LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Christoph Hellwig <hch@infradead.org>,
	Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>,
	Gregory Haskins <ghaskins@novell.com>,
	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>,
	Thomas Gleixner <tglx@linutronix.de>,
	Tim Bird <tim.bird@am.sony.com>, Sam Ravnborg <sam@ravnborg.org>,
	"Frank Ch. Eigler" <fche@redhat.com>,
	Jan Kiszka <jan.kiszka@siemens.com>,
	John Stultz <johnstul@us.ibm.com>,
	Arjan van de Ven <arjan@infradead.org>,
	Steven Rostedt <srostedt@redhat.com>
Subject: [PATCH 02/22 -v7] Add basic support for gcc profiler instrumentation
Date: Tue, 29 Jan 2008 22:15:23 -0500	[thread overview]
Message-ID: <20080130031840.337019504@goodmis.org> (raw)
In-Reply-To: <20080130031521.258552785@goodmis.org>

[-- Attachment #1: mcount-add-basic-support-for-gcc-profiler-instrum.patch --]
[-- Type: text/plain, Size: 12600 bytes --]

If CONFIG_MCOUNT is selected and /proc/sys/kernel/mcount_enabled is set to a
non-zero value the mcount routine will be called everytime we enter a kernel
function that is not marked with the "notrace" attribute.

The mcount routine will then call a registered function if a function
happens to be registered.

[This code has been highly hacked by Steven Rostedt, so don't
 blame Arnaldo for all of this ;-) ]

Update:
  It is now possible to register more than one mcount function.
  If only one mcount function is registered, that will be the
  function that mcount calls directly. If more than one function
  is registered, then mcount will call a function that will loop
  through the functions to call.

Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
---
 Makefile                   |    3 
 arch/x86/Kconfig           |    1 
 arch/x86/kernel/entry_32.S |   25 +++++++
 arch/x86/kernel/entry_64.S |   36 +++++++++++
 include/linux/linkage.h    |    2 
 include/linux/mcount.h     |   38 ++++++++++++
 kernel/sysctl.c            |   11 +++
 lib/Kconfig.debug          |    1 
 lib/Makefile               |    2 
 lib/tracing/Kconfig        |   10 +++
 lib/tracing/Makefile       |    3 
 lib/tracing/mcount.c       |  141 +++++++++++++++++++++++++++++++++++++++++++++
 12 files changed, 273 insertions(+)

Index: linux-mcount.git/Makefile
===================================================================
--- linux-mcount.git.orig/Makefile	2008-01-29 17:01:56.000000000 -0500
+++ linux-mcount.git/Makefile	2008-01-29 17:26:17.000000000 -0500
@@ -509,6 +509,9 @@ endif
 
 include $(srctree)/arch/$(SRCARCH)/Makefile
 
+ifdef CONFIG_MCOUNT
+KBUILD_CFLAGS	+= -pg
+endif
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls
 else
Index: linux-mcount.git/arch/x86/Kconfig
===================================================================
--- linux-mcount.git.orig/arch/x86/Kconfig	2008-01-29 16:59:15.000000000 -0500
+++ linux-mcount.git/arch/x86/Kconfig	2008-01-29 17:26:18.000000000 -0500
@@ -19,6 +19,7 @@ config X86_64
 config X86
 	bool
 	default y
+	select HAVE_MCOUNT
 
 config GENERIC_TIME
 	bool
Index: linux-mcount.git/arch/x86/kernel/entry_32.S
===================================================================
--- linux-mcount.git.orig/arch/x86/kernel/entry_32.S	2008-01-29 16:59:15.000000000 -0500
+++ linux-mcount.git/arch/x86/kernel/entry_32.S	2008-01-29 17:26:18.000000000 -0500
@@ -75,6 +75,31 @@ DF_MASK		= 0x00000400 
 NT_MASK		= 0x00004000
 VM_MASK		= 0x00020000
 
+#ifdef CONFIG_MCOUNT
+.globl mcount
+mcount:
+	/* unlikely(mcount_enabled) */
+	cmpl $0, mcount_enabled
+	jnz trace
+	ret
+
+trace:
+	/* taken from glibc */
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	movl 0xc(%esp), %edx
+	movl 0x4(%ebp), %eax
+
+	call   *mcount_trace_function
+
+	popl %edx
+	popl %ecx
+	popl %eax
+
+	ret
+#endif
+
 #ifdef CONFIG_PREEMPT
 #define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
 #else
Index: linux-mcount.git/arch/x86/kernel/entry_64.S
===================================================================
--- linux-mcount.git.orig/arch/x86/kernel/entry_64.S	2008-01-29 16:59:15.000000000 -0500
+++ linux-mcount.git/arch/x86/kernel/entry_64.S	2008-01-29 17:26:18.000000000 -0500
@@ -53,6 +53,42 @@
 
 	.code64
 
+#ifdef CONFIG_MCOUNT
+
+ENTRY(mcount)
+	/* unlikely(mcount_enabled) */
+	cmpl $0, mcount_enabled
+	jnz trace
+	retq
+
+trace:
+	/* taken from glibc */
+	subq $0x38, %rsp
+	movq %rax, (%rsp)
+	movq %rcx, 8(%rsp)
+	movq %rdx, 16(%rsp)
+	movq %rsi, 24(%rsp)
+	movq %rdi, 32(%rsp)
+	movq %r8, 40(%rsp)
+	movq %r9, 48(%rsp)
+
+	movq 0x38(%rsp), %rsi
+	movq 8(%rbp), %rdi
+
+	call   *mcount_trace_function
+
+	movq 48(%rsp), %r9
+	movq 40(%rsp), %r8
+	movq 32(%rsp), %rdi
+	movq 24(%rsp), %rsi
+	movq 16(%rsp), %rdx
+	movq 8(%rsp), %rcx
+	movq (%rsp), %rax
+	addq $0x38, %rsp
+
+	retq
+#endif
+
 #ifndef CONFIG_PREEMPT
 #define retint_kernel retint_restore_args
 #endif	
Index: linux-mcount.git/include/linux/linkage.h
===================================================================
--- linux-mcount.git.orig/include/linux/linkage.h	2008-01-29 16:59:15.000000000 -0500
+++ linux-mcount.git/include/linux/linkage.h	2008-01-29 17:26:18.000000000 -0500
@@ -3,6 +3,8 @@
 
 #include <asm/linkage.h>
 
+#define notrace __attribute__((no_instrument_function))
+
 #ifdef __cplusplus
 #define CPP_ASMLINKAGE extern "C"
 #else
Index: linux-mcount.git/include/linux/mcount.h
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ linux-mcount.git/include/linux/mcount.h	2008-01-29 17:26:18.000000000 -0500
@@ -0,0 +1,38 @@
+#ifndef _LINUX_MCOUNT_H
+#define _LINUX_MCOUNT_H
+
+#ifdef CONFIG_MCOUNT
+extern int mcount_enabled;
+
+#include <linux/linkage.h>
+
+#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
+#define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
+
+typedef void (*mcount_func_t)(unsigned long ip, unsigned long parent_ip);
+
+struct mcount_ops {
+	mcount_func_t func;
+	struct mcount_ops *next;
+};
+
+/*
+ * The mcount_ops must be a static and should also
+ * be read_mostly.  These functions do modify read_mostly variables
+ * so use them sparely. Never free an mcount_op or modify the
+ * next pointer after it has been registered. Even after unregistering
+ * it, the next pointer may still be used internally.
+ */
+int register_mcount_function(struct mcount_ops *ops);
+int unregister_mcount_function(struct mcount_ops *ops);
+void clear_mcount_function(void);
+
+extern void mcount(void);
+
+#else /* !CONFIG_MCOUNT */
+# define register_mcount_function(ops) do { } while (0)
+# define unregister_mcount_function(ops) do { } while (0)
+# define clear_mcount_function(ops) do { } while (0)
+#endif /* CONFIG_MCOUNT */
+#endif /* _LINUX_MCOUNT_H */
Index: linux-mcount.git/kernel/sysctl.c
===================================================================
--- linux-mcount.git.orig/kernel/sysctl.c	2008-01-29 17:02:10.000000000 -0500
+++ linux-mcount.git/kernel/sysctl.c	2008-01-29 17:26:18.000000000 -0500
@@ -46,6 +46,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/acpi.h>
 #include <linux/reboot.h>
+#include <linux/mcount.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -514,6 +515,16 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+#ifdef CONFIG_MCOUNT
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "mcount_enabled",
+		.data		= &mcount_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
 #ifdef CONFIG_KMOD
 	{
 		.ctl_name	= KERN_MODPROBE,
Index: linux-mcount.git/lib/Kconfig.debug
===================================================================
--- linux-mcount.git.orig/lib/Kconfig.debug	2008-01-29 17:02:10.000000000 -0500
+++ linux-mcount.git/lib/Kconfig.debug	2008-01-29 17:26:18.000000000 -0500
@@ -562,5 +562,6 @@ config LATENCYTOP
 	  Enable this option if you want to use the LatencyTOP tool
 	  to find out which userspace is blocking on what kernel operations.
 
+source lib/tracing/Kconfig
 
 source "samples/Kconfig"
Index: linux-mcount.git/lib/Makefile
===================================================================
--- linux-mcount.git.orig/lib/Makefile	2008-01-29 17:02:10.000000000 -0500
+++ linux-mcount.git/lib/Makefile	2008-01-29 17:26:18.000000000 -0500
@@ -67,6 +67,8 @@ obj-$(CONFIG_AUDIT_GENERIC) += audit.o
 obj-$(CONFIG_SWIOTLB) += swiotlb.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
 
+obj-$(CONFIG_MCOUNT) += tracing/
+
 lib-$(CONFIG_GENERIC_BUG) += bug.o
 
 hostprogs-y	:= gen_crc32table
Index: linux-mcount.git/lib/tracing/Kconfig
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ linux-mcount.git/lib/tracing/Kconfig	2008-01-29 17:26:18.000000000 -0500
@@ -0,0 +1,10 @@
+
+# Archs that enable MCOUNT should select HAVE_MCOUNT
+config HAVE_MCOUNT
+       bool
+
+# MCOUNT itself is useless, or will just be added overhead.
+# It needs something to register a function with it.
+config MCOUNT
+	bool
+	select FRAME_POINTER
Index: linux-mcount.git/lib/tracing/Makefile
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ linux-mcount.git/lib/tracing/Makefile	2008-01-29 17:26:18.000000000 -0500
@@ -0,0 +1,3 @@
+obj-$(CONFIG_MCOUNT) += libmcount.o
+
+libmcount-y := mcount.o
Index: linux-mcount.git/lib/tracing/mcount.c
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ linux-mcount.git/lib/tracing/mcount.c	2008-01-29 17:26:18.000000000 -0500
@@ -0,0 +1,141 @@
+/*
+ * Infrastructure for profiling code inserted by 'gcc -pg'.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Originally ported from the -rt patch by:
+ *   Copyright (C) 2007 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Based on code in the latency_tracer, that is:
+ *
+ *  Copyright (C) 2004-2006 Ingo Molnar
+ *  Copyright (C) 2004 William Lee Irwin III
+ */
+
+#include <linux/module.h>
+#include <linux/mcount.h>
+
+/*
+ * Since we have nothing protecting between the test of
+ * mcount_trace_function and the call to it, we can't
+ * set it to NULL without risking a race that will have
+ * the kernel call the NULL pointer. Instead, we just
+ * set the function pointer to a dummy function.
+ */
+notrace void dummy_mcount_tracer(unsigned long ip,
+				 unsigned long parent_ip)
+{
+	/* do nothing */
+}
+
+static DEFINE_SPINLOCK(mcount_func_lock);
+static struct mcount_ops mcount_list_end __read_mostly =
+{
+	.func = dummy_mcount_tracer,
+};
+
+static struct mcount_ops *mcount_list __read_mostly = &mcount_list_end;
+mcount_func_t mcount_trace_function __read_mostly = dummy_mcount_tracer;
+int mcount_enabled __read_mostly;
+
+/* mcount is defined per arch in assembly */
+EXPORT_SYMBOL_GPL(mcount);
+
+notrace void mcount_list_func(unsigned long ip, unsigned long parent_ip)
+{
+	struct mcount_ops *op = mcount_list;
+
+	while (op != &mcount_list_end) {
+		op->func(ip, parent_ip);
+		op = op->next;
+	};
+}
+
+/**
+ * register_mcount_function - register a function for profiling
+ * @ops - ops structure that holds the function for profiling.
+ *
+ * Register a function to be called by all functions in the
+ * kernel.
+ *
+ * Note: @ops->func and all the functions it calls must be labeled
+ *       with "notrace", otherwise it will go into a
+ *       recursive loop.
+ */
+int register_mcount_function(struct mcount_ops *ops)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&mcount_func_lock, flags);
+	ops->next = mcount_list;
+	/* must have next seen before we update the list pointer */
+	smp_wmb();
+	mcount_list = ops;
+	/*
+	 * For one func, simply call it directly.
+	 * For more than one func, call the chain.
+	 */
+	if (ops->next == &mcount_list_end)
+		mcount_trace_function = ops->func;
+	else
+		mcount_trace_function = mcount_list_func;
+	spin_unlock_irqrestore(&mcount_func_lock, flags);
+
+	return 0;
+}
+
+/**
+ * unregister_mcount_function - unresgister a function for profiling.
+ * @ops - ops structure that holds the function to unregister
+ *
+ * Unregister a function that was added to be called by mcount profiling.
+ */
+int unregister_mcount_function(struct mcount_ops *ops)
+{
+	unsigned long flags;
+	struct mcount_ops **p;
+	int ret = 0;
+
+	spin_lock_irqsave(&mcount_func_lock, flags);
+
+	/*
+	 * If we are the only function, then the mcount pointer is
+	 * pointing directly to that function.
+	 */
+	if (mcount_list == ops && ops->next == &mcount_list_end) {
+		mcount_trace_function = dummy_mcount_tracer;
+		mcount_list = &mcount_list_end;
+		goto out;
+	}
+
+	for (p = &mcount_list; *p != &mcount_list_end; p = &(*p)->next)
+		if (*p == ops)
+			break;
+
+	if (*p != ops) {
+		ret = -1;
+		goto out;
+	}
+
+	*p = (*p)->next;
+
+	/* If we only have one func left, then call that directly */
+	if (mcount_list->next == &mcount_list_end)
+		mcount_trace_function = mcount_list->func;
+
+ out:
+	spin_unlock_irqrestore(&mcount_func_lock, flags);
+
+	return 0;
+}
+
+/**
+ * clear_mcount_function - reset the mcount function
+ *
+ * This NULLs the mcount function and in essence stops
+ * tracing.  There may be lag
+ */
+void clear_mcount_function(void)
+{
+	mcount_trace_function = dummy_mcount_tracer;
+}

-- 

  parent reply	other threads:[~2008-01-30  3:19 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-01-30  3:15 [PATCH 00/22 -v7] mcount and latency tracing utility -v7 Steven Rostedt
2008-01-30  3:15 ` [PATCH 01/22 -v7] printk - dont wakeup klogd with interrupts disabled Steven Rostedt
2008-01-30  3:15 ` Steven Rostedt [this message]
2008-01-30  8:46   ` [PATCH 02/22 -v7] Add basic support for gcc profiler instrumentation Peter Zijlstra
2008-01-30 13:08     ` Steven Rostedt
2008-01-30 14:09       ` Steven Rostedt
2008-01-30 14:25         ` Peter Zijlstra
2008-02-01 22:34           ` Paul E. McKenney
2008-02-02  1:56             ` Steven Rostedt
2008-02-02 21:41               ` Paul E. McKenney
2008-02-04 17:09                 ` Steven Rostedt
2008-02-04 21:40                   ` Paul E. McKenney
2008-02-04 22:03                     ` Steven Rostedt
2008-02-04 22:41                       ` Mathieu Desnoyers
2008-02-05  6:11                         ` Paul E. McKenney
2008-02-05  5:13                       ` Paul E. McKenney
2008-01-30 13:21   ` Jan Kiszka
2008-01-30 13:53     ` Steven Rostedt
2008-01-30 14:28       ` Steven Rostedt
2008-01-30  3:15 ` [PATCH 03/22 -v7] Annotate core code that should not be traced Steven Rostedt
2008-01-30  3:15 ` [PATCH 04/22 -v7] x86_64: notrace annotations Steven Rostedt
2008-01-30  3:15 ` [PATCH 05/22 -v7] add notrace annotations to vsyscall Steven Rostedt
2008-01-30  8:49   ` Peter Zijlstra
2008-01-30 13:15     ` Steven Rostedt
2008-01-30  3:15 ` [PATCH 06/22 -v7] handle accurate time keeping over long delays Steven Rostedt
2008-01-30  3:15 ` [PATCH 07/22 -v7] initialize the clock source to jiffies clock Steven Rostedt
2008-01-30  3:15 ` [PATCH 08/22 -v7] add get_monotonic_cycles Steven Rostedt
2008-01-30  3:15 ` [PATCH 09/22 -v7] add notrace annotations to timing events Steven Rostedt
2008-01-30  3:15 ` [PATCH 10/22 -v7] mcount based trace in the form of a header file library Steven Rostedt
2008-01-30  3:15 ` [PATCH 11/22 -v7] Add context switch marker to sched.c Steven Rostedt
2008-01-30  3:15 ` [PATCH 12/22 -v7] Make the task State char-string visible to all Steven Rostedt
2008-01-30  3:15 ` [PATCH 13/22 -v7] Add tracing of context switches Steven Rostedt
2008-01-30  3:15 ` [PATCH 14/22 -v7] Generic command line storage Steven Rostedt
2008-01-30  3:15 ` [PATCH 15/22 -v7] trace generic call to schedule switch Steven Rostedt
2008-01-30  3:15 ` [PATCH 16/22 -v7] Add marker in try_to_wake_up Steven Rostedt
2008-01-30  3:15 ` [PATCH 17/22 -v7] mcount tracer for wakeup latency timings Steven Rostedt
2008-01-30  9:31   ` Peter Zijlstra
2008-01-30 13:18     ` Steven Rostedt
2008-01-30  3:15 ` [PATCH 18/22 -v7] Trace irq disabled critical timings Steven Rostedt
2008-01-30  3:15 ` [PATCH 19/22 -v7] trace preempt off " Steven Rostedt
2008-01-30  9:40   ` Peter Zijlstra
2008-01-30 13:40     ` Steven Rostedt
2008-01-30  3:15 ` [PATCH 20/22 -v7] Add markers to various events Steven Rostedt
2008-01-30  3:15 ` [PATCH 21/22 -v7] Add event tracer Steven Rostedt
2008-01-30  3:15 ` [PATCH 22/22 -v7] Critical latency timings histogram Steven Rostedt

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=20080130031840.337019504@goodmis.org \
    --to=rostedt@goodmis.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@ghostprotocols.net \
    --cc=akpm@linux-foundation.org \
    --cc=arjan@infradead.org \
    --cc=fche@redhat.com \
    --cc=ghaskins@novell.com \
    --cc=hch@infradead.org \
    --cc=jan.kiszka@siemens.com \
    --cc=johnstul@us.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@polymtl.ca \
    --cc=mingo@elte.hu \
    --cc=sam@ravnborg.org \
    --cc=srostedt@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=tim.bird@am.sony.com \
    --cc=torvalds@linux-foundation.org \
    --subject='Re: [PATCH 02/22 -v7] Add basic support for gcc profiler instrumentation' \
    /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

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).