On Thu, 2010-03-04 at 09:00 +0800, Zhang, Yanmin wrote:
> On Wed, 2010-03-03 at 11:15 +0100, Peter Zijlstra wrote:
> > On Wed, 2010-03-03 at 17:27 +0800, Zhang, Yanmin wrote:
> > > -#ifndef perf_misc_flags
> > > -#define perf_misc_flags(regs) (user_mode(regs) ? PERF_RECORD_MISC_USER
> > > : \
> > > - PERF_RECORD_MISC_KERNEL)
> > > -#define perf_instruction_pointer(regs) instruction_pointer(regs)
> > > -#endif
> >
> > Ah, that #ifndef is for powerpc, which I think you just broke.
> Thanks for the reminder. I deleted powerpc codes when building cscope
> lib.
>
> It seems perf_save_virt_ip/perf_reset_virt_ip interfaces are ugly. I plan to
> change them to a callback function struct and kvm registers its version to
> perf.
>
> Such like:
> struct perf_guest_info_callbacks {
> int (*is_in_guest)();
> u64 (*get_guest_ip)();
> int (*copy_guest_stack)();
> int (*reset_in_guest)();
> ...
> };
> int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *);
> int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *);
>
> It's more scalable and neater.
In case you guys might lose patience, I worked out a new patch against
2.6.34-rc1.
It could work with:
#perf kvm --guest --guestkallsyms /guest/os/kernel/proc/kallsyms --guestmodules
/guest/os/proc/modules top
It also support to collect both host side and guest side at the same time:
#perf kvm --host --guest --guestkallsyms /guest/os/kernel/proc/kallsyms
--guestmodules
/guest/os/proc/modules top
The first output line of top has guest kernel/user space percentage.
Or just host side:
#perf kvm --host
As tool perf source codes have lots of changes, I am still working on perf kvm
record
and report.
---
diff -Nraup linux-2.6.34-rc1/arch/x86/include/asm/ptrace.h
linux-2.6.34-rc1_work/arch/x86/include/asm/ptrace.h
--- linux-2.6.34-rc1/arch/x86/include/asm/ptrace.h 2010-03-09
13:04:20.730596079 +0800
+++ linux-2.6.34-rc1_work/arch/x86/include/asm/ptrace.h 2010-03-10
17:06:34.228953260 +0800
@@ -167,6 +167,15 @@ static inline int user_mode(struct pt_re
#endif
}
+static inline int user_mode_cs(u16 cs)
+{
+#ifdef CONFIG_X86_32
+ return (cs & SEGMENT_RPL_MASK) == USER_RPL;
+#else
+ return !!(cs & 3);
+#endif
+}
+
static inline int user_mode_vm(struct pt_regs *regs)
{
#ifdef CONFIG_X86_32
diff -Nraup linux-2.6.34-rc1/arch/x86/kvm/vmx.c
linux-2.6.34-rc1_work/arch/x86/kvm/vmx.c
--- linux-2.6.34-rc1/arch/x86/kvm/vmx.c 2010-03-09 13:04:20.758593132 +0800
+++ linux-2.6.34-rc1_work/arch/x86/kvm/vmx.c 2010-03-10 17:11:49.709019136
+0800
@@ -26,6 +26,7 @@
#include <linux/sched.h>
#include <linux/moduleparam.h>
#include <linux/ftrace_event.h>
+#include <linux/perf_event.h>
#include "kvm_cache_regs.h"
#include "x86.h"
@@ -3632,6 +3633,43 @@ static void update_cr8_intercept(struct
vmcs_write32(TPR_THRESHOLD, irr);
}
+DEFINE_PER_CPU(int, kvm_in_guest) = {0};
+
+static void kvm_set_in_guest(void)
+{
+ percpu_write(kvm_in_guest, 1);
+}
+
+static int kvm_is_in_guest(void)
+{
+ return percpu_read(kvm_in_guest);
+}
+
+static int kvm_is_user_mode(void)
+{
+ int user_mode;
+ user_mode = user_mode_cs(vmcs_read16(GUEST_CS_SELECTOR));
+ return user_mode;
+}
+
+static u64 kvm_get_guest_ip(void)
+{
+ return vmcs_readl(GUEST_RIP);
+}
+
+static void kvm_reset_in_guest(void)
+{
+ if (percpu_read(kvm_in_guest))
+ percpu_write(kvm_in_guest, 0);
+}
+
+static struct perf_guest_info_callbacks kvm_guest_cbs = {
+ .is_in_guest = kvm_is_in_guest,
+ .is_user_mode = kvm_is_user_mode,
+ .get_guest_ip = kvm_get_guest_ip,
+ .reset_in_guest = kvm_reset_in_guest
+};
+
static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
{
u32 exit_intr_info;
@@ -3653,8 +3691,11 @@ static void vmx_complete_interrupts(stru
/* We need to handle NMIs before interrupts are enabled */
if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
- (exit_intr_info & INTR_INFO_VALID_MASK))
+ (exit_intr_info & INTR_INFO_VALID_MASK)) {
+ kvm_set_in_guest();
asm("int $2");
+ kvm_reset_in_guest();
+ }
idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
@@ -4251,6 +4292,8 @@ static int __init vmx_init(void)
if (bypass_guest_pf)
kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull);
+ perf_register_guest_info_callbacks(&kvm_guest_cbs);
+
return 0;
out3:
@@ -4266,6 +4309,8 @@ out:
static void __exit vmx_exit(void)
{
+ perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
+
free_page((unsigned long)vmx_msr_bitmap_legacy);
free_page((unsigned long)vmx_msr_bitmap_longmode);
free_page((unsigned long)vmx_io_bitmap_b);
diff -Nraup linux-2.6.34-rc1/include/linux/perf_event.h
linux-2.6.34-rc1_work/include/linux/perf_event.h
--- linux-2.6.34-rc1/include/linux/perf_event.h 2010-03-09 13:04:28.905944253
+0800
+++ linux-2.6.34-rc1_work/include/linux/perf_event.h 2010-03-10
17:06:34.228953260 +0800
@@ -287,11 +287,13 @@ struct perf_event_mmap_page {
__u64 data_tail; /* user-space written tail */
};
-#define PERF_RECORD_MISC_CPUMODE_MASK (3 << 0)
+#define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0)
#define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0)
#define PERF_RECORD_MISC_KERNEL (1 << 0)
#define PERF_RECORD_MISC_USER (2 << 0)
#define PERF_RECORD_MISC_HYPERVISOR (3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER (5 << 0)
struct perf_event_header {
__u32 type;
@@ -439,6 +441,13 @@ enum perf_callchain_context {
# include <asm/perf_event.h>
#endif
+struct perf_guest_info_callbacks {
+ int (*is_in_guest) (void);
+ int (*is_user_mode) (void);
+ u64 (*get_guest_ip) (void);
+ void (*reset_in_guest) (void);
+};
+
#ifdef CONFIG_HAVE_HW_BREAKPOINT
#include <asm/hw_breakpoint.h>
#endif
@@ -849,6 +858,10 @@ static inline void perf_event_mmap(struc
__perf_event_mmap(vma);
}
+extern u64 perf_instruction_pointer(struct pt_regs *regs);
+int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *);
+int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *);
+
extern void perf_event_comm(struct task_struct *tsk);
extern void perf_event_fork(struct task_struct *tsk);
@@ -862,12 +875,6 @@ extern void perf_event_init(void);
extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int
entry_size);
extern void perf_bp_event(struct perf_event *event, void *data);
-#ifndef perf_misc_flags
-#define perf_misc_flags(regs) (user_mode(regs) ? PERF_RECORD_MISC_USER : \
- PERF_RECORD_MISC_KERNEL)
-#define perf_instruction_pointer(regs) instruction_pointer(regs)
-#endif
-
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size,
int nmi, int sample);
@@ -902,6 +909,13 @@ perf_sw_event(u32 event_id, u64 nr, int
static inline void
perf_bp_event(struct perf_event *event, void *data) { }
+static inline int perf_register_guest_info_callbacks
+(struct perf_guest_info_callbacks *) {return 0; }
+static inline int perf_unregister_guest_info_callbacks
+(struct perf_guest_info_callbacks *) {return 0; }
+
+#define perf_instruction_pointer(event, regs) instruction_pointer(regs)
+
static inline void perf_event_mmap(struct vm_area_struct *vma) { }
static inline void perf_event_comm(struct task_struct *tsk) { }
static inline void perf_event_fork(struct task_struct *tsk) { }
diff -Nraup linux-2.6.34-rc1/kernel/perf_event.c
linux-2.6.34-rc1_work/kernel/perf_event.c
--- linux-2.6.34-rc1/kernel/perf_event.c 2010-03-09 13:04:30.085942017
+0800
+++ linux-2.6.34-rc1_work/kernel/perf_event.c 2010-03-10 17:06:34.232905199
+0800
@@ -2807,6 +2807,50 @@ __weak struct perf_callchain_entry *perf
}
/*
+ * We assume there is only KVM supporting the callbacks.
+ * Later on, we might change it to a list if there is
+ * another virtualization implementation supporting the callbacks.
+ */
+static struct perf_guest_info_callbacks *perf_guest_cbs;
+
+int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks * cbs)
+{
+ perf_guest_cbs = cbs;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks);
+
+int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *
cbs)
+{
+ perf_guest_cbs = NULL;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
+
+u64 perf_instruction_pointer(struct pt_regs *regs)
+{
+ u64 ip;
+ if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ ip = perf_guest_cbs->get_guest_ip();
+ } else
+ ip = instruction_pointer(regs);
+ return ip;
+}
+
+#ifndef perf_misc_flags
+static inline unsigned int perf_misc_flags(struct pt_regs *regs)
+{
+ if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ return perf_guest_cbs->is_user_mode() ?
+ PERF_RECORD_MISC_GUEST_USER :
+ PERF_RECORD_MISC_GUEST_KERNEL;
+ } else
+ return user_mode(regs) ? PERF_RECORD_MISC_USER :
+ PERF_RECORD_MISC_KERNEL;
+}
+#endif
+
+/*
* Output
*/
static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail,
diff -Nraup linux-2.6.34-rc1/tools/perf/builtin-diff.c
linux-2.6.34-rc1_work/tools/perf/builtin-diff.c
--- linux-2.6.34-rc1/tools/perf/builtin-diff.c 2010-03-09 13:04:31.373942905
+0800
+++ linux-2.6.34-rc1_work/tools/perf/builtin-diff.c 2010-03-10
17:06:34.232905199 +0800
@@ -222,6 +222,9 @@ int cmd_diff(int argc, const char **argv
input_new = argv[1];
} else
input_new = argv[0];
+ } else if (symbol_conf.guest_vmlinux_name ||
symbol_conf.guest_kallsyms) {
+ input_old = "perf.data.host";
+ input_new = "perf.data.guest";
}
symbol_conf.exclude_other = false;
diff -Nraup linux-2.6.34-rc1/tools/perf/builtin.h
linux-2.6.34-rc1_work/tools/perf/builtin.h
--- linux-2.6.34-rc1/tools/perf/builtin.h 2010-03-09 13:04:31.377861392
+0800
+++ linux-2.6.34-rc1_work/tools/perf/builtin.h 2010-03-10 17:06:34.232905199
+0800
@@ -32,5 +32,6 @@ extern int cmd_version(int argc, const c
extern int cmd_probe(int argc, const char **argv, const char *prefix);
extern int cmd_kmem(int argc, const char **argv, const char *prefix);
extern int cmd_lock(int argc, const char **argv, const char *prefix);
+extern int cmd_kvm(int argc, const char **argv, const char *prefix);
#endif
diff -Nraup linux-2.6.34-rc1/tools/perf/builtin-kvm.c
linux-2.6.34-rc1_work/tools/perf/builtin-kvm.c
--- linux-2.6.34-rc1/tools/perf/builtin-kvm.c 1970-01-01 08:00:00.000000000
+0800
+++ linux-2.6.34-rc1_work/tools/perf/builtin-kvm.c 2010-03-10
17:06:34.232905199 +0800
@@ -0,0 +1,123 @@
+#include "builtin.h"
+#include "perf.h"
+
+#include "util/util.h"
+#include "util/cache.h"
+#include "util/symbol.h"
+#include "util/thread.h"
+#include "util/header.h"
+#include "util/session.h"
+
+#include "util/parse-options.h"
+#include "util/trace-event.h"
+
+#include "util/debug.h"
+
+#include <sys/prctl.h>
+
+#include <semaphore.h>
+#include <pthread.h>
+#include <math.h>
+
+static char *file_name = NULL;
+static char name_buffer[256];
+
+int perf_host = 1;
+int perf_guest = 0;
+
+static const char * const kvm_usage[] = {
+ "perf kvm [<options>] {top|record|report|diff}",
+ NULL
+};
+
+static const struct option kvm_options[] = {
+ OPT_STRING('i', "input", &file_name, "file",
+ "Input file name"),
+ OPT_STRING('o', "output", &file_name, "file",
+ "Output file name"),
+ OPT_BOOLEAN(0, "guest", &perf_guest,
+ "Collect guest os data"),
+ OPT_BOOLEAN(0, "host", &perf_host,
+ "Collect guest os data"),
+ OPT_STRING(0, "guestvmlinux", &symbol_conf.guest_vmlinux_name, "file",
+ "file saving guest os vmlinux"),
+ OPT_STRING(0, "guestkallsyms", &symbol_conf.guest_kallsyms, "file",
+ "file saving guest os /proc/kallsyms"),
+ OPT_STRING(0, "guestmodules", &symbol_conf.guest_modules, "file",
+ "file saving guest os /proc/modules"),
+ OPT_END()
+};
+
+static int __cmd_record(int argc, const char **argv)
+{
+ int rec_argc, i = 0, j;
+ const char **rec_argv;
+
+ rec_argc = argc + 2;
+ rec_argv = calloc(rec_argc + 1, sizeof(char *));
+ rec_argv[i++] = strdup("record");
+ rec_argv[i++] = strdup("-o");
+ rec_argv[i++] = strdup(file_name);
+ for (j = 1; j < argc; j++, i++)
+ rec_argv[i] = argv[j];
+
+ BUG_ON(i != rec_argc);
+
+ return cmd_record(i, rec_argv, NULL);
+}
+
+static int __cmd_report(int argc, const char **argv)
+{
+ int rec_argc, i = 0, j;
+ const char **rec_argv;
+
+ rec_argc = argc + 2;
+ rec_argv = calloc(rec_argc + 1, sizeof(char *));
+ rec_argv[i++] = strdup("report");
+ rec_argv[i++] = strdup("-i");
+ rec_argv[i++] = strdup(file_name);
+ for (j = 1; j < argc; j++, i++)
+ rec_argv[i] = argv[j];
+
+ BUG_ON(i != rec_argc);
+
+ return cmd_report(i, rec_argv, NULL);
+}
+
+int cmd_kvm(int argc, const char **argv, const char *prefix __used)
+{
+ perf_host = perf_guest = 0;
+
+ argc = parse_options(argc, argv, kvm_options, kvm_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (!argc)
+ usage_with_options(kvm_usage, kvm_options);
+
+ if (!perf_host)
+ perf_guest = 1;
+
+ if (!file_name) {
+ if (perf_host && !perf_guest)
+ sprintf(name_buffer, "perf.data.host");
+ else if (!perf_host && perf_guest)
+ sprintf(name_buffer, "perf.data.guest");
+ else
+ sprintf(name_buffer, "perf.data.kvm");
+ file_name = name_buffer;
+ }
+
+ if (!strncmp(argv[0], "rec", 3)) {
+ return __cmd_record(argc, argv);
+ } else if (!strncmp(argv[0], "rep", 3)) {
+ return __cmd_report(argc, argv);
+ } else if (!strncmp(argv[0], "diff", 4)) {
+ return cmd_diff(argc, argv, NULL);
+ } else if (!strncmp(argv[0], "top", 3)) {
+ return cmd_top(argc, argv, NULL);
+ } else {
+ usage_with_options(kvm_usage, kvm_options);
+ }
+
+ return 0;
+}
+
diff -Nraup linux-2.6.34-rc1/tools/perf/builtin-top.c
linux-2.6.34-rc1_work/tools/perf/builtin-top.c
--- linux-2.6.34-rc1/tools/perf/builtin-top.c 2010-03-09 13:04:31.377861392
+0800
+++ linux-2.6.34-rc1_work/tools/perf/builtin-top.c 2010-03-10
17:06:34.232905199 +0800
@@ -409,7 +409,8 @@ static double sym_weight(const struct sy
}
static long samples;
-static long userspace_samples;
+static long kernel_samples, userspace_samples;
+static long guest_us_samples, guest_kernel_samples;
static const char CONSOLE_CLEAR[] = "[H[2J";
static void __list_insert_active_sym(struct sym_entry *syme)
@@ -449,7 +450,10 @@ static void print_sym_table(void)
int printed = 0, j;
int counter, snap = !display_weighted ? sym_counter : 0;
float samples_per_sec = samples/delay_secs;
- float ksamples_per_sec = (samples-userspace_samples)/delay_secs;
+ float ksamples_per_sec = (kernel_samples)/delay_secs;
+ float userspace_samples_per_sec = (userspace_samples)/delay_secs;
+ float guest_kernel_samples_per_sec = (guest_kernel_samples)/delay_secs;
+ float guest_us_samples_per_sec = (guest_us_samples)/delay_secs;
float sum_ksamples = 0.0;
struct sym_entry *syme, *n;
struct rb_root tmp = RB_ROOT;
@@ -457,7 +461,8 @@ static void print_sym_table(void)
int sym_width = 0, dso_width = 0, max_dso_width;
const int win_width = winsize.ws_col - 1;
- samples = userspace_samples = 0;
+ samples = kernel_samples = userspace_samples = 0;
+ guest_kernel_samples = guest_us_samples = 0;
/* Sort the active symbols */
pthread_mutex_lock(&active_symbols_lock);
@@ -488,9 +493,19 @@ static void print_sym_table(void)
puts(CONSOLE_CLEAR);
printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
- printf( " PerfTop:%8.0f irqs/sec kernel:%4.1f%% [",
- samples_per_sec,
- 100.0 -
(100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)));
+ if (!perf_guest) {
+ printf( " PerfTop:%8.0f irqs/sec kernel:%4.1f%% [",
+ samples_per_sec,
+ 100.0 -
(100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)));
+ } else {
+ printf( " PerfTop:%8.0f irqs/sec kernel:%4.1f%% user:%4.1f%%
guest kernel:%4.1f%% guest user:%4.1f%% [",
+ samples_per_sec,
+ 100.0 -
(100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)),
+ 100.0 -
(100.0*((samples_per_sec-userspace_samples_per_sec)/samples_per_sec)),
+ 100.0 -
(100.0*((samples_per_sec-guest_kernel_samples_per_sec)/samples_per_sec)),
+ 100.0 -
(100.0*((samples_per_sec-guest_us_samples_per_sec)/samples_per_sec))
+ );
+ }
if (nr_counters == 1 || !display_weighted) {
printf("%Ld", (u64)attrs[0].sample_period);
@@ -947,9 +962,17 @@ static void event__process_sample(const
return;
break;
case PERF_RECORD_MISC_KERNEL:
+ ++kernel_samples;
if (hide_kernel_symbols)
return;
break;
+ case PERF_RECORD_MISC_GUEST_KERNEL:
+ ++guest_kernel_samples;
+ break;
+ case PERF_RECORD_MISC_GUEST_USER:
+ ++guest_us_samples;
+ /* TODO: we don't process guest user from host side. */
+ return;
default:
return;
}
diff -Nraup linux-2.6.34-rc1/tools/perf/Makefile
linux-2.6.34-rc1_work/tools/perf/Makefile
--- linux-2.6.34-rc1/tools/perf/Makefile 2010-03-09 13:04:31.341942020
+0800
+++ linux-2.6.34-rc1_work/tools/perf/Makefile 2010-03-10 17:06:34.232905199
+0800
@@ -458,6 +458,7 @@ BUILTIN_OBJS += builtin-trace.o
BUILTIN_OBJS += builtin-probe.o
BUILTIN_OBJS += builtin-kmem.o
BUILTIN_OBJS += builtin-lock.o
+BUILTIN_OBJS += builtin-kvm.o
PERFLIBS = $(LIB_FILE)
diff -Nraup linux-2.6.34-rc1/tools/perf/perf.c
linux-2.6.34-rc1_work/tools/perf/perf.c
--- linux-2.6.34-rc1/tools/perf/perf.c 2010-03-09 13:04:31.377861392 +0800
+++ linux-2.6.34-rc1_work/tools/perf/perf.c 2010-03-10 17:06:34.232905199
+0800
@@ -304,6 +304,7 @@ static void handle_internal_command(int
{ "probe", cmd_probe, 0 },
{ "kmem", cmd_kmem, 0 },
{ "lock", cmd_lock, 0 },
+ { "kvm", cmd_kvm, 0 },
};
unsigned int i;
static const char ext[] = STRIP_EXTENSION;
diff -Nraup linux-2.6.34-rc1/tools/perf/perf.h
linux-2.6.34-rc1_work/tools/perf/perf.h
--- linux-2.6.34-rc1/tools/perf/perf.h 2010-03-09 13:04:16.357945701 +0800
+++ linux-2.6.34-rc1_work/tools/perf/perf.h 2010-03-10 17:06:34.236904596
+0800
@@ -131,4 +131,6 @@ struct ip_callchain {
u64 ips[0];
};
+extern int perf_host, perf_guest;
+
#endif
diff -Nraup linux-2.6.34-rc1/tools/perf/util/event.c
linux-2.6.34-rc1_work/tools/perf/util/event.c
--- linux-2.6.34-rc1/tools/perf/util/event.c 2010-03-09 13:04:31.381941876
+0800
+++ linux-2.6.34-rc1_work/tools/perf/util/event.c 2010-03-10
17:06:34.236904596 +0800
@@ -442,12 +442,16 @@ void thread__find_addr_map(struct thread
al->thread = self;
al->addr = addr;
- if (cpumode == PERF_RECORD_MISC_KERNEL) {
+ if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
al->level = 'k';
mg = &session->kmaps;
- } else if (cpumode == PERF_RECORD_MISC_USER)
+ } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
al->level = '.';
- else {
+ } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
+ al->level = 'g';
+ mg = &session->guest_kmaps;
+ } else {
+ /* TODO: We don't support guest user space. Might support late
*/
al->level = 'H';
al->map = NULL;
return;
@@ -464,10 +468,18 @@ try_again:
* "[vdso]" dso, but for now lets use the old trick of looking
* in the whole kernel symbol list.
*/
- if ((long long)al->addr < 0 && mg != &session->kmaps) {
+ if ((long long)al->addr < 0 &&
+ mg != &session->kmaps &&
+ cpumode == PERF_RECORD_MISC_KERNEL) {
mg = &session->kmaps;
goto try_again;
}
+ if ((long long)al->addr < 0 &&
+ mg != &session->guest_kmaps &&
+ cpumode == PERF_RECORD_MISC_GUEST_KERNEL) {
+ mg = &session->guest_kmaps;
+ goto try_again;
+ }
} else
al->addr = al->map->map_ip(al->map, al->addr);
}
diff -Nraup linux-2.6.34-rc1/tools/perf/util/session.c
linux-2.6.34-rc1_work/tools/perf/util/session.c
--- linux-2.6.34-rc1/tools/perf/util/session.c 2010-03-09 13:04:31.385942104
+0800
+++ linux-2.6.34-rc1_work/tools/perf/util/session.c 2010-03-10
17:06:34.236904596 +0800
@@ -54,7 +54,12 @@ out_close:
static inline int perf_session__create_kernel_maps(struct perf_session *self)
{
- return map_groups__create_kernel_maps(&self->kmaps, self->vmlinux_maps);
+ int ret;
+ ret = map_groups__create_kernel_maps(&self->kmaps, self->vmlinux_maps);
+ if (ret >= 0)
+ ret = map_groups__create_guest_kernel_maps(&self->guest_kmaps,
+ self->guest_vmlinux_maps);
+ return ret;
}
struct perf_session *perf_session__new(const char *filename, int mode, bool
force)
@@ -76,6 +81,7 @@ struct perf_session *perf_session__new(c
self->cwdlen = 0;
self->unknown_events = 0;
map_groups__init(&self->kmaps);
+ map_groups__init(&self->guest_kmaps);
if (mode == O_RDONLY) {
if (perf_session__open(self, force) < 0)
diff -Nraup linux-2.6.34-rc1/tools/perf/util/session.h
linux-2.6.34-rc1_work/tools/perf/util/session.h
--- linux-2.6.34-rc1/tools/perf/util/session.h 2010-03-09 13:04:31.385942104
+0800
+++ linux-2.6.34-rc1_work/tools/perf/util/session.h 2010-03-10
17:06:34.236904596 +0800
@@ -16,9 +16,11 @@ struct perf_session {
unsigned long size;
unsigned long mmap_window;
struct map_groups kmaps;
+ struct map_groups guest_kmaps;
struct rb_root threads;
struct thread *last_match;
struct map *vmlinux_maps[MAP__NR_TYPES];
+ struct map *guest_vmlinux_maps[MAP__NR_TYPES];
struct events_stats events_stats;
unsigned long event_total[PERF_RECORD_MAX];
unsigned long unknown_events;
@@ -83,6 +85,6 @@ static inline struct map *
perf_session__new_module_map(struct perf_session *self,
u64 start, const char *filename)
{
- return map_groups__new_module(&self->kmaps, start, filename);
+ return map_groups__new_module(&self->kmaps, start, filename, 0);
}
#endif /* __PERF_SESSION_H */
diff -Nraup linux-2.6.34-rc1/tools/perf/util/symbol.c
linux-2.6.34-rc1_work/tools/perf/util/symbol.c
--- linux-2.6.34-rc1/tools/perf/util/symbol.c 2010-03-09 13:04:31.385942104
+0800
+++ linux-2.6.34-rc1_work/tools/perf/util/symbol.c 2010-03-10
17:06:34.236904596 +0800
@@ -27,6 +27,8 @@ enum dso_origin {
DSO__ORIG_BUILDID,
DSO__ORIG_DSO,
DSO__ORIG_KMODULE,
+ DSO__ORIG_GUEST_KERNEL,
+ DSO__ORIG_GUEST_KMODULE,
DSO__ORIG_NOT_FOUND,
};
@@ -34,6 +36,8 @@ static void dsos__add(struct list_head *
static struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
static int dso__load_kernel_sym(struct dso *self, struct map *map,
symbol_filter_t filter);
+static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
+ symbol_filter_t filter);
static int vmlinux_path__nr_entries;
static char **vmlinux_path;
@@ -184,6 +188,7 @@ struct dso *dso__new(const char *name)
self->loaded = 0;
self->sorted_by_name = 0;
self->has_build_id = 0;
+ self->kernel = DSO_TYPE_USER;
}
return self;
@@ -523,13 +528,19 @@ static int dso__split_kallsyms(struct ds
char dso_name[PATH_MAX];
struct dso *dso;
- snprintf(dso_name, sizeof(dso_name), "[kernel].%d",
- kernel_range++);
+ if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+ snprintf(dso_name, sizeof(dso_name),
"[guest.kernel].%d",
+ kernel_range++);
+ else
+ snprintf(dso_name, sizeof(dso_name),
"[kernel].%d",
+ kernel_range++);
dso = dso__new(dso_name);
if (dso == NULL)
return -1;
+ dso->kernel = self->kernel;
+
curr_map = map__new2(pos->start, dso, map->type);
if (curr_map == NULL) {
dso__delete(dso);
@@ -563,7 +574,10 @@ int dso__load_kallsyms(struct dso *self,
return -1;
symbols__fixup_end(&self->symbols[map->type]);
- self->origin = DSO__ORIG_KERNEL;
+ if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+ self->origin = DSO__ORIG_GUEST_KERNEL;
+ else
+ self->origin = DSO__ORIG_KERNEL;
return dso__split_kallsyms(self, map, filter);
}
@@ -951,7 +965,7 @@ static int dso__load_sym(struct dso *sel
nr_syms = shdr.sh_size / shdr.sh_entsize;
memset(&sym, 0, sizeof(sym));
- if (!self->kernel) {
+ if (self->kernel == DSO_TYPE_USER) {
self->adjust_symbols = (ehdr.e_type == ET_EXEC ||
elf_section_by_name(elf, &ehdr, &shdr,
".gnu.prelink_undo",
@@ -983,7 +997,7 @@ static int dso__load_sym(struct dso *sel
section_name = elf_sec__name(&shdr, secstrs);
- if (self->kernel || kmodule) {
+ if (self->kernel != DSO_TYPE_USER || kmodule) {
char dso_name[PATH_MAX];
if (strcmp(section_name,
@@ -1009,6 +1023,7 @@ static int dso__load_sym(struct dso *sel
curr_dso = dso__new(dso_name);
if (curr_dso == NULL)
goto out_elf_end;
+ curr_dso->kernel = self->kernel;
curr_map = map__new2(start, curr_dso,
map->type);
if (curr_map == NULL) {
@@ -1017,9 +1032,15 @@ static int dso__load_sym(struct dso *sel
}
curr_map->map_ip = identity__map_ip;
curr_map->unmap_ip = identity__map_ip;
- curr_dso->origin = DSO__ORIG_KERNEL;
+ if (curr_dso->kernel == DSO_TYPE_GUEST_KERNEL) {
+ curr_dso->origin =
DSO__ORIG_GUEST_KERNEL;
+ dsos__add(&dsos__guest_kernel,
curr_dso);
+ } else {
+ curr_dso->origin = DSO__ORIG_KERNEL;
+ dsos__add(&dsos__kernel, curr_dso);
+ }
+
map_groups__insert(kmap->kmaps, curr_map);
- dsos__add(&dsos__kernel, curr_dso);
dso__set_loaded(curr_dso, map->type);
} else
curr_dso = curr_map->dso;
@@ -1240,6 +1261,8 @@ char dso__symtab_origin(const struct dso
[DSO__ORIG_BUILDID] = 'b',
[DSO__ORIG_DSO] = 'd',
[DSO__ORIG_KMODULE] = 'K',
+ [DSO__ORIG_GUEST_KERNEL] = 'g',
+ [DSO__ORIG_GUEST_KMODULE] = 'G',
};
if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND)
@@ -1258,8 +1281,10 @@ int dso__load(struct dso *self, struct m
dso__set_loaded(self, map->type);
- if (self->kernel)
+ if (self->kernel == DSO_TYPE_KERNEL)
return dso__load_kernel_sym(self, map, filter);
+ else if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+ return dso__load_guest_kernel_sym(self, map, filter);
name = malloc(size);
if (!name)
@@ -1463,7 +1488,7 @@ static int map_groups__set_modules_path(
static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
{
struct map *self = zalloc(sizeof(*self) +
- (dso->kernel ? sizeof(struct kmap) : 0));
+ (dso->kernel != DSO_TYPE_USER ? sizeof(struct kmap) :
0));
if (self != NULL) {
/*
* ->end will be filled after we load all the symbols
@@ -1475,11 +1500,15 @@ static struct map *map__new2(u64 start,
}
struct map *map_groups__new_module(struct map_groups *self, u64 start,
- const char *filename)
+ const char *filename, int guest)
{
struct map *map;
struct dso *dso = __dsos__findnew(&dsos__kernel, filename);
+ if (!guest)
+ dso = __dsos__findnew(&dsos__kernel, filename);
+ else
+ dso = __dsos__findnew(&dsos__guest_kernel, filename);
if (dso == NULL)
return NULL;
@@ -1487,16 +1516,20 @@ struct map *map_groups__new_module(struc
if (map == NULL)
return NULL;
- dso->origin = DSO__ORIG_KMODULE;
+ if (guest)
+ dso->origin = DSO__ORIG_GUEST_KMODULE;
+ else
+ dso->origin = DSO__ORIG_KMODULE;
map_groups__insert(self, map);
return map;
}
-static int map_groups__create_modules(struct map_groups *self)
+static int __map_groups__create_modules(struct map_groups *self,
+ const char * filename, int guest)
{
char *line = NULL;
size_t n;
- FILE *file = fopen("/proc/modules", "r");
+ FILE *file = fopen(filename, "r");
struct map *map;
if (file == NULL)
@@ -1530,16 +1563,17 @@ static int map_groups__create_modules(st
*sep = '\0';
snprintf(name, sizeof(name), "[%s]", line);
- map = map_groups__new_module(self, start, name);
+ map = map_groups__new_module(self, start, name, guest);
if (map == NULL)
goto out_delete_line;
- dso__kernel_module_get_build_id(map->dso);
+ if (!guest)
+ dso__kernel_module_get_build_id(map->dso);
}
free(line);
fclose(file);
- return map_groups__set_modules_path(self);
+ return 0;
out_delete_line:
free(line);
@@ -1547,6 +1581,21 @@ out_failure:
return -1;
}
+static int map_groups__create_modules(struct map_groups *self)
+{
+ int ret;
+
+ ret = __map_groups__create_modules(self, "/proc/modules", 0);
+ if (ret >= 0)
+ ret = map_groups__set_modules_path(self);
+ return ret;
+}
+
+static int map_groups__create_guest_modules(struct map_groups *self)
+{
+ return __map_groups__create_modules(self, symbol_conf.guest_modules,
1);
+}
+
static int dso__load_vmlinux(struct dso *self, struct map *map,
const char *vmlinux, symbol_filter_t filter)
{
@@ -1706,8 +1755,44 @@ out_fixup:
return err;
}
+static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
+ symbol_filter_t filter)
+{
+ int err;
+ const char *kallsyms_filename;
+ /*
+ * if the user specified a vmlinux filename, use it and only
+ * it, reporting errors to the user if it cannot be used.
+ * Or use file guest_kallsyms inputted by user on commandline
+ */
+ if (symbol_conf.guest_vmlinux_name != NULL) {
+ err = dso__load_vmlinux(self, map,
+ symbol_conf.guest_vmlinux_name, filter);
+ goto out_try_fixup;
+ }
+
+ kallsyms_filename = symbol_conf.guest_kallsyms;
+ if (!kallsyms_filename)
+ return -1;
+ err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+ if (err > 0)
+ pr_debug("Using %s for symbols\n", kallsyms_filename);
+
+out_try_fixup:
+ if (err > 0) {
+ if (kallsyms_filename != NULL)
+ dso__set_long_name(self,
strdup("[guest.kernel.kallsyms]"));
+ map__fixup_start(map);
+ map__fixup_end(map);
+ }
+
+ return err;
+}
+
LIST_HEAD(dsos__user);
LIST_HEAD(dsos__kernel);
+LIST_HEAD(dsos__guest_user);
+LIST_HEAD(dsos__guest_kernel);
static void dsos__add(struct list_head *head, struct dso *dso)
{
@@ -1754,6 +1839,8 @@ void dsos__fprintf(FILE *fp)
{
__dsos__fprintf(&dsos__kernel, fp);
__dsos__fprintf(&dsos__user, fp);
+ __dsos__fprintf(&dsos__guest_kernel, fp);
+ __dsos__fprintf(&dsos__guest_user, fp);
}
static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
@@ -1783,7 +1870,19 @@ struct dso *dso__new_kernel(const char *
if (self != NULL) {
self->short_name = "[kernel]";
- self->kernel = 1;
+ self->kernel = DSO_TYPE_KERNEL;
+ }
+
+ return self;
+}
+
+struct dso *dso__new_guest_kernel(const char *name)
+{
+ struct dso *self = dso__new(name ?: "[guest.kernel.kallsyms]");
+
+ if (self != NULL) {
+ self->short_name = "[guest.kernel]";
+ self->kernel = DSO_TYPE_GUEST_KERNEL;
}
return self;
@@ -1808,6 +1907,16 @@ static struct dso *dsos__create_kernel(c
return kernel;
}
+static struct dso *dsos__create_guest_kernel(const char *vmlinux)
+{
+ struct dso *kernel = dso__new_guest_kernel(vmlinux);
+
+ kernel->kernel = DSO_TYPE_GUEST_KERNEL;
+ if (kernel != NULL)
+ dsos__add(&dsos__guest_kernel, kernel);
+ return kernel;
+}
+
int __map_groups__create_kernel_maps(struct map_groups *self,
struct map *vmlinux_maps[MAP__NR_TYPES],
struct dso *kernel)
@@ -1956,3 +2065,24 @@ int map_groups__create_kernel_maps(struc
map_groups__fixup_end(self);
return 0;
}
+
+int map_groups__create_guest_kernel_maps(struct map_groups *self,
+ struct map *vmlinux_maps[MAP__NR_TYPES])
+{
+ struct dso *kernel =
dsos__create_guest_kernel(symbol_conf.guest_vmlinux_name);
+
+ if (kernel == NULL)
+ return -1;
+
+ if (__map_groups__create_kernel_maps(self, vmlinux_maps, kernel) < 0)
+ return -1;
+
+ if (symbol_conf.use_modules && map_groups__create_guest_modules(self) <
0)
+ pr_debug("Problems creating module maps, continuing
anyway...\n");
+ /*
+ * Now that we have all the maps created, just set the ->end of them:
+ */
+ map_groups__fixup_end(self);
+ return 0;
+}
+
diff -Nraup linux-2.6.34-rc1/tools/perf/util/symbol.h
linux-2.6.34-rc1_work/tools/perf/util/symbol.h
--- linux-2.6.34-rc1/tools/perf/util/symbol.h 2010-03-09 13:04:31.385942104
+0800
+++ linux-2.6.34-rc1_work/tools/perf/util/symbol.h 2010-03-10
17:06:34.236904596 +0800
@@ -66,7 +66,10 @@ struct symbol_conf {
full_paths;
const char *vmlinux_name,
*field_sep;
- char *dso_list_str,
+ const char *guest_vmlinux_name,
+ *guest_kallsyms,
+ *guest_modules;
+ char *dso_list_str,
*comm_list_str,
*sym_list_str,
*col_width_list_str;
@@ -97,6 +100,12 @@ struct addr_location {
bool filtered;
};
+enum dso_kernel_type {
+ DSO_TYPE_USER = 0,
+ DSO_TYPE_KERNEL,
+ DSO_TYPE_GUEST_KERNEL
+};
+
struct dso {
struct list_head node;
struct rb_root symbols[MAP__NR_TYPES];
@@ -104,7 +113,7 @@ struct dso {
u8 adjust_symbols:1;
u8 slen_calculated:1;
u8 has_build_id:1;
- u8 kernel:1;
+ enum dso_kernel_type kernel;
u8 hit:1;
unsigned char origin;
u8 sorted_by_name;
@@ -118,6 +127,7 @@ struct dso {
struct dso *dso__new(const char *name);
struct dso *dso__new_kernel(const char *name);
+struct dso *dso__new_guest_kernel(const char *name);
void dso__delete(struct dso *self);
bool dso__loaded(const struct dso *self, enum map_type type);
@@ -130,7 +140,7 @@ static inline void dso__set_loaded(struc
void dso__sort_by_name(struct dso *self, enum map_type type);
-extern struct list_head dsos__user, dsos__kernel;
+extern struct list_head dsos__user, dsos__kernel, dsos__guest_user,
dsos__guest_kernel;
struct dso *__dsos__findnew(struct list_head *head, const char *name);
diff -Nraup linux-2.6.34-rc1/tools/perf/util/thread.h
linux-2.6.34-rc1_work/tools/perf/util/thread.h
--- linux-2.6.34-rc1/tools/perf/util/thread.h 2010-03-09 13:04:31.385942104
+0800
+++ linux-2.6.34-rc1_work/tools/perf/util/thread.h 2010-03-10
17:06:34.236904596 +0800
@@ -79,6 +79,9 @@ int __map_groups__create_kernel_maps(str
int map_groups__create_kernel_maps(struct map_groups *self,
struct map *vmlinux_maps[MAP__NR_TYPES]);
+int map_groups__create_guest_kernel_maps(struct map_groups *self,
+ struct map *vmlinux_maps[MAP__NR_TYPES]);
+
struct map *map_groups__new_module(struct map_groups *self, u64 start,
- const char *filename);
+ const char *filename, int guest);
#endif /* __PERF_THREAD_H */
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
