Messages in this thread | | | Date | Wed, 25 Jul 2012 19:35:05 +0200 | From | Frederic Weisbecker <> | Subject | Re: [PATCH 03/17] perf, x86: Add copy_from_user_nmi_nochk for best effort copy |
| |
On Wed, Jul 25, 2012 at 07:30:31PM +0200, Jiri Olsa wrote: > On Wed, Jul 25, 2012 at 07:16:43PM +0200, Jiri Olsa wrote: > > On Wed, Jul 25, 2012 at 06:11:53PM +0200, Frederic Weisbecker wrote: > > > On Sun, Jul 22, 2012 at 02:14:26PM +0200, Jiri Olsa wrote: > > > > Adding copy_from_user_nmi_nochk that provides the best effort > > > > copy regardless the requesting size crossing the task boundary. > > > > > > > > This is going to be useful for stack dump we need in post > > > > DWARF CFI based unwind, where we have predefined size of > > > > the user stack to dump, and we need to store the most of > > > > the requested dump size, regardless this size is crossing > > > > the task boundary. > > > > > > What does that imply when we cross this limit? Are we still in the > > > task stack? > > > > We store all we could from 'stack pointer' to 'stack pointer' + dump size. > > > > I discussed this with Oleg and we could probably find vma for the 'stack pointer' > > and check for its size and narrow the dump - maybe more complex, but probably faster > > in comparison with dumping pages we're not interested in. > > > > thanks, > > jirka > > I can send this update later together with vdso > and 'syscall regs storage' features ;)
Sure! As long as we are fine with the kernel ABI, the rest can be done incrementally.
| |