summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig5
-rw-r--r--mm/Makefile4
-rw-r--r--mm/allocpercpu.c177
-rw-r--r--mm/backing-dev.c8
-rw-r--r--mm/bootmem.c24
-rw-r--r--mm/filemap.c51
-rw-r--r--mm/kmemleak.c4
-rw-r--r--mm/memcontrol.c6
-rw-r--r--mm/memory-failure.c2
-rw-r--r--mm/memory_hotplug.c24
-rw-r--r--mm/mmap.c46
-rw-r--r--mm/mremap.c241
-rw-r--r--mm/page-writeback.c12
-rw-r--r--mm/percpu.c145
-rw-r--r--mm/slab.c136
-rw-r--r--mm/slub.c20
-rw-r--r--mm/truncate.c2
-rw-r--r--mm/util.c44
-rw-r--r--mm/vmalloc.c4
-rw-r--r--mm/vmstat.c7
20 files changed, 487 insertions, 475 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index fd3386242cf0..44cf6f0a3a6d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -128,12 +128,9 @@ config SPARSEMEM_VMEMMAP
config MEMORY_HOTPLUG
bool "Allow for memory hot-add"
depends on SPARSEMEM || X86_64_ACPI_NUMA
- depends on HOTPLUG && !(HIBERNATION && !S390) && ARCH_ENABLE_MEMORY_HOTPLUG
+ depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG
depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
-comment "Memory hotplug is currently incompatible with Software Suspend"
- depends on SPARSEMEM && HOTPLUG && HIBERNATION && !S390
-
config MEMORY_HOTPLUG_SPARSE
def_bool y
depends on SPARSEMEM && MEMORY_HOTPLUG
diff --git a/mm/Makefile b/mm/Makefile
index ebf849042ed3..82131d0f8d85 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -34,11 +34,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
obj-$(CONFIG_FS_XIP) += filemap_xip.o
obj-$(CONFIG_MIGRATION) += migrate.o
-ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
obj-$(CONFIG_SMP) += percpu.o
-else
-obj-$(CONFIG_SMP) += allocpercpu.o
-endif
obj-$(CONFIG_QUICKLIST) += quicklist.o
obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
deleted file mode 100644
index df34ceae0c67..000000000000
--- a/mm/allocpercpu.c
+++ /dev/null
@@ -1,177 +0,0 @@
-/*
- * linux/mm/allocpercpu.c
- *
- * Separated from slab.c August 11, 2006 Christoph Lameter
- */
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/bootmem.h>
-#include <asm/sections.h>
-
-#ifndef cache_line_size
-#define cache_line_size() L1_CACHE_BYTES
-#endif
-
-/**
- * percpu_depopulate - depopulate per-cpu data for given cpu
- * @__pdata: per-cpu data to depopulate
- * @cpu: depopulate per-cpu data for this cpu
- *
- * Depopulating per-cpu data for a cpu going offline would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- */
-static void percpu_depopulate(void *__pdata, int cpu)
-{
- struct percpu_data *pdata = __percpu_disguise(__pdata);
-
- kfree(pdata->ptrs[cpu]);
- pdata->ptrs[cpu] = NULL;
-}
-
-/**
- * percpu_depopulate_mask - depopulate per-cpu data for some cpu's
- * @__pdata: per-cpu data to depopulate
- * @mask: depopulate per-cpu data for cpu's selected through mask bits
- */
-static void __percpu_depopulate_mask(void *__pdata, const cpumask_t *mask)
-{
- int cpu;
- for_each_cpu_mask_nr(cpu, *mask)
- percpu_depopulate(__pdata, cpu);
-}
-
-#define percpu_depopulate_mask(__pdata, mask) \
- __percpu_depopulate_mask((__pdata), &(mask))
-
-/**
- * percpu_populate - populate per-cpu data for given cpu
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @cpu: populate per-data for this cpu
- *
- * Populating per-cpu data for a cpu coming online would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- * Per-cpu object is populated with zeroed buffer.
- */
-static void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu)
-{
- struct percpu_data *pdata = __percpu_disguise(__pdata);
- int node = cpu_to_node(cpu);
-
- /*
- * We should make sure each CPU gets private memory.
- */
- size = roundup(size, cache_line_size());
-
- BUG_ON(pdata->ptrs[cpu]);
- if (node_online(node))
- pdata->ptrs[cpu] = kmalloc_node(size, gfp|__GFP_ZERO, node);
- else
- pdata->ptrs[cpu] = kzalloc(size, gfp);
- return pdata->ptrs[cpu];
-}
-
-/**
- * percpu_populate_mask - populate per-cpu data for more cpu's
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @mask: populate per-cpu data for cpu's selected through mask bits
- *
- * Per-cpu objects are populated with zeroed buffers.
- */
-static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
- cpumask_t *mask)
-{
- cpumask_t populated;
- int cpu;
-
- cpus_clear(populated);
- for_each_cpu_mask_nr(cpu, *mask)
- if (unlikely(!percpu_populate(__pdata, size, gfp, cpu))) {
- __percpu_depopulate_mask(__pdata, &populated);
- return -ENOMEM;
- } else
- cpu_set(cpu, populated);
- return 0;
-}
-
-#define percpu_populate_mask(__pdata, size, gfp, mask) \
- __percpu_populate_mask((__pdata), (size), (gfp), &(mask))
-
-/**
- * alloc_percpu - initial setup of per-cpu data
- * @size: size of per-cpu object
- * @align: alignment
- *
- * Allocate dynamic percpu area. Percpu objects are populated with
- * zeroed buffers.
- */
-void *__alloc_percpu(size_t size, size_t align)
-{
- /*
- * We allocate whole cache lines to avoid false sharing
- */
- size_t sz = roundup(nr_cpu_ids * sizeof(void *), cache_line_size());
- void *pdata = kzalloc(sz, GFP_KERNEL);
- void *__pdata = __percpu_disguise(pdata);
-
- /*
- * Can't easily make larger alignment work with kmalloc. WARN
- * on it. Larger alignment should only be used for module
- * percpu sections on SMP for which this path isn't used.
- */
- WARN_ON_ONCE(align > SMP_CACHE_BYTES);
-
- if (unlikely(!pdata))
- return NULL;
- if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL,
- &cpu_possible_map)))
- return __pdata;
- kfree(pdata);
- return NULL;
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu);
-
-/**
- * free_percpu - final cleanup of per-cpu data
- * @__pdata: object to clean up
- *
- * We simply clean up any per-cpu object left. No need for the client to
- * track and specify through a bis mask which per-cpu objects are to free.
- */
-void free_percpu(void *__pdata)
-{
- if (unlikely(!__pdata))
- return;
- __percpu_depopulate_mask(__pdata, cpu_possible_mask);
- kfree(__percpu_disguise(__pdata));
-}
-EXPORT_SYMBOL_GPL(free_percpu);
-
-/*
- * Generic percpu area setup.
- */
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-
-EXPORT_SYMBOL(__per_cpu_offset);
-
-void __init setup_per_cpu_areas(void)
-{
- unsigned long size, i;
- char *ptr;
- unsigned long nr_possible_cpus = num_possible_cpus();
-
- /* Copy section for each CPU (we discard the original) */
- size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
- ptr = alloc_bootmem_pages(size * nr_possible_cpus);
-
- for_each_possible_cpu(i) {
- __per_cpu_offset[i] = ptr - __per_cpu_start;
- memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
- ptr += size;
- }
-}
-#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 11aee09dd2a6..0e8ca0347707 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -604,10 +604,14 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
/*
* Finally, kill the kernel threads. We don't need to be RCU
- * safe anymore, since the bdi is gone from visibility.
+ * safe anymore, since the bdi is gone from visibility. Force
+ * unfreeze of the thread before calling kthread_stop(), otherwise
+ * it would never exet if it is currently stuck in the refrigerator.
*/
- list_for_each_entry(wb, &bdi->wb_list, list)
+ list_for_each_entry(wb, &bdi->wb_list, list) {
+ thaw_process(wb->task);
kthread_stop(wb->task);
+ }
}
/*
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 555d5d2731c6..d1dc23cc7f10 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -143,6 +143,30 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
}
+/*
+ * free_bootmem_late - free bootmem pages directly to page allocator
+ * @addr: starting address of the range
+ * @size: size of the range in bytes
+ *
+ * This is only useful when the bootmem allocator has already been torn
+ * down, but we are still initializing the system. Pages are given directly
+ * to the page allocator, no bootmem metadata is updated because it is gone.
+ */
+void __init free_bootmem_late(unsigned long addr, unsigned long size)
+{
+ unsigned long cursor, end;
+
+ kmemleak_free_part(__va(addr), size);
+
+ cursor = PFN_UP(addr);
+ end = PFN_DOWN(addr + size);
+
+ for (; cursor < end; cursor++) {
+ __free_pages_bootmem(pfn_to_page(cursor), 0);
+ totalram_pages++;
+ }
+}
+
static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
{
int aligned;
diff --git a/mm/filemap.c b/mm/filemap.c
index ef169f37156d..8b4d88f9249e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -260,27 +260,27 @@ int filemap_flush(struct address_space *mapping)
EXPORT_SYMBOL(filemap_flush);
/**
- * wait_on_page_writeback_range - wait for writeback to complete
- * @mapping: target address_space
- * @start: beginning page index
- * @end: ending page index
+ * filemap_fdatawait_range - wait for writeback to complete
+ * @mapping: address space structure to wait for
+ * @start_byte: offset in bytes where the range starts
+ * @end_byte: offset in bytes where the range ends (inclusive)
*
- * Wait for writeback to complete against pages indexed by start->end
- * inclusive
+ * Walk the list of under-writeback pages of the given address space
+ * in the given range and wait for all of them.
*/
-int wait_on_page_writeback_range(struct address_space *mapping,
- pgoff_t start, pgoff_t end)
+int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
+ loff_t end_byte)
{
+ pgoff_t index = start_byte >> PAGE_CACHE_SHIFT;
+ pgoff_t end = end_byte >> PAGE_CACHE_SHIFT;
struct pagevec pvec;
int nr_pages;
int ret = 0;
- pgoff_t index;
- if (end < start)
+ if (end_byte < start_byte)
return 0;
pagevec_init(&pvec, 0);
- index = start;
while ((index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_WRITEBACK,
@@ -310,25 +310,6 @@ int wait_on_page_writeback_range(struct address_space *mapping,
return ret;
}
-
-/**
- * filemap_fdatawait_range - wait for all under-writeback pages to complete in a given range
- * @mapping: address space structure to wait for
- * @start: offset in bytes where the range starts
- * @end: offset in bytes where the range ends (inclusive)
- *
- * Walk the list of under-writeback pages of the given address space
- * in the given range and wait for all of them.
- *
- * This is just a simple wrapper so that callers don't have to convert offsets
- * to page indexes themselves
- */
-int filemap_fdatawait_range(struct address_space *mapping, loff_t start,
- loff_t end)
-{
- return wait_on_page_writeback_range(mapping, start >> PAGE_CACHE_SHIFT,
- end >> PAGE_CACHE_SHIFT);
-}
EXPORT_SYMBOL(filemap_fdatawait_range);
/**
@@ -345,8 +326,7 @@ int filemap_fdatawait(struct address_space *mapping)
if (i_size == 0)
return 0;
- return wait_on_page_writeback_range(mapping, 0,
- (i_size - 1) >> PAGE_CACHE_SHIFT);
+ return filemap_fdatawait_range(mapping, 0, i_size - 1);
}
EXPORT_SYMBOL(filemap_fdatawait);
@@ -393,9 +373,8 @@ int filemap_write_and_wait_range(struct address_space *mapping,
WB_SYNC_ALL);
/* See comment of filemap_write_and_wait() */
if (err != -EIO) {
- int err2 = wait_on_page_writeback_range(mapping,
- lstart >> PAGE_CACHE_SHIFT,
- lend >> PAGE_CACHE_SHIFT);
+ int err2 = filemap_fdatawait_range(mapping,
+ lstart, lend);
if (!err)
err = err2;
}
@@ -1844,7 +1823,7 @@ static size_t __iovec_copy_from_user_inatomic(char *vaddr,
/*
* Copy as much as we can into the page and return the number of bytes which
- * were sucessfully copied. If a fault is encountered then return the number of
+ * were successfully copied. If a fault is encountered then return the number of
* bytes which were copied.
*/
size_t iov_iter_copy_from_user_atomic(struct page *page,
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 8bf765c4f58d..13f33b3081ec 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1050,8 +1050,8 @@ static void scan_object(struct kmemleak_object *object)
unsigned long flags;
/*
- * Once the object->lock is aquired, the corresponding memory block
- * cannot be freed (the same lock is aquired in delete_object).
+ * Once the object->lock is acquired, the corresponding memory block
+ * cannot be freed (the same lock is acquired in delete_object).
*/
spin_lock_irqsave(&object->lock, flags);
if (object->flags & OBJECT_NO_SCAN)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f99f5991d6bb..c31a310aa146 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -209,7 +209,7 @@ struct mem_cgroup {
int prev_priority; /* for recording reclaim priority */
/*
- * While reclaiming in a hiearchy, we cache the last child we
+ * While reclaiming in a hierarchy, we cache the last child we
* reclaimed from.
*/
int last_scanned_child;
@@ -1720,7 +1720,7 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
/*
* While swap-in, try_charge -> commit or cancel, the page is locked.
* And when try_charge() successfully returns, one refcnt to memcg without
- * struct page_cgroup is aquired. This refcnt will be cumsumed by
+ * struct page_cgroup is acquired. This refcnt will be consumed by
* "commit()" or removed by "cancel()"
*/
int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
@@ -2466,7 +2466,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
cgroup_lock();
/*
- * If parent's use_hiearchy is set, we can't make any modifications
+ * If parent's use_hierarchy is set, we can't make any modifications
* in the child subtrees. If it is unset, then the change can
* occur, provided the current cgroup has no children.
*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index dacc64183874..1ac49fef95ab 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -174,7 +174,7 @@ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
list_for_each_entry_safe (tk, next, to_kill, nd) {
if (doit) {
/*
- * In case something went wrong with munmaping
+ * In case something went wrong with munmapping
* make sure the process doesn't catch the
* signal and then access the memory. Just kill it.
* the signal handlers
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 821dee596377..2047465cd27c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -26,6 +26,7 @@
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/pfn.h>
+#include <linux/suspend.h>
#include <asm/tlbflush.h>
@@ -447,7 +448,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
}
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
-static pg_data_t *hotadd_new_pgdat(int nid, u64 start)
+/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
+static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
{
struct pglist_data *pgdat;
unsigned long zones_size[MAX_NR_ZONES] = {0};
@@ -484,14 +486,18 @@ int __ref add_memory(int nid, u64 start, u64 size)
struct resource *res;
int ret;
+ lock_system_sleep();
+
res = register_memory_resource(start, size);
+ ret = -EEXIST;
if (!res)
- return -EEXIST;
+ goto out;
if (!node_online(nid)) {
pgdat = hotadd_new_pgdat(nid, start);
+ ret = -ENOMEM;
if (!pgdat)
- return -ENOMEM;
+ goto out;
new_pgdat = 1;
}
@@ -514,7 +520,8 @@ int __ref add_memory(int nid, u64 start, u64 size)
BUG_ON(ret);
}
- return ret;
+ goto out;
+
error:
/* rollback pgdat allocation and others */
if (new_pgdat)
@@ -522,6 +529,8 @@ error:
if (res)
release_memory_resource(res);
+out:
+ unlock_system_sleep();
return ret;
}
EXPORT_SYMBOL_GPL(add_memory);
@@ -758,6 +767,8 @@ int offline_pages(unsigned long start_pfn,
if (!test_pages_in_a_zone(start_pfn, end_pfn))
return -EINVAL;
+ lock_system_sleep();
+
zone = page_zone(pfn_to_page(start_pfn));
node = zone_to_nid(zone);
nr_pages = end_pfn - start_pfn;
@@ -765,7 +776,7 @@ int offline_pages(unsigned long start_pfn,
/* set above range as isolated */
ret = start_isolate_page_range(start_pfn, end_pfn);
if (ret)
- return ret;
+ goto out;
arg.start_pfn = start_pfn;
arg.nr_pages = nr_pages;
@@ -843,6 +854,7 @@ repeat:
writeback_set_ratelimit();
memory_notify(MEM_OFFLINE, &arg);
+ unlock_system_sleep();
return 0;
failed_removal:
@@ -852,6 +864,8 @@ failed_removal:
/* pushback to free area */
undo_isolate_page_range(start_pfn, end_pfn);
+out:
+ unlock_system_sleep();
return ret;
}
diff --git a/mm/mmap.c b/mm/mmap.c
index 73f5e4b64010..ed70a68e882a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -20,7 +20,6 @@
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/security.h>
-#include <linux/ima.h>
#include <linux/hugetlb.h>
#include <linux/profile.h>
#include <linux/module.h>
@@ -932,13 +931,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
if (!(flags & MAP_FIXED))
addr = round_hint_to_min(addr);
- error = arch_mmap_check(addr, len, flags);
- if (error)
- return error;
-
/* Careful about overflows.. */
len = PAGE_ALIGN(len);
- if (!len || len > TASK_SIZE)
+ if (!len)
return -ENOMEM;
/* offset overflow? */
@@ -949,24 +944,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
if (mm->map_count > sysctl_max_map_count)
return -ENOMEM;
- if (flags & MAP_HUGETLB) {
- struct user_struct *user = NULL;
- if (file)
- return -EINVAL;
-
- /*
- * VM_NORESERVE is used because the reservations will be
- * taken when vm_ops->mmap() is called
- * A dummy user value is used because we are not locking
- * memory so no accounting is necessary
- */
- len = ALIGN(len, huge_page_size(&default_hstate));
- file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
- &user, HUGETLB_ANONHUGE_INODE);
- if (IS_ERR(file))
- return PTR_ERR(file);
- }
-
/* Obtain the address to map to. we verify (or select) it and ensure
* that it represents a valid section of the address space.
*/
@@ -1061,9 +1038,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
error = security_file_mmap(file, reqprot, prot, flags, addr, 0);
if (error)
return error;
- error = ima_file_mmap(file, prot);
- if (error)
- return error;
return mmap_region(file, addr, len, flags, vm_flags, pgoff);
}
@@ -1459,6 +1433,14 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
unsigned long (*get_area)(struct file *, unsigned long,
unsigned long, unsigned long, unsigned long);
+ unsigned long error = arch_mmap_check(addr, len, flags);
+ if (error)
+ return error;
+
+ /* Careful about overflows.. */
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
get_area = current->mm->get_unmapped_area;
if (file && file->f_op && file->f_op->get_unmapped_area)
get_area = file->f_op->get_unmapped_area;
@@ -2003,20 +1985,14 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
if (!len)
return addr;
- if ((addr + len) > TASK_SIZE || (addr + len) < addr)
- return -EINVAL;
-
- if (is_hugepage_only_range(mm, addr, len))
- return -EINVAL;
-
error = security_file_mmap(NULL, 0, 0, 0, addr, 1);
if (error)
return error;
flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
- error = arch_mmap_check(addr, len, flags);
- if (error)
+ error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
+ if (error & ~PAGE_MASK)
return error;
/*
diff --git a/mm/mremap.c b/mm/mremap.c
index 97bff2547719..845190898d59 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -261,6 +261,137 @@ static unsigned long move_vma(struct vm_area_struct *vma,
return new_addr;
}
+static struct vm_area_struct *vma_to_resize(unsigned long addr,
+ unsigned long old_len, unsigned long new_len, unsigned long *p)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma = find_vma(mm, addr);
+
+ if (!vma || vma->vm_start > addr)
+ goto Efault;
+
+ if (is_vm_hugetlb_page(vma))
+ goto Einval;
+
+ /* We can't remap across vm area boundaries */
+ if (old_len > vma->vm_end - addr)
+ goto Efault;
+
+ if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) {
+ if (new_len > old_len)
+ goto Efault;
+ }
+
+ if (vma->vm_flags & VM_LOCKED) {
+ unsigned long locked, lock_limit;
+ locked = mm->locked_vm << PAGE_SHIFT;
+ lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+ locked += new_len - old_len;
+ if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+ goto Eagain;
+ }
+
+ if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT))
+ goto Enomem;
+
+ if (vma->vm_flags & VM_ACCOUNT) {
+ unsigned long charged = (new_len - old_len) >> PAGE_SHIFT;
+ if (security_vm_enough_memory(charged))
+ goto Efault;
+ *p = charged;
+ }
+
+ return vma;
+
+Efault: /* very odd choice for most of the cases, but... */
+ return ERR_PTR(-EFAULT);
+Einval:
+ return ERR_PTR(-EINVAL);
+Enomem:
+ return ERR_PTR(-ENOMEM);
+Eagain:
+ return ERR_PTR(-EAGAIN);
+}
+
+static unsigned long mremap_to(unsigned long addr,
+ unsigned long old_len, unsigned long new_addr,
+ unsigned long new_len)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ unsigned long ret = -EINVAL;
+ unsigned long charged = 0;
+ unsigned long map_flags;
+
+ if (new_addr & ~PAGE_MASK)
+ goto out;
+
+ if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
+ goto out;
+
+ /* Check if the location we're moving into overlaps the
+ * old location at all, and fail if it does.
+ */
+ if ((new_addr <= addr) && (new_addr+new_len) > addr)
+ goto out;
+
+ if ((addr <= new_addr) && (addr+old_len) > new_addr)
+ goto out;
+
+ ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
+ if (ret)
+ goto out;
+
+ ret = do_munmap(mm, new_addr, new_len);
+ if (ret)
+ goto out;
+
+ if (old_len >= new_len) {
+ ret = do_munmap(mm, addr+new_len, old_len - new_len);
+ if (ret && old_len != new_len)
+ goto out;
+ old_len = new_len;
+ }
+
+ vma = vma_to_resize(addr, old_len, new_len, &charged);
+ if (IS_ERR(vma)) {
+ ret = PTR_ERR(vma);
+ goto out;
+ }
+
+ map_flags = MAP_FIXED;
+ if (vma->vm_flags & VM_MAYSHARE)
+ map_flags |= MAP_SHARED;
+
+ ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff +
+ ((addr - vma->vm_start) >> PAGE_SHIFT),
+ map_flags);
+ if (ret & ~PAGE_MASK)
+ goto out1;
+
+ ret = move_vma(vma, addr, old_len, new_len, new_addr);
+ if (!(ret & ~PAGE_MASK))
+ goto out;
+out1:
+ vm_unacct_memory(charged);
+
+out:
+ return ret;
+}
+
+static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
+{
+ unsigned long end = vma->vm_end + delta;
+ if (end < vma->vm_end) /* overflow */
+ return 0;
+ if (vma->vm_next && vma->vm_next->vm_start < end) /* intersection */
+ return 0;
+ if (get_unmapped_area(NULL, vma->vm_start, end - vma->vm_start,
+ 0, MAP_FIXED) & ~PAGE_MASK)
+ return 0;
+ return 1;
+}
+
/*
* Expand (or shrink) an existing mapping, potentially moving it at the
* same time (controlled by the MREMAP_MAYMOVE flag and available VM space)
@@ -294,32 +425,10 @@ unsigned long do_mremap(unsigned long addr,
if (!new_len)
goto out;
- /* new_addr is only valid if MREMAP_FIXED is specified */
if (flags & MREMAP_FIXED) {
- if (new_addr & ~PAGE_MASK)
- goto out;
- if (!(flags & MREMAP_MAYMOVE))
- goto out;
-
- if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
- goto out;
-
- /* Check if the location we're moving into overlaps the
- * old location at all, and fail if it does.
- */
- if ((new_addr <= addr) && (new_addr+new_len) > addr)
- goto out;
-
- if ((addr <= new_addr) && (addr+old_len) > new_addr)
- goto out;
-
- ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
- if (ret)
- goto out;
-
- ret = do_munmap(mm, new_addr, new_len);
- if (ret)
- goto out;
+ if (flags & MREMAP_MAYMOVE)
+ ret = mremap_to(addr, old_len, new_addr, new_len);
+ goto out;
}
/*
@@ -332,60 +441,23 @@ unsigned long do_mremap(unsigned long addr,
if (ret && old_len != new_len)
goto out;
ret = addr;
- if (!(flags & MREMAP_FIXED) || (new_addr == addr))
- goto out;
- old_len = new_len;
+ goto out;
}
/*
- * Ok, we need to grow.. or relocate.
+ * Ok, we need to grow..
*/
- ret = -EFAULT;
- vma = find_vma(mm, addr);
- if (!vma || vma->vm_start > addr)
- goto out;
- if (is_vm_hugetlb_page(vma)) {
- ret = -EINVAL;
- goto out;
- }
- /* We can't remap across vm area boundaries */
- if (old_len > vma->vm_end - addr)
- goto out;
- if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) {
- if (new_len > old_len)
- goto out;
- }
- if (vma->vm_flags & VM_LOCKED) {
- unsigned long locked, lock_limit;
- locked = mm->locked_vm << PAGE_SHIFT;
- lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
- locked += new_len - old_len;
- ret = -EAGAIN;
- if (locked > lock_limit && !capable(CAP_IPC_LOCK))
- goto out;
- }
- if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) {
- ret = -ENOMEM;
+ vma = vma_to_resize(addr, old_len, new_len, &charged);
+ if (IS_ERR(vma)) {
+ ret = PTR_ERR(vma);
goto out;
}
- if (vma->vm_flags & VM_ACCOUNT) {
- charged = (new_len - old_len) >> PAGE_SHIFT;
- if (security_vm_enough_memory(charged))
- goto out_nc;
- }
-
/* old_len exactly to the end of the area..
- * And we're not relocating the area.
*/
- if (old_len == vma->vm_end - addr &&
- !((flags & MREMAP_FIXED) && (addr != new_addr)) &&
- (old_len != new_len || !(flags & MREMAP_MAYMOVE))) {
- unsigned long max_addr = TASK_SIZE;
- if (vma->vm_next)
- max_addr = vma->vm_next->vm_start;
+ if (old_len == vma->vm_end - addr) {
/* can we just expand the current mapping? */
- if (max_addr - addr >= new_len) {
+ if (vma_expandable(vma, new_len - old_len)) {
int pages = (new_len - old_len) >> PAGE_SHIFT;
vma_adjust(vma, vma->vm_start,
@@ -409,28 +481,27 @@ unsigned long do_mremap(unsigned long addr,
*/
ret = -ENOMEM;
if (flags & MREMAP_MAYMOVE) {
- if (!(flags & MREMAP_FIXED)) {
- unsigned long map_flags = 0;
- if (vma->vm_flags & VM_MAYSHARE)
- map_flags |= MAP_SHARED;
-
- new_addr = get_unmapped_area(vma->vm_file, 0, new_len,
- vma->vm_pgoff, map_flags);
- if (new_addr & ~PAGE_MASK) {
- ret = new_addr;
- goto out;
- }
-
- ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
- if (ret)
- goto out;
+ unsigned long map_flags = 0;
+ if (vma->vm_flags & VM_MAYSHARE)
+ map_flags |= MAP_SHARED;
+
+ new_addr = get_unmapped_area(vma->vm_file, 0, new_len,
+ vma->vm_pgoff +
+ ((addr - vma->vm_start) >> PAGE_SHIFT),
+ map_flags);
+ if (new_addr & ~PAGE_MASK) {
+ ret = new_addr;
+ goto out;
}
+
+ ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
+ if (ret)
+ goto out;
ret = move_vma(vma, addr, old_len, new_len, new_addr);
}
out:
if (ret & ~PAGE_MASK)
vm_unacct_memory(charged);
-out_nc:
return ret;
}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 2c5d79236ead..0b19943ecf8b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -821,7 +821,6 @@ int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
- struct backing_dev_info *bdi = mapping->backing_dev_info;
int ret = 0;
int done = 0;
struct pagevec pvec;
@@ -834,11 +833,6 @@ int write_cache_pages(struct address_space *mapping,
int range_whole = 0;
long nr_to_write = wbc->nr_to_write;
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- wbc->encountered_congestion = 1;
- return 0;
- }
-
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
@@ -957,12 +951,6 @@ continue_unlock:
break;
}
}
-
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- wbc->encountered_congestion = 1;
- done = 1;
- break;
- }
}
pagevec_release(&pvec);
cond_resched();
diff --git a/mm/percpu.c b/mm/percpu.c
index d90797160c2a..442010cc91c6 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -46,8 +46,6 @@
*
* To use this allocator, arch code should do the followings.
*
- * - drop CONFIG_HAVE_LEGACY_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
@@ -74,6 +72,7 @@
#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 */
@@ -355,62 +354,86 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
}
/**
- * pcpu_extend_area_map - extend area map for allocation
- * @chunk: target chunk
+ * pcpu_need_to_extend - determine whether chunk area map needs to be extended
+ * @chunk: chunk of interest
*
- * 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.
+ * Determine whether area map of @chunk needs to be extended to
+ * accomodate a new allocation.
*
* CONTEXT:
- * pcpu_alloc_mutex, pcpu_lock. pcpu_lock is released and reacquired
- * if area map is extended.
+ * pcpu_lock.
*
* RETURNS:
- * 0 if noop, 1 if successfully extended, -errno on failure.
+ * New target map allocation length if extension is necessary, 0
+ * otherwise.
*/
-static int pcpu_extend_area_map(struct pcpu_chunk *chunk, unsigned long *flags)
+static int pcpu_need_to_extend(struct pcpu_chunk *chunk)
{
int new_alloc;
- int *new;
- size_t size;
- /* has enough? */
if (chunk->map_alloc >= chunk->map_used + 2)
return 0;
- spin_unlock_irqrestore(&pcpu_lock, *flags);
-
new_alloc = PCPU_DFL_MAP_ALLOC;
while (new_alloc < chunk->map_used + 2)
new_alloc *= 2;
- new = pcpu_mem_alloc(new_alloc * sizeof(new[0]));
- if (!new) {
- spin_lock_irqsave(&pcpu_lock, *flags);
+ return new_alloc;
+}
+
+/**
+ * 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 to have @new_alloc entries.
+ *
+ * CONTEXT:
+ * Does GFP_KERNEL allocation. Grabs and releases pcpu_lock.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
+{
+ 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_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_irqsave(&pcpu_lock, *flags);
- 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;
+
+ 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;
}
@@ -1049,7 +1072,7 @@ static void *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)) {
@@ -1064,14 +1087,25 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved)
/* 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, &flags) < 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;
}
@@ -1083,14 +1117,20 @@ restart:
if (size > chunk->contig_hint)
continue;
- switch (pcpu_extend_area_map(chunk, &flags)) {
- 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);
@@ -1261,6 +1301,27 @@ void free_percpu(void *ptr)
}
EXPORT_SYMBOL_GPL(free_percpu);
+/**
+ * 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 ((unsigned long)addr < VMALLOC_START ||
+ (unsigned long)addr >= VMALLOC_END)
+ return __pa(addr);
+ else
+ return page_to_phys(vmalloc_to_page(addr));
+}
+
static inline size_t pcpu_calc_fc_sizes(size_t static_size,
size_t reserved_size,
ssize_t *dyn_sizep)
diff --git a/mm/slab.c b/mm/slab.c
index c3d092dca039..3f4822938f46 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -604,6 +604,26 @@ static struct kmem_cache cache_cache = {
#define BAD_ALIEN_MAGIC 0x01020304ul
+/*
+ * chicken and egg problem: delay the per-cpu array allocation
+ * until the general caches are up.
+ */
+static enum {
+ NONE,
+ PARTIAL_AC,
+ PARTIAL_L3,
+ EARLY,
+ FULL
+} g_cpucache_up;
+
+/*
+ * used by boot code to determine if it can use slab based allocator
+ */
+int slab_is_available(void)
+{
+ return g_cpucache_up >= EARLY;
+}
+
#ifdef CONFIG_LOCKDEP
/*
@@ -620,40 +640,52 @@ static struct kmem_cache cache_cache = {
static struct lock_class_key on_slab_l3_key;
static struct lock_class_key on_slab_alc_key;
-static inline void init_lock_keys(void)
-
+static void init_node_lock_keys(int q)
{
- int q;
struct cache_sizes *s = malloc_sizes;
- while (s->cs_size != ULONG_MAX) {
- for_each_node(q) {
- struct array_cache **alc;
- int r;
- struct kmem_list3 *l3 = s->cs_cachep->nodelists[q];
- if (!l3 || OFF_SLAB(s->cs_cachep))
- continue;
- lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
- alc = l3->alien;
- /*
- * FIXME: This check for BAD_ALIEN_MAGIC
- * should go away when common slab code is taught to
- * work even without alien caches.
- * Currently, non NUMA code returns BAD_ALIEN_MAGIC
- * for alloc_alien_cache,
- */
- if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
- continue;
- for_each_node(r) {
- if (alc[r])
- lockdep_set_class(&alc[r]->lock,
- &on_slab_alc_key);
- }
+ if (g_cpucache_up != FULL)
+ return;
+
+ for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
+ struct array_cache **alc;
+ struct kmem_list3 *l3;
+ int r;
+
+ l3 = s->cs_cachep->nodelists[q];
+ if (!l3 || OFF_SLAB(s->cs_cachep))
+ return;
+ lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
+ alc = l3->alien;
+ /*
+ * FIXME: This check for BAD_ALIEN_MAGIC
+ * should go away when common slab code is taught to
+ * work even without alien caches.
+ * Currently, non NUMA code returns BAD_ALIEN_MAGIC
+ * for alloc_alien_cache,
+ */
+ if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
+ return;
+ for_each_node(r) {
+ if (alc[r])
+ lockdep_set_class(&alc[r]->lock,
+ &on_slab_alc_key);
}
- s++;
}
}
+
+static inline void init_lock_keys(void)
+{
+ int node;
+
+ for_each_node(node)
+ init_node_lock_keys(node);
+}
#else
+static void init_node_lock_keys(int q)
+{
+}
+
static inline void init_lock_keys(void)
{
}
@@ -665,27 +697,7 @@ static inline void init_lock_keys(void)
static DEFINE_MUTEX(cache_chain_mutex);
static struct list_head cache_chain;
-/*
- * chicken and egg problem: delay the per-cpu array allocation
- * until the general caches are up.
- */
-static enum {
- NONE,
- PARTIAL_AC,
- PARTIAL_L3,
- EARLY,
- FULL
-} g_cpucache_up;
-
-/*
- * used by boot code to determine if it can use slab based allocator
- */
-int slab_is_available(void)
-{
- return g_cpucache_up >= EARLY;
-}
-
-static DEFINE_PER_CPU(struct delayed_work, reap_work);
+static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
{
@@ -826,7 +838,7 @@ __setup("noaliencache", noaliencache_setup);
* objects freed on different nodes from which they were allocated) and the
* flushing of remote pcps by calling drain_node_pages.
*/
-static DEFINE_PER_CPU(unsigned long, reap_node);
+static DEFINE_PER_CPU(unsigned long, slab_reap_node);
static void init_reap_node(int cpu)
{
@@ -836,17 +848,17 @@ static void init_reap_node(int cpu)
if (node == MAX_NUMNODES)
node = first_node(node_online_map);
- per_cpu(reap_node, cpu) = node;
+ per_cpu(slab_reap_node, cpu) = node;
}
static void next_reap_node(void)
{
- int node = __get_cpu_var(reap_node);
+ int node = __get_cpu_var(slab_reap_node);
node = next_node(node, node_online_map);
if (unlikely(node >= MAX_NUMNODES))
node = first_node(node_online_map);
- __get_cpu_var(reap_node) = node;
+ __get_cpu_var(slab_reap_node) = node;
}
#else
@@ -863,7 +875,7 @@ static void next_reap_node(void)
*/
static void __cpuinit start_cpu_timer(int cpu)
{
- struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
+ struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
/*
* When this gets called from do_initcalls via cpucache_init(),
@@ -1027,7 +1039,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
*/
static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
{
- int node = __get_cpu_var(reap_node);
+ int node = __get_cpu_var(slab_reap_node);
if (l3->alien) {
struct array_cache *ac = l3->alien[node];
@@ -1254,6 +1266,8 @@ static int __cpuinit cpuup_prepare(long cpu)
kfree(shared);
free_alien_cache(alien);
}
+ init_node_lock_keys(node);
+
return 0;
bad:
cpuup_canceled(cpu);
@@ -1286,9 +1300,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
* anything expensive but will only modify reap_work
* and reschedule the timer.
*/
- cancel_rearming_delayed_work(&per_cpu(reap_work, cpu));
+ cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu));
/* Now the cache_reaper is guaranteed to be not running. */
- per_cpu(reap_work, cpu).work.func = NULL;
+ per_cpu(slab_reap_work, cpu).work.func = NULL;
break;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
@@ -3103,13 +3117,19 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
} else {
STATS_INC_ALLOCMISS(cachep);
objp = cache_alloc_refill(cachep, flags);
+ /*
+ * the 'ac' may be updated by cache_alloc_refill(),
+ * and kmemleak_erase() requires its correct value.
+ */
+ ac = cpu_cache_get(cachep);
}
/*
* To avoid a false negative, if an object that is in one of the
* per-CPU caches is leaked, we need to make sure kmemleak doesn't
* treat the array pointers as a reference to the object.
*/
- kmemleak_erase(&ac->entry[ac->avail]);
+ if (objp)
+ kmemleak_erase(&ac->entry[ac->avail]);
return objp;
}
@@ -3306,7 +3326,7 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
cache_alloc_debugcheck_before(cachep, flags);
local_irq_save(save_flags);
- if (unlikely(nodeid == -1))
+ if (nodeid == -1)
nodeid = numa_node_id();
if (unlikely(!cachep->nodelists[nodeid])) {
diff --git a/mm/slub.c b/mm/slub.c
index 4a89c3d231b2..8d71aaf888d7 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1735,7 +1735,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
}
local_irq_restore(flags);
- if (unlikely((gfpflags & __GFP_ZERO) && object))
+ if (unlikely(gfpflags & __GFP_ZERO) && object)
memset(object, 0, objsize);
kmemcheck_slab_alloc(s, gfpflags, object, c->objsize);
@@ -4371,12 +4371,28 @@ static int show_stat(struct kmem_cache *s, char *buf, enum stat_item si)
return len + sprintf(buf + len, "\n");
}
+static void clear_stat(struct kmem_cache *s, enum stat_item si)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ get_cpu_slab(s, cpu)->stat[si] = 0;
+}
+
#define STAT_ATTR(si, text) \
static ssize_t text##_show(struct kmem_cache *s, char *buf) \
{ \
return show_stat(s, buf, si); \
} \
-SLAB_ATTR_RO(text); \
+static ssize_t text##_store(struct kmem_cache *s, \
+ const char *buf, size_t length) \
+{ \
+ if (buf[0] != '0') \
+ return -EINVAL; \
+ clear_stat(s, si); \
+ return length; \
+} \
+SLAB_ATTR(text); \
STAT_ATTR(ALLOC_FASTPATH, alloc_fastpath);
STAT_ATTR(ALLOC_SLOWPATH, alloc_slowpath);
diff --git a/mm/truncate.c b/mm/truncate.c
index 450cebdabfc0..2c147a7e5f2c 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -490,7 +490,7 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
* Any pages which are found to be mapped into pagetables are unmapped prior to
* invalidation.
*
- * Returns -EIO if any pages could not be invalidated.
+ * Returns -EBUSY if any pages could not be invalidated.
*/
int invalidate_inode_pages2(struct address_space *mapping)
{
diff --git a/mm/util.c b/mm/util.c
index 7c35ad95f927..b377ce430803 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -4,6 +4,10 @@
#include <linux/module.h>
#include <linux/err.h>
#include <linux/sched.h>
+#include <linux/hugetlb.h>
+#include <linux/syscalls.h>
+#include <linux/mman.h>
+#include <linux/file.h>
#include <asm/uaccess.h>
#define CREATE_TRACE_POINTS
@@ -268,6 +272,46 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start,
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, unsigned long, pgoff)
+{
+ struct file * file = NULL;
+ unsigned long retval = -EBADF;
+
+ if (!(flags & MAP_ANONYMOUS)) {
+ if (unlikely(flags & MAP_HUGETLB))
+ return -EINVAL;
+ file = fget(fd);
+ if (!file)
+ goto out;
+ } else if (flags & MAP_HUGETLB) {
+ struct user_struct *user = NULL;
+ /*
+ * VM_NORESERVE is used because the reservations will be
+ * taken when vm_ops->mmap() is called
+ * A dummy user value is used because we are not locking
+ * memory so no accounting is necessary
+ */
+ len = ALIGN(len, huge_page_size(&default_hstate));
+ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
+ &user, HUGETLB_ANONHUGE_INODE);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+ }
+
+ flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+
+ down_write(&current->mm->mmap_sem);
+ retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ up_write(&current->mm->mmap_sem);
+
+ if (file)
+ fput(file);
+out:
+ return retval;
+}
+
/* Tracepoints definitions. */
EXPORT_TRACEPOINT_SYMBOL(kmalloc);
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 0f551a4a44cd..9b08d790df6f 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -761,7 +761,7 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask)
spin_lock(&vbq->lock);
list_add(&vb->free_list, &vbq->free);
spin_unlock(&vbq->lock);
- put_cpu_var(vmap_cpu_blocks);
+ put_cpu_var(vmap_block_queue);
return vb;
}
@@ -826,7 +826,7 @@ again:
}
spin_unlock(&vb->lock);
}
- put_cpu_var(vmap_cpu_blocks);
+ put_cpu_var(vmap_block_queue);
rcu_read_unlock();
if (!addr) {
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c81321f9feec..dad2327e4580 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -883,11 +883,10 @@ static void vmstat_update(struct work_struct *w)
static void __cpuinit start_cpu_timer(int cpu)
{
- struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);
+ struct delayed_work *work = &per_cpu(vmstat_work, cpu);
- INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update);
- schedule_delayed_work_on(cpu, vmstat_work,
- __round_jiffies_relative(HZ, cpu));
+ INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update);
+ schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
}
/*