<cmetc...@mellanox.com>,Andrew Morton <a...@linux-foundation.org>,"Paul E . McKenney" <paul...@linux.vnet.ibm.com>,Nicolas Pitre <nicolas.pi...@linaro.org>,Christopher Li <spa...@chrisli.org>,"Rafael J . Wysocki" <rafael.j.wyso...@intel.com>,Lukas Wunner <lu...@wunner.de>,Mika Westerberg <mika.westerb...@linux.intel.com>,Dou Liyang <douly.f...@cn.fujitsu.com>,Daniel Borkmann <dan...@iogearbox.net>,Alexei Starovoitov <a...@kernel.org>,Masahiro Yamada <yamada.masah...@socionext.com>,Markus Trippelsdorf <mar...@trippelsdorf.de>,Steven Rostedt <rost...@goodmis.org>,Rik van Riel <r...@redhat.com>,David Howells <dhowe...@redhat.com>,Waiman Long <long...@redhat.com>,Kyle Huey <m...@kylehuey.com>,Peter Foley <pefol...@pefoley.com>,Tim Chen <tim.c.c...@linux.intel.com>,Catalin Marinas <catalin.mari...@arm.com>,Ard Biesheuvel <ard.biesheu...@linaro.org>,Michal Hocko <mho...@suse.com>,Matthew Wilcox <mawil...@microsoft.com>,Paul Bolle <pebo...@tiscali.nl>,Rob Landley <r...@landley.net>,Baoquan He <b...@redhat.com>,Daniel Micay <danielmi...@gmail.com>,the arch/x86 maintainers <x...@kernel.org>,Linux Crypto Mailing List <linux-cry...@vger.kernel.org>,LKML <linux-ker...@vger.kernel.org>,xen-devel <xen-de...@lists.xenproject.org>,kvm list <k...@vger.kernel.org>,Linux PM list <linux...@vger.kernel.org>,linux-arch <linux-a...@vger.kernel.org>,Sparse Mailing-list <linux-spa...@vger.kernel.org>,Kernel Hardening <kernel-harden...@lists.openwall.com>,Linus Torvalds <torva...@linux-foundation.org>,Peter Zijlstra <a.p.zijls...@chello.nl>,Borislav Petkov <b...@alien8.de> From: "H.J. Lu" <hjl.to...@gmail.com> Message-ID: <cffa3e3a-3136-4faf-80e1-96a515a5c...@gmail.com>
On September 23, 2017 3:06:16 AM GMT+08:00, "H. Peter Anvin" <h...@zytor.com> wrote: >On 09/22/17 11:57, Kees Cook wrote: >> On Fri, Sep 22, 2017 at 11:38 AM, H. Peter Anvin <h...@zytor.com> >wrote: >>> We lose EBX on 32 bits, but we don't lose RBX on 64 bits - since >x86-64 >>> has RIP-relative addressing there is no need for a dedicated PIC >register. >> >> FWIW, since gcc 5, the PIC register isn't totally lost. It is now >> reusable, and that seems to have improved performance: >> https://gcc.gnu.org/gcc-5/changes.html > >It still talks about a PIC register on x86-64, which confuses me. >Perhaps older gcc's would allocate a PIC register under certain >circumstances, and then lose it for the entire function? > >For i386, the PIC register is required by the ABI to be %ebx at the >point any PLT entry is called. Not an issue with -mno-plt which goes >straight to the GOT, although in most cases there needs to be a PIC >register to find the GOT unless load-time relocation is permitted. > > -hpa We need a static PIE option so that compiler can optimize it without using hidden visibility. -- Sent from my Android device with K-9 Mail. Please excuse my brevity. _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel
