[PATCH] KVM: add VM-exit profiling

This adds the profile=kvm boot option, which enables KVM to profile VM
exits.

Use: "readprofile -m ./System.map | sort -n" to see the resulting
output:

   [...]
   18246 serial_out                               148.3415
   18945 native_flush_tlb                         378.9000
   23618 serial_in                                212.7748
   29279 __spin_unlock_irq                        622.9574
   43447 native_apic_write                        2068.9048
   52702 enable_8259A_irq                         742.2817
   54250 vgacon_scroll                             89.3740
   67394 ide_inb                                  6126.7273
   79514 copy_page_range                           98.1654
   84868 do_wp_page                                86.6000
  140266 pit_read                                 783.6089
  151436 ide_outb                                 25239.3333
  152668 native_io_delay                          21809.7143
  174783 mask_and_ack_8259A                       783.7803
  362404 native_set_pte_at                        36240.4000
 1688747 total                                      0.5009

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Avi Kivity <avi@qumranet.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 30 insertions, 0 deletions

diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index ccc06b1b91b5..714f6a7841cd 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
+#include <linux/profile.h>
 #include <asm/desc.h>
 
 #include "kvm_svm.h"
@@ -1558,6 +1559,13 @@ again:
 
 	reload_tss(vcpu);
 
+	/*
+	 * Profile KVM exit RIPs:
+	 */
+	if (unlikely(prof_on == KVM_PROFILING))
+		profile_hit(KVM_PROFILING,
+			(void *)(unsigned long)vcpu->svm->vmcb->save.rip);
+
 	stgi();
 
 	kvm_reput_irq(vcpu);
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index d4701cb4c654..ce219e3f557f 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
+#include <linux/profile.h>
 #include <asm/io.h>
 #include <asm/desc.h>
 
@@ -1859,6 +1860,12 @@ again:
 	asm ("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
 #endif
 
+	/*
+	 * Profile KVM exit RIPs:
+	 */
+	if (unlikely(prof_on == KVM_PROFILING))
+		profile_hit(KVM_PROFILING, (void *)vmcs_readl(GUEST_RIP));
+
 	kvm_run->exit_type = 0;
 	if (fail) {
 		kvm_run->exit_type = KVM_EXIT_TYPE_FAIL_ENTRY;
diff --git a/include/linux/profile.h b/include/linux/profile.h
index 5670b340c4ef..eec48f5f9348 100644
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -15,6 +15,7 @@ extern int prof_on __read_mostly;
 #define CPU_PROFILING	1
 #define SCHED_PROFILING	2
 #define SLEEP_PROFILING	3
+#define KVM_PROFILING	4
 
 struct proc_dir_entry;
 struct pt_regs;
diff --git a/kernel/profile.c b/kernel/profile.c
index 11550b2290b6..a6574a18514e 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -40,7 +40,10 @@ int (*timer_hook)(struct pt_regs *) __read_mostly;
 
 static atomic_t *prof_buffer;
 static unsigned long prof_len, prof_shift;
+
 int prof_on __read_mostly;
+EXPORT_SYMBOL_GPL(prof_on);
+
 static cpumask_t prof_cpu_mask = CPU_MASK_ALL;
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits);
@@ -52,6 +55,7 @@ static int __init profile_setup(char * str)
 {
 	static char __initdata schedstr[] = "schedule";
 	static char __initdata sleepstr[] = "sleep";
+	static char __initdata kvmstr[] = "kvm";
 	int par;
 
 	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
@@ -72,6 +76,15 @@ static int __init profile_setup(char * str)
 		printk(KERN_INFO
 			"kernel schedule profiling enabled (shift: %ld)\n",
 			prof_shift);
+	} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
+		prof_on = KVM_PROFILING;
+		if (str[strlen(kvmstr)] == ',')
+			str += strlen(kvmstr) + 1;
+		if (get_option(&str, &par))
+			prof_shift = par;
+		printk(KERN_INFO
+			"kernel KVM profiling enabled (shift: %ld)\n",
+			prof_shift);
 	} else if (get_option(&str, &par)) {
 		prof_shift = par;
 		prof_on = CPU_PROFILING;
@@ -318,6 +331,7 @@ out:
 	local_irq_restore(flags);
 	put_cpu();
 }
+EXPORT_SYMBOL_GPL(profile_hits);
 
 static int __devinit profile_cpu_callback(struct notifier_block *info,
 					unsigned long action, void *__cpu)