2.3.40 blows away on shm swap test

[Manfred Spraul]

From: "Christoph Rohland" <hans-christoph.rohland en sap.com>
> Code;  c0114d64 <flush_tlb_all_ipi+18/58>   <=====
>    0:   8b 52 0c                  movl   0xc(%edx),%edx   <=====
> Code;  c0114d67 <flush_tlb_all_ipi+1b/58>
>    3:   81 c2 00 00 00 40         addl   $0x40000000,%edx

That's Ingo's new __flush_tlb_all() optimization:
he tries to avoid loading from %%cr3 by loading the information from
current->active_mm->pgd.

Ingo, could you undo that change?
current->active_mm may be NULL in the middle of a task switch [between
mmdrop() and switch_to() in schedule()]

--
    Manfred


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo en vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/