virtualization.lists.linux-foundation.org archive mirror
 help / color / mirror / Atom feed
From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Andi Kleen <ak@muc.de>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org, virtualization@lists.osdl.org,
	xen-devel@lists.xensource.com, Chris Wright <chrisw@sous-sol.org>,
	Zachary Amsden <zach@vmware.com>,
	Rusty Russell <rusty@rustcorp.com.au>,
	Ian Pratt <ian.pratt@xensource.com>,
	Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Subject: [patch 17/26] Xen-paravirt_ops: Add nosegneg capability to the vsyscall page notes
Date: Tue, 27 Feb 2007 00:13:54 -0800	[thread overview]
Message-ID: <20070227081635.765724334@goop.org> (raw)
In-Reply-To: 20070227081337.434798469@goop.org

[-- Attachment #1: xen-vsyscall-note.patch --]
[-- Type: text/plain, Size: 2113 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>
Acked-by: Zachary Amsden <zach@vmware.com>

---
 arch/i386/kernel/vsyscall-note.S |   28 ++++++++++++++++++++++++++++
 1 file 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:[~2007-02-27  8:13 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-02-27  8:13 [patch 00/26] Xen-paravirt_ops: Xen guest implementation for paravirt_ops interface Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 01/26] Xen-paravirt_ops: Fix typo in sync_constant_test_bit()s name Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 02/26] Xen-paravirt_ops: ignore vgacon if hardware not present Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 03/26] Xen-paravirt_ops: use paravirt_nop to consistently mark no-op operations Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 04/26] Xen-paravirt_ops: Add pagetable accessors to pack and unpack pagetable entries Jeremy Fitzhardinge
2007-02-27 10:08   ` Ingo Molnar
2007-02-27 18:52     ` Jeremy Fitzhardinge
2007-02-28  8:32       ` Ingo Molnar
2007-02-28 20:12         ` Jeremy Fitzhardinge
2007-02-28 21:02         ` Rusty Russell
2007-02-27  8:13 ` [patch 05/26] Xen-paravirt_ops: paravirt_ops: hooks to set up initial pagetable Jeremy Fitzhardinge
2007-02-27 10:09   ` Ingo Molnar
2007-02-27 18:53     ` Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 06/26] Xen-paravirt_ops: paravirt_ops: allocate a fixmap slot Jeremy Fitzhardinge
2007-02-27 10:11   ` Ingo Molnar
2007-02-27 18:55     ` Jeremy Fitzhardinge
2007-02-28  0:49       ` Jeremy Fitzhardinge
2007-02-28  8:30         ` Ingo Molnar
2007-02-28 20:09           ` Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 07/26] Xen-paravirt_ops: Allow paravirt backend to choose kernel PMD sharing Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 08/26] Xen-paravirt_ops: add hooks to intercept mm creation and destruction Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 09/26] Xen-paravirt_ops: remove HAVE_ARCH_MM_LIFETIME, define no-op architecture implementations Jeremy Fitzhardinge
2007-02-27 15:15   ` James Bottomley
2007-02-27 17:21     ` Jeremy Fitzhardinge
2007-02-27 17:35       ` James Bottomley
2007-02-27 17:56         ` Jeremy Fitzhardinge
2007-02-27 18:04           ` James Bottomley
2007-02-27 18:48             ` Jeremy Fitzhardinge
2007-02-27 18:53               ` James Bottomley
2007-02-27  8:13 ` [patch 10/26] Xen-paravirt_ops: rename struct paravirt_patch to paravirt_patch_site for clarity Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 11/26] Xen-paravirt_ops: Use patch site IDs computed from offset in paravirt_ops structure Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 12/26] Xen-paravirt_ops: Fix patch site clobbers to include return register Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 13/26] Xen-paravirt_ops: Consistently wrap paravirt ops callsites to make them patchable Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 14/26] Xen-paravirt_ops: add common patching machinery Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 15/26] Xen-paravirt_ops: Add apply_to_page_range() which applies a function to a pte range Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 16/26] Xen-paravirt_ops: Allocate and free vmalloc areas Jeremy Fitzhardinge
2007-02-27  8:13 ` Jeremy Fitzhardinge [this message]
2007-02-27  8:13 ` [patch 18/26] Xen-paravirt_ops: Add XEN config options Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 19/26] Xen-paravirt_ops: Add Xen interface header files Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 20/26] Xen-paravirt_ops: Core Xen implementation Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 21/26] Xen-paravirt_ops: Use the hvc console infrastructure for Xen console Jeremy Fitzhardinge
2007-02-27  8:13 ` [patch 22/26] Xen-paravirt_ops: Add early printk support via hvc console Jeremy Fitzhardinge
2007-02-27  8:14 ` [patch 23/26] Xen-paravirt_ops: Add Xen grant table support Jeremy Fitzhardinge
2007-02-27  8:14 ` [patch 24/26] Xen-paravirt_ops: Add the Xenbus sysfs and virtual device hotplug driver Jeremy Fitzhardinge
2007-02-27  8:14 ` [patch 25/26] Xen-paravirt_ops: Add Xen virtual block device driver Jeremy Fitzhardinge
2007-02-27  8:14 ` [patch 26/26] Xen-paravirt_ops: Add the Xen virtual network " Jeremy Fitzhardinge
  -- strict thread matches above, loose matches on Subject: below --
2007-03-01 23:24 [patch 00/26] Xen-paravirt_ops: Xen guest implementation for paravirt_ops interface Jeremy Fitzhardinge
2007-03-01 23:25 ` [patch 17/26] Xen-paravirt_ops: Add nosegneg capability to the vsyscall page notes Jeremy Fitzhardinge
2007-03-16  9:15   ` Ingo Molnar
2007-03-16 21:26     ` Roland McGrath
2007-03-16 21:56       ` Jeremy Fitzhardinge
2007-03-16 22:20         ` Roland McGrath

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=20070227081635.765724334@goop.org \
    --to=jeremy@goop.org \
    --cc=Christian.Limpach@cl.cam.ac.uk \
    --cc=ak@muc.de \
    --cc=akpm@linux-foundation.org \
    --cc=chrisw@sous-sol.org \
    --cc=ian.pratt@xensource.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rusty@rustcorp.com.au \
    --cc=virtualization@lists.osdl.org \
    --cc=xen-devel@lists.xensource.com \
    --cc=zach@vmware.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).