#include <asm/atomic.h>
#include <asm/semaphore.h>
-#define CPUSET_SUPER_MAGIC 0x27e0eb
+#define CPUSET_SUPER_MAGIC 0x27e0eb
+
+/* See "Frequency meter" comments, below. */
+
+struct fmeter {
+ int cnt; /* unprocessed events count */
+ int val; /* most recent output value */
+ time_t time; /* clock (secs) when val computed */
+ spinlock_t lock; /* guards read or write of above */
+};
struct cpuset {
unsigned long flags; /* "unsigned long" so bitops work */
* Copy of global cpuset_mems_generation as of the most
* recent time this cpuset changed its mems_allowed.
*/
- int mems_generation;
+ int mems_generation;
+
+ struct fmeter fmeter; /* memory_pressure filter */
};
/* bits in struct cpuset flags field */
typedef enum {
CS_CPU_EXCLUSIVE,
CS_MEM_EXCLUSIVE,
+ CS_MEMORY_MIGRATE,
CS_REMOVED,
CS_NOTIFY_ON_RELEASE
} cpuset_flagbits_t;
return !!test_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
}
+static inline int is_memory_migrate(const struct cpuset *cs)
+{
+ return !!test_bit(CS_MEMORY_MIGRATE, &cs->flags);
+}
+
/*
* Increment this atomic integer everytime any cpuset changes its
* mems_allowed value. Users of cpusets can track this generation
.count = ATOMIC_INIT(0),
.sibling = LIST_HEAD_INIT(top_cpuset.sibling),
.children = LIST_HEAD_INIT(top_cpuset.children),
- .parent = NULL,
- .dentry = NULL,
- .mems_generation = 0,
};
static struct vfsmount *cpuset_mount;
-static struct super_block *cpuset_sb = NULL;
+static struct super_block *cpuset_sb;
/*
* We have two global cpuset semaphores below. They can nest.
BUG_ON(!nodes_intersects(*pmask, node_online_map));
}
-/*
- * Refresh current tasks mems_allowed and mems_generation from current
- * tasks cpuset.
+/**
+ * cpuset_update_task_memory_state - update task memory placement
+ *
+ * If the current tasks cpusets mems_allowed changed behind our
+ * backs, update current->mems_allowed, mems_generation and task NUMA
+ * mempolicy to the new value.
+ *
+ * Task mempolicy is updated by rebinding it relative to the
+ * current->cpuset if a task has its memory placement changed.
+ * Do not call this routine if in_interrupt().
*
- * Call without callback_sem or task_lock() held. May be called with
- * or without manage_sem held. Will acquire task_lock() and might
- * acquire callback_sem during call.
+ * Call without callback_sem or task_lock() held. May be called
+ * with or without manage_sem held. Except in early boot or
+ * an exiting task, when tsk->cpuset is NULL, this routine will
+ * acquire task_lock(). We don't need to use task_lock to guard
+ * against another task changing a non-NULL cpuset pointer to NULL,
+ * as that is only done by a task on itself, and if the current task
+ * is here, it is not simultaneously in the exit code NULL'ing its
+ * cpuset pointer. This routine also might acquire callback_sem and
+ * current->mm->mmap_sem during call.
*
* The task_lock() is required to dereference current->cpuset safely.
* Without it, we could pick up the pointer value of current->cpuset
* task has been modifying its cpuset.
*/
-static void refresh_mems(void)
+void cpuset_update_task_memory_state()
{
int my_cpusets_mem_gen;
+ struct task_struct *tsk = current;
+ struct cpuset *cs = tsk->cpuset;
- task_lock(current);
- my_cpusets_mem_gen = current->cpuset->mems_generation;
- task_unlock(current);
+ if (unlikely(!cs))
+ return;
- if (current->cpuset_mems_generation != my_cpusets_mem_gen) {
- struct cpuset *cs;
- nodemask_t oldmem = current->mems_allowed;
+ task_lock(tsk);
+ my_cpusets_mem_gen = cs->mems_generation;
+ task_unlock(tsk);
+
+ if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
+ nodemask_t oldmem = tsk->mems_allowed;
+ int migrate;
down(&callback_sem);
- task_lock(current);
- cs = current->cpuset;
- guarantee_online_mems(cs, ¤t->mems_allowed);
- current->cpuset_mems_generation = cs->mems_generation;
- task_unlock(current);
+ task_lock(tsk);
+ cs = tsk->cpuset; /* Maybe changed when task not locked */
+ migrate = is_memory_migrate(cs);
+ guarantee_online_mems(cs, &tsk->mems_allowed);
+ tsk->cpuset_mems_generation = cs->mems_generation;
+ task_unlock(tsk);
up(&callback_sem);
- if (!nodes_equal(oldmem, current->mems_allowed))
- numa_policy_rebind(&oldmem, ¤t->mems_allowed);
+ mpol_rebind_task(tsk, &tsk->mems_allowed);
+ if (!nodes_equal(oldmem, tsk->mems_allowed)) {
+ if (migrate) {
+ do_migrate_pages(tsk->mm, &oldmem,
+ &tsk->mems_allowed,
+ MPOL_MF_MOVE_ALL);
+ }
+ }
}
}
trialcs = *cs;
retval = nodelist_parse(buf, trialcs.mems_allowed);
if (retval < 0)
- return retval;
+ goto done;
nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, node_online_map);
- if (nodes_empty(trialcs.mems_allowed))
- return -ENOSPC;
- retval = validate_change(cs, &trialcs);
- if (retval == 0) {
- down(&callback_sem);
- cs->mems_allowed = trialcs.mems_allowed;
- atomic_inc(&cpuset_mems_generation);
- cs->mems_generation = atomic_read(&cpuset_mems_generation);
- up(&callback_sem);
+ if (nodes_empty(trialcs.mems_allowed)) {
+ retval = -ENOSPC;
+ goto done;
}
+ retval = validate_change(cs, &trialcs);
+ if (retval < 0)
+ goto done;
+
+ down(&callback_sem);
+ cs->mems_allowed = trialcs.mems_allowed;
+ atomic_inc(&cpuset_mems_generation);
+ cs->mems_generation = atomic_read(&cpuset_mems_generation);
+ up(&callback_sem);
+
+done:
return retval;
}
+/*
+ * Call with manage_sem held.
+ */
+
+static int update_memory_pressure_enabled(struct cpuset *cs, char *buf)
+{
+ if (simple_strtoul(buf, NULL, 10) != 0)
+ cpuset_memory_pressure_enabled = 1;
+ else
+ cpuset_memory_pressure_enabled = 0;
+ return 0;
+}
+
/*
* update_flag - read a 0 or a 1 in a file and update associated flag
* bit: the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
- * CS_NOTIFY_ON_RELEASE)
+ * CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE)
* cs: the cpuset to update
* buf: the buffer where we read the 0 or 1
*
return 0;
}
+/*
+ * Frequency meter - How fast is some event occuring?
+ *
+ * These routines manage a digitally filtered, constant time based,
+ * event frequency meter. There are four routines:
+ * fmeter_init() - initialize a frequency meter.
+ * fmeter_markevent() - called each time the event happens.
+ * fmeter_getrate() - returns the recent rate of such events.
+ * fmeter_update() - internal routine used to update fmeter.
+ *
+ * A common data structure is passed to each of these routines,
+ * which is used to keep track of the state required to manage the
+ * frequency meter and its digital filter.
+ *
+ * The filter works on the number of events marked per unit time.
+ * The filter is single-pole low-pass recursive (IIR). The time unit
+ * is 1 second. Arithmetic is done using 32-bit integers scaled to
+ * simulate 3 decimal digits of precision (multiplied by 1000).
+ *
+ * With an FM_COEF of 933, and a time base of 1 second, the filter
+ * has a half-life of 10 seconds, meaning that if the events quit
+ * happening, then the rate returned from the fmeter_getrate()
+ * will be cut in half each 10 seconds, until it converges to zero.
+ *
+ * It is not worth doing a real infinitely recursive filter. If more
+ * than FM_MAXTICKS ticks have elapsed since the last filter event,
+ * just compute FM_MAXTICKS ticks worth, by which point the level
+ * will be stable.
+ *
+ * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid
+ * arithmetic overflow in the fmeter_update() routine.
+ *
+ * Given the simple 32 bit integer arithmetic used, this meter works
+ * best for reporting rates between one per millisecond (msec) and
+ * one per 32 (approx) seconds. At constant rates faster than one
+ * per msec it maxes out at values just under 1,000,000. At constant
+ * rates between one per msec, and one per second it will stabilize
+ * to a value N*1000, where N is the rate of events per second.
+ * At constant rates between one per second and one per 32 seconds,
+ * it will be choppy, moving up on the seconds that have an event,
+ * and then decaying until the next event. At rates slower than
+ * about one in 32 seconds, it decays all the way back to zero between
+ * each event.
+ */
+
+#define FM_COEF 933 /* coefficient for half-life of 10 secs */
+#define FM_MAXTICKS ((time_t)99) /* useless computing more ticks than this */
+#define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */
+#define FM_SCALE 1000 /* faux fixed point scale */
+
+/* Initialize a frequency meter */
+static void fmeter_init(struct fmeter *fmp)
+{
+ fmp->cnt = 0;
+ fmp->val = 0;
+ fmp->time = 0;
+ spin_lock_init(&fmp->lock);
+}
+
+/* Internal meter update - process cnt events and update value */
+static void fmeter_update(struct fmeter *fmp)
+{
+ time_t now = get_seconds();
+ time_t ticks = now - fmp->time;
+
+ if (ticks == 0)
+ return;
+
+ ticks = min(FM_MAXTICKS, ticks);
+ while (ticks-- > 0)
+ fmp->val = (FM_COEF * fmp->val) / FM_SCALE;
+ fmp->time = now;
+
+ fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE;
+ fmp->cnt = 0;
+}
+
+/* Process any previous ticks, then bump cnt by one (times scale). */
+static void fmeter_markevent(struct fmeter *fmp)
+{
+ spin_lock(&fmp->lock);
+ fmeter_update(fmp);
+ fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE);
+ spin_unlock(&fmp->lock);
+}
+
+/* Process any previous ticks, then return current value. */
+static int fmeter_getrate(struct fmeter *fmp)
+{
+ int val;
+
+ spin_lock(&fmp->lock);
+ fmeter_update(fmp);
+ val = fmp->val;
+ spin_unlock(&fmp->lock);
+ return val;
+}
+
/*
* Attack task specified by pid in 'pidbuf' to cpuset 'cs', possibly
* writing the path of the old cpuset in 'ppathbuf' if it needs to be
struct task_struct *tsk;
struct cpuset *oldcs;
cpumask_t cpus;
+ nodemask_t from, to;
if (sscanf(pidbuf, "%d", &pid) != 1)
return -EIO;
guarantee_online_cpus(cs, &cpus);
set_cpus_allowed(tsk, cpus);
+ from = oldcs->mems_allowed;
+ to = cs->mems_allowed;
+
up(&callback_sem);
+ if (is_memory_migrate(cs))
+ do_migrate_pages(tsk->mm, &from, &to, MPOL_MF_MOVE_ALL);
put_task_struct(tsk);
if (atomic_dec_and_test(&oldcs->count))
check_for_release(oldcs, ppathbuf);
typedef enum {
FILE_ROOT,
FILE_DIR,
+ FILE_MEMORY_MIGRATE,
FILE_CPULIST,
FILE_MEMLIST,
FILE_CPU_EXCLUSIVE,
FILE_MEM_EXCLUSIVE,
FILE_NOTIFY_ON_RELEASE,
+ FILE_MEMORY_PRESSURE_ENABLED,
+ FILE_MEMORY_PRESSURE,
FILE_TASKLIST,
} cpuset_filetype_t;
case FILE_NOTIFY_ON_RELEASE:
retval = update_flag(CS_NOTIFY_ON_RELEASE, cs, buffer);
break;
+ case FILE_MEMORY_MIGRATE:
+ retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
+ break;
+ case FILE_MEMORY_PRESSURE_ENABLED:
+ retval = update_memory_pressure_enabled(cs, buffer);
+ break;
+ case FILE_MEMORY_PRESSURE:
+ retval = -EACCES;
+ break;
case FILE_TASKLIST:
retval = attach_task(cs, buffer, &pathbuf);
break;
case FILE_NOTIFY_ON_RELEASE:
*s++ = notify_on_release(cs) ? '1' : '0';
break;
+ case FILE_MEMORY_MIGRATE:
+ *s++ = is_memory_migrate(cs) ? '1' : '0';
+ break;
+ case FILE_MEMORY_PRESSURE_ENABLED:
+ *s++ = cpuset_memory_pressure_enabled ? '1' : '0';
+ break;
+ case FILE_MEMORY_PRESSURE:
+ s += sprintf(s, "%d", fmeter_getrate(&cs->fmeter));
+ break;
default:
retval = -EINVAL;
goto out;
/*
* cpuset_create_dir - create a directory for an object.
- * cs: the cpuset we create the directory for.
+ * cs: the cpuset we create the directory for.
* It must have a valid ->parent field
* And we are going to fill its ->dentry field.
* name: The name to give to the cpuset directory. Will be copied.
.private = FILE_NOTIFY_ON_RELEASE,
};
+static struct cftype cft_memory_migrate = {
+ .name = "memory_migrate",
+ .private = FILE_MEMORY_MIGRATE,
+};
+
+static struct cftype cft_memory_pressure_enabled = {
+ .name = "memory_pressure_enabled",
+ .private = FILE_MEMORY_PRESSURE_ENABLED,
+};
+
+static struct cftype cft_memory_pressure = {
+ .name = "memory_pressure",
+ .private = FILE_MEMORY_PRESSURE,
+};
+
static int cpuset_populate_dir(struct dentry *cs_dentry)
{
int err;
return err;
if ((err = cpuset_add_file(cs_dentry, &cft_notify_on_release)) < 0)
return err;
+ if ((err = cpuset_add_file(cs_dentry, &cft_memory_migrate)) < 0)
+ return err;
+ if ((err = cpuset_add_file(cs_dentry, &cft_memory_pressure)) < 0)
+ return err;
if ((err = cpuset_add_file(cs_dentry, &cft_tasks)) < 0)
return err;
return 0;
return -ENOMEM;
down(&manage_sem);
- refresh_mems();
+ cpuset_update_task_memory_state();
cs->flags = 0;
if (notify_on_release(parent))
set_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
INIT_LIST_HEAD(&cs->children);
atomic_inc(&cpuset_mems_generation);
cs->mems_generation = atomic_read(&cpuset_mems_generation);
+ fmeter_init(&cs->fmeter);
cs->parent = parent;
/* the vfs holds both inode->i_sem already */
down(&manage_sem);
- refresh_mems();
+ cpuset_update_task_memory_state();
if (atomic_read(&cs->count) > 0) {
up(&manage_sem);
return -EBUSY;
top_cpuset.cpus_allowed = CPU_MASK_ALL;
top_cpuset.mems_allowed = NODE_MASK_ALL;
+ fmeter_init(&top_cpuset.fmeter);
atomic_inc(&cpuset_mems_generation);
top_cpuset.mems_generation = atomic_read(&cpuset_mems_generation);
top_cpuset.dentry = root;
root->d_inode->i_op = &cpuset_dir_inode_operations;
err = cpuset_populate_dir(root);
+ /* memory_pressure_enabled is in root cpuset only */
+ if (err == 0)
+ err = cpuset_add_file(root, &cft_memory_pressure_enabled);
out:
return err;
}
*
* We don't need to task_lock() this reference to tsk->cpuset,
* because tsk is already marked PF_EXITING, so attach_task() won't
- * mess with it.
+ * mess with it, or task is a failed fork, never visible to attach_task.
**/
void cpuset_exit(struct task_struct *tsk)
{
struct cpuset *cs;
- BUG_ON(!(tsk->flags & PF_EXITING));
-
cs = tsk->cpuset;
tsk->cpuset = NULL;
* tasks cpuset.
**/
-cpumask_t cpuset_cpus_allowed(const struct task_struct *tsk)
+cpumask_t cpuset_cpus_allowed(struct task_struct *tsk)
{
cpumask_t mask;
down(&callback_sem);
- task_lock((struct task_struct *)tsk);
+ task_lock(tsk);
guarantee_online_cpus(tsk->cpuset, &mask);
- task_unlock((struct task_struct *)tsk);
+ task_unlock(tsk);
up(&callback_sem);
return mask;
}
/**
- * cpuset_update_current_mems_allowed - update mems parameters to new values
- *
- * If the current tasks cpusets mems_allowed changed behind our backs,
- * update current->mems_allowed and mems_generation to the new value.
- * Do not call this routine if in_interrupt().
+ * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset.
+ * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed.
*
- * Call without callback_sem or task_lock() held. May be called
- * with or without manage_sem held. Unless exiting, it will acquire
- * task_lock(). Also might acquire callback_sem during call to
- * refresh_mems().
- */
+ * Description: Returns the nodemask_t mems_allowed of the cpuset
+ * attached to the specified @tsk. Guaranteed to return some non-empty
+ * subset of node_online_map, even if this means going outside the
+ * tasks cpuset.
+ **/
-void cpuset_update_current_mems_allowed(void)
+nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
{
- struct cpuset *cs;
- int need_to_refresh = 0;
+ nodemask_t mask;
- task_lock(current);
- cs = current->cpuset;
- if (!cs)
- goto done;
- if (current->cpuset_mems_generation != cs->mems_generation)
- need_to_refresh = 1;
-done:
- task_unlock(current);
- if (need_to_refresh)
- refresh_mems();
-}
+ down(&callback_sem);
+ task_lock(tsk);
+ guarantee_online_mems(tsk->cpuset, &mask);
+ task_unlock(tsk);
+ up(&callback_sem);
-/**
- * cpuset_restrict_to_mems_allowed - limit nodes to current mems_allowed
- * @nodes: pointer to a node bitmap that is and-ed with mems_allowed
- */
-void cpuset_restrict_to_mems_allowed(unsigned long *nodes)
-{
- bitmap_and(nodes, nodes, nodes_addr(current->mems_allowed),
- MAX_NUMNODES);
+ return mask;
}
/**
return overlap;
}
+/*
+ * Collection of memory_pressure is suppressed unless
+ * this flag is enabled by writing "1" to the special
+ * cpuset file 'memory_pressure_enabled' in the root cpuset.
+ */
+
+int cpuset_memory_pressure_enabled __read_mostly;
+
+/**
+ * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
+ *
+ * Keep a running average of the rate of synchronous (direct)
+ * page reclaim efforts initiated by tasks in each cpuset.
+ *
+ * This represents the rate at which some task in the cpuset
+ * ran low on memory on all nodes it was allowed to use, and
+ * had to enter the kernels page reclaim code in an effort to
+ * create more free memory by tossing clean pages or swapping
+ * or writing dirty pages.
+ *
+ * Display to user space in the per-cpuset read-only file
+ * "memory_pressure". Value displayed is an integer
+ * representing the recent rate of entry into the synchronous
+ * (direct) page reclaim by any task attached to the cpuset.
+ **/
+
+void __cpuset_memory_pressure_bump(void)
+{
+ struct cpuset *cs;
+
+ task_lock(current);
+ cs = current->cpuset;
+ fmeter_markevent(&cs->fmeter);
+ task_unlock(current);
+}
+
/*
* proc_cpuset_show()
* - Print tasks cpuset path into seq_file.