// SPDX-License-Identifier: GPL-2.0-only /* * Linux VM pressure * * Copyright 2012 Linaro Ltd. * Anton Vorontsov <[email protected]> * * Based on ideas from Andrew Morton, David Rientjes, KOSAKI Motohiro, * Leonid Moiseichuk, Mel Gorman, Minchan Kim and Pekka Enberg. */ #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/slab.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 = …; /* * 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 = …; static const unsigned int vmpressure_level_critical = …; /* * 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 = …; static struct vmpressure *work_to_vmpressure(struct work_struct *work) { … } static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) { … } enum vmpressure_levels { … }; enum vmpressure_modes { … }; static const char * const vmpressure_str_levels[] = …; static const char * const vmpressure_str_modes[] = …; static enum vmpressure_levels vmpressure_level(unsigned long pressure) { … } static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, unsigned long reclaimed) { … } struct vmpressure_event { … }; static bool vmpressure_event(struct vmpressure *vmpr, const enum vmpressure_levels level, bool ancestor, bool signalled) { … } static void vmpressure_work_fn(struct work_struct *work) { … } /** * vmpressure() - Account memory pressure through scanned/reclaimed ratio * @gfp: reclaimer's gfp mask * @memcg: cgroup memory controller handle * @tree: legacy subtree mode * @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. * * If @tree is set, vmpressure is in traditional userspace reporting * mode: @memcg is considered the pressure root and userspace is * notified of the entire subtree's reclaim efficiency. * * If @tree is not set, reclaim efficiency is recorded for @memcg, and * only in-kernel users are notified. * * This function does not return any value. */ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed) { … } /** * 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) { … } #define MAX_VMPRESSURE_ARGS_LEN … /** * vmpressure_register_event() - Bind vmpressure notifications to an eventfd * @memcg: memcg that is interested in vmpressure notifications * @eventfd: eventfd context to link notifications with * @args: event arguments (pressure level threshold, optional mode) * * This function associates eventfd context with the vmpressure * infrastructure, so that the notifications will be delivered to the * @eventfd. The @args parameter is a comma-delimited string that denotes a * pressure level threshold (one of vmpressure_str_levels, i.e. "low", "medium", * or "critical") and an optional mode (one of vmpressure_str_modes, i.e. * "hierarchy" or "local"). * * To be used as memcg event method. * * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could * not be parsed. */ int vmpressure_register_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd, const char *args) { … } /** * vmpressure_unregister_event() - Unbind eventfd from vmpressure * @memcg: memcg 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). * * To be used as memcg event method. */ void vmpressure_unregister_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd) { … } /** * 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) { … } /** * 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) { … }
Codebase Browser
linux