Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <CAKwvOd=jmi_7LvZbS0PA5-zt62m5ZFPUNG7JtMQVmerCR63ebQ@mail.gmail.com>
 <BDEF22F0-84A5-4A36-B153-13E6A4260922@zytor.com> <CAKwvOdnLt5qr_5ah86qdsocTxUbo_3X1y3PPRp1EZwt=__NxnA@mail.gmail.com>
 <dd1626ae-114f-3817-c8b2-f845e079bfc6@zytor.com> <CAKwvOdkEHqv7Ut8H6Rb+gSvfWsMHqO=E3f7yxm=06m9yEn=h6w@mail.gmail.com>
 <26B017D5-4063-46CB-8768-B0E5E7CD3838@zytor.com> <CAKwvOdk_4g5PsRUoLgOeWEwt+d0diyD_Ycx6s7LQsJrSMsBEuA@mail.gmail.com>
 <319FB971-ABB6-4BE7-969B-D87D84853196@zytor.com> <CAKwvOdmryseROx=iSs6CZ86-tr90Fni8RC_w6Y7nFSXGW=508g@mail.gmail.com>
 <31A5469A-176F-451F-886A-ECD649DDC78C@zytor.com>
In-Reply-To: <31A5469A-176F-451F-886A-ECD649DDC78C@zytor.com>
From:   Nick Desaulniers <ndesaulniers@google.com>
Date:   Fri, 25 May 2018 10:31:51 -0700
Message-ID: <CAKwvOdkpWZC4vWK8hDdgUGseTmK4Hz5uDHn_mP9yc=jbfdVPmg@mail.gmail.com>
Subject: Re: [clang] stack protector and f1f029c7bf
To:     hpa@zytor.com
Cc:     Alistair Strachan <astrachan@google.com>,
        Manoj Gupta <manojgupta@google.com>,
        Matthias Kaehlcke <mka@google.com>,
        Greg Hackmann <ghackmann@google.com>, sedat.dilek@gmail.com,
        tstellar@redhat.com, LKML <linux-kernel@vger.kernel.org>,
        Kees Cook <keescook@google.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Fri, May 25, 2018 at 9:53 AM <hpa@zytor.com> wrote:
> On May 25, 2018 9:46:42 AM PDT, Nick Desaulniers <ndesaulniers@google.com>
wrote:
> >On Fri, May 25, 2018 at 9:33 AM <hpa@zytor.com> wrote:
> >> On May 25, 2018 9:27:40 AM PDT, Nick Desaulniers
> ><ndesaulniers@google.com> wrote:
> >When you say
> >
> >> It still should be available as as inline, however, but now "extern
> >inline".
> >
> >Am I understanding correctly that native_save_fl should be inlined into
> >all
> >call sites (modulo the problematic pv_irq_ops.save_fl case)?  Because
> >for
> >these two assembly implementations, it's not, but maybe there's
> >something
> >missing in my implementation?

> Yes, that's what "extern inline" means. Maybe it needs a must inline
annotation, but that's really messed up.

I don't think it's possible to inline a function from an external
translation unit without something like LTO.

If I move the implementation of native_save_fl() to a separate .c (with out
of line assembly) or .S, neither clang nor gcc will inline that assembly to
any call sites, whether the declaration of native_save_fl() looks like:

extern inline unsigned long native_save_fl(void);

or

__attribute__((always_inline))

extern inline unsigned long native_save_fl(void);

I think an external copy is the best approach for the paravirt code:

diff --git a/arch/x86/kernel/irqflags.c b/arch/x86/kernel/irqflags.c
new file mode 100644
index 000000000000..e173ba8bee7b
--- /dev/null
+++ b/arch/x86/kernel/irqflags.c
@@ -0,0 +1,24 @@
+#include <asm/asm.h>
+
+extern unsigned long native_save_fl_no_stack_protector(void);
+extern void native_restore_fl_no_stack_protector(unsigned long flags);
+
+asm(
+".pushsection .text;"
+".global native_save_fl_no_stack_protector;"
+".type native_save_fl_no_stack_protector, @function;"
+"native_save_fl_no_stack_protector:"
+"pushf;"
+"pop %" _ASM_AX ";"
+"ret;"
+".popsection");
+
+asm(
+".pushsection .text;"
+".global native_restore_fl_no_stack_protector;"
+".type native_restore_fl_no_stack_protector, @function;"
+"native_restore_fl_no_stack_protector:"
+"push %" _ASM_DI ";"
+"popf;"
+"ret;"
+".popsection");
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 02d6f5cf4e70..8824d01c0c35 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -61,6 +61,7 @@ obj-y                 += alternative.o i8253.o
hw_breakpoint.o
  obj-y                  += tsc.o tsc_msr.o io_delay.o rtc.o
  obj-y                  += pci-iommu_table.o
  obj-y                  += resource.o
+obj-y                  += irqflags.o

  obj-y                          += process.o
  obj-y                          += fpu/
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -322,9 +322,12 @@ struct pv_time_ops pv_time_ops = {
         .steal_clock = native_steal_clock,
  };

+extern unsigned long native_save_fl_no_stack_protector(void);
+extern void native_restore_fl_no_stack_protector(unsigned long flags);
+
  __visible struct pv_irq_ops pv_irq_ops = {
-       .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
-       .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
+       .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl_no_stack_protector),
+       .restore_fl =
__PV_IS_CALLEE_SAVE(native_restore_fl_no_stack_protector),
         .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
         .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
         .safe_halt = native_safe_halt,

Thoughts?
-- 
Thanks,
~Nick Desaulniers