All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Andi Kleen <ak@muc.de>
Cc: Andrew Morton <akpm@osdl.org>,
	virtualization@lists.osdl.org, xen-devel@lists.xensource.com,
	Chris Wright <chrisw@sous-sol.org>,
	Ian Pratt <ian.pratt@xensource.com>,
	linux-kernel@vger.kernel.org
Subject: [patch 13/21] Xen-paravirt: Add nosegneg capability to the vsyscall page notes
Date: Tue, 13 Feb 2007 14:17:42 -0800	[thread overview]
Message-ID: <20070213221830.466651996@goop.org> (raw)
In-Reply-To: 20070213221729.772002682@goop.org

[-- Attachment #1: xen-vsyscall-note.patch --]
[-- Type: text/plain, Size: 2120 bytes --]

Add the "nosegneg" fake capabilty to the vsyscall page notes. This is
used by the runtime linker to select a glibc version which then
disables negative-offset accesses to the thread-local segment via
%gs. These accesses require emulation in Xen (because segments are
truncated to protect the hypervisor address space) and avoiding them
provides a measurable performance boost.

Signed-off-by: Ian Pratt <ian.pratt@xensource.com>
Signed-off-by: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
---
 arch/i386/kernel/vsyscall-note.S |   28 +++++++++++++++++++++++++++++
 1 files changed, 28 insertions(+)

===================================================================
--- a/arch/i386/kernel/vsyscall-note.S
+++ b/arch/i386/kernel/vsyscall-note.S
@@ -23,3 +24,31 @@ 3:	.balign 4;		/* pad out section */			 
 	ASM_ELF_NOTE_BEGIN(".note.kernel-version", "a", UTS_SYSNAME, 0)
 	.long LINUX_VERSION_CODE
 	ASM_ELF_NOTE_END
+
+#ifdef CONFIG_XEN
+/*
+ * Add a special note telling glibc's dynamic linker a fake hardware
+ * flavor that it will use to choose the search path for libraries in the
+ * same way it uses real hardware capabilities like "mmx".
+ * We supply "nosegneg" as the fake capability, to indicate that we
+ * do not like negative offsets in instructions using segment overrides,
+ * since we implement those inefficiently.  This makes it possible to
+ * install libraries optimized to avoid those access patterns in someplace
+ * like /lib/i686/tls/nosegneg.  Note that an /etc/ld.so.conf.d/file
+ * corresponding to the bits here is needed to make ldconfig work right.
+ * It should contain:
+ *	hwcap 0 nosegneg
+ * to match the mapping of bit to name that we give here.
+ */
+#define NOTE_KERNELCAP_BEGIN(ncaps, mask) \
+	ASM_ELF_NOTE_BEGIN(".note.kernelcap", "a", "GNU", 2) \
+	.long ncaps, mask
+#define NOTE_KERNELCAP(bit, name) \
+	.byte bit; .asciz name
+#define NOTE_KERNELCAP_END ASM_ELF_NOTE_END
+
+NOTE_KERNELCAP_BEGIN(1, 1)
+NOTE_KERNELCAP(1, "nosegneg")
+NOTE_KERNELCAP_END
+#endif
+

-- 

  parent reply	other threads:[~2007-02-13 22:17 UTC|newest]

Thread overview: 106+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-02-13 22:17 [patch 00/21] Xen-paravirt: Xen guest implementation for paravirt_ops interface Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 01/21] Xen-paravirt: Fix typo in sync_constant_test_bit()s name Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 02/21] Xen-paravirt: Handle a zero-sized VT console Jeremy Fitzhardinge
2007-02-14  9:24   ` Gerd Hoffmann
2007-02-14  9:24     ` Gerd Hoffmann
2007-02-13 22:17 ` [patch 03/21] Xen-paravirt: Add pagetable accessors to pack and unpack pagetable entries Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 04/21] Xen-paravirt: paravirt_ops: hooks to set up initial pagetable Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 05/21] Xen-paravirt: paravirt_ops: allocate a fixmap slot Jeremy Fitzhardinge
2007-02-14  1:23   ` Dan Hecht
2007-02-14  1:36     ` Jeremy Fitzhardinge
2007-02-14  1:36       ` Jeremy Fitzhardinge
2007-02-14  2:34       ` Dan Hecht
2007-02-14  8:43         ` Gerd Hoffmann
2007-02-14  8:37       ` [Xen-devel] " Jan Beulich
2007-02-14  8:37         ` Jan Beulich
2007-02-14  9:15         ` [Xen-devel] " Andi Kleen
2007-02-14  9:15           ` Andi Kleen
2007-02-13 22:17 ` [patch 06/21] Xen-paravirt: remove ctor for pgd cache Jeremy Fitzhardinge
2007-02-13 22:39   ` Zachary Amsden
2007-02-13 22:17 ` [patch 07/21] Xen-paravirt: Allow paravirt backend to choose kernel PMD sharing Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 08/21] Xen-paravirt: Allow paravirt backend to select PGD allocation alignment Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 09/21] Xen-paravirt: add hooks to intercept mm creation and destruction Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 10/21] Xen-paravirt: Name: dont export paravirt_ops structure, do individual functions Jeremy Fitzhardinge
2007-02-14  1:06   ` Zachary Amsden
2007-02-14  1:06     ` Zachary Amsden
2007-02-14  1:16     ` Jeremy Fitzhardinge
2007-02-14  1:16       ` Jeremy Fitzhardinge
2007-02-14  1:18       ` Zachary Amsden
2007-02-14  1:18         ` Zachary Amsden
2007-02-14  1:37         ` Jeremy Fitzhardinge
2007-02-14  1:37           ` Jeremy Fitzhardinge
2007-02-14  1:43           ` Zachary Amsden
2007-02-14  1:43             ` Zachary Amsden
2007-02-14  1:44             ` Jeremy Fitzhardinge
2007-02-14  1:44               ` Jeremy Fitzhardinge
2007-02-14  5:51     ` Rusty Russell
2007-02-14  5:51       ` Rusty Russell
2007-02-14 19:36     ` Christoph Hellwig
2007-02-13 22:17 ` [patch 11/21] Xen-paravirt: Add apply_to_page_range() which applies a function to a pte range Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 12/21] Xen-paravirt: Allocate and free vmalloc areas Jeremy Fitzhardinge
2007-02-13 22:17 ` Jeremy Fitzhardinge [this message]
2007-02-13 22:45   ` [patch 13/21] Xen-paravirt: Add nosegneg capability to the vsyscall page notes Zachary Amsden
2007-02-13 22:45     ` Zachary Amsden
2007-02-13 22:49     ` Jeremy Fitzhardinge
2007-02-13 22:49       ` Jeremy Fitzhardinge
2007-02-13 22:54       ` Zachary Amsden
2007-02-13 22:54         ` Zachary Amsden
2007-02-13 23:13         ` Jeremy Fitzhardinge
2007-02-13 23:13           ` Jeremy Fitzhardinge
2007-02-14  5:38     ` [Xen-devel] " Rusty Russell
2007-02-14  5:38       ` Rusty Russell
2007-02-13 22:17 ` [patch 14/21] Xen-paravirt: Add XEN config options and disable unsupported config options Jeremy Fitzhardinge
2007-02-13 22:53   ` Dan Hecht
2007-02-13 22:53     ` Dan Hecht
2007-02-13 23:29     ` Jeremy Fitzhardinge
2007-02-13 23:29       ` Jeremy Fitzhardinge
2007-02-13 23:58       ` [Xen-devel] " Zachary Amsden
2007-02-13 23:58         ` Zachary Amsden
2007-02-13 23:58       ` Dan Hecht
2007-02-13 22:17 ` [patch 15/21] Xen-paravirt: Add Xen interface header files Jeremy Fitzhardinge
2007-02-14 20:45   ` Eric W. Biederman
2007-02-14 20:45     ` Eric W. Biederman
2007-02-15  0:10     ` Jeremy Fitzhardinge
2007-02-15  0:10       ` Jeremy Fitzhardinge
2007-02-15 17:32       ` Christoph Hellwig
2007-02-13 22:17 ` [patch 16/21] Xen-paravirt: Add code into head.S to handle being booted by Xen Jeremy Fitzhardinge
2007-02-13 23:54   ` Andi Kleen
2007-02-14  0:39     ` Jeremy Fitzhardinge
2007-02-14  0:39       ` Jeremy Fitzhardinge
2007-02-14  8:56       ` [Xen-devel] " Jan Beulich
2007-02-14  8:56         ` Jan Beulich
2007-02-14 18:53     ` Jeremy Fitzhardinge
2007-02-14 18:53       ` Jeremy Fitzhardinge
2007-02-14 20:10       ` Eric W. Biederman
2007-02-14 20:10         ` Eric W. Biederman
2007-02-14 20:41         ` Jeremy Fitzhardinge
2007-02-14 20:41           ` Jeremy Fitzhardinge
2007-02-14 21:06           ` Eric W. Biederman
2007-02-14 21:06             ` Eric W. Biederman
2007-02-15  0:13             ` Jeremy Fitzhardinge
2007-02-15  0:13               ` Jeremy Fitzhardinge
2007-02-15  1:39               ` Eric W. Biederman
2007-02-15  1:39                 ` Eric W. Biederman
2007-02-15  1:52                 ` Jeremy Fitzhardinge
2007-02-15  1:52                   ` Jeremy Fitzhardinge
2007-02-15  2:18                   ` Eric W. Biederman
2007-02-15  2:18                     ` Eric W. Biederman
2007-02-15  2:23                     ` Jeremy Fitzhardinge
2007-02-15  2:23                       ` Jeremy Fitzhardinge
2007-02-15  2:41                       ` Eric W. Biederman
2007-02-15  2:41                         ` Eric W. Biederman
2007-02-14 20:33   ` Eric W. Biederman
2007-02-14 20:33     ` Eric W. Biederman
2007-02-14 20:42     ` Jeremy Fitzhardinge
2007-02-14 20:42       ` Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 17/21] Xen-paravirt: Add the Xen virtual console driver Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 18/21] Xen-paravirt: Add Xen grant table support Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 19/21] Xen-paravirt: Add the Xenbus sysfs and virtual device hotplug driver Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 20/21] Xen-paravirt: Add Xen virtual block device driver Jeremy Fitzhardinge
2007-02-13 22:17 ` [patch 21/21] Xen-paravirt: Add the Xen virtual network " Jeremy Fitzhardinge
2007-02-14 20:40   ` Eric W. Biederman
2007-02-14 20:40     ` Eric W. Biederman
2007-02-16  2:24 [patch 00/21] Xen-paravirt: Xen guest implementation for paravirt_ops interface Jeremy Fitzhardinge
2007-02-16  2:25 ` [patch 13/21] Xen-paravirt: Add nosegneg capability to the vsyscall page notes Jeremy Fitzhardinge
2007-02-16  2:25   ` Jeremy Fitzhardinge
2007-02-16  6:06   ` Zachary Amsden
2007-02-16  6:06     ` Zachary Amsden

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=20070213221830.466651996@goop.org \
    --to=jeremy@goop.org \
    --cc=ak@muc.de \
    --cc=akpm@osdl.org \
    --cc=chrisw@sous-sol.org \
    --cc=ian.pratt@xensource.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=virtualization@lists.osdl.org \
    --cc=xen-devel@lists.xensource.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.