On Wed, Mar 28, 2018 at 04:33:26PM +0200, Mark Wielaard wrote:
> On Tue, 2018-03-20 at 23:32 +0100, Mark Wielaard wrote:
> > On Sun, Mar 18, 2018 at 01:43:23AM +0100, Mark Wielaard wrote:
> > > If possible use process_vm_readv to read 4K blocks instead of fetching
> > > each word individually with
On Tue, 2018-03-20 at 23:32 +0100, Mark Wielaard wrote:
> On Sun, Mar 18, 2018 at 01:43:23AM +0100, Mark Wielaard wrote:
> > If possible use process_vm_readv to read 4K blocks instead of fetching
> > each word individually with ptrace. For unwinding this often means we
> > only have to do one proce
On Wed, Mar 21, 2018 at 02:28:48AM +0300, Dmitry V. Levin wrote:
> On Sun, Mar 18, 2018 at 01:43:23AM +0100, Mark Wielaard wrote:
> > + /* Let the ptrace fallback deal with the corner case of the address
> > + possibly crossing a page boundery. */
> > + if ((addr & ((Dwarf_Addr)__LIBDWFL_REM
On Sun, Mar 18, 2018 at 01:43:23AM +0100, Mark Wielaard wrote:
[...]
> @@ -115,12 +116,80 @@ __libdwfl_ptrace_attach (pid_t tid, bool
> *tid_was_stoppedp)
>return true;
> }
>
> +#ifdef HAVE_PROCESS_VM_READV
> +static bool
> +read_cached_memory (struct __libdwfl_pid_arg *pid_arg,
> +
On Sun, Mar 18, 2018 at 01:43:23AM +0100, Mark Wielaard wrote:
> If possible use process_vm_readv to read 4K blocks instead of fetching
> each word individually with ptrace. For unwinding this often means we
> only have to do one process_vm_readv of the stack instead of dozens of
> ptrace calls. Th
