Re: 2.3.40 blows away on shm swap test

From: Manfred Spraul (manfreds@colorfullife.com)
Date: Fri Jan 21 2000 - 20:19:51 EST


From: "Christoph Rohland" <hans-christoph.rohland@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@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Sun Jan 23 2000 - 21:00:26 EST