/*
- * 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>
* 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 boot-time determined number of units and the
- * first chunk is used for static percpu variables in the kernel image
+ * 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. ie. in
- * vmalloc area
+ * When a chunk is filled up, another chunk is allocated.
*
* c0 c1 c2
* ------------------- ------------------- ------------
#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 */
/* 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
struct pcpu_chunk {
int map_used; /* # of map entries used */
int map_alloc; /* # of map entries allocated */
int *map; /* allocation map */
- struct vm_struct **vms; /* mapped vmalloc regions */
+ void *data; /* chunk data */
bool immutable; /* no [de]population allowed */
unsigned long populated[]; /* populated bitmap */
};
*
* 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
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 */
return pcpu_size_to_slot(chunk->free_size);
}
-static int pcpu_page_idx(unsigned int cpu, int page_idx)
-{
- return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx;
-}
-
-static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk,
- unsigned int cpu, int page_idx)
-{
- return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] +
- (page_idx << PAGE_SHIFT);
-}
-
-static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
- unsigned int cpu, int page_idx)
-{
- /* must not be used on pre-mapped chunk */
- WARN_ON(chunk->immutable);
-
- return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, 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 (struct pcpu_chunk *)page->index;
}
-static void pcpu_next_unpop(struct pcpu_chunk *chunk, int *rs, int *re, int end)
+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 __maybe_unused pcpu_chunk_addr(struct pcpu_chunk *chunk,
+ unsigned int cpu, int page_idx)
+{
+ return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] +
+ (page_idx << PAGE_SHIFT);
+}
+
+static void __maybe_unused pcpu_next_unpop(struct pcpu_chunk *chunk,
+ int *rs, int *re, int end)
{
*rs = find_next_zero_bit(chunk->populated, end, *rs);
*re = find_next_bit(chunk->populated, end, *rs + 1);
}
-static void pcpu_next_pop(struct pcpu_chunk *chunk, int *rs, int *re, int end)
+static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
+ int *rs, int *re, int end)
{
*rs = find_next_bit(chunk->populated, end, *rs);
*re = find_next_zero_bit(chunk->populated, end, *rs + 1);
}
/**
- * 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
+ * accomodate 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->base_addr;
+ int new_alloc;
- /* is it in the first chunk? */
- if (addr >= first_start && addr < first_start + pcpu_unit_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 + 2)
+ return 0;
- /*
- * 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(vmalloc_to_page(addr));
+ new_alloc = PCPU_DFL_MAP_ALLOC;
+ while (new_alloc < chunk->map_used + 2)
+ 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)
- __releases(lock) __acquires(lock)
+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_alloc(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);
+
+ if (new_alloc <= chunk->map_alloc)
+ goto out_unlock;
- size = chunk->map_alloc * sizeof(chunk->map[0]);
- memcpy(new, chunk->map, size);
+ old_size = chunk->map_alloc * sizeof(chunk->map[0]);
+ memcpy(new, chunk->map, old_size);
/*
* 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 = chunk->map;
chunk->map_alloc = new_alloc;
chunk->map = new;
+ new = NULL;
+
+out_unlock:
+ spin_unlock_irqrestore(&pcpu_lock, flags);
+
+ /*
+ * 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);
+
return 0;
}
pcpu_chunk_relocate(chunk, oslot);
}
-/**
- * pcpu_get_pages_and_bitmap - get temp pages array and bitmap
- * @chunk: chunk of interest
- * @bitmapp: output parameter for bitmap
- * @may_alloc: may allocate the array
- *
- * Returns pointer to array of pointers to struct page and bitmap,
- * both of which can be indexed with pcpu_page_idx(). The returned
- * array is cleared to zero and *@bitmapp is copied from
- * @chunk->populated. Note that there is only one array and bitmap
- * and access exclusion is the caller's responsibility.
- *
- * CONTEXT:
- * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc.
- * Otherwise, don't care.
- *
- * RETURNS:
- * Pointer to temp pages array on success, NULL on failure.
- */
-static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
- unsigned long **bitmapp,
- bool may_alloc)
-{
- static struct page **pages;
- static unsigned long *bitmap;
- size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
- size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) *
- sizeof(unsigned long);
-
- if (!pages || !bitmap) {
- if (may_alloc && !pages)
- pages = pcpu_mem_alloc(pages_size);
- if (may_alloc && !bitmap)
- bitmap = pcpu_mem_alloc(bitmap_size);
- if (!pages || !bitmap)
- return NULL;
- }
-
- memset(pages, 0, pages_size);
- bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages);
-
- *bitmapp = bitmap;
- return pages;
-}
-
-/**
- * pcpu_free_pages - free pages which were allocated for @chunk
- * @chunk: chunk pages were allocated for
- * @pages: array of pages to be freed, indexed by pcpu_page_idx()
- * @populated: populated bitmap
- * @page_start: page index of the first page to be freed
- * @page_end: page index of the last page to be freed + 1
- *
- * Free pages [@page_start and @page_end) in @pages for all units.
- * The pages were allocated for @chunk.
- */
-static void pcpu_free_pages(struct pcpu_chunk *chunk,
- struct page **pages, unsigned long *populated,
- int page_start, int page_end)
-{
- unsigned int cpu;
- int i;
-
- for_each_possible_cpu(cpu) {
- for (i = page_start; i < page_end; i++) {
- struct page *page = pages[pcpu_page_idx(cpu, i)];
-
- if (page)
- __free_page(page);
- }
- }
-}
-
-/**
- * pcpu_alloc_pages - allocates pages for @chunk
- * @chunk: target chunk
- * @pages: array to put the allocated pages into, indexed by pcpu_page_idx()
- * @populated: populated bitmap
- * @page_start: page index of the first page to be allocated
- * @page_end: page index of the last page to be allocated + 1
- *
- * Allocate pages [@page_start,@page_end) into @pages for all units.
- * The allocation is for @chunk. Percpu core doesn't care about the
- * content of @pages and will pass it verbatim to pcpu_map_pages().
- */
-static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
- struct page **pages, unsigned long *populated,
- int page_start, int page_end)
+static struct pcpu_chunk *pcpu_alloc_chunk(void)
{
- const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
- unsigned int cpu;
- int i;
-
- for_each_possible_cpu(cpu) {
- for (i = page_start; i < page_end; i++) {
- struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
-
- *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
- if (!*pagep) {
- pcpu_free_pages(chunk, pages, populated,
- page_start, page_end);
- return -ENOMEM;
- }
- }
- }
- return 0;
-}
-
-/**
- * pcpu_pre_unmap_flush - flush cache prior to unmapping
- * @chunk: chunk the regions to be flushed belongs to
- * @page_start: page index of the first page to be flushed
- * @page_end: page index of the last page to be flushed + 1
- *
- * Pages in [@page_start,@page_end) of @chunk are about to be
- * unmapped. Flush cache. As 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.
- */
-static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
- int page_start, int page_end)
-{
- flush_cache_vunmap(
- pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
- pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
-}
-
-static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
-{
- unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT);
-}
-
-/**
- * pcpu_unmap_pages - unmap pages out of a pcpu_chunk
- * @chunk: chunk of interest
- * @pages: pages array which can be used to pass information to free
- * @populated: populated bitmap
- * @page_start: page index of the first page to unmap
- * @page_end: page index of the last page to unmap + 1
- *
- * For each cpu, unmap pages [@page_start,@page_end) out of @chunk.
- * Corresponding elements in @pages were cleared by the caller and can
- * be used to carry information to pcpu_free_pages() which will be
- * called after all unmaps are finished. The caller should call
- * proper pre/post flush functions.
- */
-static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
- struct page **pages, unsigned long *populated,
- int page_start, int page_end)
-{
- unsigned int cpu;
- int i;
+ struct pcpu_chunk *chunk;
- for_each_possible_cpu(cpu) {
- for (i = page_start; i < page_end; i++) {
- struct page *page;
+ chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL);
+ if (!chunk)
+ return NULL;
- page = pcpu_chunk_page(chunk, cpu, i);
- WARN_ON(!page);
- pages[pcpu_page_idx(cpu, i)] = page;
- }
- __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start),
- page_end - page_start);
+ chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
+ if (!chunk->map) {
+ kfree(chunk);
+ return NULL;
}
- for (i = page_start; i < page_end; i++)
- __clear_bit(i, populated);
-}
+ chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
+ chunk->map[chunk->map_used++] = pcpu_unit_size;
-/**
- * pcpu_post_unmap_tlb_flush - flush TLB after unmapping
- * @chunk: pcpu_chunk the regions to be flushed belong to
- * @page_start: page index of the first page to be flushed
- * @page_end: page index of the last page to be flushed + 1
- *
- * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush
- * TLB for the regions. This can be skipped if the area is to be
- * returned to vmalloc as vmalloc will handle TLB flushing lazily.
- *
- * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
- * for the whole region.
- */
-static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
- int page_start, int page_end)
-{
- flush_tlb_kernel_range(
- pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
- pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
-}
+ INIT_LIST_HEAD(&chunk->list);
+ chunk->free_size = pcpu_unit_size;
+ chunk->contig_hint = pcpu_unit_size;
-static int __pcpu_map_pages(unsigned long addr, struct page **pages,
- int nr_pages)
-{
- return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT,
- PAGE_KERNEL, pages);
+ return chunk;
}
-/**
- * pcpu_map_pages - map pages into a pcpu_chunk
- * @chunk: chunk of interest
- * @pages: pages array containing pages to be mapped
- * @populated: populated bitmap
- * @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. The
- * caller is responsible for calling pcpu_post_map_flush() after all
- * mappings are complete.
- *
- * This function is responsible for setting corresponding bits in
- * @chunk->populated bitmap and whatever is necessary for reverse
- * lookup (addr -> chunk).
- */
-static int pcpu_map_pages(struct pcpu_chunk *chunk,
- struct page **pages, unsigned long *populated,
- int page_start, int page_end)
+static void pcpu_free_chunk(struct pcpu_chunk *chunk)
{
- unsigned int cpu, tcpu;
- int i, err;
-
- for_each_possible_cpu(cpu) {
- err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start),
- &pages[pcpu_page_idx(cpu, page_start)],
- page_end - page_start);
- if (err < 0)
- goto err;
- }
-
- /* mapping successful, link chunk and mark populated */
- for (i = page_start; i < page_end; i++) {
- for_each_possible_cpu(cpu)
- pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)],
- chunk);
- __set_bit(i, populated);
- }
-
- return 0;
-
-err:
- for_each_possible_cpu(tcpu) {
- if (tcpu == cpu)
- break;
- __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
- page_end - page_start);
- }
- return err;
+ if (!chunk)
+ return;
+ pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0]));
+ kfree(chunk);
}
-/**
- * pcpu_post_map_flush - flush cache after mapping
- * @chunk: pcpu_chunk the regions to be flushed belong to
- * @page_start: page index of the first page to be flushed
- * @page_end: page index of the last page to be flushed + 1
- *
- * Pages [@page_start,@page_end) of @chunk have been mapped. Flush
- * cache.
- *
- * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
- * for the whole region.
+/*
+ * 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 void pcpu_post_map_flush(struct pcpu_chunk *chunk,
- int page_start, int page_end)
-{
- flush_cache_vmap(
- pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
- pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
-}
+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
/**
- * 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.
+ * pcpu_chunk_addr_search - determine chunk containing specified address
+ * @addr: address for which the chunk needs to be determined.
*
- * CONTEXT:
- * pcpu_alloc_mutex.
+ * RETURNS:
+ * The address of the found chunk.
*/
-static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)
+static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
{
- int page_start = PFN_DOWN(off);
- int page_end = PFN_UP(off + size);
- struct page **pages;
- unsigned long *populated;
- int rs, re;
-
- /* quick path, check whether it's empty already */
- pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
- if (rs == page_start && re == page_end)
- return;
- break;
+ /* 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;
}
- /* immutable chunks can't be depopulated */
- WARN_ON(chunk->immutable);
-
/*
- * If control reaches here, there must have been at least one
- * successful population attempt so the temp pages array must
- * be available now.
+ * 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.
*/
- pages = pcpu_get_pages_and_bitmap(chunk, &populated, false);
- BUG_ON(!pages);
-
- /* unmap and free */
- pcpu_pre_unmap_flush(chunk, page_start, page_end);
-
- pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
- pcpu_unmap_pages(chunk, pages, populated, rs, re);
-
- /* no need to flush tlb, vmalloc will handle it lazily */
-
- pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
- pcpu_free_pages(chunk, pages, populated, rs, re);
-
- /* commit new bitmap */
- bitmap_copy(chunk->populated, populated, pcpu_unit_pages);
-}
-
-/**
- * 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)
-{
- int page_start = PFN_DOWN(off);
- int page_end = PFN_UP(off + size);
- int free_end = page_start, unmap_end = page_start;
- struct page **pages;
- unsigned long *populated;
- unsigned int cpu;
- int rs, re, rc;
-
- /* quick path, check whether all pages are already there */
- pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) {
- if (rs == page_start && re == page_end)
- goto clear;
- break;
- }
-
- /* need to allocate and map pages, this chunk can't be immutable */
- WARN_ON(chunk->immutable);
-
- pages = pcpu_get_pages_and_bitmap(chunk, &populated, true);
- if (!pages)
- return -ENOMEM;
-
- /* alloc and map */
- pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
- rc = pcpu_alloc_pages(chunk, pages, populated, rs, re);
- if (rc)
- goto err_free;
- free_end = re;
- }
-
- pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
- rc = pcpu_map_pages(chunk, pages, populated, rs, re);
- if (rc)
- goto err_unmap;
- unmap_end = re;
- }
- pcpu_post_map_flush(chunk, page_start, page_end);
-
- /* commit new bitmap */
- bitmap_copy(chunk->populated, populated, pcpu_unit_pages);
-clear:
- for_each_possible_cpu(cpu)
- memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
- return 0;
-
-err_unmap:
- pcpu_pre_unmap_flush(chunk, page_start, unmap_end);
- pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end)
- pcpu_unmap_pages(chunk, pages, populated, rs, re);
- pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end);
-err_free:
- pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end)
- pcpu_free_pages(chunk, pages, populated, rs, re);
- return rc;
-}
-
-static void free_pcpu_chunk(struct pcpu_chunk *chunk)
-{
- if (!chunk)
- return;
- if (chunk->vms)
- pcpu_free_vm_areas(chunk->vms, pcpu_nr_groups);
- pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0]));
- kfree(chunk);
-}
-
-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->vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,
- pcpu_nr_groups, pcpu_atom_size,
- GFP_KERNEL);
- if (!chunk->vms) {
- free_pcpu_chunk(chunk);
- return NULL;
- }
-
- INIT_LIST_HEAD(&chunk->list);
- chunk->free_size = pcpu_unit_size;
- chunk->contig_hint = pcpu_unit_size;
- chunk->base_addr = chunk->vms[0]->addr - pcpu_group_offsets[0];
-
- return chunk;
+ addr += pcpu_unit_offsets[raw_smp_processor_id()];
+ return pcpu_get_page_chunk(pcpu_addr_to_page(addr));
}
/**
* 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;
const char *err;
- int slot, off;
+ int slot, off, new_alloc;
+ unsigned long flags;
if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
WARN(true, "illegal size (%zu) or align (%zu) for "
}
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) {
- err = "failed to extend area map of reserved chunk";
+
+ 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;
}
if (size > chunk->contig_hint)
continue;
- switch (pcpu_extend_area_map(chunk)) {
- case 0:
- break;
- case 1:
- goto restart; /* pcpu_lock dropped, restart */
- default:
- err = "failed to extend area map";
- 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);
}
/* hmmm... no space left, create a new chunk */
- spin_unlock_irq(&pcpu_lock);
+ spin_unlock_irqrestore(&pcpu_lock, flags);
- chunk = alloc_pcpu_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;
return __addr_to_pcpu_ptr(chunk->base_addr + off);
fail_unlock:
- spin_unlock_irq(&pcpu_lock);
+ spin_unlock_irqrestore(&pcpu_lock, flags);
fail_unlock_mutex:
mutex_unlock(&pcpu_alloc_mutex);
if (warn_limit) {
* 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);
}
* 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);
}
list_for_each_entry_safe(chunk, next, &todo, list) {
pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size);
- free_pcpu_chunk(chunk);
+ pcpu_destroy_chunk(chunk);
}
mutex_unlock(&pcpu_alloc_mutex);
* 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;
if (!ptr)
return;
+ addr = __pcpu_ptr_to_addr(ptr);
+
spin_lock_irqsave(&pcpu_lock, flags);
chunk = pcpu_chunk_addr_search(addr);
}
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)
+{
+ 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;
+ }
+ 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.
+ *
+ * RETURNS:
+ * The physical address for @addr.
+ */
+phys_addr_t per_cpu_ptr_to_phys(void *addr)
+{
+ if (pcpu_addr_in_first_chunk(addr)) {
+ if ((unsigned long)addr < VMALLOC_START ||
+ (unsigned long)addr >= VMALLOC_END)
+ return __pa(addr);
+ else
+ return page_to_phys(vmalloc_to_page(addr));
+ } else
+ return page_to_phys(pcpu_addr_to_page(addr));
+}
+
static inline size_t pcpu_calc_fc_sizes(size_t static_size,
size_t reserved_size,
ssize_t *dyn_sizep)
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(pcpu_verify_alloc_info(ai) < 0);
/* process group information and build config tables accordingly */
group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0]));