linux/arch/x86/oprofile/nmi_int.c

804 lines
17 KiB
C
Raw Normal View History

/**
* @file nmi_int.c
*
* @remark Copyright 2002-2009 OProfile authors
* @remark Read the file COPYING
*
* @author John Levon <levon@movementarian.org>
* @author Robert Richter <robert.richter@amd.com>
* @author Barry Kasindorf <barry.kasindorf@amd.com>
* @author Jason Yeh <jason.yeh@amd.com>
* @author Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
*/
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/oprofile.h>
#include <linux/sysdev.h>
#include <linux/slab.h>
#include <linux/moduleparam.h>
#include <linux/kdebug.h>
#include <linux/cpu.h>
#include <asm/nmi.h>
#include <asm/msr.h>
#include <asm/apic.h>
#include "op_counter.h"
#include "op_x86_model.h"
static struct op_x86_model_spec *model;
static DEFINE_PER_CPU(struct op_msrs, cpu_msrs);
static DEFINE_PER_CPU(unsigned long, saved_lvtpc);
/* must be protected with get_online_cpus()/put_online_cpus(): */
static int nmi_enabled;
static int ctr_running;
struct op_counter_config counter_config[OP_MAX_COUNTER];
/* common functions */
u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
struct op_counter_config *counter_config)
{
u64 val = 0;
u16 event = (u16)counter_config->event;
val |= ARCH_PERFMON_EVENTSEL_INT;
val |= counter_config->user ? ARCH_PERFMON_EVENTSEL_USR : 0;
val |= counter_config->kernel ? ARCH_PERFMON_EVENTSEL_OS : 0;
val |= (counter_config->unit_mask & 0xFF) << 8;
event &= model->event_mask ? model->event_mask : 0xFF;
val |= event & 0xFF;
val |= (event & 0x0F00) << 24;
return val;
}
static int profile_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
{
struct die_args *args = (struct die_args *)data;
int ret = NOTIFY_DONE;
switch (val) {
case DIE_NMI:
if (ctr_running)
model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs));
else if (!nmi_enabled)
break;
else
model->stop(&__get_cpu_var(cpu_msrs));
ret = NOTIFY_STOP;
break;
default:
break;
}
return ret;
}
static void nmi_cpu_save_registers(struct op_msrs *msrs)
{
struct op_msr *counters = msrs->counters;
struct op_msr *controls = msrs->controls;
unsigned int i;
for (i = 0; i < model->num_counters; ++i) {
if (counters[i].addr)
rdmsrl(counters[i].addr, counters[i].saved);
}
for (i = 0; i < model->num_controls; ++i) {
if (controls[i].addr)
rdmsrl(controls[i].addr, controls[i].saved);
}
}
static void nmi_cpu_start(void *dummy)
{
struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
oprofile/x86: fix uninitialized counter usage during cpu hotplug This fixes a NULL pointer dereference that is triggered when taking a cpu offline after oprofile was initialized, e.g.: $ opcontrol --init $ opcontrol --start-daemon $ opcontrol --shutdown $ opcontrol --deinit $ echo 0 > /sys/devices/system/cpu/cpu1/online See the crash dump below. Though the counter has been disabled the cpu notifier is still active and trying to use already freed counter data. This fix is for linux-stable. To proper fix this, the hotplug code must be rewritten. Thus I will leave a WARN_ON_ONCE() message with this patch. BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<ffffffff8132ad57>] op_amd_stop+0x2d/0x8e PGD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/system/cpu/cpu1/online CPU 1 Modules linked in: Pid: 0, comm: swapper Not tainted 2.6.34-rc5-oprofile-x86_64-standard-00210-g8c00f06 #16 Anaheim/Anaheim RIP: 0010:[<ffffffff8132ad57>] [<ffffffff8132ad57>] op_amd_stop+0x2d/0x8e RSP: 0018:ffff880001843f28 EFLAGS: 00010006 RAX: 0000000000000000 RBX: 0000000000000000 RCX: dead000000200200 RDX: ffff880001843f68 RSI: dead000000100100 RDI: 0000000000000000 RBP: ffff880001843f48 R08: 0000000000000000 R09: ffff880001843f08 R10: ffffffff8102c9a5 R11: ffff88000184ea80 R12: 0000000000000000 R13: ffff88000184f6c0 R14: 0000000000000000 R15: 0000000000000000 FS: 00007fec6a92e6f0(0000) GS:ffff880001840000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000000 CR3: 000000000163b000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 0, threadinfo ffff88042fcd8000, task ffff88042fcd51d0) Stack: ffff880001843f48 0000000000000001 ffff88042e9f7d38 ffff880001843f68 <0> ffff880001843f58 ffffffff8132a602 ffff880001843f98 ffffffff810521b3 <0> ffff880001843f68 ffff880001843f68 ffff880001843f88 ffff88042fcd9fd8 Call Trace: <IRQ> [<ffffffff8132a602>] nmi_cpu_stop+0x21/0x23 [<ffffffff810521b3>] generic_smp_call_function_single_interrupt+0xdf/0x11b [<ffffffff8101804f>] smp_call_function_single_interrupt+0x22/0x31 [<ffffffff810029f3>] call_function_single_interrupt+0x13/0x20 <EOI> [<ffffffff8102c9a5>] ? wake_up_process+0x10/0x12 [<ffffffff81008701>] ? default_idle+0x22/0x37 [<ffffffff8100896d>] c1e_idle+0xdf/0xe6 [<ffffffff813f1170>] ? atomic_notifier_call_chain+0x13/0x15 [<ffffffff810012fb>] cpu_idle+0x4b/0x7e [<ffffffff813e8a4e>] start_secondary+0x1ae/0x1b2 Code: 89 e5 41 55 49 89 fd 41 54 45 31 e4 53 31 db 48 83 ec 08 89 df e8 be f8 ff ff 48 98 48 83 3c c5 10 67 7a 81 00 74 1f 49 8b 45 08 <42> 8b 0c 20 0f 32 48 c1 e2 20 25 ff ff bf ff 48 09 d0 48 89 c2 RIP [<ffffffff8132ad57>] op_amd_stop+0x2d/0x8e RSP <ffff880001843f28> CR2: 0000000000000000 ---[ end trace 679ac372d674b757 ]--- Kernel panic - not syncing: Fatal exception in interrupt Pid: 0, comm: swapper Tainted: G D 2.6.34-rc5-oprofile-x86_64-standard-00210-g8c00f06 #16 Call Trace: <IRQ> [<ffffffff813ebd6a>] panic+0x9e/0x10c [<ffffffff810474b0>] ? up+0x34/0x39 [<ffffffff81031ccc>] ? kmsg_dump+0x112/0x12c [<ffffffff813eeff1>] oops_end+0x81/0x8e [<ffffffff8101efee>] no_context+0x1f3/0x202 [<ffffffff8101f1b7>] __bad_area_nosemaphore+0x1ba/0x1e0 [<ffffffff81028d24>] ? enqueue_task_fair+0x16d/0x17a [<ffffffff810264dc>] ? activate_task+0x42/0x53 [<ffffffff8102c967>] ? try_to_wake_up+0x272/0x284 [<ffffffff8101f1eb>] bad_area_nosemaphore+0xe/0x10 [<ffffffff813f0f3f>] do_page_fault+0x1c8/0x37c [<ffffffff81028d24>] ? enqueue_task_fair+0x16d/0x17a [<ffffffff813ee55f>] page_fault+0x1f/0x30 [<ffffffff8102c9a5>] ? wake_up_process+0x10/0x12 [<ffffffff8132ad57>] ? op_amd_stop+0x2d/0x8e [<ffffffff8132ad46>] ? op_amd_stop+0x1c/0x8e [<ffffffff8132a602>] nmi_cpu_stop+0x21/0x23 [<ffffffff810521b3>] generic_smp_call_function_single_interrupt+0xdf/0x11b [<ffffffff8101804f>] smp_call_function_single_interrupt+0x22/0x31 [<ffffffff810029f3>] call_function_single_interrupt+0x13/0x20 <EOI> [<ffffffff8102c9a5>] ? wake_up_process+0x10/0x12 [<ffffffff81008701>] ? default_idle+0x22/0x37 [<ffffffff8100896d>] c1e_idle+0xdf/0xe6 [<ffffffff813f1170>] ? atomic_notifier_call_chain+0x13/0x15 [<ffffffff810012fb>] cpu_idle+0x4b/0x7e [<ffffffff813e8a4e>] start_secondary+0x1ae/0x1b2 ------------[ cut here ]------------ WARNING: at /local/rrichter/.source/linux/arch/x86/kernel/smp.c:118 native_smp_send_reschedule+0x27/0x53() Hardware name: Anaheim Modules linked in: Pid: 0, comm: swapper Tainted: G D 2.6.34-rc5-oprofile-x86_64-standard-00210-g8c00f06 #16 Call Trace: <IRQ> [<ffffffff81017f32>] ? native_smp_send_reschedule+0x27/0x53 [<ffffffff81030ee2>] warn_slowpath_common+0x77/0xa4 [<ffffffff81030f1e>] warn_slowpath_null+0xf/0x11 [<ffffffff81017f32>] native_smp_send_reschedule+0x27/0x53 [<ffffffff8102634b>] resched_task+0x60/0x62 [<ffffffff8102653a>] check_preempt_curr_idle+0x10/0x12 [<ffffffff8102c8ea>] try_to_wake_up+0x1f5/0x284 [<ffffffff8102c986>] default_wake_function+0xd/0xf [<ffffffff810a110d>] pollwake+0x57/0x5a [<ffffffff8102c979>] ? default_wake_function+0x0/0xf [<ffffffff81026be5>] __wake_up_common+0x46/0x75 [<ffffffff81026ed0>] __wake_up+0x38/0x50 [<ffffffff81031694>] printk_tick+0x39/0x3b [<ffffffff8103ac37>] update_process_times+0x3f/0x5c [<ffffffff8104dc63>] tick_periodic+0x5d/0x69 [<ffffffff8104dc90>] tick_handle_periodic+0x21/0x71 [<ffffffff81018fd0>] smp_apic_timer_interrupt+0x82/0x95 [<ffffffff81002853>] apic_timer_interrupt+0x13/0x20 [<ffffffff81030cb5>] ? panic_blink_one_second+0x0/0x7b [<ffffffff813ebdd6>] ? panic+0x10a/0x10c [<ffffffff810474b0>] ? up+0x34/0x39 [<ffffffff81031ccc>] ? kmsg_dump+0x112/0x12c [<ffffffff813eeff1>] ? oops_end+0x81/0x8e [<ffffffff8101efee>] ? no_context+0x1f3/0x202 [<ffffffff8101f1b7>] ? __bad_area_nosemaphore+0x1ba/0x1e0 [<ffffffff81028d24>] ? enqueue_task_fair+0x16d/0x17a [<ffffffff810264dc>] ? activate_task+0x42/0x53 [<ffffffff8102c967>] ? try_to_wake_up+0x272/0x284 [<ffffffff8101f1eb>] ? bad_area_nosemaphore+0xe/0x10 [<ffffffff813f0f3f>] ? do_page_fault+0x1c8/0x37c [<ffffffff81028d24>] ? enqueue_task_fair+0x16d/0x17a [<ffffffff813ee55f>] ? page_fault+0x1f/0x30 [<ffffffff8102c9a5>] ? wake_up_process+0x10/0x12 [<ffffffff8132ad57>] ? op_amd_stop+0x2d/0x8e [<ffffffff8132ad46>] ? op_amd_stop+0x1c/0x8e [<ffffffff8132a602>] ? nmi_cpu_stop+0x21/0x23 [<ffffffff810521b3>] ? generic_smp_call_function_single_interrupt+0xdf/0x11b [<ffffffff8101804f>] ? smp_call_function_single_interrupt+0x22/0x31 [<ffffffff810029f3>] ? call_function_single_interrupt+0x13/0x20 <EOI> [<ffffffff8102c9a5>] ? wake_up_process+0x10/0x12 [<ffffffff81008701>] ? default_idle+0x22/0x37 [<ffffffff8100896d>] ? c1e_idle+0xdf/0xe6 [<ffffffff813f1170>] ? atomic_notifier_call_chain+0x13/0x15 [<ffffffff810012fb>] ? cpu_idle+0x4b/0x7e [<ffffffff813e8a4e>] ? start_secondary+0x1ae/0x1b2 ---[ end trace 679ac372d674b758 ]--- Cc: Andi Kleen <andi@firstfloor.org> Cc: stable <stable@kernel.org> Signed-off-by: Robert Richter <robert.richter@amd.com>
2010-05-03 17:44:32 +00:00
if (!msrs->controls)
WARN_ON_ONCE(1);
else
model->start(msrs);
}
static int nmi_start(void)
{
get_online_cpus();
on_each_cpu(nmi_cpu_start, NULL, 1);
ctr_running = 1;
put_online_cpus();
return 0;
}
static void nmi_cpu_stop(void *dummy)
{
struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
oprofile/x86: fix uninitialized counter usage during cpu hotplug This fixes a NULL pointer dereference that is triggered when taking a cpu offline after oprofile was initialized, e.g.: $ opcontrol --init $ opcontrol --start-daemon $ opcontrol --shutdown $ opcontrol --deinit $ echo 0 > /sys/devices/system/cpu/cpu1/online See the crash dump below. Though the counter has been disabled the cpu notifier is still active and trying to use already freed counter data. This fix is for linux-stable. To proper fix this, the hotplug code must be rewritten. Thus I will leave a WARN_ON_ONCE() message with this patch. BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<ffffffff8132ad57>] op_amd_stop+0x2d/0x8e PGD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/system/cpu/cpu1/online CPU 1 Modules linked in: Pid: 0, comm: swapper Not tainted 2.6.34-rc5-oprofile-x86_64-standard-00210-g8c00f06 #16 Anaheim/Anaheim RIP: 0010:[<ffffffff8132ad57>] [<ffffffff8132ad57>] op_amd_stop+0x2d/0x8e RSP: 0018:ffff880001843f28 EFLAGS: 00010006 RAX: 0000000000000000 RBX: 0000000000000000 RCX: dead000000200200 RDX: ffff880001843f68 RSI: dead000000100100 RDI: 0000000000000000 RBP: ffff880001843f48 R08: 0000000000000000 R09: ffff880001843f08 R10: ffffffff8102c9a5 R11: ffff88000184ea80 R12: 0000000000000000 R13: ffff88000184f6c0 R14: 0000000000000000 R15: 0000000000000000 FS: 00007fec6a92e6f0(0000) GS:ffff880001840000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000000 CR3: 000000000163b000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 0, threadinfo ffff88042fcd8000, task ffff88042fcd51d0) Stack: ffff880001843f48 0000000000000001 ffff88042e9f7d38 ffff880001843f68 <0> ffff880001843f58 ffffffff8132a602 ffff880001843f98 ffffffff810521b3 <0> ffff880001843f68 ffff880001843f68 ffff880001843f88 ffff88042fcd9fd8 Call Trace: <IRQ> [<ffffffff8132a602>] nmi_cpu_stop+0x21/0x23 [<ffffffff810521b3>] generic_smp_call_function_single_interrupt+0xdf/0x11b [<ffffffff8101804f>] smp_call_function_single_interrupt+0x22/0x31 [<ffffffff810029f3>] call_function_single_interrupt+0x13/0x20 <EOI> [<ffffffff8102c9a5>] ? wake_up_process+0x10/0x12 [<ffffffff81008701>] ? default_idle+0x22/0x37 [<ffffffff8100896d>] c1e_idle+0xdf/0xe6 [<ffffffff813f1170>] ? atomic_notifier_call_chain+0x13/0x15 [<ffffffff810012fb>] cpu_idle+0x4b/0x7e [<ffffffff813e8a4e>] start_secondary+0x1ae/0x1b2 Code: 89 e5 41 55 49 89 fd 41 54 45 31 e4 53 31 db 48 83 ec 08 89 df e8 be f8 ff ff 48 98 48 83 3c c5 10 67 7a 81 00 74 1f 49 8b 45 08 <42> 8b 0c 20 0f 32 48 c1 e2 20 25 ff ff bf ff 48 09 d0 48 89 c2 RIP [<ffffffff8132ad57>] op_amd_stop+0x2d/0x8e RSP <ffff880001843f28> CR2: 0000000000000000 ---[ end trace 679ac372d674b757 ]--- Kernel panic - not syncing: Fatal exception in interrupt Pid: 0, comm: swapper Tainted: G D 2.6.34-rc5-oprofile-x86_64-standard-00210-g8c00f06 #16 Call Trace: <IRQ> [<ffffffff813ebd6a>] panic+0x9e/0x10c [<ffffffff810474b0>] ? up+0x34/0x39 [<ffffffff81031ccc>] ? kmsg_dump+0x112/0x12c [<ffffffff813eeff1>] oops_end+0x81/0x8e [<ffffffff8101efee>] no_context+0x1f3/0x202 [<ffffffff8101f1b7>] __bad_area_nosemaphore+0x1ba/0x1e0 [<ffffffff81028d24>] ? enqueue_task_fair+0x16d/0x17a [<ffffffff810264dc>] ? activate_task+0x42/0x53 [<ffffffff8102c967>] ? try_to_wake_up+0x272/0x284 [<ffffffff8101f1eb>] bad_area_nosemaphore+0xe/0x10 [<ffffffff813f0f3f>] do_page_fault+0x1c8/0x37c [<ffffffff81028d24>] ? enqueue_task_fair+0x16d/0x17a [<ffffffff813ee55f>] page_fault+0x1f/0x30 [<ffffffff8102c9a5>] ? wake_up_process+0x10/0x12 [<ffffffff8132ad57>] ? op_amd_stop+0x2d/0x8e [<ffffffff8132ad46>] ? op_amd_stop+0x1c/0x8e [<ffffffff8132a602>] nmi_cpu_stop+0x21/0x23 [<ffffffff810521b3>] generic_smp_call_function_single_interrupt+0xdf/0x11b [<ffffffff8101804f>] smp_call_function_single_interrupt+0x22/0x31 [<ffffffff810029f3>] call_function_single_interrupt+0x13/0x20 <EOI> [<ffffffff8102c9a5>] ? wake_up_process+0x10/0x12 [<ffffffff81008701>] ? default_idle+0x22/0x37 [<ffffffff8100896d>] c1e_idle+0xdf/0xe6 [<ffffffff813f1170>] ? atomic_notifier_call_chain+0x13/0x15 [<ffffffff810012fb>] cpu_idle+0x4b/0x7e [<ffffffff813e8a4e>] start_secondary+0x1ae/0x1b2 ------------[ cut here ]------------ WARNING: at /local/rrichter/.source/linux/arch/x86/kernel/smp.c:118 native_smp_send_reschedule+0x27/0x53() Hardware name: Anaheim Modules linked in: Pid: 0, comm: swapper Tainted: G D 2.6.34-rc5-oprofile-x86_64-standard-00210-g8c00f06 #16 Call Trace: <IRQ> [<ffffffff81017f32>] ? native_smp_send_reschedule+0x27/0x53 [<ffffffff81030ee2>] warn_slowpath_common+0x77/0xa4 [<ffffffff81030f1e>] warn_slowpath_null+0xf/0x11 [<ffffffff81017f32>] native_smp_send_reschedule+0x27/0x53 [<ffffffff8102634b>] resched_task+0x60/0x62 [<ffffffff8102653a>] check_preempt_curr_idle+0x10/0x12 [<ffffffff8102c8ea>] try_to_wake_up+0x1f5/0x284 [<ffffffff8102c986>] default_wake_function+0xd/0xf [<ffffffff810a110d>] pollwake+0x57/0x5a [<ffffffff8102c979>] ? default_wake_function+0x0/0xf [<ffffffff81026be5>] __wake_up_common+0x46/0x75 [<ffffffff81026ed0>] __wake_up+0x38/0x50 [<ffffffff81031694>] printk_tick+0x39/0x3b [<ffffffff8103ac37>] update_process_times+0x3f/0x5c [<ffffffff8104dc63>] tick_periodic+0x5d/0x69 [<ffffffff8104dc90>] tick_handle_periodic+0x21/0x71 [<ffffffff81018fd0>] smp_apic_timer_interrupt+0x82/0x95 [<ffffffff81002853>] apic_timer_interrupt+0x13/0x20 [<ffffffff81030cb5>] ? panic_blink_one_second+0x0/0x7b [<ffffffff813ebdd6>] ? panic+0x10a/0x10c [<ffffffff810474b0>] ? up+0x34/0x39 [<ffffffff81031ccc>] ? kmsg_dump+0x112/0x12c [<ffffffff813eeff1>] ? oops_end+0x81/0x8e [<ffffffff8101efee>] ? no_context+0x1f3/0x202 [<ffffffff8101f1b7>] ? __bad_area_nosemaphore+0x1ba/0x1e0 [<ffffffff81028d24>] ? enqueue_task_fair+0x16d/0x17a [<ffffffff810264dc>] ? activate_task+0x42/0x53 [<ffffffff8102c967>] ? try_to_wake_up+0x272/0x284 [<ffffffff8101f1eb>] ? bad_area_nosemaphore+0xe/0x10 [<ffffffff813f0f3f>] ? do_page_fault+0x1c8/0x37c [<ffffffff81028d24>] ? enqueue_task_fair+0x16d/0x17a [<ffffffff813ee55f>] ? page_fault+0x1f/0x30 [<ffffffff8102c9a5>] ? wake_up_process+0x10/0x12 [<ffffffff8132ad57>] ? op_amd_stop+0x2d/0x8e [<ffffffff8132ad46>] ? op_amd_stop+0x1c/0x8e [<ffffffff8132a602>] ? nmi_cpu_stop+0x21/0x23 [<ffffffff810521b3>] ? generic_smp_call_function_single_interrupt+0xdf/0x11b [<ffffffff8101804f>] ? smp_call_function_single_interrupt+0x22/0x31 [<ffffffff810029f3>] ? call_function_single_interrupt+0x13/0x20 <EOI> [<ffffffff8102c9a5>] ? wake_up_process+0x10/0x12 [<ffffffff81008701>] ? default_idle+0x22/0x37 [<ffffffff8100896d>] ? c1e_idle+0xdf/0xe6 [<ffffffff813f1170>] ? atomic_notifier_call_chain+0x13/0x15 [<ffffffff810012fb>] ? cpu_idle+0x4b/0x7e [<ffffffff813e8a4e>] ? start_secondary+0x1ae/0x1b2 ---[ end trace 679ac372d674b758 ]--- Cc: Andi Kleen <andi@firstfloor.org> Cc: stable <stable@kernel.org> Signed-off-by: Robert Richter <robert.richter@amd.com>
2010-05-03 17:44:32 +00:00
if (!msrs->controls)
WARN_ON_ONCE(1);
else
model->stop(msrs);
}
static void nmi_stop(void)
{
get_online_cpus();
on_each_cpu(nmi_cpu_stop, NULL, 1);
ctr_running = 0;
put_online_cpus();
}
#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
static DEFINE_PER_CPU(int, switch_index);
static inline int has_mux(void)
{
return !!model->switch_ctrl;
}
inline int op_x86_phys_to_virt(int phys)
{
return __this_cpu_read(switch_index) + phys;
}
inline int op_x86_virt_to_phys(int virt)
{
return virt % model->num_counters;
}
static void nmi_shutdown_mux(void)
{
int i;
if (!has_mux())
return;
for_each_possible_cpu(i) {
kfree(per_cpu(cpu_msrs, i).multiplex);
per_cpu(cpu_msrs, i).multiplex = NULL;
per_cpu(switch_index, i) = 0;
}
}
static int nmi_setup_mux(void)
{
size_t multiplex_size =
sizeof(struct op_msr) * model->num_virt_counters;
int i;
if (!has_mux())
return 1;
for_each_possible_cpu(i) {
per_cpu(cpu_msrs, i).multiplex =
kzalloc(multiplex_size, GFP_KERNEL);
if (!per_cpu(cpu_msrs, i).multiplex)
return 0;
}
return 1;
}
static void nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs)
{
int i;
struct op_msr *multiplex = msrs->multiplex;
if (!has_mux())
return;
for (i = 0; i < model->num_virt_counters; ++i) {
if (counter_config[i].enabled) {
multiplex[i].saved = -(u64)counter_config[i].count;
} else {
multiplex[i].saved = 0;
}
}
per_cpu(switch_index, cpu) = 0;
}
static void nmi_cpu_save_mpx_registers(struct op_msrs *msrs)
{
struct op_msr *counters = msrs->counters;
struct op_msr *multiplex = msrs->multiplex;
int i;
for (i = 0; i < model->num_counters; ++i) {
int virt = op_x86_phys_to_virt(i);
if (counters[i].addr)
rdmsrl(counters[i].addr, multiplex[virt].saved);
}
}
static void nmi_cpu_restore_mpx_registers(struct op_msrs *msrs)
{
struct op_msr *counters = msrs->counters;
struct op_msr *multiplex = msrs->multiplex;
int i;
for (i = 0; i < model->num_counters; ++i) {
int virt = op_x86_phys_to_virt(i);
if (counters[i].addr)
wrmsrl(counters[i].addr, multiplex[virt].saved);
}
}
static void nmi_cpu_switch(void *dummy)
{
int cpu = smp_processor_id();
int si = per_cpu(switch_index, cpu);
struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu);
nmi_cpu_stop(NULL);
nmi_cpu_save_mpx_registers(msrs);
/* move to next set */
si += model->num_counters;
if ((si >= model->num_virt_counters) || (counter_config[si].count == 0))
per_cpu(switch_index, cpu) = 0;
else
per_cpu(switch_index, cpu) = si;
model->switch_ctrl(model, msrs);
nmi_cpu_restore_mpx_registers(msrs);
nmi_cpu_start(NULL);
}
/*
* Quick check to see if multiplexing is necessary.
* The check should be sufficient since counters are used
* in ordre.
*/
static int nmi_multiplex_on(void)
{
return counter_config[model->num_counters].count ? 0 : -EINVAL;
}
static int nmi_switch_event(void)
{
if (!has_mux())
return -ENOSYS; /* not implemented */
if (nmi_multiplex_on() < 0)
return -EINVAL; /* not necessary */
get_online_cpus();
if (ctr_running)
on_each_cpu(nmi_cpu_switch, NULL, 1);
put_online_cpus();
return 0;
}
static inline void mux_init(struct oprofile_operations *ops)
{
if (has_mux())
ops->switch_events = nmi_switch_event;
}
static void mux_clone(int cpu)
{
if (!has_mux())
return;
memcpy(per_cpu(cpu_msrs, cpu).multiplex,
per_cpu(cpu_msrs, 0).multiplex,
sizeof(struct op_msr) * model->num_virt_counters);
}
#else
inline int op_x86_phys_to_virt(int phys) { return phys; }
inline int op_x86_virt_to_phys(int virt) { return virt; }
static inline void nmi_shutdown_mux(void) { }
static inline int nmi_setup_mux(void) { return 1; }
static inline void
nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs) { }
static inline void mux_init(struct oprofile_operations *ops) { }
static void mux_clone(int cpu) { }
#endif
static void free_msrs(void)
{
int i;
for_each_possible_cpu(i) {
kfree(per_cpu(cpu_msrs, i).counters);
per_cpu(cpu_msrs, i).counters = NULL;
kfree(per_cpu(cpu_msrs, i).controls);
per_cpu(cpu_msrs, i).controls = NULL;
}
nmi_shutdown_mux();
}
static int allocate_msrs(void)
{
size_t controls_size = sizeof(struct op_msr) * model->num_controls;
size_t counters_size = sizeof(struct op_msr) * model->num_counters;
int i;
for_each_possible_cpu(i) {
per_cpu(cpu_msrs, i).counters = kzalloc(counters_size,
GFP_KERNEL);
if (!per_cpu(cpu_msrs, i).counters)
goto fail;
per_cpu(cpu_msrs, i).controls = kzalloc(controls_size,
GFP_KERNEL);
if (!per_cpu(cpu_msrs, i).controls)
goto fail;
}
if (!nmi_setup_mux())
goto fail;
return 1;
fail:
free_msrs();
return 0;
}
static void nmi_cpu_setup(void *dummy)
{
int cpu = smp_processor_id();
struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu);
nmi_cpu_save_registers(msrs);
spin_lock(&oprofilefs_lock);
model->setup_ctrs(model, msrs);
nmi_cpu_setup_mux(cpu, msrs);
spin_unlock(&oprofilefs_lock);
per_cpu(saved_lvtpc, cpu) = apic_read(APIC_LVTPC);
apic_write(APIC_LVTPC, APIC_DM_NMI);
}
static struct notifier_block profile_exceptions_nb = {
.notifier_call = profile_exceptions_notify,
.next = NULL,
.priority = NMI_LOCAL_LOW_PRIOR,
};
static void nmi_cpu_restore_registers(struct op_msrs *msrs)
{
struct op_msr *counters = msrs->counters;
struct op_msr *controls = msrs->controls;
unsigned int i;
for (i = 0; i < model->num_controls; ++i) {
if (controls[i].addr)
wrmsrl(controls[i].addr, controls[i].saved);
}
for (i = 0; i < model->num_counters; ++i) {
if (counters[i].addr)
wrmsrl(counters[i].addr, counters[i].saved);
}
}
static void nmi_cpu_shutdown(void *dummy)
{
unsigned int v;
int cpu = smp_processor_id();
struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu);
/* restoring APIC_LVTPC can trigger an apic error because the delivery
* mode and vector nr combination can be illegal. That's by design: on
* power on apic lvt contain a zero vector nr which are legal only for
* NMI delivery mode. So inhibit apic err before restoring lvtpc
*/
v = apic_read(APIC_LVTERR);
apic_write(APIC_LVTERR, v | APIC_LVT_MASKED);
apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu));
apic_write(APIC_LVTERR, v);
nmi_cpu_restore_registers(msrs);
if (model->cpu_down)
model->cpu_down();
}
static void nmi_cpu_up(void *dummy)
{
if (nmi_enabled)
nmi_cpu_setup(dummy);
if (ctr_running)
nmi_cpu_start(dummy);
}
static void nmi_cpu_down(void *dummy)
{
if (ctr_running)
nmi_cpu_stop(dummy);
if (nmi_enabled)
nmi_cpu_shutdown(dummy);
}
static int nmi_create_files(struct super_block *sb, struct dentry *root)
{
unsigned int i;
for (i = 0; i < model->num_virt_counters; ++i) {
struct dentry *dir;
char buf[4];
/* quick little hack to _not_ expose a counter if it is not
* available for use. This should protect userspace app.
* NOTE: assumes 1:1 mapping here (that counters are organized
* sequentially in their struct assignment).
*/
if (!avail_to_resrv_perfctr_nmi_bit(op_x86_virt_to_phys(i)))
continue;
snprintf(buf, sizeof(buf), "%d", i);
dir = oprofilefs_mkdir(sb, root, buf);
oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
}
return 0;
}
static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action,
void *data)
{
int cpu = (unsigned long)data;
switch (action) {
case CPU_DOWN_FAILED:
case CPU_ONLINE:
smp_call_function_single(cpu, nmi_cpu_up, NULL, 0);
break;
case CPU_DOWN_PREPARE:
smp_call_function_single(cpu, nmi_cpu_down, NULL, 1);
break;
}
return NOTIFY_DONE;
}
static struct notifier_block oprofile_cpu_nb = {
.notifier_call = oprofile_cpu_notifier
};
static int nmi_setup(void)
{
int err = 0;
int cpu;
if (!allocate_msrs())
return -ENOMEM;
/* We need to serialize save and setup for HT because the subset
* of msrs are distinct for save and setup operations
*/
/* Assume saved/restored counters are the same on all CPUs */
err = model->fill_in_addresses(&per_cpu(cpu_msrs, 0));
if (err)
goto fail;
for_each_possible_cpu(cpu) {
if (!cpu)
continue;
memcpy(per_cpu(cpu_msrs, cpu).counters,
per_cpu(cpu_msrs, 0).counters,
sizeof(struct op_msr) * model->num_counters);
memcpy(per_cpu(cpu_msrs, cpu).controls,
per_cpu(cpu_msrs, 0).controls,
sizeof(struct op_msr) * model->num_controls);
mux_clone(cpu);
}
nmi_enabled = 0;
ctr_running = 0;
barrier();
err = register_die_notifier(&profile_exceptions_nb);
if (err)
goto fail;
get_online_cpus();
register_cpu_notifier(&oprofile_cpu_nb);
on_each_cpu(nmi_cpu_setup, NULL, 1);
nmi_enabled = 1;
put_online_cpus();
return 0;
fail:
free_msrs();
return err;
}
static void nmi_shutdown(void)
{
struct op_msrs *msrs;
get_online_cpus();
unregister_cpu_notifier(&oprofile_cpu_nb);
on_each_cpu(nmi_cpu_shutdown, NULL, 1);
nmi_enabled = 0;
ctr_running = 0;
put_online_cpus();
barrier();
unregister_die_notifier(&profile_exceptions_nb);
msrs = &get_cpu_var(cpu_msrs);
model->shutdown(msrs);
free_msrs();
put_cpu_var(cpu_msrs);
}
#ifdef CONFIG_PM
static int nmi_suspend(struct sys_device *dev, pm_message_t state)
{
/* Only one CPU left, just stop that one */
if (nmi_enabled == 1)
nmi_cpu_stop(NULL);
return 0;
}
static int nmi_resume(struct sys_device *dev)
{
if (nmi_enabled == 1)
nmi_cpu_start(NULL);
return 0;
}
static struct sysdev_class oprofile_sysclass = {
.name = "oprofile",
.resume = nmi_resume,
.suspend = nmi_suspend,
};
static struct sys_device device_oprofile = {
.id = 0,
.cls = &oprofile_sysclass,
};
static int __init init_sysfs(void)
{
int error;
error = sysdev_class_register(&oprofile_sysclass);
if (error)
return error;
error = sysdev_register(&device_oprofile);
if (error)
sysdev_class_unregister(&oprofile_sysclass);
return error;
}
static void exit_sysfs(void)
{
sysdev_unregister(&device_oprofile);
sysdev_class_unregister(&oprofile_sysclass);
}
#else
static inline int init_sysfs(void) { return 0; }
static inline void exit_sysfs(void) { }
#endif /* CONFIG_PM */
static int __init p4_init(char **cpu_type)
{
__u8 cpu_model = boot_cpu_data.x86_model;
if (cpu_model > 6 || cpu_model == 5)
return 0;
#ifndef CONFIG_SMP
*cpu_type = "i386/p4";
model = &op_p4_spec;
return 1;
#else
switch (smp_num_siblings) {
case 1:
*cpu_type = "i386/p4";
model = &op_p4_spec;
return 1;
case 2:
*cpu_type = "i386/p4-ht";
model = &op_p4_ht2_spec;
return 1;
}
#endif
printk(KERN_INFO "oprofile: P4 HyperThreading detected with > 2 threads\n");
printk(KERN_INFO "oprofile: Reverting to timer mode.\n");
return 0;
}
static int force_arch_perfmon;
static int force_cpu_type(const char *str, struct kernel_param *kp)
{
if (!strcmp(str, "arch_perfmon")) {
force_arch_perfmon = 1;
printk(KERN_INFO "oprofile: forcing architectural perfmon\n");
}
return 0;
}
module_param_call(cpu_type, force_cpu_type, NULL, NULL, 0);
static int __init ppro_init(char **cpu_type)
{
__u8 cpu_model = boot_cpu_data.x86_model;
struct op_x86_model_spec *spec = &op_ppro_spec; /* default */
if (force_arch_perfmon && cpu_has_arch_perfmon)
return 0;
/*
* Documentation on identifying Intel processors by CPU family
* and model can be found in the Intel Software Developer's
* Manuals (SDM):
*
* http://www.intel.com/products/processor/manuals/
*
* As of May 2010 the documentation for this was in the:
* "Intel 64 and IA-32 Architectures Software Developer's
* Manual Volume 3B: System Programming Guide", "Table B-1
* CPUID Signature Values of DisplayFamily_DisplayModel".
*/
switch (cpu_model) {
case 0 ... 2:
*cpu_type = "i386/ppro";
break;
case 3 ... 5:
*cpu_type = "i386/pii";
break;
case 6 ... 8:
x86/oprofile: fix Intel cpu family 6 detection Alan Jenkins wrote: > This is on an EeePC 701, /proc/cpuinfo as attached. > > Is this expected? Will the next release work? > > Thanks, Alan > > # opcontrol --setup --no-vmlinux > cpu_type 'unset' is not valid > you should upgrade oprofile or force the use of timer mode > > # opcontrol -v > opcontrol: oprofile 0.9.4 compiled on Nov 29 2008 22:44:10 > > # cat /dev/oprofile/cpu_type > i386/p6 > # uname -r > 2.6.28-rc6eeepc Hi Alan, Looking at the kernel driver code for oprofile it can return the "i386/p6" for the cpu_type. However, looking at the user-space oprofile code there isn't the matching entry in libop/op_cpu_type.c or the events/unit_mask files in events/i386 directory. The Intel AP-485 says this is a "Intel Pentium M processor model D". Seems like the oprofile kernel driver should be identifying the processor as "i386/p6_mobile" The driver identification code doesn't look quite right in nmi_init.c http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git;a=blob;f=arch/x86/oprofile/nmi_int.c;h=022cd41ea9b4106e5884277096e80e9088a7c7a9;hb=HEAD has: 409 case 10 ... 13: 410 *cpu_type = "i386/p6"; 411 break; Referring to the Intel AP-485: case 10 and 11 should produce "i386/piii" case 13 should produce "i386/p6_mobile" I didn't see anything for case 12. Something like the attached patch. I don't have a celeron machine to verify that changes in this area of the kernel fix thing. -Will Signed-off-by: William Cohen <wcohen@redhat.com> Tested-by: Alan Jenkins <alan-jenkins@tuffmail.co.uk> Acked-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2008-11-30 20:39:10 +00:00
case 10 ... 11:
*cpu_type = "i386/piii";
break;
case 9:
x86/oprofile: fix Intel cpu family 6 detection Alan Jenkins wrote: > This is on an EeePC 701, /proc/cpuinfo as attached. > > Is this expected? Will the next release work? > > Thanks, Alan > > # opcontrol --setup --no-vmlinux > cpu_type 'unset' is not valid > you should upgrade oprofile or force the use of timer mode > > # opcontrol -v > opcontrol: oprofile 0.9.4 compiled on Nov 29 2008 22:44:10 > > # cat /dev/oprofile/cpu_type > i386/p6 > # uname -r > 2.6.28-rc6eeepc Hi Alan, Looking at the kernel driver code for oprofile it can return the "i386/p6" for the cpu_type. However, looking at the user-space oprofile code there isn't the matching entry in libop/op_cpu_type.c or the events/unit_mask files in events/i386 directory. The Intel AP-485 says this is a "Intel Pentium M processor model D". Seems like the oprofile kernel driver should be identifying the processor as "i386/p6_mobile" The driver identification code doesn't look quite right in nmi_init.c http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git;a=blob;f=arch/x86/oprofile/nmi_int.c;h=022cd41ea9b4106e5884277096e80e9088a7c7a9;hb=HEAD has: 409 case 10 ... 13: 410 *cpu_type = "i386/p6"; 411 break; Referring to the Intel AP-485: case 10 and 11 should produce "i386/piii" case 13 should produce "i386/p6_mobile" I didn't see anything for case 12. Something like the attached patch. I don't have a celeron machine to verify that changes in this area of the kernel fix thing. -Will Signed-off-by: William Cohen <wcohen@redhat.com> Tested-by: Alan Jenkins <alan-jenkins@tuffmail.co.uk> Acked-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2008-11-30 20:39:10 +00:00
case 13:
*cpu_type = "i386/p6_mobile";
break;
case 14:
*cpu_type = "i386/core";
break;
case 0x0f:
case 0x16:
case 0x17:
case 0x1d:
*cpu_type = "i386/core_2";
break;
case 0x1a:
case 0x1e:
case 0x2e:
spec = &op_arch_perfmon_spec;
*cpu_type = "i386/core_i7";
break;
case 0x1c:
*cpu_type = "i386/atom";
break;
default:
/* Unknown */
return 0;
}
model = spec;
return 1;
}
int __init op_nmi_init(struct oprofile_operations *ops)
{
__u8 vendor = boot_cpu_data.x86_vendor;
__u8 family = boot_cpu_data.x86;
char *cpu_type = NULL;
int ret = 0;
if (!cpu_has_apic)
return -ENODEV;
switch (vendor) {
case X86_VENDOR_AMD:
/* Needs to be at least an Athlon (or hammer in 32bit mode) */
switch (family) {
case 6:
cpu_type = "i386/athlon";
break;
case 0xf:
/*
* Actually it could be i386/hammer too, but
* give user space an consistent name.
*/
cpu_type = "x86-64/hammer";
break;
case 0x10:
cpu_type = "x86-64/family10";
break;
case 0x11:
cpu_type = "x86-64/family11h";
break;
case 0x12:
cpu_type = "x86-64/family12h";
break;
case 0x14:
cpu_type = "x86-64/family14h";
break;
case 0x15:
cpu_type = "x86-64/family15h";
break;
default:
return -ENODEV;
}
model = &op_amd_spec;
break;
case X86_VENDOR_INTEL:
switch (family) {
/* Pentium IV */
case 0xf:
p4_init(&cpu_type);
break;
/* A P6-class processor */
case 6:
ppro_init(&cpu_type);
break;
default:
break;
}
if (cpu_type)
break;
if (!cpu_has_arch_perfmon)
return -ENODEV;
/* use arch perfmon as fallback */
cpu_type = "i386/arch_perfmon";
model = &op_arch_perfmon_spec;
break;
default:
return -ENODEV;
}
/* default values, can be overwritten by model */
ops->create_files = nmi_create_files;
ops->setup = nmi_setup;
ops->shutdown = nmi_shutdown;
ops->start = nmi_start;
ops->stop = nmi_stop;
ops->cpu_type = cpu_type;
if (model->init)
ret = model->init(ops);
if (ret)
return ret;
if (!model->num_virt_counters)
model->num_virt_counters = model->num_counters;
mux_init(ops);
ret = init_sysfs();
if (ret)
return ret;
printk(KERN_INFO "oprofile: using NMI interrupt.\n");
return 0;
}
void op_nmi_exit(void)
{
exit_sysfs();
}