From e7b8e675d9c71b868b66f62f725a948047514719 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Tue, 26 Jan 2010 04:40:03 -0500 Subject: tracing: Unify arch_syscall_addr() implementations Most implementations of arch_syscall_addr() are the same, so create a default version in common code and move the one piece that differs (the syscall table) to asm/syscall.h. New arch ports don't have to waste time copying & pasting this simple function. The s390/sparc versions need to be different, so document why. Signed-off-by: Mike Frysinger Acked-by: David S. Miller Acked-by: Paul Mundt Acked-by: Heiko Carstens Cc: Steven Rostedt LKML-Reference: <1264498803-17278-1-git-send-email-vapier@gentoo.org> Signed-off-by: Frederic Weisbecker --- arch/x86/include/asm/syscall.h | 2 ++ arch/x86/kernel/ftrace.c | 10 ---------- 2 files changed, 2 insertions(+), 10 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 8d33bc5462d..c4a348f7bd4 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,6 +16,8 @@ #include #include +extern const unsigned long sys_call_table[]; + /* * Only the low 32 bits of orig_ax are meaningful, so we return int. * This importantly ignores the high bits on 64-bit, so comparisons diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 30968924543..0d93a941934 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -484,13 +484,3 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - -#ifdef CONFIG_FTRACE_SYSCALLS - -extern unsigned long *sys_call_table; - -unsigned long __init arch_syscall_addr(int nr) -{ - return (unsigned long)(&sys_call_table)[nr]; -} -#endif -- cgit v1.2.3-70-g09d2 From f850c30c8b426ba1688cb63b1a3e534eed03a138 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 10 Feb 2010 17:25:17 +0100 Subject: tracing/kprobes: Make Kconfig dependencies generic KPROBES_EVENT actually depends on the regs and stack access API (b1cf540f) and not on x86. So introduce a new config option which architectures can select if they have the API implemented and switch x86. Signed-off-by: Heiko Carstens Acked-by: Masami Hiramatsu Cc: Ingo Molnar Cc: Martin Schwidefsky LKML-Reference: <20100210162517.GB6933@osiris.boeblingen.de.ibm.com> Signed-off-by: Frederic Weisbecker --- arch/Kconfig | 3 +++ arch/x86/Kconfig | 1 + kernel/trace/Kconfig | 2 +- 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/Kconfig b/arch/Kconfig index 9d055b4f058..04e3aa77da2 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -121,6 +121,9 @@ config HAVE_DMA_ATTRS config USE_GENERIC_SMP_HELPERS bool +config HAVE_REGS_AND_STACK_ACCESS_API + bool + config HAVE_CLK bool help diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 55298e89157..07baa12929b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -45,6 +45,7 @@ config X86 select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_EFFICIENT_UNALIGNED_ACCESS select USER_STACKTRACE_SUPPORT + select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_DMA_API_DEBUG select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 6c22d8a2f28..40fef552f01 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -451,7 +451,7 @@ config BLK_DEV_IO_TRACE config KPROBE_EVENT depends on KPROBES - depends on X86 + depends on HAVE_REGS_AND_STACK_ACCESS_API bool "Enable kprobes-based dynamic events" select TRACING default y -- cgit v1.2.3-70-g09d2 From 0c54dd341fb701928b8e5dca91ced1870c55b05b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 25 Feb 2010 08:42:06 -0500 Subject: ftrace: Remove memory barriers from NMI code when not needed The code in stop_machine that modifies the kernel text has a bit of logic to handle the case of NMIs. stop_machine does not prevent NMIs from executing, and if an NMI were to trigger on another CPU as the modifying CPU is changing the NMI text, a GPF could result. To prevent the GPF, the NMI calls ftrace_nmi_enter() which may modify the code first, then any other NMIs will just change the text to the same content which will do no harm. The code that stop_machine called must wait for NMIs to finish while it changes each location in the kernel. That code may also change the text to what the NMI changed it to. The key is that the text will never change content while another CPU is executing it. To make the above work, the call to ftrace_nmi_enter() must also do a smp_mb() as well as atomic_inc(). But for applications like perf that require a high number of NMIs for profiling, this can have a dramatic effect on the system. Not only is it doing a full memory barrier on both nmi_enter() as well as nmi_exit() it is also modifying a global variable with an atomic operation. This kills performance on large SMP machines. Since the memory barriers are only needed when ftrace is in the process of modifying the text (which is seldom), this patch adds a "modifying_code" variable that gets set before stop machine is executed and cleared afterwards. The NMIs will check this variable and store it in a per CPU "save_modifying_code" variable that it will use to check if it needs to do the memory barriers and atomic dec on NMI exit. Acked-by: Peter Zijlstra Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 30968924543..605ef196fdd 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -30,14 +30,32 @@ #ifdef CONFIG_DYNAMIC_FTRACE +/* + * modifying_code is set to notify NMIs that they need to use + * memory barriers when entering or exiting. But we don't want + * to burden NMIs with unnecessary memory barriers when code + * modification is not being done (which is most of the time). + * + * A mutex is already held when ftrace_arch_code_modify_prepare + * and post_process are called. No locks need to be taken here. + * + * Stop machine will make sure currently running NMIs are done + * and new NMIs will see the updated variable before we need + * to worry about NMIs doing memory barriers. + */ +static int modifying_code __read_mostly; +static DEFINE_PER_CPU(int, save_modifying_code); + int ftrace_arch_code_modify_prepare(void) { set_kernel_text_rw(); + modifying_code = 1; return 0; } int ftrace_arch_code_modify_post_process(void) { + modifying_code = 0; set_kernel_text_ro(); return 0; } @@ -149,6 +167,11 @@ static void ftrace_mod_code(void) void ftrace_nmi_enter(void) { + __get_cpu_var(save_modifying_code) = modifying_code; + + if (!__get_cpu_var(save_modifying_code)) + return; + if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) { smp_rmb(); ftrace_mod_code(); @@ -160,6 +183,9 @@ void ftrace_nmi_enter(void) void ftrace_nmi_exit(void) { + if (!__get_cpu_var(save_modifying_code)) + return; + /* Finish all executions before clearing nmi_running */ smp_mb(); atomic_dec(&nmi_running); -- cgit v1.2.3-70-g09d2