S: Odd Fixes
F: drivers/char/hvc_*
- VIRTIO CONSOLE DRIVER
- S: Maintained
- F: drivers/char/virtio_console.c
-
iSCSI BOOT FIRMWARE TABLE (iBFT) DRIVER
S: Supported
-F: kernel/perf_event.c
+F: kernel/perf_event*.c
F: include/linux/perf_event.h
-F: arch/*/kernel/perf_event.c
-F: arch/*/kernel/*/perf_event.c
-F: arch/*/kernel/*/*/perf_event.c
+F: arch/*/kernel/perf_event*.c
+F: arch/*/kernel/*/perf_event*.c
+F: arch/*/kernel/*/*/perf_event*.c
F: arch/*/include/asm/perf_event.h
-F: arch/*/lib/perf_event.c
+F: arch/*/lib/perf_event*.c
F: arch/*/kernel/perf_callchain.c
F: tools/perf/
F: Documentation/filesystems/vfat.txt
F: fs/fat/
+ VIRTIO CONSOLE DRIVER
+ S: Maintained
+ F: drivers/char/virtio_console.c
+ F: include/linux/virtio_console.h
+
VIRTIO HOST (VHOST)
select HAVE_ARCH_KMEMCHECK
select HAVE_USER_RETURN_NOTIFIER
+config INSTRUCTION_DECODER
+ def_bool (KPROBES || PERF_EVENTS)
+
config OUTPUT_FORMAT
string
default "elf32-i386" if X86_32
config NODES_SHIFT
int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
- range 1 9
- default "9" if MAXSMP
+ range 1 10
+ default "10" if MAXSMP
default "6" if X86_64
default "4" if X86_NUMAQ
default "3"
#include <linux/kdebug.h>
#include <linux/sched.h>
#include <linux/uaccess.h>
+ #include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/cpu.h>
#include <linux/bitops.h>
#include <asm/nmi.h>
#include <asm/compat.h>
-static u64 perf_event_mask __read_mostly;
+#if 0
+#undef wrmsrl
+#define wrmsrl(msr, val) \
+do { \
+ trace_printk("wrmsrl(%lx, %lx)\n", (unsigned long)(msr),\
+ (unsigned long)(val)); \
+ native_write_msr((msr), (u32)((u64)(val)), \
+ (u32)((u64)(val) >> 32)); \
+} while (0)
+#endif
-/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS 4
+/*
+ * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
+ */
+static unsigned long
+copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
+{
+ unsigned long offset, addr = (unsigned long)from;
+ int type = in_nmi() ? KM_NMI : KM_IRQ0;
+ unsigned long size, len = 0;
+ struct page *page;
+ void *map;
+ int ret;
-/* The size of a BTS record in bytes: */
-#define BTS_RECORD_SIZE 24
+ do {
+ ret = __get_user_pages_fast(addr, 1, 0, &page);
+ if (!ret)
+ break;
-/* The size of a per-cpu BTS buffer in bytes: */
-#define BTS_BUFFER_SIZE (BTS_RECORD_SIZE * 2048)
+ offset = addr & (PAGE_SIZE - 1);
+ size = min(PAGE_SIZE - offset, n - len);
-/* The BTS overflow threshold in bytes from the end of the buffer: */
-#define BTS_OVFL_TH (BTS_RECORD_SIZE * 128)
+ map = kmap_atomic(page, type);
+ memcpy(to, map+offset, size);
+ kunmap_atomic(map, type);
+ put_page(page);
+ len += size;
+ to += size;
+ addr += size;
-/*
- * Bits in the debugctlmsr controlling branch tracing.
- */
-#define X86_DEBUGCTL_TR (1 << 6)
-#define X86_DEBUGCTL_BTS (1 << 7)
-#define X86_DEBUGCTL_BTINT (1 << 8)
-#define X86_DEBUGCTL_BTS_OFF_OS (1 << 9)
-#define X86_DEBUGCTL_BTS_OFF_USR (1 << 10)
+ } while (len < n);
-/*
- * A debug store configuration.
- *
- * We only support architectures that use 64bit fields.
- */
-struct debug_store {
- u64 bts_buffer_base;
- u64 bts_index;
- u64 bts_absolute_maximum;
- u64 bts_interrupt_threshold;
- u64 pebs_buffer_base;
- u64 pebs_index;
- u64 pebs_absolute_maximum;
- u64 pebs_interrupt_threshold;
- u64 pebs_event_reset[MAX_PEBS_EVENTS];
-};
+ return len;
+}
struct event_constraint {
union {
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};
+#define MAX_LBR_ENTRIES 16
+
struct cpu_hw_events {
+ /*
+ * Generic x86 PMC bits
+ */
struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */
unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
- unsigned long interrupts;
int enabled;
- struct debug_store *ds;
int n_events;
int n_added;
int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
u64 tags[X86_PMC_IDX_MAX];
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
+
+ /*
+ * Intel DebugStore bits
+ */
+ struct debug_store *ds;
+ u64 pebs_enabled;
+
+ /*
+ * Intel LBR bits
+ */
+ int lbr_users;
+ void *lbr_context;
+ struct perf_branch_stack lbr_stack;
+ struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
+
+ /*
+ * AMD specific bits
+ */
struct amd_nb *amd_nb;
};
#define EVENT_CONSTRAINT(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n))
+/*
+ * Constraint on the Event code.
+ */
#define INTEL_EVENT_CONSTRAINT(c, n) \
- EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK)
+ EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
+/*
+ * Constraint on the Event code + UMask + fixed-mask
+ *
+ * filter mask to validate fixed counter events.
+ * the following filters disqualify for fixed counters:
+ * - inv
+ * - edge
+ * - cnt-mask
+ * The other filters are supported by fixed counters.
+ * The any-thread option is supported starting with v3.
+ */
#define FIXED_EVENT_CONSTRAINT(c, n) \
- EVENT_CONSTRAINT(c, (1ULL << (32+n)), INTEL_ARCH_FIXED_MASK)
+ EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK)
+
+/*
+ * Constraint on the Event code + UMask
+ */
+#define PEBS_EVENT_CONSTRAINT(c, n) \
+ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
#define EVENT_CONSTRAINT_END \
EVENT_CONSTRAINT(0, 0, 0)
#define for_each_event_constraint(e, c) \
for ((e) = (c); (e)->cmask; (e)++)
+union perf_capabilities {
+ struct {
+ u64 lbr_format : 6;
+ u64 pebs_trap : 1;
+ u64 pebs_arch_reg : 1;
+ u64 pebs_format : 4;
+ u64 smm_freeze : 1;
+ };
+ u64 capabilities;
+};
+
/*
* struct x86_pmu - generic x86 pmu
*/
struct x86_pmu {
+ /*
+ * Generic x86 PMC bits
+ */
const char *name;
int version;
int (*handle_irq)(struct pt_regs *);
void (*disable_all)(void);
- void (*enable_all)(void);
+ void (*enable_all)(int added);
void (*enable)(struct perf_event *);
void (*disable)(struct perf_event *);
+ int (*hw_config)(struct perf_event *event);
+ int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
unsigned eventsel;
unsigned perfctr;
u64 (*event_map)(int);
- u64 (*raw_event)(u64);
int max_events;
- int num_events;
- int num_events_fixed;
- int event_bits;
- u64 event_mask;
+ int num_counters;
+ int num_counters_fixed;
+ int cntval_bits;
+ u64 cntval_mask;
int apic;
u64 max_period;
- u64 intel_ctrl;
- void (*enable_bts)(u64 config);
- void (*disable_bts)(void);
-
struct event_constraint *
(*get_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
void (*put_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
struct event_constraint *event_constraints;
+ void (*quirks)(void);
int (*cpu_prepare)(int cpu);
void (*cpu_starting)(int cpu);
void (*cpu_dying)(int cpu);
void (*cpu_dead)(int cpu);
+
+ /*
+ * Intel Arch Perfmon v2+
+ */
+ u64 intel_ctrl;
+ union perf_capabilities intel_cap;
+
+ /*
+ * Intel DebugStore bits
+ */
+ int bts, pebs;
+ int pebs_record_size;
+ void (*drain_pebs)(struct pt_regs *regs);
+ struct event_constraint *pebs_constraints;
+
+ /*
+ * Intel LBR
+ */
+ unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */
+ int lbr_nr; /* hardware stack size */
};
static struct x86_pmu x86_pmu __read_mostly;
x86_perf_event_update(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- int shift = 64 - x86_pmu.event_bits;
+ int shift = 64 - x86_pmu.cntval_bits;
u64 prev_raw_count, new_raw_count;
int idx = hwc->idx;
s64 delta;
static atomic_t active_events;
static DEFINE_MUTEX(pmc_reserve_mutex);
+#ifdef CONFIG_X86_LOCAL_APIC
+
static bool reserve_pmc_hardware(void)
{
-#ifdef CONFIG_X86_LOCAL_APIC
int i;
if (nmi_watchdog == NMI_LOCAL_APIC)
disable_lapic_nmi_watchdog();
- for (i = 0; i < x86_pmu.num_events; i++) {
+ for (i = 0; i < x86_pmu.num_counters; i++) {
if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
goto perfctr_fail;
}
- for (i = 0; i < x86_pmu.num_events; i++) {
+ for (i = 0; i < x86_pmu.num_counters; i++) {
if (!reserve_evntsel_nmi(x86_pmu.eventsel + i))
goto eventsel_fail;
}
-#endif
return true;
-#ifdef CONFIG_X86_LOCAL_APIC
eventsel_fail:
for (i--; i >= 0; i--)
release_evntsel_nmi(x86_pmu.eventsel + i);
- i = x86_pmu.num_events;
+ i = x86_pmu.num_counters;
perfctr_fail:
for (i--; i >= 0; i--)
enable_lapic_nmi_watchdog();
return false;
-#endif
}
static void release_pmc_hardware(void)
{
-#ifdef CONFIG_X86_LOCAL_APIC
int i;
- for (i = 0; i < x86_pmu.num_events; i++) {
+ for (i = 0; i < x86_pmu.num_counters; i++) {
release_perfctr_nmi(x86_pmu.perfctr + i);
release_evntsel_nmi(x86_pmu.eventsel + i);
}
if (nmi_watchdog == NMI_LOCAL_APIC)
enable_lapic_nmi_watchdog();
-#endif
-}
-
-static inline bool bts_available(void)
-{
- return x86_pmu.enable_bts != NULL;
-}
-
-static void init_debug_store_on_cpu(int cpu)
-{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
- if (!ds)
- return;
-
- wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA,
- (u32)((u64)(unsigned long)ds),
- (u32)((u64)(unsigned long)ds >> 32));
-}
-
-static void fini_debug_store_on_cpu(int cpu)
-{
- if (!per_cpu(cpu_hw_events, cpu).ds)
- return;
-
- wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
-}
-
-static void release_bts_hardware(void)
-{
- int cpu;
-
- if (!bts_available())
- return;
-
- get_online_cpus();
-
- for_each_online_cpu(cpu)
- fini_debug_store_on_cpu(cpu);
-
- for_each_possible_cpu(cpu) {
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
- if (!ds)
- continue;
-
- per_cpu(cpu_hw_events, cpu).ds = NULL;
-
- kfree((void *)(unsigned long)ds->bts_buffer_base);
- kfree(ds);
- }
-
- put_online_cpus();
}
-static int reserve_bts_hardware(void)
-{
- int cpu, err = 0;
-
- if (!bts_available())
- return 0;
-
- get_online_cpus();
-
- for_each_possible_cpu(cpu) {
- struct debug_store *ds;
- void *buffer;
-
- err = -ENOMEM;
- buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
- if (unlikely(!buffer))
- break;
-
- ds = kzalloc(sizeof(*ds), GFP_KERNEL);
- if (unlikely(!ds)) {
- kfree(buffer);
- break;
- }
+#else
- ds->bts_buffer_base = (u64)(unsigned long)buffer;
- ds->bts_index = ds->bts_buffer_base;
- ds->bts_absolute_maximum =
- ds->bts_buffer_base + BTS_BUFFER_SIZE;
- ds->bts_interrupt_threshold =
- ds->bts_absolute_maximum - BTS_OVFL_TH;
+static bool reserve_pmc_hardware(void) { return true; }
+static void release_pmc_hardware(void) {}
- per_cpu(cpu_hw_events, cpu).ds = ds;
- err = 0;
- }
-
- if (err)
- release_bts_hardware();
- else {
- for_each_online_cpu(cpu)
- init_debug_store_on_cpu(cpu);
- }
-
- put_online_cpus();
+#endif
- return err;
-}
+static int reserve_ds_buffers(void);
+static void release_ds_buffers(void);
static void hw_perf_event_destroy(struct perf_event *event)
{
if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) {
release_pmc_hardware();
- release_bts_hardware();
+ release_ds_buffers();
mutex_unlock(&pmc_reserve_mutex);
}
}
return 0;
}
+static int x86_pmu_hw_config(struct perf_event *event)
+{
+ /*
+ * Generate PMC IRQs:
+ * (keep 'enabled' bit clear for now)
+ */
+ event->hw.config = ARCH_PERFMON_EVENTSEL_INT;
+
+ /*
+ * Count user and OS events unless requested not to
+ */
+ if (!event->attr.exclude_user)
+ event->hw.config |= ARCH_PERFMON_EVENTSEL_USR;
+ if (!event->attr.exclude_kernel)
+ event->hw.config |= ARCH_PERFMON_EVENTSEL_OS;
+
+ if (event->attr.type == PERF_TYPE_RAW)
+ event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
+
+ return 0;
+}
+
/*
* Setup the hardware configuration for a given attr_type
*/
if (atomic_read(&active_events) == 0) {
if (!reserve_pmc_hardware())
err = -EBUSY;
- else
- err = reserve_bts_hardware();
+ else {
+ err = reserve_ds_buffers();
+ if (err)
+ release_pmc_hardware();
+ }
}
if (!err)
atomic_inc(&active_events);
event->destroy = hw_perf_event_destroy;
- /*
- * Generate PMC IRQs:
- * (keep 'enabled' bit clear for now)
- */
- hwc->config = ARCH_PERFMON_EVENTSEL_INT;
-
hwc->idx = -1;
hwc->last_cpu = -1;
hwc->last_tag = ~0ULL;
- /*
- * Count user and OS events unless requested not to.
- */
- if (!attr->exclude_user)
- hwc->config |= ARCH_PERFMON_EVENTSEL_USR;
- if (!attr->exclude_kernel)
- hwc->config |= ARCH_PERFMON_EVENTSEL_OS;
+ /* Processor specifics */
+ err = x86_pmu.hw_config(event);
+ if (err)
+ return err;
if (!hwc->sample_period) {
hwc->sample_period = x86_pmu.max_period;
return -EOPNOTSUPP;
}
- /*
- * Raw hw_event type provide the config in the hw_event structure
- */
- if (attr->type == PERF_TYPE_RAW) {
- hwc->config |= x86_pmu.raw_event(attr->config);
- if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) &&
- perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
- return -EACCES;
+ if (attr->type == PERF_TYPE_RAW)
return 0;
- }
if (attr->type == PERF_TYPE_HW_CACHE)
return set_ext_hw_attr(hwc, attr);
if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
(hwc->sample_period == 1)) {
/* BTS is not supported by this architecture. */
- if (!bts_available())
+ if (!x86_pmu.bts)
return -EOPNOTSUPP;
/* BTS is currently only allowed for user-mode. */
- if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+ if (!attr->exclude_kernel)
return -EOPNOTSUPP;
}
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_events; idx++) {
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
u64 val;
if (!test_bit(idx, cpuc->active_mask))
x86_pmu.disable_all();
}
-static void x86_pmu_enable_all(void)
+static void x86_pmu_enable_all(int added)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_events; idx++) {
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
struct perf_event *event = cpuc->events[idx];
u64 val;
* assign events to counters starting with most
* constrained events.
*/
- wmax = x86_pmu.num_events;
+ wmax = x86_pmu.num_counters;
/*
* when fixed event counters are present,
* wmax is incremented by 1 to account
* for one more choice
*/
- if (x86_pmu.num_events_fixed)
+ if (x86_pmu.num_counters_fixed)
wmax++;
for (w = 1, num = n; num && w <= wmax; w++) {
struct perf_event *event;
int n, max_count;
- max_count = x86_pmu.num_events + x86_pmu.num_events_fixed;
+ max_count = x86_pmu.num_counters + x86_pmu.num_counters_fixed;
/* current number of events already accepted */
n = cpuc->n_events;
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct perf_event *event;
struct hw_perf_event *hwc;
- int i;
+ int i, added = cpuc->n_added;
if (!x86_pmu_initialized())
return;
cpuc->enabled = 1;
barrier();
- x86_pmu.enable_all();
+ x86_pmu.enable_all(added);
}
static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc)
{
- (void)checking_wrmsrl(hwc->config_base + hwc->idx,
+ wrmsrl(hwc->config_base + hwc->idx,
hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE);
}
static inline void x86_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- (void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config);
+
+ wrmsrl(hwc->config_base + hwc->idx, hwc->config);
}
static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
struct hw_perf_event *hwc = &event->hw;
s64 left = atomic64_read(&hwc->period_left);
s64 period = hwc->sample_period;
- int err, ret = 0, idx = hwc->idx;
+ int ret = 0, idx = hwc->idx;
if (idx == X86_PMC_IDX_FIXED_BTS)
return 0;
*/
atomic64_set(&hwc->prev_count, (u64)-left);
- err = checking_wrmsrl(hwc->event_base + idx,
- (u64)(-left) & x86_pmu.event_mask);
+ wrmsrl(hwc->event_base + idx,
+ (u64)(-left) & x86_pmu.cntval_mask);
perf_event_update_userpage(event);
if (n < 0)
return n;
- ret = x86_schedule_events(cpuc, n, assign);
+ ret = x86_pmu.schedule_events(cpuc, n, assign);
if (ret)
return ret;
/*
void perf_event_print_debug(void)
{
u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
+ u64 pebs;
struct cpu_hw_events *cpuc;
unsigned long flags;
int cpu, idx;
- if (!x86_pmu.num_events)
+ if (!x86_pmu.num_counters)
return;
local_irq_save(flags);
rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow);
rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed);
+ rdmsrl(MSR_IA32_PEBS_ENABLE, pebs);
pr_info("\n");
pr_info("CPU#%d: ctrl: %016llx\n", cpu, ctrl);
pr_info("CPU#%d: status: %016llx\n", cpu, status);
pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow);
pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed);
+ pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs);
}
- pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
+ pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
- for (idx = 0; idx < x86_pmu.num_events; idx++) {
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
rdmsrl(x86_pmu.perfctr + idx, pmc_count);
pr_info("CPU#%d: gen-PMC%d left: %016llx\n",
cpu, idx, prev_left);
}
- for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
+ for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
cpuc = &__get_cpu_var(cpu_hw_events);
- for (idx = 0; idx < x86_pmu.num_events; idx++) {
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
if (!test_bit(idx, cpuc->active_mask))
continue;
hwc = &event->hw;
val = x86_perf_event_update(event);
- if (val & (1ULL << (x86_pmu.event_bits - 1)))
+ if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
continue;
/*
void perf_events_lapic_init(void)
{
-#ifdef CONFIG_X86_LOCAL_APIC
if (!x86_pmu.apic || !x86_pmu_initialized())
return;
* Always use NMI for PMU
*/
apic_write(APIC_LVTPC, APIC_DM_NMI);
-#endif
}
static int __kprobes
regs = args->regs;
-#ifdef CONFIG_X86_LOCAL_APIC
apic_write(APIC_LVTPC, APIC_DM_NMI);
-#endif
/*
* Can't rely on the handled return value to say it was our NMI, two
* events could trigger 'simultaneously' raising two back-to-back NMIs.
int assign[X86_PMC_IDX_MAX];
int n0, n1, ret;
+ if (!x86_pmu_initialized())
+ return 0;
+
/* n0 = total number of events */
n0 = collect_events(cpuc, leader, true);
if (n0 < 0)
return n0;
- ret = x86_schedule_events(cpuc, n0, assign);
+ ret = x86_pmu.schedule_events(cpuc, n0, assign);
if (ret)
return ret;
#include "perf_event_amd.c"
#include "perf_event_p6.c"
+#include "perf_event_p4.c"
+#include "perf_event_intel_lbr.c"
+#include "perf_event_intel_ds.c"
#include "perf_event_intel.c"
static int __cpuinit
pr_cont("%s PMU driver.\n", x86_pmu.name);
- if (x86_pmu.num_events > X86_PMC_MAX_GENERIC) {
+ if (x86_pmu.quirks)
+ x86_pmu.quirks();
+
+ if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
- x86_pmu.num_events, X86_PMC_MAX_GENERIC);
- x86_pmu.num_events = X86_PMC_MAX_GENERIC;
+ x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
+ x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
}
- perf_event_mask = (1 << x86_pmu.num_events) - 1;
- perf_max_events = x86_pmu.num_events;
+ x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+ perf_max_events = x86_pmu.num_counters;
- if (x86_pmu.num_events_fixed > X86_PMC_MAX_FIXED) {
+ if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
- x86_pmu.num_events_fixed, X86_PMC_MAX_FIXED);
- x86_pmu.num_events_fixed = X86_PMC_MAX_FIXED;
+ x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
+ x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
}
- perf_event_mask |=
- ((1LL << x86_pmu.num_events_fixed)-1) << X86_PMC_IDX_FIXED;
- x86_pmu.intel_ctrl = perf_event_mask;
+ x86_pmu.intel_ctrl |=
+ ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
perf_events_lapic_init();
register_die_notifier(&perf_event_nmi_notifier);
unconstrained = (struct event_constraint)
- __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1,
- 0, x86_pmu.num_events);
+ __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
+ 0, x86_pmu.num_counters);
if (x86_pmu.event_constraints) {
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if (c->cmask != INTEL_ARCH_FIXED_MASK)
+ if (c->cmask != X86_RAW_EVENT_MASK)
continue;
- c->idxmsk64 |= (1ULL << x86_pmu.num_events) - 1;
- c->weight += x86_pmu.num_events;
+ c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+ c->weight += x86_pmu.num_counters;
}
}
pr_info("... version: %d\n", x86_pmu.version);
- pr_info("... bit width: %d\n", x86_pmu.event_bits);
- pr_info("... generic registers: %d\n", x86_pmu.num_events);
- pr_info("... value mask: %016Lx\n", x86_pmu.event_mask);
+ pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
+ pr_info("... generic registers: %d\n", x86_pmu.num_counters);
+ pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask);
pr_info("... max period: %016Lx\n", x86_pmu.max_period);
- pr_info("... fixed-purpose events: %d\n", x86_pmu.num_events_fixed);
- pr_info("... event mask: %016Lx\n", perf_event_mask);
+ pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed);
+ pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl);
perf_cpu_notifier(x86_pmu_notifier);
}
.unthrottle = x86_pmu_unthrottle,
};
+/*
+ * validate that we can schedule this event
+ */
+static int validate_event(struct perf_event *event)
+{
+ struct cpu_hw_events *fake_cpuc;
+ struct event_constraint *c;
+ int ret = 0;
+
+ fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO);
+ if (!fake_cpuc)
+ return -ENOMEM;
+
+ c = x86_pmu.get_event_constraints(fake_cpuc, event);
+
+ if (!c || !c->weight)
+ ret = -ENOSPC;
+
+ if (x86_pmu.put_event_constraints)
+ x86_pmu.put_event_constraints(fake_cpuc, event);
+
+ kfree(fake_cpuc);
+
+ return ret;
+}
+
/*
* validate a single event group
*
fake_cpuc->n_events = n;
- ret = x86_schedule_events(fake_cpuc, n, NULL);
+ ret = x86_pmu.schedule_events(fake_cpuc, n, NULL);
out_free:
kfree(fake_cpuc);
if (event->group_leader != event)
err = validate_group(event);
+ else
+ err = validate_event(event);
event->pmu = tmp;
}
{
struct perf_callchain_entry *entry = data;
- if (reliable)
- callchain_store(entry, addr);
+ callchain_store(entry, addr);
}
static const struct stacktrace_ops backtrace_ops = {
dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
}
-/*
- * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
- */
-static unsigned long
-copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
-{
- unsigned long offset, addr = (unsigned long)from;
- int type = in_nmi() ? KM_NMI : KM_IRQ0;
- unsigned long size, len = 0;
- struct page *page;
- void *map;
- int ret;
-
- do {
- ret = __get_user_pages_fast(addr, 1, 0, &page);
- if (!ret)
- break;
-
- offset = addr & (PAGE_SIZE - 1);
- size = min(PAGE_SIZE - offset, n - len);
-
- map = kmap_atomic(page, type);
- memcpy(to, map+offset, size);
- kunmap_atomic(map, type);
- put_page(page);
-
- len += size;
- to += size;
- addr += size;
-
- } while (len < n);
-
- return len;
-}
-
#ifdef CONFIG_COMPAT
static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
return intel_perfmon_event_map[hw_event];
}
-static __initconst u64 westmere_hw_cache_event_ids
+static __initconst const u64 westmere_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
},
};
-static __initconst u64 nehalem_hw_cache_event_ids
+static __initconst const u64 nehalem_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
},
};
-static __initconst u64 core2_hw_cache_event_ids
+static __initconst const u64 core2_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
},
};
-static __initconst u64 atom_hw_cache_event_ids
+static __initconst const u64 atom_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
},
};
-static u64 intel_pmu_raw_event(u64 hw_event)
-{
-#define CORE_EVNTSEL_EVENT_MASK 0x000000FFULL
-#define CORE_EVNTSEL_UNIT_MASK 0x0000FF00ULL
-#define CORE_EVNTSEL_EDGE_MASK 0x00040000ULL
-#define CORE_EVNTSEL_INV_MASK 0x00800000ULL
-#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL
-
-#define CORE_EVNTSEL_MASK \
- (INTEL_ARCH_EVTSEL_MASK | \
- INTEL_ARCH_UNIT_MASK | \
- INTEL_ARCH_EDGE_MASK | \
- INTEL_ARCH_INV_MASK | \
- INTEL_ARCH_CNT_MASK)
-
- return hw_event & CORE_EVNTSEL_MASK;
-}
-
-static void intel_pmu_enable_bts(u64 config)
-{
- unsigned long debugctlmsr;
-
- debugctlmsr = get_debugctlmsr();
-
- debugctlmsr |= X86_DEBUGCTL_TR;
- debugctlmsr |= X86_DEBUGCTL_BTS;
- debugctlmsr |= X86_DEBUGCTL_BTINT;
-
- if (!(config & ARCH_PERFMON_EVENTSEL_OS))
- debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS;
-
- if (!(config & ARCH_PERFMON_EVENTSEL_USR))
- debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR;
-
- update_debugctlmsr(debugctlmsr);
-}
-
-static void intel_pmu_disable_bts(void)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- unsigned long debugctlmsr;
-
- if (!cpuc->ds)
- return;
-
- debugctlmsr = get_debugctlmsr();
-
- debugctlmsr &=
- ~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT |
- X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR);
-
- update_debugctlmsr(debugctlmsr);
-}
-
static void intel_pmu_disable_all(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
+
+ intel_pmu_pebs_disable_all();
+ intel_pmu_lbr_disable_all();
}
-static void intel_pmu_enable_all(void)
+static void intel_pmu_enable_all(int added)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ intel_pmu_pebs_enable_all();
+ intel_pmu_lbr_enable_all();
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
}
}
+/*
+ * Workaround for:
+ * Intel Errata AAK100 (model 26)
+ * Intel Errata AAP53 (model 30)
+ * Intel Errata BD53 (model 44)
+ *
+ * These chips need to be 'reset' when adding counters by programming
+ * the magic three (non counting) events 0x4300D2, 0x4300B1 and 0x4300B5
+ * either in sequence on the same PMC or on different PMCs.
+ */
+static void intel_pmu_nhm_enable_all(int added)
+{
+ if (added) {
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ int i;
+
+ wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 0, 0x4300D2);
+ wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x4300B1);
+ wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x4300B5);
+
+ wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x3);
+ wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
+
+ for (i = 0; i < 3; i++) {
+ struct perf_event *event = cpuc->events[i];
+
+ if (!event)
+ continue;
+
+ __x86_pmu_enable_event(&event->hw);
+ }
+ }
+ intel_pmu_enable_all(added);
+}
+
static inline u64 intel_pmu_get_status(void)
{
u64 status;
wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
}
-static inline void
-intel_pmu_disable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
{
int idx = hwc->idx - X86_PMC_IDX_FIXED;
u64 ctrl_val, mask;
rdmsrl(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
- (void)checking_wrmsrl(hwc->config_base, ctrl_val);
-}
-
-static void intel_pmu_drain_bts_buffer(void)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct debug_store *ds = cpuc->ds;
- struct bts_record {
- u64 from;
- u64 to;
- u64 flags;
- };
- struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
- struct bts_record *at, *top;
- struct perf_output_handle handle;
- struct perf_event_header header;
- struct perf_sample_data data;
- struct pt_regs regs;
-
- if (!event)
- return;
-
- if (!ds)
- return;
-
- at = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
- top = (struct bts_record *)(unsigned long)ds->bts_index;
-
- if (top <= at)
- return;
-
- ds->bts_index = ds->bts_buffer_base;
-
- perf_sample_data_init(&data, 0);
-
- data.period = event->hw.last_period;
- regs.ip = 0;
-
- /*
- * Prepare a generic sample, i.e. fill in the invariant fields.
- * We will overwrite the from and to address before we output
- * the sample.
- */
- perf_prepare_sample(&header, &data, event, ®s);
-
- if (perf_output_begin(&handle, event,
- header.size * (top - at), 1, 1))
- return;
-
- for (; at < top; at++) {
- data.ip = at->from;
- data.addr = at->to;
-
- perf_output_sample(&handle, &header, &data, event);
- }
-
- perf_output_end(&handle);
-
- /* There's new data available. */
- event->hw.interrupts++;
- event->pending_kill = POLL_IN;
+ wrmsrl(hwc->config_base, ctrl_val);
}
-static inline void
-intel_pmu_disable_event(struct perf_event *event)
+static void intel_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
}
x86_pmu_disable_event(event);
+
+ if (unlikely(event->attr.precise))
+ intel_pmu_pebs_disable(event);
}
-static inline void
-intel_pmu_enable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
{
int idx = hwc->idx - X86_PMC_IDX_FIXED;
u64 ctrl_val, bits, mask;
- int err;
/*
* Enable IRQ generation (0x8),
rdmsrl(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
ctrl_val |= bits;
- err = checking_wrmsrl(hwc->config_base, ctrl_val);
+ wrmsrl(hwc->config_base, ctrl_val);
}
static void intel_pmu_enable_event(struct perf_event *event)
return;
}
+ if (unlikely(event->attr.precise))
+ intel_pmu_pebs_enable(event);
+
__x86_pmu_enable_event(hwc);
}
unsigned long flags;
int idx;
- if (!x86_pmu.num_events)
+ if (!x86_pmu.num_counters)
return;
local_irq_save(flags);
printk("clearing PMU state on CPU#%d\n", smp_processor_id());
- for (idx = 0; idx < x86_pmu.num_events; idx++) {
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
checking_wrmsrl(x86_pmu.perfctr + idx, 0ull);
}
- for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
+ for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
- }
+
if (ds)
ds->bts_index = ds->bts_buffer_base;
intel_pmu_drain_bts_buffer();
status = intel_pmu_get_status();
if (!status) {
- intel_pmu_enable_all();
+ intel_pmu_enable_all(0);
return 0;
}
inc_irq_stat(apic_perf_irqs);
ack = status;
+
+ intel_pmu_lbr_read();
+
+ /*
+ * PEBS overflow sets bit 62 in the global status register
+ */
+ if (__test_and_clear_bit(62, (unsigned long *)&status))
+ x86_pmu.drain_pebs(regs);
+
for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[bit];
goto again;
done:
- intel_pmu_enable_all();
+ intel_pmu_enable_all(0);
return 1;
}
-static struct event_constraint bts_constraint =
- EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
-
static struct event_constraint *
-intel_special_constraints(struct perf_event *event)
+intel_bts_constraints(struct perf_event *event)
{
- unsigned int hw_event;
-
- hw_event = event->hw.config & INTEL_ARCH_EVENT_MASK;
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned int hw_event, bts_event;
- if (unlikely((hw_event ==
- x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) &&
- (event->hw.sample_period == 1))) {
+ hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
+ bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
+ if (unlikely(hw_event == bts_event && hwc->sample_period == 1))
return &bts_constraint;
- }
+
return NULL;
}
{
struct event_constraint *c;
- c = intel_special_constraints(event);
+ c = intel_bts_constraints(event);
+ if (c)
+ return c;
+
+ c = intel_pebs_constraints(event);
if (c)
return c;
return x86_get_event_constraints(cpuc, event);
}
-static __initconst struct x86_pmu core_pmu = {
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+ int ret = x86_pmu_hw_config(event);
+
+ if (ret)
+ return ret;
+
+ if (event->attr.type != PERF_TYPE_RAW)
+ return 0;
+
+ if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY))
+ return 0;
+
+ if (x86_pmu.version < 3)
+ return -EINVAL;
+
+ if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
+ event->hw.config |= ARCH_PERFMON_EVENTSEL_ANY;
+
+ return 0;
+}
+
+static __initconst const struct x86_pmu core_pmu = {
.name = "core",
.handle_irq = x86_pmu_handle_irq,
.disable_all = x86_pmu_disable_all,
.enable_all = x86_pmu_enable_all,
.enable = x86_pmu_enable_event,
.disable = x86_pmu_disable_event,
+ .hw_config = x86_pmu_hw_config,
+ .schedule_events = x86_schedule_events,
.eventsel = MSR_ARCH_PERFMON_EVENTSEL0,
.perfctr = MSR_ARCH_PERFMON_PERFCTR0,
.event_map = intel_pmu_event_map,
- .raw_event = intel_pmu_raw_event,
.max_events = ARRAY_SIZE(intel_perfmon_event_map),
.apic = 1,
/*
.event_constraints = intel_core_event_constraints,
};
-static __initconst struct x86_pmu intel_pmu = {
+static void intel_pmu_cpu_starting(int cpu)
+{
+ init_debug_store_on_cpu(cpu);
+ /*
+ * Deal with CPUs that don't clear their LBRs on power-up.
+ */
+ intel_pmu_lbr_reset();
+}
+
+static void intel_pmu_cpu_dying(int cpu)
+{
+ fini_debug_store_on_cpu(cpu);
+}
+
+static __initconst const struct x86_pmu intel_pmu = {
.name = "Intel",
.handle_irq = intel_pmu_handle_irq,
.disable_all = intel_pmu_disable_all,
.enable_all = intel_pmu_enable_all,
.enable = intel_pmu_enable_event,
.disable = intel_pmu_disable_event,
+ .hw_config = intel_pmu_hw_config,
+ .schedule_events = x86_schedule_events,
.eventsel = MSR_ARCH_PERFMON_EVENTSEL0,
.perfctr = MSR_ARCH_PERFMON_PERFCTR0,
.event_map = intel_pmu_event_map,
- .raw_event = intel_pmu_raw_event,
.max_events = ARRAY_SIZE(intel_perfmon_event_map),
.apic = 1,
/*
* the generic event period:
*/
.max_period = (1ULL << 31) - 1,
- .enable_bts = intel_pmu_enable_bts,
- .disable_bts = intel_pmu_disable_bts,
.get_event_constraints = intel_get_event_constraints,
- .cpu_starting = init_debug_store_on_cpu,
- .cpu_dying = fini_debug_store_on_cpu,
+ .cpu_starting = intel_pmu_cpu_starting,
+ .cpu_dying = intel_pmu_cpu_dying,
};
+static void intel_clovertown_quirks(void)
+{
+ /*
+ * PEBS is unreliable due to:
+ *
+ * AJ67 - PEBS may experience CPL leaks
+ * AJ68 - PEBS PMI may be delayed by one event
+ * AJ69 - GLOBAL_STATUS[62] will only be set when DEBUGCTL[12]
+ * AJ106 - FREEZE_LBRS_ON_PMI doesn't work in combination with PEBS
+ *
+ * AJ67 could be worked around by restricting the OS/USR flags.
+ * AJ69 could be worked around by setting PMU_FREEZE_ON_PMI.
+ *
+ * AJ106 could possibly be worked around by not allowing LBR
+ * usage from PEBS, including the fixup.
+ * AJ68 could possibly be worked around by always programming
+ * a pebs_event_reset[0] value and coping with the lost events.
+ *
+ * But taken together it might just make sense to not enable PEBS on
+ * these chips.
+ */
+ printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
+ x86_pmu.pebs = 0;
+ x86_pmu.pebs_constraints = NULL;
+}
+
static __init int intel_pmu_init(void)
{
union cpuid10_edx edx;
int version;
if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
- /* check for P6 processor family */
- if (boot_cpu_data.x86 == 6) {
- return p6_pmu_init();
- } else {
+ switch (boot_cpu_data.x86) {
+ case 0x6:
+ return p6_pmu_init();
+ case 0xf:
+ return p4_pmu_init();
+ }
return -ENODEV;
- }
}
/*
x86_pmu = intel_pmu;
x86_pmu.version = version;
- x86_pmu.num_events = eax.split.num_events;
- x86_pmu.event_bits = eax.split.bit_width;
- x86_pmu.event_mask = (1ULL << eax.split.bit_width) - 1;
+ x86_pmu.num_counters = eax.split.num_counters;
+ x86_pmu.cntval_bits = eax.split.bit_width;
+ x86_pmu.cntval_mask = (1ULL << eax.split.bit_width) - 1;
/*
* Quirk: v2 perfmon does not report fixed-purpose events, so
* assume at least 3 events:
*/
if (version > 1)
- x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3);
+ x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
+
+ /*
+ * v2 and above have a perf capabilities MSR
+ */
+ if (version > 1) {
+ u64 capabilities;
+
+ rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
+ x86_pmu.intel_cap.capabilities = capabilities;
+ }
+
+ intel_ds_init();
/*
* Install the hw-cache-events table:
break;
case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+ x86_pmu.quirks = intel_clovertown_quirks;
case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
case 29: /* six-core 45 nm xeon "Dunnington" */
memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ intel_pmu_lbr_init_core();
+
x86_pmu.event_constraints = intel_core2_event_constraints;
pr_cont("Core2 events, ");
break;
case 26: /* 45 nm nehalem, "Bloomfield" */
case 30: /* 45 nm nehalem, "Lynnfield" */
+ case 46: /* 45 nm nehalem-ex, "Beckton" */
memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ intel_pmu_lbr_init_nhm();
+
x86_pmu.event_constraints = intel_nehalem_event_constraints;
- pr_cont("Nehalem/Corei7 events, ");
+ x86_pmu.enable_all = intel_pmu_nhm_enable_all;
+ pr_cont("Nehalem events, ");
break;
+
case 28: /* Atom */
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ intel_pmu_lbr_init_atom();
+
x86_pmu.event_constraints = intel_gen_event_constraints;
pr_cont("Atom events, ");
break;
memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ intel_pmu_lbr_init_nhm();
+
x86_pmu.event_constraints = intel_westmere_event_constraints;
+ x86_pmu.enable_all = intel_pmu_nhm_enable_all;
pr_cont("Westmere events, ");
break;
--- /dev/null
- for_each_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) {
+#ifdef CONFIG_CPU_SUP_INTEL
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS 4
+
+/* The size of a BTS record in bytes: */
+#define BTS_RECORD_SIZE 24
+
+#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE PAGE_SIZE
+
+/*
+ * pebs_record_32 for p4 and core not supported
+
+struct pebs_record_32 {
+ u32 flags, ip;
+ u32 ax, bc, cx, dx;
+ u32 si, di, bp, sp;
+};
+
+ */
+
+struct pebs_record_core {
+ u64 flags, ip;
+ u64 ax, bx, cx, dx;
+ u64 si, di, bp, sp;
+ u64 r8, r9, r10, r11;
+ u64 r12, r13, r14, r15;
+};
+
+struct pebs_record_nhm {
+ u64 flags, ip;
+ u64 ax, bx, cx, dx;
+ u64 si, di, bp, sp;
+ u64 r8, r9, r10, r11;
+ u64 r12, r13, r14, r15;
+ u64 status, dla, dse, lat;
+};
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+ u64 bts_buffer_base;
+ u64 bts_index;
+ u64 bts_absolute_maximum;
+ u64 bts_interrupt_threshold;
+ u64 pebs_buffer_base;
+ u64 pebs_index;
+ u64 pebs_absolute_maximum;
+ u64 pebs_interrupt_threshold;
+ u64 pebs_event_reset[MAX_PEBS_EVENTS];
+};
+
+static void init_debug_store_on_cpu(int cpu)
+{
+ struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+ if (!ds)
+ return;
+
+ wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA,
+ (u32)((u64)(unsigned long)ds),
+ (u32)((u64)(unsigned long)ds >> 32));
+}
+
+static void fini_debug_store_on_cpu(int cpu)
+{
+ if (!per_cpu(cpu_hw_events, cpu).ds)
+ return;
+
+ wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
+}
+
+static void release_ds_buffers(void)
+{
+ int cpu;
+
+ if (!x86_pmu.bts && !x86_pmu.pebs)
+ return;
+
+ get_online_cpus();
+
+ for_each_online_cpu(cpu)
+ fini_debug_store_on_cpu(cpu);
+
+ for_each_possible_cpu(cpu) {
+ struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+ if (!ds)
+ continue;
+
+ per_cpu(cpu_hw_events, cpu).ds = NULL;
+
+ kfree((void *)(unsigned long)ds->pebs_buffer_base);
+ kfree((void *)(unsigned long)ds->bts_buffer_base);
+ kfree(ds);
+ }
+
+ put_online_cpus();
+}
+
+static int reserve_ds_buffers(void)
+{
+ int cpu, err = 0;
+
+ if (!x86_pmu.bts && !x86_pmu.pebs)
+ return 0;
+
+ get_online_cpus();
+
+ for_each_possible_cpu(cpu) {
+ struct debug_store *ds;
+ void *buffer;
+ int max, thresh;
+
+ err = -ENOMEM;
+ ds = kzalloc(sizeof(*ds), GFP_KERNEL);
+ if (unlikely(!ds))
+ break;
+ per_cpu(cpu_hw_events, cpu).ds = ds;
+
+ if (x86_pmu.bts) {
+ buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
+ if (unlikely(!buffer))
+ break;
+
+ max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+ thresh = max / 16;
+
+ ds->bts_buffer_base = (u64)(unsigned long)buffer;
+ ds->bts_index = ds->bts_buffer_base;
+ ds->bts_absolute_maximum = ds->bts_buffer_base +
+ max * BTS_RECORD_SIZE;
+ ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+ thresh * BTS_RECORD_SIZE;
+ }
+
+ if (x86_pmu.pebs) {
+ buffer = kzalloc(PEBS_BUFFER_SIZE, GFP_KERNEL);
+ if (unlikely(!buffer))
+ break;
+
+ max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+
+ ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+ ds->pebs_index = ds->pebs_buffer_base;
+ ds->pebs_absolute_maximum = ds->pebs_buffer_base +
+ max * x86_pmu.pebs_record_size;
+ /*
+ * Always use single record PEBS
+ */
+ ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
+ x86_pmu.pebs_record_size;
+ }
+
+ err = 0;
+ }
+
+ if (err)
+ release_ds_buffers();
+ else {
+ for_each_online_cpu(cpu)
+ init_debug_store_on_cpu(cpu);
+ }
+
+ put_online_cpus();
+
+ return err;
+}
+
+/*
+ * BTS
+ */
+
+static struct event_constraint bts_constraint =
+ EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
+
+static void intel_pmu_enable_bts(u64 config)
+{
+ unsigned long debugctlmsr;
+
+ debugctlmsr = get_debugctlmsr();
+
+ debugctlmsr |= DEBUGCTLMSR_TR;
+ debugctlmsr |= DEBUGCTLMSR_BTS;
+ debugctlmsr |= DEBUGCTLMSR_BTINT;
+
+ if (!(config & ARCH_PERFMON_EVENTSEL_OS))
+ debugctlmsr |= DEBUGCTLMSR_BTS_OFF_OS;
+
+ if (!(config & ARCH_PERFMON_EVENTSEL_USR))
+ debugctlmsr |= DEBUGCTLMSR_BTS_OFF_USR;
+
+ update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_disable_bts(void)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ unsigned long debugctlmsr;
+
+ if (!cpuc->ds)
+ return;
+
+ debugctlmsr = get_debugctlmsr();
+
+ debugctlmsr &=
+ ~(DEBUGCTLMSR_TR | DEBUGCTLMSR_BTS | DEBUGCTLMSR_BTINT |
+ DEBUGCTLMSR_BTS_OFF_OS | DEBUGCTLMSR_BTS_OFF_USR);
+
+ update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_drain_bts_buffer(void)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct debug_store *ds = cpuc->ds;
+ struct bts_record {
+ u64 from;
+ u64 to;
+ u64 flags;
+ };
+ struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
+ struct bts_record *at, *top;
+ struct perf_output_handle handle;
+ struct perf_event_header header;
+ struct perf_sample_data data;
+ struct pt_regs regs;
+
+ if (!event)
+ return;
+
+ if (!ds)
+ return;
+
+ at = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
+ top = (struct bts_record *)(unsigned long)ds->bts_index;
+
+ if (top <= at)
+ return;
+
+ ds->bts_index = ds->bts_buffer_base;
+
+ perf_sample_data_init(&data, 0);
+ data.period = event->hw.last_period;
+ regs.ip = 0;
+
+ /*
+ * Prepare a generic sample, i.e. fill in the invariant fields.
+ * We will overwrite the from and to address before we output
+ * the sample.
+ */
+ perf_prepare_sample(&header, &data, event, ®s);
+
+ if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1))
+ return;
+
+ for (; at < top; at++) {
+ data.ip = at->from;
+ data.addr = at->to;
+
+ perf_output_sample(&handle, &header, &data, event);
+ }
+
+ perf_output_end(&handle);
+
+ /* There's new data available. */
+ event->hw.interrupts++;
+ event->pending_kill = POLL_IN;
+}
+
+/*
+ * PEBS
+ */
+
+static struct event_constraint intel_core_pebs_events[] = {
+ PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */
+ PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
+ PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
+ PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
+ PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */
+ PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
+ PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */
+ PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
+ PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_nehalem_pebs_events[] = {
+ PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */
+ PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */
+ PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */
+ PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */
+ PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */
+ PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
+ PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */
+ PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
+ PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint *
+intel_pebs_constraints(struct perf_event *event)
+{
+ struct event_constraint *c;
+
+ if (!event->attr.precise)
+ return NULL;
+
+ if (x86_pmu.pebs_constraints) {
+ for_each_event_constraint(c, x86_pmu.pebs_constraints) {
+ if ((event->hw.config & c->cmask) == c->code)
+ return c;
+ }
+ }
+
+ return &emptyconstraint;
+}
+
+static void intel_pmu_pebs_enable(struct perf_event *event)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
+
+ hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
+
+ cpuc->pebs_enabled |= 1ULL << hwc->idx;
+ WARN_ON_ONCE(cpuc->enabled);
+
+ if (x86_pmu.intel_cap.pebs_trap)
+ intel_pmu_lbr_enable(event);
+}
+
+static void intel_pmu_pebs_disable(struct perf_event *event)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
+
+ cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
+ if (cpuc->enabled)
+ wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+
+ hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
+
+ if (x86_pmu.intel_cap.pebs_trap)
+ intel_pmu_lbr_disable(event);
+}
+
+static void intel_pmu_pebs_enable_all(void)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+ if (cpuc->pebs_enabled)
+ wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+}
+
+static void intel_pmu_pebs_disable_all(void)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+ if (cpuc->pebs_enabled)
+ wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+}
+
+#include <asm/insn.h>
+
+static inline bool kernel_ip(unsigned long ip)
+{
+#ifdef CONFIG_X86_32
+ return ip > PAGE_OFFSET;
+#else
+ return (long)ip < 0;
+#endif
+}
+
+static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ unsigned long from = cpuc->lbr_entries[0].from;
+ unsigned long old_to, to = cpuc->lbr_entries[0].to;
+ unsigned long ip = regs->ip;
+
+ /*
+ * We don't need to fixup if the PEBS assist is fault like
+ */
+ if (!x86_pmu.intel_cap.pebs_trap)
+ return 1;
+
+ /*
+ * No LBR entry, no basic block, no rewinding
+ */
+ if (!cpuc->lbr_stack.nr || !from || !to)
+ return 0;
+
+ /*
+ * Basic blocks should never cross user/kernel boundaries
+ */
+ if (kernel_ip(ip) != kernel_ip(to))
+ return 0;
+
+ /*
+ * unsigned math, either ip is before the start (impossible) or
+ * the basic block is larger than 1 page (sanity)
+ */
+ if ((ip - to) > PAGE_SIZE)
+ return 0;
+
+ /*
+ * We sampled a branch insn, rewind using the LBR stack
+ */
+ if (ip == to) {
+ regs->ip = from;
+ return 1;
+ }
+
+ do {
+ struct insn insn;
+ u8 buf[MAX_INSN_SIZE];
+ void *kaddr;
+
+ old_to = to;
+ if (!kernel_ip(ip)) {
+ int bytes, size = MAX_INSN_SIZE;
+
+ bytes = copy_from_user_nmi(buf, (void __user *)to, size);
+ if (bytes != size)
+ return 0;
+
+ kaddr = buf;
+ } else
+ kaddr = (void *)to;
+
+ kernel_insn_init(&insn, kaddr);
+ insn_get_length(&insn);
+ to += insn.length;
+ } while (to < ip);
+
+ if (to == ip) {
+ regs->ip = old_to;
+ return 1;
+ }
+
+ /*
+ * Even though we decoded the basic block, the instruction stream
+ * never matched the given IP, either the TO or the IP got corrupted.
+ */
+ return 0;
+}
+
+static int intel_pmu_save_and_restart(struct perf_event *event);
+
+static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct debug_store *ds = cpuc->ds;
+ struct perf_event *event = cpuc->events[0]; /* PMC0 only */
+ struct pebs_record_core *at, *top;
+ struct perf_sample_data data;
+ struct perf_raw_record raw;
+ struct pt_regs regs;
+ int n;
+
+ if (!ds || !x86_pmu.pebs)
+ return;
+
+ at = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_record_core *)(unsigned long)ds->pebs_index;
+
+ /*
+ * Whatever else happens, drain the thing
+ */
+ ds->pebs_index = ds->pebs_buffer_base;
+
+ if (!test_bit(0, cpuc->active_mask))
+ return;
+
+ WARN_ON_ONCE(!event);
+
+ if (!event->attr.precise)
+ return;
+
+ n = top - at;
+ if (n <= 0)
+ return;
+
+ if (!intel_pmu_save_and_restart(event))
+ return;
+
+ /*
+ * Should not happen, we program the threshold at 1 and do not
+ * set a reset value.
+ */
+ WARN_ON_ONCE(n > 1);
+ at += n - 1;
+
+ perf_sample_data_init(&data, 0);
+ data.period = event->hw.last_period;
+
+ if (event->attr.sample_type & PERF_SAMPLE_RAW) {
+ raw.size = x86_pmu.pebs_record_size;
+ raw.data = at;
+ data.raw = &raw;
+ }
+
+ /*
+ * We use the interrupt regs as a base because the PEBS record
+ * does not contain a full regs set, specifically it seems to
+ * lack segment descriptors, which get used by things like
+ * user_mode().
+ *
+ * In the simple case fix up only the IP and BP,SP regs, for
+ * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
+ * A possible PERF_SAMPLE_REGS will have to transfer all regs.
+ */
+ regs = *iregs;
+ regs.ip = at->ip;
+ regs.bp = at->bp;
+ regs.sp = at->sp;
+
+ if (intel_pmu_pebs_fixup_ip(®s))
+ regs.flags |= PERF_EFLAGS_EXACT;
+ else
+ regs.flags &= ~PERF_EFLAGS_EXACT;
+
+ if (perf_event_overflow(event, 1, &data, ®s))
+ x86_pmu_stop(event);
+}
+
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct debug_store *ds = cpuc->ds;
+ struct pebs_record_nhm *at, *top;
+ struct perf_sample_data data;
+ struct perf_event *event = NULL;
+ struct perf_raw_record raw;
+ struct pt_regs regs;
+ u64 status = 0;
+ int bit, n;
+
+ if (!ds || !x86_pmu.pebs)
+ return;
+
+ at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
+
+ ds->pebs_index = ds->pebs_buffer_base;
+
+ n = top - at;
+ if (n <= 0)
+ return;
+
+ /*
+ * Should not happen, we program the threshold at 1 and do not
+ * set a reset value.
+ */
+ WARN_ON_ONCE(n > MAX_PEBS_EVENTS);
+
+ for ( ; at < top; at++) {
++ for_each_set_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) {
+ event = cpuc->events[bit];
+ if (!test_bit(bit, cpuc->active_mask))
+ continue;
+
+ WARN_ON_ONCE(!event);
+
+ if (!event->attr.precise)
+ continue;
+
+ if (__test_and_set_bit(bit, (unsigned long *)&status))
+ continue;
+
+ break;
+ }
+
+ if (!event || bit >= MAX_PEBS_EVENTS)
+ continue;
+
+ if (!intel_pmu_save_and_restart(event))
+ continue;
+
+ perf_sample_data_init(&data, 0);
+ data.period = event->hw.last_period;
+
+ if (event->attr.sample_type & PERF_SAMPLE_RAW) {
+ raw.size = x86_pmu.pebs_record_size;
+ raw.data = at;
+ data.raw = &raw;
+ }
+
+ /*
+ * See the comment in intel_pmu_drain_pebs_core()
+ */
+ regs = *iregs;
+ regs.ip = at->ip;
+ regs.bp = at->bp;
+ regs.sp = at->sp;
+
+ if (intel_pmu_pebs_fixup_ip(®s))
+ regs.flags |= PERF_EFLAGS_EXACT;
+ else
+ regs.flags &= ~PERF_EFLAGS_EXACT;
+
+ if (perf_event_overflow(event, 1, &data, ®s))
+ x86_pmu_stop(event);
+ }
+}
+
+/*
+ * BTS, PEBS probe and setup
+ */
+
+static void intel_ds_init(void)
+{
+ /*
+ * No support for 32bit formats
+ */
+ if (!boot_cpu_has(X86_FEATURE_DTES64))
+ return;
+
+ x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
+ x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+ if (x86_pmu.pebs) {
+ char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
+ int format = x86_pmu.intel_cap.pebs_format;
+
+ switch (format) {
+ case 0:
+ printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
+ x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
+ x86_pmu.pebs_constraints = intel_core_pebs_events;
+ break;
+
+ case 1:
+ printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
+ x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
+ x86_pmu.pebs_constraints = intel_nehalem_pebs_events;
+ break;
+
+ default:
+ printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
+ x86_pmu.pebs = 0;
+ break;
+ }
+ }
+}
+
+#else /* CONFIG_CPU_SUP_INTEL */
+
+static int reserve_ds_buffers(void)
+{
+ return 0;
+}
+
+static void release_ds_buffers(void)
+{
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */
/*
* Pentium III FXSR, SSE support
- *
- * BTS tracing
*/
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/errno.h>
+ #include <linux/slab.h>
#include <linux/ptrace.h>
#include <linux/regset.h>
#include <linux/tracehook.h>
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/signal.h>
-#include <linux/workqueue.h>
#include <linux/perf_event.h>
#include <linux/hw_breakpoint.h>
#include <asm/desc.h>
#include <asm/prctl.h>
#include <asm/proto.h>
-#include <asm/ds.h>
#include <asm/hw_breakpoint.h>
#include "tls.h"
0, IO_BITMAP_BYTES);
}
-#ifdef CONFIG_X86_PTRACE_BTS
-/*
- * A branch trace store context.
- *
- * Contexts may only be installed by ptrace_bts_config() and only for
- * ptraced tasks.
- *
- * Contexts are destroyed when the tracee is detached from the tracer.
- * The actual destruction work requires interrupts enabled, so the
- * work is deferred and will be scheduled during __ptrace_unlink().
- *
- * Contexts hold an additional task_struct reference on the traced
- * task, as well as a reference on the tracer's mm.
- *
- * Ptrace already holds a task_struct for the duration of ptrace operations,
- * but since destruction is deferred, it may be executed after both
- * tracer and tracee exited.
- */
-struct bts_context {
- /* The branch trace handle. */
- struct bts_tracer *tracer;
-
- /* The buffer used to store the branch trace and its size. */
- void *buffer;
- unsigned int size;
-
- /* The mm that paid for the above buffer. */
- struct mm_struct *mm;
-
- /* The task this context belongs to. */
- struct task_struct *task;
-
- /* The signal to send on a bts buffer overflow. */
- unsigned int bts_ovfl_signal;
-
- /* The work struct to destroy a context. */
- struct work_struct work;
-};
-
-static int alloc_bts_buffer(struct bts_context *context, unsigned int size)
-{
- void *buffer = NULL;
- int err = -ENOMEM;
-
- err = account_locked_memory(current->mm, current->signal->rlim, size);
- if (err < 0)
- return err;
-
- buffer = kzalloc(size, GFP_KERNEL);
- if (!buffer)
- goto out_refund;
-
- context->buffer = buffer;
- context->size = size;
- context->mm = get_task_mm(current);
-
- return 0;
-
- out_refund:
- refund_locked_memory(current->mm, size);
- return err;
-}
-
-static inline void free_bts_buffer(struct bts_context *context)
-{
- if (!context->buffer)
- return;
-
- kfree(context->buffer);
- context->buffer = NULL;
-
- refund_locked_memory(context->mm, context->size);
- context->size = 0;
-
- mmput(context->mm);
- context->mm = NULL;
-}
-
-static void free_bts_context_work(struct work_struct *w)
-{
- struct bts_context *context;
-
- context = container_of(w, struct bts_context, work);
-
- ds_release_bts(context->tracer);
- put_task_struct(context->task);
- free_bts_buffer(context);
- kfree(context);
-}
-
-static inline void free_bts_context(struct bts_context *context)
-{
- INIT_WORK(&context->work, free_bts_context_work);
- schedule_work(&context->work);
-}
-
-static inline struct bts_context *alloc_bts_context(struct task_struct *task)
-{
- struct bts_context *context = kzalloc(sizeof(*context), GFP_KERNEL);
- if (context) {
- context->task = task;
- task->bts = context;
-
- get_task_struct(task);
- }
-
- return context;
-}
-
-static int ptrace_bts_read_record(struct task_struct *child, size_t index,
- struct bts_struct __user *out)
-{
- struct bts_context *context;
- const struct bts_trace *trace;
- struct bts_struct bts;
- const unsigned char *at;
- int error;
-
- context = child->bts;
- if (!context)
- return -ESRCH;
-
- trace = ds_read_bts(context->tracer);
- if (!trace)
- return -ESRCH;
-
- at = trace->ds.top - ((index + 1) * trace->ds.size);
- if ((void *)at < trace->ds.begin)
- at += (trace->ds.n * trace->ds.size);
-
- if (!trace->read)
- return -EOPNOTSUPP;
-
- error = trace->read(context->tracer, at, &bts);
- if (error < 0)
- return error;
-
- if (copy_to_user(out, &bts, sizeof(bts)))
- return -EFAULT;
-
- return sizeof(bts);
-}
-
-static int ptrace_bts_drain(struct task_struct *child,
- long size,
- struct bts_struct __user *out)
-{
- struct bts_context *context;
- const struct bts_trace *trace;
- const unsigned char *at;
- int error, drained = 0;
-
- context = child->bts;
- if (!context)
- return -ESRCH;
-
- trace = ds_read_bts(context->tracer);
- if (!trace)
- return -ESRCH;
-
- if (!trace->read)
- return -EOPNOTSUPP;
-
- if (size < (trace->ds.top - trace->ds.begin))
- return -EIO;
-
- for (at = trace->ds.begin; (void *)at < trace->ds.top;
- out++, drained++, at += trace->ds.size) {
- struct bts_struct bts;
-
- error = trace->read(context->tracer, at, &bts);
- if (error < 0)
- return error;
-
- if (copy_to_user(out, &bts, sizeof(bts)))
- return -EFAULT;
- }
-
- memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
-
- error = ds_reset_bts(context->tracer);
- if (error < 0)
- return error;
-
- return drained;
-}
-
-static int ptrace_bts_config(struct task_struct *child,
- long cfg_size,
- const struct ptrace_bts_config __user *ucfg)
-{
- struct bts_context *context;
- struct ptrace_bts_config cfg;
- unsigned int flags = 0;
-
- if (cfg_size < sizeof(cfg))
- return -EIO;
-
- if (copy_from_user(&cfg, ucfg, sizeof(cfg)))
- return -EFAULT;
-
- context = child->bts;
- if (!context)
- context = alloc_bts_context(child);
- if (!context)
- return -ENOMEM;
-
- if (cfg.flags & PTRACE_BTS_O_SIGNAL) {
- if (!cfg.signal)
- return -EINVAL;
-
- return -EOPNOTSUPP;
- context->bts_ovfl_signal = cfg.signal;
- }
-
- ds_release_bts(context->tracer);
- context->tracer = NULL;
-
- if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) {
- int err;
-
- free_bts_buffer(context);
- if (!cfg.size)
- return 0;
-
- err = alloc_bts_buffer(context, cfg.size);
- if (err < 0)
- return err;
- }
-
- if (cfg.flags & PTRACE_BTS_O_TRACE)
- flags |= BTS_USER;
-
- if (cfg.flags & PTRACE_BTS_O_SCHED)
- flags |= BTS_TIMESTAMPS;
-
- context->tracer =
- ds_request_bts_task(child, context->buffer, context->size,
- NULL, (size_t)-1, flags);
- if (unlikely(IS_ERR(context->tracer))) {
- int error = PTR_ERR(context->tracer);
-
- free_bts_buffer(context);
- context->tracer = NULL;
- return error;
- }
-
- return sizeof(cfg);
-}
-
-static int ptrace_bts_status(struct task_struct *child,
- long cfg_size,
- struct ptrace_bts_config __user *ucfg)
-{
- struct bts_context *context;
- const struct bts_trace *trace;
- struct ptrace_bts_config cfg;
-
- context = child->bts;
- if (!context)
- return -ESRCH;
-
- if (cfg_size < sizeof(cfg))
- return -EIO;
-
- trace = ds_read_bts(context->tracer);
- if (!trace)
- return -ESRCH;
-
- memset(&cfg, 0, sizeof(cfg));
- cfg.size = trace->ds.end - trace->ds.begin;
- cfg.signal = context->bts_ovfl_signal;
- cfg.bts_size = sizeof(struct bts_struct);
-
- if (cfg.signal)
- cfg.flags |= PTRACE_BTS_O_SIGNAL;
-
- if (trace->ds.flags & BTS_USER)
- cfg.flags |= PTRACE_BTS_O_TRACE;
-
- if (trace->ds.flags & BTS_TIMESTAMPS)
- cfg.flags |= PTRACE_BTS_O_SCHED;
-
- if (copy_to_user(ucfg, &cfg, sizeof(cfg)))
- return -EFAULT;
-
- return sizeof(cfg);
-}
-
-static int ptrace_bts_clear(struct task_struct *child)
-{
- struct bts_context *context;
- const struct bts_trace *trace;
-
- context = child->bts;
- if (!context)
- return -ESRCH;
-
- trace = ds_read_bts(context->tracer);
- if (!trace)
- return -ESRCH;
-
- memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
-
- return ds_reset_bts(context->tracer);
-}
-
-static int ptrace_bts_size(struct task_struct *child)
-{
- struct bts_context *context;
- const struct bts_trace *trace;
-
- context = child->bts;
- if (!context)
- return -ESRCH;
-
- trace = ds_read_bts(context->tracer);
- if (!trace)
- return -ESRCH;
-
- return (trace->ds.top - trace->ds.begin) / trace->ds.size;
-}
-
-/*
- * Called from __ptrace_unlink() after the child has been moved back
- * to its original parent.
- */
-void ptrace_bts_untrace(struct task_struct *child)
-{
- if (unlikely(child->bts)) {
- free_bts_context(child->bts);
- child->bts = NULL;
- }
-}
-#endif /* CONFIG_X86_PTRACE_BTS */
-
/*
* Called by kernel/ptrace.c when detaching..
*
break;
#endif
- /*
- * These bits need more cooking - not enabled yet:
- */
-#ifdef CONFIG_X86_PTRACE_BTS
- case PTRACE_BTS_CONFIG:
- ret = ptrace_bts_config
- (child, data, (struct ptrace_bts_config __user *)addr);
- break;
-
- case PTRACE_BTS_STATUS:
- ret = ptrace_bts_status
- (child, data, (struct ptrace_bts_config __user *)addr);
- break;
-
- case PTRACE_BTS_SIZE:
- ret = ptrace_bts_size(child);
- break;
-
- case PTRACE_BTS_GET:
- ret = ptrace_bts_read_record
- (child, data, (struct bts_struct __user *) addr);
- break;
-
- case PTRACE_BTS_CLEAR:
- ret = ptrace_bts_clear(child);
- break;
-
- case PTRACE_BTS_DRAIN:
- ret = ptrace_bts_drain
- (child, data, (struct bts_struct __user *) addr);
- break;
-#endif /* CONFIG_X86_PTRACE_BTS */
-
default:
ret = ptrace_request(child, request, addr, data);
break;
case PTRACE_GET_THREAD_AREA:
case PTRACE_SET_THREAD_AREA:
-#ifdef CONFIG_X86_PTRACE_BTS
- case PTRACE_BTS_CONFIG:
- case PTRACE_BTS_STATUS:
- case PTRACE_BTS_SIZE:
- case PTRACE_BTS_GET:
- case PTRACE_BTS_CLEAR:
- case PTRACE_BTS_DRAIN:
-#endif /* CONFIG_X86_PTRACE_BTS */
return arch_ptrace(child, request, addr, data);
default:
struct file_ra_state;
struct user_struct;
struct writeback_control;
-struct rlimit;
#ifndef CONFIG_DISCONTIGMEM /* Don't use mapnrs, do it properly */
extern unsigned long max_mapnr;
int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *);
int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *);
int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *);
- int (*hugetlb_entry)(pte_t *, unsigned long, unsigned long,
- struct mm_walk *);
+ int (*hugetlb_entry)(pte_t *, unsigned long,
+ unsigned long, unsigned long, struct mm_walk *);
struct mm_struct *mm;
void *private;
};
int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
void vmemmap_populate_print_last(void);
-extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
- size_t size);
-extern void refund_locked_memory(struct mm_struct *mm, size_t size);
enum mf_flags {
MF_COUNT_INCREASED = 1 << 0,
p->prev_utime = cputime_zero;
p->prev_stime = cputime_zero;
#endif
+ #if defined(SPLIT_RSS_COUNTING)
+ memset(&p->rss_stat, 0, sizeof(p->rss_stat));
+ #endif
p->default_timer_slack_ns = current->timer_slack_ns;
p->memcg_batch.do_batch = 0;
p->memcg_batch.memcg = NULL;
#endif
-
- p->bts = NULL;
-
p->stack_start = stack_start;
/* Perform scheduler related setup. Assign this task to a CPU. */
#include <linux/smp.h>
#include <linux/file.h>
#include <linux/poll.h>
+ #include <linux/slab.h>
#include <linux/sysfs.h>
#include <linux/dcache.h>
#include <linux/percpu.h>
if (cpuctx->task_ctx == ctx)
return;
+ perf_disable();
+
/*
* We want to keep the following priority order:
* cpu pinned (that don't need to move), task pinned,
ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
cpuctx->task_ctx = ctx;
+
+ perf_enable();
}
#define MAX_INTERRUPTS (~0ULL)
}
static const struct file_operations perf_fops = {
+ .llseek = no_llseek,
.release = perf_release,
.read = perf_read,
.poll = perf_poll,
#include <linux/debugfs.h>
#include <linux/ctype.h>
#include <linux/ftrace.h>
+ #include <linux/slab.h>
#include <asm/tlb.h>
#include <asm/irq_regs.h>
return 1;
}
-/*
- * wait_task_context_switch - wait for a thread to complete at least one
- * context switch.
- *
- * @p must not be current.
- */
-void wait_task_context_switch(struct task_struct *p)
-{
- unsigned long nvcsw, nivcsw, flags;
- int running;
- struct rq *rq;
-
- nvcsw = p->nvcsw;
- nivcsw = p->nivcsw;
- for (;;) {
- /*
- * The runqueue is assigned before the actual context
- * switch. We need to take the runqueue lock.
- *
- * We could check initially without the lock but it is
- * very likely that we need to take the lock in every
- * iteration.
- */
- rq = task_rq_lock(p, &flags);
- running = task_running(rq, p);
- task_rq_unlock(rq, &flags);
-
- if (likely(!running))
- break;
- /*
- * The switch count is incremented before the actual
- * context switch. We thus wait for two switches to be
- * sure at least one completed.
- */
- if ((p->nvcsw - nvcsw) > 1)
- break;
- if ((p->nivcsw - nivcsw) > 1)
- break;
-
- cpu_relax();
- }
-}
-
/*
* wait_task_inactive - wait for a thread to unschedule.
*
get_task_struct(mt);
task_rq_unlock(rq, &flags);
- wake_up_process(rq->migration_thread);
+ wake_up_process(mt);
put_task_struct(mt);
wait_for_completion(&req.done);
tlb_migrate_finish(p->mm);
#include <linux/stringify.h>
#include <linux/kthread.h>
#include <linux/delay.h>
+ #include <linux/slab.h>
static inline int trace_valid_entry(struct trace_entry *entry)
{
case TRACE_BRANCH:
case TRACE_GRAPH_ENT:
case TRACE_GRAPH_RET:
- case TRACE_HW_BRANCHES:
case TRACE_KSYM:
return 1;
}
}
#endif /* CONFIG_BRANCH_TRACER */
-#ifdef CONFIG_HW_BRANCH_TRACER
-int
-trace_selftest_startup_hw_branches(struct tracer *trace,
- struct trace_array *tr)
-{
- struct trace_iterator *iter;
- struct tracer tracer;
- unsigned long count;
- int ret;
-
- if (!trace->open) {
- printk(KERN_CONT "missing open function...");
- return -1;
- }
-
- ret = tracer_init(trace, tr);
- if (ret) {
- warn_failed_init_tracer(trace, ret);
- return ret;
- }
-
- /*
- * The hw-branch tracer needs to collect the trace from the various
- * cpu trace buffers - before tracing is stopped.
- */
- iter = kzalloc(sizeof(*iter), GFP_KERNEL);
- if (!iter)
- return -ENOMEM;
-
- memcpy(&tracer, trace, sizeof(tracer));
-
- iter->trace = &tracer;
- iter->tr = tr;
- iter->pos = -1;
- mutex_init(&iter->mutex);
-
- trace->open(iter);
-
- mutex_destroy(&iter->mutex);
- kfree(iter);
-
- tracing_stop();
-
- ret = trace_test_buffer(tr, &count);
- trace->reset(tr);
- tracing_start();
-
- if (!ret && !count) {
- printk(KERN_CONT "no entries found..");
- ret = -1;
- }
-
- return ret;
-}
-#endif /* CONFIG_HW_BRANCH_TRACER */
-
#ifdef CONFIG_KSYM_TRACER
static int ksym_selftest_dummy;
projects / linux.git / commitdiff