Home Home > GIT Browse > openSUSE-15.0
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorTakashi Iwai <tiwai@suse.de>2018-08-14 20:19:25 +0200
committerTakashi Iwai <tiwai@suse.de>2018-08-14 20:19:25 +0200
commit2db6c2161e6587f4f17b51ca07bf5eaeac6d1c84 (patch)
tree589840fe5ae8b4dfa09c5d1ceaddd1196a07b59a
parent9fb5ebbeeea648043995b71742e6617d2710d2ef (diff)
parent7efdc9e6ea1689800d8b6d136deb5d34c3640ea3 (diff)
Merge branch 'SLE15' into openSUSE-15.0openSUSE-15.0
-rw-r--r--drivers/edac/altera_edac.c2
-rw-r--r--drivers/edac/mv64x60_edac.c2
-rw-r--r--drivers/edac/octeon_edac-lmc.c1
-rw-r--r--drivers/edac/sb_edac.c1
-rw-r--r--drivers/media/platform/omap3isp/isp.c7
-rw-r--r--drivers/media/v4l2-core/videobuf2-core.c9
-rw-r--r--drivers/pci/pci-acpi.c2
-rw-r--r--drivers/usb/host/xhci.c40
-rw-r--r--drivers/usb/host/xhci.h4
-rw-r--r--include/linux/sched.h1
-rw-r--r--kernel/sched/core.c9
-rw-r--r--kernel/sched/debug.c4
-rw-r--r--kernel/sched/fair.c221
-rw-r--r--kernel/sched/sched.h3
14 files changed, 160 insertions, 146 deletions
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index 7717b094fabb..b659c4393e3c 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -1114,7 +1114,7 @@ static void *ocram_alloc_mem(size_t size, void **other)
static void ocram_free_mem(void *p, size_t size, void *other)
{
- gen_pool_free((struct gen_pool *)other, (u32)p, size);
+ gen_pool_free((struct gen_pool *)other, (unsigned long)p, size);
}
static const struct edac_device_prv_data ocramecc_data = {
diff --git a/drivers/edac/mv64x60_edac.c b/drivers/edac/mv64x60_edac.c
index 14b7e7b71eaa..308534de5179 100644
--- a/drivers/edac/mv64x60_edac.c
+++ b/drivers/edac/mv64x60_edac.c
@@ -758,7 +758,7 @@ static int mv64x60_mc_err_probe(struct platform_device *pdev)
/* Non-ECC RAM? */
printk(KERN_WARNING "%s: No ECC DIMMs discovered\n", __func__);
res = -ENODEV;
- goto err2;
+ goto err;
}
edac_dbg(3, "init mci\n");
diff --git a/drivers/edac/octeon_edac-lmc.c b/drivers/edac/octeon_edac-lmc.c
index 9c1ffe3e912b..aeb222ca3ed1 100644
--- a/drivers/edac/octeon_edac-lmc.c
+++ b/drivers/edac/octeon_edac-lmc.c
@@ -78,6 +78,7 @@ static void octeon_lmc_edac_poll_o2(struct mem_ctl_info *mci)
if (!pvt->inject)
int_reg.u64 = cvmx_read_csr(CVMX_LMCX_INT(mci->mc_idx));
else {
+ int_reg.u64 = 0;
if (pvt->error_type == 1)
int_reg.s.sec_err = 1;
if (pvt->error_type == 2)
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 0cde8927d1cb..2a81464d83ed 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -2485,6 +2485,7 @@ static int ibridge_mci_bind_devs(struct mem_ctl_info *mci,
case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA:
case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TA:
pvt->pci_ta = pdev;
+ break;
case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_RAS:
case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_RAS:
pvt->pci_ras = pdev;
diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index 09cd3f66eb4f..161b709026c0 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -1934,6 +1934,7 @@ error_csiphy:
static void isp_detach_iommu(struct isp_device *isp)
{
+ arm_iommu_detach_device(isp->dev);
arm_iommu_release_mapping(isp->mapping);
isp->mapping = NULL;
}
@@ -1950,8 +1951,7 @@ static int isp_attach_iommu(struct isp_device *isp)
mapping = arm_iommu_create_mapping(&platform_bus_type, SZ_1G, SZ_2G);
if (IS_ERR(mapping)) {
dev_err(isp->dev, "failed to create ARM IOMMU mapping\n");
- ret = PTR_ERR(mapping);
- goto error;
+ return PTR_ERR(mapping);
}
isp->mapping = mapping;
@@ -1966,7 +1966,8 @@ static int isp_attach_iommu(struct isp_device *isp)
return 0;
error:
- isp_detach_iommu(isp);
+ arm_iommu_release_mapping(isp->mapping);
+ isp->mapping = NULL;
return ret;
}
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 170be467ef96..974833f8b948 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -914,9 +914,12 @@ void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state)
dprintk(4, "done processing on buffer %d, state: %d\n",
vb->index, state);
- /* sync buffers */
- for (plane = 0; plane < vb->num_planes; ++plane)
- call_void_memop(vb, finish, vb->planes[plane].mem_priv);
+ if (state != VB2_BUF_STATE_QUEUED &&
+ state != VB2_BUF_STATE_REQUEUEING) {
+ /* sync buffers */
+ for (plane = 0; plane < vb->num_planes; ++plane)
+ call_void_memop(vb, finish, vb->planes[plane].mem_priv);
+ }
spin_lock_irqsave(&q->done_lock, flags);
if (state == VB2_BUF_STATE_QUEUED ||
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 61296f20c37a..27af30571022 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -663,7 +663,7 @@ void acpi_pci_add_bus(struct pci_bus *bus)
union acpi_object *obj;
struct pci_host_bridge *bridge;
- if (acpi_pci_disabled || !bus->bridge)
+ if (acpi_pci_disabled || !bus->bridge || !ACPI_HANDLE(bus->bridge))
return;
acpi_pci_slot_enumerate(bus);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 8a43dbf1784d..ae9073550ca0 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -856,6 +856,41 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
spin_unlock_irqrestore(&xhci->lock, flags);
}
+static bool xhci_pending_portevent(struct xhci_hcd *xhci)
+{
+ __le32 __iomem **port_array;
+ int port_index;
+ u32 status;
+ u32 portsc;
+
+ status = readl(&xhci->op_regs->status);
+ if (status & STS_EINT)
+ return true;
+ /*
+ * Checking STS_EINT is not enough as there is a lag between a change
+ * bit being set and the Port Status Change Event that it generated
+ * being written to the Event Ring. See note in xhci 1.1 section 4.19.2.
+ */
+
+ port_index = xhci->num_usb2_ports;
+ port_array = xhci->usb2_ports;
+ while (port_index--) {
+ portsc = readl(port_array[port_index]);
+ if (portsc & PORT_CHANGE_MASK ||
+ (portsc & PORT_PLS_MASK) == XDEV_RESUME)
+ return true;
+ }
+ port_index = xhci->num_usb3_ports;
+ port_array = xhci->usb3_ports;
+ while (port_index--) {
+ portsc = readl(port_array[port_index]);
+ if (portsc & PORT_CHANGE_MASK ||
+ (portsc & PORT_PLS_MASK) == XDEV_RESUME)
+ return true;
+ }
+ return false;
+}
+
/*
* Stop HC (not bus-specific)
*
@@ -955,7 +990,7 @@ EXPORT_SYMBOL_GPL(xhci_suspend);
*/
int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
{
- u32 command, temp = 0, status;
+ u32 command, temp = 0;
struct usb_hcd *hcd = xhci_to_hcd(xhci);
struct usb_hcd *secondary_hcd;
int retval = 0;
@@ -1077,8 +1112,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
done:
if (retval == 0) {
/* Resume root hubs only when have pending events. */
- status = readl(&xhci->op_regs->status);
- if (status & STS_EINT) {
+ if (xhci_pending_portevent(xhci)) {
usb_hcd_resume_root_hub(xhci->shared_hcd);
usb_hcd_resume_root_hub(hcd);
}
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 27cf7d80decb..df250ffca7f8 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -392,6 +392,10 @@ struct xhci_op_regs {
#define PORT_PLC (1 << 22)
/* port configure error change - port failed to configure its link partner */
#define PORT_CEC (1 << 23)
+#define PORT_CHANGE_MASK (PORT_CSC | PORT_PEC | PORT_WRC | PORT_OCC | \
+ PORT_RC | PORT_PLC | PORT_CEC)
+
+
/* Cold Attach Status - xHC can set this bit to report device attached during
* Sx state. Warm port reset should be perfomed to clear this bit and move port
* to connected state.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ab635a760932..1a80ec3854eb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -922,6 +922,7 @@ struct task_struct {
u64 last_sum_exec_runtime;
struct callback_head numa_work;
+ /* UNUSED field preserved due to KABI */
struct list_head numa_entry;
struct numa_group *numa_group;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2961e0780fde..00db918ee688 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1227,6 +1227,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
__set_task_cpu(p, new_cpu);
}
+#ifdef CONFIG_NUMA_BALANCING
static void __migrate_swap_task(struct task_struct *p, int cpu)
{
if (task_on_rq_queued(p)) {
@@ -1308,16 +1309,17 @@ unlock:
/*
* Cross migrate two tasks
*/
-int migrate_swap(struct task_struct *cur, struct task_struct *p)
+int migrate_swap(struct task_struct *cur, struct task_struct *p,
+ int target_cpu, int curr_cpu)
{
struct migration_swap_arg arg;
int ret = -EINVAL;
arg = (struct migration_swap_arg){
.src_task = cur,
- .src_cpu = task_cpu(cur),
+ .src_cpu = curr_cpu,
.dst_task = p,
- .dst_cpu = task_cpu(p),
+ .dst_cpu = target_cpu,
};
if (arg.src_cpu == arg.dst_cpu)
@@ -1342,6 +1344,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
out:
return ret;
}
+#endif /* CONFIG_NUMA_BALANCING */
/*
* wait_task_inactive - wait for a thread to unschedule.
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index ebe2d0c87c2f..46f1e44191c4 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -833,8 +833,8 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
unsigned long tpf, unsigned long gsf, unsigned long gpf)
{
SEQ_printf(m, "numa_faults node=%d ", node);
- SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
- SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+ SEQ_printf(m, "task_private=%lu task_shared=%lu ", tpf, tsf);
+ SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gpf, gsf);
}
#endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1b51f69ffb2f..d1eb02bf9106 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1340,7 +1340,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
* of each group. Skip other nodes.
*/
if (sched_numa_topology_type == NUMA_BACKPLANE &&
- dist > maxdist)
+ dist >= maxdist)
continue;
/* Add up the faults from nearby nodes. */
@@ -1478,14 +1478,12 @@ static unsigned long capacity_of(int cpu);
/* Cached statistics for all CPUs within a node */
struct numa_stats {
- unsigned long nr_running;
unsigned long load;
/* Total compute capacity of CPUs on a node */
unsigned long compute_capacity;
- /* Approximate capacity in terms of runnable tasks on a node */
- unsigned long task_capacity;
+ unsigned int nr_running;
int has_free_capacity;
};
@@ -1523,9 +1521,9 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
capacity = cpus / smt; /* cores */
- ns->task_capacity = min_t(unsigned, capacity,
+ capacity = min_t(unsigned, capacity,
DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
- ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
+ ns->has_free_capacity = (ns->nr_running < capacity);
}
struct task_numa_env {
@@ -1574,28 +1572,12 @@ static bool load_too_imbalanced(long src_load, long dst_load,
src_capacity = env->src_stats.compute_capacity;
dst_capacity = env->dst_stats.compute_capacity;
- /* We care about the slope of the imbalance, not the direction. */
- if (dst_load < src_load)
- swap(dst_load, src_load);
+ imb = abs(dst_load * src_capacity - src_load * dst_capacity);
- /* Is the difference below the threshold? */
- imb = dst_load * src_capacity * 100 -
- src_load * dst_capacity * env->imbalance_pct;
- if (imb <= 0)
- return false;
-
- /*
- * The imbalance is above the allowed threshold.
- * Compare it with the old imbalance.
- */
orig_src_load = env->src_stats.load;
orig_dst_load = env->dst_stats.load;
- if (orig_dst_load < orig_src_load)
- swap(orig_dst_load, orig_src_load);
-
- old_imb = orig_dst_load * src_capacity * 100 -
- orig_src_load * dst_capacity * env->imbalance_pct;
+ old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity);
/* Would this change make things worse? */
return (imb > old_imb);
@@ -1608,9 +1590,8 @@ static bool load_too_imbalanced(long src_load, long dst_load,
* be exchanged with the source task
*/
static void task_numa_compare(struct task_numa_env *env,
- long taskimp, long groupimp)
+ long taskimp, long groupimp, bool maymove)
{
- struct rq *src_rq = cpu_rq(env->src_cpu);
struct rq *dst_rq = cpu_rq(env->dst_cpu);
struct task_struct *cur;
long src_load, dst_load;
@@ -1631,97 +1612,73 @@ static void task_numa_compare(struct task_numa_env *env,
if (cur == env->p)
goto unlock;
+ if (!cur) {
+ if (maymove || imp > env->best_imp)
+ goto assign;
+ else
+ goto unlock;
+ }
+
/*
* "imp" is the fault differential for the source task between the
* source and destination node. Calculate the total differential for
* the source task and potential destination task. The more negative
- * the value is, the more rmeote accesses that would be expected to
+ * the value is, the more remote accesses that would be expected to
* be incurred if the tasks were swapped.
*/
- if (cur) {
- /* Skip this swap candidate if cannot move to the source cpu */
- if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
- goto unlock;
+ /* Skip this swap candidate if cannot move to the source cpu */
+ if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
+ goto unlock;
+ /*
+ * If dst and source tasks are in the same NUMA group, or not
+ * in any group then look only at task weights.
+ */
+ if (cur->numa_group == env->p->numa_group) {
+ imp = taskimp + task_weight(cur, env->src_nid, dist) -
+ task_weight(cur, env->dst_nid, dist);
/*
- * If dst and source tasks are in the same NUMA group, or not
- * in any group then look only at task weights.
+ * Add some hysteresis to prevent swapping the
+ * tasks within a group over tiny differences.
*/
- if (cur->numa_group == env->p->numa_group) {
- imp = taskimp + task_weight(cur, env->src_nid, dist) -
- task_weight(cur, env->dst_nid, dist);
- /*
- * Add some hysteresis to prevent swapping the
- * tasks within a group over tiny differences.
- */
- if (cur->numa_group)
- imp -= imp/16;
- } else {
- /*
- * Compare the group weights. If a task is all by
- * itself (not part of a group), use the task weight
- * instead.
- */
- if (cur->numa_group)
- imp += group_weight(cur, env->src_nid, dist) -
- group_weight(cur, env->dst_nid, dist);
- else
- imp += task_weight(cur, env->src_nid, dist) -
- task_weight(cur, env->dst_nid, dist);
- }
+ if (cur->numa_group)
+ imp -= imp / 16;
+ } else {
+ /*
+ * Compare the group weights. If a task is all by itself
+ * (not part of a group), use the task weight instead.
+ */
+ if (cur->numa_group && env->p->numa_group)
+ imp += group_weight(cur, env->src_nid, dist) -
+ group_weight(cur, env->dst_nid, dist);
+ else
+ imp += task_weight(cur, env->src_nid, dist) -
+ task_weight(cur, env->dst_nid, dist);
}
- if (imp <= env->best_imp && moveimp <= env->best_imp)
+ if (imp <= env->best_imp)
goto unlock;
- if (!cur) {
- /* Is there capacity at our destination? */
- if (env->src_stats.nr_running <= env->src_stats.task_capacity &&
- !env->dst_stats.has_free_capacity)
- goto unlock;
-
- goto balance;
- }
-
- /* Balance doesn't matter much if we're running a task per cpu */
- if (imp > env->best_imp && src_rq->nr_running == 1 &&
- dst_rq->nr_running == 1)
+ if (maymove && moveimp > imp && moveimp > env->best_imp) {
+ imp = moveimp - 1;
+ cur = NULL;
goto assign;
+ }
/*
* In the overloaded case, try and keep the load balanced.
*/
-balance:
- load = task_h_load(env->p);
+ load = task_h_load(env->p) - task_h_load(cur);
+ if (!load)
+ goto assign;
+
dst_load = env->dst_stats.load + load;
src_load = env->src_stats.load - load;
- if (moveimp > imp && moveimp > env->best_imp) {
- /*
- * If the improvement from just moving env->p direction is
- * better than swapping tasks around, check if a move is
- * possible. Store a slightly smaller score than moveimp,
- * so an actually idle CPU will win.
- */
- if (!load_too_imbalanced(src_load, dst_load, env)) {
- imp = moveimp - 1;
- cur = NULL;
- goto assign;
- }
- }
-
- if (imp <= env->best_imp)
- goto unlock;
-
- if (cur) {
- load = task_h_load(cur);
- dst_load -= load;
- src_load += load;
- }
-
if (load_too_imbalanced(src_load, dst_load, env))
goto unlock;
+assign:
/*
* One idle CPU per node is evaluated for a task numa move.
* Call select_idle_sibling to maybe find a better one.
@@ -1737,7 +1694,6 @@ balance:
local_irq_enable();
}
-assign:
task_numa_assign(env, cur, imp);
unlock:
rcu_read_unlock();
@@ -1746,15 +1702,27 @@ unlock:
static void task_numa_find_cpu(struct task_numa_env *env,
long taskimp, long groupimp)
{
+ long src_load, dst_load, load;
+ bool maymove = false;
int cpu;
+ load = task_h_load(env->p);
+ dst_load = env->dst_stats.load + load;
+ src_load = env->src_stats.load - load;
+
+ /*
+ * If the improvement from just moving env->p direction is better
+ * than swapping tasks around, check if a move is possible.
+ */
+ maymove = !load_too_imbalanced(src_load, dst_load, env);
+
for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
/* Skip this CPU if the source task cannot migrate */
if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
continue;
env->dst_cpu = cpu;
- task_numa_compare(env, taskimp, groupimp);
+ task_numa_compare(env, taskimp, groupimp, maymove);
}
}
@@ -1823,7 +1791,7 @@ static int task_numa_migrate(struct task_struct *p)
* elsewhere, so there is no point in (re)trying.
*/
if (unlikely(!sd)) {
- p->numa_preferred_nid = task_node(p);
+ sched_setnuma(p, task_node(p));
return -EINVAL;
}
@@ -1882,15 +1850,13 @@ static int task_numa_migrate(struct task_struct *p)
* trying for a better one later. Do not set the preferred node here.
*/
if (p->numa_group) {
- struct numa_group *ng = p->numa_group;
-
if (env.best_cpu == -1)
nid = env.src_nid;
else
- nid = env.dst_nid;
+ nid = cpu_to_node(env.best_cpu);
- if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
- sched_setnuma(p, env.dst_nid);
+ if (nid != p->numa_preferred_nid)
+ sched_setnuma(p, nid);
}
/* No better CPU than the current one was found. */
@@ -1910,7 +1876,8 @@ static int task_numa_migrate(struct task_struct *p)
return ret;
}
- ret = migrate_swap(p, env.best_task);
+ ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
+
if (ret != 0)
trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
put_task_struct(env.best_task);
@@ -2170,8 +2137,8 @@ static int preferred_group_nid(struct task_struct *p, int nid)
static void task_numa_placement(struct task_struct *p)
{
- int seq, nid, max_nid = -1, max_group_nid = -1;
- unsigned long max_faults = 0, max_group_faults = 0;
+ int seq, nid, max_nid = -1;
+ unsigned long max_faults = 0;
unsigned long fault_types[2] = { 0, 0 };
unsigned long total_faults;
u64 runtime, period;
@@ -2250,33 +2217,30 @@ static void task_numa_placement(struct task_struct *p)
}
}
- if (faults > max_faults) {
- max_faults = faults;
+ if (!p->numa_group) {
+ if (faults > max_faults) {
+ max_faults = faults;
+ max_nid = nid;
+ }
+ } else if (group_faults > max_faults) {
+ max_faults = group_faults;
max_nid = nid;
}
-
- if (group_faults > max_group_faults) {
- max_group_faults = group_faults;
- max_group_nid = nid;
- }
}
- update_task_scan_period(p, fault_types[0], fault_types[1]);
-
if (p->numa_group) {
numa_group_count_active_nodes(p->numa_group);
spin_unlock_irq(group_lock);
- max_nid = preferred_group_nid(p, max_group_nid);
+ max_nid = preferred_group_nid(p, max_nid);
}
if (max_faults) {
/* Set the new preferred node */
if (max_nid != p->numa_preferred_nid)
sched_setnuma(p, max_nid);
-
- if (task_node(p) != p->numa_preferred_nid)
- numa_migrate_preferred(p);
}
+
+ update_task_scan_period(p, fault_types[0], fault_types[1]);
}
static inline int get_numa_group(struct numa_group *grp)
@@ -2476,14 +2440,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
numa_is_active_node(mem_node, ng))
local = 1;
- task_numa_placement(p);
-
/*
* Retry task to preferred node migration periodically, in case it
* case it previously failed, or the scheduler moved us.
*/
- if (time_after(jiffies, p->numa_migrate_retry))
+ if (time_after(jiffies, p->numa_migrate_retry)) {
+ task_numa_placement(p);
numa_migrate_preferred(p);
+ }
if (migrated)
p->numa_pages_migrated += pages;
@@ -7101,8 +7065,8 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
{
struct numa_group *numa_group = rcu_dereference(p->numa_group);
- unsigned long src_faults, dst_faults;
- int src_nid, dst_nid;
+ unsigned long src_weight, dst_weight;
+ int src_nid, dst_nid, dist;
if (!static_branch_likely(&sched_numa_balancing))
return -1;
@@ -7129,18 +7093,19 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
return 0;
/* Leaving a core idle is often worse than degrading locality. */
- if (env->idle != CPU_NOT_IDLE)
+ if (env->idle == CPU_IDLE)
return -1;
+ dist = node_distance(src_nid, dst_nid);
if (numa_group) {
- src_faults = group_faults(p, src_nid);
- dst_faults = group_faults(p, dst_nid);
+ src_weight = group_weight(p, src_nid, dist);
+ dst_weight = group_weight(p, dst_nid, dist);
} else {
- src_faults = task_faults(p, src_nid);
- dst_faults = task_faults(p, dst_nid);
+ src_weight = task_weight(p, src_nid, dist);
+ dst_weight = task_weight(p, dst_nid, dist);
}
- return dst_faults < src_faults;
+ return dst_weight < src_weight;
}
#else
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ad8fb71dfcb6..3bcb21b6d77f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -947,7 +947,8 @@ enum numa_faults_stats {
};
extern void sched_setnuma(struct task_struct *p, int node);
extern int migrate_task_to(struct task_struct *p, int cpu);
-extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern int migrate_swap(struct task_struct *p, struct task_struct *t,
+ int cpu, int scpu);
extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
#else
static inline void