Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094/* SPDX-License-Identifier: GPL-2.0 *//* * DAMON api */
#ifndef _DAMON_H_#define _DAMON_H_
#include <linux/math64.h>#include <linux/memcontrol.h>#include <linux/mutex.h>#include <linux/prandom.h>#include <linux/time64.h>#include <linux/types.h>
/* Minimal region size. Every damon_region is aligned by this. */#define DAMON_MIN_REGION_SZ PAGE_SIZE/* Maximum number of monitoring probes. */#define DAMON_MAX_PROBES (4)/* Max priority score for DAMON-based operation schemes */#define DAMOS_MAX_SCORE (99)
/** * struct damon_addr_range - Represents an address region of [@start, @end). * @start: Start address of the region (inclusive). * @end: End address of the region (exclusive). */struct damon_addr_range { unsigned long start; unsigned long end;};
/** * struct damon_size_range - Represents size for filter to operate on [@min, @max]. * @min: Min size (inclusive). * @max: Max size (inclusive). */struct damon_size_range { unsigned long min; unsigned long max;};
/** * struct damon_region - Represents a monitoring target region. * @ar: The address range of the region. * @sampling_addr: Address of the sample for the next access check. * @nr_accesses: Access frequency of this region. * @nr_accesses_bp: @nr_accesses in basis point (0.01%) that updated for * each sampling interval. * @probe_hits: Number of probe-positive region samples. * @list: List head for siblings. * @age: Age of this region. * * For any use case, @ar should be non-zero positive size. * * @nr_accesses is reset to zero for every &damon_attrs->aggr_interval and be * increased for every &damon_attrs->sample_interval if an access to the region * during the last sampling interval is found. The update of this field should * not be done with direct access but with the helper function, * damon_update_region_access_rate(). * * @nr_accesses_bp is another representation of @nr_accesses in basis point * (1 in 10,000) that updated for every &damon_attrs->sample_interval in a * manner similar to moving sum. By the algorithm, this value becomes * @nr_accesses * 10000 for every &struct damon_attrs->aggr_interval. This can * be used when the aggregation interval is too huge and therefore cannot wait * for it before getting the access monitoring results. * * @age is initially zero, increased for each aggregation interval, and reset * to zero again if the access frequency is significantly changed. If two * regions are merged into a new region, both @nr_accesses and @age of the new * region are set as region size-weighted average of those of the two regions. */struct damon_region { struct damon_addr_range ar; unsigned long sampling_addr; unsigned int nr_accesses; unsigned int nr_accesses_bp; unsigned char probe_hits[DAMON_MAX_PROBES]; struct list_head list;
unsigned int age;/* private: Internal value for age calculation. */ unsigned int last_nr_accesses;};
/** * struct damon_target - Represents a monitoring target. * @pid: The PID of the virtual address space to monitor. * @nr_regions: Number of monitoring target regions of this target. * @regions_list: Head of the monitoring target regions of this target. * @list: List head for siblings. * @obsolete: Whether the commit destination target is obsolete. * * Each monitoring context could have multiple targets. For example, a context * for virtual memory address spaces could have multiple target processes. The * @pid should be set for appropriate &struct damon_operations including the * virtual address spaces monitoring operations. * * @obsolete is used only for damon_commit_targets() source targets, to specify * the matching destination targets are obsolete. Read damon_commit_targets() * to see how it is handled. */struct damon_target { struct pid *pid; unsigned int nr_regions; struct list_head regions_list; struct list_head list; bool obsolete;};
/** * enum damos_action - Represents an action of a Data Access Monitoring-based * Operation Scheme. * * @DAMOS_WILLNEED: Call ``madvise()`` for the region with MADV_WILLNEED. * @DAMOS_COLD: Call ``madvise()`` for the region with MADV_COLD. * @DAMOS_PAGEOUT: Reclaim the region. * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. * @DAMOS_COLLAPSE: Call ``madvise()`` for the region with MADV_COLLAPSE. * @DAMOS_LRU_PRIO: Prioritize the region on its LRU lists. * @DAMOS_LRU_DEPRIO: Deprioritize the region on its LRU lists. * @DAMOS_MIGRATE_HOT: Migrate the regions prioritizing warmer regions. * @DAMOS_MIGRATE_COLD: Migrate the regions prioritizing colder regions. * @DAMOS_STAT: Do nothing but count the stat. * @NR_DAMOS_ACTIONS: Total number of DAMOS actions * * The support of each action is up to running &struct damon_operations. * Refer to 'Operation Action' section of Documentation/mm/damon/design.rst for * status of the supports. * * Note that DAMOS_PAGEOUT doesn't trigger demotions. */enum damos_action { DAMOS_WILLNEED, DAMOS_COLD, DAMOS_PAGEOUT, DAMOS_HUGEPAGE, DAMOS_NOHUGEPAGE, DAMOS_COLLAPSE, DAMOS_LRU_PRIO, DAMOS_LRU_DEPRIO, DAMOS_MIGRATE_HOT, DAMOS_MIGRATE_COLD, DAMOS_STAT, /* Do nothing but only record the stat */ NR_DAMOS_ACTIONS,};
/** * enum damos_quota_goal_metric - Represents the metric to be used as the goal * * @DAMOS_QUOTA_USER_INPUT: User-input value. * @DAMOS_QUOTA_SOME_MEM_PSI_US: System level some memory PSI in us. * @DAMOS_QUOTA_NODE_MEM_USED_BP: MemUsed ratio of a node. * @DAMOS_QUOTA_NODE_MEM_FREE_BP: MemFree ratio of a node. * @DAMOS_QUOTA_NODE_MEMCG_USED_BP: MemUsed ratio of a node for a cgroup. * @DAMOS_QUOTA_NODE_MEMCG_FREE_BP: MemFree ratio of a node for a cgroup. * @DAMOS_QUOTA_ACTIVE_MEM_BP: Active to total LRU memory ratio. * @DAMOS_QUOTA_INACTIVE_MEM_BP: Inactive to total LRU memory ratio. * @DAMOS_QUOTA_NODE_ELIGIBLE_MEM_BP: Scheme-eligible memory ratio of a * node in basis points (0-10000). * @NR_DAMOS_QUOTA_GOAL_METRICS: Number of DAMOS quota goal metrics. * * Metrics equal to larger than @NR_DAMOS_QUOTA_GOAL_METRICS are unsupported. */enum damos_quota_goal_metric { DAMOS_QUOTA_USER_INPUT, DAMOS_QUOTA_SOME_MEM_PSI_US, DAMOS_QUOTA_NODE_MEM_USED_BP, DAMOS_QUOTA_NODE_MEM_FREE_BP, DAMOS_QUOTA_NODE_MEMCG_USED_BP, DAMOS_QUOTA_NODE_MEMCG_FREE_BP, DAMOS_QUOTA_ACTIVE_MEM_BP, DAMOS_QUOTA_INACTIVE_MEM_BP, DAMOS_QUOTA_NODE_ELIGIBLE_MEM_BP, NR_DAMOS_QUOTA_GOAL_METRICS,};
/** * struct damos_quota_goal - DAMOS scheme quota auto-tuning goal. * @metric: Metric to be used for representing the goal. * @target_value: Target value of @metric to achieve with the tuning. * @current_value: Current value of @metric. * @last_psi_total: Last measured total PSI * @nid: Node id. * @memcg_id: Memcg id. * @list: List head for siblings. * * Data structure for getting the current score of the quota tuning goal. The * score is calculated by how close @current_value and @target_value are. Then * the score is entered to DAMON's internal feedback loop mechanism to get the * auto-tuned quota. * * If @metric is DAMOS_QUOTA_USER_INPUT, @current_value should be manually * entered by the user, probably inside the kdamond callbacks. Otherwise, * DAMON sets @current_value with self-measured value of @metric. * * If @metric is DAMOS_QUOTA_NODE_MEM_{USED,FREE}_BP, @nid represents the node * id of the target node to account the used/free memory. * * If @metric is DAMOS_QUOTA_NODE_MEMCG_{USED,FREE}_BP, @nid and @memcg_id * represents the node id and the cgroup to account the used memory for. */struct damos_quota_goal { enum damos_quota_goal_metric metric; unsigned long target_value; unsigned long current_value; /* metric-dependent fields */ union { u64 last_psi_total; struct { int nid; u64 memcg_id; }; }; struct list_head list;};
/** * enum damos_quota_goal_tuner - Goal-based quota tuning logic. * @DAMOS_QUOTA_GOAL_TUNER_CONSIST: Aim long term consistent quota. * @DAMOS_QUOTA_GOAL_TUNER_TEMPORAL: Aim zero quota asap. */enum damos_quota_goal_tuner { DAMOS_QUOTA_GOAL_TUNER_CONSIST, DAMOS_QUOTA_GOAL_TUNER_TEMPORAL,};
/** * struct damos_quota - Controls the aggressiveness of the given scheme. * @reset_interval: Charge reset interval in milliseconds. * @ms: Maximum milliseconds that the scheme can use. * @sz: Maximum bytes of memory that the action can be applied. * @goals: Head of quota tuning goals (&damos_quota_goal) list. * @goal_tuner: Goal-based @esz tuning algorithm to use. * @esz: Effective size quota in bytes. * @fail_charge_num: Failed regions charge rate numerator. * @fail_charge_denom: Failed regions charge rate denominator. * * @weight_sz: Weight of the region's size for prioritization. * @weight_nr_accesses: Weight of the region's nr_accesses for prioritization. * @weight_age: Weight of the region's age for prioritization. * * To avoid consuming too much CPU time or IO resources for applying the * &struct damos->action to large memory, DAMON allows users to set time and/or * size quotas. The quotas can be set by writing non-zero values to &ms and * &sz, respectively. If the time quota is set, DAMON tries to use only up to * &ms milliseconds within &reset_interval for applying the action. If the * size quota is set, DAMON tries to apply the action only up to &sz bytes * within &reset_interval. * * To convince the different types of quotas and goals, DAMON internally * converts those into one single size quota called "effective quota". DAMON * internally uses it as the only one real quota. The conversion is made as * follows. * * The time quota is transformed to a size quota using estimated throughput of * the scheme's action. DAMON then compares it against &sz and uses smaller * one as the effective quota. * * If @goals is not empty, DAMON calculates yet another size quota based on the * goals using its internal feedback loop algorithm, for every @reset_interval. * Then, if the new size quota is smaller than the effective quota, it uses the * new size quota as the effective quota. * * The resulting effective size quota in bytes is set to @esz. * * For DAMOS action applying failed amount of regions, charging those same to * those that the action has successfully applied may be unfair. For the * reason, 'the size * @fail_charge_num / @fail_charge_denom' is charged. * * For selecting regions within the quota, DAMON prioritizes current scheme's * target memory regions using the &struct damon_operations->get_scheme_score. * You could customize the prioritization logic by setting &weight_sz, * &weight_nr_accesses, and &weight_age, because monitoring operations are * encouraged to respect those. */struct damos_quota { unsigned long reset_interval; unsigned long ms; unsigned long sz; struct list_head goals; enum damos_quota_goal_tuner goal_tuner; unsigned long esz;
unsigned int fail_charge_num; unsigned int fail_charge_denom;
unsigned int weight_sz; unsigned int weight_nr_accesses; unsigned int weight_age;
/* private: */ /* For throughput estimation */ unsigned long total_charged_sz; unsigned long total_charged_ns;
/* For charging the quota */ unsigned long charged_sz; unsigned long charged_from; struct damon_target *charge_target_from; unsigned long charge_addr_from;
/* For prioritization */ unsigned int min_score;
/* For feedback loop */ unsigned long esz_bp;};
/** * enum damos_wmark_metric - Represents the watermark metric. * * @DAMOS_WMARK_NONE: Ignore the watermarks of the given scheme. * @DAMOS_WMARK_FREE_MEM_RATE: Free memory rate of the system in [0,1000]. * @NR_DAMOS_WMARK_METRICS: Total number of DAMOS watermark metrics */enum damos_wmark_metric { DAMOS_WMARK_NONE, DAMOS_WMARK_FREE_MEM_RATE, NR_DAMOS_WMARK_METRICS,};
/** * struct damos_watermarks - Controls when a given scheme should be activated. * @metric: Metric for the watermarks. * @interval: Watermarks check time interval in microseconds. * @high: High watermark. * @mid: Middle watermark. * @low: Low watermark. * * If &metric is &DAMOS_WMARK_NONE, the scheme is always active. Being active * means DAMON does monitoring and applying the action of the scheme to * appropriate memory regions. Else, DAMON checks &metric of the system for at * least every &interval microseconds and works as below. * * If &metric is higher than &high, the scheme is inactivated. If &metric is * between &mid and &low, the scheme is activated. If &metric is lower than * &low, the scheme is inactivated. */struct damos_watermarks { enum damos_wmark_metric metric; unsigned long interval; unsigned long high; unsigned long mid; unsigned long low;
/* private: */ bool activated;};
/** * struct damos_stat - Statistics on a given scheme. * @nr_tried: Total number of regions that the scheme is tried to be applied. * @sz_tried: Total size of regions that the scheme is tried to be applied. * @nr_applied: Total number of regions that the scheme is applied. * @sz_applied: Total size of regions that the scheme is applied. * @sz_ops_filter_passed: * Total bytes that passed ops layer-handled DAMOS filters. * @qt_exceeds: Total number of times the quota of the scheme has exceeded. * @nr_snapshots: * Total number of DAMON snapshots that the scheme has tried. * * "Tried an action to a region" in this context means the DAMOS core logic * determined the region as eligible to apply the action. The access pattern * (&struct damos_access_pattern), quotas (&struct damos_quota), watermarks * (&struct damos_watermarks) and filters (&struct damos_filter) that handled * on core logic can affect this. The core logic asks the operation set * (&struct damon_operations) to apply the action to the region. * * "Applied an action to a region" in this context means the operation set * (&struct damon_operations) successfully applied the action to the region, at * least to a part of the region. The filters (&struct damos_filter) that * handled on operation set layer and type of the action and pages of the * region can affect this. For example, if a filter is set to exclude * anonymous pages and the region has only anonymous pages, the region will be * failed at applying the action. If the action is &DAMOS_PAGEOUT and all * pages of the region are already paged out, the region will be failed at * applying the action. */struct damos_stat { unsigned long nr_tried; unsigned long sz_tried; unsigned long nr_applied; unsigned long sz_applied; unsigned long sz_ops_filter_passed; unsigned long qt_exceeds; unsigned long nr_snapshots;};
/** * enum damos_filter_type - Type of memory for &struct damos_filter * @DAMOS_FILTER_TYPE_ANON: Anonymous pages. * @DAMOS_FILTER_TYPE_ACTIVE: Active pages. * @DAMOS_FILTER_TYPE_MEMCG: Specific memcg's pages. * @DAMOS_FILTER_TYPE_YOUNG: Recently accessed pages. * @DAMOS_FILTER_TYPE_HUGEPAGE_SIZE: Page is part of a hugepage. * @DAMOS_FILTER_TYPE_UNMAPPED: Unmapped pages. * @DAMOS_FILTER_TYPE_ADDR: Address range. * @DAMOS_FILTER_TYPE_TARGET: Data Access Monitoring target. * @NR_DAMOS_FILTER_TYPES: Number of filter types. * * The anon pages type and memcg type filters are handled by underlying * &struct damon_operations as a part of scheme action trying, and therefore * accounted as 'tried'. In contrast, other types are handled by core layer * before trying of the action and therefore not accounted as 'tried'. * * The support of the filters that handled by &struct damon_operations depend * on the running &struct damon_operations. * &enum DAMON_OPS_PADDR supports both anon pages type and memcg type filters, * while &enum DAMON_OPS_VADDR and &enum DAMON_OPS_FVADDR don't support any of * the two types. */enum damos_filter_type { DAMOS_FILTER_TYPE_ANON, DAMOS_FILTER_TYPE_ACTIVE, DAMOS_FILTER_TYPE_MEMCG, DAMOS_FILTER_TYPE_YOUNG, DAMOS_FILTER_TYPE_HUGEPAGE_SIZE, DAMOS_FILTER_TYPE_UNMAPPED, DAMOS_FILTER_TYPE_ADDR, DAMOS_FILTER_TYPE_TARGET, NR_DAMOS_FILTER_TYPES,};
/** * struct damos_filter - DAMOS action target memory filter. * @type: Type of the target memory. * @matching: Whether this is for @type-matching memory. * @allow: Whether to include or exclude the @matching memory. * @memcg_id: Memcg id of the question if @type is DAMOS_FILTER_MEMCG. * @addr_range: Address range if @type is DAMOS_FILTER_TYPE_ADDR. * @target_idx: Index of the &struct damon_target of * &damon_ctx->adaptive_targets if @type is * DAMOS_FILTER_TYPE_TARGET. * @sz_range: Size range if @type is DAMOS_FILTER_TYPE_HUGEPAGE_SIZE. * @list: List head for siblings. * * Before applying the &damos->action to a memory region, DAMOS checks if each * byte of the region matches to this given condition and avoid applying the * action if so. Support of each filter type depends on the running &struct * damon_operations and the type. Refer to &enum damos_filter_type for more * details. */struct damos_filter { enum damos_filter_type type; bool matching; bool allow; union { u64 memcg_id; struct damon_addr_range addr_range; int target_idx; struct damon_size_range sz_range; }; struct list_head list;};
struct damon_ctx;struct damos;
/** * struct damos_walk_control - Control damos_walk(). * * @walk_fn: Function to be called back for each region. * @data: Data that will be passed to walk functions. * * Control damos_walk(), which requests specific kdamond to invoke the given * function to each region that eligible to apply actions of the kdamond's * schemes. Refer to damos_walk() for more details. */struct damos_walk_control { void (*walk_fn)(void *data, struct damon_ctx *ctx, struct damon_target *t, struct damon_region *r, struct damos *s, unsigned long sz_filter_passed); void *data;/* private: internal use only */ /* informs if the kdamond finished handling of the walk request */ struct completion completion; /* informs if the walk is canceled. */ bool canceled;};
/** * struct damos_access_pattern - Target access pattern of the given scheme. * @min_sz_region: Minimum size of target regions. * @max_sz_region: Maximum size of target regions. * @min_nr_accesses: Minimum ``->nr_accesses`` of target regions. * @max_nr_accesses: Maximum ``->nr_accesses`` of target regions. * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. */struct damos_access_pattern { unsigned long min_sz_region; unsigned long max_sz_region; unsigned int min_nr_accesses; unsigned int max_nr_accesses; unsigned int min_age_region; unsigned int max_age_region;};
/** * struct damos_migrate_dests - Migration destination nodes and their weights. * @node_id_arr: Array of migration destination node ids. * @weight_arr: Array of migration weights for @node_id_arr. * @nr_dests: Length of the @node_id_arr and @weight_arr arrays. * * @node_id_arr is an array of the ids of migration destination nodes. * @weight_arr is an array of the weights for those. The weights in * @weight_arr are for nodes in @node_id_arr of same array index. */struct damos_migrate_dests { unsigned int *node_id_arr; unsigned int *weight_arr; size_t nr_dests;};
/** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @pattern: Access pattern of target regions. * @action: &damos_action to be applied to the target regions. * @apply_interval_us: The time between applying the @action. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. * @migrate_dests: Destination nodes if @action is "migrate_{hot,cold}". * @target_nid: Destination node if @action is "migrate_{hot,cold}". * @core_filters: Additional set of &struct damos_filter for &action. * @ops_filters: ops layer handling &struct damos_filter objects list. * @last_applied: Last @action applied ops-managing entity. * @stat: Statistics of this scheme. * @max_nr_snapshots: Upper limit of nr_snapshots stat. * @list: List head for siblings. * * For each @apply_interval_us, DAMON finds regions which fit in the * &pattern and applies &action to those. To avoid consuming too much * CPU time or IO resources for the &action, "a is used. * * If @apply_interval_us is zero, &damon_attrs->aggr_interval is used instead. * * To do the work only when needed, schemes can be activated for specific * system situations using &wmarks. If all schemes that registered to the * monitoring context are inactive, DAMON stops monitoring either, and just * repeatedly checks the watermarks. * * @migrate_dests specifies multiple migration target nodes with different * weights for migrate_hot or migrate_cold actions. @target_nid is ignored if * this is set. * * @target_nid is used to set the migration target node for migrate_hot or * migrate_cold actions, and @migrate_dests is unset. * * Before applying the &action to a memory region, &struct damon_operations * implementation could check pages of the region and skip &action to respect * &core_filters * * The minimum entity that @action can be applied depends on the underlying * &struct damon_operations. Since it may not be aligned with the core layer * abstract, namely &struct damon_region, &struct damon_operations could apply * @action to same entity multiple times. Large folios that underlying on * multiple &struct damon region objects could be such examples. The &struct * damon_operations can use @last_applied to avoid that. DAMOS core logic * unsets @last_applied when each regions walking for applying the scheme is * finished. * * After applying the &action to each region, &stat is updated. * * If &max_nr_snapshots is set as non-zero and &stat.nr_snapshots be same to or * greater than it, the scheme is deactivated. */struct damos { struct damos_access_pattern pattern; enum damos_action action; unsigned long apply_interval_us;/* private: internal use only */ /* * number of sample intervals that should be passed before applying * @action */ unsigned long next_apply_sis; /* informs if ongoing DAMOS walk for this scheme is finished */ bool walk_completed; /* * If the current region in the filtering stage is allowed by core * layer-handled filters. If true, operations layer allows it, too. */ bool core_filters_allowed; /* whether to reject core/ops filters umatched regions */ bool core_filters_default_reject; bool ops_filters_default_reject;/* public: */ struct damos_quota quota; struct damos_watermarks wmarks; union { struct { int target_nid; struct damos_migrate_dests migrate_dests; }; }; struct list_head core_filters; struct list_head ops_filters; void *last_applied; struct damos_stat stat; unsigned long max_nr_snapshots; struct list_head list;};
/** * enum damon_ops_id - Identifier for each monitoring operations implementation * * @DAMON_OPS_VADDR: Monitoring operations for virtual address spaces * @DAMON_OPS_FVADDR: Monitoring operations for only fixed ranges of virtual * address spaces * @DAMON_OPS_PADDR: Monitoring operations for the physical address space * @NR_DAMON_OPS: Number of monitoring operations implementations */enum damon_ops_id { DAMON_OPS_VADDR, DAMON_OPS_FVADDR, DAMON_OPS_PADDR, NR_DAMON_OPS,};
/** * struct damon_operations - Monitoring operations for given use cases. * * @id: Identifier of this operations set. * @init: Initialize operations-related data structures. * @update: Update operations-related data structures. * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @apply_probes: Apply probes for each region. * @get_scheme_score: Get the score of a region for a scheme. * @apply_scheme: Apply a DAMON-based operation scheme. * @target_valid: Determine if the target is valid. * @cleanup_target: Clean up each target before deallocation. * * DAMON can be extended for various address spaces and usages. For this, * users should register the low level operations for their target address * space and usecase via the &damon_ctx.ops. Then, the monitoring thread * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting * the monitoring, @update after each &damon_attrs.ops_update_interval, and * @check_accesses, @target_valid and @prepare_access_checks after each * &damon_attrs.sample_interval. * * Each &struct damon_operations instance having valid @id can be registered * via damon_register_ops() and selected by damon_select_ops() later. * @init should initialize operations-related data structures. For example, * this could be used to construct proper monitoring target regions and link * those to @damon_ctx.adaptive_targets. * @update should update the operations-related data structures. For example, * this could be used to update monitoring target regions for current status. * @prepare_access_checks should manipulate the monitoring regions to be * prepared for the next access check. * @check_accesses should check the accesses to each region that made after the * last preparation and update the number of observed accesses of each region. * It should also return max number of observed accesses that made as a result * of its update. The value will be used for regions adjustment threshold. * @apply_probes should apply the data attribute probes to each region and * accordingly update the probe hits counter of the region. * @get_scheme_score should return the priority score of a region for a scheme * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action * to the region and return bytes of the region that the action is successfully * applied. It should also report how many bytes of the region has passed * filters (&struct damos_filter) that handled by itself. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup_target is called before the target will be deallocated. */struct damon_operations { enum damon_ops_id id; void (*init)(struct damon_ctx *context); void (*update)(struct damon_ctx *context); void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); void (*apply_probes)(struct damon_ctx *context); int (*get_scheme_score)(struct damon_ctx *context, struct damon_region *r, struct damos *scheme); unsigned long (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme, unsigned long *sz_filter_passed); bool (*target_valid)(struct damon_target *t); void (*cleanup_target)(struct damon_target *t);};
/* * struct damon_call_control - Control damon_call(). * * @fn: Function to be called back. * @data: Data that will be passed to @fn. * @repeat: Repeat invocations. * @return_code: Return code from @fn invocation. * @dealloc_on_cancel: If @repeat is true, de-allocate when canceled. * * Control damon_call(), which requests specific kdamond to invoke a given * function. Refer to damon_call() for more details. */struct damon_call_control { int (*fn)(void *data); void *data; bool repeat; int return_code; bool dealloc_on_cancel;/* private: internal use only */ /* informs if the kdamond finished handling of the request */ struct completion completion; /* informs if the kdamond canceled @fn infocation */ bool canceled; /* List head for siblings. */ struct list_head list;};
/** * struct damon_intervals_goal - Monitoring intervals auto-tuning goal. * * @access_bp: Access events observation ratio to achieve in bp. * @aggrs: Number of aggregations to achieve @access_bp within. * @min_sample_us: Minimum resulting sampling interval in microseconds. * @max_sample_us: Maximum resulting sampling interval in microseconds. * * DAMON automatically tunes &damon_attrs->sample_interval and * &damon_attrs->aggr_interval aiming the ratio in bp (1/10,000) of * DAMON-observed access events to theoretical maximum amount within @aggrs * aggregations be same to @access_bp. The logic increases * &damon_attrs->aggr_interval and &damon_attrs->sampling_interval in same * ratio if the current access events observation ratio is lower than the * target for each @aggrs aggregations, and vice versa. * * If @aggrs is zero, the tuning is disabled and hence this struct is ignored. */struct damon_intervals_goal { unsigned long access_bp; unsigned long aggrs; unsigned long min_sample_us; unsigned long max_sample_us;};
/** * enum damon_filter_type - Type of &struct damon_filter * * @DAMON_FILTER_TYPE_ANON: Anonymous pages. * @DAMON_FILTER_TYPE_MEMCG: Specific memcg's pages. */enum damon_filter_type { DAMON_FILTER_TYPE_ANON, DAMON_FILTER_TYPE_MEMCG,};
/** * struct damon_filter - DAMON region filter for &struct damon_probe. * * @type: Type of the region. * @matching: Whether this filter is for the type-matching ones. * @allow: Whether the @type-@matching ones should pass this filter. * @memcg_id: Memcg id of the question if @type is DAMON_FILTER_MEMCG. * @list: Siblings list. */struct damon_filter { enum damon_filter_type type; bool matching; bool allow; union { u64 memcg_id; }; struct list_head list;};
/** * struct damon_probe - Data region attribute probe. * * @filters: Filters for assessing if a given region is for this probe. * @list: Siblings list. */struct damon_probe { struct list_head filters; struct list_head list;};
/** * struct damon_attrs - Monitoring attributes for accuracy/overhead control. * * @sample_interval: The time between access samplings. * @aggr_interval: The time between monitor results aggregations. * @ops_update_interval: The time between monitoring operations updates. * @intervals_goal: Intervals auto-tuning goal. * @min_nr_regions: The minimum number of adaptive monitoring * regions. * @max_nr_regions: The maximum number of adaptive monitoring * regions. * * For each @sample_interval, DAMON checks whether each region is accessed or * not during the last @sample_interval. If such access is found, DAMON * aggregates the information by increasing &damon_region->nr_accesses for * @aggr_interval time. For each @aggr_interval, the count is reset. DAMON * also checks whether the target memory regions need update (e.g., by * ``mmap()`` calls from the application, in case of virtual memory monitoring) * and applies the changes for each @ops_update_interval. All time intervals * are in micro-seconds. Please refer to &struct damon_operations and &struct * damon_call_control for more detail. */struct damon_attrs { unsigned long sample_interval; unsigned long aggr_interval; unsigned long ops_update_interval; struct damon_intervals_goal intervals_goal; unsigned long min_nr_regions; unsigned long max_nr_regions;/* private: internal use only */ /* * @aggr_interval to @sample_interval ratio. * Core-external components call damon_set_attrs() with &damon_attrs * that this field is unset. In the case, damon_set_attrs() sets this * field of resulting &damon_attrs. Core-internal components such as * kdamond_tune_intervals() calls damon_set_attrs() with &damon_attrs * that this field is set. In the case, damon_set_attrs() just keep * it. */ unsigned long aggr_samples;};
/** * struct damon_ctx - Represents a context for each monitoring. This is the * main interface that allows users to set the attributes and get the results * of the monitoring. * * @attrs: Monitoring attributes for accuracy/overhead control. * * For each monitoring context, one kernel thread for the monitoring, namely * kdamond, is created. The pid of kdamond can be retrieved using * damon_kdamond_pid(). * * Once started, kdamond runs until explicitly required to be terminated or * every monitoring target is invalid. The validity of the targets is checked * via the &damon_operations.target_valid of @ops. The termination can also be * explicitly requested by calling damon_stop(). To know if a kdamond is * running, damon_is_running() can be used. * * While the kdamond is running, all accesses to &struct damon_ctx from a * thread other than the kdamond should be made using safe DAMON APIs, * including damon_call() and damos_walk(). * * @ops: Set of monitoring operations for given use cases. * @probes: Head of probes (&damon_probe) list. * @addr_unit: Scale factor for core to ops address conversion. * @min_region_sz: Minimum region size. * @pause: Pause kdamond main loop. * @adaptive_targets: Head of monitoring targets (&damon_target) list. * @schemes: Head of schemes (&damos) list. * @rnd_state: Per-ctx PRNG state for damon_rand(). */struct damon_ctx { struct damon_attrs attrs;
/* private: internal use only */ /* number of sample intervals that passed since this context started */ unsigned long passed_sample_intervals; /* * number of sample intervals that should be passed before next * aggregation */ unsigned long next_aggregation_sis; /* * number of sample intervals that should be passed before next ops * update */ unsigned long next_ops_update_sis; /* * number of sample intervals that should be passed before next * intervals tuning */ unsigned long next_intervals_tune_sis; /* for waiting until the execution of the kdamond_fn is started */ struct completion kdamond_started; /* for scheme quotas prioritization */ unsigned long *regions_score_histogram;
/* lists of &struct damon_call_control */ struct list_head call_controls; bool call_controls_obsolete; struct mutex call_controls_lock;
struct damos_walk_control *walk_control; bool walk_control_obsolete; struct mutex walk_control_lock;
/* * indicate if this may be corrupted. Currentonly this is set only for * damon_commit_ctx() failure. */ bool maybe_corrupted;
/* Working thread of the given DAMON context */ struct task_struct *kdamond; /* Protects @kdamond field access */ struct mutex kdamond_lock;
/* public: */ struct damon_operations ops; struct list_head probes; unsigned long addr_unit; unsigned long min_region_sz; bool pause;
struct list_head adaptive_targets; struct list_head schemes;
struct rnd_state rnd_state;};
/* Get a random number in [@l, @r) using @ctx's lockless PRNG. */static inline unsigned long damon_rand(struct damon_ctx *ctx, unsigned long l, unsigned long r){ unsigned long span = r - l; u64 rnd;
if (span <= U32_MAX) { rnd = prandom_u32_state(&ctx->rnd_state); return l + (unsigned long)((rnd * span) >> 32); } rnd = ((u64)prandom_u32_state(&ctx->rnd_state) << 32) | prandom_u32_state(&ctx->rnd_state); return l + mul_u64_u64_shr(rnd, span, 64);}
static inline struct damon_region *damon_next_region(struct damon_region *r){ return container_of(r->list.next, struct damon_region, list);}
static inline struct damon_region *damon_prev_region(struct damon_region *r){ return container_of(r->list.prev, struct damon_region, list);}
static inline struct damon_region *damon_last_region(struct damon_target *t){ return list_last_entry(&t->regions_list, struct damon_region, list);}
static inline struct damon_region *damon_first_region(struct damon_target *t){ return list_first_entry(&t->regions_list, struct damon_region, list);}
static inline unsigned long damon_sz_region(struct damon_region *r){ return r->ar.end - r->ar.start;}
#define damon_for_each_filter(f, p) \ list_for_each_entry(f, &(p)->filters, list)
#define damon_for_each_filter_safe(f, next, p) \ list_for_each_entry_safe(f, next, &(p)->filters, list)
#define damon_for_each_probe(p, ctx) \ list_for_each_entry(p, &(ctx)->probes, list)
#define damon_for_each_probe_safe(p, next, ctx) \ list_for_each_entry_safe(p, next, &(ctx)->probes, list)
#define damon_for_each_region(r, t) \ list_for_each_entry(r, &(t)->regions_list, list)
#define damon_for_each_region_from(r, t) \ list_for_each_entry_from(r, &(t)->regions_list, list)
#define damon_for_each_region_safe(r, next, t) \ list_for_each_entry_safe(r, next, &(t)->regions_list, list)
#define damon_for_each_target(t, ctx) \ list_for_each_entry(t, &(ctx)->adaptive_targets, list)
#define damon_for_each_target_safe(t, next, ctx) \ list_for_each_entry_safe(t, next, &(ctx)->adaptive_targets, list)
#define damon_for_each_scheme(s, ctx) \ list_for_each_entry(s, &(ctx)->schemes, list)
#define damon_for_each_scheme_safe(s, next, ctx) \ list_for_each_entry_safe(s, next, &(ctx)->schemes, list)
#define damos_for_each_quota_goal(goal, quota) \ list_for_each_entry(goal, &(quota)->goals, list)
#define damos_for_each_quota_goal_safe(goal, next, quota) \ list_for_each_entry_safe(goal, next, &(quota)->goals, list)
#define damos_for_each_core_filter(f, scheme) \ list_for_each_entry(f, &(scheme)->core_filters, list)
#define damos_for_each_core_filter_safe(f, next, scheme) \ list_for_each_entry_safe(f, next, &(scheme)->core_filters, list)
#define damos_for_each_ops_filter(f, scheme) \ list_for_each_entry(f, &(scheme)->ops_filters, list)
#define damos_for_each_ops_filter_safe(f, next, scheme) \ list_for_each_entry_safe(f, next, &(scheme)->ops_filters, list)
#ifdef CONFIG_DAMON
struct damon_filter *damon_new_filter(enum damon_filter_type type, bool matching, bool allow);void damon_add_filter(struct damon_probe *probe, struct damon_filter *f);void damon_destroy_filter(struct damon_filter *f);
struct damon_probe *damon_new_probe(void);void damon_add_probe(struct damon_ctx *ctx, struct damon_probe *probe);
struct damon_region *damon_new_region(unsigned long start, unsigned long end);
int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, unsigned int nr_ranges, unsigned long min_region_sz);void damon_update_region_access_rate(struct damon_region *r, bool accessed, struct damon_attrs *attrs);
struct damos_filter *damos_new_filter(enum damos_filter_type type, bool matching, bool allow);void damos_add_filter(struct damos *s, struct damos_filter *f);bool damos_filter_for_ops(enum damos_filter_type type);void damos_destroy_filter(struct damos_filter *f);
struct damos_quota_goal *damos_new_quota_goal( enum damos_quota_goal_metric metric, unsigned long target_value);void damos_add_quota_goal(struct damos_quota *q, struct damos_quota_goal *g);void damos_destroy_quota_goal(struct damos_quota_goal *goal);
struct damos *damon_new_scheme(struct damos_access_pattern *pattern, enum damos_action action, unsigned long apply_interval_us, struct damos_quota *quota, struct damos_watermarks *wmarks, int target_nid);void damon_add_scheme(struct damon_ctx *ctx, struct damos *s);void damon_destroy_scheme(struct damos *s);int damos_commit_quota_goals(struct damos_quota *dst, struct damos_quota *src);
struct damon_target *damon_new_target(void);void damon_add_target(struct damon_ctx *ctx, struct damon_target *t);bool damon_targets_empty(struct damon_ctx *ctx);void damon_free_target(struct damon_target *t);void damon_destroy_target(struct damon_target *t, struct damon_ctx *ctx);unsigned int damon_nr_regions(struct damon_target *t);
struct damon_ctx *damon_new_ctx(void);void damon_destroy_ctx(struct damon_ctx *ctx);int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs);void damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes);int damon_commit_ctx(struct damon_ctx *old_ctx, struct damon_ctx *new_ctx);int damon_nr_running_ctxs(void);bool damon_is_registered_ops(enum damon_ops_id id);int damon_register_ops(struct damon_operations *ops);int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id);
static inline bool damon_target_has_pid(const struct damon_ctx *ctx){ return ctx->ops.id == DAMON_OPS_VADDR || ctx->ops.id == DAMON_OPS_FVADDR;}
static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs){ unsigned long sample_interval; unsigned long max_nr_accesses;
sample_interval = attrs->sample_interval ? : 1; max_nr_accesses = min(attrs->aggr_interval / sample_interval, (unsigned long)UINT_MAX); return max_nr_accesses ? : 1;}
bool damon_initialized(void);int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive);int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);bool damon_is_running(struct damon_ctx *ctx);int damon_kdamond_pid(struct damon_ctx *ctx);
int damon_call(struct damon_ctx *ctx, struct damon_call_control *control);int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control);
int damon_set_region_system_rams_default(struct damon_target *t, unsigned long *start, unsigned long *end, unsigned long addr_unit, unsigned long min_region_sz);
#endif /* CONFIG_DAMON */
#endif /* _DAMON_H */