Messages in this thread |  | | | Subject | Re: [RFC 0/6] uprobes: kill uprobes_srcu/uprobe_srcu_id | | From | Peter Zijlstra <> | | Date | Mon, 16 Apr 2012 12:16:59 +0200 |
| |
On Mon, 2012-04-16 at 01:44 +0200, Oleg Nesterov wrote:
> No. Please note that if is_swbp_at_addr_fast() sets is_swbp == 0 we > restart this insn.
Ah, see I was missing something.. Hmm ok, let me think about this a little more though.. but at least I think I'm now (finally!) seeing what you propose.
> And. I have another reason for down_write() in register/unregister. > I am still not sure this is possible (I had no time to try to > implement), but it seems to me we can kill the uprobe counter in > mm_struct.
You mean by making register/unregister down_write, you're exclusive with munmap() and thus we can rely on is_swbp_at_addr_fast() to inspect the address to see if there's a breakpoint or not and avoid the rest of the work that way?
|  |