linux/mm/vmpressure.c
Linus Torvalds 32dad03d16 Merge branch 'for-3.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup updates from Tejun Heo:
 "A lot of activities on the cgroup front.  Most changes aren't visible
  to userland at all at this point and are laying foundation for the
  planned unified hierarchy.

   - The biggest change is decoupling the lifetime management of css
     (cgroup_subsys_state) from that of cgroup's.  Because controllers
     (cpu, memory, block and so on) will need to be dynamically enabled
     and disabled, css which is the association point between a cgroup
     and a controller may come and go dynamically across the lifetime of
     a cgroup.  Till now, css's were created when the associated cgroup
     was created and stayed till the cgroup got destroyed.

     Assumptions around this tight coupling permeated through cgroup
     core and controllers.  These assumptions are gradually removed,
     which consists bulk of patches, and css destruction path is
     completely decoupled from cgroup destruction path.  Note that
     decoupling of creation path is relatively easy on top of these
     changes and the patchset is pending for the next window.

   - cgroup has its own event mechanism cgroup.event_control, which is
     only used by memcg.  It is overly complex trying to achieve high
     flexibility whose benefits seem dubious at best.  Going forward,
     new events will simply generate file modified event and the
     existing mechanism is being made specific to memcg.  This pull
     request contains prepatory patches for such change.

   - Various fixes and cleanups"

Fixed up conflict in kernel/cgroup.c as per Tejun.

* 'for-3.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (69 commits)
  cgroup: fix cgroup_css() invocation in css_from_id()
  cgroup: make cgroup_write_event_control() use css_from_dir() instead of __d_cgrp()
  cgroup: make cgroup_event hold onto cgroup_subsys_state instead of cgroup
  cgroup: implement CFTYPE_NO_PREFIX
  cgroup: make cgroup_css() take cgroup_subsys * instead and allow NULL subsys
  cgroup: rename cgroup_css_from_dir() to css_from_dir() and update its syntax
  cgroup: fix cgroup_write_event_control()
  cgroup: fix subsystem file accesses on the root cgroup
  cgroup: change cgroup_from_id() to css_from_id()
  cgroup: use css_get() in cgroup_create() to check CSS_ROOT
  cpuset: remove an unncessary forward declaration
  cgroup: RCU protect each cgroup_subsys_state release
  cgroup: move subsys file removal to kill_css()
  cgroup: factor out kill_css()
  cgroup: decouple cgroup_subsys_state destruction from cgroup destruction
  cgroup: replace cgroup->css_kill_cnt with ->nr_css
  cgroup: bounce cgroup_subsys_state ref kill confirmation to a work item
  cgroup: move cgroup->subsys[] assignment to online_css()
  cgroup: reorganize css init / exit paths
  cgroup: add __rcu modifier to cgroup->subsys[]
  ...
2013-09-03 18:25:03 -07:00

388 lines
12 KiB
C

/*
* Linux VM pressure
*
* Copyright 2012 Linaro Ltd.
* Anton Vorontsov <anton.vorontsov@linaro.org>
*
* Based on ideas from Andrew Morton, David Rientjes, KOSAKI Motohiro,
* Leonid Moiseichuk, Mel Gorman, Minchan Kim and Pekka Enberg.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
*/
#include <linux/cgroup.h>
#include <linux/fs.h>
#include <linux/log2.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/vmstat.h>
#include <linux/eventfd.h>
#include <linux/swap.h>
#include <linux/printk.h>
#include <linux/vmpressure.h>
/*
* The window size (vmpressure_win) is the number of scanned pages before
* we try to analyze scanned/reclaimed ratio. So the window is used as a
* rate-limit tunable for the "low" level notification, and also for
* averaging the ratio for medium/critical levels. Using small window
* sizes can cause lot of false positives, but too big window size will
* delay the notifications.
*
* As the vmscan reclaimer logic works with chunks which are multiple of
* SWAP_CLUSTER_MAX, it makes sense to use it for the window size as well.
*
* TODO: Make the window size depend on machine size, as we do for vmstat
* thresholds. Currently we set it to 512 pages (2MB for 4KB pages).
*/
static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 16;
/*
* These thresholds are used when we account memory pressure through
* scanned/reclaimed ratio. The current values were chosen empirically. In
* essence, they are percents: the higher the value, the more number
* unsuccessful reclaims there were.
*/
static const unsigned int vmpressure_level_med = 60;
static const unsigned int vmpressure_level_critical = 95;
/*
* When there are too little pages left to scan, vmpressure() may miss the
* critical pressure as number of pages will be less than "window size".
* However, in that case the vmscan priority will raise fast as the
* reclaimer will try to scan LRUs more deeply.
*
* The vmscan logic considers these special priorities:
*
* prio == DEF_PRIORITY (12): reclaimer starts with that value
* prio <= DEF_PRIORITY - 2 : kswapd becomes somewhat overwhelmed
* prio == 0 : close to OOM, kernel scans every page in an lru
*
* Any value in this range is acceptable for this tunable (i.e. from 12 to
* 0). Current value for the vmpressure_level_critical_prio is chosen
* empirically, but the number, in essence, means that we consider
* critical level when scanning depth is ~10% of the lru size (vmscan
* scans 'lru_size >> prio' pages, so it is actually 12.5%, or one
* eights).
*/
static const unsigned int vmpressure_level_critical_prio = ilog2(100 / 10);
static struct vmpressure *work_to_vmpressure(struct work_struct *work)
{
return container_of(work, struct vmpressure, work);
}
static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr)
{
struct cgroup_subsys_state *css = vmpressure_to_css(vmpr);
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
memcg = parent_mem_cgroup(memcg);
if (!memcg)
return NULL;
return memcg_to_vmpressure(memcg);
}
enum vmpressure_levels {
VMPRESSURE_LOW = 0,
VMPRESSURE_MEDIUM,
VMPRESSURE_CRITICAL,
VMPRESSURE_NUM_LEVELS,
};
static const char * const vmpressure_str_levels[] = {
[VMPRESSURE_LOW] = "low",
[VMPRESSURE_MEDIUM] = "medium",
[VMPRESSURE_CRITICAL] = "critical",
};
static enum vmpressure_levels vmpressure_level(unsigned long pressure)
{
if (pressure >= vmpressure_level_critical)
return VMPRESSURE_CRITICAL;
else if (pressure >= vmpressure_level_med)
return VMPRESSURE_MEDIUM;
return VMPRESSURE_LOW;
}
static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
unsigned long reclaimed)
{
unsigned long scale = scanned + reclaimed;
unsigned long pressure;
/*
* We calculate the ratio (in percents) of how many pages were
* scanned vs. reclaimed in a given time frame (window). Note that
* time is in VM reclaimer's "ticks", i.e. number of pages
* scanned. This makes it possible to set desired reaction time
* and serves as a ratelimit.
*/
pressure = scale - (reclaimed * scale / scanned);
pressure = pressure * 100 / scale;
pr_debug("%s: %3lu (s: %lu r: %lu)\n", __func__, pressure,
scanned, reclaimed);
return vmpressure_level(pressure);
}
struct vmpressure_event {
struct eventfd_ctx *efd;
enum vmpressure_levels level;
struct list_head node;
};
static bool vmpressure_event(struct vmpressure *vmpr,
unsigned long scanned, unsigned long reclaimed)
{
struct vmpressure_event *ev;
enum vmpressure_levels level;
bool signalled = false;
level = vmpressure_calc_level(scanned, reclaimed);
mutex_lock(&vmpr->events_lock);
list_for_each_entry(ev, &vmpr->events, node) {
if (level >= ev->level) {
eventfd_signal(ev->efd, 1);
signalled = true;
}
}
mutex_unlock(&vmpr->events_lock);
return signalled;
}
static void vmpressure_work_fn(struct work_struct *work)
{
struct vmpressure *vmpr = work_to_vmpressure(work);
unsigned long scanned;
unsigned long reclaimed;
/*
* Several contexts might be calling vmpressure(), so it is
* possible that the work was rescheduled again before the old
* work context cleared the counters. In that case we will run
* just after the old work returns, but then scanned might be zero
* here. No need for any locks here since we don't care if
* vmpr->reclaimed is in sync.
*/
if (!vmpr->scanned)
return;
spin_lock(&vmpr->sr_lock);
scanned = vmpr->scanned;
reclaimed = vmpr->reclaimed;
vmpr->scanned = 0;
vmpr->reclaimed = 0;
spin_unlock(&vmpr->sr_lock);
do {
if (vmpressure_event(vmpr, scanned, reclaimed))
break;
/*
* If not handled, propagate the event upward into the
* hierarchy.
*/
} while ((vmpr = vmpressure_parent(vmpr)));
}
/**
* vmpressure() - Account memory pressure through scanned/reclaimed ratio
* @gfp: reclaimer's gfp mask
* @memcg: cgroup memory controller handle
* @scanned: number of pages scanned
* @reclaimed: number of pages reclaimed
*
* This function should be called from the vmscan reclaim path to account
* "instantaneous" memory pressure (scanned/reclaimed ratio). The raw
* pressure index is then further refined and averaged over time.
*
* This function does not return any value.
*/
void vmpressure(gfp_t gfp, struct mem_cgroup *memcg,
unsigned long scanned, unsigned long reclaimed)
{
struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
/*
* Here we only want to account pressure that userland is able to
* help us with. For example, suppose that DMA zone is under
* pressure; if we notify userland about that kind of pressure,
* then it will be mostly a waste as it will trigger unnecessary
* freeing of memory by userland (since userland is more likely to
* have HIGHMEM/MOVABLE pages instead of the DMA fallback). That
* is why we include only movable, highmem and FS/IO pages.
* Indirect reclaim (kswapd) sets sc->gfp_mask to GFP_KERNEL, so
* we account it too.
*/
if (!(gfp & (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_IO | __GFP_FS)))
return;
/*
* If we got here with no pages scanned, then that is an indicator
* that reclaimer was unable to find any shrinkable LRUs at the
* current scanning depth. But it does not mean that we should
* report the critical pressure, yet. If the scanning priority
* (scanning depth) goes too high (deep), we will be notified
* through vmpressure_prio(). But so far, keep calm.
*/
if (!scanned)
return;
spin_lock(&vmpr->sr_lock);
vmpr->scanned += scanned;
vmpr->reclaimed += reclaimed;
scanned = vmpr->scanned;
spin_unlock(&vmpr->sr_lock);
if (scanned < vmpressure_win)
return;
schedule_work(&vmpr->work);
}
/**
* vmpressure_prio() - Account memory pressure through reclaimer priority level
* @gfp: reclaimer's gfp mask
* @memcg: cgroup memory controller handle
* @prio: reclaimer's priority
*
* This function should be called from the reclaim path every time when
* the vmscan's reclaiming priority (scanning depth) changes.
*
* This function does not return any value.
*/
void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
{
/*
* We only use prio for accounting critical level. For more info
* see comment for vmpressure_level_critical_prio variable above.
*/
if (prio > vmpressure_level_critical_prio)
return;
/*
* OK, the prio is below the threshold, updating vmpressure
* information before shrinker dives into long shrinking of long
* range vmscan. Passing scanned = vmpressure_win, reclaimed = 0
* to the vmpressure() basically means that we signal 'critical'
* level.
*/
vmpressure(gfp, memcg, vmpressure_win, 0);
}
/**
* vmpressure_register_event() - Bind vmpressure notifications to an eventfd
* @css: css that is interested in vmpressure notifications
* @cft: cgroup control files handle
* @eventfd: eventfd context to link notifications with
* @args: event arguments (used to set up a pressure level threshold)
*
* This function associates eventfd context with the vmpressure
* infrastructure, so that the notifications will be delivered to the
* @eventfd. The @args parameter is a string that denotes pressure level
* threshold (one of vmpressure_str_levels, i.e. "low", "medium", or
* "critical").
*
* This function should not be used directly, just pass it to (struct
* cftype).register_event, and then cgroup core will handle everything by
* itself.
*/
int vmpressure_register_event(struct cgroup_subsys_state *css,
struct cftype *cft, struct eventfd_ctx *eventfd,
const char *args)
{
struct vmpressure *vmpr = css_to_vmpressure(css);
struct vmpressure_event *ev;
int level;
for (level = 0; level < VMPRESSURE_NUM_LEVELS; level++) {
if (!strcmp(vmpressure_str_levels[level], args))
break;
}
if (level >= VMPRESSURE_NUM_LEVELS)
return -EINVAL;
ev = kzalloc(sizeof(*ev), GFP_KERNEL);
if (!ev)
return -ENOMEM;
ev->efd = eventfd;
ev->level = level;
mutex_lock(&vmpr->events_lock);
list_add(&ev->node, &vmpr->events);
mutex_unlock(&vmpr->events_lock);
return 0;
}
/**
* vmpressure_unregister_event() - Unbind eventfd from vmpressure
* @css: css handle
* @cft: cgroup control files handle
* @eventfd: eventfd context that was used to link vmpressure with the @cg
*
* This function does internal manipulations to detach the @eventfd from
* the vmpressure notifications, and then frees internal resources
* associated with the @eventfd (but the @eventfd itself is not freed).
*
* This function should not be used directly, just pass it to (struct
* cftype).unregister_event, and then cgroup core will handle everything
* by itself.
*/
void vmpressure_unregister_event(struct cgroup_subsys_state *css,
struct cftype *cft,
struct eventfd_ctx *eventfd)
{
struct vmpressure *vmpr = css_to_vmpressure(css);
struct vmpressure_event *ev;
mutex_lock(&vmpr->events_lock);
list_for_each_entry(ev, &vmpr->events, node) {
if (ev->efd != eventfd)
continue;
list_del(&ev->node);
kfree(ev);
break;
}
mutex_unlock(&vmpr->events_lock);
}
/**
* vmpressure_init() - Initialize vmpressure control structure
* @vmpr: Structure to be initialized
*
* This function should be called on every allocated vmpressure structure
* before any usage.
*/
void vmpressure_init(struct vmpressure *vmpr)
{
spin_lock_init(&vmpr->sr_lock);
mutex_init(&vmpr->events_lock);
INIT_LIST_HEAD(&vmpr->events);
INIT_WORK(&vmpr->work, vmpressure_work_fn);
}
/**
* vmpressure_cleanup() - shuts down vmpressure control structure
* @vmpr: Structure to be cleaned up
*
* This function should be called before the structure in which it is
* embedded is cleaned up.
*/
void vmpressure_cleanup(struct vmpressure *vmpr)
{
/*
* Make sure there is no pending work before eventfd infrastructure
* goes away.
*/
flush_work(&vmpr->work);
}