/* pci bus to socket mapping */
static int pcibus_to_physid[256] = { [0 ... 255] = -1, };
+static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+
static DEFINE_RAW_SPINLOCK(uncore_box_lock);
/* mask of cpus that collect uncore events */
DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31");
+DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31");
+DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
{
};
static struct attribute *snbep_uncore_pcu_formats_attr[] = {
- &format_attr_event.attr,
+ &format_attr_event_ext.attr,
&format_attr_occ_sel.attr,
&format_attr_edge.attr,
&format_attr_inv.attr,
&format_attr_edge.attr,
&format_attr_inv.attr,
&format_attr_thresh8.attr,
+ &format_attr_match_rds.attr,
+ &format_attr_match_rnid30.attr,
+ &format_attr_match_rnid4.attr,
+ &format_attr_match_dnid.attr,
+ &format_attr_match_mc.attr,
+ &format_attr_match_opc.attr,
+ &format_attr_match_vnw.attr,
+ &format_attr_match0.attr,
+ &format_attr_match1.attr,
+ &format_attr_mask_rds.attr,
+ &format_attr_mask_rnid30.attr,
+ &format_attr_mask_rnid4.attr,
+ &format_attr_mask_dnid.attr,
+ &format_attr_mask_mc.attr,
+ &format_attr_mask_opc.attr,
+ &format_attr_mask_vnw.attr,
+ &format_attr_mask0.attr,
+ &format_attr_mask1.attr,
NULL,
};
static struct uncore_event_desc snbep_uncore_qpi_events[] = {
INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"),
INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
- INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"),
- INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"),
+ INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"),
+ INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"),
{ /* end: all zeroes */ },
};
SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
};
+#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \
+ .init_box = snbep_uncore_pci_init_box, \
+ .disable_box = snbep_uncore_pci_disable_box, \
+ .enable_box = snbep_uncore_pci_enable_box, \
+ .disable_event = snbep_uncore_pci_disable_event, \
+ .read_counter = snbep_uncore_pci_read_counter
+
static struct intel_uncore_ops snbep_uncore_pci_ops = {
- .init_box = snbep_uncore_pci_init_box,
- .disable_box = snbep_uncore_pci_disable_box,
- .enable_box = snbep_uncore_pci_enable_box,
- .disable_event = snbep_uncore_pci_disable_event,
- .enable_event = snbep_uncore_pci_enable_event,
- .read_counter = snbep_uncore_pci_read_counter,
+ SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+ .enable_event = snbep_uncore_pci_enable_event, \
};
static struct event_constraint snbep_uncore_cbox_constraints[] = {
NULL,
};
+enum {
+ SNBEP_PCI_QPI_PORT0_FILTER,
+ SNBEP_PCI_QPI_PORT1_FILTER,
+};
+
+static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) {
+ reg1->idx = 0;
+ reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0;
+ reg1->config = event->attr.config1;
+ reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0;
+ reg2->config = event->attr.config2;
+ }
+ return 0;
+}
+
+static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE) {
+ int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
+ struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx];
+ WARN_ON_ONCE(!filter_pdev);
+ if (filter_pdev) {
+ pci_write_config_dword(filter_pdev, reg1->reg,
+ (u32)reg1->config);
+ pci_write_config_dword(filter_pdev, reg1->reg + 4,
+ (u32)(reg1->config >> 32));
+ pci_write_config_dword(filter_pdev, reg2->reg,
+ (u32)reg2->config);
+ pci_write_config_dword(filter_pdev, reg2->reg + 4,
+ (u32)(reg2->config >> 32));
+ }
+ }
+
+ pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops snbep_uncore_qpi_ops = {
+ SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+ .enable_event = snbep_qpi_enable_event,
+ .hw_config = snbep_qpi_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
#define SNBEP_UNCORE_PCI_COMMON_INIT() \
.perf_ctr = SNBEP_PCI_PMON_CTR0, \
.event_ctl = SNBEP_PCI_PMON_CTL0, \
};
static struct intel_uncore_type snbep_uncore_qpi = {
- .name = "qpi",
- .num_counters = 4,
- .num_boxes = 2,
- .perf_ctr_bits = 48,
- .perf_ctr = SNBEP_PCI_PMON_CTR0,
- .event_ctl = SNBEP_PCI_PMON_CTL0,
- .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
- .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
- .ops = &snbep_uncore_pci_ops,
- .event_descs = snbep_uncore_qpi_events,
- .format_group = &snbep_uncore_qpi_format_group,
+ .name = "qpi",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCI_PMON_CTR0,
+ .event_ctl = SNBEP_PCI_PMON_CTL0,
+ .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &snbep_uncore_qpi_ops,
+ .event_descs = snbep_uncore_qpi_events,
+ .format_group = &snbep_uncore_qpi_format_group,
};
static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = {
{ /* Home Agent */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
- .driver_data = SNBEP_PCI_UNCORE_HA,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0),
},
{ /* MC Channel 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
- .driver_data = SNBEP_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0),
},
{ /* MC Channel 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
- .driver_data = SNBEP_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1),
},
{ /* MC Channel 2 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
- .driver_data = SNBEP_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2),
},
{ /* MC Channel 3 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
- .driver_data = SNBEP_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3),
},
{ /* QPI Port 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
- .driver_data = SNBEP_PCI_UNCORE_QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0),
},
{ /* QPI Port 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
- .driver_data = SNBEP_PCI_UNCORE_QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1),
},
{ /* R2PCIe */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
- .driver_data = SNBEP_PCI_UNCORE_R2PCIE,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0),
},
{ /* R3QPI Link 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
- .driver_data = SNBEP_PCI_UNCORE_R3QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0),
},
{ /* R3QPI Link 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
- .driver_data = SNBEP_PCI_UNCORE_R3QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT0_FILTER),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT1_FILTER),
},
{ /* end: all zeroes */ }
};
static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = {
{ /* Home Agent 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
- .driver_data = IVT_PCI_UNCORE_HA,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0),
},
{ /* Home Agent 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
- .driver_data = IVT_PCI_UNCORE_HA,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1),
},
{ /* MC0 Channel 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0),
},
{ /* MC0 Channel 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1),
},
{ /* MC0 Channel 3 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2),
},
{ /* MC0 Channel 4 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3),
},
{ /* MC1 Channel 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4),
},
{ /* MC1 Channel 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5),
},
{ /* MC1 Channel 3 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6),
},
{ /* MC1 Channel 4 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7),
},
{ /* QPI0 Port 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
- .driver_data = IVT_PCI_UNCORE_QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0),
},
{ /* QPI0 Port 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
- .driver_data = IVT_PCI_UNCORE_QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1),
},
{ /* QPI1 Port 2 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
- .driver_data = IVT_PCI_UNCORE_QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2),
},
{ /* R2PCIe */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
- .driver_data = IVT_PCI_UNCORE_R2PCIE,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0),
},
{ /* R3QPI0 Link 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
- .driver_data = IVT_PCI_UNCORE_R3QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0),
},
{ /* R3QPI0 Link 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
- .driver_data = IVT_PCI_UNCORE_R3QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1),
},
{ /* R3QPI1 Link 2 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
- .driver_data = IVT_PCI_UNCORE_R3QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2),
},
{ /* end: all zeroes */ }
};
/*
* add a pci uncore device
*/
-static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
+static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
- int i, phys_id;
+ struct intel_uncore_type *type;
+ int phys_id;
phys_id = pcibus_to_physid[pdev->bus->number];
if (phys_id < 0)
return -ENODEV;
+ if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
+ extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev;
+ pci_set_drvdata(pdev, NULL);
+ return 0;
+ }
+
+ type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
box = uncore_alloc_box(type, 0);
if (!box)
return -ENOMEM;
* for performance monitoring unit with multiple boxes,
* each box has a different function id.
*/
- for (i = 0; i < type->num_boxes; i++) {
- pmu = &type->pmus[i];
- if (pmu->func_id == pdev->devfn)
- break;
- if (pmu->func_id < 0) {
- pmu->func_id = pdev->devfn;
- break;
- }
- pmu = NULL;
- }
-
- if (!pmu) {
- kfree(box);
- return -EINVAL;
- }
+ pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
+ if (pmu->func_id < 0)
+ pmu->func_id = pdev->devfn;
+ else
+ WARN_ON_ONCE(pmu->func_id != pdev->devfn);
box->phys_id = phys_id;
box->pci_dev = pdev;
static void uncore_pci_remove(struct pci_dev *pdev)
{
struct intel_uncore_box *box = pci_get_drvdata(pdev);
- struct intel_uncore_pmu *pmu = box->pmu;
- int cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+ struct intel_uncore_pmu *pmu;
+ int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+ box = pci_get_drvdata(pdev);
+ if (!box) {
+ for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
+ if (extra_pci_dev[phys_id][i] == pdev) {
+ extra_pci_dev[phys_id][i] = NULL;
+ break;
+ }
+ }
+ WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX);
+ return;
+ }
+
+ pmu = box->pmu;
if (WARN_ON_ONCE(phys_id != box->phys_id))
return;
kfree(box);
}
-static int uncore_pci_probe(struct pci_dev *pdev,
- const struct pci_device_id *id)
-{
- return uncore_pci_add(pci_uncores[id->driver_data], pdev);
-}
-
static int __init uncore_pci_init(void)
{
int ret;
/**
* task_curr - is this task currently executing on a CPU?
* @p: the task in question.
+ *
+ * Return: 1 if the task is currently executing. 0 otherwise.
*/
inline int task_curr(const struct task_struct *p)
{
* the simpler "current->state = TASK_RUNNING" to mark yourself
* runnable without the overhead of this.
*
- * Returns %true if @p was woken up, %false if it was already running
+ * Return: %true if @p was woken up, %false if it was already running.
* or @state didn't match @p's state.
*/
static int
unsigned long flags;
int cpu, success = 0;
- smp_wmb();
+ /*
+ * If we are going to wake up a thread waiting for CONDITION we
+ * need to ensure that CONDITION=1 done by the caller can not be
+ * reordered with p->state check below. This pairs with mb() in
+ * set_current_state() the waiting thread does.
+ */
+ smp_mb__before_spinlock();
raw_spin_lock_irqsave(&p->pi_lock, flags);
if (!(p->state & state))
goto out;
* @p: The process to be woken up.
*
* Attempt to wake up the nominated process and move it to the set of runnable
- * processes. Returns 1 if the process was woken up, 0 if it was already
- * running.
+ * processes.
+ *
+ * Return: 1 if the process was woken up, 0 if it was already running.
*
* It may be assumed that this function implies a write memory barrier before
* changing the task state if and only if any tasks are woken up.
* This makes sure that uptime, CFS vruntime, load
* balancing, etc... continue to move forward, even
* with a very low granularity.
+ *
+ * Return: Maximum deferment in nanoseconds.
*/
u64 scheduler_tick_max_deferment(void)
{
if (sched_feat(HRTICK))
hrtick_clear(rq);
+ /*
+ * Make sure that signal_pending_state()->signal_pending() below
+ * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
+ * done by the caller to avoid the race with signal_wake_up().
+ */
+ smp_mb__before_spinlock();
raw_spin_lock_irq(&rq->lock);
switch_count = &prev->nivcsw;
* specified timeout to expire. The timeout is in jiffies. It is not
* interruptible.
*
- * The return value is 0 if timed out, and positive (at least 1, or number of
- * jiffies left till timeout) if completed.
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
*/
unsigned long __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
* specified timeout to expire. The timeout is in jiffies. It is not
* interruptible. The caller is accounted as waiting for IO.
*
- * The return value is 0 if timed out, and positive (at least 1, or number of
- * jiffies left till timeout) if completed.
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
*/
unsigned long __sched
wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
* This waits for completion of a specific task to be signaled. It is
* interruptible.
*
- * The return value is -ERESTARTSYS if interrupted, 0 if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
*/
int __sched wait_for_completion_interruptible(struct completion *x)
{
* This waits for either a completion of a specific task to be signaled or for a
* specified timeout to expire. It is interruptible. The timeout is in jiffies.
*
- * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
- * positive (at least 1, or number of jiffies left till timeout) if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
*/
long __sched
wait_for_completion_interruptible_timeout(struct completion *x,
* This waits to be signaled for completion of a specific task. It can be
* interrupted by a kill signal.
*
- * The return value is -ERESTARTSYS if interrupted, 0 if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
*/
int __sched wait_for_completion_killable(struct completion *x)
{
* signaled or for a specified timeout to expire. It can be
* interrupted by a kill signal. The timeout is in jiffies.
*
- * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
- * positive (at least 1, or number of jiffies left till timeout) if completed.
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
*/
long __sched
wait_for_completion_killable_timeout(struct completion *x,
* try_wait_for_completion - try to decrement a completion without blocking
* @x: completion structure
*
- * Returns: 0 if a decrement cannot be done without blocking
+ * Return: 0 if a decrement cannot be done without blocking
* 1 if a decrement succeeded.
*
* If a completion is being used as a counting completion,
* completion_done - Test to see if a completion has any waiters
* @x: completion structure
*
- * Returns: 0 if there are waiters (wait_for_completion() in progress)
+ * Return: 0 if there are waiters (wait_for_completion() in progress)
* 1 if there are no waiters.
*
*/
* task_prio - return the priority value of a given task.
* @p: the task in question.
*
- * This is the priority value as seen by users in /proc.
+ * Return: The priority value as seen by users in /proc.
* RT tasks are offset by -200. Normal tasks are centered
* around 0, value goes from -16 to +15.
*/
/**
* task_nice - return the nice value of a given task.
* @p: the task in question.
+ *
+ * Return: The nice value [ -20 ... 0 ... 19 ].
*/
int task_nice(const struct task_struct *p)
{
/**
* idle_cpu - is a given cpu idle currently?
* @cpu: the processor in question.
+ *
+ * Return: 1 if the CPU is currently idle. 0 otherwise.
*/
int idle_cpu(int cpu)
{
/**
* idle_task - return the idle task for a given cpu.
* @cpu: the processor in question.
+ *
+ * Return: The idle task for the cpu @cpu.
*/
struct task_struct *idle_task(int cpu)
{
/**
* find_process_by_pid - find a process with a matching PID value.
* @pid: the pid in question.
+ *
+ * The task of @pid, if found. %NULL otherwise.
*/
static struct task_struct *find_process_by_pid(pid_t pid)
{
* @policy: new policy.
* @param: structure containing the new RT priority.
*
+ * Return: 0 on success. An error code otherwise.
+ *
* NOTE that the task may be already dead.
*/
int sched_setscheduler(struct task_struct *p, int policy,
* current context has permission. For example, this is needed in
* stop_machine(): we create temporary high priority worker threads,
* but our caller might not have that capability.
+ *
+ * Return: 0 on success. An error code otherwise.
*/
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
const struct sched_param *param)
* @pid: the pid in question.
* @policy: new policy.
* @param: structure containing the new RT priority.
+ *
+ * Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
struct sched_param __user *, param)
* sys_sched_setparam - set/change the RT priority of a thread
* @pid: the pid in question.
* @param: structure containing the new RT priority.
+ *
+ * Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
{
/**
* sys_sched_getscheduler - get the policy (scheduling class) of a thread
* @pid: the pid in question.
+ *
+ * Return: On success, the policy of the thread. Otherwise, a negative error
+ * code.
*/
SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
{
* sys_sched_getparam - get the RT priority of a thread
* @pid: the pid in question.
* @param: structure containing the RT priority.
+ *
+ * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
+ * code.
*/
SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
{
* @pid: pid of the process
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
* @user_mask_ptr: user-space pointer to the new cpu mask
+ *
+ * Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
unsigned long __user *, user_mask_ptr)
* @pid: pid of the process
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
* @user_mask_ptr: user-space pointer to hold the current cpu mask
+ *
+ * Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
unsigned long __user *, user_mask_ptr)
*
* This function yields the current CPU to other tasks. If there are no
* other threads running on this CPU then this function will return.
+ *
+ * Return: 0.
*/
SYSCALL_DEFINE0(sched_yield)
{
* It's the caller's job to ensure that the target task struct
* can't go away on us before we can do any checks.
*
- * Returns:
+ * Return:
* true (>0) if we indeed boosted the target task.
* false (0) if we failed to boost the target.
* -ESRCH if there's no task to yield to.
* sys_sched_get_priority_max - return maximum RT priority.
* @policy: scheduling class.
*
- * this syscall returns the maximum rt_priority that can be used
- * by a given scheduling class.
+ * Return: On success, this syscall returns the maximum
+ * rt_priority that can be used by a given scheduling class.
+ * On failure, a negative error code is returned.
*/
SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
{
* sys_sched_get_priority_min - return minimum RT priority.
* @policy: scheduling class.
*
- * this syscall returns the minimum rt_priority that can be used
- * by a given scheduling class.
+ * Return: On success, this syscall returns the minimum
+ * rt_priority that can be used by a given scheduling class.
+ * On failure, a negative error code is returned.
*/
SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
{
*
* this syscall writes the default timeslice value of a given process
* into the user-space timespec buffer. A value of '0' means infinity.
+ *
+ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
+ * an error code.
*/
SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
struct timespec __user *, interval)
* two cpus are in the same cache domain, see cpus_share_cache().
*/
DEFINE_PER_CPU(struct sched_domain *, sd_llc);
+DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
static void update_top_cache_domain(int cpu)
{
struct sched_domain *sd;
int id = cpu;
+ int size = 1;
sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
- if (sd)
+ if (sd) {
id = cpumask_first(sched_domain_span(sd));
+ size = cpumask_weight(sched_domain_span(sd));
+ }
rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
+ per_cpu(sd_llc_size, cpu) = size;
per_cpu(sd_llc_id, cpu) = id;
}
* @cpu: the processor in question.
*
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ *
+ * Return: The current task for @cpu.
*/
struct task_struct *curr_task(int cpu)
{
*/
update_entity_load_avg(curr, 1);
update_cfs_rq_blocked_load(cfs_rq, 1);
+ update_cfs_shares(cfs_rq);
#ifdef CONFIG_SCHED_HRTICK
/*
return 0;
}
+static void record_wakee(struct task_struct *p)
+{
+ /*
+ * Rough decay (wiping) for cost saving, don't worry
+ * about the boundary, really active task won't care
+ * about the loss.
+ */
+ if (jiffies > current->wakee_flip_decay_ts + HZ) {
+ current->wakee_flips = 0;
+ current->wakee_flip_decay_ts = jiffies;
+ }
+
+ if (current->last_wakee != p) {
+ current->last_wakee = p;
+ current->wakee_flips++;
+ }
+}
static void task_waking_fair(struct task_struct *p)
{
#endif
se->vruntime -= min_vruntime;
+ record_wakee(p);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
#endif
+static int wake_wide(struct task_struct *p)
+{
+ int factor = this_cpu_read(sd_llc_size);
+
+ /*
+ * Yeah, it's the switching-frequency, could means many wakee or
+ * rapidly switch, use factor here will just help to automatically
+ * adjust the loose-degree, so bigger node will lead to more pull.
+ */
+ if (p->wakee_flips > factor) {
+ /*
+ * wakee is somewhat hot, it needs certain amount of cpu
+ * resource, so if waker is far more hot, prefer to leave
+ * it alone.
+ */
+ if (current->wakee_flips > (factor * p->wakee_flips))
+ return 1;
+ }
+
+ return 0;
+}
+
static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
{
s64 this_load, load;
unsigned long weight;
int balanced;
+ /*
+ * If we wake multiple tasks be careful to not bounce
+ * ourselves around too much.
+ */
+ if (wake_wide(p))
+ return 0;
+
idx = sd->wake_idx;
this_cpu = smp_processor_id();
prev_cpu = task_cpu(p);
}
/*
- * Compute the cpu's hierarchical load factor for each task group.
+ * Compute the hierarchical load factor for cfs_rq and all its ascendants.
* This needs to be done in a top-down fashion because the load of a child
* group is a fraction of its parents load.
*/
-static int tg_load_down(struct task_group *tg, void *data)
-{
- unsigned long load;
- long cpu = (long)data;
-
- if (!tg->parent) {
- load = cpu_rq(cpu)->avg.load_avg_contrib;
- } else {
- load = tg->parent->cfs_rq[cpu]->h_load;
- load = div64_ul(load * tg->se[cpu]->avg.load_avg_contrib,
- tg->parent->cfs_rq[cpu]->runnable_load_avg + 1);
- }
-
- tg->cfs_rq[cpu]->h_load = load;
-
- return 0;
-}
-
-static void update_h_load(long cpu)
+static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
{
- struct rq *rq = cpu_rq(cpu);
+ struct rq *rq = rq_of(cfs_rq);
+ struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)];
unsigned long now = jiffies;
+ unsigned long load;
- if (rq->h_load_throttle == now)
+ if (cfs_rq->last_h_load_update == now)
return;
- rq->h_load_throttle = now;
+ cfs_rq->h_load_next = NULL;
+ for_each_sched_entity(se) {
+ cfs_rq = cfs_rq_of(se);
+ cfs_rq->h_load_next = se;
+ if (cfs_rq->last_h_load_update == now)
+ break;
+ }
- rcu_read_lock();
- walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
- rcu_read_unlock();
+ if (!se) {
+ cfs_rq->h_load = rq->avg.load_avg_contrib;
+ cfs_rq->last_h_load_update = now;
+ }
+
+ while ((se = cfs_rq->h_load_next) != NULL) {
+ load = cfs_rq->h_load;
+ load = div64_ul(load * se->avg.load_avg_contrib,
+ cfs_rq->runnable_load_avg + 1);
+ cfs_rq = group_cfs_rq(se);
+ cfs_rq->h_load = load;
+ cfs_rq->last_h_load_update = now;
+ }
}
static unsigned long task_h_load(struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(p);
+ update_cfs_rq_h_load(cfs_rq);
return div64_ul(p->se.avg.load_avg_contrib * cfs_rq->h_load,
cfs_rq->runnable_load_avg + 1);
}
{
}
-static inline void update_h_load(long cpu)
-{
-}
-
static unsigned long task_h_load(struct task_struct *p)
{
return p->se.avg.load_avg_contrib;
* get_sd_load_idx - Obtain the load index for a given sched domain.
* @sd: The sched_domain whose load_idx is to be obtained.
* @idle: The Idle status of the CPU for whose sd load_icx is obtained.
+ *
+ * Return: The load index.
*/
static inline int get_sd_load_idx(struct sched_domain *sd,
enum cpu_idle_type idle)
*
* Determine if @sg is a busier group than the previously selected
* busiest group.
+ *
+ * Return: %true if @sg is a busier group than the previously selected
+ * busiest group. %false otherwise.
*/
static bool update_sd_pick_busiest(struct lb_env *env,
struct sd_lb_stats *sds,
* assuming lower CPU number will be equivalent to lower a SMT thread
* number.
*
- * Returns 1 when packing is required and a task should be moved to
+ * Return: 1 when packing is required and a task should be moved to
* this CPU. The amount of the imbalance is returned in *imbalance.
*
* @env: The load balancing environment.
* @balance: Pointer to a variable indicating if this_cpu
* is the appropriate cpu to perform load balancing at this_level.
*
- * Returns: - the busiest group if imbalance exists.
+ * Return: - The busiest group if imbalance exists.
* - If no imbalance and user has opted for power-savings balance,
* return the least loaded group whose CPUs can be
* put to idle by rebalancing its tasks onto our group.
env.src_rq = busiest;
env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running);
- update_h_load(env.src_cpu);
more_balance:
local_irq_save(flags);
double_rq_lock(env.dst_rq, busiest);