summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/hugetlb.c2
-rw-r--r--mm/memcontrol.c4
-rw-r--r--mm/mlock.c41
-rw-r--r--mm/page_alloc.c2
-rw-r--r--mm/percpu-km.c104
-rw-r--r--mm/percpu-vm.c451
-rw-r--r--mm/percpu.c585
-rw-r--r--mm/rmap.c9
-rw-r--r--mm/slub.c2
9 files changed, 675 insertions, 525 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ffbdfc86aedf..4c9e6bbf3772 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1039,7 +1039,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
page = alloc_buddy_huge_page(h, vma, addr);
if (!page) {
hugetlb_put_quota(inode->i_mapping, chg);
- return ERR_PTR(-VM_FAULT_OOM);
+ return ERR_PTR(-VM_FAULT_SIGBUS);
}
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6c755de385f7..c8569bc298ff 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1438,7 +1438,7 @@ static void drain_local_stock(struct work_struct *dummy)
/*
* Cache charges(val) which is from res_counter, to local per_cpu area.
- * This will be consumed by consumt_stock() function, later.
+ * This will be consumed by consume_stock() function, later.
*/
static void refill_stock(struct mem_cgroup *mem, int val)
{
@@ -1601,7 +1601,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
* There is a small race that "from" or "to" can be
* freed by rmdir, so we use css_tryget().
*/
- rcu_read_lock();
from = mc.from;
to = mc.to;
if (from && css_tryget(&from->css)) {
@@ -1622,7 +1621,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
do_continue = (to == mem_over_limit);
css_put(&to->css);
}
- rcu_read_unlock();
if (do_continue) {
DEFINE_WAIT(wait);
prepare_to_wait(&mc.waitq, &wait,
diff --git a/mm/mlock.c b/mm/mlock.c
index 8f4e2dfceec1..3f82720e0515 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -607,44 +607,3 @@ void user_shm_unlock(size_t size, struct user_struct *user)
spin_unlock(&shmlock_user_lock);
free_uid(user);
}
-
-int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
- size_t size)
-{
- unsigned long lim, vm, pgsz;
- int error = -ENOMEM;
-
- pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
- down_write(&mm->mmap_sem);
-
- lim = ACCESS_ONCE(rlim[RLIMIT_AS].rlim_cur) >> PAGE_SHIFT;
- vm = mm->total_vm + pgsz;
- if (lim < vm)
- goto out;
-
- lim = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur) >> PAGE_SHIFT;
- vm = mm->locked_vm + pgsz;
- if (lim < vm)
- goto out;
-
- mm->total_vm += pgsz;
- mm->locked_vm += pgsz;
-
- error = 0;
- out:
- up_write(&mm->mmap_sem);
- return error;
-}
-
-void refund_locked_memory(struct mm_struct *mm, size_t size)
-{
- unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
- down_write(&mm->mmap_sem);
-
- mm->total_vm -= pgsz;
- mm->locked_vm -= pgsz;
-
- up_write(&mm->mmap_sem);
-}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d03c946d5566..a6326c71b663 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2579,7 +2579,7 @@ static int default_zonelist_order(void)
struct zone *z;
int average_size;
/*
- * ZONE_DMA and ZONE_DMA32 can be very small area in the sytem.
+ * ZONE_DMA and ZONE_DMA32 can be very small area in the system.
* If they are really small and used heavily, the system can fall
* into OOM very easily.
* This function detect ZONE_DMA/DMA32 size and confgigures zone order.
diff --git a/mm/percpu-km.c b/mm/percpu-km.c
new file mode 100644
index 000000000000..df680855540a
--- /dev/null
+++ b/mm/percpu-km.c
@@ -0,0 +1,104 @@
+/*
+ * mm/percpu-km.c - kernel memory based chunk allocation
+ *
+ * Copyright (C) 2010 SUSE Linux Products GmbH
+ * Copyright (C) 2010 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Chunks are allocated as a contiguous kernel memory using gfp
+ * allocation. This is to be used on nommu architectures.
+ *
+ * To use percpu-km,
+ *
+ * - define CONFIG_NEED_PER_CPU_KM from the arch Kconfig.
+ *
+ * - CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK must not be defined. It's
+ * not compatible with PER_CPU_KM. EMBED_FIRST_CHUNK should work
+ * fine.
+ *
+ * - NUMA is not supported. When setting up the first chunk,
+ * @cpu_distance_fn should be NULL or report all CPUs to be nearer
+ * than or at LOCAL_DISTANCE.
+ *
+ * - It's best if the chunk size is power of two multiple of
+ * PAGE_SIZE. Because each chunk is allocated as a contiguous
+ * kernel memory block using alloc_pages(), memory will be wasted if
+ * chunk size is not aligned. percpu-km code will whine about it.
+ */
+
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+#error "contiguous percpu allocation is incompatible with paged first chunk"
+#endif
+
+#include <linux/log2.h>
+
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
+{
+ /* noop */
+ return 0;
+}
+
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)
+{
+ /* nada */
+}
+
+static struct pcpu_chunk *pcpu_create_chunk(void)
+{
+ const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
+ struct pcpu_chunk *chunk;
+ struct page *pages;
+ int i;
+
+ chunk = pcpu_alloc_chunk();
+ if (!chunk)
+ return NULL;
+
+ pages = alloc_pages(GFP_KERNEL, order_base_2(nr_pages));
+ if (!pages) {
+ pcpu_free_chunk(chunk);
+ return NULL;
+ }
+
+ for (i = 0; i < nr_pages; i++)
+ pcpu_set_page_chunk(nth_page(pages, i), chunk);
+
+ chunk->data = pages;
+ chunk->base_addr = page_address(pages) - pcpu_group_offsets[0];
+ return chunk;
+}
+
+static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
+{
+ const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
+
+ if (chunk && chunk->data)
+ __free_pages(chunk->data, order_base_2(nr_pages));
+ pcpu_free_chunk(chunk);
+}
+
+static struct page *pcpu_addr_to_page(void *addr)
+{
+ return virt_to_page(addr);
+}
+
+static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)
+{
+ size_t nr_pages, alloc_pages;
+
+ /* all units must be in a single group */
+ if (ai->nr_groups != 1) {
+ printk(KERN_CRIT "percpu: can't handle more than one groups\n");
+ return -EINVAL;
+ }
+
+ nr_pages = (ai->groups[0].nr_units * ai->unit_size) >> PAGE_SHIFT;
+ alloc_pages = roundup_pow_of_two(nr_pages);
+
+ if (alloc_pages > nr_pages)
+ printk(KERN_WARNING "percpu: wasting %zu pages per chunk\n",
+ alloc_pages - nr_pages);
+
+ return 0;
+}
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
new file mode 100644
index 000000000000..7d9c1d0ebd3f
--- /dev/null
+++ b/mm/percpu-vm.c
@@ -0,0 +1,451 @@
+/*
+ * mm/percpu-vm.c - vmalloc area based chunk allocation
+ *
+ * Copyright (C) 2010 SUSE Linux Products GmbH
+ * Copyright (C) 2010 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Chunks are mapped into vmalloc areas and populated page by page.
+ * This is the default chunk allocator.
+ */
+
+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));
+}
+
+/**
+ * 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)
+{
+ 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;
+
+ for_each_possible_cpu(cpu) {
+ for (i = page_start; i < page_end; i++) {
+ struct page *page;
+
+ 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);
+ }
+
+ for (i = page_start; i < page_end; i++)
+ __clear_bit(i, populated);
+}
+
+/**
+ * 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));
+}
+
+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);
+}
+
+/**
+ * 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)
+{
+ 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;
+}
+
+/**
+ * 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.
+ */
+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));
+}
+
+/**
+ * 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 */
+ rs = page_start;
+ pcpu_next_pop(chunk, &rs, &re, page_end);
+ if (rs == page_start && re == page_end)
+ goto clear;
+
+ /* 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;
+}
+
+/**
+ * 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)
+{
+ 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 */
+ rs = page_start;
+ pcpu_next_unpop(chunk, &rs, &re, page_end);
+ if (rs == page_start && re == page_end)
+ return;
+
+ /* 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.
+ */
+ 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);
+}
+
+static struct pcpu_chunk *pcpu_create_chunk(void)
+{
+ struct pcpu_chunk *chunk;
+ struct vm_struct **vms;
+
+ chunk = pcpu_alloc_chunk();
+ if (!chunk)
+ return NULL;
+
+ vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,
+ pcpu_nr_groups, pcpu_atom_size, GFP_KERNEL);
+ if (!vms) {
+ pcpu_free_chunk(chunk);
+ return NULL;
+ }
+
+ chunk->data = vms;
+ chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0];
+ return chunk;
+}
+
+static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
+{
+ if (chunk && chunk->data)
+ pcpu_free_vm_areas(chunk->data, pcpu_nr_groups);
+ pcpu_free_chunk(chunk);
+}
+
+static struct page *pcpu_addr_to_page(void *addr)
+{
+ return vmalloc_to_page(addr);
+}
+
+static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)
+{
+ /* no extra restriction */
+ return 0;
+}
diff --git a/mm/percpu.c b/mm/percpu.c
index 6e09741ddc62..39f7dfd59585 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>
@@ -7,14 +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 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
* ------------------- ------------------- ------------
@@ -99,7 +98,7 @@ 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 */
};
@@ -177,6 +176,21 @@ 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 */
@@ -198,27 +212,6 @@ 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)
-{
- 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)
{
@@ -231,13 +224,27 @@ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page)
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);
@@ -326,36 +333,6 @@ 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.
- *
- * RETURNS:
- * The address of the found chunk.
- */
-static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
-{
- void *first_start = pcpu_first_chunk->base_addr;
-
- /* 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;
- }
-
- /*
- * 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));
-}
-
-/**
* pcpu_need_to_extend - determine whether chunk area map needs to be extended
* @chunk: chunk of interest
*
@@ -623,434 +600,92 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
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)
+static struct pcpu_chunk *pcpu_alloc_chunk(void)
{
- 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 = pages[pcpu_page_idx(cpu, i)];
+ chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL);
+ if (!chunk)
+ return NULL;
- if (page)
- __free_page(page);
- }
+ chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
+ if (!chunk->map) {
+ kfree(chunk);
+ return NULL;
}
-}
-/**
- * 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)
-{
- const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
- unsigned int cpu;
- int i;
+ chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
+ chunk->map[chunk->map_used++] = pcpu_unit_size;
- 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;
-}
+ INIT_LIST_HEAD(&chunk->list);
+ chunk->free_size = pcpu_unit_size;
+ chunk->contig_hint = pcpu_unit_size;
-/**
- * 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));
+ return chunk;
}
-static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
+static void pcpu_free_chunk(struct pcpu_chunk *chunk)
{
- unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT);
+ if (!chunk)
+ return;
+ pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0]));
+ kfree(chunk);
}
-/**
- * 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.
+/*
+ * 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_unmap_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;
-
- 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);
- }
-
- for (i = page_start; i < page_end; i++)
- __clear_bit(i, populated);
-}
+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_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.
+ * pcpu_chunk_addr_search - determine chunk containing specified address
+ * @addr: address for which the chunk needs to be determined.
*
- * 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));
-}
-
-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);
-}
-
-/**
- * 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).
+ * RETURNS:
+ * The address of the found chunk.
*/
-static int pcpu_map_pages(struct pcpu_chunk *chunk,
- struct page **pages, unsigned long *populated,
- int page_start, int page_end)
+static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
{
- 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);
+ /* 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;
}
- return err;
-}
-
-/**
- * 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.
- */
-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));
-}
-
-/**
- * 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)
-{
- 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 */
- rs = page_start;
- pcpu_next_unpop(chunk, &rs, &re, page_end);
- if (rs == page_start && re == page_end)
- return;
-
- /* 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 */
- rs = page_start;
- pcpu_next_pop(chunk, &rs, &re, page_end);
- if (rs == page_start && re == page_end)
- goto clear;
-
- /* 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));
}
/**
@@ -1142,7 +777,7 @@ restart:
/* hmmm... no space left, create a new chunk */
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;
@@ -1254,7 +889,7 @@ static void pcpu_reclaim(struct work_struct *work)
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);
@@ -1343,11 +978,14 @@ bool is_kernel_percpu_address(unsigned long addr)
*/
phys_addr_t per_cpu_ptr_to_phys(void *addr)
{
- if ((unsigned long)addr < VMALLOC_START ||
- (unsigned long)addr >= VMALLOC_END)
- return __pa(addr);
- else
- return page_to_phys(vmalloc_to_page(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,
@@ -1719,6 +1357,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
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]));
diff --git a/mm/rmap.c b/mm/rmap.c
index 07fc94758799..0feeef860a8f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -336,14 +336,13 @@ vma_address(struct page *page, struct vm_area_struct *vma)
/*
* At what user virtual address is page expected in vma?
- * checking that the page matches the vma.
+ * Caller should check the page is actually part of the vma.
*/
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
{
- if (PageAnon(page)) {
- if (vma->anon_vma != page_anon_vma(page))
- return -EFAULT;
- } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
+ if (PageAnon(page))
+ ;
+ else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
if (!vma->vm_file ||
vma->vm_file->f_mapping != page->mapping)
return -EFAULT;
diff --git a/mm/slub.c b/mm/slub.c
index 7d6c8b1ccf63..d2a54fe71ea2 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2153,7 +2153,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
int local_node;
if (slab_state >= UP && (s < kmalloc_caches ||
- s > kmalloc_caches + KMALLOC_CACHES))
+ s >= kmalloc_caches + KMALLOC_CACHES))
local_node = page_to_nid(virt_to_page(s));
else
local_node = 0;