Hello, On Sat, Jul 23, 2011 at 12:49:22PM +0400, Pavel Emelyanov wrote: > On 07/23/2011 12:37 PM, Tejun Heo wrote: > > Just use ptrace. Seizing all threads in a process, gather file and > > memory map info from /proc, inject a parasite to dump memory pages and > > do whatever else. There's nothing special about TLS, fs/gs base is > > already included in ptrace register dump in x86_64. Dunno how it's > > handled in 32bit but if it's not available exporting it isn't a big > > deal. Rebuilding the process image from the captured information > > shouldn't be too hard. > > You're talking about your recent set for ptrace? Can you propose a > quick scratch of how you propose to dump and restore registers and > memory with this? Hmmm... I thought I just did that writing the above paragraph, so even without the parasite treak, ptrace has access to full memory space and registers of the tracee, so the basic stuff is already dumpable && restorable - at its simplest, dumper can PEEKDATA for each mapped memory area (as indicated by /proc/PID/maps), use GETREGS and GETFPREGS to acquire register states, save them. To restore, launch a process, attach to it, let it mmap all the recorded areas and fill it from the saved data and SETREGS/SETFPREGS to restore the register states and let go. This of course is over-simplified but this should work. There are some missing things like finding out which signals are pending and with what siginfo but those can be solved with small additions to /proc. Thanks. -- tejun _______________________________________________ Containers mailing list Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linux-foundation.org/mailman/listinfo/containers
