profiling: dynamically enable readprofile at runtime

Way too often, I have a machine that exhibits some kind of crappy
behavior.  The CPU looks wedged in the kernel or it is spending way too
much system time and I wonder what is responsible.

I try to run readprofile.  But, of course, Ubuntu doesn't enable it by
default.  Dang!

The reason we boot-time enable it is that it takes a big bufffer that we
generally can only bootmem alloc.  But, does it hurt to at least try and
runtime-alloc it?

To use:
echo 2 > /sys/kernel/profile

Then run readprofile like normal.

This should fix the compile issue with allmodconfig.  I've compile-tested
on a bunch more configs now including a few more architectures.

Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/ABI/testing/sysfs-profiling b/Documentation/ABI/testing/sysfs-profiling
new file mode 100644 (file)
index 0000000..b02d8b8
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-profiling
@@ -0,0 +1,13 @@
+What:          /sys/kernel/profile
+Date:          September 2008
+Contact:       Dave Hansen <dave@linux.vnet.ibm.com>
+Description:
+               /sys/kernel/profile is the runtime equivalent
+               of the boot-time profile= option.
+
+               You can get the same effect running:
+
+                       echo 2 > /sys/kernel/profile
+
+               as you would by issuing profile=2 on the boot
+               command line.

diff --git a/include/linux/profile.h b/include/linux/profile.h
index 7e7087239af5fc0497ebf40bf92d65cb99b5749f..570045053ce9bf04bbda46d21a97feb3b76dadb2 100644 (file)
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -35,7 +35,9 @@ enum profile_type {
 extern int prof_on __read_mostly;
 
 /* init basic kernel profiler */
-void __init profile_init(void);
+int profile_init(void);
+int profile_setup(char *str);
+int create_proc_profile(void);
 void profile_tick(int type);
 
 /*
@@ -84,9 +86,9 @@ struct pt_regs;
 
 #define prof_on 0
 
-static inline void profile_init(void)
+static inline int profile_init(void)
 {
-       return;
+       return 0;
 }
 
 static inline void profile_tick(int type)

diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index e53bc30e9ba5aa8b55311fd6700191b0f21a9597..08dd8ed86c77a7f7d05316a794f2eaf2f378c058 100644 (file)
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
+#include <linux/profile.h>
 #include <linux/sched.h>
 
 #define KERNEL_ATTR_RO(_name) \
@@ -53,6 +54,37 @@ static ssize_t uevent_helper_store(struct kobject *kobj,
 KERNEL_ATTR_RW(uevent_helper);
 #endif
 
+#ifdef CONFIG_PROFILING
+static ssize_t profiling_show(struct kobject *kobj,
+                                 struct kobj_attribute *attr, char *buf)
+{
+       return sprintf(buf, "%d\n", prof_on);
+}
+static ssize_t profiling_store(struct kobject *kobj,
+                                  struct kobj_attribute *attr,
+                                  const char *buf, size_t count)
+{
+       int ret;
+
+       if (prof_on)
+               return -EEXIST;
+       /*
+        * This eventually calls into get_option() which
+        * has a ton of callers and is not const.  It is
+        * easiest to cast it away here.
+        */
+       profile_setup((char *)buf);
+       ret = profile_init();
+       if (ret)
+               return ret;
+       ret = create_proc_profile();
+       if (ret)
+               return ret;
+       return count;
+}
+KERNEL_ATTR_RW(profiling);
+#endif
+
 #ifdef CONFIG_KEXEC
 static ssize_t kexec_loaded_show(struct kobject *kobj,
                                 struct kobj_attribute *attr, char *buf)
@@ -109,6 +141,9 @@ static struct attribute * kernel_attrs[] = {
        &uevent_seqnum_attr.attr,
        &uevent_helper_attr.attr,
 #endif
+#ifdef CONFIG_PROFILING
+       &profiling_attr.attr,
+#endif
 #ifdef CONFIG_KEXEC
        &kexec_loaded_attr.attr,
        &kexec_crash_loaded_attr.attr,

diff --git a/kernel/profile.c b/kernel/profile.c
index cd26bed4cc26535ca7398eae07fb9b800b762f2e..a9e422df6bf63e28648432efa7f0503aa09ffe8f 100644 (file)
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -22,6 +22,8 @@
 #include <linux/cpu.h>
 #include <linux/highmem.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <asm/sections.h>
 #include <asm/irq_regs.h>
 #include <asm/ptrace.h>
@@ -50,11 +52,11 @@ static DEFINE_PER_CPU(int, cpu_profile_flip);
 static DEFINE_MUTEX(profile_flip_mutex);
 #endif /* CONFIG_SMP */
 
-static int __init profile_setup(char *str)
+int profile_setup(char *str)
 {
-       static char __initdata schedstr[] = "schedule";
-       static char __initdata sleepstr[] = "sleep";
-       static char __initdata kvmstr[] = "kvm";
+       static char schedstr[] = "schedule";
+       static char sleepstr[] = "sleep";
+       static char kvmstr[] = "kvm";
        int par;
 
        if (!strncmp(str, sleepstr, strlen(sleepstr))) {
@@ -100,14 +102,33 @@ static int __init profile_setup(char *str)
 __setup("profile=", profile_setup);
 
 
-void __init profile_init(void)
+int profile_init(void)
 {
+       int buffer_bytes;
        if (!prof_on)
-               return;
+               return 0;
 
        /* only text is profiled */
        prof_len = (_etext - _stext) >> prof_shift;
-       prof_buffer = alloc_bootmem(prof_len*sizeof(atomic_t));
+       buffer_bytes = prof_len*sizeof(atomic_t);
+       if (!slab_is_available()) {
+               prof_buffer = alloc_bootmem(buffer_bytes);
+               return 0;
+       }
+
+       prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
+       if (prof_buffer)
+               return 0;
+
+       prof_buffer = alloc_pages_exact(buffer_bytes, GFP_KERNEL|__GFP_ZERO);
+       if (prof_buffer)
+               return 0;
+
+       prof_buffer = vmalloc(buffer_bytes);
+       if (prof_buffer)
+               return 0;
+
+       return -ENOMEM;
 }
 
 /* Profile event notifications */
@@ -527,7 +548,7 @@ static void __init profile_nop(void *unused)
 {
 }
 
-static int __init create_hash_tables(void)
+static int create_hash_tables(void)
 {
        int cpu;
 
@@ -575,14 +596,14 @@ out_cleanup:
 #define create_hash_tables()                   ({ 0; })
 #endif
 
-static int __init create_proc_profile(void)
+int create_proc_profile(void)
 {
        struct proc_dir_entry *entry;
 
        if (!prof_on)
                return 0;
        if (create_hash_tables())
-               return -1;
+               return -ENOMEM;
        entry = proc_create("profile", S_IWUSR | S_IRUGO,
                            NULL, &proc_profile_operations);
        if (!entry)