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 CC: Andi Kleen CC: "H. Peter Anvin" CC: Chuck Ebbert CC: Christoph Hellwig CC: Jeremy Fitzhardinge CC: Thomas Gleixner CC: Ingo Molnar CC: Rusty Russell --- 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 + * + * This file is released under the GPLv2. + * See the file COPYING for more details. + */ + +#include + +/** + * 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 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/