public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Thomas Garnier <thgarnie@google.com>
To: "Herbert Xu" <herbert@gondor.apana.org.au>,
	"David S . Miller" <davem@davemloft.net>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Ingo Molnar" <mingo@redhat.com>,
	"H . Peter Anvin" <hpa@zytor.com>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Josh Poimboeuf" <jpoimboe@redhat.com>,
	"Thomas Garnier" <thgarnie@google.com>,
	"Arnd Bergmann" <arnd@arndb.de>,
	"Matthias Kaehlcke" <mka@chromium.org>,
	"Boris Ostrovsky" <boris.ostrovsky@oracle.com>,
	"Juergen Gross" <jgross@suse.com>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Radim Krčmář" <rkrcmar@redhat.com>,
	"Joerg Roedel" <joro@8bytes.org>,
	"Andy Lutomirski" <luto@kernel.org>,
	"Borislav Petkov" <bp@alien8.de>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	"Brian Gerst" <brgerst@gmail.com>, "Borislav Petkov" <bp@suse.de>,
	"Christian Borntraeger" <borntraeger@de.ibm.com>,
	"Rafael J . Wysocki" <rjw@rjwysocki.net>
Cc: linux-arch@vger.kernel.org, kvm@vger.kernel.org,
	linux-pm@vger.kernel.org, x86@kernel.org,
	linux-kernel@vger.kernel.org, linux-sparse@vger.kernel.org,
	linux-crypto@vger.kernel.org,
	kernel-hardening@lists.openwall.com,
	xen-devel@lists.xenproject.org
Subject: [RFC 19/22] x86/pie: Add option to build the kernel as PIE for x86_64
Date: Tue, 18 Jul 2017 15:33:30 -0700	[thread overview]
Message-ID: <20170718223333.110371-20-thgarnie@google.com> (raw)
In-Reply-To: <20170718223333.110371-1-thgarnie@google.com>

Add the CONFIG_X86_PIE option which builds the kernel as a Position
Independent Executable (PIE). The kernel is currently build with the
mcmodel=kernel option which forces it to stay on the top 2G of the
virtual address space. With PIE, the kernel will be able to move below
the -2G limit increasing the KASLR range from 1GB to 3GB.

The modules do not support PIE due to how they are linked. Disable PIE
for them and default to mcmodel=kernel for now.

The PIE configuration is not yet compatible with XEN_PVH. Xen PVH
generates 32-bit assembly and uses a long jump to transition to 64-bit.
A long jump require an absolute reference that is not compatible with
PIE.

Performance/Size impact:

Hackbench (50% and 1600% loads):
 - PIE disabled: no significant change (-0.50% / +0.50%)
 - PIE enabled: 7% to 8% on half load, 10% on heavy load.

These results are aligned with the different research on user-mode PIE
impact on cpu intensive benchmarks (around 10% on x86_64).

slab_test (average of 10 runs):
 - PIE disabled: no significant change (-1% / +1%)
 - PIE enabled: 3% to 4%

Kernbench (average of 10 Half and Optimal runs):
 Elapsed Time:
 - PIE disabled: no significant change (-0.22% / +0.06%)
 - PIE enabled: around 0.50%
 System Time:
 - PIE disabled: no significant change (-0.99% / -1.28%)
 - PIE enabled: 5% to 6%

Size of vmlinux (Ubuntu configuration):
 File size:
 - PIE disabled: 472928672 bytes (-0.000169% from baseline)
 - PIE enabled: 216878461 bytes (-54.14% from baseline)
 .text sections:
 - PIE disabled: 9373572 bytes (+0.04% from baseline)
 - PIE enabled: 9499138 bytes (+1.38% from baseline)

The big decrease in vmlinux file size is due to the lower number of
relocations appended to the file.

Signed-off-by: Thomas Garnier <thgarnie@google.com>
---
 arch/x86/Kconfig  | 6 ++++++
 arch/x86/Makefile | 9 +++++++++
 2 files changed, 15 insertions(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 781521b7cf9e..b26ee6751021 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2080,6 +2080,12 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING
 
 	   If unsure, leave at the default value.
 
+config X86_PIE
+	bool
+	depends on X86_64 && !XEN_PVH
+	select DEFAULT_HIDDEN
+	select MODULE_REL_CRCS if MODVERSIONS
+
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
 	depends on SMP
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 1e902f926be3..452a9621af8f 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -45,8 +45,12 @@ export REALMODE_CFLAGS
 export BITS
 
 ifdef CONFIG_X86_NEED_RELOCS
+ifdef CONFIG_X86_PIE
+        LDFLAGS_vmlinux := -pie -shared -Bsymbolic
+else
         LDFLAGS_vmlinux := --emit-relocs
 endif
+endif
 
 #
 # Prevent GCC from generating any FP code by mistake.
@@ -132,7 +136,12 @@ else
         KBUILD_CFLAGS += $(cflags-y)
 
         KBUILD_CFLAGS += -mno-red-zone
+ifdef CONFIG_X86_PIE
+        KBUILD_CFLAGS += -fPIC
+        KBUILD_CFLAGS_MODULE += -fno-PIC -mcmodel=kernel
+else
         KBUILD_CFLAGS += -mcmodel=kernel
+endif
 
         # -funit-at-a-time shrinks the kernel .text considerably
         # unfortunately it makes reading oopses harder.
-- 
2.13.2.932.g7449e964c-goog


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

  parent reply	other threads:[~2017-07-18 22:33 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-07-18 22:33 x86: PIE support and option to extend KASLR randomization Thomas Garnier
2017-07-18 22:33 ` [RFC 01/22] x86/crypto: Adapt assembly for PIE support Thomas Garnier
2017-07-18 22:33 ` [RFC 02/22] x86: Use symbol name on bug table " Thomas Garnier
2017-07-18 22:33 ` [RFC 03/22] x86: Use symbol name in jump " Thomas Garnier
2017-07-18 22:33 ` [RFC 04/22] x86: Add macro to get symbol address " Thomas Garnier
2017-07-18 22:33 ` [RFC 05/22] xen: Adapt assembly " Thomas Garnier
2017-07-18 22:33 ` [RFC 06/22] kvm: " Thomas Garnier
2017-07-19  2:49   ` Brian Gerst
2017-07-19 15:40     ` Thomas Garnier
2017-07-19 22:27       ` H. Peter Anvin
2017-07-19 22:44         ` Thomas Garnier
2017-07-19 22:58         ` Ard Biesheuvel
2017-07-19 23:47           ` H. Peter Anvin
2017-07-18 22:33 ` [RFC 07/22] x86: relocate_kernel - " Thomas Garnier
2017-07-19 22:58   ` H. Peter Anvin
2017-07-19 23:23     ` Thomas Garnier
2017-07-18 22:33 ` [RFC 08/22] x86/entry/64: " Thomas Garnier
2017-07-18 22:33 ` [RFC 09/22] x86: pm-trace - " Thomas Garnier
2017-07-18 22:33 ` [RFC 10/22] x86/CPU: " Thomas Garnier
2017-07-18 22:33 ` [RFC 11/22] x86/acpi: " Thomas Garnier
2017-07-18 22:33 ` [RFC 12/22] x86/boot/64: " Thomas Garnier
2017-07-18 22:33 ` [RFC 13/22] x86/power/64: " Thomas Garnier
2017-07-19 18:41   ` Pavel Machek
2017-07-18 22:33 ` [RFC 14/22] x86/paravirt: " Thomas Garnier
2017-07-18 22:33 ` [RFC 15/22] x86/boot/64: Use _text in a global " Thomas Garnier
2017-07-18 22:33 ` [RFC 16/22] x86/percpu: Adapt percpu " Thomas Garnier
2017-07-19  3:08   ` Brian Gerst
2017-07-19 18:26     ` Thomas Garnier
2017-07-19 23:33       ` H. Peter Anvin
2017-07-20  2:21         ` H. Peter Anvin
2017-07-20  3:03           ` H. Peter Anvin
2017-07-20 14:26         ` Thomas Garnier
2017-08-02 16:42           ` Thomas Garnier
2017-08-02 16:56             ` Kees Cook
2017-08-02 18:05               ` Thomas Garnier
2017-07-18 22:33 ` [RFC 17/22] compiler: Option to default to hidden symbols Thomas Garnier
2017-07-18 22:33 ` [RFC 18/22] x86/relocs: Handle DYN relocations for PIE support Thomas Garnier
2017-07-18 22:33 ` Thomas Garnier [this message]
2017-07-18 22:33 ` [RFC 20/22] x86/relocs: Add option to generate 64-bit relocations Thomas Garnier
2017-07-19 22:33   ` H. Peter Anvin
2017-07-19 22:47     ` Thomas Garnier
2017-07-19 23:08       ` H. Peter Anvin
2017-07-19 23:25         ` Thomas Garnier
2017-07-19 23:45           ` H. Peter Anvin
2017-07-18 22:33 ` [RFC 21/22] x86/module: Add support for mcmodel large and PLTs Thomas Garnier
2017-07-19  1:35   ` H. Peter Anvin
2017-07-19  3:59     ` Brian Gerst
2017-07-19 15:58       ` Thomas Garnier
2017-07-19 17:34         ` Brian Gerst
2017-07-24 16:32           ` Thomas Garnier
2017-07-18 22:33 ` [RFC 22/22] x86/kaslr: Add option to extend KASLR range from 1GB to 3GB Thomas Garnier
2017-07-19 12:10   ` Baoquan He
2017-07-19 13:49     ` Baoquan He
2017-07-19 14:08 ` x86: PIE support and option to extend KASLR randomization Christopher Lameter
2017-07-19 19:21   ` Kees Cook

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170718223333.110371-20-thgarnie@google.com \
    --to=thgarnie@google.com \
    --cc=arnd@arndb.de \
    --cc=boris.ostrovsky@oracle.com \
    --cc=borntraeger@de.ibm.com \
    --cc=bp@alien8.de \
    --cc=bp@suse.de \
    --cc=brgerst@gmail.com \
    --cc=davem@davemloft.net \
    --cc=herbert@gondor.apana.org.au \
    --cc=hpa@zytor.com \
    --cc=jgross@suse.com \
    --cc=joro@8bytes.org \
    --cc=jpoimboe@redhat.com \
    --cc=kernel-hardening@lists.openwall.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=linux-sparse@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=mka@chromium.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rjw@rjwysocki.net \
    --cc=rkrcmar@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    --cc=xen-devel@lists.xenproject.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox