diff options
author | Jakub Kicinski <kuba@kernel.org> | 2024-03-22 02:14:13 +0300 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2024-03-22 02:15:08 +0300 |
commit | 537c2e91d3549e5d6020bb0576cf9b54a845255f (patch) | |
tree | c09e8a1b7d733cde19b0c72678c28fb2bc97ff6b /mm/vmalloc.c | |
parent | 237bb5f7f7f55ec5f773469a974c61a49c298625 (diff) | |
parent | cba9ffdb9913dfe6be29f049ce920ce451ce7cc4 (diff) | |
download | linux-537c2e91d3549e5d6020bb0576cf9b54a845255f.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'mm/vmalloc.c')
-rw-r--r-- | mm/vmalloc.c | 1080 |
1 files changed, 813 insertions, 267 deletions
diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 1e36322d83d8..22aa63f4ef63 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -800,17 +800,9 @@ EXPORT_SYMBOL(vmalloc_to_pfn); #define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0 -static DEFINE_SPINLOCK(vmap_area_lock); static DEFINE_SPINLOCK(free_vmap_area_lock); -/* Export for kexec only */ -LIST_HEAD(vmap_area_list); -static struct rb_root vmap_area_root = RB_ROOT; static bool vmap_initialized __read_mostly; -static struct rb_root purge_vmap_area_root = RB_ROOT; -static LIST_HEAD(purge_vmap_area_list); -static DEFINE_SPINLOCK(purge_vmap_area_lock); - /* * This kmem_cache is used for vmap_area objects. Instead of * allocating from slab we reuse an object from this cache to @@ -844,6 +836,129 @@ static struct rb_root free_vmap_area_root = RB_ROOT; */ static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node); +/* + * This structure defines a single, solid model where a list and + * rb-tree are part of one entity protected by the lock. Nodes are + * sorted in ascending order, thus for O(1) access to left/right + * neighbors a list is used as well as for sequential traversal. + */ +struct rb_list { + struct rb_root root; + struct list_head head; + spinlock_t lock; +}; + +/* + * A fast size storage contains VAs up to 1M size. A pool consists + * of linked between each other ready to go VAs of certain sizes. + * An index in the pool-array corresponds to number of pages + 1. + */ +#define MAX_VA_SIZE_PAGES 256 + +struct vmap_pool { + struct list_head head; + unsigned long len; +}; + +/* + * An effective vmap-node logic. Users make use of nodes instead + * of a global heap. It allows to balance an access and mitigate + * contention. + */ +static struct vmap_node { + /* Simple size segregated storage. */ + struct vmap_pool pool[MAX_VA_SIZE_PAGES]; + spinlock_t pool_lock; + bool skip_populate; + + /* Bookkeeping data of this node. */ + struct rb_list busy; + struct rb_list lazy; + + /* + * Ready-to-free areas. + */ + struct list_head purge_list; + struct work_struct purge_work; + unsigned long nr_purged; +} single; + +/* + * Initial setup consists of one single node, i.e. a balancing + * is fully disabled. Later on, after vmap is initialized these + * parameters are updated based on a system capacity. + */ +static struct vmap_node *vmap_nodes = &single; +static __read_mostly unsigned int nr_vmap_nodes = 1; +static __read_mostly unsigned int vmap_zone_size = 1; + +static inline unsigned int +addr_to_node_id(unsigned long addr) +{ + return (addr / vmap_zone_size) % nr_vmap_nodes; +} + +static inline struct vmap_node * +addr_to_node(unsigned long addr) +{ + return &vmap_nodes[addr_to_node_id(addr)]; +} + +static inline struct vmap_node * +id_to_node(unsigned int id) +{ + return &vmap_nodes[id % nr_vmap_nodes]; +} + +/* + * We use the value 0 to represent "no node", that is why + * an encoded value will be the node-id incremented by 1. + * It is always greater then 0. A valid node_id which can + * be encoded is [0:nr_vmap_nodes - 1]. If a passed node_id + * is not valid 0 is returned. + */ +static unsigned int +encode_vn_id(unsigned int node_id) +{ + /* Can store U8_MAX [0:254] nodes. */ + if (node_id < nr_vmap_nodes) + return (node_id + 1) << BITS_PER_BYTE; + + /* Warn and no node encoded. */ + WARN_ONCE(1, "Encode wrong node id (%u)\n", node_id); + return 0; +} + +/* + * Returns an encoded node-id, the valid range is within + * [0:nr_vmap_nodes-1] values. Otherwise nr_vmap_nodes is + * returned if extracted data is wrong. + */ +static unsigned int +decode_vn_id(unsigned int val) +{ + unsigned int node_id = (val >> BITS_PER_BYTE) - 1; + + /* Can store U8_MAX [0:254] nodes. */ + if (node_id < nr_vmap_nodes) + return node_id; + + /* If it was _not_ zero, warn. */ + WARN_ONCE(node_id != UINT_MAX, + "Decode wrong node id (%d)\n", node_id); + + return nr_vmap_nodes; +} + +static bool +is_vn_id_valid(unsigned int node_id) +{ + if (node_id < nr_vmap_nodes) + return true; + + return false; +} + static __always_inline unsigned long va_size(struct vmap_area *va) { @@ -875,10 +990,11 @@ unsigned long vmalloc_nr_pages(void) } /* Look up the first VA which satisfies addr < va_end, NULL if none. */ -static struct vmap_area *find_vmap_area_exceed_addr(unsigned long addr) +static struct vmap_area * +__find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root) { struct vmap_area *va = NULL; - struct rb_node *n = vmap_area_root.rb_node; + struct rb_node *n = root->rb_node; addr = (unsigned long)kasan_reset_tag((void *)addr); @@ -899,6 +1015,41 @@ static struct vmap_area *find_vmap_area_exceed_addr(unsigned long addr) return va; } +/* + * Returns a node where a first VA, that satisfies addr < va_end, resides. + * If success, a node is locked. A user is responsible to unlock it when a + * VA is no longer needed to be accessed. + * + * Returns NULL if nothing found. + */ +static struct vmap_node * +find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va) +{ + struct vmap_node *vn, *va_node = NULL; + struct vmap_area *va_lowest; + int i; + + for (i = 0; i < nr_vmap_nodes; i++) { + vn = &vmap_nodes[i]; + + spin_lock(&vn->busy.lock); + va_lowest = __find_vmap_area_exceed_addr(addr, &vn->busy.root); + if (va_lowest) { + if (!va_node || va_lowest->va_start < (*va)->va_start) { + if (va_node) + spin_unlock(&va_node->busy.lock); + + *va = va_lowest; + va_node = vn; + continue; + } + } + spin_unlock(&vn->busy.lock); + } + + return va_node; +} + static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) { struct rb_node *n = root->rb_node; @@ -1454,9 +1605,9 @@ classify_va_fit_type(struct vmap_area *va, } static __always_inline int -adjust_va_to_fit_type(struct rb_root *root, struct list_head *head, - struct vmap_area *va, unsigned long nva_start_addr, - unsigned long size) +va_clip(struct rb_root *root, struct list_head *head, + struct vmap_area *va, unsigned long nva_start_addr, + unsigned long size) { struct vmap_area *lva = NULL; enum fit_type type = classify_va_fit_type(va, nva_start_addr, size); @@ -1553,6 +1704,32 @@ adjust_va_to_fit_type(struct rb_root *root, struct list_head *head, return 0; } +static unsigned long +va_alloc(struct vmap_area *va, + struct rb_root *root, struct list_head *head, + unsigned long size, unsigned long align, + unsigned long vstart, unsigned long vend) +{ + unsigned long nva_start_addr; + int ret; + + if (va->va_start > vstart) + nva_start_addr = ALIGN(va->va_start, align); + else + nva_start_addr = ALIGN(vstart, align); + + /* Check the "vend" restriction. */ + if (nva_start_addr + size > vend) + return vend; + + /* Update the free vmap_area. */ + ret = va_clip(root, head, va, nva_start_addr, size); + if (WARN_ON_ONCE(ret)) + return vend; + + return nva_start_addr; +} + /* * Returns a start address of the newly allocated area, if success. * Otherwise a vend is returned that indicates failure. @@ -1565,7 +1742,6 @@ __alloc_vmap_area(struct rb_root *root, struct list_head *head, bool adjust_search_size = true; unsigned long nva_start_addr; struct vmap_area *va; - int ret; /* * Do not adjust when: @@ -1583,18 +1759,8 @@ __alloc_vmap_area(struct rb_root *root, struct list_head *head, if (unlikely(!va)) return vend; - if (va->va_start > vstart) - nva_start_addr = ALIGN(va->va_start, align); - else - nva_start_addr = ALIGN(vstart, align); - - /* Check the "vend" restriction. */ - if (nva_start_addr + size > vend) - return vend; - - /* Update the free vmap_area. */ - ret = adjust_va_to_fit_type(root, head, va, nva_start_addr, size); - if (WARN_ON_ONCE(ret)) + nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend); + if (nva_start_addr == vend) return vend; #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK @@ -1609,12 +1775,14 @@ __alloc_vmap_area(struct rb_root *root, struct list_head *head, */ static void free_vmap_area(struct vmap_area *va) { + struct vmap_node *vn = addr_to_node(va->va_start); + /* * Remove from the busy tree/list. */ - spin_lock(&vmap_area_lock); - unlink_va(va, &vmap_area_root); - spin_unlock(&vmap_area_lock); + spin_lock(&vn->busy.lock); + unlink_va(va, &vn->busy.root); + spin_unlock(&vn->busy.lock); /* * Insert/Merge it back to the free tree/list. @@ -1647,6 +1815,104 @@ preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) kmem_cache_free(vmap_area_cachep, va); } +static struct vmap_pool * +size_to_va_pool(struct vmap_node *vn, unsigned long size) +{ + unsigned int idx = (size - 1) / PAGE_SIZE; + + if (idx < MAX_VA_SIZE_PAGES) + return &vn->pool[idx]; + + return NULL; +} + +static bool +node_pool_add_va(struct vmap_node *n, struct vmap_area *va) +{ + struct vmap_pool *vp; + + vp = size_to_va_pool(n, va_size(va)); + if (!vp) + return false; + + spin_lock(&n->pool_lock); + list_add(&va->list, &vp->head); + WRITE_ONCE(vp->len, vp->len + 1); + spin_unlock(&n->pool_lock); + + return true; +} + +static struct vmap_area * +node_pool_del_va(struct vmap_node *vn, unsigned long size, + unsigned long align, unsigned long vstart, + unsigned long vend) +{ + struct vmap_area *va = NULL; + struct vmap_pool *vp; + int err = 0; + + vp = size_to_va_pool(vn, size); + if (!vp || list_empty(&vp->head)) + return NULL; + + spin_lock(&vn->pool_lock); + if (!list_empty(&vp->head)) { + va = list_first_entry(&vp->head, struct vmap_area, list); + + if (IS_ALIGNED(va->va_start, align)) { + /* + * Do some sanity check and emit a warning + * if one of below checks detects an error. + */ + err |= (va_size(va) != size); + err |= (va->va_start < vstart); + err |= (va->va_end > vend); + + if (!WARN_ON_ONCE(err)) { + list_del_init(&va->list); + WRITE_ONCE(vp->len, vp->len - 1); + } else { + va = NULL; + } + } else { + list_move_tail(&va->list, &vp->head); + va = NULL; + } + } + spin_unlock(&vn->pool_lock); + + return va; +} + +static struct vmap_area * +node_alloc(unsigned long size, unsigned long align, + unsigned long vstart, unsigned long vend, + unsigned long *addr, unsigned int *vn_id) +{ + struct vmap_area *va; + + *vn_id = 0; + *addr = vend; + + /* + * Fallback to a global heap if not vmalloc or there + * is only one node. + */ + if (vstart != VMALLOC_START || vend != VMALLOC_END || + nr_vmap_nodes == 1) + return NULL; + + *vn_id = raw_smp_processor_id() % nr_vmap_nodes; + va = node_pool_del_va(id_to_node(*vn_id), size, align, vstart, vend); + *vn_id = encode_vn_id(*vn_id); + + if (va) + *addr = va->va_start; + + return va; +} + /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. @@ -1657,9 +1923,11 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, int node, gfp_t gfp_mask, unsigned long va_flags) { + struct vmap_node *vn; struct vmap_area *va; unsigned long freed; unsigned long addr; + unsigned int vn_id; int purged = 0; int ret; @@ -1670,23 +1938,37 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, return ERR_PTR(-EBUSY); might_sleep(); - gfp_mask = gfp_mask & GFP_RECLAIM_MASK; - - va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); - if (unlikely(!va)) - return ERR_PTR(-ENOMEM); /* - * Only scan the relevant parts containing pointers to other objects - * to avoid false negatives. + * If a VA is obtained from a global heap(if it fails here) + * it is anyway marked with this "vn_id" so it is returned + * to this pool's node later. Such way gives a possibility + * to populate pools based on users demand. + * + * On success a ready to go VA is returned. */ - kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); + va = node_alloc(size, align, vstart, vend, &addr, &vn_id); + if (!va) { + gfp_mask = gfp_mask & GFP_RECLAIM_MASK; + + va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); + if (unlikely(!va)) + return ERR_PTR(-ENOMEM); + + /* + * Only scan the relevant parts containing pointers to other objects + * to avoid false negatives. + */ + kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); + } retry: - preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); - addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list, - size, align, vstart, vend); - spin_unlock(&free_vmap_area_lock); + if (addr == vend) { + preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); + addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list, + size, align, vstart, vend); + spin_unlock(&free_vmap_area_lock); + } trace_alloc_vmap_area(addr, size, align, vstart, vend, addr == vend); @@ -1700,11 +1982,13 @@ retry: va->va_start = addr; va->va_end = addr + size; va->vm = NULL; - va->flags = va_flags; + va->flags = (va_flags | vn_id); - spin_lock(&vmap_area_lock); - insert_vmap_area(va, &vmap_area_root, &vmap_area_list); - spin_unlock(&vmap_area_lock); + vn = addr_to_node(va->va_start); + + spin_lock(&vn->busy.lock); + insert_vmap_area(va, &vn->busy.root, &vn->busy.head); + spin_unlock(&vn->busy.lock); BUG_ON(!IS_ALIGNED(va->va_start, align)); BUG_ON(va->va_start < vstart); @@ -1789,70 +2073,199 @@ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); +static cpumask_t purge_nodes; -/* - * Purges all lazily-freed vmap areas. - */ -static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) +static void +reclaim_list_global(struct list_head *head) { - unsigned long resched_threshold; - unsigned int num_purged_areas = 0; - struct list_head local_purge_list; - struct vmap_area *va, *n_va; + struct vmap_area *va, *n; - lockdep_assert_held(&vmap_purge_lock); + if (list_empty(head)) + return; - spin_lock(&purge_vmap_area_lock); - purge_vmap_area_root = RB_ROOT; - list_replace_init(&purge_vmap_area_list, &local_purge_list); - spin_unlock(&purge_vmap_area_lock); + spin_lock(&free_vmap_area_lock); + list_for_each_entry_safe(va, n, head, list) + merge_or_add_vmap_area_augment(va, + &free_vmap_area_root, &free_vmap_area_list); + spin_unlock(&free_vmap_area_lock); +} - if (unlikely(list_empty(&local_purge_list))) - goto out; +static void +decay_va_pool_node(struct vmap_node *vn, bool full_decay) +{ + struct vmap_area *va, *nva; + struct list_head decay_list; + struct rb_root decay_root; + unsigned long n_decay; + int i; - start = min(start, - list_first_entry(&local_purge_list, - struct vmap_area, list)->va_start); + decay_root = RB_ROOT; + INIT_LIST_HEAD(&decay_list); - end = max(end, - list_last_entry(&local_purge_list, - struct vmap_area, list)->va_end); + for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { + struct list_head tmp_list; - flush_tlb_kernel_range(start, end); - resched_threshold = lazy_max_pages() << 1; + if (list_empty(&vn->pool[i].head)) + continue; - spin_lock(&free_vmap_area_lock); - list_for_each_entry_safe(va, n_va, &local_purge_list, list) { - unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; - unsigned long orig_start = va->va_start; - unsigned long orig_end = va->va_end; + INIT_LIST_HEAD(&tmp_list); + + /* Detach the pool, so no-one can access it. */ + spin_lock(&vn->pool_lock); + list_replace_init(&vn->pool[i].head, &tmp_list); + spin_unlock(&vn->pool_lock); + + if (full_decay) + WRITE_ONCE(vn->pool[i].len, 0); + + /* Decay a pool by ~25% out of left objects. */ + n_decay = vn->pool[i].len >> 2; + + list_for_each_entry_safe(va, nva, &tmp_list, list) { + list_del_init(&va->list); + merge_or_add_vmap_area(va, &decay_root, &decay_list); + + if (!full_decay) { + WRITE_ONCE(vn->pool[i].len, vn->pool[i].len - 1); + + if (!--n_decay) + break; + } + } /* - * Finally insert or merge lazily-freed area. It is - * detached and there is no need to "unlink" it from - * anything. + * Attach the pool back if it has been partly decayed. + * Please note, it is supposed that nobody(other contexts) + * can populate the pool therefore a simple list replace + * operation takes place here. */ - va = merge_or_add_vmap_area_augment(va, &free_vmap_area_root, - &free_vmap_area_list); + if (!full_decay && !list_empty(&tmp_list)) { + spin_lock(&vn->pool_lock); + list_replace_init(&tmp_list, &vn->pool[i].head); + spin_unlock(&vn->pool_lock); + } + } - if (!va) - continue; + reclaim_list_global(&decay_list); +} + +static void purge_vmap_node(struct work_struct *work) +{ + struct vmap_node *vn = container_of(work, + struct vmap_node, purge_work); + struct vmap_area *va, *n_va; + LIST_HEAD(local_list); + + vn->nr_purged = 0; + + list_for_each_entry_safe(va, n_va, &vn->purge_list, list) { + unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; + unsigned long orig_start = va->va_start; + unsigned long orig_end = va->va_end; + unsigned int vn_id = decode_vn_id(va->flags); + + list_del_init(&va->list); if (is_vmalloc_or_module_addr((void *)orig_start)) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); atomic_long_sub(nr, &vmap_lazy_nr); - num_purged_areas++; + vn->nr_purged++; - if (atomic_long_read(&vmap_lazy_nr) < resched_threshold) - cond_resched_lock(&free_vmap_area_lock); + if (is_vn_id_valid(vn_id) && !vn->skip_populate) + if (node_pool_add_va(vn, va)) + continue; + + /* Go back to global. */ + list_add(&va->list, &local_list); } - spin_unlock(&free_vmap_area_lock); -out: - trace_purge_vmap_area_lazy(start, end, num_purged_areas); - return num_purged_areas > 0; + reclaim_list_global(&local_list); +} + +/* + * Purges all lazily-freed vmap areas. + */ +static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end, + bool full_pool_decay) +{ + unsigned long nr_purged_areas = 0; + unsigned int nr_purge_helpers; + unsigned int nr_purge_nodes; + struct vmap_node *vn; + int i; + + lockdep_assert_held(&vmap_purge_lock); + + /* + * Use cpumask to mark which node has to be processed. + */ + purge_nodes = CPU_MASK_NONE; + + for (i = 0; i < nr_vmap_nodes; i++) { + vn = &vmap_nodes[i]; + + INIT_LIST_HEAD(&vn->purge_list); + vn->skip_populate = full_pool_decay; + decay_va_pool_node(vn, full_pool_decay); + + if (RB_EMPTY_ROOT(&vn->lazy.root)) + continue; + + spin_lock(&vn->lazy.lock); + WRITE_ONCE(vn->lazy.root.rb_node, NULL); + list_replace_init(&vn->lazy.head, &vn->purge_list); + spin_unlock(&vn->lazy.lock); + + start = min(start, list_first_entry(&vn->purge_list, + struct vmap_area, list)->va_start); + + end = max(end, list_last_entry(&vn->purge_list, + struct vmap_area, list)->va_end); + + cpumask_set_cpu(i, &purge_nodes); + } + + nr_purge_nodes = cpumask_weight(&purge_nodes); + if (nr_purge_nodes > 0) { + flush_tlb_kernel_range(start, end); + + /* One extra worker is per a lazy_max_pages() full set minus one. */ + nr_purge_helpers = atomic_long_read(&vmap_lazy_nr) / lazy_max_pages(); + nr_purge_helpers = clamp(nr_purge_helpers, 1U, nr_purge_nodes) - 1; + + for_each_cpu(i, &purge_nodes) { + vn = &vmap_nodes[i]; + + if (nr_purge_helpers > 0) { + INIT_WORK(&vn->purge_work, purge_vmap_node); + + if (cpumask_test_cpu(i, cpu_online_mask)) + schedule_work_on(i, &vn->purge_work); + else + schedule_work(&vn->purge_work); + + nr_purge_helpers--; + } else { + vn->purge_work.func = NULL; + purge_vmap_node(&vn->purge_work); + nr_purged_areas += vn->nr_purged; + } + } + + for_each_cpu(i, &purge_nodes) { + vn = &vmap_nodes[i]; + + if (vn->purge_work.func) { + flush_work(&vn->purge_work); + nr_purged_areas += vn->nr_purged; + } + } + } + + trace_purge_vmap_area_lazy(start, end, nr_purged_areas); + return nr_purged_areas > 0; } /* @@ -1863,22 +2276,15 @@ static void reclaim_and_purge_vmap_areas(void) { mutex_lock(&vmap_purge_lock); purge_fragmented_blocks_allcpus(); - __purge_vmap_area_lazy(ULONG_MAX, 0); + __purge_vmap_area_lazy(ULONG_MAX, 0, true); mutex_unlock(&vmap_purge_lock); } static void drain_vmap_area_work(struct work_struct *work) { - unsigned long nr_lazy; - - do { - mutex_lock(&vmap_purge_lock); - __purge_vmap_area_lazy(ULONG_MAX, 0); - mutex_unlock(&vmap_purge_lock); - - /* Recheck if further work is required. */ - nr_lazy = atomic_long_read(&vmap_lazy_nr); - } while (nr_lazy > lazy_max_pages()); + mutex_lock(&vmap_purge_lock); + __purge_vmap_area_lazy(ULONG_MAX, 0, false); + mutex_unlock(&vmap_purge_lock); } /* @@ -1890,6 +2296,8 @@ static void free_vmap_area_noflush(struct vmap_area *va) { unsigned long nr_lazy_max = lazy_max_pages(); unsigned long va_start = va->va_start; + unsigned int vn_id = decode_vn_id(va->flags); + struct vmap_node *vn; unsigned long nr_lazy; if (WARN_ON_ONCE(!list_empty(&va->list))) @@ -1899,12 +2307,15 @@ static void free_vmap_area_noflush(struct vmap_area *va) PAGE_SHIFT, &vmap_lazy_nr); /* - * Merge or place it to the purge tree/list. + * If it was request by a certain node we would like to + * return it to that node, i.e. its pool for later reuse. */ - spin_lock(&purge_vmap_area_lock); - merge_or_add_vmap_area(va, - &purge_vmap_area_root, &purge_vmap_area_list); - spin_unlock(&purge_vmap_area_lock); + vn = is_vn_id_valid(vn_id) ? + id_to_node(vn_id):addr_to_node(va->va_start); + + spin_lock(&vn->lazy.lock); + insert_vmap_area(va, &vn->lazy.root, &vn->lazy.head); + spin_unlock(&vn->lazy.lock); trace_free_vmap_area_noflush(va_start, nr_lazy, nr_lazy_max); @@ -1928,26 +2339,62 @@ static void free_unmap_vmap_area(struct vmap_area *va) struct vmap_area *find_vmap_area(unsigned long addr) { + struct vmap_node *vn; struct vmap_area *va; + int i, j; - spin_lock(&vmap_area_lock); - va = __find_vmap_area(addr, &vmap_area_root); - spin_unlock(&vmap_area_lock); + /* + * An addr_to_node_id(addr) converts an address to a node index + * where a VA is located. If VA spans several zones and passed + * addr is not the same as va->va_start, what is not common, we + * may need to scan extra nodes. See an example: + * + * <----va----> + * -|-----|-----|-----|-----|- + * 1 2 0 1 + * + * VA resides in node 1 whereas it spans 1, 2 an 0. If passed + * addr is within 2 or 0 nodes we should do extra work. + */ + i = j = addr_to_node_id(addr); + do { + vn = &vmap_nodes[i]; - return va; + spin_lock(&vn->busy.lock); + va = __find_vmap_area(addr, &vn->busy.root); + spin_unlock(&vn->busy.lock); + + if (va) + return va; + } while ((i = (i + 1) % nr_vmap_nodes) != j); + + return NULL; } static struct vmap_area *find_unlink_vmap_area(unsigned long addr) { + struct vmap_node *vn; struct vmap_area *va; + int i, j; - spin_lock(&vmap_area_lock); - va = __find_vmap_area(addr, &vmap_area_root); - if (va) - unlink_va(va, &vmap_area_root); - spin_unlock(&vmap_area_lock); + /* + * Check the comment in the find_vmap_area() about the loop. + */ + i = j = addr_to_node_id(addr); + do { + vn = &vmap_nodes[i]; - return va; + spin_lock(&vn->busy.lock); + va = __find_vmap_area(addr, &vn->busy.root); + if (va) + unlink_va(va, &vn->busy.root); + spin_unlock(&vn->busy.lock); + + if (va) + return va; + } while ((i = (i + 1) % nr_vmap_nodes) != j); + + return NULL; } /*** Per cpu kva allocator ***/ @@ -2149,6 +2596,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) static void free_vmap_block(struct vmap_block *vb) { + struct vmap_node *vn; struct vmap_block *tmp; struct xarray *xa; @@ -2156,9 +2604,10 @@ static void free_vmap_block(struct vmap_block *vb) tmp = xa_erase(xa, addr_to_vb_idx(vb->va->va_start)); BUG_ON(tmp != vb); - spin_lock(&vmap_area_lock); - unlink_va(vb->va, &vmap_area_root); - spin_unlock(&vmap_area_lock); + vn = addr_to_node(vb->va->va_start); + spin_lock(&vn->busy.lock); + unlink_va(vb->va, &vn->busy.root); + spin_unlock(&vn->busy.lock); free_vmap_area_noflush(vb->va); kfree_rcu(vb, rcu_head); @@ -2375,7 +2824,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) } free_purged_blocks(&purge_list); - if (!__purge_vmap_area_lazy(start, end) && flush) + if (!__purge_vmap_area_lazy(start, end, false) && flush) flush_tlb_kernel_range(start, end); mutex_unlock(&vmap_purge_lock); } @@ -2569,47 +3018,6 @@ void __init vm_area_register_early(struct vm_struct *vm, size_t align) kasan_populate_early_vm_area_shadow(vm->addr, vm->size); } -static void vmap_init_free_space(void) -{ - unsigned long vmap_start = 1; - const unsigned long vmap_end = ULONG_MAX; - struct vmap_area *busy, *free; - - /* - * B F B B B F - * -|-----|.....|-----|-----|-----|.....|- - * | The KVA space | - * |<--------------------------------->| - */ - list_for_each_entry(busy, &vmap_area_list, list) { - if (busy->va_start - vmap_start > 0) { - free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); - if (!WARN_ON_ONCE(!free)) { - free->va_start = vmap_start; - free->va_end = busy->va_start; - - insert_vmap_area_augment(free, NULL, - &free_vmap_area_root, - &free_vmap_area_list); - } - } - - vmap_start = busy->va_end; - } - - if (vmap_end - vmap_start > 0) { - free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); - if (!WARN_ON_ONCE(!free)) { - free->va_start = vmap_start; - free->va_end = vmap_end; - - insert_vmap_area_augment(free, NULL, - &free_vmap_area_root, - &free_vmap_area_list); - } - } -} - static inline void setup_vmalloc_vm_locked(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { @@ -2623,9 +3031,11 @@ static inline void setup_vmalloc_vm_locked(struct vm_struct *vm, static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { - spin_lock(&vmap_area_lock); + struct vmap_node *vn = addr_to_node(va->va_start); + + spin_lock(&vn->busy.lock); setup_vmalloc_vm_locked(vm, va, flags, caller); - spin_unlock(&vmap_area_lock); + spin_unlock(&vn->busy.lock); } static void clear_vm_uninitialized_flag(struct vm_struct *vm) @@ -3813,10 +4223,12 @@ finished: */ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) { + struct vmap_node *vn; struct vmap_area *va; struct vm_struct *vm; char *vaddr; size_t n, size, flags, remains; + unsigned long next; addr = kasan_reset_tag(addr); @@ -3826,16 +4238,15 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) remains = count; - spin_lock(&vmap_area_lock); - va = find_vmap_area_exceed_addr((unsigned long)addr); - if (!va) + vn = find_vmap_area_exceed_addr_lock((unsigned long) addr, &va); + if (!vn) goto finished_zero; /* no intersects with alive vmap_area */ if ((unsigned long)addr + remains <= va->va_start) goto finished_zero; - list_for_each_entry_from(va, &vmap_area_list, list) { + do { size_t copied; if (remains == 0) @@ -3850,10 +4261,10 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) WARN_ON(flags == VMAP_BLOCK); if (!vm && !flags) - continue; + goto next_va; if (vm && (vm->flags & VM_UNINITIALIZED)) - continue; + goto next_va; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); @@ -3862,7 +4273,7 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) size = vm ? get_vm_area_size(vm) : va_size(va); if (addr >= vaddr + size) - continue; + goto next_va; if (addr < vaddr) { size_t to_zero = min_t(size_t, vaddr - addr, remains); @@ -3891,15 +4302,22 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) if (copied != n) goto finished; - } + + next_va: + next = va->va_end; + spin_unlock(&vn->busy.lock); + } while ((vn = find_vmap_area_exceed_addr_lock(next, &va))); finished_zero: - spin_unlock(&vmap_area_lock); + if (vn) + spin_unlock(&vn->busy.lock); + /* zero-fill memory holes */ return count - remains + zero_iter(iter, remains); finished: /* Nothing remains, or We couldn't copy/zero everything. */ - spin_unlock(&vmap_area_lock); + if (vn) + spin_unlock(&vn->busy.lock); return count - remains; } @@ -4212,9 +4630,8 @@ retry: /* It is a BUG(), but trigger recovery instead. */ goto recovery; - ret = adjust_va_to_fit_type(&free_vmap_area_root, - &free_vmap_area_list, - va, start, size); + ret = va_clip(&free_vmap_area_root, + &free_vmap_area_list, va, start, size); if (WARN_ON_ONCE(unlikely(ret))) /* It is a BUG(), but trigger recovery instead. */ goto recovery; @@ -4234,14 +4651,15 @@ retry: } /* insert all vm's */ - spin_lock(&vmap_area_lock); for (area = 0; area < nr_vms; area++) { - insert_vmap_area(vas[area], &vmap_area_root, &vmap_area_list); + struct vmap_node *vn = addr_to_node(vas[area]->va_start); + spin_lock(&vn->busy.lock); + insert_vmap_area(vas[area], &vn->busy.root, &vn->busy.head); setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); + spin_unlock(&vn->busy.lock); } - spin_unlock(&vmap_area_lock); /* * Mark allocated areas as accessible. Do it now as a best-effort @@ -4350,60 +4768,39 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) #ifdef CONFIG_PRINTK bool vmalloc_dump_obj(void *object) { - void *objp = (void *)PAGE_ALIGN((unsigned long)object); const void *caller; struct vm_struct *vm; struct vmap_area *va; + struct vmap_node *vn; unsigned long addr; unsigned int nr_pages; - if (!spin_trylock(&vmap_area_lock)) + addr = PAGE_ALIGN((unsigned long) object); + vn = addr_to_node(addr); + + if (!spin_trylock(&vn->busy.lock)) return false; - va = __find_vmap_area((unsigned long)objp, &vmap_area_root); - if (!va) { - spin_unlock(&vmap_area_lock); + + va = __find_vmap_area(addr, &vn->busy.root); + if (!va || !va->vm) { + spin_unlock(&vn->busy.lock); return false; } vm = va->vm; - if (!vm) { - spin_unlock(&vmap_area_lock); - return false; - } - addr = (unsigned long)vm->addr; + addr = (unsigned long) vm->addr; caller = vm->caller; nr_pages = vm->nr_pages; - spin_unlock(&vmap_area_lock); + spin_unlock(&vn->busy.lock); + pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n", nr_pages, addr, caller); + return true; } #endif #ifdef CONFIG_PROC_FS -static void *s_start(struct seq_file *m, loff_t *pos) - __acquires(&vmap_purge_lock) - __acquires(&vmap_area_lock) -{ - mutex_lock(&vmap_purge_lock); - spin_lock(&vmap_area_lock); - - return seq_list_start(&vmap_area_list, *pos); -} - -static void *s_next(struct seq_file *m, void *p, loff_t *pos) -{ - return seq_list_next(p, &vmap_area_list, pos); -} - -static void s_stop(struct seq_file *m, void *p) - __releases(&vmap_area_lock) - __releases(&vmap_purge_lock) -{ - spin_unlock(&vmap_area_lock); - mutex_unlock(&vmap_purge_lock); -} - static void show_numa_info(struct seq_file *m, struct vm_struct *v) { if (IS_ENABLED(CONFIG_NUMA)) { @@ -4430,105 +4827,237 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) static void show_purge_info(struct seq_file *m) { + struct vmap_node *vn; struct vmap_area *va; + int i; + + for (i = 0; i < nr_vmap_nodes; i++) { + vn = &vmap_nodes[i]; - spin_lock(&purge_vmap_area_lock); - list_for_each_entry(va, &purge_vmap_area_list, list) { - seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", - (void *)va->va_start, (void *)va->va_end, - va->va_end - va->va_start); + spin_lock(&vn->lazy.lock); + list_for_each_entry(va, &vn->lazy.head, list) { + seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", + (void *)va->va_start, (void *)va->va_end, + va->va_end - va->va_start); + } + spin_unlock(&vn->lazy.lock); } - spin_unlock(&purge_vmap_area_lock); } -static int s_show(struct seq_file *m, void *p) +static int vmalloc_info_show(struct seq_file *m, void *p) { + struct vmap_node *vn; struct vmap_area *va; struct vm_struct *v; + int i; - va = list_entry(p, struct vmap_area, list); + for (i = 0; i < nr_vmap_nodes; i++) { + vn = &vmap_nodes[i]; - if (!va->vm) { - if (va->flags & VMAP_RAM) - seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", - (void *)va->va_start, (void *)va->va_end, - va->va_end - va->va_start); + spin_lock(&vn->busy.lock); + list_for_each_entry(va, &vn->busy.head, list) { + if (!va->vm) { + if (va->flags & VMAP_RAM) + seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", + (void *)va->va_start, (void *)va->va_end, + va->va_end - va->va_start); - goto final; - } + continue; + } - v = va->vm; + v = va->vm; - seq_printf(m, "0x%pK-0x%pK %7ld", - v->addr, v->addr + v->size, v->size); + seq_printf(m, "0x%pK-0x%pK %7ld", + v->addr, v->addr + v->size, v->size); - if (v->caller) - seq_printf(m, " %pS", v->caller); + if (v->caller) + seq_printf(m, " %pS", v->caller); - if (v->nr_pages) - seq_printf(m, " pages=%d", v->nr_pages); + if (v->nr_pages) + seq_printf(m, " pages=%d", v->nr_pages); - if (v->phys_addr) - seq_printf(m, " phys=%pa", &v->phys_addr); + if (v->phys_addr) + seq_printf(m, " phys=%pa", &v->phys_addr); - if (v->flags & VM_IOREMAP) - seq_puts(m, " ioremap"); + if (v->flags & VM_IOREMAP) + seq_puts(m, " ioremap"); - if (v->flags & VM_SPARSE) - seq_puts(m, " sparse"); + if (v->flags & VM_SPARSE) + seq_puts(m, " sparse"); - if (v->flags & VM_ALLOC) - seq_puts(m, " vmalloc"); + if (v->flags & VM_ALLOC) + seq_puts(m, " vmalloc"); - if (v->flags & VM_MAP) - seq_puts(m, " vmap"); + if (v->flags & VM_MAP) + seq_puts(m, " vmap"); - if (v->flags & VM_USERMAP) - seq_puts(m, " user"); + if (v->flags & VM_USERMAP) + seq_puts(m, " user"); - if (v->flags & VM_DMA_COHERENT) - seq_puts(m, " dma-coherent"); + if (v->flags & VM_DMA_COHERENT) + seq_puts(m, " dma-coherent"); - if (is_vmalloc_addr(v->pages)) - seq_puts(m, " vpages"); + if (is_vmalloc_addr(v->pages)) + seq_puts(m, " vpages"); - show_numa_info(m, v); - seq_putc(m, '\n'); + show_numa_info(m, v); + seq_putc(m, '\n'); + } + spin_unlock(&vn->busy.lock); + } /* * As a final step, dump "unpurged" areas. */ -final: - if (list_is_last(&va->list, &vmap_area_list)) - show_purge_info(m); - + show_purge_info(m); return 0; } -static const struct seq_operations vmalloc_op = { - .start = s_start, - .next = s_next, - .stop = s_stop, - .show = s_show, -}; - static int __init proc_vmalloc_init(void) { + void *priv_data = NULL; + if (IS_ENABLED(CONFIG_NUMA)) - proc_create_seq_private("vmallocinfo", 0400, NULL, - &vmalloc_op, - nr_node_ids * sizeof(unsigned int), NULL); - else - proc_create_seq("vmallocinfo", 0400, NULL, &vmalloc_op); + priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); + + proc_create_single_data("vmallocinfo", + 0400, NULL, vmalloc_info_show, priv_data); + return 0; } module_init(proc_vmalloc_init); #endif +static void __init vmap_init_free_space(void) +{ + unsigned long vmap_start = 1; + const unsigned long vmap_end = ULONG_MAX; + struct vmap_area *free; + struct vm_struct *busy; + + /* + * B F B B B F + * -|-----|.....|-----|-----|-----|.....|- + * | The KVA space | + * |<--------------------------------->| + */ + for (busy = vmlist; busy; busy = busy->next) { + if ((unsigned long) busy->addr - vmap_start > 0) { + free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); + if (!WARN_ON_ONCE(!free)) { + free->va_start = vmap_start; + free->va_end = (unsigned long) busy->addr; + + insert_vmap_area_augment(free, NULL, + &free_vmap_area_root, + &free_vmap_area_list); + } + } + + vmap_start = (unsigned long) busy->addr + busy->size; + } + + if (vmap_end - vmap_start > 0) { + free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); + if (!WARN_ON_ONCE(!free)) { + free->va_start = vmap_start; + free->va_end = vmap_end; + + insert_vmap_area_augment(free, NULL, + &free_vmap_area_root, + &free_vmap_area_list); + } + } +} + +static void vmap_init_nodes(void) +{ + struct vmap_node *vn; + int i, n; + +#if BITS_PER_LONG == 64 + /* + * A high threshold of max nodes is fixed and bound to 128, + * thus a scale factor is 1 for systems where number of cores + * are less or equal to specified threshold. + * + * As for NUMA-aware notes. For bigger systems, for example + * NUMA with multi-sockets, where we can end-up with thousands + * of cores in total, a "sub-numa-clustering" should be added. + * + * In this case a NUMA domain is considered as a single entity + * with dedicated sub-nodes in it which describe one group or + * set of cores. Therefore a per-domain purging is supposed to + * be added as well as a per-domain balancing. + */ + n = clamp_t(unsigned int, num_possible_cpus(), 1, 128); + + if (n > 1) { + vn = kmalloc_array(n, sizeof(*vn), GFP_NOWAIT | __GFP_NOWARN); + if (vn) { + /* Node partition is 16 pages. */ + vmap_zone_size = (1 << 4) * PAGE_SIZE; + nr_vmap_nodes = n; + vmap_nodes = vn; + } else { + pr_err("Failed to allocate an array. Disable a node layer\n"); + } + } +#endif + + for (n = 0; n < nr_vmap_nodes; n++) { + vn = &vmap_nodes[n]; + vn->busy.root = RB_ROOT; + INIT_LIST_HEAD(&vn->busy.head); + spin_lock_init(&vn->busy.lock); + + vn->lazy.root = RB_ROOT; + INIT_LIST_HEAD(&vn->lazy.head); + spin_lock_init(&vn->lazy.lock); + + for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { + INIT_LIST_HEAD(&vn->pool[i].head); + WRITE_ONCE(vn->pool[i].len, 0); + } + + spin_lock_init(&vn->pool_lock); + } +} + +static unsigned long +vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + unsigned long count; + struct vmap_node *vn; + int i, j; + + for (count = 0, i = 0; i < nr_vmap_nodes; i++) { + vn = &vmap_nodes[i]; + + for (j = 0; j < MAX_VA_SIZE_PAGES; j++) + count += READ_ONCE(vn->pool[j].len); + } + + return count ? count : SHRINK_EMPTY; +} + +static unsigned long +vmap_node_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + int i; + + for (i = 0; i < nr_vmap_nodes; i++) + decay_va_pool_node(&vmap_nodes[i], true); + + return SHRINK_STOP; +} + void __init vmalloc_init(void) { + struct shrinker *vmap_node_shrinker; struct vmap_area *va; + struct vmap_node *vn; struct vm_struct *tmp; int i; @@ -4550,6 +5079,11 @@ void __init vmalloc_init(void) xa_init(&vbq->vmap_blocks); } + /* + * Setup nodes before importing vmlist. + */ + vmap_init_nodes(); + /* Import existing vmlist entries. */ for (tmp = vmlist; tmp; tmp = tmp->next) { va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); @@ -4559,7 +5093,9 @@ void __init vmalloc_init(void) va->va_start = (unsigned long)tmp->addr; va->va_end = va->va_start + tmp->size; va->vm = tmp; - insert_vmap_area(va, &vmap_area_root, &vmap_area_list); + + vn = addr_to_node(va->va_start); + insert_vmap_area(va, &vn->busy.root, &vn->busy.head); } /* @@ -4567,4 +5103,14 @@ void __init vmalloc_init(void) */ vmap_init_free_space(); vmap_initialized = true; + + vmap_node_shrinker = shrinker_alloc(0, "vmap-node"); + if (!vmap_node_shrinker) { + pr_err("Failed to allocate vmap-node shrinker!\n"); + return; + } + + vmap_node_shrinker->count_objects = vmap_node_shrink_count; + vmap_node_shrinker->scan_objects = vmap_node_shrink_scan; + shrinker_register(vmap_node_shrinker); } |