[RFC] [PATCH 3/7] Execution out of line (XOL)

[Jim Keniston]

On Thu, 2010-01-14 at 12:08 +0100, Peter Zijlstra wrote:
> On Mon, 2010-01-11 at 17:55 +0530, Srikar Dronamraju wrote:
> > Execution out of line (XOL)
> > 
> > Slot allocation mechanism for Execution Out of Line strategy in User
> > space breakpointing Inftrastructure. (XOL)
> > 
> > This patch provides slot allocation mechanism for execution out of
> > line strategy for use with user space breakpoint infrastructure.
> > This patch requires utrace support in kernel.
> > 
> > This patch provides five functions xol_get_insn_slot(),
> > xol_free_insn_slot(), xol_put_area(), xol_get_area() and
> > xol_validate_vaddr().
> > 
> > Current slot allocation mechanism:
> > 1. Allocate one dedicated slot per user breakpoint.
> > 2. If the allocated vma is completely used, expand current vma.
> > 3. If we cant expand the vma, allocate a new vma.
> 
> 
> Say what?
> 
> I see the text, but non of it makes any sense at all.
> 

Yeah, there's not a lot of context there.  I hope it will make more
sense if you read section 1.1 of Documentation/uprobes.txt (patch #6).
Or look at get_insn_slot() in kprobes, and understand that we're trying
to do something similar in uprobes, where the instruction copies have to
reside in the user address space of the probed process.

Jim