// SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo <[email protected]> * * Copyright (C) 2017 Facebook Inc. * Copyright (C) 2017 Dennis Zhou <[email protected]> * * The percpu allocator handles both static and dynamic areas. Percpu * areas are allocated in chunks which are divided into units. There is * a 1-to-1 mapping for units to possible cpus. These units are grouped * based on NUMA properties of the machine. * * c0 c1 c2 * ------------------- ------------------- ------------ * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u * ------------------- ...... ------------------- .... ------------ * * Allocation is done by offsets into a unit's address space. Ie., an * area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0, * c1:u1, c1:u2, etc. On NUMA machines, the mapping may be non-linear * and even sparse. Access is handled by configuring percpu base * registers according to the cpu to unit mappings and offsetting the * base address using pcpu_unit_size. * * There is special consideration for the first chunk which must handle * the static percpu variables in the kernel image as allocation services * are not online yet. In short, the first chunk is structured like so: * * <Static | [Reserved] | Dynamic> * * The static data is copied from the original section managed by the * linker. The reserved section, if non-zero, primarily manages static * percpu variables from kernel modules. Finally, the dynamic section * takes care of normal allocations. * * The allocator organizes chunks into lists according to free size and * memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT * flag should be passed. All memcg-aware allocations are sharing one set * of chunks and all unaccounted allocations and allocations performed * by processes belonging to the root memory cgroup are using the second set. * * The allocator tries to allocate from the fullest chunk first. Each chunk * is managed by a bitmap with metadata blocks. The allocation map is updated * on every allocation and free to reflect the current state while the boundary * map is only updated on allocation. Each metadata block contains * information to help mitigate the need to iterate over large portions * of the bitmap. The reverse mapping from page to chunk is stored in * the page's index. Lastly, units are lazily backed and grow in unison. * * There is a unique conversion that goes on here between bytes and bits. * Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE. The chunk * tracks the number of pages it is responsible for in nr_pages. Helper * functions are used to convert from between the bytes, bits, and blocks. * All hints are managed in bits unless explicitly stated. * * To use this allocator, arch code should do the following: * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be * different from the default * * - use pcpu_setup_first_chunk() during percpu area initialization to * setup the first chunk containing the kernel static percpu area */ #define pr_fmt(fmt) … #include <linux/bitmap.h> #include <linux/cpumask.h> #include <linux/memblock.h> #include <linux/err.h> #include <linux/list.h> #include <linux/log2.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/pfn.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/memcontrol.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/io.h> #define CREATE_TRACE_POINTS #include <trace/events/percpu.h> #include "percpu-internal.h" /* * The slots are sorted by the size of the biggest continuous free area. * 1-31 bytes share the same slot. */ #define PCPU_SLOT_BASE_SHIFT … /* chunks in slots below this are subject to being sidelined on failed alloc */ #define PCPU_SLOT_FAIL_THRESHOLD … #define PCPU_EMPTY_POP_PAGES_LOW … #define PCPU_EMPTY_POP_PAGES_HIGH … #ifdef CONFIG_SMP /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ #ifndef __addr_to_pcpu_ptr #define __addr_to_pcpu_ptr(addr) … #endif #ifndef __pcpu_ptr_to_addr #define __pcpu_ptr_to_addr(ptr) … #endif #else /* CONFIG_SMP */ /* on UP, it's always identity mapped */ #define __addr_to_pcpu_ptr … #define __pcpu_ptr_to_addr … #endif /* CONFIG_SMP */ static int pcpu_unit_pages __ro_after_init; static int pcpu_unit_size __ro_after_init; static int pcpu_nr_units __ro_after_init; static int pcpu_atom_size __ro_after_init; int pcpu_nr_slots __ro_after_init; static int pcpu_free_slot __ro_after_init; int pcpu_sidelined_slot __ro_after_init; int pcpu_to_depopulate_slot __ro_after_init; static size_t pcpu_chunk_struct_size __ro_after_init; /* cpus with the lowest and highest unit addresses */ static unsigned int pcpu_low_unit_cpu __ro_after_init; static unsigned int pcpu_high_unit_cpu __ro_after_init; /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __ro_after_init; static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */ const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */ /* group information, used for vm allocation */ static int pcpu_nr_groups __ro_after_init; static const unsigned long *pcpu_group_offsets __ro_after_init; static const size_t *pcpu_group_sizes __ro_after_init; /* * The first chunk which always exists. Note that unlike other * chunks, this one can be allocated and mapped in several different * ways and thus often doesn't live in the vmalloc area. */ struct pcpu_chunk *pcpu_first_chunk __ro_after_init; /* * Optional reserved chunk. This chunk reserves part of the first * chunk and serves it for reserved allocations. When the reserved * region doesn't exist, the following variable is NULL. */ struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init; DEFINE_SPINLOCK(…); /* all internal data structures */ static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ /* * The number of empty populated pages, protected by pcpu_lock. * The reserved chunk doesn't contribute to the count. */ int pcpu_nr_empty_pop_pages; /* * The number of populated pages in use by the allocator, protected by * pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets * allocated/deallocated, it is allocated/deallocated in all units of a chunk * and increments/decrements this count by 1). */ static unsigned long pcpu_nr_populated; /* * Balance work is used to populate or destroy chunks asynchronously. We * try to keep the number of populated free pages between * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one * empty chunk. */ static void pcpu_balance_workfn(struct work_struct *work); static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn); static bool pcpu_async_enabled __read_mostly; static bool pcpu_atomic_alloc_failed; static void pcpu_schedule_balance_work(void) { … } /** * pcpu_addr_in_chunk - check if the address is served from this chunk * @chunk: chunk of interest * @addr: percpu address * * RETURNS: * True if the address is served from this chunk. */ static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr) { … } static int __pcpu_size_to_slot(int size) { … } static int pcpu_size_to_slot(int size) { … } static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) { … } /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { … } /* obtain pointer to a chunk from a page struct */ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { … } static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { … } static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx) { … } static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { … } /* * The following are helper functions to help access bitmaps and convert * between bitmap offsets to address offsets. */ static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index) { … } static unsigned long pcpu_off_to_block_index(int off) { … } static unsigned long pcpu_off_to_block_off(int off) { … } static unsigned long pcpu_block_off_to_off(int index, int off) { … } /** * pcpu_check_block_hint - check against the contig hint * @block: block of interest * @bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * * Check to see if the allocation can fit in the block's contig hint. * Note, a chunk uses the same hints as a block so this can also check against * the chunk's contig hint. */ static bool pcpu_check_block_hint(struct pcpu_block_md *block, int bits, size_t align) { … } /* * pcpu_next_hint - determine which hint to use * @block: block of interest * @alloc_bits: size of allocation * * This determines if we should scan based on the scan_hint or first_free. * In general, we want to scan from first_free to fulfill allocations by * first fit. However, if we know a scan_hint at position scan_hint_start * cannot fulfill an allocation, we can begin scanning from there knowing * the contig_hint will be our fallback. */ static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits) { … } /** * pcpu_next_md_free_region - finds the next hint free area * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Helper function for pcpu_for_each_md_free_region. It checks * block->contig_hint and performs aggregation across blocks to find the * next hint. It modifies bit_off and bits in-place to be consumed in the * loop. */ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, int *bits) { … } /** * pcpu_next_fit_region - finds fit areas for a given allocation request * @chunk: chunk of interest * @alloc_bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * @bit_off: chunk offset * @bits: size of free area * * Finds the next free region that is viable for use with a given size and * alignment. This only returns if there is a valid area to be used for this * allocation. block->first_free is returned if the allocation request fits * within the block to see if the request can be fulfilled prior to the contig * hint. */ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, int align, int *bit_off, int *bits) { … } /* * Metadata free area iterators. These perform aggregation of free areas * based on the metadata blocks and return the offset @bit_off and size in * bits of the free area @bits. pcpu_for_each_fit_region only returns when * a fit is found for the allocation request. */ #define pcpu_for_each_md_free_region(chunk, bit_off, bits) … #define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) … /** * pcpu_mem_zalloc - allocate memory * @size: bytes to allocate * @gfp: allocation flags * * Allocate @size bytes. If @size is smaller than PAGE_SIZE, * kzalloc() is used; otherwise, the equivalent of vzalloc() is used. * This is to facilitate passing through whitelisted flags. The * returned memory is always zeroed. * * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) { … } /** * pcpu_mem_free - free memory * @ptr: memory to free * * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). */ static void pcpu_mem_free(void *ptr) { … } static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, bool move_front) { … } static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot) { … } /** * pcpu_chunk_relocate - put chunk in the appropriate chunk slot * @chunk: chunk of interest * @oslot: the previous slot it was on * * This function is called after an allocation or free changed @chunk. * New slot according to the changed state is determined and @chunk is * moved to the slot. Note that the reserved chunk is never put on * chunk slots. * * CONTEXT: * pcpu_lock. */ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { … } static void pcpu_isolate_chunk(struct pcpu_chunk *chunk) { … } static void pcpu_reintegrate_chunk(struct pcpu_chunk *chunk) { … } /* * pcpu_update_empty_pages - update empty page counters * @chunk: chunk of interest * @nr: nr of empty pages * * This is used to keep track of the empty pages now based on the premise * a md_block covers a page. The hint update functions recognize if a block * is made full or broken to calculate deltas for keeping track of free pages. */ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { … } /* * pcpu_region_overlap - determines if two regions overlap * @a: start of first region, inclusive * @b: end of first region, exclusive * @x: start of second region, inclusive * @y: end of second region, exclusive * * This is used to determine if the hint region [a, b) overlaps with the * allocated region [x, y). */ static inline bool pcpu_region_overlap(int a, int b, int x, int y) { … } /** * pcpu_block_update - updates a block given a free area * @block: block of interest * @start: start offset in block * @end: end offset in block * * Updates a block given a known free area. The region [start, end) is * expected to be the entirety of the free area within a block. Chooses * the best starting offset if the contig hints are equal. */ static void pcpu_block_update(struct pcpu_block_md *block, int start, int end) { … } /* * pcpu_block_update_scan - update a block given a free area from a scan * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Finding the final allocation spot first goes through pcpu_find_block_fit() * to find a block that can hold the allocation and then pcpu_alloc_area() * where a scan is used. When allocations require specific alignments, * we can inadvertently create holes which will not be seen in the alloc * or free paths. * * This takes a given free area hole and updates a block as it may change the * scan_hint. We need to scan backwards to ensure we don't miss free bits * from alignment. */ static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off, int bits) { … } /** * pcpu_chunk_refresh_hint - updates metadata about a chunk * @chunk: chunk of interest * @full_scan: if we should scan from the beginning * * Iterates over the metadata blocks to find the largest contig area. * A full scan can be avoided on the allocation path as this is triggered * if we broke the contig_hint. In doing so, the scan_hint will be before * the contig_hint or after if the scan_hint == contig_hint. This cannot * be prevented on freeing as we want to find the largest area possibly * spanning blocks. */ static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan) { … } /** * pcpu_block_refresh_hint * @chunk: chunk of interest * @index: index of the metadata block * * Scans over the block beginning at first_free and updates the block * metadata accordingly. */ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) { … } /** * pcpu_block_update_hint_alloc - update hint on allocation path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. The metadata only has to be * refreshed by a full scan iff the chunk's contig hint is broken. Block level * scans are required if the block's contig hint is broken. */ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off, int bits) { … } /** * pcpu_block_update_hint_free - updates the block hints on the free path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. This avoids a blind block * refresh by making use of the block contig hints. If this fails, it scans * forward and backward to determine the extent of the free area. This is * capped at the boundary of blocks. * * A chunk update is triggered if a page becomes free, a block becomes free, * or the free spans across blocks. This tradeoff is to minimize iterating * over the block metadata to update chunk_md->contig_hint. * chunk_md->contig_hint may be off by up to a page, but it will never be more * than the available space. If the contig hint is contained in one block, it * will be accurate. */ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, int bits) { … } /** * pcpu_is_populated - determines if the region is populated * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of area * @next_off: return value for the next offset to start searching * * For atomic allocations, check if the backing pages are populated. * * RETURNS: * Bool if the backing pages are populated. * next_index is to skip over unpopulated blocks in pcpu_find_block_fit. */ static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits, int *next_off) { … } /** * pcpu_find_block_fit - finds the block index to start searching * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE bytes) * @pop_only: use populated regions only * * Given a chunk and an allocation spec, find the offset to begin searching * for a free region. This iterates over the bitmap metadata blocks to * find an offset that will be guaranteed to fit the requirements. It is * not quite first fit as if the allocation does not fit in the contig hint * of a block or chunk, it is skipped. This errs on the side of caution * to prevent excess iteration. Poor alignment can cause the allocator to * skip over blocks and chunks that have valid free areas. * * RETURNS: * The offset in the bitmap to begin searching. * -1 if no offset is found. */ static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits, size_t align, bool pop_only) { … } /* * pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off() * @map: the address to base the search on * @size: the bitmap size in bits * @start: the bitnumber to start searching at * @nr: the number of zeroed bits we're looking for * @align_mask: alignment mask for zero area * @largest_off: offset of the largest area skipped * @largest_bits: size of the largest area skipped * * The @align_mask should be one less than a power of 2. * * This is a modified version of bitmap_find_next_zero_area_off() to remember * the largest area that was skipped. This is imperfect, but in general is * good enough. The largest remembered region is the largest failed region * seen. This does not include anything we possibly skipped due to alignment. * pcpu_block_update_scan() does scan backwards to try and recover what was * lost to alignment. While this can cause scanning to miss earlier possible * free areas, smaller allocations will eventually fill those holes. */ static unsigned long pcpu_find_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned long nr, unsigned long align_mask, unsigned long *largest_off, unsigned long *largest_bits) { … } /** * pcpu_alloc_area - allocates an area from a pcpu_chunk * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE) * @start: bit_off to start searching * * This function takes in a @start offset to begin searching to fit an * allocation of @alloc_bits with alignment @align. It needs to scan * the allocation map because if it fits within the block's contig hint, * @start will be block->first_free. This is an attempt to fill the * allocation prior to breaking the contig hint. The allocation and * boundary maps are updated accordingly if it confirms a valid * free area. * * RETURNS: * Allocated addr offset in @chunk on success. * -1 if no matching area is found. */ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits, size_t align, int start) { … } /** * pcpu_free_area - frees the corresponding offset * @chunk: chunk of interest * @off: addr offset into chunk * * This function determines the size of an allocation to free using * the boundary bitmap and clears the allocation map. * * RETURNS: * Number of freed bytes. */ static int pcpu_free_area(struct pcpu_chunk *chunk, int off) { … } static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits) { … } static void pcpu_init_md_blocks(struct pcpu_chunk *chunk) { … } /** * pcpu_alloc_first_chunk - creates chunks that serve the first chunk * @tmp_addr: the start of the region served * @map_size: size of the region served * * This is responsible for creating the chunks that serve the first chunk. The * base_addr is page aligned down of @tmp_addr while the region end is page * aligned up. Offsets are kept track of to determine the region served. All * this is done to appease the bitmap allocator in avoiding partial blocks. * * RETURNS: * Chunk serving the region at @tmp_addr of @map_size. */ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, int map_size) { … } static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) { … } static void pcpu_free_chunk(struct pcpu_chunk *chunk) { … } /** * pcpu_chunk_populated - post-population bookkeeping * @chunk: pcpu_chunk which got populated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been populated to @chunk. Update * the bookkeeping information accordingly. Must be called after each * successful population. */ static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, int page_end) { … } /** * pcpu_chunk_depopulated - post-depopulation bookkeeping * @chunk: pcpu_chunk which got depopulated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been depopulated from @chunk. * Update the bookkeeping information accordingly. Must be called after * each successful depopulation. */ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, int page_start, int page_end) { … } /* * Chunk management implementation. * * To allow different implementations, chunk alloc/free and * [de]population are implemented in a separate file which is pulled * into this file and compiled together. The following functions * should be implemented. * * pcpu_populate_chunk - populate the specified range of a chunk * pcpu_depopulate_chunk - depopulate the specified range of a chunk * pcpu_post_unmap_tlb_flush - flush tlb for the specified range of a chunk * pcpu_create_chunk - create a new chunk * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop * pcpu_addr_to_page - translate address to physical address * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp); static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end); static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end); static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); #ifdef CONFIG_NEED_PER_CPU_KM #include "percpu-km.c" #else #include "percpu-vm.c" #endif /** * pcpu_chunk_addr_search - determine chunk containing specified address * @addr: address for which the chunk needs to be determined. * * This is an internal function that handles all but static allocations. * Static percpu address values should never be passed into the allocator. * * RETURNS: * The address of the found chunk. */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { … } #ifdef CONFIG_MEMCG static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { … } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { … } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { … } #else /* CONFIG_MEMCG */ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MEM_ALLOC_PROFILING static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, size_t size) { if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) { alloc_tag_add(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, current->alloc_tag, size); } } static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) alloc_tag_sub(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, size); } #else static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, size_t size) { … } static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { … } #endif /** * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @reserved: allocate from the reserved chunk if available * @gfp: allocation flags * * Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN * then no warning will be triggered on invalid or failed allocation * requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, gfp_t gfp) { … } EXPORT_SYMBOL_GPL(…); /** * pcpu_balance_free - manage the amount of free chunks * @empty_only: free chunks only if there are no populated pages * * If empty_only is %false, reclaim all fully free chunks regardless of the * number of populated pages. Otherwise, only reclaim chunks that have no * populated pages. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_free(bool empty_only) { … } /** * pcpu_balance_populated - manage the amount of populated pages * * Maintain a certain amount of populated pages to satisfy atomic allocations. * It is possible that this is called when physical memory is scarce causing * OOM killer to be triggered. We should avoid doing so until an actual * allocation causes the failure as it is possible that requests can be * serviced from already backed regions. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_populated(void) { … } /** * pcpu_reclaim_populated - scan over to_depopulate chunks and free empty pages * * Scan over chunks in the depopulate list and try to release unused populated * pages back to the system. Depopulated chunks are sidelined to prevent * repopulating these pages unless required. Fully free chunks are reintegrated * and freed accordingly (1 is kept around). If we drop below the empty * populated pages threshold, reintegrate the chunk if it has empty free pages. * Each chunk is scanned in the reverse order to keep populated pages close to * the beginning of the chunk. * * CONTEXT: * pcpu_lock (can be dropped temporarily) * */ static void pcpu_reclaim_populated(void) { … } /** * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * * For each chunk type, manage the number of fully free chunks and the number of * populated pages. An important thing to consider is when pages are freed and * how they contribute to the global counts. */ static void pcpu_balance_workfn(struct work_struct *work) { … } /** * pcpu_alloc_size - the size of the dynamic percpu area * @ptr: pointer to the dynamic percpu area * * Returns the size of the @ptr allocation. This is undefined for statically * defined percpu variables as there is no corresponding chunk->bound_map. * * RETURNS: * The size of the dynamic percpu area. * * CONTEXT: * Can be called from atomic context. */ size_t pcpu_alloc_size(void __percpu *ptr) { … } /** * free_percpu - free percpu area * @ptr: pointer to area to free * * Free percpu area @ptr. * * CONTEXT: * Can be called from atomic context. */ void free_percpu(void __percpu *ptr) { … } EXPORT_SYMBOL_GPL(…); bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) { … } /** * is_kernel_percpu_address - test whether address is from static percpu area * @addr: address to test * * Test whether @addr belongs to in-kernel static percpu area. Module * static percpu areas are not considered. For those, use * is_module_percpu_address(). * * RETURNS: * %true if @addr is from in-kernel static percpu area, %false otherwise. */ bool is_kernel_percpu_address(unsigned long addr) { … } /** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * * Given @addr which is dereferenceable address obtained via one of * percpu access macros, this function translates it into its physical * address. The caller is responsible for ensuring @addr stays valid * until this function finishes. * * percpu allocator has special setup for the first chunk, which currently * supports either embedding in linear address space or vmalloc mapping, * and, from the second one, the backing allocator (currently either vm or * km) provides translation. * * The addr can be translated simply without checking if it falls into the * first chunk. But the current code reflects better how percpu allocator * actually works, and the verification can discover both bugs in percpu * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current * code. * * RETURNS: * The physical address for @addr. */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { … } /** * pcpu_alloc_alloc_info - allocate percpu allocation info * @nr_groups: the number of groups * @nr_units: the number of units * * Allocate ai which is large enough for @nr_groups groups containing * @nr_units units. The returned ai's groups[0].cpu_map points to the * cpu_map array which is long enough for @nr_units and filled with * NR_CPUS. It's the caller's responsibility to initialize cpu_map * pointer of other groups. * * RETURNS: * Pointer to the allocated pcpu_alloc_info on success, NULL on * failure. */ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, int nr_units) { … } /** * pcpu_free_alloc_info - free percpu allocation info * @ai: pcpu_alloc_info to free * * Free @ai which was allocated by pcpu_alloc_alloc_info(). */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { … } /** * pcpu_dump_alloc_info - print out information about pcpu_alloc_info * @lvl: loglevel * @ai: allocation info to dump * * Print out information about @ai using loglevel @lvl. */ static void pcpu_dump_alloc_info(const char *lvl, const struct pcpu_alloc_info *ai) { … } /** * pcpu_setup_first_chunk - initialize the first percpu chunk * @ai: pcpu_alloc_info describing how to percpu area is shaped * @base_addr: mapped address * * Initialize the first percpu chunk which contains the kernel static * percpu area. This function is to be called from arch percpu area * setup path. * * @ai contains all information necessary to initialize the first * chunk and prime the dynamic percpu allocator. * * @ai->static_size is the size of static percpu area. * * @ai->reserved_size, if non-zero, specifies the amount of bytes to * reserve after the static area in the first chunk. This reserves * the first chunk such that it's available only through reserved * percpu allocation. This is primarily used to serve module percpu * static areas on architectures where the addressing model has * limited offset range for symbol relocations to guarantee module * percpu symbols fall inside the relocatable range. * * @ai->dyn_size determines the number of bytes available for dynamic * allocation in the first chunk. The area between @ai->static_size + * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused. * * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE * and equal to or larger than @ai->static_size + @ai->reserved_size + * @ai->dyn_size. * * @ai->atom_size is the allocation atom size and used as alignment * for vm areas. * * @ai->alloc_size is the allocation size and always multiple of * @ai->atom_size. This is larger than @ai->atom_size if * @ai->unit_size is larger than @ai->atom_size. * * @ai->nr_groups and @ai->groups describe virtual memory layout of * percpu areas. Units which should be colocated are put into the * same group. Dynamic VM areas will be allocated according to these * groupings. If @ai->nr_groups is zero, a single group containing * all units is assumed. * * The caller should have mapped the first chunk at @base_addr and * copied static data to each unit. * * The first chunk will always contain a static and a dynamic region. * However, the static region is not managed by any chunk. If the first * chunk also contains a reserved region, it is served by two chunks - * one for the reserved region and one for the dynamic region. They * share the same vm, but use offset regions in the area allocation map. * The chunk serving the dynamic region is circulated in the chunk slots * and available for dynamic allocation like any other chunk. */ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr) { … } #ifdef CONFIG_SMP const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = …; enum pcpu_fc pcpu_chosen_fc __initdata = …; static int __init percpu_alloc_setup(char *str) { … } early_param(…); /* * pcpu_embed_first_chunk() is used by the generic percpu setup. * Build it if needed by the arch config or the generic setup is going * to be used. */ #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \ !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) #define BUILD_EMBED_FIRST_CHUNK #endif /* build pcpu_page_first_chunk() iff needed by the arch config */ #if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) #define BUILD_PAGE_FIRST_CHUNK #endif /* pcpu_build_alloc_info() is used by both embed and page first chunk */ #if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK) /** * pcpu_build_alloc_info - build alloc_info considering distances between CPUs * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * * This function determines grouping of units, their mappings to cpus * and other parameters considering needed percpu size, allocation * atom size and distances between CPUs. * * Groups are always multiples of atom size and CPUs which are of * LOCAL_DISTANCE both ways are grouped together and share space for * units in the same group. The returned configuration is guaranteed * to have CPUs on different nodes on different groups and >=75% usage * of allocated virtual address space. * * RETURNS: * On success, pointer to the new allocation_info is returned. On * failure, ERR_PTR value is returned. */ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn) { … } static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { … } static void __init pcpu_fc_free(void *ptr, size_t size) { … } #endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ #if defined(BUILD_EMBED_FIRST_CHUNK) /** * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated * by calling pcpu_fc_alloc and used as-is without being mapped into * vmalloc area. Allocations are always whole multiples of @atom_size * aligned to @atom_size. * * This enables the first chunk to piggy back on the linear physical * mapping which often uses larger page size. Please note that this * can result in very sparse cpu->unit mapping on NUMA machines thus * requiring large vmalloc address space. Don't use this allocator if * vmalloc space is not orders of magnitude larger than distances * between node memory addresses (ie. 32bit NUMA machines). * * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit * size, the leftover is returned using pcpu_fc_free. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { … } #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK #include <asm/pgalloc.h> #ifndef P4D_TABLE_SIZE #define P4D_TABLE_SIZE … #endif #ifndef PUD_TABLE_SIZE #define PUD_TABLE_SIZE … #endif #ifndef PMD_TABLE_SIZE #define PMD_TABLE_SIZE … #endif #ifndef PTE_TABLE_SIZE #define PTE_TABLE_SIZE … #endif void __init __weak pcpu_populate_pte(unsigned long addr) { … } /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up page-remapped first percpu * chunk and can be called where pcpu_setup_first_chunk() is expected. * * This is the basic allocator. Static percpu area is allocated * page-by-page into vmalloc area. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { … } #endif /* BUILD_PAGE_FIRST_CHUNK */ #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA /* * Generic SMP percpu area setup. * * The embedding helper is used because its behavior closely resembles * the original non-dynamic generic percpu area setup. This is * important because many archs have addressing restrictions and might * fail if the percpu area is located far away from the previous * location. As an added bonus, in non-NUMA cases, embedding is * generally a good idea TLB-wise because percpu area can piggy back * on the physical linear memory mapping which uses large page * mappings on applicable archs. */ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); void __init setup_per_cpu_areas(void) { unsigned long delta; unsigned int cpu; int rc; /* * Always reserve area for module percpu variables. That's * what the legacy allocator did. */ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, NULL); if (rc < 0) panic("Failed to initialize percpu areas."); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; } #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ #else /* CONFIG_SMP */ /* * UP percpu area setup. * * UP always uses km-based percpu allocator with identity mapping. * Static percpu variables are indistinguishable from the usual static * variables and don't require any special preparation. */ void __init setup_per_cpu_areas(void) { const size_t unit_size = roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE, PERCPU_DYNAMIC_RESERVE)); struct pcpu_alloc_info *ai; void *fc; ai = pcpu_alloc_alloc_info(1, 1); fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(fc)); ai->dyn_size = unit_size; ai->unit_size = unit_size; ai->atom_size = unit_size; ai->alloc_size = unit_size; ai->groups[0].nr_units = 1; ai->groups[0].cpu_map[0] = 0; pcpu_setup_first_chunk(ai, fc); pcpu_free_alloc_info(ai); } #endif /* CONFIG_SMP */ /* * pcpu_nr_pages - calculate total number of populated backing pages * * This reflects the number of pages populated to back chunks. Metadata is * excluded in the number exposed in meminfo as the number of backing pages * scales with the number of cpus and can quickly outweigh the memory used for * metadata. It also keeps this calculation nice and simple. * * RETURNS: * Total number of populated backing pages in use by the allocator. */ unsigned long pcpu_nr_pages(void) { … } /* * Percpu allocator is initialized early during boot when neither slab or * workqueue is available. Plug async management until everything is up * and running. */ static int __init percpu_enable_async(void) { … } subsys_initcall(percpu_enable_async);
Codebase Browser
linux