diff options
Diffstat (limited to 'mm/percpu.c')
| -rw-r--r-- | mm/percpu.c | 1921 |
1 files changed, 1308 insertions, 613 deletions
diff --git a/mm/percpu.c b/mm/percpu.c index c0b2c1a76e8..2ddf9a990db 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1,5 +1,5 @@ /* - * linux/mm/percpu.c - percpu memory allocator + * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo <tj@kernel.org> @@ -7,13 +7,13 @@ * This file is released under the GPLv2. * * This is percpu allocator which can handle both static and dynamic - * areas. Percpu areas are allocated in chunks in vmalloc area. Each - * chunk is consisted of num_possible_cpus() units and the first chunk - * is used for static percpu variables in the kernel image (special - * boot time alloc/init handling necessary as these areas need to be - * brought up before allocation services are running). Unit grows as - * necessary and all units grow or shrink in unison. When a chunk is - * filled up, another chunk is allocated. ie. in vmalloc area + * areas. Percpu areas are allocated in chunks. Each chunk is + * consisted of boot-time determined number of units and the first + * chunk is used for static percpu variables in the kernel image + * (special boot time alloc/init handling necessary as these areas + * need to be brought up before allocation services are running). + * Unit grows as necessary and all units grow or shrink in unison. + * When a chunk is filled up, another chunk is allocated. * * c0 c1 c2 * ------------------- ------------------- ------------ @@ -22,14 +22,16 @@ * * Allocation is done in offset-size areas of single unit space. Ie, * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0, - * c1:u1, c1:u2 and c1:u3. Percpu access can be done by configuring - * percpu base registers pcpu_unit_size apart. + * c1:u1, c1:u2 and c1:u3. On UMA, units corresponds directly to + * cpus. On NUMA, the mapping can be non-linear and even sparse. + * Percpu access can be done by configuring percpu base registers + * according to cpu to unit mapping and pcpu_unit_size. * - * There are usually many small percpu allocations many of them as - * small as 4 bytes. The allocator organizes chunks into lists + * There are usually many small percpu allocations many of them being + * as small as 4 bytes. The allocator organizes chunks into lists * according to free size and tries to allocate from the fullest one. * Each chunk keeps the maximum contiguous area size hint which is - * guaranteed to be eqaul to or larger than the maximum contiguous + * guaranteed to be equal to or larger than the maximum contiguous * area in the chunk. This helps the allocator not to iterate the * chunk maps unnecessarily. * @@ -43,8 +45,6 @@ * * To use this allocator, arch code should do the followings. * - * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA - * * - 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 @@ -55,7 +55,9 @@ #include <linux/bitmap.h> #include <linux/bootmem.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> @@ -65,49 +67,73 @@ #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> +#include <linux/kmemleak.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/tlbflush.h> +#include <asm/io.h> #define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */ #define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */ +#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 *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr \ - + (unsigned long)__per_cpu_start) + (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 *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr \ - - (unsigned long)__per_cpu_start) + (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 */ struct pcpu_chunk { struct list_head list; /* linked to pcpu_slot lists */ int free_size; /* free bytes in the chunk */ int contig_hint; /* max contiguous size hint */ - struct vm_struct *vm; /* mapped vmalloc region */ - int map_used; /* # of map entries used */ + void *base_addr; /* base address of this chunk */ + int map_used; /* # of map entries used before the sentry */ int map_alloc; /* # of map entries allocated */ int *map; /* allocation map */ + void *data; /* chunk data */ + int first_free; /* no free below this */ bool immutable; /* no [de]population allowed */ - struct page **page; /* points to page array */ - struct page *page_ar[]; /* #cpus * UNIT_PAGES */ + unsigned long populated[]; /* populated bitmap */ }; static int pcpu_unit_pages __read_mostly; static int pcpu_unit_size __read_mostly; -static int pcpu_chunk_size __read_mostly; +static int pcpu_nr_units __read_mostly; +static int pcpu_atom_size __read_mostly; static int pcpu_nr_slots __read_mostly; static size_t pcpu_chunk_struct_size __read_mostly; +/* cpus with the lowest and highest unit addresses */ +static unsigned int pcpu_low_unit_cpu __read_mostly; +static unsigned int pcpu_high_unit_cpu __read_mostly; + /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __read_mostly; EXPORT_SYMBOL_GPL(pcpu_base_addr); +static const int *pcpu_unit_map __read_mostly; /* cpu -> unit */ +const unsigned long *pcpu_unit_offsets __read_mostly; /* cpu -> unit offset */ + +/* group information, used for vm allocation */ +static int pcpu_nr_groups __read_mostly; +static const unsigned long *pcpu_group_offsets __read_mostly; +static const size_t *pcpu_group_sizes __read_mostly; + /* * The first chunk which always exists. Note that unlike other * chunks, this one can be allocated and mapped in several different @@ -129,13 +155,16 @@ static int pcpu_reserved_chunk_limit; * Synchronization rules. * * There are two locks - pcpu_alloc_mutex and pcpu_lock. The former - * protects allocation/reclaim paths, chunks and chunk->page arrays. - * The latter is a spinlock and protects the index data structures - - * chunk slots, chunks and area maps in chunks. + * protects allocation/reclaim paths, chunks, populated bitmap and + * vmalloc mapping. The latter is a spinlock and protects the index + * data structures - chunk slots, chunks and area maps in chunks. * * During allocation, pcpu_alloc_mutex is kept locked all the time and * pcpu_lock is grabbed and released as necessary. All actual memory - * allocations are done using GFP_KERNEL with pcpu_lock released. + * allocations are done using GFP_KERNEL with pcpu_lock released. In + * general, percpu memory can't be allocated with irq off but + * irqsave/restore are still used in alloc path so that it can be used + * from early init path - sched_init() specifically. * * Free path accesses and alters only the index data structures, so it * can be safely called from atomic context. When memory needs to be @@ -155,6 +184,21 @@ static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */ static void pcpu_reclaim(struct work_struct *work); static DECLARE_WORK(pcpu_reclaim_work, pcpu_reclaim); +static bool pcpu_addr_in_first_chunk(void *addr) +{ + void *first_start = pcpu_first_chunk->base_addr; + + return addr >= first_start && addr < first_start + pcpu_unit_size; +} + +static bool pcpu_addr_in_reserved_chunk(void *addr) +{ + void *first_start = pcpu_first_chunk->base_addr; + + return addr >= first_start && + addr < first_start + pcpu_reserved_chunk_limit; +} + static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ @@ -176,48 +220,66 @@ static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) return pcpu_size_to_slot(chunk->free_size); } -static int pcpu_page_idx(unsigned int cpu, int page_idx) +/* set the pointer to a chunk in a page struct */ +static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { - return cpu * pcpu_unit_pages + page_idx; + page->index = (unsigned long)pcpu; } -static struct page **pcpu_chunk_pagep(struct pcpu_chunk *chunk, - unsigned int cpu, int page_idx) +/* obtain pointer to a chunk from a page struct */ +static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { - return &chunk->page[pcpu_page_idx(cpu, page_idx)]; + return (struct pcpu_chunk *)page->index; } -static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, - unsigned int cpu, int page_idx) +static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { - return (unsigned long)chunk->vm->addr + - (pcpu_page_idx(cpu, page_idx) << PAGE_SHIFT); + return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } -static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk, - int page_idx) +static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) { - return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL; + return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] + + (page_idx << PAGE_SHIFT); } -/* set the pointer to a chunk in a page struct */ -static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) +static void __maybe_unused pcpu_next_unpop(struct pcpu_chunk *chunk, + int *rs, int *re, int end) { - page->index = (unsigned long)pcpu; + *rs = find_next_zero_bit(chunk->populated, end, *rs); + *re = find_next_bit(chunk->populated, end, *rs + 1); } -/* obtain pointer to a chunk from a page struct */ -static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) +static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk, + int *rs, int *re, int end) { - return (struct pcpu_chunk *)page->index; + *rs = find_next_bit(chunk->populated, end, *rs); + *re = find_next_zero_bit(chunk->populated, end, *rs + 1); } +/* + * (Un)populated page region iterators. Iterate over (un)populated + * page regions between @start and @end in @chunk. @rs and @re should + * be integer variables and will be set to start and end page index of + * the current region. + */ +#define pcpu_for_each_unpop_region(chunk, rs, re, start, end) \ + for ((rs) = (start), pcpu_next_unpop((chunk), &(rs), &(re), (end)); \ + (rs) < (re); \ + (rs) = (re) + 1, pcpu_next_unpop((chunk), &(rs), &(re), (end))) + +#define pcpu_for_each_pop_region(chunk, rs, re, start, end) \ + for ((rs) = (start), pcpu_next_pop((chunk), &(rs), &(re), (end)); \ + (rs) < (re); \ + (rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end))) + /** - * pcpu_mem_alloc - allocate memory + * pcpu_mem_zalloc - allocate memory * @size: bytes to allocate * * Allocate @size bytes. If @size is smaller than PAGE_SIZE, - * kzalloc() is used; otherwise, vmalloc() is used. The returned + * kzalloc() is used; otherwise, vzalloc() is used. The returned * memory is always zeroed. * * CONTEXT: @@ -226,16 +288,15 @@ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ -static void *pcpu_mem_alloc(size_t size) +static void *pcpu_mem_zalloc(size_t size) { + if (WARN_ON_ONCE(!slab_is_available())) + return NULL; + if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); - else { - void *ptr = vmalloc(size); - if (ptr) - memset(ptr, 0, size); - return ptr; - } + else + return vzalloc(size); } /** @@ -243,7 +304,7 @@ static void *pcpu_mem_alloc(size_t size) * @ptr: memory to free * @size: size of the area * - * Free @ptr. @ptr should have been allocated using pcpu_mem_alloc(). + * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). */ static void pcpu_mem_free(void *ptr, size_t size) { @@ -279,127 +340,82 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) } /** - * pcpu_chunk_addr_search - determine chunk containing specified address - * @addr: address for which the chunk needs to be determined. + * pcpu_need_to_extend - determine whether chunk area map needs to be extended + * @chunk: chunk of interest + * + * Determine whether area map of @chunk needs to be extended to + * accommodate a new allocation. + * + * CONTEXT: + * pcpu_lock. * * RETURNS: - * The address of the found chunk. + * New target map allocation length if extension is necessary, 0 + * otherwise. */ -static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) +static int pcpu_need_to_extend(struct pcpu_chunk *chunk) { - void *first_start = pcpu_first_chunk->vm->addr; + int new_alloc; - /* is it in the first chunk? */ - if (addr >= first_start && addr < first_start + pcpu_chunk_size) { - /* is it in the reserved area? */ - if (addr < first_start + pcpu_reserved_chunk_limit) - return pcpu_reserved_chunk; - return pcpu_first_chunk; - } + if (chunk->map_alloc >= chunk->map_used + 3) + return 0; - return pcpu_get_page_chunk(vmalloc_to_page(addr)); + new_alloc = PCPU_DFL_MAP_ALLOC; + while (new_alloc < chunk->map_used + 3) + new_alloc *= 2; + + return new_alloc; } /** - * pcpu_extend_area_map - extend area map for allocation - * @chunk: target chunk + * pcpu_extend_area_map - extend area map of a chunk + * @chunk: chunk of interest + * @new_alloc: new target allocation length of the area map * - * Extend area map of @chunk so that it can accomodate an allocation. - * A single allocation can split an area into three areas, so this - * function makes sure that @chunk->map has at least two extra slots. + * Extend area map of @chunk to have @new_alloc entries. * * CONTEXT: - * pcpu_alloc_mutex, pcpu_lock. pcpu_lock is released and reacquired - * if area map is extended. + * Does GFP_KERNEL allocation. Grabs and releases pcpu_lock. * * RETURNS: - * 0 if noop, 1 if successfully extended, -errno on failure. + * 0 on success, -errno on failure. */ -static int pcpu_extend_area_map(struct pcpu_chunk *chunk) +static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc) { - int new_alloc; - int *new; - size_t size; - - /* has enough? */ - if (chunk->map_alloc >= chunk->map_used + 2) - return 0; - - spin_unlock_irq(&pcpu_lock); - - new_alloc = PCPU_DFL_MAP_ALLOC; - while (new_alloc < chunk->map_used + 2) - new_alloc *= 2; + int *old = NULL, *new = NULL; + size_t old_size = 0, new_size = new_alloc * sizeof(new[0]); + unsigned long flags; - new = pcpu_mem_alloc(new_alloc * sizeof(new[0])); - if (!new) { - spin_lock_irq(&pcpu_lock); + new = pcpu_mem_zalloc(new_size); + if (!new) return -ENOMEM; - } - /* - * Acquire pcpu_lock and switch to new area map. Only free - * could have happened inbetween, so map_used couldn't have - * grown. - */ - spin_lock_irq(&pcpu_lock); - BUG_ON(new_alloc < chunk->map_used + 2); + /* acquire pcpu_lock and switch to new area map */ + spin_lock_irqsave(&pcpu_lock, flags); - size = chunk->map_alloc * sizeof(chunk->map[0]); - memcpy(new, chunk->map, size); + if (new_alloc <= chunk->map_alloc) + goto out_unlock; - /* - * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is - * one of the first chunks and still using static map. - */ - if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC) - pcpu_mem_free(chunk->map, size); + old_size = chunk->map_alloc * sizeof(chunk->map[0]); + old = chunk->map; + + memcpy(new, old, old_size); chunk->map_alloc = new_alloc; chunk->map = new; - return 0; -} - -/** - * pcpu_split_block - split a map block - * @chunk: chunk of interest - * @i: index of map block to split - * @head: head size in bytes (can be 0) - * @tail: tail size in bytes (can be 0) - * - * Split the @i'th map block into two or three blocks. If @head is - * non-zero, @head bytes block is inserted before block @i moving it - * to @i+1 and reducing its size by @head bytes. - * - * If @tail is non-zero, the target block, which can be @i or @i+1 - * depending on @head, is reduced by @tail bytes and @tail byte block - * is inserted after the target block. - * - * @chunk->map must have enough free slots to accomodate the split. - * - * CONTEXT: - * pcpu_lock. - */ -static void pcpu_split_block(struct pcpu_chunk *chunk, int i, - int head, int tail) -{ - int nr_extra = !!head + !!tail; + new = NULL; - BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra); +out_unlock: + spin_unlock_irqrestore(&pcpu_lock, flags); - /* insert new subblocks */ - memmove(&chunk->map[i + nr_extra], &chunk->map[i], - sizeof(chunk->map[0]) * (chunk->map_used - i)); - chunk->map_used += nr_extra; + /* + * pcpu_mem_free() might end up calling vfree() which uses + * IRQ-unsafe lock and thus can't be called under pcpu_lock. + */ + pcpu_mem_free(old, old_size); + pcpu_mem_free(new, new_size); - if (head) { - chunk->map[i + 1] = chunk->map[i] - head; - chunk->map[i++] = head; - } - if (tail) { - chunk->map[i++] -= tail; - chunk->map[i] = tail; - } + return 0; } /** @@ -426,19 +442,27 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) int oslot = pcpu_chunk_slot(chunk); int max_contig = 0; int i, off; + bool seen_free = false; + int *p; - for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) { - bool is_last = i + 1 == chunk->map_used; + for (i = chunk->first_free, p = chunk->map + i; i < chunk->map_used; i++, p++) { int head, tail; + int this_size; + + off = *p; + if (off & 1) + continue; /* extra for alignment requirement */ head = ALIGN(off, align) - off; - BUG_ON(i == 0 && head != 0); - if (chunk->map[i] < 0) - continue; - if (chunk->map[i] < head + size) { - max_contig = max(chunk->map[i], max_contig); + this_size = (p[1] & ~1) - off; + if (this_size < head + size) { + if (!seen_free) { + chunk->first_free = i; + seen_free = true; + } + max_contig = max(this_size, max_contig); continue; } @@ -448,44 +472,59 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) * than sizeof(int), which is very small but isn't too * uncommon for percpu allocations. */ - if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) { - if (chunk->map[i - 1] > 0) - chunk->map[i - 1] += head; - else { - chunk->map[i - 1] -= head; + if (head && (head < sizeof(int) || !(p[-1] & 1))) { + *p = off += head; + if (p[-1] & 1) chunk->free_size -= head; - } - chunk->map[i] -= head; - off += head; + else + max_contig = max(*p - p[-1], max_contig); + this_size -= head; head = 0; } /* if tail is small, just keep it around */ - tail = chunk->map[i] - head - size; - if (tail < sizeof(int)) + tail = this_size - head - size; + if (tail < sizeof(int)) { tail = 0; + size = this_size - head; + } /* split if warranted */ if (head || tail) { - pcpu_split_block(chunk, i, head, tail); + int nr_extra = !!head + !!tail; + + /* insert new subblocks */ + memmove(p + nr_extra + 1, p + 1, + sizeof(chunk->map[0]) * (chunk->map_used - i)); + chunk->map_used += nr_extra; + if (head) { - i++; - off += head; - max_contig = max(chunk->map[i - 1], max_contig); + if (!seen_free) { + chunk->first_free = i; + seen_free = true; + } + *++p = off += head; + ++i; + max_contig = max(head, max_contig); + } + if (tail) { + p[1] = off + size; + max_contig = max(tail, max_contig); } - if (tail) - max_contig = max(chunk->map[i + 1], max_contig); } + if (!seen_free) + chunk->first_free = i + 1; + /* update hint and mark allocated */ - if (is_last) + if (i + 1 == chunk->map_used) chunk->contig_hint = max_contig; /* fully scanned */ else chunk->contig_hint = max(chunk->contig_hint, max_contig); - chunk->free_size -= chunk->map[i]; - chunk->map[i] = -chunk->map[i]; + chunk->free_size -= size; + *p |= 1; pcpu_chunk_relocate(chunk, oslot); return off; @@ -513,254 +552,142 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) { int oslot = pcpu_chunk_slot(chunk); - int i, off; - - for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) - if (off == freeme) - break; + int off = 0; + unsigned i, j; + int to_free = 0; + int *p; + + freeme |= 1; /* we are searching for <given offset, in use> pair */ + + i = 0; + j = chunk->map_used; + while (i != j) { + unsigned k = (i + j) / 2; + off = chunk->map[k]; + if (off < freeme) + i = k + 1; + else if (off > freeme) + j = k; + else + i = j = k; + } BUG_ON(off != freeme); - BUG_ON(chunk->map[i] > 0); - chunk->map[i] = -chunk->map[i]; - chunk->free_size += chunk->map[i]; + if (i < chunk->first_free) + chunk->first_free = i; + + p = chunk->map + i; + *p = off &= ~1; + chunk->free_size += (p[1] & ~1) - off; + /* merge with next? */ + if (!(p[1] & 1)) + to_free++; /* merge with previous? */ - if (i > 0 && chunk->map[i - 1] >= 0) { - chunk->map[i - 1] += chunk->map[i]; - chunk->map_used--; - memmove(&chunk->map[i], &chunk->map[i + 1], - (chunk->map_used - i) * sizeof(chunk->map[0])); + if (i > 0 && !(p[-1] & 1)) { + to_free++; i--; + p--; } - /* merge with next? */ - if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) { - chunk->map[i] += chunk->map[i + 1]; - chunk->map_used--; - memmove(&chunk->map[i + 1], &chunk->map[i + 2], - (chunk->map_used - (i + 1)) * sizeof(chunk->map[0])); + if (to_free) { + chunk->map_used -= to_free; + memmove(p + 1, p + 1 + to_free, + (chunk->map_used - i) * sizeof(chunk->map[0])); } - chunk->contig_hint = max(chunk->map[i], chunk->contig_hint); + chunk->contig_hint = max(chunk->map[i + 1] - chunk->map[i] - 1, chunk->contig_hint); pcpu_chunk_relocate(chunk, oslot); } -/** - * pcpu_unmap - unmap pages out of a pcpu_chunk - * @chunk: chunk of interest - * @page_start: page index of the first page to unmap - * @page_end: page index of the last page to unmap + 1 - * @flush: whether to flush cache and tlb or not - * - * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. - * If @flush is true, vcache is flushed before unmapping and tlb - * after. - */ -static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, - bool flush) +static struct pcpu_chunk *pcpu_alloc_chunk(void) { - unsigned int last = num_possible_cpus() - 1; - unsigned int cpu; - - /* unmap must not be done on immutable chunk */ - WARN_ON(chunk->immutable); - - /* - * Each flushing trial can be very expensive, issue flush on - * the whole region at once rather than doing it for each cpu. - * This could be an overkill but is more scalable. - */ - if (flush) - flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start), - pcpu_chunk_addr(chunk, last, page_end)); - - for_each_possible_cpu(cpu) - unmap_kernel_range_noflush( - pcpu_chunk_addr(chunk, cpu, page_start), - (page_end - page_start) << PAGE_SHIFT); - - /* ditto as flush_cache_vunmap() */ - if (flush) - flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start), - pcpu_chunk_addr(chunk, last, page_end)); -} - -/** - * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk - * @chunk: chunk to depopulate - * @off: offset to the area to depopulate - * @size: size of the area to depopulate in bytes - * @flush: whether to flush cache and tlb or not - * - * For each cpu, depopulate and unmap pages [@page_start,@page_end) - * from @chunk. If @flush is true, vcache is flushed before unmapping - * and tlb after. - * - * CONTEXT: - * pcpu_alloc_mutex. - */ -static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size, - bool flush) -{ - int page_start = PFN_DOWN(off); - int page_end = PFN_UP(off + size); - int unmap_start = -1; - int uninitialized_var(unmap_end); - unsigned int cpu; - int i; - - for (i = page_start; i < page_end; i++) { - for_each_possible_cpu(cpu) { - struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); - - if (!*pagep) - continue; - - __free_page(*pagep); - - /* - * If it's partial depopulation, it might get - * populated or depopulated again. Mark the - * page gone. - */ - *pagep = NULL; - - unmap_start = unmap_start < 0 ? i : unmap_start; - unmap_end = i + 1; - } - } - - if (unmap_start >= 0) - pcpu_unmap(chunk, unmap_start, unmap_end, flush); -} - -/** - * pcpu_map - map pages into a pcpu_chunk - * @chunk: chunk of interest - * @page_start: page index of the first page to map - * @page_end: page index of the last page to map + 1 - * - * For each cpu, map pages [@page_start,@page_end) into @chunk. - * vcache is flushed afterwards. - */ -static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end) -{ - unsigned int last = num_possible_cpus() - 1; - unsigned int cpu; - int err; - - /* map must not be done on immutable chunk */ - WARN_ON(chunk->immutable); - - for_each_possible_cpu(cpu) { - err = map_kernel_range_noflush( - pcpu_chunk_addr(chunk, cpu, page_start), - (page_end - page_start) << PAGE_SHIFT, - PAGE_KERNEL, - pcpu_chunk_pagep(chunk, cpu, page_start)); - if (err < 0) - return err; - } - - /* flush at once, please read comments in pcpu_unmap() */ - flush_cache_vmap(pcpu_chunk_addr(chunk, 0, page_start), - pcpu_chunk_addr(chunk, last, page_end)); - return 0; -} - -/** - * pcpu_populate_chunk - populate and map an area of a pcpu_chunk - * @chunk: chunk of interest - * @off: offset to the area to populate - * @size: size of the area to populate in bytes - * - * For each cpu, populate and map pages [@page_start,@page_end) into - * @chunk. The area is cleared on return. - * - * CONTEXT: - * pcpu_alloc_mutex, does GFP_KERNEL allocation. - */ -static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) -{ - const gfp_t alloc_mask = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; - int page_start = PFN_DOWN(off); - int page_end = PFN_UP(off + size); - int map_start = -1; - int uninitialized_var(map_end); - unsigned int cpu; - int i; - - for (i = page_start; i < page_end; i++) { - if (pcpu_chunk_page_occupied(chunk, i)) { - if (map_start >= 0) { - if (pcpu_map(chunk, map_start, map_end)) - goto err; - map_start = -1; - } - continue; - } - - map_start = map_start < 0 ? i : map_start; - map_end = i + 1; + struct pcpu_chunk *chunk; - for_each_possible_cpu(cpu) { - struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size); + if (!chunk) + return NULL; - *pagep = alloc_pages_node(cpu_to_node(cpu), - alloc_mask, 0); - if (!*pagep) - goto err; - pcpu_set_page_chunk(*pagep, chunk); - } + chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC * + sizeof(chunk->map[0])); + if (!chunk->map) { + pcpu_mem_free(chunk, pcpu_chunk_struct_size); + return NULL; } - if (map_start >= 0 && pcpu_map(chunk, map_start, map_end)) - goto err; + chunk->map_alloc = PCPU_DFL_MAP_ALLOC; + chunk->map[0] = 0; + chunk->map[1] = pcpu_unit_size | 1; + chunk->map_used = 1; - for_each_possible_cpu(cpu) - memset(chunk->vm->addr + cpu * pcpu_unit_size + off, 0, - size); + INIT_LIST_HEAD(&chunk->list); + chunk->free_size = pcpu_unit_size; + chunk->contig_hint = pcpu_unit_size; - return 0; -err: - /* likely under heavy memory pressure, give memory back */ - pcpu_depopulate_chunk(chunk, off, size, true); - return -ENOMEM; + return chunk; } -static void free_pcpu_chunk(struct pcpu_chunk *chunk) +static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; - if (chunk->vm) - free_vm_area(chunk->vm); pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0])); - kfree(chunk); + pcpu_mem_free(chunk, pcpu_chunk_struct_size); } -static struct pcpu_chunk *alloc_pcpu_chunk(void) -{ - struct pcpu_chunk *chunk; - - chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL); - if (!chunk) - return NULL; - - chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); - chunk->map_alloc = PCPU_DFL_MAP_ALLOC; - chunk->map[chunk->map_used++] = pcpu_unit_size; - chunk->page = chunk->page_ar; +/* + * 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_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 off, int size); +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size); +static struct pcpu_chunk *pcpu_create_chunk(void); +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 - chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL); - if (!chunk->vm) { - free_pcpu_chunk(chunk); - return NULL; +/** + * pcpu_chunk_addr_search - determine chunk containing specified address + * @addr: address for which the chunk needs to be determined. + * + * RETURNS: + * The address of the found chunk. + */ +static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) +{ + /* is it in the first chunk? */ + if (pcpu_addr_in_first_chunk(addr)) { + /* is it in the reserved area? */ + if (pcpu_addr_in_reserved_chunk(addr)) + return pcpu_reserved_chunk; + return pcpu_first_chunk; } - INIT_LIST_HEAD(&chunk->list); - chunk->free_size = pcpu_unit_size; - chunk->contig_hint = pcpu_unit_size; - - return chunk; + /* + * The address is relative to unit0 which might be unused and + * thus unmapped. Offset the address to the unit space of the + * current processor before looking it up in the vmalloc + * space. Note that any possible cpu id can be used here, so + * there's no need to worry about preemption or cpu hotplug. + */ + addr += pcpu_unit_offsets[raw_smp_processor_id()]; + return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); } /** @@ -777,10 +704,24 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void) * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ -static void *pcpu_alloc(size_t size, size_t align, bool reserved) +static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved) { + static int warn_limit = 10; struct pcpu_chunk *chunk; - int slot, off; + const char *err; + int slot, off, new_alloc; + unsigned long flags; + void __percpu *ptr; + + /* + * We want the lowest bit of offset available for in-use/free + * indicator, so force >= 16bit alignment and make size even. + */ + if (unlikely(align < 2)) + align = 2; + + if (unlikely(size & 1)) + size++; if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) { WARN(true, "illegal size (%zu) or align (%zu) for " @@ -789,17 +730,31 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved) } mutex_lock(&pcpu_alloc_mutex); - spin_lock_irq(&pcpu_lock); + spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ if (reserved && pcpu_reserved_chunk) { chunk = pcpu_reserved_chunk; - if (size > chunk->contig_hint || - pcpu_extend_area_map(chunk) < 0) + + if (size > chunk->contig_hint) { + err = "alloc from reserved chunk failed"; goto fail_unlock; + } + + while ((new_alloc = pcpu_need_to_extend(chunk))) { + spin_unlock_irqrestore(&pcpu_lock, flags); + if (pcpu_extend_area_map(chunk, new_alloc) < 0) { + err = "failed to extend area map of reserved chunk"; + goto fail_unlock_mutex; + } + spin_lock_irqsave(&pcpu_lock, flags); + } + off = pcpu_alloc_area(chunk, size, align); if (off >= 0) goto area_found; + + err = "alloc from reserved chunk failed"; goto fail_unlock; } @@ -810,13 +765,20 @@ restart: if (size > chunk->contig_hint) continue; - switch (pcpu_extend_area_map(chunk)) { - case 0: - break; - case 1: - goto restart; /* pcpu_lock dropped, restart */ - default: - goto fail_unlock; + new_alloc = pcpu_need_to_extend(chunk); + if (new_alloc) { + spin_unlock_irqrestore(&pcpu_lock, flags); + if (pcpu_extend_area_map(chunk, + new_alloc) < 0) { + err = "failed to extend area map"; + goto fail_unlock_mutex; + } + spin_lock_irqsave(&pcpu_lock, flags); + /* + * pcpu_lock has been dropped, need to + * restart cpu_slot list walking. + */ + goto restart; } off = pcpu_alloc_area(chunk, size, align); @@ -826,34 +788,47 @@ restart: } /* hmmm... no space left, create a new chunk */ - spin_unlock_irq(&pcpu_lock); + spin_unlock_irqrestore(&pcpu_lock, flags); - chunk = alloc_pcpu_chunk(); - if (!chunk) + chunk = pcpu_create_chunk(); + if (!chunk) { + err = "failed to allocate new chunk"; goto fail_unlock_mutex; + } - spin_lock_irq(&pcpu_lock); + spin_lock_irqsave(&pcpu_lock, flags); pcpu_chunk_relocate(chunk, -1); goto restart; area_found: - spin_unlock_irq(&pcpu_lock); + spin_unlock_irqrestore(&pcpu_lock, flags); /* populate, map and clear the area */ if (pcpu_populate_chunk(chunk, off, size)) { - spin_lock_irq(&pcpu_lock); + spin_lock_irqsave(&pcpu_lock, flags); pcpu_free_area(chunk, off); + err = "failed to populate"; goto fail_unlock; } mutex_unlock(&pcpu_alloc_mutex); - return __addr_to_pcpu_ptr(chunk->vm->addr + off); + /* return address relative to base address */ + ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); + kmemleak_alloc_percpu(ptr, size); + return ptr; fail_unlock: - spin_unlock_irq(&pcpu_lock); + spin_unlock_irqrestore(&pcpu_lock, flags); fail_unlock_mutex: mutex_unlock(&pcpu_alloc_mutex); + if (warn_limit) { + pr_warning("PERCPU: allocation failed, size=%zu align=%zu, " + "%s\n", size, align, err); + dump_stack(); + if (!--warn_limit) + pr_info("PERCPU: limit reached, disable warning\n"); + } return NULL; } @@ -862,8 +837,8 @@ fail_unlock_mutex: * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * - * Allocate percpu area of @size bytes aligned at @align. Might - * sleep. Might trigger writeouts. + * Allocate zero-filled percpu area of @size bytes aligned at @align. + * Might sleep. Might trigger writeouts. * * CONTEXT: * Does GFP_KERNEL allocation. @@ -871,7 +846,7 @@ fail_unlock_mutex: * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ -void *__alloc_percpu(size_t size, size_t align) +void __percpu *__alloc_percpu(size_t size, size_t align) { return pcpu_alloc(size, align, false); } @@ -882,9 +857,10 @@ EXPORT_SYMBOL_GPL(__alloc_percpu); * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * - * Allocate percpu area of @size bytes aligned at @align from reserved - * percpu area if arch has set it up; otherwise, allocation is served - * from the same dynamic area. Might sleep. Might trigger writeouts. + * Allocate zero-filled percpu area of @size bytes aligned at @align + * from reserved percpu area if arch has set it up; otherwise, + * allocation is served from the same dynamic area. Might sleep. + * Might trigger writeouts. * * CONTEXT: * Does GFP_KERNEL allocation. @@ -892,7 +868,7 @@ EXPORT_SYMBOL_GPL(__alloc_percpu); * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ -void *__alloc_reserved_percpu(size_t size, size_t align) +void __percpu *__alloc_reserved_percpu(size_t size, size_t align) { return pcpu_alloc(size, align, true); } @@ -926,12 +902,13 @@ static void pcpu_reclaim(struct work_struct *work) } spin_unlock_irq(&pcpu_lock); - mutex_unlock(&pcpu_alloc_mutex); list_for_each_entry_safe(chunk, next, &todo, list) { - pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size, false); - free_pcpu_chunk(chunk); + pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size); + pcpu_destroy_chunk(chunk); } + + mutex_unlock(&pcpu_alloc_mutex); } /** @@ -943,9 +920,9 @@ static void pcpu_reclaim(struct work_struct *work) * CONTEXT: * Can be called from atomic context. */ -void free_percpu(void *ptr) +void free_percpu(void __percpu *ptr) { - void *addr = __pcpu_ptr_to_addr(ptr); + void *addr; struct pcpu_chunk *chunk; unsigned long flags; int off; @@ -953,10 +930,14 @@ void free_percpu(void *ptr) if (!ptr) return; + kmemleak_free_percpu(ptr); + + addr = __pcpu_ptr_to_addr(ptr); + spin_lock_irqsave(&pcpu_lock, flags); chunk = pcpu_chunk_addr_search(addr); - off = addr - chunk->vm->addr; + off = addr - chunk->base_addr; pcpu_free_area(chunk, off); @@ -976,29 +957,222 @@ void free_percpu(void *ptr) EXPORT_SYMBOL_GPL(free_percpu); /** + * 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) +{ +#ifdef CONFIG_SMP + const size_t static_size = __per_cpu_end - __per_cpu_start; + void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); + unsigned int cpu; + + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(base, cpu); + + if ((void *)addr >= start && (void *)addr < start + static_size) + return true; + } +#endif + /* on UP, can't distinguish from other static vars, always false */ + return false; +} + +/** + * 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 tranlated 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) +{ + void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); + bool in_first_chunk = false; + unsigned long first_low, first_high; + unsigned int cpu; + + /* + * The following test on unit_low/high isn't strictly + * necessary but will speed up lookups of addresses which + * aren't in the first chunk. + */ + first_low = pcpu_chunk_addr(pcpu_first_chunk, pcpu_low_unit_cpu, 0); + first_high = pcpu_chunk_addr(pcpu_first_chunk, pcpu_high_unit_cpu, + pcpu_unit_pages); + if ((unsigned long)addr >= first_low && + (unsigned long)addr < first_high) { + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(base, cpu); + + if (addr >= start && addr < start + pcpu_unit_size) { + in_first_chunk = true; + break; + } + } + } + + if (in_first_chunk) { + if (!is_vmalloc_addr(addr)) + return __pa(addr); + else + return page_to_phys(vmalloc_to_page(addr)) + + offset_in_page(addr); + } else + return page_to_phys(pcpu_addr_to_page(addr)) + + offset_in_page(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) +{ + struct pcpu_alloc_info *ai; + size_t base_size, ai_size; + void *ptr; + int unit; + + base_size = ALIGN(sizeof(*ai) + nr_groups * sizeof(ai->groups[0]), + __alignof__(ai->groups[0].cpu_map[0])); + ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); + + ptr = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), 0); + if (!ptr) + return NULL; + ai = ptr; + ptr += base_size; + + ai->groups[0].cpu_map = ptr; + + for (unit = 0; unit < nr_units; unit++) + ai->groups[0].cpu_map[unit] = NR_CPUS; + + ai->nr_groups = nr_groups; + ai->__ai_size = PFN_ALIGN(ai_size); + + return ai; +} + +/** + * 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) +{ + memblock_free_early(__pa(ai), ai->__ai_size); +} + +/** + * 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) +{ + int group_width = 1, cpu_width = 1, width; + char empty_str[] = "--------"; + int alloc = 0, alloc_end = 0; + int group, v; + int upa, apl; /* units per alloc, allocs per line */ + + v = ai->nr_groups; + while (v /= 10) + group_width++; + + v = num_possible_cpus(); + while (v /= 10) + cpu_width++; + empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0'; + + upa = ai->alloc_size / ai->unit_size; + width = upa * (cpu_width + 1) + group_width + 3; + apl = rounddown_pow_of_two(max(60 / width, 1)); + + printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu", + lvl, ai->static_size, ai->reserved_size, ai->dyn_size, + ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size); + + for (group = 0; group < ai->nr_groups; group++) { + const struct pcpu_group_info *gi = &ai->groups[group]; + int unit = 0, unit_end = 0; + + BUG_ON(gi->nr_units % upa); + for (alloc_end += gi->nr_units / upa; + alloc < alloc_end; alloc++) { + if (!(alloc % apl)) { + printk(KERN_CONT "\n"); + printk("%spcpu-alloc: ", lvl); + } + printk(KERN_CONT "[%0*d] ", group_width, group); + + for (unit_end += upa; unit < unit_end; unit++) + if (gi->cpu_map[unit] != NR_CPUS) + printk(KERN_CONT "%0*d ", cpu_width, + gi->cpu_map[unit]); + else + printk(KERN_CONT "%s ", empty_str); + } + } + printk(KERN_CONT "\n"); +} + +/** * pcpu_setup_first_chunk - initialize the first percpu chunk - * @get_page_fn: callback to fetch page pointer - * @static_size: the size of static percpu area in bytes - * @reserved_size: the size of reserved percpu area in bytes - * @dyn_size: free size for dynamic allocation in bytes, -1 for auto - * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto - * @base_addr: mapped address, NULL for auto - * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary + * @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 * perpcu area. This function is to be called from arch percpu area - * setup path. The first two parameters are mandatory. The rest are - * optional. - * - * @get_page_fn() should return pointer to percpu page given cpu - * number and page number. It should at least return enough pages to - * cover the static area. The returned pages for static area should - * have been initialized with valid data. If @unit_size is specified, - * it can also return pages after the static area. NULL return - * indicates end of pages for the cpu. Note that @get_page_fn() must - * return the same number of pages for all cpus. - * - * @reserved_size, if non-zero, specifies the amount of bytes to + * 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 @@ -1006,22 +1180,29 @@ EXPORT_SYMBOL_GPL(free_percpu); * limited offset range for symbol relocations to guarantee module * percpu symbols fall inside the relocatable range. * - * @dyn_size, if non-negative, determines the number of bytes - * available for dynamic allocation in the first chunk. Specifying - * non-negative value makes percpu leave alone the area beyond - * @static_size + @reserved_size + @dyn_size. + * @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. * - * @unit_size, if non-negative, specifies unit size and must be - * aligned to PAGE_SIZE and equal to or larger than @static_size + - * @reserved_size + if non-negative, @dyn_size. + * @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. * - * Non-null @base_addr means that the caller already allocated virtual - * region for the first chunk and mapped it. percpu must not mess - * with the chunk. Note that @base_addr with 0 @unit_size or non-NULL - * @populate_pte_fn doesn't make any sense. + * @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. * - * @populate_pte_fn is used to populate the pagetable. NULL means the - * caller already populated the pagetable. + * The caller should have mapped the first chunk at @base_addr and + * copied static data to each unit. * * If the first chunk ends up with both reserved and dynamic areas, it * is served by two chunks - one to serve the core static and reserved @@ -1031,56 +1212,119 @@ EXPORT_SYMBOL_GPL(free_percpu); * and available for dynamic allocation like any other chunks. * * RETURNS: - * The determined pcpu_unit_size which can be used to initialize - * percpu access. + * 0 on success, -errno on failure. */ -size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, - size_t static_size, size_t reserved_size, - ssize_t dyn_size, ssize_t unit_size, - void *base_addr, - pcpu_populate_pte_fn_t populate_pte_fn) +int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, + void *base_addr) { - static struct vm_struct first_vm; - static int smap[2], dmap[2]; - size_t size_sum = static_size + reserved_size + - (dyn_size >= 0 ? dyn_size : 0); + static char cpus_buf[4096] __initdata; + static int smap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata; + static int dmap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata; + size_t dyn_size = ai->dyn_size; + size_t size_sum = ai->static_size + ai->reserved_size + dyn_size; struct pcpu_chunk *schunk, *dchunk = NULL; + unsigned long *group_offsets; + size_t *group_sizes; + unsigned long *unit_off; unsigned int cpu; - int nr_pages; - int err, i; - - /* santiy checks */ - BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC || - ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC); - BUG_ON(!static_size); - if (unit_size >= 0) { - BUG_ON(unit_size < size_sum); - BUG_ON(unit_size & ~PAGE_MASK); - BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE); - } else - BUG_ON(base_addr); - BUG_ON(base_addr && populate_pte_fn); + int *unit_map; + int group, unit, i; + + cpumask_scnprintf(cpus_buf, sizeof(cpus_buf), cpu_possible_mask); + +#define PCPU_SETUP_BUG_ON(cond) do { \ + if (unlikely(cond)) { \ + pr_emerg("PERCPU: failed to initialize, %s", #cond); \ + pr_emerg("PERCPU: cpu_possible_mask=%s\n", cpus_buf); \ + pcpu_dump_alloc_info(KERN_EMERG, ai); \ + BUG(); \ + } \ +} while (0) + + /* sanity checks */ + PCPU_SETUP_BUG_ON(ai->nr_groups <= 0); +#ifdef CONFIG_SMP + PCPU_SETUP_BUG_ON(!ai->static_size); + PCPU_SETUP_BUG_ON((unsigned long)__per_cpu_start & ~PAGE_MASK); +#endif + PCPU_SETUP_BUG_ON(!base_addr); + PCPU_SETUP_BUG_ON((unsigned long)base_addr & ~PAGE_MASK); + PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); + PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK); + PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); + PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE); + PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); + + /* process group information and build config tables accordingly */ + group_offsets = memblock_virt_alloc(ai->nr_groups * + sizeof(group_offsets[0]), 0); + group_sizes = memblock_virt_alloc(ai->nr_groups * + sizeof(group_sizes[0]), 0); + unit_map = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0); + unit_off = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0); + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + unit_map[cpu] = UINT_MAX; + + pcpu_low_unit_cpu = NR_CPUS; + pcpu_high_unit_cpu = NR_CPUS; + + for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) { + const struct pcpu_group_info *gi = &ai->groups[group]; + + group_offsets[group] = gi->base_offset; + group_sizes[group] = gi->nr_units * ai->unit_size; + + for (i = 0; i < gi->nr_units; i++) { + cpu = gi->cpu_map[i]; + if (cpu == NR_CPUS) + continue; - if (unit_size >= 0) - pcpu_unit_pages = unit_size >> PAGE_SHIFT; - else - pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT, - PFN_UP(size_sum)); + PCPU_SETUP_BUG_ON(cpu > nr_cpu_ids); + PCPU_SETUP_BUG_ON(!cpu_possible(cpu)); + PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX); - pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; - pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size; - pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) - + num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *); + unit_map[cpu] = unit + i; + unit_off[cpu] = gi->base_offset + i * ai->unit_size; + + /* determine low/high unit_cpu */ + if (pcpu_low_unit_cpu == NR_CPUS || + unit_off[cpu] < unit_off[pcpu_low_unit_cpu]) + pcpu_low_unit_cpu = cpu; + if (pcpu_high_unit_cpu == NR_CPUS || + unit_off[cpu] > unit_off[pcpu_high_unit_cpu]) + pcpu_high_unit_cpu = cpu; + } + } + pcpu_nr_units = unit; + + for_each_possible_cpu(cpu) + PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX); + + /* we're done parsing the input, undefine BUG macro and dump config */ +#undef PCPU_SETUP_BUG_ON + pcpu_dump_alloc_info(KERN_DEBUG, ai); - if (dyn_size < 0) - dyn_size = pcpu_unit_size - static_size - reserved_size; + pcpu_nr_groups = ai->nr_groups; + pcpu_group_offsets = group_offsets; + pcpu_group_sizes = group_sizes; + pcpu_unit_map = unit_map; + pcpu_unit_offsets = unit_off; + + /* determine basic parameters */ + pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; + pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; + pcpu_atom_size = ai->atom_size; + pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + + BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long); /* * Allocate chunk slots. The additional last slot is for * empty chunks. */ pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; - pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0])); + pcpu_slot = memblock_virt_alloc( + pcpu_nr_slots * sizeof(pcpu_slot[0]), 0); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_slot[i]); @@ -1091,183 +1335,634 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, * covers static area + reserved area (mostly used for module * static percpu allocation). */ - schunk = alloc_bootmem(pcpu_chunk_struct_size); + schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0); INIT_LIST_HEAD(&schunk->list); - schunk->vm = &first_vm; + schunk->base_addr = base_addr; schunk->map = smap; schunk->map_alloc = ARRAY_SIZE(smap); - schunk->page = schunk->page_ar; + schunk->immutable = true; + bitmap_fill(schunk->populated, pcpu_unit_pages); - if (reserved_size) { - schunk->free_size = reserved_size; + if (ai->reserved_size) { + schunk->free_size = ai->reserved_size; pcpu_reserved_chunk = schunk; - pcpu_reserved_chunk_limit = static_size + reserved_size; + pcpu_reserved_chunk_limit = ai->static_size + ai->reserved_size; } else { schunk->free_size = dyn_size; dyn_size = 0; /* dynamic area covered */ } schunk->contig_hint = schunk->free_size; - schunk->map[schunk->map_used++] = -static_size; + schunk->map[0] = 1; + schunk->map[1] = ai->static_size; + schunk->map_used = 1; if (schunk->free_size) - schunk->map[schunk->map_used++] = schunk->free_size; + schunk->map[++schunk->map_used] = 1 | (ai->static_size + schunk->free_size); + else + schunk->map[1] |= 1; /* init dynamic chunk if necessary */ if (dyn_size) { - dchunk = alloc_bootmem(sizeof(struct pcpu_chunk)); + dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0); INIT_LIST_HEAD(&dchunk->list); - dchunk->vm = &first_vm; + dchunk->base_addr = base_addr; dchunk->map = dmap; dchunk->map_alloc = ARRAY_SIZE(dmap); - dchunk->page = schunk->page_ar; /* share page map with schunk */ + dchunk->immutable = true; + bitmap_fill(dchunk->populated, pcpu_unit_pages); dchunk->contig_hint = dchunk->free_size = dyn_size; - dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit; - dchunk->map[dchunk->map_used++] = dchunk->free_size; + dchunk->map[0] = 1; + dchunk->map[1] = pcpu_reserved_chunk_limit; + dchunk->map[2] = (pcpu_reserved_chunk_limit + dchunk->free_size) | 1; + dchunk->map_used = 2; } - /* allocate vm address */ - first_vm.flags = VM_ALLOC; - first_vm.size = pcpu_chunk_size; + /* link the first chunk in */ + pcpu_first_chunk = dchunk ?: schunk; + pcpu_chunk_relocate(pcpu_first_chunk, -1); - if (!base_addr) - vm_area_register_early(&first_vm, PAGE_SIZE); - else { - /* - * Pages already mapped. No need to remap into - * vmalloc area. In this case the first chunks can't - * be mapped or unmapped by percpu and are marked - * immutable. - */ - first_vm.addr = base_addr; - schunk->immutable = true; - if (dchunk) - dchunk->immutable = true; - } + /* we're done */ + pcpu_base_addr = base_addr; + return 0; +} - /* assign pages */ - nr_pages = -1; - for_each_possible_cpu(cpu) { - for (i = 0; i < pcpu_unit_pages; i++) { - struct page *page = get_page_fn(cpu, i); +#ifdef CONFIG_SMP + +const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = { + [PCPU_FC_AUTO] = "auto", + [PCPU_FC_EMBED] = "embed", + [PCPU_FC_PAGE] = "page", +}; + +enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO; + +static int __init percpu_alloc_setup(char *str) +{ + if (!str) + return -EINVAL; + + if (0) + /* nada */; +#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK + else if (!strcmp(str, "embed")) + pcpu_chosen_fc = PCPU_FC_EMBED; +#endif +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK + else if (!strcmp(str, "page")) + pcpu_chosen_fc = PCPU_FC_PAGE; +#endif + else + pr_warning("PERCPU: unknown allocator %s specified\n", str); + + return 0; +} +early_param("percpu_alloc", percpu_alloc_setup); + +/* + * 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 - if (!page) +/* 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 mutliples 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 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 int group_map[NR_CPUS] __initdata; + static int group_cnt[NR_CPUS] __initdata; + const size_t static_size = __per_cpu_end - __per_cpu_start; + int nr_groups = 1, nr_units = 0; + size_t size_sum, min_unit_size, alloc_size; + int upa, max_upa, uninitialized_var(best_upa); /* units_per_alloc */ + int last_allocs, group, unit; + unsigned int cpu, tcpu; + struct pcpu_alloc_info *ai; + unsigned int *cpu_map; + + /* this function may be called multiple times */ + memset(group_map, 0, sizeof(group_map)); + memset(group_cnt, 0, sizeof(group_cnt)); + + /* calculate size_sum and ensure dyn_size is enough for early alloc */ + size_sum = PFN_ALIGN(static_size + reserved_size + + max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE)); + dyn_size = size_sum - static_size - reserved_size; + + /* + * Determine min_unit_size, alloc_size and max_upa such that + * alloc_size is multiple of atom_size and is the smallest + * which can accommodate 4k aligned segments which are equal to + * or larger than min_unit_size. + */ + min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); + + alloc_size = roundup(min_unit_size, atom_size); + upa = alloc_size / min_unit_size; + while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK)) + upa--; + max_upa = upa; + + /* group cpus according to their proximity */ + for_each_possible_cpu(cpu) { + group = 0; + next_group: + for_each_possible_cpu(tcpu) { + if (cpu == tcpu) break; - *pcpu_chunk_pagep(schunk, cpu, i) = page; + if (group_map[tcpu] == group && cpu_distance_fn && + (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE || + cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) { + group++; + nr_groups = max(nr_groups, group + 1); + goto next_group; + } } + group_map[cpu] = group; + group_cnt[group]++; + } - BUG_ON(i < PFN_UP(static_size)); + /* + * Expand unit size until address space usage goes over 75% + * and then as much as possible without using more address + * space. + */ + last_allocs = INT_MAX; + for (upa = max_upa; upa; upa--) { + int allocs = 0, wasted = 0; - if (nr_pages < 0) - nr_pages = i; - else - BUG_ON(nr_pages != i); - } + if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK)) + continue; - /* map them */ - if (populate_pte_fn) { - for_each_possible_cpu(cpu) - for (i = 0; i < nr_pages; i++) - populate_pte_fn(pcpu_chunk_addr(schunk, - cpu, i)); - - err = pcpu_map(schunk, 0, nr_pages); - if (err) - panic("failed to setup static percpu area, err=%d\n", - err); + for (group = 0; group < nr_groups; group++) { + int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); + allocs += this_allocs; + wasted += this_allocs * upa - group_cnt[group]; + } + + /* + * Don't accept if wastage is over 1/3. The + * greater-than comparison ensures upa==1 always + * passes the following check. + */ + if (wasted > num_possible_cpus() / 3) + continue; + + /* and then don't consume more memory */ + if (allocs > last_allocs) + break; + last_allocs = allocs; + best_upa = upa; } + upa = best_upa; - /* link the first chunk in */ - pcpu_first_chunk = dchunk ?: schunk; - pcpu_chunk_relocate(pcpu_first_chunk, -1); + /* allocate and fill alloc_info */ + for (group = 0; group < nr_groups; group++) + nr_units += roundup(group_cnt[group], upa); - /* we're done */ - pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0); - return pcpu_unit_size; -} + ai = pcpu_alloc_alloc_info(nr_groups, nr_units); + if (!ai) + return ERR_PTR(-ENOMEM); + cpu_map = ai->groups[0].cpu_map; -/* - * Embedding first chunk setup helper. - */ -static void *pcpue_ptr __initdata; -static size_t pcpue_size __initdata; -static size_t pcpue_unit_size __initdata; + for (group = 0; group < nr_groups; group++) { + ai->groups[group].cpu_map = cpu_map; + cpu_map += roundup(group_cnt[group], upa); + } -static struct page * __init pcpue_get_page(unsigned int cpu, int pageno) -{ - size_t off = (size_t)pageno << PAGE_SHIFT; + ai->static_size = static_size; + ai->reserved_size = reserved_size; + ai->dyn_size = dyn_size; + ai->unit_size = alloc_size / upa; + ai->atom_size = atom_size; + ai->alloc_size = alloc_size; - if (off >= pcpue_size) - return NULL; + for (group = 0, unit = 0; group_cnt[group]; group++) { + struct pcpu_group_info *gi = &ai->groups[group]; + + /* + * Initialize base_offset as if all groups are located + * back-to-back. The caller should update this to + * reflect actual allocation. + */ + gi->base_offset = unit * ai->unit_size; + + for_each_possible_cpu(cpu) + if (group_map[cpu] == group) + gi->cpu_map[gi->nr_units++] = cpu; + gi->nr_units = roundup(gi->nr_units, upa); + unit += gi->nr_units; + } + BUG_ON(unit != nr_units); - return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off); + return ai; } +#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 - * @static_size: the size of static percpu area in bytes * @reserved_size: the size of reserved percpu area in bytes - * @dyn_size: free size for dynamic allocation in bytes, -1 for auto - * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto + * @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 + * @alloc_fn: function to allocate percpu page + * @free_fn: function to free percpu page * * 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 - * as a contiguous area using bootmem allocator and used as-is without - * being mapped into vmalloc area. This enables the first chunk to - * piggy back on the linear physical mapping which often uses larger - * page size. + * by calling @alloc_fn and used as-is without being mapped into + * vmalloc area. Allocations are always whole multiples of @atom_size + * aligned to @atom_size. * - * When @dyn_size is positive, dynamic area might be larger than - * specified to fill page alignment. Also, when @dyn_size is auto, - * @dyn_size does not fill the whole first chunk but only what's - * necessary for page alignment after static and reserved areas. + * 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 to the bootmem allocator. + * size, the leftover is returned using @free_fn. * * RETURNS: - * The determined pcpu_unit_size which can be used to initialize - * percpu access on success, -errno on failure. + * 0 on success, -errno on failure. */ -ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size, - ssize_t dyn_size, ssize_t unit_size) +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_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn) { - unsigned int cpu; + void *base = (void *)ULONG_MAX; + void **areas = NULL; + struct pcpu_alloc_info *ai; + size_t size_sum, areas_size, max_distance; + int group, i, rc; + + ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, + cpu_distance_fn); + if (IS_ERR(ai)) + return PTR_ERR(ai); + + size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; + areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); + + areas = memblock_virt_alloc_nopanic(areas_size, 0); + if (!areas) { + rc = -ENOMEM; + goto out_free; + } - /* determine parameters and allocate */ - pcpue_size = PFN_ALIGN(static_size + reserved_size + - (dyn_size >= 0 ? dyn_size : 0)); - if (dyn_size != 0) - dyn_size = pcpue_size - static_size - reserved_size; + /* allocate, copy and determine base address */ + for (group = 0; group < ai->nr_groups; group++) { + struct pcpu_group_info *gi = &ai->groups[group]; + unsigned int cpu = NR_CPUS; + void *ptr; + + for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++) + cpu = gi->cpu_map[i]; + BUG_ON(cpu == NR_CPUS); + + /* allocate space for the whole group */ + ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size); + if (!ptr) { + rc = -ENOMEM; + goto out_free_areas; + } + /* kmemleak tracks the percpu allocations separately */ + kmemleak_free(ptr); + areas[group] = ptr; - if (unit_size >= 0) { - BUG_ON(unit_size < pcpue_size); - pcpue_unit_size = unit_size; - } else - pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); + base = min(ptr, base); + } - pcpue_ptr = __alloc_bootmem_nopanic( - num_possible_cpus() * pcpue_unit_size, - PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); - if (!pcpue_ptr) - return -ENOMEM; + /* + * Copy data and free unused parts. This should happen after all + * allocations are complete; otherwise, we may end up with + * overlapping groups. + */ + for (group = 0; group < ai->nr_groups; group++) { + struct pcpu_group_info *gi = &ai->groups[group]; + void *ptr = areas[group]; + + for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { + if (gi->cpu_map[i] == NR_CPUS) { + /* unused unit, free whole */ + free_fn(ptr, ai->unit_size); + continue; + } + /* copy and return the unused part */ + memcpy(ptr, __per_cpu_load, ai->static_size); + free_fn(ptr + size_sum, ai->unit_size - size_sum); + } + } - /* return the leftover and copy */ - for_each_possible_cpu(cpu) { - void *ptr = pcpue_ptr + cpu * pcpue_unit_size; + /* base address is now known, determine group base offsets */ + max_distance = 0; + for (group = 0; group < ai->nr_groups; group++) { + ai->groups[group].base_offset = areas[group] - base; + max_distance = max_t(size_t, max_distance, + ai->groups[group].base_offset); + } + max_distance += ai->unit_size; + + /* warn if maximum distance is further than 75% of vmalloc space */ + if (max_distance > VMALLOC_TOTAL * 3 / 4) { + pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc " + "space 0x%lx\n", max_distance, + VMALLOC_TOTAL); +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK + /* and fail if we have fallback */ + rc = -EINVAL; + goto out_free; +#endif + } + + pr_info("PERCPU: Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n", + PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size, + ai->dyn_size, ai->unit_size); + + rc = pcpu_setup_first_chunk(ai, base); + goto out_free; + +out_free_areas: + for (group = 0; group < ai->nr_groups; group++) + if (areas[group]) + free_fn(areas[group], + ai->groups[group].nr_units * ai->unit_size); +out_free: + pcpu_free_alloc_info(ai); + if (areas) + memblock_free_early(__pa(areas), areas_size); + return rc; +} +#endif /* BUILD_EMBED_FIRST_CHUNK */ + +#ifdef BUILD_PAGE_FIRST_CHUNK +/** + * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages + * @reserved_size: the size of reserved percpu area in bytes + * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE + * @free_fn: function to free percpu page, always called with PAGE_SIZE + * @populate_pte_fn: function to populate pte + * + * 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_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn, + pcpu_fc_populate_pte_fn_t populate_pte_fn) +{ + static struct vm_struct vm; + struct pcpu_alloc_info *ai; + char psize_str[16]; + int unit_pages; + size_t pages_size; + struct page **pages; + int unit, i, j, rc; + + snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); + + ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL); + if (IS_ERR(ai)) + return PTR_ERR(ai); + BUG_ON(ai->nr_groups != 1); + BUG_ON(ai->groups[0].nr_units != num_possible_cpus()); + + unit_pages = ai->unit_size >> PAGE_SHIFT; + + /* unaligned allocations can't be freed, round up to page size */ + pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * + sizeof(pages[0])); + pages = memblock_virt_alloc(pages_size, 0); + + /* allocate pages */ + j = 0; + for (unit = 0; unit < num_possible_cpus(); unit++) + for (i = 0; i < unit_pages; i++) { + unsigned int cpu = ai->groups[0].cpu_map[unit]; + void *ptr; + + ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE); + if (!ptr) { + pr_warning("PERCPU: failed to allocate %s page " + "for cpu%u\n", psize_str, cpu); + goto enomem; + } + /* kmemleak tracks the percpu allocations separately */ + kmemleak_free(ptr); + pages[j++] = virt_to_page(ptr); + } - free_bootmem(__pa(ptr + pcpue_size), - pcpue_unit_size - pcpue_size); - memcpy(ptr, __per_cpu_load, static_size); + /* allocate vm area, map the pages and copy static data */ + vm.flags = VM_ALLOC; + vm.size = num_possible_cpus() * ai->unit_size; + vm_area_register_early(&vm, PAGE_SIZE); + + for (unit = 0; unit < num_possible_cpus(); unit++) { + unsigned long unit_addr = + (unsigned long)vm.addr + unit * ai->unit_size; + + for (i = 0; i < unit_pages; i++) + populate_pte_fn(unit_addr + (i << PAGE_SHIFT)); + + /* pte already populated, the following shouldn't fail */ + rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], + unit_pages); + if (rc < 0) + panic("failed to map percpu area, err=%d\n", rc); + + /* + * FIXME: Archs with virtual cache should flush local + * cache for the linear mapping here - something + * equivalent to flush_cache_vmap() on the local cpu. + * flush_cache_vmap() can't be used as most supporting + * data structures are not set up yet. + */ + + /* copy static data */ + memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); } /* we're ready, commit */ - pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n", - pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size); + pr_info("PERCPU: %d %s pages/cpu @%p s%zu r%zu d%zu\n", + unit_pages, psize_str, vm.addr, ai->static_size, + ai->reserved_size, ai->dyn_size); + + rc = pcpu_setup_first_chunk(ai, vm.addr); + goto out_free_ar; + +enomem: + while (--j >= 0) + free_fn(page_address(pages[j]), PAGE_SIZE); + rc = -ENOMEM; +out_free_ar: + memblock_free_early(__pa(pages), pages_size); + pcpu_free_alloc_info(ai); + return rc; +} +#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); + +static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, + size_t align) +{ + return memblock_virt_alloc_from_nopanic( + size, align, __pa(MAX_DMA_ADDRESS)); +} + +static void __init pcpu_dfl_fc_free(void *ptr, size_t size) +{ + memblock_free_early(__pa(ptr), size); +} + +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, + pcpu_dfl_fc_alloc, pcpu_dfl_fc_free); + 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_virt_alloc_from_nopanic(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_free(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; + + if (pcpu_setup_first_chunk(ai, fc) < 0) + panic("Failed to initialize percpu areas."); +} + +#endif /* CONFIG_SMP */ - return pcpu_setup_first_chunk(pcpue_get_page, static_size, - reserved_size, dyn_size, - pcpue_unit_size, pcpue_ptr, NULL); +/* + * First and reserved chunks are initialized with temporary allocation + * map in initdata so that they can be used before slab is online. + * This function is called after slab is brought up and replaces those + * with properly allocated maps. + */ +void __init percpu_init_late(void) +{ + struct pcpu_chunk *target_chunks[] = + { pcpu_first_chunk, pcpu_reserved_chunk, NULL }; + struct pcpu_chunk *chunk; + unsigned long flags; + int i; + + for (i = 0; (chunk = target_chunks[i]); i++) { + int *map; + const size_t size = PERCPU_DYNAMIC_EARLY_SLOTS * sizeof(map[0]); + + BUILD_BUG_ON(size > PAGE_SIZE); + + map = pcpu_mem_zalloc(size); + BUG_ON(!map); + + spin_lock_irqsave(&pcpu_lock, flags); + memcpy(map, chunk->map, size); + chunk->map = map; + spin_unlock_irqrestore(&pcpu_lock, flags); + } } |