[PATCH v2 1/9] powerpc/64s: fix hash page fault interrupt handler

[Nicholas Piggin]

The early bad fault or key fault test in do_hash_fault() ends up calling
into ___do_page_fault without having gone through an interrupt handler
wrapper (except the initial _RAW one). This can end up calling local irq
functions while the interrupt has not been reconciled, which will likely
cause crashes and it trips up on a later patch that adds more assertions.

pkey_exec_prot from selftests causes this path to be executed.

There is no real reason to run the in_nmi() test should be performed
before the key fault check. In fact if a perf interrupt in the hash
fault code did a stack walk that was made to take a key fault somehow
then running ___do_page_fault could possibly cause another hash fault
causing problems. Move the in_nmi() test first, and then do everything
else inside the regular interrupt handler function.

Fixes: 3a96570ffceb ("powerpc: convert interrupt handlers to use wrappers")
Reported-by: Sachin Sant <sach...@linux.vnet.ibm.com>
Tested-by: Sachin Sant <sach...@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npig...@gmail.com>
---
 arch/powerpc/mm/book3s64/hash_utils.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/arch/powerpc/mm/book3s64/hash_utils.c 
b/arch/powerpc/mm/book3s64/hash_utils.c
index 96d9aa164007..ac5720371c0d 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1522,8 +1522,8 @@ int hash_page(unsigned long ea, unsigned long access, 
unsigned long trap,
 }
 EXPORT_SYMBOL_GPL(hash_page);
 
-DECLARE_INTERRUPT_HANDLER_RET(__do_hash_fault);
-DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
+DECLARE_INTERRUPT_HANDLER(__do_hash_fault);
+DEFINE_INTERRUPT_HANDLER(__do_hash_fault)
 {
        unsigned long ea = regs->dar;
        unsigned long dsisr = regs->dsisr;
@@ -1533,6 +1533,11 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
        unsigned int region_id;
        long err;
 
+       if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_KEYFAULT))) {
+               hash__do_page_fault(regs);
+               return;
+       }
+
        region_id = get_region_id(ea);
        if ((region_id == VMALLOC_REGION_ID) || (region_id == IO_REGION_ID))
                mm = &init_mm;
@@ -1571,9 +1576,10 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
                        bad_page_fault(regs, SIGBUS);
                }
                err = 0;
-       }
 
-       return err;
+       } else if (err) {
+               hash__do_page_fault(regs);
+       }
 }
 
 /*
@@ -1582,13 +1588,6 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
  */
 DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
 {
-       unsigned long dsisr = regs->dsisr;
-
-       if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_KEYFAULT))) {
-               hash__do_page_fault(regs);
-               return 0;
-       }
-
        /*
         * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
         * don't call hash_page, just fail the fault. This is required to
@@ -1607,8 +1606,7 @@ DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
                return 0;
        }
 
-       if (__do_hash_fault(regs))
-               hash__do_page_fault(regs);
+       __do_hash_fault(regs);
 
        return 0;
 }
-- 
2.23.0