From: Zachary Amsden Subject: [PATCH 3/6] IOPL handling for paravirt guests Date: Thu, 14 Dec 2006 22:52:09 -0800 Message-ID: <200612150652.kBF6q9e0025520@zach-dev.vmware.com> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Return-path: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: virtualization-bounces@lists.osdl.org Errors-To: virtualization-bounces@lists.osdl.org To: Andrew Morton , Linus Torvalds , Linux Kernel Mailing List , Andi Kleen , Virtualization Mailing List , Zachary Amsden List-Id: virtualization@lists.linuxfoundation.org I found a clever way to make the extra IOPL switching invisible to non-paravirt compiles - since kernel_rpl is statically defined to be zero there, and only non-zero rpl kernel have a problem restoring IOPL, as popf does not restore IOPL flags unless run at CPL-0. Subject: IOPL handling for paravirt guests Signed-off-by: Zachary Amsden diff -r 8110943fd7ad arch/i386/kernel/process.c --- a/arch/i386/kernel/process.c Thu Dec 14 16:15:20 2006 -0800 +++ b/arch/i386/kernel/process.c Thu Dec 14 16:21:57 2006 -0800 @@ -665,6 +665,15 @@ struct task_struct fastcall * __switch_t load_TLS(next, cpu); = /* + * Restore IOPL if needed. In normal use, the flags restore + * in the switch assembly will handle this. But if the kernel + * is running virtualized at a non-zero CPL, the popf will + * not restore flags, so it must be done in a separate step. + */ + if (get_kernel_rpl() && unlikely(prev->iopl !=3D next->iopl)) + set_iopl_mask(next->iopl); + + /* * Now maybe handle debug registers and/or IO bitmaps */ if (unlikely((task_thread_info(next_p)->flags & _TIF_WORK_CTXSW)