b406a636d60c4ea2263658dde5be6 100644 (file)
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -615,6 +615,24 @@ void __init exc_lvl_early_init(void)
 }
 #endif
 
+/*
+ * Emergency stacks are used for a range of things, from asynchronous
+ * NMIs (system reset, machine check) to synchronous, process context.
+ * We set preempt_count to zero, even though that isn't necessarily correct. To
+ * get the right value we'd need to copy it from the previous thread_info, but
+ * doing that might fault causing more problems.
+ * TODO: what to do with accounting?
+ */
+static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
+{
+       ti->task = NULL;
+       ti->cpu = cpu;
+       ti->preempt_count = 0;
+       ti->local_flags = 0;
+       ti->flags = 0;
+       klp_init_thread_info(ti);
+}
+
 /*
  * Stack space used when we detect a bad kernel stack pointer, and
  * early in SMP boots before relocation is enabled. Exclusive emergency
@@ -633,24 +651,31 @@ void __init emergency_stack_init(void)
         * Since we use these as temporary stacks during secondary CPU
         * bringup, we need to get at them in real mode. This means they
         * must also be within the RMO region.
+        *
+        * The IRQ stacks allocated elsewhere in this file are zeroed and
+        * initialized in kernel/irq.c. These are initialized here in order
+        * to have emergency stacks available as early as possible.
         */
        limit = min(safe_stack_limit(), ppc64_rma_size);
 
        for_each_possible_cpu(i) {
                struct thread_info *ti;
                ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-               klp_init_thread_info(ti);
+               memset(ti, 0, THREAD_SIZE);
+               emerg_stack_init_thread_info(ti, i);
                paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
                /* emergency stack for NMI exception handling. */
                ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-               klp_init_thread_info(ti);
+               memset(ti, 0, THREAD_SIZE);
+               emerg_stack_init_thread_info(ti, i);
                paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE;
 
                /* emergency stack for machine check exception handling. */
                ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-               klp_init_thread_info(ti);
+               memset(ti, 0, THREAD_SIZE);
+               emerg_stack_init_thread_info(ti, i);
                paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
 #endif
        }