From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755196Ab0IQP2t (ORCPT ); Fri, 17 Sep 2010 11:28:49 -0400 Received: from hrndva-omtalb.mail.rr.com ([71.74.56.125]:55542 "EHLO hrndva-omtalb.mail.rr.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754380Ab0IQP2r (ORCPT ); Fri, 17 Sep 2010 11:28:47 -0400 X-Authority-Analysis: v=1.1 cv=2ipXt8Ao/PPbK329gQN1nC6XU/V8QMABDttguNTIlb0= c=1 sm=0 a=9nV7qiHO8IIA:10 a=Q9fys5e9bTEA:10 a=OPBmh+XkhLl+Enan7BmTLg==:17 a=20KFwNOVAAAA:8 a=meVymXHHAAAA:8 a=5koX4MaKYlLvq6bZrWwA:9 a=Kmke6y2lVEhZaD4X1BsA:7 a=peicfVW20tDoGQ5-uu-roB0-7s0A:4 a=PUjeQqilurYA:10 a=jEp0ucaQiEUA:10 a=jeBq3FmKZ4MA:10 a=OPBmh+XkhLl+Enan7BmTLg==:117 X-Cloudmark-Score: 0 X-Originating-IP: 67.242.120.143 Subject: Re: [PATCH 01/10] jump label v11: make dynamic no-op selection available outside of ftrace From: Steven Rostedt To: Jason Baron Cc: linux-kernel@vger.kernel.org, mingo@elte.hu, mathieu.desnoyers@polymtl.ca, hpa@zytor.com, tglx@linutronix.de, andi@firstfloor.org, roland@redhat.com, rth@redhat.com, mhiramat@redhat.com, fweisbec@gmail.com, avi@redhat.com, davem@davemloft.net, vgoyal@redhat.com, sam@ravnborg.org, tony@bakeyournoodle.com In-Reply-To: <96259ae74172dcac99c0020c249743c523a92e18.1284733808.git.jbaron@redhat.com> References: <96259ae74172dcac99c0020c249743c523a92e18.1284733808.git.jbaron@redhat.com> Content-Type: text/plain; charset="ISO-8859-15" Date: Fri, 17 Sep 2010 11:28:44 -0400 Message-ID: <1284737324.23787.79.camel@gandalf.stny.rr.com> Mime-Version: 1.0 X-Mailer: Evolution 2.30.2 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2010-09-17 at 11:08 -0400, Jason Baron wrote: > Move Steve's code for finding the best 5-byte no-op from ftrace.c to alternative.c. > The idea is that other consumers (in this case jump label) want to make use of > that code. > > Signed-off-by: Jason Baron Acked-by: Steven Rostedt -- Steve > --- > arch/x86/include/asm/alternative.h | 8 ++++ > arch/x86/kernel/alternative.c | 64 ++++++++++++++++++++++++++++++++++++ > arch/x86/kernel/ftrace.c | 63 +---------------------------------- > arch/x86/kernel/setup.c | 6 +++ > 4 files changed, 79 insertions(+), 62 deletions(-) > > diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h > index bc6abb7..27a35b6 100644 > --- a/arch/x86/include/asm/alternative.h > +++ b/arch/x86/include/asm/alternative.h > @@ -180,4 +180,12 @@ static inline void apply_paravirt(struct paravirt_patch_site *start, > extern void *text_poke(void *addr, const void *opcode, size_t len); > extern void *text_poke_smp(void *addr, const void *opcode, size_t len); > > +#if defined(CONFIG_DYNAMIC_FTRACE) > +#define IDEAL_NOP_SIZE_5 5 > +extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5]; > +extern void arch_init_ideal_nop5(void); > +#else > +static inline void arch_init_ideal_nop5(void) {} > +#endif > + > #endif /* _ASM_X86_ALTERNATIVE_H */ > diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c > index f65ab8b..1849d80 100644 > --- a/arch/x86/kernel/alternative.c > +++ b/arch/x86/kernel/alternative.c > @@ -641,3 +641,67 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) > return addr; > } > > +#if defined(CONFIG_DYNAMIC_FTRACE) > + > +unsigned char ideal_nop5[IDEAL_NOP_SIZE_5]; > + > +void __init arch_init_ideal_nop5(void) > +{ > + extern const unsigned char ftrace_test_p6nop[]; > + extern const unsigned char ftrace_test_nop5[]; > + extern const unsigned char ftrace_test_jmp[]; > + int faulted = 0; > + > + /* > + * There is no good nop for all x86 archs. > + * We will default to using the P6_NOP5, but first we > + * will test to make sure that the nop will actually > + * work on this CPU. If it faults, we will then > + * go to a lesser efficient 5 byte nop. If that fails > + * we then just use a jmp as our nop. This isn't the most > + * efficient nop, but we can not use a multi part nop > + * since we would then risk being preempted in the middle > + * of that nop, and if we enabled tracing then, it might > + * cause a system crash. > + * > + * TODO: check the cpuid to determine the best nop. > + */ > + asm volatile ( > + "ftrace_test_jmp:" > + "jmp ftrace_test_p6nop\n" > + "nop\n" > + "nop\n" > + "nop\n" /* 2 byte jmp + 3 bytes */ > + "ftrace_test_p6nop:" > + P6_NOP5 > + "jmp 1f\n" > + "ftrace_test_nop5:" > + ".byte 0x66,0x66,0x66,0x66,0x90\n" > + "1:" > + ".section .fixup, \"ax\"\n" > + "2: movl $1, %0\n" > + " jmp ftrace_test_nop5\n" > + "3: movl $2, %0\n" > + " jmp 1b\n" > + ".previous\n" > + _ASM_EXTABLE(ftrace_test_p6nop, 2b) > + _ASM_EXTABLE(ftrace_test_nop5, 3b) > + : "=r"(faulted) : "0" (faulted)); > + > + switch (faulted) { > + case 0: > + pr_info("converting mcount calls to 0f 1f 44 00 00\n"); > + memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5); > + break; > + case 1: > + pr_info("converting mcount calls to 66 66 66 66 90\n"); > + memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5); > + break; > + case 2: > + pr_info("converting mcount calls to jmp . + 5\n"); > + memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5); > + break; > + } > + > +} > +#endif > diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c > index cd37469..3afb33f 100644 > --- a/arch/x86/kernel/ftrace.c > +++ b/arch/x86/kernel/ftrace.c > @@ -257,14 +257,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) > return mod_code_status; > } > > - > - > - > -static unsigned char ftrace_nop[MCOUNT_INSN_SIZE]; > - > static unsigned char *ftrace_nop_replace(void) > { > - return ftrace_nop; > + return ideal_nop5; > } > > static int > @@ -338,62 +333,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func) > > int __init ftrace_dyn_arch_init(void *data) > { > - extern const unsigned char ftrace_test_p6nop[]; > - extern const unsigned char ftrace_test_nop5[]; > - extern const unsigned char ftrace_test_jmp[]; > - int faulted = 0; > - > - /* > - * There is no good nop for all x86 archs. > - * We will default to using the P6_NOP5, but first we > - * will test to make sure that the nop will actually > - * work on this CPU. If it faults, we will then > - * go to a lesser efficient 5 byte nop. If that fails > - * we then just use a jmp as our nop. This isn't the most > - * efficient nop, but we can not use a multi part nop > - * since we would then risk being preempted in the middle > - * of that nop, and if we enabled tracing then, it might > - * cause a system crash. > - * > - * TODO: check the cpuid to determine the best nop. > - */ > - asm volatile ( > - "ftrace_test_jmp:" > - "jmp ftrace_test_p6nop\n" > - "nop\n" > - "nop\n" > - "nop\n" /* 2 byte jmp + 3 bytes */ > - "ftrace_test_p6nop:" > - P6_NOP5 > - "jmp 1f\n" > - "ftrace_test_nop5:" > - ".byte 0x66,0x66,0x66,0x66,0x90\n" > - "1:" > - ".section .fixup, \"ax\"\n" > - "2: movl $1, %0\n" > - " jmp ftrace_test_nop5\n" > - "3: movl $2, %0\n" > - " jmp 1b\n" > - ".previous\n" > - _ASM_EXTABLE(ftrace_test_p6nop, 2b) > - _ASM_EXTABLE(ftrace_test_nop5, 3b) > - : "=r"(faulted) : "0" (faulted)); > - > - switch (faulted) { > - case 0: > - pr_info("converting mcount calls to 0f 1f 44 00 00\n"); > - memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE); > - break; > - case 1: > - pr_info("converting mcount calls to 66 66 66 66 90\n"); > - memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE); > - break; > - case 2: > - pr_info("converting mcount calls to jmp . + 5\n"); > - memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE); > - break; > - } > - > /* The return code is retured via data */ > *(unsigned long *)data = 0; > > diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c > index 1427c36..fb37842 100644 > --- a/arch/x86/kernel/setup.c > +++ b/arch/x86/kernel/setup.c > @@ -112,6 +112,7 @@ > #include > #endif > #include > +#include > > /* > * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. > @@ -689,6 +690,7 @@ void __init setup_arch(char **cmdline_p) > { > int acpi = 0; > int k8 = 0; > + unsigned long flags; > > #ifdef CONFIG_X86_32 > memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); > @@ -1036,6 +1038,10 @@ void __init setup_arch(char **cmdline_p) > x86_init.oem.banner(); > > mcheck_init(); > + > + local_irq_save(flags); > + arch_init_ideal_nop5(); > + local_irq_restore(flags); > } > > #ifdef CONFIG_X86_32