powerpc/fsl-booke: Fix problem with _tlbil_va being interrupted
PATCH 1/1 powerpc/fsl-booke: Fix problem with _tlbil_va being interrupted
An example calling sequence which we did see:
copy_user_highpage -> kmap_atomic -> flush_tlb_page -> _tlbil_va
We got interrupted after setting up the MAS registers before the tlbwe and the interrupt handler that caused the interrupt also did a kmap_atomic (ide code) and thus on returning from the interrupt the MAS registers no longer contained the proper values.
Since we dont save/restore MAS registers for normal interrupts we need to disable interrupts in _tlbil_va to ensure atomicity.
--- arch/powerpc/kernel/misc_32.S | 3 +++ 1 files changed, 3 insertions(+), 0 deletions(-)
arch/powerpc/kernel/misc_32.S +3 -0
@@ -479,6 +479,8 @@ _GLOBAL(_tlbil_pid) * (no broadcast) */ _GLOBAL(_tlbil_va) + mfmsr r10 + wrteei 0 slwi r4,r4,16 mtspr SPRN_MAS6,r4 /* assume AS=0 for now */ tlbsx 0,r3
@@ -490,6 +492,7 @@ _GLOBAL(_tlbil_va) tlbwe msync isync + wrtee r10 blr #endif /* CONFIG_FSL_BOOKE */
Signature · 1 line
1.5.6.5
Quoted 9 lines · Kumar Gala
An example calling sequence which we did see:
copy_user_highpage->kmap_atomic->flush_tlb_page->_tlbil_vaWe got interrupted after setting up the MAS registers before the tlbwe and the interrupt handler that caused the interrupt also did a
kmap_atomic(ide code) and thus on returning from the interrupt the MAS registers no longer contained the proper values.
Quoted 4 lines
Since we dont save/restore MAS registers for normal interrupts we need to disable interrupts in
_tlbil_vato ensure atomicity.Signed-off-by Kumar Gala <[email protected]>
---
Paul, this is a 2.6.28 regression, it should probably go to Linus in case he hasn't released yet :-)
Cheers,
Ben.