hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf: Fix loss of notification with multi-event
  perf, x86: Force IBS LVT offset assignment for family 10h
  perf, x86: Disable PEBS on SandyBridge chips
  trace_events_filter: Use rcu_assign_pointer() when setting ftrace_event_call->filter
  perf session: Fix crash with invalid CPU list
  perf python: Fix undefined symbol problem
  perf/x86: Enable raw event access to Intel offcore events
  perf: Don't use -ENOSPC for out of PMU resources
  perf: Do not set task_ctx pointer in cpuctx if there are no events in the context
  perf/x86: Fix PEBS instruction unwind
  oprofile, x86: Fix crash when unloading module (nmi timer mode)
  oprofile: Fix crash when unloading module (hr timer mode)
This commit is contained in:
Linus Torvalds 2011-12-05 16:54:00 -08:00
parent 40c043b077 dc440d10e1
commit 232ea34455
19 changed files with 185 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
arch/arm/kernel/perf_event.c
View File

@ -353,15 +353,15 @@ validate_group(struct perf_event *event)
fake_pmu.used_mask = fake_used_mask;
if (!validate_event(&fake_pmu, leader))
return -ENOSPC;
return -EINVAL;
list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
if (!validate_event(&fake_pmu, sibling))
return -ENOSPC;
return -EINVAL;
}
if (!validate_event(&fake_pmu, event))
return -ENOSPC;
return -EINVAL;
return 0;
}

8
arch/mips/kernel/perf_event_mipsxx.c
View File

@ -623,7 +623,7 @@ static int mipspmu_event_init(struct perf_event *event)
if (!atomic_inc_not_zero(&active_events)) {
if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
atomic_dec(&active_events);
return -ENOSPC;
return -EINVAL;
}
mutex_lock(&pmu_reserve_mutex);
@ -732,15 +732,15 @@ static int validate_group(struct perf_event *event)
memset(&fake_cpuc, 0, sizeof(fake_cpuc));
if (!validate_event(&fake_cpuc, leader))
return -ENOSPC;
return -EINVAL;
list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
if (!validate_event(&fake_cpuc, sibling))
return -ENOSPC;
return -EINVAL;
}
if (!validate_event(&fake_cpuc, event))
return -ENOSPC;
return -EINVAL;
return 0;
}

16
arch/x86/kernel/cpu/perf_event.c
View File

@ -312,12 +312,8 @@ int x86_setup_perfctr(struct perf_event *event)
return -EOPNOTSUPP;
}
/*
* Do not allow config1 (extended registers) to propagate,
* there's no sane user-space generalization yet:
*/
if (attr->type == PERF_TYPE_RAW)
return 0;
return x86_pmu_extra_regs(event->attr.config, event);
if (attr->type == PERF_TYPE_HW_CACHE)
return set_ext_hw_attr(hwc, event);
@ -588,7 +584,7 @@ done:
x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
}
}
return num ? -ENOSPC : 0;
return num ? -EINVAL : 0;
}
/*
@ -607,7 +603,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
if (is_x86_event(leader)) {
if (n >= max_count)
return -ENOSPC;
return -EINVAL;
cpuc->event_list[n] = leader;
n++;
}
@ -620,7 +616,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
continue;
if (n >= max_count)
return -ENOSPC;
return -EINVAL;
cpuc->event_list[n] = event;
n++;
@ -1316,7 +1312,7 @@ static int validate_event(struct perf_event *event)
c = x86_pmu.get_event_constraints(fake_cpuc, event);
if (!c || !c->weight)
ret = -ENOSPC;
ret = -EINVAL;
if (x86_pmu.put_event_constraints)
x86_pmu.put_event_constraints(fake_cpuc, event);
@ -1341,7 +1337,7 @@ static int validate_group(struct perf_event *event)
{
struct perf_event *leader = event->group_leader;
struct cpu_hw_events *fake_cpuc;
int ret = -ENOSPC, n;
int ret = -EINVAL, n;
fake_cpuc = allocate_fake_cpuc();
if (IS_ERR(fake_cpuc))

29
arch/x86/kernel/cpu/perf_event_amd_ibs.c
View File

@ -199,8 +199,7 @@ static int force_ibs_eilvt_setup(void)
goto out;
}
pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
pr_info("IBS: LVT offset %d assigned\n", offset);
return 0;
out:
@ -265,19 +264,23 @@ perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *h
static __init int amd_ibs_init(void)
{
u32 caps;
int ret;
int ret = -EINVAL;
caps = __get_ibs_caps();
if (!caps)
return -ENODEV; /* ibs not supported by the cpu */
if (!ibs_eilvt_valid()) {
ret = force_ibs_eilvt_setup();
if (ret) {
pr_err("Failed to setup IBS, %d\n", ret);
return ret;
}
}
/*
* Force LVT offset assignment for family 10h: The offsets are
* not assigned by the BIOS for this family, so the OS is
* responsible for doing it. If the OS assignment fails, fall
* back to BIOS settings and try to setup this.
*/
if (boot_cpu_data.x86 == 0x10)
force_ibs_eilvt_setup();
if (!ibs_eilvt_valid())
goto out;
get_online_cpus();
ibs_caps = caps;
@ -287,7 +290,11 @@ static __init int amd_ibs_init(void)
smp_call_function(setup_APIC_ibs, NULL, 1);
put_online_cpus();
return perf_event_ibs_init();
ret = perf_event_ibs_init();
out:
if (ret)
pr_err("Failed to setup IBS, %d\n", ret);
return ret;
}
/* Since we need the pci subsystem to init ibs we can't do this earlier: */

8
arch/x86/kernel/cpu/perf_event_intel.c
View File

@ -1545,6 +1545,13 @@ static void intel_clovertown_quirks(void)
x86_pmu.pebs_constraints = NULL;
}
static void intel_sandybridge_quirks(void)
{
printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
x86_pmu.pebs = 0;
x86_pmu.pebs_constraints = NULL;
}
__init int intel_pmu_init(void)
{
union cpuid10_edx edx;
@ -1694,6 +1701,7 @@ __init int intel_pmu_init(void)
break;
case 42: /* SandyBridge */
x86_pmu.quirks = intel_sandybridge_quirks;
case 45: /* SandyBridge, "Romely-EP" */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));

6
arch/x86/kernel/cpu/perf_event_intel_ds.c
View File

@ -493,6 +493,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
unsigned long from = cpuc->lbr_entries[0].from;
unsigned long old_to, to = cpuc->lbr_entries[0].to;
unsigned long ip = regs->ip;
int is_64bit = 0;
/*
* We don't need to fixup if the PEBS assist is fault like
@ -544,7 +545,10 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
} else
kaddr = (void *)to;
kernel_insn_init(&insn, kaddr);
#ifdef CONFIG_X86_64
is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
#endif
insn_init(&insn, kaddr, is_64bit);
insn_get_length(&insn);
to += insn.length;
} while (to < ip);

2
arch/x86/kernel/cpu/perf_event_p4.c
View File

@ -1268,7 +1268,7 @@ reserve:
}
done:
return num ? -ENOSPC : 0;
return num ? -EINVAL : 0;
}
static __initconst const struct x86_pmu p4_pmu = {

5
arch/x86/oprofile/init.c
View File

@ -21,6 +21,7 @@ extern int op_nmi_timer_init(struct oprofile_operations *ops);
extern void op_nmi_exit(void);
extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth);
static int nmi_timer;
int __init oprofile_arch_init(struct oprofile_operations *ops)
{
@ -31,8 +32,9 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
#ifdef CONFIG_X86_LOCAL_APIC
ret = op_nmi_init(ops);
#endif
nmi_timer = (ret != 0);
#ifdef CONFIG_X86_IO_APIC
if (ret < 0)
if (nmi_timer)
ret = op_nmi_timer_init(ops);
#endif
ops->backtrace = x86_backtrace;
@ -44,6 +46,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
void oprofile_arch_exit(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
if (!nmi_timer)
op_nmi_exit();
#endif
}

27
drivers/oprofile/oprof.c
View File

@ -239,25 +239,44 @@ int oprofile_set_ulong(unsigned long *addr, unsigned long val)
return err;
}
static int timer_mode;
static int __init oprofile_init(void)
{
int err;
/* always init architecture to setup backtrace support */
err = oprofile_arch_init(&oprofile_ops);
if (err < 0 || timer) {
printk(KERN_INFO "oprofile: using timer interrupt.\n");
timer_mode = err || timer; /* fall back to timer mode on errors */
if (timer_mode) {
if (!err)
oprofile_arch_exit();
err = oprofile_timer_init(&oprofile_ops);
if (err)
return err;
}
return oprofilefs_register();
err = oprofilefs_register();
if (!err)
return 0;
/* failed */
if (timer_mode)
oprofile_timer_exit();
else
oprofile_arch_exit();
return err;
}
static void __exit oprofile_exit(void)
{
oprofile_timer_exit();
oprofilefs_unregister();
if (timer_mode)
oprofile_timer_exit();
else
oprofile_arch_exit();
}

1
drivers/oprofile/timer_int.c
View File

@ -110,6 +110,7 @@ int oprofile_timer_init(struct oprofile_operations *ops)
ops->start = oprofile_hrtimer_start;
ops->stop = oprofile_hrtimer_stop;
ops->cpu_type = "timer";
printk(KERN_INFO "oprofile: using timer interrupt.\n");
return 0;
}

1
include/linux/perf_event.h
View File

@ -822,6 +822,7 @@ struct perf_event {
int mmap_locked;
struct user_struct *mmap_user;
struct ring_buffer *rb;
struct list_head rb_entry;
/* poll related */
wait_queue_head_t waitq;

87
kernel/events/core.c
View File

@ -185,6 +185,9 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
static void update_context_time(struct perf_event_context *ctx);
static u64 perf_event_time(struct perf_event *event);
static void ring_buffer_attach(struct perf_event *event,
struct ring_buffer *rb);
void __weak perf_event_print_debug(void) { }
extern __weak const char *perf_pmu_name(void)
@ -2173,6 +2176,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
perf_event_sched_in(cpuctx, ctx, task);
if (ctx->nr_events)
cpuctx->task_ctx = ctx;
perf_pmu_enable(ctx->pmu);
@ -3190,12 +3194,33 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
struct ring_buffer *rb;
unsigned int events = POLL_HUP;
/*
* Race between perf_event_set_output() and perf_poll(): perf_poll()
* grabs the rb reference but perf_event_set_output() overrides it.
* Here is the timeline for two threads T1, T2:
* t0: T1, rb = rcu_dereference(event->rb)
* t1: T2, old_rb = event->rb
* t2: T2, event->rb = new rb
* t3: T2, ring_buffer_detach(old_rb)
* t4: T1, ring_buffer_attach(rb1)
* t5: T1, poll_wait(event->waitq)
*
* To avoid this problem, we grab mmap_mutex in perf_poll()
* thereby ensuring that the assignment of the new ring buffer
* and the detachment of the old buffer appear atomic to perf_poll()
*/
mutex_lock(&event->mmap_mutex);
rcu_read_lock();
rb = rcu_dereference(event->rb);
if (rb)
if (rb) {
ring_buffer_attach(event, rb);
events = atomic_xchg(&rb->poll, 0);
}
rcu_read_unlock();
mutex_unlock(&event->mmap_mutex);
poll_wait(file, &event->waitq, wait);
return events;
@ -3496,6 +3521,49 @@ unlock:
return ret;
}
static void ring_buffer_attach(struct perf_event *event,
struct ring_buffer *rb)
{
unsigned long flags;
if (!list_empty(&event->rb_entry))
return;
spin_lock_irqsave(&rb->event_lock, flags);
if (!list_empty(&event->rb_entry))
goto unlock;
list_add(&event->rb_entry, &rb->event_list);
unlock:
spin_unlock_irqrestore(&rb->event_lock, flags);
}
static void ring_buffer_detach(struct perf_event *event,
struct ring_buffer *rb)
{
unsigned long flags;
if (list_empty(&event->rb_entry))
return;
spin_lock_irqsave(&rb->event_lock, flags);
list_del_init(&event->rb_entry);
wake_up_all(&event->waitq);
spin_unlock_irqrestore(&rb->event_lock, flags);
}
static void ring_buffer_wakeup(struct perf_event *event)
{
struct ring_buffer *rb;
rcu_read_lock();
rb = rcu_dereference(event->rb);
list_for_each_entry_rcu(event, &rb->event_list, rb_entry) {
wake_up_all(&event->waitq);
}
rcu_read_unlock();
}
static void rb_free_rcu(struct rcu_head *rcu_head)
{
struct ring_buffer *rb;
@ -3521,9 +3589,19 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event)
static void ring_buffer_put(struct ring_buffer *rb)
{
struct perf_event *event, *n;
unsigned long flags;
if (!atomic_dec_and_test(&rb->refcount))
return;
spin_lock_irqsave(&rb->event_lock, flags);
list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) {
list_del_init(&event->rb_entry);
wake_up_all(&event->waitq);
}
spin_unlock_irqrestore(&rb->event_lock, flags);
call_rcu(&rb->rcu_head, rb_free_rcu);
}
@ -3546,6 +3624,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
vma->vm_mm->pinned_vm -= event->mmap_locked;
rcu_assign_pointer(event->rb, NULL);
ring_buffer_detach(event, rb);
mutex_unlock(&event->mmap_mutex);
ring_buffer_put(rb);
@ -3700,7 +3779,7 @@ static const struct file_operations perf_fops = {
void perf_event_wakeup(struct perf_event *event)
{
wake_up_all(&event->waitq);
ring_buffer_wakeup(event);
if (event->pending_kill) {
kill_fasync(&event->fasync, SIGIO, event->pending_kill);
@ -5822,6 +5901,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
INIT_LIST_HEAD(&event->group_entry);
INIT_LIST_HEAD(&event->event_entry);
INIT_LIST_HEAD(&event->sibling_list);
INIT_LIST_HEAD(&event->rb_entry);
init_waitqueue_head(&event->waitq);
init_irq_work(&event->pending, perf_pending_event);
@ -6028,6 +6109,8 @@ set:
old_rb = event->rb;
rcu_assign_pointer(event->rb, rb);
if (old_rb)
ring_buffer_detach(event, old_rb);
ret = 0;
unlock:
mutex_unlock(&event->mmap_mutex);

3
kernel/events/internal.h
View File

@ -22,6 +22,9 @@ struct ring_buffer {
local_t lost; /* nr records lost */
long watermark; /* wakeup watermark */
/* poll crap */
spinlock_t event_lock;
struct list_head event_list;
struct perf_event_mmap_page *user_page;
void *data_pages[0];

3
kernel/events/ring_buffer.c
View File

@ -209,6 +209,9 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
rb->writable = 1;
atomic_set(&rb->refcount, 1);
INIT_LIST_HEAD(&rb->event_list);
spin_lock_init(&rb->event_lock);
}
#ifndef CONFIG_PERF_USE_VMALLOC

6
kernel/trace/trace_events_filter.c
View File

@ -1686,7 +1686,7 @@ static int replace_system_preds(struct event_subsystem *system,
* replace the filter for the call.
*/
filter = call->filter;
call->filter = filter_item->filter;
rcu_assign_pointer(call->filter, filter_item->filter);
filter_item->filter = filter;
fail = false;
@ -1741,7 +1741,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
filter = call->filter;
if (!filter)
goto out_unlock;
call->filter = NULL;
RCU_INIT_POINTER(call->filter, NULL);
/* Make sure the filter is not being used */
synchronize_sched();
__free_filter(filter);
@ -1782,7 +1782,7 @@ out:
* string
*/
tmp = call->filter;
call->filter = filter;
rcu_assign_pointer(call->filter, filter);
if (tmp) {
/* Make sure the call is done with the filter */
synchronize_sched();

10
tools/perf/util/evsel.c
View File

@ -34,6 +34,16 @@ int __perf_evsel__sample_size(u64 sample_type)
return size;
}
static void hists__init(struct hists *hists)
{
memset(hists, 0, sizeof(*hists));
hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
hists->entries_in = &hists->entries_in_array[0];
hists->entries_collapsed = RB_ROOT;
hists->entries = RB_ROOT;
pthread_mutex_init(&hists->lock, NULL);
}
void perf_evsel__init(struct perf_evsel *evsel,
struct perf_event_attr *attr, int idx)
{

10
tools/perf/util/hist.c
View File

@ -1211,13 +1211,3 @@ size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp)
return ret;
}
void hists__init(struct hists *hists)
{
memset(hists, 0, sizeof(*hists));
hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
hists->entries_in = &hists->entries_in_array[0];
hists->entries_collapsed = RB_ROOT;
hists->entries = RB_ROOT;
pthread_mutex_init(&hists->lock, NULL);
}

2
tools/perf/util/hist.h
View File

@ -63,8 +63,6 @@ struct hists {
struct callchain_cursor callchain_cursor;
};
void hists__init(struct hists *hists);
struct hist_entry *__hists__add_entry(struct hists *self,
struct addr_location *al,
struct symbol *parent, u64 period);

4
tools/perf/util/session.c
View File

@ -1333,6 +1333,10 @@ int perf_session__cpu_bitmap(struct perf_session *session,
}
map = cpu_map__new(cpu_list);
if (map == NULL) {
pr_err("Invalid cpu_list\n");
return -1;
}
for (i = 0; i < map->nr; i++) {
int cpu = map->map[i];