From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
To: akpm@linux-foundation.org, Ingo Molnar <mingo@elte.hu>,
linux-kernel@vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>,
Andi Kleen <ak@muc.de>, "H. Peter Anvin" <hpa@zytor.com>,
Chuck Ebbert <cebbert@redhat.com>,
Christoph Hellwig <hch@infradead.org>,
Jeremy Fitzhardinge <jeremy@goop.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
Rusty Russell <rusty@rustcorp.com.au>
Subject: [patch 16/26] Immediate Values - x86 Optimization
Date: Thu, 24 Jan 2008 15:27:22 -0500 [thread overview]
Message-ID: <20080124203339.058366192@polymtl.ca> (raw)
In-Reply-To: 20080124202706.250598537@polymtl.ca
[-- Attachment #1: immediate-values-x86-optimization.patch --]
[-- Type: text/plain, Size: 5092 bytes --]
x86 optimization of the immediate values which uses a movl with code patching
to set/unset the value used to populate the register used as variable source.
Changelog:
- Use text_poke_early with cr0 WP save/restore to patch the bypass. We are doing
non atomic writes to a code region only touched by us (nobody can execute it
since we are protected by the imv_mutex).
- Put imv_set and _imv_set in the architecture independent header.
- Use $0 instead of %2 with (0) operand.
- Add x86_64 support, ready for i386+x86_64 -> x86 merge.
- Use asm-x86/asm.h.
Ok, so the most flexible solution that I see, that should fit for both
x86 and x86_64 would be :
1 byte : "=q" : "a", "b", "c", or "d" register for the i386. For
x86-64 it is equivalent to "r" class (for 8-bit
instructions that do not use upper halves).
2, 4, 8 bytes : "=r" : A register operand is allowed provided that it is in a
general register.
- "Redux" immediate values : no need to put a breakpoint, therefore, no
need to know where the instruction starts. It's therefore OK to have a
REX prefix.
- Bugfix : 8 bytes 64 bits immediate value was declared as "4 bytes" in the
immediate structure.
- Change the immediate.c update code to support variable length opcodes.
- Vastly simplified, using a busy looping IPI with interrupts disabled.
Does not protect against NMI nor MCE.
- Pack the __imv section. Use smallest types required for size (char).
- Use imv_* instead of immediate_*.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
CC: Andi Kleen <ak@muc.de>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Chuck Ebbert <cebbert@redhat.com>
CC: Christoph Hellwig <hch@infradead.org>
CC: Jeremy Fitzhardinge <jeremy@goop.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Ingo Molnar <mingo@redhat.com>
CC: Rusty Russell <rusty@rustcorp.com.au>
---
arch/x86/Kconfig | 1
include/asm-x86/immediate.h | 77 ++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 78 insertions(+)
Index: linux-2.6-lttng.mm/include/asm-x86/immediate.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-2.6-lttng.mm/include/asm-x86/immediate.h 2008-01-24 14:30:09.000000000 -0500
@@ -0,0 +1,77 @@
+#ifndef _ASM_X86_IMMEDIATE_H
+#define _ASM_X86_IMMEDIATE_H
+
+/*
+ * Immediate values. x86 architecture optimizations.
+ *
+ * (C) Copyright 2006 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#include <asm/asm.h>
+
+/**
+ * imv_read - read immediate variable
+ * @name: immediate value name
+ *
+ * Reads the value of @name.
+ * Optimized version of the immediate.
+ * Do not use in __init and __exit functions. Use _imv_read() instead.
+ * If size is bigger than the architecture long size, fall back on a memory
+ * read.
+ *
+ * Make sure to populate the initial static 64 bits opcode with a value
+ * what will generate an instruction with 8 bytes immediate value (not the REX.W
+ * prefixed one that loads a sign extended 32 bits immediate value in a r64
+ * register).
+ */
+#define imv_read(name) \
+ ({ \
+ __typeof__(name##__imv) value; \
+ BUILD_BUG_ON(sizeof(value) > 8); \
+ switch (sizeof(value)) { \
+ case 1: \
+ asm(".section __imv,\"a\",@progbits\n\t" \
+ _ASM_PTR "%c1, (3f)-%c2\n\t" \
+ ".byte %c2\n\t" \
+ ".previous\n\t" \
+ "mov $0,%0\n\t" \
+ "3:\n\t" \
+ : "=q" (value) \
+ : "i" (&name##__imv), \
+ "i" (sizeof(value))); \
+ break; \
+ case 2: \
+ case 4: \
+ asm(".section __imv,\"a\",@progbits\n\t" \
+ _ASM_PTR "%c1, (3f)-%c2\n\t" \
+ ".byte %c2\n\t" \
+ ".previous\n\t" \
+ "mov $0,%0\n\t" \
+ "3:\n\t" \
+ : "=r" (value) \
+ : "i" (&name##__imv), \
+ "i" (sizeof(value))); \
+ break; \
+ case 8: \
+ if (sizeof(long) < 8) { \
+ value = name##__imv; \
+ break; \
+ } \
+ asm(".section __imv,\"a\",@progbits\n\t" \
+ _ASM_PTR "%c1, (3f)-%c2\n\t" \
+ ".byte %c2\n\t" \
+ ".previous\n\t" \
+ "mov $0xFEFEFEFE01010101,%0\n\t" \
+ "3:\n\t" \
+ : "=r" (value) \
+ : "i" (&name##__imv), \
+ "i" (sizeof(value))); \
+ break; \
+ }; \
+ value; \
+ })
+
+#endif /* _ASM_X86_IMMEDIATE_H */
Index: linux-2.6-lttng.mm/arch/x86/Kconfig
===================================================================
--- linux-2.6-lttng.mm.orig/arch/x86/Kconfig 2008-01-24 14:18:34.000000000 -0500
+++ linux-2.6-lttng.mm/arch/x86/Kconfig 2008-01-24 14:30:09.000000000 -0500
@@ -20,6 +20,7 @@ config X86
def_bool y
select HAVE_OPROFILE
select HAVE_KPROBES
+ select HAVE_IMMEDIATE
config GENERIC_LOCKBREAK
def_bool n
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
next prev parent reply other threads:[~2008-01-24 20:43 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-01-24 20:27 [patch 00/26] Instrumentation Support Enhancement (2.6.24-rc8-mm1) Mathieu Desnoyers
2008-01-24 20:27 ` [patch 01/26] Linux Kernel Markers Support for Proprierary Modules Mathieu Desnoyers
2008-01-24 22:19 ` Jon Masters
2008-01-24 20:27 ` [patch 02/26] Fix ARM to play nicely with generic Instrumentation menu Mathieu Desnoyers
2008-01-24 21:13 ` Russell King
2008-01-24 21:23 ` Mathieu Desnoyers
2008-01-24 22:17 ` Russell King
2008-01-24 20:27 ` [patch 03/26] Move Kconfig.instrumentation to arch/Kconfig and init/Kconfig Mathieu Desnoyers
2008-01-24 21:00 ` Randy Dunlap
2008-01-24 21:05 ` Mathieu Desnoyers
2008-01-24 22:03 ` Mathieu Desnoyers
2008-01-24 23:05 ` Haavard Skinnemoen
2008-01-24 20:27 ` [patch 04/26] Kprobes - use a mutex to protect the instruction pages list Mathieu Desnoyers
2008-01-24 20:27 ` [patch 05/26] Kprobes - do not use kprobes mutex in arch code Mathieu Desnoyers
2008-01-24 20:27 ` [patch 06/26] Kprobes - declare kprobe_mutex static Mathieu Desnoyers
2008-01-24 20:27 ` [patch 07/26] Add INIT_ARRAY() to kernel.h Mathieu Desnoyers
2008-01-24 20:39 ` Jan Engelhardt
2008-01-24 20:54 ` [patch 07/26] Add INIT_ARRAY() to kernel.h (updated) Mathieu Desnoyers
2008-01-24 21:08 ` Jan Engelhardt
2008-01-24 21:18 ` Mathieu Desnoyers
2008-01-24 20:58 ` [patch 07/26] Add INIT_ARRAY() to kernel.h Randy Dunlap
2008-01-24 21:04 ` Mathieu Desnoyers
2008-01-24 22:02 ` Stefan Richter
2008-01-24 22:10 ` [patch 07/26] Add INIT_ARRAY() to kernel.h (update 2) Mathieu Desnoyers
2008-01-24 22:50 ` Alexey Dobriyan
2008-01-24 23:04 ` [patch 07/26] Add INIT_ARRAY() to kernel.h H. Peter Anvin
2008-01-25 13:14 ` Mathieu Desnoyers
2008-01-25 8:03 ` Jan Engelhardt
2008-01-24 23:03 ` H. Peter Anvin
2008-01-24 20:27 ` [patch 08/26] Text Edit Lock - Architecture Independent Code Mathieu Desnoyers
2008-01-24 20:27 ` [patch 09/26] Text Edit Lock - Alternative code for x86 Mathieu Desnoyers
2008-01-24 20:27 ` [patch 10/26] Text Edit Lock - kprobes architecture independent support Mathieu Desnoyers
2008-01-24 20:27 ` [patch 11/26] Text Edit Lock - kprobes x86 Mathieu Desnoyers
2008-01-24 20:27 ` [patch 12/26] Text Edit Lock - x86_32 standardize debug rodata Mathieu Desnoyers
2008-01-24 20:27 ` [patch 13/26] Text Edit Lock - x86_64 " Mathieu Desnoyers
2008-01-24 20:27 ` [patch 14/26] Immediate Values - Architecture Independent Code Mathieu Desnoyers
2008-01-24 20:27 ` [patch 15/26] Immediate Values - Kconfig menu in EMBEDDED Mathieu Desnoyers
2008-01-24 20:27 ` Mathieu Desnoyers [this message]
2008-01-24 20:27 ` [patch 17/26] Add text_poke and sync_core to powerpc Mathieu Desnoyers
2008-01-24 20:27 ` [patch 18/26] Immediate Values - Powerpc Optimization Mathieu Desnoyers
2008-01-24 20:27 ` [patch 19/26] Immediate Values - Documentation Mathieu Desnoyers
2008-01-24 20:27 ` [patch 20/26] Scheduler Profiling - Use Immediate Values Mathieu Desnoyers
2008-01-24 20:27 ` [patch 21/26] Immediate Values - Move Kprobes x86 restore_interrupt to kdebug.h Mathieu Desnoyers
2008-01-24 20:27 ` [patch 22/26] Add __discard section to x86 Mathieu Desnoyers
2008-01-24 20:27 ` [patch 23/26] Immediate Values - x86 Optimization NMI and MCE support Mathieu Desnoyers
2008-01-24 20:27 ` [patch 24/26] Immediate Values - Powerpc Optimization NMI " Mathieu Desnoyers
2008-01-24 20:27 ` [patch 25/26] Immediate Values Use Arch NMI and MCE Support Mathieu Desnoyers
2008-01-24 20:27 ` [patch 26/26] Linux Kernel Markers - Use Immediate Values Mathieu Desnoyers
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=20080124203339.058366192@polymtl.ca \
--to=mathieu.desnoyers@polymtl.ca \
--cc=ak@muc.de \
--cc=akpm@linux-foundation.org \
--cc=cebbert@redhat.com \
--cc=hch@infradead.org \
--cc=hpa@zytor.com \
--cc=jeremy@goop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mingo@redhat.com \
--cc=rusty@rustcorp.com.au \
--cc=tglx@linutronix.de \
/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