// 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 <tj@kernel.org> * * Copyright (C) 2017 Facebook Inc. * Copyright (C) 2017 Dennis Zhou <dennis@kernel.org> * * 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) KBUILD_MODNAME ": " 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 5/* chunks in slots below this are subject to being sidelined on failed alloc */#define PCPU_SLOT_FAIL_THRESHOLD 3 #define PCPU_EMPTY_POP_PAGES_LOW 2#define PCPU_EMPTY_POP_PAGES_HIGH 4 #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) \ (void __percpu *)((unsigned long)(addr) - \ (unsigned long)pcpu_base_addr + \ (unsigned long)__per_cpu_start)#endif#ifndef __pcpu_ptr_to_addr#define __pcpu_ptr_to_addr(ptr) \ (void __force *)((unsigned long)(ptr) + \ (unsigned long)pcpu_base_addr - \ (unsigned long)__per_cpu_start)#endif#else /* CONFIG_SMP *//* on UP, it's always identity mapped */#define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr)#define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr)#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(pcpu_lock); /* 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){ if (pcpu_async_enabled) schedule_work(&pcpu_balance_work);} /** * 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){ void *start_addr, *end_addr; if (!chunk) return false; start_addr = chunk->base_addr + chunk->start_offset; end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE - chunk->end_offset; return addr >= start_addr && addr < end_addr;} static int __pcpu_size_to_slot(int size){ int highbit = fls(size); /* size is in bytes */ return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1);} static int pcpu_size_to_slot(int size){ if (size == pcpu_unit_size) return pcpu_free_slot; return __pcpu_size_to_slot(size);} static int pcpu_chunk_slot(const struct pcpu_chunk *chunk){ const struct pcpu_block_md *chunk_md = &chunk->chunk_md; if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || chunk_md->contig_hint == 0) return 0; return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE);} /* set the pointer to a chunk in a page struct */static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu){ page->private = (unsigned long)pcpu;} /* obtain pointer to a chunk from a page struct */static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page){ return (struct pcpu_chunk *)page->private;} static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx){ return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx;} static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx){ return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT);} static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx){ return (unsigned long)chunk->base_addr + pcpu_unit_page_offset(cpu, 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){ return chunk->alloc_map + (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG);} static unsigned long pcpu_off_to_block_index(int off){ return off / PCPU_BITMAP_BLOCK_BITS;} static unsigned long pcpu_off_to_block_off(int off){ return off & (PCPU_BITMAP_BLOCK_BITS - 1);} static unsigned long pcpu_block_off_to_off(int index, int off){ return index * PCPU_BITMAP_BLOCK_BITS + 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){ int bit_off = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; return bit_off + bits <= block->contig_hint;} /* * 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){ /* * The three conditions below determine if we can skip past the * scan_hint. First, does the scan hint exist. Second, is the * contig_hint after the scan_hint (possibly not true iff * contig_hint == scan_hint). Third, is the allocation request * larger than the scan_hint. */ if (block->scan_hint && block->contig_hint_start > block->scan_hint_start && alloc_bits > block->scan_hint) return block->scan_hint_start + block->scan_hint; return block->first_free;} /** * 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){ int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; return; } /* * This checks three things. First is there a contig_hint to * check. Second, have we checked this hint before by * comparing the block_off. Third, is this the same as the * right contig hint. In the last case, it spills over into * the next block and should be handled by the contig area * across blocks code. */ *bits = block->contig_hint; if (*bits && block->contig_hint_start >= block_off && *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) { *bit_off = pcpu_block_off_to_off(i, block->contig_hint_start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; }} /** * 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){ int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (*bits >= alloc_bits) return; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; } /* check block->contig_hint */ *bits = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; /* * This uses the block offset to determine if this has been * checked in the prior iteration. */ if (block->contig_hint && block->contig_hint_start >= block_off && block->contig_hint >= *bits + alloc_bits) { int start = pcpu_next_hint(block, alloc_bits); *bits += alloc_bits + block->contig_hint_start - start; *bit_off = pcpu_block_off_to_off(i, start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); *bits = PCPU_BITMAP_BLOCK_BITS - *bit_off; *bit_off = pcpu_block_off_to_off(i, *bit_off); if (*bits >= alloc_bits) return; } /* no valid offsets were found - fail condition */ *bit_off = pcpu_chunk_map_bits(chunk);} /* * 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) \ for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits) + 1, \ pcpu_next_md_free_region((chunk), &(bit_off), &(bits))) #define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \ for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits), \ pcpu_next_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. *Lines 1–500 of 3388. Load more
// 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 <tj@kernel.org> * * Copyright (C) 2017 Facebook Inc. * Copyright (C) 2017 Dennis Zhou <dennis@kernel.org> * * 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) KBUILD_MODNAME ": " 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 5 /* chunks in slots below this are subject to being sidelined on failed alloc */ #define PCPU_SLOT_FAIL_THRESHOLD 3 #define PCPU_EMPTY_POP_PAGES_LOW 2 #define PCPU_EMPTY_POP_PAGES_HIGH 4 #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) \ (void __percpu *)((unsigned long)(addr) - \ (unsigned long)pcpu_base_addr + \ (unsigned long)__per_cpu_start) #endif #ifndef __pcpu_ptr_to_addr #define __pcpu_ptr_to_addr(ptr) \ (void __force *)((unsigned long)(ptr) + \ (unsigned long)pcpu_base_addr - \ (unsigned long)__per_cpu_start) #endif #else /* CONFIG_SMP */ /* on UP, it's always identity mapped */ #define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr) #define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr) #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(pcpu_lock); /* 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) { if (pcpu_async_enabled) schedule_work(&pcpu_balance_work); } /** * 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) { void *start_addr, *end_addr; if (!chunk) return false; start_addr = chunk->base_addr + chunk->start_offset; end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE - chunk->end_offset; return addr >= start_addr && addr < end_addr; } static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); } static int pcpu_size_to_slot(int size) { if (size == pcpu_unit_size) return pcpu_free_slot; return __pcpu_size_to_slot(size); } static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) { const struct pcpu_block_md *chunk_md = &chunk->chunk_md; if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || chunk_md->contig_hint == 0) return 0; return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE); } /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { page->private = (unsigned long)pcpu; } /* obtain pointer to a chunk from a page struct */ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { return (struct pcpu_chunk *)page->private; } static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx) { return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); } static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { return (unsigned long)chunk->base_addr + pcpu_unit_page_offset(cpu, 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) { return chunk->alloc_map + (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG); } static unsigned long pcpu_off_to_block_index(int off) { return off / PCPU_BITMAP_BLOCK_BITS; } static unsigned long pcpu_off_to_block_off(int off) { return off & (PCPU_BITMAP_BLOCK_BITS - 1); } static unsigned long pcpu_block_off_to_off(int index, int off) { return index * PCPU_BITMAP_BLOCK_BITS + 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) { int bit_off = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; return bit_off + bits <= block->contig_hint; } /* * 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) { /* * The three conditions below determine if we can skip past the * scan_hint. First, does the scan hint exist. Second, is the * contig_hint after the scan_hint (possibly not true iff * contig_hint == scan_hint). Third, is the allocation request * larger than the scan_hint. */ if (block->scan_hint && block->contig_hint_start > block->scan_hint_start && alloc_bits > block->scan_hint) return block->scan_hint_start + block->scan_hint; return block->first_free; } /** * 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) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; return; } /* * This checks three things. First is there a contig_hint to * check. Second, have we checked this hint before by * comparing the block_off. Third, is this the same as the * right contig hint. In the last case, it spills over into * the next block and should be handled by the contig area * across blocks code. */ *bits = block->contig_hint; if (*bits && block->contig_hint_start >= block_off && *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) { *bit_off = pcpu_block_off_to_off(i, block->contig_hint_start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; } } /** * 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) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (*bits >= alloc_bits) return; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; } /* check block->contig_hint */ *bits = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; /* * This uses the block offset to determine if this has been * checked in the prior iteration. */ if (block->contig_hint && block->contig_hint_start >= block_off && block->contig_hint >= *bits + alloc_bits) { int start = pcpu_next_hint(block, alloc_bits); *bits += alloc_bits + block->contig_hint_start - start; *bit_off = pcpu_block_off_to_off(i, start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); *bits = PCPU_BITMAP_BLOCK_BITS - *bit_off; *bit_off = pcpu_block_off_to_off(i, *bit_off); if (*bits >= alloc_bits) return; } /* no valid offsets were found - fail condition */ *bit_off = pcpu_chunk_map_bits(chunk); } /* * 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) \ for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits) + 1, \ pcpu_next_md_free_region((chunk), &(bit_off), &(bits))) #define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \ for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits), \ pcpu_next_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. *