Fwd: [patch] x86: ptrace and core-dump extensions for xstate
Hui Zhu <teawater <at> gmail.com>
2010-02-02 05:59:01 GMT
I am not sure. Maybe we need do something around it after
linux-kernel support it.
---------- Forwarded message ----------
From: Suresh Siddha <suresh.b.siddha <at> intel.com>
Date: Tue, Feb 2, 2010 at 10:00
Subject: [patch] x86: ptrace and core-dump extensions for xstate
To: "H. Peter Anvin" <hpa <at> zytor.com>, Ingo Molnar <mingo <at> elte.hu>,
Thomas Gleixner <tglx <at> linutronix.de>, Roland McGrath
<roland <at> redhat.com>
Cc: LKML <linux-kernel <at> vger.kernel.org>, "Lu, Hongjiu"
<hongjiu.lu <at> intel.com>, "Lachner, Peter" <peter.lachner <at> intel.com>
Kernel ptrace, core dump extensions to support AVX state etc. This interface
(PTRACE_GETXSTATEREGS, PTRACE_SETXSTATEREGS, NT_X86_XSTATE) is designed to
support all the future state that gets supported using xsave/xrstor
Looking at the memory layout saved by "xsave", one can't say which state
is represented in the memory layout. This is because if a particular state is
in init state, in the xsave hdr it can be represented by bit '0'. And hence
we can't really say by the xsave header wether a state is in init state or
the state is not saved in the memory layout.
And hence the xsave memory layout available through the PTRACE_GETXSTATEREGS
and the core dump(NT_X86_XSTATE) uses SW usable bytes [464..511] to convey
what state is represented in the memory layout.