* Disallow per-task kernel breakpoints since these would
* complicate the stepping code.
*/
- if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.bp_target)
+ if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
return -EINVAL;
return 0;
.notifier_call = hw_breakpoint_reset_notify,
};
-#ifdef CONFIG_ARM64_CPU_SUSPEND
+#ifdef CONFIG_CPU_PM
extern void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *));
#else
static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
u16 __read_mostly tlb_lld_4m[NR_INFO];
u16 __read_mostly tlb_lld_1g[NR_INFO];
-void cpu_detect_tlb(struct cpuinfo_x86 *c)
+static void cpu_detect_tlb(struct cpuinfo_x86 *c)
{
if (this_cpu->c_detect_tlb)
this_cpu->c_detect_tlb(c);
- printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n"
- "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n",
+ pr_info("Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n",
tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
- tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES],
- tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES],
- tlb_lld_1g[ENTRIES]);
+ tlb_lli_4m[ENTRIES]);
+
+ pr_info("Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n",
+ tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES],
+ tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
}
void detect_ht(struct cpuinfo_x86 *c)
c->x86_capability[10] = eax;
}
+ /* Additional Intel-defined flags: level 0x0000000F */
+ if (c->cpuid_level >= 0x0000000F) {
+ u32 eax, ebx, ecx, edx;
+
+ /* QoS sub-leaf, EAX=0Fh, ECX=0 */
+ cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
+ c->x86_capability[11] = edx;
+ if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
+ /* will be overridden if occupancy monitoring exists */
+ c->x86_cache_max_rmid = ebx;
+
+ /* QoS sub-leaf, EAX=0Fh, ECX=1 */
+ cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
+ c->x86_capability[12] = edx;
+ if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) {
+ c->x86_cache_max_rmid = ecx;
+ c->x86_cache_occ_scale = ebx;
+ }
+ } else {
+ c->x86_cache_max_rmid = -1;
+ c->x86_cache_occ_scale = -1;
+ }
+ }
+
/* AMD-defined flags: level 0x80000001 */
xlvl = cpuid_eax(0x80000000);
c->extended_cpuid_level = xlvl;
detect_nopl(c);
}
+ static void x86_init_cache_qos(struct cpuinfo_x86 *c)
+ {
+ /*
+ * The heavy lifting of max_rmid and cache_occ_scale are handled
+ * in get_cpu_cap(). Here we just set the max_rmid for the boot_cpu
+ * in case CQM bits really aren't there in this CPU.
+ */
+ if (c != &boot_cpu_data) {
+ boot_cpu_data.x86_cache_max_rmid =
+ min(boot_cpu_data.x86_cache_max_rmid,
+ c->x86_cache_max_rmid);
+ }
+ }
+
/*
* This does the hard work of actually picking apart the CPU stuff...
*/
init_hypervisor(c);
x86_init_rdrand(c);
+ x86_init_cache_qos(c);
/*
* Clear/Set all flags overriden by options, need do it
barrier();
x86_configure_nx();
- enable_x2apic();
+ x2apic_setup();
/*
* set up and load the per-CPU TSS
wait_for_master_cpu(cpu);
+ /*
+ * Initialize the CR4 shadow before doing anything that could
+ * try to read it.
+ */
+ cr4_init_shadow();
+
show_ucode_info_early();
printk(KERN_INFO "Initializing CPU#%d\n", cpu);
#include <linux/sysfs.h>
#include <linux/perf_regs.h>
#include <linux/workqueue.h>
+ #include <linux/cgroup.h>
#include <asm/local.h>
struct perf_callchain_entry {
struct hrtimer hrtimer;
};
struct { /* tracepoint */
- struct task_struct *tp_target;
/* for tp_event->class */
struct list_head tp_list;
};
+ struct { /* intel_cqm */
+ int cqm_state;
+ int cqm_rmid;
+ struct list_head cqm_events_entry;
+ struct list_head cqm_groups_entry;
+ struct list_head cqm_group_entry;
+ };
#ifdef CONFIG_HAVE_HW_BREAKPOINT
struct { /* breakpoint */
/*
* problem hw_breakpoint has with context
* creation and event initalization.
*/
- struct task_struct *bp_target;
struct arch_hw_breakpoint info;
struct list_head bp_list;
};
#endif
};
+ struct task_struct *target;
int state;
local64_t prev_count;
u64 sample_period;
*/
size_t task_ctx_size;
+
+ /*
+ * Return the count value for a counter.
+ */
+ u64 (*count) (struct perf_event *event); /*optional*/
};
/**
int page;
};
+ #ifdef CONFIG_CGROUP_PERF
+
+ /*
+ * perf_cgroup_info keeps track of time_enabled for a cgroup.
+ * This is a per-cpu dynamically allocated data structure.
+ */
+ struct perf_cgroup_info {
+ u64 time;
+ u64 timestamp;
+ };
+
+ struct perf_cgroup {
+ struct cgroup_subsys_state css;
+ struct perf_cgroup_info __percpu *info;
+ };
+
+ /*
+ * Must ensure cgroup is pinned (css_get) before calling
+ * this function. In other words, we cannot call this function
+ * if there is no cgroup event for the current CPU context.
+ */
+ static inline struct perf_cgroup *
+ perf_cgroup_from_task(struct task_struct *task)
+ {
+ return container_of(task_css(task, perf_event_cgrp_id),
+ struct perf_cgroup, css);
+ }
+ #endif /* CONFIG_CGROUP_PERF */
+
#ifdef CONFIG_PERF_EVENTS
extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
__perf_event_task_sched_out(prev, next);
}
+ static inline u64 __perf_event_count(struct perf_event *event)
+ {
+ return local64_read(&event->count) + atomic64_read(&event->child_count);
+ }
+
extern void perf_event_mmap(struct vm_area_struct *vma);
extern struct perf_guest_info_callbacks *perf_guest_cbs;
extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
const char *event_str;
};
+ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
+ char *page);
+
#define PMU_EVENT_ATTR(_name, _var, _id, _show) \
static struct perf_pmu_events_attr _var = { \
.attr = __ATTR(_name, 0444, _show, NULL), \
.id = _id, \
};
+#define PMU_EVENT_ATTR_STRING(_name, _var, _str) \
+static struct perf_pmu_events_attr _var = { \
+ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \
+ .id = 0, \
+ .event_str = _str, \
+};
+
#define PMU_FORMAT_ATTR(_name, _format) \
static ssize_t \
_name##_show(struct device *dev, \
#include <linux/syscalls.h>
#include <linux/anon_inodes.h>
#include <linux/kernel_stat.h>
+ #include <linux/cgroup.h>
#include <linux/perf_event.h>
#include <linux/ftrace_event.h>
#include <linux/hw_breakpoint.h>
#include <linux/mm_types.h>
- #include <linux/cgroup.h>
#include <linux/module.h>
#include <linux/mman.h>
#include <linux/compat.h>
#ifdef CONFIG_CGROUP_PERF
- /*
- * perf_cgroup_info keeps track of time_enabled for a cgroup.
- * This is a per-cpu dynamically allocated data structure.
- */
- struct perf_cgroup_info {
- u64 time;
- u64 timestamp;
- };
-
- struct perf_cgroup {
- struct cgroup_subsys_state css;
- struct perf_cgroup_info __percpu *info;
- };
-
- /*
- * Must ensure cgroup is pinned (css_get) before calling
- * this function. In other words, we cannot call this function
- * if there is no cgroup event for the current CPU context.
- */
- static inline struct perf_cgroup *
- perf_cgroup_from_task(struct task_struct *task)
- {
- return container_of(task_css(task, perf_event_cgrp_id),
- struct perf_cgroup, css);
- }
-
static inline bool
perf_cgroup_match(struct perf_event *event)
{
static inline u64 perf_event_count(struct perf_event *event)
{
- return local64_read(&event->count) + atomic64_read(&event->child_count);
+ if (event->pmu->count)
+ return event->pmu->count(event);
+
+ return __perf_event_count(event);
}
static u64 perf_event_read(struct perf_event *event)
ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING);
WARN_ON_ONCE(ctx->parent_ctx);
perf_remove_from_context(event, true);
- mutex_unlock(&ctx->mutex);
+ perf_event_ctx_unlock(event, ctx);
_free_event(event);
}
* If we have rb pages ensure they're a power-of-two number, so we
* can do bitmasks instead of modulo.
*/
- if (!is_power_of_2(nr_pages))
+ if (nr_pages != 0 && !is_power_of_2(nr_pages))
return -EINVAL;
if (vma_size != PAGE_SIZE * (1 + nr_pages))
{
struct perf_event *event = container_of(entry,
struct perf_event, pending);
+ int rctx;
+
+ rctx = perf_swevent_get_recursion_context();
+ /*
+ * If we 'fail' here, that's OK, it means recursion is already disabled
+ * and we won't recurse 'further'.
+ */
if (event->pending_disable) {
event->pending_disable = 0;
event->pending_wakeup = 0;
perf_event_wakeup(event);
}
+
+ if (rctx >= 0)
+ perf_swevent_put_recursion_context(rctx);
}
/*
struct perf_event *group_leader,
struct perf_event *parent_event,
perf_overflow_handler_t overflow_handler,
- void *context)
+ void *context, int cgroup_fd)
{
struct pmu *pmu;
struct perf_event *event;
if (task) {
event->attach_state = PERF_ATTACH_TASK;
-
- if (attr->type == PERF_TYPE_TRACEPOINT)
- event->hw.tp_target = task;
- #ifdef CONFIG_HAVE_HW_BREAKPOINT
/*
- * hw_breakpoint is a bit difficult here..
+ * XXX pmu::event_init needs to know what task to account to
+ * and we cannot use the ctx information because we need the
+ * pmu before we get a ctx.
*/
- else if (attr->type == PERF_TYPE_BREAKPOINT)
- event->hw.bp_target = task;
- #endif
+ event->hw.target = task;
}
if (!overflow_handler && parent_event) {
if (!has_branch_stack(event))
event->attr.branch_sample_type = 0;
+ if (cgroup_fd != -1) {
+ err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
+ if (err)
+ goto err_ns;
+ }
+
pmu = perf_init_event(event);
if (!pmu)
goto err_ns;
event->destroy(event);
module_put(pmu->module);
err_ns:
+ if (is_cgroup_event(event))
+ perf_detach_cgroup(event);
if (event->ns)
put_pid_ns(event->ns);
kfree(event);
int move_group = 0;
int err;
int f_flags = O_RDWR;
+ int cgroup_fd = -1;
/* for future expandability... */
if (flags & ~PERF_FLAG_ALL)
get_online_cpus();
+ if (flags & PERF_FLAG_PID_CGROUP)
+ cgroup_fd = pid;
+
event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
- NULL, NULL);
+ NULL, NULL, cgroup_fd);
if (IS_ERR(event)) {
err = PTR_ERR(event);
goto err_cpus;
}
- if (flags & PERF_FLAG_PID_CGROUP) {
- err = perf_cgroup_connect(pid, event, &attr, group_leader);
- if (err) {
- __free_event(event);
- goto err_cpus;
- }
- }
-
if (is_sampling_event(event)) {
if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) {
err = -ENOTSUPP;
*/
event = perf_event_alloc(attr, cpu, task, NULL, NULL,
- overflow_handler, context);
+ overflow_handler, context, -1);
if (IS_ERR(event)) {
err = PTR_ERR(event);
goto err;
parent_event->cpu,
child,
group_leader, parent_event,
- NULL, NULL);
+ NULL, NULL, -1);
if (IS_ERR(child_event))
return child_event;
!= 1024);
}
+ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
+ char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr =
+ container_of(attr, struct perf_pmu_events_attr, attr);
+
+ if (pmu_attr->event_str)
+ return sprintf(page, "%s\n", pmu_attr->event_str);
+
+ return 0;
+}
+
static int __init perf_event_sysfs_init(void)
{
struct pmu *pmu;
return true;
list_for_each_entry(event, &filter->perf_events, hw.tp_list) {
- if (event->hw.tp_target->mm == mm)
+ if (event->hw.target->mm == mm)
return true;
}
static inline bool
uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
{
- return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm);
+ return __uprobe_perf_filter(&tu->filter, event->hw.target->mm);
}
static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
bool done;
write_lock(&tu->filter.rwlock);
- if (event->hw.tp_target) {
+ if (event->hw.target) {
list_del(&event->hw.tp_list);
done = tu->filter.nr_systemwide ||
- (event->hw.tp_target->flags & PF_EXITING) ||
+ (event->hw.target->flags & PF_EXITING) ||
uprobe_filter_event(tu, event);
} else {
tu->filter.nr_systemwide--;
int err;
write_lock(&tu->filter.rwlock);
- if (event->hw.tp_target) {
+ if (event->hw.target) {
/*
* event->parent != NULL means copy_process(), we can avoid
* uprobe_apply(). current->mm must be probed and we can rely
struct dentry *d_tracer;
d_tracer = tracing_init_dentry();
- if (!d_tracer)
+ if (IS_ERR(d_tracer))
return 0;
trace_create_file("uprobe_events", 0644, d_tracer,