From c6833e10008f976a173dd5abdf992e492cbc3bcf Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2022 16:39:52 +0800 Subject: memory tiering: rate limit NUMA migration throughput In NUMA balancing memory tiering mode, if there are hot pages in slow memory node and cold pages in fast memory node, we need to promote/demote hot/cold pages between the fast and cold memory nodes. A choice is to promote/demote as fast as possible. But the CPU cycles and memory bandwidth consumed by the high promoting/demoting throughput will hurt the latency of some workload because of accessing inflating and slow memory bandwidth contention. A way to resolve this issue is to restrict the max promoting/demoting throughput. It will take longer to finish the promoting/demoting. But the workload latency will be better. This is implemented in this patch as the page promotion rate limit mechanism. The number of the candidate pages to be promoted to the fast memory node via NUMA balancing is counted, if the count exceeds the limit specified by the users, the NUMA balancing promotion will be stopped until the next second. A new sysctl knob kernel.numa_balancing_promote_rate_limit_MBps is added for the users to specify the limit. Link: https://lkml.kernel.org/r/20220713083954.34196-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reviewed-by: Baolin Wang Tested-by: Baolin Wang Cc: Dave Hansen Cc: Johannes Weiner Cc: Mel Gorman Cc: Michal Hocko Cc: osalvador Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shakeel Butt Cc: Wei Xu Cc: Yang Shi Cc: Zhong Jiang Cc: Zi Yan Signed-off-by: Andrew Morton --- mm/vmstat.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm/vmstat.c') diff --git a/mm/vmstat.c b/mm/vmstat.c index 90af9a8572f5..c109167a669c 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1252,6 +1252,7 @@ const char * const vmstat_text[] = { #endif #ifdef CONFIG_NUMA_BALANCING "pgpromote_success", + "pgpromote_candidate", #endif /* enum writeback_stat_item counters */ -- cgit v1.2.3-70-g09d2 From 6c542ab75714fe90dae292aeb3e91ac53f5ff599 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 18 Aug 2022 18:40:37 +0530 Subject: mm/demotion: build demotion targets based on explicit memory tiers This patch switch the demotion target building logic to use memory tiers instead of NUMA distance. All N_MEMORY NUMA nodes will be placed in the default memory tier and additional memory tiers will be added by drivers like dax kmem. This patch builds the demotion target for a NUMA node by looking at all memory tiers below the tier to which the NUMA node belongs. The closest node in the immediately following memory tier is used as a demotion target. Since we are now only building demotion target for N_MEMORY NUMA nodes the CPU hotplug calls are removed in this patch. Link: https://lkml.kernel.org/r/20220818131042.113280-6-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: "Huang, Ying" Acked-by: Wei Xu Cc: Alistair Popple Cc: Bharata B Rao Cc: Dan Williams Cc: Dave Hansen Cc: Davidlohr Bueso Cc: Hesham Almatary Cc: Jagdish Gediya Cc: Johannes Weiner Cc: Jonathan Cameron Cc: Michal Hocko Cc: Tim Chen Cc: Yang Shi Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/memory-tiers.h | 13 ++ include/linux/migrate.h | 13 -- mm/memory-tiers.c | 238 ++++++++++++++++++++++++-- mm/migrate.c | 394 ------------------------------------------- mm/vmstat.c | 4 - 5 files changed, 239 insertions(+), 423 deletions(-) (limited to 'mm/vmstat.c') diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 49d281866dca..ce9c6bac6725 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -37,6 +37,14 @@ struct memory_dev_type *alloc_memory_type(int adistance); void destroy_memory_type(struct memory_dev_type *memtype); void init_node_memory_type(int node, struct memory_dev_type *default_type); void clear_node_memory_type(int node, struct memory_dev_type *memtype); +#ifdef CONFIG_MIGRATION +int next_demotion_node(int node); +#else +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} +#endif #else @@ -63,5 +71,10 @@ static inline void clear_node_memory_type(int node, struct memory_dev_type *memt { } + +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} #endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 96f8c84413fe..704a04f5a074 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -100,19 +100,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, #endif /* CONFIG_MIGRATION */ -#if defined(CONFIG_MIGRATION) && defined(CONFIG_NUMA) -extern void set_migration_target_nodes(void); -extern void migrate_on_reclaim_init(void); -extern int next_demotion_node(int node); -#else -static inline void set_migration_target_nodes(void) {} -static inline void migrate_on_reclaim_init(void) {} -static inline int next_demotion_node(int node) -{ - return NUMA_NO_NODE; -} -#endif - #ifdef CONFIG_COMPACTION bool PageMovable(struct page *page); void __SetPageMovable(struct page *page, const struct movable_operations *ops); diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index babc10a5cc13..ea57fc1f37ac 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -6,6 +6,8 @@ #include #include +#include "internal.h" + struct memory_tier { /* hierarchy of memory tiers */ struct list_head list; @@ -19,6 +21,10 @@ struct memory_tier { int adistance_start; }; +struct demotion_nodes { + nodemask_t preferred; +}; + struct node_memory_type_map { struct memory_dev_type *memtype; int map_count; @@ -28,6 +34,66 @@ static DEFINE_MUTEX(memory_tier_lock); static LIST_HEAD(memory_tiers); static struct node_memory_type_map node_memory_types[MAX_NUMNODES]; static struct memory_dev_type *default_dram_type; +#ifdef CONFIG_MIGRATION +/* + * node_demotion[] examples: + * + * Example 1: + * + * Node 0 & 1 are CPU + DRAM nodes, node 2 & 3 are PMEM nodes. + * + * node distances: + * node 0 1 2 3 + * 0 10 20 30 40 + * 1 20 10 40 30 + * 2 30 40 10 40 + * 3 40 30 40 10 + * + * memory_tiers0 = 0-1 + * memory_tiers1 = 2-3 + * + * node_demotion[0].preferred = 2 + * node_demotion[1].preferred = 3 + * node_demotion[2].preferred = + * node_demotion[3].preferred = + * + * Example 2: + * + * Node 0 & 1 are CPU + DRAM nodes, node 2 is memory-only DRAM node. + * + * node distances: + * node 0 1 2 + * 0 10 20 30 + * 1 20 10 30 + * 2 30 30 10 + * + * memory_tiers0 = 0-2 + * + * node_demotion[0].preferred = + * node_demotion[1].preferred = + * node_demotion[2].preferred = + * + * Example 3: + * + * Node 0 is CPU + DRAM nodes, Node 1 is HBM node, node 2 is PMEM node. + * + * node distances: + * node 0 1 2 + * 0 10 20 30 + * 1 20 10 40 + * 2 30 40 10 + * + * memory_tiers0 = 1 + * memory_tiers1 = 0 + * memory_tiers2 = 2 + * + * node_demotion[0].preferred = 2 + * node_demotion[1].preferred = 0 + * node_demotion[2].preferred = + * + */ +static struct demotion_nodes *node_demotion __read_mostly; +#endif /* CONFIG_MIGRATION */ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memtype) { @@ -73,6 +139,154 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty return new_memtier; } +static struct memory_tier *__node_get_memory_tier(int node) +{ + struct memory_dev_type *memtype; + + memtype = node_memory_types[node]; + if (memtype && node_isset(node, memtype->nodes)) + return memtype->memtier; + return NULL; +} + +#ifdef CONFIG_MIGRATION +/** + * next_demotion_node() - Get the next node in the demotion path + * @node: The starting node to lookup the next node + * + * Return: node id for next memory node in the demotion path hierarchy + * from @node; NUMA_NO_NODE if @node is terminal. This does not keep + * @node online or guarantee that it *continues* to be the next demotion + * target. + */ +int next_demotion_node(int node) +{ + struct demotion_nodes *nd; + int target; + + if (!node_demotion) + return NUMA_NO_NODE; + + nd = &node_demotion[node]; + + /* + * node_demotion[] is updated without excluding this + * function from running. + * + * Make sure to use RCU over entire code blocks if + * node_demotion[] reads need to be consistent. + */ + rcu_read_lock(); + /* + * If there are multiple target nodes, just select one + * target node randomly. + * + * In addition, we can also use round-robin to select + * target node, but we should introduce another variable + * for node_demotion[] to record last selected target node, + * that may cause cache ping-pong due to the changing of + * last target node. Or introducing per-cpu data to avoid + * caching issue, which seems more complicated. So selecting + * target node randomly seems better until now. + */ + target = node_random(&nd->preferred); + rcu_read_unlock(); + + return target; +} + +static void disable_all_demotion_targets(void) +{ + int node; + + for_each_node_state(node, N_MEMORY) + node_demotion[node].preferred = NODE_MASK_NONE; + /* + * Ensure that the "disable" is visible across the system. + * Readers will see either a combination of before+disable + * state or disable+after. They will never see before and + * after state together. + */ + synchronize_rcu(); +} + +static __always_inline nodemask_t get_memtier_nodemask(struct memory_tier *memtier) +{ + nodemask_t nodes = NODE_MASK_NONE; + struct memory_dev_type *memtype; + + list_for_each_entry(memtype, &memtier->memory_types, tier_sibiling) + nodes_or(nodes, nodes, memtype->nodes); + + return nodes; +} + +/* + * Find an automatic demotion target for all memory + * nodes. Failing here is OK. It might just indicate + * being at the end of a chain. + */ +static void establish_demotion_targets(void) +{ + struct memory_tier *memtier; + struct demotion_nodes *nd; + int target = NUMA_NO_NODE, node; + int distance, best_distance; + nodemask_t tier_nodes; + + lockdep_assert_held_once(&memory_tier_lock); + + if (!node_demotion || !IS_ENABLED(CONFIG_MIGRATION)) + return; + + disable_all_demotion_targets(); + + for_each_node_state(node, N_MEMORY) { + best_distance = -1; + nd = &node_demotion[node]; + + memtier = __node_get_memory_tier(node); + if (!memtier || list_is_last(&memtier->list, &memory_tiers)) + continue; + /* + * Get the lower memtier to find the demotion node list. + */ + memtier = list_next_entry(memtier, list); + tier_nodes = get_memtier_nodemask(memtier); + /* + * find_next_best_node, use 'used' nodemask as a skip list. + * Add all memory nodes except the selected memory tier + * nodelist to skip list so that we find the best node from the + * memtier nodelist. + */ + nodes_andnot(tier_nodes, node_states[N_MEMORY], tier_nodes); + + /* + * Find all the nodes in the memory tier node list of same best distance. + * add them to the preferred mask. We randomly select between nodes + * in the preferred mask when allocating pages during demotion. + */ + do { + target = find_next_best_node(node, &tier_nodes); + if (target == NUMA_NO_NODE) + break; + + distance = node_distance(node, target); + if (distance == best_distance || best_distance == -1) { + best_distance = distance; + node_set(target, nd->preferred); + } else { + break; + } + } while (1); + } +} + +#else +static inline void disable_all_demotion_targets(void) {} +static inline void establish_demotion_targets(void) {} +#endif /* CONFIG_MIGRATION */ + static inline void __init_node_memory_type(int node, struct memory_dev_type *memtype) { if (!node_memory_types[node].memtype) @@ -109,16 +323,6 @@ static struct memory_tier *set_node_memory_tier(int node) return memtier; } -static struct memory_tier *__node_get_memory_tier(int node) -{ - struct memory_dev_type *memtype; - - memtype = node_memory_types[node]; - if (memtype && node_isset(node, memtype->nodes)) - return memtype->memtier; - return NULL; -} - static void destroy_memory_tier(struct memory_tier *memtier) { list_del(&memtier->list); @@ -207,6 +411,7 @@ EXPORT_SYMBOL_GPL(clear_node_memory_type); static int __meminit memtier_hotplug_callback(struct notifier_block *self, unsigned long action, void *_arg) { + struct memory_tier *memtier; struct memory_notify *arg = _arg; /* @@ -219,12 +424,15 @@ static int __meminit memtier_hotplug_callback(struct notifier_block *self, switch (action) { case MEM_OFFLINE: mutex_lock(&memory_tier_lock); - clear_node_memory_tier(arg->status_change_nid); + if (clear_node_memory_tier(arg->status_change_nid)) + establish_demotion_targets(); mutex_unlock(&memory_tier_lock); break; case MEM_ONLINE: mutex_lock(&memory_tier_lock); - set_node_memory_tier(arg->status_change_nid); + memtier = set_node_memory_tier(arg->status_change_nid); + if (!IS_ERR(memtier)) + establish_demotion_targets(); mutex_unlock(&memory_tier_lock); break; } @@ -237,6 +445,11 @@ static int __init memory_tier_init(void) int node; struct memory_tier *memtier; +#ifdef CONFIG_MIGRATION + node_demotion = kcalloc(nr_node_ids, sizeof(struct demotion_nodes), + GFP_KERNEL); + WARN_ON(!node_demotion); +#endif mutex_lock(&memory_tier_lock); /* * For now we can have 4 faster memory tiers with smaller adistance @@ -259,6 +472,7 @@ static int __init memory_tier_init(void) */ break; } + establish_demotion_targets(); mutex_unlock(&memory_tier_lock); hotplug_memory_notifier(memtier_hotplug_callback, MEMTIER_HOTPLUG_PRIO); diff --git a/mm/migrate.c b/mm/migrate.c index 30477cf4868d..2a2329bf7c1a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2198,398 +2198,4 @@ out: return 0; } #endif /* CONFIG_NUMA_BALANCING */ - -/* - * node_demotion[] example: - * - * Consider a system with two sockets. Each socket has - * three classes of memory attached: fast, medium and slow. - * Each memory class is placed in its own NUMA node. The - * CPUs are placed in the node with the "fast" memory. The - * 6 NUMA nodes (0-5) might be split among the sockets like - * this: - * - * Socket A: 0, 1, 2 - * Socket B: 3, 4, 5 - * - * When Node 0 fills up, its memory should be migrated to - * Node 1. When Node 1 fills up, it should be migrated to - * Node 2. The migration path start on the nodes with the - * processors (since allocations default to this node) and - * fast memory, progress through medium and end with the - * slow memory: - * - * 0 -> 1 -> 2 -> stop - * 3 -> 4 -> 5 -> stop - * - * This is represented in the node_demotion[] like this: - * - * { nr=1, nodes[0]=1 }, // Node 0 migrates to 1 - * { nr=1, nodes[0]=2 }, // Node 1 migrates to 2 - * { nr=0, nodes[0]=-1 }, // Node 2 does not migrate - * { nr=1, nodes[0]=4 }, // Node 3 migrates to 4 - * { nr=1, nodes[0]=5 }, // Node 4 migrates to 5 - * { nr=0, nodes[0]=-1 }, // Node 5 does not migrate - * - * Moreover some systems may have multiple slow memory nodes. - * Suppose a system has one socket with 3 memory nodes, node 0 - * is fast memory type, and node 1/2 both are slow memory - * type, and the distance between fast memory node and slow - * memory node is same. So the migration path should be: - * - * 0 -> 1/2 -> stop - * - * This is represented in the node_demotion[] like this: - * { nr=2, {nodes[0]=1, nodes[1]=2} }, // Node 0 migrates to node 1 and node 2 - * { nr=0, nodes[0]=-1, }, // Node 1 dose not migrate - * { nr=0, nodes[0]=-1, }, // Node 2 does not migrate - */ - -/* - * Writes to this array occur without locking. Cycles are - * not allowed: Node X demotes to Y which demotes to X... - * - * If multiple reads are performed, a single rcu_read_lock() - * must be held over all reads to ensure that no cycles are - * observed. - */ -#define DEFAULT_DEMOTION_TARGET_NODES 15 - -#if MAX_NUMNODES < DEFAULT_DEMOTION_TARGET_NODES -#define DEMOTION_TARGET_NODES (MAX_NUMNODES - 1) -#else -#define DEMOTION_TARGET_NODES DEFAULT_DEMOTION_TARGET_NODES -#endif - -struct demotion_nodes { - unsigned short nr; - short nodes[DEMOTION_TARGET_NODES]; -}; - -static struct demotion_nodes *node_demotion __read_mostly; - -/** - * next_demotion_node() - Get the next node in the demotion path - * @node: The starting node to lookup the next node - * - * Return: node id for next memory node in the demotion path hierarchy - * from @node; NUMA_NO_NODE if @node is terminal. This does not keep - * @node online or guarantee that it *continues* to be the next demotion - * target. - */ -int next_demotion_node(int node) -{ - struct demotion_nodes *nd; - unsigned short target_nr, index; - int target; - - if (!node_demotion) - return NUMA_NO_NODE; - - nd = &node_demotion[node]; - - /* - * node_demotion[] is updated without excluding this - * function from running. RCU doesn't provide any - * compiler barriers, so the READ_ONCE() is required - * to avoid compiler reordering or read merging. - * - * Make sure to use RCU over entire code blocks if - * node_demotion[] reads need to be consistent. - */ - rcu_read_lock(); - target_nr = READ_ONCE(nd->nr); - - switch (target_nr) { - case 0: - target = NUMA_NO_NODE; - goto out; - case 1: - index = 0; - break; - default: - /* - * If there are multiple target nodes, just select one - * target node randomly. - * - * In addition, we can also use round-robin to select - * target node, but we should introduce another variable - * for node_demotion[] to record last selected target node, - * that may cause cache ping-pong due to the changing of - * last target node. Or introducing per-cpu data to avoid - * caching issue, which seems more complicated. So selecting - * target node randomly seems better until now. - */ - index = get_random_int() % target_nr; - break; - } - - target = READ_ONCE(nd->nodes[index]); - -out: - rcu_read_unlock(); - return target; -} - -/* Disable reclaim-based migration. */ -static void __disable_all_migrate_targets(void) -{ - int node, i; - - if (!node_demotion) - return; - - for_each_online_node(node) { - node_demotion[node].nr = 0; - for (i = 0; i < DEMOTION_TARGET_NODES; i++) - node_demotion[node].nodes[i] = NUMA_NO_NODE; - } -} - -static void disable_all_migrate_targets(void) -{ - __disable_all_migrate_targets(); - - /* - * Ensure that the "disable" is visible across the system. - * Readers will see either a combination of before+disable - * state or disable+after. They will never see before and - * after state together. - * - * The before+after state together might have cycles and - * could cause readers to do things like loop until this - * function finishes. This ensures they can only see a - * single "bad" read and would, for instance, only loop - * once. - */ - synchronize_rcu(); -} - -/* - * Find an automatic demotion target for 'node'. - * Failing here is OK. It might just indicate - * being at the end of a chain. - */ -static int establish_migrate_target(int node, nodemask_t *used, - int best_distance) -{ - int migration_target, index, val; - struct demotion_nodes *nd; - - if (!node_demotion) - return NUMA_NO_NODE; - - nd = &node_demotion[node]; - - migration_target = find_next_best_node(node, used); - if (migration_target == NUMA_NO_NODE) - return NUMA_NO_NODE; - - /* - * If the node has been set a migration target node before, - * which means it's the best distance between them. Still - * check if this node can be demoted to other target nodes - * if they have a same best distance. - */ - if (best_distance != -1) { - val = node_distance(node, migration_target); - if (val > best_distance) - goto out_clear; - } - - index = nd->nr; - if (WARN_ONCE(index >= DEMOTION_TARGET_NODES, - "Exceeds maximum demotion target nodes\n")) - goto out_clear; - - nd->nodes[index] = migration_target; - nd->nr++; - - return migration_target; -out_clear: - node_clear(migration_target, *used); - return NUMA_NO_NODE; -} - -/* - * When memory fills up on a node, memory contents can be - * automatically migrated to another node instead of - * discarded at reclaim. - * - * Establish a "migration path" which will start at nodes - * with CPUs and will follow the priorities used to build the - * page allocator zonelists. - * - * The difference here is that cycles must be avoided. If - * node0 migrates to node1, then neither node1, nor anything - * node1 migrates to can migrate to node0. Also one node can - * be migrated to multiple nodes if the target nodes all have - * a same best-distance against the source node. - * - * This function can run simultaneously with readers of - * node_demotion[]. However, it can not run simultaneously - * with itself. Exclusion is provided by memory hotplug events - * being single-threaded. - */ -static void __set_migration_target_nodes(void) -{ - nodemask_t next_pass; - nodemask_t this_pass; - nodemask_t used_targets = NODE_MASK_NONE; - int node, best_distance; - - /* - * Avoid any oddities like cycles that could occur - * from changes in the topology. This will leave - * a momentary gap when migration is disabled. - */ - disable_all_migrate_targets(); - - /* - * Allocations go close to CPUs, first. Assume that - * the migration path starts at the nodes with CPUs. - */ - next_pass = node_states[N_CPU]; -again: - this_pass = next_pass; - next_pass = NODE_MASK_NONE; - /* - * To avoid cycles in the migration "graph", ensure - * that migration sources are not future targets by - * setting them in 'used_targets'. Do this only - * once per pass so that multiple source nodes can - * share a target node. - * - * 'used_targets' will become unavailable in future - * passes. This limits some opportunities for - * multiple source nodes to share a destination. - */ - nodes_or(used_targets, used_targets, this_pass); - - for_each_node_mask(node, this_pass) { - best_distance = -1; - - /* - * Try to set up the migration path for the node, and the target - * migration nodes can be multiple, so doing a loop to find all - * the target nodes if they all have a best node distance. - */ - do { - int target_node = - establish_migrate_target(node, &used_targets, - best_distance); - - if (target_node == NUMA_NO_NODE) - break; - - if (best_distance == -1) - best_distance = node_distance(node, target_node); - - /* - * Visit targets from this pass in the next pass. - * Eventually, every node will have been part of - * a pass, and will become set in 'used_targets'. - */ - node_set(target_node, next_pass); - } while (1); - } - /* - * 'next_pass' contains nodes which became migration - * targets in this pass. Make additional passes until - * no more migrations targets are available. - */ - if (!nodes_empty(next_pass)) - goto again; -} - -/* - * For callers that do not hold get_online_mems() already. - */ -void set_migration_target_nodes(void) -{ - get_online_mems(); - __set_migration_target_nodes(); - put_online_mems(); -} - -/* - * This leaves migrate-on-reclaim transiently disabled between - * the MEM_GOING_OFFLINE and MEM_OFFLINE events. This runs - * whether reclaim-based migration is enabled or not, which - * ensures that the user can turn reclaim-based migration at - * any time without needing to recalculate migration targets. - * - * These callbacks already hold get_online_mems(). That is why - * __set_migration_target_nodes() can be used as opposed to - * set_migration_target_nodes(). - */ -#ifdef CONFIG_MEMORY_HOTPLUG -static int __meminit migrate_on_reclaim_callback(struct notifier_block *self, - unsigned long action, void *_arg) -{ - struct memory_notify *arg = _arg; - - /* - * Only update the node migration order when a node is - * changing status, like online->offline. This avoids - * the overhead of synchronize_rcu() in most cases. - */ - if (arg->status_change_nid < 0) - return notifier_from_errno(0); - - switch (action) { - case MEM_GOING_OFFLINE: - /* - * Make sure there are not transient states where - * an offline node is a migration target. This - * will leave migration disabled until the offline - * completes and the MEM_OFFLINE case below runs. - */ - disable_all_migrate_targets(); - break; - case MEM_OFFLINE: - case MEM_ONLINE: - /* - * Recalculate the target nodes once the node - * reaches its final state (online or offline). - */ - __set_migration_target_nodes(); - break; - case MEM_CANCEL_OFFLINE: - /* - * MEM_GOING_OFFLINE disabled all the migration - * targets. Reenable them. - */ - __set_migration_target_nodes(); - break; - case MEM_GOING_ONLINE: - case MEM_CANCEL_ONLINE: - break; - } - - return notifier_from_errno(0); -} -#endif - -void __init migrate_on_reclaim_init(void) -{ - node_demotion = kcalloc(nr_node_ids, - sizeof(struct demotion_nodes), - GFP_KERNEL); - WARN_ON(!node_demotion); -#ifdef CONFIG_MEMORY_HOTPLUG - hotplug_memory_notifier(migrate_on_reclaim_callback, 100); -#endif - /* - * At this point, all numa nodes with memory/CPus have their state - * properly set, so we can build the demotion order now. - * Let us hold the cpu_hotplug lock just, as we could possibily have - * CPU hotplug events during boot. - */ - cpus_read_lock(); - set_migration_target_nodes(); - cpus_read_unlock(); -} #endif /* CONFIG_NUMA */ - - diff --git a/mm/vmstat.c b/mm/vmstat.c index c109167a669c..779f1ea6e8ea 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -28,7 +28,6 @@ #include #include #include -#include #include "internal.h" @@ -2068,7 +2067,6 @@ static int vmstat_cpu_online(unsigned int cpu) if (!node_state(cpu_to_node(cpu), N_CPU)) { node_set_state(cpu_to_node(cpu), N_CPU); - set_migration_target_nodes(); } return 0; @@ -2093,7 +2091,6 @@ static int vmstat_cpu_dead(unsigned int cpu) return 0; node_clear_state(node, N_CPU); - set_migration_target_nodes(); return 0; } @@ -2126,7 +2123,6 @@ void __init init_mm_internals(void) start_shepherd_timer(); #endif - migrate_on_reclaim_init(); #ifdef CONFIG_PROC_FS proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op); -- cgit v1.2.3-70-g09d2 From 7964cf8caa4dfa42c4149f3833d3878713cda3dc Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:51 +0000 Subject: mm: remove vmacache By using the maple tree and the maple tree state, the vmacache is no longer beneficial and is complicating the VMA code. Remove the vmacache to reduce the work in keeping it up to date and code complexity. Link: https://lkml.kernel.org/r/20220906194824.2110408-26-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Acked-by: Vlastimil Babka Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: "Matthew Wilcox (Oracle)" Cc: SeongJae Park Cc: Sven Schnelle Cc: Will Deacon Signed-off-by: Andrew Morton --- fs/exec.c | 3 -- fs/proc/task_mmu.c | 1 - include/linux/mm_types.h | 1 - include/linux/mm_types_task.h | 12 ----- include/linux/sched.h | 1 - include/linux/vm_event_item.h | 4 -- include/linux/vmacache.h | 28 ---------- include/linux/vmstat.h | 6 --- kernel/debug/debug_core.c | 12 ----- kernel/fork.c | 5 -- lib/Kconfig.debug | 8 --- mm/Makefile | 2 +- mm/debug.c | 4 +- mm/mmap.c | 31 +---------- mm/nommu.c | 37 ++----------- mm/vmacache.c | 117 ------------------------------------------ mm/vmstat.c | 4 -- 17 files changed, 9 insertions(+), 267 deletions(-) delete mode 100644 include/linux/vmacache.h delete mode 100644 mm/vmacache.c (limited to 'mm/vmstat.c') diff --git a/fs/exec.c b/fs/exec.c index 507a317d54db..2b919b30dc97 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include #include @@ -1027,8 +1026,6 @@ static int exec_mmap(struct mm_struct *mm) activate_mm(active_mm, mm); if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); - tsk->mm->vmacache_seqnum = 0; - vmacache_flush(tsk); task_unlock(tsk); lru_gen_use_mm(mm); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index db2f3a2946a0..9f70bc1c2766 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include #include #include #include diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ac747273c4d6..4541b74b1bdb 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -475,7 +475,6 @@ struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct maple_tree mm_mt; - u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index c1bc6731125c..0bb4b6da9993 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -24,18 +24,6 @@ IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) #define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) -/* - * The per task VMA cache array: - */ -#define VMACACHE_BITS 2 -#define VMACACHE_SIZE (1U << VMACACHE_BITS) -#define VMACACHE_MASK (VMACACHE_SIZE - 1) - -struct vmacache { - u64 seqnum; - struct vm_area_struct *vmas[VMACACHE_SIZE]; -}; - /* * When updating this, please also update struct resident_page_types[] in * kernel/fork.c diff --git a/include/linux/sched.h b/include/linux/sched.h index a2dcfb91df03..fbac3c19fe35 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -861,7 +861,6 @@ struct task_struct { struct mm_struct *active_mm; /* Per-thread vma caching: */ - struct vmacache vmacache; #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index f3fc36cd2276..3518dba1e02f 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -129,10 +129,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, #endif /* CONFIG_DEBUG_TLBFLUSH */ -#ifdef CONFIG_DEBUG_VM_VMACACHE - VMACACHE_FIND_CALLS, - VMACACHE_FIND_HITS, -#endif #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h deleted file mode 100644 index 6fce268a4588..000000000000 --- a/include/linux/vmacache.h +++ /dev/null @@ -1,28 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_VMACACHE_H -#define __LINUX_VMACACHE_H - -#include -#include - -static inline void vmacache_flush(struct task_struct *tsk) -{ - memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); -} - -extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); -extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, - unsigned long addr); - -#ifndef CONFIG_MMU -extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, - unsigned long start, - unsigned long end); -#endif - -static inline void vmacache_invalidate(struct mm_struct *mm) -{ - mm->vmacache_seqnum++; -} - -#endif /* __LINUX_VMACACHE_H */ diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index bfe38869498d..19cf5b6892ce 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -125,12 +125,6 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif -#ifdef CONFIG_DEBUG_VM_VMACACHE -#define count_vm_vmacache_event(x) count_vm_event(x) -#else -#define count_vm_vmacache_event(x) do {} while (0) -#endif - #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 7beceb447211..d5e9ccde3ab8 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -50,7 +50,6 @@ #include #include #include -#include #include #include #include @@ -283,17 +282,6 @@ static void kgdb_flush_swbreak_addr(unsigned long addr) if (!CACHE_FLUSH_IS_SAFE) return; - if (current->mm) { - int i; - - for (i = 0; i < VMACACHE_SIZE; i++) { - if (!current->vmacache.vmas[i]) - continue; - flush_cache_range(current->vmacache.vmas[i], - addr, addr + BREAK_INSTR_SIZE); - } - } - /* Force flush instruction cache if it was outside the mm */ flush_icache_range(addr, addr + BREAK_INSTR_SIZE); } diff --git a/kernel/fork.c b/kernel/fork.c index 5f81c009bb20..430f63cd7a37 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -43,7 +43,6 @@ #include #include #include -#include #include #include #include @@ -1128,7 +1127,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm->mmap = NULL; mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); - mm->vmacache_seqnum = 0; atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); @@ -1585,9 +1583,6 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) if (!oldmm) return 0; - /* initialize the new vmacache entries */ - vmacache_flush(tsk); - if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2becf60995e1..6d1544d9201e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -812,14 +812,6 @@ config DEBUG_VM If unsure, say N. -config DEBUG_VM_VMACACHE - bool "Debug VMA caching" - depends on DEBUG_VM - help - Enable this to turn on VMA caching debug information. Doing so - can cause significant overhead, so only enable it in non-production - environments. - config DEBUG_VM_MAPLE_TREE bool "Debug VM maple trees" depends on DEBUG_VM diff --git a/mm/Makefile b/mm/Makefile index 488f604e77e0..a731d1decbb1 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -52,7 +52,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o percpu.o slab_common.o \ - compaction.o vmacache.o \ + compaction.o \ interval_tree.o list_lru.o workingset.o \ debug.o gup.o mmap_lock.o $(mmu-y) diff --git a/mm/debug.c b/mm/debug.c index bef329bf28f0..2d625ca0e326 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -155,7 +155,7 @@ EXPORT_SYMBOL(dump_vma); void dump_mm(const struct mm_struct *mm) { - pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n" + pr_emerg("mm %px mmap %px task_size %lu\n" #ifdef CONFIG_MMU "get_unmapped_area %px\n" #endif @@ -183,7 +183,7 @@ void dump_mm(const struct mm_struct *mm) "tlb_flush_pending %d\n" "def_flags: %#lx(%pGv)\n", - mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size, + mm, mm->mmap, mm->task_size, #ifdef CONFIG_MMU mm->get_unmapped_area, #endif diff --git a/mm/mmap.c b/mm/mmap.c index 7a1adc916957..7872642e8993 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -680,9 +679,6 @@ inline int vma_expand(struct ma_state *mas, struct vm_area_struct *vma, /* Remove from mm linked list - also updates highest_vm_end */ __vma_unlink_list(mm, next); - /* Kill the cache */ - vmacache_invalidate(mm); - if (file) __remove_shared_vm_struct(next, file, mapping); @@ -923,8 +919,6 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, __vma_unlink_list(mm, next); if (remove_next == 2) __vma_unlink_list(mm, next_next); - /* Kill the cache */ - vmacache_invalidate(mm); if (file) { __remove_shared_vm_struct(next, file, mapping); @@ -2233,19 +2227,10 @@ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr) { - struct vm_area_struct *vma; unsigned long index = start_addr; mmap_assert_locked(mm); - /* Check the cache first. */ - vma = vmacache_find(mm, start_addr); - if (likely(vma)) - return vma; - - vma = mt_find(&mm->mm_mt, &index, end_addr - 1); - if (vma) - vmacache_update(start_addr, vma); - return vma; + return mt_find(&mm->mm_mt, &index, end_addr - 1); } EXPORT_SYMBOL(find_vma_intersection); @@ -2259,19 +2244,10 @@ EXPORT_SYMBOL(find_vma_intersection); */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma; unsigned long index = addr; mmap_assert_locked(mm); - /* Check the cache first. */ - vma = vmacache_find(mm, addr); - if (likely(vma)) - return vma; - - vma = mt_find(&mm->mm_mt, &index, ULONG_MAX); - if (vma) - vmacache_update(addr, vma); - return vma; + return mt_find(&mm->mm_mt, &index, ULONG_MAX); } EXPORT_SYMBOL(find_vma); @@ -2660,9 +2636,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct ma_state *mas, mm->highest_vm_end = prev ? vm_end_gap(prev) : 0; tail_vma->vm_next = NULL; - /* Kill the cache */ - vmacache_invalidate(mm); - /* * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or * VM_GROWSUP VMA. Such VMAs can change their size under diff --git a/mm/nommu.c b/mm/nommu.c index 2702790d05d3..265a444a2cc2 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -598,23 +597,12 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) */ static void delete_vma_from_mm(struct vm_area_struct *vma) { - int i; - struct address_space *mapping; - struct mm_struct *mm = vma->vm_mm; - struct task_struct *curr = current; MA_STATE(mas, &vma->vm_mm->mm_mt, 0, 0); - mm->map_count--; - for (i = 0; i < VMACACHE_SIZE; i++) { - /* if the vma is cached, invalidate the entire cache */ - if (curr->vmacache.vmas[i] == vma) { - vmacache_invalidate(mm); - break; - } - } - + vma->vm_mm->map_count--; /* remove the VMA from the mapping */ if (vma->vm_file) { + struct address_space *mapping; mapping = vma->vm_file->f_mapping; i_mmap_lock_write(mapping); @@ -626,7 +614,7 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) /* remove from the MM's tree and list */ vma_mas_remove(vma, &mas); - __vma_unlink_list(mm, vma); + __vma_unlink_list(vma->vm_mm, vma); } /* @@ -659,20 +647,9 @@ EXPORT_SYMBOL(find_vma_intersection); */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma; MA_STATE(mas, &mm->mm_mt, addr, addr); - /* check the cache first */ - vma = vmacache_find(mm, addr); - if (likely(vma)) - return vma; - - vma = mas_walk(&mas); - - if (vma) - vmacache_update(addr, vma); - - return vma; + return mas_walk(&mas); } EXPORT_SYMBOL(find_vma); @@ -706,11 +683,6 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, unsigned long end = addr + len; MA_STATE(mas, &mm->mm_mt, addr, addr); - /* check the cache first */ - vma = vmacache_find_exact(mm, addr, end); - if (vma) - return vma; - vma = mas_walk(&mas); if (!vma) return NULL; @@ -719,7 +691,6 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, if (vma->vm_end != end) return NULL; - vmacache_update(addr, vma); return vma; } diff --git a/mm/vmacache.c b/mm/vmacache.c deleted file mode 100644 index 01a6e6688ec1..000000000000 --- a/mm/vmacache.c +++ /dev/null @@ -1,117 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2014 Davidlohr Bueso. - */ -#include -#include -#include -#include - -/* - * Hash based on the pmd of addr if configured with MMU, which provides a good - * hit rate for workloads with spatial locality. Otherwise, use pages. - */ -#ifdef CONFIG_MMU -#define VMACACHE_SHIFT PMD_SHIFT -#else -#define VMACACHE_SHIFT PAGE_SHIFT -#endif -#define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK) - -/* - * This task may be accessing a foreign mm via (for example) - * get_user_pages()->find_vma(). The vmacache is task-local and this - * task's vmacache pertains to a different mm (ie, its own). There is - * nothing we can do here. - * - * Also handle the case where a kernel thread has adopted this mm via - * kthread_use_mm(). That kernel thread's vmacache is not applicable to this mm. - */ -static inline bool vmacache_valid_mm(struct mm_struct *mm) -{ - return current->mm == mm && !(current->flags & PF_KTHREAD); -} - -void vmacache_update(unsigned long addr, struct vm_area_struct *newvma) -{ - if (vmacache_valid_mm(newvma->vm_mm)) - current->vmacache.vmas[VMACACHE_HASH(addr)] = newvma; -} - -static bool vmacache_valid(struct mm_struct *mm) -{ - struct task_struct *curr; - - if (!vmacache_valid_mm(mm)) - return false; - - curr = current; - if (mm->vmacache_seqnum != curr->vmacache.seqnum) { - /* - * First attempt will always be invalid, initialize - * the new cache for this task here. - */ - curr->vmacache.seqnum = mm->vmacache_seqnum; - vmacache_flush(curr); - return false; - } - return true; -} - -struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) -{ - int idx = VMACACHE_HASH(addr); - int i; - - count_vm_vmacache_event(VMACACHE_FIND_CALLS); - - if (!vmacache_valid(mm)) - return NULL; - - for (i = 0; i < VMACACHE_SIZE; i++) { - struct vm_area_struct *vma = current->vmacache.vmas[idx]; - - if (vma) { -#ifdef CONFIG_DEBUG_VM_VMACACHE - if (WARN_ON_ONCE(vma->vm_mm != mm)) - break; -#endif - if (vma->vm_start <= addr && vma->vm_end > addr) { - count_vm_vmacache_event(VMACACHE_FIND_HITS); - return vma; - } - } - if (++idx == VMACACHE_SIZE) - idx = 0; - } - - return NULL; -} - -#ifndef CONFIG_MMU -struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, - unsigned long start, - unsigned long end) -{ - int idx = VMACACHE_HASH(start); - int i; - - count_vm_vmacache_event(VMACACHE_FIND_CALLS); - - if (!vmacache_valid(mm)) - return NULL; - - for (i = 0; i < VMACACHE_SIZE; i++) { - struct vm_area_struct *vma = current->vmacache.vmas[idx]; - - if (vma && vma->vm_start == start && vma->vm_end == end) { - count_vm_vmacache_event(VMACACHE_FIND_HITS); - return vma; - } - if (++idx == VMACACHE_SIZE) - idx = 0; - } - - return NULL; -} -#endif diff --git a/mm/vmstat.c b/mm/vmstat.c index 779f1ea6e8ea..bd8040f25c27 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1389,10 +1389,6 @@ const char * const vmstat_text[] = { "nr_tlb_local_flush_one", #endif /* CONFIG_DEBUG_TLBFLUSH */ -#ifdef CONFIG_DEBUG_VM_VMACACHE - "vmacache_find_calls", - "vmacache_find_hits", -#endif #ifdef CONFIG_SWAP "swap_ra", "swap_ra_hit", -- cgit v1.2.3-70-g09d2