On Sat, Oct 22, 2005 at 05:19:30PM +0100, Hugh Dickins wrote: > The sh __do_page_fault: which handles both kernel faults (without lock) > and user mm faults (locked - though it set_pte without locking before). > > The sh64 flush_cache_range and helpers: which wrongly thought callers > held page_table_lock before (only its tlb_start_vma did, and no longer > does so); moved the flush loop down, and adjusted the large versus small > range decision to consider a range which spans page tables as large. > > Signed-off-by: Hugh Dickins <[email protected]> Yes, that was very clearly broken, thanks for noting this. I won't be able to test the sh64 bits until later this week, but both of these changes look good to me. I'll take care of cleaning up any breakage this introduces, thanks Hugh. Acked-by: Paul Mundt <[email protected]>
Attachment:
pgpNFONHEOgw9.pgp
Description: PGP signature
- References:
- [PATCH 0/9] mm: page fault scalability
- From: Hugh Dickins <[email protected]>
- [PATCH 1/9] mm: i386 sh sh64 ready for split ptlock
- From: Hugh Dickins <[email protected]>
- [PATCH 0/9] mm: page fault scalability
- Prev by Date: Re: ioctls, etc. (was Re: [PATCH 1/4] sas: add flag for locally attachedPHYs)
- Next by Date: Re: spitz (zaurus sl-c3000) support
- Previous by thread: [PATCH 1/9] mm: i386 sh sh64 ready for split ptlock
- Next by thread: [PATCH 2/9] mm: arm ready for split ptlock
- Index(es):
 |